v1.1 update yolov7 & yolov8

.gitignore

@@ -1 +1,17 @@
-.idea
+.idea
+__pycache__
+*.pyc
+*.pyo
+*.pyd
+*.log
+*.bak
+*.swp
+*.tmp
+*.db
+*.sqlite
+*.sqlite3
+*.db-journal
+*.db-shm
+*.db-wal
+my_model/v7-tiny-cbam.pt
+my_model/v7-x.pt

app.py

@@ -1,17 +1,130 @@
 import streamlit as st
 import os
 from PIL import Image
+import random
+import cv2
+
+from infer.yolov7.get_results import get_yolov7_result
+from infer.yolov5.get_results import get_yolov5_result
+from infer.yolov8.get_results import get_yolov8_result
 
 image_path = "image/"
+txt_path = "label/"
+random.seed(0)
 each_image_name = os.listdir(image_path)
+random.shuffle(each_image_name)
+
+label_names = ['epiglottis', 'vocal cord', 'trachea', 'carina', 'right main bronchus', 'intermediate bronchus',
+               'right upper lobar bronchus', 'right middle lobar bronchus', 'right lower lobar bronchus', 'right superior segment bronchus',
+               'right basal bronchus', 'left main bronchus', 'left upper lobar bronchus', 'left division bronchus',
+               'left lingular bronchus', 'left lower bronchus', 'left superior segment', 'left basal bronchus']
+
+model_list = ['YOLO-V8',
+              'YOLO-V7',
+              'YOLO-V5']
 
 st.set_page_config(layout="wide")
-body1 = st.container()
 
-with body1:
-    body1_col1, body1_col2, body1_col3, body1_col4 = st.columns([1, 3, 3, 3])
+def inference(image, model_name, conf_threshold, iou_threshold):
+    if model_name == "YOLO-V7":
+        return get_yolov7_result(image, conf_threshold, iou_threshold, label_names)
+    elif model_name == "YOLO-V5":
+        #return get_yolov5_result(image, conf_threshold, iou_threshold, label_names)
+        return None, None
+    elif model_name == "YOLO-V8":
+        return get_yolov8_result(image, conf_threshold, iou_threshold, label_names)
+    else:
+        return None, None
+
+def image_on_click(image_index):
+    with body1_col2:
+        st.header("Image Information")
+        image_name = each_image_name[image_index]
+        image = Image.open(os.path.join(image_path, image_name))
+        cv2_image = cv2.imread(os.path.join(image_path, image_name))
+        cv2_image_copy = cv2_image.copy()
+        cv2_h, cv2_w, _ = cv2_image.shape
+        st.write("Image Width: " ,image.width)
+        st.write("Image Height: " ,image.height)
+        temp_label_list = []
+        with open(os.path.join(txt_path, image_name.replace(".png",".txt")), "r") as f:
+            lines = f.readlines()
+            for line in lines:
+                line = line.split(" ")
+                label_index = int(line[0]) - 1
+                label_name = label_names[label_index]
+                x_center = float(line[1])
+                y_center = float(line[2])
+                width = float(line[3])
+                height = float(line[4])
+                x_center, y_center, width, height = [x_center * cv2_w, y_center * cv2_h, width * cv2_w, height * cv2_h]
+
+                x_min = int(x_center - width / 2)
+                y_min = int(y_center - height / 2)
+                x_max = int(x_center + width / 2)
+                y_max = int(y_center + height / 2)
+
+                cv2.rectangle(cv2_image, (x_min, y_min), (x_max, y_max), (0, 255, 0), 2)
+
+                label_size, _ = cv2.getTextSize(label_name, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 2)
+                label_x_min = x_min
+                label_y_min = y_min - label_size[1] - 10
+                label_x_max = x_min + label_size[0]
+                label_y_max = y_min
+                cv2.rectangle(cv2_image, (label_x_min, label_y_min), (label_x_max, label_y_max), (0, 255, 0), cv2.FILLED)
+                cv2.putText(cv2_image, label_name, (label_x_min, label_y_min + label_size[1] + 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5,
+                            (0, 0, 0), 1)
 
+                temp_label_list.append(label_name)
+        st.write("Label:" + str(temp_label_list))
+        cv2_image = cv2_image[...,::-1]
+
+        st.image(cv2_image, image_name.replace(".png","") + " label image")
+
+        with body1_col3:
+            st.header("Inference Result")
+            result_image, result_list = inference(cv2_image_copy, selected_model, conf_threshold, iou_threshold)
+            if result_list is not None:
+                for each_list in result_list:
+                    st.markdown(f'Label:  <span style="color:rgb{each_list[1][::-1]}">{each_list[0]}</span> &nbsp; Conf:  <span style="color:red">{"{:.3f}".format(each_list[2])}</span>', unsafe_allow_html=True)
+            if result_image is not None:
+                st.image(result_image, image_name.replace(".png","") + " result image")
+            else:
+                st.warning("Not implemented yet")
+
+body1 = st.container()
+with body1:
+    body1_col1, body1_col2, body1_col3 = st.columns([2,1,1])
     with body1_col1:
-        for i in range(3):
-            image = Image.open(os.path.join(image_path, each_image_name[i]))
-            st.image(image, caption="")
+        st.header("Select an image")
+        image_cols = st.columns(5)
+        for i, col in enumerate(image_cols):
+            with col:
+                image = Image.open(os.path.join(image_path, each_image_name[i]))
+                st.image(image, each_image_name[i].replace(".png",""))
+        button_cols = st.columns(5)
+        for i, col in enumerate(button_cols):
+            with col:
+                st.button('Select', key=i, use_container_width=True, on_click=image_on_click, args=(i,))
+
+        selected_model = st.selectbox('Select the inference model', model_list)
+        conf_threshold = st.slider('Select the confidence threshold', 0.0, 1.0, 0.60)
+        iou_threshold = st.slider('Select the IOU threshold', 0.0, 1.0, 0.45)
+
+
+st.markdown("""
+    <style>
+    .footer {
+        position: fixed;
+        left: 0;
+        bottom: 0;
+        width: 100%;
+        text-align: center;
+    }
+    </style>
+    <div class="footer">
+        <p>Our paper: <a href="#">Enhanced Object Detection in Pediatric Bronchoscopy Images using YOLO-based Algorithms with CBAM Attention Mechanism</a></p>
+        <p>Author: Jianqi Yan</p>
+        <p>Copyright &copy; 2024, Quanbao Technologies Co. Ltd </p>
+    </div>
+    """, unsafe_allow_html=True)

infer/__init__.py

@@ -0,0 +1,2 @@
+# init
+from .yolov7 import *

infer/yolov5/get_results.py

@@ -0,0 +1,32 @@
+import torch
+import cv2
+import numpy as np
+import streamlit as st
+
+colors = [(np.random.randint(0, 255), np.random.randint(0, 255), np.random.randint(0, 255)) for _ in range(20)]
+
+def get_yolov5_result(image, conf_threshold, iou_threshold, class_names):
+    weights = 'my_model/v5-n.pt'
+    device = 'cpu'
+    model = torch.hub.load('ultralytics/yolov5', 'custom', path=weights, force_reload=True)
+    model.to(device)
+    model.eval()
+
+    results = model(image, size=320)
+    st.write(results.pandas().xyxy[0])
+
+    img0 = image.copy()
+    result_list = []
+
+    for i, det in enumerate(results.xyxy[0]):
+        if det[4] > conf_threshold:
+            label = class_names[int(det[5]) - 1]
+            color = colors[int(det[5]) % len(colors)]
+            result_list.append([label, color, det[4]])
+            cv2.rectangle(img0, (int(det[0]), int(det[1])), (int(det[2]), int(det[3])), color, 2)
+            cv2.putText(img0, label, (int(det[0]), int(det[1]) - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
+
+    img0 = img0[...,::-1]
+    return img0, result_list
+
+

infer/yolov7/__init__.py

@@ -0,0 +1,2 @@
+# init
+from .models import *

infer/yolov7/cfg/baseline/r50-csp.yaml

@@ -0,0 +1,49 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-ResNet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Stem, [128]],  # 0-P1/2
+   [-1, 3, ResCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 2-P3/8
+   [-1, 4, ResCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 4-P3/8
+   [-1, 6, ResCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 6-P3/8
+   [-1, 3, ResCSPC, [1024]],  # 7
+  ]
+
+# CSP-Res-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 8
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [5, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResCSPB, [256]], # 13
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [3, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResCSPB, [128]], # 18
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 13], 1, Concat, [1]],  # cat
+   [-1, 2, ResCSPB, [256]], # 22
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 8], 1, Concat, [1]],  # cat
+   [-1, 2, ResCSPB, [512]], # 26
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[19,23,27], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/baseline/x50-csp.yaml

@@ -0,0 +1,49 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-ResNeXt backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Stem, [128]],  # 0-P1/2
+   [-1, 3, ResXCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 2-P3/8
+   [-1, 4, ResXCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 4-P3/8
+   [-1, 6, ResXCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 6-P3/8
+   [-1, 3, ResXCSPC, [1024]],  # 7
+  ]
+
+# CSP-ResX-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 8
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [5, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResXCSPB, [256]], # 13
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [3, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, ResXCSPB, [128]], # 18
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 13], 1, Concat, [1]],  # cat
+   [-1, 2, ResXCSPB, [256]], # 22
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 8], 1, Concat, [1]],  # cat
+   [-1, 2, ResXCSPB, [512]], # 26
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[19,23,27], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/baseline/yolor-csp-x.yaml

@@ -0,0 +1,52 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, BottleneckCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, BottleneckCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, BottleneckCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+   [-1, 4, BottleneckCSPC, [1024]],  # 10
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 11
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [8, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [256]], # 16 
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [6, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [128]], # 21
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [256]], # 25
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [512]], # 29
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[22,26,30], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/baseline/yolor-csp.yaml

@@ -0,0 +1,52 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, BottleneckCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, BottleneckCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, BottleneckCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+   [-1, 4, BottleneckCSPC, [1024]],  # 10
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 11
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [8, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [256]], # 16 
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [6, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [128]], # 21
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [256]], # 25
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [512]], # 29
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[22,26,30], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/baseline/yolor-d6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.25  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, DownC, [128]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, DownC, [256]],  # 4-P3/8
+   [-1, 15, BottleneckCSPA, [256]],
+   [-1, 1, DownC, [512]],  # 6-P4/16
+   [-1, 15, BottleneckCSPA, [512]],
+   [-1, 1, DownC, [768]], # 8-P5/32
+   [-1, 7, BottleneckCSPA, [768]],
+   [-1, 1, DownC, [1024]], # 10-P6/64
+   [-1, 7, BottleneckCSPA, [1024]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 12
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [384]], # 17
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, DownC, [256]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 31
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, DownC, [384]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [384]], # 35
+   [-1, 1, Conv, [768, 3, 1]],
+   [-2, 1, DownC, [512]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [512]], # 39
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/baseline/yolor-e6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.25  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, DownC, [128]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, DownC, [256]],  # 4-P3/8
+   [-1, 7, BottleneckCSPA, [256]],
+   [-1, 1, DownC, [512]],  # 6-P4/16
+   [-1, 7, BottleneckCSPA, [512]],
+   [-1, 1, DownC, [768]], # 8-P5/32
+   [-1, 3, BottleneckCSPA, [768]],
+   [-1, 1, DownC, [1024]], # 10-P6/64
+   [-1, 3, BottleneckCSPA, [1024]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 12
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [384]], # 17
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, DownC, [256]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 31
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, DownC, [384]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [384]], # 35
+   [-1, 1, Conv, [768, 3, 1]],
+   [-2, 1, DownC, [512]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [512]], # 39
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/baseline/yolor-p6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.0  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
+   [-1, 7, BottleneckCSPA, [256]],
+   [-1, 1, Conv, [384, 3, 2]],  # 6-P4/16
+   [-1, 7, BottleneckCSPA, [384]],
+   [-1, 1, Conv, [512, 3, 2]], # 8-P5/32
+   [-1, 3, BottleneckCSPA, [512]],
+   [-1, 1, Conv, [640, 3, 2]], # 10-P6/64
+   [-1, 3, BottleneckCSPA, [640]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [320]], # 12
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [256, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 17
+   [-1, 1, Conv, [192, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [192, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [192]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [192, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [192]], # 31
+   [-1, 1, Conv, [384, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 35
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [320, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [320]], # 39
+   [-1, 1, Conv, [640, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/baseline/yolor-w6.yaml

@@ -0,0 +1,63 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # expand model depth
+width_multiple: 1.0  # expand layer channels
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 3, BottleneckCSPA, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 4-P3/8
+   [-1, 7, BottleneckCSPA, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 6-P4/16
+   [-1, 7, BottleneckCSPA, [512]],
+   [-1, 1, Conv, [768, 3, 2]], # 8-P5/32
+   [-1, 3, BottleneckCSPA, [768]],
+   [-1, 1, Conv, [1024, 3, 2]], # 10-P6/64
+   [-1, 3, BottleneckCSPA, [1024]],  # 11
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 12
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-6, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [384]], # 17
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-13, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [256]], # 22
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [-20, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 3, BottleneckCSPB, [128]], # 27
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 22], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [256]], # 31
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [384, 3, 2]],
+   [[-1, 17], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [384]], # 35
+   [-1, 1, Conv, [768, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 12], 1, Concat, [1]],  # cat
+   [-1, 3, BottleneckCSPB, [512]], # 39
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[28,32,36,40], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/baseline/yolov3-spp.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/baseline/yolov3.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, [1, 1]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/baseline/yolov4-csp.yaml

@@ -0,0 +1,52 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# CSP-Darknet backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, BottleneckCSPC, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, BottleneckCSPC, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, BottleneckCSPC, [512]],
+   [-1, 1, Conv, [1024, 3, 2]], # 9-P5/32
+   [-1, 4, BottleneckCSPC, [1024]],  # 10
+  ]
+
+# CSP-Dark-PAN head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 11
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [8, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [256]], # 16 
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [6, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   [-1, 2, BottleneckCSPB, [128]], # 21
+   [-1, 1, Conv, [256, 3, 1]],
+   [-2, 1, Conv, [256, 3, 2]],
+   [[-1, 16], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [256]], # 25
+   [-1, 1, Conv, [512, 3, 1]],
+   [-2, 1, Conv, [512, 3, 2]],
+   [[-1, 11], 1, Concat, [1]],  # cat
+   [-1, 2, BottleneckCSPB, [512]], # 29
+   [-1, 1, Conv, [1024, 3, 1]],
+
+   [[22,26,30], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/deploy/yolov7-d6.yaml

@@ -0,0 +1,202 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-d6 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [96, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [192]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]],  # 14
+         
+   [-1, 1, DownC, [384]],  # 15-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]],  # 27
+         
+   [-1, 1, DownC, [768]],  # 28-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 40
+         
+   [-1, 1, DownC, [1152]],  # 41-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1152, 1, 1]],  # 53
+         
+   [-1, 1, DownC, [1536]],  # 54-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1536, 1, 1]],  # 66
+  ]
+
+# yolov7-d6 head
+head:
+  [[-1, 1, SPPCSPC, [768]], # 67
+  
+   [-1, 1, Conv, [576, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [53, 1, Conv, [576, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 83
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [40, 1, Conv, [384, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 99
+   
+   [-1, 1, Conv, [192, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [27, 1, Conv, [192, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]], # 115
+      
+   [-1, 1, DownC, [384]],
+   [[-1, 99], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 129
+      
+   [-1, 1, DownC, [576]],
+   [[-1, 83], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 143
+      
+   [-1, 1, DownC, [768]],
+   [[-1, 67], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]], # 157
+   
+   [115, 1, Conv, [384, 3, 1]],
+   [129, 1, Conv, [768, 3, 1]],
+   [143, 1, Conv, [1152, 3, 1]],
+   [157, 1, Conv, [1536, 3, 1]],
+
+   [[158,159,160,161], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/deploy/yolov7-e6.yaml

@@ -0,0 +1,180 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-e6 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+         
+   [-1, 1, DownC, [320]],  # 13-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 23
+         
+   [-1, 1, DownC, [640]],  # 24-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 34
+         
+   [-1, 1, DownC, [960]],  # 35-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 45
+         
+   [-1, 1, DownC, [1280]],  # 46-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 56
+  ]
+
+# yolov7-e6 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 57
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 71
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [34, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 85
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [23, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 99
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 85], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 111
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 71], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 123
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 57], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 135
+   
+   [99, 1, Conv, [320, 3, 1]],
+   [111, 1, Conv, [640, 3, 1]],
+   [123, 1, Conv, [960, 3, 1]],
+   [135, 1, Conv, [1280, 3, 1]],
+
+   [[136,137,138,139], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/deploy/yolov7-e6e.yaml

@@ -0,0 +1,301 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-e6e backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+   [-11, 1, Conv, [64, 1, 1]],
+   [-12, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 22
+   [[-1, -11], 1, Shortcut, [1]],  # 23
+         
+   [-1, 1, DownC, [320]],  # 24-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 34
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 44
+   [[-1, -11], 1, Shortcut, [1]],  # 45
+         
+   [-1, 1, DownC, [640]],  # 46-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 56
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 66
+   [[-1, -11], 1, Shortcut, [1]],  # 67
+         
+   [-1, 1, DownC, [960]],  # 68-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 78
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 88
+   [[-1, -11], 1, Shortcut, [1]],  # 89
+         
+   [-1, 1, DownC, [1280]],  # 90-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 100 
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 110
+   [[-1, -11], 1, Shortcut, [1]],  # 111 
+  ]
+
+# yolov7-e6e head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 112
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [89, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 126
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 136
+   [[-1, -11], 1, Shortcut, [1]],  # 137
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [67, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 151
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 161
+   [[-1, -11], 1, Shortcut, [1]],  # 162
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 176
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 186
+   [[-1, -11], 1, Shortcut, [1]],  # 187
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 162], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 199
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 209
+   [[-1, -11], 1, Shortcut, [1]],  # 210
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 137], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 222
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 232
+   [[-1, -11], 1, Shortcut, [1]],  # 233
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 112], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 245
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 255
+   [[-1, -11], 1, Shortcut, [1]],  # 256
+   
+   [187, 1, Conv, [320, 3, 1]],
+   [210, 1, Conv, [640, 3, 1]],
+   [233, 1, Conv, [960, 3, 1]],
+   [256, 1, Conv, [1280, 3, 1]],
+
+   [[257,258,259,260], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/deploy/yolov7-tiny-silu.yaml

@@ -0,0 +1,112 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv7-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 2]],  # 0-P1/2  
+  
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P2/4    
+   
+   [-1, 1, Conv, [32, 1, 1]],
+   [-2, 1, Conv, [32, 1, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1]],  # 7
+   
+   [-1, 1, MP, []],  # 8-P3/8
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 14
+   
+   [-1, 1, MP, []],  # 15-P4/16
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 21
+   
+   [-1, 1, MP, []],  # 22-P5/32
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 28
+  ]
+
+# YOLOv7-tiny head
+head:
+  [[-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, SP, [5]],
+   [-2, 1, SP, [9]],
+   [-3, 1, SP, [13]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [[-1, -7], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 37
+  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [21, 1, Conv, [128, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 47
+  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [14, 1, Conv, [64, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [32, 1, 1]],
+   [-2, 1, Conv, [32, 1, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, Conv, [32, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1]],  # 57
+   
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, 47], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 65
+   
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 37], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 73
+      
+   [57, 1, Conv, [128, 3, 1]],
+   [65, 1, Conv, [256, 3, 1]],
+   [73, 1, Conv, [512, 3, 1]],
+
+   [[74,75,76], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/deploy/yolov7-tiny.yaml

@@ -0,0 +1,112 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# yolov7-tiny backbone
+backbone:
+  # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
+  [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 0-P1/2  
+  
+   [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 1-P2/4    
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 7
+   
+   [-1, 1, MP, []],  # 8-P3/8
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 14
+   
+   [-1, 1, MP, []],  # 15-P4/16
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 21
+   
+   [-1, 1, MP, []],  # 22-P5/32
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 28
+  ]
+
+# yolov7-tiny head
+head:
+  [[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, SP, [5]],
+   [-2, 1, SP, [9]],
+   [-3, 1, SP, [13]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -7], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 37
+  
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 47
+  
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 57
+   
+   [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 47], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 65
+   
+   [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 37], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 73
+      
+   [57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+
+   [[74,75,76], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/deploy/yolov7-w6.yaml

@@ -0,0 +1,158 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7-w6 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 10
+         
+   [-1, 1, Conv, [256, 3, 2]],  # 11-P3/8
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 19
+         
+   [-1, 1, Conv, [512, 3, 2]],  # 20-P4/16
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 28
+         
+   [-1, 1, Conv, [768, 3, 2]],  # 29-P5/32
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 37
+         
+   [-1, 1, Conv, [1024, 3, 2]],  # 38-P6/64
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 46
+  ]
+
+# yolov7-w6 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 47
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 59
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 71
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [19, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 83
+      
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 71], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 93
+      
+   [-1, 1, Conv, [384, 3, 2]],
+   [[-1, 59], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 103
+      
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 47], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 113
+   
+   [83, 1, Conv, [256, 3, 1]],
+   [93, 1, Conv, [512, 3, 1]],
+   [103, 1, Conv, [768, 3, 1]],
+   [113, 1, Conv, [1024, 3, 1]],
+
+   [[114,115,116,117], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/deploy/yolov7.yaml

@@ -0,0 +1,140 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [64, 3, 1]],
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 11
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 24
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 37
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-3, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 50
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 51
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 63
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [24, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 75
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3, 63], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 88
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3, 51], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 101
+   
+   [75, 1, RepConv, [256, 3, 1]],
+   [88, 1, RepConv, [512, 3, 1]],
+   [101, 1, RepConv, [1024, 3, 1]],
+
+   [[102,103,104], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/deploy/yolov7x.yaml

@@ -0,0 +1,156 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7x backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [40, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [80, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [80, 3, 1]],
+   
+   [-1, 1, Conv, [160, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 13
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 18-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 28
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 33-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 43
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [640, 1, 1]],
+   [-3, 1, Conv, [640, 1, 1]],
+   [-1, 1, Conv, [640, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 48-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 58
+  ]
+
+# yolov7x head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 59
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [43, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 73
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 87
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3, 73], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 102
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3, 59], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 117
+   
+   [87, 1, Conv, [320, 3, 1]],
+   [102, 1, Conv, [640, 3, 1]],
+   [117, 1, Conv, [1280, 3, 1]],
+
+   [[118,119,120], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/training/yolov7-d6.yaml

@@ -0,0 +1,207 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [96, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [192]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]],  # 14
+         
+   [-1, 1, DownC, [384]],  # 15-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]],  # 27
+         
+   [-1, 1, DownC, [768]],  # 28-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 40
+         
+   [-1, 1, DownC, [1152]],  # 41-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1152, 1, 1]],  # 53
+         
+   [-1, 1, DownC, [1536]],  # 54-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [1536, 1, 1]],  # 66
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [768]], # 67
+  
+   [-1, 1, Conv, [576, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [53, 1, Conv, [576, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 83
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [40, 1, Conv, [384, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 99
+   
+   [-1, 1, Conv, [192, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [27, 1, Conv, [192, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [192, 1, 1]], # 115
+      
+   [-1, 1, DownC, [384]],
+   [[-1, 99], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 129
+      
+   [-1, 1, DownC, [576]],
+   [[-1, 83], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [576, 1, 1]], # 143
+      
+   [-1, 1, DownC, [768]],
+   [[-1, 67], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8, -9, -10], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]], # 157
+   
+   [115, 1, Conv, [384, 3, 1]],
+   [129, 1, Conv, [768, 3, 1]],
+   [143, 1, Conv, [1152, 3, 1]],
+   [157, 1, Conv, [1536, 3, 1]],
+   
+   [115, 1, Conv, [384, 3, 1]],
+   [99, 1, Conv, [768, 3, 1]],
+   [83, 1, Conv, [1152, 3, 1]],
+   [67, 1, Conv, [1536, 3, 1]],
+
+   [[158,159,160,161,162,163,164,165], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/training/yolov7-e6.yaml

@@ -0,0 +1,185 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+         
+   [-1, 1, DownC, [320]],  # 13-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 23
+         
+   [-1, 1, DownC, [640]],  # 24-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 34
+         
+   [-1, 1, DownC, [960]],  # 35-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 45
+         
+   [-1, 1, DownC, [1280]],  # 46-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 56
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 57
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 71
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [34, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 85
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [23, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 99
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 85], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 111
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 71], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 123
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 57], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 135
+   
+   [99, 1, Conv, [320, 3, 1]],
+   [111, 1, Conv, [640, 3, 1]],
+   [123, 1, Conv, [960, 3, 1]],
+   [135, 1, Conv, [1280, 3, 1]],
+   
+   [99, 1, Conv, [320, 3, 1]],
+   [85, 1, Conv, [640, 3, 1]],
+   [71, 1, Conv, [960, 3, 1]],
+   [57, 1, Conv, [1280, 3, 1]],
+
+   [[136,137,138,139,140,141,142,143], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/training/yolov7-e6e.yaml

@@ -0,0 +1,306 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args],
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [80, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, DownC, [160]],  # 2-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 12
+   [-11, 1, Conv, [64, 1, 1]],
+   [-12, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]],  # 22
+   [[-1, -11], 1, Shortcut, [1]],  # 23
+         
+   [-1, 1, DownC, [320]],  # 24-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 34
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 44
+   [[-1, -11], 1, Shortcut, [1]],  # 45
+         
+   [-1, 1, DownC, [640]],  # 46-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 56
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 66
+   [[-1, -11], 1, Shortcut, [1]],  # 67
+         
+   [-1, 1, DownC, [960]],  # 68-P5/32  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 78
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [960, 1, 1]],  # 88
+   [[-1, -11], 1, Shortcut, [1]],  # 89
+         
+   [-1, 1, DownC, [1280]],  # 90-P6/64  
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 100 
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 110
+   [[-1, -11], 1, Shortcut, [1]],  # 111 
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 112
+  
+   [-1, 1, Conv, [480, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [89, 1, Conv, [480, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 126
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 136
+   [[-1, -11], 1, Shortcut, [1]],  # 137
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [67, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 151
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 161
+   [[-1, -11], 1, Shortcut, [1]],  # 162
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [45, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 176
+   [-11, 1, Conv, [128, 1, 1]],
+   [-12, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 186
+   [[-1, -11], 1, Shortcut, [1]],  # 187
+      
+   [-1, 1, DownC, [320]],
+   [[-1, 162], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 199
+   [-11, 1, Conv, [256, 1, 1]],
+   [-12, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 209
+   [[-1, -11], 1, Shortcut, [1]],  # 210
+      
+   [-1, 1, DownC, [480]],
+   [[-1, 137], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 222
+   [-11, 1, Conv, [384, 1, 1]],
+   [-12, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [480, 1, 1]], # 232
+   [[-1, -11], 1, Shortcut, [1]],  # 233
+      
+   [-1, 1, DownC, [640]],
+   [[-1, 112], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 245
+   [-11, 1, Conv, [512, 1, 1]],
+   [-12, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 255
+   [[-1, -11], 1, Shortcut, [1]],  # 256
+   
+   [187, 1, Conv, [320, 3, 1]],
+   [210, 1, Conv, [640, 3, 1]],
+   [233, 1, Conv, [960, 3, 1]],
+   [256, 1, Conv, [1280, 3, 1]],
+   
+   [186, 1, Conv, [320, 3, 1]],
+   [161, 1, Conv, [640, 3, 1]],
+   [136, 1, Conv, [960, 3, 1]],
+   [112, 1, Conv, [1280, 3, 1]],
+
+   [[257,258,259,260,261,262,263,264], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/training/yolov7-tiny.yaml

@@ -0,0 +1,112 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# yolov7-tiny backbone
+backbone:
+  # [from, number, module, args] c2, k=1, s=1, p=None, g=1, act=True
+  [[-1, 1, Conv, [32, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 0-P1/2  
+  
+   [-1, 1, Conv, [64, 3, 2, None, 1, nn.LeakyReLU(0.1)]],  # 1-P2/4    
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 7
+   
+   [-1, 1, MP, []],  # 8-P3/8
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 14
+   
+   [-1, 1, MP, []],  # 15-P4/16
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 21
+   
+   [-1, 1, MP, []],  # 22-P5/32
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 28
+  ]
+
+# yolov7-tiny head
+head:
+  [[-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, SP, [5]],
+   [-2, 1, SP, [9]],
+   [-3, 1, SP, [13]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -7], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 37
+  
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [21, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 47
+  
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [14, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [32, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [32, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 57
+   
+   [-1, 1, Conv, [128, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 47], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [64, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [64, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 65
+   
+   [-1, 1, Conv, [256, 3, 2, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, 37], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-2, 1, Conv, [128, 1, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [-1, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [[-1, -2, -3, -4], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1, None, 1, nn.LeakyReLU(0.1)]],  # 73
+      
+   [57, 1, Conv, [128, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [65, 1, Conv, [256, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+   [73, 1, Conv, [512, 3, 1, None, 1, nn.LeakyReLU(0.1)]],
+
+   [[74,75,76], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/training/yolov7-w6.yaml

@@ -0,0 +1,163 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, ReOrg, []],  # 0
+   [-1, 1, Conv, [64, 3, 1]],  # 1-P1/2
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 2-P2/4
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]],  # 10
+         
+   [-1, 1, Conv, [256, 3, 2]],  # 11-P3/8
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 19
+         
+   [-1, 1, Conv, [512, 3, 2]],  # 20-P4/16
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 28
+         
+   [-1, 1, Conv, [768, 3, 2]],  # 29-P5/32
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [-1, 1, Conv, [384, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [768, 1, 1]],  # 37
+         
+   [-1, 1, Conv, [1024, 3, 2]],  # 38-P6/64
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 46
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 47
+  
+   [-1, 1, Conv, [384, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [384, 1, 1]], # route backbone P5
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 59
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 71
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [19, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 83
+      
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 71], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 93
+      
+   [-1, 1, Conv, [384, 3, 2]],
+   [[-1, 59], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [384, 1, 1]],
+   [-2, 1, Conv, [384, 1, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [-1, 1, Conv, [192, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [384, 1, 1]], # 103
+      
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 47], 1, Concat, [1]],  # cat
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 113
+   
+   [83, 1, Conv, [256, 3, 1]],
+   [93, 1, Conv, [512, 3, 1]],
+   [103, 1, Conv, [768, 3, 1]],
+   [113, 1, Conv, [1024, 3, 1]],
+   
+   [83, 1, Conv, [320, 3, 1]],
+   [71, 1, Conv, [640, 3, 1]],
+   [59, 1, Conv, [960, 3, 1]],
+   [47, 1, Conv, [1280, 3, 1]],
+
+   [[114,115,116,117,118,119,120,121], 1, IAuxDetect, [nc, anchors]],   # Detect(P3, P4, P5, P6)
+  ]

infer/yolov7/cfg/training/yolov7.yaml

@@ -0,0 +1,140 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [64, 3, 1]],
+   
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]],  # 11
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 16-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]],  # 24
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 29-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 37
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-3, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 42-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [1024, 1, 1]],  # 50
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [512]], # 51
+  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [37, 1, Conv, [256, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 63
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [24, 1, Conv, [128, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [128, 1, 1]], # 75
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [128, 1, 1]],
+   [-3, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 2]],
+   [[-1, -3, 63], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [256, 1, 1]], # 88
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-3, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, -3, 51], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -2, -3, -4, -5, -6], 1, Concat, [1]],
+   [-1, 1, Conv, [512, 1, 1]], # 101
+   
+   [75, 1, RepConv, [256, 3, 1]],
+   [88, 1, RepConv, [512, 3, 1]],
+   [101, 1, RepConv, [1024, 3, 1]],
+
+   [[102,103,104], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/cfg/training/yolov7x.yaml

@@ -0,0 +1,156 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [12,16, 19,36, 40,28]  # P3/8
+  - [36,75, 76,55, 72,146]  # P4/16
+  - [142,110, 192,243, 459,401]  # P5/32
+
+# yolov7 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [40, 3, 1]],  # 0
+  
+   [-1, 1, Conv, [80, 3, 2]],  # 1-P1/2      
+   [-1, 1, Conv, [80, 3, 1]],
+   
+   [-1, 1, Conv, [160, 3, 2]],  # 3-P2/4  
+   [-1, 1, Conv, [64, 1, 1]],
+   [-2, 1, Conv, [64, 1, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, Conv, [64, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]],  # 13
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 18-P3/8  
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]],  # 28
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 33-P4/16  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 43
+         
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [640, 1, 1]],
+   [-3, 1, Conv, [640, 1, 1]],
+   [-1, 1, Conv, [640, 3, 2]],
+   [[-1, -3], 1, Concat, [1]],  # 48-P5/32  
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [1280, 1, 1]],  # 58
+  ]
+
+# yolov7 head
+head:
+  [[-1, 1, SPPCSPC, [640]], # 59
+  
+   [-1, 1, Conv, [320, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [43, 1, Conv, [320, 1, 1]], # route backbone P4
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 73
+   
+   [-1, 1, Conv, [160, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [28, 1, Conv, [160, 1, 1]], # route backbone P3
+   [[-1, -2], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [128, 1, 1]],
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, Conv, [128, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [160, 1, 1]], # 87
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [160, 1, 1]],
+   [-3, 1, Conv, [160, 1, 1]],
+   [-1, 1, Conv, [160, 3, 2]],
+   [[-1, -3, 73], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [256, 1, 1]],
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, Conv, [256, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [320, 1, 1]], # 102
+      
+   [-1, 1, MP, []],
+   [-1, 1, Conv, [320, 1, 1]],
+   [-3, 1, Conv, [320, 1, 1]],
+   [-1, 1, Conv, [320, 3, 2]],
+   [[-1, -3, 59], 1, Concat, [1]],
+   
+   [-1, 1, Conv, [512, 1, 1]],
+   [-2, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, Conv, [512, 3, 1]],
+   [[-1, -3, -5, -7, -8], 1, Concat, [1]],
+   [-1, 1, Conv, [640, 1, 1]], # 117
+   
+   [87, 1, Conv, [320, 3, 1]],
+   [102, 1, Conv, [640, 3, 1]],
+   [117, 1, Conv, [1280, 3, 1]],
+
+   [[118,119,120], 1, IDetect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

infer/yolov7/data/coco.yaml

@@ -0,0 +1,23 @@
+# COCO 2017 dataset http://cocodataset.org
+
+# download command/URL (optional)
+download: bash ./scripts/get_coco.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ./coco/train2017.txt  # 118287 images
+val: ./coco/val2017.txt  # 5000 images
+test: ./coco/test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]

infer/yolov7/data/hyp.scratch.custom.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.3  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.7  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.2  # image translation (+/- fraction)
+scale: 0.5  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.0  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.0  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

infer/yolov7/data/hyp.scratch.p5.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.1  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.3  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.7  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.2  # image translation (+/- fraction)
+scale: 0.9  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.15  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.15  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

infer/yolov7/data/hyp.scratch.p6.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.2  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.3  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 0.7  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.2  # image translation (+/- fraction)
+scale: 0.9  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.15  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.15  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

infer/yolov7/data/hyp.scratch.tiny.yaml

@@ -0,0 +1,31 @@
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.01  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.5  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 1.0  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.1  # image translation (+/- fraction)
+scale: 0.5  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.05  # image mixup (probability)
+copy_paste: 0.0  # image copy paste (probability)
+paste_in: 0.05  # image copy paste (probability), use 0 for faster training
+loss_ota: 1 # use ComputeLossOTA, use 0 for faster training

infer/yolov7/get_results.py

@@ -0,0 +1,43 @@
+import torch
+import cv2
+from infer.yolov7.models.experimental import attempt_load
+from infer.yolov7.utils.datasets import letterbox
+from infer.yolov7.utils.general import non_max_suppression, scale_coords
+from infer.yolov7.utils.torch_utils import select_device
+import numpy as np
+
+colors = [(np.random.randint(0, 255), np.random.randint(0, 255), np.random.randint(0, 255)) for _ in range(20)]
+
+def get_yolov7_result(image, conf_threshold, iou_threshold, class_names):
+    weights = 'my_model/v7-tiny.pt'
+    device = select_device('cpu')
+    model = attempt_load(weights, map_location=device)
+    model.eval()
+
+    img = letterbox(image, new_shape=320)[0]
+    img = img[:, :, ::-1].transpose(2, 0, 1)
+    img = torch.from_numpy(img.copy()).to(device)
+    img = img.float()
+    img /= 255.0
+    if img.ndimension() == 3:
+        img = img.unsqueeze(0)
+
+    with torch.no_grad():
+        pred = model(img, augment=False)[0]
+        pred = non_max_suppression(pred, conf_threshold, iou_threshold, classes=None, agnostic=False)
+
+    img0 = image.copy()
+    result_list = []
+
+    for i, det in enumerate(pred):
+        if len(det):
+            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img0.shape).round()
+            for *xyxy, conf, cls in reversed(det):
+                x1, y1, x2, y2 = map(int, xyxy)
+                label = f'{class_names[int(cls) - 1]} {conf:.2f}'
+                color = colors[int(cls) % len(colors)]
+                result_list.append([class_names[int(cls) - 1], color, conf])
+                cv2.rectangle(img0, (x1, y1), (x2, y2), color, 2)
+                cv2.putText(img0, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)
+    img0 = img0[...,::-1]
+    return img0, result_list

infer/yolov7/models/__init__.py

@@ -0,0 +1,2 @@
+# init
+from .yolo import *

infer/yolov7/models/common.py

@@ -0,0 +1,2019 @@
+import math
+from copy import copy
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torchvision.ops import DeformConv2d
+from PIL import Image
+from torch.cuda import amp
+
+from infer.yolov7.utils.datasets import letterbox
+from infer.yolov7.utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh
+from infer.yolov7.utils.plots import color_list, plot_one_box
+from infer.yolov7.utils.torch_utils import time_synchronized
+
+
+##### basic ####
+
+def autopad(k, p=None):  # kernel, padding
+    # Pad to 'same'
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+class MP(nn.Module):
+    def __init__(self, k=2):
+        super(MP, self).__init__()
+        self.m = nn.MaxPool2d(kernel_size=k, stride=k)
+
+    def forward(self, x):
+        return self.m(x)
+
+
+class SP(nn.Module):
+    def __init__(self, k=3, s=1):
+        super(SP, self).__init__()
+        self.m = nn.MaxPool2d(kernel_size=k, stride=s, padding=k // 2)
+
+    def forward(self, x):
+        return self.m(x)
+    
+    
+class ReOrg(nn.Module):
+    def __init__(self):
+        super(ReOrg, self).__init__()
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1)
+
+
+class Concat(nn.Module):
+    def __init__(self, dimension=1):
+        super(Concat, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class Chuncat(nn.Module):
+    def __init__(self, dimension=1):
+        super(Chuncat, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        x1 = []
+        x2 = []
+        for xi in x:
+            xi1, xi2 = xi.chunk(2, self.d)
+            x1.append(xi1)
+            x2.append(xi2)
+        return torch.cat(x1+x2, self.d)
+
+
+class Shortcut(nn.Module):
+    def __init__(self, dimension=0):
+        super(Shortcut, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return x[0]+x[1]
+
+
+class Foldcut(nn.Module):
+    def __init__(self, dimension=0):
+        super(Foldcut, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        x1, x2 = x.chunk(2, self.d)
+        return x1+x2
+
+
+class Conv(nn.Module):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Conv, self).__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def fuseforward(self, x):
+        return self.act(self.conv(x))
+    
+
+class RobustConv(nn.Module):
+    # Robust convolution (use high kernel size 7-11 for: downsampling and other layers). Train for 300 - 450 epochs.
+    def __init__(self, c1, c2, k=7, s=1, p=None, g=1, act=True, layer_scale_init_value=1e-6):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(RobustConv, self).__init__()
+        self.conv_dw = Conv(c1, c1, k=k, s=s, p=p, g=c1, act=act)
+        self.conv1x1 = nn.Conv2d(c1, c2, 1, 1, 0, groups=1, bias=True)
+        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones(c2)) if layer_scale_init_value > 0 else None
+
+    def forward(self, x):
+        x = x.to(memory_format=torch.channels_last)
+        x = self.conv1x1(self.conv_dw(x))
+        if self.gamma is not None:
+            x = x.mul(self.gamma.reshape(1, -1, 1, 1)) 
+        return x
+
+
+class RobustConv2(nn.Module):
+    # Robust convolution 2 (use [32, 5, 2] or [32, 7, 4] or [32, 11, 8] for one of the paths in CSP).
+    def __init__(self, c1, c2, k=7, s=4, p=None, g=1, act=True, layer_scale_init_value=1e-6):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(RobustConv2, self).__init__()
+        self.conv_strided = Conv(c1, c1, k=k, s=s, p=p, g=c1, act=act)
+        self.conv_deconv = nn.ConvTranspose2d(in_channels=c1, out_channels=c2, kernel_size=s, stride=s, 
+                                              padding=0, bias=True, dilation=1, groups=1
+        )
+        self.gamma = nn.Parameter(layer_scale_init_value * torch.ones(c2)) if layer_scale_init_value > 0 else None
+
+    def forward(self, x):
+        x = self.conv_deconv(self.conv_strided(x))
+        if self.gamma is not None:
+            x = x.mul(self.gamma.reshape(1, -1, 1, 1)) 
+        return x
+    
+
+def DWConv(c1, c2, k=1, s=1, act=True):
+    # Depthwise convolution
+    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super(GhostConv, self).__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat([y, self.cv2(y)], 1)
+
+
+class Stem(nn.Module):
+    # Stem
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Stem, self).__init__()
+        c_ = int(c2/2)  # hidden channels
+        self.cv1 = Conv(c1, c_, 3, 2)
+        self.cv2 = Conv(c_, c_, 1, 1)
+        self.cv3 = Conv(c_, c_, 3, 2)
+        self.pool = torch.nn.MaxPool2d(2, stride=2)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        return self.cv4(torch.cat((self.cv3(self.cv2(x)), self.pool(x)), dim=1))
+
+
+class DownC(nn.Module):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, n=1, k=2):
+        super(DownC, self).__init__()
+        c_ = int(c1)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2//2, 3, k)
+        self.cv3 = Conv(c1, c2//2, 1, 1)
+        self.mp = nn.MaxPool2d(kernel_size=k, stride=k)
+
+    def forward(self, x):
+        return torch.cat((self.cv2(self.cv1(x)), self.cv3(self.mp(x))), dim=1)
+
+
+class SPP(nn.Module):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super(SPP, self).__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+    
+
+class Bottleneck(nn.Module):
+    # Darknet bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super(Bottleneck, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Res(nn.Module):
+    # ResNet bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super(Res, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c_, 3, 1, g=g)
+        self.cv3 = Conv(c_, c2, 1, 1)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv3(self.cv2(self.cv1(x))) if self.add else self.cv3(self.cv2(self.cv1(x)))
+
+
+class ResX(Res):
+    # ResNet bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__(c1, c2, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+
+
+class Ghost(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super(Ghost, self).__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pw
+                                  DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+                                  GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
+                                      Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+##### end of basic #####
+
+
+##### cspnet #####
+
+class SPPCSPC(nn.Module):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
+        super(SPPCSPC, self).__init__()
+        c_ = int(2 * c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(c_, c_, 3, 1)
+        self.cv4 = Conv(c_, c_, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+        self.cv5 = Conv(4 * c_, c_, 1, 1)
+        self.cv6 = Conv(c_, c_, 3, 1)
+        self.cv7 = Conv(2 * c_, c2, 1, 1)
+
+    def forward(self, x):
+        x1 = self.cv4(self.cv3(self.cv1(x)))
+        y1 = self.cv6(self.cv5(torch.cat([x1] + [m(x1) for m in self.m], 1)))
+        y2 = self.cv2(x)
+        return self.cv7(torch.cat((y1, y2), dim=1))
+
+class GhostSPPCSPC(SPPCSPC):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5, k=(5, 9, 13)):
+        super().__init__(c1, c2, n, shortcut, g, e, k)
+        c_ = int(2 * c2 * e)  # hidden channels
+        self.cv1 = GhostConv(c1, c_, 1, 1)
+        self.cv2 = GhostConv(c1, c_, 1, 1)
+        self.cv3 = GhostConv(c_, c_, 3, 1)
+        self.cv4 = GhostConv(c_, c_, 1, 1)
+        self.cv5 = GhostConv(4 * c_, c_, 1, 1)
+        self.cv6 = GhostConv(c_, c_, 3, 1)
+        self.cv7 = GhostConv(2 * c_, c2, 1, 1)
+
+
+class GhostStem(Stem):
+    # Stem
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super().__init__(c1, c2, k, s, p, g, act)
+        c_ = int(c2/2)  # hidden channels
+        self.cv1 = GhostConv(c1, c_, 3, 2)
+        self.cv2 = GhostConv(c_, c_, 1, 1)
+        self.cv3 = GhostConv(c_, c_, 3, 2)
+        self.cv4 = GhostConv(2 * c_, c2, 1, 1)
+        
+
+class BottleneckCSPA(nn.Module):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(BottleneckCSPA, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1, 1)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.m(self.cv1(x))
+        y2 = self.cv2(x)
+        return self.cv3(torch.cat((y1, y2), dim=1))
+
+
+class BottleneckCSPB(nn.Module):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(BottleneckCSPB, self).__init__()
+        c_ = int(c2)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1, 1)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        x1 = self.cv1(x)
+        y1 = self.m(x1)
+        y2 = self.cv2(x1)
+        return self.cv3(torch.cat((y1, y2), dim=1))
+
+
+class BottleneckCSPC(nn.Module):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(BottleneckCSPC, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(c_, c_, 1, 1)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(torch.cat((y1, y2), dim=1))
+
+
+class ResCSPA(BottleneckCSPA):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[Res(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class ResCSPB(BottleneckCSPB):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2)  # hidden channels
+        self.m = nn.Sequential(*[Res(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class ResCSPC(BottleneckCSPC):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[Res(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class ResXCSPA(ResCSPA):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[Res(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+
+class ResXCSPB(ResCSPB):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2)  # hidden channels
+        self.m = nn.Sequential(*[Res(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+
+class ResXCSPC(ResCSPC):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[Res(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+
+class GhostCSPA(BottleneckCSPA):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[Ghost(c_, c_) for _ in range(n)])
+
+
+class GhostCSPB(BottleneckCSPB):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2)  # hidden channels
+        self.m = nn.Sequential(*[Ghost(c_, c_) for _ in range(n)])
+
+
+class GhostCSPC(BottleneckCSPC):
+    # CSP https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[Ghost(c_, c_) for _ in range(n)])
+
+##### end of cspnet #####
+
+
+##### yolor #####
+
+class ImplicitA(nn.Module):
+    def __init__(self, channel, mean=0., std=.02):
+        super(ImplicitA, self).__init__()
+        self.channel = channel
+        self.mean = mean
+        self.std = std
+        self.implicit = nn.Parameter(torch.zeros(1, channel, 1, 1))
+        nn.init.normal_(self.implicit, mean=self.mean, std=self.std)
+
+    def forward(self, x):
+        return self.implicit + x
+    
+
+class ImplicitM(nn.Module):
+    def __init__(self, channel, mean=1., std=.02):
+        super(ImplicitM, self).__init__()
+        self.channel = channel
+        self.mean = mean
+        self.std = std
+        self.implicit = nn.Parameter(torch.ones(1, channel, 1, 1))
+        nn.init.normal_(self.implicit, mean=self.mean, std=self.std)
+
+    def forward(self, x):
+        return self.implicit * x
+    
+##### end of yolor #####
+
+
+##### repvgg #####
+
+class RepConv(nn.Module):
+    # Represented convolution
+    # https://arxiv.org/abs/2101.03697
+
+    def __init__(self, c1, c2, k=3, s=1, p=None, g=1, act=True, deploy=False):
+        super(RepConv, self).__init__()
+
+        self.deploy = deploy
+        self.groups = g
+        self.in_channels = c1
+        self.out_channels = c2
+
+        assert k == 3
+        assert autopad(k, p) == 1
+
+        padding_11 = autopad(k, p) - k // 2
+
+        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+        if deploy:
+            self.rbr_reparam = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=True)
+
+        else:
+            self.rbr_identity = (nn.BatchNorm2d(num_features=c1) if c2 == c1 and s == 1 else None)
+
+            self.rbr_dense = nn.Sequential(
+                nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False),
+                nn.BatchNorm2d(num_features=c2),
+            )
+
+            self.rbr_1x1 = nn.Sequential(
+                nn.Conv2d( c1, c2, 1, s, padding_11, groups=g, bias=False),
+                nn.BatchNorm2d(num_features=c2),
+            )
+
+    def forward(self, inputs):
+        if hasattr(self, "rbr_reparam"):
+            return self.act(self.rbr_reparam(inputs))
+
+        if self.rbr_identity is None:
+            id_out = 0
+        else:
+            id_out = self.rbr_identity(inputs)
+
+        return self.act(self.rbr_dense(inputs) + self.rbr_1x1(inputs) + id_out)
+    
+    def get_equivalent_kernel_bias(self):
+        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
+        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
+        kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
+        return (
+            kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid,
+            bias3x3 + bias1x1 + biasid,
+        )
+
+    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
+        if kernel1x1 is None:
+            return 0
+        else:
+            return nn.functional.pad(kernel1x1, [1, 1, 1, 1])
+
+    def _fuse_bn_tensor(self, branch):
+        if branch is None:
+            return 0, 0
+        if isinstance(branch, nn.Sequential):
+            kernel = branch[0].weight
+            running_mean = branch[1].running_mean
+            running_var = branch[1].running_var
+            gamma = branch[1].weight
+            beta = branch[1].bias
+            eps = branch[1].eps
+        else:
+            assert isinstance(branch, nn.BatchNorm2d)
+            if not hasattr(self, "id_tensor"):
+                input_dim = self.in_channels // self.groups
+                kernel_value = np.zeros(
+                    (self.in_channels, input_dim, 3, 3), dtype=np.float32
+                )
+                for i in range(self.in_channels):
+                    kernel_value[i, i % input_dim, 1, 1] = 1
+                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
+            kernel = self.id_tensor
+            running_mean = branch.running_mean
+            running_var = branch.running_var
+            gamma = branch.weight
+            beta = branch.bias
+            eps = branch.eps
+        std = (running_var + eps).sqrt()
+        t = (gamma / std).reshape(-1, 1, 1, 1)
+        return kernel * t, beta - running_mean * gamma / std
+
+    def repvgg_convert(self):
+        kernel, bias = self.get_equivalent_kernel_bias()
+        return (
+            kernel.detach().cpu().numpy(),
+            bias.detach().cpu().numpy(),
+        )
+
+    def fuse_conv_bn(self, conv, bn):
+
+        std = (bn.running_var + bn.eps).sqrt()
+        bias = bn.bias - bn.running_mean * bn.weight / std
+
+        t = (bn.weight / std).reshape(-1, 1, 1, 1)
+        weights = conv.weight * t
+
+        bn = nn.Identity()
+        conv = nn.Conv2d(in_channels = conv.in_channels,
+                              out_channels = conv.out_channels,
+                              kernel_size = conv.kernel_size,
+                              stride=conv.stride,
+                              padding = conv.padding,
+                              dilation = conv.dilation,
+                              groups = conv.groups,
+                              bias = True,
+                              padding_mode = conv.padding_mode)
+
+        conv.weight = torch.nn.Parameter(weights)
+        conv.bias = torch.nn.Parameter(bias)
+        return conv
+
+    def fuse_repvgg_block(self):    
+        if self.deploy:
+            return
+        print(f"RepConv.fuse_repvgg_block")
+                
+        self.rbr_dense = self.fuse_conv_bn(self.rbr_dense[0], self.rbr_dense[1])
+        
+        self.rbr_1x1 = self.fuse_conv_bn(self.rbr_1x1[0], self.rbr_1x1[1])
+        rbr_1x1_bias = self.rbr_1x1.bias
+        weight_1x1_expanded = torch.nn.functional.pad(self.rbr_1x1.weight, [1, 1, 1, 1])
+        
+        # Fuse self.rbr_identity
+        if (isinstance(self.rbr_identity, nn.BatchNorm2d) or isinstance(self.rbr_identity, nn.modules.batchnorm.SyncBatchNorm)):
+            # print(f"fuse: rbr_identity == BatchNorm2d or SyncBatchNorm")
+            identity_conv_1x1 = nn.Conv2d(
+                    in_channels=self.in_channels,
+                    out_channels=self.out_channels,
+                    kernel_size=1,
+                    stride=1,
+                    padding=0,
+                    groups=self.groups, 
+                    bias=False)
+            identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.to(self.rbr_1x1.weight.data.device)
+            identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.squeeze().squeeze()
+            # print(f" identity_conv_1x1.weight = {identity_conv_1x1.weight.shape}")
+            identity_conv_1x1.weight.data.fill_(0.0)
+            identity_conv_1x1.weight.data.fill_diagonal_(1.0)
+            identity_conv_1x1.weight.data = identity_conv_1x1.weight.data.unsqueeze(2).unsqueeze(3)
+            # print(f" identity_conv_1x1.weight = {identity_conv_1x1.weight.shape}")
+
+            identity_conv_1x1 = self.fuse_conv_bn(identity_conv_1x1, self.rbr_identity)
+            bias_identity_expanded = identity_conv_1x1.bias
+            weight_identity_expanded = torch.nn.functional.pad(identity_conv_1x1.weight, [1, 1, 1, 1])            
+        else:
+            # print(f"fuse: rbr_identity != BatchNorm2d, rbr_identity = {self.rbr_identity}")
+            bias_identity_expanded = torch.nn.Parameter( torch.zeros_like(rbr_1x1_bias) )
+            weight_identity_expanded = torch.nn.Parameter( torch.zeros_like(weight_1x1_expanded) )            
+        
+
+        #print(f"self.rbr_1x1.weight = {self.rbr_1x1.weight.shape}, ")
+        #print(f"weight_1x1_expanded = {weight_1x1_expanded.shape}, ")
+        #print(f"self.rbr_dense.weight = {self.rbr_dense.weight.shape}, ")
+
+        self.rbr_dense.weight = torch.nn.Parameter(self.rbr_dense.weight + weight_1x1_expanded + weight_identity_expanded)
+        self.rbr_dense.bias = torch.nn.Parameter(self.rbr_dense.bias + rbr_1x1_bias + bias_identity_expanded)
+                
+        self.rbr_reparam = self.rbr_dense
+        self.deploy = True
+
+        if self.rbr_identity is not None:
+            del self.rbr_identity
+            self.rbr_identity = None
+
+        if self.rbr_1x1 is not None:
+            del self.rbr_1x1
+            self.rbr_1x1 = None
+
+        if self.rbr_dense is not None:
+            del self.rbr_dense
+            self.rbr_dense = None
+
+
+class RepBottleneck(Bottleneck):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__(c1, c2, shortcut=True, g=1, e=0.5)
+        c_ = int(c2 * e)  # hidden channels
+        self.cv2 = RepConv(c_, c2, 3, 1, g=g)
+
+
+class RepBottleneckCSPA(BottleneckCSPA):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[RepBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+
+class RepBottleneckCSPB(BottleneckCSPB):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2)  # hidden channels
+        self.m = nn.Sequential(*[RepBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+
+class RepBottleneckCSPC(BottleneckCSPC):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[RepBottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+
+class RepRes(Res):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__(c1, c2, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.cv2 = RepConv(c_, c_, 3, 1, g=g)
+
+
+class RepResCSPA(ResCSPA):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[RepRes(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class RepResCSPB(ResCSPB):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2)  # hidden channels
+        self.m = nn.Sequential(*[RepRes(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class RepResCSPC(ResCSPC):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[RepRes(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class RepResX(ResX):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super().__init__(c1, c2, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.cv2 = RepConv(c_, c_, 3, 1, g=g)
+
+
+class RepResXCSPA(ResXCSPA):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[RepResX(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class RepResXCSPB(ResXCSPB):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=32, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2)  # hidden channels
+        self.m = nn.Sequential(*[RepResX(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+
+class RepResXCSPC(ResXCSPC):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=32, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)  # hidden channels
+        self.m = nn.Sequential(*[RepResX(c_, c_, shortcut, g, e=0.5) for _ in range(n)])
+
+##### end of repvgg #####
+
+
+##### transformer #####
+
+class TransformerLayer(nn.Module):
+    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+    def __init__(self, c, num_heads):
+        super().__init__()
+        self.q = nn.Linear(c, c, bias=False)
+        self.k = nn.Linear(c, c, bias=False)
+        self.v = nn.Linear(c, c, bias=False)
+        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+        self.fc1 = nn.Linear(c, c, bias=False)
+        self.fc2 = nn.Linear(c, c, bias=False)
+
+    def forward(self, x):
+        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+        x = self.fc2(self.fc1(x)) + x
+        return x
+
+
+class TransformerBlock(nn.Module):
+    # Vision Transformer https://arxiv.org/abs/2010.11929
+    def __init__(self, c1, c2, num_heads, num_layers):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+        self.linear = nn.Linear(c2, c2)  # learnable position embedding
+        self.tr = nn.Sequential(*[TransformerLayer(c2, num_heads) for _ in range(num_layers)])
+        self.c2 = c2
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        b, _, w, h = x.shape
+        p = x.flatten(2)
+        p = p.unsqueeze(0)
+        p = p.transpose(0, 3)
+        p = p.squeeze(3)
+        e = self.linear(p)
+        x = p + e
+
+        x = self.tr(x)
+        x = x.unsqueeze(3)
+        x = x.transpose(0, 3)
+        x = x.reshape(b, self.c2, w, h)
+        return x
+
+##### end of transformer #####
+
+
+##### yolov5 #####
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Focus, self).__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+        # return self.conv(self.contract(x))
+        
+
+class SPPF(nn.Module):
+    # Spatial Pyramid Pooling - Fast (SPPF) layer for YOLOv5 by Glenn Jocher
+    def __init__(self, c1, c2, k=5):  # equivalent to SPP(k=(5, 9, 13))
+        super().__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * 4, c2, 1, 1)
+        self.m = nn.MaxPool2d(kernel_size=k, stride=1, padding=k // 2)
+
+    def forward(self, x):
+        x = self.cv1(x)
+        y1 = self.m(x)
+        y2 = self.m(y1)
+        return self.cv2(torch.cat([x, y1, y2, self.m(y2)], 1))
+    
+    
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        N, C, H, W = x.size()  # assert (H / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(N, C, H // s, s, W // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
+        return x.view(N, C * s * s, H // s, W // s)  # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        N, C, H, W = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(N, s, s, C // s ** 2, H, W)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
+        return x.view(N, C // s ** 2, H * s, W * s)  # x(1,16,160,160)
+
+
+class NMS(nn.Module):
+    # Non-Maximum Suppression (NMS) module
+    conf = 0.25  # confidence threshold
+    iou = 0.45  # IoU threshold
+    classes = None  # (optional list) filter by class
+
+    def __init__(self):
+        super(NMS, self).__init__()
+
+    def forward(self, x):
+        return non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)
+
+
+class autoShape(nn.Module):
+    # input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    classes = None  # (optional list) filter by class
+
+    def __init__(self, model):
+        super(autoShape, self).__init__()
+        self.model = model.eval()
+
+    def autoshape(self):
+        print('autoShape already enabled, skipping... ')  # model already converted to model.autoshape()
+        return self
+
+    @torch.no_grad()
+    def forward(self, imgs, size=640, augment=False, profile=False):
+        # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
+        #   filename:   imgs = 'data/samples/zidane.jpg'
+        #   URI:             = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
+        #   PIL:             = Image.open('image.jpg')  # HWC x(640,1280,3)
+        #   numpy:           = np.zeros((640,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        t = [time_synchronized()]
+        p = next(self.model.parameters())  # for device and type
+        if isinstance(imgs, torch.Tensor):  # torch
+            with amp.autocast(enabled=p.device.type != 'cpu'):
+                return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference
+
+        # Pre-process
+        n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])  # number of images, list of images
+        shape0, shape1, files = [], [], []  # image and inference shapes, filenames
+        for i, im in enumerate(imgs):
+            f = f'image{i}'  # filename
+            if isinstance(im, str):  # filename or uri
+                im, f = np.asarray(Image.open(requests.get(im, stream=True).raw if im.startswith('http') else im)), im
+            elif isinstance(im, Image.Image):  # PIL Image
+                im, f = np.asarray(im), getattr(im, 'filename', f) or f
+            files.append(Path(f).with_suffix('.jpg').name)
+            if im.shape[0] < 5:  # image in CHW
+                im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+            im = im[:, :, :3] if im.ndim == 3 else np.tile(im[:, :, None], 3)  # enforce 3ch input
+            s = im.shape[:2]  # HWC
+            shape0.append(s)  # image shape
+            g = (size / max(s))  # gain
+            shape1.append([y * g for y in s])
+            imgs[i] = im  # update
+        shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)]  # inference shape
+        x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs]  # pad
+        x = np.stack(x, 0) if n > 1 else x[0][None]  # stack
+        x = np.ascontiguousarray(x.transpose((0, 3, 1, 2)))  # BHWC to BCHW
+        x = torch.from_numpy(x).to(p.device).type_as(p) / 255.  # uint8 to fp16/32
+        t.append(time_synchronized())
+
+        with amp.autocast(enabled=p.device.type != 'cpu'):
+            # Inference
+            y = self.model(x, augment, profile)[0]  # forward
+            t.append(time_synchronized())
+
+            # Post-process
+            y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)  # NMS
+            for i in range(n):
+                scale_coords(shape1, y[i][:, :4], shape0[i])
+
+            t.append(time_synchronized())
+            return Detections(imgs, y, files, t, self.names, x.shape)
+
+
+class Detections:
+    # detections class for YOLOv5 inference results
+    def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
+        super(Detections, self).__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs]  # normalizations
+        self.imgs = imgs  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.files = files  # image filenames
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)  # number of images (batch size)
+        self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3))  # timestamps (ms)
+        self.s = shape  # inference BCHW shape
+
+    def display(self, pprint=False, show=False, save=False, render=False, save_dir=''):
+        colors = color_list()
+        for i, (img, pred) in enumerate(zip(self.imgs, self.pred)):
+            str = f'image {i + 1}/{len(self.pred)}: {img.shape[0]}x{img.shape[1]} '
+            if pred is not None:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    str += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                if show or save or render:
+                    for *box, conf, cls in pred:  # xyxy, confidence, class
+                        label = f'{self.names[int(cls)]} {conf:.2f}'
+                        plot_one_box(box, img, label=label, color=colors[int(cls) % 10])
+            img = Image.fromarray(img.astype(np.uint8)) if isinstance(img, np.ndarray) else img  # from np
+            if pprint:
+                print(str.rstrip(', '))
+            if show:
+                img.show(self.files[i])  # show
+            if save:
+                f = self.files[i]
+                img.save(Path(save_dir) / f)  # save
+                print(f"{'Saved' * (i == 0)} {f}", end=',' if i < self.n - 1 else f' to {save_dir}\n')
+            if render:
+                self.imgs[i] = np.asarray(img)
+
+    def print(self):
+        self.display(pprint=True)  # print results
+        print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' % self.t)
+
+    def show(self):
+        self.display(show=True)  # show results
+
+    def save(self, save_dir='runs/hub/exp'):
+        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp')  # increment save_dir
+        Path(save_dir).mkdir(parents=True, exist_ok=True)
+        self.display(save=True, save_dir=save_dir)  # save results
+
+    def render(self):
+        self.display(render=True)  # render results
+        return self.imgs
+
+    def pandas(self):
+        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+        new = copy(self)  # return copy
+        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
+        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
+        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
+            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+        return new
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
+        for d in x:
+            for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+                setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+    def __len__(self):
+        return self.n
+
+
+class Classify(nn.Module):
+    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Classify, self).__init__()
+        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g)  # to x(b,c2,1,1)
+        self.flat = nn.Flatten()
+
+    def forward(self, x):
+        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
+        return self.flat(self.conv(z))  # flatten to x(b,c2)
+
+##### end of yolov5 ######
+
+
+##### orepa #####
+
+def transI_fusebn(kernel, bn):
+    gamma = bn.weight
+    std = (bn.running_var + bn.eps).sqrt()
+    return kernel * ((gamma / std).reshape(-1, 1, 1, 1)), bn.bias - bn.running_mean * gamma / std
+    
+    
+class ConvBN(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size,
+                             stride=1, padding=0, dilation=1, groups=1, deploy=False, nonlinear=None):
+        super().__init__()
+        if nonlinear is None:
+            self.nonlinear = nn.Identity()
+        else:
+            self.nonlinear = nonlinear
+        if deploy:
+            self.conv = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
+                                      stride=stride, padding=padding, dilation=dilation, groups=groups, bias=True)
+        else:
+            self.conv = nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=kernel_size,
+                                            stride=stride, padding=padding, dilation=dilation, groups=groups, bias=False)
+            self.bn = nn.BatchNorm2d(num_features=out_channels)
+
+    def forward(self, x):
+        if hasattr(self, 'bn'):
+            return self.nonlinear(self.bn(self.conv(x)))
+        else:
+            return self.nonlinear(self.conv(x))
+
+    def switch_to_deploy(self):
+        kernel, bias = transI_fusebn(self.conv.weight, self.bn)
+        conv = nn.Conv2d(in_channels=self.conv.in_channels, out_channels=self.conv.out_channels, kernel_size=self.conv.kernel_size,
+                                      stride=self.conv.stride, padding=self.conv.padding, dilation=self.conv.dilation, groups=self.conv.groups, bias=True)
+        conv.weight.data = kernel
+        conv.bias.data = bias
+        for para in self.parameters():
+            para.detach_()
+        self.__delattr__('conv')
+        self.__delattr__('bn')
+        self.conv = conv    
+
+class OREPA_3x3_RepConv(nn.Module):
+
+    def __init__(self, in_channels, out_channels, kernel_size,
+                 stride=1, padding=0, dilation=1, groups=1,
+                 internal_channels_1x1_3x3=None,
+                 deploy=False, nonlinear=None, single_init=False):
+        super(OREPA_3x3_RepConv, self).__init__()
+        self.deploy = deploy
+
+        if nonlinear is None:
+            self.nonlinear = nn.Identity()
+        else:
+            self.nonlinear = nonlinear
+
+        self.kernel_size = kernel_size
+        self.in_channels = in_channels
+        self.out_channels = out_channels
+        self.groups = groups
+        assert padding == kernel_size // 2
+
+        self.stride = stride
+        self.padding = padding
+        self.dilation = dilation
+
+        self.branch_counter = 0
+
+        self.weight_rbr_origin = nn.Parameter(torch.Tensor(out_channels, int(in_channels/self.groups), kernel_size, kernel_size))
+        nn.init.kaiming_uniform_(self.weight_rbr_origin, a=math.sqrt(1.0))
+        self.branch_counter += 1
+
+
+        if groups < out_channels:
+            self.weight_rbr_avg_conv = nn.Parameter(torch.Tensor(out_channels, int(in_channels/self.groups), 1, 1))
+            self.weight_rbr_pfir_conv = nn.Parameter(torch.Tensor(out_channels, int(in_channels/self.groups), 1, 1))
+            nn.init.kaiming_uniform_(self.weight_rbr_avg_conv, a=1.0)
+            nn.init.kaiming_uniform_(self.weight_rbr_pfir_conv, a=1.0)
+            self.weight_rbr_avg_conv.data
+            self.weight_rbr_pfir_conv.data
+            self.register_buffer('weight_rbr_avg_avg', torch.ones(kernel_size, kernel_size).mul(1.0/kernel_size/kernel_size))
+            self.branch_counter += 1
+
+        else:
+            raise NotImplementedError
+        self.branch_counter += 1
+
+        if internal_channels_1x1_3x3 is None:
+            internal_channels_1x1_3x3 = in_channels if groups < out_channels else 2 * in_channels   # For mobilenet, it is better to have 2X internal channels
+
+        if internal_channels_1x1_3x3 == in_channels:
+            self.weight_rbr_1x1_kxk_idconv1 = nn.Parameter(torch.zeros(in_channels, int(in_channels/self.groups), 1, 1))
+            id_value = np.zeros((in_channels, int(in_channels/self.groups), 1, 1))
+            for i in range(in_channels):
+                id_value[i, i % int(in_channels/self.groups), 0, 0] = 1
+            id_tensor = torch.from_numpy(id_value).type_as(self.weight_rbr_1x1_kxk_idconv1)
+            self.register_buffer('id_tensor', id_tensor)
+
+        else:
+            self.weight_rbr_1x1_kxk_conv1 = nn.Parameter(torch.Tensor(internal_channels_1x1_3x3, int(in_channels/self.groups), 1, 1))
+            nn.init.kaiming_uniform_(self.weight_rbr_1x1_kxk_conv1, a=math.sqrt(1.0))
+        self.weight_rbr_1x1_kxk_conv2 = nn.Parameter(torch.Tensor(out_channels, int(internal_channels_1x1_3x3/self.groups), kernel_size, kernel_size))
+        nn.init.kaiming_uniform_(self.weight_rbr_1x1_kxk_conv2, a=math.sqrt(1.0))
+        self.branch_counter += 1
+
+        expand_ratio = 8
+        self.weight_rbr_gconv_dw = nn.Parameter(torch.Tensor(in_channels*expand_ratio, 1, kernel_size, kernel_size))
+        self.weight_rbr_gconv_pw = nn.Parameter(torch.Tensor(out_channels, in_channels*expand_ratio, 1, 1))
+        nn.init.kaiming_uniform_(self.weight_rbr_gconv_dw, a=math.sqrt(1.0))
+        nn.init.kaiming_uniform_(self.weight_rbr_gconv_pw, a=math.sqrt(1.0))
+        self.branch_counter += 1
+
+        if out_channels == in_channels and stride == 1:
+            self.branch_counter += 1
+
+        self.vector = nn.Parameter(torch.Tensor(self.branch_counter, self.out_channels))
+        self.bn = nn.BatchNorm2d(out_channels)
+
+        self.fre_init()
+
+        nn.init.constant_(self.vector[0, :], 0.25)    #origin
+        nn.init.constant_(self.vector[1, :], 0.25)      #avg
+        nn.init.constant_(self.vector[2, :], 0.0)      #prior
+        nn.init.constant_(self.vector[3, :], 0.5)    #1x1_kxk
+        nn.init.constant_(self.vector[4, :], 0.5)     #dws_conv
+
+
+    def fre_init(self):
+        prior_tensor = torch.Tensor(self.out_channels, self.kernel_size, self.kernel_size)
+        half_fg = self.out_channels/2
+        for i in range(self.out_channels):
+            for h in range(3):
+                for w in range(3):
+                    if i < half_fg:
+                        prior_tensor[i, h, w] = math.cos(math.pi*(h+0.5)*(i+1)/3)
+                    else:
+                        prior_tensor[i, h, w] = math.cos(math.pi*(w+0.5)*(i+1-half_fg)/3)
+
+        self.register_buffer('weight_rbr_prior', prior_tensor)
+
+    def weight_gen(self):
+
+        weight_rbr_origin = torch.einsum('oihw,o->oihw', self.weight_rbr_origin, self.vector[0, :])
+
+        weight_rbr_avg = torch.einsum('oihw,o->oihw', torch.einsum('oihw,hw->oihw', self.weight_rbr_avg_conv, self.weight_rbr_avg_avg), self.vector[1, :])
+        
+        weight_rbr_pfir = torch.einsum('oihw,o->oihw', torch.einsum('oihw,ohw->oihw', self.weight_rbr_pfir_conv, self.weight_rbr_prior), self.vector[2, :])
+
+        weight_rbr_1x1_kxk_conv1 = None
+        if hasattr(self, 'weight_rbr_1x1_kxk_idconv1'):
+            weight_rbr_1x1_kxk_conv1 = (self.weight_rbr_1x1_kxk_idconv1 + self.id_tensor).squeeze()
+        elif hasattr(self, 'weight_rbr_1x1_kxk_conv1'):
+            weight_rbr_1x1_kxk_conv1 = self.weight_rbr_1x1_kxk_conv1.squeeze()
+        else:
+            raise NotImplementedError
+        weight_rbr_1x1_kxk_conv2 = self.weight_rbr_1x1_kxk_conv2
+
+        if self.groups > 1:
+            g = self.groups
+            t, ig = weight_rbr_1x1_kxk_conv1.size()
+            o, tg, h, w = weight_rbr_1x1_kxk_conv2.size()
+            weight_rbr_1x1_kxk_conv1 = weight_rbr_1x1_kxk_conv1.view(g, int(t/g), ig)
+            weight_rbr_1x1_kxk_conv2 = weight_rbr_1x1_kxk_conv2.view(g, int(o/g), tg, h, w)
+            weight_rbr_1x1_kxk = torch.einsum('gti,gothw->goihw', weight_rbr_1x1_kxk_conv1, weight_rbr_1x1_kxk_conv2).view(o, ig, h, w)
+        else:
+            weight_rbr_1x1_kxk = torch.einsum('ti,othw->oihw', weight_rbr_1x1_kxk_conv1, weight_rbr_1x1_kxk_conv2)
+
+        weight_rbr_1x1_kxk = torch.einsum('oihw,o->oihw', weight_rbr_1x1_kxk, self.vector[3, :])
+
+        weight_rbr_gconv = self.dwsc2full(self.weight_rbr_gconv_dw, self.weight_rbr_gconv_pw, self.in_channels)
+        weight_rbr_gconv = torch.einsum('oihw,o->oihw', weight_rbr_gconv, self.vector[4, :])    
+
+        weight = weight_rbr_origin + weight_rbr_avg + weight_rbr_1x1_kxk + weight_rbr_pfir + weight_rbr_gconv
+
+        return weight
+
+    def dwsc2full(self, weight_dw, weight_pw, groups):
+        
+        t, ig, h, w = weight_dw.size()
+        o, _, _, _ = weight_pw.size()
+        tg = int(t/groups)
+        i = int(ig*groups)
+        weight_dw = weight_dw.view(groups, tg, ig, h, w)
+        weight_pw = weight_pw.squeeze().view(o, groups, tg)
+        
+        weight_dsc = torch.einsum('gtihw,ogt->ogihw', weight_dw, weight_pw)
+        return weight_dsc.view(o, i, h, w)
+
+    def forward(self, inputs):
+        weight = self.weight_gen()
+        out = F.conv2d(inputs, weight, bias=None, stride=self.stride, padding=self.padding, dilation=self.dilation, groups=self.groups)
+
+        return self.nonlinear(self.bn(out))
+
+class RepConv_OREPA(nn.Module):
+
+    def __init__(self, c1, c2, k=3, s=1, padding=1, dilation=1, groups=1, padding_mode='zeros', deploy=False, use_se=False, nonlinear=nn.SiLU()):
+        super(RepConv_OREPA, self).__init__()
+        self.deploy = deploy
+        self.groups = groups
+        self.in_channels = c1
+        self.out_channels = c2
+
+        self.padding = padding
+        self.dilation = dilation
+        self.groups = groups
+
+        assert k == 3
+        assert padding == 1
+
+        padding_11 = padding - k // 2
+
+        if nonlinear is None:
+            self.nonlinearity = nn.Identity()
+        else:
+            self.nonlinearity = nonlinear
+
+        if use_se:
+            self.se = SEBlock(self.out_channels, internal_neurons=self.out_channels // 16)
+        else:
+            self.se = nn.Identity()
+
+        if deploy:
+            self.rbr_reparam = nn.Conv2d(in_channels=self.in_channels, out_channels=self.out_channels, kernel_size=k, stride=s,
+                                      padding=padding, dilation=dilation, groups=groups, bias=True, padding_mode=padding_mode)
+
+        else:
+            self.rbr_identity = nn.BatchNorm2d(num_features=self.in_channels) if self.out_channels == self.in_channels and s == 1 else None
+            self.rbr_dense = OREPA_3x3_RepConv(in_channels=self.in_channels, out_channels=self.out_channels, kernel_size=k, stride=s, padding=padding, groups=groups, dilation=1)
+            self.rbr_1x1 = ConvBN(in_channels=self.in_channels, out_channels=self.out_channels, kernel_size=1, stride=s, padding=padding_11, groups=groups, dilation=1)
+            print('RepVGG Block, identity = ', self.rbr_identity)
+
+
+    def forward(self, inputs):
+        if hasattr(self, 'rbr_reparam'):
+            return self.nonlinearity(self.se(self.rbr_reparam(inputs)))
+
+        if self.rbr_identity is None:
+            id_out = 0
+        else:
+            id_out = self.rbr_identity(inputs)
+
+        out1 = self.rbr_dense(inputs)
+        out2 = self.rbr_1x1(inputs)
+        out3 = id_out
+        out = out1 + out2 + out3
+
+        return self.nonlinearity(self.se(out))
+
+
+    #   Optional. This improves the accuracy and facilitates quantization.
+    #   1.  Cancel the original weight decay on rbr_dense.conv.weight and rbr_1x1.conv.weight.
+    #   2.  Use like this.
+    #       loss = criterion(....)
+    #       for every RepVGGBlock blk:
+    #           loss += weight_decay_coefficient * 0.5 * blk.get_cust_L2()
+    #       optimizer.zero_grad()
+    #       loss.backward()
+
+    # Not used for OREPA
+    def get_custom_L2(self):
+        K3 = self.rbr_dense.weight_gen()
+        K1 = self.rbr_1x1.conv.weight
+        t3 = (self.rbr_dense.bn.weight / ((self.rbr_dense.bn.running_var + self.rbr_dense.bn.eps).sqrt())).reshape(-1, 1, 1, 1).detach()
+        t1 = (self.rbr_1x1.bn.weight / ((self.rbr_1x1.bn.running_var + self.rbr_1x1.bn.eps).sqrt())).reshape(-1, 1, 1, 1).detach()
+
+        l2_loss_circle = (K3 ** 2).sum() - (K3[:, :, 1:2, 1:2] ** 2).sum()      # The L2 loss of the "circle" of weights in 3x3 kernel. Use regular L2 on them.
+        eq_kernel = K3[:, :, 1:2, 1:2] * t3 + K1 * t1                           # The equivalent resultant central point of 3x3 kernel.
+        l2_loss_eq_kernel = (eq_kernel ** 2 / (t3 ** 2 + t1 ** 2)).sum()        # Normalize for an L2 coefficient comparable to regular L2.
+        return l2_loss_eq_kernel + l2_loss_circle
+
+    def get_equivalent_kernel_bias(self):
+        kernel3x3, bias3x3 = self._fuse_bn_tensor(self.rbr_dense)
+        kernel1x1, bias1x1 = self._fuse_bn_tensor(self.rbr_1x1)
+        kernelid, biasid = self._fuse_bn_tensor(self.rbr_identity)
+        return kernel3x3 + self._pad_1x1_to_3x3_tensor(kernel1x1) + kernelid, bias3x3 + bias1x1 + biasid
+
+    def _pad_1x1_to_3x3_tensor(self, kernel1x1):
+        if kernel1x1 is None:
+            return 0
+        else:
+            return torch.nn.functional.pad(kernel1x1, [1,1,1,1])
+
+    def _fuse_bn_tensor(self, branch):
+        if branch is None:
+            return 0, 0
+        if not isinstance(branch, nn.BatchNorm2d):
+            if isinstance(branch, OREPA_3x3_RepConv):
+                kernel = branch.weight_gen()
+            elif isinstance(branch, ConvBN):
+                kernel = branch.conv.weight
+            else:
+                raise NotImplementedError
+            running_mean = branch.bn.running_mean
+            running_var = branch.bn.running_var
+            gamma = branch.bn.weight
+            beta = branch.bn.bias
+            eps = branch.bn.eps
+        else:
+            if not hasattr(self, 'id_tensor'):
+                input_dim = self.in_channels // self.groups
+                kernel_value = np.zeros((self.in_channels, input_dim, 3, 3), dtype=np.float32)
+                for i in range(self.in_channels):
+                    kernel_value[i, i % input_dim, 1, 1] = 1
+                self.id_tensor = torch.from_numpy(kernel_value).to(branch.weight.device)
+            kernel = self.id_tensor
+            running_mean = branch.running_mean
+            running_var = branch.running_var
+            gamma = branch.weight
+            beta = branch.bias
+            eps = branch.eps
+        std = (running_var + eps).sqrt()
+        t = (gamma / std).reshape(-1, 1, 1, 1)
+        return kernel * t, beta - running_mean * gamma / std
+
+    def switch_to_deploy(self):
+        if hasattr(self, 'rbr_reparam'):
+            return
+        print(f"RepConv_OREPA.switch_to_deploy")
+        kernel, bias = self.get_equivalent_kernel_bias()
+        self.rbr_reparam = nn.Conv2d(in_channels=self.rbr_dense.in_channels, out_channels=self.rbr_dense.out_channels,
+                                     kernel_size=self.rbr_dense.kernel_size, stride=self.rbr_dense.stride,
+                                     padding=self.rbr_dense.padding, dilation=self.rbr_dense.dilation, groups=self.rbr_dense.groups, bias=True)
+        self.rbr_reparam.weight.data = kernel
+        self.rbr_reparam.bias.data = bias
+        for para in self.parameters():
+            para.detach_()
+        self.__delattr__('rbr_dense')
+        self.__delattr__('rbr_1x1')
+        if hasattr(self, 'rbr_identity'):
+            self.__delattr__('rbr_identity') 
+
+##### end of orepa #####
+
+
+##### swin transformer #####    
+    
+class WindowAttention(nn.Module):
+
+    def __init__(self, dim, window_size, num_heads, qkv_bias=True, qk_scale=None, attn_drop=0., proj_drop=0.):
+
+        super().__init__()
+        self.dim = dim
+        self.window_size = window_size  # Wh, Ww
+        self.num_heads = num_heads
+        head_dim = dim // num_heads
+        self.scale = qk_scale or head_dim ** -0.5
+
+        # define a parameter table of relative position bias
+        self.relative_position_bias_table = nn.Parameter(
+            torch.zeros((2 * window_size[0] - 1) * (2 * window_size[1] - 1), num_heads))  # 2*Wh-1 * 2*Ww-1, nH
+
+        # get pair-wise relative position index for each token inside the window
+        coords_h = torch.arange(self.window_size[0])
+        coords_w = torch.arange(self.window_size[1])
+        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
+        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
+        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
+        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
+        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
+        relative_coords[:, :, 1] += self.window_size[1] - 1
+        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
+        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
+        self.register_buffer("relative_position_index", relative_position_index)
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+
+        nn.init.normal_(self.relative_position_bias_table, std=.02)
+        self.softmax = nn.Softmax(dim=-1)
+
+    def forward(self, x, mask=None):
+
+        B_, N, C = x.shape
+        qkv = self.qkv(x).reshape(B_, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)
+
+        q = q * self.scale
+        attn = (q @ k.transpose(-2, -1))
+
+        relative_position_bias = self.relative_position_bias_table[self.relative_position_index.view(-1)].view(
+            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
+        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
+        attn = attn + relative_position_bias.unsqueeze(0)
+
+        if mask is not None:
+            nW = mask.shape[0]
+            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
+            attn = attn.view(-1, self.num_heads, N, N)
+            attn = self.softmax(attn)
+        else:
+            attn = self.softmax(attn)
+
+        attn = self.attn_drop(attn)
+
+        # print(attn.dtype, v.dtype)
+        try:
+            x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
+        except:
+            #print(attn.dtype, v.dtype)
+            x = (attn.half() @ v).transpose(1, 2).reshape(B_, N, C)
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+class Mlp(nn.Module):
+
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.SiLU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+def window_partition(x, window_size):
+
+    B, H, W, C = x.shape
+    assert H % window_size == 0, 'feature map h and w can not divide by window size'
+    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
+    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
+    return windows
+
+def window_reverse(windows, window_size, H, W):
+    
+    B = int(windows.shape[0] / (H * W / window_size / window_size))
+    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
+    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
+    return x
+
+
+class SwinTransformerLayer(nn.Module):
+
+    def __init__(self, dim, num_heads, window_size=8, shift_size=0,
+                 mlp_ratio=4., qkv_bias=True, qk_scale=None, drop=0., attn_drop=0., drop_path=0.,
+                 act_layer=nn.SiLU, norm_layer=nn.LayerNorm):
+        super().__init__()
+        self.dim = dim
+        self.num_heads = num_heads
+        self.window_size = window_size
+        self.shift_size = shift_size
+        self.mlp_ratio = mlp_ratio
+        # if min(self.input_resolution) <= self.window_size:
+        #     # if window size is larger than input resolution, we don't partition windows
+        #     self.shift_size = 0
+        #     self.window_size = min(self.input_resolution)
+        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
+
+        self.norm1 = norm_layer(dim)
+        self.attn = WindowAttention(
+            dim, window_size=(self.window_size, self.window_size), num_heads=num_heads,
+            qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
+
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+    def create_mask(self, H, W):
+        # calculate attention mask for SW-MSA
+        img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
+        h_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        w_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        cnt = 0
+        for h in h_slices:
+            for w in w_slices:
+                img_mask[:, h, w, :] = cnt
+                cnt += 1
+
+        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
+        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
+        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
+        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
+
+        return attn_mask
+
+    def forward(self, x):
+        # reshape x[b c h w] to x[b l c]
+        _, _, H_, W_ = x.shape
+
+        Padding = False
+        if min(H_, W_) < self.window_size or H_ % self.window_size!=0 or W_ % self.window_size!=0:
+            Padding = True
+            # print(f'img_size {min(H_, W_)} is less than (or not divided by) window_size {self.window_size}, Padding.')
+            pad_r = (self.window_size - W_ % self.window_size) % self.window_size
+            pad_b = (self.window_size - H_ % self.window_size) % self.window_size
+            x = F.pad(x, (0, pad_r, 0, pad_b))
+
+        # print('2', x.shape)
+        B, C, H, W = x.shape
+        L = H * W
+        x = x.permute(0, 2, 3, 1).contiguous().view(B, L, C)  # b, L, c
+
+        # create mask from init to forward
+        if self.shift_size > 0:
+            attn_mask = self.create_mask(H, W).to(x.device)
+        else:
+            attn_mask = None
+
+        shortcut = x
+        x = self.norm1(x)
+        x = x.view(B, H, W, C)
+
+        # cyclic shift
+        if self.shift_size > 0:
+            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
+        else:
+            shifted_x = x
+
+        # partition windows
+        x_windows = window_partition(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
+        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C
+
+        # W-MSA/SW-MSA
+        attn_windows = self.attn(x_windows, mask=attn_mask)  # nW*B, window_size*window_size, C
+
+        # merge windows
+        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
+        shifted_x = window_reverse(attn_windows, self.window_size, H, W)  # B H' W' C
+
+        # reverse cyclic shift
+        if self.shift_size > 0:
+            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
+        else:
+            x = shifted_x
+        x = x.view(B, H * W, C)
+
+        # FFN
+        x = shortcut + self.drop_path(x)
+        x = x + self.drop_path(self.mlp(self.norm2(x)))
+
+        x = x.permute(0, 2, 1).contiguous().view(-1, C, H, W)  # b c h w
+
+        if Padding:
+            x = x[:, :, :H_, :W_]  # reverse padding
+
+        return x
+
+
+class SwinTransformerBlock(nn.Module):
+    def __init__(self, c1, c2, num_heads, num_layers, window_size=8):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+
+        # remove input_resolution
+        self.blocks = nn.Sequential(*[SwinTransformerLayer(dim=c2, num_heads=num_heads, window_size=window_size,
+                                 shift_size=0 if (i % 2 == 0) else window_size // 2) for i in range(num_layers)])
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        x = self.blocks(x)
+        return x
+
+
+class STCSPA(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(STCSPA, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1, 1)
+        num_heads = c_ // 32
+        self.m = SwinTransformerBlock(c_, c_, num_heads, n)
+        #self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.m(self.cv1(x))
+        y2 = self.cv2(x)
+        return self.cv3(torch.cat((y1, y2), dim=1))
+
+
+class STCSPB(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(STCSPB, self).__init__()
+        c_ = int(c2)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1, 1)
+        num_heads = c_ // 32
+        self.m = SwinTransformerBlock(c_, c_, num_heads, n)
+        #self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        x1 = self.cv1(x)
+        y1 = self.m(x1)
+        y2 = self.cv2(x1)
+        return self.cv3(torch.cat((y1, y2), dim=1))
+
+
+class STCSPC(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(STCSPC, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(c_, c_, 1, 1)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        num_heads = c_ // 32
+        self.m = SwinTransformerBlock(c_, c_, num_heads, n)
+        #self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(torch.cat((y1, y2), dim=1))
+
+##### end of swin transformer #####   
+
+
+##### swin transformer v2 ##### 
+  
+class WindowAttention_v2(nn.Module):
+
+    def __init__(self, dim, window_size, num_heads, qkv_bias=True, attn_drop=0., proj_drop=0.,
+                 pretrained_window_size=[0, 0]):
+
+        super().__init__()
+        self.dim = dim
+        self.window_size = window_size  # Wh, Ww
+        self.pretrained_window_size = pretrained_window_size
+        self.num_heads = num_heads
+
+        self.logit_scale = nn.Parameter(torch.log(10 * torch.ones((num_heads, 1, 1))), requires_grad=True)
+
+        # mlp to generate continuous relative position bias
+        self.cpb_mlp = nn.Sequential(nn.Linear(2, 512, bias=True),
+                                     nn.ReLU(inplace=True),
+                                     nn.Linear(512, num_heads, bias=False))
+
+        # get relative_coords_table
+        relative_coords_h = torch.arange(-(self.window_size[0] - 1), self.window_size[0], dtype=torch.float32)
+        relative_coords_w = torch.arange(-(self.window_size[1] - 1), self.window_size[1], dtype=torch.float32)
+        relative_coords_table = torch.stack(
+            torch.meshgrid([relative_coords_h,
+                            relative_coords_w])).permute(1, 2, 0).contiguous().unsqueeze(0)  # 1, 2*Wh-1, 2*Ww-1, 2
+        if pretrained_window_size[0] > 0:
+            relative_coords_table[:, :, :, 0] /= (pretrained_window_size[0] - 1)
+            relative_coords_table[:, :, :, 1] /= (pretrained_window_size[1] - 1)
+        else:
+            relative_coords_table[:, :, :, 0] /= (self.window_size[0] - 1)
+            relative_coords_table[:, :, :, 1] /= (self.window_size[1] - 1)
+        relative_coords_table *= 8  # normalize to -8, 8
+        relative_coords_table = torch.sign(relative_coords_table) * torch.log2(
+            torch.abs(relative_coords_table) + 1.0) / np.log2(8)
+
+        self.register_buffer("relative_coords_table", relative_coords_table)
+
+        # get pair-wise relative position index for each token inside the window
+        coords_h = torch.arange(self.window_size[0])
+        coords_w = torch.arange(self.window_size[1])
+        coords = torch.stack(torch.meshgrid([coords_h, coords_w]))  # 2, Wh, Ww
+        coords_flatten = torch.flatten(coords, 1)  # 2, Wh*Ww
+        relative_coords = coords_flatten[:, :, None] - coords_flatten[:, None, :]  # 2, Wh*Ww, Wh*Ww
+        relative_coords = relative_coords.permute(1, 2, 0).contiguous()  # Wh*Ww, Wh*Ww, 2
+        relative_coords[:, :, 0] += self.window_size[0] - 1  # shift to start from 0
+        relative_coords[:, :, 1] += self.window_size[1] - 1
+        relative_coords[:, :, 0] *= 2 * self.window_size[1] - 1
+        relative_position_index = relative_coords.sum(-1)  # Wh*Ww, Wh*Ww
+        self.register_buffer("relative_position_index", relative_position_index)
+
+        self.qkv = nn.Linear(dim, dim * 3, bias=False)
+        if qkv_bias:
+            self.q_bias = nn.Parameter(torch.zeros(dim))
+            self.v_bias = nn.Parameter(torch.zeros(dim))
+        else:
+            self.q_bias = None
+            self.v_bias = None
+        self.attn_drop = nn.Dropout(attn_drop)
+        self.proj = nn.Linear(dim, dim)
+        self.proj_drop = nn.Dropout(proj_drop)
+        self.softmax = nn.Softmax(dim=-1)
+
+    def forward(self, x, mask=None):
+        
+        B_, N, C = x.shape
+        qkv_bias = None
+        if self.q_bias is not None:
+            qkv_bias = torch.cat((self.q_bias, torch.zeros_like(self.v_bias, requires_grad=False), self.v_bias))
+        qkv = F.linear(input=x, weight=self.qkv.weight, bias=qkv_bias)
+        qkv = qkv.reshape(B_, N, 3, self.num_heads, -1).permute(2, 0, 3, 1, 4)
+        q, k, v = qkv[0], qkv[1], qkv[2]  # make torchscript happy (cannot use tensor as tuple)
+
+        # cosine attention
+        attn = (F.normalize(q, dim=-1) @ F.normalize(k, dim=-1).transpose(-2, -1))
+        logit_scale = torch.clamp(self.logit_scale, max=torch.log(torch.tensor(1. / 0.01))).exp()
+        attn = attn * logit_scale
+
+        relative_position_bias_table = self.cpb_mlp(self.relative_coords_table).view(-1, self.num_heads)
+        relative_position_bias = relative_position_bias_table[self.relative_position_index.view(-1)].view(
+            self.window_size[0] * self.window_size[1], self.window_size[0] * self.window_size[1], -1)  # Wh*Ww,Wh*Ww,nH
+        relative_position_bias = relative_position_bias.permute(2, 0, 1).contiguous()  # nH, Wh*Ww, Wh*Ww
+        relative_position_bias = 16 * torch.sigmoid(relative_position_bias)
+        attn = attn + relative_position_bias.unsqueeze(0)
+
+        if mask is not None:
+            nW = mask.shape[0]
+            attn = attn.view(B_ // nW, nW, self.num_heads, N, N) + mask.unsqueeze(1).unsqueeze(0)
+            attn = attn.view(-1, self.num_heads, N, N)
+            attn = self.softmax(attn)
+        else:
+            attn = self.softmax(attn)
+
+        attn = self.attn_drop(attn)
+
+        try:
+            x = (attn @ v).transpose(1, 2).reshape(B_, N, C)
+        except:
+            x = (attn.half() @ v).transpose(1, 2).reshape(B_, N, C)
+            
+        x = self.proj(x)
+        x = self.proj_drop(x)
+        return x
+
+    def extra_repr(self) -> str:
+        return f'dim={self.dim}, window_size={self.window_size}, ' \
+               f'pretrained_window_size={self.pretrained_window_size}, num_heads={self.num_heads}'
+
+    def flops(self, N):
+        # calculate flops for 1 window with token length of N
+        flops = 0
+        # qkv = self.qkv(x)
+        flops += N * self.dim * 3 * self.dim
+        # attn = (q @ k.transpose(-2, -1))
+        flops += self.num_heads * N * (self.dim // self.num_heads) * N
+        #  x = (attn @ v)
+        flops += self.num_heads * N * N * (self.dim // self.num_heads)
+        # x = self.proj(x)
+        flops += N * self.dim * self.dim
+        return flops
+    
+class Mlp_v2(nn.Module):
+    def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.SiLU, drop=0.):
+        super().__init__()
+        out_features = out_features or in_features
+        hidden_features = hidden_features or in_features
+        self.fc1 = nn.Linear(in_features, hidden_features)
+        self.act = act_layer()
+        self.fc2 = nn.Linear(hidden_features, out_features)
+        self.drop = nn.Dropout(drop)
+
+    def forward(self, x):
+        x = self.fc1(x)
+        x = self.act(x)
+        x = self.drop(x)
+        x = self.fc2(x)
+        x = self.drop(x)
+        return x
+
+
+def window_partition_v2(x, window_size):
+    
+    B, H, W, C = x.shape
+    x = x.view(B, H // window_size, window_size, W // window_size, window_size, C)
+    windows = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(-1, window_size, window_size, C)
+    return windows
+
+
+def window_reverse_v2(windows, window_size, H, W):
+    
+    B = int(windows.shape[0] / (H * W / window_size / window_size))
+    x = windows.view(B, H // window_size, W // window_size, window_size, window_size, -1)
+    x = x.permute(0, 1, 3, 2, 4, 5).contiguous().view(B, H, W, -1)
+    return x
+
+
+class SwinTransformerLayer_v2(nn.Module):
+
+    def __init__(self, dim, num_heads, window_size=7, shift_size=0,
+                 mlp_ratio=4., qkv_bias=True, drop=0., attn_drop=0., drop_path=0.,
+                 act_layer=nn.SiLU, norm_layer=nn.LayerNorm, pretrained_window_size=0):
+        super().__init__()
+        self.dim = dim
+        #self.input_resolution = input_resolution
+        self.num_heads = num_heads
+        self.window_size = window_size
+        self.shift_size = shift_size
+        self.mlp_ratio = mlp_ratio
+        #if min(self.input_resolution) <= self.window_size:
+        #    # if window size is larger than input resolution, we don't partition windows
+        #    self.shift_size = 0
+        #    self.window_size = min(self.input_resolution)
+        assert 0 <= self.shift_size < self.window_size, "shift_size must in 0-window_size"
+
+        self.norm1 = norm_layer(dim)
+        self.attn = WindowAttention_v2(
+            dim, window_size=(self.window_size, self.window_size), num_heads=num_heads,
+            qkv_bias=qkv_bias, attn_drop=attn_drop, proj_drop=drop,
+            pretrained_window_size=(pretrained_window_size, pretrained_window_size))
+
+        self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
+        self.norm2 = norm_layer(dim)
+        mlp_hidden_dim = int(dim * mlp_ratio)
+        self.mlp = Mlp_v2(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
+
+    def create_mask(self, H, W):
+        # calculate attention mask for SW-MSA
+        img_mask = torch.zeros((1, H, W, 1))  # 1 H W 1
+        h_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        w_slices = (slice(0, -self.window_size),
+                    slice(-self.window_size, -self.shift_size),
+                    slice(-self.shift_size, None))
+        cnt = 0
+        for h in h_slices:
+            for w in w_slices:
+                img_mask[:, h, w, :] = cnt
+                cnt += 1
+
+        mask_windows = window_partition(img_mask, self.window_size)  # nW, window_size, window_size, 1
+        mask_windows = mask_windows.view(-1, self.window_size * self.window_size)
+        attn_mask = mask_windows.unsqueeze(1) - mask_windows.unsqueeze(2)
+        attn_mask = attn_mask.masked_fill(attn_mask != 0, float(-100.0)).masked_fill(attn_mask == 0, float(0.0))
+
+        return attn_mask
+
+    def forward(self, x):
+        # reshape x[b c h w] to x[b l c]
+        _, _, H_, W_ = x.shape
+
+        Padding = False
+        if min(H_, W_) < self.window_size or H_ % self.window_size!=0 or W_ % self.window_size!=0:
+            Padding = True
+            # print(f'img_size {min(H_, W_)} is less than (or not divided by) window_size {self.window_size}, Padding.')
+            pad_r = (self.window_size - W_ % self.window_size) % self.window_size
+            pad_b = (self.window_size - H_ % self.window_size) % self.window_size
+            x = F.pad(x, (0, pad_r, 0, pad_b))
+
+        # print('2', x.shape)
+        B, C, H, W = x.shape
+        L = H * W
+        x = x.permute(0, 2, 3, 1).contiguous().view(B, L, C)  # b, L, c
+
+        # create mask from init to forward
+        if self.shift_size > 0:
+            attn_mask = self.create_mask(H, W).to(x.device)
+        else:
+            attn_mask = None
+
+        shortcut = x
+        x = x.view(B, H, W, C)
+
+        # cyclic shift
+        if self.shift_size > 0:
+            shifted_x = torch.roll(x, shifts=(-self.shift_size, -self.shift_size), dims=(1, 2))
+        else:
+            shifted_x = x
+
+        # partition windows
+        x_windows = window_partition_v2(shifted_x, self.window_size)  # nW*B, window_size, window_size, C
+        x_windows = x_windows.view(-1, self.window_size * self.window_size, C)  # nW*B, window_size*window_size, C
+
+        # W-MSA/SW-MSA
+        attn_windows = self.attn(x_windows, mask=attn_mask)  # nW*B, window_size*window_size, C
+
+        # merge windows
+        attn_windows = attn_windows.view(-1, self.window_size, self.window_size, C)
+        shifted_x = window_reverse_v2(attn_windows, self.window_size, H, W)  # B H' W' C
+
+        # reverse cyclic shift
+        if self.shift_size > 0:
+            x = torch.roll(shifted_x, shifts=(self.shift_size, self.shift_size), dims=(1, 2))
+        else:
+            x = shifted_x
+        x = x.view(B, H * W, C)
+        x = shortcut + self.drop_path(self.norm1(x))
+
+        # FFN
+        x = x + self.drop_path(self.norm2(self.mlp(x)))
+        x = x.permute(0, 2, 1).contiguous().view(-1, C, H, W)  # b c h w
+        
+        if Padding:
+            x = x[:, :, :H_, :W_]  # reverse padding
+
+        return x
+
+    def extra_repr(self) -> str:
+        return f"dim={self.dim}, input_resolution={self.input_resolution}, num_heads={self.num_heads}, " \
+               f"window_size={self.window_size}, shift_size={self.shift_size}, mlp_ratio={self.mlp_ratio}"
+
+    def flops(self):
+        flops = 0
+        H, W = self.input_resolution
+        # norm1
+        flops += self.dim * H * W
+        # W-MSA/SW-MSA
+        nW = H * W / self.window_size / self.window_size
+        flops += nW * self.attn.flops(self.window_size * self.window_size)
+        # mlp
+        flops += 2 * H * W * self.dim * self.dim * self.mlp_ratio
+        # norm2
+        flops += self.dim * H * W
+        return flops
+
+
+class SwinTransformer2Block(nn.Module):
+    def __init__(self, c1, c2, num_heads, num_layers, window_size=7):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+
+        # remove input_resolution
+        self.blocks = nn.Sequential(*[SwinTransformerLayer_v2(dim=c2, num_heads=num_heads, window_size=window_size,
+                                 shift_size=0 if (i % 2 == 0) else window_size // 2) for i in range(num_layers)])
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        x = self.blocks(x)
+        return x
+
+
+class ST2CSPA(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(ST2CSPA, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1, 1)
+        num_heads = c_ // 32
+        self.m = SwinTransformer2Block(c_, c_, num_heads, n)
+        #self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.m(self.cv1(x))
+        y2 = self.cv2(x)
+        return self.cv3(torch.cat((y1, y2), dim=1))
+
+
+class ST2CSPB(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=False, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(ST2CSPB, self).__init__()
+        c_ = int(c2)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1, 1)
+        num_heads = c_ // 32
+        self.m = SwinTransformer2Block(c_, c_, num_heads, n)
+        #self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        x1 = self.cv1(x)
+        y1 = self.m(x1)
+        y2 = self.cv2(x1)
+        return self.cv3(torch.cat((y1, y2), dim=1))
+
+
+class ST2CSPC(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(ST2CSPC, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(c_, c_, 1, 1)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        num_heads = c_ // 32
+        self.m = SwinTransformer2Block(c_, c_, num_heads, n)
+        #self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(torch.cat((y1, y2), dim=1))
+
+##### end of swin transformer v2 #####   

infer/yolov7/models/experimental.py

@@ -0,0 +1,277 @@
+# -*- coding: UTF-8 -*-
+
+import numpy as np
+import random
+import torch
+import torch.nn as nn
+
+from infer.yolov7.models.common import Conv, DWConv
+from infer.yolov7.utils.google_utils import attempt_download
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super(CrossConv, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Sum(nn.Module):
+    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+    def __init__(self, n, weight=False):  # n: number of inputs
+        super(Sum, self).__init__()
+        self.weight = weight  # apply weights boolean
+        self.iter = range(n - 1)  # iter object
+        if weight:
+            self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True)  # layer weights
+
+    def forward(self, x):
+        y = x[0]  # no weight
+        if self.weight:
+            w = torch.sigmoid(self.w) * 2
+            for i in self.iter:
+                y = y + x[i + 1] * w[i]
+        else:
+            for i in self.iter:
+                y = y + x[i + 1]
+        return y
+
+
+class MixConv2d(nn.Module):
+    # Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
+    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
+        super(MixConv2d, self).__init__()
+        groups = len(k)
+        if equal_ch:  # equal c_ per group
+            i = torch.linspace(0, groups - 1E-6, c2).floor()  # c2 indices
+            c_ = [(i == g).sum() for g in range(groups)]  # intermediate channels
+        else:  # equal weight.numel() per group
+            b = [c2] + [0] * groups
+            a = np.eye(groups + 1, groups, k=-1)
+            a -= np.roll(a, 1, axis=1)
+            a *= np.array(k) ** 2
+            a[0] = 1
+            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
+
+        self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+
+    def forward(self, x):
+        return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super(Ensemble, self).__init__()
+
+    def forward(self, x, augment=False):
+        y = []
+        for module in self:
+            y.append(module(x, augment)[0])
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.stack(y).mean(0)  # mean ensemble
+        y = torch.cat(y, 1)  # nms ensemble
+        return y, None  # inference, train output
+
+
+
+
+
+class ORT_NMS(torch.autograd.Function):
+    '''ONNX-Runtime NMS operation'''
+    @staticmethod
+    def forward(ctx,
+                boxes,
+                scores,
+                max_output_boxes_per_class=torch.tensor([100]),
+                iou_threshold=torch.tensor([0.45]),
+                score_threshold=torch.tensor([0.25])):
+        device = boxes.device
+        batch = scores.shape[0]
+        num_det = random.randint(0, 100)
+        batches = torch.randint(0, batch, (num_det,)).sort()[0].to(device)
+        idxs = torch.arange(100, 100 + num_det).to(device)
+        zeros = torch.zeros((num_det,), dtype=torch.int64).to(device)
+        selected_indices = torch.cat([batches[None], zeros[None], idxs[None]], 0).T.contiguous()
+        selected_indices = selected_indices.to(torch.int64)
+        return selected_indices
+
+    @staticmethod
+    def symbolic(g, boxes, scores, max_output_boxes_per_class, iou_threshold, score_threshold):
+        return g.op("NonMaxSuppression", boxes, scores, max_output_boxes_per_class, iou_threshold, score_threshold)
+
+
+class TRT_NMS(torch.autograd.Function):
+    '''TensorRT NMS operation'''
+    @staticmethod
+    def forward(
+        ctx,
+        boxes,
+        scores,
+        background_class=-1,
+        box_coding=1,
+        iou_threshold=0.45,
+        max_output_boxes=100,
+        plugin_version="1",
+        score_activation=0,
+        score_threshold=0.25,
+    ):
+        batch_size, num_boxes, num_classes = scores.shape
+        num_det = torch.randint(0, max_output_boxes, (batch_size, 1), dtype=torch.int32)
+        det_boxes = torch.randn(batch_size, max_output_boxes, 4)
+        det_scores = torch.randn(batch_size, max_output_boxes)
+        det_classes = torch.randint(0, num_classes, (batch_size, max_output_boxes), dtype=torch.int32)
+        return num_det, det_boxes, det_scores, det_classes
+
+    @staticmethod
+    def symbolic(g,
+                 boxes,
+                 scores,
+                 background_class=-1,
+                 box_coding=1,
+                 iou_threshold=0.45,
+                 max_output_boxes=100,
+                 plugin_version="1",
+                 score_activation=0,
+                 score_threshold=0.25):
+        out = g.op("TRT::EfficientNMS_TRT",
+                   boxes,
+                   scores,
+                   background_class_i=background_class,
+                   box_coding_i=box_coding,
+                   iou_threshold_f=iou_threshold,
+                   max_output_boxes_i=max_output_boxes,
+                   plugin_version_s=plugin_version,
+                   score_activation_i=score_activation,
+                   score_threshold_f=score_threshold,
+                   outputs=4)
+        nums, boxes, scores, classes = out
+        return nums, boxes, scores, classes
+
+
+class ONNX_ORT(nn.Module):
+    '''onnx module with ONNX-Runtime NMS operation.'''
+    def __init__(self, max_obj=100, iou_thres=0.45, score_thres=0.25, max_wh=640, device=None, n_classes=80):
+        super().__init__()
+        self.device = device if device else torch.device("cpu")
+        self.max_obj = torch.tensor([max_obj]).to(device)
+        self.iou_threshold = torch.tensor([iou_thres]).to(device)
+        self.score_threshold = torch.tensor([score_thres]).to(device)
+        self.max_wh = max_wh # if max_wh != 0 : non-agnostic else : agnostic
+        self.convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
+                                           dtype=torch.float32,
+                                           device=self.device)
+        self.n_classes=n_classes
+
+    def forward(self, x):
+        boxes = x[:, :, :4]
+        conf = x[:, :, 4:5]
+        scores = x[:, :, 5:]
+        if self.n_classes == 1:
+            scores = conf # for models with one class, cls_loss is 0 and cls_conf is always 0.5,
+                                 # so there is no need to multiplicate.
+        else:
+            scores *= conf  # conf = obj_conf * cls_conf
+        boxes @= self.convert_matrix
+        max_score, category_id = scores.max(2, keepdim=True)
+        dis = category_id.float() * self.max_wh
+        nmsbox = boxes + dis
+        max_score_tp = max_score.transpose(1, 2).contiguous()
+        selected_indices = ORT_NMS.apply(nmsbox, max_score_tp, self.max_obj, self.iou_threshold, self.score_threshold)
+        X, Y = selected_indices[:, 0], selected_indices[:, 2]
+        selected_boxes = boxes[X, Y, :]
+        selected_categories = category_id[X, Y, :].float()
+        selected_scores = max_score[X, Y, :]
+        X = X.unsqueeze(1).float()
+        return torch.cat([X, selected_boxes, selected_categories, selected_scores], 1)
+
+class ONNX_TRT(nn.Module):
+    '''onnx module with TensorRT NMS operation.'''
+    def __init__(self, max_obj=100, iou_thres=0.45, score_thres=0.25, max_wh=None ,device=None, n_classes=80):
+        super().__init__()
+        assert max_wh is None
+        self.device = device if device else torch.device('cpu')
+        self.background_class = -1,
+        self.box_coding = 1,
+        self.iou_threshold = iou_thres
+        self.max_obj = max_obj
+        self.plugin_version = '1'
+        self.score_activation = 0
+        self.score_threshold = score_thres
+        self.n_classes=n_classes
+
+    def forward(self, x):
+        boxes = x[:, :, :4]
+        conf = x[:, :, 4:5]
+        scores = x[:, :, 5:]
+        if self.n_classes == 1:
+            scores = conf # for models with one class, cls_loss is 0 and cls_conf is always 0.5,
+                                 # so there is no need to multiplicate.
+        else:
+            scores *= conf  # conf = obj_conf * cls_conf
+        num_det, det_boxes, det_scores, det_classes = TRT_NMS.apply(boxes, scores, self.background_class, self.box_coding,
+                                                                    self.iou_threshold, self.max_obj,
+                                                                    self.plugin_version, self.score_activation,
+                                                                    self.score_threshold)
+        return num_det, det_boxes, det_scores, det_classes
+
+
+class End2End(nn.Module):
+    '''export onnx or tensorrt model with NMS operation.'''
+    def __init__(self, model, max_obj=100, iou_thres=0.45, score_thres=0.25, max_wh=None, device=None, n_classes=80):
+        super().__init__()
+        device = device if device else torch.device('cpu')
+        assert isinstance(max_wh,(int)) or max_wh is None
+        self.model = model.to(device)
+        self.model.model[-1].end2end = True
+        self.patch_model = ONNX_TRT if max_wh is None else ONNX_ORT
+        self.end2end = self.patch_model(max_obj, iou_thres, score_thres, max_wh, device, n_classes)
+        self.end2end.eval()
+
+    def forward(self, x):
+        x = self.model(x)
+        x = self.end2end(x)
+        return x
+
+
+
+
+
+def attempt_load(weights, map_location=None):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    import sys
+    sys.path.insert(0, "infer\yolov7")
+
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        #attempt_download(w)
+        ckpt = torch.load(w, map_location=map_location)  # load
+        model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval())  # FP32 model
+    
+    # Compatibility updates
+    for m in model.modules():
+        if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
+            m.inplace = True  # pytorch 1.7.0 compatibility
+        elif type(m) is nn.Upsample:
+            m.recompute_scale_factor = None  # torch 1.11.0 compatibility
+        elif type(m) is Conv:
+            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+    
+    if len(model) == 1:
+        return model[-1]  # return model
+    else:
+        print('Ensemble created with %s\n' % weights)
+        for k in ['names', 'stride']:
+            setattr(model, k, getattr(model[-1], k))
+        return model  # return ensemble
+
+

infer/yolov7/models/yolo.py

@@ -0,0 +1,843 @@
+import argparse
+import logging
+import sys
+from copy import deepcopy
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+logger = logging.getLogger(__name__)
+import torch
+from infer.yolov7.models.common import *
+from infer.yolov7.models.experimental import *
+from infer.yolov7.utils.autoanchor import check_anchor_order
+from infer.yolov7.utils.general import make_divisible, check_file, set_logging
+from infer.yolov7.utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
+    select_device, copy_attr
+from infer.yolov7.utils.loss import SigmoidBin
+
+try:
+    import thop  # for FLOPS computation
+except ImportError:
+    thop = None
+
+
+class Detect(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+    end2end = False
+    include_nms = False
+    concat = False
+
+    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
+        super(Detect, self).__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+
+    def forward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+                y = x[i].sigmoid()
+                if not torch.onnx.is_in_onnx_export():
+                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                else:
+                    xy, wh, conf = y.split((2, 2, self.nc + 1), 4)  # y.tensor_split((2, 4, 5), 4)  # torch 1.8.0
+                    xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5))  # new xy
+                    wh = wh ** 2 * (4 * self.anchor_grid[i].data)  # new wh
+                    y = torch.cat((xy, wh, conf), 4)
+                z.append(y.view(bs, -1, self.no))
+
+        if self.training:
+            out = x
+        elif self.end2end:
+            out = torch.cat(z, 1)
+        elif self.include_nms:
+            z = self.convert(z)
+            out = (z, )
+        elif self.concat:
+            out = torch.cat(z, 1)
+        else:
+            out = (torch.cat(z, 1), x)
+
+        return out
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+    def convert(self, z):
+        z = torch.cat(z, 1)
+        box = z[:, :, :4]
+        conf = z[:, :, 4:5]
+        score = z[:, :, 5:]
+        score *= conf
+        convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
+                                           dtype=torch.float32,
+                                           device=z.device)
+        box @= convert_matrix                          
+        return (box, score)
+
+
+class IDetect(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+    end2end = False
+    include_nms = False
+    concat = False
+
+    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
+        super(IDetect, self).__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        
+        self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
+        self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)
+
+    def forward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](self.ia[i](x[i]))  # conv
+            x[i] = self.im[i](x[i])
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x)
+    
+    def fuseforward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                if not torch.onnx.is_in_onnx_export():
+                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                else:
+                    xy, wh, conf = y.split((2, 2, self.nc + 1), 4)  # y.tensor_split((2, 4, 5), 4)  # torch 1.8.0
+                    xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5))  # new xy
+                    wh = wh ** 2 * (4 * self.anchor_grid[i].data)  # new wh
+                    y = torch.cat((xy, wh, conf), 4)
+                z.append(y.view(bs, -1, self.no))
+
+        if self.training:
+            out = x
+        elif self.end2end:
+            out = torch.cat(z, 1)
+        elif self.include_nms:
+            z = self.convert(z)
+            out = (z, )
+        elif self.concat:
+            out = torch.cat(z, 1)            
+        else:
+            out = (torch.cat(z, 1), x)
+
+        return out
+    
+    def fuse(self):
+        print("IDetect.fuse")
+        # fuse ImplicitA and Convolution
+        for i in range(len(self.m)):
+            c1,c2,_,_ = self.m[i].weight.shape
+            c1_,c2_, _,_ = self.ia[i].implicit.shape
+            self.m[i].bias += torch.matmul(self.m[i].weight.reshape(c1,c2),self.ia[i].implicit.reshape(c2_,c1_)).squeeze(1)
+
+        # fuse ImplicitM and Convolution
+        for i in range(len(self.m)):
+            c1,c2, _,_ = self.im[i].implicit.shape
+            self.m[i].bias *= self.im[i].implicit.reshape(c2)
+            self.m[i].weight *= self.im[i].implicit.transpose(0,1)
+            
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+    def convert(self, z):
+        z = torch.cat(z, 1)
+        box = z[:, :, :4]
+        conf = z[:, :, 4:5]
+        score = z[:, :, 5:]
+        score *= conf
+        convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
+                                           dtype=torch.float32,
+                                           device=z.device)
+        box @= convert_matrix                          
+        return (box, score)
+
+
+class IKeypoint(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+
+    def __init__(self, nc=80, anchors=(), nkpt=17, ch=(), inplace=True, dw_conv_kpt=False):  # detection layer
+        super(IKeypoint, self).__init__()
+        self.nc = nc  # number of classes
+        self.nkpt = nkpt
+        self.dw_conv_kpt = dw_conv_kpt
+        self.no_det=(nc + 5)  # number of outputs per anchor for box and class
+        self.no_kpt = 3*self.nkpt ## number of outputs per anchor for keypoints
+        self.no = self.no_det+self.no_kpt
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        self.flip_test = False
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no_det * self.na, 1) for x in ch)  # output conv
+        
+        self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
+        self.im = nn.ModuleList(ImplicitM(self.no_det * self.na) for _ in ch)
+        
+        if self.nkpt is not None:
+            if self.dw_conv_kpt: #keypoint head is slightly more complex
+                self.m_kpt = nn.ModuleList(
+                            nn.Sequential(DWConv(x, x, k=3), Conv(x,x),
+                                          DWConv(x, x, k=3), Conv(x, x),
+                                          DWConv(x, x, k=3), Conv(x,x),
+                                          DWConv(x, x, k=3), Conv(x, x),
+                                          DWConv(x, x, k=3), Conv(x, x),
+                                          DWConv(x, x, k=3), nn.Conv2d(x, self.no_kpt * self.na, 1)) for x in ch)
+            else: #keypoint head is a single convolution
+                self.m_kpt = nn.ModuleList(nn.Conv2d(x, self.no_kpt * self.na, 1) for x in ch)
+
+        self.inplace = inplace  # use in-place ops (e.g. slice assignment)
+
+    def forward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            if self.nkpt is None or self.nkpt==0:
+                x[i] = self.im[i](self.m[i](self.ia[i](x[i])))  # conv
+            else :
+                x[i] = torch.cat((self.im[i](self.m[i](self.ia[i](x[i]))), self.m_kpt[i](x[i])), axis=1)
+
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+            x_det = x[i][..., :6]
+            x_kpt = x[i][..., 6:]
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+                kpt_grid_x = self.grid[i][..., 0:1]
+                kpt_grid_y = self.grid[i][..., 1:2]
+
+                if self.nkpt == 0:
+                    y = x[i].sigmoid()
+                else:
+                    y = x_det.sigmoid()
+
+                if self.inplace:
+                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].view(1, self.na, 1, 1, 2) # wh
+                    if self.nkpt != 0:
+                        x_kpt[..., 0::3] = (x_kpt[..., ::3] * 2. - 0.5 + kpt_grid_x.repeat(1,1,1,1,17)) * self.stride[i]  # xy
+                        x_kpt[..., 1::3] = (x_kpt[..., 1::3] * 2. - 0.5 + kpt_grid_y.repeat(1,1,1,1,17)) * self.stride[i]  # xy
+                        #x_kpt[..., 0::3] = (x_kpt[..., ::3] + kpt_grid_x.repeat(1,1,1,1,17)) * self.stride[i]  # xy
+                        #x_kpt[..., 1::3] = (x_kpt[..., 1::3] + kpt_grid_y.repeat(1,1,1,1,17)) * self.stride[i]  # xy
+                        #print('=============')
+                        #print(self.anchor_grid[i].shape)
+                        #print(self.anchor_grid[i][...,0].unsqueeze(4).shape)
+                        #print(x_kpt[..., 0::3].shape)
+                        #x_kpt[..., 0::3] = ((x_kpt[..., 0::3].tanh() * 2.) ** 3 * self.anchor_grid[i][...,0].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_x.repeat(1,1,1,1,17) * self.stride[i]  # xy
+                        #x_kpt[..., 1::3] = ((x_kpt[..., 1::3].tanh() * 2.) ** 3 * self.anchor_grid[i][...,1].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_y.repeat(1,1,1,1,17) * self.stride[i]  # xy
+                        #x_kpt[..., 0::3] = (((x_kpt[..., 0::3].sigmoid() * 4.) ** 2 - 8.) * self.anchor_grid[i][...,0].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_x.repeat(1,1,1,1,17) * self.stride[i]  # xy
+                        #x_kpt[..., 1::3] = (((x_kpt[..., 1::3].sigmoid() * 4.) ** 2 - 8.) * self.anchor_grid[i][...,1].unsqueeze(4).repeat(1,1,1,1,self.nkpt)) + kpt_grid_y.repeat(1,1,1,1,17) * self.stride[i]  # xy
+                        x_kpt[..., 2::3] = x_kpt[..., 2::3].sigmoid()
+
+                    y = torch.cat((xy, wh, y[..., 4:], x_kpt), dim = -1)
+
+                else:  # for YOLOv5 on AWS Inferentia https://github.com/ultralytics/yolov5/pull/2953
+                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                    if self.nkpt != 0:
+                        y[..., 6:] = (y[..., 6:] * 2. - 0.5 + self.grid[i].repeat((1,1,1,1,self.nkpt))) * self.stride[i]  # xy
+                    y = torch.cat((xy, wh, y[..., 4:]), -1)
+
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+
+class IAuxDetect(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+    end2end = False
+    include_nms = False
+    concat = False
+
+    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
+        super(IAuxDetect, self).__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[:self.nl])  # output conv
+        self.m2 = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch[self.nl:])  # output conv
+        
+        self.ia = nn.ModuleList(ImplicitA(x) for x in ch[:self.nl])
+        self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch[:self.nl])
+
+    def forward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](self.ia[i](x[i]))  # conv
+            x[i] = self.im[i](x[i])
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+            
+            x[i+self.nl] = self.m2[i](x[i+self.nl])
+            x[i+self.nl] = x[i+self.nl].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                if not torch.onnx.is_in_onnx_export():
+                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                else:
+                    xy, wh, conf = y.split((2, 2, self.nc + 1), 4)  # y.tensor_split((2, 4, 5), 4)  # torch 1.8.0
+                    xy = xy * (2. * self.stride[i]) + (self.stride[i] * (self.grid[i] - 0.5))  # new xy
+                    wh = wh ** 2 * (4 * self.anchor_grid[i].data)  # new wh
+                    y = torch.cat((xy, wh, conf), 4)
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x[:self.nl])
+
+    def fuseforward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                if not torch.onnx.is_in_onnx_export():
+                    y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                else:
+                    xy = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                    wh = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i].data  # wh
+                    y = torch.cat((xy, wh, y[..., 4:]), -1)
+                z.append(y.view(bs, -1, self.no))
+
+        if self.training:
+            out = x
+        elif self.end2end:
+            out = torch.cat(z, 1)
+        elif self.include_nms:
+            z = self.convert(z)
+            out = (z, )
+        elif self.concat:
+            out = torch.cat(z, 1)            
+        else:
+            out = (torch.cat(z, 1), x)
+
+        return out
+    
+    def fuse(self):
+        print("IAuxDetect.fuse")
+        # fuse ImplicitA and Convolution
+        for i in range(len(self.m)):
+            c1,c2,_,_ = self.m[i].weight.shape
+            c1_,c2_, _,_ = self.ia[i].implicit.shape
+            self.m[i].bias += torch.matmul(self.m[i].weight.reshape(c1,c2),self.ia[i].implicit.reshape(c2_,c1_)).squeeze(1)
+
+        # fuse ImplicitM and Convolution
+        for i in range(len(self.m)):
+            c1,c2, _,_ = self.im[i].implicit.shape
+            self.m[i].bias *= self.im[i].implicit.reshape(c2)
+            self.m[i].weight *= self.im[i].implicit.transpose(0,1)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+    def convert(self, z):
+        z = torch.cat(z, 1)
+        box = z[:, :, :4]
+        conf = z[:, :, 4:5]
+        score = z[:, :, 5:]
+        score *= conf
+        convert_matrix = torch.tensor([[1, 0, 1, 0], [0, 1, 0, 1], [-0.5, 0, 0.5, 0], [0, -0.5, 0, 0.5]],
+                                           dtype=torch.float32,
+                                           device=z.device)
+        box @= convert_matrix                          
+        return (box, score)
+
+
+class IBin(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+
+    def __init__(self, nc=80, anchors=(), ch=(), bin_count=21):  # detection layer
+        super(IBin, self).__init__()
+        self.nc = nc  # number of classes
+        self.bin_count = bin_count
+
+        self.w_bin_sigmoid = SigmoidBin(bin_count=self.bin_count, min=0.0, max=4.0)
+        self.h_bin_sigmoid = SigmoidBin(bin_count=self.bin_count, min=0.0, max=4.0)
+        # classes, x,y,obj
+        self.no = nc + 3 + \
+            self.w_bin_sigmoid.get_length() + self.h_bin_sigmoid.get_length()   # w-bce, h-bce
+            # + self.x_bin_sigmoid.get_length() + self.y_bin_sigmoid.get_length()
+        
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+        
+        self.ia = nn.ModuleList(ImplicitA(x) for x in ch)
+        self.im = nn.ModuleList(ImplicitM(self.no * self.na) for _ in ch)
+
+    def forward(self, x):
+
+        #self.x_bin_sigmoid.use_fw_regression = True
+        #self.y_bin_sigmoid.use_fw_regression = True
+        self.w_bin_sigmoid.use_fw_regression = True
+        self.h_bin_sigmoid.use_fw_regression = True
+        
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](self.ia[i](x[i]))  # conv
+            x[i] = self.im[i](x[i])
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                #y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                
+
+                #px = (self.x_bin_sigmoid.forward(y[..., 0:12]) + self.grid[i][..., 0]) * self.stride[i]
+                #py = (self.y_bin_sigmoid.forward(y[..., 12:24]) + self.grid[i][..., 1]) * self.stride[i]
+
+                pw = self.w_bin_sigmoid.forward(y[..., 2:24]) * self.anchor_grid[i][..., 0]
+                ph = self.h_bin_sigmoid.forward(y[..., 24:46]) * self.anchor_grid[i][..., 1]
+
+                #y[..., 0] = px
+                #y[..., 1] = py
+                y[..., 2] = pw
+                y[..., 3] = ph
+                
+                y = torch.cat((y[..., 0:4], y[..., 46:]), dim=-1)
+                
+                z.append(y.view(bs, -1, y.shape[-1]))
+
+        return x if self.training else (torch.cat(z, 1), x)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+
+class Model(nn.Module):
+    def __init__(self, cfg='yolor-csp-c.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
+        super(Model, self).__init__()
+        self.traced = False
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.SafeLoader)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        if anchors:
+            logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
+            self.yaml['anchors'] = round(anchors)  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        # print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            s = 256  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+        if isinstance(m, IDetect):
+            s = 256  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+        if isinstance(m, IAuxDetect):
+            s = 256  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))[:4]])  # forward
+            #print(m.stride)
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_aux_biases()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+        if isinstance(m, IBin):
+            s = 256  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_biases_bin()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+        if isinstance(m, IKeypoint):
+            s = 256  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            check_anchor_order(m)
+            m.anchors /= m.stride.view(-1, 1, 1)
+            self.stride = m.stride
+            self._initialize_biases_kpt()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        logger.info('')
+
+    def forward(self, x, augment=False, profile=False):
+        if augment:
+            img_size = x.shape[-2:]  # height, width
+            s = [1, 0.83, 0.67]  # scales
+            f = [None, 3, None]  # flips (2-ud, 3-lr)
+            y = []  # outputs
+            for si, fi in zip(s, f):
+                xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+                yi = self.forward_once(xi)[0]  # forward
+                # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+                yi[..., :4] /= si  # de-scale
+                if fi == 2:
+                    yi[..., 1] = img_size[0] - yi[..., 1]  # de-flip ud
+                elif fi == 3:
+                    yi[..., 0] = img_size[1] - yi[..., 0]  # de-flip lr
+                y.append(yi)
+            return torch.cat(y, 1), None  # augmented inference, train
+        else:
+            return self.forward_once(x, profile)  # single-scale inference, train
+
+    def forward_once(self, x, profile=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+
+            if not hasattr(self, 'traced'):
+                self.traced=False
+
+            if self.traced:
+                if isinstance(m, Detect) or isinstance(m, IDetect) or isinstance(m, IAuxDetect) or isinstance(m, IKeypoint):
+                    break
+
+            if profile:
+                c = isinstance(m, (Detect, IDetect, IAuxDetect, IBin))
+                o = thop.profile(m, inputs=(x.copy() if c else x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPS
+                for _ in range(10):
+                    m(x.copy() if c else x)
+                t = time_synchronized()
+                for _ in range(10):
+                    m(x.copy() if c else x)
+                dt.append((time_synchronized() - t) * 100)
+                print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
+
+            x = m(x)  # run
+            
+            y.append(x if m.i in self.save else None)  # save output
+
+        if profile:
+            print('%.1fms total' % sum(dt))
+        return x
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _initialize_aux_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, mi2, s in zip(m.m, m.m2, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+            b2 = mi2.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b2.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b2.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi2.bias = torch.nn.Parameter(b2.view(-1), requires_grad=True)
+
+    def _initialize_biases_bin(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Bin() module
+        bc = m.bin_count
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            old = b[:, (0,1,2,bc+3)].data
+            obj_idx = 2*bc+4
+            b[:, :obj_idx].data += math.log(0.6 / (bc + 1 - 0.99))
+            b[:, obj_idx].data += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b[:, (obj_idx+1):].data += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            b[:, (0,1,2,bc+3)].data = old
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _initialize_biases_kpt(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _print_biases(self):
+        m = self.model[-1]  # Detect() module
+        for mi in m.m:  # from
+            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
+            print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+    # def _print_weights(self):
+    #     for m in self.model.modules():
+    #         if type(m) is Bottleneck:
+    #             print('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        print('Fusing layers... ')
+        for m in self.model.modules():
+            if isinstance(m, RepConv):
+                #print(f" fuse_repvgg_block")
+                m.fuse_repvgg_block()
+            elif isinstance(m, RepConv_OREPA):
+                #print(f" switch_to_deploy")
+                m.switch_to_deploy()
+            elif type(m) is Conv and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.fuseforward  # update forward
+            elif isinstance(m, (IDetect, IAuxDetect)):
+                m.fuse()
+                m.forward = m.fuseforward
+        self.info()
+        return self
+
+    def nms(self, mode=True):  # add or remove NMS module
+        present = type(self.model[-1]) is NMS  # last layer is NMS
+        if mode and not present:
+            print('Adding NMS... ')
+            m = NMS()  # module
+            m.f = -1  # from
+            m.i = self.model[-1].i + 1  # index
+            self.model.add_module(name='%s' % m.i, module=m)  # add
+            self.eval()
+        elif not mode and present:
+            print('Removing NMS... ')
+            self.model = self.model[:-1]  # remove
+        return self
+
+    def autoshape(self):  # add autoShape module
+        print('Adding autoShape... ')
+        m = autoShape(self)  # wrap model
+        copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())  # copy attributes
+        return m
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    logger.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except:
+                pass
+
+        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [nn.Conv2d, Conv, RobustConv, RobustConv2, DWConv, GhostConv, RepConv, RepConv_OREPA, DownC, 
+                 SPP, SPPF, SPPCSPC, GhostSPPCSPC, MixConv2d, Focus, Stem, GhostStem, CrossConv, 
+                 Bottleneck, BottleneckCSPA, BottleneckCSPB, BottleneckCSPC, 
+                 RepBottleneck, RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC,  
+                 Res, ResCSPA, ResCSPB, ResCSPC, 
+                 RepRes, RepResCSPA, RepResCSPB, RepResCSPC, 
+                 ResX, ResXCSPA, ResXCSPB, ResXCSPC, 
+                 RepResX, RepResXCSPA, RepResXCSPB, RepResXCSPC, 
+                 Ghost, GhostCSPA, GhostCSPB, GhostCSPC,
+                 SwinTransformerBlock, STCSPA, STCSPB, STCSPC,
+                 SwinTransformer2Block, ST2CSPA, ST2CSPB, ST2CSPC]:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in [DownC, SPPCSPC, GhostSPPCSPC, 
+                     BottleneckCSPA, BottleneckCSPB, BottleneckCSPC, 
+                     RepBottleneckCSPA, RepBottleneckCSPB, RepBottleneckCSPC, 
+                     ResCSPA, ResCSPB, ResCSPC, 
+                     RepResCSPA, RepResCSPB, RepResCSPC, 
+                     ResXCSPA, ResXCSPB, ResXCSPC, 
+                     RepResXCSPA, RepResXCSPB, RepResXCSPC,
+                     GhostCSPA, GhostCSPB, GhostCSPC,
+                     STCSPA, STCSPB, STCSPC,
+                     ST2CSPA, ST2CSPB, ST2CSPC]:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum([ch[x] for x in f])
+        elif m is Chuncat:
+            c2 = sum([ch[x] for x in f])
+        elif m is Shortcut:
+            c2 = ch[f[0]]
+        elif m is Foldcut:
+            c2 = ch[f] // 2
+        elif m in [Detect, IDetect, IAuxDetect, IBin, IKeypoint]:
+            args.append([ch[x] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+        elif m is ReOrg:
+            c2 = ch[f] * 4
+        elif m is Contract:
+            c2 = ch[f] * args[0] ** 2
+        elif m is Expand:
+            c2 = ch[f] // args[0] ** 2
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum([x.numel() for x in m_.parameters()])  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        logger.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n, np, t, args))  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cfg', type=str, default='yolor-csp-c.yaml', help='model.yaml')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--profile', action='store_true', help='profile model speed')
+    opt = parser.parse_args()
+    opt.cfg = check_file(opt.cfg)  # check file
+    set_logging()
+    device = select_device(opt.device)
+
+    # Create model
+    model = Model(opt.cfg).to(device)
+    model.train()
+    
+    if opt.profile:
+        img = torch.rand(1, 3, 640, 640).to(device)
+        y = model(img, profile=True)
+
+    # Profile
+    # img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+    # y = model(img, profile=True)
+
+    # Tensorboard
+    # from torch.utils.tensorboard import SummaryWriter
+    # tb_writer = SummaryWriter()
+    # print("Run 'tensorboard --logdir=models/runs' to view tensorboard at http://localhost:6006/")
+    # tb_writer.add_graph(model.model, img)  # add model to tensorboard
+    # tb_writer.add_image('test', img[0], dataformats='CWH')  # add model to tensorboard

infer/yolov7/utils/__init__.py

@@ -0,0 +1 @@
+# init

infer/yolov7/utils/activations.py

@@ -0,0 +1,72 @@
+# Activation functions
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
+class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
+    @staticmethod
+    def forward(x):
+        return x * torch.sigmoid(x)
+
+
+class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
+    @staticmethod
+    def forward(x):
+        # return x * F.hardsigmoid(x)  # for torchscript and CoreML
+        return x * F.hardtanh(x + 3, 0., 6.) / 6.  # for torchscript, CoreML and ONNX
+
+
+class MemoryEfficientSwish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x * torch.sigmoid(x)
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            return grad_output * (sx * (1 + x * (1 - sx)))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
+class Mish(nn.Module):
+    @staticmethod
+    def forward(x):
+        return x * F.softplus(x).tanh()
+
+
+class MemoryEfficientMish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            fx = F.softplus(x).tanh()
+            return grad_output * (fx + x * sx * (1 - fx * fx))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
+class FReLU(nn.Module):
+    def __init__(self, c1, k=3):  # ch_in, kernel
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
+        self.bn = nn.BatchNorm2d(c1)
+
+    def forward(self, x):
+        return torch.max(x, self.bn(self.conv(x)))

infer/yolov7/utils/add_nms.py

@@ -0,0 +1,155 @@
+import numpy as np
+import onnx
+from onnx import shape_inference
+try:
+    import onnx_graphsurgeon as gs
+except Exception as e:
+    print('Import onnx_graphsurgeon failure: %s' % e)
+
+import logging
+
+LOGGER = logging.getLogger(__name__)
+
+class RegisterNMS(object):
+    def __init__(
+        self,
+        onnx_model_path: str,
+        precision: str = "fp32",
+    ):
+
+        self.graph = gs.import_onnx(onnx.load(onnx_model_path))
+        assert self.graph
+        LOGGER.info("ONNX graph created successfully")
+        # Fold constants via ONNX-GS that PyTorch2ONNX may have missed
+        self.graph.fold_constants()
+        self.precision = precision
+        self.batch_size = 1
+    def infer(self):
+        """
+        Sanitize the graph by cleaning any unconnected nodes, do a topological resort,
+        and fold constant inputs values. When possible, run shape inference on the
+        ONNX graph to determine tensor shapes.
+        """
+        for _ in range(3):
+            count_before = len(self.graph.nodes)
+
+            self.graph.cleanup().toposort()
+            try:
+                for node in self.graph.nodes:
+                    for o in node.outputs:
+                        o.shape = None
+                model = gs.export_onnx(self.graph)
+                model = shape_inference.infer_shapes(model)
+                self.graph = gs.import_onnx(model)
+            except Exception as e:
+                LOGGER.info(f"Shape inference could not be performed at this time:\n{e}")
+            try:
+                self.graph.fold_constants(fold_shapes=True)
+            except TypeError as e:
+                LOGGER.error(
+                    "This version of ONNX GraphSurgeon does not support folding shapes, "
+                    f"please upgrade your onnx_graphsurgeon module. Error:\n{e}"
+                )
+                raise
+
+            count_after = len(self.graph.nodes)
+            if count_before == count_after:
+                # No new folding occurred in this iteration, so we can stop for now.
+                break
+
+    def save(self, output_path):
+        """
+        Save the ONNX model to the given location.
+        Args:
+            output_path: Path pointing to the location where to write
+                out the updated ONNX model.
+        """
+        self.graph.cleanup().toposort()
+        model = gs.export_onnx(self.graph)
+        onnx.save(model, output_path)
+        LOGGER.info(f"Saved ONNX model to {output_path}")
+
+    def register_nms(
+        self,
+        *,
+        score_thresh: float = 0.25,
+        nms_thresh: float = 0.45,
+        detections_per_img: int = 100,
+    ):
+        """
+        Register the ``EfficientNMS_TRT`` plugin node.
+        NMS expects these shapes for its input tensors:
+            - box_net: [batch_size, number_boxes, 4]
+            - class_net: [batch_size, number_boxes, number_labels]
+        Args:
+            score_thresh (float): The scalar threshold for score (low scoring boxes are removed).
+            nms_thresh (float): The scalar threshold for IOU (new boxes that have high IOU
+                overlap with previously selected boxes are removed).
+            detections_per_img (int): Number of best detections to keep after NMS.
+        """
+
+        self.infer()
+        # Find the concat node at the end of the network
+        op_inputs = self.graph.outputs
+        op = "EfficientNMS_TRT"
+        attrs = {
+            "plugin_version": "1",
+            "background_class": -1,  # no background class
+            "max_output_boxes": detections_per_img,
+            "score_threshold": score_thresh,
+            "iou_threshold": nms_thresh,
+            "score_activation": False,
+            "box_coding": 0,
+        }
+
+        if self.precision == "fp32":
+            dtype_output = np.float32
+        elif self.precision == "fp16":
+            dtype_output = np.float16
+        else:
+            raise NotImplementedError(f"Currently not supports precision: {self.precision}")
+
+        # NMS Outputs
+        output_num_detections = gs.Variable(
+            name="num_dets",
+            dtype=np.int32,
+            shape=[self.batch_size, 1],
+        )  # A scalar indicating the number of valid detections per batch image.
+        output_boxes = gs.Variable(
+            name="det_boxes",
+            dtype=dtype_output,
+            shape=[self.batch_size, detections_per_img, 4],
+        )
+        output_scores = gs.Variable(
+            name="det_scores",
+            dtype=dtype_output,
+            shape=[self.batch_size, detections_per_img],
+        )
+        output_labels = gs.Variable(
+            name="det_classes",
+            dtype=np.int32,
+            shape=[self.batch_size, detections_per_img],
+        )
+
+        op_outputs = [output_num_detections, output_boxes, output_scores, output_labels]
+
+        # Create the NMS Plugin node with the selected inputs. The outputs of the node will also
+        # become the final outputs of the graph.
+        self.graph.layer(op=op, name="batched_nms", inputs=op_inputs, outputs=op_outputs, attrs=attrs)
+        LOGGER.info(f"Created NMS plugin '{op}' with attributes: {attrs}")
+
+        self.graph.outputs = op_outputs
+
+        self.infer()
+
+    def save(self, output_path):
+        """
+        Save the ONNX model to the given location.
+        Args:
+            output_path: Path pointing to the location where to write
+                out the updated ONNX model.
+        """
+        self.graph.cleanup().toposort()
+        model = gs.export_onnx(self.graph)
+        onnx.save(model, output_path)
+        LOGGER.info(f"Saved ONNX model to {output_path}")

infer/yolov7/utils/autoanchor.py

@@ -0,0 +1,160 @@
+# Auto-anchor utils
+
+import numpy as np
+import torch
+import yaml
+from scipy.cluster.vq import kmeans
+from tqdm import tqdm
+
+from infer.yolov7.utils.general import colorstr
+
+
+def check_anchor_order(m):
+    # Check anchor order against stride order for YOLO Detect() module m, and correct if necessary
+    a = m.anchor_grid.prod(-1).view(-1)  # anchor area
+    da = a[-1] - a[0]  # delta a
+    ds = m.stride[-1] - m.stride[0]  # delta s
+    if da.sign() != ds.sign():  # same order
+        print('Reversing anchor order')
+        m.anchors[:] = m.anchors.flip(0)
+        m.anchor_grid[:] = m.anchor_grid.flip(0)
+
+
+def check_anchors(dataset, model, thr=4.0, imgsz=640):
+    # Check anchor fit to data, recompute if necessary
+    prefix = colorstr('autoanchor: ')
+    print(f'\n{prefix}Analyzing anchors... ', end='')
+    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
+    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
+    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
+
+    def metric(k):  # compute metric
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        best = x.max(1)[0]  # best_x
+        aat = (x > 1. / thr).float().sum(1).mean()  # anchors above threshold
+        bpr = (best > 1. / thr).float().mean()  # best possible recall
+        return bpr, aat
+
+    anchors = m.anchor_grid.clone().cpu().view(-1, 2)  # current anchors
+    bpr, aat = metric(anchors)
+    print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
+    if bpr < 0.98:  # threshold to recompute
+        print('. Attempting to improve anchors, please wait...')
+        na = m.anchor_grid.numel() // 2  # number of anchors
+        try:
+            anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
+        except Exception as e:
+            print(f'{prefix}ERROR: {e}')
+        new_bpr = metric(anchors)[0]
+        if new_bpr > bpr:  # replace anchors
+            anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
+            m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid)  # for inference
+            check_anchor_order(m)
+            m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1)  # loss
+            print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
+        else:
+            print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
+    print('')  # newline
+
+
+def kmean_anchors(path='./data/coco.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+    """ Creates kmeans-evolved anchors from training dataset
+
+        Arguments:
+            path: path to dataset *.yaml, or a loaded dataset
+            n: number of anchors
+            img_size: image size used for training
+            thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
+            gen: generations to evolve anchors using genetic algorithm
+            verbose: print all results
+
+        Return:
+            k: kmeans evolved anchors
+
+        Usage:
+            from utils.autoanchor import *; _ = kmean_anchors()
+    """
+    thr = 1. / thr
+    prefix = colorstr('autoanchor: ')
+
+    def metric(k, wh):  # compute metrics
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        # x = wh_iou(wh, torch.tensor(k))  # iou metric
+        return x, x.max(1)[0]  # x, best_x
+
+    def anchor_fitness(k):  # mutation fitness
+        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
+        return (best * (best > thr).float()).mean()  # fitness
+
+    def print_results(k):
+        k = k[np.argsort(k.prod(1))]  # sort small to large
+        x, best = metric(k, wh0)
+        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
+        print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
+        print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
+              f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
+        for i, x in enumerate(k):
+            print('%i,%i' % (round(x[0]), round(x[1])), end=',  ' if i < len(k) - 1 else '\n')  # use in *.cfg
+        return k
+
+    if isinstance(path, str):  # *.yaml file
+        with open(path) as f:
+            data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # model dict
+        from utils.datasets import LoadImagesAndLabels
+        dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
+    else:
+        dataset = path  # dataset
+
+    # Get label wh
+    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
+
+    # Filter
+    i = (wh0 < 3.0).any(1).sum()
+    if i:
+        print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
+    wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels
+    # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1
+
+    # Kmeans calculation
+    print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
+    s = wh.std(0)  # sigmas for whitening
+    k, dist = kmeans(wh / s, n, iter=30)  # points, mean distance
+    assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}')
+    k *= s
+    wh = torch.tensor(wh, dtype=torch.float32)  # filtered
+    wh0 = torch.tensor(wh0, dtype=torch.float32)  # unfiltered
+    k = print_results(k)
+
+    # Plot
+    # k, d = [None] * 20, [None] * 20
+    # for i in tqdm(range(1, 21)):
+    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
+    # ax = ax.ravel()
+    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
+    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
+    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
+    # fig.savefig('wh.png', dpi=200)
+
+    # Evolve
+    npr = np.random
+    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
+    pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:')  # progress bar
+    for _ in pbar:
+        v = np.ones(sh)
+        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
+            v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
+        kg = (k.copy() * v).clip(min=2.0)
+        fg = anchor_fitness(kg)
+        if fg > f:
+            f, k = fg, kg.copy()
+            pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
+            if verbose:
+                print_results(k)
+
+    return print_results(k)

infer/yolov7/utils/aws/__init__.py

@@ -0,0 +1 @@
+#init

infer/yolov7/utils/aws/mime.sh

@@ -0,0 +1,26 @@
+# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
+# This script will run on every instance restart, not only on first start
+# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
+
+Content-Type: multipart/mixed; boundary="//"
+MIME-Version: 1.0
+
+--//
+Content-Type: text/cloud-config; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="cloud-config.txt"
+
+#cloud-config
+cloud_final_modules:
+- [scripts-user, always]
+
+--//
+Content-Type: text/x-shellscript; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="userdata.txt"
+
+#!/bin/bash
+# --- paste contents of userdata.sh here ---
+--//

infer/yolov7/utils/aws/resume.py

@@ -0,0 +1,37 @@
+# Resume all interrupted trainings in yolor/ dir including DDP trainings
+# Usage: $ python utils/aws/resume.py
+
+import os
+import sys
+from pathlib import Path
+
+import torch
+import yaml
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+
+port = 0  # --master_port
+path = Path('').resolve()
+for last in path.rglob('*/**/last.pt'):
+    ckpt = torch.load(last)
+    if ckpt['optimizer'] is None:
+        continue
+
+    # Load opt.yaml
+    with open(last.parent.parent / 'opt.yaml') as f:
+        opt = yaml.load(f, Loader=yaml.SafeLoader)
+
+    # Get device count
+    d = opt['device'].split(',')  # devices
+    nd = len(d)  # number of devices
+    ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1)  # distributed data parallel
+
+    if ddp:  # multi-GPU
+        port += 1
+        cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
+    else:  # single-GPU
+        cmd = f'python train.py --resume {last}'
+
+    cmd += ' > /dev/null 2>&1 &'  # redirect output to dev/null and run in daemon thread
+    print(cmd)
+    os.system(cmd)

infer/yolov7/utils/aws/userdata.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
+# This script will run only once on first instance start (for a re-start script see mime.sh)
+# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
+# Use >300 GB SSD
+
+cd home/ubuntu
+if [ ! -d yolor ]; then
+  echo "Running first-time script." # install dependencies, download COCO, pull Docker
+  git clone -b main https://github.com/WongKinYiu/yolov7 && sudo chmod -R 777 yolov7
+  cd yolov7
+  bash data/scripts/get_coco.sh && echo "Data done." &
+  sudo docker pull nvcr.io/nvidia/pytorch:21.08-py3 && echo "Docker done." &
+  python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
+  wait && echo "All tasks done." # finish background tasks
+else
+  echo "Running re-start script." # resume interrupted runs
+  i=0
+  list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
+  while IFS= read -r id; do
+    ((i++))
+    echo "restarting container $i: $id"
+    sudo docker start $id
+    # sudo docker exec -it $id python train.py --resume # single-GPU
+    sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
+  done <<<"$list"
+fi

infer/yolov7/utils/datasets.py

@@ -0,0 +1,1320 @@
+# Dataset utils and dataloaders
+
+import glob
+import logging
+import math
+import os
+import random
+import shutil
+import time
+from itertools import repeat
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+from threading import Thread
+
+import cv2
+import numpy as np
+import torch
+import torch.nn.functional as F
+from PIL import Image, ExifTags
+from torch.utils.data import Dataset
+from tqdm import tqdm
+
+import pickle
+from copy import deepcopy
+#from pycocotools import mask as maskUtils
+from torchvision.utils import save_image
+from torchvision.ops import roi_pool, roi_align, ps_roi_pool, ps_roi_align
+
+from infer.yolov7.utils.general import check_requirements, xyxy2xywh, xywh2xyxy, xywhn2xyxy, xyn2xy, segment2box, segments2boxes, \
+    resample_segments, clean_str
+from infer.yolov7.utils.torch_utils import torch_distributed_zero_first
+
+# Parameters
+help_url = 'https://github.com/ultralytics/yolov5/wiki/Train-Custom-Data'
+img_formats = ['bmp', 'jpg', 'jpeg', 'png', 'tif', 'tiff', 'dng', 'webp', 'mpo']  # acceptable image suffixes
+vid_formats = ['mov', 'avi', 'mp4', 'mpg', 'mpeg', 'm4v', 'wmv', 'mkv']  # acceptable video suffixes
+logger = logging.getLogger(__name__)
+
+# Get orientation exif tag
+for orientation in ExifTags.TAGS.keys():
+    if ExifTags.TAGS[orientation] == 'Orientation':
+        break
+
+
+def get_hash(files):
+    # Returns a single hash value of a list of files
+    return sum(os.path.getsize(f) for f in files if os.path.isfile(f))
+
+
+def exif_size(img):
+    # Returns exif-corrected PIL size
+    s = img.size  # (width, height)
+    try:
+        rotation = dict(img._getexif().items())[orientation]
+        if rotation == 6:  # rotation 270
+            s = (s[1], s[0])
+        elif rotation == 8:  # rotation 90
+            s = (s[1], s[0])
+    except:
+        pass
+
+    return s
+
+
+def create_dataloader(path, imgsz, batch_size, stride, opt, hyp=None, augment=False, cache=False, pad=0.0, rect=False,
+                      rank=-1, world_size=1, workers=8, image_weights=False, quad=False, prefix=''):
+    # Make sure only the first process in DDP process the dataset first, and the following others can use the cache
+    with torch_distributed_zero_first(rank):
+        dataset = LoadImagesAndLabels(path, imgsz, batch_size,
+                                      augment=augment,  # augment images
+                                      hyp=hyp,  # augmentation hyperparameters
+                                      rect=rect,  # rectangular training
+                                      cache_images=cache,
+                                      single_cls=opt.single_cls,
+                                      stride=int(stride),
+                                      pad=pad,
+                                      image_weights=image_weights,
+                                      prefix=prefix)
+
+    batch_size = min(batch_size, len(dataset))
+    nw = min([os.cpu_count() // world_size, batch_size if batch_size > 1 else 0, workers])  # number of workers
+    sampler = torch.utils.data.distributed.DistributedSampler(dataset) if rank != -1 else None
+    loader = torch.utils.data.DataLoader if image_weights else InfiniteDataLoader
+    # Use torch.utils.data.DataLoader() if dataset.properties will update during training else InfiniteDataLoader()
+    dataloader = loader(dataset,
+                        batch_size=batch_size,
+                        num_workers=nw,
+                        sampler=sampler,
+                        pin_memory=True,
+                        collate_fn=LoadImagesAndLabels.collate_fn4 if quad else LoadImagesAndLabels.collate_fn)
+    return dataloader, dataset
+
+
+class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
+    """ Dataloader that reuses workers
+
+    Uses same syntax as vanilla DataLoader
+    """
+
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+        object.__setattr__(self, 'batch_sampler', _RepeatSampler(self.batch_sampler))
+        self.iterator = super().__iter__()
+
+    def __len__(self):
+        return len(self.batch_sampler.sampler)
+
+    def __iter__(self):
+        for i in range(len(self)):
+            yield next(self.iterator)
+
+
+class _RepeatSampler(object):
+    """ Sampler that repeats forever
+
+    Args:
+        sampler (Sampler)
+    """
+
+    def __init__(self, sampler):
+        self.sampler = sampler
+
+    def __iter__(self):
+        while True:
+            yield from iter(self.sampler)
+
+
+class LoadImages:  # for inference
+    def __init__(self, path, img_size=640, stride=32):
+        p = str(Path(path).absolute())  # os-agnostic absolute path
+        if '*' in p:
+            files = sorted(glob.glob(p, recursive=True))  # glob
+        elif os.path.isdir(p):
+            files = sorted(glob.glob(os.path.join(p, '*.*')))  # dir
+        elif os.path.isfile(p):
+            files = [p]  # files
+        else:
+            raise Exception(f'ERROR: {p} does not exist')
+
+        images = [x for x in files if x.split('.')[-1].lower() in img_formats]
+        videos = [x for x in files if x.split('.')[-1].lower() in vid_formats]
+        ni, nv = len(images), len(videos)
+
+        self.img_size = img_size
+        self.stride = stride
+        self.files = images + videos
+        self.nf = ni + nv  # number of files
+        self.video_flag = [False] * ni + [True] * nv
+        self.mode = 'image'
+        if any(videos):
+            self.new_video(videos[0])  # new video
+        else:
+            self.cap = None
+        assert self.nf > 0, f'No images or videos found in {p}. ' \
+                            f'Supported formats are:\nimages: {img_formats}\nvideos: {vid_formats}'
+
+    def __iter__(self):
+        self.count = 0
+        return self
+
+    def __next__(self):
+        if self.count == self.nf:
+            raise StopIteration
+        path = self.files[self.count]
+
+        if self.video_flag[self.count]:
+            # Read video
+            self.mode = 'video'
+            ret_val, img0 = self.cap.read()
+            if not ret_val:
+                self.count += 1
+                self.cap.release()
+                if self.count == self.nf:  # last video
+                    raise StopIteration
+                else:
+                    path = self.files[self.count]
+                    self.new_video(path)
+                    ret_val, img0 = self.cap.read()
+
+            self.frame += 1
+            print(f'video {self.count + 1}/{self.nf} ({self.frame}/{self.nframes}) {path}: ', end='')
+
+        else:
+            # Read image
+            self.count += 1
+            img0 = cv2.imread(path)  # BGR
+            assert img0 is not None, 'Image Not Found ' + path
+            #print(f'image {self.count}/{self.nf} {path}: ', end='')
+
+        # Padded resize
+        img = letterbox(img0, self.img_size, stride=self.stride)[0]
+
+        # Convert
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = np.ascontiguousarray(img)
+
+        return path, img, img0, self.cap
+
+    def new_video(self, path):
+        self.frame = 0
+        self.cap = cv2.VideoCapture(path)
+        self.nframes = int(self.cap.get(cv2.CAP_PROP_FRAME_COUNT))
+
+    def __len__(self):
+        return self.nf  # number of files
+
+
+class LoadWebcam:  # for inference
+    def __init__(self, pipe='0', img_size=640, stride=32):
+        self.img_size = img_size
+        self.stride = stride
+
+        if pipe.isnumeric():
+            pipe = eval(pipe)  # local camera
+        # pipe = 'rtsp://192.168.1.64/1'  # IP camera
+        # pipe = 'rtsp://username:password@192.168.1.64/1'  # IP camera with login
+        # pipe = 'http://wmccpinetop.axiscam.net/mjpg/video.mjpg'  # IP golf camera
+
+        self.pipe = pipe
+        self.cap = cv2.VideoCapture(pipe)  # video capture object
+        self.cap.set(cv2.CAP_PROP_BUFFERSIZE, 3)  # set buffer size
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            self.cap.release()
+            cv2.destroyAllWindows()
+            raise StopIteration
+
+        # Read frame
+        if self.pipe == 0:  # local camera
+            ret_val, img0 = self.cap.read()
+            img0 = cv2.flip(img0, 1)  # flip left-right
+        else:  # IP camera
+            n = 0
+            while True:
+                n += 1
+                self.cap.grab()
+                if n % 30 == 0:  # skip frames
+                    ret_val, img0 = self.cap.retrieve()
+                    if ret_val:
+                        break
+
+        # Print
+        assert ret_val, f'Camera Error {self.pipe}'
+        img_path = 'webcam.jpg'
+        print(f'webcam {self.count}: ', end='')
+
+        # Padded resize
+        img = letterbox(img0, self.img_size, stride=self.stride)[0]
+
+        # Convert
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = np.ascontiguousarray(img)
+
+        return img_path, img, img0, None
+
+    def __len__(self):
+        return 0
+
+
+class LoadStreams:  # multiple IP or RTSP cameras
+    def __init__(self, sources='streams.txt', img_size=640, stride=32):
+        self.mode = 'stream'
+        self.img_size = img_size
+        self.stride = stride
+
+        if os.path.isfile(sources):
+            with open(sources, 'r') as f:
+                sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
+        else:
+            sources = [sources]
+
+        n = len(sources)
+        self.imgs = [None] * n
+        self.sources = [clean_str(x) for x in sources]  # clean source names for later
+        for i, s in enumerate(sources):
+            # Start the thread to read frames from the video stream
+            print(f'{i + 1}/{n}: {s}... ', end='')
+            url = eval(s) if s.isnumeric() else s
+            if 'youtube.com/' in str(url) or 'youtu.be/' in str(url):  # if source is YouTube video
+                check_requirements(('pafy', 'youtube_dl'))
+                import pafy
+                url = pafy.new(url).getbest(preftype="mp4").url
+            cap = cv2.VideoCapture(url)
+            assert cap.isOpened(), f'Failed to open {s}'
+            w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+            h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+            self.fps = cap.get(cv2.CAP_PROP_FPS) % 100
+
+            _, self.imgs[i] = cap.read()  # guarantee first frame
+            thread = Thread(target=self.update, args=([i, cap]), daemon=True)
+            print(f' success ({w}x{h} at {self.fps:.2f} FPS).')
+            thread.start()
+        print('')  # newline
+
+        # check for common shapes
+        s = np.stack([letterbox(x, self.img_size, stride=self.stride)[0].shape for x in self.imgs], 0)  # shapes
+        self.rect = np.unique(s, axis=0).shape[0] == 1  # rect inference if all shapes equal
+        if not self.rect:
+            print('WARNING: Different stream shapes detected. For optimal performance supply similarly-shaped streams.')
+
+    def update(self, index, cap):
+        # Read next stream frame in a daemon thread
+        n = 0
+        while cap.isOpened():
+            n += 1
+            # _, self.imgs[index] = cap.read()
+            cap.grab()
+            if n == 4:  # read every 4th frame
+                success, im = cap.retrieve()
+                self.imgs[index] = im if success else self.imgs[index] * 0
+                n = 0
+            time.sleep(1 / self.fps)  # wait time
+
+    def __iter__(self):
+        self.count = -1
+        return self
+
+    def __next__(self):
+        self.count += 1
+        img0 = self.imgs.copy()
+        if cv2.waitKey(1) == ord('q'):  # q to quit
+            cv2.destroyAllWindows()
+            raise StopIteration
+
+        # Letterbox
+        img = [letterbox(x, self.img_size, auto=self.rect, stride=self.stride)[0] for x in img0]
+
+        # Stack
+        img = np.stack(img, 0)
+
+        # Convert
+        img = img[:, :, :, ::-1].transpose(0, 3, 1, 2)  # BGR to RGB, to bsx3x416x416
+        img = np.ascontiguousarray(img)
+
+        return self.sources, img, img0, None
+
+    def __len__(self):
+        return 0  # 1E12 frames = 32 streams at 30 FPS for 30 years
+
+
+def img2label_paths(img_paths):
+    # Define label paths as a function of image paths
+    sa, sb = os.sep + 'images' + os.sep, os.sep + 'labels' + os.sep  # /images/, /labels/ substrings
+    return ['txt'.join(x.replace(sa, sb, 1).rsplit(x.split('.')[-1], 1)) for x in img_paths]
+
+
+class LoadImagesAndLabels(Dataset):  # for training/testing
+    def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
+                 cache_images=False, single_cls=False, stride=32, pad=0.0, prefix=''):
+        self.img_size = img_size
+        self.augment = augment
+        self.hyp = hyp
+        self.image_weights = image_weights
+        self.rect = False if image_weights else rect
+        self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
+        self.mosaic_border = [-img_size // 2, -img_size // 2]
+        self.stride = stride
+        self.path = path        
+        #self.albumentations = Albumentations() if augment else None
+
+        try:
+            f = []  # image files
+            for p in path if isinstance(path, list) else [path]:
+                p = Path(p)  # os-agnostic
+                if p.is_dir():  # dir
+                    f += glob.glob(str(p / '**' / '*.*'), recursive=True)
+                    # f = list(p.rglob('**/*.*'))  # pathlib
+                elif p.is_file():  # file
+                    with open(p, 'r') as t:
+                        t = t.read().strip().splitlines()
+                        parent = str(p.parent) + os.sep
+                        f += [x.replace('./', parent) if x.startswith('./') else x for x in t]  # local to global path
+                        # f += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
+                else:
+                    raise Exception(f'{prefix}{p} does not exist')
+            self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in img_formats])
+            # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in img_formats])  # pathlib
+            assert self.img_files, f'{prefix}No images found'
+        except Exception as e:
+            raise Exception(f'{prefix}Error loading data from {path}: {e}\nSee {help_url}')
+
+        # Check cache
+        self.label_files = img2label_paths(self.img_files)  # labels
+        cache_path = (p if p.is_file() else Path(self.label_files[0]).parent).with_suffix('.cache')  # cached labels
+        if cache_path.is_file():
+            cache, exists = torch.load(cache_path), True  # load
+            #if cache['hash'] != get_hash(self.label_files + self.img_files) or 'version' not in cache:  # changed
+            #    cache, exists = self.cache_labels(cache_path, prefix), False  # re-cache
+        else:
+            cache, exists = self.cache_labels(cache_path, prefix), False  # cache
+
+        # Display cache
+        nf, nm, ne, nc, n = cache.pop('results')  # found, missing, empty, corrupted, total
+        if exists:
+            d = f"Scanning '{cache_path}' images and labels... {nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+            tqdm(None, desc=prefix + d, total=n, initial=n)  # display cache results
+        assert nf > 0 or not augment, f'{prefix}No labels in {cache_path}. Can not train without labels. See {help_url}'
+
+        # Read cache
+        cache.pop('hash')  # remove hash
+        cache.pop('version')  # remove version
+        labels, shapes, self.segments = zip(*cache.values())
+        self.labels = list(labels)
+        self.shapes = np.array(shapes, dtype=np.float64)
+        self.img_files = list(cache.keys())  # update
+        self.label_files = img2label_paths(cache.keys())  # update
+        if single_cls:
+            for x in self.labels:
+                x[:, 0] = 0
+
+        n = len(shapes)  # number of images
+        bi = np.floor(np.arange(n) / batch_size).astype(int)  # batch index
+        nb = bi[-1] + 1  # number of batches
+        self.batch = bi  # batch index of image
+        self.n = n
+        self.indices = range(n)
+
+        # Rectangular Training
+        if self.rect:
+            # Sort by aspect ratio
+            s = self.shapes  # wh
+            ar = s[:, 1] / s[:, 0]  # aspect ratio
+            irect = ar.argsort()
+            self.img_files = [self.img_files[i] for i in irect]
+            self.label_files = [self.label_files[i] for i in irect]
+            self.labels = [self.labels[i] for i in irect]
+            self.shapes = s[irect]  # wh
+            ar = ar[irect]
+
+            # Set training image shapes
+            shapes = [[1, 1]] * nb
+            for i in range(nb):
+                ari = ar[bi == i]
+                mini, maxi = ari.min(), ari.max()
+                if maxi < 1:
+                    shapes[i] = [maxi, 1]
+                elif mini > 1:
+                    shapes[i] = [1, 1 / mini]
+
+            self.batch_shapes = np.ceil(np.array(shapes) * img_size / stride + pad).astype(int) * stride
+
+        # Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
+        self.imgs = [None] * n
+        if cache_images:
+            if cache_images == 'disk':
+                self.im_cache_dir = Path(Path(self.img_files[0]).parent.as_posix() + '_npy')
+                self.img_npy = [self.im_cache_dir / Path(f).with_suffix('.npy').name for f in self.img_files]
+                self.im_cache_dir.mkdir(parents=True, exist_ok=True)
+            gb = 0  # Gigabytes of cached images
+            self.img_hw0, self.img_hw = [None] * n, [None] * n
+            results = ThreadPool(8).imap(lambda x: load_image(*x), zip(repeat(self), range(n)))
+            pbar = tqdm(enumerate(results), total=n)
+            for i, x in pbar:
+                if cache_images == 'disk':
+                    if not self.img_npy[i].exists():
+                        np.save(self.img_npy[i].as_posix(), x[0])
+                    gb += self.img_npy[i].stat().st_size
+                else:
+                    self.imgs[i], self.img_hw0[i], self.img_hw[i] = x
+                    gb += self.imgs[i].nbytes
+                pbar.desc = f'{prefix}Caching images ({gb / 1E9:.1f}GB)'
+            pbar.close()
+
+    def cache_labels(self, path=Path('./labels.cache'), prefix=''):
+        # Cache dataset labels, check images and read shapes
+        x = {}  # dict
+        nm, nf, ne, nc = 0, 0, 0, 0  # number missing, found, empty, duplicate
+        pbar = tqdm(zip(self.img_files, self.label_files), desc='Scanning images', total=len(self.img_files))
+        for i, (im_file, lb_file) in enumerate(pbar):
+            try:
+                # verify images
+                im = Image.open(im_file)
+                im.verify()  # PIL verify
+                shape = exif_size(im)  # image size
+                segments = []  # instance segments
+                assert (shape[0] > 9) & (shape[1] > 9), f'image size {shape} <10 pixels'
+                assert im.format.lower() in img_formats, f'invalid image format {im.format}'
+
+                # verify labels
+                if os.path.isfile(lb_file):
+                    nf += 1  # label found
+                    with open(lb_file, 'r') as f:
+                        l = [x.split() for x in f.read().strip().splitlines()]
+                        if any([len(x) > 8 for x in l]):  # is segment
+                            classes = np.array([x[0] for x in l], dtype=np.float32)
+                            segments = [np.array(x[1:], dtype=np.float32).reshape(-1, 2) for x in l]  # (cls, xy1...)
+                            l = np.concatenate((classes.reshape(-1, 1), segments2boxes(segments)), 1)  # (cls, xywh)
+                        l = np.array(l, dtype=np.float32)
+                    if len(l):
+                        assert l.shape[1] == 5, 'labels require 5 columns each'
+                        assert (l >= 0).all(), 'negative labels'
+                        assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels'
+                        assert np.unique(l, axis=0).shape[0] == l.shape[0], 'duplicate labels'
+                    else:
+                        ne += 1  # label empty
+                        l = np.zeros((0, 5), dtype=np.float32)
+                else:
+                    nm += 1  # label missing
+                    l = np.zeros((0, 5), dtype=np.float32)
+                x[im_file] = [l, shape, segments]
+            except Exception as e:
+                nc += 1
+                print(f'{prefix}WARNING: Ignoring corrupted image and/or label {im_file}: {e}')
+
+            pbar.desc = f"{prefix}Scanning '{path.parent / path.stem}' images and labels... " \
+                        f"{nf} found, {nm} missing, {ne} empty, {nc} corrupted"
+        pbar.close()
+
+        if nf == 0:
+            print(f'{prefix}WARNING: No labels found in {path}. See {help_url}')
+
+        x['hash'] = get_hash(self.label_files + self.img_files)
+        x['results'] = nf, nm, ne, nc, i + 1
+        x['version'] = 0.1  # cache version
+        torch.save(x, path)  # save for next time
+        logging.info(f'{prefix}New cache created: {path}')
+        return x
+
+    def __len__(self):
+        return len(self.img_files)
+
+    # def __iter__(self):
+    #     self.count = -1
+    #     print('ran dataset iter')
+    #     #self.shuffled_vector = np.random.permutation(self.nF) if self.augment else np.arange(self.nF)
+    #     return self
+
+    def __getitem__(self, index):
+        index = self.indices[index]  # linear, shuffled, or image_weights
+
+        hyp = self.hyp
+        mosaic = self.mosaic and random.random() < hyp['mosaic']
+        if mosaic:
+            # Load mosaic
+            if random.random() < 0.8:
+                img, labels = load_mosaic(self, index)
+            else:
+                img, labels = load_mosaic9(self, index)
+            shapes = None
+
+            # MixUp https://arxiv.org/pdf/1710.09412.pdf
+            if random.random() < hyp['mixup']:
+                if random.random() < 0.8:
+                    img2, labels2 = load_mosaic(self, random.randint(0, len(self.labels) - 1))
+                else:
+                    img2, labels2 = load_mosaic9(self, random.randint(0, len(self.labels) - 1))
+                r = np.random.beta(8.0, 8.0)  # mixup ratio, alpha=beta=8.0
+                img = (img * r + img2 * (1 - r)).astype(np.uint8)
+                labels = np.concatenate((labels, labels2), 0)
+
+        else:
+            # Load image
+            img, (h0, w0), (h, w) = load_image(self, index)
+
+            # Letterbox
+            shape = self.batch_shapes[self.batch[index]] if self.rect else self.img_size  # final letterboxed shape
+            img, ratio, pad = letterbox(img, shape, auto=False, scaleup=self.augment)
+            shapes = (h0, w0), ((h / h0, w / w0), pad)  # for COCO mAP rescaling
+
+            labels = self.labels[index].copy()
+            if labels.size:  # normalized xywh to pixel xyxy format
+                labels[:, 1:] = xywhn2xyxy(labels[:, 1:], ratio[0] * w, ratio[1] * h, padw=pad[0], padh=pad[1])
+
+        if self.augment:
+            # Augment imagespace
+            if not mosaic:
+                img, labels = random_perspective(img, labels,
+                                                 degrees=hyp['degrees'],
+                                                 translate=hyp['translate'],
+                                                 scale=hyp['scale'],
+                                                 shear=hyp['shear'],
+                                                 perspective=hyp['perspective'])
+            
+            
+            #img, labels = self.albumentations(img, labels)
+
+            # Augment colorspace
+            augment_hsv(img, hgain=hyp['hsv_h'], sgain=hyp['hsv_s'], vgain=hyp['hsv_v'])
+
+            # Apply cutouts
+            # if random.random() < 0.9:
+            #     labels = cutout(img, labels)
+            
+            if random.random() < hyp['paste_in']:
+                sample_labels, sample_images, sample_masks = [], [], [] 
+                while len(sample_labels) < 30:
+                    sample_labels_, sample_images_, sample_masks_ = load_samples(self, random.randint(0, len(self.labels) - 1))
+                    sample_labels += sample_labels_
+                    sample_images += sample_images_
+                    sample_masks += sample_masks_
+                    #print(len(sample_labels))
+                    if len(sample_labels) == 0:
+                        break
+                labels = pastein(img, labels, sample_labels, sample_images, sample_masks)
+
+        nL = len(labels)  # number of labels
+        if nL:
+            labels[:, 1:5] = xyxy2xywh(labels[:, 1:5])  # convert xyxy to xywh
+            labels[:, [2, 4]] /= img.shape[0]  # normalized height 0-1
+            labels[:, [1, 3]] /= img.shape[1]  # normalized width 0-1
+
+        if self.augment:
+            # flip up-down
+            if random.random() < hyp['flipud']:
+                img = np.flipud(img)
+                if nL:
+                    labels[:, 2] = 1 - labels[:, 2]
+
+            # flip left-right
+            if random.random() < hyp['fliplr']:
+                img = np.fliplr(img)
+                if nL:
+                    labels[:, 1] = 1 - labels[:, 1]
+
+        labels_out = torch.zeros((nL, 6))
+        if nL:
+            labels_out[:, 1:] = torch.from_numpy(labels)
+
+        # Convert
+        img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+        img = np.ascontiguousarray(img)
+
+        return torch.from_numpy(img), labels_out, self.img_files[index], shapes
+
+    @staticmethod
+    def collate_fn(batch):
+        img, label, path, shapes = zip(*batch)  # transposed
+        for i, l in enumerate(label):
+            l[:, 0] = i  # add target image index for build_targets()
+        return torch.stack(img, 0), torch.cat(label, 0), path, shapes
+
+    @staticmethod
+    def collate_fn4(batch):
+        img, label, path, shapes = zip(*batch)  # transposed
+        n = len(shapes) // 4
+        img4, label4, path4, shapes4 = [], [], path[:n], shapes[:n]
+
+        ho = torch.tensor([[0., 0, 0, 1, 0, 0]])
+        wo = torch.tensor([[0., 0, 1, 0, 0, 0]])
+        s = torch.tensor([[1, 1, .5, .5, .5, .5]])  # scale
+        for i in range(n):  # zidane torch.zeros(16,3,720,1280)  # BCHW
+            i *= 4
+            if random.random() < 0.5:
+                im = F.interpolate(img[i].unsqueeze(0).float(), scale_factor=2., mode='bilinear', align_corners=False)[
+                    0].type(img[i].type())
+                l = label[i]
+            else:
+                im = torch.cat((torch.cat((img[i], img[i + 1]), 1), torch.cat((img[i + 2], img[i + 3]), 1)), 2)
+                l = torch.cat((label[i], label[i + 1] + ho, label[i + 2] + wo, label[i + 3] + ho + wo), 0) * s
+            img4.append(im)
+            label4.append(l)
+
+        for i, l in enumerate(label4):
+            l[:, 0] = i  # add target image index for build_targets()
+
+        return torch.stack(img4, 0), torch.cat(label4, 0), path4, shapes4
+
+
+# Ancillary functions --------------------------------------------------------------------------------------------------
+def load_image(self, index):
+    # loads 1 image from dataset, returns img, original hw, resized hw
+    img = self.imgs[index]
+    if img is None:  # not cached
+        path = self.img_files[index]
+        img = cv2.imread(path)  # BGR
+        assert img is not None, 'Image Not Found ' + path
+        h0, w0 = img.shape[:2]  # orig hw
+        r = self.img_size / max(h0, w0)  # resize image to img_size
+        if r != 1:  # always resize down, only resize up if training with augmentation
+            interp = cv2.INTER_AREA if r < 1 and not self.augment else cv2.INTER_LINEAR
+            img = cv2.resize(img, (int(w0 * r), int(h0 * r)), interpolation=interp)
+        return img, (h0, w0), img.shape[:2]  # img, hw_original, hw_resized
+    else:
+        return self.imgs[index], self.img_hw0[index], self.img_hw[index]  # img, hw_original, hw_resized
+
+
+def augment_hsv(img, hgain=0.5, sgain=0.5, vgain=0.5):
+    r = np.random.uniform(-1, 1, 3) * [hgain, sgain, vgain] + 1  # random gains
+    hue, sat, val = cv2.split(cv2.cvtColor(img, cv2.COLOR_BGR2HSV))
+    dtype = img.dtype  # uint8
+
+    x = np.arange(0, 256, dtype=np.int16)
+    lut_hue = ((x * r[0]) % 180).astype(dtype)
+    lut_sat = np.clip(x * r[1], 0, 255).astype(dtype)
+    lut_val = np.clip(x * r[2], 0, 255).astype(dtype)
+
+    img_hsv = cv2.merge((cv2.LUT(hue, lut_hue), cv2.LUT(sat, lut_sat), cv2.LUT(val, lut_val))).astype(dtype)
+    cv2.cvtColor(img_hsv, cv2.COLOR_HSV2BGR, dst=img)  # no return needed
+
+
+def hist_equalize(img, clahe=True, bgr=False):
+    # Equalize histogram on BGR image 'img' with img.shape(n,m,3) and range 0-255
+    yuv = cv2.cvtColor(img, cv2.COLOR_BGR2YUV if bgr else cv2.COLOR_RGB2YUV)
+    if clahe:
+        c = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
+        yuv[:, :, 0] = c.apply(yuv[:, :, 0])
+    else:
+        yuv[:, :, 0] = cv2.equalizeHist(yuv[:, :, 0])  # equalize Y channel histogram
+    return cv2.cvtColor(yuv, cv2.COLOR_YUV2BGR if bgr else cv2.COLOR_YUV2RGB)  # convert YUV image to RGB
+
+
+def load_mosaic(self, index):
+    # loads images in a 4-mosaic
+
+    labels4, segments4 = [], []
+    s = self.img_size
+    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
+    indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
+    for i, index in enumerate(indices):
+        # Load image
+        img, _, (h, w) = load_image(self, index)
+
+        # place img in img4
+        if i == 0:  # top left
+            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
+            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
+        elif i == 1:  # top right
+            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+        elif i == 2:  # bottom left
+            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+        elif i == 3:  # bottom right
+            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
+        padw = x1a - x1b
+        padh = y1a - y1b
+
+        # Labels
+        labels, segments = self.labels[index].copy(), self.segments[index].copy()
+        if labels.size:
+            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
+            segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
+        labels4.append(labels)
+        segments4.extend(segments)
+
+    # Concat/clip labels
+    labels4 = np.concatenate(labels4, 0)
+    for x in (labels4[:, 1:], *segments4):
+        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
+    # img4, labels4 = replicate(img4, labels4)  # replicate
+
+    # Augment
+    #img4, labels4, segments4 = remove_background(img4, labels4, segments4)
+    #sample_segments(img4, labels4, segments4, probability=self.hyp['copy_paste'])
+    img4, labels4, segments4 = copy_paste(img4, labels4, segments4, probability=self.hyp['copy_paste'])
+    img4, labels4 = random_perspective(img4, labels4, segments4,
+                                       degrees=self.hyp['degrees'],
+                                       translate=self.hyp['translate'],
+                                       scale=self.hyp['scale'],
+                                       shear=self.hyp['shear'],
+                                       perspective=self.hyp['perspective'],
+                                       border=self.mosaic_border)  # border to remove
+
+    return img4, labels4
+
+
+def load_mosaic9(self, index):
+    # loads images in a 9-mosaic
+
+    labels9, segments9 = [], []
+    s = self.img_size
+    indices = [index] + random.choices(self.indices, k=8)  # 8 additional image indices
+    for i, index in enumerate(indices):
+        # Load image
+        img, _, (h, w) = load_image(self, index)
+
+        # place img in img9
+        if i == 0:  # center
+            img9 = np.full((s * 3, s * 3, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
+            h0, w0 = h, w
+            c = s, s, s + w, s + h  # xmin, ymin, xmax, ymax (base) coordinates
+        elif i == 1:  # top
+            c = s, s - h, s + w, s
+        elif i == 2:  # top right
+            c = s + wp, s - h, s + wp + w, s
+        elif i == 3:  # right
+            c = s + w0, s, s + w0 + w, s + h
+        elif i == 4:  # bottom right
+            c = s + w0, s + hp, s + w0 + w, s + hp + h
+        elif i == 5:  # bottom
+            c = s + w0 - w, s + h0, s + w0, s + h0 + h
+        elif i == 6:  # bottom left
+            c = s + w0 - wp - w, s + h0, s + w0 - wp, s + h0 + h
+        elif i == 7:  # left
+            c = s - w, s + h0 - h, s, s + h0
+        elif i == 8:  # top left
+            c = s - w, s + h0 - hp - h, s, s + h0 - hp
+
+        padx, pady = c[:2]
+        x1, y1, x2, y2 = [max(x, 0) for x in c]  # allocate coords
+
+        # Labels
+        labels, segments = self.labels[index].copy(), self.segments[index].copy()
+        if labels.size:
+            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padx, pady)  # normalized xywh to pixel xyxy format
+            segments = [xyn2xy(x, w, h, padx, pady) for x in segments]
+        labels9.append(labels)
+        segments9.extend(segments)
+
+        # Image
+        img9[y1:y2, x1:x2] = img[y1 - pady:, x1 - padx:]  # img9[ymin:ymax, xmin:xmax]
+        hp, wp = h, w  # height, width previous
+
+    # Offset
+    yc, xc = [int(random.uniform(0, s)) for _ in self.mosaic_border]  # mosaic center x, y
+    img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
+
+    # Concat/clip labels
+    labels9 = np.concatenate(labels9, 0)
+    labels9[:, [1, 3]] -= xc
+    labels9[:, [2, 4]] -= yc
+    c = np.array([xc, yc])  # centers
+    segments9 = [x - c for x in segments9]
+
+    for x in (labels9[:, 1:], *segments9):
+        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
+    # img9, labels9 = replicate(img9, labels9)  # replicate
+
+    # Augment
+    #img9, labels9, segments9 = remove_background(img9, labels9, segments9)
+    img9, labels9, segments9 = copy_paste(img9, labels9, segments9, probability=self.hyp['copy_paste'])
+    img9, labels9 = random_perspective(img9, labels9, segments9,
+                                       degrees=self.hyp['degrees'],
+                                       translate=self.hyp['translate'],
+                                       scale=self.hyp['scale'],
+                                       shear=self.hyp['shear'],
+                                       perspective=self.hyp['perspective'],
+                                       border=self.mosaic_border)  # border to remove
+
+    return img9, labels9
+
+
+def load_samples(self, index):
+    # loads images in a 4-mosaic
+
+    labels4, segments4 = [], []
+    s = self.img_size
+    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
+    indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
+    for i, index in enumerate(indices):
+        # Load image
+        img, _, (h, w) = load_image(self, index)
+
+        # place img in img4
+        if i == 0:  # top left
+            img4 = np.full((s * 2, s * 2, img.shape[2]), 114, dtype=np.uint8)  # base image with 4 tiles
+            x1a, y1a, x2a, y2a = max(xc - w, 0), max(yc - h, 0), xc, yc  # xmin, ymin, xmax, ymax (large image)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), h - (y2a - y1a), w, h  # xmin, ymin, xmax, ymax (small image)
+        elif i == 1:  # top right
+            x1a, y1a, x2a, y2a = xc, max(yc - h, 0), min(xc + w, s * 2), yc
+            x1b, y1b, x2b, y2b = 0, h - (y2a - y1a), min(w, x2a - x1a), h
+        elif i == 2:  # bottom left
+            x1a, y1a, x2a, y2a = max(xc - w, 0), yc, xc, min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = w - (x2a - x1a), 0, w, min(y2a - y1a, h)
+        elif i == 3:  # bottom right
+            x1a, y1a, x2a, y2a = xc, yc, min(xc + w, s * 2), min(s * 2, yc + h)
+            x1b, y1b, x2b, y2b = 0, 0, min(w, x2a - x1a), min(y2a - y1a, h)
+
+        img4[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
+        padw = x1a - x1b
+        padh = y1a - y1b
+
+        # Labels
+        labels, segments = self.labels[index].copy(), self.segments[index].copy()
+        if labels.size:
+            labels[:, 1:] = xywhn2xyxy(labels[:, 1:], w, h, padw, padh)  # normalized xywh to pixel xyxy format
+            segments = [xyn2xy(x, w, h, padw, padh) for x in segments]
+        labels4.append(labels)
+        segments4.extend(segments)
+
+    # Concat/clip labels
+    labels4 = np.concatenate(labels4, 0)
+    for x in (labels4[:, 1:], *segments4):
+        np.clip(x, 0, 2 * s, out=x)  # clip when using random_perspective()
+    # img4, labels4 = replicate(img4, labels4)  # replicate
+
+    # Augment
+    #img4, labels4, segments4 = remove_background(img4, labels4, segments4)
+    sample_labels, sample_images, sample_masks = sample_segments(img4, labels4, segments4, probability=0.5)
+
+    return sample_labels, sample_images, sample_masks
+
+
+def copy_paste(img, labels, segments, probability=0.5):
+    # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
+    n = len(segments)
+    if probability and n:
+        h, w, c = img.shape  # height, width, channels
+        im_new = np.zeros(img.shape, np.uint8)
+        for j in random.sample(range(n), k=round(probability * n)):
+            l, s = labels[j], segments[j]
+            box = w - l[3], l[2], w - l[1], l[4]
+            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
+            if (ioa < 0.30).all():  # allow 30% obscuration of existing labels
+                labels = np.concatenate((labels, [[l[0], *box]]), 0)
+                segments.append(np.concatenate((w - s[:, 0:1], s[:, 1:2]), 1))
+                cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
+
+        result = cv2.bitwise_and(src1=img, src2=im_new)
+        result = cv2.flip(result, 1)  # augment segments (flip left-right)
+        i = result > 0  # pixels to replace
+        # i[:, :] = result.max(2).reshape(h, w, 1)  # act over ch
+        img[i] = result[i]  # cv2.imwrite('debug.jpg', img)  # debug
+
+    return img, labels, segments
+
+
+def remove_background(img, labels, segments):
+    # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
+    n = len(segments)
+    h, w, c = img.shape  # height, width, channels
+    im_new = np.zeros(img.shape, np.uint8)
+    img_new = np.ones(img.shape, np.uint8) * 114
+    for j in range(n):
+        cv2.drawContours(im_new, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
+
+        result = cv2.bitwise_and(src1=img, src2=im_new)
+        
+        i = result > 0  # pixels to replace
+        img_new[i] = result[i]  # cv2.imwrite('debug.jpg', img)  # debug
+
+    return img_new, labels, segments
+
+
+def sample_segments(img, labels, segments, probability=0.5):
+    # Implement Copy-Paste augmentation https://arxiv.org/abs/2012.07177, labels as nx5 np.array(cls, xyxy)
+    n = len(segments)
+    sample_labels = []
+    sample_images = []
+    sample_masks = []
+    if probability and n:
+        h, w, c = img.shape  # height, width, channels
+        for j in random.sample(range(n), k=round(probability * n)):
+            l, s = labels[j], segments[j]
+            box = l[1].astype(int).clip(0,w-1), l[2].astype(int).clip(0,h-1), l[3].astype(int).clip(0,w-1), l[4].astype(int).clip(0,h-1) 
+            
+            #print(box)
+            if (box[2] <= box[0]) or (box[3] <= box[1]):
+                continue
+            
+            sample_labels.append(l[0])
+            
+            mask = np.zeros(img.shape, np.uint8)
+            
+            cv2.drawContours(mask, [segments[j].astype(np.int32)], -1, (255, 255, 255), cv2.FILLED)
+            sample_masks.append(mask[box[1]:box[3],box[0]:box[2],:])
+            
+            result = cv2.bitwise_and(src1=img, src2=mask)
+            i = result > 0  # pixels to replace
+            mask[i] = result[i]  # cv2.imwrite('debug.jpg', img)  # debug
+            #print(box)
+            sample_images.append(mask[box[1]:box[3],box[0]:box[2],:])
+
+    return sample_labels, sample_images, sample_masks
+
+
+def replicate(img, labels):
+    # Replicate labels
+    h, w = img.shape[:2]
+    boxes = labels[:, 1:].astype(int)
+    x1, y1, x2, y2 = boxes.T
+    s = ((x2 - x1) + (y2 - y1)) / 2  # side length (pixels)
+    for i in s.argsort()[:round(s.size * 0.5)]:  # smallest indices
+        x1b, y1b, x2b, y2b = boxes[i]
+        bh, bw = y2b - y1b, x2b - x1b
+        yc, xc = int(random.uniform(0, h - bh)), int(random.uniform(0, w - bw))  # offset x, y
+        x1a, y1a, x2a, y2a = [xc, yc, xc + bw, yc + bh]
+        img[y1a:y2a, x1a:x2a] = img[y1b:y2b, x1b:x2b]  # img4[ymin:ymax, xmin:xmax]
+        labels = np.append(labels, [[labels[i, 0], x1a, y1a, x2a, y2a]], axis=0)
+
+    return img, labels
+
+
+def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True, stride=32):
+    # Resize and pad image while meeting stride-multiple constraints
+    shape = img.shape[:2]  # current shape [height, width]
+    if isinstance(new_shape, int):
+        new_shape = (new_shape, new_shape)
+
+    # Scale ratio (new / old)
+    r = min(new_shape[0] / shape[0], new_shape[1] / shape[1])
+    if not scaleup:  # only scale down, do not scale up (for better test mAP)
+        r = min(r, 1.0)
+
+    # Compute padding
+    ratio = r, r  # width, height ratios
+    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
+    dw, dh = new_shape[1] - new_unpad[0], new_shape[0] - new_unpad[1]  # wh padding
+    if auto:  # minimum rectangle
+        dw, dh = np.mod(dw, stride), np.mod(dh, stride)  # wh padding
+    elif scaleFill:  # stretch
+        dw, dh = 0.0, 0.0
+        new_unpad = (new_shape[1], new_shape[0])
+        ratio = new_shape[1] / shape[1], new_shape[0] / shape[0]  # width, height ratios
+
+    dw /= 2  # divide padding into 2 sides
+    dh /= 2
+
+    if shape[::-1] != new_unpad:  # resize
+        img = cv2.resize(img, new_unpad, interpolation=cv2.INTER_LINEAR)
+    top, bottom = int(round(dh - 0.1)), int(round(dh + 0.1))
+    left, right = int(round(dw - 0.1)), int(round(dw + 0.1))
+    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
+    return img, ratio, (dw, dh)
+
+
+def random_perspective(img, targets=(), segments=(), degrees=10, translate=.1, scale=.1, shear=10, perspective=0.0,
+                       border=(0, 0)):
+    # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
+    # targets = [cls, xyxy]
+
+    height = img.shape[0] + border[0] * 2  # shape(h,w,c)
+    width = img.shape[1] + border[1] * 2
+
+    # Center
+    C = np.eye(3)
+    C[0, 2] = -img.shape[1] / 2  # x translation (pixels)
+    C[1, 2] = -img.shape[0] / 2  # y translation (pixels)
+
+    # Perspective
+    P = np.eye(3)
+    P[2, 0] = random.uniform(-perspective, perspective)  # x perspective (about y)
+    P[2, 1] = random.uniform(-perspective, perspective)  # y perspective (about x)
+
+    # Rotation and Scale
+    R = np.eye(3)
+    a = random.uniform(-degrees, degrees)
+    # a += random.choice([-180, -90, 0, 90])  # add 90deg rotations to small rotations
+    s = random.uniform(1 - scale, 1.1 + scale)
+    # s = 2 ** random.uniform(-scale, scale)
+    R[:2] = cv2.getRotationMatrix2D(angle=a, center=(0, 0), scale=s)
+
+    # Shear
+    S = np.eye(3)
+    S[0, 1] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # x shear (deg)
+    S[1, 0] = math.tan(random.uniform(-shear, shear) * math.pi / 180)  # y shear (deg)
+
+    # Translation
+    T = np.eye(3)
+    T[0, 2] = random.uniform(0.5 - translate, 0.5 + translate) * width  # x translation (pixels)
+    T[1, 2] = random.uniform(0.5 - translate, 0.5 + translate) * height  # y translation (pixels)
+
+    # Combined rotation matrix
+    M = T @ S @ R @ P @ C  # order of operations (right to left) is IMPORTANT
+    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
+        if perspective:
+            img = cv2.warpPerspective(img, M, dsize=(width, height), borderValue=(114, 114, 114))
+        else:  # affine
+            img = cv2.warpAffine(img, M[:2], dsize=(width, height), borderValue=(114, 114, 114))
+
+    # Visualize
+    # import matplotlib.pyplot as plt
+    # ax = plt.subplots(1, 2, figsize=(12, 6))[1].ravel()
+    # ax[0].imshow(img[:, :, ::-1])  # base
+    # ax[1].imshow(img2[:, :, ::-1])  # warped
+
+    # Transform label coordinates
+    n = len(targets)
+    if n:
+        use_segments = any(x.any() for x in segments)
+        new = np.zeros((n, 4))
+        if use_segments:  # warp segments
+            segments = resample_segments(segments)  # upsample
+            for i, segment in enumerate(segments):
+                xy = np.ones((len(segment), 3))
+                xy[:, :2] = segment
+                xy = xy @ M.T  # transform
+                xy = xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]  # perspective rescale or affine
+
+                # clip
+                new[i] = segment2box(xy, width, height)
+
+        else:  # warp boxes
+            xy = np.ones((n * 4, 3))
+            xy[:, :2] = targets[:, [1, 2, 3, 4, 1, 4, 3, 2]].reshape(n * 4, 2)  # x1y1, x2y2, x1y2, x2y1
+            xy = xy @ M.T  # transform
+            xy = (xy[:, :2] / xy[:, 2:3] if perspective else xy[:, :2]).reshape(n, 8)  # perspective rescale or affine
+
+            # create new boxes
+            x = xy[:, [0, 2, 4, 6]]
+            y = xy[:, [1, 3, 5, 7]]
+            new = np.concatenate((x.min(1), y.min(1), x.max(1), y.max(1))).reshape(4, n).T
+
+            # clip
+            new[:, [0, 2]] = new[:, [0, 2]].clip(0, width)
+            new[:, [1, 3]] = new[:, [1, 3]].clip(0, height)
+
+        # filter candidates
+        i = box_candidates(box1=targets[:, 1:5].T * s, box2=new.T, area_thr=0.01 if use_segments else 0.10)
+        targets = targets[i]
+        targets[:, 1:5] = new[i]
+
+    return img, targets
+
+
+def box_candidates(box1, box2, wh_thr=2, ar_thr=20, area_thr=0.1, eps=1e-16):  # box1(4,n), box2(4,n)
+    # Compute candidate boxes: box1 before augment, box2 after augment, wh_thr (pixels), aspect_ratio_thr, area_ratio
+    w1, h1 = box1[2] - box1[0], box1[3] - box1[1]
+    w2, h2 = box2[2] - box2[0], box2[3] - box2[1]
+    ar = np.maximum(w2 / (h2 + eps), h2 / (w2 + eps))  # aspect ratio
+    return (w2 > wh_thr) & (h2 > wh_thr) & (w2 * h2 / (w1 * h1 + eps) > area_thr) & (ar < ar_thr)  # candidates
+
+
+def bbox_ioa(box1, box2):
+    # Returns the intersection over box2 area given box1, box2. box1 is 4, box2 is nx4. boxes are x1y1x2y2
+    box2 = box2.transpose()
+
+    # Get the coordinates of bounding boxes
+    b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+    b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+
+    # Intersection area
+    inter_area = (np.minimum(b1_x2, b2_x2) - np.maximum(b1_x1, b2_x1)).clip(0) * \
+                 (np.minimum(b1_y2, b2_y2) - np.maximum(b1_y1, b2_y1)).clip(0)
+
+    # box2 area
+    box2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1) + 1e-16
+
+    # Intersection over box2 area
+    return inter_area / box2_area
+    
+
+def cutout(image, labels):
+    # Applies image cutout augmentation https://arxiv.org/abs/1708.04552
+    h, w = image.shape[:2]
+
+    # create random masks
+    scales = [0.5] * 1 + [0.25] * 2 + [0.125] * 4 + [0.0625] * 8 + [0.03125] * 16  # image size fraction
+    for s in scales:
+        mask_h = random.randint(1, int(h * s))
+        mask_w = random.randint(1, int(w * s))
+
+        # box
+        xmin = max(0, random.randint(0, w) - mask_w // 2)
+        ymin = max(0, random.randint(0, h) - mask_h // 2)
+        xmax = min(w, xmin + mask_w)
+        ymax = min(h, ymin + mask_h)
+
+        # apply random color mask
+        image[ymin:ymax, xmin:xmax] = [random.randint(64, 191) for _ in range(3)]
+
+        # return unobscured labels
+        if len(labels) and s > 0.03:
+            box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
+            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area
+            labels = labels[ioa < 0.60]  # remove >60% obscured labels
+
+    return labels
+    
+
+def pastein(image, labels, sample_labels, sample_images, sample_masks):
+    # Applies image cutout augmentation https://arxiv.org/abs/1708.04552
+    h, w = image.shape[:2]
+
+    # create random masks
+    scales = [0.75] * 2 + [0.5] * 4 + [0.25] * 4 + [0.125] * 4 + [0.0625] * 6  # image size fraction
+    for s in scales:
+        if random.random() < 0.2:
+            continue
+        mask_h = random.randint(1, int(h * s))
+        mask_w = random.randint(1, int(w * s))
+
+        # box
+        xmin = max(0, random.randint(0, w) - mask_w // 2)
+        ymin = max(0, random.randint(0, h) - mask_h // 2)
+        xmax = min(w, xmin + mask_w)
+        ymax = min(h, ymin + mask_h)   
+        
+        box = np.array([xmin, ymin, xmax, ymax], dtype=np.float32)
+        if len(labels):
+            ioa = bbox_ioa(box, labels[:, 1:5])  # intersection over area     
+        else:
+            ioa = np.zeros(1)
+        
+        if (ioa < 0.30).all() and len(sample_labels) and (xmax > xmin+20) and (ymax > ymin+20):  # allow 30% obscuration of existing labels
+            sel_ind = random.randint(0, len(sample_labels)-1)
+            #print(len(sample_labels))
+            #print(sel_ind)
+            #print((xmax-xmin, ymax-ymin))
+            #print(image[ymin:ymax, xmin:xmax].shape)
+            #print([[sample_labels[sel_ind], *box]])
+            #print(labels.shape)
+            hs, ws, cs = sample_images[sel_ind].shape
+            r_scale = min((ymax-ymin)/hs, (xmax-xmin)/ws)
+            r_w = int(ws*r_scale)
+            r_h = int(hs*r_scale)
+            
+            if (r_w > 10) and (r_h > 10):
+                r_mask = cv2.resize(sample_masks[sel_ind], (r_w, r_h))
+                r_image = cv2.resize(sample_images[sel_ind], (r_w, r_h))
+                temp_crop = image[ymin:ymin+r_h, xmin:xmin+r_w]
+                m_ind = r_mask > 0
+                if m_ind.astype(np.int32).sum() > 60:
+                    temp_crop[m_ind] = r_image[m_ind]
+                    #print(sample_labels[sel_ind])
+                    #print(sample_images[sel_ind].shape)
+                    #print(temp_crop.shape)
+                    box = np.array([xmin, ymin, xmin+r_w, ymin+r_h], dtype=np.float32)
+                    if len(labels):
+                        labels = np.concatenate((labels, [[sample_labels[sel_ind], *box]]), 0)
+                    else:
+                        labels = np.array([[sample_labels[sel_ind], *box]])
+                              
+                    image[ymin:ymin+r_h, xmin:xmin+r_w] = temp_crop
+
+    return labels
+
+class Albumentations:
+    # YOLOv5 Albumentations class (optional, only used if package is installed)
+    def __init__(self):
+        self.transform = None
+        import albumentations as A
+
+        self.transform = A.Compose([
+            A.CLAHE(p=0.01),
+            A.RandomBrightnessContrast(brightness_limit=0.2, contrast_limit=0.2, p=0.01),
+            A.RandomGamma(gamma_limit=[80, 120], p=0.01),
+            A.Blur(p=0.01),
+            A.MedianBlur(p=0.01),
+            A.ToGray(p=0.01),
+            A.ImageCompression(quality_lower=75, p=0.01),],
+            bbox_params=A.BboxParams(format='pascal_voc', label_fields=['class_labels']))
+
+            #logging.info(colorstr('albumentations: ') + ', '.join(f'{x}' for x in self.transform.transforms if x.p))
+
+    def __call__(self, im, labels, p=1.0):
+        if self.transform and random.random() < p:
+            new = self.transform(image=im, bboxes=labels[:, 1:], class_labels=labels[:, 0])  # transformed
+            im, labels = new['image'], np.array([[c, *b] for c, b in zip(new['class_labels'], new['bboxes'])])
+        return im, labels
+
+
+def create_folder(path='./new'):
+    # Create folder
+    if os.path.exists(path):
+        shutil.rmtree(path)  # delete output folder
+    os.makedirs(path)  # make new output folder
+
+
+def flatten_recursive(path='../coco'):
+    # Flatten a recursive directory by bringing all files to top level
+    new_path = Path(path + '_flat')
+    create_folder(new_path)
+    for file in tqdm(glob.glob(str(Path(path)) + '/**/*.*', recursive=True)):
+        shutil.copyfile(file, new_path / Path(file).name)
+
+
+def extract_boxes(path='../coco/'):  # from utils.datasets import *; extract_boxes('../coco128')
+    # Convert detection dataset into classification dataset, with one directory per class
+
+    path = Path(path)  # images dir
+    shutil.rmtree(path / 'classifier') if (path / 'classifier').is_dir() else None  # remove existing
+    files = list(path.rglob('*.*'))
+    n = len(files)  # number of files
+    for im_file in tqdm(files, total=n):
+        if im_file.suffix[1:] in img_formats:
+            # image
+            im = cv2.imread(str(im_file))[..., ::-1]  # BGR to RGB
+            h, w = im.shape[:2]
+
+            # labels
+            lb_file = Path(img2label_paths([str(im_file)])[0])
+            if Path(lb_file).exists():
+                with open(lb_file, 'r') as f:
+                    lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels
+
+                for j, x in enumerate(lb):
+                    c = int(x[0])  # class
+                    f = (path / 'classifier') / f'{c}' / f'{path.stem}_{im_file.stem}_{j}.jpg'  # new filename
+                    if not f.parent.is_dir():
+                        f.parent.mkdir(parents=True)
+
+                    b = x[1:] * [w, h, w, h]  # box
+                    # b[2:] = b[2:].max()  # rectangle to square
+                    b[2:] = b[2:] * 1.2 + 3  # pad
+                    b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
+
+                    b[[0, 2]] = np.clip(b[[0, 2]], 0, w)  # clip boxes outside of image
+                    b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
+                    assert cv2.imwrite(str(f), im[b[1]:b[3], b[0]:b[2]]), f'box failure in {f}'
+
+
+def autosplit(path='../coco', weights=(0.9, 0.1, 0.0), annotated_only=False):
+    """ Autosplit a dataset into train/val/test splits and save path/autosplit_*.txt files
+    Usage: from utils.datasets import *; autosplit('../coco')
+    Arguments
+        path:           Path to images directory
+        weights:        Train, val, test weights (list)
+        annotated_only: Only use images with an annotated txt file
+    """
+    path = Path(path)  # images dir
+    files = sum([list(path.rglob(f"*.{img_ext}")) for img_ext in img_formats], [])  # image files only
+    n = len(files)  # number of files
+    indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
+
+    txt = ['autosplit_train.txt', 'autosplit_val.txt', 'autosplit_test.txt']  # 3 txt files
+    [(path / x).unlink() for x in txt if (path / x).exists()]  # remove existing
+
+    print(f'Autosplitting images from {path}' + ', using *.txt labeled images only' * annotated_only)
+    for i, img in tqdm(zip(indices, files), total=n):
+        if not annotated_only or Path(img2label_paths([str(img)])[0]).exists():  # check label
+            with open(path / txt[i], 'a') as f:
+                f.write(str(img) + '\n')  # add image to txt file
+    
+    
+def load_segmentations(self, index):
+    key = '/work/handsomejw66/coco17/' + self.img_files[index]
+    #print(key)
+    # /work/handsomejw66/coco17/
+    return self.segs[key]