init

.gitignore

@@ -0,0 +1,4 @@
+.ipynb_checkpoints/*
+__pycache__/
+*.bin
+.vscode/

app.py

@@ -0,0 +1,246 @@
+import json
+from functools import partial
+from pathlib import Path
+
+import gradio as gr
+from PIL import Image
+import torch
+import numpy as np
+from gradio_image_prompter import ImagePrompter
+import sys
+sys.path.append("..")
+
+from inference import ModelFactory
+from face import FaceAlgo
+from sam_everything import SamAnything
+
+
+components = {}
+
+params = {
+    "algo_type": None,
+    "input_image":None
+}
+
+
+def gradio(*keys):
+    if len(keys) == 1 and type(keys[0]) in [list, tuple]:
+        keys = keys[0]
+
+    return [components[k] for k in keys]
+
+
+algo_map = {
+    "目标检测":"detect",
+    "单阶段目标检测":"onestep_detect",
+    "分类":"classification",
+    "特征提取":"feature",
+    "语义分割":"semantic",
+    "实例分割":"instance",
+    "关键点检测":"keypoint",
+    "全景分割":"panoptic",
+    "YOLO":"yolo",
+}
+
+face_algo_map = {
+    "人脸检测":"detect",
+    "人脸识别":"recognize",
+    "人脸比对":"compare",
+    "特征提取":"feature",
+    "属性分析":"attr",
+}
+
+def create_ui():
+    with gr.Blocks() as demo:
+        with gr.Tab("基础算法"):
+            with gr.Row():
+                with gr.Column(scale=2):
+                    components["algo_type"] = gr.Dropdown(
+                                    ["目标检测","单阶段目标检测", "分类", "特征提取","语义分割","实例分割","关键点检测","全景分割","YOLO"],value="全景分割",
+                                    label="算法类别",interactive=True
+                            )
+                with gr.Column(scale=2):
+                    components["submit_btn"] = gr.Button(value="解析")
+            with gr.Row():
+                with gr.Column(scale=2):
+                    with gr.Row(elem_id='audio-container'):
+                        with gr.Group():
+                            components["image_input"] = gr.Image(type="pil",elem_id='image-input',label='输入')
+                with gr.Column(scale=2):
+                    with gr.Row():
+                        with gr.Group():
+                            components["image_output"] = gr.Image(type="pil",elem_id='image-output',label='输出',interactive=False)
+
+            with gr.Row():
+                with gr.Group():
+                    components["result_output"] = gr.JSON(label="推理结果")
+
+        with gr.Tab("人脸算法"):   
+            with gr.Row():
+                with gr.Column(scale=2):
+                    components["face_type"] = gr.Dropdown(
+                                    ["人脸检测","人脸识别", "人脸比对", "特征提取","属性分析"],value="人脸检测",
+                                    label="算法类别",interactive=True
+                            )
+                with gr.Column(scale=2):
+                    components["face_submit_btn"] = gr.Button(value="解析")
+            with gr.Row():
+                with gr.Column(scale=2):
+                    with gr.Row(elem_id=''):
+                        with gr.Group():
+                            components["face_input"] = gr.Gallery(elem_id='face-input',label='输入',columns=2,type="pil")
+                with gr.Column(scale=2):
+                    with gr.Row():
+                        with gr.Group():
+                            components["face_image_output"] = gr.Gallery(elem_id='face_image_output',label='输出',columns=2,interactive=False)
+
+            with gr.Row():
+                with gr.Group():
+                    components["face_output"] = gr.JSON(label="推理结果")
+        with gr.Tab("SAM everything"): 
+            with gr.Row():
+                with gr.Column(scale=2):
+                    components["sam_submit_btn"] = gr.Button(value="解析")
+            with gr.Row():
+                with gr.Column(scale=2):
+                    with gr.Group():
+                        # components["sam_input"] = gr.ImageEditor(elem_id='sam-input',label='输入',type="pil")
+                        components["sam_input"] = ImagePrompter(elem_id='sam-input',label='输入',type="pil")
+                with gr.Column(scale=2):
+                    with gr.Group():
+                        components["sam_output"] = gr.Gallery(elem_id='sam_output',label='输出',columns=1,interactive=False)
+
+        # with gr.Tab("OCR"):  
+
+        create_event_handlers()
+    return demo
+
+
+def create_event_handlers():
+    params["algo_type"] = gr.State("全景分割")
+    params["input_image"] = gr.State()
+    params["face_type"] = gr.State("人脸检测")
+    
+
+    components["image_input"].upload(
+        lambda x: x, gradio('image_input'), params["input_image"]
+    )
+    
+    components["algo_type"].change(
+        lambda x: x, gradio('algo_type'), params["algo_type"]
+    )
+
+    components["submit_btn"].click(
+        do_refernce,gradio('algo_type','image_input'),gradio("result_output",'image_output')
+    )
+
+    components["face_type"].change(
+        ui_by_facetype, gradio('face_type'), params["face_type"]
+    )
+
+    components["face_submit_btn"].click(
+        do_face_refernce,gradio('face_type','face_input'),gradio("face_output",'face_image_output')
+    )
+
+    # components["sam_input"].upload(
+    #     do_sam_everything,gradio('sam_input'),gradio("sam_output")
+    # )
+
+    # components["sam_input"].change(
+    #     do_sam_everything,gradio('sam_input'),gradio("sam_output")
+    # )
+
+    components["sam_submit_btn"].click(
+        do_sam_everything,gradio('sam_input'),gradio("sam_output")
+    )
+
+def do_refernce(algo_type,input_image):
+# def do_refernce():
+    print("input image",input_image)
+    print(algo_type)
+
+    if input_image is None:
+        gr.Warning('请上传图片')
+        return None
+    algo_type = algo_map[algo_type]
+    factory = ModelFactory()
+    output,output_image = factory.predict(pil_image=input_image,task_type=algo_type)
+    if output_image is None or len(output_image) == 0:
+        return output,None
+    print("output image",output_image[0])
+    return output,output_image[0]
+
+def ui_by_facetype(face_type):
+    print("ui_by_facetype",face_type)
+
+
+def do_face_refernce(algo_type,input_images):
+    print("input image",input_images)
+    print(algo_type)
+
+    if input_images is None:
+        gr.Warning('请上传图片')
+        return None,None
+    
+    input1 = input_images[0][0]
+    input2 = None
+    algo_type = face_algo_map[algo_type]
+    if algo_type == "compare" and len(input_images) >=2:
+        input2 = input_images[1][0]
+    elif algo_type == "compare" and len(input_images) < 2:
+        gr.Warning('请上传两张图片')    
+        return None,None
+
+    m = FaceAlgo()  # pragma: no cover
+    out,faces = m.predict(pil_image=input1,pil_image1=input2,algo_type=algo_type)
+
+    return out,faces
+
+def do_sam_everything(im):
+    sam_anything = SamAnything()
+    print(im)
+    image_pil = im['image']
+    points = im['points']
+    images = None
+    if points is None or len(points) == 0:
+        _, images = sam_anything.seg_all(image_pil)
+    else:
+        point_coords = []
+        box = None
+        for item in points:
+            if item[2] == 1:
+                # 点类型
+                point_coords.append([item[0],item[1]])
+            else:
+                # box类型,只使用最后一个box
+                box = [item[0],item[1],item[3],item[4]]
+                box = np.array(box)
+        
+        if box is not None:
+            _, images = sam_anything.seg_with_promp(image_pil,box=box)
+        else:
+            coords = np.array(point_coords)
+            print("point_coords:",coords.shape)
+            _, images = sam_anything.seg_with_promp(image_pil,point_coords=coords)
+        
+    return images
+
+def point_to_mask(pil_image):
+    # 遍历每个像素
+    width, height = pil_image.size
+    print(width, height)
+    points_list = []
+    for x in range(width):
+        for y in range(height):
+            # 获取像素的RGB值
+            pix_val = pil_image.getpixel((x, y))
+            if pix_val[0] != 0 and pix_val[1] != 0 and pix_val[2] != 0:
+                points_list.append((x, y))
+    points_array = np.array(points_list)
+    points_array_reshaped = points_array.reshape(-1, 2)
+    return points_array_reshaped
+
+if __name__ == "__main__":
+    demo = create_ui()
+    # demo.launch(server_name="10.151.124.137")
+    demo.launch()

configs/Base-RCNN-C4.yaml

@@ -0,0 +1,18 @@
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  RPN:
+    PRE_NMS_TOPK_TEST: 6000
+    POST_NMS_TOPK_TEST: 1000
+  ROI_HEADS:
+    NAME: "Res5ROIHeads"
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

configs/Base-RCNN-DilatedC5.yaml

@@ -0,0 +1,31 @@
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  RESNETS:
+    OUT_FEATURES: ["res5"]
+    RES5_DILATION: 2
+  RPN:
+    IN_FEATURES: ["res5"]
+    PRE_NMS_TOPK_TEST: 6000
+    POST_NMS_TOPK_TEST: 1000
+  ROI_HEADS:
+    NAME: "StandardROIHeads"
+    IN_FEATURES: ["res5"]
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+  ROI_MASK_HEAD:
+    NAME: "MaskRCNNConvUpsampleHead"
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

configs/Base-RCNN-FPN.yaml

@@ -0,0 +1,42 @@
+MODEL:
+  META_ARCHITECTURE: "GeneralizedRCNN"
+  BACKBONE:
+    NAME: "build_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res2", "res3", "res4", "res5"]
+  FPN:
+    IN_FEATURES: ["res2", "res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: [[32], [64], [128], [256], [512]]  # One size for each in feature map
+    ASPECT_RATIOS: [[0.5, 1.0, 2.0]]  # Three aspect ratios (same for all in feature maps)
+  RPN:
+    IN_FEATURES: ["p2", "p3", "p4", "p5", "p6"]
+    PRE_NMS_TOPK_TRAIN: 2000  # Per FPN level
+    PRE_NMS_TOPK_TEST: 1000  # Per FPN level
+    # Detectron1 uses 2000 proposals per-batch,
+    # (See "modeling/rpn/rpn_outputs.py" for details of this legacy issue)
+    # which is approximately 1000 proposals per-image since the default batch size for FPN is 2.
+    POST_NMS_TOPK_TRAIN: 1000
+    POST_NMS_TOPK_TEST: 1000
+  ROI_HEADS:
+    NAME: "StandardROIHeads"
+    IN_FEATURES: ["p2", "p3", "p4", "p5"]
+  ROI_BOX_HEAD:
+    NAME: "FastRCNNConvFCHead"
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+  ROI_MASK_HEAD:
+    NAME: "MaskRCNNConvUpsampleHead"
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.02
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

configs/Base-RetinaNet.yaml

@@ -0,0 +1,25 @@
+MODEL:
+  META_ARCHITECTURE: "RetinaNet"
+  BACKBONE:
+    NAME: "build_retinanet_resnet_fpn_backbone"
+  RESNETS:
+    OUT_FEATURES: ["res3", "res4", "res5"]
+  ANCHOR_GENERATOR:
+    SIZES: !!python/object/apply:eval ["[[x, x * 2**(1.0/3), x * 2**(2.0/3) ] for x in [32, 64, 128, 256, 512 ]]"]
+  FPN:
+    IN_FEATURES: ["res3", "res4", "res5"]
+  RETINANET:
+    IOU_THRESHOLDS: [0.4, 0.5]
+    IOU_LABELS: [0, -1, 1]
+    SMOOTH_L1_LOSS_BETA: 0.0
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  TEST: ("coco_2017_val",)
+SOLVER:
+  IMS_PER_BATCH: 16
+  BASE_LR: 0.01  # Note that RetinaNet uses a different default learning rate
+  STEPS: (60000, 80000)
+  MAX_ITER: 90000
+INPUT:
+  MIN_SIZE_TRAIN: (640, 672, 704, 736, 768, 800)
+VERSION: 2

configs/COCO-Detection/fast_rcnn_R_50_FPN_1x.yaml

@@ -0,0 +1,17 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  LOAD_PROPOSALS: True
+  RESNETS:
+    DEPTH: 50
+  PROPOSAL_GENERATOR:
+    NAME: "PrecomputedProposals"
+DATASETS:
+  TRAIN: ("coco_2017_train",)
+  PROPOSAL_FILES_TRAIN: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_train_box_proposals_21bc3a.pkl", )
+  TEST: ("coco_2017_val",)
+  PROPOSAL_FILES_TEST: ("detectron2://COCO-Detection/rpn_R_50_FPN_1x/137258492/coco_2017_val_box_proposals_ee0dad.pkl", )
+DATALOADER:
+  # proposals are part of the dataset_dicts, and take a lot of RAM
+  NUM_WORKERS: 2

configs/COCO-Detection/faster_rcnn_R_101_C4_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/faster_rcnn_R_101_DC5_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/faster_rcnn_R_101_FPN_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/faster_rcnn_R_50_C4_1x.yaml

@@ -0,0 +1,6 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50

configs/COCO-Detection/faster_rcnn_R_50_C4_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/faster_rcnn_R_50_DC5_1x.yaml

@@ -0,0 +1,6 @@
+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50

configs/COCO-Detection/faster_rcnn_R_50_DC5_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/faster_rcnn_R_50_FPN_1x.yaml

@@ -0,0 +1,6 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50

configs/COCO-Detection/faster_rcnn_R_50_FPN_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/faster_rcnn_X_101_32x8d_FPN_3x.yaml

@@ -0,0 +1,13 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  MASK_ON: False
+  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
+  PIXEL_STD: [57.375, 57.120, 58.395]
+  RESNETS:
+    STRIDE_IN_1X1: False  # this is a C2 model
+    NUM_GROUPS: 32
+    WIDTH_PER_GROUP: 8
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/fcos_R_50_FPN_1x.py

@@ -0,0 +1,11 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.fcos import model
+from ..common.train import train
+
+dataloader.train.mapper.use_instance_mask = False
+optimizer.lr = 0.01
+
+model.backbone.bottom_up.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

configs/COCO-Detection/retinanet_R_101_FPN_3x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "../Base-RetinaNet.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/retinanet_R_50_FPN_1x.py

@@ -0,0 +1,11 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.retinanet import model
+from ..common.train import train
+
+dataloader.train.mapper.use_instance_mask = False
+model.backbone.bottom_up.freeze_at = 2
+optimizer.lr = 0.01
+
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

configs/COCO-Detection/retinanet_R_50_FPN_1x.yaml

@@ -0,0 +1,5 @@
+_BASE_: "../Base-RetinaNet.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50

configs/COCO-Detection/retinanet_R_50_FPN_3x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "../Base-RetinaNet.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Detection/rpn_R_50_C4_1x.yaml

@@ -0,0 +1,10 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  META_ARCHITECTURE: "ProposalNetwork"
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+  RPN:
+    PRE_NMS_TOPK_TEST: 12000
+    POST_NMS_TOPK_TEST: 2000

configs/COCO-Detection/rpn_R_50_FPN_1x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  META_ARCHITECTURE: "ProposalNetwork"
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: False
+  RESNETS:
+    DEPTH: 50
+  RPN:
+    POST_NMS_TOPK_TEST: 2000

configs/COCO-InstanceSegmentation/mask_rcnn_R_101_C4_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_R_101_DC5_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_R_101_FPN_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.py

@@ -0,0 +1,8 @@
+from ..common.train import train
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_c4 import model
+
+model.backbone.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_1x.yaml

@@ -0,0 +1,6 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_C4_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-C4.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_1x.yaml

@@ -0,0 +1,6 @@
+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_DC5_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-DilatedC5.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.py

@@ -0,0 +1,8 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_fpn import model
+from ..common.train import train
+
+model.backbone.bottom_up.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x.yaml

@@ -0,0 +1,6 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_1x_giou.yaml

@@ -0,0 +1,12 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+  RPN:
+    BBOX_REG_LOSS_TYPE: "giou"
+    BBOX_REG_LOSS_WEIGHT: 2.0
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: "giou"
+    BBOX_REG_LOSS_WEIGHT: 10.0

configs/COCO-InstanceSegmentation/mask_rcnn_R_50_FPN_3x.yaml

@@ -0,0 +1,9 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  MASK_ON: True
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_X_101_32x8d_FPN_3x.yaml

@@ -0,0 +1,13 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  MASK_ON: True
+  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
+  PIXEL_STD: [57.375, 57.120, 58.395]
+  RESNETS:
+    STRIDE_IN_1X1: False  # this is a C2 model
+    NUM_GROUPS: 32
+    WIDTH_PER_GROUP: 8
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-InstanceSegmentation/mask_rcnn_regnetx_4gf_dds_fpn_1x.py

@@ -0,0 +1,34 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_fpn import model
+from ..common.train import train
+
+from detectron2.config import LazyCall as L
+from detectron2.modeling.backbone import RegNet
+from detectron2.modeling.backbone.regnet import SimpleStem, ResBottleneckBlock
+
+
+# Replace default ResNet with RegNetX-4GF from the DDS paper. Config source:
+# https://github.com/facebookresearch/pycls/blob/2c152a6e5d913e898cca4f0a758f41e6b976714d/configs/dds_baselines/regnetx/RegNetX-4.0GF_dds_8gpu.yaml#L4-L9  # noqa
+model.backbone.bottom_up = L(RegNet)(
+    stem_class=SimpleStem,
+    stem_width=32,
+    block_class=ResBottleneckBlock,
+    depth=23,
+    w_a=38.65,
+    w_0=96,
+    w_m=2.43,
+    group_width=40,
+    freeze_at=2,
+    norm="FrozenBN",
+    out_features=["s1", "s2", "s3", "s4"],
+)
+model.pixel_std = [57.375, 57.120, 58.395]
+
+optimizer.weight_decay = 5e-5
+train.init_checkpoint = (
+    "https://dl.fbaipublicfiles.com/pycls/dds_baselines/160906383/RegNetX-4.0GF_dds_8gpu.pyth"
+)
+# RegNets benefit from enabling cudnn benchmark mode
+train.cudnn_benchmark = True

configs/COCO-InstanceSegmentation/mask_rcnn_regnety_4gf_dds_fpn_1x.py

@@ -0,0 +1,35 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco import dataloader
+from ..common.models.mask_rcnn_fpn import model
+from ..common.train import train
+
+from detectron2.config import LazyCall as L
+from detectron2.modeling.backbone import RegNet
+from detectron2.modeling.backbone.regnet import SimpleStem, ResBottleneckBlock
+
+
+# Replace default ResNet with RegNetY-4GF from the DDS paper. Config source:
+# https://github.com/facebookresearch/pycls/blob/2c152a6e5d913e898cca4f0a758f41e6b976714d/configs/dds_baselines/regnety/RegNetY-4.0GF_dds_8gpu.yaml#L4-L10  # noqa
+model.backbone.bottom_up = L(RegNet)(
+    stem_class=SimpleStem,
+    stem_width=32,
+    block_class=ResBottleneckBlock,
+    depth=22,
+    w_a=31.41,
+    w_0=96,
+    w_m=2.24,
+    group_width=64,
+    se_ratio=0.25,
+    freeze_at=2,
+    norm="FrozenBN",
+    out_features=["s1", "s2", "s3", "s4"],
+)
+model.pixel_std = [57.375, 57.120, 58.395]
+
+optimizer.weight_decay = 5e-5
+train.init_checkpoint = (
+    "https://dl.fbaipublicfiles.com/pycls/dds_baselines/160906838/RegNetY-4.0GF_dds_8gpu.pyth"
+)
+# RegNets benefit from enabling cudnn benchmark mode
+train.cudnn_benchmark = True

configs/COCO-Keypoints/Base-Keypoint-RCNN-FPN.yaml

@@ -0,0 +1,15 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  KEYPOINT_ON: True
+  ROI_HEADS:
+    NUM_CLASSES: 1
+  ROI_BOX_HEAD:
+    SMOOTH_L1_BETA: 0.5  # Keypoint AP degrades (though box AP improves) when using plain L1 loss
+  RPN:
+    # Detectron1 uses 2000 proposals per-batch, but this option is per-image in detectron2.
+    # 1000 proposals per-image is found to hurt box AP.
+    # Therefore we increase it to 1500 per-image.
+    POST_NMS_TOPK_TRAIN: 1500
+DATASETS:
+  TRAIN: ("keypoints_coco_2017_train",)
+  TEST: ("keypoints_coco_2017_val",)

configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.py

@@ -0,0 +1,8 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco_keypoint import dataloader
+from ..common.models.keypoint_rcnn_fpn import model
+from ..common.train import train
+
+model.backbone.bottom_up.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_1x.yaml

@@ -0,0 +1,5 @@
+_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50

configs/COCO-Keypoints/keypoint_rcnn_R_50_FPN_3x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-Keypoints/keypoint_rcnn_X_101_32x8d_FPN_3x.yaml

@@ -0,0 +1,12 @@
+_BASE_: "Base-Keypoint-RCNN-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/FAIR/X-101-32x8d.pkl"
+  PIXEL_STD: [57.375, 57.120, 58.395]
+  RESNETS:
+    STRIDE_IN_1X1: False  # this is a C2 model
+    NUM_GROUPS: 32
+    WIDTH_PER_GROUP: 8
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-PanopticSegmentation/Base-Panoptic-FPN.yaml

@@ -0,0 +1,11 @@
+_BASE_: "../Base-RCNN-FPN.yaml"
+MODEL:
+  META_ARCHITECTURE: "PanopticFPN"
+  MASK_ON: True
+  SEM_SEG_HEAD:
+    LOSS_WEIGHT: 0.5
+DATASETS:
+  TRAIN: ("coco_2017_train_panoptic_separated",)
+  TEST: ("coco_2017_val_panoptic_separated",)
+DATALOADER:
+  FILTER_EMPTY_ANNOTATIONS: False

configs/COCO-PanopticSegmentation/panoptic_fpn_R_101_3x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-Panoptic-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-101.pkl"
+  RESNETS:
+    DEPTH: 101
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000

configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.py

@@ -0,0 +1,8 @@
+from ..common.optim import SGD as optimizer
+from ..common.coco_schedule import lr_multiplier_1x as lr_multiplier
+from ..common.data.coco_panoptic_separated import dataloader
+from ..common.models.panoptic_fpn import model
+from ..common.train import train
+
+model.backbone.bottom_up.freeze_at = 2
+train.init_checkpoint = "detectron2://ImageNetPretrained/MSRA/R-50.pkl"

configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_1x.yaml

@@ -0,0 +1,5 @@
+_BASE_: "Base-Panoptic-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50

configs/COCO-PanopticSegmentation/panoptic_fpn_R_50_3x.yaml

@@ -0,0 +1,8 @@
+_BASE_: "Base-Panoptic-FPN.yaml"
+MODEL:
+  WEIGHTS: "detectron2://ImageNetPretrained/MSRA/R-50.pkl"
+  RESNETS:
+    DEPTH: 50
+SOLVER:
+  STEPS: (210000, 250000)
+  MAX_ITER: 270000