Hugging Face's logo

Spaces:
kai1217
/
YOLOv7_demo
Sleeping

App Files Community
YOLOv7_demo
File size: 7,023 Bytes 
f935b99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
 
from fastai.vision.all import *
from io import BytesIO
import requests
import streamlit as st

import numpy as np
import torch
import time
import cv2
from numpy import random
from streamlit_image_select import image_select
from models.experimental import attempt_load
from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
from utils.plots import plot_one_box

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 detect_modify(img0, model, conf=0.4, imgsz=640, conf_thres = 0.25, iou_thres=0.45):
    st.image(img0, caption="Your image", use_column_width=True)

    stride = int(model.stride.max())  # model stride
    imgsz = check_img_size(imgsz, s=stride)  # check img_size

    # Padded resize
    img0 = cv2.cvtColor(np.asarray(img0), cv2.COLOR_RGB2BGR)
    img = letterbox(img0, imgsz, stride=stride)[0]
    # Convert
    img = img[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
    img = np.ascontiguousarray(img)

    
    # Get names and colors
    names = model.module.names if hasattr(model, 'module') else model.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]

    # Run inference
    old_img_w = old_img_h = imgsz
    old_img_b = 1

    t0 = time.time()
    img = torch.from_numpy(img).to(device)
    # img /= 255.0  # 0 - 255 to 0.0 - 1.0
    img = img/255.0
    if img.ndimension() == 3:
        img = img.unsqueeze(0)

    # Inference
    # t1 = time_synchronized()
    with torch.no_grad():   # Calculating gradients would cause a GPU memory leak
        pred = model(img)[0]
    # t2 = time_synchronized()

    # Apply NMS
    pred = non_max_suppression(pred, conf_thres, iou_thres)
    # t3 = time_synchronized()

    # Process detections
    # for i, det in enumerate(pred):  # detections per image
        
    gn = torch.tensor(img0.shape)[[1, 0, 1, 0]]  # normalization gain whwh

    det = pred[0]
    if len(det):
        # Rescale boxes from img_size to im0 size
        det[:, :4] = scale_coords(img.shape[2:], det[:, :4], img0.shape).round()

        # Print results
        s = ''
        for c in det[:, -1].unique():
            n = (det[:, -1] == c).sum()  # detections per class
            s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string

        # Write results
        for *xyxy, conf, cls in reversed(det):
            label = f'{names[int(cls)]} {conf:.2f}'
            plot_one_box(xyxy, img0, label=label, color=colors[int(cls)], line_thickness=1)

    f"""
    ### Prediction result:
    """
    img0 = cv2.cvtColor(np.asarray(img0), cv2.COLOR_BGR2RGB)
    st.image(img0, caption="Prediction Result", use_column_width=True)


#set paramters
imgsz = 640
conf = 0.4
iou_thres=0.45
device = torch.device("cpu")
path = "./"


"""
# YOLOv7/ YOLOv7-X
This is a object detection model for Chair, (Lamp, Rest,) Sofa, and Table.
"""

weight_path = './' + st.selectbox('Select Model',
    ['yolov7_best', 'yolov7x_best', 'yolov7_finder_best', 'yolov7x_finder_best']) + '.pt'

conf_thres = (st.slider("Confidence Threshold (%)", 0, 100, 40))/100

# Load model
model = attempt_load(weight_path, map_location=torch.device('cpu'))  # load FP32 model

option = st.radio("Select one way to demo: ", ["upload image", "image URL", "or try some preset images"])

if option == "upload image":
    uploaded_file = st.file_uploader("Please upload an image.")

    if uploaded_file is not None:
        img = PILImage.create(uploaded_file)
        detect_modify(img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)

elif option == "image URL":
    url = st.text_input("Please input a url.")
    if url != "":
        try:
            response = requests.get(url)
            pil_img = PILImage.create(BytesIO(response.content))
            detect_modify(pil_img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
        except:
            st.text("Problem reading image from", url)

elif option == "or try some preset images":

    img_select = image_select(
    label="Select a picture to detect",
    images=[
    # Chair
    "https://www.ikea.com/au/en/images/products/nordviken-chair-antique-stain__0832454_pe777681_s5.jpg",
    # Sofa
    "https://assets.boconcept.com/b1c0b22e-ef01-4d5b-af4d-ad43018a1f5b/1560164_PNG-Web%2072dpi.png?format=pjpg&auto=webp&fit=bounds&width=3020&quality=75%2C60&height=2265",
    # Table
    "https://habitt.com/cdn/shop/files/2_2_51e1b37c-8035-4abd-8e93-331f145525f5.jpg?v=1697278017",
    # Table
    "https://m.media-amazon.com/images/I/51zvHEqiKOL._AC_UF1000,1000_QL80_.jpg",


    "https://wpmedia.roomsketcher.com/content/uploads/2021/12/09085551/Living_room_idea_wood_details.jpg",

    "https://goodhomes.wwmindia.com/content/2022/jan/living-room-picture-by-studio-noughts.jpg",

    "https://media.houseandgarden.co.uk/photos/618946a9eea7137eaf372dee/master/w_1600%2Cc_limit/038-2.jpg",

    "https://www.checkatrade.com/blog/wp-content/uploads/2023/10/Feature-navy-living-room.jpg"
    ],
    captions=["Picture 1", "Picture 2", "Picture 3", "Picture 4", 
              "Picture 5", "Picture 6", "Picture 7", "Picture 8"],)

    if (img_select):
        url = str(img_select)[:100]
        
        try:
            response = requests.get(url)
            pil_img = PILImage.create(BytesIO(response.content))
            detect_modify(pil_img, model, conf=conf, imgsz=imgsz, conf_thres=conf_thres, iou_thres=iou_thres)
        except:
            st.text("Problem reading image from", url)