File size: 8,243 Bytes
0afe34f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
dd84c71
322296b
dd84c71
 
 
b54919c
dd84c71
322296b
 
 
 
dd84c71
0afe34f
 
659b86c
1697d72
0afe34f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
659b86c
0afe34f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
659b86c
0afe34f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4749e95
322296b
0afe34f
 
dfdbd45
0afe34f
e3d794c
e250ffd
0afe34f
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
import torch
import argparse
import gradio as gr
from PIL import Image
from numpy import random
from pathlib import Path
import os
import time
import torch.backends.cudnn as cudnn
from models.experimental import attempt_load
import cv2
from utils.datasets import LoadStreams, LoadImages
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
from utils.torch_utils import select_device, load_classifier, time_synchronized, TracedModel


os.system('git clone https://github.com/WongKinYiu/yolov7')
os.system('wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7.pt')
#os.system('wget https://github.com/WongKinYiu/yolov7/releases/download/v0.1/yolov7-mask.pt')

#model='best'  
def Custom_detect(img,mode):
    if mode=='Custom-Detection':
        model='best'
    #if mode=='Instance-Segmentation':
     #   model='yolov7-mask'
    if mode=='Yolov7-model-detection':
        model='yolov7'
    
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default=model+".pt", help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='Temp_files/', help='source') 
    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
    parser.add_argument('--view-img', action='store_true', help='display results')
    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    parser.add_argument('--update', action='store_true', help='update all models')
    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
    parser.add_argument('--name', default='exp', help='save results to project/name')
    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
    parser.add_argument('--trace', action='store_true', help='trace model')
    opt = parser.parse_args()
    img.save("Temp_files/test.jpg")
    source, weights, view_img, save_txt, imgsz, trace = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size, opt.trace
    save_img = True 
    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
    save_dir = Path(increment_path(Path(opt.project)/opt.name,exist_ok=opt.exist_ok))
    
    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  
    set_logging()
    device = select_device(opt.device)
    half = device.type != 'cpu' 
    model = attempt_load(weights, map_location=device) 
    stride = int(model.stride.max())  
    imgsz = check_img_size(imgsz, s=stride)
    if trace:
        model = TracedModel(model, device, opt.img_size)
    if half:
        model.half() 
        
    classify = False
    if classify:
        modelc = load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
    vid_path, vid_writer = None, None
    if webcam:
        view_img = check_imshow()
        cudnn.benchmark = True 
        dataset = LoadStreams(source, img_size=imgsz, stride=stride)
    else:
        dataset = LoadImages(source, img_size=imgsz, stride=stride)
    names = model.module.names if hasattr(model, 'module') else model.names
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in names]
    if device.type != 'cpu':
        model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters()))) 
    t0 = time.time()
    for path, img, im0s, vid_cap in dataset:
        img = torch.from_numpy(img).to(device)
        img = img.half() if half else img.float() 
        img /= 255.0  
        if img.ndimension() == 3:
            img = img.unsqueeze(0)

        # Inference
        t1 = time_synchronized()
        pred = model(img, augment=opt.augment)[0]

        pred = non_max_suppression(pred,opt.conf_thres,opt.iou_thres,classes=opt.classes, agnostic=opt.agnostic_nms) 
        t2 = time_synchronized()
        
        
        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)
    
        for i, det in enumerate(pred): 
            if webcam: 
                p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
            else:
                p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)

            p = Path(p)  
            save_path = str(save_dir / p.name)
            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
            s += '%gx%g ' % img.shape[2:]  
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  
            if len(det):
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum()  
                    s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  

                
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist() 
                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh) 
                        with open(txt_path + '.txt', 'a') as f:
                            f.write(('%g ' * len(line)).rstrip() % line + '\n')

                    if save_img or view_img:
                        label = f'{names[int(cls)]} {conf:.2f}'
                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=2)
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  

            if save_img:
                if dataset.mode == 'image':                
                    cv2.imwrite(save_path, im0)
                else: 
                    if vid_path != save_path: 
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()
                        if vid_cap: 
                            fps = vid_cap.get(cv2.CAP_PROP_FPS)
                            w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
                            h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
                        else: 
                            fps, w, h = 30, im0.shape[1], im0.shape[0]
                            save_path += '.mp4'
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
                    vid_writer.write(im0)

    if save_txt or save_img:
        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''

    print(f'Done. ({time.time() - t0:.3f}s)')

    return Image.fromarray(im0[:,:,::-1])
inp = gr.Image(type="pil")
#"Custom-Detection","Yolov7-model-detection"
inp2= gr.Dropdown(choices=['Custom-Detection','Yolov7-model-detection'])
output = gr.Image(type="pil")

examples=[["Examples/Image1.jpg","Image1"],["Examples/Image14.jpg","Image14"],["Examples/Image32.jpg","Image32"]]

io=gr.Interface(fn=Custom_detect, inputs=[inp,inp2], outputs=output, title='Vehicle Detection With Custom YOLOv7')
io.launch()