YOLOv5桌面应用开发，手把手教学实操（中）——附源代码

pip install Pyqt5

def model_init(self):        # 模型相关参数配置        parser = argparse.ArgumentParser()#best1.pt效果最好        parser.add_argument('--weights', nargs='+', type=str, default='weights/best1.pt', help='model.pt path(s)')        parser.add_argument('--source', type=str, default='data/images', help='source')  # file/folder, 0 for webcam        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='0', 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')        self.opt = parser.parse_args()        print(self.opt)        # 默认使用opt中的设置（权重等）来对模型进行初始化        source, weights, view_img, save_txt, imgsz = self.opt.source, self.opt.weights, self.opt.view_img, self.opt.save_txt, self.opt.img_size        # 若openfile_name_model不为空，则使用此权重进行初始化        if self.openfile_name_model:            weights = self.openfile_name_model            print("Using button choose model")        # self.device = select_device(self.opt.device)        self.device = torch.device('cuda:0')        self.half = self.device.type != 'cpu'  # half precision only supported on CUDA        cudnn.benchmark = True        # Load model        self.model = attempt_load(weights, map_location=self.device)  # load FP32 model        stride = int(self.model.stride.max())  # model stride        self.imgsz = check_img_size(imgsz, s=stride)  # check img_size        if self.half:          self.model.half()  # to FP16        # Get names and colors        self.names = self.model.module.names if hasattr(self.model, 'module') else self.model.names        self.colors = [[random.randint(0, 255) for _ in range(3)] for _ in self.names]        print("model initial done")

def detect(self):    t0 = time.time()    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img    _ = model(img.half() if half else img) if device.type != 'cpu' else None  # run once    for path, img, im0s, vid_cap in dataset:        img = torch.from_numpy(img).to(device)        img = img.half() if half else img.float()  # uint8 to fp16/32        img /= 255.0  # 0 - 255 to 0.0 - 1.0        if img.ndimension() == 3:            img = img.unsqueeze(0)         # Inference        t1 = time_synchronized()        pred = model(img, augment=opt.augment)[0]         # Apply NMS        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)         # Process detections        for i, det in enumerate(pred):  # detections per image            if webcam:  # batch_size >= 1                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)  # to Path            save_path = str(save_dir / p.name)  # img.jpg            txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt            s += '%gx%g ' % img.shape[2:]  # print string            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh            if len(det):                # Rescale boxes from img_size to im0 size                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()                 # Print results                for c in det[:, -1].unique():                    n = (det[:, -1] == c).sum()  # detections per class                    s += f'{n} {names[int(c)]}s, '  # add to string                 # Write results                for *xyxy, conf, cls in reversed(det):                    if save_txt:  # Write to file                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh                        line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format                        with open(txt_path + '.txt', 'a') as f:                            f.write(('%g ' * len(line)).rstrip() % line + '\n')                     if save_img or view_img:  # Add bbox to image                        label = f'{names[int(cls)]} {conf:.2f}'                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)], line_thickness=3)

def detect(self,image)   pass def show_video(self)     这里的image可以是摄像头，图片，视频，网络摄像头     比如使用opencv     num = 0     self.cap = cv2.VideoCapture(camera_num)     image = self.cap.read()     a = self.detect(image)     对这里的image进行处理显示

def play_music(self)   winsound.PlaySound('选择你要播放的WAV音频',winsound.SND_ASYNC)   time.sleep(休眠时间以s计数，我设置的是0.5)

 pred = model(img, augment=opt.augment)[0]