输入指令

python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source yourvideo.mp4  # On video
python detect.py --weights yolov7.pt --conf 0.25 --img-size 640 --source inference/images/horses.jpg  # On image

参数解析

if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--weights', nargs='+', type=str, default='/kaxier01/projects/FAS/yolov7/weights/yolov7.pt', help='model.pt path(s)')
    parser.add_argument('--source', type=str, default='/kaxier01/projects/FAS/yolov7/inference/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='', 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='yolov7_640_detect', 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('--no-trace', action='store_true', help='don`t trace model')
    opt = parser.parse_args()
    print(opt)

    with torch.no_grad():
        if opt.update:  # update all models (to fix SourceChangeWarning)
            for opt.weights in ['yolov7.pt']:
                detect()
                strip_optimizer(opt.weights)
        else:
            detect()

根据输入参数判断输入图片是来自本地还是网络

save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))

创建保存检测结果的文件夹(以增量的方式创建，若文件夹detect_results已经存在，则新建文件夹为detect_results2，以此类推)

def increment_path(path, exist_ok=True, sep=''):
    # Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc.
    path = Path(path)  # os-agnostic
    if (path.exists() and exist_ok) or (not path.exists()):
        return str(path)
    else:
        dirs = glob.glob(f"{path}{sep}*")  # similar paths
        matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
        i = [int(m.groups()[0]) for m in matches if m]  # indices
        n = max(i) + 1 if i else 2  # increment number
        return f"{path}{sep}{n}"  # update path

save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
(save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir

根据参数指定device，

set_logging()
device = select_device(opt.device)
half = device.type != 'cpu'  # half precision only supported on CUDA

加载模型，若代码在gpu上运行，则将模型参数类型由FP32转为FP16

def make_divisible(x, divisor):
    # Returns x evenly divisible by divisor
    return math.ceil(x / divisor) * divisor

def check_img_size(img_size, s=32):
    # 功能：将图片分辨率调整为32的倍数
    new_size = make_divisible(img_size, int(s))  # ceil gs-multiple
    if new_size != img_size:
        print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
    return new_size

model = attempt_load(weights, map_location=device)  # load FP32 model
stride = int(model.stride.max())  # model stride
imgsz = check_img_size(imgsz, s=stride)  # check img_size

if trace:
   model = TracedModel(model, device, opt.img_size)

if half:
   model.half()  # to FP16

加载数据集，判断输入文件的格式

if webcam:
   view_img = check_imshow()
   cudnn.benchmark = True  # set True to speed up constant image size inference
   dataset = LoadStreams(source, img_size=imgsz, stride=stride)
else:
   dataset = LoadImages(source, img_size=imgsz, stride=stride)

LoadImages类

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

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)
    # 计算缩放比
    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
    # 计算缩放后图片的宽高
    new_unpad = int(round(shape[1] * r)), int(round(shape[0] * r))
    # 计算需要填充的边的像素
    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))
    # 添加灰边
    img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=color)  # add border
    return img, ratio, (dw, dh)

图片预处理，1、numpy转tensor；2、unit8->fp16/32；3、图片归一化；4、若图片维度为3，则将维度提升为4，

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)

模型推理

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

推理结果后处理

pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)

处理检测结果

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
            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' * (n > 1)}, "  # 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=1)

            # Print time (inference + NMS)
            print(f'{s}Done. ({(1E3 * (t2 - t1)):.1f}ms) Inference, ({(1E3 * (t3 - t2)):.1f}ms) NMS')

            # Stream results
            if view_img:
                cv2.imshow(str(p), im0)
                cv2.waitKey(1)  # 1 millisecond

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'image':
                    cv2.imwrite(save_path, im0)
                    print(f" The image with the result is saved in: {save_path}")
                else:  # 'video' or 'stream'
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer
                        if vid_cap:  # video
                            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:  # stream
                            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)

运行结果