detect.py

import argparse

from models import *  # set ONNX_EXPORT in models.py
from utils.datasets import *
from utils.utils import *


def detect(save_img=False):
    imgsz = (320, 192) if ONNX_EXPORT else opt.img_size  # (320, 192) or (416, 256) or (608, 352) for (height, width)
    out, source, weights, half, view_img, save_txt = opt.output, opt.source, opt.weights, opt.half, opt.view_img, opt.save_txt
    webcam = source == '0' or source.startswith('rtsp') or source.startswith('http') or source.endswith('.txt')

    # Initialize
    device = torch_utils.select_device(device='cpu' if ONNX_EXPORT else opt.device)
    if os.path.exists(out):
        shutil.rmtree(out)  # delete output folder
    os.makedirs(out)  # make new output folder

    # Initialize model
    model = Darknet(opt.cfg, imgsz)

    # Load weights, strict=False
    attempt_download(weights)
    if weights.endswith('.pt'):  # pytorch format
        model.load_state_dict(torch.load(weights, map_location=device)['model'], strict=False)
    else:  # darknet format
        load_darknet_weights(model, weights)

    # Second-stage classifier
    classify = False
    if classify:
        modelc = torch_utils.load_classifier(name='resnet101', n=2)  # initialize
        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model'])  # load weights
        modelc.to(device).eval()

    # Eval mode
    model.to(device).eval()

    # Fuse Conv2d + BatchNorm2d layers

    # model.fuse()

    # Export mode
    if ONNX_EXPORT:
        model.fuse()
        img = torch.zeros((1, 3) + imgsz)  # (1, 3, 320, 192)
        f = opt.weights.replace(opt.weights.split('.')[-1], 'onnx')  # *.onnx filename
        torch.onnx.export(model, img, f, verbose=False, opset_version=11,
                          input_names=['images'], output_names=['classes', 'boxes'])

        # Validate exported model
        import onnx
        model = onnx.load(f)  # Load the ONNX model
        onnx.checker.check_model(model)  # Check that the IR is well formed
        print(onnx.helper.printable_graph(model.graph))  # Print a human readable representation of the graph
        return

    # Half precision
    half = half and device.type != 'cpu'  # half precision only supported on CUDA
    if half:
        model.half()

    # Set Dataloader
    vid_path, vid_writer = None, None
    if webcam:
        view_img = True
        torch.backends.cudnn.benchmark = True  # set True to speed up constant image size inference
        dataset = LoadStreams(source, img_size=imgsz)
    else:
        save_img = True
        dataset = LoadImages(source, img_size=imgsz)

    # Get names and colors
    names = load_classes(opt.names)
    colors = [[random.randint(0, 255) for _ in range(3)] for _ in range(len(names))]

    # Run inference
    t0 = time.time()
    img = torch.zeros((1, 3, imgsz, imgsz), device=device)  # init img
    _ = model(img.half() if half else img.float()) 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 = torch_utils.time_synchronized()
        pred = model(img, augment=opt.augment)[0]
        t2 = torch_utils.time_synchronized()

        # to float
        if half:
            pred = pred.float()

        # Apply NMS
        pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres,
                                   multi_label=False, classes=opt.classes, agnostic=opt.agnostic_nms)

        # Apply Classifier
        if classify:
            pred = apply_classifier(pred, modelc, img, im0s)

        # Process detections, 결과 처리 부분: 각 이미지에 대해 탐지된 객체들을 처리합니다.
        for i, det in enumerate(pred):  # 각 이미지 i에 대한 탐지된 객체들(det)을 반복
            if webcam:  # batch_size >= 1, 웹캠 입력인 경우
                p, s, im0 = path[i], '%g: ' % i, im0s[i].copy()
            else: # 이미지 파일 입력인 경우
                p, s, im0 = path, '', im0s

            save_path = str(Path(out) / Path(p).name) # 결과 이미지 저장 경로
            s += '%gx%g ' % img.shape[2:]  # 이미지 크기 출력 문자열
            gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # 이미지 크기에 따른 정규화 계수

            if det is not None and len(det): # 탐지된 객체가 있을 경우
                # 탐지된 바운딩 박스 크기를 원본 이미지 크기로 조정
                det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()

                # Print results, 결과 출력
                for c in det[:, -1].unique():
                    n = (det[:, -1] == c).sum() # 클래스별 탐지된 객체 수
                    s += '%g %ss, ' % (n, names[int(c)]) # 클래스명과 객체 수를 문자열에 추가

                # Write results, 바운딩 박스 및 레이블 추가
                for *xyxy, conf, cls in reversed(det):
                    if save_txt:  # Write to file, 텍스트 파일에 저장할지 여부를 확인합니다.
                        # 바운딩 박스 좌표를 정규화된 형태로 변환합니다.
                        xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
                        # 텍스트 파일에 레이블 포맷에 맞게 기록합니다.
                        with open(save_path[:save_path.rfind('.')] + '.txt', 'a') as file:
                            file.write(('%g ' * 5 + '\n') % (cls, *xywh))  # label format, 레이블 포맷

                    if save_img or view_img:  # Add bbox to image
                        img_pil = None  # PIL 이미지 초기화
                        for det in pred:
                            label = '%s, 정확도: %.2f' % (names[int(cls)], conf) # 레이블 및 신뢰도
                            print(f"Before plot_one_box: {img_pil}")
                            img_pil = plot_one_box(xyxy, im0, label=label, color=colors[int(cls)]) # 바운딩 박스 및 레이블 추가
                            print(f"After plot_one_box: {img_pil}")
    
                        # 모든 검출을 처리한 후 최종 이미지(img_pil) 저장
                        if img_pil is not None and save_img:
                            img_pil.save(save_path, 'JPEG') # 결과 이미지 저장

            # 처리 시간 출력 (추론 + NMS)
            print('%sDone. (%.3fs)' % (s, t2 - t1))

            # Stream results
            if view_img:
                cv2.imshow(p, im0)
                if cv2.waitKey(1) == ord('q'):  # q to quit, 'q' 키를 누르면 종료
                    raise StopIteration

            # Save results (image with detections)
            if save_img:
                if dataset.mode == 'images':
                    img_pil.save(save_path, 'JPEG') # 결과 이미지 저장
                    # cv2.imwrite(save_path, im0)
                else:
                    if vid_path != save_path:  # new video
                        vid_path = save_path
                        if isinstance(vid_writer, cv2.VideoWriter):
                            vid_writer.release()  # release previous video writer

                        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))
                        vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*opt.fourcc), fps, (w, h))
                    vid_writer.write(im0)

    if save_txt or save_img:
        print('Results saved to %s' % os.getcwd() + os.sep + out)
        if platform == 'darwin':  # MacOS
            os.system('open ' + save_path)

    print('Done. (%.3fs)' % (time.time() - t0))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--cfg', type=str, default='cfg/yolov3-spp.cfg', help='*.cfg path')
    parser.add_argument('--names', type=str, default='data/403food.names', help='*.names path')
    parser.add_argument('--weights', type=str, default='weights/best_403food_e200b150v2.pt', help='weights path')
    parser.add_argument('--source', type=str, default='data/samples', help='source')  # input file/folder, 0 for webcam
    parser.add_argument('--output', type=str, default='output', help='output folder')  # output folder
    parser.add_argument('--img-size', type=int, default=256, help='inference size (pixels)') # 해상도 이슈 수정 (접시)
    parser.add_argument('--conf-thres', type=float, default=0.5, help='object confidence threshold')
    parser.add_argument('--iou-thres', type=float, default=0.6, help='IOU threshold for NMS')
    parser.add_argument('--fou rcc', type=str, default='mp4v', help='output video codec (verify ffmpeg support)')
    parser.add_argument('--half', action='store_true', help='half precision FP16 inference')
    parser.add_argument('--device', default='', help='device id (i.e. 0 or 0,1) 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('--classes', nargs='+', type=int, help='filter by class')
    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
    parser.add_argument('--augment', action='store_true', help='augmented inference')
    opt = parser.parse_args()
    opt.cfg = check_file(opt.cfg)  # check file
    opt.names = check_file(opt.names)  # check file
    print(opt)

    with torch.no_grad():
        detect()