# YOLOv5 🚀 by Ultralytics, GPL-3.0 license """ Run YOLOv5 segmentation inference on images, videos, directories, streams, etc. Usage - sources: $ python segment/predict.py --weights yolov5s-seg.pt --source 0 # webcam img.jpg # image vid.mp4 # video screen # screenshot path/ # directory list.txt # list of images list.streams # list of streams 'path/*.jpg' # glob 'https://youtu.be/Zgi9g1ksQHc' # YouTube 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream Usage - formats: $ python segment/predict.py --weights yolov5s-seg.pt # PyTorch yolov5s-seg.torchscript # TorchScript yolov5s-seg.onnx # ONNX Runtime or OpenCV DNN with --dnn yolov5s-seg_openvino_model # OpenVINO yolov5s-seg.engine # TensorRT yolov5s-seg.mlmodel # CoreML (macOS-only) yolov5s-seg_saved_model # TensorFlow SavedModel yolov5s-seg.pb # TensorFlow GraphDef yolov5s-seg.tflite # TensorFlow Lite yolov5s-seg_edgetpu.tflite # TensorFlow Edge TPU yolov5s-seg_paddle_model # PaddlePaddle """ import argparse import os import platform import sys from pathlib import Path import torch FILE = Path(__file__).resolve() ROOT = FILE.parents[0] # YOLOv5 root directory if str(ROOT) not in sys.path: sys.path.append(str(ROOT)) # add ROOT to PATH ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams, LoadImages_batch from utils.general import (LOGGER, Profile, check_file, check_img_size, check_imshow, check_requirements, colorstr, cv2, increment_path, non_max_suppression, print_args, scale_boxes, scale_segments, strip_optimizer) from utils.plots import Annotator, colors, save_one_box from utils.segment.general import masks2segments, process_mask, process_mask_native from utils.segment.dataloaders import polygons2masks from utils.torch_utils import select_device, smart_inference_mode import numpy as np @smart_inference_mode() def run( weights=ROOT / 'yolov5s.pt', # model.pt path(s) source=ROOT / 'data/HRSID_YOLO/val', # file/dir/URL/glob/screen/0(webcam) data=ROOT / 'data/HRSID_YOLO/dataset.yaml', # dataset.yaml path imgsz=(640, 640), # inference size (height, width) conf_thres=0.25, # confidence threshold iou_thres=0.45, # NMS IOU threshold max_det=1000, # maximum detections per image device='', # cuda device, i.e. 0 or 0,1,2,3 or cpu view_img=False, # show results save_txt=False, # save results to *.txt save_conf=False, # save confidences in --save-txt labels save_crop=False, # save cropped prediction boxes nosave=False, # do not save images/videos classes=None, # filter by class: --class 0, or --class 0 2 3 agnostic_nms=False, # class-agnostic NMS augment=False, # augmented inference visualize=False, # visualize features update=False, # update all models project=ROOT / 'runs/predict-seg', # save results to project/name name='exp', # save results to project/name exist_ok=False, # existing project/name ok, do not increment line_thickness=3, # bounding box thickness (pixels) hide_labels=False, # hide labels hide_conf=False, # hide confidences half=False, # use FP16 half-precision inference dnn=False, # use OpenCV DNN for ONNX inference vid_stride=1, # video frame-rate stride retina_masks=False, batch_size=16, ): source = str(source) save_img = not nosave and not source.endswith('.txt') # save inference images is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS) is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://')) webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file) screenshot = source.lower().startswith('screen') if is_url and is_file: source = check_file(source) # download # Directories save_dir = increment_path(Path(project) / name, exist_ok=exist_ok) # increment run (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir (save_dir / 'jsons' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir logFile = save_dir / 'detect.txt' import logging LOGGER = logging.getLogger('yolov5') logging.basicConfig(level=logging.INFO) # 创建一个FileHandler,并将日志写入指定的日志文件中 fileHandler = logging.FileHandler(logFile, mode='a', encoding="utf-8") fileHandler.setLevel(logging.INFO) # 定义Handler的日志输出格式 # formatter = logging.Formatter('%(asctime)s - %(name)s - %(levelname)s - %(message)s') formatter = logging.Formatter('%(asctime)s - %(message)s') fileHandler.setFormatter(formatter) # 添加Handler LOGGER.addHandler(fileHandler) # Load model device = select_device(device) model = DetectMultiBackend(weights, device=device, dnn=dnn, data=data, fp16=half) stride, names, pt = model.stride, model.names, model.pt nmm = len(list(names.keys())) imgsz = check_img_size(imgsz, s=stride) # check image size # Dataloader bs = batch_size # batch_size if webcam: view_img = check_imshow(warn=True) dataset = LoadStreams(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) bs = len(dataset) elif screenshot: dataset = LoadScreenshots(source, img_size=imgsz, stride=stride, auto=pt) else: if bs == 1: dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) else: from torch.utils.data import DataLoader dataset = LoadImages_batch(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) bs = min(bs, len(dataset)) dataloader = DataLoader(dataset, batch_size=bs, shuffle=True, num_workers=4, pin_memory=True, collate_fn=LoadImages_batch.collate_fn) vid_path, vid_writer = [None] * bs, [None] * bs # Run inference model.warmup(imgsz=(1 if pt else bs, 3, *imgsz)) # warmup seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) if bs == 1: for path, im, im0s, vid_cap, s in dataset: with dt[0]: im = torch.from_numpy(im).to(model.device) im = im.half() if model.fp16 else im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 if len(im.shape) == 3: im = im[None] # expand for batch dim # Inference with dt[1]: visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred, proto = model(im, augment=augment, visualize=visualize)[:2] # NMS with dt[2]: # if pred.numel() > 0: # numel() 返回张量中元素的数量 # pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, # max_det=max_det, nm=nm) # else: # print("No valid predictions, skipping non_max_suppression.") # pred = torch.empty((0, 6)) # 返回一个空的张量以避免后续错误 # print(pred) pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det, nm=nmm) # Second-stage classifier (optional) # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Process predictions for i, det in enumerate(pred): # per image seen += 1 if webcam: # batch_size >= 1 p, im0, frame = path[i], im0s[i].copy(), dataset.count s += f'{i}: ' else: p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) p = Path(p) # to Path save_path = str(save_dir / p.name) # im.jpg txt_path = str(save_dir / 'labels' / p.stem) + ( '' if dataset.mode == 'image' else f'_{frame}') # im.txt labelme_path = str(save_dir / 'jsons' / p.stem) + ( '' if dataset.mode == 'image' else f'_{frame}') # im.json label_dict = {} label_dict['version'] = '5.0.1' label_dict['flags'] = {} label_dict['imageData'] = None label_dict['imagePath'] = p.name label_dict['imageHeight'] = im0.shape[0] label_dict['imageWidth'] = im0.shape[1] label_dict['shapes'] = [] s += '%gx%g ' % im.shape[2:] # print string imc = im0.copy() if save_crop else im0 # for save_crop annotator = Annotator(im0, line_width=line_thickness, example=str(names)) if len(det): if retina_masks: # scale bbox first the crop masks det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() # rescale boxes to im0 size masks = process_mask_native(proto[i], det[:, 6:], det[:, :4], im0.shape[:2]) # HWC else: masks = process_mask(proto[i], det[:, 6:], det[:, :4], im.shape[2:], upsample=True) # HWC det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() # rescale boxes to im0 size # Segments if save_txt: segments = [ scale_segments(im0.shape if retina_masks else im.shape[2:], x, im0.shape, normalize=False) for x in reversed(masks2segments(masks))] # ,strategy='concat' # Print results for c in det[:, 5].unique(): n = (det[:, 5] == c).sum() # detections per class s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string # Mask plotting annotator.masks( masks, colors=[colors(x, True) for x in det[:, 5]], im_gpu=torch.as_tensor(im0, dtype=torch.float16).to(device).permute(2, 0, 1).flip( 0).contiguous() / 255 if retina_masks else im[i]) # Write results for j, (*xyxy, conf, cls) in enumerate(reversed(det[:, :6])): if save_txt: # Write to file seg = segments[j].reshape(-1) # (n,2) to (n*2) line = (cls, *seg, conf) if save_conf else (cls, *seg) # label format with open(f'{txt_path}.txt', 'a') as f: f.write(('%g ' * len(line)).rstrip() % line + '\n') # add save_labeme format tmp = {} tmp['label'] = names[int(cls)] # tmp['label_id'] = int(cls) tmp['points'] = segments[ j].tolist() # [[float(xyxy[0].detach().item()), float(xyxy[1].detach().item())], [float(xyxy[2].detach().item()), float(xyxy[3].detach().item())]] tmp['group_id'] = None tmp['shape_type'] = 'polygon' # 注意修改 tmp['flags'] = {} # tmp['bbox'] = [xyxy[0].tolist(),xyxy[1].tolist()] label_dict['shapes'].append(tmp) if save_img or save_crop or view_img: # Add bbox to image c = int(cls) # integer class label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}') annotator.box_label(xyxy, label, color=colors(c, True), flag=False) # # annotator.draw.polygon(segments[j], outline=colors(c, True), width=3) if save_crop: save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) if save_txt: # Write to file import json with open(f'{labelme_path}.json', 'w') as f: json.dump(label_dict, f) # Stream results im0 = annotator.result() if view_img: if platform.system() == 'Linux' and p not in windows: windows.append(p) cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0]) cv2.imshow(str(p), im0) if cv2.waitKey(1) == ord('q'): # 1 millisecond exit() # Save results (image with detections) if save_img: if dataset.mode == 'image': cv2.imwrite(save_path, im0) else: # 'video' or 'stream' if vid_path[i] != save_path: # new video vid_path[i] = save_path if isinstance(vid_writer[i], cv2.VideoWriter): vid_writer[i].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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) # Print time (inference-only) LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms") f_for_val = open('x.excel', 'w') f_for_val.writelines(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms") else: for batch_i, (paths, im, im0s, s) in enumerate(dataloader): with dt[0]: im = im.to(device, non_blocking=True) im = im.half() if model.fp16 else im.float() # uint8 to fp16/32 im /= 255 # 0 - 255 to 0.0 - 1.0 # Inference with dt[1]: # visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False pred, proto = model(im, augment=augment, visualize=False)[:2] # NMS with dt[2]: if pred.numel() > 0: # numel() 返回张量中元素的数量 pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det, nm=nm) else: print("No valid predictions, skipping non_max_suppression.") pred = torch.empty((0, 6)) # 返回一个空的张量以避免后续错误 pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det, nm=nmm) # Second-stage classifier (optional) # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Process predictions for i, det in enumerate(pred): # per image seen += 1 if webcam: # batch_size >= 1 p, im0, frame = paths[i], im0s[i].copy(), dataset.count s += f'{i}: ' else: p, im0, frame = paths[i], im0s[i].numpy().copy(), getattr(dataset, 'frame', 0) s[i] += f'{i}: ' p = Path(p) # to Path save_path = str(save_dir / p.name) # im.jpg txt_path = str(save_dir / 'labels' / p.stem) + ( '' if dataset.mode == 'image' else f'_{frame}') # im.txt labelme_path = str(save_dir / 'jsons' / p.stem) + ( '' if dataset.mode == 'image' else f'_{frame}') # im.json label_dict = {} label_dict['version'] = '5.0.1' label_dict['flags'] = {} label_dict['imageData'] = None label_dict['imagePath'] = p.name label_dict['imageHeight'] = im0.shape[0] label_dict['imageWidth'] = im0.shape[1] label_dict['shapes'] = [] s += '%gx%g ' % im.shape[2:] # print string imc = im0.copy() if save_crop else im0 # for save_crop annotator = Annotator(im0, line_width=line_thickness, example=str(names)) if len(det): if retina_masks: # scale bbox first the crop masks det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() # rescale boxes to im0 size masks = process_mask_native(proto[i], det[:, 6:], det[:, :4], im0.shape[:2]) # HWC else: masks = process_mask(proto[i], det[:, 6:], det[:, :4], im.shape[2:], upsample=True) # HWC det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() # rescale boxes to im0 size # Segments if save_txt: segments = [ scale_segments(im0.shape if retina_masks else im.shape[2:], x, im0.shape, normalize=False) for x in reversed(masks2segments(masks))] # Print results for c in det[:, 5].unique(): n = (det[:, 5] == c).sum() # detections per class s += f"{n} {names[int(c)]}{'s' * (n > 1)}, " # add to string # Mask plotting annotator.masks( masks, colors=[colors(x, True) for x in det[:, 5]], im_gpu=torch.as_tensor(im0, dtype=torch.float16).to(device).permute(2, 0, 1).flip( 0).contiguous() / 255 if retina_masks else im[i]) # Write results for j, (*xyxy, conf, cls) in enumerate(reversed(det[:, :6])): if save_txt: # Write to file seg = segments[j].reshape(-1) # (n,2) to (n*2) line = (cls, *seg, conf) if save_conf else (cls, *seg) # label format with open(f'{txt_path}.txt', 'a') as f: f.write(('%g ' * len(line)).rstrip() % line + '\n') # add save_labeme format tmp = {} tmp['label'] = names[int(cls)] tmp['points'] = segments[ j].tolist() # E[float(xyxy[0].detach().item()), float(xyxy[1].detach().item())], [float(xyxy[2].detach().item()), float(xyxy[3].detach().item())] tmp['group_id'] = None tmp['shape_type'] = 'polygon' # 注意修改 # area = component_polygon_area(segments[j]) # tmp['area'] = area # tmp['lenth'] = component_polygon_Circle(segments[j])# 宽度 # tmp['width'] = component_polygon_Circle(segments[j]) tmp['flags'] = {} label_dict['shapes'].append(tmp) if save_img or save_crop or view_img: # Add bbox to image c = int(cls) # integer class label = None if hide_labels else (names[c] if hide_conf else f'{names[c]} {conf:.2f}') annotator.box_label(xyxy, label, color=colors(c, True), flag=False) # annotator.draw.polygon(segments[j], outline=colors(c, True), width=3) if save_crop: save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) if save_txt: # Write to file import json with open(f'{labelme_path}.json', 'w') as f: json.dump(label_dict, f) # # copy file # import shutil # #shutil.copyfile(f'{labelme_path}.json', os.path.dirname(source) + f'{labelme_path}.json') # if os.path.isdir(source): # shutil.copyfile(f'{labelme_path}.json',os.path.join(source,f'{p.stem}.json')) # else: # shutil.copyfile(f'{labelme_path}.json',os.path.join(os.path.dirname(source),f'{p.stem}.json')) else: # 不存在 检测结果 if save_txt: # Write to file # add save_labeme format tmp = {} tmp['label'] = "" # names[int(cls)] tmp['points'] = [ []] # segments[j].tolist() #E[float(xyxy[0].detach().item()), float(xyxy[1].detach().item())], [float(xyxy[2].detach().item()), float(xyxy[3].detach().item())] tmp['group_id'] = None tmp['shape_type'] = 'polygon' # 注意修改 # area = component_polygon_area(segments[j]) # tmp['area'] = area # tmp['lenth'] = component_polygon_Circle(segments[j])# 宽度 # tmp['width'] = component_polygon_Circle(segments[j]) tmp['flags'] = {} label_dict['shapes'].append(tmp) import json with open(f'{labelme_path}.json', 'w') as f: json.dump(label_dict, f) # Stream results im0 = annotator.result() if view_img: if platform.system() == 'Linux' and p not in windows: windows.append(p) cv2.namedWindow(str(p), cv2.WINDOW_NORMAL | cv2.WINDOW_KEEPRATIO) # allow window resize (Linux) cv2.resizeWindow(str(p), im0.shape[1], im0.shape[0]) cv2.imshow(str(p), im0) if cv2.waitKey(1) == ord('q'): # 1 millisecond exit() # Save results (image with detections) if save_img: if dataset.mode == 'image': cv2.imwrite(save_path, im0) else: # 'video' or 'stream' if vid_path[i] != save_path: # new video vid_path[i] = save_path if isinstance(vid_writer[i], cv2.VideoWriter): vid_writer[i].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 = str(Path(save_path).with_suffix('.mp4')) # force *.mp4 suffix on results videos vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) vid_writer[i].write(im0) # Print time (inference-only) LOGGER.info(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms") f_for_val.writelines(f"{s}{'' if len(det) else '(no detections), '}{dt[1].dt * 1E3:.1f}ms") f_for_val.close() # Print results t = tuple(x.t / seen * 1E3 for x in dt) # speeds per image LOGGER.info(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t) 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 '' LOGGER.info(f"Results saved to {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights[0]) # update model (to fix SourceChangeWarning) def parse_opt(): parser = argparse.ArgumentParser() parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'weights\\best.pt', help='model path(s)') parser.add_argument('--source', type=str, default=ROOT / 'data\\HRSID_YOLO\\test\\images', help='file/dir/URL/glob/screen/0(webcam)') parser.add_argument('--data', type=str, default=ROOT / 'data\HRSID_YOLO\dataset.yaml', help='(optional) dataset.yaml path') parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[640], help='inference size h,w') parser.add_argument('--conf-thres', type=float, default=0.25, help='confidence threshold') parser.add_argument('--iou-thres', type=float, default=0.45, help='NMS IoU threshold') parser.add_argument('--max-det', type=int, default=1000, help='maximum detections per image') 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='show results') parser.add_argument('--save-txt', action='store_true', default=True, help='save results to *.txt') parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels') parser.add_argument('--save-crop', action='store_true', help='save cropped prediction boxes') parser.add_argument('--nosave', action='store_true', default=True, help='do not save images/videos') parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --classes 0, or --classes 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('--visualize', action='store_true', help='visualize features') parser.add_argument('--update', action='store_true', help='update all models') parser.add_argument('--project', default=ROOT / '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('--line-thickness', default=3, type=int, help='bounding box thickness (pixels)') parser.add_argument('--hide-labels', default=False, action='store_true', help='hide labels') parser.add_argument('--hide-conf', default=False, action='store_true', help='hide confidences') parser.add_argument('--half', action='store_true', help='use FP16 half-precision inference') parser.add_argument('--dnn', action='store_true', help='use OpenCV DNN for ONNX inference') parser.add_argument('--vid-stride', type=int, default=1, help='video frame-rate stride') parser.add_argument('--retina-masks', action='store_true', help='whether to plot masks in native resolution') parser.add_argument('--batch-size', type=int, default=1, help='total batch size for all GPUs, -1 for autobatch') opt = parser.parse_args() opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand print_args(vars(opt)) return opt def main(opt): check_requirements(exclude=('tensorboard', 'thop')) run(**vars(opt)) if __name__ == "__main__": opt = parse_opt() main(opt)