From eaab2324444fb511530edce115f427b9cb4de604 Mon Sep 17 00:00:00 2001 From: Your Name <1260635600@qq.com> Date: Thu, 16 May 2024 21:10:47 +0800 Subject: [PATCH 1/4] Add a function to find the nearest target --- contributionDetect.py | 310 ++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 310 insertions(+) create mode 100644 contributionDetect.py diff --git a/contributionDetect.py b/contributionDetect.py new file mode 100644 index 00000000000..b72b3abc1fb --- /dev/null +++ b/contributionDetect.py @@ -0,0 +1,310 @@ +# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license +""" +Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc. + +Usage - sources: + $ python detect.py --weights yolov5s.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/LNwODJXcvt4' # YouTube + 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream + +Usage - formats: + $ python detect.py --weights yolov5s.pt # PyTorch + yolov5s.torchscript # TorchScript + yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn + yolov5s_openvino_model # OpenVINO + yolov5s.engine # TensorRT + yolov5s.mlmodel # CoreML (macOS-only) + yolov5s_saved_model # TensorFlow SavedModel + yolov5s.pb # TensorFlow GraphDef + yolov5s.tflite # TensorFlow Lite + yolov5s_edgetpu.tflite # TensorFlow Edge TPU + yolov5s_paddle_model # PaddlePaddle +""" + +import argparse +import csv +import os +import platform +import sys +from pathlib import Path +import numpy as np +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 ultralytics.utils.plotting import Annotator, colors, save_one_box + +from models.common import DetectMultiBackend +from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams +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, strip_optimizer, xyxy2xywh) +from utils.torch_utils import select_device, smart_inference_mode + + +@smart_inference_mode() +def run( + weights=ROOT / 'yolov5s.pt', # model path or triton URL + source=ROOT / 'data/images', # file/dir/URL/glob/screen/0(webcam) + data=ROOT / 'data/coco128.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_csv=False, # save results in CSV format + 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/detect', # 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 +): + 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 + + # 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 + imgsz = check_img_size(imgsz, s=stride) # check image size + + # Dataloader + bs = 1 # 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: + dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) + vid_path, vid_writer = [None] * bs, [None] * bs + + # Run inference + model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup + seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) + 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 = model(im, augment=augment, visualize=visualize) + + # NMS + with dt[2]: + pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) + + # Second-stage classifier (optional) + # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) + + # Define the path for the CSV file + csv_path = save_dir / 'predictions.csv' + + # Create or append to the CSV file + def write_to_csv(image_name, prediction, confidence): + data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence} + with open(csv_path, mode='a', newline='') as f: + writer = csv.DictWriter(f, fieldnames=data.keys()) + if not csv_path.is_file(): + writer.writeheader() + writer.writerow(data) + + # 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 + s += '%gx%g ' % im.shape[2:] # print string + gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh + imc = im0.copy() if save_crop else im0 # for save_crop + annotator = Annotator(im0, line_width=line_thickness, example=str(names)) + + # Calculate the center of the image + img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) + min_distance = None + closest_box = None + + if len(det): + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() + + # Calculate the center of the image + img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) + + # Calculate centers of all detection boxes and find the closest one to the image center + centers = np.array([[(xyxy[0].cpu() + xyxy[2].cpu()) / 2, (xyxy[1].cpu() + xyxy[3].cpu()) / 2] for *xyxy, _, _ in reversed(det)]) + distances = np.linalg.norm(centers - img_center, axis=1) + closest_idx = np.argmin(distances) + + # Draw boxes, marking the closest one in green + for j, (*xyxy, conf, cls) in enumerate(reversed(det)): + color = (0, 255, 0) if j == closest_idx else colors(int(cls), True) + annotator.box_label(xyxy, f'{names[int(cls)]} {conf:.2f}', color=color) + + + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() + + # 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 + + # Write results + for *xyxy, conf, cls in reversed(det): + c = int(cls) # integer class + label = names[c] if hide_conf else f'{names[c]}' + confidence = float(conf) + confidence_str = f'{confidence:.2f}' + + if save_csv: + write_to_csv(p.name, label, confidence_str) + + 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 save_conf else (cls, *xywh) # label format + with open(f'{txt_path}.txt', 'a') as f: + f.write(('%g ' * len(line)).rstrip() % line + '\n') + + 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)) + if save_crop: + save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) + + # 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) + cv2.waitKey(1) # 1 millisecond + + # 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") + + # 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 / 'yolov5s.pt', help='model path or triton URL') + parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)') + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.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='', 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', help='save results to *.txt') + parser.add_argument('--save-csv', action='store_true', help='save results in CSV format') + 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', 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') + 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(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop')) + run(**vars(opt)) + +# python detect.py --weights runs/train/exp10/weights/best.pt --source project/test +# python detect.py --weights runs/train/exp10/weights/best.pt --source project/test + +if __name__ == '__main__': + opt = parse_opt() + main(opt) From d458a53ef700e9e4c3a2eb5db77e0c2e6be29a56 Mon Sep 17 00:00:00 2001 From: Your Name <1260635600@qq.com> Date: Thu, 16 May 2024 21:15:33 +0800 Subject: [PATCH 2/4] Add a function to find the nearest target --- contributionDetect.py | 310 ------------------------------------------ 1 file changed, 310 deletions(-) delete mode 100644 contributionDetect.py diff --git a/contributionDetect.py b/contributionDetect.py deleted file mode 100644 index b72b3abc1fb..00000000000 --- a/contributionDetect.py +++ /dev/null @@ -1,310 +0,0 @@ -# YOLOv5 🚀 by Ultralytics, AGPL-3.0 license -""" -Run YOLOv5 detection inference on images, videos, directories, globs, YouTube, webcam, streams, etc. - -Usage - sources: - $ python detect.py --weights yolov5s.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/LNwODJXcvt4' # YouTube - 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream - -Usage - formats: - $ python detect.py --weights yolov5s.pt # PyTorch - yolov5s.torchscript # TorchScript - yolov5s.onnx # ONNX Runtime or OpenCV DNN with --dnn - yolov5s_openvino_model # OpenVINO - yolov5s.engine # TensorRT - yolov5s.mlmodel # CoreML (macOS-only) - yolov5s_saved_model # TensorFlow SavedModel - yolov5s.pb # TensorFlow GraphDef - yolov5s.tflite # TensorFlow Lite - yolov5s_edgetpu.tflite # TensorFlow Edge TPU - yolov5s_paddle_model # PaddlePaddle -""" - -import argparse -import csv -import os -import platform -import sys -from pathlib import Path -import numpy as np -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 ultralytics.utils.plotting import Annotator, colors, save_one_box - -from models.common import DetectMultiBackend -from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams -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, strip_optimizer, xyxy2xywh) -from utils.torch_utils import select_device, smart_inference_mode - - -@smart_inference_mode() -def run( - weights=ROOT / 'yolov5s.pt', # model path or triton URL - source=ROOT / 'data/images', # file/dir/URL/glob/screen/0(webcam) - data=ROOT / 'data/coco128.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_csv=False, # save results in CSV format - 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/detect', # 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 -): - 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 - - # 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 - imgsz = check_img_size(imgsz, s=stride) # check image size - - # Dataloader - bs = 1 # 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: - dataset = LoadImages(source, img_size=imgsz, stride=stride, auto=pt, vid_stride=vid_stride) - vid_path, vid_writer = [None] * bs, [None] * bs - - # Run inference - model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup - seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) - 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 = model(im, augment=augment, visualize=visualize) - - # NMS - with dt[2]: - pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) - - # Second-stage classifier (optional) - # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) - - # Define the path for the CSV file - csv_path = save_dir / 'predictions.csv' - - # Create or append to the CSV file - def write_to_csv(image_name, prediction, confidence): - data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence} - with open(csv_path, mode='a', newline='') as f: - writer = csv.DictWriter(f, fieldnames=data.keys()) - if not csv_path.is_file(): - writer.writeheader() - writer.writerow(data) - - # 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 - s += '%gx%g ' % im.shape[2:] # print string - gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh - imc = im0.copy() if save_crop else im0 # for save_crop - annotator = Annotator(im0, line_width=line_thickness, example=str(names)) - - # Calculate the center of the image - img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) - min_distance = None - closest_box = None - - if len(det): - # Rescale boxes from img_size to im0 size - det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() - - # Calculate the center of the image - img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) - - # Calculate centers of all detection boxes and find the closest one to the image center - centers = np.array([[(xyxy[0].cpu() + xyxy[2].cpu()) / 2, (xyxy[1].cpu() + xyxy[3].cpu()) / 2] for *xyxy, _, _ in reversed(det)]) - distances = np.linalg.norm(centers - img_center, axis=1) - closest_idx = np.argmin(distances) - - # Draw boxes, marking the closest one in green - for j, (*xyxy, conf, cls) in enumerate(reversed(det)): - color = (0, 255, 0) if j == closest_idx else colors(int(cls), True) - annotator.box_label(xyxy, f'{names[int(cls)]} {conf:.2f}', color=color) - - - # Rescale boxes from img_size to im0 size - det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() - - # 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 - - # Write results - for *xyxy, conf, cls in reversed(det): - c = int(cls) # integer class - label = names[c] if hide_conf else f'{names[c]}' - confidence = float(conf) - confidence_str = f'{confidence:.2f}' - - if save_csv: - write_to_csv(p.name, label, confidence_str) - - 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 save_conf else (cls, *xywh) # label format - with open(f'{txt_path}.txt', 'a') as f: - f.write(('%g ' * len(line)).rstrip() % line + '\n') - - 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)) - if save_crop: - save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) - - # 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) - cv2.waitKey(1) # 1 millisecond - - # 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") - - # 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 / 'yolov5s.pt', help='model path or triton URL') - parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)') - parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.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='', 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', help='save results to *.txt') - parser.add_argument('--save-csv', action='store_true', help='save results in CSV format') - 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', 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') - 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(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop')) - run(**vars(opt)) - -# python detect.py --weights runs/train/exp10/weights/best.pt --source project/test -# python detect.py --weights runs/train/exp10/weights/best.pt --source project/test - -if __name__ == '__main__': - opt = parse_opt() - main(opt) From 33238cf579ffe22c11758ac3d24223bdc82e12ca Mon Sep 17 00:00:00 2001 From: Your Name <1260635600@qq.com> Date: Thu, 16 May 2024 21:29:00 +0800 Subject: [PATCH 3/4] Add a function to find the closest target --- detect.py | 230 +++++++++++++++++++++++++++--------------------------- 1 file changed, 114 insertions(+), 116 deletions(-) diff --git a/detect.py b/detect.py index c58aa80a68f..b72b3abc1fb 100644 --- a/detect.py +++ b/detect.py @@ -34,7 +34,7 @@ import platform import sys from pathlib import Path - +import numpy as np import torch FILE = Path(__file__).resolve() @@ -47,68 +47,54 @@ from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams -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, - strip_optimizer, - xyxy2xywh, -) +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, strip_optimizer, xyxy2xywh) from utils.torch_utils import select_device, smart_inference_mode @smart_inference_mode() def run( - weights=ROOT / "yolov5s.pt", # model path or triton URL - source=ROOT / "data/images", # file/dir/URL/glob/screen/0(webcam) - data=ROOT / "data/coco128.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_csv=False, # save results in CSV format - 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/detect", # 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 + weights=ROOT / 'yolov5s.pt', # model path or triton URL + source=ROOT / 'data/images', # file/dir/URL/glob/screen/0(webcam) + data=ROOT / 'data/coco128.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_csv=False, # save results in CSV format + 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/detect', # 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 ): source = str(source) - save_img = not nosave and not source.endswith(".txt") # save inference images + 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") + 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 / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir # Load model device = select_device(device) @@ -130,7 +116,7 @@ def run( # Run inference model.warmup(imgsz=(1 if pt or model.triton else bs, 3, *imgsz)) # warmup - seen, windows, dt = 0, [], (Profile(device=device), Profile(device=device), Profile(device=device)) + seen, windows, dt = 0, [], (Profile(), Profile(), Profile()) for path, im, im0s, vid_cap, s in dataset: with dt[0]: im = torch.from_numpy(im).to(model.device) @@ -138,22 +124,12 @@ def run( im /= 255 # 0 - 255 to 0.0 - 1.0 if len(im.shape) == 3: im = im[None] # expand for batch dim - if model.xml and im.shape[0] > 1: - ims = torch.chunk(im, im.shape[0], 0) # Inference with dt[1]: visualize = increment_path(save_dir / Path(path).stem, mkdir=True) if visualize else False - if model.xml and im.shape[0] > 1: - pred = None - for image in ims: - if pred is None: - pred = model(image, augment=augment, visualize=visualize).unsqueeze(0) - else: - pred = torch.cat((pred, model(image, augment=augment, visualize=visualize).unsqueeze(0)), dim=0) - pred = [pred, None] - else: - pred = model(im, augment=augment, visualize=visualize) + pred = model(im, augment=augment, visualize=visualize) + # NMS with dt[2]: pred = non_max_suppression(pred, conf_thres, iou_thres, classes, agnostic_nms, max_det=max_det) @@ -162,13 +138,12 @@ def run( # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Define the path for the CSV file - csv_path = save_dir / "predictions.csv" + csv_path = save_dir / 'predictions.csv' # Create or append to the CSV file def write_to_csv(image_name, prediction, confidence): - """Writes prediction data for an image to a CSV file, appending if the file exists.""" - data = {"Image Name": image_name, "Prediction": prediction, "Confidence": confidence} - with open(csv_path, mode="a", newline="") as f: + data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence} + with open(csv_path, mode='a', newline='') as f: writer = csv.DictWriter(f, fieldnames=data.keys()) if not csv_path.is_file(): writer.writeheader() @@ -179,21 +154,44 @@ def write_to_csv(image_name, prediction, confidence): seen += 1 if webcam: # batch_size >= 1 p, im0, frame = path[i], im0s[i].copy(), dataset.count - s += f"{i}: " + s += f'{i}: ' else: - p, im0, frame = path, im0s.copy(), getattr(dataset, "frame", 0) + 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 - s += "%gx%g " % im.shape[2:] # print string + txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # im.txt + s += '%gx%g ' % im.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh imc = im0.copy() if save_crop else im0 # for save_crop annotator = Annotator(im0, line_width=line_thickness, example=str(names)) + + # Calculate the center of the image + img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) + min_distance = None + closest_box = None + if len(det): # Rescale boxes from img_size to im0 size det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() + # Calculate the center of the image + img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) + + # Calculate centers of all detection boxes and find the closest one to the image center + centers = np.array([[(xyxy[0].cpu() + xyxy[2].cpu()) / 2, (xyxy[1].cpu() + xyxy[3].cpu()) / 2] for *xyxy, _, _ in reversed(det)]) + distances = np.linalg.norm(centers - img_center, axis=1) + closest_idx = np.argmin(distances) + + # Draw boxes, marking the closest one in green + for j, (*xyxy, conf, cls) in enumerate(reversed(det)): + color = (0, 255, 0) if j == closest_idx else colors(int(cls), True) + annotator.box_label(xyxy, f'{names[int(cls)]} {conf:.2f}', color=color) + + + # Rescale boxes from img_size to im0 size + det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() + # Print results for c in det[:, 5].unique(): n = (det[:, 5] == c).sum() # detections per class @@ -202,9 +200,9 @@ def write_to_csv(image_name, prediction, confidence): # Write results for *xyxy, conf, cls in reversed(det): c = int(cls) # integer class - label = names[c] if hide_conf else f"{names[c]}" + label = names[c] if hide_conf else f'{names[c]}' confidence = float(conf) - confidence_str = f"{confidence:.2f}" + confidence_str = f'{confidence:.2f}' if save_csv: write_to_csv(p.name, label, confidence_str) @@ -212,20 +210,20 @@ def write_to_csv(image_name, prediction, confidence): 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 save_conf else (cls, *xywh) # label format - with open(f"{txt_path}.txt", "a") as f: - f.write(("%g " * len(line)).rstrip() % line + "\n") + with open(f'{txt_path}.txt', 'a') as f: + f.write(('%g ' * len(line)).rstrip() % line + '\n') 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}") + 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)) if save_crop: - save_one_box(xyxy, imc, file=save_dir / "crops" / names[c] / f"{p.stem}.jpg", BGR=True) + save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) # Stream results im0 = annotator.result() if view_img: - if platform.system() == "Linux" and p not in windows: + 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]) @@ -234,7 +232,7 @@ def write_to_csv(image_name, prediction, confidence): # Save results (image with detections) if save_img: - if dataset.mode == "image": + if dataset.mode == 'image': cv2.imwrite(save_path, im0) else: # 'video' or 'stream' if vid_path[i] != save_path: # new video @@ -247,54 +245,53 @@ def write_to_csv(image_name, prediction, confidence): 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)) + 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") # 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) + 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 "" + 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(): - """Parses command-line arguments for YOLOv5 detection, setting inference options and model configurations.""" parser = argparse.ArgumentParser() - parser.add_argument("--weights", nargs="+", type=str, default=ROOT / "yolov5s.pt", help="model path or triton URL") - parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)") - parser.add_argument("--data", type=str, default=ROOT / "data/coco128.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="", 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", help="save results to *.txt") - parser.add_argument("--save-csv", action="store_true", help="save results in CSV format") - 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", 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('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path or triton URL') + parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)') + parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.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='', 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', help='save results to *.txt') + parser.add_argument('--save-csv', action='store_true', help='save results in CSV format') + 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', 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') opt = parser.parse_args() opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand print_args(vars(opt)) @@ -302,11 +299,12 @@ def parse_opt(): def main(opt): - """Executes YOLOv5 model inference with given options, checking requirements before running the model.""" - check_requirements(ROOT / "requirements.txt", exclude=("tensorboard", "thop")) + check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop')) run(**vars(opt)) +# python detect.py --weights runs/train/exp10/weights/best.pt --source project/test +# python detect.py --weights runs/train/exp10/weights/best.pt --source project/test -if __name__ == "__main__": +if __name__ == '__main__': opt = parse_opt() main(opt) From c962fca82842e347ffa45d4a8c54ed97dcbbbfe8 Mon Sep 17 00:00:00 2001 From: UltralyticsAssistant Date: Thu, 16 May 2024 13:41:57 +0000 Subject: [PATCH 4/4] Auto-format by https://ultralytics.com/actions --- detect.py | 196 ++++++++++++++++++++++++++++++------------------------ 1 file changed, 108 insertions(+), 88 deletions(-) diff --git a/detect.py b/detect.py index b72b3abc1fb..5a5b013b9df 100644 --- a/detect.py +++ b/detect.py @@ -34,6 +34,7 @@ import platform import sys from pathlib import Path + import numpy as np import torch @@ -47,54 +48,68 @@ from models.common import DetectMultiBackend from utils.dataloaders import IMG_FORMATS, VID_FORMATS, LoadImages, LoadScreenshots, LoadStreams -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, strip_optimizer, xyxy2xywh) +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, + strip_optimizer, + xyxy2xywh, +) from utils.torch_utils import select_device, smart_inference_mode @smart_inference_mode() def run( - weights=ROOT / 'yolov5s.pt', # model path or triton URL - source=ROOT / 'data/images', # file/dir/URL/glob/screen/0(webcam) - data=ROOT / 'data/coco128.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_csv=False, # save results in CSV format - 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/detect', # 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 + weights=ROOT / "yolov5s.pt", # model path or triton URL + source=ROOT / "data/images", # file/dir/URL/glob/screen/0(webcam) + data=ROOT / "data/coco128.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_csv=False, # save results in CSV format + 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/detect", # 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 ): source = str(source) - save_img = not nosave and not source.endswith('.txt') # save inference images + 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') + 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 / "labels" if save_txt else save_dir).mkdir(parents=True, exist_ok=True) # make dir # Load model device = select_device(device) @@ -138,12 +153,12 @@ def run( # pred = utils.general.apply_classifier(pred, classifier_model, im, im0s) # Define the path for the CSV file - csv_path = save_dir / 'predictions.csv' + csv_path = save_dir / "predictions.csv" # Create or append to the CSV file def write_to_csv(image_name, prediction, confidence): - data = {'Image Name': image_name, 'Prediction': prediction, 'Confidence': confidence} - with open(csv_path, mode='a', newline='') as f: + data = {"Image Name": image_name, "Prediction": prediction, "Confidence": confidence} + with open(csv_path, mode="a", newline="") as f: writer = csv.DictWriter(f, fieldnames=data.keys()) if not csv_path.is_file(): writer.writeheader() @@ -154,14 +169,14 @@ def write_to_csv(image_name, prediction, confidence): seen += 1 if webcam: # batch_size >= 1 p, im0, frame = path[i], im0s[i].copy(), dataset.count - s += f'{i}: ' + s += f"{i}: " else: - p, im0, frame = path, im0s.copy(), getattr(dataset, 'frame', 0) + 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 - s += '%gx%g ' % im.shape[2:] # print string + txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}") # im.txt + s += "%gx%g " % im.shape[2:] # print string gn = torch.tensor(im0.shape)[[1, 0, 1, 0]] # normalization gain whwh imc = im0.copy() if save_crop else im0 # for save_crop annotator = Annotator(im0, line_width=line_thickness, example=str(names)) @@ -179,15 +194,19 @@ def write_to_csv(image_name, prediction, confidence): img_center = np.array([im0.shape[1] // 2, im0.shape[0] // 2]) # Calculate centers of all detection boxes and find the closest one to the image center - centers = np.array([[(xyxy[0].cpu() + xyxy[2].cpu()) / 2, (xyxy[1].cpu() + xyxy[3].cpu()) / 2] for *xyxy, _, _ in reversed(det)]) + centers = np.array( + [ + [(xyxy[0].cpu() + xyxy[2].cpu()) / 2, (xyxy[1].cpu() + xyxy[3].cpu()) / 2] + for *xyxy, _, _ in reversed(det) + ] + ) distances = np.linalg.norm(centers - img_center, axis=1) closest_idx = np.argmin(distances) # Draw boxes, marking the closest one in green for j, (*xyxy, conf, cls) in enumerate(reversed(det)): color = (0, 255, 0) if j == closest_idx else colors(int(cls), True) - annotator.box_label(xyxy, f'{names[int(cls)]} {conf:.2f}', color=color) - + annotator.box_label(xyxy, f"{names[int(cls)]} {conf:.2f}", color=color) # Rescale boxes from img_size to im0 size det[:, :4] = scale_boxes(im.shape[2:], det[:, :4], im0.shape).round() @@ -200,9 +219,9 @@ def write_to_csv(image_name, prediction, confidence): # Write results for *xyxy, conf, cls in reversed(det): c = int(cls) # integer class - label = names[c] if hide_conf else f'{names[c]}' + label = names[c] if hide_conf else f"{names[c]}" confidence = float(conf) - confidence_str = f'{confidence:.2f}' + confidence_str = f"{confidence:.2f}" if save_csv: write_to_csv(p.name, label, confidence_str) @@ -210,20 +229,20 @@ def write_to_csv(image_name, prediction, confidence): 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 save_conf else (cls, *xywh) # label format - with open(f'{txt_path}.txt', 'a') as f: - f.write(('%g ' * len(line)).rstrip() % line + '\n') + with open(f"{txt_path}.txt", "a") as f: + f.write(("%g " * len(line)).rstrip() % line + "\n") 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}') + 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)) if save_crop: - save_one_box(xyxy, imc, file=save_dir / 'crops' / names[c] / f'{p.stem}.jpg', BGR=True) + save_one_box(xyxy, imc, file=save_dir / "crops" / names[c] / f"{p.stem}.jpg", BGR=True) # Stream results im0 = annotator.result() if view_img: - if platform.system() == 'Linux' and p not in windows: + 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]) @@ -232,7 +251,7 @@ def write_to_csv(image_name, prediction, confidence): # Save results (image with detections) if save_img: - if dataset.mode == 'image': + if dataset.mode == "image": cv2.imwrite(save_path, im0) else: # 'video' or 'stream' if vid_path[i] != save_path: # new video @@ -245,18 +264,18 @@ def write_to_csv(image_name, prediction, confidence): 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)) + 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") # 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) + 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 '' + 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) @@ -264,34 +283,34 @@ def write_to_csv(image_name, prediction, confidence): def parse_opt(): parser = argparse.ArgumentParser() - parser.add_argument('--weights', nargs='+', type=str, default=ROOT / 'yolov5s.pt', help='model path or triton URL') - parser.add_argument('--source', type=str, default=ROOT / 'data/images', help='file/dir/URL/glob/screen/0(webcam)') - parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.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='', 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', help='save results to *.txt') - parser.add_argument('--save-csv', action='store_true', help='save results in CSV format') - 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', 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("--weights", nargs="+", type=str, default=ROOT / "yolov5s.pt", help="model path or triton URL") + parser.add_argument("--source", type=str, default=ROOT / "data/images", help="file/dir/URL/glob/screen/0(webcam)") + parser.add_argument("--data", type=str, default=ROOT / "data/coco128.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="", 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", help="save results to *.txt") + parser.add_argument("--save-csv", action="store_true", help="save results in CSV format") + 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", 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") opt = parser.parse_args() opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand print_args(vars(opt)) @@ -299,12 +318,13 @@ def parse_opt(): def main(opt): - check_requirements(ROOT / 'requirements.txt', exclude=('tensorboard', 'thop')) + check_requirements(ROOT / "requirements.txt", exclude=("tensorboard", "thop")) run(**vars(opt)) + # python detect.py --weights runs/train/exp10/weights/best.pt --source project/test # python detect.py --weights runs/train/exp10/weights/best.pt --source project/test -if __name__ == '__main__': +if __name__ == "__main__": opt = parse_opt() main(opt)