diff --git a/data/my_date.yaml b/data/my_date.yaml index d1960edc9..792e45830 100644 --- a/data/my_date.yaml +++ b/data/my_date.yaml @@ -6,17 +6,26 @@ # └── datasets # └── coco128 ← downloads here - # Train/val/test sets as 1) dir: path/to/imgs, 2) file: path/to/imgs.txt, or 3) list: [path/to/imgs1, path/to/imgs2, ..] -path: D:/lzy/yolov5/yolov5/data_org/yolo_dataset # dataset root dir -train: train/images # train images (relative to 'path') 128 images -val: valid/images # val images (relative to 'path') 128 images +path: D:/lzy/yolov5/yolov5/data_org/yolo_dataset # dataset root dir +train: train/images # train images (relative to 'path') 128 images +val: valid/images # val images (relative to 'path') 128 images test: test/images # test images (optional) # Classes -nc: 11 # number of classes -names: ['animasls', 'cat', 'chicken', 'cow', 'dog', 'fox', - 'goat', 'horse', 'person', 'recoon', 'skunk'] # class names - +nc: 11 # number of classes +names: [ + "animasls", + "cat", + "chicken", + "cow", + "dog", + "fox", + "goat", + "horse", + "person", + "recoon", + "skunk", + ] # class names # Download script/URL (optional) diff --git a/data_process/data_process.ipynb b/data_process/data_process.ipynb index 485f3e37c..8af39ea89 100644 --- a/data_process/data_process.ipynb +++ b/data_process/data_process.ipynb @@ -7,9 +7,10 @@ "metadata": {}, "outputs": [], "source": [ + "import json\n", "import os\n", - "import cv2 as cv\n", - "import json" + "\n", + "import cv2 as cv" ] }, { @@ -19,7 +20,7 @@ "metadata": {}, "outputs": [], "source": [ - "img = cv.imread(r\"D:\\lzy\\yolov5\\yolov5\\data_org\\yolo_dataset\\test\\images\\9_jpg.rf.eb8e232922688878a850763f2127e8fd.jpg\")\n" + "img = cv.imread(r\"D:\\lzy\\yolov5\\yolov5\\data_org\\yolo_dataset\\test\\images\\9_jpg.rf.eb8e232922688878a850763f2127e8fd.jpg\")" ] }, { @@ -67,7 +68,7 @@ "outputs": [], "source": [ "# 读取文件\n", - "with open(label_path, 'r') as f:\n", + "with open(label_path) as f:\n", " content = json.load(f)\n", "pass" ] @@ -81,8 +82,8 @@ "source": [ "# 创建一个id到图片名称的映射，以字典形式存储\n", "dict_id2img = dict()\n", - "for img_info in content['images']:\n", - " dict_id2img[img_info['id']] = img_info['file_name']\n", + "for img_info in content[\"images\"]:\n", + " dict_id2img[img_info[\"id\"]] = img_info[\"file_name\"]\n", "pass" ] }, @@ -93,8 +94,8 @@ "metadata": {}, "outputs": [], "source": [ - "img_height = content['images'][0]['height']\n", - "img_width = content['images'][0]['height']" + "img_height = content[\"images\"][0][\"height\"]\n", + "img_width = content[\"images\"][0][\"height\"]" ] }, { @@ -105,15 +106,15 @@ "outputs": [], "source": [ "# 开始读取标签信息，处理后写入txt文件\n", - "for label_info in content['annotations']:\n", - " img_name = dict_id2img[label_info['image_id']]\n", - " class_name = label_info['category_id']\n", - " x_center = (label_info['bbox'][0] + label_info['bbox'][2] / 2) / img_height\n", - " y_center = (label_info['bbox'][1] + label_info['bbox'][3] / 2) / img_width\n", - " w = label_info['bbox'][1] / 640\n", - " h = label_info['bbox'][3] / 640\n", - " with open(os.path.join(img_folder.replace(\"images\", \"labels\"), img_name.replace(\".jpg\", \".txt\")), 'a') as f:\n", - " f.write(\"{} {} {} {} {}\\n\".format(class_name, x_center, y_center, w, h))" + "for label_info in content[\"annotations\"]:\n", + " img_name = dict_id2img[label_info[\"image_id\"]]\n", + " class_name = label_info[\"category_id\"]\n", + " x_center = (label_info[\"bbox\"][0] + label_info[\"bbox\"][2] / 2) / img_height\n", + " y_center = (label_info[\"bbox\"][1] + label_info[\"bbox\"][3] / 2) / img_width\n", + " w = label_info[\"bbox\"][1] / 640\n", + " h = label_info[\"bbox\"][3] / 640\n", + " with open(os.path.join(img_folder.replace(\"images\", \"labels\"), img_name.replace(\".jpg\", \".txt\")), \"a\") as f:\n", + " f.write(f\"{class_name} {x_center} {y_center} {w} {h}\\n\")" ] } ], diff --git a/detect copy.py b/detect copy.py index c9787c2cf..1f3eae81a 100644 --- a/detect copy.py +++ b/detect copy.py @@ -24,88 +24,110 @@ ROOT = Path(os.path.relpath(ROOT, Path.cwd())) # relative from models.experimental import attempt_load from utils.datasets import LoadImages, LoadStreams -from utils.general import apply_classifier, check_img_size, check_imshow, check_requirements, check_suffix, colorstr, \ - increment_path, non_max_suppression, print_args, save_one_box, scale_coords, set_logging, \ - strip_optimizer, xyxy2xywh +from utils.general import ( + apply_classifier, + check_img_size, + check_imshow, + check_requirements, + check_suffix, + colorstr, + increment_path, + non_max_suppression, + print_args, + save_one_box, + scale_coords, + set_logging, + strip_optimizer, + xyxy2xywh, +) from utils.plots import Annotator, colors from utils.torch_utils import load_classifier, select_device, time_sync @torch.no_grad() -def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) - source=ROOT / 'data/images', # file/dir/URL/glob, 0 for webcam - imgsz=640, # inference size (pixels) - 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/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 - ): +def run( + weights=ROOT / "yolov5s.pt", # model.pt path(s) + source=ROOT / "data/images", # file/dir/URL/glob, 0 for webcam + imgsz=640, # inference size (pixels) + 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/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 +): source = str(source) - save_img = not nosave and not source.endswith('.txt') # save inference images - webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith( - ('rtsp://', 'rtmp://', 'http://', 'https://')) + save_img = not nosave and not source.endswith(".txt") # save inference images + webcam = ( + source.isnumeric() + or source.endswith(".txt") + or source.lower().startswith(("rtsp://", "rtmp://", "http://", "https://")) + ) # 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 # Initialize set_logging() device = select_device(device) - half &= device.type != 'cpu' # half precision only supported on CUDA + half &= device.type != "cpu" # half precision only supported on CUDA # Load model w = str(weights[0] if isinstance(weights, list) else weights) - classify, suffix, suffixes = False, Path(w).suffix.lower(), ['.pt', '.onnx', '.tflite', '.pb', ''] + classify, suffix, suffixes = False, Path(w).suffix.lower(), [".pt", ".onnx", ".tflite", ".pb", ""] check_suffix(w, suffixes) # check weights have acceptable suffix pt, onnx, tflite, pb, saved_model = (suffix == x for x in suffixes) # backend booleans - stride, names = 64, [f'class{i}' for i in range(1000)] # assign defaults + stride, names = 64, [f"class{i}" for i in range(1000)] # assign defaults if pt: - model = torch.jit.load(w) if 'torchscript' in w else attempt_load(weights, map_location=device) + model = torch.jit.load(w) if "torchscript" in w else attempt_load(weights, map_location=device) stride = int(model.stride.max()) # model stride - names = model.module.names if hasattr(model, 'module') else model.names # get class names + names = model.module.names if hasattr(model, "module") else model.names # get class names if half: model.half() # to FP16 if classify: # second-stage classifier - modelc = load_classifier(name='resnet50', n=2) # initialize - modelc.load_state_dict(torch.load('resnet50.pt', map_location=device)['model']).to(device).eval() + modelc = load_classifier(name="resnet50", n=2) # initialize + modelc.load_state_dict(torch.load("resnet50.pt", map_location=device)["model"]).to(device).eval() elif onnx: if dnn: # check_requirements(('opencv-python>=4.5.4',)) net = cv2.dnn.readNetFromONNX(w) else: - check_requirements(('onnx', 'onnxruntime')) + check_requirements(("onnx", "onnxruntime")) import onnxruntime + session = onnxruntime.InferenceSession(w, None) else: # TensorFlow models - check_requirements(('tensorflow>=2.4.1',)) + check_requirements(("tensorflow>=2.4.1",)) import tensorflow as tf + if pb: # https://www.tensorflow.org/guide/migrate#a_graphpb_or_graphpbtxt + def wrap_frozen_graph(gd, inputs, outputs): x = tf.compat.v1.wrap_function(lambda: tf.compat.v1.import_graph_def(gd, name=""), []) # wrapped import - return x.prune(tf.nest.map_structure(x.graph.as_graph_element, inputs), - tf.nest.map_structure(x.graph.as_graph_element, outputs)) + return x.prune( + tf.nest.map_structure(x.graph.as_graph_element, inputs), + tf.nest.map_structure(x.graph.as_graph_element, outputs), + ) graph_def = tf.Graph().as_graph_def() - graph_def.ParseFromString(open(w, 'rb').read()) + graph_def.ParseFromString(open(w, "rb").read()) frozen_func = wrap_frozen_graph(gd=graph_def, inputs="x:0", outputs="Identity:0") elif saved_model: model = tf.keras.models.load_model(w) @@ -114,7 +136,7 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) interpreter.allocate_tensors() # allocate input_details = interpreter.get_input_details() # inputs output_details = interpreter.get_output_details() # outputs - int8 = input_details[0]['dtype'] == np.uint8 # is TFLite quantized uint8 model + int8 = input_details[0]["dtype"] == np.uint8 # is TFLite quantized uint8 model imgsz = check_img_size(imgsz, s=stride) # check image size # Dataloader @@ -129,13 +151,13 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) vid_path, vid_writer = [None] * bs, [None] * bs # Run inference - if pt and device.type != 'cpu': + if pt and device.type != "cpu": model(torch.zeros(1, 3, *imgsz).to(device).type_as(next(model.parameters()))) # run once dt, seen = [0.0, 0.0, 0.0], 0 for path, img, im0s, vid_cap in dataset: t1 = time_sync() if onnx: - img = img.astype('float32') + img = img.astype("float32") else: img = torch.from_numpy(img).to(device) img = img.half() if half else img.float() # uint8 to fp16/32 @@ -163,13 +185,13 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) pred = model(imn, training=False).numpy() elif tflite: if int8: - scale, zero_point = input_details[0]['quantization'] + scale, zero_point = input_details[0]["quantization"] imn = (imn / scale + zero_point).astype(np.uint8) # de-scale - interpreter.set_tensor(input_details[0]['index'], imn) + interpreter.set_tensor(input_details[0]["index"], imn) interpreter.invoke() - pred = interpreter.get_tensor(output_details[0]['index']) + pred = interpreter.get_tensor(output_details[0]["index"]) if int8: - scale, zero_point = output_details[0]['quantization'] + scale, zero_point = output_details[0]["quantization"] pred = (pred.astype(np.float32) - zero_point) * scale # re-scale pred[..., 0] *= imgsz[1] # x pred[..., 1] *= imgsz[0] # y @@ -191,14 +213,14 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) for i, det in enumerate(pred): # per image seen += 1 if webcam: # batch_size >= 1 - p, s, im0, frame = path[i], f'{i}: ', im0s[i].copy(), dataset.count + p, s, im0, frame = path[i], f"{i}: ", im0s[i].copy(), dataset.count else: - p, s, im0, frame = path, '', im0s.copy(), getattr(dataset, 'frame', 0) + p, s, im0, frame = path, "", im0s.copy(), getattr(dataset, "frame", 0) p = Path(p) # to Path save_path = str(save_dir / p.name) # img.jpg - txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}') # img.txt - s += '%gx%g ' % img.shape[2:] # print string + txt_path = str(save_dir / "labels" / p.stem) + ("" if dataset.mode == "image" else f"_{frame}") # img.txt + s += "{:g}x{:g} ".format(*img.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)) @@ -216,18 +238,18 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) 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(txt_path + '.txt', 'a') as f: - f.write(('%g ' * len(line)).rstrip() % line + '\n') + with open(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) # Print time (inference-only) - print(f'{s}Done. ({t3 - t2:.3f}s)') + print(f"{s}Done. ({t3 - t2:.3f}s)") # Stream results im0 = annotator.result() @@ -237,7 +259,7 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) # 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 @@ -250,15 +272,15 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT)) else: # stream fps, w, h = 30, im0.shape[1], im0.shape[0] - save_path += '.mp4' - vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h)) + save_path += ".mp4" + vid_writer[i] = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*"mp4v"), fps, (w, h)) vid_writer[i].write(im0) # Print results - t = tuple(x / seen * 1E3 for x in dt) # speeds per image - print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {(1, 3, *imgsz)}' % t) + t = tuple(x / seen * 1e3 for x in dt) # speeds per image + print(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 "" print(f"Results saved to {colorstr('bold', save_dir)}{s}") if update: strip_optimizer(weights) # update model (to fix SourceChangeWarning) @@ -266,31 +288,42 @@ def run(weights=ROOT / 'yolov5s.pt', # model.pt path(s) def parse_opt(): parser = argparse.ArgumentParser() - parser.add_argument('--weights', nargs='+', type=str, default=r'D:\lzy\yolov5\yolov5\runs\train\exp15\weights\best.pt', help='model path(s)') - parser.add_argument('--source', type=str, default=r'D:\lzy\yolov5\yolov5\data_org\yolo_dataset\test\images', help='file/dir/URL/glob, 0 for webcam') - 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-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( + "--weights", + nargs="+", + type=str, + default=r"D:\lzy\yolov5\yolov5\runs\train\exp15\weights\best.pt", + help="model path(s)", + ) + parser.add_argument( + "--source", + type=str, + default=r"D:\lzy\yolov5\yolov5\data_org\yolo_dataset\test\images", + help="file/dir/URL/glob, 0 for webcam", + ) + 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-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") opt = parser.parse_args() opt.imgsz *= 2 if len(opt.imgsz) == 1 else 1 # expand print_args(FILE.stem, opt) @@ -298,7 +331,7 @@ def parse_opt(): def main(opt): - check_requirements(exclude=('tensorboard', 'thop')) + check_requirements(exclude=("tensorboard", "thop")) run(**vars(opt)) diff --git a/train.py b/train.py index cda4b5120..c71185b3e 100644 --- a/train.py +++ b/train.py @@ -51,7 +51,7 @@ from utils.autoanchor import check_anchors from utils.autobatch import check_train_batch_size from utils.callbacks import Callbacks from utils.dataloaders import create_dataloader -from utils.downloads import attempt_download, is_url +from utils.downloads import attempt_download from utils.general import ( LOGGER, TQDM_BAR_FORMAT, @@ -79,7 +79,6 @@ from utils.general import ( yaml_save, ) from utils.loggers import LOGGERS, Loggers -from utils.loggers.comet.comet_utils import check_comet_resume from utils.loss import ComputeLoss from utils.metrics import fitness from utils.plots import plot_evolve @@ -564,38 +563,38 @@ def parse_opt(known=False): - Tutorial: https://docs.ultralytics.com/yolov5/tutorials/train_custom_data """ parser = argparse.ArgumentParser() - parser.add_argument('--weights', type=str, default=ROOT / 'yolov5s.pt', help='initial weights path') - parser.add_argument('--cfg', type=str, default='', help='model.yaml path') - parser.add_argument('--data', type=str, default=ROOT / 'data/coco128.yaml', help='dataset.yaml path') - parser.add_argument('--hyp', type=str, default=ROOT / 'data/hyps/hyp.scratch.yaml', help='hyperparameters path') - parser.add_argument('--epochs', type=int, default=300) - parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs') - parser.add_argument('--imgsz', '--img', '--img-size', type=int, default=640, help='train, val image size (pixels)') - parser.add_argument('--rect', action='store_true', help='rectangular training') - parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training') - parser.add_argument('--nosave', action='store_true', help='only save final checkpoint') - parser.add_argument('--noval', action='store_true', help='only validate final epoch') - parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check') - parser.add_argument('--evolve', type=int, nargs='?', const=300, help='evolve hyperparameters for x generations') - parser.add_argument('--bucket', type=str, default='', help='gsutil bucket') - parser.add_argument('--cache', type=str, nargs='?', const='ram', help='--cache images in "ram" (default) or "disk"') - parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training') - parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu') - parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%') - parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class') - parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer') - parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode') - parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers') - parser.add_argument('--project', default=ROOT / 'runs/train', help='save to project/name') - parser.add_argument('--name', default='exp', help='save to project/name') - parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment') - parser.add_argument('--quad', action='store_true', help='quad dataloader') - parser.add_argument('--linear-lr', action='store_true', help='linear LR') - parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon') - parser.add_argument('--patience', type=int, default=100, help='EarlyStopping patience (epochs without improvement)') - parser.add_argument('--freeze', type=int, default=0, help='Number of layers to freeze. backbone=10, all=24') - parser.add_argument('--save-period', type=int, default=-1, help='Save checkpoint every x epochs (disabled if < 1)') - parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify') + parser.add_argument("--weights", type=str, default=ROOT / "yolov5s.pt", help="initial weights path") + parser.add_argument("--cfg", type=str, default="", help="model.yaml path") + parser.add_argument("--data", type=str, default=ROOT / "data/coco128.yaml", help="dataset.yaml path") + parser.add_argument("--hyp", type=str, default=ROOT / "data/hyps/hyp.scratch.yaml", help="hyperparameters path") + parser.add_argument("--epochs", type=int, default=300) + parser.add_argument("--batch-size", type=int, default=16, help="total batch size for all GPUs") + parser.add_argument("--imgsz", "--img", "--img-size", type=int, default=640, help="train, val image size (pixels)") + parser.add_argument("--rect", action="store_true", help="rectangular training") + parser.add_argument("--resume", nargs="?", const=True, default=False, help="resume most recent training") + parser.add_argument("--nosave", action="store_true", help="only save final checkpoint") + parser.add_argument("--noval", action="store_true", help="only validate final epoch") + parser.add_argument("--noautoanchor", action="store_true", help="disable autoanchor check") + parser.add_argument("--evolve", type=int, nargs="?", const=300, help="evolve hyperparameters for x generations") + parser.add_argument("--bucket", type=str, default="", help="gsutil bucket") + parser.add_argument("--cache", type=str, nargs="?", const="ram", help='--cache images in "ram" (default) or "disk"') + parser.add_argument("--image-weights", action="store_true", help="use weighted image selection for training") + parser.add_argument("--device", default="", help="cuda device, i.e. 0 or 0,1,2,3 or cpu") + parser.add_argument("--multi-scale", action="store_true", help="vary img-size +/- 50%%") + parser.add_argument("--single-cls", action="store_true", help="train multi-class data as single-class") + parser.add_argument("--adam", action="store_true", help="use torch.optim.Adam() optimizer") + parser.add_argument("--sync-bn", action="store_true", help="use SyncBatchNorm, only available in DDP mode") + parser.add_argument("--workers", type=int, default=8, help="maximum number of dataloader workers") + parser.add_argument("--project", default=ROOT / "runs/train", help="save to project/name") + parser.add_argument("--name", default="exp", help="save to project/name") + parser.add_argument("--exist-ok", action="store_true", help="existing project/name ok, do not increment") + parser.add_argument("--quad", action="store_true", help="quad dataloader") + parser.add_argument("--linear-lr", action="store_true", help="linear LR") + parser.add_argument("--label-smoothing", type=float, default=0.0, help="Label smoothing epsilon") + parser.add_argument("--patience", type=int, default=100, help="EarlyStopping patience (epochs without improvement)") + parser.add_argument("--freeze", type=int, default=0, help="Number of layers to freeze. backbone=10, all=24") + parser.add_argument("--save-period", type=int, default=-1, help="Save checkpoint every x epochs (disabled if < 1)") + parser.add_argument("--local_rank", type=int, default=-1, help="DDP parameter, do not modify") # Logger arguments parser.add_argument("--entity", default=None, help="Entity") @@ -634,11 +633,11 @@ def main(opt, callbacks=Callbacks()): # Resume if opt.resume and not check_wandb_resume(opt) and not opt.evolve: # resume an interrupted run ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run() # specified or most recent path - assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist' - with open(Path(ckpt).parent.parent / 'opt.yaml', errors='ignore') as f: + assert os.path.isfile(ckpt), "ERROR: --resume checkpoint does not exist" + with open(Path(ckpt).parent.parent / "opt.yaml", errors="ignore") as f: opt = argparse.Namespace(**yaml.safe_load(f)) # replace - opt.cfg, opt.weights, opt.resume = '', ckpt, True # reinstate - LOGGER.info(f'Resuming training from {ckpt}') + opt.cfg, opt.weights, opt.resume = "", ckpt, True # reinstate + LOGGER.info(f"Resuming training from {ckpt}") else: opt.data, opt.cfg, opt.hyp, opt.weights, opt.project = ( check_file(opt.data),