信息如下： Traceback (most recent call last):24493 .........] ETA: 41m File "preview.py", line 33, in for i, sample in enumerate(preview): File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 345, in next data = self._next_data() File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 385, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/opt/conda/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/home/lungchi/easy_detection/dataloader/list_dataset.py", line 21, in getitem return dataset[index - total] File "/home/lungchi/easy_detection/dataloader/voc.py", line 213, in getitem 'labels': labels File "/opt/conda/lib/python3.7/site-packages/albumentations/core/composition.py", line 188, in call p.preprocess(data) File "/opt/conda/lib/python3.7/site-packages/albumentations/core/utils.py", line 84, in preprocess data[data_name] = self.check_and_convert(data[data_name], rows, cols, direction="to") File "/opt/conda/lib/python3.7/site-packages/albumentations/core/utils.py", line 92, in check_and_convert return self.convert_to_albumentations(data, rows, cols) File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 51, in convert_to_albumentations return convert_bboxes_to_albumentations(data, self.params.format, rows, cols, check_validity=True) File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 306, in convert_bboxes_to_albumentations return [convert_bbox_to_albumentations(bbox, source_format, rows, cols, check_validity) for bbox in bboxes] File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 306, in return [convert_bbox_to_albumentations(bbox, source_format, rows, cols, check_validity) for bbox in bboxes] File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 254, in convert_bbox_to_albumentations check_bbox(bbox) File "/opt/conda/lib/python3.7/site-packages/albumentations/augmentations/bbox_utils.py", line 333, in check_bbox "to be in the range [0.0, 1.0], got {value}.".format(bbox=bbox, name=name, value=value) ValueError: Expected y_max for bbox (0.19440914866581957, 0.14192139737991266, 0.7903430749682337, 1.0087336244541485, 1) to be in the range [0.0, 1.0], got 1.0087336244541485.

Use Yolo2, train VOC ok, eval ok, but when I try to convert to onnx model, failed~

convert by

input_shape = (3, 224, 224)
torch.randn(1, input_shape[0], input_shape[1], input_shape[2], dtype=torch.float32, requires_grad=False).to(device)
torch.onnx.export(model, input, "out/model.onnx", export_params=True, input_names = ["input0"], output_names=["output0"])

error:

  File "/home/neucrack/project/others/detection_template/utils/convert.py", line 15, in torch_to_onnx
    torch.onnx.export(net, x, out_name, export_params=True, input_names = input_names, output_names=output_names)
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/onnx/__init__.py", line 225, in export
    return utils.export(model, args, f, export_params, verbose, training,
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/onnx/utils.py", line 85, in export
    _export(model, args, f, export_params, verbose, training, input_names, output_names,
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/onnx/utils.py", line 632, in _export
    _model_to_graph(model, args, verbose, input_names,
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/onnx/utils.py", line 409, in _model_to_graph
    graph, params, torch_out = _create_jit_graph(model, args,
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/onnx/utils.py", line 379, in _create_jit_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/onnx/utils.py", line 342, in _trace_and_get_graph_from_model
    torch.jit._get_trace_graph(model, args, strict=False, _force_outplace=False, _return_inputs_states=True)
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/jit/_trace.py", line 1149, in _get_trace_graph
    outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/jit/_trace.py", line 126, in forward
    graph, out = torch._C._create_graph_by_tracing(
  File "/home/neucrack/miniconda3/lib/python3.8/site-packages/torch/jit/_trace.py", line 120, in wrapper
    out_vars, _ = _flatten(outs)
RuntimeError: Only tuples, lists and Variables supported as JIT inputs/outputs. Dictionaries and strings are also accepted but their usage is not recommended. But got unsupported type numpy.ndarray

get_started.md中原话： “4. 如果需要使用Tensorboard可视化预测结果，可以在上面的命令最后加上--vis参数。然后运行tensorboard --logdir results/cache查看检测的可视化结果”， 但是查看了代码发现，并没有预测结果可视化功能，请问是还没更新吗

按您的步骤来，在运行单卡训练程序python3 train.py --config configs/faster_rcnn_voc.yml时遇到报错 ：TypeError: resnet50() missing 1 required positional argument: 'epoch' 请问如何解决这个报错

具体如下： Use dataset: datasets/voc, split: train Load Anno... Step: [=========== 16551/16551 =====>] ETA: 0s 57m
aeroplane: 1171 (2.92%) bicycle: 1064 (2.66%) bird: 1605 (4.01%) boat: 1140 (2.85%) bottle: 1764 (4.40%) bus: 822 (2.05%) car: 3267 (8.16%) cat: 1593 (3.98%) chair: 3152 (7.87%) cow: 847 (2.11%) diningtable: 824 (2.06%) dog: 2025 (5.06%) horse: 1072 (2.68%) motorbike: 1052 (2.63%) person: 13256 (33.09%) pottedplant: 1487 (3.71%) sheep: 1070 (2.67%) sofa: 814 (2.03%) train: 925 (2.31%) tvmonitor: 1108 (2.77%) Total bboxes: 40058 7165 difficult bboxes ignored. Use dataset: datasets/voc, split: test Load Anno... Step: [=========== 4952/4952 =======>] ETA: 0s 30m
aeroplane: 285 (2.37%) bicycle: 337 (2.80%) bird: 459 (3.81%) boat: 263 (2.19%) bottle: 469 (3.90%) bus: 213 (1.77%) car: 1201 (9.98%) cat: 358 (2.98%) chair: 756 (6.28%) cow: 244 (2.03%) diningtable: 206 (1.71%) dog: 489 (4.06%) horse: 348 (2.89%) motorbike: 325 (2.70%) person: 4528 (37.63%) pottedplant: 480 (3.99%) sheep: 242 (2.01%) sofa: 239 (1.99%) train: 282 (2.34%) tvmonitor: 308 (2.56%) Total bboxes: 12032 2944 difficult bboxes ignored. [INFO] 2022-10-01 14:51:59 ==================Configs================== [INFO] 2022-10-01 14:51:59 MODEL: [INFO] 2022-10-01 14:51:59 NAME: Faster_RCNN [INFO] 2022-10-01 14:51:59 BACKBONE: resnet50 [INFO] 2022-10-01 14:51:59
[INFO] 2022-10-01 14:51:59 DATA: [INFO] 2022-10-01 14:51:59 DATASET: voc [INFO] 2022-10-01 14:51:59 TRANSFORM: frcnn [INFO] 2022-10-01 14:51:59 SCALE: [800, 1333] [INFO] 2022-10-01 14:51:59 OPTIMIZE: [INFO] 2022-10-01 14:51:59 OPTIMIZER: sgd [INFO] 2022-10-01 14:51:59 BASE_LR: 0.001 [INFO] 2022-10-01 14:51:59 SCHEDULER: 1x [INFO] 2022-10-01 14:51:59 BATCH_SIZE: 2 [INFO] 2022-10-01 14:51:59 TEST: [INFO] 2022-10-01 14:51:59 NMS_THRESH : 0.5
[INFO] 2022-10-01 14:51:59 CONF_THRESH: 0.05 [INFO] 2022-10-01 14:51:59 MISC: [INFO] 2022-10-01 14:51:59 VAL_FREQ: 1 [INFO] 2022-10-01 14:51:59 SAVE_FREQ: 1 [INFO] 2022-10-01 14:51:59 NUM_WORKERS: 0 [INFO] 2022-10-01 14:51:59 ==================Options================== [INFO] 2022-10-01 14:51:59 config=configs/faster_rcnn_voc.yml [INFO] 2022-10-01 14:51:59 debug=False [INFO] 2022-10-01 14:51:59 device=cuda:0 [INFO] 2022-10-01 14:51:59 epochs=500 [INFO] 2022-10-01 14:51:59 gpu_id=0 [INFO] 2022-10-01 14:51:59 load=None [INFO] 2022-10-01 14:51:59 local_rank=None [INFO] 2022-10-01 14:51:59 no_val=False [INFO] 2022-10-01 14:51:59 resume=False [INFO] 2022-10-01 14:51:59 save_path=None [INFO] 2022-10-01 14:51:59 tag=faster_rcnn_voc [INFO] 2022-10-01 14:51:59 vis=False [INFO] 2022-10-01 14:51:59 =========================================== Traceback (most recent call last): File "train.py", line 65, in model = Model(config) File "/media/omnisky/c387317d-6f40-4cef-9f5b-e9477942c7c61/fattyhu/catkin_ws/src/easy_detection-master/network/Faster_RCNN/Model.py", line 61, in init self.detector = fasterrcnn_resnet50_fpn(pretrained=False, **kargs) File "/media/omnisky/c387317d-6f40-4cef-9f5b-e9477942c7c61/fattyhu/catkin_ws/src/easy_detection-master/network/Faster_RCNN/frcnn/faster_rcnn.py", line 335, in fasterrcnn_resnet50_fpn backbone = resnet_fpn_backbone('resnet50', pretrained_backbone, norm_layer=norm_layer) File "/media/omnisky/c387317d-6f40-4cef-9f5b-e9477942c7c61/fattyhu/catkin_ws/src/easy_detection-master/network/Faster_RCNN/frcnn/backbone_utils.py", line 47, in resnet_fpn_backbone norm_layer=torch.nn.SyncBatchNorm) TypeError: resnet50() missing 1 required positional argument: 'epoch'

运行指令时候python3 train.py --config configs/faster_rcnn_voc.yml，出现了如下警告： .\easy_detection-master\network\SSD\utils\nms.py:15: UserWarning: No NMS is available. Please upgrade torchvision to 0.3.0+ or compile c++ NMS using cd ext & python build.py build_ext develop warnings.warn('No NMS is available. Please upgrade torchvision to 0.3.0+ or compile c++ NMS ' 求大神解答！

运行命令为：python3 inference.py --config configs/faster_rcnn_voc.yml 代码中的LOAD_CHECKPOINT、INFERENCE_LIST、IMAGE_FOLDER均改为自己的数据集和权重。 错误为：File "/home/easy_detection-master/network/Faster_RCNN/Model.py", line 40, in init if 'SCALE' in config.DATA: AttributeError: 'Option' object has no attribute 'DATA'

感谢！

when training with yolov3, I met the problem that 'Namespace' object has no attribute 'width', while it has no problem when training with yolov2. The code is shape = (opt.width, opt.height) How should I verify the code to make it run successfully! Thanks!