File "tools/train.py", line 114, in
main()
File "tools/train.py", line 110, in main
runner.train()
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1777, in train
model = self.train_loop.run() # type: ignore
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 96, in run
self.run_epoch()
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 112, in run_epoch
self.run_iter(idx, data_batch)
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 128, in run_iter
outputs = self.runner.model.train_step(
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 114, in train_step
losses = self._run_forward(data, mode='loss') # type: ignore
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 361, in _run_forward
results = self(data, mode=mode)
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, *kwargs)
File "/opt/projects/mmocr/mmocr/models/textdet/detectors/base.py", line 72, in forward
return self.loss(inputs, data_samples)
File "/opt/projects/mmocr/mmocr/models/textdet/detectors/single_stage_text_detector.py", line 76, in loss
return self.det_head.loss(inputs, data_samples)
File "/opt/projects/mmocr/mmocr/models/textdet/heads/db_head.py", line 139, in loss
losses = self.module_loss(outs, batch_data_samples)
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(input, kwargs)
File "/opt/projects/mmocr/mmocr/models/textdet/module_losses/db_module_loss.py", line 79, in forward
gt_shrinks, gt_shrink_masks, gt_thrs, gt_thr_masks = self.get_targets(
File "/opt/projects/mmocr/mmocr/models/textdet/module_losses/db_module_loss.py", line 237, in get_targets
gt_shrinks = torch.cat(gt_shrinks)
RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 722 but got size 720 for tensor number 1 in the list.
Prerequisite
Task
I'm using the official example scripts/configs for the officially supported tasks/models/datasets.
Branch
1.x branch https://github.com/open-mmlab/mmocr/tree/dev-1.x
Environment
环境变量: sys.platform: linux Python: 3.8.19 (default, Mar 20 2024, 19:58:24) [GCC 11.2.0] CUDA available: True MUSA available: False numpy_random_seed: 2147483648 GPU 0: NVIDIA A10 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 12.2, V12.2.91 GCC: gcc (Debian 10.2.1-6) 10.2.1 20210110 PyTorch: 1.10.2 PyTorch compiling details: PyTorch built with:
TorchVision: 0.11.3 OpenCV: 4.9.0 MMEngine: 0.10.3 MMOCR: 1.0.1+1d3b1ca
Reproduces the problem - code sample
{ "metainfo": { "category": [ { "id": 0, "name": "text" } ], "dataset_type": "TextDetDataset", "task_name": "textdet" }, "data_list": [ { "sample_idx": 0, "img_path": "xxx.png", "height": 842, "width": 595, "seg_map": "gt-img-xxx.txt", "instances": [ 很多 ] } ] }
Reproduces the problem - command or script
python tools/train.py configs/textdet/dbnetpp/mmocr_det_myconfig.py
Reproduces the problem - error message
_draw_border_map
错误出现的地方: canvas[y_min_valid:y_max_valid + 1, x_min_valid:x_max_valid + 1] = np.fmax( 1 - distance_map[y_min_valid - y_min:y_max_valid - y_max + height, x_min_valid - x_min:x_max_valid - x_max + width], canvas[y_min_valid:y_max_valid + 1, x_min_valid:x_max_valid + 1]) 错误的原因: y_min_valid - y_min 小于0 而且 绝对值小于 distance_map.shape[1] x_min_valid - x_min 小于0 而且 绝对值小于 distance_map.shape[0]
此问题规避之后,会有新问题:
File "tools/train.py", line 114, in
main()
File "tools/train.py", line 110, in main
runner.train()
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1777, in train
model = self.train_loop.run() # type: ignore
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 96, in run
self.run_epoch()
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 112, in run_epoch
self.run_iter(idx, data_batch)
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 128, in run_iter
outputs = self.runner.model.train_step(
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 114, in train_step
losses = self._run_forward(data, mode='loss') # type: ignore
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/mmengine/model/base_model/base_model.py", line 361, in _run_forward
results = self(data, mode=mode)
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(*input, *kwargs)
File "/opt/projects/mmocr/mmocr/models/textdet/detectors/base.py", line 72, in forward
return self.loss(inputs, data_samples)
File "/opt/projects/mmocr/mmocr/models/textdet/detectors/single_stage_text_detector.py", line 76, in loss
return self.det_head.loss(inputs, data_samples)
File "/opt/projects/mmocr/mmocr/models/textdet/heads/db_head.py", line 139, in loss
losses = self.module_loss(outs, batch_data_samples)
File "/home/beeservice/.conda/envs/open-mmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1102, in _call_impl
return forward_call(input, kwargs)
File "/opt/projects/mmocr/mmocr/models/textdet/module_losses/db_module_loss.py", line 79, in forward
gt_shrinks, gt_shrink_masks, gt_thrs, gt_thr_masks = self.get_targets(
File "/opt/projects/mmocr/mmocr/models/textdet/module_losses/db_module_loss.py", line 237, in get_targets
gt_shrinks = torch.cat(gt_shrinks)
RuntimeError: Sizes of tensors must match except in dimension 0. Expected size 722 but got size 720 for tensor number 1 in the list.
Additional information
data_textdet_train = dict( type="OCRDataset", data_root=data_root, ann_file="mmocrdet_anno.json", filter_cfg=dict(filter_empty_gt=True, min_size=32), pipeline=None, )