You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 693 and 694 in dimension 3 at ../aten/src/TH/generic/THTensor.cpp:711
#148
Open
ljmiao opened this issue
Jun 21, 2020
· 0 comments
I try to evaluate on ade20k dataset,
cd scripts/seg/ade20k
bash run_fs_res101_deeplabv3_ade20k_seg.sh val my_tag,
and get the error below:
Traceback (most recent call last):
File "main.py", line 187, in
Controller.test(runner)
File "/data/algceph/lingjian/sync-code/torchcv/lib/runner/controller.py", line 79, in test
runner.test(test_dir, out_dir)
File "/data/algceph/lingjian/sync-code/torchcv/runner/seg/fcn_segmentor_test.py", line 43, in test
for _, data_dict in enumerate(self.test_loader.get_testloader(test_dir=test_dir)):
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 582, in next
return self._process_next_batch(batch)
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/data/algceph/lingjian/sync-code/torchcv/data/test/test_data_loader.py", line 78, in
*args, trans_dict=self.configer.get('test', 'data_transformer')
File "/data/algceph/lingjian/sync-code/torchcv/lib/data/collate.py", line 67, in collate
return dict({key: stack(batch, data_key=key, device_ids=device_ids) for key in data_keys})
File "/data/algceph/lingjian/sync-code/torchcv/lib/data/collate.py", line 67, in
return dict({key: stack(batch, data_key=key, device_ids=device_ids) for key in data_keys})
File "/data/algceph/lingjian/sync-code/torchcv/lib/data/collate.py", line 33, in stack
default_collate([sample[data_key].data for sample in batch[i:i + samples_per_gpu]])
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 43, in default_collate
return torch.stack(batch, 0, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 693 and 694 in dimension 3 at ../aten/src/TH/generic/THTensor.cpp:711
The text was updated successfully, but these errors were encountered:
I try to evaluate on ade20k dataset,
cd scripts/seg/ade20k
bash run_fs_res101_deeplabv3_ade20k_seg.sh val my_tag,
and get the error below:
Traceback (most recent call last):
File "main.py", line 187, in
Controller.test(runner)
File "/data/algceph/lingjian/sync-code/torchcv/lib/runner/controller.py", line 79, in test
runner.test(test_dir, out_dir)
File "/data/algceph/lingjian/sync-code/torchcv/runner/seg/fcn_segmentor_test.py", line 43, in test
for _, data_dict in enumerate(self.test_loader.get_testloader(test_dir=test_dir)):
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 582, in next
return self._process_next_batch(batch)
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 608, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/worker.py", line 99, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/data/algceph/lingjian/sync-code/torchcv/data/test/test_data_loader.py", line 78, in
*args, trans_dict=self.configer.get('test', 'data_transformer')
File "/data/algceph/lingjian/sync-code/torchcv/lib/data/collate.py", line 67, in collate
return dict({key: stack(batch, data_key=key, device_ids=device_ids) for key in data_keys})
File "/data/algceph/lingjian/sync-code/torchcv/lib/data/collate.py", line 67, in
return dict({key: stack(batch, data_key=key, device_ids=device_ids) for key in data_keys})
File "/data/algceph/lingjian/sync-code/torchcv/lib/data/collate.py", line 33, in stack
default_collate([sample[data_key].data for sample in batch[i:i + samples_per_gpu]])
File "/data/anaconda3/lib/python3.6/site-packages/torch/utils/data/_utils/collate.py", line 43, in default_collate
return torch.stack(batch, 0, out=out)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 693 and 694 in dimension 3 at ../aten/src/TH/generic/THTensor.cpp:711
The text was updated successfully, but these errors were encountered: