May I ask, I want to train PASCAL, how should I run? I didn't change anything, but I made a mistake in running, thank you

[andrew-begain]

No description provided.

[andrew-begain]

File "/home/data/andrew/HRNet_ori/tools/train.py", line 253, in
main()
File "/home/data/andrew/HRNet_ori/tools/train.py", line 233, in main
config, testloader, model, writer_dict)
File "/home/data/andrew/HRNet_ori/lib/core/function.py", line 72, in validate
for _, batch in enumerate(tqdm(testloader)):
File "/usr/local/lib/python3.5/dist-packages/tqdm/_tqdm.py", line 1000, in iter
for obj in iterable:
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 336, in next
return self._process_next_batch(batch)
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch
raise batch.exc_type(batch.exc_msg)
RuntimeError: Traceback (most recent call last):
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop
samples = collate_fn([dataset[i] for i in batch_indices])
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 187, in default_collate
return [default_collate(samples) for samples in transposed]
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 187, in
return [default_collate(samples) for samples in transposed]
File "/usr/local/lib/python3.5/dist-packages/torch/utils/data/dataloader.py", line 173, in default_collate
return torch.stack([torch.from_numpy(b) for b in batch], 0)
RuntimeError: invalid argument 0: Sizes of tensors must match except in dimension 0. Got 375 and 427 in dimension 2 at /pytorch/aten/src/TH/generic/THTensorMath.cpp:3616

[GuangyanZhang]

HI，What are the results of your training PASCAL？The result Miou I get is 67.23,The train data loss is decreaseing,but The validation loss set remains the same,I'm very puzzle.

[andrew-begain]

@GuangyanZhang thank you very much ,Did you modify the source code while you were training?and Which data set are you using?

[GuangyanZhang]

PASCAL voc 2012