search

igormq / aes-lac-2018

Pytorch code of "A new automatic speech recognizer for Brazilian Portuguese based on deep neural networks and transfer learning" submitted to AES-LAC 2018
MIT License
21 stars 7 forks source link

IndexError: too many indices for array - train.py for the finetunemodel #4

Open navarmn opened 5 years ago

navarmn commented 5 years ago

Traceback (most recent call last): File "train.py", line 401, in trainer.run(train_loader, args.config.training.num_epochs) File "/home/navar/anaconda3/lib/python3.6/site-packages/pytorch_ignite-0.1.1-py3.6.egg/ignite/engine/engine.py", line 326, in run File "/home/navar/anaconda3/lib/python3.6/site-packages/pytorch_ignite-0.1.1-py3.6.egg/ignite/engine/engine.py", line 291, in _handle_exception File "/home/navar/anaconda3/lib/python3.6/site-packages/pytorch_ignite-0.1.1-py3.6.egg/ignite/engine/engine.py", line 313, in run File "/home/navar/anaconda3/lib/python3.6/site-packages/pytorch_ignite-0.1.1-py3.6.egg/ignite/engine/engine.py", line 280, in _run_once_on_dataset File "/home/navar/anaconda3/lib/python3.6/site-packages/pytorch_ignite-0.1.1-py3.6.egg/ignite/engine/engine.py", line 291, in _handle_exception File "/home/navar/anaconda3/lib/python3.6/site-packages/pytorch_ignite-0.1.1-py3.6.egg/ignite/engine/engine.py", line 268, in _run_once_on_dataset File "/home/navar/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 336, in next return self._process_next_batch(batch) File "/home/navar/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 357, in _process_next_batch raise batch.exc_type(batch.exc_msg) IndexError: Traceback (most recent call last): File "/home/navar/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 106, in _worker_loop samples = collate_fn([dataset[i] for i in batch_indices]) File "/home/navar/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py", line 106, in samples = collate_fn([dataset[i] for i in batch_indices]) File "/mnt/Work/Projects/2018-Locktec-SAVOZ/general/aes-lac-2018-master/codes/data.py", line 65, in getitem target = self.target_transforms(target) File "/mnt/Work/Projects/2018-Locktec-SAVOZ/general/aes-lac-2018-master/codes/transforms.py", line 382, in call return labels[:, np.newaxis] IndexError: too many indices for array

avdcc commented 4 years ago

Where you able to solve this error? I am having the same problem

navarmn commented 4 years ago

I guess i have found a Turnaround. It is been a while since a used this repo. Let me take a look.

Em ter, 3 de dez de 2019 09:58, Adriano Campinho notifications@github.com escreveu:

Where you able to solve this error? I am having the same problem

— You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub https://github.com/igormq/aes-lac-2018/issues/4?email_source=notifications&email_token=AH5B2OXX5N3PE6SMZSHST53QWZJYDA5CNFSM4GLZJW6KYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOEFZI6II#issuecomment-561155873, or unsubscribe https://github.com/notifications/unsubscribe-auth/AH5B2OVSOYMK7UULADJMKADQWZJYDANCNFSM4GLZJW6A .