aes-lac-2018

aes-lac-2018 copied to clipboard

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

2

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...

navarmn

KeyError: 'lang' - in python train.py scripts/pt_BR-finetune.json

1

Traceback (most recent call last): File "train.py", line 167, in model = tu.finetune_model(model, args.config.model) File "/home/navar/savoz/aes-lac-2018/codes/utils/training_utils.py", line 90, in finetune_model num_classes = NUM_CLASSES[obj['lang']] KeyError: 'lang'

navarmn

python3 train.py scripts/pt_BR-finetune.json - not working

1

Traceback (most recent call last): File "train.py", line 402, in trainer.run(train_loader, args.config.training.num_epochs) File "/usr/local/lib/python3.6/dist-packages/pytorch_ignite-0.1.2-py3.6.egg/ignite/engine/engine.py", line 326, in run File "/usr/local/lib/python3.6/dist-packages/pytorch_ignite-0.1.2-py3.6.egg/ignite/engine/engine.py", line 291, in _handle_exception File "/usr/local/lib/python3.6/dist-packages/pytorch_ignite-0.1.2-py3.6.egg/ignite/engine/engine.py", line 313, in run...

navarmn

ValueError: too many values to unpack (expected 4) - Training the backbone model.

1

Epoch: [1][20577/20578] Time 0.761 Data 0.001 Loss 136.7847 Epoch: [1][20578/20578] Time 0.761 Data 0.001 Loss 157.6949 Traceback (most recent call last): File "train.py", line 401, in trainer.run(train_loader, args.config.training.num_epochs) File "/usr/local/lib/python3.6/dist-packages/pytorch_ignite-0.1.2-py3.6.egg/ignite/engine/engine.py",...

navarmn

I have got this erros when trying to test your model. I have followed the path to create the manifest.csv

1

Traceback (most recent call last): File "test.py", line 49, in dataset = AudioDataset(args.data_dir, args.manifest, transforms=transforms, target_transforms=target_transforms) File "/workspace/codes/data.py", line 30, in __init__ if zipfile.is_zipfile(self.data_dir): File "/opt/conda/lib/python3.7/zipfile.py", line 180, in is_zipfile...

navarmn