API tools faq
paste
zudvin

5 minut video crash learning

zudvin
Oct 9th, 2022
1,406
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Bash 3.04 KB | None | 0 0
raw download clone embed print report
  1. emotionnet-worker-audio | [2022-10-09 22:57:36,118: WARNING/ForkPoolWorker-2] X_test:(15, 128, 517), Y_test:(15,)
  2. emotionnet-worker-audio | [2022-10-09 22:57:36,178: WARNING/ForkPoolWorker-2]
  3. emotionnet-worker-audio | Selected device is cpu
  4. emotionnet-worker-audio | [2022-10-09 22:57:36,189: WARNING/ForkPoolWorker-2] Number of trainable params:
  5. emotionnet-worker-audio | [2022-10-09 22:57:36,189: WARNING/ForkPoolWorker-2]
  6. emotionnet-worker-audio | [2022-10-09 22:57:36,190: WARNING/ForkPoolWorker-2] 394855
  7.   0%|          | 0/10 [00:00<?, ?it/s]22:57:36,190: WARNING/ForkPoolWorker-2]
  8. emotionnet-worker-audio | [2022-10-09 22:57:36,190: WARNING/ForkPoolWorker-2]
  9. emotionnet-worker-audio |       Start training 10 epoches...
  10.   0%|          | 0/10 [00:00<?, ?it/s]22:57:36,370: WARNING/ForkPoolWorker-2]
  11. emotionnet-worker-audio | [2022-10-09 22:57:36,409: ERROR/ForkPoolWorker-2] Task train_audio[f9d7121c-10db-45db-a953-61026dd193fe] raised unexpected: RuntimeError('The size of tensor a (7) must match the size of tensor b (8) at non-singleton dimension 1')
  12. emotionnet-worker-audio | Traceback (most recent call last):
  13. emotionnet-worker-audio |   File "/usr/local/lib/python3.8/site-packages/celery/app/trace.py", line 451, in trace_task
  14. emotionnet-worker-audio |     R = retval = fun(*args, **kwargs)
  15. emotionnet-worker-audio |   File "/usr/local/lib/python3.8/site-packages/celery/app/trace.py", line 734, in __protected_call__
  16. emotionnet-worker-audio |     return self.run(*args, **kwargs)
  17. emotionnet-worker-audio |   File "/code/app/worker.py", line 208, in create_task_train_audio
  18. emotionnet-worker-audio |     result = train(
  19. emotionnet-worker-audio |   File "/code/ml/train_audio.py", line 565, in train
  20. emotionnet-worker-audio |     loss, acc = train_step(X_tensor, Y_tensor)
  21. emotionnet-worker-audio |   File "/code/ml/train_audio.py", line 134, in train_step
  22. emotionnet-worker-audio |     loss = loss_fnc(output_logits, Y)
  23. emotionnet-worker-audio |   File "/code/ml/train_audio.py", line 528, in loss_fnc
  24. emotionnet-worker-audio |     return nn.L1Loss()(input=predictions, target=targets)
  25. emotionnet-worker-audio |   File "/usr/local/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
  26. emotionnet-worker-audio |     return forward_call(*input, **kwargs)
  27. emotionnet-worker-audio |   File "/usr/local/lib/python3.8/site-packages/torch/nn/modules/loss.py", line 96, in forward
  28. emotionnet-worker-audio |     return F.l1_loss(input, target, reduction=self.reduction)
  29. emotionnet-worker-audio |   File "/usr/local/lib/python3.8/site-packages/torch/nn/functional.py", line 3248, in l1_loss
  30. emotionnet-worker-audio |     expanded_input, expanded_target = torch.broadcast_tensors(input, target)
  31. emotionnet-worker-audio |   File "/usr/local/lib/python3.8/site-packages/torch/functional.py", line 73, in broadcast_tensors
  32. emotionnet-worker-audio |     return _VF.broadcast_tensors(tensors)  # type: ignore[attr-defined]
  33. emotionnet-worker-audio | RuntimeError: The size of tensor a (7) must match the size of tensor b (8) at non-singleton dimension 1
  34.  
Tags: log BASH
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!