tensor shape mismatch when training on 24khz LibriTTS dataset #58
Description
Traceback (most recent call last):
File "/home/v-zhikangniu/descript-audio-codec/scripts/train.py", line 441, in
train(args, accel)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/argbind/argbind.py", line 159, in cmd_func
return func(*cmd_args, **kwargs)
File "/home/v-zhikangniu/descript-audio-codec/scripts/train.py", line 425, in train
validate(state, val_dataloader, accel)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/audiotools/ml/decorators.py", line 375, in decorated
output = fn(*args, **kwargs)
File "/home/v-zhikangniu/descript-audio-codec/scripts/train.py", line 344, in validate
output = val_loop(batch, state, accel)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/audiotools/ml/decorators.py", line 321, in decorated
output = fn(*args, **kwargs)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/audiotools/ml/decorators.py", line 107, in decorated
output = fn(*args, **kwargs)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "/home/v-zhikangniu/descript-audio-codec/scripts/train.py", line 220, in val_loop
"loss": state.mel_loss(recons, signal),
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/home/v-zhikangniu/descript-audio-codec/dac/nn/loss.py", line 322, in forward
loss += self.log_weight * self.loss_fn(
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1511, in _wrapped_call_impl
return self._call_impl(*args, **kwargs)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl
return forward_call(*args, **kwargs)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/nn/modules/loss.py", line 101, in forward
return F.l1_loss(input, target, reduction=self.reduction)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/nn/functional.py", line 3308, in l1_loss
expanded_input, expanded_target = torch.broadcast_tensors(input, target)
File "/home/v-zhikangniu/miniconda3/envs/dac/lib/python3.9/site-packages/torch/functional.py", line 76, in broadcast_tensors
return _VF.broadcast_tensors(tensors) # type: ignore[attr-defined]
RuntimeError: The size of tensor a (15000) must match the size of tensor b (15001) at non-singleton dimension 3