RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [68]] is at version 3; expected version 2 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

[ASAmbitious]

Bug description

Traceback (most recent call last):
File "main_train.py", line 61, in
main(cfg)
File "main_train.py", line 50, in main
trainer.fit()
File "/mnt/inais/data1/syp/wgan/fabric/decalib/trainer.py", line 373, in fit
self.fabric.backward(all_loss)
File "/root/miniconda3/envs/DECA_2/lib/python3.7/site-packages/lightning/fabric/fabric.py", line 359, in backward
self._precision.backward(tensor, module, *args, **kwargs)
File "/root/miniconda3/envs/DECA_2/lib/python3.7/site-packages/lightning/fabric/plugins/precision/precision.py", line 73, in backward
tensor.backward(*args, **kwargs)
File "/root/miniconda3/envs/DECA_2/lib/python3.7/site-packages/torch/_tensor.py", line 396, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/root/miniconda3/envs/DECA_2/lib/python3.7/site-packages/torch/autograd/init.py", line 175, in backward
allow_unreachable=True, accumulate_grad=True) # Calls into the C++ engine to run the backward pass
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [68]] is at version 3; expected version 2 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
I encountered this problem during operation, how should I solve it?

What version are you seeing the problem on?

master

How to reproduce the bug

No response

Error messages and logs

# Error messages and logs here please

Environment

Current environment

#- Lightning Component (e.g. Trainer, LightningModule, LightningApp, LightningWork, LightningFlow):
#- PyTorch Lightning Version (e.g., 1.5.0):
#- Lightning App Version (e.g., 0.5.2):
#- PyTorch Version (e.g., 2.0):
#- Python version (e.g., 3.9):
#- OS (e.g., Linux):
#- CUDA/cuDNN version:
#- GPU models and configuration:
#- How you installed Lightning(`conda`, `pip`, source):
#- Running environment of LightningApp (e.g. local, cloud):

More info

No response

[LawJarp-A]

Without code to reproduce this particular error, it'll be difficult to solve it. Maybe provide the model code and training code?