alilotfi92 / infomaxvae Goto Github PK

when i ran infoMaxVAE.py, i got the error like:

Traceback (most recent call last):
  File "../infoMaxVAE.py", line 183, in <module>
    info_loss.backward()
  File "../lib/python3.8/site-packages/torch/tensor.py", line 221, in backward
    torch.autograd.backward(self, gradient, retain_graph, create_graph)
  File "../lib/python3.8/site-packages/torch/autograd/__init__.py", line 130, in backward
    Variable._execution_engine.run_backward(
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [1000, 4]], which is output 0 of TBackward, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

so, what can i do to fix this error?

during trainning procedure, when info_loss.bacjkward() it outpout those :
File "infomaxVAE.py", line 188, in
info_loss.backward()
File "/usr/local/anaconda3/envs/sshape/lib/python3.7/site-packages/torch/_tensor.py", line 363, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/usr/local/anaconda3/envs/sshape/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 [20, 118, 1, 1]] is at version 2; expected version 1 instead. Hint: the backtrace further above shows the operation that failed to compute its gradient. The variable in question was changed in there or anywhere later. Good luck!

it seems info_loss be modified elsewhere, any idea how to fix this?