I’m trying to take a second-order derivative of the RNN loss function, but I got an error “trying to differentiate twice a function that was markedwith @once_differentiable”. Does this mean the current pytorch implementation does not support 2nd order derivative?
it doesn’t support 2nd order derivative for RNNs yet.
Wow! I have just experienced this limitation. I am implementing an WGAN with an LSTM in the generator and an LSTM in the discriminator and when I calculate the gradients I get
RuntimeError: CudnnRNNLegacyBackward is not differentiable twice
Is there any workaround? When do you think it is going to be implemented?
Thanks a lot
Wow! I didn’t know it! It is really good; impressive work. I have just adapted the SLOGAN loss to my net (for language generation) and now I can train it with 2 RNNs. It seems to be stabilizing, though it gets into a hard mode collapse. Lets wait a bit still… Thanks!!!
Any updates on the issue?
because I am running into same problem RuntimeError: CudnnRNNLegacyBackward is not differentiable twice
As far as I know, this is still the same. You might have better luck using LSTMCell and friends.
Best regards
Thomas
Has there been any update on this? I am facing the same problem.