li-lab-mcgill / singlecell-deepfeature Goto Github PK

TypeError: forward() takes from 2 to 4 positional arguments but 5 were given

when running: history = trainer.train(n_epochs=150, lr= lr1, eps=eps, disc_lr= lr * 1, enc_lr = lr 0.0 )
&
history = trainer.train(n_epochs=50, lr= lr1, eps=eps, disc_lr= lr * 1, enc_lr = lr 0.05)

in MDDBrianCells_scGAN.py

python 3.8, Ubuntu 20.04LTS, CUDA 10.1, latest Tensorflow and Torch.

Hi:
when I run
history = trainer.train(n_epochs=20, lr= lr1, eps=eps, disc_lr= lr * 1, enc_lr = lr 0.0),
the code "D_loss.backward(retain_graph=True)" was crashed, and indicated the following errors:

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [64, 10]], which is output 0 of TBackward, 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!
can you help me if possible?

enviroments:
pytorch: 1.7.0