Training neural network

Hey guys, i am replicating the CycleGAN in this experiment [1] and i am facing this error:
RuntimeError: $ Torch: not enough memory: you tried to allocate 0GB. Buy new RAM! at /b/wheel/pytorch-src/torch/lib/TH/THGeneral.c:270
I believe this error is due to te fact that the virtual machine of mine does not have a GPU of any kind, but is very weird, because I had disabled all cuda configurations in the code.


I wonder if it’s because of the data loader. Can you try running the experiment with 0 workers in the DataLoader?

But I also have this problem even I have GPUs when I try to use CPU

Facing this issue when I am trying to load on CPUs however no error is received on GPU.
Can the error issued be made more descriptive? Current error description was not very helpful to successfully figure out the cause of issue.