Closed Enescigdem closed 2 years ago
I think you will need to move both the model and input data to the CPU before the forward pass, e.g., something like audio_mode.to('cpu')
and input.to('cpu')
.
-Yuan
Thanks a lot but I had to make CUDA_VISIBLE_DEVICES=-1 to accomplish.
Yes, that should also work as all device
will be cpu
when you set CUDA_VISIBLE_DEVICES=-1
.
Hello, I tried to do inference on cpu.BUT ; RuntimeError: module must have its parameters and buffers on device cuda:0 error arose. What steps should be done ?