Open bernardcwj opened 6 years ago
@bernardcwj @da03 Do you find a way to solve this problem?
Hmm a simple workaround is to just use modules from nn instead of cudnn, but I think training on CPU would be too slow to be realistic.
I am training it on cpu, one epoch spends 5 hours
I wish to test the model on a CPU, how can i achieve that? I have tried setting the gpd_id as 0 but it returns an error stating spatialconvolution requires cuda. Therefore, i included a line cudnn.convert(model[1], nn) in model.lua before line 55 to overcome the error. But now i'm getting another error:
Any help is appreciated! Thanks