Closed problemsniper closed 6 years ago
Hi! Looks like the model is on the GPU, but the data is on the CPU. The WaveNetTrainer class has the attribute dtype
which should be torch.cuda.FloatTensor
if you're using a GPU. Are you running the train_script.py or the Jupyter notebook?
JUPYTER notebook which is deployed on the GPU AWS instance and accessing it from my Mac
Hello, how did you fix this error?
Adding a model.cuda()
before training solve the issue.
I am getting this error on runtime. Does any one know what the problem might be?