search

insilicomedicine / GENTRL

Generative Tensorial Reinforcement Learning (GENTRL) model
596 stars 215 forks source link

how can i fix this problem ? #10

Open aimons opened 4 years ago

aimons commented 4 years ago

RuntimeError Traceback (most recent call last)

in () ----> 1 model.train_as_vaelp(train_loader, lr=1e-4) ~\Documents\GENTRL\gentrl\gentrl.py in train_as_vaelp(self, train_loader, num_epochs, verbose_step, lr) 156 z_batch = (means + torch.randn_like(log_stds) * 157 torch.exp(0.5 * log_stds)) --> 158 cur_batch = torch.cat([z_batch, y_batch], dim=1) 159 if buf is None: 160 buf = cur_batch RuntimeError: Expected object of backend CPU but got backend CUDA for sequence element 1 in sequence argument at position #1 'tensors'