Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for argument #2 'other'

[jnuvenus]

Hello, When I run LSTNet 'python main.py --gpu 0 --horizon 24 --data data/electricity.txt --save save/elec.pt --output_fun Linear' return error as follows.

Traceback (most recent call last):
File "main.py", line 150, in
val_loss, val_rae, val_corr = evaluate(Data, Data.valid[0], Data.valid[1], model, evaluateL2, evaluateL1, args.batch_size);
File "main.py", line 36, in evaluate
rae = (total_loss_l1/n_samples)/data.rae
RuntimeError: Expected object of type torch.cuda.FloatTensor but found type torch.FloatTensor for argument #2 'other'

Have you ever had a similar error? How to solve this problem?

[BernardOng]

I had this same exact issue and was able to resolve it by correcting all the UserWarnings on the tensor.item() suggested corrections.

On main.py, lines 60, 32, and 33,
Need to convert all the data[0] to item()
example: whatevertensor.data[0] change to --> whatevertensor.item()

After I edited that, the whole thing ran fine. My GPU kicked in and the training was completed.