Open twodog668 opened 1 year ago
Hi,
I once used the dataset_idx/dataloader_idx because I test multiple test sets/validation sets when training the model. I.e., after I train 1 epoch, I test each validation sets (namely idx 1, idx 2, idx 3, etc.) during the validation stage.
I think the update of pytorch lightning removes this parameters. I suggest using the pytorch lightning 1.8.1 version
I got a problem in testing the model like that: TypeError : test_step() missing 1 required positional argument: 'dataset_idx', and I can't fix it. Could you please help me fix it? This problem is in model/tonet.py, 454 row. Thank you very much.