Closed fuzhaiping closed 3 months ago
Hi, thanks for your interest in our work.
When specifying val_seq = None
, the sequence list would be automatically initialised in the corresponding dataloader. For example, please refer to L34 to L51 in data/dataloaders/dvs_loader.py
.
If you are loading your own dataset via data/dataloaders/example_loader.py
, no default sequence list is given. Then, the val_seq
is needed to be manually specified as the list of sub-directories in your dataset folder.
Thank you very much for your reply!
When write "None", Program error.