Asad Norouzi
It seems that the data volume is contributing to this error. If you train with the 300 subset of the dataset, it will not crash! I still need to figure...
I forgot to update this issue earlier! The error is when your machine does not have enough memory for data loader to cache the data. If this happens to you...
@Morgan-Gan You can solve this problem by applying the following change: ```opp_labels = (batch_box_preds[..., -1] > 0) ^ dir_labels.bool()``` I think it's just due to different pytorch versions.