GX

Results 4 issues of GX

Traceback (most recent call last): File "/mnt/Pycharm_Remote/DLCT_test/train.py", line 335, in scores = evaluate_metrics(model, dict_dataloader_val, text_field) File "/mnt/Pycharm_Remote/DLCT_test/train.py", line 61, in evaluate_metrics **{'boxes': boxes, 'grids': grids, 'masks': masks}) File "/mnt/Pycharm_Remote/DLCT_test/models/captioning_model.py", line...

When I ran the validation on the VidSTG dataset, the gpu memory occupied 50G, is this normal?

**LAION Dataset** During the training phase, it is necessary to load the LAION dataset, but the README does not mention the storage format of this dataset.

Excellent pioneering work! I attempted to replicate the results on HCSTVG-v1. Since the paper did not mention the global batch size on HCSTVG, I trained with both 16 and 8...