A question about how to split SENSE dataset

[PengqiH]

Hello, I am curious about how the VScrowd dataset is partitioned during DRnet training. I noticed that the authors of VScrowd currently name each folder as train_xx, test_xx, but in the info.json file of your code repository, I see entries like:"0817_1_cut_01_rot": 70,"0817_1_cut_02_rot": 77,"0817_2_cut_01": 53,Additionally, in the code file DRNet\datasets\dataset_prepare\video_vis.py, there is the line:for scene in sorted(os.listdir(video_path)[51:])which indicates that the first 51 scenes are skipped (I'm not sure if I've located the wrong code snippet).