hbdat / eccv20_multi_task_procedure_learning Goto Github PK

Hey!

While extracting features for the ProceL dataset, I noticed that you have added the self.num_files by 1.

Due to the addition, the rest of the code was taking one extra file and raising an error when the corresponding image file was not present. However, I was able to run through all the frames without adding 1. Could you please let me know why you had to do it?

Also, here:

Regards,
Siddhant Bansal

Hi, since some videos of Procel Dataset are missing or private now, shall you share a full copy of this dataset? Thanks.

Hey!

The script FeatureVGGDataset.py imports and uses raw_data_dir from global_setting. However, raw_data_dir variable is not declared in global_setting.

For my purpose, I was able to run the code by setting raw_data_dir to None in global_setting. However, I guess, we should add a condition in FeatureVGGDataset.py at line 41

Regards,
Siddhant Bansal

Hey!

The following part of the code requires the .mat file to have the key named superframe_time

Can you please shed some light on the possible reason for this issue?

Regards,
Siddhant Bansal

Hello, thank you for providing the implementation of your paper! I was trying to replicate the results in the paper. Will it be possible for you to share the models trained for this work?