You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
The code generates h5 files for which each video has some wierd keys (corresponding to their urls like "HzYtvOYOEoU_21_32"). But SAAT expects keys to be of integer form like 0, 1, 2 and so on.
The easiest mapping would have been obtained by replacing vid with cnthere, which means keys (as expected by SAAT) is the index of video while enumerating.
Could you please confirm if this was the actual mapping that is supposed to be used? It is a bit risky to assume anything on my own for key mappings,
The text was updated successfully, but these errors were encountered:
Hi, for videos msrvtt dataset, the index can be read from their filename, i.e., 'video'+str(index)+'.mp4'. For those in the msvd dataset, I generate the indices by going through all the video files. I can upload the mapping file if you need it.
Hi, I checked the link I provided in 'Data' README and found I've uploaded the files. You can see the mapping file in input->msvd, and the maskrcnn_code.zip.
The code generates h5 files for which each video has some wierd keys (corresponding to their urls like "HzYtvOYOEoU_21_32"). But SAAT expects keys to be of integer form like 0, 1, 2 and so on.
The easiest mapping would have been obtained by replacing
vid
withcnt
here, which means keys (as expected by SAAT) is the index of video while enumerating.Could you please confirm if this was the actual mapping that is supposed to be used? It is a bit risky to assume anything on my own for key mappings,
The text was updated successfully, but these errors were encountered: