search

MichiganCOG / ViP

Video Platform for Action Recognition and Object Detection in Pytorch
MIT License
220 stars 37 forks source link

Variable clip length #29

Closed natlouis closed 5 years ago

natlouis commented 5 years ago

In certain cases the input to the network is not raw frames, but some computed features. All of the processed frames can be loaded at once, so it'd be useful to not specify the clip length and just read all available data per video.

This only works with batch_size = 1, but this is when the pseudo batch loop can come in handy.

ehofesmann commented 5 years ago

We will update _extract_clips in the case where num_clips>0 and clip_length=-1 so that it returns the entire video.

ehofesmann commented 5 years ago

Fixed in pull request #36