IBM / action-recognition-pytorch

This is the pytorch implementation of some representative action recognition approaches including I3D, S3D, TSN and TAM.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Incorrect implementation of TSN

JiaMingLin opened this issue · comments

Hi, thanks for this fantastic work.
But I notice there is only forward implementation of TSN in this project, backward prop is missing.
According to original paper, eq(5) in [L. Wang, TPAMI, 2019] , the gradient should be divided by "K", the number of segments.

[L. Wang, TPAMI, 2019] L. Wang, et al. "Temporal Segment Networks for Action Recognition in Videos", TPAMI VOL. 41, NO. 11 2019.