yoosan / i3d-tensorflow

Inflated 3D ConvNets for video understanding

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Can you tell me more detail about training on UCF-101

imnotk opened this issue · comments

I train I3d model on UCF-101 split 1 with pretrained Kinetics-imagenet weights, but I only can get the accuracy on test split about 45% , but train accuracy about 95% on rgb modality.
So how did you get the 95.2% accuracy on split 1 , can you give me some advise?