Tortoise17

HI, I am working out. but so far nothing successful or complete. I will tell you if once I am successful with this.

@Nandini2801 This is `pytorch` version [Kinetics-PyTorch](https://github.com/hassony2/kinetics_i3d_pytorch) which is working. But still I need to know how to extract features from second last layer.

Sorry, now in above repl is the code.

has anyone trained from scratch/pretrained the model flow i3d and two-stream i3d? please if someone can share.

I am also looking for same answer. Or any way to convert them to .h5 format?

@joaoluiscarreira thank you so much. Is there any command line with which I can input the mp4 and get back the logits and features? or do I have to export...

I am also trying. Please share if anyone has any update or success. @gayanDeegala @Soumi7

I also have same issue. Is there any solution for this or any hint to get rid of such fuzzy ending parts?

@billharbert I guess you are searching https://github.com/Strans/agilegeo this repo_?

Hi. Not yet. but if I will get. i will definitely share. I am also looking like you.