search

Atze00 / MoViNet-pytorch

MoViNets PyTorch implementation: Mobile Video Networks for Efficient Video Recognition;
MIT License
256 stars 50 forks source link

accuracy drop #11

Closed zongzhesun closed 3 years ago

zongzhesun commented 3 years ago

I used your model code to reproduce, but the results are far from the results published in the paper. If possible, can you share some more complete implementation code, thank you very much for your work! This is my mailbox, 973507183@qq.com. Looking forward to your reply.

Atze00 commented 3 years ago

I shared almost everything, what are you looking for? As it is written in the readme, I haven't tried to reproduce the results. Putting the same input inside the networks you obtain the same output of the official tf models, so they should have the same accuracy, you can look it up on the tests. Could you share the code you used for evaluation? there could be come slight differences on the preprocessing methods. How big is the drop in accuracy?