search

facebookresearch / TimeSformer

The official pytorch implementation of our paper "Is Space-Time Attention All You Need for Video Understanding?"
Other
1.56k stars 213 forks source link

Inference code reg #102

Open Jeba-create opened 2 years ago

Jeba-create commented 2 years ago

Thank you so much for such a wonderful work. Could you please share the sample code to do inference on custom datasets or to some random images?

Jeba-create commented 2 years ago

sorry,I got the required code from example.ipynb

lamsongianm commented 2 years ago

Thank you for your contribution. I am a beginner in action recognition, and I have confused about how to use the model's output (2,400) to predict the action. Could you provide the sample code? Thanks a lot. @gberta