ajabri / videowalk

Repository for "Space-Time Correspondence as a Contrastive Random Walk" (NeurIPS 2020)

http://ajabri.github.io/videowalk

Is it possible to use the trained model for fine tuning?

zobeirraisi opened this issue 3 years ago · comments

Zobeir Raisi commented 3 years ago

Thanks for fantastic work, I have some questions:

How can we Fine-Tune on a costume dataset?
IS it possible to train the model on a small dataset?
Can you please how to visualize it in another video (demo)?