facebookresearch / facebookresearch/SlowFast

Which model and layers was used to make this video.

Open
#531 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
Python
Stars
7.4k
Forks
1.3k
PR merge metrics
No merged PRs in 30d

Description

May I ask which model and layer structure was used to make this video, it works great. I've tried to reproduce it, but having trouble matching the model and code, and I'm not sure which layers are the output to show.
[Multiscale Vision Transformers](https://ai.facebook.com/blog/multiscale-vision-transformers-an-architecture-for-modeling-visual-data/)
![bird_mvit](https://user-images.githubusercontent.com/17022025/159638998-34f10551-0f0f-452f-beff-a8eed1111711.png)

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.