xyzforever/BEVT

PyTorch implementation of BEVT (CVPR 2022) https://arxiv.org/abs/2112.01529

41
/ 100
Emerging

This project helps machine learning engineers and researchers to pretrain video transformers for classifying complex video content. It takes large datasets of unlabelled videos and images as input, and outputs a highly accurate model capable of recognizing actions or events within new videos. This is ideal for those working in computer vision research or developing video analysis applications.

161 stars. No commits in the last 6 months.

Use this if you need to train a robust video recognition model and want to leverage state-of-the-art self-supervised pretraining techniques to achieve high accuracy on various video tasks.

Not ideal if you are a beginner looking for a simple, out-of-the-box solution without deep understanding of PyTorch, transformers, and large-scale model training.

video-classification action-recognition machine-learning-engineering computer-vision deep-learning-research
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

161

Forks

19

Language

Python

License

Apache-2.0

Last pushed

Jul 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xyzforever/BEVT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.