metal3d/keras-video-generators

Keras generators to generate sequences from videos as input

54
/ 100
Established

This project helps machine learning engineers or researchers working with video data for tasks like action recognition or anomaly detection. It takes collections of video files and efficiently prepares sequences of individual frames from them. The output is ready-to-use batches of video frames that can be fed directly into deep learning models, especially those designed for sequential data.

100 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to train deep learning models on video data and want an efficient way to extract and pre-process frame sequences for Keras or TensorFlow.

Not ideal if you are not working with Keras/TensorFlow, or if you only need to process single images rather than sequences of frames from videos.

video-analysis deep-learning-engineering computer-vision action-recognition
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

100

Forks

30

Language

Jupyter Notebook

License

MIT

Last pushed

Nov 25, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/metal3d/keras-video-generators"

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