juliuskunze/cwvae-jax
Clockwork VAEs in JAX/Flax
This project offers a deep generative model designed to predict future frames in videos over very long periods. It takes raw video data as input and outputs predictions of high-level content, such as object positions and identities, for up to 1000 frames into the future. It's for researchers and practitioners working on advanced video analysis and prediction tasks.
No commits in the last 6 months.
Use this if you need to generate accurate, long-term video predictions, focusing on high-level content rather than just short, sharp sequences.
Not ideal if you are looking for short-term, highly precise frame-by-frame predictions, or if you are working with the 'mazes' dataset, as replication has not been confirmed.
Stars
32
Forks
3
Language
Python
License
MIT
Category
Last pushed
Jul 16, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/juliuskunze/cwvae-jax"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
explosion/thinc
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
google-deepmind/optax
Optax is a gradient processing and optimization library for JAX.
patrick-kidger/diffrax
Numerical differential equation solvers in JAX. Autodifferentiable and GPU-capable....
google/grain
Library for reading and processing ML training data.
patrick-kidger/equinox
Elegant easy-to-use neural networks + scientific computing in JAX. https://docs.kidger.site/equinox/