affjljoo3581/deit3-jax
Jax/Flax implementation of DeiT and DeiT-III (ViT)
This project offers pre-trained vision models for classifying images, which are key for tasks like identifying objects in photos. It takes raw image datasets and outputs highly accurate image classification models. Data scientists, machine learning engineers, and researchers can use this to quickly build robust image recognition systems.
No commits in the last 6 months.
Use this if you need to train or fine-tune state-of-the-art image classification models efficiently on Google's Tensor Processing Units (TPUs).
Not ideal if you primarily work with PyTorch or do not have access to or prefer not to use JAX/Flax and TPUs for your deep learning projects.
Stars
19
Forks
6
Language
Shell
License
Apache-2.0
Category
Last pushed
Dec 21, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/affjljoo3581/deit3-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/