Keras. Deep learning toolkit that works with TensorFlow, JAX, or PyTorch.

Problem

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Audience

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Market

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Pricing

The full read on this project is a sign-in away — what it solves, who it serves, and where it sits in the market.

Vaya's read on this project

Problem, audience, market, and the verdict — sign in to see it.

Updates

December 2023

CTC API for JAX (#18952) Dec 18
Increase generality of reloading logic Dec 17
Fix code style. Dec 17
standard input_shape if include_top is false (#18954) Dec 17
Update version number. Dec 15
Add `ops.random.alpha_dropout` and `layers.AlphaDropout` (#18940) Dec 15
CTC loss for TF and torch (#18929) Dec 14
Update multiprocessing import in py_dataset_adapter.py (#18938) Dec 13
Tweaks to TensofFlow support for SparseTensor/IndexedSlices. (#18937) Dec 13
Fix Adafactor when variables have 2 dimensions or more. (#18936) Dec 13
add get_config() to SeedGenerator (#18933) Dec 13
Update deserialization mechanics Dec 13
Update `alpha` broadcasting and put `beta` on device (#18927) Dec 12
Fix descrepancies in Conv Module docstrings regarding data_format (#1… Dec 12
Fixes Torch GPU Test for Binomial and Beta Distribution (#18926) Dec 12
Nit Dec 11
Add masking to BatchNormalization (#18921) Dec 11
Docstring fixes. Dec 11
Improve one_hot/multi_hot Dec 11
Implement `binomial` and `beta` distribution functions in `keras.rand… Dec 11