Go to file
Keras Team 4fd825ddf9 Initial commit for tensorflow/python/keras to Github project keras-team/keras.
Currently the code is still under development/migration and it is NOT the source of truth. The code in tensorflow/tensorflow repository IS the source of truth for the moment. Please send any PR to that. We will send announcement for the formal switch when we finish all the migration/workflow work.

We will add more documents and setup the developer workflow in the near future.

PiperOrigin-RevId: 345532569
2020-12-07 14:33:04 -08:00
keras Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
.bazelrc Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
BUILD Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
CONTRIBUTING.md Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
LICENSE Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
README.md Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
requirements.txt Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00
WORKSPACE Initial commit for tensorflow/python/keras to Github project keras-team/keras. 2020-12-07 14:33:04 -08:00

Keras: Deep Learning for Python

Keras logo

license

You have just found Keras.

Keras is a high-level neural networks API, written in Python and capable of running on top of TensorFlow, CNTK, or Theano. It was developed with a focus on enabling fast experimentation. Being able to go from idea to result with the least possible delay is key to doing good research.

Use Keras if you need a deep learning library that:

  • Allows for easy and fast prototyping (through user friendliness, modularity, and extensibility).
  • Supports both convolutional networks and recurrent networks, as well as combinations of the two.
  • Runs seamlessly on CPU and GPU.

Read the documentation at Keras.io.

Keras is compatible with: Python 2.7-3.6.


Under Construction

We are repurpose this package to be the new home for tensorflow.keras code. In the meantime, please use keras via Tensorflow.