Contents

keras 2.9.0

0

Deep learning for humans.

Keras is a deep learning API written in Python, running on top of the machine learning platform TensorFlow. The core data structures of Keras are layers and models. The philosophy is to keep simple things simple, while allowing the user to be fully in control when they need to (the ultimate control being the easy extensibility of the source code via subclassing). Deep learning for humans.

Stars: 55874, Watchers: 55874, Forks: 19164, Open Issues: 321

The keras-team/keras repo was created 7 years ago and was last updated 7 minutes ago.
The project is extremely popular with a mindblowing 55874 github stars!

How to Install keras

You can install keras using pip

pip install keras

or add it to a project with poetry

poetry add keras

Package Details

Author
Keras team
License
Apache 2.0
Homepage
https://keras.io/
PyPi
https://pypi.org/project/keras/
GitHub Repo
https://github.com/keras-team/keras

Classifiers

  • Scientific/Engineering
  • Scientific/Engineering/Artificial Intelligence
  • Scientific/Engineering/Mathematics
  • Software Development
  • Software Development/Libraries
  • Software Development/Libraries/Python Modules
No  keras  pypi packages just yet.

Errors

A list of common keras errors.

Code Examples

Here are some keras code examples and snippets.

GitHub Issues

The keras package has 321 open issues on GitHub

  • Keras Testing: Fix ModuleNotFoundError in Keras memory_test, and re-enable on TAP.
  • Stop testing keras in the core tf docstest
  • Reorganize regularization layers into smaller logically organized files hosted under a regularization directory.
  • Add a keras doctest modeled on tensorflow doctest
  • Remove legacy multi_gpu_utils (irrelevant since the introduction of distribution strategies).
  • Support checkpointing ShardedVariables in optimizer slot variables.
  • Fix tf.name_scope support for Keras nested layers.
  • mode.predict freezes
  • The model saving is disturbed by the error raised intentionaly.
  • Shape issues in tf.keras.metrics.SparseTopKCategoricalAccuracy with multiple dimensions
  • Update global_clipnorm
  • TensorFlow "TypeError: Target data is missing" though dataset with 2 dimension tuple was supplied
  • Refactor SGD __decayed_lr to allow tf.Variable to be used as decay parameter
  • SGD decay cannot be a tf.Variable
  • Higher validation and test loss and lower accuracy using tf.data.dataset with tfrecords than using numpy

See more issues on GitHub

Related Packages & Articles

gensim 4.2.0

Python framework for fast Vector Space Modelling