Skip to main content

Industry-strength computer Vision extensions for Keras.

Project description

KerasCV

Downloads Python Tensorflow Contributions Welcome

KerasCV is a repository of modular building blocks (layers, metrics, losses, data-augmentation) that applied computer vision engineers can leverage to quickly assemble production-grade, state-of-the-art training and inference pipelines for common use cases such as image classification, object detection, image segmentation, image data augmentation, etc.

KerasCV can be understood as a horizontal extension of the Keras API: the components are new first-party Keras objects (layers, metrics, etc) that are too specialized to be added to core Keras, but that receive the same level of polish and backwards compatibility guarantees as the rest of the Keras API and that are maintained by the Keras team itself (unlike TFAddons).

KerasCV's primary goal is to provide a coherent, elegant, and pleasant API to train state of the art computer vision models. Users should be able to train state of the art models using only Keras, KerasCV, and TensorFlow core (i.e. tf.data) components.

To learn more about the future project direction, please check the roadmap.

Quick Links

Contributors

If you'd like to contribute, please see our contributing guide.

To find an issue to tackle, please check our call for contributions.

Thank you to all of our wonderful contributors!

Citing KerasCV

If KerasCV helps your research, we appreciate your citations. Here is the BibTeX entry:

@misc{wood2022kerascv,
  title={KerasCV},
  author={Wood, Luke and Zhu, Scott and Chollet, Fran\c{c}ois and others},
  year={2022},
  howpublished={\url{https://github.com/keras-team/keras-cv}},
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

keras-cv-0.2.10.tar.gz (110.3 kB view details)

Uploaded Source

Built Distribution

keras_cv-0.2.10-py3-none-any.whl (227.4 kB view details)

Uploaded Python 3

File details

Details for the file keras-cv-0.2.10.tar.gz.

File metadata

  • Download URL: keras-cv-0.2.10.tar.gz
  • Upload date:
  • Size: 110.3 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.7.13

File hashes

Hashes for keras-cv-0.2.10.tar.gz
Algorithm Hash digest
SHA256 242de82078cb168a487bbfc3bd16e64b4c1ea629d65de6898f467beca0d1b437
MD5 30495b760384161fac651802b3618ffa
BLAKE2b-256 8673e866d94e08c18eb62aa4257a55511a626c81f0a460dc991d270e3b037b12

See more details on using hashes here.

Provenance

File details

Details for the file keras_cv-0.2.10-py3-none-any.whl.

File metadata

  • Download URL: keras_cv-0.2.10-py3-none-any.whl
  • Upload date:
  • Size: 227.4 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/4.0.1 CPython/3.7.13

File hashes

Hashes for keras_cv-0.2.10-py3-none-any.whl
Algorithm Hash digest
SHA256 74e96e93bffcc946d24f3d50c74c944de4acc238bfa3a5b11e8e9069bd53bec8
MD5 28198beab110f622a8d4f14aba9df17c
BLAKE2b-256 a3f04861d7d40bd26fe36370f36d2cb46ca53d9b31fc7d00c66b13fe3c3887c5

See more details on using hashes here.

Provenance

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page