Skip to main content

OpenVINO backend implementation for Keras

Local development

For development, you need the keras repository and the keras-openvino repository checked out locally. That's because the unit tests code is in the keras repository.

We first check out the main keras repository and the pluggable_backend branch. Then, we install the required dependencies.

gh repo clone keras-team/keras
cd keras
git checkout pluggable_backend
pip install -r requirements.txt
cd ..

Assuming you have a fork of keras-openvino, you will run the following. This also installs keras-openvino locally so that keras can find and import the keras-openvino module.

gh repo clone <your_github_handle>/keras-openvino
cd keras-openvino
pip install -r requirements.txt
pip install -e .
cd ..

Running tests happens from the root of the keras repository.

cd keras
KERAS_BACKEND=openvino pytest keras --ignore=keras/src/applications

Formatting the code

The code is formatted and linted with Ruff, run through pre-commit. The first time you are setting up the repo, please run pre-commit install. Note that this needs to be done only once at the beginning.

Now, whenever you run git commit -m "<message>", the code is automatically formatted and linted. If there's any error, the commit will not go through. Please fix the error (most of the times, the error is fixed automatically by the formatter/linter) and re-run the following:

git add .
git commit -m "<message>"

In case you want to run the above manually on all files, you can do the following:

pre-commit run --all-files

Release files for keras-openvino 0.0.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for keras-openvino 0.0.1
File Size Uploaded
keras_openvino-0.0.1.tar.gz 112.0 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for keras-openvino 0.0.1
File Interpreter ABI Platform
keras_openvino-0.0.1-py3-none-any.whl Python 3 none any Details

Total release size: 228.9 kB

Release files / keras_openvino-0.0.1.tar.gz

Download URL keras_openvino-0.0.1.tar.gz
Size 112.0 kB
Tags Source
SHA-256 checksum
How to use checksums
83125d9eaecc79617e01cbffe41baf19413eeafe8c61ad2cc8b667a71b42b31f
BLAKE2b-256 checksum
How to use checksums
d54dc55b8dc89a286ccdbfdbc6593833b688c7942f88229c38040ac3bfc771cb
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.14

Release files / keras_openvino-0.0.1-py3-none-any.whl

Download URL keras_openvino-0.0.1-py3-none-any.whl
Size 116.9 kB
Tags Python 3
SHA-256 checksum
How to use checksums
1fa80fb0215227b83f8dc5d4b2bf12c93ebdcbc2584f9dd22e500076c6dae5c2
BLAKE2b-256 checksum
How to use checksums
201583e429a06ba6ee4889f5e486c29a1072333a2288474d7e93dda6ea023b8a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.11.14

Release history Release notifications | RSS feed

This release

0.0.1 This release

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page