onnx 1.20.1

Open Neural Network Exchange

08-10-2021 303 words 2 minutes 0 views

Contents

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Currently we focus on the capabilities needed for inferencing (scoring).

20349 Stars :star:

Stars: 20349, Watchers: 20349, Forks: 3871, Open Issues: 285

The onnx/onnx repo was created 8 years ago and the last code push was 5 hours ago.
The project is extremely popular with a mindblowing 20349 github stars!

How to Install onnx

You can install onnx using pip

pip install onnx

or add it to a project with poetry

poetry add onnx

Package Details

Author: None
License: None
Homepage: None
PyPi:: https://pypi.org/project/onnx/
GitHub Repo:: https://github.com/onnx/onnx

Classifiers

No onnx pypi packages just yet.

Errors

A list of common onnx errors.

Code Examples

Here are some onnx code examples and snippets.

GitHub Issues

The onnx package has 285 open issues on GitHub

WIP: Fix pr_checks
Error: Resource not accessible by integration; action suggest-changes does not work
Fix default attribute values in shape inference
Build option for OpenSSF Compiler Hardening Flags
RFC template for large proposals
[Operator] Grouped matrix multiply
CMake fails to find ONNX sources on macOS unless onnx_SOURCE_DIR is manually set
Fix build failure caused by CMake cache pollution
directly use onnx-weekly at model zoo script
Fix: prevent int64 overflow when computing tensor element count
Fix Reshape shape inference to use dim_param when inputProduct is 0
Clarify DFT behavior when inverse=True and onesided=True (irfft)
Some operator attribute defaults conflict with protobuf defaults
Build failure during iterative wheel builds due to CMake cache pollution.
Python Wheels for the Raspberry Pi (https://www.piwheels.org/project/onnx/)

See more issues on GitHub

Related Packages & Articles

thinc 9.1.1

A refreshing functional take on deep learning, compatible with your favorite libraries

horovod 0.28.1

Horovod is a powerful distributed training framework for Python that allows you to train deep learning models across multiple GPUs and servers quickly and efficiently. It falls under the category of distributed computing libraries. Built on top of TensorFlow, PyTorch, and other popular deep learning frameworks, Horovod simplifies the process of scaling up your model training by handling the complexities of distributed training under the hood.