sdpython/onnx-array-api
Array APIs to write ONNX Graphs
This tool helps developers translate their existing numerical functions written with NumPy into the ONNX format, which is essential for deploying machine learning models across various platforms. It takes your Python functions that use NumPy-like array operations and outputs an ONNX graph, allowing those functions to run efficiently in ONNX-compatible environments. This is specifically for developers building or optimizing conversion libraries for machine learning models.
Used by 1 other package. Available on PyPI.
Use this if you are a developer building a converter library and need to efficiently translate numerical array computations, especially those expressed with NumPy, into ONNX graphs.
Not ideal if you are an end-user simply looking to run an existing ONNX model or if you are not involved in developing conversion tools or libraries.
Stars
11
Forks
—
Language
Python
License
MIT
Category
Last pushed
Jan 18, 2026
Commits (30d)
0
Dependencies
3
Reverse dependents
1
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/sdpython/onnx-array-api"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance ML inferencing and training accelerator
onnx/onnx
Open standard for machine learning interoperability
PINTO0309/onnx2tf
Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The...
NVIDIA/TensorRT
NVIDIA® TensorRT™ is an SDK for high-performance deep learning inference on NVIDIA GPUs. This...
onnx/onnxmltools
ONNXMLTools enables conversion of models to ONNX