yuzawa-san/onnxruntime-java
A type-safe, lightweight, modern, and performant binding Java binding of Microsoft's ONNX Runtime
This project offers a modern and high-performance way to integrate ONNX (Open Neural Network Exchange) machine learning models into Java applications. It allows Java developers to take pre-trained ONNX models as input and run them efficiently, producing predictions or classifications. The primary users are Java developers building applications that need to embed or utilize AI/ML capabilities directly.
Use this if you are a Java developer building applications that require fast, type-safe execution of ONNX machine learning models.
Not ideal if your project uses Java versions older than 23 or if you prefer existing JNI-based ONNX Runtime bindings.
Stars
29
Forks
1
Language
Java
License
MIT
Category
Last pushed
Mar 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/yuzawa-san/onnxruntime-java"
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