ONNX-Scala
ONNX-Scala provides an API and backend for deep and classical machine learning in Scala.
About ONNX-Scala
ONNX-Scala is an open-source ONNX API and backend for Scala 3 for deep learning and classical machine learning. It provides full-model inference by loading an ONNX file from disk and passing it to the underlying backend, and a fine-grained, versioned API for individual ONNX operators.
It is cross-built for Scala JVM, Scala.js/JavaScript and Scala Native, and lists support for ONNX 1.17.0 with ONNX Runtime 1.20.0. The full-model API is untyped in its inputs and can fail at runtime, but allows dynamic shapes when the model supports symbolic dimensions.
Key features
- Run full ONNX models through backend for inference
- Versioned, numerically generic API for individual ONNX operators
- Cross-built for Scala JVM, Scala.js and Scala Native
- Typed tensors with shape and denotation checking in Scala 3
- Load ONNX model files from disk at runtime
- Support dynamic input shapes where model allows symbolic dimensions
Best for: Scala 3 developers running ONNX deep learning or classical machine learning models.
Good for
- Passes full model graph as-is to backend for optimization
- Cross-built for JVM, JavaScript and Native targets in Scala 3
- Supports ONNX 1.17.0 with backward compatibility for older model versions
Watch out for
- Full-model API is untyped in inputs and can fail at runtime
- JVM use adds overhead moving data between JVM and native memory
ONNX-Scala at a glance
- Category
- Development › Developer Tools
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
Guides for Developer Tools
ONNX-Scala alternatives
Tools and sites you could use instead, ranked by how closely they match.
The fastai deep learning library includes documentation and setup guidance, including instructions for use with Google Colab.
Open source
24 alternatives
Netron displays neural network, deep learning, and machine learning models across formats such as ONNX, TensorFlow, and PyTorch.
Open source
24 alternatives
Tesseract provides an open-source OCR engine for extracting text from images, with its main repository hosted on GitHub.
Open source
24 alternatives
The anneal project is a Go machine learning compiler with graph rewriting, autodiff, and a WebGPU backend.
Open source
24 alternatives
Machine learning pipelines can use whylogs, an open-source library for logging data quality and model performance.
Open source
24 alternatives
The Pattern Recognition Toolbox provides MATLAB tools for pattern recognition and machine learning.
Open source
24 alternativesPopular in Developer Tools
Well-known listings from the same topic.
AppDevToolsappdevtools.comCommand Not Foundcommand-not-found.comTestFlighttestflight.apple.com/join/A8GwCnq8Sourcegraphabout.sourcegraph.comProject Wallaceprojectwallace.comCarbon Calculatorwebsitecarbon.com
ONNX-Scala FAQ
How do I add ONNX-Scala to a project?
Add libraryDependencies += "org.emergent-order" %% "onnx-scala-backends" % "0.17.0" to the build.sbt in your project.
What Scala and ONNX versions does it target?
Code snippets are written in Scala 3, cross-built for Scala JVM, Scala.js/JavaScript and Scala Native, with ONNX 1.17.0 and ONNX Runtime 1.20.0.
Can I use different batch sizes per model call?
Yes, with the full-model API if your model supports this via symbolic dimensions, per ONNX Shape Inference.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.