What is a .ONNX file?
.ONNX is a Native code, ML & misc (more) file (Data & code). Analyser identifies a .ONNX file and reads the metadata in its header, right in your browser.
- Did you know
- ONNX, the Open Neural Network Exchange, is a shared format for machine-learning models so they can move between frameworks like PyTorch and TensorFlow.
- It was launched by Microsoft and Facebook in 2017 to break the lock-in of each framework's own model format.
- A trained model exported to .onnx can then run through the optimised ONNX Runtime on servers, phones or the web.
- What Analyser reads
- Identify and read cross-platform binaries, ML models and build artefacts: ONNX neural-network models (the framework that exported it and the IR/model version), native Node.js/Electron add-ons (.node) and macOS dynamic libraries (.dylib - Mach-O/PE/ELF container and architecture), LevelDB/RocksDB tables (.ldb), Git pack reverse indexes (.rev - RIDX header), Citation File Format metadata (CITATION.cff, content-gated against binary CFF fonts), compiler response files (.rsp), Razer Chroma animations (.chroma), build stamps/markers (.stamp) and pattern/grid data (.cgp).
- Depth of analysis
- .ONNX is an identification-grade format: Analyser recognises it from its bytes and decodes the header metadata it carries, rather than opening it in a full viewer. Formats that do get a full viewer are marked "Full" on the formats page.
- Open a .ONNX file
- Drag a .ONNX file onto the Analyser home page (or tap to pick one). It is identified entirely in your browser - nothing is uploaded, there is no account, and it works offline once installed.