What is a .ONNX file?
ONNX is a framework-neutral way to write down a trained neural network: a graph of operations, the tensors flowing between them, and the learned weights. A model trained in PyTorch can be exported to ONNX and run anywhere that speaks it.
- Did you know
- An ONNX file stores no list of connections at all - one node follows another purely because they name the same tensor, so the graph has to be reassembled from those names.
- 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 shows you
- Open machine-learning models and read what is actually in them. ONNX models and frozen TensorFlow graphs are drawn as a graph: every operation as a box, every tensor flowing between them as a line, laid out left to right by depth so parallel branches sit side by side. Neither format stores the connections - a node follows another because one of its inputs is one of the other's outputs - so the edges are recovered by matching those names. Alongside the picture: the operation mix that fingerprints the architecture, the input and output shapes (including the dynamic ones a model leaves open), every weight tensor with its shape, and the total parameter count. Weight files are read too - Safetensors and GGUF give up their full tensor list, precision and parameter count, and a GGUF also declares its architecture, context length and quantisation. A PyTorch checkpoint is a Python pickle, which is a program rather than a document, so nothing in it is ever run: the opcodes are read as bytes and every module it would import is listed, with anything a file of numbers has no business touching flagged. Keras models have their layer list read from the architecture JSON.
- Open a .ONNX file
- Drag a .ONNX file onto the Analyser home page (or tap to pick one). It opens entirely in your browser - nothing is uploaded, there is no account, and it works offline once installed.