onnx
What is a .onnx file?
application/octet-stream
ONNX (Open Neural Network Exchange) is a portable, protobuf-based graph format for machine-learning models. It records typed inputs and outputs, tensor initializers, operators, attributes, and an opset version so inference runtimes can exchange a model without sharing its training framework.
How to use a .onnx file
Load an example .onnx model in an ONNX-compatible runtime, feed it the JSON input from the same fixture group, and compare the resulting tensor with the published expected output. Check names, shapes, dtypes, opset, and tolerance as well as numeric values; each Novus model is validated with the ONNX checker and reference evaluator before publication.
Download example .onnx files
- ONNX Inference Contract - Static Identity ModelA one-node identity graph with a fixed 1x4 float tensor, useful as the smallest loader and inference smoke test. The matching JSON input and expected output make the model immediately usable in a CI inference assertion.
- ONNX Inference Contract - Affine MatMul plus Add ModelA two-node affine transform with fixed weights and bias, exercising initializers, MatMul dimensions and Add broadcasting. The matching JSON input and expected output make the model immediately usable in a CI inference assertion.
- ONNX Inference Contract - Two-Input Broadcast Add ModelA two-input Add graph where a length-two bias broadcasts across a 2x2 matrix, checking input binding and broadcasting rules. The matching JSON input and expected output make the model immediately usable in a CI inference assertion.
- ONNX Inference Contract - Dynamic-Batch ReduceSum ModelA ReduceSum graph with a symbolic batch dimension and fixed feature width, for dynamic-shape import and batch-output tests. The matching JSON input and expected output make the model immediately usable in a CI inference assertion.