A lightweight, portable pure C99 onnx inference engine for embedded devices with hardware acceleration support.

The library's .c and .h files can be dropped into a project and compiled along with it. Before use, should be allocated struct onnx_context_t * and you can pass an array of struct resolver_t * for hardware acceleration.

The filename is path to the format of onnx model.

struct onnx_context_t * ctx = onnx_context_alloc_from_file(filename, NULL, 0);

Then, you can get input and output tensor using onnx_tensor_search function.

struct onnx_tensor_t * input = onnx_tensor_search(ctx, "input-tensor-name");
struct onnx_tensor_t * output = onnx_tensor_search(ctx, "output-tensor-name");

When the input tensor has been setting, you can run inference engine using onnx_run function and the result will putting into the output tensor.

onnx_run(ctx);

Finally, you must free struct onnx_context_t * using onnx_context_free function.

onnx_context_free(ctx);

Just type make at the root directory, you will see a static library and some binary of examples and tests for usage.

cd libonnx
make

TBD.

This library based on the onnx version 1.8.0 with the newest opset 13 support. The supported operator table in the documents directory.

• The chinese discussion posts
• The onnx operators documentation
• The tutorials for creating ONNX models
• The pre-trained onnx models

This library is free software; you can redistribute it and or modify it under the terms of the MIT license. See MIT License for details.