model2c 1.0.0

ML model to low-level inference convertor

model2c

About the Project

Python API and Command Line tool to convert ML models into low-level inference for embedded platforms

Getting Started

Prerequisites

Make sure you have onnx2c installed and added to PATH.

Make sure you have ProtocolBuffers libraries installed, e.g.:

• Ubuntu: apt install libprotobuf-dev protobuf-compiler
• MacOS: brew install protobuf

Get the sources:

git clone https://github.com/kraiskil/onnx2c.git
cd onnx2c
git submodule update --init

Then run a standard CMake build

mkdir build
cd build
cmake ..
make onnx2c

And finally add to path

export PATH=$PATH:/path/to/onnx2c/folder

Installation

You can can install the package through pypi:

pip install model2c

Or you can clone the repo and build directly from source:

git clone [e-mail]:h3x4g0ns/model2c.git
cd model2c
make install

Usage

Train a model with correponding data until sufficient metrics are obtained.

import torch
import model2c.pytorch import convert

# run convertor
convert(model=torch_model, input_shape=(batch_size, 1, 224, 224))
print(f"size of output model: {os.path.getsize('model.c')/1024} kilobytes")

Support

model2c currently supports the following ML frameworks

• torch
• tf/keras

To Do

• torch convert
• tf convert
• make command line utility
• include dynamic axis for batch size