frugally-deep and keras2cpp
These are competitors—both convert and deploy Keras/TensorFlow models to C++ inference, with frugally-deep offering a more mature header-only approach while keras2cpp provides a lightweight alternative for Keras 2 specifically.
About frugally-deep
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
This tool helps C++ developers integrate Keras (TensorFlow) machine learning models directly into their C++ applications. You can build and train your model in Python using Keras, then convert it to a lightweight format. The C++ application then takes this converted model and uses it to make predictions, without needing to link against the full TensorFlow library. This is ideal for C++ developers building high-performance or resource-constrained applications that need to leverage pre-trained AI models.
About keras2cpp
gosha20777/keras2cpp
it's a small library for running trained Keras 2 models from a native C++ code.
This is for C++ developers who have trained machine learning models using Keras 2 in Python and need to integrate them into native C++ applications. It takes a Keras model saved from Python and allows you to load and run predictions with it directly in C++. This is ideal for developers building high-performance or embedded C++ applications that require pre-trained machine learning capabilities.
Scores updated daily from GitHub, PyPI, and npm data. How scores work