pplonski/keras2cpp
This is a bunch of code to port Keras neural network model into pure C++.
This project helps developers integrate Keras neural network models into C++ applications. It takes a Keras model's architecture and weights, saved as JSON and HDF5 files respectively, and converts them into C++ code. The output is a C++ representation of the neural network that can be compiled and run natively, enabling the use of trained models in C++ environments without Python dependencies.
681 stars. No commits in the last 6 months.
Use this if you need to deploy a Keras-trained convolutional neural network (CNN) model, particularly for image processing tasks, into a pure C++ application.
Not ideal if your Keras model uses activation functions other than ReLU or Softmax, or if you require support for complex network architectures beyond simple CNNs.
Stars
681
Forks
152
Language
C++
License
MIT
Category
Last pushed
Apr 14, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/pplonski/keras2cpp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Dobiasd/frugally-deep
A lightweight header-only library for using Keras (TensorFlow) models in C++.
flashlight/flashlight
A C++ standalone library for machine learning
wichtounet/dll
Fast Deep Learning Library (DLL) for C++ (ANNs, CNNs, RBMs, DBNs...)
NVlabs/tiny-cuda-nn
Lightning fast C++/CUDA neural network framework
KasperskyLab/knp
Kaspersky Neuromorphic Platform