fengwang/ceras

Ceras is yet another tiny deep learning engine, in pure c++ and header only.

/ 100

Emerging

Ceras is a lightweight deep learning engine designed for C++ developers building neural networks. It helps you define, train, and evaluate deep learning models by taking raw numerical data as input and producing trained models or predictions. It's ideal for C++ programmers who need fine-grained control over their deep learning implementations, from defining individual layers to managing training parameters.

127 stars.

Use this if you are a C++ developer who needs a header-only deep learning library to quickly prototype and deploy neural network models with optional GPU acceleration.

Not ideal if you are not familiar with C++ or prefer a high-level API for deep learning without needing to delve into implementation details.

deep-learning-framework neural-networks machine-learning-engineering C++-development AI-model-building

No License No Package No Dependents

Maintenance 6 / 25

Adoption 10 / 25

Maturity 8 / 25

Community 13 / 25

How are scores calculated?

Stars

127

Forks

Language

C++

License

—

Higher-rated alternatives

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

Explore ML Frameworks

All categories Trending ML Framework directory Insights