ggsharma/microgradpp
A header-only C++ autograd engine and neural network library inspired by Karpathy's micrograd. Learn backpropagation in modern C++17.
This helps C++ developers build and train simple neural networks directly within their C++ projects. It takes numerical data or image inputs and produces trained models capable of making predictions or classifications. It's designed for C++ programmers who want to implement machine learning without relying on Python-based frameworks, especially those who appreciate straightforward, educational tools.
Use this if you are a C++ developer looking for a straightforward, high-performance way to integrate machine learning, particularly neural networks and automatic differentiation, into your C++ applications, especially with computer vision tasks.
Not ideal if you are a Python developer, need advanced features like recurrent neural networks, or require a library with extensive pre-built models and complex optimization algorithms.
Stars
15
Forks
1
Language
C++
License
GPL-3.0
Category
Last pushed
Jan 14, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/ggsharma/microgradpp"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
JonathanRaiman/theano_lstm
:microscope: Nano size Theano LSTM module
google/tangent
Source-to-Source Debuggable Derivatives in Pure Python
ahrefs/ocannl
OCANNL: OCaml Compiles Algorithms for Neural Networks Learning
yoshoku/numo-openblas
Numo::OpenBLAS builds and uses OpenBLAS as a background library for Numo::Linalg
statusfailed/catgrad
a categorical deep learning compiler