AkiRusProd/numpy-nn-model
Сustom torch style machine learning framework with automatic differentiation implemented on numpy, allows build GANs, VAEs, etc.
This is a custom machine learning framework designed for deep learning researchers and practitioners who need fine-grained control over neural network architectures and training. It allows you to build complex models like Generative Adversarial Networks (GANs) or Variational Autoencoders (VAEs) from basic components. You input your datasets and model specifications, and it outputs trained models and predictions, giving you full transparency into the inner workings of the neural network.
Use this if you are a deep learning researcher or advanced practitioner who wants to understand and modify the foundational elements of a machine learning framework, or if you need to implement novel architectures not easily supported by higher-level libraries.
Not ideal if you are a beginner looking for a simple, high-level tool to quickly train standard models, or if you prioritize ease of use and rapid prototyping over deep customization and understanding.
Stars
81
Forks
5
Language
Python
License
—
Category
Last pushed
Feb 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AkiRusProd/numpy-nn-model"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
digantamisra98/Mish
Official Repository for "Mish: A Self Regularized Non-Monotonic Neural Activation Function" [BMVC 2020]
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.