henrysrtaylor/DeepNum
A modular Deep Learning framework built from scratch using NumPy. Implements different layers, activation functions, and loss with backpropagation. Developed for self-educational purposes to bridge the gap between high-level theory and low-level implementation.
Stars
—
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 20, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/henrysrtaylor/DeepNum"
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]
itdxer/neupy
NeuPy is a Tensorflow based python library for prototyping and building neural networks
Sentdex/nnfs_book
Sample code from the Neural Networks from Scratch book.
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.