Joaomlg/neural-network-from-scratch
CNN implemented from scratch using Python and Numpy
This project helps you understand how a Convolutional Neural Network works by letting you build and train one from basic numerical operations. You provide image data, and it outputs a trained model that can classify those images. This is for students, researchers, or anyone curious about the fundamental mechanics of deep learning.
No commits in the last 6 months.
Use this if you want to learn the mathematical and computational building blocks of image recognition systems without relying on high-level libraries.
Not ideal if you need to solve a real-world image classification problem quickly or require advanced deep learning features.
Stars
14
Forks
5
Language
Python
License
MIT
Category
Last pushed
Nov 15, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Joaomlg/neural-network-from-scratch"
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.