vzhou842/cnn-from-scratch
A Convolutional Neural Network implemented from scratch (using only numpy) in Python.
This project helps machine learning practitioners understand the inner workings of a Convolutional Neural Network (CNN) by showing its implementation using only fundamental Python libraries. It takes raw image data and processes it through the CNN architecture, demonstrating how features are extracted and classified. Aspiring data scientists, AI engineers, or students learning deep learning concepts would find this useful for educational purposes.
360 stars. No commits in the last 6 months.
Use this if you are a developer or student who wants to learn the fundamental mathematical and algorithmic details of how a Convolutional Neural Network processes data, without relying on high-level deep learning frameworks.
Not ideal if you need a high-performance, production-ready CNN implementation or are looking to train complex models efficiently.
Stars
360
Forks
119
Language
Python
License
MIT
Category
Last pushed
Aug 02, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vzhou842/cnn-from-scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
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
nicklashansen/rnn_lstm_from_scratch
How to build RNNs and LSTMs from scratch with NumPy.
Synthaze/EpyNN
Educational python for Neural Networks.