dorajam/Convolutional-Network
A convolutional neural network from scratch
This project helps software developers and machine learning engineers understand how a Convolutional Neural Network (CNN) learns to recognize images. You input image data, and the project allows you to visually observe how the network's internal 'filters' evolve during training to detect patterns. It's designed for those who want to dive deep into the mechanics of CNNs without relying on high-level machine learning frameworks.
103 stars. No commits in the last 6 months.
Use this if you are a developer or machine learning student seeking a low-level, from-scratch implementation to grasp the fundamental architecture and visual learning process of a convolutional neural network.
Not ideal if you need a fast, production-ready image recognition system or want to train a model on large datasets efficiently, as this implementation prioritizes clarity over performance.
Stars
103
Forks
50
Language
Python
License
—
Category
Last pushed
Nov 09, 2016
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/dorajam/Convolutional-Network"
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.