cnn-from-scratch and Convolutional-Network
These are competitors—both implement CNNs from scratch using only numpy for educational purposes, serving the same use case of learning neural network fundamentals without external deep learning frameworks.
About cnn-from-scratch
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.
About Convolutional-Network
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.
Scores updated daily from GitHub, PyPI, and npm data. How scores work