computer-vision and Deep-Learning-Computer-Vision
These are complements rather than competitors—one provides comprehensive course materials (lectures and assignments), while the other provides worked assignment solutions that students would use alongside the original course to verify or learn from completed implementations.
About computer-vision
khanhnamle1994/computer-vision
Programming Assignments and Lectures for Stanford's CS 231: Convolutional Neural Networks for Visual Recognition
This resource provides a comprehensive learning path for understanding and implementing visual recognition systems using deep learning. You'll gain practical skills in setting up, training, and fine-tuning neural networks for tasks like image classification. This is ideal for aspiring machine learning engineers, data scientists, or researchers who want to build sophisticated computer vision applications.
About Deep-Learning-Computer-Vision
seloufian/Deep-Learning-Computer-Vision
My assignment solutions for Stanford’s CS231n (CNNs for Visual Recognition) and Michigan’s EECS 498-007/598-005 (Deep Learning for Computer Vision), version 2020.
This project provides comprehensive assignment solutions for two leading university courses in deep learning and computer vision: Stanford's CS231n and Michigan's EECS 498-007/598-005. It takes theoretical concepts from lectures and applies them through practical implementations, using Python with NumPy, TensorFlow, and PyTorch. The solutions are designed for machine learning practitioners and researchers who want to deepen their understanding of computer vision algorithms.
Related comparisons
Scores updated daily from GitHub, PyPI, and npm data. How scores work