This repository contains code and resources related to computer vision research and applications. Computer vision is a field of artificial intelligence that trains computers to interpret and understand visual data like images and videos.
This repository contains the following:
-
Image classification models: Code and notebooks for training and evaluating image classification models like convolutional neural networks (CNNs) on datasets like MNIST, CIFAR-10, ImageNet, etc.
-
Object detection models: Code and notebooks for training and using object detection models like YOLO, SSD, on datasets like COCO.
-
Image segmentation models: Code and notebooks for semantic segmentation and instance segmentation using models like Mask R-CNN.
-
Computer vision theory and concepts: Reference notebooks explaining computer vision concepts like image filters, feature extraction, object tracking, etc.
-
Tutorials and examples: End-to-end tutorials for solving different computer vision tasks using OpenCV, PyTorch, TensorFlow, etc.
The code was developed and tested on Python 3.6+. To set up:
- Clone this repository
- Run the Jupyter notebooks or Python scripts for demos and examples
Pull requests are welcome! Feel free to contribute tutorials, fixes, documentation updates, or additions to the code.
Papers, blogs, datasets, and other resources used in this repository: