Computer Vision toolbox with implementations for object detection, segmentation, style transfer, and saliency visualisation using PyTorch, OpenCV, NumPy, and Sklearn. Trained models include ResNet-18, RCNNs, YOLO, FCNN, and UNet for various vision tasks, with tracking via Weights & Biases.
Please Note: Some datasets for some of the assignments have been removed due to their multi-GB size.