Deep Learning

arTransfer is a neural style transfer application that allows you to train your own models or use pre-trained models to stylize images.

YOLOv8 models implemented for real time Pose detection, object detection, image segmentation tasks.

This repository contains a project for detecting fraudulent credit card transactions using machine learning. The dataset used for this project is sourced from Kaggle’s Credit Card Fraud Detection dataset.

Resnet Paper Link Deeper networks can capture more complex features and improve performance on challenging datasets like ImageNet. However, increasing the depth of these networks introduces significant challenges, such as vanishing and exploding gradients, which hamper training.

Paper Walkthrough Link to the Paper 1. Abstract The proposed network, called U-Net, has two main parts: one part captures the overall context of the image, and the other part ensures precise localization of features.