Computer Vision Projects
FCOS,FULLY CONVOLUTIONAL ONE STAGE OBJECT DETECTOR IMPLEMENTATION
One of the central problems in computer vision is to recoginze and localize object instance with an input image. In this project, we will implement FCOS - a fully convolutional one stage object detector, using Pytorch. We will follow its journal version, which incorporates better designs and provides more detail. Further, we will train FCOS on PASCAL VOC 2007
CONVOLUTION / ViT / ADVERSARIAL SAMPLES
This project is about learning convolutional and Transformer neural networks for image classification. This project will implement, design and train different types of deep networks for scene recognition using PyTorch.
IMAGE PROCESSING
This project was about practicing the basic image processing function and assembling them into a data augmentation pipeline for training models. The basic image processing techniques, such as image resizing, image cropping, color manipulation, image rotation, and rotation without black pixels, were implemented
ROCK PAPER SCISSOR AI GAME:
This project is a real-time rock-paper-scissor game that players can play against computer. I apply neural networks and train the model with our gesture. The computer will be able to sense the hand gesture of a player. As the player posing one of the three gestures in a specific region, the screen simultaneously shows its choice and tells who wins.