Computer Vision 🖥️ 👀

Computer vision is a field of artificial intelligence (AI) that enables computers and systems to derive meaningful information from digital images, videos and other visual inputs — and take actions or make recommendations based on that information.

Here are my Implementations of different architectures using Pytorch

CNN Architecture

-LeNet5 paper code

-GoogleNet paper code

-Resnet paper code

-VGG19 paper code

Image Segmentation

-UNet paper code

Vision Transformer

-Vit (original) paper code

GANS

-FC-Gan paper code

-DCGAN paper code

-Pix2Pix paper code

Tech Used

• Pytorch
• Numpy
• Jupyter notebook
• Pytorch Lightning
• hydra
• Yaml
• VSCode

Projects

-Hieroglyphics Detector From Research to Production (my Dream Project) code

-Neural Style Transfer code

-Resize Network from Scratch Paper code

-Video Classification using Resnet code Colab