This project utilizes a Deep Convolutional Generative Adversarial Network (DCGAN) to generate realistic human face images based on the Flickr-Faces-HQ (FFHQ) dataset. By training a GAN on high-quality face images, the model learns to synthesize diverse and lifelike faces.

Fine-tuned GPT-2 transformer model for fake detection

Contains the dataset and code of the 'Optimizing Wound Diagnosis and Management through AI Tech' project

[Brainlesion 2021] Official PyTorch Implementation for Reciprocal Adversarial Learning for Brain Tumor Segmentation: A Solution to BraTS Challenge 2021 Segmentation Task

Photo realistic single image super resolution using Generative Adversarial Network

Implemented pose aware face recognition network to Improve the performance of face recognition task for the faces at extreme joint pitch and yaw view angles.

Real-time Domain Adapation in Semantic Segmentation project

Data labeling using weak supervision

Generation of Human-Like handwritten digits using different GAN Architectures. The models were developed using Low-Level Tensorflow.

MNIST Generative model

This is the PyTorch implementation of Pix2Pix Paper.

Video frame interpolation using the Vimeo-90k dataset.

Tensorflow implements the most primitive GAN