Fully Convolutional DenseNet (A.K.A 100 layer tiramisu) for semantic segmentation of images implemented in TensorFlow.

Deep Convolutional Neural Networks for Semantic Segmentation of Multi-Band Satellite Images

Implementation of The One Hundred Layers Tiramisu for semantic segmentation in Keras

A cost model for compiler performance optimization using deep learning.

Reinforcement learning for compiler performance optimization.

This repository contains few Convolution based networks implemented for detecting cilia which is completed on CSCI 8360, Data Science Practicum at the University of Georgia, Spring 2018.

Implemented Tiramisu network using pytorch.

Identifies Salt Deposits by analyzing subsurface images.