A basic example of semantic segmentation with fully convolutional networks on the Oxford IIIT pet dataset.

This repository contains the code for Comparing Deep Learning and Classical Computer Vision for Semantic Segmentation: A comprehensive analysis of cutting-edge techniques and algorithms for precise object segmentation in computer vision tasks. This work was done under the Computer Vision course at IIT Jodhpur.

This repository contains homework assignments for a deep learning course, featuring projects on Fully Connected Networks (FCN), Natural Language Processing (NLP), and Variational Autoencoders (VAE)

Some of my projects as a former mentor, reviewer, and beta-tester of Robotics and Self-Driving Car ND

The transition from primary to secondary protein structure involves the folding of linear amino acid sequences (primary structure) into regular patterns like alpha-helices and beta-sheets (secondary structure). Deep learning-based prediction algorithms leverage neural network architectures to infer these patterns from primary sequence data.

SageMaker implementation of LSTM-FCN model for time series classification.

Pytorch implementation for V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation

Simple PyTorch implementations of U-Net/FullyConvNet (FCN) for image segmentation

Fully convolutional neural network for semantic segmentation of pet images.

Deep and Machine Learning for Microscopy

Custom rebuild of the footstep planner package from https://github.com/ROBOTIS-GIT/humanoid_navigation, used in the Master thesis of Mike Simon in Feb 2022.

Semantic Segmentation Architectures Implemented in PyTorch

Cell Segmenter using Machine Learning

In this repository, we thoroughly examine the concepts of Image Segmentation and provide a comprehensive Python implementation using the Tensorflow framework.

Stroke-GFCN: segmentation of Ischemic brain lesions

liver segmentation using deep learning

🚘 Easiest Fully Convolutional Networks

The project uses the FCN-8 architecture and VGG-16 pretrained model as backbone to segment roads on the KITTI dataset.

Implementation of `Fully Convolutional Networks for Semantic Segmentation` by Jonathan Long, Evan Shelhamer, Trevor Darrell, UC Berkeley