Nisha George's repositories
lottery-ticket
Prune deep neural networks to find sparse trainable networks, almost 10% the original size.
linux-conky
My linux conky files
hessian-regularizer-disentangle
This repository contains my original work of a novel Hessian regularizer for disentangling neural networks. This work was done as part of my master thesis in Computer Science at Saarland University.
2DGeometricShapesGenerator
2D Geometric shapes generator
Autoencoders-Variants
Pytorch implementations of various types of autoencoders
lstm-math
Neural network that solves math equations on the character level
Text-Classifier
Classify news into different categories using neural networks
Music-Genre-Classification
Using neural networks to classify music genre, feature extraction based on DSP
TGA-Resize
Code for TGA image resizing
PolyLaneNet
Code for the paper entitled "PolyLaneNet: Lane Estimation via Deep Polynomial Regression" (ICPR 2020)
semantic-segmentation-pytorch
Pytorch implementation for Semantic Segmentation/Scene Parsing on MIT ADE20K dataset
Codes-for-Lane-Detection
Learning Lightweight Lane Detection CNNs by Self Attention Distillation (ICCV 2019)
loss-landscape
Code for visualizing the loss landscape of neural nets
MedicalNet
Many studies have shown that the performance on deep learning is significantly affected by volume of training data. The MedicalNet project provides a series of 3D-ResNet pre-trained models and relative code.
backboned-unet
Build U-Nets for segmentation from pre-trained TorchVision models.