Karan Shah's repositories
Rooftop-Instance-Segmentation
VGG-16 Model to Segment Rooftops from Aerial Imagery
NYU_depth_v2_extractor
Simple Tool To Extract nyu_depth_v2_labeled.mat
Livingstone-2
Repackaged NASA Livingstone-2 Oliver and L2 engine in Java and C++
NEAT-Flappy-Bird
NEAT algorithm JS
Brain-tumor-segmentation
Quick Brain Tumor Segmentation tryout for everyone
Monocular-Depth-Estimation
Replicated results from DenseDepth using DenseNet169 in Python.
alexnet_pytorch
AlexNet implementation in Pytorch
ANN-Color-Predictor
Improving web UX by giving access to developers, the best suited view comfort of clients.
CIFARGAN_JetsonTK1
A small GAN which creates datasets from CIFAR subsets.
DE_resnet_unet_hyb
Depth estimation from RGB images using fully convolutional neural networks
DenseDepth
High Quality Monocular Depth Estimation via Transfer Learning
Densenet-Tensorflow
Simple Tensorflow implementation of Densenet using Cifar10, MNIST
fl-tutorial
Official MICCAI 2022 Federated Learning for Healthcare Tutorial Repo
gst-video-analytics
This repository contains a collection of GStreamer* elements to enable CNN model based video analytics capabilities (such as object detection, classification, recognition) in GStreamer* framework.
Haystack-Mathematician-Challenge-TCH2018
Test files for the challenge
karpathy.github.io
my blog
keras
Deep Learning for humans
openfl
An open framework for Federated Learning.
Processing-p5.js
Lil games and Neural Network implementations using node.js and p5.js
pytorch-grad-cam
PyTorch implementation of Grad-CAM
RotateNetworks
The rep for the RotateNetworks in ICPR18, Beijing, China.
singularity
Repo for GitHub pages
Tata-Crucible
Files for the challenge 'Haystack Mathematician'
tensorflow
An Open Source Machine Learning Framework for Everyone
Tensorflow-TensorRT
This repository is for my YT video series about optimizing a Tensorflow deep learning model using TensorRT. We demonstrate optimizing LeNet-like model and YOLOv3 model, and get 3.7x and 1.5x faster for the former and the latter, respectively, compared to the original models.