Rajat Agarwal's repositories
SuperResolution-with-Perceptual-loss
In this project I have used an convolution neural network with perceptual loss to convert low res image into high res image.
HackerEarth-Portea-Challenge
Rank-16 ,In HackerEarth Portea challenge we have to predict and classify patient's lifetime revenue into four given buckets
AV-Genpact-Hackathon
Rank 13/764. This repository consist code of Genpact Machine Learning Hackathon on Analytics Vidhya
awesome-computer-vision
A curated list of awesome computer vision resources
HackerEarth-caavo
Rank 11/529
Kaggle-Toxic-classifier
This a part of Kaggle Competion, Toxic Comment Classification Challenge by Jigsaw .This was a multilabel classification challenge.This code is a improved version of my submission in the competion.
mlcourse.ai
Open Machine Learning Course
Unet-for-Image-Segmentation
In this project I have done image segmentation on Carvana Dataset from Kaggle. I have used U-net like architecture for segmentation
DIF
A simple and fast web app to remove duplicate images from your datasets.
Kaggle-siim-melanoma
Training pipeline for image classification in PyTorch.
react-weather-app
Weather app in react
avo
Generate x86 Assembly with Go
cleverhans
An adversarial example library for constructing attacks, building defenses, and benchmarking both
CricLang
CricLang is a fun dynamically typed language written in Go for cricket enthusiasts.
fashion-mnist-classifier-using-NN
We train a Neural Network with 3 hidden layers to classify Fashion-MNIST dataset using Tensorflow and numpy
Grab_Challenge
This repository contains code for Grab Challenge. In this challenge the task is to design a model to classify the model and make of cars
Kaggle-TalkingData-FraudDetection
https://www.kaggle.com/rajat94
polyaxon
Machine Learning Platform for Kubernetes
pytorch-lightning
The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.
snorkel
A system for quickly generating training data with weak supervision
streamlit
Streamlit — The fastest way to build data apps in Python
telegraf
The plugin-driven server agent for collecting & reporting metrics.