Malay Agarwal's repositories
generative-ai-with-llms-notes
Notes for the course Generative AI With Large Language Models, offered by DeepLearning.AI on Coursera
real_python_data_cleaning_tutorial
Companion notebook for Real Python's Data Cleaning Tutorial
MesoNet-DeepFakeDetection
A CNN-based DeepFake detector called MesoNet, replicated from a 2018 paper available at https://arxiv.org/abs/1809.00888
DeepNeuralNetworksFromScratch
Different kinds of deep neural networks (DNNs) implemented from scratch using Python and NumPy, with a TensorFlow-like object-oriented API.
fast-ats-pytorch
Implementation of "Processing Megapixel Images with Deep Attention-Sampling Models" in PyTorch.
Deep-Learning-Specialization-Coursera
Deep Learning Specialization Course by Coursera. Neural Networks, Deep Learning, Hyper Tuning, Regularization, Optimization, Data Processing, Convolutional NN, Sequence Models are including this Course.
Kaggle-Spaceship-Titanic
Use ensembling and Optuna to solve the Saceship Titanic competition.
MesoNet-DeepfakeDetection-API
A Django REST API to get results from MesoNet (https://github.com/MalayAgarwal-Lee/MesoNet-DeepFakeDetection), a DeepFake detector
SteeringWheelAnglePredictor
A CNN-based deep learning model to predict steering wheel angles for a car, replicated from a 2016 paper available at https://arxiv.org/abs/1604.07316
Algorithms
C implementation of popular algorithms and solutions for problems from CLRS
Kaggle-Dogs-Vs-Cats
PyTorch pipeline for the Dogs vs. Cats competition on Kaggle.
Kaggle-Titanic
EDA and solution for the titanic competition.
kickstart.nvim
A launch point for your personal nvim configuration
lane_detection_opencv
A lane detector built using Python and OpenCV
Library-Management-System
A Java based application for Library Management
MesoNet-DeepfakeDetection-WebApp
A web app to obtain predictions from MesoNet, a CNN-based deepfake detector.
Prime-Factorization
A Python script which can factorize numbers to their prime counterparts.
simple-rss
A simple CLI tool to get your RSS feeds in one place.
StreamingCNN
To train deep convolutional neural networks, the input data and the activations need to be kept in memory. Given the limited memory available in current GPUs, this limits the maximum dimensions of the input data. Here we demonstrate a method to train convolutional neural networks while holding only parts of the image in memory.
striver-dp-series
Solutions to Striver DP Series in C++ and Python
textual-monopoly
The game of monopoly implemented using Textual.
Tic-Tac-Toe
A game of Tic-Tac-Toe made in Python