GC-MVSNet: Multi-View, Multi-Scale, Geometrically-Consistent Multi-View Stereo

Sentiment Analysis of YouTube Comments using YouTube Data API v3

Path Finding Using A_star Algorithm for Real-world map data (using co-ordinates)

Game Playing AI for Quintris (A modified version of Tetris)

Optical Character Recognition using Probabilistic Models (Bayesian Network and Hidden Markov Model)

A PyTorch Implementation of Deeply Supervised Depth Map Super Resolution as Novel View Synthesis (https://arxiv.org/abs/1808.08688).

Reproduce the paper named 'HOW MUCH POSITION INFORMATION DO CONVOLUTIONAL NEURAL NETWORKS ENCODE?', which published as a conference paper at ICLR 2020.

⚡VoltaML is a lightweight library to convert and run your ML/DL deep learning models in high performance inference runtimes like TensorRT, TorchScript, ONNX and TVM.

An example showcasing the deployment of a PyTorch model using Flask on Heroku.

This is the backend code for url shortner(cr-ly).

Implementation of popular data structures and algorithms.

Implementation of the deep convolutional GAN paper titled "Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks" using PyTorch and PyTorch Lightning.

Implementation of the neural style transfer paper titled "Image Style Transfer Using Convolutional Neural Networks" using PyTorch.

Using pose-net to count the number of squats done

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )