Official code for ResUNetplusplus for medical image segmentation (TensorFlow & Pytorch implementation)

Basic Gesture Recognition Using mmWave Sensor - TI AWR1642

2D Convolutional Recurrent Neural Networks implemented in PyTorch

Numpy implementation of deep learning

This code uses the pyTorch Conv2D modules to make the PIV algorithms work faster on GPU

This PyTorch-based project implements a deep neural network for multi-class classification of fashion items. The dataset consists of images categorized into three classes: glasses vs. sunglasses, shoes, and trousers vs. jeans.

A FAST pure numpy based 1D, 2D, even n-dimensional convolution library.

The "witin_nn" framework, based on PyTorch, maps neural networks to chip computations and supports operators including Linear, Conv2d, and GruCell. It enables 8-12 bit quantization for inputs/outputs and weights, implementing QAT.

Reinforcement Learning with Actor-Critic to play Breakout-v4 (Atari) from OpenAI Gym

In this project, used TensorFlow to build a neural network to classify road signs based on an image of those signs.

Handwriting digit recognition using keras.Conv2D and MNIST database.

Image Classification with 2D Convolutions, Deeplearning

Image classification using neural networks. Completed for school. Part 1 is a classical 80s style shallow network, and part 2 is a more modern network. For part 2, I added activation functions, implemented L2 Regularization, changed network depth and width, and used Convolutional Neural Nets to improve performance. Check README

• Developed a Keras model for classification and a Flutter Mobile App for users to detect pox. • Submitted for International Journal Elsevier.