Neural Network Compression Framework for enhanced OpenVINO™ inference

Implementation of our Pattern Recognition paper "DMT: Dynamic Mutual Training for Semi-Supervised Learning"

A Natural Language Inference (NLI) model based on Transformers (BERT and ALBERT)

This repository containts the pytorch scripts to train mixed-precision networks for microcontroller deployment, based on the memory contraints of the target device.

A pytorch helper library for Mixed Precision Training, Initialization, Metrics and More Utilities to simplify training of deep learning models

Let's train CIFAR 10 Pytorch with Half-Precision!

Using Deep Learning To Identify And Classify Building Damage

Code repository for "Reducing Underflow in Mixed Precision Training by Gradient Scaling" presented at IJCAI '20

Pytorch implementation of the paper Mixed Precision DNNs: All you need is a good parametrization.

Steel Defect Detection using U-Net. Optimising training and inference using Automatic Mixed Precision and TensorRT respectively.

[CVPR 2015] FaceNet: A Unified Embedding for Face Recognition and Clustering

demo for pytorch-distributed

A Python package for simulating low precision arithmetic in scientific computing and machine learning

[TMLR, 2024] Modular Quantization-Aware Training for 6D Object Pose Estimation

A Tiny Version of the Original ultralytics/yolov5

This repository contains the code and reports for the course INFR11132 Machine Learning Practical. Overall Mark Achieved - 75%

This project implements a neural network-based chess AI using TensorFlow and Keras. The model uses convolutional layers and residual blocks to predict the best chess moves and evaluate board states. It combines policy and value predictions to create a robust chess-playing AI, inspired by AlphaZero's architecture.

A deep learning project for sport image classification using a custom VGG19-based architecture with integrated Grad-CAM heatmap visualization for model interpretability.

A food vision app is an image classification app for 101 dishes demonstrating the power of transfer learning