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)

Distributed, mixed-precision training with PyTorch

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.

demo for pytorch-distributed

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

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

A Tiny Version of the Original ultralytics/yolov5

Modular Quantization-Aware Training for 6D Object Pose Estimation

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

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.

This repository contains a Convolutional Neural Network (CNN) model designed for brain tumor classification using MRI images. The model employs multiple convolutional layers, batch normalization, dropout for regularization, and fully connected layers to achieve high accuracy.