A flexible utility for converting tensor precision in PyTorch models and safetensors files, enabling efficient deployment across various platforms.

Features injected recurrent neural networks for short-term traffic speed prediction

A comprehensive toolkit built with PyTorch, designed to facilitate the training, evaluation, and visualization of autoencoders. From simple linear autoencoders to convolutional and variational architectures, this project offers an intuitive and expandable framework for anyone delving into the realm of unsupervised learning.

Convolutional Neural Network using MobileNetV2 for Fashion MNIST classification, showcasing key Keras callbacks (EarlyStopping, ModelCheckpoint, TensorBoard) for optimised training and evaluation.