Creating your own custom callbacks with Keras

A guide on custom implementation of metric, logging, monitoring, and lr schedule callbacks in Keras

In-memory cache with write-back strategy. DO NOT USE, it's very slow.

A series of Jupyter notebooks exploring TensorFlow and Keras APIs for deep learning. Covers CNNs on CIFAR10/MNIST, subclassing models, transfer learning, data pipelines, augmentation, image loading, low-level APIs, and custom layers/functions. Demonstrates practical implementations with fine-tuning, preprocessing, and visualization techniques.

A lightweight and flexible callback utility for JavaScript. Easily add, organize, and execute callback functions.

This project demonstrates the development and training of a Feedforward Neural Network (FFNN) for predicting cardiovascular risk using a structured tabular dataset.