Popular GitHub Repositories for Callbacks

A delightful Ruby way to work with AI. No configuration madness, no complex callbacks, no handler hell – just beautiful, expressive Ruby code.

Toolbox of models, callbacks, and datasets for AI/ML researchers.

A companion guide for the blog post series, LangChain Decoded.

A library of useful callbacks for hybrid scientific machine learning (SciML) with augmented differential equation solvers

A collection of Models, Datasets, DataModules, Callbacks, Metrics, Losses and Loggers to better integrate pytorch-lightning with transformers.

Yet another neural network library

Review materials for the TWiML Study Group. Contains annotated versions of the original Jupyter noteboooks (look for names like *_jcat.ipynb ), slide decks from weekly Zoom meetups, etc.

Tiny ResNet inspired FPN network (<2M params) for Rotated Object Detection using 5-parameter Modulated Rotation Loss

The code trains an LSTM-based residual model on human motion data and applies transfer learning to detect robotic joint faults. It preprocesses data, maps robot features to human-like patterns, and fine-tunes a model while freezing early layers. The optimized model is evaluated with class weighting, callbacks, and feature importance analysis.

This ESP32-based data logger offers an affordable and flexible solution for custom sensor integration. It allows users to incorporate their own sensor libraries and define callbacks within the repository, making it highly adaptable for a wide range of data collection applications.

TF 2.x and PyTorch Lightning Callbacks for GPU monitoring

Create a multi-output machine learning dataframe and apply LSTM/Bidirectional LSTM with Tensorflow early stopping/model Checkpoint callbacks to predict the temperature for next several days

Pneumo.ai is a Streamlit web app for detecting pneumonia from X-rays, leveraging CNN variants like AlexNet, VGG, and ResNet18, with ResNet18 leading with an accuracy of 0.89. It employs early stopping callbacks for efficient model training, visualizes training using TensorBoard, and optimizes inference time with pruning and quantization techniques.