Ml Library Python Packages

pytorch-dml

PyTorch library for Deep Mutual Learning, knowledge distillation, and collaborative neural network training with advanced features and research-backed strategies.

humanml

HumanML is a human-centered machine learning library designed to simplify the machine learning workflow while providing professional results. The library automates data preprocessing, model selection, training, evaluation, and reporting, making machine learning accessible to all users.

crawl-relevance-layers

Pure Python async web crawling with BM25 + semantic relevance ranking.

torchresidual

Flexible residual connections for PyTorch with a clean API. Build complex skip connections using Record/Apply modules. 5 operations (add, concat, gated, highway, multiply), learnable alphas, automatic projection. Thread-safe for DataParallel/DDP. Fully typed and tested.

sk-autod

Auto-diagnosis for training curves

earcp

A Self-Regulating Coherence-Aware Ensemble Architecture for Sequential Decision Making/EARCP: Ensemble Auto-Régulé par Cohérence et Performance