1 repo
Schedulers that react to training metrics to adjust learning rates dynamically.
Distinguishing note: Focuses on metric-based feedback loops rather than fixed schedule patterns.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Adaptive Schedulers. Refine with filters or upvote what's useful.
This project is a comprehensive library of state-of-the-art neural network architectures designed for image classification and feature extraction. It provides a complete deep learning training framework that supports distributed execution, allowing users to build, train, and fine-tune vision models using optimized schedulers and pre-configured training recipes. The library distinguishes itself through a modular backbone architecture that treats neural networks as decoupled feature extractors, enabling the retrieval of multi-scale outputs for downstream tasks like object detection and segmenta
Plateau learning rate scheduling reduces the learning rate when monitored metrics stop improving to stabilize the training process.