1 repo
Awesome GitHub RepositoriesLearning Rate Decay Functions
Mathematical functions used to modulate learning rates over time during the training process.
Distinguishing note: This is a specific mathematical implementation of a decay strategy, distinct from the general scheduler configuration.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Learning Rate Decay Functions. Refine with filters or upvote what's useful.
Awesome Learning Rate Decay Functions GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- huggingface/pytorch-image-models
huggingface/pytorch-image-models
36,386View on GitHubThis 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
Tanh learning rate scheduling adjusts the learning rate using a hyperbolic tangent function to provide a smooth transition in decay.
Pythonaugmixconvnextdistributed-training
