1 repo
Awesome GitHub RepositoriesParameter Optimization Strategies
Methods for controlling gradient updates and training modes for specific model layers or stages.
Distinguishing note: Focuses on the dynamic unfreezing of backbone stages during training, distinct from general learning rate scheduling.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Parameter Optimization Strategies. Refine with filters or upvote what's useful.
Awesome Parameter Optimization Strategies GitHub Repositories
Find the best repos with AI.We'll search the best matching repositories with AI.
- open-mmlab/mmdetection
open-mmlab/mmdetection
32,409View on GitHubThis project is a modular research toolkit designed for developing, training, and evaluating deep learning models for object detection, segmentation, and video instance tracking. It provides a flexible training engine that manages complex neural network execution, including distributed training, custom lifecycle hooks, and weight optimization. The framework is built around a hierarchical configuration system that allows users to define architectures, data pipelines, and training hyperparameters through composable, inheritable files. The project distinguishes itself through its highly modular
Updates parameter gradients for specific backbone stages during training using custom hooks that modify training modes.
Pythoncascade-rcnnconvnextdetr
