1 repo
Tools for initializing models with pre-trained weights to accelerate convergence.
Distinguishing note: Focuses on cross-architecture weight initialization.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Transfer Learning Utilities. Refine with filters or upvote what's useful.
This 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
Allows initializing a custom two-stage detector with weights from a pre-trained single-stage model.