1 repo
Mechanisms for connecting external pre-trained network backbones to custom models.
Distinguishing note: Focuses on weight mapping and parameter loading for external backbones.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Backbone Integrations. 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 connecting external backbone networks to detection models by mapping pre-trained weight prefixes.