1 repositorio
Awesome GitHub RepositoriesCheckpoint Simplifiers
Utilities for removing redundant training data and optimizer states from model checkpoint files to minimize size.
Distinct from Model Checkpointing: Distinct from Model Checkpointing: focuses on post-training size reduction and pruning of metadata rather than the act of saving/restoring state.
Explore 1 awesome GitHub repository matching artificial intelligence & ml · Checkpoint Simplifiers. Refine with filters or upvote what's useful.
Awesome Checkpoint Simplifiers GitHub Repositories
Encuentra los mejores repositorios con IA.Buscaremos los repositorios que mejor coincidan usando IA.
- open-mmlab/mmpose
open-mmlab/mmpose
7,374Ver en GitHubMMPose is a PyTorch-based pose estimation toolbox and deep learning training pipeline designed for detecting 2D and 3D keypoints on humans, animals, and faces. It serves as a computer vision model zoo and a framework for both 2D pose estimation and 3D pose lifting. The project is distinguished by its modular architecture and extensibility, employing a registry-based system and hierarchical configurations to allow for custom algorithm integration and model pipeline customization. It supports diverse estimation paradigms, including top-down, bottom-up, and two-stage pose lifting workflows. The
Implements utilities to strip redundant optimizer states and training information from checkpoints to reduce model file size.
Pythonanimal-pose-estimationbenchmarkcpm
