Skip to content

GaoShanwen/pytorch-toolkit-dev

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

pytorch-toolkit-dev

building a multitask training platform based on Pytorch

Introduction

cls-dev branch for classfication or re-identification tasks.

Supported Functions

  • Classfication (Single-label, Multi-label) and Re-identification tasks.
  • Metric learning for Re-identification.
  • Visualize training curve (wandb / tensorboard).
  • Remove similarity or noise data, weighted k-nearest neighbor for reid.
  • Visualize Precision-Recall / Receiver-Operating-Characteristic curve.
  • Mixed-Precision Training for faster speed.
  • Visualize models' heatmaps and U-MAPs.
  • Convert pth model to onnx / rknn / ncnn format.

Major Motivation

1.👀 Use the State-of-the-Art image classfication toolkit.

  • Various backbones and pretrained models
  • Bag of training tricks
  • Large-scale training configs
  • High efficiency and extensibility
  • Powerful toolkits

2.🚀 Enhance codes' reusability.

3.🛠️ Minimize our project.

Quick Start

Install Environment

For detailed installation guides, please refer to INSTALL.md.

Command Guides

  • Train & Validate with Training Curve

Refer to README-Train/Val Models for details.

  • Convert Pth Model To ONNX/RKNN

Refer to README-Convert Models for details.

License

This project is released under the Apache 2.0 license.

Contribute

Feel free to create a pull request if you want to contribute (e.g. networks or tricks).