https://github.com/lxc86739795/human_vehicle_parsing_platform

A pytorch codebase for human parsing and vehicle parsing
https://github.com/lxc86739795/human_vehicle_parsing_platform

codebase human parsing person pytorch segmentation vehicle vehicleid veri-wild veri776

Last synced: about 2 months ago
JSON representation

A pytorch codebase for human parsing and vehicle parsing

• Host: GitHub
• URL: https://github.com/lxc86739795/human_vehicle_parsing_platform
• Owner: lxc86739795
• Created: 2020-11-26T04:28:28.000Z (almost 4 years ago)
• Default Branch: main
• Last Pushed: 2021-10-11T02:55:08.000Z (almost 3 years ago)
• Last Synced: 2024-05-22T04:17:28.988Z (4 months ago)
• Topics: codebase, human, parsing, person, pytorch, segmentation, vehicle, vehicleid, veri-wild, veri776
• Language: Python
• Homepage:
• Size: 1.24 MB
• Stars: 90
• Watchers: 2
• Forks: 8
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

• Vehicle_reID-Collection - code

README

        
# parsing_platform

A pytorch codebase for human parsing and vehicle parsing.

## Introduction

A pytorch codebase for human parsing and vehicle parsing. The introduction of our new MVP dataset for vehicle parsing can be found [HERE](https://xinchenliu.com/MVP.html).

    ![Image](./images/human_parsing_vis.png)  ![Image](./images/vehicle_parsing_vis.png)

## Requirements

- Linux or macOS with python ≥ 3.6

- PyTorch = 0.4.1

- torchvision that matches the Pytorch installation. You can install them together at [pytorch.org](https://pytorch.org/) to make sure of this.

- tensorboard (needed for visualization): `pip install tensorboard`

## Supported methods

- [x] PSPNet

- [x] DeepLabV3

- [x] CCNet

- [x] DANet

- [x] OCNet

- [x] CE2P

- [x] HRNet

- [x] BraidNet

## Supported datasets

- [x] Look-Into-Person [LIP](https://github.com/lemondan/HumanParsing-Dataset)

- [x] Multi-grained Vehicle Parsing [MVP](https://xinchenliu.com/MVP.html)

## Train and Test

The scripts to train and test models are in `train_test`.

The scripts for PSPNet, DeepLabV3, and HRNet are ready for directly running.

The train/val/test splitting files used in our experiments can be found [here](https://github.com/lxc86739795/human_vehicle_parsing_platform/blob/main/split.zip).

## Model Zoo

**Models trained on the MVP dataset for vehicle parsing**:

| Method | Dataset | Pixel Acc | Mean Acc | mIoU | download |

| :---: | :---: | :---: |:---: | :---: |:---: |

| PSPNet | MVP-Coarse | 90.26% | 89.08% | 79.78% | [model](https://github.com/lxc86739795/parsing_platform/releases/download/v0.1/pspnet_mvp_coarse.pth) |

| PSPNet | MVP-Fine | 86.21% | 69.61% | 57.47% | [model](https://github.com/lxc86739795/parsing_platform/releases/download/v0.1/pspnet_mvp_fine.pth) |

| DeepLabV3 | MVP-Coarse | 90.55% | 89.45% | 80.41% | [model](https://github.com/lxc86739795/parsing_platform/releases/download/v0.1/deeplabv3_mvp_coarse.pth) |

| DeepLabV3 | MVP-Fine | 87.42% | 73.50% | 61.60% | [model](https://github.com/lxc86739795/parsing_platform/releases/download/v0.1/deeplabv3_mvp_fine.pth) |

| HRNet | MVP-Coarse | 90.40% | 89.36% | 80.04% | [model](https://github.com/lxc86739795/parsing_platform/releases/download/v0.1/hrnet_mvp_coarse.pth) |

| HRNet | MVP-Fine | 86.47% | 72.62% | 60.21% | [model](https://github.com/lxc86739795/parsing_platform/releases/download/v0.1/hrnet_mvp_fine.pth) |

\* The performance is evaluated on the test set.

\** The PSPNet and HRNet models are trained with cross-entropy loss. The DeepLabV3 models are trained with cross-entropy + IoU loss.

\*** We also released several pre-trained model on the LIP dataset. Please refer to [models](https://github.com/lxc86739795/human_vehicle_parsing_platform/releases/tag/v0.1).

## Citation

```BibTeX

@inproceedings{mm/LiuZLSM19,

  author    = {Xinchen Liu and

               Meng Zhang and

               Wu Liu and

               Jingkuan Song and

               Tao Mei},

  title     = {BraidNet: Braiding Semantics and Details for Accurate Human Parsing},

  booktitle = ACM MM,

  pages     = {338--346},

  year      = {2019}

}

@inproceedings{mm/LiuLZY020,

  author    = {Xinchen Liu and

               Wu Liu and

               Jinkai Zheng and

               Chenggang Yan and

               Tao Mei},

  title     = {Beyond the Parts: Learning Multi-view Cross-part Correlation for Vehicle

               Re-identification},

  booktitle = {ACM MM},

  pages     = {907--915},

  year      = {2020}

}