Data

Tools

Indexes

Applications

Experiments

Open Source Science

mfpsg

mask2former psg

https://github.com/wangqixun/mfpsg

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (5.3%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

mask2former psg

Basic Info
  • Host: GitHub
  • Owner: wangqixun
  • License: apache-2.0
  • Language: Python
  • Default Branch: main
  • Size: 27.1 MB
Statistics
  • Stars: 22
  • Watchers: 2
  • Forks: 1
  • Open Issues: 1
  • Releases: 0
Created almost 4 years ago · Last pushed over 3 years ago
Metadata Files
Readme License Citation

README.md

Mask2Former PSG

整体框架还是基于mmdet，其中relation部分借鉴transformers


Install

环境参考 get_started.md pip install -e .

apex 建议通过下面代码安装 git clone https://github.com/NVIDIA/apex cd apex pip install -v --disable-pip-version-check --no-cache-dir --global-option="--cpp_ext" --global-option="--cuda_ext" ./ panopticapi pip install git+https://github.com/cocodataset/panopticapi.git


数据准备

下载 coco instance val 2017，用于验证 psg val 的instance map

修改 wqx/main.py 中下列文件路径 ```python if name == 'main': # raw data file rawpsgdata='/share/data/psg/dataset/forparticipants/psgtrainval.json' rawcocovaljsonfile='/share/data/coco/annotations/instancesval2017.json'

# output file
output_coco80_val_instance_json = '/share/wangqixun/workspace/bs/psg/psg/data/instances_val2017_coco80.json'
output_tra_json='/share/wangqixun/workspace/bs/psg/psg/data/psg_tra.json'
output_val_json='/share/wangqixun/workspace/bs/psg/psg/data/psg_val.json'
output_val_instance_json='/share/wangqixun/workspace/bs/psg/psg/data/psg_instance_val.json'

执行 python wqx/main.py ```


(可能)需要的一些预训练权重

分割部分:

mask2former， 预训练权重

关系分类：

transformers， 预训练权重


训练

  • 调整 configs/psg/mask2former_r50.py 中预训练路径、输出路径、tra val 数据路径 python # 模型中预训练部分 model['relationship_head']['pretrained_transformers'] = "/path/chinese-roberta-wwm-ext" load_from = "/path/mask2former_r50_lsj_8x2_50e_coco-panoptic_20220326_224516-11a44721.pth" # tra 数据部分 data['train']['ann_file'] = 'data/psg_tra.json' data['train']['img_prefix'] = '/path/psg/dataset/' data['train']['seg_prefix'] = '/path/psg/dataset/' # val 数据部分 data['val']['ann_file'] = 'data/psg_val.json' data['val']['img_prefix'] = '/path/psg/dataset/' data['val']['seg_prefix'] = '/path/psg/dataset/' data['val']['ins_ann_file'] = 'data/psg_instance_val.json' # test 数据部分 data['test']['ann_file'] = 'data/psg_val.json' data['test']['img_prefix'] = '/path/psg/dataset/' data['test']['seg_prefix'] = '/path/psg/dataset/' data['test']['ins_ann_file'] = 'data/psg_instance_val.json' # 输出路径 work_dir = 'output/v0'
  • 训练咯 # 8卡训练 bash tools/dist_train.sh configs/psg/mask2former_r50.py 8


Submit

  • 调整 wqx/infer_p.py 中 cfg 和 ckp python if __name__ == '__main__': get_val_p( mode='v0', cfg='configs/psg/mask2former_r50.py', ckp='output/v0/latest.pth', )
  • 推理 mkdir -p /share/wangqixun/workspace/bs/psg/mfpsg/submit/val/submission/panseg python wqx/infer_p.py
  • 打包 cd submit/v0 zip -r submission.zip submission/

Owner

  • Login: wangqixun
  • Kind: user

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMDetection Contributors"
title: "OpenMMLab Detection Toolbox and Benchmark"
date-released: 2018-08-22
url: "https://github.com/open-mmlab/mmdetection"
license: Apache-2.0

GitHub Events

Total
  • Issues event: 1
Last Year
  • Issues event: 1

Issues and Pull Requests

Last synced: 10 months ago

All Time
  • Total issues: 1
  • Total pull requests: 0
  • Average time to close issues: almost 2 years
  • Average time to close pull requests: N/A
  • Total issue authors: 1
  • Total pull request authors: 0
  • Average comments per issue: 1.0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • sirosann (1)
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

docker/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
docker/serve/Dockerfile docker
  • pytorch/pytorch ${PYTORCH}-cuda${CUDA}-cudnn${CUDNN}-devel build
requirements/albu.txt pypi
  • albumentations >=0.3.2
requirements/build.txt pypi
  • cython *
  • numpy *
requirements/docs.txt pypi
  • docutils ==0.16.0
  • myst-parser *
  • sphinx ==4.0.2
  • sphinx-copybutton *
  • sphinx_markdown_tables *
  • sphinx_rtd_theme ==0.5.2
requirements/mminstall.txt pypi
  • mmcv-full >=1.3.17
requirements/optional.txt pypi
  • cityscapesscripts *
  • imagecorruptions *
  • scipy *
  • sklearn *
  • timm *
requirements/readthedocs.txt pypi
  • mmcv *
  • torch *
  • torchvision *
requirements/runtime.txt pypi
  • matplotlib *
  • numpy *
  • pycocotools *
  • six *
  • terminaltables *
requirements/tests.txt pypi
  • asynctest * test
  • codecov * test
  • flake8 * test
  • interrogate * test
  • isort ==4.3.21 test
  • kwarray * test
  • onnx ==1.7.0 test
  • onnxruntime >=1.8.0 test
  • protobuf <=3.20.1 test
  • pytest * test
  • ubelt * test
  • xdoctest >=0.10.0 test
  • yapf * test