Data

Tools

Indexes

Applications

Experiments

Open Source Science

semi-mmseg

https://github.com/dreamkily/semi-mmseg

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 (9.0%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: dreamkily
  • License: apache-2.0
  • Default Branch: main
  • Size: 2.68 MB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created almost 4 years ago · Last pushed almost 4 years ago
Metadata Files
Readme Contributing License Code of conduct Citation

README.md

Semi-supervised Semantic Segmentation with Mutual Knowledge Distillation

This project hosts the codo for implementing the MKD algorithm for semi-supervised learning

Installation

Requirements

  • Linux (Windows is not officially supported)
  • Python 3.6+
  • PyTorch 1.10 or higher
  • CUDA 9.0 or higher
  • GCC 4.9 or higher
  • mmcv-full

Install MKD

a. Create a conda virtual environment and activate it.

shell conda create -n mkd python=3.6 -y conda activate mkd

b. Install PyTorch and torchvision following the official instructions, e.g.,

shell conda install pytorch=1.10.0 torchvision cudatoolkit=10.2 -c pytorch -y

c. Install mmcv-full.

shell pip install mmcv-full==1.4.8 -f https://download.openmmlab.com/mmcv/dist/cu102/torch1.10.0/index.html

d. Install other third-party libraries.

shell pip install terminaltables imgaug onnxruntime==1.6.0 onnx albumentations Scikit-Image pycocotools tensorboard pillow==8.4.0

e. Clone the MKD repository.

shell git clone https://github.com/jianlong-yuan/semi-mmseg.git cd semi-mmseg

f. Install.

shell pip install -r requirements.txt pip install -e . # or "python setup.py develop"

Prepare datasets

It is recommended to symlink your dataset root (assuming YOUR_DATA_ROOT) to $semi-mmseg/data. If your folder structure is different, you may need to change the corresponding paths in config files.

Prepare PASCAL VOC 2012 and Cityscapes

Assuming that you usually store datasets in $YOUR_DATA_ROOT (e.g.,/home/YOUR_NAME/data/).

The different split lists will be store in data directory.

MKD ├── configs ├── data │ ├── cityscapes │ │ ├── images │ │ ├── segmentation │ | ├── splits │ │ | |    ├── cps_splits │ │ | |    ├── u2pl_splits │ ├── VOCdevkit │ │ ├── VOC2012 │ │ | ├── Annotations │ │ | ├── ImageSets │ │ | ├── JPEGImages │ │ | ├── SegmentationClass │ │ | ├── SegmentationClassAug │ │ | ├── SegmentationObject │ │ | ├── splits │ │ | |    ├── cps_splits │ │ | |    ├── pseudoseg_splits │ │ | |    ├── u2pl_splits

Training

./tools/dist_train.sh configs/semi_ablations/cps_meanteacher_3b_w1.5_w.1.0_fdmt1.5.py

Acknowledgement

We would like to thank the MMSegmentation for its open-source project.

Owner

  • Name: dreamkily(Mengzhu Wang)
  • Login: dreamkily
  • Kind: user
  • Location: China

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
  - name: "MMSegmentation Contributors"
title: "OpenMMLab Semantic Segmentation Toolbox and Benchmark"
date-released: 2020-07-10
url: "https://github.com/open-mmlab/mmsegmentation"
license: Apache-2.0

GitHub Events

Total
Last Year