可信计算>> plant-seg>> 返回
项目作者： hci-unihd

项目描述 ：
A tool for cell instance aware segmentation in densely packed 3D volumetric images
高级语言： Python
项目地址: git://github.com/hci-unihd/plant-seg.git
创建时间： 2019-10-18T10:56:08Z
项目社区：https://github.com/hci-unihd/plant-seg
开源协议：MIT License
下载


PlantSeg

alt text

Conda Build and Test
Docs Build and Publish

Anaconda-Server Badge
Anaconda-Server Badge
Anaconda-Server Badge
Anaconda-Server Badge

Illustration of Pipeline

PlantSeg is a tool for cell instance aware segmentation in densely packed 3D volumetric images.
The pipeline uses a two stages segmentation strategy (Neural Network + Segmentation).
The pipeline is tuned for plant cell tissue acquired with confocal and light sheet microscopy.
Pre-trained models are provided.

Table of Contents

Getting Started

For detailed usage checkout our documentation 📖.

Installation

Please go to the documentation for more detailed instructions. In short, we recommend using mamba to install PlantSeg, which is currently supported on Linux and Windows.

  • GPU version, CUDA=12.x (replace 12.1 with 11.8 for CUDA=11.x)

    1.   mamba create -n plant-seg -c pytorch -c nvidia -c conda-forge pytorch pytorch-cuda=12.1 plant-seg --no-channel-priority

  • CPU version

    1.   mamba create -n plant-seg -c pytorch -c nvidia -c conda-forge pytorch cpuonly plant-seg --no-channel-priority

The above command will create new conda environment plant-seg together with all required dependencies.

Repository Index

The PlantSeg repository is organised as follows:

  • plantseg: Contains the source code of PlantSeg.
  • conda-reicpe: Contains all necessary code and configuration to create the anaconda package.
  • docs: Contains the documentation of PlantSeg.
  • evaluation: Contains all script required to reproduce the quantitative evaluation in
    Wolny et al..
  • examples: Contains the files required to test PlantSeg.
  • tests: Contains automated tests that ensures the PlantSeg functionality are not compromised during an update.

Citation

  1. @article{wolny2020accurate,
  2.   title={Accurate and versatile 3D segmentation of plant tissues at cellular resolution},
  3.   author={Wolny, Adrian and Cerrone, Lorenzo and Vijayan, Athul and Tofanelli, Rachele and Barro, Amaya Vilches and Louveaux, Marion and Wenzl, Christian and Strauss, S{\"o}ren and Wilson-S{\'a}nchez, David and Lymbouridou, Rena and others},
  4.   journal={Elife},
  5.   volume={9},
  6.   pages={e57613},
  7.   year={2020},
  8.   publisher={eLife Sciences Publications Limited}
  9. }