Skip to content

A graphical annotation tool to address different Computer Vision tasks.

Notifications You must be signed in to change notification settings

OpenSciML/CvStudio

Folders and files

NameName
Last commit message
Last commit date

Latest commit

Oct 13, 2020
ccf79dd · Oct 13, 2020

History

4 Commits
Oct 13, 2020
Oct 10, 2020
Oct 10, 2020
Oct 10, 2020
Oct 10, 2020
Oct 13, 2020
Oct 10, 2020
Oct 10, 2020
Oct 10, 2020
Oct 10, 2020
Oct 10, 2020

Repository files navigation

CV-Studio

CV-Studio is a graphical annotation tool to address different Computer Vision tasks.

CV-Studio is developed in Python, Qt, SQLite and uses PyTorch's resources to train deep learning models.

Interface

CVStudio supports:

Datasets:

  • Create and manage your datasets for images.
  • Manually annotate images:
    • Using a label system for classification problems.
    • Using a bounding box for localization and object detection problems.
    • Using a polygon tool or freehand selection for segmentation tasks.
  • Auto-annotate images with a pretrained model to continue tagging the images by your own.

Watch a demo video

Roadmap

  • Datasets: Annotations for videos.
  • Platforms: macOS support.

Installation

Note: CV-Studio only have been developed and tested on Windows, and linux. Future platforms are in the roadmap.

1. Install cvstudio

pip install cvstudio

2. Install pytorch

  • Using GPU:
    pip install --pre torch torchvision -f https://download.pytorch.org/whl/nightly/cu101/torch_nightly.html             
  • Using CPU:
   pip install --pre torch torchvision -f https://download.pytorch.org/whl/nightly/cpu/torch_nightly.html        

3. Download pre-trained models

This command must be executed from the CVStudio folder: Windows (PowerShell)

   Invoke-WebRequest -OutFile ./models/MS_DeepLab_resnet_trained_VOC.pth https://data.vision.ee.ethz.ch/csergi/share/DEXTR/MS_DeepLab_resnet_trained_VOC.pth
   Invoke-WebRequest -OutFile ./models/dextr_pascal-sbd.pth https://data.vision.ee.ethz.ch/csergi/share/DEXTR/dextr_pascal-sbd.pth

Linux

    wget https://data.vision.ee.ethz.ch/csergi/share/DEXTR/MS_DeepLab_resnet_trained_VOC.pth -P ./models
    wget https://data.vision.ee.ethz.ch/csergi/share/DEXTR/dextr_pascal-sbd.pth -P ./models

4. Run CVStudio

    cvstudio

Documentation

Check out the wiki.

How to contribute

Send a pull request.

License

Free software: MIT license

Citation: haruiz. CV-Studio. Git code (2019). https://github.com/haruiz/CvStudio

Credits

Images and Icons

Models

Deep Extreme Cut: From Extreme Points to Object Segmentation

About

A graphical annotation tool to address different Computer Vision tasks.

Resources

Stars

Watchers

Forks

Packages

No packages published