Skip to content

Streamlit App that performs object detection and instance segmentation with Detectron2

License

Notifications You must be signed in to change notification settings

Think-Evolve-Consulting/Detectron2-Instance-Segmentation

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Detectron2 Instance Segmentation

Streamlit App that performs object detection and instance segmentation powered by Detectron2.

app_preview

Dependencies

Running the application can be done following the instructions above:

  1. To create a Python Virtual Environment (virtualenv) to run the code, type:

    python3 -m venv my-env

  2. Activate the new environment:

    • Windows: my-env\Scripts\activate.bat
    • macOS and Linux: source my-env/bin/activate
  3. Install all the dependencies from requirements.txt:

    pip install -r requirements.txt

Use

Within the virtual environment:

streamlit run app.py

A web application will open in the prompted URL. The user should upload an image file (jpg, jpeg, png) with the button available. Then, the image will be fed to a model which will output tehe original image with the detections drawn on it.

There's another app:

streamlit run app_discriminative.py

It behaves as the other one, but includes the following options:

  • Select which classes to detect: Multiselect to choose which of the classes that the model's been trained on are going to be used in the inference.

Acknowledgments

License

This project is licensed under the MIT License - see the LICENSE.md file for details

About

Streamlit App that performs object detection and instance segmentation with Detectron2

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%