Skip to content

The project uses a computer vision model to extract structured features from floor plan images for a fire risk assessment.

License

Notifications You must be signed in to change notification settings

whchien/deep-floor-plan-recognition

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

DeepFloor: Floor Plan Recognition

In collaboration with Gemeente Amsterdam in 2020, this project aims to extract structured features from floor plan images as inputs for their fire risk model. This core image recognition model was originated from DeepFloorplan. We incorporated the model backbone and built a Django website for demo purpose.

How to run the demo?

  1. Install packages:
pip install -r requirements/requirements.demo.txt
  1. Download the pretrained model to deepfloor/pretrained folder.

  2. Run the command:

python manage.py runserver

About

The project uses a computer vision model to extract structured features from floor plan images for a fire risk assessment.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published