Skip to content
master
Switch branches/tags
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
app
 
 
img
 
 
 
 
 
 

Sudoku Computer Vision Solver

A deep neural network trained from scratch. > 99% accurate in various lighting conditions.

Setup

  1. Clone this repository (fork it first if you want to deploy to Heroku):

    git clone https://github.com/chrisluedtke/sudoku-cv.git
    
  2. Within project repository, create a virtual environment:

    python -m venv env
    
  3. Activate the environment:

    Windows:

    env\Scripts\activate
    
  4. pip install --user --upgrade pip

  5. Install requirements:

    pip install -r requirements-opencv.txt
    

    or

    pip install -r requirements-pi.txt
    
  6. Create a .env with contents:

    FLASK_APP=app:APP
    FLASK_ENV=development
    CAMERA=opencv
    
  7. Run the web app (the database will be initialized automatically):

    flask run
    
  8. Navigate to the locally served page, typically http://localhost:5000/

  9. Optional: Create an ipython kernel to use Jupyter Notebook with this environment (see documentation).

    ipython kernel install --user --name=sudoku
    
    • You may also need to copy the .dll files from envLib/site-packages/pywin32_system32 to env/Lib/site-packages/win32

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published