Skip to content

Charlotte's Handwritten Digit Recognizer: Image classification powered by a neural network implemented with Keras and TensorFlow.js

Notifications You must be signed in to change notification settings

anna-charlotte/digit_recognizer

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Charlotte's Handwritten Digit Recognizer

Image classification powered by a neural network implemented with Keras and TensorFlow.js

Try it out yourself at https://anna-charlotte.github.io/digit_recognizer/frontend/index.html

frontend/images/webapp_screenshot.png

Usage

Train model:

  1. Clone repository: git clone https://github.com/anna-charlotte/digit_recognizer.git
  2. Install requirements: poetry install
  3. Activate virtual environment: poetry shell
  4. Create the data directory: mkdir data
  5. Download the data from https://www.kaggle.com/datasets/oddrationale/mnist-in-csv?resource=download and save it to the data directory.
  6. Create additional training data: python src/create_new_data.py
  7. Train model: python src/digit_recognizer.py

About

Charlotte's Handwritten Digit Recognizer: Image classification powered by a neural network implemented with Keras and TensorFlow.js

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published