Skip to main content

A simple digits recognition neural network

Project description

Convolutional Neural Network using MNIST dataset for Digit Recognition

Release CI CD Coverage Documentation Status Downloads License: MIT

Official repository: https://github.com/MartinBraquet/ml-digits-recognition.

Test online: https://martinbraquet.com/index.php/solo_page_digits_recognition.

Alt Text

Installation from PyPI

pip install ml-digits-recognition

Usage

from ml_digits_recognition import drawing
drawing.run()

Installation from Source

pip install -r requirements.txt

Documentation

Click here for a full description.

Visualization of the convolutional neural network:

nn_visualization.ipynb

Training

Train the model and save it as model.pt.

ml_digits_recognition_training.ipynb

Accuracy vs epochs.

Loss vs epochs.

Test

Test in Jupiter Notebook. The model can be loaded from the training above in model.pt or from the default precise model in model_precise.pt.

ml_digits_recognition_test.ipynb

Test in Python.

python src/ml_digits_recognition/drawing.py

Tools

Draw a digit and save it as a PNG file.

user_input_drawing.ipynb

Issues / Bug reports / Feature requests

Please open an issue.

Contributions

Contributions are welcome. Please check the outstanding issues and feel free to open a pull request.

Contributors

Contributors

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

ml_digits_recognition-0.0.8.tar.gz (57.7 kB view details)

Uploaded Source

Built Distribution

ml_digits_recognition-0.0.8-py3-none-any.whl (56.8 kB view details)

Uploaded Python 3

File details

Details for the file ml_digits_recognition-0.0.8.tar.gz.

File metadata

  • Download URL: ml_digits_recognition-0.0.8.tar.gz
  • Upload date:
  • Size: 57.7 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.0.0 CPython/3.9.19

File hashes

Hashes for ml_digits_recognition-0.0.8.tar.gz
Algorithm Hash digest
SHA256 7f0b3983739397dd75410f4e6b662160b314e1b7f55aa5be99e97132c17a4886
MD5 07efabdce177add8623ba45579f6b9fc
BLAKE2b-256 1af70770fc1966648fabb2790198d6c8fcfddb6130fdb4b8a9acea6f0f0300ec

See more details on using hashes here.

File details

Details for the file ml_digits_recognition-0.0.8-py3-none-any.whl.

File metadata

File hashes

Hashes for ml_digits_recognition-0.0.8-py3-none-any.whl
Algorithm Hash digest
SHA256 efbe3498b71bf17e2978186794c1273a4b57048818c4728009a8550874962fe1
MD5 1f4b1f7509e0115ff802b58442a7e2b5
BLAKE2b-256 aa605cd6f7bcaff7409e7b21bed3e29dccb20e65cbdcc9046908d85ea7eb816f

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page