https://github.com/scientifichackers/minst-flutter-app
https://github.com/scientifichackers/minst-flutter-app
Last synced: 12 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/scientifichackers/minst-flutter-app
- Owner: scientifichackers
- Created: 2019-11-16T00:32:20.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-11-16T01:26:47.000Z (over 6 years ago)
- Last Synced: 2025-02-28T22:20:40.194Z (over 1 year ago)
- Language: Dart
- Size: 65.4 KB
- Stars: 2
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# minst-flutter-app
A flutter app that lets you experiment with a MNIST (28x28) tf-keras model in real-time!
Works over websockets, using the amazing [Starlette](https://www.starlette.io/) web framework.
## How to use this code?
1. Save model using `model.save(mnist_model.h5)`
2. Download model file to `client/server/mnist_model.h5`.
3. Deploy python server by running the following commands in the `server/` directory (on a publically accessible server) -
```
pip install -e .
uvicorn --port server:app
```
3. Change [`serverUrl`](https://github.com/scientifichackers/minst-flutter-app/blob/c7470999a0608706ca24daae1207c1ceac5af6a2/client/lib/src/constants.dart#L25) accordingly.
4. In the `client/` directory, `flutter run`.
## Thanks
Thanks to [this](https://github.com/sergiofraile/when_flutter_meets_tensorflow_part_4) medium article for the hand drawing canvas code.