https://github.com/larswaechter/quickdraw-cnn
A convolutional neural network using Tensorflow and Google's Quick, Draw! dataset to recognize hand drawn images.
https://github.com/larswaechter/quickdraw-cnn
artificial-intelligence machine-learning quickdraw-dataset tensorflow
Last synced: about 1 year ago
JSON representation
A convolutional neural network using Tensorflow and Google's Quick, Draw! dataset to recognize hand drawn images.
- Host: GitHub
- URL: https://github.com/larswaechter/quickdraw-cnn
- Owner: larswaechter
- License: mit
- Created: 2022-02-19T15:55:25.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2023-03-07T15:54:14.000Z (over 3 years ago)
- Last Synced: 2025-03-31T16:14:16.459Z (about 1 year ago)
- Topics: artificial-intelligence, machine-learning, quickdraw-dataset, tensorflow
- Language: JavaScript
- Homepage: https://larswaechter.dev/blog/recognizing-hand-drawn-doodles/
- Size: 7.53 MB
- Stars: 13
- Watchers: 2
- Forks: 3
- Open Issues: 2
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# quickdraw-cnn
A convolutional neural network using Tensorflow and Google's Quick, Draw! [dataset](https://github.com/googlecreativelab/quickdraw-dataset) to recognize hand drawn images including a webapp to draw them.
Read my [blog post](https://larswaechter.dev/blog/recognizing-hand-drawn-doodles/) for more information. You can find a webapp demo [here](https://quickdraw-cnn.fly.dev/).
## Setup
### cnn
Switch to the `cnn` directory, create a new virtual environment and install the required packages:
```
python -m venv ./venv
source ./venv/bin/activate
pip install -r requirements.txt
```
Then, launch Jupyter in the target directory:
```
jupyter notebook
```
### webapp
#### Native
Switch to the `webapp` directory, create another venv and install the requirements as mentioned above. You can run the webapp using the following command:
```
uvicorn main:app
```
The webapp should be available at [http://127.0.0.1:8000](http://127.0.0.1:8000).
#### Docker
Alternatively, you can also run it via Docker:
```
docker build . -t quickdraw-webapp
docker run -p 443:443 quickdraw-webapp
```
The webapp should be available at [http://0.0.0.0:443](http://0.0.0.0:443).