A pretty and customizable web app to deploy your DL model with ease
- Clone this repo
- Install requirements
- Run the script
- Check http://localhost:5000
- Done! ๐
๐Screenshot:
$ git clone https://github.com/nursnaaz/DataScience-Webinar-Inceptez-28-06-2020.git
$ pip install -r requirements.txt
Make sure you have the following installed:
- Flask
- h5py
- Keras
- Keras-Applications
- Keras-Preprocessing
- numpy
- scikit-learn
- scipy
- tensorflow
- opencv-python
Python 3.7+ are supported and tested.
$ python app.py
Open http://localhost:5000 and have fun. ๐
Place your trained .h5
file saved by model.save()
under models directory.
To deploy it for public use, you need to have a public linux server - Ubuntu.
Run the script and hide it in background with tmux
or screen
.
$ python app.py
You can also use gunicorn instead of gevent
$ gunicorn --workers=50 --threads=20 --bind 0.0.0.0:8000 app:app
More deployment options, check here
Check Siraj's "How to Deploy a Keras Model to Production" video. The corresponding repo.