https://github.com/aakashns/servefastai
Serve FastAI models and get a web-based UI with a single line of code
https://github.com/aakashns/servefastai
deep-learning fastai
Last synced: 6 months ago
JSON representation
Serve FastAI models and get a web-based UI with a single line of code
- Host: GitHub
- URL: https://github.com/aakashns/servefastai
- Owner: aakashns
- Created: 2018-10-30T14:34:56.000Z (almost 7 years ago)
- Default Branch: master
- Last Pushed: 2019-07-19T23:18:44.000Z (about 6 years ago)
- Last Synced: 2024-09-15T07:39:44.994Z (about 1 year ago)
- Topics: deep-learning, fastai
- Language: JavaScript
- Homepage: https://youtu.be/xwN7arEgvBg
- Size: 446 KB
- Stars: 30
- Watchers: 5
- Forks: 2
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# servefastai
Serve FastAI models and get a web-based UI to test them out with a single line of code. See a [video demo here](https://youtu.be/xwN7arEgvBg).
## Installation
Install with `pip`. Make sure you have `fastai` already installed.
```
pip install servefastai --upgrade
```
## Usage
```
from servefastai import serve
serve(learn)
```
`learn` should be a FastAI learner object. Navigate to http://PUBLIC_IP:9999 , where `PUBLIC_IP` is the public IP address of the machine running the Jupyter notebook. You will see a form where you can upload one or more images. Upload the images and click submit to view the predictions.