Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/guillaumegenthial/api_ner
API for Tensorflow model in Flask
https://github.com/guillaumegenthial/api_ner
flask-api
Last synced: about 2 months ago
JSON representation
API for Tensorflow model in Flask
- Host: GitHub
- URL: https://github.com/guillaumegenthial/api_ner
- Owner: guillaumegenthial
- License: apache-2.0
- Created: 2017-09-15T01:23:05.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2017-11-20T23:20:12.000Z (about 7 years ago)
- Last Synced: 2023-11-07T18:17:55.950Z (about 1 year ago)
- Topics: flask-api
- Language: Python
- Homepage: https://guillaumegenthial.github.io/serving.html
- Size: 97.3 MB
- Stars: 104
- Watchers: 7
- Forks: 50
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# Simple Flask API for a Tensorflow Model
See the [blog post](https://guillaumegenthial.github.io/serving.html) covering the main steps.
To be hosted on Heroku (files `Procfile`, `requirements.txt` and `runtime.txt`).
To run locally,
```
python app.py
```The model is from [another repo](https://github.com/guillaumegenthial/sequence_tagging) on my github and is in the `model` directory. The flask app is defined in `app.py` which contains generic logic. The model-specific logic for the API is in the `serve.py` file.
An example of client is in the `client` directory.