Skip to content

Latest commit

 

History

History
33 lines (19 loc) · 868 Bytes

README.md

File metadata and controls

33 lines (19 loc) · 868 Bytes

Tensorflow object detector web service

Rudimentary flask web service that wraps the Tensorflow Object Detection API.

Instructions

Build the docker image:

docker-compose build

Start the service:

docker-compose up -d

This starts the web service at localhost:5000 and some jupyter service at localhost:8888 (to get the exact location enter docker-compose logs app and search the logs for the jupyter url).

Apply object detection on a random cat: http://localhost:5000/detect_objects

You can also apply object detection to your own given image:

http://localhost:5000/detect_objects?url=$YOUR_URL