Build this image with docker build -t imagescorer .
and run it with docker run -p 8080:8080 imagescorer
.
If you have HTTPie installed, you can use the included payload.py
script to test, e.g.,
./payload.py some_file.jpg | http -j localhost:8080/v2/yolo
The first score will be slower than subsequent ones.
Currently there's not really any error checking. In particular, malformed images are likely to just result in a straight-up 500 error.
This uses Darkflow's implementation of YOLO.
This server was generated by the swagger-codegen project. By using the OpenAPI-Spec from a remote server, you can easily generate a server stub. This is an example of building a swagger-enabled Flask server.
This example uses the Connexion library on top of Flask.
Python 3.5.2+
To run the server, please execute the following from the root directory:
pip3 install -r requirements.txt
python3 -m swagger_server
and open your browser to here:
http://localhost:8080/v2/ui/
Your Swagger definition lives here:
http://localhost:8080/v2/swagger.json
To launch the integration tests, use tox:
sudo pip install tox
tox
To run the server on a Docker container, please execute the following from the root directory:
# building the image
docker build -t swagger_server .
# starting up a container
docker run -p 8080:8080 swagger_server