VGG 16 Feature Extractor

An endpoint for uploading images and getting back VGG16 image feature embeddings

---

Docker Installation

Build the image

cd publicart-ml-endpoint
docker build -t keras_flask .
docker run -e MODEL_PATH=models/your_model.h5 -p 5000:5000

You can mount your model into the container.

docker run -e MODEL_PATH=/mnt/models/your_model.h5  -v volume-name:/mnt/models -p 5000:5000 keras_flask

Local Installation

Clone the repo

$ git clone https://github.com/rememberlenny/publicart-ml-endpoint.git

Install requirements

$ pip install -r requirements.txt

Make sure you have the following installed:

• tensorflow
• keras
• flask
• pillow
• h5py
• gevent
• gunicorn

Run with Python

Python 2.7 or 3.5+ are supported and tested.

$ python app.py

Play

Open http://localhost:5000 and have fun. 😃

---

Deployment

Run the app

Run the script and hide it in background with tmux or screen.

$ python app.py

You can also use gunicorn instead of gevent

$ gunicorn -b 127.0.0.1:5000 app:app

More deployment options, check here

Set up Nginx

To redirect the traffic to your local app. Configure your Nginx .conf file.

server {
    listen  80;

    client_max_body_size 20M;

    location / {
        proxy_pass http://127.0.0.1:5000;
    }
}