IBM Code Model Asset Exchange: Image Translation (Grayscale to Color)

This repository contains code to instantiate and deploy an image translation model. This model is a Generative Adversarial Network (GAN) that was trained by the IBM CODAIT Team on COCO dataset images converted to grayscale and produces colored images. The input to the model is a grayscale image (jpeg or png), and the output is a colored 256 by 256 image (increased resolution will be added in future releases).

The model is based on Christopher Hesse's Tensorflow implementation of the pix2pix model. The model files are hosted on IBM Cloud Object Storage. The code in this repository deploys the model as a web service in a Docker container. This repository was developed as part of the IBM Code Model Asset Exchange.

Model Metadata

References

• J. Isola, J. Zhu, T. Zhou, A. Efros, "Image-to-Image Translation with Conditional Adversarial Networks", CVPR 2017
• pix2pix TensorFlow GitHub Repository

Licenses

Pre-requisites:

• docker: The Docker command-line interface. Follow the installation instructions for your system.
• The minimum recommended resources for this model is 2GB Memory and 2 CPUs.

Steps

1. Deploy from Docker Hub
2. Deploy on Kubernetes
3. Run Locally

Deploy from Docker Hub

To run the docker image, which automatically starts the model serving API, run:

$ docker run -it -p 5000:5000 codait/max-image-colorizer

This will pull a pre-built image from Docker Hub (or use an existing image if already cached locally) and run it. If you'd rather checkout and build the model locally you can follow the run locally steps below.

Deploy on Kubernetes

You can also deploy the model on Kubernetes using the latest docker image on Docker Hub.

On your Kubernetes cluster, run the following commands:

$ kubectl apply -f https://raw.githubusercontent.com/IBM/MAX-Image-Colorizer/master/max-image-colorizer.yaml

The model will be available internally at port 5000, but can also be accessed externally through the NodePort.

Run Locally

1. Build the Model
2. Deploy the Model
3. Use the Model
4. Development
5. Cleanup

1. Build the Model

Clone this repository locally. In a terminal, run the following command:

git clone https://github.com/IBM/MAX-Image-Colorizer.git

Change directory into the repository base folder:

cd MAX-Image-Colorizer

To build the docker image locally, run:

docker build -t max-image-colorizer .

All required model assets will be downloaded during the build process. Note that currently this docker image is CPU only (we will add support for GPU images later).

2. Deploy the Model

To run the docker image, which automatically starts the model serving API, run:

docker run -it -p 5000:5000 max-image-colorizer

3. Use the Model

The API server automatically generates an interactive Swagger documentation page. Go to http://localhost:5000 to load it. From there you can explore the API and also create test requests.

Use the model/predict endpoint to load a test grayscale image (you can use one of the test images from the assets folder) and get a colored image.

You can also test it on the command line, for example:

curl -F "image=@assets/bw-city.jpg" -XPOST http://localhost:5000/model/predict > result.png && open result.png

4. Development

To run the Flask API app in debug mode, edit config.py to set DEBUG = True under the application settings. You will then need to rebuild the docker image (see step 1).

5. Cleanup

To stop the docker container type CTRL + C in your terminal.