ibm/max-image-colorizer

Adds color to black and white images.

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 and the public API is powered by IBM Cloud.

Model Metadata

Domain	Application	Industry	Framework	Training Data	Input Data Format
Vision	Image Coloring	General	TensorFlow	COCO Dataset	JPEG or PNG Image

References

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

Licenses

Component	License	Link
This repository	Apache 2.0	LICENSE
Model Code (3rd party)	MIT	TensorFlow pix2pix Repository
Model Weights	Apache 2.0	LICENSE
Test Assets	CC0 License	Asset README

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.
• If you are on x86-64/AMD64, your CPU must support AVX at the minimum.

Deployment options

• Deploy from Quay
• Deploy on Red Hat OpenShift
• Deploy on Kubernetes
• Run Locally

Deploy from Quay

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

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

This will pull a pre-built image from the Quay.io container registry (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 Red Hat OpenShift

You can deploy the model-serving microservice on Red Hat OpenShift by following the instructions for the OpenShift web console or the OpenShift Container Platform CLI in this tutorial, specifying quay.io/codait/max-image-colorizer as the image name.

Deploy on Kubernetes

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

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.

A more elaborate tutorial on how to deploy this MAX model to production on IBM Cloud can be found here.

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=@samples/bw-city.jpg" -XPOST http://localhost:5000/model/predict > 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.

Resources and Contributions

If you are interested in contributing to the Model Asset Exchange project or have any queries, please follow the instructions here.

max-image-colorizer's Issues

Add request param descriptions and update Swagger models help text

Example in PR:
IBM/MAX-Object-Detector#20

inconsistent link to COS directory for model files

the README contains this link to the model files:

• http://max-assets.s3-api.us-geo.objectstorage.softlayer.net/tf/pix2pix/pix2pix-bw-to-color.tar.gz

this works. however, it is different than the link in the Dockerfile:

• http://max-assets.s3-api.us-geo.objectstorage.softlayer.net/image-colorizer/1.0/assets.tar.gz

i would expect both of these to point to the same set of model files.
in addition, both of the links should be pointing to the new US cross region:

s3.us.cloud-object-storage.appdomain.cloud

because the old one has been deprecated:

s3-api.us-geo.objectstorage.softlayer.net

Remove open command from README

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

however open is a command specific to OSX, we should remove this or specify it only works on Mac

pip install from requirements.txt

Example PR:
IBM/MAX-Review-Text-Generator#7

README instruction for docker image use invalid reference format

$ docker --version
Docker version 17.09.0-ce, build afdb6d4

$ docker build -t MAX-Image-Colorizer .
invalid argument "MAX-Image-Colorizer" for t: invalid reference format: repository name must be lowercase
See 'docker build --help'.

I had to replace MAX-Image-Colorizer with max-image-colorizer to start the build successfully.

/model/predict: Handle invalid input gracefully

API endpoint /model/predict returns HTTP status code 500 if an invalid image input is provided. It should return status code 400 if an error is caused by input that cannot be processed because it doesn't meet the [stated] requirements.

Make it trainable