Image Colorizer

Overview

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.

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

Options available for deploying this model

• Deploy from Dockerhub:

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

  Show more

• Deploy on Red Hat OpenShift:

  Follow the instructions for the OpenShift web console or the OpenShift Container Platform CLI in this tutorial and specify codait/max-image-colorizer as the image name.

• Deploy on Kubernetes:

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

  Show more

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

• Locally: Follow the instructions in the model README on GitHub

Example Usage

Once deployed you can upload an image using the UI:

You can also test the model from the command line. For example:

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

Resources and Contributions

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