Kubernetes with OpenShift World Tour: Get hands-on experience and build applications fast! Find a workshop!

Image Classifier – ResNet50

Overview

This model recognizes the 1000 different classes of objects in the ImageNet 2012 Large Scale Visual Recognition Challenge. The model consists of a deep convolutional net using the ResNet-50 architecture that was trained on the ImageNet-2012 data set. The input to the model is a 224×224 image, and the output is a list of estimated class probilities. The model is based on the Keras built-in model for ResNet-50.

Model Metadata

Domain Application Industry Framework Training Data Input Data Format
Vision Image Classification General Keras ImageNet Image (RGB/HWC)

References

Licenses

Component License Link
Model GitHub Repository Apache 2.0 LICENSE
Model Weights MIT Keras ResNet-50
Model Code (3rd party) MIT Keras LICENSE
Test Assets CC0 Samples README

Options available for deploying this model

This model can be deployed using the following mechanisms:

  • Deploy from Dockerhub:

    docker run -it -p 5000:5000 codait/max-resnet-50
    
  • 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-resnet-50 as the image name.

  • Deploy on Kubernetes:

    kubectl apply -f https://raw.githubusercontent.com/IBM/MAX-ResNet-50/master/max-resnet-50.yaml
    

    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

You can test or use this model

Test the model using cURL

Once deployed, you can test the model from the command line. For example:

curl -F "image=@samples/coffee.jpg" -XPOST http://localhost:5000/model/predict

You should see a JSON response like that below:

{
  "status": "ok",
  "predictions": [
    {
      "label_id": "n07920052",
      "label": "espresso",
      "probability": 0.9637148976326
    },
    {
      "label_id": "n02877765",
      "label": "bottlecap",
      "probability": 0.007265966385603
    },
    {
      "label_id": "n07930864",
      "label": "cup",
      "probability": 0.0059303143061697
    },
    {
      "label_id": "n07693725",
      "label": "bagel",
      "probability": 0.0023403959348798
    },
    {
      "label_id": "n04476259",
      "label": "tray",
      "probability": 0.0019735493697226
    }
  ]
}

Test the model in a serverless app

You can utilize this model in a serverless application by following the instructions in the Leverage deep learning in IBM Cloud Functions tutorial.

Options available for training this model

This model can be trained using the following mechanisms: