Model Explanations with Anchor Images

In this demo we will:

• Launch an income classification model which has image training features

• Send a request to get a prediction

• Create an explainer for the model

• Send the same request and then get an explanation for it

This model provides a model trained to classify images based on CIFAR10 dataset.

The explainer uses the anchors technique to provide insight into why a particular classification was made by the model. We’ll see patterns in an input image that are most relevant to the prediction outcome.

Create Model

Use the following model URI with tensorflow runtime.

gs://seldon-models/tfserving/cifar10/resnet32

Get Predictions

Run a single prediction using the tensorflow payload format of an image truck.

Add an Anchor Images Explainer

Create a model explainer using the URI below for the saved explainer.

gs://seldon-models/tfserving/cifar10/explainer-py36-0.5.2

Get Explanation for one Request

View all requests and then explain it using the JSON below: