Serving Preflight and Classify
A 3-step recipe with TensorFlow. We can help you get access.
Recipe · 3 steps
Serving Preflight and Classify
with TensorFlow · Artificial Intelligence Management
Check model status, read the signature, then run classification inference.
- Confirm the ModelServer has the model loaded and reports a version in the AVAILABLE state before any inference is attempted.
- Read the metadata of the latest available version to confirm the model exposes a classification signature and to see the features it expects.
- Submit the examples for classification against the model's latest available version, returning label and score pairs for each example.
What you'll need to have ready
- modelName: The name the model was registered under in the ModelServer.
- signatureName: Optional classification signature to target. When omitted the ModelServer uses the model's default serving signature.
- context: Optional context features shared across every supplied example, merged into each example by the ModelServer.
- examples: The tf.Example style input records to classify, one result returned per example.
For your developer
Arazzo workflow tensorflow:classify-preflight, 3 operations: getModelStatus → getModelMetadata → classifyModel. Specs on APIs.io.