Model Catalog
Prerequisites
Register New Model
Select the
Model Catalog
tab at the top of the page.Click
Register a new model
to open the registration modal.Enter the following parameters:
Model Name
cifar10
URI
gs://seldon-models/triton/tf_cifar10
Artifact Type
Tensorflow
Version
v1.0
Task Type
Classification
Project
seldon
Append tags and metric parameters with the following values. To add more parameters, use the
+
button. To delete a parameter, use thex
button:Tags:
KeyValueauthor
Seldon
training_set
Resnet32
Metrics:
KeyValuep1
0.8
p2
0.6
Click
Register Model
.
Deploying Models From The Model Catalog
Select the
Model Catalog
tab at the top of the page.Click on the vertical ellipses "⋮" icon for the model named
cifar10
.In the dropdown menu that appears, select Deploy.
In the wizard which appears, enter the following details:
Name
cifar10
Namespace
seldon
Type
Seldon ML Pipeline
Runtime
Tensorflow
Click
Next
steps, then clickLaunch
.
Select the Overview
header tab to verify that your model has been deployed.
Edit Model Metadata
From The Model Catalog
From the
Overview
page, selectModel Catalog
at the top of the page.Select a model.
On the side drawer that opens, click
Edit Metadata
.Add a new tag with the following values:
KeyValuestage
production
Click
Save Metadata
at the top right hand side of the side drawer to save your edit.
From A Deployment's Dashboard
From the Overview page, select a pipeline or deployment.
In the dashboard, click on the model within
Pipeline Components
(orDeployment Components
for Core 1). This should open a drawer on the right hand side.Click
Edit Metadata
.Under the Tags section, press the
+
button to add a new tag.For the new tag, enter the following parameters:
KeyValuestage
production
Click
Save Metadata
on the top right of the side drawer.
Last updated
Was this helpful?