Automatically deploying the newest model

If you are using the production work flow within a project group, you can also turn on auto deploy. When auto deploy is turned on, IBM® Maximo® Visual Inspection automatically deploys a model when it is successfully trained and when it is marked as production.

IBM Maximo Visual Inspection automatically undeploys any deployed models when the associated trained model is marked as rejected. Additionally, it tracks the latest model that is marked as production or untested and ensures that the latest production-ready model is deployed for a project group.
Note: If you do not mark a model as production or rejected, and you manually deploy it, IBM Maximo Visual Inspection can't automatically undeploy it.

Overview

IBM Maximo Visual Inspection does the following actions when auto deploy is enabled:

When a model is newly trained:

  • The latest trained model is marked untested, and it is automatically deployed.
  • If another model marked untested is already deployed, the older deployed model is undeployed.
  • The goal of this process is to help people who want to test the latest trained model.

When a model is marked as production:

It is automatically deployed. The goal of this process is to always keep the latest production-ready model deployed. If it is already deployed, the following actions happen:
  1. The deployed model becomes the current deployed production model.
  2. Any other deployed production model is undeployed.
  3. IBM Maximo Visual Inspection finds the most recent trained model that has an untested status and deploys it. If no other trained model is marked as untested, attempted inferences to the latest untested model fail.

When a model is changed from untested to rejected:

When a trained model is marked as rejected, the associated deployed model is undeployed.

When a model is changed from production to rejected:

When a trained model is marked as rejected, the associated deployed model is undeployed. IBM Maximo Visual Inspection finds the most recent trained model with Production status and deploys it. If no other trained model is marked as Production, attempted inferences to the latest Production model fail.

Although auto deploy tracks and deploys the latest model marked with each status, you can manually deploy more models from the project group by using the Models page. However, those additional models are not accessible by using the API shortcuts.

Figure 1. Auto deploy in IBM Maximo Visual Inspection
This image describes the auto deploy flow. Models are trained, deployed, tested, then are rejected or accepted. Rejected models are undeployed. Accepted models are moved to Production status and are automatically deployed.

Enabling auto deploy

To enable auto deploy, you need to set two pieces of information by using the API. You can use CURL to set them.

curl -kXPUT -H "x-auth-token: insights-auth-token-value" https://insights-server.your_company.com/visual-insights/projects/{project-UUID} -d '{"enforce_pwf": "true", "auto_deploy":"true"}'
Note: Case is ignored for the true string, but the word must be true. For example, it does not work if you set the value as yes.