Deploying a trained model

Deploy a trained model to prepare it for use in inspections.

Before you begin

Ensure that you have the following GPU storage:

  • At least one GPU available.
  • Enough GPUs available for your workload. The number of active GPU tasks that you can run at the same time depends on the number of GPUs on your server.

Procedure

  1. Click Models and then open the model that you want to deploy.
  2. Click Deploy model.
  3. Enter a deployed model name.
  4. If your model was trained with the Optimized for speed (Tiny YOLO v3) training model, select the accelerator type from the Deploy to accelerator list.
  5. Optional: Set Advanced deployment to On.You can then choose one of the following options:
    • Select an uploaded custom inference script.
    • Select an uploaded custom inference script and save the inference results to a data set.
    • Save the inference results to a data set.
    Note: For more information about custom inference scripts, see Deploying trained models.
  6. Click Deploy.
    The Deployed models page opens. When the model is deployed, the status that is displayed is Ready. For more information about deploying models, see Deploying trained models.
  7. Optional: To test other videos or images against the deployed model or to get the deployed model API endpoint, click Deployed Models, and then open the deployed model.
    For more information about APIs, see REST APIs.
  8. Optional: To delete a deployed model, click Deployed models model Undeploy.
    Note: When you delete a deployed model, the trained model is not removed from IBM Maximo Visual Inspection and is visible on the Models page.