Implement computer vision solutions →hardMultiple ChoiceObjective-mapped

AI-102 Implement computer vision solutions Practice Question

Exhibit

Refer to the exhibit.

```json
{
  "source": "/subscriptions/{subscription-id}/resourceGroups/{resource-group}/providers/Microsoft.MachineLearningServices/workspaces/{workspace-name}",
  "properties": {
    "model": {
      "name": "logo-detector",
      "version": 1,
      "type": "customvision"
    },
    "endpoint": {
      "name": "logo-endpoint",
      "authMode": "Key",
      "properties": {
        "compute": "CPU",
        "scoringTimeout": "PT5M"
      }
    }
  }
}
```

You are deploying a Custom Vision model to an Azure Machine Learning managed endpoint using the above ARM template snippet. The deployment fails with a timeout error. Which parameter should you adjust?

⚠ Common exam trap

Many candidates confuse timeout errors with performance issues and incorrectly choose GPU compute (Option B), not realizing that the default timeout is a hard limit that must be explicitly increased via the scoringTimeout parameter.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Increase scoringTimeout to 'PT10M'

The deployment fails due to a timeout error, which indicates that the model inference is taking longer than the default scoring timeout (typically 5 seconds for Azure ML managed endpoints). Increasing the scoringTimeout parameter to 'PT10M' (ISO 8601 duration for 10 minutes) extends the allowed time for the endpoint to respond, resolving the timeout without altering compute or authentication settings.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Change model version to 2
Why it's wrong here
Version change unrelated to timeout.
✗
Change compute to 'GPU'
Why it's wrong here
May improve speed but timeout is the issue.
✗
Change authMode to 'AAD'
Why it's wrong here
Authentication mode doesn't affect timeout.
✓
Increase scoringTimeout to 'PT10M'
Why this is correct
Extends timeout to accommodate slow inference.

Visual reference

Go deeper

AI-102 Implement computer vision solutions Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question