Exam DP-100 topic 4 question 20 discussion

The answer should be B : async : Create a batch inference pipeline from the training pipeline

Should be B. .... batch inferencing is used to apply a predictive model to multiple cases asynchronously - usually writing the results to a file or database. https://docs.microsoft.com/en-us/learn/modules/deploy-batch-inference-pipelines-with-azure-machine-learning/1-introduction

asynchronously ==>batch

use this link to help you answer this question: https://learn.microsoft.com/en-us/azure/machine-learning/concept-endpoints-batch?view=azureml-api-2#pipeline-component-deployment

Real time inference??? it is Batch inference.

I think that the answer is B

Async= B

B.B. Create a batch inference pipeline from the training pipeline. Asynchronous predictions are typically done with batch inferencing. Azure Machine Learning provides the batch inference pipeline, which is suited for large volumes of data where the results aren't needed in real-time. This differs from a real-time inference pipeline, which provides synchronous, real-time predictions. So, to generate predictions asynchronously for a dataset of input data values, you should create a batch inference pipeline from the training pipeline.

B and C.

we are talking to get Asynch response so it should be Batch Inference

Another one wrong this should be B, please correct this answer I have paid for it to be sure the answers are correct.

Examtopic should try to review all these wrong answer choices. It is obvious that the word to focus on in this question is ""asynchronous". The answer is B - batch inferencing

Async = batch Sync = realtime

"asynchronously" is the key word here. Asynchronous predictions means batch inferencing

B. Asynchronous predictions = Batch inferencing

Similar question On Exam: 03 March 2022

On exam 2021/7/10