Huawei H13-321 Online Practice Questions and Exam Preparation

Huawei H13-321 Online Questions & Answers

• Question 121:

  What are the main functions of MoXing? (Single choice)

  A. Deep learning tool library developed by Huawei
  B. Deep learning engine developed by Huawei
  C. Package and acceleration of distributed training acceleration framework and API interface of deep learning engines such as TensorFlow
  D. Simple encapsulation of API interfaces for deep learning engines such as TensorFlow
  C. Package and acceleration of distributed training acceleration framework and API interface of deep learning engines such as TensorFlow

• Question 122:

  Through the image algorithm, the foreground and background of a person who takes a picture taken by an ordinary mobile phone are segmented, and then the () operation is performed on the () part, which can achieve the same effect as a SLR camera.

  A. Background, median filtering
  B. Foreground, mean filtering
  C. Background, mean filtering
  D. Foreground, median filter value
  C. Background, mean filtering

• Question 123:

  HUAWEI CLOUD's cloud monitoring service can monitor the relevant indicators of image recognition. Users can learn about the use of image recognition in time through the indicators. Each service has the number of successful calls and two indicators.

  A. TRUE
  B. FALSE
  A. TRUE

• Question 124:

  (Judgment) The original value of the recording pixel is S, The pixel value after the change is D. The mapping function of gray scale change is d=ks. When k>1, gray scale stretching of the dark part of the image can be achieved.

  A. TRUE
  B. FALSE
  B. FALSE

• Question 125:

  In the Huawei cloud content detection service, which of the following parameters is not a public request message header.

  A. X-Sdlk-Date
  B. Authorization
  C. Post
  D. Host
  C. Post

• Question 126:

  The Gaussian filter of the same size has better denoising effect than the mean filter.

  A. TRUE
  B. FALSE
  A. TRUE

• Question 127:

  (Judgment) The Gaussian model is to accurately quantify things with a Gaussian density function, and decompose a thing into several models based on Bernoulli distribution.

  A. TRUE
  B. FALSE
  A. TRUE

• Question 128:

  In Chinese, the part-of-speech of a word is often not fixed. Generally speaking, words with the same homonym and different shapes have different grammars in different scenes, which brings great difficulties to the part-of-speech tagging.

  A. TRUE
  B. FALSE
  A. TRUE

• Question 129:

  On October 10, 2018, Huawei released a full-stack full-scenario AI solution. Does Huawei's full stack solution include?

  A. CAN
  B. Application enable
  C. Ascend
  D. MindSpore
  A. CAN
  B. Application enable
  C. Ascend
  D. MindSpore

• Question 130:

  The lower the value on the diagonal of the confusion matrix, the better the classification effect of the classifier.

  A. TRUE
  B. FALSE
  A. TRUE