Huawei H13-321-ENU 問題練習

Question No : 1
Convolve a pair of three-channel color images with two 3x3 convolution kernels.
How many channels does the resulting feature map have? (Single choice)

• A.1
• B.2
• C.3
• D.4

答えを確認する

正解:

Question No : 2
Dropout is to randomly discard a certain proportion of sample data during model training.

• A.TRUE
• B.FALSE

答えを確認する

正解:

Question No : 3
In the Gaussian mixture model, since the distribution of each sample point is unknown, it is impossible to use the maximum function to solve the parameters.

• A.TRUE
• B.FALSE

答えを確認する

正解:

Question No : 4
(Judgment) Back propagation is a common method used to train artificial neural networks.

• A.TRUE
• B.FALSE

答えを確認する

正解:

Question No : 5
What is the word segmentation method in the jieba framework?

• A.cut
• B.lcut_for_search
• C.lcut
• D.cut_for_search

答えを確認する

正解:

Question No : 6
An APP that can display plant names and breeding methods after taking photos of plants in pots. Its core is the use of image classification technology.

• A.TRUE
• B.FALSE

答えを確認する

正解:

Question No : 7
Use a 3*3 convolution kernel to convolve a three-channel color image.
What is the number of parameters to be learned?

• A.27
• B.9
• C.28
• D.10

答えを確認する

正解:

Question No : 8
Image recognition tasks can be divided into three levels, according to the abstraction of the processing content, from low to high?

• A.Image processing, image analysis, image understanding
• B.Image analysis, image understanding, image processing
• C.Image understanding. Image analysis. Image Processing
• D.Image analysis, image processing, image understanding

答えを確認する

正解:

Question No : 9
The request/response of HUAWEI CAI API in accordance with the design of RESTful API includes the following.

• A.Response message header
• B.Request URL
• C.Request message header
• D.Response message body
• E.Request message body

答えを確認する

正解:

Question No : 10
Markov chain is a discrete event stochastic process with Markov properties in exponential science.

• A.TRUE
• B.FALSE

答えを確認する

正解:

Question No : 11
The accuracy of the target detection position can be evaluated by the IOD value. The iout calculation method is to find the ratio of the union and intersection of the true annotations of the detection results.

• A.TRUE
• B.FALSE

答えを確認する

正解:

Question No : 12
Which of the following templates can achieve the sharpness of the image?

• A.010 111 010
• B.010 131 010
• C.0-10 -14-1 0-10
• D.0-10 -16-1 0-10

答えを確認する

正解:

Question No : 13
When photographing a document with a mobile phone, the document in the image is distorted due to the shooting angle. You can find () coordinates of the corresponding key points, () transform the image, and correct the document image.

• A.4, Affine
• B.4, perspective
• C.3, perspective
• D.3, Affine

答えを確認する

正解:

Question No : 14
When taking light, the face is relatively dark. Use gamma correction to enhance the image to achieve a clear light effect.
Which of the Y limit can be selected. (Single choice)

• A.1
• B.0
• C.0.5
• D.2

答えを確認する

正解:

Question No : 15
Modifying the H component of the HSV color space will change the image? (Single choice)

• A.Hue
• B.Brightness
• C.Saturation
• D.Contrast

答えを確認する

正解: