H13-321 Sample Questions Answers

Many mobile phones provide eye protection screen display mode, which can reduce blue light and relieve fatigue. This function can be achieved by adjusting the displayed image.

Taking pictures indoors on a cloudy day, the light is not good, what is the shape of the brightness histogram of the photo? (Single choice)

(Judgment) Back propagation is a common method used to train artificial neural networks.

A model in which several linear models are mixed together is called a linear mixed model.

Dropout is to randomly discard a certain proportion of sample data during model training.

Speech recognition technology is to let the machine convert speech into text through recognition and understanding.

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.

What is included in the data preprocessing in the voice task?

Which of the following options are applications of natural language processing?

The convergence point of gradient descent calculation depends on the cost function.

What are the traditional voice models?

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.

The various indicators of the bilinear interpolation method are better than the nearest neighbor interpolation method. The nearest neighbor interpolation method has been eliminated by the bilinear interpolation method in practical applications.

The task of image recognition can be divided into three levels, according to the amount of data of the operation object, from small to large?

The image filter operation is also called template operation. Common template operations include template convolution and template row.

What algorithm engines are supported by ModelArts training assignments? (Multiple Choice)

Color images can be converted from the HSV color space to the RGB color space, but the RGB color space cannot be directly converted to the HSV color space.

In the vehicle detection scene of traffic law enforcement, the penalties for vehicles that violate regulations are rather missed, instead of false alarms, so as not to produce false fines, which of the system's instructions are high?

Which of the following options is the method of automatically calculating the gradient.

Using two 3*3 convolutions to check a three-channel color image into a convolution, how many channels are there for the feature map?

A door that is not a cell in LSM?

What is the spatial adjacency of the two pixels with coordinates (21, 13) and coordinates (22.12)?

The hidden layer is the intermediate layer between the input and output houses in the neural network, and the training data does not give the required output for each of these layers.