Deep Learning Result Parser

Function

This Step can parse the cascaded model package’s inference result exported by the Deep Learning Model Package Inference Step.

Usage Scenario

When “Deep Learning Model Package Inference” is used for the inference with a cascaded model package, this Step follows the “Deep Learning Model Package Inference” Step.

When multiple images are input for a simultaneous inference and you want to check the parsing result of every image, it is recommended to add an Unpack Data Step between the “Deep Learning Model Package Inference” and “Deep Learning Result Parser” Step.

Input and Output

Usage

Directly follows the “Deep Learning Model Package Inference” Step

When this Step follows the “Deep Learning Model Package Inference” Step, this Step can display different parameters according to different “Deep Learning Value Type”.

For example, if this Step is followed by the “Object Detection” output port of the “Deep Learning Model Package Inference”, then this Step will display the parameters related to the object detection. A parameter description for each scene can be found in Deep Learning Model Package Inference.

Use with an “Unpack Data” Step

The “Unpack Data” Step is added between the “Deep Learning Model Package Inference” and “Deep Learning Result Parser” Steps as shown below.

• The Output Size in the “Unpack Data” Step is the same as the input image size.

• After unpacking the data, the “Deep Learning Result Parser” Step may not automatically determine the scenario of the model due to missing subtype data. Thus, the output port of the “Deep Learning Result Parser” Step will not be generated. You will need to set the Deep Learning Value Type in this Step.

Attention

Once the Deep Learning Value Type is selected, it cannot be changed. If you want to change the Deep Learning Value Type, please delete and re-add the “Deep Learning Result Parser” Step.