CloudSoftwareHardware

ON THIS PAGE

  • Cast
  • Node properties
  • How to place it
  • Inputs and Outputs
  • Usage
  • Examples of functionality
  • Reference

Cast

Cast Node is used to convert NNData messages to ImgFrame. This is useful in cases where applications need to use outputs from a NeuralNetwork node to be fed into nodes that only accept ImgFrame.

Node properties

  • outputFrameType - The type of the output frame. The type should be the same as the NN output frame type.
  • offset - The offset to be applied to the output frame. Default is 0.
  • scale - The scale factor to be applied to the output frame. Default is 1.
Offset and scale are used to define a linear transformation of the pixel values. The formula is output = input * scale + offset.

How to place it

Python
C++

Python

Python
1pipeline = dai.Pipeline()
2cast = pipeline.create(dai.node.Cast)

Inputs and Outputs

React Flow

Usage

Python
C++

Python

Python
1pipeline = dai.Pipeline()
2
3nn = pipeline.create(dai.node.NeuralNetwork)
4# Load a custom blob
5nn.setBlobPath("path_to_blob")
6
7cast = pipeline.create(dai.node.Cast)
8cast.setOutputFrameType(dai.ImgFrame.Type.BGR888p)
9cast.setScale(1)
10
11# Link the output of NN to the input of Cast
12nn.out.link(cast.input)
13
14# Send the casted output to a host via XLink
15xout = pipeline.create(dai.node.XLinkOut)
16xout.setStreamName("castOut")
17cast.output.link(xout.input)

Examples of functionality

Reference

Need assistance?

Head over to Discussion Forum for technical support or any other questions you might have.