Table Of Contents
Detect Objects (G Dataflow)
Detects learned objects in the image.
This node provides a reference design to classify an image using the loaded model.
ROI descriptor
Rectangle region specifying the location of the sample in the image.
If ROI Descriptor is empty, the entire image is considered to be the region.
Global Rectangle
Coordinates of the bounding rectangle.
Contours
Individual shapes that define an ROI.
ID
Object specifying if contour is the external or internal edge of an ROI.
Type
Shape type of the contour.
Coordinates
Relative position of the contour.
model session in
Reference to the loaded model file.
image in
Input for model graph Input Node Name.
Image will be converted to multi dimensional tensor based on loaded model.
input node name
Name of the Input data node in the loaded model graph.
output node names
Name of the Output data node in the loaded model graph.
This requires four node names.
number of objects
String that specifies output node name for receiving number of detected objects using the loaded model. The corresponding node must output single dimensional tensor.
labels
String to specify the output node name for receiving labels of detected objects. The corresponding node must output double dimensional tensor.
scores
String to specify the output node name for receiving scores for the detected objects. The corresponding node must output double dimensional tensor.
bounding boxes
String to specify the output node name for receiving bounding boxes (top, left, bottom, right) of detected objects. The corresponding node must output three dimensional tensor.
error in
Error conditions that occur before this node runs.
The node responds to this input according to standard error behavior.
Standard Error Behavior
Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.
Default: No error
labels
Array of clusters containing Class ID and Label..
This is used for constructing detected objects.
model session out
Reference to the modified loaded model.
image out
Reference to the source image.
detected objects
Array of detected objects in the image.
label
Class label name.
This string is referenced based on Labels input. If Labels is not supplied, the class ID is converted to a string.
Score
Probablity score for the classification result.
Score ranges are based on output of the loaded model. It typically varies between 0 and 1.
bounding box
Array of points that define the boundary of the detected object.
Typically the model graph outputs unit bounding boxes. They are converted to image dimensions. You can connect this array directly to the Overlay Multiple Lines node to overlay the location of a match on your image.
number of objects
Number of detected objects in the image.
error out
Error information.
The node produces this output according to standard error behavior.
Standard Error Behavior
Many nodes provide an error in input and an error out output so that the node can respond to and communicate errors that occur while code is running. The value of error in specifies whether an error occurred before the node runs. Most nodes respond to values of error in in a standard, predictable way.
Where This Node Can Run:
Desktop OS: Windows
FPGA: Not supported
Web Server: Not supported in VIs that run in a web application