ADLINK Technology EVA SDK, User Manual, Page: 85 / 117

EVA SDK User's Manual
Image Analytic Plugins
81
only-max-prob
“only-max-prob” gboolean
Keep the remaining maximum probability class of the Inference result. If this is true, the element will ignore the
class-num property.
Flags: Read, Write
Default value: false
label
“label” gchararray
The deep learning model label.
Flags: Read, Write
Default value: NULL
5.1.4 adtrans_yolo
This element implements a buffer list chain function. Previous elements should push a buffer list into this element.
The last buffer in the list will be seen as an inference result.
5.1.4.1 Examples Using gst-launch
The following pipeline translates the OpenVINO inference result using the yolov3 type model into a human-
readable format.
gst-launch-1.0 videotestsrc ! advino model=yolov3.xml device=GPU ! adtran_yolo
label=yolo_VINO_labels.txt mask="(3,4,5),(0,1,2),(6,7,8)" blob-size=26,52,13
input-width=416 input-height=416 ! ximagesink
The following pipeline translates the TensorRT inference result using the detection type model with yolov3 topology
into a human-readable format.
gst-launch-1.0 videotestsrc ! adrt model=yolov3_608_tx2.engine scale=0.004 mean="0
0 0" device=0 batch=1 ! adtran_yolo label=yolo_RT_labels.txt blob-size="13,26,52"
mask="(6,7,8),(3,4,5),(0,1,2)" ! ximagesink
Note : The element ‘xvimagesink’ is only supported on Linux. It is recommended to use the ‘glimagesink’ or
‘d3dvideosink’ elements to display the window on Windows.