ADLINK Technology EVA SDK, User Manual, Page: 99 / 117

EVA SDK User's Manual
Image Analytic Plugins
95
5.1.10.3 Pad Templates
sink_%u
video/x-raw:
format: { BGR }
width: [ 0, 2147483647 ]
height: [ 0, 2147483647 ]
framerate: [ 0/1, 2147483647/1 ]
Presence – always
Direction – sink
src
video/x-raw:
format: { BGR }
width: [ 0, 2147483647 ]
height: [ 0, 2147483647 ]
framerate: [ 0/1, 2147483647/1 ]
Presence – always
Direction – src
5.1.11 adonnx
Initializes the ONNXRuntime inference engine plugins to infer a data stream with the following parameters.
1. Onnx model path
2. Scale (must be a float number)
3. Mean (must be a string of 3 numbers representing a vector of mean values used in training)
4. Standard deviation (must be a string of 3 numbers representing a vector of standard deviation values used in
training)
5. rgbconv—converts image input order to RGB from BGR
6. nchw—converts input to nchw (batch, channel, height, width), or keeps it at nhwc (batch, height, width,
channel )
7. Device—string of device used to inference
Note : This element must connect with adtranslator plugins to handle inference data, or the pipeline will have
unexpected results.