ADLINK Technology EVA SDK, User Manual, Page: 94 / 117

90
Image Analytic Plugins
batch
“batch” gint
Batch size of input to inference (number of image to inference at same time) need at least 1. This value will be
limited by the availability of memory on the inference devices. If the batch size is set to larger than 1, the
advideobatch element needs to be used before this plugin.
Flags: Read / Write
Default value: 1
rgbconv
“rebconv” gboolean
Sets whether to convert the color format of an input image to RGB.
Flags: Read / Write
Default value: false
5.1.8 advino
Initializes the OpenVINO inference engine plugins to infer a data stream with the following parameters.
1. OpenVINO optimized engine Model path
2. Inference device type: (1) CPU<default>; (2) GPU; (3) VPU; (4) FPGA; (5) MYRIAD
(Reference: OpenVINO support devices link)
Some MYRIAD boards contain multiple MYRIAD cores, so users can inference a specific core or select one via the
OpenVINO inference scheduler.
The following command can query the available devices.
$ python3 -c "from openvino.inference_engine import IECore;
print(IECore().available_devices)"
['CPU', 'GPU', 'HDDL', 'MYRIAD.7.1-ma2480', 'MYRIAD.7.2-ma2480']
This element pushes a buffer list where the last buffer is the inference result raw data needed to be analyzed by
the next element, and the other result is the original incoming frame buffer.
Unexpected results can occur if you pipe an element that does not implement a buffer list chain function.
For more details, refer to Convert for OpenVINO Model .
Note :
1. Only supported on Intel platforms.
2. This element must connect with adtranslator plugins to handle inference data, or the pipeline will have
unexpected results.