ADLINK Technology EVA SDK, User Manual, Page: 102 / 117

98
Image Analytic Plugins
std
“mean” gchararray
Sets the standard deviation vector value needed to apply to input data. The standard deviation value of the
dataset is the standard deviation value of the pixels of all the images across all the color channels (e.g. RBG).
Greyscale images will have just one mean value and color images like ImageNet will have 3 mean values.
Flags: Read / Write
Default value: "1,1,1"
device
“device” gchararray
Selects which device will be used to inference, use GPU index start from 0. The format is “cpu:0” for CPU and
“gpu:index” for GPU.
Flags: Read / Write
Default value: "gpu:0"
inps
“inps” gint
Specifies which input size is used. Only use with a model that does not list input size of the input layer. If set to 0,
uses the model defined size.
Flags: Read / Write
Default value: 0
rgbconv
“rebconv” gboolean
Sets whether to convert the color format of an input image to RGB.
Flags: Read / Write
Default value: False
nchw
“nchw” gboolean
Sets whether to convert the input order of an input image to from nhwc (number of image, height, width, channel)
to nchw (number of image, channel, height, width).
Flags: Read / Write
Default value: True
5.1.12 adtrans_tinyyolov2_py
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.