ie_api.PreProcessInfo Class Reference

This class stores pre-process information for the input. More...

Public Member Functions
def	__init__ (self)
def	__dealloc__ (self)
def	get_number_of_channels (self)
	Returns a number of channels to preprocess.
def	init (self, number_of_channels)
	Initializes with given number of channels.
def	set_mean_image (self, mean_image)
	Sets mean image values if operation is applicable. More...
def	set_mean_image_for_channel (self, mean_image, channel)
	Sets mean image values if operation is applicable. More...
def	mean_variant (self)
	Mean Variant to be applied for input before inference if needed. More...
def	mean_variant (self, variant)
def	resize_algorithm (self)
	Resize Algorithm to be applied for input before inference if needed. More...
def	resize_algorithm (self, alg)
def	color_format (self)
	Color format to be used in on-demand color conversions applied to input before inference. More...
def	color_format (self, fmt)

Data Fields
	mean_variant
	Mean Variant to be applied for input before inference if needed. More...
	resize_algorithm
	Resize Algorithm to be applied for input before inference if needed. More...
	color_format
	Color format to be used in on-demand color conversions applied to input before inference. More...

Detailed Description

This class stores pre-process information for the input.

Member Function Documentation

color_format()

def ie_api.PreProcessInfo.color_format

(

self

)

Color format to be used in on-demand color conversions applied to input before inference.

Usage example:

net = ie_core.read_network(model=path_to_xml_file, weights=path_to_bin_file)
net.input_info['data'].preprocess_info.color_format = ColorFormat.BGR

mean_variant()

def ie_api.PreProcessInfo.mean_variant

(

self

)

Mean Variant to be applied for input before inference if needed.

Usage example:

net = ie_core.read_network(model=path_to_xml_file, weights=path_to_bin_file)
net.input_info['data'].preprocess_info.mean_variant = MeanVariant.MEAN_IMAGE

resize_algorithm()

def ie_api.PreProcessInfo.resize_algorithm

(

self

)

Resize Algorithm to be applied for input before inference if needed.

Note

It's need to set your input via the set_blob method.

Usage example:

net = ie_core.read_network(model=path_to_xml_file, weights=path_to_bin_file)
net.input_info['data'].preprocess_info.resize_algorithm = ResizeAlgorithm.RESIZE_BILINEAR
exec_net = ie_core.load_network(net, 'CPU')
tensor_desc = ie.TensorDesc("FP32", [1, 3, image.shape[2], image.shape[3]], "NCHW")
img_blob = ie.Blob(tensor_desc, image)
request = exec_net.requests[0]
request.set_blob('data', img_blob)
request.infer()

set_mean_image()

def ie_api.PreProcessInfo.set_mean_image	(		self,
			mean_image
	)

Sets mean image values if operation is applicable.

Also sets the mean type to MEAN_IMAGE for all channels

set_mean_image_for_channel()

def ie_api.PreProcessInfo.set_mean_image_for_channel	(		self,
			mean_image,
			channel
	)

Sets mean image values if operation is applicable.

Also sets the mean type to MEAN_IMAGE for a particular channel

Field Documentation

color_format

ie_api.PreProcessInfo.color_format

Color format to be used in on-demand color conversions applied to input before inference.

Usage example:

net = ie_core.read_network(model=path_to_xml_file, weights=path_to_bin_file)
net.input_info['data'].preprocess_info.color_format = ColorFormat.BGR

mean_variant

ie_api.PreProcessInfo.mean_variant

Mean Variant to be applied for input before inference if needed.

Usage example:

net = ie_core.read_network(model=path_to_xml_file, weights=path_to_bin_file)
net.input_info['data'].preprocess_info.mean_variant = MeanVariant.MEAN_IMAGE

resize_algorithm

ie_api.PreProcessInfo.resize_algorithm

Resize Algorithm to be applied for input before inference if needed.

Note

It's need to set your input via the set_blob method.

Usage example:

net = ie_core.read_network(model=path_to_xml_file, weights=path_to_bin_file)
net.input_info['data'].preprocess_info.resize_algorithm = ResizeAlgorithm.RESIZE_BILINEAR
exec_net = ie_core.load_network(net, 'CPU')
tensor_desc = ie.TensorDesc("FP32", [1, 3, image.shape[2], image.shape[3]], "NCHW")
img_blob = ie.Blob(tensor_desc, image)
request = exec_net.requests[0]
request.set_blob('data', img_blob)
request.infer()

---

The documentation for this class was generated from the following file:

• ie_api.pyx