openvino.inference_engine.PreProcessInfo¶

class openvino.inference_engine.PreProcessInfo¶

Bases: object

OpenVINO Inference Engine Python API is deprecated and will be removed in the 2024.0 release. For instructions on transitioning to the new API, please refer to https://docs.openvino.ai/latest/openvino_2_0_transition_guide.html

This class stores pre-process information for the input

__init__()¶

Methods

`__delattr__`(name, /)	Implement delattr(self, name).
`__dir__`()	Default dir() implementation.
`__eq__`(value, /)	Return self==value.
`__format__`(format_spec, /)	Default object formatter.
`__ge__`(value, /)	Return self>=value.
`__getattribute__`(name, /)	Return getattr(self, name).
`__getitem__`(key, /)	Return self[key].
`__gt__`(value, /)	Return self>value.
`__hash__`()	Return hash(self).
`__init__`()
`__init_subclass__`	This method is called when a class is subclassed.
`__le__`(value, /)	Return self<=value.
`__lt__`(value, /)	Return self<value.
`__ne__`(value, /)	Return self!=value.
`__new__`(**kwargs)
`__reduce__`	PreProcessInfo.__reduce_cython__(self)
`__reduce_ex__`(protocol, /)	Helper for pickle.
`__repr__`()	Return repr(self).
`__setattr__`(name, value, /)	Implement setattr(self, name, value).
`__setstate__`	PreProcessInfo.__setstate_cython__(self, __pyx_state)
`__sizeof__`()	Size of object in memory, in bytes.
`__str__`()	Return str(self).
`__subclasshook__`	Abstract classes can override this to customize issubclass().
`get_number_of_channels`(self)	Returns a number of channels to preprocess
`init`(self, size_t number_of_channels)	Initializes with given number of channels
`set_mean_image`(self, Blob mean_image)	Sets mean image values if operation is applicable.
`set_mean_image_for_channel`(self, ...)	Sets mean image values if operation is applicable.

Attributes

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

__class__¶: alias of type

__delattr__(name, /)¶: Implement delattr(self, name).

__dir__()¶: Default dir() implementation.

__eq__(value, /)¶: Return self==value.

__format__(format_spec, /)¶: Default object formatter.

__ge__(value, /)¶: Return self>=value.

__getattribute__(name, /)¶: Return getattr(self, name).

__getitem__(key, /)¶: Return self[key].

__gt__(value, /)¶: Return self>value.

__hash__()¶: Return hash(self).

__init__()¶

__init_subclass__()¶

This method is called when a class is subclassed.

The default implementation does nothing. It may be overridden to extend subclasses.

__le__(value, /)¶: Return self<=value.

__lt__(value, /)¶: Return self<value.

__ne__(value, /)¶: Return self!=value.

__new__(**kwargs)¶

__reduce__()¶: PreProcessInfo.__reduce_cython__(self)

__reduce_ex__(protocol, /)¶: Helper for pickle.

__repr__()¶: Return repr(self).

__setattr__(name, value, /)¶: Implement setattr(self, name, value).

__setstate__()¶: PreProcessInfo.__setstate_cython__(self, __pyx_state)

__sizeof__()¶: Size of object in memory, in bytes.

__str__()¶: Return str(self).

__subclasshook__()¶

Abstract classes can override this to customize issubclass().

This is invoked early on by abc.ABCMeta.__subclasscheck__(). It should return True, False or NotImplemented. If it returns NotImplemented, the normal algorithm is used. Otherwise, it overrides the normal algorithm (and the outcome is cached).

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

get_number_of_channels(self)¶: Returns a number of channels to preprocess

init(self, size_t number_of_channels)¶: Initializes with given number of channels

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¶

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(self, Blob 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(self, Blob mean_image, size_t channel)¶: Sets mean image values if operation is applicable. Also sets the mean type to MEAN_IMAGE for a particular channel