openvino_genai.ImageGenerationPerfMetrics#

class openvino_genai.ImageGenerationPerfMetrics#

Bases: pybind11_object

Holds performance metrics for each generate call.

PerfMetrics holds fields with mean and standard deviations for the following metrics: - Generate iteration duration, ms - Inference duration for unet model, ms - Inference duration for transformer model, ms

Additional fields include: - Load time, ms - Generate total duration, ms - inference durations for each encoder, ms - inference duration of vae_encoder model, ms - inference duration of vae_decoder model, ms

Preferable way to access values is via get functions. Getters calculate mean and std values from raw_metrics and return pairs. If mean and std were already calculated, getters return cached values.

Parameters:

  • get_text_encoder_infer_duration (dict[str, float]) – Returns the inference duration of every text encoder in milliseconds.

  • get_vae_encoder_infer_duration (float) – Returns the inference duration of vae encoder in milliseconds.

  • get_vae_decoder_infer_duration (float) – Returns the inference duration of vae decoder in milliseconds.

  • get_load_time (float) – Returns the load time in milliseconds.

  • get_generate_duration (float) – Returns the generate duration in milliseconds.

  • get_inference_duration (float) – Returns the total inference durations (including encoder, unet/transformer and decoder inference) in milliseconds.

  • get_first_and_other_iter_duration (tuple) – Returns the first iteration duration and the average duration of other iterations in one generation in milliseconds.

  • get_iteration_duration (MeanStdPair) – Returns the mean and standard deviation of one generation iteration in milliseconds.

  • get_first_and_second_unet_infer_duration (tuple) – Returns the first inference duration and the average duration of other inferences in one generation in milliseconds.

  • get_unet_infer_duration (MeanStdPair) – Returns the mean and standard deviation of one unet inference in milliseconds.

  • get_first_and_other_trans_infer_duration (tuple) – Returns the first inference duration and the average duration of other inferences in one generation in milliseconds.

  • get_transformer_infer_duration (MeanStdPair) – Returns the mean and standard deviation of one transformer inference in milliseconds.

  • raw_metrics (RawImageGenerationPerfMetrics) – A structure of RawImageGenerationPerfMetrics type that holds raw metrics.

__init__(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → None#

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).

__getstate__()

Helper for pickle.

__gt__(value, /)

Return self>value.

__hash__()

Return hash(self).

__init__(self)

__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__()

Helper for pickle.

__reduce_ex__(protocol, /)

Helper for pickle.

__repr__()

Return repr(self).

__setattr__(name, value, /)

Implement setattr(self, name, value).

__sizeof__()

Size of object in memory, in bytes.

__str__()

Return str(self).

__subclasshook__

Abstract classes can override this to customize issubclass().

_pybind11_conduit_v1_

get_first_and_other_iter_duration(self)

get_first_and_other_trans_infer_duration(self)

get_first_and_other_unet_infer_duration(self)

get_generate_duration(self)

get_inference_duration(self)

get_iteration_duration(self)

get_load_time(self)

get_text_encoder_infer_duration(self)

get_transformer_infer_duration(self)

get_unet_infer_duration(self)

get_vae_decoder_infer_duration(self)

get_vae_encoder_infer_duration(self)

Attributes

__annotations__

raw_metrics

__annotations__ = {}#
__class__#

alias of pybind11_type

__delattr__(name, /)#

Implement delattr(self, name).

__dir__()#

Default dir() implementation.

__eq__(value, /)#

Return self==value.

__format__(format_spec, /)#

Default object formatter.

Return str(self) if format_spec is empty. Raise TypeError otherwise.

__ge__(value, /)#

Return self>=value.

__getattribute__(name, /)#

Return getattr(self, name).

__getstate__()#

Helper for pickle.

__gt__(value, /)#

Return self>value.

__hash__()#

Return hash(self).

__init__(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → None#
__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__()#

Helper for pickle.

__reduce_ex__(protocol, /)#

Helper for pickle.

__repr__()#

Return repr(self).

__setattr__(name, value, /)#

Implement setattr(self, name, value).

__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).

_pybind11_conduit_v1_()#
get_first_and_other_iter_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → tuple#
get_first_and_other_trans_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → tuple#
get_first_and_other_unet_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → tuple#
get_generate_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → float#
get_inference_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → float#
get_iteration_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → openvino_genai.py_openvino_genai.MeanStdPair#
get_load_time(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → float#
get_text_encoder_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → dict[str, float]#
get_transformer_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → openvino_genai.py_openvino_genai.MeanStdPair#
get_unet_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → openvino_genai.py_openvino_genai.MeanStdPair#
get_vae_decoder_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → float#
get_vae_encoder_infer_duration(self: openvino_genai.py_openvino_genai.ImageGenerationPerfMetrics) → float#
property raw_metrics#