natas_hw
/
openvino
0
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

[DOCS] Update code examples with imports and save_model (#23654) 

Updating code examples with imports for ``convert_model`` and adding an
example of how to save a converted model. This PR addresses the 120254
ticket.

---------

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
This commit is contained in:
Sebastian Golebiewski 2024-03-27 07:14:06 +01:00 committed by GitHub
parent 6306ee1a86
commit 8c0cd7dfd1
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
5 changed files with 144 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

25
docs/articles_en/documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-convert-models-as-python-objects.rst
View File

@ -15,7 +15,11 @@ Model conversion API is represented by ``convert_model()`` method in openvino.to
.. note::
Model conversion can be performed by the ``convert_model()`` method and MO command line tool. The functionality from this article is applicable for ``convert_model()`` only and it is not present in command line tool.
Model conversion can be performed only when you install
:doc:`the development tools <../../../legacy-features/install-dev-tools>`, which provide
both the ``convert_model()`` method and ``mo`` command-line tool.
The functionality from this article is applicable for ``convert_model()`` only and it is
not present in command-line tool.
``convert_model()`` returns an openvino.runtime.Model object which can be compiled and inferred or serialized to IR.
@ -26,6 +30,7 @@ Example of converting a PyTorch model directly from memory:
:force:
import torchvision
from openvino.tools.mo import convert_model
model = torchvision.models.resnet50(weights='DEFAULT')
ov_model = convert_model(model)
@ -43,6 +48,7 @@ Example of using native Python classes to set ``input_shape``, ``mean_values`` a
:force:
from openvino.runtime import PartialShape, Layout
from openvino.tools.mo import convert_model
ov_model = convert_model(model, input_shape=PartialShape([1,3,100,100]), mean_values=[127, 127, 127], layout=Layout("NCHW"))
@ -51,6 +57,9 @@ Example of using strings for setting ``input_shape``, ``mean_values`` and ``layo
.. code-block:: py
:force:
from openvino.runtime import Layout
from openvino.tools.mo import convert_model
ov_model = convert_model(model, input_shape="[1,3,100,100]", mean_values="[127,127,127]", layout="NCHW")
@ -62,6 +71,8 @@ Example of using a tuple in the ``input`` parameter to cut a model:
.. code-block:: py
:force:
from openvino.tools.mo import convert_model
ov_model = convert_model(model, input=("input_name", [3], np.float32))
For complex cases, when a value needs to be set in the ``input`` parameter, the ``InputCutInfo`` class can be used. ``InputCutInfo`` accepts four parameters: ``name``, ``shape``, ``type``, and ``value``.
@ -100,6 +111,9 @@ Example of using lists to set shapes, types and layout for multiple inputs:
.. code-block:: py
:force:
from openvino.runtime import Layout
from openvino.tools.mo import convert_model, LayoutMap
ov_model = convert_model(model, input=[("input1", [1,3,100,100], np.float32), ("input2", [1,3,100,100], np.float32)], layout=[Layout("NCHW"), LayoutMap("NCHW", "NHWC")])
``layout``, ``source_layout`` and ``dest_layout`` accept an ``openvino.runtime.Layout`` object or ``string``.
@ -127,3 +141,12 @@ Example of using the ``LayoutMap`` class to change the layout of a model input:
ov_model = convert_model(model, layout=LayoutMap("NCHW", "NHWC"))
Example of using the ``serialize`` method to save the converted model to OpenVINO IR:
.. code-block:: py
:force:
from openvino.runtime import serialize
serialize(ov_model, "model.xml")

43
docs/articles_en/documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-supported-model-formats.rst
View File

@ -65,6 +65,11 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
import torchvision
from openvino.tools.mo import convert_model
core = openvino.Core()
model = torchvision.models.resnet50(weights='DEFAULT')
ov_model = convert_model(model)
compiled_model = core.compile_model(ov_model, "AUTO")
@ -108,6 +113,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
from openvino.tools.mo import convert_model
core = openvino.Core()
ov_model = convert_model("saved_model.pb")
compiled_model = core.compile_model(ov_model, "AUTO")
@ -209,6 +218,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
from openvino.tools.mo import convert_model
core = openvino.Core()
ov_model = convert_model("<INPUT_MODEL>.tflite")
compiled_model = core.compile_model(ov_model, "AUTO")
@ -229,7 +242,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = read_model("<INPUT_MODEL>.tflite")
import openvino
core = openvino.Core()
ov_model = core.read_model("<INPUT_MODEL>.tflite")
compiled_model = core.compile_model(ov_model, "AUTO")
* The ``compile_model()`` method:
@ -243,6 +259,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
core = openvino.Core()
compiled_model = core.compile_model("<INPUT_MODEL>.tflite", "AUTO")
For a guide on how to run inference, see how to
@ -327,6 +346,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
from openvino.tools.mo import convert_model
core = openvino.Core()
ov_model = convert_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")
@ -347,7 +370,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = read_model("<INPUT_MODEL>.onnx")
import openvino
core = openvino.Core()
ov_model = core.read_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")
* The ``compile_model()`` method:
@ -361,6 +387,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
core = openvino.Core()
compiled_model = core.compile_model("<INPUT_MODEL>.onnx", "AUTO")
For a guide on how to run inference, see how to :doc:`Integrate OpenVINO™ with Your Application <../../../../openvino-workflow/running-inference/integrate-openvino-with-your-application>`.
@ -448,6 +477,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
from openvino.tools.mo import convert_model
core = openvino.Core()
ov_model = convert_model("<INPUT_MODEL>.pdmodel")
compiled_model = core.compile_model(ov_model, "AUTO")
@ -467,6 +500,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
core = openvino.Core()
ov_model = read_model("<INPUT_MODEL>.pdmodel")
compiled_model = core.compile_model(ov_model, "AUTO")
@ -481,6 +517,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import openvino
core = openvino.Core()
compiled_model = core.compile_model("<INPUT_MODEL>.pdmodel", "AUTO")
For a guide on how to run inference, see how to

8
docs/articles_en/documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-supported-model-formats/[legacy]-convert-onnx.rst
View File

@ -4,7 +4,7 @@
=============================================
.. meta::
:description: Learn how to convert a model from the
:description: Learn how to convert a model from the
ONNX format to the OpenVINO Intermediate Representation.
@ -12,7 +12,7 @@
The code described here has been **deprecated!** Do not use it to avoid working with a legacy solution. It will be kept for some time to ensure backwards compatibility, but **you should not use** it in contemporary applications.
This guide describes a deprecated conversion method. The guide on the new and recommended method can be found in the :doc:`Converting an ONNX Model <../../../../../openvino-workflow/model-preparation/convert-model-onnx>` article.
This guide describes a deprecated conversion method. The guide on the new and recommended method can be found in the :doc:`Converting an ONNX Model <../../../../../openvino-workflow/model-preparation/convert-model-onnx>` article.
.. note:: ONNX models are supported via FrontEnd API. You may skip conversion to IR and read models directly by OpenVINO runtime API. Refer to the :doc:`inference example <../../../../../openvino-workflow/running-inference/integrate-openvino-with-your-application>` for more details. Using ``convert_model`` is still necessary in more complex cases, such as new custom inputs/outputs in model pruning, adding pre-processing, or using Python conversion extensions.
@ -32,6 +32,10 @@ The model conversion process assumes you have an ONNX model that was directly do
.. code-block:: py
:force:
import openvino
from openvino.tools.mo import convert_model
core = openvino.Core()
ov_model = convert_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")

22
docs/articles_en/documentation/legacy-features/transition-legacy-conversion-api/legacy-conversion-api/[legacy]-supported-model-formats/[legacy]-convert-tensorflow.rst
View File

@ -208,6 +208,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
model = tf.keras.applications.ResNet50(weights="imagenet")
ov_model = convert_model(model)
@ -218,6 +221,7 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
:force:
import tensorflow_hub as hub
from openvino.tools.mo import convert_model
model = hub.KerasLayer("https://tfhub.dev/google/imagenet/mobilenet_v1_100_224/classification/5")
ov_model = convert_model(model, input_shape=[-1, 224, 224, 3])
@ -227,6 +231,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
class MyModule(tf.Module):
def __init__(self, name=None):
super().__init__(name=name)
@ -243,6 +250,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
with tf.compat.v1.Session() as sess:
inp1 = tf.compat.v1.placeholder(tf.float32, [100], 'Input1')
inp2 = tf.compat.v1.placeholder(tf.float32, [100], 'Input2')
@ -257,6 +267,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
with tf.compat.v1.Session() as sess:
inp1 = tf.compat.v1.placeholder(tf.float32, [100], 'Input1')
inp2 = tf.compat.v1.placeholder(tf.float32, [100], 'Input2')
@ -271,6 +284,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
@tf.function(
input_signature=[tf.TensorSpec(shape=[1, 2, 3], dtype=tf.float32),
tf.TensorSpec(shape=[1, 2, 3], dtype=tf.float32)])
@ -284,6 +300,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
with tf.compat.v1.Session() as sess:
inp1 = tf.compat.v1.placeholder(tf.float32, [100], 'Input1')
inp2 = tf.compat.v1.placeholder(tf.float32, [100], 'Input2')
@ -297,6 +316,9 @@ Model conversion API supports passing TensorFlow/TensorFlow2 models directly fro
.. code-block:: py
:force:
import tensorflow as tf
from openvino.tools.mo import convert_model
model = tf.keras.Model(...)
checkpoint = tf.train.Checkpoint(model)
save_path = checkpoint.save(save_directory)

73
docs/articles_en/openvino-workflow/model-preparation/convert-model-to-ir.rst
View File

@ -51,9 +51,12 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
import torchvision
import openvino as ov
model = torchvision.models.resnet50(weights='DEFAULT')
ov_model = convert_model(model)
compiled_model = core.compile_model(ov_model, "AUTO")
ov_model = ov.convert_model(model)
compiled_model = ov.compile_model(ov_model, "AUTO")
For more details on conversion, refer to the
:doc:`guide <convert-model-pytorch>`
@ -94,8 +97,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = convert_model("saved_model.pb")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
ov_model = ov.convert_model("saved_model.pb")
compiled_model = ov.compile_model(ov_model, "AUTO")
For more details on conversion, refer to the
:doc:`guide <convert-model-tensorflow>`
@ -115,8 +120,11 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = read_model("saved_model.pb")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
core = ov.Core()
ov_model = core.read_model("saved_model.pb")
compiled_model = ov.compile_model(ov_model, "AUTO")
For a guide on how to run inference, see how to
:doc:`Integrate OpenVINO™ with Your Application <../running-inference/integrate-openvino-with-your-application>`.
@ -195,8 +203,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = convert_model("<INPUT_MODEL>.tflite")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
ov_model = ov.convert_model("<INPUT_MODEL>.tflite")
compiled_model = ov.compile_model(ov_model, "AUTO")
For more details on conversion, refer to the
:doc:`guide <convert-model-tensorflow-lite>`
@ -215,8 +225,11 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = read_model("<INPUT_MODEL>.tflite")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
core = ov.Core()
ov_model = core.read_model("<INPUT_MODEL>.tflite")
compiled_model = ov.compile_model(ov_model, "AUTO")
* The ``compile_model()`` method:
@ -229,7 +242,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
compiled_model = core.compile_model("<INPUT_MODEL>.tflite", "AUTO")
import openvino as ov
compiled_model = ov.compile_model("<INPUT_MODEL>.tflite", "AUTO")
For a guide on how to run inference, see how to
:doc:`Integrate OpenVINO™ with Your Application <../running-inference/integrate-openvino-with-your-application>`.
@ -313,8 +328,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = convert_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
ov_model = ov.convert_model("<INPUT_MODEL>.onnx")
compiled_model = ov.compile_model(ov_model, "AUTO")
For more details on conversion, refer to the
:doc:`guide <convert-model-onnx>`
@ -333,8 +350,11 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = read_model("<INPUT_MODEL>.onnx")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
core = ov.Core()
ov_model = core.read_model("<INPUT_MODEL>.onnx")
compiled_model = ov.compile_model(ov_model, "AUTO")
* The ``compile_model()`` method:
@ -347,7 +367,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
compiled_model = core.compile_model("<INPUT_MODEL>.onnx", "AUTO")
import openvino as ov
compiled_model = ov.compile_model("<INPUT_MODEL>.onnx", "AUTO")
For a guide on how to run inference, see how to :doc:`Integrate OpenVINO™ with Your Application <../running-inference/integrate-openvino-with-your-application>`.
@ -434,8 +456,10 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = convert_model("<INPUT_MODEL>.pdmodel")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
ov_model = ov.convert_model("<INPUT_MODEL>.pdmodel")
compiled_model = ov.compile_model(ov_model, "AUTO")
For more details on conversion, refer to the
:doc:`guide <convert-model-paddle>`
@ -453,8 +477,11 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
ov_model = read_model("<INPUT_MODEL>.pdmodel")
compiled_model = core.compile_model(ov_model, "AUTO")
import openvino as ov
core = ov.Core()
ov_model = core.read_model("<INPUT_MODEL>.pdmodel")
compiled_model = ov.compile_model(ov_model, "AUTO")
* The ``compile_model()`` method:
@ -467,7 +494,9 @@ Here are code examples of how to use these methods with different model formats:
.. code-block:: py
:force:
compiled_model = core.compile_model("<INPUT_MODEL>.pdmodel", "AUTO")
import openvino as ov
compiled_model = ov.compile_model("<INPUT_MODEL>.pdmodel", "AUTO")
For a guide on how to run inference, see how to
:doc:`Integrate OpenVINO™ with Your Application <../running-inference/integrate-openvino-with-your-application>`.
@ -580,7 +609,7 @@ An example showing how to take advantage of OpenVINO IR, saving a model in OpenV
ov_model = core.read_model("model.xml")
# 4. Compile model from memory
compiled_model = core.compile_model(ov_model)
compiled_model = ov.compile_model(ov_model)
Additional Resources
####################