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

DOCS shift to rst - Hello Classification Samples (#16681)

This commit is contained in:
Maciej Smyk 2023-04-03 08:23:44 +02:00 committed by GitHub
parent 8491f15ba7
commit f5dced8e69
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
3 changed files with 331 additions and 234 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

171
samples/c/hello_classification/README.md
View File

@ -1,98 +1,139 @@
# Hello Classification C Sample {#openvino_inference_engine_ie_bridges_c_samples_hello_classification_README}
@sphinxdirective
This sample demonstrates how to execute an inference of image classification networks like AlexNet and GoogLeNet using Synchronous Inference Request API and input auto-resize feature.
Hello Classification C sample application demonstrates how to use the C API from OpenVINO in applications.
| Feature | API | Description |
| :--- | :--- | :--- |
| OpenVINO Runtime Version | `ov_get_openvino_version` | Get Openvino API version |
| Basic Infer Flow | `ov_core_create`, `ov_core_read_model`, `ov_core_compile_model`, `ov_compiled_model_create_infer_request`, `ov_infer_request_set_input_tensor_by_index`, `ov_infer_request_get_output_tensor_by_index` | Common API to do inference: read and compile a model, create an infer request, configure input and output tensors |
| Synchronous Infer | `ov_infer_request_infer` | Do synchronous inference |
| Model Operations | `ov_model_const_input`, `ov_model_const_output` | Get inputs and outputs of a model |
| Tensor Operations | `ov_tensor_create_from_host_ptr` | Create a tensor shape |
| Preprocessing | `ov_preprocess_prepostprocessor_create`, `ov_preprocess_prepostprocessor_get_input_info_by_index`, `ov_preprocess_input_info_get_tensor_info`, `ov_preprocess_input_tensor_info_set_from`, `ov_preprocess_input_tensor_info_set_layout`, `ov_preprocess_input_info_get_preprocess_steps`, `ov_preprocess_preprocess_steps_resize`, `ov_preprocess_input_model_info_set_layout`, `ov_preprocess_output_set_element_type`, `ov_preprocess_prepostprocessor_build` | Set image of the original size as input for a model with other input size. Resize and layout conversions are performed automatically by the corresponding plugin just before inference. |
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Feature | API | Description |
+=====================================+=============================================================+=========================================================================================================================================================================================+
| OpenVINO Runtime Version | ``ov_get_openvino_version`` | Get Openvino API version |
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Basic Infer Flow | ``ov_core_create``, | Common API to do inference: read and compile a model, create an infer request, configure input and output tensors |
| | ``ov_core_read_model``, | |
| | ``ov_core_compile_model``, | |
| | ``ov_compiled_model_create_infer_request``, | |
| | ``ov_infer_request_set_input_tensor_by_index``, | |
| | ``ov_infer_request_get_output_tensor_by_index`` | |
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Synchronous Infer | ``ov_infer_request_infer`` | Do synchronous inference |
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model Operations | ``ov_model_const_input``, | Get inputs and outputs of a model |
| | ``ov_model_const_output`` | +
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Tensor Operations | ``ov_tensor_create_from_host_ptr`` | Create a tensor shape |
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Preprocessing | ``ov_preprocess_prepostprocessor_create``, | Set image of the original size as input for a model with other input size. Resize and layout conversions are performed automatically by the corresponding plugin just before inference. |
| | ``ov_preprocess_prepostprocessor_get_input_info_by_index``, | |
| | ``ov_preprocess_input_info_get_tensor_info``, | |
| | ``ov_preprocess_input_tensor_info_set_from``, | |
| | ``ov_preprocess_input_tensor_info_set_layout``, | |
| | ``ov_preprocess_input_info_get_preprocess_steps``, | |
| | ``ov_preprocess_preprocess_steps_resize``, | |
| | ``ov_preprocess_input_model_info_set_layout``, | |
| | ``ov_preprocess_output_set_element_type``, | |
| | ``ov_preprocess_prepostprocessor_build`` | |
+-------------------------------------+-------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Options | Values |
|:--- |:---
| Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1)
| Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx)
| Validated images | The sample uses OpenCV\* to [read input image](https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56) (\*.bmp, \*.png)
| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) |
| Other language realization | [C++](../../../samples/cpp/hello_classification/README.md), [Python](../../python/hello_classification/README.md) |
+----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Options | Values |
+============================+============================================================================================================================================================================+
| Validated Models | :doc:`alexnet <omz_models_model_alexnet>`, :doc:`googlenet-v1 <omz_models_model_googlenet_v1>` |
+----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model Format | Inference Engine Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
+----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Validated images | The sample uses OpenCV\* to `read input image <https://docs.opencv.org/master/d4/da8/group__imgcodecs.html#ga288b8b3da0892bd651fce07b3bbd3a56>`__ (\*.bmp, \*.png) |
+----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Supported devices | :doc:`All <openvino_docs_OV_UG_supported_plugins_Supported_Devices>` |
+----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Other language realization | :doc:`C++ <openvino_inference_engine_samples_hello_classification_README>`, :doc:`Python <openvino_inference_engine_ie_bridges_python_sample_hello_classification_README>` |
+----------------------------+----------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
## How It Works
How It Works
############
Upon the start-up, the sample application reads command line parameters, loads specified network and an image to the Inference Engine plugin.
Then, the sample creates an synchronous inference request object. When inference is done, the application outputs data to the standard output stream.
You can see the explicit description of
each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/integrate_with_your_application.md) section of "Integrate OpenVINO™ Runtime with Your Application" guide.
each sample step at :doc:`Integration Steps <openvino_docs_OV_UG_Integrate_OV_with_your_application>` section of "Integrate OpenVINO™ Runtime with Your Application" guide.
## Building
Building
########
To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in Inference Engine Samples guide.
To build the sample, please use instructions available at :doc:`Build the Sample Applications <openvino_docs_OV_UG_Samples_Overview>` section in Inference Engine Samples guide.
## Running
Running
#######
To run the sample, you need specify a model and image:
- you can use [public](@ref omz_models_group_public) or [Intel's](@ref omz_models_group_intel) pre-trained models from the Open Model Zoo. The models can be downloaded using the [Model Downloader](@ref omz_tools_downloader).
- you can use images from the media files collection available at https://storage.openvinotoolkit.org/data/test_data.
- You can use :doc:`public <omz_models_group_public>` or :doc:`Intel's <omz_models_group_intel>` pre-trained models from the Open Model Zoo. The models can be downloaded using the :doc:`Model Downloader <omz_tools_downloader>`.
- You can use images from the media files collection available at `the storage <https://storage.openvinotoolkit.org/data/test_data>`__.
> **NOTES**:
>
> - By default, OpenVINO™ Toolkit Samples and Demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using the Model Optimizer tool with `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](../../../docs/MO_DG/prepare_model/convert_model/Converting_Model.md).
>
> - Before running the sample with a trained model, make sure the model is converted to the Inference Engine format (\*.xml + \*.bin) using the [Model Optimizer tool](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md).
>
> - The sample accepts models in ONNX format (\*.onnx) that do not require preprocessing.
.. note::
- By default, OpenVINO™ Toolkit Samples and Demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using the Model Optimizer tool with `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of :doc:`Embedding Preprocessing Computation <openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model>`.
- Before running the sample with a trained model, make sure the model is converted to the Inference Engine format (\*.xml + \*.bin) using the :doc:`Model Optimizer tool <openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide>`.
- The sample accepts models in ONNX format (\*.onnx) that do not require preprocessing.
Example
+++++++
### Example
1. Download a pre-trained model using [Model Downloader](@ref omz_tools_downloader):
```
python <path_to_omz_tools>/downloader.py --name alexnet
```
.. code-block:: console
python <path_to_omz_tools>/downloader.py --name alexnet
2. If a model is not in the Inference Engine IR or ONNX format, it must be converted. You can do this using the model converter script:
```
python <path_to_omz_tools>/converter.py --name alexnet
```
.. code-block:: console
python <path_to_omz_tools>/converter.py --name alexnet
3. Perform inference of `car.bmp` using `alexnet` model on a `GPU`, for example:
```
<path_to_sample>/hello_classification_c <path_to_model>/alexnet.xml <path_to_image>/car.bmp GPU
```
3. Perform inference of ``car.bmp`` using ``alexnet`` model on a ``GPU``, for example:
.. code-block:: console
<path_to_sample>/hello_classification_c <path_to_model>/alexnet.xml <path_to_image>/car.bmp GPU
## Sample Output
Sample Output
#############
The application outputs top-10 inference results.
```
Top 10 results:
.. code-block:: console
Top 10 results:
Image /opt/intel/openvino/samples/scripts/car.png
classid probability
------- -----------
656 0.666479
654 0.112940
581 0.068487
874 0.033385
436 0.026132
817 0.016731
675 0.010980
511 0.010592
569 0.008178
717 0.006336
This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool
Image /opt/intel/openvino/samples/scripts/car.png
See Also
########
classid probability
------- -----------
656 0.666479
654 0.112940
581 0.068487
874 0.033385
436 0.026132
817 0.016731
675 0.010980
511 0.010592
569 0.008178
717 0.006336
- :doc:`Integrate OpenVINO™ into Your Application <openvino_docs_OV_UG_Integrate_OV_with_your_application>`
- :doc:`Using OpenVINO™ Samples <openvino_docs_OV_UG_Samples_Overview>`
- :doc:`Model Downloader <omz_tools_downloader>`
- :doc:`Model Optimizer <openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide>`
- :doc:`C API Reference <pot_compression_api_README>`
This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool
```
@endsphinxdirective
## See Also
- [Integrate OpenVINO™ into Your Application](../../../docs/OV_Runtime_UG/integrate_with_your_application.md)
- [Using OpenVINO™ Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md)
- [Model Downloader](@ref omz_tools_downloader)
- [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md)
- [C API Reference](https://docs.openvino.ai/latest/api/api_reference.html)

204
samples/cpp/hello_classification/README.md
View File

@ -1,117 +1,155 @@
# Hello Classification C++ Sample {#openvino_inference_engine_samples_hello_classification_README}
This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API.
@sphinxdirective
This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API.
Models with only one input and output are supported.
The following C++ API is used in the application:
| Feature | API | Description |
| :--- | :--- | :--- |
| OpenVINO Runtime Version | `ov::get_openvino_version` | Get Openvino API version |
| Basic Infer Flow | `ov::Core::read_model`, `ov::Core::compile_model`, `ov::CompiledModel::create_infer_request`, `ov::InferRequest::set_input_tensor`, `ov::InferRequest::get_output_tensor` | Common API to do inference: read and compile a model, create an infer request, configure input and output tensors |
| Synchronous Infer | `ov::InferRequest::infer` | Do synchronous inference |
| Model Operations | `ov::Model::inputs`, `ov::Model::outputs` | Get inputs and outputs of a model |
| Tensor Operations | `ov::Tensor::get_shape` | Get a tensor shape |
| Preprocessing | `ov::preprocess::InputTensorInfo::set_element_type`, `ov::preprocess::InputTensorInfo::set_layout`, `ov::preprocess::InputTensorInfo::set_spatial_static_shape`, `ov::preprocess::PreProcessSteps::resize`, `ov::preprocess::InputModelInfo::set_layout`, `ov::preprocess::OutputTensorInfo::set_element_type`, `ov::preprocess::PrePostProcessor::build` | Set image of the original size as input for a model with other input size. Resize and layout conversions are performed automatically by the corresponding plugin just before inference. |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Feature | API | Description |
+=====================================+================================================================+=========================================================================================================================================================================================+
| OpenVINO Runtime Version | ``ov::get_openvino_version`` | Get Openvino API version |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Basic Infer Flow | ``ov::Core::read_model``, | Common API to do inference: read and compile a model, create an infer request, configure input and output tensors |
| | ``ov::Core::compile_model``, | |
| | ``ov::CompiledModel::create_infer_request``, | |
| | ``ov::InferRequest::set_input_tensor``, | |
| | ``ov::InferRequest::get_output_tensor`` | |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Synchronous Infer | ``ov::InferRequest::infer`` | Do synchronous inference |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model Operations | ``ov::Model::inputs``, | Get inputs and outputs of a model |
| | ``ov::Model::outputs`` | |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Tensor Operations | ``ov::Tensor::get_shape`` | Get a tensor shape |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Preprocessing | ``ov::preprocess::InputTensorInfo::set_element_type``, | Set image of the original size as input for a model with other input size. Resize and layout conversions are performed automatically by the corresponding plugin just before inference. |
| | ``ov::preprocess::InputTensorInfo::set_layout``, | |
| | ``ov::preprocess::InputTensorInfo::set_spatial_static_shape``, | |
| | ``ov::preprocess::PreProcessSteps::resize``, | |
| | ``ov::preprocess::InputModelInfo::set_layout``, | |
| | ``ov::preprocess::OutputTensorInfo::set_element_type``, | |
| | ``ov::preprocess::PrePostProcessor::build`` | |
+-------------------------------------+----------------------------------------------------------------+-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Options | Values |
| :--- | :--- |
| Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1) |
| Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) |
| Other language realization | [C](../../../samples/c/hello_classification/README.md), [Python](../../../samples/python/hello_classification/README.md) |
+-------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Options | Values |
+=====================================+=======================================================================================================================================================================================+
| Validated Models | :doc:`alexnet <omz_models_model_alexnet>`, :doc:`googlenet-v1 <omz_models_model_googlenet_v1>` |
+-------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model Format | OpenVINO™ toolkit Intermediate Representation (\*.xml + \*.bin), ONNX (\*.onnx) |
+-------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Supported devices | :doc:`All <openvino_docs_OV_UG_supported_plugins_Supported_Devices>` |
+-------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Other language realization | :doc:`C <openvino_inference_engine_ie_bridges_c_samples_hello_classification_README>`, :doc:`Python <openvino_inference_engine_ie_bridges_python_sample_hello_classification_README>` |
+-------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
## How It Works
How It Works
############
At startup, the sample application reads command line parameters, prepares input data, loads a specified model and image to the OpenVINO™ Runtime plugin and performs synchronous inference. Then processes output data and write it to a standard output stream.
You can see the explicit description of
each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/integrate_with_your_application.md) section of "Integrate OpenVINO™ Runtime with Your Application" guide.
each sample step at :doc:`Integration Steps <openvino_docs_OV_UG_Integrate_OV_with_your_application>` section of "Integrate OpenVINO™ Runtime with Your Application" guide.
## Building
Building
########
To build the sample, please use instructions available at [Build the Sample Applications](../../../docs/OV_Runtime_UG/Samples_Overview.md) section in OpenVINO™ Toolkit Samples guide.
To build the sample, please use instructions available at :doc:`Build the Sample Applications <openvino_docs_OV_UG_Samples_Overview>` section in OpenVINO™ Toolkit Samples guide.
## Running
Running
#######
```
hello_classification <path_to_model> <path_to_image> <device_name>
```
.. code-block:: console
hello_classification <path_to_model> <path_to_image> <device_name>
To run the sample, you need to specify a model and image:
- You can use [public](@ref omz_models_group_public) or [Intel's](@ref omz_models_group_intel) pre-trained models from the Open Model Zoo. The models can be downloaded using the [Model Downloader](@ref omz_tools_downloader).
- You can use images from the media files collection available at https://storage.openvinotoolkit.org/data/test_data.
> **NOTES**:
>
> - By default, OpenVINO™ Toolkit Samples and Demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using the Model Optimizer tool with `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](../../../docs/MO_DG/prepare_model/convert_model/Converting_Model.md).
>
> - Before running the sample with a trained model, make sure the model is converted to the intermediate representation (IR) format (\*.xml + \*.bin) using the [Model Optimizer tool](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md).
>
> - The sample accepts models in ONNX format (.onnx) that do not require preprocessing.
- You can use :doc:`public <omz_models_group_public>` or :doc:`Intel's <omz_models_group_intel>` pre-trained models from the Open Model Zoo. The models can be downloaded using the :doc:`Model Downloader <omz_tools_downloader>`.
- You can use images from the media files collection available at `the storage <https://storage.openvinotoolkit.org/data/test_data>`__.
### Example
.. note::
- By default, OpenVINO™ Toolkit Samples and Demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using the Model Optimizer tool with ``--reverse_input_channels`` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of :doc:`Embedding Preprocessing Computation <openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model>`.
- Before running the sample with a trained model, make sure the model is converted to the intermediate representation (IR) format (\*.xml + \*.bin) using the :doc:`Model Optimizer tool <openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide>`.
- The sample accepts models in ONNX format (.onnx) that do not require preprocessing.
1. Install the `openvino-dev` Python package to use Open Model Zoo Tools:
```
python -m pip install openvino-dev[caffe]
```
Example
+++++++
1. Install the ``openvino-dev`` Python package to use Open Model Zoo Tools:
.. code-block:: console
python -m pip install openvino-dev[caffe]
2. Download a pre-trained model using:
```
omz_downloader --name googlenet-v1
```
.. code-block:: console
omz_downloader --name googlenet-v1
3. If a model is not in the IR or ONNX format, it must be converted. You can do this using the model converter:
```
omz_converter --name googlenet-v1
```
.. code-block:: console
omz_converter --name googlenet-v1
4. Perform inference of `car.bmp` using the `googlenet-v1` model on a `GPU`, for example:
```
hello_classification googlenet-v1.xml car.bmp GPU
```
4. Perform inference of ``car.bmp`` using the ``googlenet-v1`` model on a ``GPU``, for example:
.. code-block:: console
hello_classification googlenet-v1.xml car.bmp GPU
## Sample Output
Sample Output
#############
The application outputs top-10 inference results.
```
[ INFO ] OpenVINO Runtime version ......... <version>
[ INFO ] Build ........... <build>
[ INFO ]
[ INFO ] Loading model files: /models/googlenet-v1.xml
[ INFO ] model name: GoogleNet
[ INFO ] inputs
[ INFO ] input name: data
[ INFO ] input type: f32
[ INFO ] input shape: {1, 3, 224, 224}
[ INFO ] outputs
[ INFO ] output name: prob
[ INFO ] output type: f32
[ INFO ] output shape: {1, 1000}
.. code-block:: console
[ INFO ] OpenVINO Runtime version ......... <version>
[ INFO ] Build ........... <build>
[ INFO ]
[ INFO ] Loading model files: /models/googlenet-v1.xml
[ INFO ] model name: GoogleNet
[ INFO ] inputs
[ INFO ] input name: data
[ INFO ] input type: f32
[ INFO ] input shape: {1, 3, 224, 224}
[ INFO ] outputs
[ INFO ] output name: prob
[ INFO ] output type: f32
[ INFO ] output shape: {1, 1000}
Top 10 results:
Image /images/car.bmp
classid probability
------- -----------
656 0.8139648
654 0.0550537
468 0.0178375
436 0.0165405
705 0.0111694
817 0.0105820
581 0.0086823
575 0.0077515
734 0.0064468
785 0.0043983
Top 10 results:
See Also
########
Image /images/car.bmp
- :doc:`Integrate the OpenVINO™ Runtime with Your Application <openvino_docs_OV_UG_Integrate_OV_with_your_application>`
- :doc:`Using OpenVINO™ Toolkit Samples <openvino_docs_OV_UG_Samples_Overview>`
- :doc:`Model Downloader <omz_tools_downloader>`
- :doc:`Model Optimizer <openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide>`
classid probability
------- -----------
656 0.8139648
654 0.0550537
468 0.0178375
436 0.0165405
705 0.0111694
817 0.0105820
581 0.0086823
575 0.0077515
734 0.0064468
785 0.0043983
```
@endsphinxdirective
## See Also
- [Integrate the OpenVINO™ Runtime with Your Application](../../../docs/OV_Runtime_UG/integrate_with_your_application.md)
- [Using OpenVINO™ Toolkit Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md)
- [Model Downloader](@ref omz_tools_downloader)
- [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md)

190
samples/python/hello_classification/README.md
View File

@ -1,116 +1,134 @@
# Hello Classification Python* Sample {#openvino_inference_engine_ie_bridges_python_sample_hello_classification_README}
This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API.
@sphinxdirective
This sample demonstrates how to do inference of image classification models using Synchronous Inference Request API.
Models with only 1 input and output are supported.
The following Python API is used in the application:
| Feature | API | Description |
| :---------------- | :--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| Basic Infer Flow | [openvino.runtime.Core], [openvino.runtime.Core.read_model], [openvino.runtime.Core.compile_model] | Common API to do inference |
| Synchronous Infer | [openvino.runtime.CompiledModel.infer_new_request] | Do synchronous inference |
| Model Operations | [openvino.runtime.Model.inputs], [openvino.runtime.Model.outputs] | Managing of model |
| Preprocessing | [openvino.preprocess.PrePostProcessor], [openvino.preprocess.InputTensorInfo.set_element_type],[openvino.preprocess.InputTensorInfo.set_layout],[openvino.preprocess.InputTensorInfo.set_spatial_static_shape],[openvino.preprocess.PreProcessSteps.resize],[openvino.preprocess.InputModelInfo.set_layout],[openvino.preprocess.OutputTensorInfo.set_element_type],[openvino.preprocess.PrePostProcessor.build] | Set image of the original size as input for a model with other input size. Resize and layout conversions will be performed automatically by the corresponding plugin just before inference |
+-----------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Feature | API | Description |
+=============================+===========================================================================================================================================================================================================================================+============================================================================================================================================================================================+
| Basic Infer Flow | `openvino.runtime.Core <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Core.html>`__ , | |
| | `openvino.runtime.Core.read_model <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Core.html#openvino.runtime.Core.read_model>`__ , | |
| | `openvino.runtime.Core.compile_model <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Core.html#openvino.runtime.Core.compile_model>`__ | Common API to do inference |
+-----------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Synchronous Infer | `openvino.runtime.CompiledModel.infer_new_request <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.CompiledModel.html#openvino.runtime.CompiledModel.infer_new_request>`__ | Do synchronous inference |
+-----------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model Operations | `openvino.runtime.Model.inputs <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Model.html#openvino.runtime.Model.inputs>`__ , | Managing of model |
| | `openvino.runtime.Model.outputs <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Model.html#openvino.runtime.Model.outputs>`__ | |
+-----------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Preprocessing | `openvino.preprocess.PrePostProcessor <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.PrePostProcessor.html>`__ , | Set image of the original size as input for a model with other input size. Resize and layout conversions will be performed automatically by the corresponding plugin just before inference |
| | `openvino.preprocess.InputTensorInfo.set_element_type <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputTensorInfo.html#openvino.preprocess.InputTensorInfo.set_element_type>`__ , | |
| | `openvino.preprocess.InputTensorInfo.set_layout <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputTensorInfo.html#openvino.preprocess.InputTensorInfo.set_layout>`__ , | |
| | `openvino.preprocess.InputTensorInfo.set_spatial_static_shape <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputTensorInfo.html#openvino.preprocess.InputTensorInfo.set_spatial_static_shape>`__ , | |
| | `openvino.preprocess.PreProcessSteps.resize <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.PreProcessSteps.html#openvino.preprocess.PreProcessSteps.resize>`__ , | |
| | `openvino.preprocess.InputModelInfo.set_layout <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputModelInfo.html#openvino.preprocess.InputModelInfo.set_layout>`__ , | |
| | `openvino.preprocess.OutputTensorInfo.set_element_type <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.OutputTensorInfo.html#openvino.preprocess.OutputTensorInfo.set_element_type>`__ , | |
| | `openvino.preprocess.PrePostProcessor.build <https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.PrePostProcessor.html#openvino.preprocess.PrePostProcessor.build>`__ | |
+-----------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Options | Values |
| :------------------------- | :------------------------------------------------------------------------------------------------------ |
| Validated Models | [alexnet](@ref omz_models_model_alexnet), [googlenet-v1](@ref omz_models_model_googlenet_v1) |
| Model Format | OpenVINO™ toolkit Intermediate Representation (.xml + .bin), ONNX (.onnx) |
| Supported devices | [All](../../../docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md) |
| Other language realization | [C++](../../../samples/cpp/hello_classification/README.md), [C](../../c/hello_classification/README.md) |
+-----------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Options | Values |
+===================================+===================================================================================================================================================================+
| Validated Models | :doc:`alexnet <omz_models_model_alexnet>`, :doc:`googlenet-v1 <omz_models_model_googlenet_v1>` |
+-----------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Model Format | OpenVINO™ toolkit Intermediate Representation (.xml + .bin), ONNX (.onnx) |
+-----------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Supported devices | :doc:`All <openvino_docs_OV_UG_supported_plugins_Supported_Devices>` |
+-----------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
| Other language realization | :doc:`C++ <openvino_inference_engine_samples_hello_classification_README>`, :doc:`C <openvino_inference_engine_ie_bridges_c_samples_hello_classification_README>` |
+-----------------------------------+-------------------------------------------------------------------------------------------------------------------------------------------------------------------+
## How It Works
How It Works
############
At startup, the sample application reads command-line parameters, prepares input data, loads a specified model and image to the OpenVINO™ Runtime plugin, performs synchronous inference, and processes output data, logging each step in a standard output stream.
You can see the explicit description of
each sample step at [Integration Steps](../../../docs/OV_Runtime_UG/integrate_with_your_application.md) section of "Integrate OpenVINO™ Runtime with Your Application" guide.
You can see the explicit description of each sample step at :doc:`Integration Steps <openvino_docs_OV_UG_Integrate_OV_with_your_application>` section of "Integrate OpenVINO™ Runtime with Your Application" guide.
## Running
Running
#######
```
python hello_classification.py <path_to_model> <path_to_image> <device_name>
```
.. code-block:: console
python hello_classification.py <path_to_model> <path_to_image> <device_name>
To run the sample, you need to specify a model and image:
- You can use [public](@ref omz_models_group_public) or [Intel's](@ref omz_models_group_intel) pre-trained models from the Open Model Zoo. The models can be downloaded using the [Model Downloader](@ref omz_tools_downloader).
- You can use images from the media files collection available at https://storage.openvinotoolkit.org/data/test_data.
> **NOTES**:
>
> - By default, OpenVINO™ Toolkit Samples and demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using the Model Optimizer tool with `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Embedding Preprocessing Computation](../../../docs/MO_DG/prepare_model/convert_model/Converting_Model.md).
>
> - Before running the sample with a trained model, make sure the model is converted to the intermediate representation (IR) format (\*.xml + \*.bin) using the [Model Optimizer tool](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md).
>
> - The sample accepts models in ONNX format (.onnx) that do not require preprocessing.
- You can use :doc:`public <omz_models_group_public>` or :doc:`Intel's <omz_models_group_intel>` pre-trained models from the Open Model Zoo. The models can be downloaded using the :doc:`Model Downloader <omz_tools_downloader>`.
- You can use images from the media files collection available at `the storage <https://storage.openvinotoolkit.org/data/test_data>`__.
### Example
.. note::
- By default, OpenVINO™ Toolkit Samples and demos expect input with BGR channels order. If you trained your model to work with RGB order, you need to manually rearrange the default channels order in the sample or demo application or reconvert your model using the Model Optimizer tool with ``--reverse_input_channels`` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of :doc:`Embedding Preprocessing Computation <openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model>`.
- Before running the sample with a trained model, make sure the model is converted to the intermediate representation (IR) format (\*.xml + \*.bin) using the :doc:`Model Optimizer tool <openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide>`.
- The sample accepts models in ONNX format (.onnx) that do not require preprocessing.
1. Install the `openvino-dev` Python package to use Open Model Zoo Tools:
```
python -m pip install openvino-dev[caffe]
```
Example
+++++++
1. Install the ``openvino-dev`` Python package to use Open Model Zoo Tools:
.. code-block:: console
python -m pip install openvino-dev[caffe]
2. Download a pre-trained model:
```
omz_downloader --name alexnet
```
.. code-block:: console
omz_downloader --name alexnet
3. If a model is not in the IR or ONNX format, it must be converted. You can do this using the model converter:
```
omz_converter --name alexnet
```
.. code-block:: console
omz_converter --name alexnet
4. Perform inference of `banana.jpg` using the `alexnet` model on a `GPU`, for example:
```
python hello_classification.py alexnet.xml banana.jpg GPU
```
4. Perform inference of ``banana.jpg`` using the ``alexnet`` model on a ``GPU``, for example:
.. code-block:: console
python hello_classification.py alexnet.xml banana.jpg GPU
## Sample Output
Sample Output
#############
The sample application logs each step in a standard output stream and outputs top-10 inference results.
```
[ INFO ] Creating OpenVINO Runtime Core
[ INFO ] Reading the model: /models/alexnet/alexnet.xml
[ INFO ] Loading the model to the plugin
[ INFO ] Starting inference in synchronous mode
[ INFO ] Image path: /images/banana.jpg
[ INFO ] Top 10 results:
[ INFO ] class_id probability
[ INFO ] --------------------
[ INFO ] 954 0.9703885
[ INFO ] 666 0.0219518
[ INFO ] 659 0.0033120
[ INFO ] 435 0.0008246
[ INFO ] 809 0.0004433
[ INFO ] 502 0.0003852
[ INFO ] 618 0.0002906
[ INFO ] 910 0.0002848
[ INFO ] 951 0.0002427
[ INFO ] 961 0.0002213
[ INFO ]
[ INFO ] This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool
```
.. code-block:: console
[ INFO ] Creating OpenVINO Runtime Core
[ INFO ] Reading the model: /models/alexnet/alexnet.xml
[ INFO ] Loading the model to the plugin
[ INFO ] Starting inference in synchronous mode
[ INFO ] Image path: /images/banana.jpg
[ INFO ] Top 10 results:
[ INFO ] class_id probability
[ INFO ] --------------------
[ INFO ] 954 0.9703885
[ INFO ] 666 0.0219518
[ INFO ] 659 0.0033120
[ INFO ] 435 0.0008246
[ INFO ] 809 0.0004433
[ INFO ] 502 0.0003852
[ INFO ] 618 0.0002906
[ INFO ] 910 0.0002848
[ INFO ] 951 0.0002427
[ INFO ] 961 0.0002213
[ INFO ]
[ INFO ] This sample is an API example, for any performance measurements please use the dedicated benchmark_app tool
## See Also
See Also
########
- [Integrate the OpenVINO™ Runtime with Your Application](../../../docs/OV_Runtime_UG/integrate_with_your_application.md)
- [Using OpenVINO™ Toolkit Samples](../../../docs/OV_Runtime_UG/Samples_Overview.md)
- [Model Downloader](@ref omz_tools_downloader)
- [Model Optimizer](../../../docs/MO_DG/Deep_Learning_Model_Optimizer_DevGuide.md)
- :doc:`Integrate the OpenVINO™ Runtime with Your Application <openvino_docs_OV_UG_Integrate_OV_with_your_application>`
- :doc:`Using OpenVINO™ Toolkit Samples <openvino_docs_OV_UG_Samples_Overview>`
- :doc:`Model Downloader <omz_tools_downloader>`
- :doc:`Model Optimizer <openvino_docs_MO_DG_Deep_Learning_Model_Optimizer_DevGuide>`
@endsphinxdirective
[openvino.runtime.Core]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Core.html
[openvino.runtime.Core.read_model]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Core.html#openvino.runtime.Core.read_model
[openvino.runtime.Core.compile_model]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Core.html#openvino.runtime.Core.compile_model
[openvino.runtime.CompiledModel.infer_new_request]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.CompiledModel.html#openvino.runtime.CompiledModel.infer_new_request
[openvino.runtime.Model.inputs]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Model.html#openvino.runtime.Model.inputs
[openvino.runtime.Model.outputs]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.runtime.Model.html#openvino.runtime.Model.outputs
[openvino.preprocess.PrePostProcessor]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.PrePostProcessor.html
[openvino.preprocess.InputTensorInfo.set_element_type]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputTensorInfo.html#openvino.preprocess.InputTensorInfo.set_element_type
[openvino.preprocess.InputTensorInfo.set_layout]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputTensorInfo.html#openvino.preprocess.InputTensorInfo.set_layout
[openvino.preprocess.InputTensorInfo.set_spatial_static_shape]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputTensorInfo.html#openvino.preprocess.InputTensorInfo.set_spatial_static_shape
[openvino.preprocess.PreProcessSteps.resize]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.PreProcessSteps.html#openvino.preprocess.PreProcessSteps.resize
[openvino.preprocess.InputModelInfo.set_layout]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.InputModelInfo.html#openvino.preprocess.InputModelInfo.set_layout
[openvino.preprocess.OutputTensorInfo.set_element_type]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.OutputTensorInfo.html#openvino.preprocess.OutputTensorInfo.set_element_type
[openvino.preprocess.PrePostProcessor.build]:https://docs.openvino.ai/2022.3/api/ie_python_api/_autosummary/openvino.preprocess.PrePostProcessor.html#openvino.preprocess.PrePostProcessor.build