Merge branch 'openvinotoolkit:master' into master

Author: ieliz

ci/dependencies.yml

@@ -1,6 +1,6 @@
-opencv_linux: '20220223_0602-4.5.5_073'
-opencv_windows: '20220223_0602-4.5.5_073'
-openvino_linux: '2022.1.0.606'
-openvino_windows: '2022.1.0.606'
-wheel_linux: '2022.1.0.dev20220222-6839'
-wheel_windows: '2022.1.0.dev20220222-6839'
+opencv_linux: '20220228_0602-4.5.5_079'
+opencv_windows: '20220228_0602-4.5.5_079'
+openvino_linux: '2022.1.0.612'
+openvino_windows: '2022.1.0.612'
+wheel_linux: '2022.1.0.dev20220228-6910'
+wheel_windows: '2022.1.0.dev20220228-6910'

ci/prepare-documentation.py

@@ -382,6 +382,11 @@ def main():
         title='OMZ Model API OVMS adapter')
     ovms_adapter_element.attrib[XML_ID_ATTRIBUTE] = 'omz_model_api_ovms_adapter'
 
+    model_api_element = add_page(output_root, navindex_element, id='omz_python_model_api',
+        path='demos/common/python/openvino/model_zoo/model_api/README.md',
+        title='OMZ Python Model API')
+    model_api_element.attrib[XML_ID_ATTRIBUTE] = 'omz_python_model_api'
+
     for md_path in all_md_paths:
         if md_path not in documentation_md_paths:
             raise RuntimeError(f'{all_md_paths[md_path]}: '

data/dataset_definitions.yml

@@ -1129,8 +1129,8 @@ datasets:
   - name: WMT_en_ru
     annotation_conversion:
       converter: wmt
-      input_file: wmt19-ru-en.en.spbpe
-      reference_file: wmt19-ru-en.ru.spbpe
+      input_file: WMT/wmt19-ru-en.en.spbpe
+      reference_file: WMT/wmt19-ru-en.ru.spbpe
 
     reader:
       type: annotation_features_extractor
@@ -1149,8 +1149,8 @@ datasets:
   - name: WMT_ru_en
     annotation_conversion:
       converter: wmt
-      input_file: wmt19-ru-en.ru.spbpe
-      reference_file: wmt19-ru-en.en.spbpe
+      input_file: WMT/wmt19-ru-en.ru.spbpe
+      reference_file: WMT/wmt19-ru-en.en.spbpe
 
     reader:
       type: annotation_features_extractor
@@ -1229,8 +1229,8 @@ datasets:
     data_source: gnhk
     annotation_conversion:
       converter: unicode_character_recognition
-      decoding_char_file: gnhk_char_list.txt
-      annotation_file: test_img_id_gt.txt
+      decoding_char_file: gnhk/gnhk.txt
+      annotation_file: gnhk/test_img_id_gt.txt
     annotation: gnhk_recognition.pickle
     dataset_meta: gnhk_recognition.json
 
@@ -1424,15 +1424,15 @@ datasets:
       image_folder: Raw-data/Single-channel/Val
       reconstructed_folder: accuracy_checker_preprocess/Single-channel/Reconstructed
       sampled_folder: accuracy_checker_preprocess/Single-channel/Sampled
-      mask_file: sampling_mask_20perc.npy
-      stats_file: stats_fs_unet_norm_20.npy
+      mask_file: hybrid-cs-model-mri/sampling_mask_20perc.npy
+      stats_file: hybrid-cs-model-mri/stats_fs_unet_norm_20.npy
 
   - name: WikiText_2_raw_gpt2
     annotation: wikitext_2_raw.pickle
     annotation_conversion:
       converter: wikitext2raw
-      vocab_file: gpt2/vocab.json
-      merges_file: gpt2/merges.txt
+      vocab_file: gpt2/gpt2-vocab.json
+      merges_file: gpt2/gpt2-merges.txt
       testing_file: wikitext-2-raw/wiki.test.raw
       max_seq_length: 1024
 

demos/3d_segmentation_demo/python/3d_segmentation_demo.py

@@ -239,7 +239,7 @@ def read_image(test_data_path, data_name, sizes=(128, 128, 128), is_series=True,
 def main():
     args = parse_arguments()
 
-    log.info('OpenVINO Inference Engine')
+    log.info('OpenVINO Runtime')
     log.info('\tbuild: {}'.format(get_version()))
     core = Core()
 

demos/3d_segmentation_demo/python/README.md

@@ -4,18 +4,12 @@ This topic demonstrates how to run the 3D Segmentation Demo, which segments 3D i
 
 ## How It Works
 
-On startup, the demo reads command-line parameters and loads a network and images to the Inference Engine plugin.
+On startup, the demo reads command-line parameters and loads a model and images to OpenVINO™ Runtime plugin.
 
 > **NOTE**: By default, Open Model Zoo 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 demo application or reconvert your model using the Model Optimizer tool with the `--reverse_input_channels` argument specified. For more information about the argument, refer to **When to Reverse Input Channels** section of [Converting a Model Using General Conversion Parameters](https://docs.openvino.ai/latest/openvino_docs_MO_DG_prepare_model_convert_model_Converting_Model.html#general-conversion-parameters).
 
 ## Preparing to Run
 
-The demo dependencies should be installed before run. That can be achieved with the following command:
-
-```sh
-python3 -mpip install --user -r <omz_dir>/demos/3d_segmentation_demo/python/requirements.txt
-```
-
 For demo input image or video files, refer to the section **Media Files Available for Demos** in the [Open Model Zoo Demos Overview](../../README.md).
 The list of models supported by the demo is in `<omz_dir>/demos/3d_segmentation_demo/python/models.lst` file.
 This file can be used as a parameter for [Model Downloader](../../../tools/model_tools/README.md) and Converter to download and, if necessary, convert models to OpenVINO IR format (\*.xml + \*.bin).
@@ -45,11 +39,10 @@ Run the application with the `-h` or `--help` option to see the usage message:
 
 ```
 usage: 3d_segmentation_demo.py [-h] -i PATH_TO_INPUT_DATA -m PATH_TO_MODEL -o
-                               PATH_TO_OUTPUT [-d TARGET_DEVICE]
-                               [-l PATH_TO_EXTENSION] [-nii]
+                               PATH_TO_OUTPUT [-d TARGET_DEVICE] [-nii]
                                [-nthreads NUMBER_THREADS]
-                               [-s [SHAPE [SHAPE ...]]]
-                               [-c PATH_TO_CLDNN_CONFIG]
+                               [-s [SHAPE [SHAPE ...]]] [-ms N1,N2,N3,N4]
+                               [--full_intensities_range]
 
 Options:
   -h, --help            Show this help message and exit.
@@ -65,18 +58,12 @@ Options:
                         Optional. Specify a target device to infer on: CPU, GPU.
                         Use "-d HETERO:<comma separated devices list>" format
                         to specify HETERO plugin.
-  -l PATH_TO_EXTENSION, --path_to_extension PATH_TO_EXTENSION
-                        Required for CPU custom layers. Absolute path to a
-                        shared library with the kernels implementations.
   -nii, --output_nifti  Show output inference results as raw values
   -nthreads NUMBER_THREADS, --number_threads NUMBER_THREADS
                         Optional. Number of threads to use for inference on
                         CPU (including HETERO cases).
   -s [SHAPE [SHAPE ...]], --shape [SHAPE [SHAPE ...]]
                         Optional. Specify shape for a network
-  -c PATH_TO_CLDNN_CONFIG, --path_to_cldnn_config PATH_TO_CLDNN_CONFIG
-                        Required for GPU custom kernels. Absolute path to an
-                        .xml file with the kernels description.
   -ms N1,N2,N3,N4, --mri_sequence N1,N2,N3,N4
                         Optional. Transfer MRI-sequence from dataset order to the network order.
   --full_intensities_range

demos/CMakeLists.txt

@@ -34,11 +34,6 @@ foreach(artifact IN ITEMS ARCHIVE COMPILE_PDB LIBRARY PDB RUNTIME)
     set("CMAKE_${artifact}_OUTPUT_DIRECTORY" "${CMAKE_CURRENT_BINARY_DIR}/${BIN_FOLDER}/$<CONFIG>")
 endforeach()
 
-if(UNIX)
-    string(APPEND CMAKE_LIBRARY_OUTPUT_DIRECTORY "/lib")
-    string(APPEND CMAKE_ARCHIVE_OUTPUT_DIRECTORY "/lib")
-endif()
-
 if(WIN32)
     if(NOT "${CMAKE_SIZEOF_VOID_P}" EQUAL "8")
         message(FATAL_ERROR "Only 64-bit supported on Windows")
@@ -134,8 +129,8 @@ macro(add_demo)
         target_include_directories(${OMZ_DEMO_NAME} PRIVATE ${OMZ_DEMO_INCLUDE_DIRECTORIES})
     endif()
 
-    target_link_libraries(${OMZ_DEMO_NAME} PRIVATE ${OpenCV_LIBRARIES} openvino::runtime ${InferenceEngine_LIBRARIES}
-                                                    ${OMZ_DEMO_DEPENDENCIES} ngraph::ngraph utils gflags)
+    target_link_libraries(${OMZ_DEMO_NAME} PRIVATE ${OpenCV_LIBRARIES} openvino::runtime
+                                                    ${OMZ_DEMO_DEPENDENCIES} utils gflags)
 
     if(UNIX)
         target_link_libraries(${OMZ_DEMO_NAME} PRIVATE pthread)
@@ -144,9 +139,6 @@ endmacro()
 
 find_package(OpenCV REQUIRED COMPONENTS core highgui videoio imgproc imgcodecs gapi)
 find_package(OpenVINO REQUIRED COMPONENTS Runtime)
-# TODO: remove InferenceEngine and ngraph after 2022.1
-find_package(InferenceEngine REQUIRED)
-find_package(ngraph REQUIRED)
 
 add_subdirectory(thirdparty/gflags)
 add_subdirectory(common/cpp)

demos/README.md

@@ -1,5 +1,6 @@
 # Open Model Zoo Demos
 
+<!--
 @sphinxdirective
 
 .. toctree::
@@ -9,19 +10,25 @@
    omz_demos_human_pose_estimation_3d_demo_python
    omz_demos_3d_segmentation_demo_python
    omz_demos_action_recognition_demo_python
+   omz_demos_background_subtraction_demo_cpp_gapi
+   omz_demos_background_subtraction_demo_python
    omz_demos_bert_named_entity_recognition_demo_python
    omz_demos_bert_question_answering_embedding_demo_python
    omz_demos_bert_question_answering_demo_python
-   omz_demos_classification_demo_cpp
+   omz_demos_classification_benchmark_demo_cpp
+   omz_demos_classification_demo_python
    omz_demos_colorization_demo_python
    omz_demos_crossroad_camera_demo_cpp
+   omz_demos_face_detection_mtcnn_demo_cpp_gapi
    omz_demos_face_detection_mtcnn_demo_python
    omz_demos_face_recognition_demo_python
    omz_demos_formula_recognition_demo_python
    omz_demos_gaze_estimation_demo_cpp_gapi
    omz_demos_interactive_face_detection_demo_cpp_gapi
    omz_demos_gaze_estimation_demo_cpp
+   omz_demos_gesture_recognition_demo_cpp_gapi
    omz_demos_gesture_recognition_demo_python
+   omz_demos_gpt2_text_prediction_demo_python
    omz_demos_handwritten_text_recognition_demo_python
    omz_demos_human_pose_estimation_demo_cpp
    omz_demos_human_pose_estimation_demo_python
@@ -36,22 +43,28 @@
    omz_demos_interactive_face_detection_demo_cpp
    omz_demos_machine_translation_demo_python
    omz_demos_monodepth_demo_python
+   omz_demos_mri_reconstruction_demo_cpp
+   omz_demos_mri_reconstruction_demo_python
    omz_demos_multi_camera_multi_target_tracking_demo_python
    omz_demos_multi_channel_face_detection_demo_cpp
    omz_demos_multi_channel_human_pose_estimation_demo_cpp
    omz_demos_multi_channel_object_detection_demo_yolov3_cpp
+   omz_demos_noise_suppression_demo_cpp
    omz_demos_noise_suppression_demo_python
    omz_demos_object_detection_demo_cpp
    omz_demos_object_detection_demo_python
    omz_demos_pedestrian_tracker_demo_cpp
    omz_demos_place_recognition_demo_python
    omz_demos_security_barrier_camera_demo_cpp
    omz_demos_single_human_pose_estimation_demo_python
+   omz_demos_smartlab_demo_python
    omz_demos_smart_classroom_demo_cpp
+   omz_demos_smart_classroom_demo_cpp_gapi
    omz_demos_social_distance_demo_cpp
    omz_demos_sound_classification_demo_python
    omz_demos_speech_recognition_deepspeech_demo_python
    omz_demos_speech_recognition_quartznet_demo_python
+   omz_demos_speech_recognition_wav2vec_demo_python
    omz_demos_mask_rcnn_demo_cpp
    omz_demos_text_detection_demo_cpp
    omz_demos_text_spotting_demo_python
@@ -60,6 +73,7 @@
    omz_demos_whiteboard_inpainting_demo_python
 
 @endsphinxdirective
+-->
 
 The Open Model Zoo demo applications are console applications that provide robust application templates to help you implement specific deep learning scenarios. These applications involve increasingly complex processing pipelines that gather analysis data from several models that run inference simultaneously, such as detecting a person in a video stream along with detecting the person's physical attributes, such as age, gender, and emotional state
 
@@ -137,7 +151,7 @@ The Open Model Zoo includes the following demos:
 - [Text Detection C++ Demo](./text_detection_demo/cpp/README.md) - Text Detection demo. It detects and recognizes multi-oriented scene text on an input image and puts a bounding box around detected area.
 - [Text Spotting Python\* Demo](./text_spotting_demo/python/README.md) - The demo demonstrates how to run Text Spotting models.
 - [Text-to-speech Python\* Demo](./text_to_speech_demo/python/README.md) - Shows an example of using Forward Tacotron and WaveRNN neural networks for text to speech task.
-- [Time Series Forecasting Python\* Demo](./time_series_forecasting_demo/python/README.md) - The demo shows how to use the OpenVINO™ toolkit to time series forecastig.
+- [Time Series Forecasting Python\* Demo](./time_series_forecasting_demo/python/README.md) - The demo shows how to use the OpenVINO™ toolkit to time series forecasting.
 - [Whiteboard Inpainting Python\* Demo](./whiteboard_inpainting_demo/python/README.md) - The demo shows how to use the OpenVINO™ toolkit to detect and hide a person on a video so that all text on a whiteboard is visible.
 
 ## Media Files Available for Demos
@@ -272,37 +286,17 @@ cmake -A x64 <open_model_zoo>/demos
   cmake --build . --config Debug
   ```
 
-### <a name="model_api_installation"></a>Python\* model API installation
+### <a name="python_requirements"></a>Dependencies for Python* Demos
 
-Python Model API with model wrappers and pipelines can be installed as a part of OpenVINO&trade; toolkit or from source.
-Installation from source is as follows:
-
-1. Install Python (version 3.6 or higher), [setuptools](https://pypi.org/project/setuptools/):
-
-2. Build the wheel with the following command:
+The dependencies for Python demos must be installed before running. It can be achieved with the following command:
 
 ```sh
-python <omz_dir>/demos/common/python/setup.py bdist_wheel
+python -mpip install --user -r <omz_dir>/demos/requirements.txt
 ```
-The built wheel should appear in the dist folder;
-Name example: `openmodelzoo_modelapi-0.0.0-py3-none-any.whl`
 
-3. Install the package in the clean environment with `--force-reinstall` key:
-```sh
-python -m pip install openmodelzoo_modelapi-0.0.0-py3-none-any.whl --force-reinstall
-```
-Alternatively, instead of building the wheel you can use the following command inside  `<omz_dir>/demos/common/python/` directory to build and install the package:
-```sh
-python -m pip install .
-```
-
-When the model API package is installed, you can import it as follows:
-```sh
-python -c "from openvino.model_zoo import model_api"
-```
+### <a name="python_model_api"></a>Python\* model API package
 
-> **NOTE**: On Linux and macOS, you may need to type `python3` instead of `python`. You may also need to [install pip](https://pip.pypa.io/en/stable/installation/).
-> For example, on Ubuntu execute the following command to get pip installed: `sudo apt install python3-pip`.
+To run Python demo applications, you need to install the Python* Model API package. Refer to [Python* Model API documentation](common/python/openvino/model_zoo/model_api/README.md#installing-python*-model-api-package) to learn about its installation.
 
 ### <a name="build_python_extensions"></a>Build the Native Python\* Extension Modules
 
@@ -383,7 +377,7 @@ set up the `PYTHONPATH` environment variable as follows, where `<bin_dir>` is th
 the built demo applications:
 
 ```sh
-export PYTHONPATH="$PYTHONPATH:<bin_dir>/lib"
+export PYTHONPATH="<bin_dir>:$PYTHONPATH"
 ```
 
 You are ready to run the demo applications. To learn about how to run a particular
@@ -409,7 +403,7 @@ set up the `PYTHONPATH` environment variable as follows, where `<bin_dir>` is th
 the built demo applications:
 
 ```bat
-set PYTHONPATH=%PYTHONPATH%;<bin_dir>
+set PYTHONPATH=<bin_dir>;%PYTHONPATH%
 ```
 
 To debug or run the demos on Windows in Microsoft Visual Studio, make sure you

demos/action_recognition_demo/python/README.md

@@ -17,17 +17,17 @@ Every step implements `PipelineStep` interface by creating a class derived from
 
 * `DataStep` reads frames from the input video.
 *  Model step depends on architecture type:
-    - For encder-decoder models there are two steps:
+    - For encoder-decoder models there are two steps:
       -  `EncoderStep` preprocesses a frame and feeds it to the encoder model to produce a frame embedding. Simple averaging of encoder's outputs over a time window is applied.
       -  `DecoderStep` feeds embeddings produced by the `EncoderStep` to the decoder model and produces predictions. For models that use `DummyDecoder`, simple averaging of encoder's outputs over a time window is applied.
     - For the specific implemented single models, the corresponding `<ModelNameStep>` does preprocessing and produces predictions.
 * `RenderStep` renders prediction results.
 
-Pipeline steps are composed in `AsyncPipeline`. Every step can be run in separate thread by adding it to the pipeline with `parallel=True` option.
+Pipeline steps are composed in `AsyncPipeline`. Every step can be run in a separate thread by adding it to the pipeline with `parallel=True` option.
 When two consequent steps occur in separate threads, they communicate via message queue (for example, deliver step result or stop signal).
 
-To ensure maximum performance, Inference Engine models are wrapped in `AsyncWrapper`
-that uses Inference Engine async API by scheduling infer requests in cyclical order
+To ensure maximum performance, models are wrapped in `AsyncWrapper`
+that uses Asynchronous Inference Request API by scheduling infer requests in cyclical order
 (inference on every new input is started asynchronously, result of the longest working infer request is returned).
 You can change the value of `num_requests` in `action_recognition_demo.py` to find an optimal number of parallel working infer requests for your inference accelerators
 (Intel(R) Neural Compute Stick devices and GPUs benefit from higher number of infer requests).

demos/action_recognition_demo/python/action_recognition_demo.py

@@ -83,7 +83,7 @@ def main():
     else:
         labels = None
 
-    log.info('OpenVINO Inference Engine')
+    log.info('OpenVINO Runtime')
     log.info('\tbuild: {}'.format(get_version()))
     core = Core()
 

demos/background_subtraction_demo/cpp_gapi/README.md

@@ -59,9 +59,8 @@ omz_converter --list models.lst
 Run the application with the `-h` option to see the following usage message:
 
 ```
-[ INFO ] OpenVINO Inference Engine
-[ INFO ]        version: <version>
-[ INFO ]        build: <number>
+[ INFO ] OpenVINO Runtime version ......... <version>
+[ INFO ] Build ........... <build>
 
 background_subtraction_demo_gapi [OPTION]
 Options: