Disable Myriad Plugin (#415)

* Disable Myriad Plugin * Changes to MYD documentation * Disable Myriad plugin for OpenVINO source builds * Add back required file plugins.xml
openvinotoolkit · Jan 16, 2023 · bdb9afa · bdb9afa
1 parent 8c7c864
commit bdb9afa
Show file tree

Hide file tree

Showing 11 changed files with 30 additions and 57 deletions.
diff --git a/README.md b/README.md
@@ -14,9 +14,9 @@ This repository contains the source code of **OpenVINO™ integration with Tenso
 This product delivers [OpenVINO™](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) inline optimizations which enhance inferencing performance with minimal code modifications.  **OpenVINO™ integration with TensorFlow accelerates** inference across many AI models on a variety of Intel<sup>®</sup> silicon such as:
 
 - Intel<sup>®</sup> CPUs
-- Intel<sup>®</sup> integrated GPUs
-- Intel<sup>®</sup> Movidius™ Vision Processing Units - referred to as VPU
-- Intel<sup>®</sup> Vision Accelerator Design with 8 Intel Movidius™ MyriadX VPUs - referred to as VAD-M or HDDL
+- Intel<sup>®</sup> integrated and discrete GPUs
+
+Note: Support for Intel Movidius™ MyriadX VPUs is no longer maintained. Consider previous releases for running on Myriad VPUs.
 
 [Note: For maximum performance, efficiency, tooling customization, and hardware control, we recommend the developers to adopt native OpenVINO™ APIs and its runtime.]
 
@@ -33,8 +33,7 @@ Check our [Interactive Installation Table](https://openvinotoolkit.github.io/ope
 
 The **OpenVINO™ integration with TensorFlow** package comes with pre-built libraries of OpenVINO™ version 2022.3.0. The users do not have to install OpenVINO™ separately. This package supports:
 - Intel<sup>®</sup> CPUs
-- Intel<sup>®</sup> integrated GPUs
-- Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs)
+- Intel<sup>®</sup> integrated and discrete GPUs
 
 
         pip3 install -U pip
@@ -46,8 +45,6 @@ For installation instructions on Windows please refer to [**OpenVINO™ integrat
 
 To use Intel<sup>®</sup> integrated GPUs for inference, make sure to install the [Intel® Graphics Compute Runtime for OpenCL™ drivers](https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_linux.html#install-gpu)
 
-To leverage Intel® Vision Accelerator Design with Movidius™ (VAD-M) for inference, install [**OpenVINO™ integration with TensorFlow** alongside the Intel® Distribution of OpenVINO™ Toolkit](./docs/INSTALL.md#install-openvino-integration-with-tensorflow-pypi-release-alongside-the-intel-distribution-of-openvino-toolkit-for-vad-m-support).
-
 For more details on installation please refer to [INSTALL.md](docs/INSTALL.md), and for build from source options please refer to [BUILD.md](docs/BUILD.md)
 
 ## Configuration
@@ -68,11 +65,11 @@ This should produce an output like:
 
         CXX11_ABI flag used for this build: 1
 
-By default, Intel<sup>®</sup> CPU is used to run inference. However, you can change the default option to either Intel<sup>®</sup> integrated GPU or Intel<sup>®</sup> VPU for AI inferencing. Invoke the following function to change the hardware on which inferencing is done.
+By default, Intel<sup>®</sup> CPU is used to run inference. However, you can change the default option to Intel<sup>®</sup> integrated or discrete GPUs (GPU, GPU.0, GPU.1 etc). Invoke the following function to change the hardware on which inferencing is done.
 
     openvino_tensorflow.set_backend('<backend_name>')
 
-Supported backends include 'CPU', 'GPU', 'GPU_FP16', 'MYRIAD', and 'VAD-M'.
+Supported backends include 'CPU', 'GPU', 'GPU_FP16'
 
 To determine what processing units are available on your system for inference, use the following function:
 
@@ -85,7 +82,7 @@ For further performance improvements, it is advised to set the environment varia
 To see what you can do with **OpenVINO™ integration with TensorFlow**, explore the demos located in the [examples](./examples) directory.  
 
 ## Docker Support
-Dockerfiles for Ubuntu* 18.04, Ubuntu* 20.04, and TensorFlow* Serving are provided which can be used to build runtime Docker* images for **OpenVINO™ integration with TensorFlow** on CPU, GPU, VPU, and VAD-M. 
+Dockerfiles for Ubuntu* 18.04, Ubuntu* 20.04, and TensorFlow* Serving are provided which can be used to build runtime Docker* images for **OpenVINO™ integration with TensorFlow** on CPU, GPU.
 For more details see [docker readme](docker/README.md).
 
 ### Prebuilt Images

diff --git a/README_cn.md b/README_cn.md
@@ -15,8 +15,6 @@
 
 - 英特尔<sup>®</sup> CPU
 - 英特尔<sup>®</sup> 集成 GPU
-- 英特尔<sup>®</sup> Movidius™ 视觉处理单元 (VPU)
-- 支持 8 颗英特尔 Movidius™ MyriadX VPU 的英特尔<sup>®</sup> 视觉加速器设计（称作 VAD-M 或 HDDL）
 
 [注：为实现最佳的性能、效率、工具定制和硬件控制，我们建议开发人员使用原生 OpenVINO™ API 及其运行时。]
 
@@ -34,7 +32,6 @@
 **OpenVINO™ integration with TensorFlow** 安装包附带 OpenVINO™ 2022.3.0 版本的预建库，用户无需单独安装 OpenVINO™。该安装包支持：
 - 英特尔<sup>®</sup> CPU
 - 英特尔<sup>®</sup> 集成 GPU
-- 英特尔<sup>®</sup> Movidius™ 视觉处理单元 (VPU)
 
 
         pip3 install -U pip
@@ -45,7 +42,6 @@
 
 如果您想使用Intel<sup>®</sup> 集成显卡进行推理，请确保安装[Intel® Graphics Compute Runtime for OpenCL™ drivers](https://docs.openvino.ai/latest/openvino_docs_install_guides_installing_openvino_linux.html#install-gpu)
 
-如果您想使用支持 Movidius™ (VAD-M)进行推理的英特尔® 视觉加速器设计 (VAD-M) 进行推理，请安装 [**OpenVINO™ integration with TensorFlow** 以及英特尔® OpenVINO™ 工具套件发布版](docs/INSTALL_cn.md#安装-openvino-integration-with-tensorflow-pypi-发布版与独立安装intel-openvino-发布版以支持vad-m)。
 
 更多安装详情，请参阅 [INSTALL.md](docs/INSTALL_cn.md), 更多源构建选项请参阅 [BUILD.md](docs/BUILD_cn.md)
 

diff --git a/docs/INSTALL.md b/docs/INSTALL.md
@@ -9,7 +9,7 @@
 
   ### Install **OpenVINO™ integration with TensorFlow** PyPi release
   * Includes pre-built libraries of OpenVINO™ version 2022.3.0. The users do not have to install OpenVINO™ separately 
-  * Supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs, and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs). No VAD-M support 
+  * Supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated and discrete GPUs
 
         pip3 install -U pip
         pip3 install tensorflow==2.9.3
@@ -19,7 +19,7 @@
 
   ### Install **OpenVINO™ integration with TensorFlow** PyPi release alongside the Intel® Distribution of OpenVINO™ Toolkit for VAD-M Support
   * Compatible with OpenVINO™ version 2022.3.0
-  * Supports Intel<sup>®</sup> Vision Accelerator Design with Movidius™ (VAD-M), it also supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs)
+  * Supports it also supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated and discrete GPUs
   * To use it:
     1. Install tensorflow and openvino-tensorflow packages from PyPi as explained in the section above
     2. Download & install Intel® Distribution of OpenVINO™ Toolkit 2022.3.0 release along with its dependencies from ([https://software.intel.com/en-us/openvino-toolkit/download](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit/download.html)).
@@ -32,7 +32,7 @@
 
   Install **OpenVINO™ integration with TensorFlow** PyPi release
   * Includes pre-built libraries of OpenVINO™ version 2022.3.0. The users do not have to install OpenVINO™ separately 
-  * Supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup>, and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs). No VAD-M support
+  * Supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated and discrete GPUs
 
         pip3 install -U pip
         pip3 install tensorflow==2.9.3
@@ -44,7 +44,7 @@
   Install **OpenVINO™ integration with TensorFlow** PyPi release alongside TensorFlow released in Github
   * TensorFlow wheel for Windows from PyPi does't have all the API symbols enabled which are required for **OpenVINO™ integration with TensorFlow**. User needs to install the TensorFlow wheel from the assets of the Github release page
   * Includes pre-built libraries of OpenVINO™ version 2022.3.0. The users do not have to install OpenVINO™ separately 
-  * Supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs, and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs). No VAD-M support
+  * Supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated and discrete GPUs
 
         pip3.9 install -U pip
         pip3.9 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v2.2.0/tensorflow-2.9.2-cp39-cp39-win_amd64.whl

diff --git a/docs/INSTALL_cn.md b/docs/INSTALL_cn.md
@@ -8,7 +8,7 @@
 
   ### 安装 **OpenVINO™ integration with TensorFlow** PyPi 发布版
   * 包括 Intel<sup>®</sup> OpenVINO™ 2022.3.0 版的预建库，用户无需单独安装 OpenVINO™。
-  * 支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 和 Intel<sup>®</sup> Movidius™ 视觉处理单元 (VPU)，但不支持 VAD-M。
+  * 支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 和
 
         pip3 install -U pip
         pip3 install tensorflow==2.9.3
@@ -18,7 +18,7 @@
 
   ### 安装 **OpenVINO™ integration with TensorFlow** PyPi 发布版与独立安装Intel® OpenVINO™ 发布版以支持VAD-M
     * 兼容 Intel<sup>®</sup> OpenVINO™ 2022.3.0版本
-    * 支持 Intel<sup>®</sup> Movidius™ (VAD-M) 的视觉加速器设计 同时支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU、Intel<sup>®</sup> Movidius™ 视觉处理单元 (VPU)。 
+    * 支持 的视觉加速器设计 同时支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 
     * 使用方法：
     1. 按照上述方法从PyPi安装tensorflow 和 openvino-tensorflow。
     2. 下载安装Intel<sup>®</sup> OpenVINO™ 2022.3.0发布版，一并安装其依赖([https://software.intel.com/en-us/openvino-toolkit/download](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit/download.html))。
@@ -31,7 +31,7 @@
 
   安装 **OpenVINO™ integration with TensorFlow** PyPi 发布版
   * 包括 Intel<sup>®</sup> OpenVINO™ 2022.3.0 版的预建库，用户无需单独安装Intel<sup>®</sup> OpenVINO™ 
-  * 支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 和 Intel<sup>®</sup> Movidius™ 视觉处理单元 (VPU)，但不支持 VAD-M。
+  * 支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 和 
 
         pip3 install -U pip
         pip3 install tensorflow==2.9.3
@@ -43,7 +43,7 @@
   安装 **OpenVINO™ integration with TensorFlow** PyPi 版本与独立安装TensorFlow Github版本
   * 基于Windows 的TensorFlow PyPi 安装版并没有使能 **OpenVINO™ integration with TensorFlow** 需要的所有API。用户需要从Github 发布中安装TensorFlow wheel。
   * 包括 OpenVINO™ 2022.3.0 版的预建库。 用户无需单独安装 Intel<sup>®</sup> OpenVINO™ 。
-  * 支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 和 Intel<sup>®</sup> Movidius™ 视觉处理单元 (VPU)，但不支持 VAD-M。
+  * 支持 Intel<sup>®</sup> CPU、Intel<sup>®</sup> 集成 GPU 和
 
         pip3.9 install -U pip
         pip3.9 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v2.2.0/tensorflow-2.9.2-cp39-cp39-win_amd64.whl

diff --git a/examples/notebooks/OpenVINO_TensorFlow_classification_example.ipynb b/examples/notebooks/OpenVINO_TensorFlow_classification_example.ipynb
@@ -10,6 +10,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "1s7OK7vW3put"
@@ -19,8 +20,7 @@
     "\n",
     "OpenVINO™ integration with TensorFlow is designed for TensorFlow developers who want to get started with OpenVINO™ in their inferencing applications. This product effectively delivers OpenVINO™ inline optimizations which enhance inferencing performance with minimal code modifications. OpenVINO™ integration with TensorFlow accelerates inference across many AI models on a variety of Intel® silicon such as: \n",
     "*   Intel® CPUs\n",
-    "*   Intel® integrated GPUs\n",
-    "*   Intel® Movidius™ Vision Processing Units - referred to as VPU\n",
+    "*   Intel® integrated and discrete GPUs\n",
     "\n",
     "**Overview**\n",
     "\n",

diff --git a/examples/notebooks/OpenVINO_TensorFlow_object_detection_example.ipynb b/examples/notebooks/OpenVINO_TensorFlow_object_detection_example.ipynb
@@ -10,6 +10,7 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "metadata": {
     "id": "atwwZdgc3d3_"
@@ -21,9 +22,7 @@
     "\n",
     "OpenVINO™ integration with TensorFlow is designed for TensorFlow developers who want to get started with OpenVINO™ in their inferencing applications. This product effectively delivers OpenVINO™ inline optimizations which enhance inferencing performance with minimal code modifications. OpenVINO™ integration with TensorFlow accelerates inference across many AI models on a variety of Intel® silicon such as: \n",
     "*   Intel® CPUs\n",
-    "*   Intel® integrated GPUs\n",
-    "*   Intel® Movidius™ Vision Processing Units - referred to as VPU\n",
-    "*   Intel® Vision Accelerator Design with 8 Intel Movidius™ MyriadX VPUs - referred to as VAD-M or HDDL\n",
+    "*   Intel® integrated and discrete GPUs\n",
     "\n",
     "**Overview**\n",
     "\n",

diff --git a/examples/notebooks/OpenVINO_TensorFlow_tfhub_object_detection_example.ipynb b/examples/notebooks/OpenVINO_TensorFlow_tfhub_object_detection_example.ipynb
@@ -17,15 +17,15 @@
    ]
   },
   {
+   "attachments": {},
    "cell_type": "markdown",
    "id": "898d9206",
    "metadata": {},
    "source": [
     "[OpenVINO™ integration with TensorFlow](https://github.com/openvinotoolkit/openvino_tensorflow) is designed for TensorFlow developers who want to get started with [OpenVINO™](https://www.intel.com/content/www/us/en/developer/tools/openvino-toolkit/overview.html) in their inferencing applications. This product delivers OpenVINO™ inline optimizations, which enhance inferencing performance of popular deep learning models with minimal code changes and without any accuracy drop. OpenVINO™ integration with TensorFlow accelerates inference across many AI models on a variety of Intel® silicon such as:\n",
     "\n",
     " - Intel® CPUs\n",
-    " - Intel® integrated GPUs\n",
-    " - Intel® Movidius™ Vision Processing Units - referred to as VPU"
+    " - Intel® integrated and discrete GPUs"
    ]
   },
   {

diff --git a/openvino_tensorflow/CMakeLists.txt b/openvino_tensorflow/CMakeLists.txt
@@ -145,9 +145,6 @@ if (APPLE)
   endif()
 
   set(IE_LIBS_PATH ${OPENVINO_ARTIFACTS_DIR}/runtime/lib/intel64/${CMAKE_BUILD_TYPE})
-  set(IE_LIBS 
-      "${IE_LIBS_PATH}/pcie-ma2x8x.mvcmd" 
-      )
   set(TBB_LIBS ${OPENVINO_ARTIFACTS_DIR}/runtime/3rdparty/tbb/lib/)
   install(FILES ${CMAKE_INSTALL_PREFIX}/../ocm/OCM/${OCM_LIB} DESTINATION "${OVTF_INSTALL_LIB_DIR}")
   install(FILES ${CMAKE_CURRENT_BINARY_DIR}/${TF_CONVERSION_EXTENSIONS_MODULE_NAME}/${TF_CONVERSION_EXTENSIONS_LIB} DESTINATION "${OVTF_INSTALL_LIB_DIR}")
@@ -161,7 +158,6 @@ elseif(WIN32)
   set (IE_LIBS 
       "${IE_LIBS_PATH}/${LIB_PREFIX}openvino_intel_gpu_plugin.${PLUGIN_LIB_EXT}"
       "${IE_LIBS_PATH}/cache.json"
-      "${IE_LIBS_PATH}/pcie-ma2x8x.elf"
      )
   set(TBB_LIBS ${OPENVINO_ARTIFACTS_DIR}/runtime/3rdparty/tbb/bin/)
   install(FILES ${CMAKE_INSTALL_PREFIX}/../ocm/OCM/${CMAKE_BUILD_TYPE}/${OCM_LIB} DESTINATION "${OVTF_INSTALL_LIB_DIR}")
@@ -183,7 +179,6 @@ else()
   set (IE_LIBS 
       "${IE_LIBS_PATH}/${LIB_PREFIX}openvino_intel_gpu_plugin.${PLUGIN_LIB_EXT}"
       "${IE_LIBS_PATH}/cache.json"
-      "${IE_LIBS_PATH}/pcie-ma2x8x.mvcmd" 
      )
   set(TBB_LIBS ${OPENVINO_ARTIFACTS_DIR}/runtime/3rdparty/tbb/lib/)
   install(FILES ${CMAKE_INSTALL_PREFIX}/../ocm/OCM/${OCM_LIB} DESTINATION "${OVTF_INSTALL_LIB_DIR}")
@@ -200,9 +195,7 @@ set (IE_LIBS
     "${IE_LIBS_PATH}/${LIB_PREFIX}openvino_c.${OV_LIB_EXT_DOT}"
     "${IE_LIBS_PATH}/${LIB_PREFIX}openvino_tensorflow_frontend.${OV_LIB_EXT_DOT}"
     "${IE_LIBS_PATH}/${LIB_PREFIX}openvino_intel_cpu_plugin.${PLUGIN_LIB_EXT}"
-    "${IE_LIBS_PATH}/${LIB_PREFIX}openvino_intel_myriad_plugin.${PLUGIN_LIB_EXT}"
-    "${IE_LIBS_PATH}/usb-ma2x8x.mvcmd" 
-    "${IE_LIBS_PATH}/plugins.xml" 
+    "${IE_LIBS_PATH}/plugins.xml"
     )
 
 # Install Openvino and TBB libraries

diff --git a/python/CreatePipWhl.cmake b/python/CreatePipWhl.cmake
@@ -91,10 +91,8 @@ if (PYTHON)
      if (APPLE)
         if(CMAKE_BUILD_TYPE STREQUAL "Debug")
             set(libMKLDNNPluginPath "${CMAKE_CURRENT_BINARY_DIR}/python/openvino_tensorflow/libopenvino_intel_cpu_plugind.so")
-            set(libmyriadPluginPath "${CMAKE_CURRENT_BINARY_DIR}/python/openvino_tensorflow/libopenvino_intel_myriad_plugind.so")
         else()
             set(libMKLDNNPluginPath "${CMAKE_CURRENT_BINARY_DIR}/python/openvino_tensorflow/libopenvino_intel_cpu_plugin.so")
-            set(libmyriadPluginPath "${CMAKE_CURRENT_BINARY_DIR}/python/openvino_tensorflow/libopenvino_intel_myriad_plugin.so")
         endif()
 
         # libMKLDNNPluginPath
@@ -111,14 +109,6 @@ if (PYTHON)
         endif()
 
         # libmyriadPluginPath
-        execute_process(COMMAND
-            install_name_tool -add_rpath
-            @loader_path
-            ${libmyriadPluginPath}
-            RESULT_VARIABLE result
-            ERROR_VARIABLE ERR
-            ERROR_STRIP_TRAILING_WHITESPACE
-        )
         if(${result})
              message(FATAL_ERROR "Cannot add rpath")
         endif()