alexsu52
diff --git a/‎CMakeLists.txt
+10-2 b/‎CMakeLists.txt
+10-2
diff --git a/‎README.md
+34-25 b/‎README.md
+34-25
diff --git a/‎README_cn.md
+96 b/‎README_cn.md
+96
diff --git a/‎build_ov.py
+2-2 b/‎build_ov.py
+2-2
@@ -124,7 +124,11 @@ if (CMAKE_CXX_COMPILER_ID STREQUAL "GNU")
 endif()
 
 if(APPLE)
-    set(LIBNGRAPH "libngraph.dylib")
+    if(CMAKE_BUILD_TYPE STREQUAL "Debug")
+        set(LIBNGRAPH "libngraphd.dylib")
+    else()
+        set(LIBNGRAPH "libngraph.dylib")
+    endif()
 else()
     set(LIBNGRAPH "libngraph.so")
 endif(APPLE)
@@ -170,7 +174,11 @@ message(STATUS "UNIT_TEST_ENABLE:           ${UNIT_TEST_ENABLE}")
 message(STATUS "OPENVINO_ARTIFACTS_DIR:     ${OPENVINO_ARTIFACTS_DIR}")
 message(STATUS "USE_PRE_BUILT_OPENVINO:       ${USE_PRE_BUILT_OPENVINO}")
 message(STATUS "OPENVINO_VERSION: ${OPENVINO_VERSION}")
-if (${OPENVINO_VERSION} MATCHES "2021.3")
+if (${OPENVINO_VERSION} MATCHES "2021.4.1")
+  add_definitions(-DOPENVINO_2021_4_1=1)
+elseif (${OPENVINO_VERSION} MATCHES "2021.4")
+  add_definitions(-DOPENVINO_2021_4=1)
+elseif (${OPENVINO_VERSION} MATCHES "2021.3")
   add_definitions(-DOPENVINO_2021_3=1)
 elseif (${OPENVINO_VERSION} MATCHES "2021.2")
   add_definitions(-DOPENVINO_2021_2=1)
 
@@ -1,46 +1,48 @@
+<p>English | <a href="./README_cn.md">简体中文</a></p>
+
 <p align="center">
   <img src="images/openvino_wbgd.png">
 </p>
 
-# **OpenVINO™ integration with TensorFlow (Preview Release)**
+# **OpenVINO™ integration with TensorFlow**
 
-This repository contains the source code of **OpenVINO™ integration with TensorFlow**, a product that delivers [OpenVINO™](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) inline optimizations and runtime needed for an enhanced level of TensorFlow compatibility. It is designed for developers who want to get started with OpenVINO™ in their inferencing applications to enhance inferencing performance with minimal code modifications. **OpenVINO™ integration with TensorFlow** accelerates inference across many [AI models](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/MODELS.md) on a variety of Intel<sup>®</sup> silicon such as:
+This repository contains the source code of **OpenVINO™ integration with TensorFlow**, designed for TensorFlow* developers who want to get started with [OpenVINO™](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) in their inferencing applications. 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](docs/MODELS.md) 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 as VPU
-- Intel<sup>®</sup> Vision Accelerator Design with 8 Intel Movidius™ MyriadX VPUs - referred as VAD-M or HDDL
+- 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
 
-[Note: For maximum performance, efficiency, tooling customization, and hardware control, we recommend going beyond this component to adopt native OpenVINO™ APIs and its runtime.]
+[Note: For maximum performance, efficiency, tooling customization, and hardware control, we recommend the developers to adopt native OpenVINO™ APIs and its runtime.]
 
 ## Installation
 ### Prerequisites
 
-- Ubuntu 18.04, 20.04
-- Python 3.6, 3.7, or 3.8
-- TensorFlow v2.5.0
+- Ubuntu 18.04, 20.04 or macOS 11.2.3
+- Python* 3.6, 3.7, 3.8 or 3.9
+- TensorFlow* v2.5.1
 
 Check our [Interactive Installation Table](https://openvinotoolkit.github.io/openvino_tensorflow/) for a menu of installation options. The table will help you configure the installation process.
 
-### Install **OpenVINO™ integration with TensorFlow** alongside PyPi TensorFlow
-
-This **OpenVINO™ integration with TensorFlow** package comes with pre-built libraries of OpenVINO™ version 2021.3 meaning you don't have to install OpenVINO™ separately. This package supports:
+The **OpenVINO™ integration with TensorFlow** package comes with pre-built libraries of OpenVINO™ version 2021.4.1. 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)
 
 
-        pip3 install -U pip==21.0.1
-        pip3 install -U tensorflow==2.5.0
-        pip3 install openvino-tensorflow
+        pip3 install pip==21.0.1
+        pip3 install tensorflow==2.5.1
+        pip3 install -U openvino-tensorflow
 
 
-If you want 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/BUILD.md#install-openvino-integration-with-tensorflow-alongside-the-intel-distribution-of-openvino-toolkit).
+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#12-install-openvino-integration-with-tensorflow-alongside-the-intel-distribution-of-openvino-toolkit).
 
-For more details on other modes of installation, please refer to [BUILD.md](docs/BUILD.md)
+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
 
-Once you've installed **OpenVINO™ integration with TensorFlow**, you can use TensorFlow to run inference using a trained model.
+Once you've installed **OpenVINO™ integration with TensorFlow**, you can use TensorFlow* to run inference using a trained model.
+
+For the best results, it is advised to enable [oneDNN Deep Neural Network Library (oneDNN)](https://github.com/oneapi-src/oneDNN) by setting the environment variable `TF_ENABLE_ONEDNN_OPTS=1`.
 
 To see if **OpenVINO™ integration with TensorFlow** is properly installed, run
 
@@ -49,27 +51,31 @@ To see if **OpenVINO™ integration with TensorFlow** is properly installed, run
 
 This should produce an output like:
 
-        TensorFlow version:  2.5.0
-        OpenVINO integration with TensorFlow version: b'0.5.0'
-        OpenVINO version used for this build: b'2021.3'
-        TensorFlow version used for this build: v2.5.0
+        TensorFlow version:  2.5.1
+        OpenVINO integration with TensorFlow version: b'1.0.0'
+        OpenVINO version used for this build: b'2021.4.1'
+        TensorFlow version used for this build: v2.5.1
         CXX11_ABI flag used for this build: 0
-        OpenVINO integration with TensorFlow built with Grappler: False
 
 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.
 
     openvino_tensorflow.set_backend('<backend_name>')
 
-Supported backends include 'CPU', 'GPU', 'MYRIAD', and 'VAD-M'.
+Supported backends include 'CPU', 'GPU', 'GPU_FP16', 'MYRIAD', and 'VAD-M'.
 
 To determine what processing units are available on your system for inference, use the following function:
 
     openvino_tensorflow.list_backends()
-For more API calls and environment variables, see [USAGE.md](https://github.com/openvinotoolkit/openvino_tensorflow/blob/master/docs/USAGE.md).
+For more API calls and environment variables, see [USAGE.md](docs/USAGE.md).
+
+[Note: If a CUDA capable device is present in the system then set the environment variable CUDA_VISIBLE_DEVICES to -1]  
 
 ## Examples
 
-To see what you can do with **OpenVINO™ integration with TensorFlow**, explore the demos located in the [examples](https://github.com/openvinotoolkit/openvino_tensorflow/tree/master/examples) directory.
+To see what you can do with **OpenVINO™ integration with TensorFlow**, explore the demos located in the [examples](./examples) directory.  
+
+## Try it on Intel<sup>®</sup> DevCloud
+Sample tutorials are also hosted on [Intel<sup>®</sup> DevCloud](https://software.intel.com/content/www/us/en/develop/tools/devcloud/edge/build/ovtfoverview.html). The demo applications are implemented using Jupyter Notebooks. You can interactively execute them on Intel<sup>®</sup> DevCloud nodes, compare the results of **OpenVINO™ integration with TensorFlow**, native TensorFlow and OpenVINO™. 
 
 ## License
 **OpenVINO™ integration with TensorFlow** is licensed under [Apache License Version 2.0](LICENSE).
@@ -88,3 +94,6 @@ We welcome community contributions to **OpenVINO™ integration with TensorFlow*
 * Submit a [pull request](https://github.com/openvinotoolkit/openvino_tensorflow/pulls).
 
 We will review your contribution as soon as possible. If any additional fixes or modifications are necessary, we will guide you and provide feedback. Before you make your contribution, make sure you can build **OpenVINO™ integration with TensorFlow** and run all the examples with your fix/patch. If you want to introduce a large feature, create test cases for your feature. Upon our verification of your pull request, we will merge it to the repository provided that the pull request has met the above mentioned requirements and proved acceptable.
+
+---
+\* Other names and brands may be claimed as the property of others.
@@ -0,0 +1,96 @@
+[English](./README.md) | 简体中文
+
+<p align="center">
+  <img src="images/openvino_wbgd.png">
+</p>
+
+# **OpenVINO™ integration with TensorFlow**
+
+该仓库包含 **OpenVINO™ integration with TensorFlow** 的源代码，该产品可提供所需的 [OpenVINO™](https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html) 内联优化和运行时，显著增强对TensorFlow 的兼容性。该产品专为开发人员设计，支持他们将 OpenVINO™ 运用在自己的推理应用，只需稍微修改代码，就可显著增强推理性能。**OpenVINO™ integration with TensorFlow** 可在各种英特尔<sup>®</sup> 芯片上加速AI模型（如下所示） [AI 模型](docs/MODELS_cn.md)的推理速度：
+
+- 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，我们建议使用原生 OpenVINO™ API 及其运行时。]
+
+## 安装
+### 前提条件
+
+- Ubuntu 18.04, 20.04 or macOS 11.2.3
+- Python* 3.6, 3.7, 3.8 or 3.9
+- TensorFlow* v2.5.1
+
+请参阅我们的[交互式安装表](https://openvinotoolkit.github.io/openvino_tensorflow/)，查看安装选项菜单。该表格将引导您完成安装过程。
+
+**OpenVINO™ integration with TensorFlow** 安装包附带 OpenVINO™ 2021.4.1 的预构建库，这意味着您无需单独安装 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 pip==21.0.1
+        pip3 install tensorflow==2.5.1
+        pip3 install -U openvino-tensorflow
+
+
+如果您想使用支持 Movidius™ 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#12-install-openvino-integration-with-tensorflow-alongside-the-intel-distribution-of-openvino-toolkit)。
+
+更多关于其他安装模式的详情，请参阅 [INSTALL.md](docs/INSTALL_cn.md), 更多构建选项请参阅 [BUILD.md](docs/BUILD_cn.md)
+
+## 配置
+
+安装 **OpenVINO™ integration with TensorFlow** 后，您可以在TensorFlow* 上对训练好的模型运行推理操作。
+
+为了获得最佳效果，建议通过设置环境变量 `TF_ENABLE_ONEDNN_OPTS=1` 来启用[oneDNN Deep Neural Network Library (oneDNN)](https://github.com/oneapi-src/oneDNN)。
+
+如要查看 **OpenVINO™ integration with TensorFlow** 是否安装正确，请运行
+
+    python3 -c "import tensorflow as tf; print('TensorFlow version: ',tf.__version__);\
+                import openvino_tensorflow; print(openvino_tensorflow.__version__)"
+
+它会生成以下输出：
+
+        TensorFlow version:  2.5.1
+        OpenVINO integration with TensorFlow version: b'1.0.0'
+        OpenVINO version used for this build: b'2021.4.1'
+        TensorFlow version used for this build: v2.5.1
+        CXX11_ABI flag used for this build: 0
+
+默认情况下，英特尔<sup>®</sup> CPU 用于运行推理。您也可以将默认选项改为英特尔<sup>®</sup> 集成 GPU 或英特尔<sup>®</sup> VPU 来进行 AI 推理。调用以下函数，更改执行推理的硬件。
+
+    openvino_tensorflow.set_backend('<backend_name>')
+
+支持的后端包括‘CPU'、‘GPU'、‘GPU_FP16'、‘MYRIAD’和‘VAD-M'。
+
+如要确定系统上的哪些处理单元用于推理，可使用以下函数：
+
+    openvino_tensorflow.list_backends()
+如欲了解更多 API 调用和环境变量的信息，请查看 [USAGE.md](docs/USAGE_cn.md)。
+
+[注意：如果系统中存在支持 CUDA 的设备，则将环境变量 CUDA_VISIBLE_DEVICES 设置为 -1]
+
+## 示例
+
+如欲了解 **OpenVINO™ integration with TensorFlow** 的具体功能，请查看[示例](./examples)目录中的演示。
+
+示例教程也托管在 [Intel<sup>®</sup> DevCloud for the Edge](https://software.intel.com/content/www/us/en/develop/tools/devcloud/edge/build/ ovtfoverview.html）。 演示应用程序是使用 Jupyter Notebooks 实现的。 您可以在Intel<sup>®</sup> DevCloud 节点上执行它们，比较 **OpenVINO™ integration with TensorFlow** 原生 TensorFlow 和 OpenVINO™ 不同实现方式的性能结果。
+
+## 许可
+**OpenVINO™ integration with TensorFlow** 依照 [Apache 许可版本 2.0](LICENSE)。通过贡献项目，您同意其中包含的许可和版权条款，并根据这些条款发布您的贡献。
+
+## 支持
+
+通过 [GitHub 问题](https://github.com/openvinotoolkit/openvino_tensorflow/issues)提交您的问题、功能请求和漏洞报告。
+
+## 如何贡献
+
+我们欢迎您为 **OpenVINO™ integration with TensorFlow** 做出社区贡献。如您在改进方面有好的想法：
+
+* 请通过 [GitHub 问题](https://github.com/openvinotoolkit/openvino_tensorflow/issues)分享您的建议。
+* 提交 [pull 请求](https://github.com/openvinotoolkit/openvino_tensorflow/pulls)。
+
+我们将以最快的速度审核您的贡献！如果需要进行其他修复或修改，我们将为您提供引导和反馈。贡献之前，请确保您可以构建 **OpenVINO™ integration with TensorFlow** 并运行所有示例和修复/补丁。如果您想推出重要特性，可以创建特性测试案例。您的 pull 请求经过验证之后，我们会将其合并到存储库中，前提是 pull 请求满足上述要求并经过认可。
+---
+\* 其他名称和品牌可能已被声称为他人资产。
@@ -11,7 +11,7 @@
 
 
 def main():
-    openvino_version = "releases/2021/3"
+    openvino_version = "2021.4.1"
     build_dir = 'build_cmake'
     cxx_abi = "1"
     print("openVINO version: ", openvino_version)
@@ -98,4 +98,4 @@ def main():
     # ./build_ovtf.py --use_openvino_from_location /prebuilt/ov/dir/artifacts/openvino
     # cd ..; mkdir ovtf_2; cd ovtf_2
     # git clone https://github.com/openvinotoolkit/openvino_tensorflow.git
-    # ./build_ovtf.py --use_openvino_from_location /prebuilt/ov/dir/artifacts/openvino
+    # ./build_ovtf.py --use_openvino_from_location /prebuilt/ov/dir/artifacts/openvino