Trademark symbol update (#89)

* Update BUILD.md

* added TM symbol

* Updated documentation

Co-authored-by: suryasidd <[email protected]>

Author: adamczap

README.md

@@ -10,7 +10,7 @@ This repository contains the source code of **OpenVINO™ integration with Tenso
 - 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
 
-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 going beyond this component to adopt native OpenVINO™ APIs and its runtime.]
 
 ## Installation
 ### Prerequisites
@@ -53,10 +53,10 @@ This should produce an output like:
         OpenVINO integration with TensorFlow version: b'0.5.0'
         OpenVINO version used for this build: b'2021.3'
         TensorFlow version used for this build: v2.4.1
-        CXX11_ABI flag used for this build: 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 inferencing is done on.
+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>')
 

docs/BUILD.md

@@ -8,7 +8,7 @@
 
 ## Use Pre-Built Packages
 
-**OpenVINO™ integration with TensorFlow** has two releases: one build with CXX11_ABI=0 and another built with CXX11_ABI=1.
+**OpenVINO™ integration with TensorFlow** has two releases: one built with CXX11_ABI=0 and another built with CXX11_ABI=1.
 
 Since TensorFlow packages available in [PyPi](https://pypi.org) are built with CXX11_ABI=0 and OpenVINO™ release packages are built with CXX11_ABI=1, binary releases of these packages **cannot be installed together**. Based on your needs, you can choose one of the two available methods:
 
@@ -20,7 +20,7 @@ Since TensorFlow packages available in [PyPi](https://pypi.org) are built with C
 
 ### Install **OpenVINO™ integration with TensorFlow** alongside PyPi TensorFlow
 
-This **OpenVINO™ integration with TensorFlow** package includes pre-built libraries of OpenVINO™ version 2021.3. The users do not have to install OpenVINO™ separately. This package supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs).
+This **OpenVINO™ integration with TensorFlow** package includes pre-built libraries of OpenVINO™ version 2021.3. The users do not have to install OpenVINO™ separately. This package supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs, and Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs).
 
 
         pip3 install -U pip==21.0.1
@@ -29,7 +29,7 @@ This **OpenVINO™ integration with TensorFlow** package includes pre-built libr
 
 ### Install **OpenVINO™ integration with TensorFlow** alongside the Intel® Distribution of OpenVINO™ Toolkit
 
-This **OpenVINO™ integration with TensorFlow** package is currently compatible with OpenVINO™ version 2021.3. This package supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs, Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs) and Intel<sup>®</sup> Vision Accelerator Design with Movidius™ (VAD-M).
+This **OpenVINO™ integration with TensorFlow** package is currently compatible with OpenVINO™ version 2021.3. This package supports Intel<sup>®</sup> CPUs, Intel<sup>®</sup> integrated GPUs, Intel<sup>®</sup> Movidius™ Vision Processing Units (VPUs), and Intel<sup>®</sup> Vision Accelerator Design with Movidius™ (VAD-M).
 
 You can build TensorFlow from source with -D_GLIBCXX_USE_CXX11_ABI=1 or use the following TensorFlow package:
 
@@ -49,23 +49,23 @@ You can build TensorFlow from source with -D_GLIBCXX_USE_CXX11_ABI=1 or use the
 
         pip3.8 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/tensorflow_abi1-2.4.1-cp38-cp38-manylinux2010_x86_64.whl
 
-3. Download & install Intel® Distribution of OpenVINO™ Toolkit 2021.3 release along with its dependencies from ([https://software.intel.com/en-us/openvino-toolkit](https://software.intel.com/en-us/openvino-toolkit)).
+3. Download & install Intel® Distribution of OpenVINO™ Toolkit 2021.3 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)).
 
 4. Initialize the OpenVINO™ environment by running the `setupvars.sh` located in <code>\<openvino\_install\_directory\>\/bin</code> using the command below:
 
         source setupvars.sh
 
 5. Install `openvino-tensorflow`. Based on your Python version, choose the appropriate package below:
 
-        pip3.6 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/openvino_tensorflow_abi1-0.5.0-cp36-cp36m-manylinux2014_x86_64.whl
+        pip3.6 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/openvino_tensorflow_abi1-0.5.0-cp36-cp36m-linux_x86_64.whl
 
         or
 
-        pip3.7 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/openvino_tensorflow_abi1-0.5.0-cp37-cp37m-manylinux2014_x86_64.whl
+        pip3.7 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/openvino_tensorflow_abi1-0.5.0-cp37-cp37m-linux_x86_64.whl
 
         or
 
-        pip3.8 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/openvino_tensorflow_abi1-0.5.0-cp38-cp38-manylinux2014_x86_64.whl
+        pip3.8 install https://github.com/openvinotoolkit/openvino_tensorflow/releases/download/v0.5.0/openvino_tensorflow_abi1-0.5.0-cp38-cp38-linux_x86_64.whl
 
 
 
@@ -79,7 +79,7 @@ You can build TensorFlow from source with -D_GLIBCXX_USE_CXX11_ABI=1 or use the
 
 ## Build From Source
 Clone the `openvino_tensorflow` repository:
-        
+
 ```bash
 $ git clone https://github.com/openvinotoolkit/openvino_tensorflow.git
 $ cd openvino_tensorflow
@@ -102,7 +102,7 @@ Use one of the following build options based on the requirements
 
 2. Pulls compatible prebuilt TF package from PyPi. Uses OpenVINO™ binary.
 
-        python3 build_ovtf.py –use_openvino_from_location=/opt/intel/openvino_2021.3.394/ --cxx11_abi_version=1
+        python3 build_ovtf.py --use_openvino_from_location=/opt/intel/openvino_2021.3.394/ --cxx11_abi_version=1
 
 
 3. Pulls and builds TF and OpenVINO™ from source
@@ -111,15 +111,15 @@ Use one of the following build options based on the requirements
 
 4. Pulls and builds TF from Source. Uses OpenVINO™ binary.
 
-        python3 build_ovtf.py –build_tf_from_source –use_openvino_from_location=/opt/intel/openvino_2021.3.394/ --cxx11_abi_version=1
+        python3 build_ovtf.py --build_tf_from_source --use_openvino_from_location=/opt/intel/openvino_2021.3.394/ --cxx11_abi_version=1
 
-5. Uses pre-built TF from the given location ([refer the Tensorflow build instructions](#tensorflow)). Pulls and builds OpenVINO™ from source. Use this if you need to build OpenVINO-TensorFlow frequently without building TF from source everytime.
+5. Uses pre-built TF from the given location ([refer the Tensorflow build instructions](#tensorflow)). Pulls and builds OpenVINO™ from source. Use this if you need to build **OpenVINO™ integration with TensorFlow** frequently without building TF from source everytime.
 
-        python3 build_ovtf.py –use_tensorflow_from_location=/path/to/tensorflow/build/
+        python3 build_ovtf.py --use_tensorflow_from_location=/path/to/tensorflow/build/
 
 6. Uses prebuilt TF from the given location ([refer the Tensorflow build instructions](#tensorflow)). Uses OpenVINO™ binary. **This is only compatible with ABI1 built TF**.
 
-        python3 build_ovtf.py –use_tensorflow_from_location=/path/to/tensorflow/build/  –use_openvino_from_location=/opt/intel/openvino_2021/ --cxx11_abi_version=1
+        python3 build_ovtf.py --use_tensorflow_from_location=/path/to/tensorflow/build/  --use_openvino_from_location=/opt/intel/openvino_2021/ --cxx11_abi_version=1
 
 Select the `help` option of `build_ovtf.py` script to learn more about various build options.
 
@@ -153,7 +153,8 @@ Test the installation:
 
         python3 test_ovtf.py
 
-This command runs all C++ and Python unit tests from the `openvino_tensorflow` source tree. It also runs various TensorFlow Python tests using OpenVINO.
+This command runs all C++ and Python unit tests from the `openvino_tensorflow` source tree. It also runs various TensorFlow Python tests using OpenVINO™.
+
 ## TensorFlow
 
 TensorFlow can be built from source using `build_tf.py`. The build artifacts can be found under ${PATH_TO_TF_BUILD}/artifacts/
@@ -178,17 +179,15 @@ TensorFlow can be built from source using `build_tf.py`. The build artifacts can
 
         python3 build_tf.py --output_dir=${PATH_TO_TF_BUILD} --tf_version=v2.4.1
 
-## OpenVINO
+## OpenVINO™
 
 OpenVINO™ can be built from source independently using `build_ov.py`
 
-## Docker
+## Build ManyLinux2014 compatible **OpenVINO™ integration with TensorFlow** wheels
 
-### Build ManyLinux2014 compatible **OpenVINO integration with TensorFlow** whls
-
-To build whl files compatible with manylinux2014, use the following commands. The build artifacts will be available in your container's /whl/ folder.
+To build wheel files compatible with manylinux2014, use the following commands. The build artifacts will be available in your container's /whl/ folder.
 
 ```bash
 cd tools/builds/
 docker build --no-cache -t openvino_tensorflow/pip --build-arg OVTF_BRANCH=releases/v0.5.0 . -f Dockerfile.manylinux2014
-```
+```

docs/USAGE.md

@@ -32,7 +32,7 @@ To enable verbose logs of the execution of the full TensorFlow pipeline and plac
 
     openvino_tensorflow.start_logging_placement()
 
-To disbale verbose logs of the execution of the full TensorFlow pipeline and placement stages along with the **OpenVINO™ integration with TensorFlow**, use the following API:
+To disable verbose logs of the execution of the full TensorFlow pipeline and placement stages along with the **OpenVINO™ integration with TensorFlow**, use the following API:
 
     openvino_tensorflow.stop_logging_placement()
 
@@ -44,7 +44,7 @@ To check the CXX11_ABI used to compile **OpenVINO™ integration with TensorFlow
 
     openvino_tensorflow.cxx11_abi_flag()
 
-To disable execution of certain operators on the OpenVINO backend, use the following API to run them on native TensorFlow runtime:
+To disable execution of certain operators on the OpenVINO™ backend, use the following API to run them on native TensorFlow runtime:
 
     openvino_tensorflow.set_disabled_ops(<string_of_operators_separated_by_commas>)
 
@@ -57,7 +57,7 @@ To disable execution of certain operators on the OpenVINO backend, use the follo
 ## Environment Variables
 
 **OPENVINO_TF_DISABLE_DEASSIGN_CLUSTERS:**
-After clusters are formed, some of the clusters may still fall back to native Tensorflow due to some reasons (e.g a cluster is too small, some conditions are not supported by the target device). If this variable is set, clusters will not be dropped and forced to run on OpenVINO backend. This may reduce the performance gain or may lead the execution to crash in some cases.
+After clusters are formed, some of the clusters may still fall back to native Tensorflow due to some reasons (e.g a cluster is too small, some conditions are not supported by the target device). If this variable is set, clusters will not be dropped and forced to run on OpenVINO™ backend. This may reduce the performance gain or may lead the execution to crash in some cases.
 
 Example:
 
@@ -78,7 +78,7 @@ Example:
     OPENVINO_TF_LOG_PLACEMENT="1"
 
 **OPENVINO_TF_BACKEND:**
-Backend device name can be set using this variable. It should be set to CPU, GPU, MYRIAD, or VAD-M.
+Backend device name can be set using this variable. It should be set to "CPU", "GPU", "MYRIAD", or "VAD-M".
 
 Example:
 
@@ -127,7 +127,7 @@ Example:
     OPENVINO_TF_DUMP_CLUSTERS=1
 
 **OPENVINO_TF_DISABLE:**
-Disables OpenVINO Integration if set to 1.
+Disables **OpenVINO™ integration with TensorFlow** if set to 1.
 
 Example: