doc: review of tensorflow serving README (#2321)

Signed-off-by: David B. Kinder <[email protected]>

Author: dbkinder

docker/tensorflow-serving/README.md

@@ -1,16 +1,16 @@
-# Intel® Extension for TensorFlow* Serving Docker Container Guide
+# Intel® Extension for TensorFlow* Serving - Docker Container Guide
 
 ## Description
 
-This document has instruction for running TensorFlow Serving using Intel® Extension for TensorFlow* in docker container.
+This document has instruction for running TensorFlow Serving using Intel® Extension for TensorFlow* in a Docker container.
 
 ## Build the Docker Image
 
-To build the docker container, enter into [docker/tensorflow-serving](./) folder and follow the below steps.
+To build the docker container, enter into [docker/tensorflow-serving](./) folder and follow these steps.
 
 ### I. Binaries Preparation
 
-Refer to [Install for Tensorflow Serving](../../docs/guide/tensorflow_serving.md) to build Tensorflow Serving binary, and refer to [Install for CPP](../../docs/install/install_for_cpp.md) to build Intel® Extension for TensorFlow* CC library form source. And then package and copy them into ./models/binaries directory.
+Refer to [Install for Tensorflow Serving](../../docs/guide/tensorflow_serving.md) to build the TensorFlow Serving binary, and refer to [Install for CPP](../../docs/install/install_for_cpp.md) to build the Intel® Extension for TensorFlow* CC library from source. Then package and copy these binaries into the `./models/binaries` directory, as shown below.
 
 ```bash
 mkdir -p ./models/binaries
@@ -21,29 +21,29 @@ cp -r <path_to_itex>/bazel-out/k8-opt-ST-*/bin/ itex-bazel-bin/
 tar cvfh itex-bazel-bin.tar itex-bazel-bin/
 cp itex-bazel-bin.tar  ./models/binaries/
 
-# Copy Tensorflow Serving binary
-cp path_to_tensorflow_serving/bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server ./models/binaries/
+# Copy TensorFlow Serving binary
+cp <path_to_tensorflow_serving>/bazel-bin/tensorflow_serving/model_servers/tensorflow_model_server ./models/binaries/
 
 ```
 
 ### II. Build the Container
 
-If you build the container using Intel GPU, make sure you meet below assumptions:
+If you build the container using an Intel GPU, make sure you meet these assumptions:
 
-* Host machine installs Intel GPU.
-* Host machine installs Linux kernel that is compatible with GPU drivers.
-* Host machine has Intel GPU driver.
+* Host machine has an Intel GPU.
+* Host machine uses a Linux kernel that is compatible with GPU drivers.
+* Host machine has a compatible Intel GPU driver installed.
 
 Refer to [Install for GPU](../docs/install/install_for_xpu.md) for detail.
 
-Run the [build.sh](./build.sh) to build target docker image.
+Run the [build.sh](./build.sh), specifying either `gpu` or `cpu` as appropriate, to build the target Docker image.
 ```bash
 ./build.sh [gpu/cpu]
 ```
 
 ## Running the Container
 
-Run following commands to start docker container. You can use `-v` option to mount your local directory into container. To make GPU available in the container, attach the GPU to the container using `--device /dev/dri` option and run the container:
+Run these commands to start the Docker container. You can use the `-v` option to mount your local directory into container. To make a GPU available in the container, attach the GPU to the container using the `--device /dev/dri` option and run the container:
 
 ```
 IMAGE_NAME=intel-extension-for-tensorflow:serving-gpu