Fix document format

Signed-off-by: NZhao Lufan <zhao.lufan30@zte.com.cn>

docs/ReleaseNotes/0.1.0/ReleaseNotes.md

@@ -8,7 +8,7 @@
 ### Model Compiler
 
 1. A new framework which is easy to expand and maintain.
-2. Compilation of models trained from Keras, Tensorflow and Pytorch for better execution on CPU/GPU.
+2. Compilation of models trained from Keras, TensorFlow and PyTorch for better execution on CPU/GPU.
 
 | Training framework | Model format | Target runtime | compiled format |
 | ------------------ | ------------ | -------------- | --------------- |
@@ -16,7 +16,7 @@
 |                    |              | OpenVINO       | IR              |
 |                    |              | TensorRT       | Plan            |
 |                    |              | TF-Lite        | tflite          |
-| TensorFlow         | Ckpt/pb      | Tf Serving     | SavedModel      |
+| TensorFlow         | ckpt/pb      | Tf Serving     | SavedModel      |
 |                    |              | OpenVINO       | IR              |
 |                    |              | TensorRT       | Plan            |
 |                    |              | TF-Lite        | tflite          |
@@ -59,12 +59,12 @@
    | OpenVINO-2020           |                  CPU |
    | TensorRT-6              |                  GPU |
    | TensorRT-7              |                  GPU |
-   | TF Lite-2.1             |         CPU(X86/ARM) |
+   | TF Lite-2.1             |        CPU (X86/ARM) |
 5. Integration of dlib to support ML runtime.
 
 ### Benchmark Test Framework for Deep Learning Model
 
-1. A containalized solution which should automatically execute compiling models, loading runtime and compiled
+1. A containerized solution which should automatically execute compiling models, loading runtime and compiled
    models, starting inference service, then run inference client script, and finally generate testing results.
 2. Supports all the compilers and runtime that can be integrated into Adlik.
 3. Supported output: inference result, inference speed, delay of inference execution.
@@ -75,7 +75,7 @@
 - [The adlik_serving doesn't load the latest version default.](https://github.com/Adlik/Adlik/issues/59)
 - [Readme documentation has no tutorial for compile model.](https://github.com/Adlik/Adlik/issues/99)
 - [Bazel build does not support 2020 OpenVINO.](https://github.com/Adlik/Adlik/issues/82)
-- [The docker images built by ci/docker/build.sh file can not compile openvino model.](https://github.com/Adlik/Adlik/issues/88)
+- [The docker images built by ci/docker/build.sh file can not compile OpenVINO model.](https://github.com/Adlik/Adlik/issues/88)
 - [Readme documentation has no tutorial for compile model.](https://github.com/Adlik/Adlik/issues/99)
 - [If user requests an output which not in model will get null response after prediction.](https://github.com/Adlik/Adlik/issues/108)
-- [Prediction will fail if information in model.pbtxt and model representation not consistent in tensorflowLite runtime.](https://github.com/Adlik/Adlik/issues/136)
+- [Prediction will fail if information in model.pbtxt and model representation not consistent in TensorFlowLite runtime.](https://github.com/Adlik/Adlik/issues/136)