Fix markdown headers (#374)

Headers should be an h1 to resolve to a header on the docs build.

Author: zachgk

CODE_OF_CONDUCT.md

@@ -1,4 +1,5 @@
-## Code of Conduct
+# Code of Conduct
+
 This project has adopted the [Amazon Open Source Code of Conduct](https://aws.github.io/code-of-conduct).
 For more information see the [Code of Conduct FAQ](https://aws.github.io/code-of-conduct-faq) or contact
 [email protected] with any additional questions or comments.

android/pytorch_android/quickdraw_recognition/README.md

@@ -1,4 +1,4 @@
-## DoodleDraw recognition
+# DoodleDraw recognition
 
 Rabbit                     |  Cat                      | banana
 :-------------------------:|:-------------------------:|:-------------------------:

aws/inferentia/README.md

@@ -1,4 +1,4 @@
-## Low cost inference with AWS Inferentia
+# Low cost inference with AWS Inferentia
 
 This demo uses Inf2 instance, read [here](inf1.md) for Inf1 demo.
 

aws/inferentia/inf1.md

@@ -1,4 +1,4 @@
-## Low cost inference with AWS Inferentia
+# Low cost inference with AWS Inferentia
 
 [AWS Inferentia](https://aws.amazon.com/machine-learning/inferentia/) is a high performance machine
 learning inference chip, custom designed by AWS. Amazon EC2 Inf1 instances are powered by AWS

development/multi-engine/performance_numbers.md

@@ -1,4 +1,4 @@
-## Performance Numbers
+# Engine loading Performance Numbers
 
 These numbers were run on a Mac Pro 2019 (2.8 Ghz Intel Core i7)
 

djl-serving/python-mode/stable-diffusion/docs/README.md

@@ -1,4 +1,5 @@
 # djl-serving运行stable diffusion
+
 建议使用docker环境的djl-serving运行stable diffusion，这样能省去很多环境上的配置操作。
 
 ## 拉取djl-serving的镜像

huggingface/inferentia/README.md

@@ -1,4 +1,4 @@
-## Serving Huggingface model with AWS Inferentia
+# Serving Huggingface model with AWS Inferentia
 
 [AWS Inferentia](https://aws.amazon.com/machine-learning/inferentia/) is a high performance machine
 learning inference chip, custom designed by AWS. Amazon EC2 Inf1 instances are powered by AWS

malicious-url-detector/docs/translators.md

@@ -1,4 +1,4 @@
-## Writing the CSV Translator
+# Writing the CSV Translator
 
 Translator classes provide a way to include methods that pre-process input and post-process output during inference. Passing a translator to a model predictor object enables automatic invocation of the logic in these methods.
 The comma separated values (CSV) Translator needs to handle the following: