Update Documentation

Update doc to 2019 R2 release

README.md

@@ -15,14 +15,16 @@ So, the logical option was to create a Docker image.
 
 -Docker CE
 
--Openvino TGZ file. Currently using l_openvino_toolkit_p_2019.1.094.tgz. Download from  https://software.intel.com/en-us/openvino-toolkit/choose-download/free-download-linux
+-Openvino TGZ file. Currently using 2019_R2, l_openvino_toolkit_p_2019.2.242.tgz.
 
+-Download from  https://software.intel.com/en-us/openvino-toolkit/choose-download/free-download-linux
 
-The final image is around 4GB but the in between images can make up to 8GB.
+
+The final image is around 3GB but the in between images can make up to 8GB.
 
 ## Instructions
 
-Since Openvino releases are quite frequent (R5 now), I choose to make the dockerfile public instead of the Docker images.
+Since Openvino releases are quite frequent (2019_R2 now), I choose to make the dockerfile public instead of the Docker images.
 You may want to experiment with other tgz Openvino versions.
 
 We have 6 images
@@ -31,17 +33,17 @@ phase1 -- installs the Openvino SDK
 
 phase2 -- downloads the demo_squeezenet_download_conver_run
 
-phase3 -- downloads the ssd, yolov3, humanpose, face motion models and convert them to FP32 and FP16
+phase3 -- downloads the ssd, yolov3, humanpose, face motion, maskrcnn models and convert them to FP32 and FP16
 
 demo   -- reduces space, adds script to run examples
 
-benchmark -- adds different traditional networks
+benchmark -- adds different traditional networks (vgg, resnet, inception)
 
 debug  -- adds debugging tools to the image.
 
 
 
-You need to build phase1 first then phase2, phas3, demo, benchmark and at last debug
+You need to build phase1 first then phase2, phase3, demo, benchmark and at last debug
 ```sh
    bash buildcmd
  ```