Basic Readme for Cifar-10 tutorial scripts

Author: dzakhar

examples/example_cifar10_caffe/README.md

@@ -114,9 +114,9 @@ configuration define and listed in table below. Before compiling application for
 
 |                      Data                              |   MODEL_BIT_DEPTH=8   |  MODEL_BIT_DEPTH=816  |  MODEL_BIT_DEPTH=16  |
 | :----------------------------------------------------: | :-------------------: | :-------------------: | :------------------: |
-| Weights <br/>*.mli_model* and *mli_model_p2 * sections |  33212 bytes          | 33212 bytes           | 66420 bytes          |
-| Activations 1 <br/>*.Zdata * section                   |  32768 bytes          | 65536 bytes           | 65536 bytes          |
-| Activations 2 <br/>*.Ydata * section                   |  8192 bytes           | 16384 bytes           | 16384 bytes          |
+| Weights <br/>*.mli_model* and *mli_model_p2* sections  |  33212 bytes          | 33212 bytes           | 66420 bytes          |
+| Activations 1 <br/>*.Zdata* section                    |  32768 bytes          | 65536 bytes           | 65536 bytes          |
+| Activations 2 <br/>*.Ydata* section                    |  8192 bytes           | 16384 bytes           | 16384 bytes          |
 | Structures <br/>*.mli_data* section                    |  384 bytes            | 384 bytes             | 384 bytes            |
 
 By default, application uses MODEL_BIT_DEPTH=16 mode. Application code size depends on target hardware configuration and compilation flags. MLI Library code is wrapped into mli_lib section.

examples/tutorial_cifar10_caffe_deployment/README.md

@@ -0,0 +1,39 @@
+Model Deployment Tutorial for Caffe and CIFAR-10: Scripts
+==================================================
+
+This folder contains python scripts to reflect deployment process described in the 
+[heading tutorial](https://embarc.org/embarc_mli/doc/build/html/Examples_Tutorials/Examples_Tutorials.html#model-deployment-tutorial-for-caffe-and-cifar-10).
+
+### Requirements
+
+- Python (tested for 3.7 and 2.7)
+- Caffe (Python module must be installed and available in environment)
+- lmdb
+- numpy
+
+### Quick start
+
+Main entry point is ``deployment_main.py`` script. To print available options run:
+
+    python deployment_main.py --help
+
+Caffe standard Cifar-10 tutorial provides tool for CIFAR-10 dataset transformation into LMDB form. User must provide paths to these folders for proper inference time data definition.
+
+    python deployment_main.py --lmdb_data_dir=<Path>
+
+### Structure
+
+``README.md``                    - This File  
+``cifar10_small.prototxt``     - Structure of trained model  
+``cifar10_small.caffemodel.h5``  - Caffe Model with coefficients trained on CIFAR-10 dataset  
+``deployment_main.py``           - Main script  
+``deployment_steps.py``          - Deployment steps implemented in a set of functions  
+``mli_fxtools.py``               - Helper classes for accounting statistics and quantization  
+
+
+### Details
+
+For more information see:
+1. [Model Deployment Tutorial for Caffe and CIFAR-10](https://embarc.org/embarc_mli/doc/build/html/Examples_Tutorials/Examples_Tutorials.html#model-deployment-tutorial-for-caffe-and-cifar-10)
+2. Python code which is well documented
+