Merge pull request #68 from csdingbin/refine

Refine By Jian

Author: Jian-Zhang

README.md

@@ -16,19 +16,15 @@ Making AI Easier: It automates provides simplified toolkits for data processing,
 
 Making AI more accessible:  Through built-in optimized, parameterized models generated by smart democratization advisor and domain-specific, neural architected search (NAS) based network constructure, it brings complex DL to commodity HW, everyone can easily access AI on existing CPU clusters without the need to be an expert on data engineering and data science. 
 
-## This solution is intended for…
+## This solution is intended for
 
-* Citizen Data Scientists will get access to a broad range of models with simplified, click to run E2E AI pipeline workflows. They can construct models using the neural architecture search rather than developing from scratch.
-* Enterprise users can get optimized performance on CPU with simplified click to run workflow covering every stage of AI. 
-* For independent software vendor, the optimized AI workflows can help to expand their AI portfolio and optimized End to End Pipeline reduced time to market. 
-* For cloud service providers, they can use the neural network Constructor’s NAS feature to improve model performance and reduce search cost.
+This solution is intended for citizen data scientists, enterprise users, independent software vendor and partial of cloud service provider.
 
 ## Papers and Blogs
 * [ICYMI – SigOpt Summit Recap Democratizing End-to-End Recommendation Systems](https://sigopt.com/blog/icymi-sigopt-summit-recap-democratizing-end-to-end-recommendation-systems-with-jian-zhang/)
 * [The SigOpt Intelligent Experimentation Platform](https://www.intel.com/content/www/us/en/developer/articles/technical/sigopt-intelligent-experimentation-platform.html#gs.gz2ls6)
 * [SDC2022 - Data Platform for End-to-end AI Democratization](https://storagedeveloper.org/events/sdc-2022/agenda/session/326)
 * [SIHG4SR: Side Information Heterogeneous Graph for Session Recommender](https://dl.acm.org/doi/abs/10.1145/3556702.3556852)
-* DeNas(link provided later)
 
 
 # ARCHITECTURE
@@ -42,7 +38,7 @@ Intel® End-to-End AI Optimization Kit is a composable toolkits for E2E AI optim
 
 * [Smart Democratization advisor (SDA)](e2eAIOK/SDA/README.md): A user-guided tool to facilitate automation of built-in model democratization via parameterized models, it generates yaml files based on user choice, provided build-in intelligence through parameterized models and leverage SigOpt for HPO. SDA converts the manual model tuning and optimization to assisted autoML and autoHPO. SDA provides a list of build-in optimized models ranging from RecSys, CV, NLP, ASR and RL. 
 
-* [Neural network constructor](#): A neural architecture search technology based on component to build compact neural network models for specific domains directly. It is a multi-model, hardware aware, train-free neural architecture search approach to build models for CV, NLP, ASR directly and leverage transfer learning model adaptor to deploy the models in user’s production environment. 
+* [Neural network constructor]: A neural architecture search technology based on component to build compact neural network models for specific domains directly. It is a multi-model, hardware aware, train-free neural architecture search approach to build models for CV, NLP, ASR directly and leverage transfer learning model adaptor to deploy the models in user’s production environment. 
 
 For more information, you may [read the docs]().
 ![Architecture](./docs/source/aiok_workflow.png). 
@@ -69,7 +65,7 @@ cd e2eAIOK; python scripts/start_e2eaiok_docker.py --backend [pytorch, tensorflo
 
 
 ## Performance 
-![Performance](./docs/source/Performance.jpg "Intel® End-to-End AI Optimization Kit Performance"). 
+![Performance](./docs/source/Performance.png "Intel® End-to-End AI Optimization Kit Performance"). 
 
 
 ## Getting Support

docs/source/Architecture.jpg

@@ -1,6 +1,6 @@
 import sys
-from e2eAIOK import SDA
-from e2eAIOK.utils.hydromodel import HydroModel
+from AIDK import SDA
+from AIDK.hydroai.hydromodel import HydroModel
 
 
 def main(input_args):

docs/source/Architecture.png

@@ -11,7 +11,7 @@
 # Quick Start
 ## Enviroment Setup
 * Firstly, ensure that intel oneapi-hpckit is installed on server.
-* Secondly, enter AIOK repo directory.
+* Secondly, enter AIDK repo directory.
 * Thirdly, start the jupyter notebook service.
 
 ``` bash

docs/source/Performance.jpg

@@ -1,4 +1,4 @@
-AIOK Performance Test Guide
+AIDK Performance Test Guide
 
 * How to perform test