AI & Computer Vision (OpenVINO) - CPBR12
5 likes415 views
This document discusses Intel's compiler optimizations. It states that Intel's compilers may optimize Intel microprocessors differently than non-Intel microprocessors. Some optimizations like SSE2, SSE3, and SSSE3 instructions are designed for Intel microprocessors. Intel does not guarantee the availability, functionality, effectiveness of optimizations on non-Intel microprocessors. The document advises checking product guides for specific instruction set coverage. It provides a notice revision date of August 4, 2011.
AI & Computer Vision (OpenVINO) - CPBR12
- 2. Intel’s compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness or any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice. Notice Revision #20110804 2
- 3. Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. No computer system can be absolutely secure. Check with your system manufacturer or retailer or learn more at www.intel.com. Performance estimates were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown." Implementation of these updates may make these results inapplicable to your device or system. Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction. This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps. Any forecasts of goods and services needed for Intel’s operations are provided for discussion purposes only. Intel will have no liability to make any purchase in connection with forecasts published in this document. ARDUINO 101 and the ARDUINO infinity logo are trademarks or registered trademarks of Arduino, LLC. Altera, Arria, the Arria logo, Intel, the Intel logo, Intel Atom, Intel Core, Intel Nervana, Intel Xeon Phi, Movidius, Saffron and Xeon are trademarks of Intel Corporation or its subsidiaries in the U.S. and/or other countries. *Other names and brands may be claimed as the property of others. Copyright 2018 Intel Corporation. 3
- 4. This document contains information on products, services and/or processes in development. All information provided here is subject to change without notice. Contact your Intel representative to obtain the latest forecast, schedule, specifications and roadmaps. Intel technologies’ features and benefits depend on system configuration and may require enabled hardware, software or service activation. Learn more at intel.com, or from the OEM or retailer. No computer system can be absolutely secure. Tests document performance of components on a particular test, in specific systems. Differences in hardware, software, or configuration will affect actual performance. Consult other sources of information to evaluate performance as you consider your purchase. For more complete information about performance and benchmark results, visit http://www.intel.com/performance. Cost reduction scenarios described are intended as examples of how a given Intel-based product, in the specified circumstances and configurations, may affect future costs and provide cost savings. Circumstances will vary. Intel does not guarantee any costs or cost reduction. Statements in this document that refer to Intel’s plans and expectations for the quarter, the year, and the future, are forward-looking statements that involve a number of risks and uncertainties. A detailed discussion of the factors that could affect Intel’s results and plans is included in Intel’s SEC filings, including the annual report on Form 10-K. The products described may contain design defects or errors known as errata which may cause the product to deviate from published specifications. Current characterized errata are available on request. Performance estimates were obtained prior to implementation of recent software patches and firmware updates intended to address exploits referred to as "Spectre" and "Meltdown." Implementation of these updates may make these results inapplicable to your device or system. No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document. Intel does not control or audit third-party benchmark data or the web sites referenced in this document. You should visit the referenced web site and confirm whether referenced data are accurate. Intel, the Intel logo, Pentium, Celeron, Atom, Core, Xeon, Movidius, Saffron and others are trademarks of Intel Corporation in the U.S. and/or other countries. *Other names and brands may be claimed as the property of others. © 2018 Intel Corporation. 4
- 7. 200% growth of information-based products & services by 2020 compared with traditional product & services¹ 62% developers deem IoT ‘very important’ to digital strategies¹ 1. IDC – Digital Transformation Predictions (source) 2. NLC – Cities and Innovation Economy: Perceptions of Local Leaders (source) 3. DataAge 2025, (link) 4. Forbes, December 10, 2017 (link) >55% percentage of all data forecast to be generated by IoT in 2025.³ >$300B annual B2B IoT revenue, led by industrial sector ⁴ 66% of cities have invested in some type of smart city technology² 7
- 10. AnExplosionofDataandSophisticatedanalytics gigabytes per day 1.5 gigabytes per minute gigabytes per minute gigabytes per minute 4020 200
- 11. 1. Amalgamation of analyst data and Intel analysis. 2. IDC FutureScape: Worldwide Internet of Things 2017 Predictions (link) 3. IDC FutureScape: Worldwide Internet of Things 2015 Predictions (link) 50% 45% of data will be stored, analyzed, and acted on at the edge22018 2019 of IoT deployments will be network constrained3 By2020 Average internetuser 1.5GB data/day Smart hospital 3TB data/day Autonomous automobile 4TB data/day Connected airplane 40TB data/day Smart factory 1PB data/day 11 11
- 13. SoftwareEnablement CommonandSeamlessDeveloperExperience Other names and brands may be claimed as the property of others. Workload Accelerators Connectivity 13
- 14. AutonomousVehicles ResponsiveRetail Manufacturing EmergencyResponse Financialservices MachineVision Cities/transportation Publicsector 14
- 15. SmartCameras VideoGateways/NVRs Datacenter/Cloud FPGAsolutionsfromintel CV Intel®MediaSDK, OPENVINOTM Industry’sBroadestMediaandComputerVisionandDeepLearningPortfolio 15
- 16. Today DigitalSecurity&Surveillance 2018+ ScalingtoIndustrial&Retail,EnabledbySWTools OpenVINO™ 16
- 18. DataAnalyticsneedsai Descriptive Analytics Diagnostic Analytics Predictive Analytics Prescriptive Analytics Cognitive Analytics Operational Analytics Advanced Analytics EmergingToday Self-Learning and Completely Automated Enterprise Simulation-Driven Analysis and Decision-Making Foresight What Will Happen, When, and Why Insight What Happened and Why Hindsight What Happened AI Datadeluge COMPUTEbreakthrough Innovationsurge
- 19. Consumer Health Finance Retail Government Energy Transport Industrial Other Smart Assistants Chatbots Search Personalization Augmented Reality Robots Enhanced Diagnostics Drug Discovery Patient Care Research Sensory Aids Algorithmic Trading Fraud Detection Research Personal Finance Risk Mitigation Support Experience Marketing Merchandising Loyalty Supply Chain Security Defense Data Insights Safety & Security Resident Engagement Smarter Cities Oil & Gas Exploration Smart Grid Operational Improvement Conservation Autonomous Cars Automated Trucking Aerospace Shipping Search & Rescue Factory Automation Predictive Maintenance Precision Agriculture Field Automation Advertising Education Gaming Professional & IT Services Telco/Media Sports Source: Intel forecast Aiwilltransform
- 20. Source: Forrester Research – Artificial Intelligence: Fact, Fiction. How Enterprises Can Crush It; What’s Possible for Enterprises in 2017 Aiadoptionisjustbeginning 58% of business and technology professionals said they're researching AI, but only… 12%said they are currently using AI systems. In a recent Forrester Research survey…
- 21. Machinelearning DeepLearning Example Features Detect similarities & anomalies in sea of data Large, diverse dataset Fully-explainable Real-time updates Practical to ‘reverse engineer’ Tabular/limited dataset Good enough accuracy Fully-explainable Difficult problem to ‘reverse engineer’ Large, uniform dataset Highest accuracy Other examples Credit fraud detection Issue and defect triage Predictive maintenance Regression Anomaly detection Feature extraction Image/speech recognition Natural language processing (NLP) Pattern detection MULTIPLEapproachestoAI Anti-Money Laundering Facial recognition Recommendation engine Cognitive Reasoning ANDMore…
- 22. Machine Learning How do you engineer the best features? Machinelearning 𝑁 × 𝑁 Arjun NEURAL NETWORK 𝒇 𝟏, 𝒇 𝟐, … , 𝒇 𝑲 Roundness of face Dist between eyes Nose width Eye socket depth Cheek bone structure Jaw line length …etc. CLASSIFIER ALGORITHM SVM Random Forest Naïve Bayes Decision Trees Logistic Regression Ensemble methods 𝑁 × 𝑁 Arjun DeepLearning How do you guide the model to find the best features?
- 23. Deeplearning:Trainingvs.inference Lots of labeled data! Training Inference Forward Backward Model weights Forward “Bicycle”? “Strawberry” “Bicycle”? Error Human Bicycle Strawberry ?????? Data set size Accuracy Didyouknow? Training requires a very large data set and deep neural network (i.e. many layers) to achieve the highest accuracy in most cases
- 24. Source: ILSVRC ImageNet winning entry classification error rate each year 2010-2016 (Left), https://www.microsoft.com/en-us/research/blog/microsoft-researchers-achieve-new-conversational-speech-recognition-milestone/ (Right)
- 25. Deeplearninginpractice Source: Intel customer engagements Source Data Inferencing Inference within broader application Innovation Cycle Time-to- Solution 15% 15% 23% 15% 15% 8% 8% Experiment with topologies Tune hyper- parameters Document resultsLabel data Load data Augment data Support inference inputs Compute-intensive (Model Training) Labor-intensive Labor-intensive 15% 15% 23% 15% 15% 8% 8% Development Cycle ∞ ∞ AI.Data Processing Decision Process Data Integration & Management Broader ApplicationDeploy RefreshProduction Deployment Data Store Defect detection
- 26. Edge Device ARTIFICIALINTELLIGENCE Platforms Finance Healthcare Energy Industrial Transport Retail Home More… Data Center TOOLKITS App Developers libraries Data Scientists foundation Library Developers * * * * FOR * * * * Hardware IT System Architects Solutions Solution Architects AI Solutions Catalog (Public & Internal) DEEPLEARNINGACCELERATORS Inference DEEPLEARNINGDEPLOYMENT OpenVINO™ † Intel® Movidius™ SDK Open Visual Inference & Neural Network Optimization toolkit for inference deployment on CPU, processor graphics, FPGA & VPU using TF, Caffe* & MXNet* Optimized inference deployment for all Intel® Movidius™ VPUs using TensorFlow* & Caffe* DEEPLEARNINGFRAMEWORKS Now optimized for CPU Optimizations in progress TensorFlow* MXNet* Caffe* BigDL/Spark* Caffe2* PyTorch* PaddlePaddle* DEEPLEARNING Intel® Deep Learning Studio‡ Open-source tool to compress deep learning development cycle MACHINELEARNINGLIBRARIES Python R Distributed • Scikit-learn • Pandas • NumPy • Cart • Random Forest • e1071 • MlLib (on Spark) • Mahout ANALYTICS,MACHINE&DEEPLEARNINGPRIMITIVES Python DAAL MKL-DNN Intel distribution optimized for machine learning Intel® Data Analytics Acceleration Library (for machine learning) Open-source deep neural network functions for CPU, processor graphics DEEPLEARNINGGRAPHCOMPILER Intel® nGraph™ Compiler (Alpha) Open-sourced compiler for deep learning model computations optimized for multiple devices (CPU, GPU, NNP) using multiple frameworks (TF, MXNet, ONNX) AIFOUNDATION A R T I F I C I A l I N T E L L I G E n C e NNP L-1000 * * * * Ai.intel.com † Formerly the Intel® Computer Vision SDK *Other names and brands may be claimed as the property of others. All products, computer systems, dates, and figures are preliminary based on current expectations, and are subject to change without notice.
- 27. 27
- 28. Optimize/ Heterogeneous Inference engine supports multiple devices for heterogeneous flows. (device-level optimization) Prepare Optimize Model optimizer: Converting Optimizing Preparing to inference (device agnostic, generic optimization) Inference Inference engine lightweight API to use in applications for inference. MKL- DNN cl-DNN CPU: Intel® Xeon®/Intel® Core™/Intel Atom® GPU FPGA Myriad™ 2/X DLA Intel® Movidius™ API Train Train a DL model. Currently supports: Caffe* Mxnet* TensorFlow* ONNX* Extend Inference engine supports extensibility and allows custom kernels for various devices. Extensibility C++ Extensibility OpenCL™ Extensibility OpenCL™/TBD Extensibility TBD ApplicationdevelopmentwithOpenVINO™Toolkit
- 29. 29 Inference Engine Simple and unified API for inference across all Intel® architecture Optimized inference on large Intel® architecture hardware targets (CPU/GEN/FPGA) Heterogeneous support allows execution of layers across hardware types Asynchronous execution improves performance Futureproof/scale development for future Intel® architecture processors Inference Engine Common API PluginArchitecture Inference Engine Runtime Intel® Movidius™ API Intel® Movidius™ Myriad™ 2 DLA Intel Integrated Graphics (GPU) CPU: Intel® Xeon®/Intel® Core™/Intel Atom® clDNN Plugin Intel® MKL-DNN Plugin OpenCL™Intrinsics* FPGA Plugin Applications/Service Intel® Arria® 10 FPGA Intel® Movidius™ Plugin
- 30. 30 Choosing the “Right” Hardware Power/Performance Efficiency Varies Running the right workload on the right piece of hardware higher efficiency Hardware acceleration is a must Heterogeneous computing? Tradeoffs Power/performance Price Software flexibility, portability PowerEfficiency Computation Flexibility Dedicated Hardware GPU CPU X1 X10 X100 Vision Processing Efficiency Vision DSPs FPGA
- 31. 31
- 33. 33 Demo available at: https://intel.ly/2IVUMRp Face Access Control Solution
- 34. 34 Internet User Interface Gateway Lock MQTT HTTP Server 1 Application Server 2 Front End MQTT Broker MQTT
- 35. 35
- 36. Learn Develop Share Online tutorials Webinars Student kits Support forums Intel Optimized Frameworks Exclusive access to Intel® AI DevCloud Project showcase opportunities at Intel Developer Mesh Industry & Academic events Comprehensive courseware Hands-on labs Cloud compute Technical Support Teach For developers, students, instructors and startups Intel®AIacademy software.intel.com/ai
- 37. Intel Distribution for OpenVINO: http://software.intel.com/openvino-toolkit OpenVINO OpenSource: http://01.org/openvinotoolkit Implementações de referência: https://intel.ly/2SwRigI OpenVINO Workshop: https://bit.ly/2Eb6k3e 37
- 38. 38