README.md

Intel® Edge AI for IoT Developers Nanodegree Program

N.B.: Please don't use the assignment and quiz solution. Try to solve the problem by yourself.

Leverage the Intel® Distribution of OpenVINO™ Toolkit to fast-track development of high-performance computer vision and deep learning inference applications, and run pre-trained deep learning models for computer vision on-premise. You will identify key hardware specifications of various hardware types (CPU, VPU, FPGA, and Integrated GPU), and utilize the Intel® DevCloud for the Edge to test model performance on the various hardware types. Finally, you will use software tools to optimize deep learning models to improve performance of Edge AI systems. - Source

Requirements

• 64-bit operating system that has 6th or newer generation of Intel processor running either Windows 10, Ubuntu 18.04.3 LTS, or macOS 10.13 or higher.
• Installing OpenVINO (version 2020.1)
• Installing Intel's Deep Learning Workbench (version 2020.1)
• Installing Intel's VTune Amplifier

Core Curriculum

1. Welcome to the Program

Lesson-1: Nanodegree Program Introduction

No	Lesson	Notes	Link/Source
1	Welcome to Udacity	Welcome note, Technology evolution	------/------
2	Welcome to the Nanodegree Program Experience	Udacity mentor supprot, Helping tools	------/------
3	How to Succeed	Introduction of instructor, Goals (short or long term), Accountability, Learning strategies, Technical advice	------/------
4	Welcome to Intel® Edge AI for IoT Developers	Design, test, and deploy an edge AI application	------/------
5	Prerequisites & Other Requirements	Python, Training and deploying deep learning models, Draining and deploying deep learning models, CLI, OpenCV	------/------
6	Notebooks and Workspaces	Jupyter Notebooks, Jupyter Graffiti	------/------
7	Graffiti Tutorial	Graffiti Tutorial	------/------

2. Edge AI Fundamentals with OpenVINO

Lesson-1: Introduction to AI at the Edge

No	Lesson	Notes	Link/Source
1	Instructor Intro	Instructor pathway & introduction	------/------
2	What is AI at the Edge?	Edge means local (or near local) processing, Less impact on a network	------/------
3	Why is AI at the Edge Important?	Network communication, Real-time processing, Sensitive data, Optimization software	------/------
4	Applications of AI at the Edge	Endless possibilities, IoT devices, Self driving, Animal tracking	------/------
5	Historical Context	Historical background edge application	[1]
6	Course Structure	Pre-trained models, Model optimizer, Inference engine, Deploying at the edge(handling input streams, processing model outputs, MQTT)	[2]
7	Why Are the Topics Distinct?	Train a model->Model optimizer->IR format->Inference engine->Edge application	------/------
8	Relevant Tools and Prerequisites	Basics of computer vision and how AI models, Python or C++, Hardware & software requiremnts	[3 - 5]
9	What You Will Build	Build and deploy a People Counter App at the Edge	------/------
10	Recap	Basics of the edge, Importance of the edge and its history, Edge application	------/------

Lesson-2: Leveraging Pre-Trained Models

No	Lesson	Notes	Link/Source
1	Introduction	Lesson objective	------/------
2	The OpenVINO™ Toolkit	An open source library useful for edge deployment due to its performance maximizations and pre-trained models	------/------
3	Pre-Trained Models in OpenVINO™	Model Zoo, in which the Free Model Set contains pre-trained models already converted using the Model Optimize	[6]
4	Types of Computer Vision Models	Classification, Detection, and Segmentation etc.	[7]
5	Case Studies in Computer Vision	SSD, ResNet and MobileNet	------/------
6	Available Pre-Trained Models in OpenVINO™	Public Model Set, Free Model Set	[6]
7	Exercise: Loading Pre-Trained Models	Find the Right Models, Download the Models, Verify the Downloads	------/------
8	Solution: Loading Pre-Trained Models	Choosing Models, Downloading Models, Verifying Downloads	------/------
9	Optimizations on the Pre-Trained Models	Dealt with different precisions of the different models	------/------
10	Choosing the Right Model for Your App	Try out different models for the application and a single use case	------/------
11	Pre-processing Inputs	Check out in any related documentation, Check color chanel, Input and output parameters	------/------
12	Exercise: Pre-processing Inputs	Build preprocess_input file for processing the inputs parameters	------/------
13	Solution: Pre-processing Inputs	Solution of pre-processing inputs	------/------
14	Handling Network Outputs	Try out different models for the application and a single use case	[8 - 9]
15	Running Your First Edge App	Load a pre-trained model into the Inference Engine, as well as call for functions to preprocess and handle the output in the appropriate locations	------/------
16	Exercise: Deploy An App at the Edge	Implement the handling of the outputs of our three models	------/------
17	Solution: Deploy An App at the Edge	Car Meta Model, Pose Estimation, Text Detection Model Output Handling	------/------
18	Recap	Basics of the Intel® Distribution of OpenVINO™ Toolkit, Different CV model types, Available Pre-Trained Model, Choosing the right Pre-Trained Model	------/------
19	Lesson Glossary	Basics of the edge, Importance of the edge and its history, Edge application	------/------

Lesson-3: The Model Optimizer

No	Lesson	Notes	Link/Source
1	Introduction	Basics of the Model Optimizer, Optimization techniques & impact, Supported Frameworks, Custom layers	------/------
2	The Model Optimizer	The model optimizer process, Local Configuration	[10]
3	Optimization Techniques	Quantization, Freezing, Fusion	[11 - 12]
4	Supported Frameworks	Caffe, TensorFlow, MXNet, ONNX, Kaldi	[13 - 17]
5	Intermediate Representations	OpenVINO™ Toolkit’s standard structure and naming for neural network architectures, XML file and a binary file	[18 - 20]
6	Using the Model Optimizer with TensorFlow Models	Using the Model Optimizer with TensorFlow Models	[21 - 22]
7	Exercise: Convert a TF Model	Excercise on convert a tf model	------/------
8	Solution: Convert a TF Model	Solution of convert a tf model	------/------
9	Using the Model Optimizer with Caffe Models	Nothing about freezing the model, Need to feed both the .caffemodel file, as well as a .prototxt file	[23]
10	Exercise: Convert a Caffe Model	Excercise on convert a caffe model	------/------
11	Solution: Convert a Caffe Model	Solution of convert a caffe model	------/------
12	Using the Model Optimizer with ONNX Models	Model Optimizer with ONNX Models, PyTorch to ONNX	[24 - 26]
13	Exercise: Convert an ONNX Model	Excercise on covert an ONNX model	------/------
14	Solution: Convert an ONNX Model	Solution of convert and ONNX model	------/------
15	Cutting Parts of a Model	Mostly applicable for TensorFlow models, Two main command line arguments to use for cutting a model: --input and --output	[27]
16	Supported Layers	Supported and unsupported layers	[28]
17	Custom Layers	Register the custom layers	[29 - 30]
18	Exercise: Custom Layers	Example Custom Layer: The Hyperbolic Cosine (cosh) Function	------/------
19	Recap	Basics of the Model Optimizer, Optimization techniques & impact, Supported Frameworks, Custom layers	------/------
20	Lesson Glossary	Short note of the lesson	------/------

Lesson-4: The Inference Engine

No	Lesson	Notes	Link/Source
1	Introduction	Inference Engine, Supported device, Feeding an Intermediate Representation to the Inference Engine, Making Inference Requests, Handling Results	------/------
2	The Inference Engine	Runs the actual inference on a model, Only works with the Intermediate Representations	[31]
3	Supported Devices	CPUs, including integrated graphics processors, GPUs, FPGAs, and VPUs	[32 - 33]
4	Using the Inference Engine with an IR	IECore, IENetwork, Check Supported Layers, CPU extension	[34 - 36]
5	Exercise: Feed an IR to the Inference Engine	Exercise on feed an IR to the inference engine	------/------
6	Solution: Feed an IR to the Inference Engine	Solution of feed an IR to the inference engine	------/------
7	Sending Inference Requests to the IE	ExecutableNetwork, Two types of inference requests: Synchronous and Asynchronous	[37 - 38]
8	Asynchronous Requests	Synchronous: only one frame is being processed at once, Asynchronous: other tasks may continue while waiting on the IE to respond	[39 - 41]
9	Exercise: Inference Requests	Inference requests (asynchronous & synchronous) excercise	------/------
10	Solution: Inference Requests	Synchronous and Asynchronous Solution	------/------
11	Handling Results	InferRequest attributes - namely, inputs, outputs and latency	[42]
12	Integrating into Your App	Adding some further customization to your app	[43 - 45]
13	Exercise: Integrate into an App	Excercise on integrate into an App	------/------
14	Solution: Integrate into an App	Solution of integrate into an App	------/------
15	Behind the Scenes of Inference Engine	Inference Engine is built and optimized in C++, The exact optimizations differ by device with the Inference Engine	[46 - 47]
16	Recap	Inference Engine, Supported device, Feeding an Intermediate Representation to the Inference Engine, Making Inference Requests, Handling Results	------/------
17	Lesson Glossary	Short note of the lesson	------/------

Lesson-5: Deploying an Edge App

No	Lesson	Notes	Link/Source
1	Introduction	OpenCV, Input Streams in OpenCV, Processing Model Outputs for Additional Useful Information, MQTT and their use with IoT devices, Performance basics	------/------
2	OpenCV Basics	Uses of OpenCV, Useful OpenCV function: VideoCapture, resize, cvtColor, rectangle, imwrite	[48]
3	Handling Input Streams	Open & Read A Video, Closing the Capture	------/------
4	Exercise: Handling Input Streams	Handle image, video or webcam, resize, Add Canny Edge Detection to the frame, Write out the frame	------/------
5	Solution: Handling Input Streams	Handle image, video or webcam, resize, Add Canny Edge Detection to the frame, Write out the frame	------/------
6	Gathering Useful Information from Model Outputs	Information from one model could even be further used in an additional model	------/------
7	Exercise: Process Model Outputs	Excercise on model outputs process	------/------
8	Solution: Process Model Outputs	Solution of model outputs process	------/------
9	Intro to MQTT	Stands for MQ Telemetry Transport, Lightweight publish/subscribe architecture, Port 1883	[49 - 50]
10	Communicating with MQTT	MQTT Python library: paho-mqtt, Publishing or subscribing parameters	[51 - 52]
11	Streaming Images to a Server	FFmpeg (“fast forward” MPEG), Setting up FFmpeg, Sending frames to FFmpeg	[53 - 55]
12	Handling Statistics and Images from a Node Server	Node server can be used to handle the data coming in from the MQTT and FFmpeg servers	[56]
13	Exercise: Server Communications	Excercise on server communication using node.js and mqtt	------/------
14	Solution: Server Communications	Solution of server communication using node.js and mqtt	------/------
15	Analyzing Performance Basics	Not to skip past the accuracy of your edge AI model, Lighter, quicker models, Lower precision	[57]
16	Model Use Cases	Figure out additional use cases for a given model or application	[58]
17	Concerning End User Needs	Consider the project needs	------/------
18	Recap	OpenCV, Input Streams in OpenCV, Processing Model Outputs for Additional Useful Information, MQTT and their use with IoT devices, Performance basics	------/------
19	Lesson Glossary	Short note of the lesson	------/------
20	Course Recap	Basics of AI at the Edge, Pre-trained models, the Model Optimizer, Inference Engine, Deploying an app at the edge	[59]
21	Partner with Intel	Benefits of partner with Intel	------/------

3. Choosing the Right Hardware

Lesson-1: Introduction to Hardware at the Edge

No	Lesson	Notes	Link/Source
1	Instructor Introduction	Instructor - Vaidheeswaran Archana, Stewart Christie	------/------
2	Course Overview	Right hardware for a particular need, Four main hardware types	[60]
3	Changes in OpenVINO 2020.1	Differences between 2020.1 vs. the older 2019 R3.1 version	[61]
4	Lesson Overview	Choosing the right hardware, Product development flow, Basic terminology, Using Intel DevCloud	------/------
5	Why is Choosing the Right Hardware Important?	Project steps for a edge application from begin to deploy	------/------
6	Design of Edge AI Systems	Stakeholders in designing Edge AI systems, Basic approach to developing a product	------/------
7	Analyze	Get all of the requirements and constraints involved	------/------
8	Design	The different components and how the data will flow from one to the next	------/------
9	Develop	Hardware & Software prototype development	------/------
10	Test and Deploy	Tested the design and selected the hardware, Simulated edge device, Debugging	------/------
11	Basic Terminology	CPU, GPU, AI Accelerators, VPU, NCS-2, FPGA, HDDL/VAD, TDP, Hetero, SYNC & ASYNC mode	------/------
12	Intel DevCloud	High-level overview of the Intel DevCloud for the Edge	[60]
13	Updating Your Workspace	Getting New Content & Resetting Data option in workspace	------/------
14	Walkthrough: Using Intel DevCloud	Showing how to request an edge node with an Intel i5 CPU and load a model on the CPU	------/------
15	Exercise: Using Intel DevCloud	Excercise on Intel DevCloud - load model, inference run, queue job	------/------
16	Lesson Review	Choosing the right hardware, Product development flow, Basic terminology, Using Intel DevCloud	------/------

Lesson-2: CPUs and Integrated GPUs

No	Lesson	Notes	Link/Source
1	Lesson Overview	CPUs and integrated GPUs overview	------/------
2	CPU Basics	Basic description about - CPU, Multiple Cores, IGPU	------/------
3	Threads and Processes	Basic description about - Threads, Processes	------/------
4	Multithreading and Multiprocessing	Choosing the right hardware, Product development flow, Basic terminology, Using Intel DevCloud	[62 - 63]
5	Introduction to Intel Processors	Different types of processors, Cost and performance across different processor types, Thermal Design Power (TDP)	[64]
6	Intel CPU Architecture	Key characteristics of Intel processors, Compatibility, Multicore, Hyperthreading, Instruction Sets	------/------
7	CPU Specifications (Part 1)	Clock Speed, Number of Cores	------/------
8	CPU Specifications (Part 2)	Important factors to consider when looking at CPU specifications	------/------
9	Exercise: CPU Scenario	Case study in CPU Scenario	[65]
10	Updating Your Workspace	Getting new content, Resetting data	------/------
11	Walkthrough: CPU and the DevCloud	Walkthrough on the CPU and the DevCloud	------/------
12	Exercise: CPU and the Devcloud	Exercise on the CPU and the Devcloud	------/------
13	Integrated GPU (IGPU)	Execution Units, Slice, Unslice, Key Characteristics of Integrated GPUs	------/------
14	Walkthrough: IGPU and the DevCloud	Walkthrough on the IGPU and the DevCloud	------/------
15	IGPU and Batch Processing	Relation between IGPU and batch processing	------/------
16	Exercise: IGPU Scenario	Real case study IGPU scenario	------/------
17	Exercise: IGPU and the DevCloud	Exercise on the IGPU and the DevCloud	------/------
18	Lesson Review	Intel processors, Intel architecture, Application of CPU, DevCloud, IGPU	------/------

Lesson-3: VPUs

No	Lesson	Notes	Link/Source
1	Lesson Overview	Architecture of VPUs, Characteristics of a particular VPU, Neural Compute Stick 2, Multi-Device Plugin	------/------
2	Introduction to VPUs	Small, low-cost, low-power devices that can dramatically improve the performance of a system	------/------
3	Architecture of VPUs	Interface unit, Imaging accelerators, Neural compute engine, Vector processors, On-chip CPUs	------/------
4	Myriad X Characteristics	Neural compute engine, Imaging accelerators, Imaging/Hardware Accelerators, On-chip memory, Vector processors, Energy consumption	[66]
5	Intel Neural Compute Stick 2	Key features of the Intel NCS2, FPS vs. Power Tradeoff	------/------
6	Exercise: VPU Scenario	Case study on VPU scenario	------/------
7	Updating Your Workspace	Getting new content, Resetting data	------/------
8	Walkthrough: VPU and the DevCloud	Walkthrough on the VPU and the DevCloud	------/------
9	Exercise: VPU and the DevCloud	Exercise on the VPU and the DevCloud	------/------
10	Multi-Device Plugin	About multi-device plugin and it's benefits	------/------
11	Walkthrough: Multi-Device Plugin and the DevCloud	Walkthrough on the CPU and the DevCloud	------/------
12	Exercise: Multi Device Plugin on DevCloud	Exercise on the CPU and the Devcloud	------/------
13	Lesson Review	Architecture of VPUs, Characteristics of a particular VPU, Neural Compute Stick 2, Multi-Device Plugin	------/------

Lesson-4: FPGAs

No	Lesson	Notes	Link/Source
1	Lesson Overview	Architecture of FPGAs, Programming FPGAs, Turning Your FPGA into an AI Accelerator, Specifications of FPGAs	------/------
2	Introduction to FPGAs	Basic description about ASICs, FPGAs	------/------
3	Architecture of FPGAs	The components of a tile or Adaptive Logic Module (ALM)	------/------
4	Programming FPGAs	Different ways to program an FPGA, Register Transfer Level (RTL), Converting an FPGA into an AI Accelerator	------/------
5	FPGA Specifications	High performance, Low latency, Flexibility, Large Networks, Robust, Long Lifespan	------/------
6	Intel Vision Accelerator Design	Important consideration to run inference on one using the Intel DevCloud	------/------
7	Exercise: FPGA Scenario	Case study on FPGA scenario	------/------
8	Updating Your Workspace	Getting new content, Resetting data	------/------
9	Walkthrough: FPGA and the DevCloud	Walkthrough on the FPGA and the DevCloud	------/------
10	Exercise: FPGA and the DevCloud	Exercise on the FPGA and the DevCloud	------/------
11	Heterogeneous Plugin	Heterogeneous (HETERO) plugin benefits	[67 - 68]
12	Exercise: Heterogeneous Plugin on DevCloud	Exercise on the Heterogeneous Plugin on DevCloud	------/------
13	Lesson Review	Architecture of FPGAs, Programming FPGAs, Turning Your FPGA into an AI Accelerator, Specifications of FPGAs	------/------
14	Course Review	CPU, GPU, VPU, FPGA, Intel DevCloud	------/------

4. Optimization Techniques and Tools

Lesson-1: Introduction to Software Optimization

No	Lesson	Notes	Link/Source
1	Instructor Introduction	Instructor - Soham Chatterjee	------/------
2	Course Overview	Performance Metrics, Reducing Model Operations, Reducing Model Size, Other Optimization Techniques	------/------
3	Installing OpenVINO	OpenVINO installation instruction	------/------
4	Lesson Overview	Lesson objective	------/------
5	What is Software Optimization and Why Does it Matter?	Hardware optimization, Software optimization	------/------
6	Types of Software Optimization	Reduce the size of the model, Reduce the number of operations	------/------
7	Performance Metrics	Software Performance, Hardware Performance, Recall, Precision, Latency and Throughput	------/------
8	Some Other Performance Metrics	FLOPs, FLOPS, MACs	------/------
9	When do we do Software Optimization?	Scenario based software optimization	[69]
10	Lesson Review	Performance Metrics, Reducing Model Operations, Reducing Model Size, Other Optimization Techniques	------/------

Lesson-2: Reducing Model Operations

No	Lesson	Notes	Link/Source
1	Lesson Overview	How to measure the performance of our model (FLOPs and MACs performance metric), How to use efficient layers in our model, How to use OpenVINO to measure the layerwise performance, Model pruning	------/------
2	Calculating Model FLOPs: Dense Layers	Calculating MACs and FLOPs number in Dense Layers	------/------
3	Calculating Model FLOPS: Convolutional Layers	Convolutional Layers (Kernal, output size), Calculating MACs and FLOPs, FLOPS in convolutional layers	[70]
4	Calculate the FLOPs in a model	Calculate the FLOPs in a model (CNN, FC layers)	------/------
5	Using Efficient Layers: Pooling Layers	Pooling layers, Types of pooling layers, Calculate the FLOPs in pooling layers	------/------
6	Exercise: Pooling Performance	Exercise on the pooling performance	------/------
7	Using Efficient Layers: Separable Convolutions	Separable Convolutions - Depthwise layer, Pointwise layer	------/------
8	Exercise: Separable Convolutions Performance	Exercise on Separable Convolutions Performance	------/------
9	Measuring Layerwise Performance	Measuring Layerwise Performance	------/------
10	Exercise: Measuring Layerwise Performance	Exercise on the measuring layerwise performance	------/------
11	Model Pruning	Three basic steps in model pruning	------/------
12	Lesson Review	How to measure the performance of our model (FLOPs and MACs performance metric), How to use efficient layers in our model, How to use OpenVINO to measure the layerwise performance, Model pruning	------/------

Lesson-3: Reducing Model Size

No	Lesson	Notes	Link/Source
1	Lesson Overview	Quantization, DL Workbench, Weight Sharing, Knowledge Distillation	------/------
2	Introduction to Quantization	Quantization, Affine transformation, Binary and Tenary NN	[71]
3	Benchmarking Model Performance	Install and run DL Workbench	[72]
4	Exercise: Benchmarking Model Performance	Exercise on benchmarking model performance	[73]
5	Advanced Benchmarking	Perform many tests with various configurations of batch size and streams	------/------
6	Exercise: Advanced Benchmarking	Run a range of performance benchmarks on a model of our choice	------/------
7	How Quantization is Done	Weight quantization, Procedure and formula of quantization	[74]
8	Quantizing a Model using DL Workbench	Using the DL Workbench to quantize a model	[75 - 76]
9	Exercise: Quantizing a Model Using DL Workbench	Exercise on quantizing a model using DL Workbench	------/------
10	Model Compression	Model compression techniques	------/------
11	Knowledge Distillation	Transfer the knowledge learned by a large, accurate model (the teacher model) to a smaller and computationally less expensive model (the student model)	------/------
12	Lesson Review	Quantization, DL Workbench, Weight Sharing, Knowledge Distillation	------/------

Lesson-4: Other Optimization Tools and Techniques

No	Lesson	Notes	Link/Source
1	Lesson Overview	Measuring latencies in our code, Using VTune Amplifier, Packaging our application	------/------
2	Introduction to Intel VTune	Install and run Intel VTune	[77 - 78]
3	Exercise: Profiling Using VTune	Exercise on profiling using VTune	------/------
4	Advanced Concepts in Intel VTune	Drill down further and see which lines in your application are the bottlenecks	------/------
5	Exercise: Advanced Profiling Using VTune Amplifier	Exercise on advanced profiling using VTune Amplifier	------/------
6	Packaging Your Application	Packaging our application	------/------
7	Exercise: Packaging Your Application	Exerciseon packaging our application	------/------
8	Exercise: Deploying Runtime Package	Exercise on deploying runtime package	------/------
9	Lesson Review	Measuring latencies in our code, Using VTune Amplifier, Packaging our application	------/------
10	Course Review	Software optimization, Performance Metrics, Reducing Model Parameters	------/------

Project

• Deploy a People Counter App at the Edge
• Smart Queuing System
• Computer Pointer Controller

Resources

• [1] A guide to internet of things infographics
• [2] Intel® Distribution of OpenVINO™ Toolkit
• [3] Hardware requirements for the Intel® Distribution of OpenVINO
• [4] Set-up like a Raspberry Pi with an Intel® Neural Compute Stick 2
• [5] Intel® DevCloud platform
• [6] Pretrained Models
• [7] Image Classification vs. Object Detection vs. Image Segmentation
• [8] Understanding SSD MultiBox — Real-Time Object Detection In Deep Learning
• [9] Going beyond the bounding box with semantic segmentation
• [10] Model Optimizer Developer Guide
• [11] Quantization
• [12] Model Optimization Techniques
• [13] Caffe
• [14] TensorFlow
• [15] MXNet
• [16] ONNX
• [17] Kaldi
• [18] Converting a Model to Intermediate Representation (IR)
• [19] Supported Framework Layers
• [20] Intermediate Representation Notation Reference Catalog
• [21] Converting a TensorFlow* Model
• [22] Tensorflow detection model zoo
• [23] Converting a Caffe* Model
• [24] Converting a ONNX* Model
• [25] ONNX Model Zoo
• [26] Converting a PyTorch model using ONNX
• [27] Cutting Off Parts of a Model
• [28] Supported Framework Layers
• [29] Custom Layers in the Model Optimizer
• [30] Offloading Sub-Graph Inference to TensorFlow*
• [31] Inference Engine Developer Guide
• [32] Supported Devices
• [33] Distribution of OpenVINO™ Toolkit on Raspberry Pi*
• [34] IE Core
• [35] IE Network
• [36] IE Python API
• [37] Executable Network documentation
• [38] Infer Request documentation
• [39] synchronous/asynchronous API
• [40] Integrate the Inference Engine with Your Application
• [41] Object Detection SSD C++ Demo, Async API Performance Showcase
• [42] InferenceEngine::Blob Class Reference
• [43] Intel®’s IoT Apps Across Industries
• [44] Starting Your First IoT Project
• [45] OpenVINO™ on a Raspberry Pi and Intel® Neural Compute Stick
• [46] What is the best programming language for Machine Learning?
• [47] Optimization Guide
• [48] OpenCV tutorial
• [49] MQTT
• [50] Basics of MQTT
• [51] paho-mqtt - PyPI
• [52] Developer Kits for IoT - Intel® Software
• [53] FFMPEG
• [54] Create your own video streaming server with Linux
• [55] OpenCV – Stream video to web browser/HTML page
• [56] Node.js
• [57] Introduction to the Performance Topics
• [58] Deep Learning for Distracted Driving Detection
• [59] Intel® DevMesh
• [60] Intel DevCloud
• [61] Changes to the OpenVINO API
• [62] A gentle introduction to multithreading
• [63] Multithreading vs. multiprocessing in Python
• [64] What Is TDP for CPUs and GPUs?
• [65] Application of IoT devices and Edge AI in the mining industry
• [66] Intel’s Realsense 3D cameras
• [67] List of supported layers for each device
• [68] Heterogeneous Plugin
• [69] Line Profiler - Python
• [70] A Beginner's Guide To Understanding Convolutional Neural Networks
• [71] Affine transformations
• [72] Install DL Workbench from Docker Hub
• [73] TensorFlow* pre-trained model
• [74] Intel(R) Math Kernel Library for Deep Neural Networks (Intel(R) MKL-DNN)
• [75] Instructions on how to create a dataset for DL Workbrench
• [76] Low-Precision 8-bit Integer Inference
• [77] Download VTune Amplifier
• [78] Get Started with Intel® VTune™ Profiler