Opis
This book explores TinyML, a fast-growing field at the unique intersection of machine learning and embedded systems to make AI ubiquitous with extremely low-powered devices such as microcontrollers.The TinyML Cookbook starts with a practical introduction to this multidisciplinary field to get you up to speed with some of the fundamentals for deploying intelligent applications on Arduino Nano 33 BLE Sense and Raspberry Pi Pico. As you progress, youll tackle various problems that you may encounter while prototyping microcontrollers, such as controlling the LED state with GPIO and a push-button, supplying power to microcontrollers with batteries, and more. Next, youll cover recipes relating to temperature, humidity, and the three „V” sensors (Voice, Vision, and Vibration) to gain the necessary skills to implement end-to-end smart applications in different scenarios. Later, youll learn best practices for building tiny models for memory-constrained microcontrollers. Finally, youll explore two of the most recent technologies, microTVM and microNPU that will help you step up your TinyML game.By the end of this book, youll be well-versed with best practices and machine learning frameworks to develop ML apps easily on microcontrollers and have a clear understanding of the key aspects to consider during the development phase. Spis treści:TinyML CookbookForewordContributorsAbout the authorAbout the reviewersPrefaceWho this book is forWhat this book coversTo get the most out of this bookDownload the example code filesDownload the color imagesConventions usedSectionsGetting readyHow to do itTheres moreGet in touchShare Your ThoughtsChapter 1: Getting Started with TinyMLTechnical requirementsIntroducing TinyMLWhat is TinyML?Why ML on microcontrollers?Why run ML locally?The opportunities and challenges for TinyMLDeployment environments for TinyMLtinyML FoundationSummary of DLDeep neural networksConvolutional neural networksQuantizationLearning the difference between power and energyVoltage versus currentPower versus energyProgramming microcontrollersMemory architecturePeripheralsPresenting Arduino Nano 33 BLE Sense and Raspberry Pi PicoSetting up Arduino Web Editor, TensorFlow, and Edge ImpulseGetting ready with Arduino Web EditorGetting ready with TensorFlowGetting ready with Edge ImpulseHow to do itRunning a sketch on Arduino Nano and Raspberry Pi PicoGetting readyHow to do itJoin us on Discord!Chapter 2: Prototyping with MicrocontrollersTechnical requirementsCode debugging 101Getting readyHow to do it…Theres moreImplementing an LED status indicator on the breadboardGetting readyHow to do it…Controlling an external LED with the GPIOGetting readyHow to do it…Turning an LED on and off with a push-buttonGetting readyHow to do it…Using interrupts to read the push-button stateGetting readyHow to do it…Powering microcontrollers with batteriesGetting startedHow to do it…Theres moreChapter 3: Building a Weather Station with TensorFlow Lite for MicrocontrollersTechnical requirementsImporting weather data from WorldWeatherOnlineGetting readyHow to do itPreparing the datasetGetting readyHow to do itTraining the ML model with TFGetting readyHow to do itEvaluating the models effectivenessGetting readyHow to do itQuantizing the model with the TFLite converterGetting readyHow to do itUsing the built-in temperature and humidity sensor on Arduino NanoGetting readyHow to do itUsing the DHT22 sensor with the Raspberry Pi PicoGetting readyHow to do itPreparing the input features for the model inferenceGetting readyHow to do itOn-device inference with TFLuGetting readyHow to do itChapter 4: Voice Controlling LEDs with Edge ImpulseTechnical requirementsAcquiring audio data with a smartphoneGetting readyHow to do itExtracting MFCC features from audio samplesGetting readyHow to do itTheres moreDesigning and training a NN modelGetting readyHow to do itTuning model performance with EON TunerGetting readyHow to do itLive classifications with a smartphoneGetting readyHow to do itLive classifications with the Arduino NanoGetting readyHow to do itContinuous inferencing on the Arduino NanoGetting readyHow to do itBuilding the circuit with the Raspberry Pi Pico to voice control LEDsGetting readyHow to do itAudio sampling with ADC and timer interrupts on the Raspberry Pi PicoGetting readyHow to do itTheres moreChapter 5: Indoor Scene Classification with TensorFlow Lite for Microcontrollers and the Arduino NanoTechnical requirementsTaking pictures with the OV7670 camera moduleGetting readyHow to do it…Grabbing camera frames from the serial port with PythonGetting readyHow to do it…Converting QQVGA images from YCbCr422 to RGB888Getting readyHow to do it…Building the dataset for indoor scene classificationGetting readyHow to do it…Transfer learning with KerasGetting readyHow to do it…Preparing and testing the quantized TFLite modelGetting readyHow to do it…Reducing RAM usage by fusing crop, resize, rescale, and quantizeGetting readyHow to do it…Chapter 6: Building a Gesture-Based Interface for YouTube PlaybackTechnical requirementsCommunicating with the MPU-6050 IMU through I2CGetting readyHow to do itAcquiring accelerometer dataGetting readyHow to do itBuilding the dataset with the Edge Impulse data forwarder toolGetting readyHow to do itDesigning and training the ML modelGetting readyHow to do itLive classifications with the Edge Impulse data forwarder toolGetting readyHow to do itGesture recognition on Raspberry Pi Pico with Arm Mbed OSGetting readyHow to do itBuilding a gesture-based interface with PyAutoGUIGetting readyHow to do itChapter 7: Running a Tiny CIFAR-10 Model on a Virtual Platform with the Zephyr OSTechnical requirementsGetting started with the Zephyr OSGetting readyHow to do itDesigning and training a tiny CIFAR-10 modelGetting readyHow to do itEvaluating the accuracy of the TFLite modelGetting readyHow to do itConverting a NumPy image to a C-byte arrayGetting readyHow to do itPreparing the skeleton of the TFLu projectGetting readyHow to do itBuilding and running the TFLu application on QEMUGetting readyHow to do itJoin us on Discord!Chapter 8: Toward the Next TinyML Generation with microNPUTechnical requirementsSetting up Arm Corstone-300 FVPGetting readyHow to do itInstalling TVM with Arm Ethos-U supportGetting readyHow to do itInstalling the Arm toolchain and Ethos-U driver stackGetting readyHow to do itGenerating C code with TVMGetting readyHow to do itGenerating C-byte arrays for input, output, and labelsGetting readyHow to do itBuilding and running the model on Ethos-U55Getting readyHow to do itWhy subscribe?Other Books You May EnjoyPackt is searching for authors like youShare Your Thoughts
listwa progowa do płytek, materiały na sufit podwieszany, barek kuchenny z blatu, płyta ogniowa, farba jedynka, umywalka wpuszczana, kabina walk in 90, zawias splatany, siekiera do drzewa, grubościówka, wykopki ziemniakow, kompozytowe deski tarasowe, jak wyburzyć ścianę, kleje stolarskie, styropian podlogowy 3 cm, szafka z lusterkiem, drenaż w ogrodzie, kosiarka spalinowa z napędem, gniazdko podwójne
yyyyy
