TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-Low-Power Microcontrollers"O'Reilly Media, Inc.", 16. des. 2019 - 504 sider Deep learning networks are getting smaller. Much smaller. The Google Assistant team can detect words with a model just 14 kilobytes in size—small enough to run on a microcontroller. With this practical book you’ll enter the field of TinyML, where deep learning and embedded systems combine to make astounding things possible with tiny devices. Pete Warden and Daniel Situnayake explain how you can train models small enough to fit into any environment. Ideal for software and hardware developers who want to build embedded systems using machine learning, this guide walks you through creating a series of TinyML projects, step-by-step. No machine learning or microcontroller experience is necessary.
|
Andre utgaver - Vis alle
TinyML: Machine Learning with TensorFlow Lite on Arduino and Ultra-low-power ... Pete Warden,Daniel Situnayake Ingen forhåndsvisning tilgjengelig - 2020 |
Vanlige uttrykk og setninger
33 BLE Sense accelerometer accelerometer data application Arduino Arduino Nano 33 array binary buffer build button called camera module capture changes Chapter Colab const int convert convolutional create dataset debug deep learning defined deploy embedded systems error_reporter feature Figure flash following command function gesture Google graph hardware implementation input tensor install interface is_initialized kTfLiteOk layer Linux Lite for Microcontrollers look loop machine learning Makefile Mbed mean absolute error memory model architecture namespace Nano 33 BLE neural network notebook NumPy operations optimizations overfitting platform pointer predictions preprocessing Python quantization run inference run the script sample score serial port source files SparkFun Edge spectrogram ST Microelectronics TensorBoard TensorFlow Lite tensorflow/lite/micro/tools/make/Makefile TfLiteStatus there’s TinyML train a model training data uint8_t update validation values variable wake-word we’ll what’s window y_value you’re