You don't need this to reproduce the demo. Coral Edge TPU USB Accelerator: Accelerates inference (prediction) speed on the Raspberry Pi.RGB NeoPixel Stick: This component adds a consistent light source to your project.12" CSI/DSI ribbon for Raspberry Pi Camera: The Pi Camera's stock cable is too short for the Pan-Tilt HAT's full range of motion.Edge TPUs (right) accelerate inferences in mobile devices. This tutorial will use MobileNetV3-SSD models available through TensorFlow's object-detection model zoo.Ĭloud TPUs (left and center) accelerate TensorFlow model training and inference. MobileNetV3-SSD : An SSD based on MobileNet architecture.MobileNetV3 : A state-of-the-art computer vision model optimized for performance on modest mobile phone processors.Single-shot detector: SSD is a type of CNN architecture specialized for real-time object detection, classification, and bounding box localization.Convolutional neural network: CNN is a type of neural network architecture that is well-suited for image classification and object detection tasks.TensorFlow Lite : An open source framework for deploying TensorFlow models on mobile and embedded devices.TensorFlow : An open source framework for dataflow programming used for machine learning and deep neural learning.Raspbian : The Raspberry Pi Foundation's official operating system for the Pi. Raspbian is derived from Debian Linux.Raspberry Pi: A small, affordable computer popular with educators, hardware hobbyists, and robot enthusiasts.Accelerating inferences of any TensorFlow Lite model with Coral's USB Edge TPU Accelerator and Edge TPU Compiler.
Sending tracking instructions to pan/tilt servo motors using a proportional–integral–derivative (PID) controller.Deploying a TensorFlow Lite object-detection model ( MobileNetV3-SSD) to a Raspberry Pi.Build materials and hardware assembly instructions.Whitepaper: Data-intensive intelligent applications in a hybrid cloud blueprint.eBook: Running Kubernetes on your Raspberry Pi.Getting started with Raspberry Pi cheat sheet.
0 kommentar(er)
