At TensorFlow Dev Summit 2019, we announced TensorFlow Lite 1.0
TensorFlow Lite is a lightweight solution for mobile and embedded devices. In this video, you will see live demos of both the Coral Dev Board, and microcontrollers in action! Learn more about these products in the links below!
In this episode of AI Adventures, Yufeng Guo introduces the TPU v2 and v3. Specifically, he goes over their architecture, how they work, and how Google Developers can get their hands on these TPUs.
This session will introduce you to Google Coral, a new platform for on-device AI application development and showcase it's machine learning acceleration power with TensorFlow demos. Coral offers the tools to bring private, fast, and efficient neural network acceleration right onto your device and enables you to grow ideas of AI application from prototype to production. You will also learn the technical specs of Edge TPU hardware and software tools, as well as application development process.
In this episode, Yufeng Guo speaks to how you can use Google Cloud AI Platform Built-in Algorithms to train and deploy machine learning models without writing any training code.
KCCSでは、IoT/AI分野のPoCを行っています。今回のPoCでは、Google が開発したAIチップ「 Edge TPU™ 」の性能を確認します。株式会社 Ristの画像認識AIを Google Coral Edge TPU USB Accelerator で実行し、シングルボード不良品判定を行います
ラズパイ(RaspberryPi 3 B+)にカメラをつなげて写ったモノをリアルタイムで予測・分類する。GoogleのCoral USB Acceleratorを使って高速に予測する。