{"type":"product","schema_version":"1.0","item_id":"100276349444","canonical_url":"https://tw.bid.yahoo.com/item/100276349444","title":"《德源科技》＊Google Coral AI人工智慧加速 加速模組 USB Accelerator Edge","subtitle":null,"condition":"全新品","currency":"TWD","observed_at":"2026-05-06T17:55:18.936Z","current_price":4413,"original_price":"5000.00","stock_status":"low_stock","available_quantity":2,"sold_quantity":1,"seller":{"id":"Y9895025221","name":"Deryuan 德源科技","positive_rate":null,"rating_count":null},"images":[{"url":"https://img.yec.tw/ob/image/8aeb1ae9-6907-4d6b-a11e-16b0cc44c0de.jpg","role":"main","alt":"商品主圖","width":null,"height":null}],"description":"1361\n \n\n※本產品原廠代理從國外進口，有些交期較長，下訂前請詢問！\n\nGoogle USB Accelerator Edge TPU 人工智慧加速加速模組\nA USB accessory that brings machine learning inferencing to existing systems. Works with Raspberry Pi and other Linux systems.\n \n\n    The USB Accelerator brings powerful ML inferencing capabilities to existing Linux systems.\n    Featuring the Edge TPU —  a small ASIC designed and built by Google— the USB Accelerator provides high performance ML inferencing with a low power cost over a USB 3.0 interface. For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at 100+ fps, in a power efficient manner. This allows you to add fast ML inferencing to your embedded AI devices in a power-efficient and privacy-preserving way.\n Models are developed in TensorFlow Lite and then compiled to run on the USB Accelerator.\n\nEdge TPU key benefits\n    - High-speed TensorFlow Lite inferencing\n    - Low power\n    - Small footprint\n A is a division of Google, that helps you build intelligent ideas with our platform for local AI.\n\nFEATURES\n    - Google Edge TPU ML accelerator coprocessor\n    - USB 3.0 Type-C socket\n    - Supports Debian Linux on host CPU\n    - Models are built using TensorFlow\n    - Fully supports MobileNet and Inception architectures though custom architectures are possible\n    - Compatible with Google Cloud\n\nSPECS\nEdge TPU ML accelerator\n    - ASIC designed by Google that provides high performance ML inferencing for TensorFlow Lite models\nArm 32-bit Cortex-M0+ Microprocessor (MCU)\n    - Up to 32 MHz max\n    - 16 KB Flash memory with ECC\n    - 2 KB RAM\nConnections\n    - USB 3.1 (gen 1) port and cable (SuperSpeed, 5Gb/s transfer speed)\n    - Included cable is USB Type-C to Type-AU\n\nLocal inferencing\nRun on-device ML inferencing on the Edge TPU designed by Google.\nWorks with Debian Linux\nConnect to any Linux-based system with an included USB Type-C cable.\nSupports TensorFlow lite\nNo need to build models from the ground up. Tensorflow Lite models can be compiled ...","shipping_methods":[{"name":"郵局掛號","fee":0,"currency":"TWD"},{"name":"7-ELEVEN取貨付款","fee":0,"currency":"TWD"},{"name":"7-ELEVEN取貨不付款","fee":0,"currency":"TWD"}],"lowest_shipping_fee":null,"payment_methods":["ATM轉帳","7-ELEVEN取貨付款"],"category_id":"2092072544","category_name":"其他電腦周邊","breadcrumb":[{"id":"23336","name":"電腦、平板與周邊","url":"/tw/%E9%9B%BB%E8%85%A6%E3%80%81%E5%B9%B3%E6%9D%BF%E8%88%87%E5%91%A8%E9%82%8A-23336-category.html"},{"id":"2092072522","name":"電腦/筆電周邊","url":"/tw/%E9%9B%BB%E8%85%A6-%E7%AD%86%E9%9B%BB%E5%91%A8%E9%82%8A-2092072522-category.html"},{"id":"2092072544","name":"其他電腦周邊","url":"/tw/%E5%85%B6%E4%BB%96%E9%9B%BB%E8%85%A6%E5%91%A8%E9%82%8A-2092072544-category.html"}],"view_count":0,"watch_count":1}