Description
The Coral USB Accelerator adds an Edge TPU coprocessor to your system, enabling high-speed machine learning inferencing on a wide range of systems, simply by connecting it to a USB port.
The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power efficient manner.
It connects via USB to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10. There is no need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.
Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge.
Model Overview
| Coral Dev Board | Coral USB Accelerator | ||
|---|---|---|---|
| ML Accelerator | Google Edge TPU coprocessor 4 TOPS (int8); 2 TOPS per watt |
||
| CPU | 4x 1.5 GHz NXP i.MX 8M SoC (Cortex-A53, Cortex-M4F) |
||
| RAM | 1/4 GB LPDDR4 | ||
| Flash Memory | eMMC | 8 GB | |
| micro-SD Slot | |||
| Coral Dev Board | Coral USB Accelerator | ||
|---|---|---|---|
| Connectivity | HDMI | 1x HDMI 2.0a | |
| USB | 1x USB 3.0 Host 1x USB-C OTG 1x micro-USB Serial Console |
1x USB-C (Data/Power) | |
| LAN | 1x Gigabit Ethernet | ||
| WLAN | 2.4 / 5.0 GHz IEEE 802.11b/g/n/ac (2x2 MIMO) | ||
| Bluetooth | Bluetooth 4.2 | ||
| GPIO | 40-pin GPIO Header | ||
| Weitere | MIPI-DSI (4 Lanes), MIPI-CSI2 (4 Lanes), 3.5mm Audio, 2x PDM microphone, 4-Pin Stereo speaker connector | ||
| Multimedia | Hardware- De-/Encoder |
H.265/HEVC/VP9 (4Kp60) AVC/H.264 (4Kp30) H.263/MPEG-2/MPEG-4p2/VC-1/VP8/RV9/AVS/MJPEG (1080p60) |
|
| Grafik | OpenGL ES 1.1, 2.0, 3.0, 3.1, Open CL 1.2, Vulkan | ||
| Power | 5V/3A (via USB-C Power) | 5V/500mA (via USB-C Data/Power) | |
| Dimensions | 88 x 60 x 24 mm | 65 x 30 x 8 mm |
| Shipping weight: | 0.09 Kg |
Related products
Datasheet (EN)
