Coral Dev Board Mini

PRODUCT DETAILS

Attention

This product has shipping restriction to certain countries. It can only be sent to countries and regions listed as below:  United States, Hong Kong, Austria, Belgium, Bulgaria, Croatia, Cyprus, Denmark, Estonia, Fiji, Germany, Greece, Hungary, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Poland, Portugal, Romania, Slovakia, Slovenia, Spain, Sweden, United Kingdom, Switzerland, Iceland, Liechtenstein, Norway, Turkey

Features

  • Performs high-speed ML inferencing: The onboard 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. See more performance benchmarks.
  • Provides a complete system: A single-board computer with SoC + ML + wireless connectivity, all on the board running a derivative of Debian Linux we call Mendel, so you can run your favorite Linux tools with this board.
  • Supports TensorFlow Lite: No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.
  • Supports AutoML Vision Edge: Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge.

Description

The Coral Dev Board Mini is a single-board computer that provides fast machine learning (ML) inferencing in a small form factor. It’s primarily designed as an evaluation device for the Accelerator Module (a surface-mounted module that provides the Edge TPU), but it’s also a fully-functional embedded system you can use for various on-device ML projects.

Specifications

CPU MediaTek 8167s SoC (Quad-core Arm Cortex-A35)
GPU IMG PowerVR GE8300 (integrated in SoC)
ML accelerator Google Edge TPU coprocessor:
4 TOPS (int8); 2 TOPS per watt
RAM 2 GB LPDDR3
Flash memory 8 GB eMMC
Expandable memory Micro-SD card slot
Wireless Wi-Fi 5 (802.11a/b/g/n/ac); Bluetooth 5.0
Audio/video 3.5mm audio jack; digital PDM microphone; 2.54mm 2-pin speaker terminal;
micro HDMI (1.4); 24-pin FFC connector for MIPI-CSI2 camera (4-lane);
39-pin FFC connector for MIPI-DSI display (4-lane)
Input/output 40-pin GPIO header; 2x USB Type-C (USB 2.0)
Box Dimensions 383x220x166mm 
Box Weight 3.49kg

Dimensions

Part List

1 x Coral Dev Board Mini

Note

If you are looking for open source SBC for commercial and industrial needs. Seeed provides customization service based on BeagleBone series boards. Seeed Studio BeagleBone® Green(BBG) and Seeed Studio BeagleBone® Green Wireless (BBGW) provide more stable industrial deployment scenarios.

ECCN/HTS

HSCODE 8543709990
USHSCODE 8543709940
UPC

Coral Dev Board Mini

$136.00

The Coral Dev Board Mini is a single-board computer that provides fast machine learning (ML) inferencing in a small form factor. It’s primarily designed as an evaluation device for the Accelerator Module (a surface-mounted module that provides the Edge TPU), but it’s also a fully-functional embedded system you can use for various on-device ML projects.

Availability: In stock Categories: , ,
View cart

Coral Dev Board Mini

$136.00

The Coral Dev Board Mini is a single-board computer that provides fast machine learning (ML) inferencing in a small form factor. It’s primarily designed as an evaluation device for the Accelerator Module (a surface-mounted module that provides the Edge TPU), but it’s also a fully-functional embedded system you can use for various on-device ML projects.

View cart

PRODUCT DETAILS

Attention

This product has shipping restriction to certain countries. It can only be sent to countries and regions listed as below:  United States, Hong Kong, Austria, Belgium, Bulgaria, Croatia, Cyprus, Denmark, Estonia, Fiji, Germany, Greece, Hungary, Ireland, Italy, Latvia, Lithuania, Luxembourg, Malta, Netherlands, Poland, Portugal, Romania, Slovakia, Slovenia, Spain, Sweden, United Kingdom, Switzerland, Iceland, Liechtenstein, Norway, Turkey

Features

  • Performs high-speed ML inferencing: The onboard 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. See more performance benchmarks.
  • Provides a complete system: A single-board computer with SoC + ML + wireless connectivity, all on the board running a derivative of Debian Linux we call Mendel, so you can run your favorite Linux tools with this board.
  • Supports TensorFlow Lite: No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.
  • Supports AutoML Vision Edge: Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge.

Description

The Coral Dev Board Mini is a single-board computer that provides fast machine learning (ML) inferencing in a small form factor. It’s primarily designed as an evaluation device for the Accelerator Module (a surface-mounted module that provides the Edge TPU), but it’s also a fully-functional embedded system you can use for various on-device ML projects.

Specifications

CPU MediaTek 8167s SoC (Quad-core Arm Cortex-A35)
GPU IMG PowerVR GE8300 (integrated in SoC)
ML accelerator Google Edge TPU coprocessor:
4 TOPS (int8); 2 TOPS per watt
RAM 2 GB LPDDR3
Flash memory 8 GB eMMC
Expandable memory Micro-SD card slot
Wireless Wi-Fi 5 (802.11a/b/g/n/ac); Bluetooth 5.0
Audio/video 3.5mm audio jack; digital PDM microphone; 2.54mm 2-pin speaker terminal;
micro HDMI (1.4); 24-pin FFC connector for MIPI-CSI2 camera (4-lane);
39-pin FFC connector for MIPI-DSI display (4-lane)
Input/output 40-pin GPIO header; 2x USB Type-C (USB 2.0)
Box Dimensions 383x220x166mm 
Box Weight 3.49kg

Dimensions

Part List

1 x Coral Dev Board Mini

Note

If you are looking for open source SBC for commercial and industrial needs. Seeed provides customization service based on BeagleBone series boards. Seeed Studio BeagleBone® Green(BBG) and Seeed Studio BeagleBone® Green Wireless (BBGW) provide more stable industrial deployment scenarios.

ECCN/HTS

HSCODE 8543709990
USHSCODE 8543709940
UPC