Overview
Coral USB Accelerator is a Google Coral Edge TPU device sold by Seeed Studio, rated by Seeed at 4 TOPS (int8). Seeed publishes a fixed price for this configuration.
Key Features
- Coral USB Accelerator rated at 4 TOPS (int8)
- ML Accelerator: Google Edge TPU coprocessor: 4 TOPS (int8); 2 TOPS per watt
- Connector: USB 3.0 (USB 3.1 Gen 1) port and cable (SuperSpeed, 5 Gbps) Included cable is USB Type-C to Type-A, and 300 mm (12 in)
- Dimensions: 65 mm x 30 mm
- Performs high-speed ML inferencing: High-speed TensorFlow Lite inferencing with low power, small footprint, local inferencing.
- Supports all major platforms: Connects via USB 3.0 Type-C to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10.
Ideal For
developers running quantised TensorFlow Lite models at the edge on an Edge TPU rather than a GPU
ML Accelerator
Google Edge TPU coprocessor: 4 TOPS (int8); 2 TOPS per watt
Connector
USB 3.0 (USB 3.1 Gen 1) port and cable (SuperSpeed, 5 Gbps) Included cable is USB Type-C to Type-A, and 300 mm (12 in) in length
Dimensions
65 mm x 30 mm
Performs high-speed ML inferencing
High-speed TensorFlow Lite inferencing with low power, small footprint, local inferencing.
Supports all major platforms
Connects via USB 3.0 Type-C to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10.
Supports TensorFlow Lite
No need to build models from the ground up. Tensorflow Lite models can be compiled to run on the edge TPE.
Supports AutoML Vision Edge
easily build and deploy fast, high-accuracy custom image classification models at the edge.
Feature
Compatible with Google Cloud.
Feature
Object tracking
Feature
Image recognition
Feature
PoseNet pose estimation
Prices may vary. Verify on vendor site.
Quick Specs
- ML Accelerator
- Google Edge TPU coprocessor: 4 TOPS (int8); 2 TOPS per watt
- Connector
- USB 3.0 (USB 3.1 Gen 1) port and cable (SuperSpeed, 5 Gbps) Included cable is USB Type-C to Type-A, and 300 mm (12 in) in length
- Dimensions
- 65 mm x 30 mm
- Performs high-speed ML inferencing
- High-speed TensorFlow Lite inferencing with low power, small footprint, local inferencing.
- Supports all major platforms
- Connects via USB 3.0 Type-C to any system running Debian Linux (including Raspberry Pi), macOS, or Windows 10.
- Supports TensorFlow Lite
- No need to build models from the ground up. Tensorflow Lite models can be compiled to run on the edge TPE.