Coral Dev Board - 4GB
- Coral Dev Board Datasheet
- Getting Started with Coral Dev Board
- Coral Dev Board I/O Pin Connections
- Coral Dev Board Camera Connection
- Coral Dev Board Serial Console Connection
- Update or Flash Coral Dev Board
The Coral Dev Board with 4GB RAM stands as an exemplary single-board computer (SBC) designed explicitly for rapid on-device machine learning (ML) prototyping and scaled production. It integrates cutting-edge components, empowering developers to accelerate ML inferencing within a compact form factor.
High-Speed ML Inferencing
At the heart of its capabilities lies the onboard Edge TPU coprocessor, showcasing unparalleled performance. Delivering an astounding 4 trillion operations per second (4 TOPS int8) with an exceptional power efficiency of 2 TOPS per watt, this board executes state-of-the-art mobile vision models, achieving approximately 400 FPS for models like MobileNet v2.
Complete System Integration
A holistic solution, this SBC amalgamates System-on-Chip (SoC), ML processing, and wireless connectivity seamlessly on a single board. Operating on Mendel, a Debian Linux derivative, it empowers developers to utilize their preferred Linux tools effortlessly.
TensorFlow Lite Compatibility
Simplified model deployment is facilitated by TensorFlow Lite support, enabling the seamless compilation and execution of models on the Edge TPU without necessitating intricate model building from scratch.
Prototyping to Production Scalability
Uniquely addressing manufacturing needs, the modular design allows for the removal of the System-on-Module (SoM) from the baseboard. Available for bulk purchase, the SoM seamlessly integrates into custom hardware setups, fostering a swift transition from prototype to mass production.
Some Examples of Possible Applications
This Dev Board finds versatile applications across various domains:
- IoT and Edge Computing: Powering intelligent IoT devices for smart homes, industrial automation, and environmental monitoring.
- Computer Vision Solutions: Enabling real-time object recognition, gesture detection, and facial recognition.
- Healthcare Innovations: Facilitating ML-based diagnostics, monitoring systems, and medical imaging analysis.
- Autonomous Systems: Empowering drones, robots, and autonomous vehicles with ML-driven decision-making capabilities.
- CPU: NXP i.MX 8M SoC (quad Cortex-A53, Cortex-M4F)
- GPU: Integrated GC7000 Lite Graphics
- ML Accelerator: Google Edge TPU coprocessor (4 TOPS int8; 2 TOPS per watt)
- RAM: 4 GB LPDDR4
- Flash Memory: 8 GB eMMC, MicroSD slot
- Wireless: Wi-Fi 2x2 MIMO (802.11b/g/n/ac 2.4/5GHz), Bluetooth 4.2
- USB: Type-C OTG, Type-C power, Type-A 3.0 host, Micro-B serial console
- LAN: Gigabit Ethernet port
- Audio: 3.5mm audio jack (CTIA compliant), Digital PDM microphone (x2), 2.54mm 4-pin terminal for stereo speakers
- Video: HDMI 2.0a (full size), 39-pin FFC connector for MIPI-DSI display (4-lane), 24-pin FFC connector for MIPI-CSI2 camera (4-lane)
- GPIO: 3.3V power rail, 40 - 255 ohms programmable impedance, ~82 mA max current
- Power: 5V DC (USB Type-C)
Pin Functions on Coral Dev GPIO
USB Type-C Power Interface
Specifications of Coral Dev Fan (Included)
- Airflow: 4.9 CFM / 138 LPM
- Peak Power: 0.65 W
- Static Pressure (0.17 in-H2O): 42 Pa
- Speed Rating: 9000 (RPM)
- Voltage Compatibility: 5V DC
- Coral Dev Board - 4GB RAM