OpenParable
Skip to content
← Back to skills

Yolo Detection 2026 Coral Tpu Win Wsl

Apps & Automation
yolo-detection-2026-coral-tpu-win-wsl

Yolo Detection 2026 Coral Tpu Win Wsl is an Agent Skill for apps & automation published in the SharpAI/DeepCamera repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Google Coral Edge TPU — real-time object detection natively via Windows WSL

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/SharpAI/DeepCamera/blob/HEAD/skills/detection/yolo-detection-2026-coral-tpu-win-wsl/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/yolo-detection-2026-coral-tpu-win-wsl, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Coral TPU Object Detection (Windows WSL)

Real-time object detection natively utilizing the Google Coral Edge TPU accelerator on your local hardware via Windows Subsystem for Linux (WSL). Detects 80 COCO classes (person, car, dog, cat, etc.) with ~4ms inference on 320x320 input.

Requirements

  • Google Coral USB Accelerator (USB 3.0 port recommended)
  • WSL2 installed and running on Windows
  • usbipd-win installed on the Windows host

How It Works

┌─────────────────────────────────────────────────────┐
│ Host (Aegis-AI on Windows)                          │
│   frame.jpg → /tmp/aegis_detection/                 │
│   stdin  ──→ ┌──────────────────────────────┐       │
│              │ WSL Container / Environment   │       │
│              │   detect.py                   │       │
│              │   ├─ loads _edgetpu.tflite     │       │
│              │   ├─ reads frame from disk     │       │
│              │   └─ runs inference on TPU    │       │
│   stdout ←── │   → JSONL detections          │       │
│              └──────────────────────────────┘       │
│   USB ──→ usbipd-win bridge to WSL                  │
└─────────────────────────────────────────────────────┘
  1. Aegis writes camera frame JPEG to shared /tmp/aegis_detection/ workspace
  2. Sends frame event via stdin JSONL to the WSL Python instance
  3. detect.py invokes PyCoral and executes natively on the mapped USB Edge TPU inside Linux
  4. Returns detections event via stdout JSONL back to Windows Host

Performance

Input SizeInferenceOn-chipNotes
320x320~4ms100%Fully on TPU, best for real-time
640x640~20msPartialSome layers on CPU (model segmented)

Cooling: The USB Accelerator aluminum case acts as a heatsink. If too hot to touch during continuous inference, it will thermal-throttle. Consider active cooling or clock_speed: standard.

Installation

Windows (WSL)

Run deploy.bat — this will:

  1. Verify usbipd is installed and bind the 18d1:9302 and 1a6e:089a Edge TPU hardware IDs.
  2. Setup a Python virtual environment exclusively within WSL.
  3. Install the Edge TPU libraries and dependencies within the WSL boundary.
  4. Auto-attach the device using usbipd seamlessly during invocation.