yolo-detection-2026-coral-tpu-macos

Name: yolo-detection-2026-coral-tpu-macos
Author: SharpAI

2.9kstars460forks

How to install yolo-detection-2026-coral-tpu-macos?

sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos

$npx -y skills add SharpAI/DeepCamera --skill yolo-detection-2026-coral-tpu-macos

Installs into the current project.

Summary

Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

Files · 1

View on GitHub

SKILL.md

1	# Coral TPU Object Detection
2
3	Real-time object detection natively utilizing the Google Coral Edge TPU accelerator on your local hardware. Detects 80 COCO classes (person, car, dog, cat, etc.) with ~4ms inference on 320x320 input.
4
5	## Requirements
6
7	- Python 3.9–3.13
8
9	## How It Works
10
11	```
12	┌─────────────────────────────────────────────────────┐
13	│ Host (Aegis-AI) │
14	│ frame.jpg → /tmp/aegis_detection/ │
15	│ stdin ──→ ┌──────────────────────────────┐ │
16	│ │ Native Python Environment │ │
17	│ │ detect.py │ │
18	│ │ ├─ loads _edgetpu.tflite │ │
19	│ │ ├─ reads frame from disk │ │
20	│ │ └─ runs inference on TPU │ │
21	│ stdout ←── │ → JSONL detections │ │
22	│ └──────────────────────────────┘ │
23	│ USB ──→ Native System USB / edgetpu drivers │
24	└─────────────────────────────────────────────────────┘
25	```
26
27	1. Aegis writes camera frame JPEG to shared `/tmp/aegis_detection/` workspace
28	2. Sends `frame` event via stdin JSONL to the local Python instance
29	3. `detect.py` invokes PyCoral and executes natively on the mapped USB Edge TPU
30	4. Returns `detections` event via stdout JSONL
31
32	## Platform Setup
33
34	### Linux
35	```bash
36	# Uses the official apt-get google-coral packages natively
37	./deploy.sh
38	```
39
40	### macOS
41	```bash
42	# Downloads and installs the libedgetpu OS payload framework inline
43	./deploy.sh
44	```
45
46	> Important Deployment Notice: The updated `deploy.sh` script will natively halt execution and prompt you securely for your OS `sudo` password to securely register the USB drivers (`libedgetpu`) system-wide. If you refuse the prompt, it gracefully outputs the exact terminal instructions for you to configure it manually.
47
48	## Performance
49
50	\| Input Size \| Inference \| On-chip \| Notes \|
51	\|-----------\|-----------\|---------\|-------\|
52	\| 320x320 \| ~4ms \| 100% \| Fully on TPU, best for real-time \|
53	\| 640x640 \| ~20ms \| Partial \| Some layers on CPU (model segmented) \|
54
55	> 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`.
56
57	## Protocol
58
59	Same JSONL as `yolo-detection-2026`:
60
61	### Skill → Aegis (stdout)
62	```jsonl
63	{"event": "ready", "model": "yolo26n_edgetpu", "device": "coral", "format": "edgetpu_tflite", "tpu_count": 1, "classes": 80}
64	{"event": "detections", "frame_id": 42, "camera_id": "front_door", "objects": [{"class": "person", "confidence": 0.85, "bbox": [100, 50, 300, 400]}]}
65	{"event": "perf_stats", "total_frames": 50, "timings_ms": {"inference": {"avg": 4.1, "p50": 3.9, "p95": 5.2}}}
66	```
67
68	### Bounding Box Format
69	`[x_min, y_min, x_max, y_max]` — pixel coordinates (xyxy).
70
71	## Installation
72
73	### Linux / macOS
74	```bash
75	./deploy.sh
76	```
77
78	The deployer builds the local Python virtual environment and installs the Edge TPU runtime. No Docker required.

People who liked this also viewed

6 picks

Type

find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 20262.6M27k
grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026633k182k
vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026573k29k
improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026522k182k
setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026454k182k
triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026424k182k

yolo-detection-2026-coral-tpu-macos

2.9kstars460forks

View on GitHub

How to install yolo-detection-2026-coral-tpu-macos?

sharpai/deepcamera/yolo-detection-2026-coral-tpu-macos

$npx -y skills add SharpAI/DeepCamera --skill yolo-detection-2026-coral-tpu-macos

Installs into the current project.

Summary

Google Coral Edge TPU — real-time object detection natively (macOS / Linux)

Files · 1

View on GitHub

SKILL.md

1	# Coral TPU Object Detection
2
3	Real-time object detection natively utilizing the Google Coral Edge TPU accelerator on your local hardware. Detects 80 COCO classes (person, car, dog, cat, etc.) with ~4ms inference on 320x320 input.
4
5	## Requirements
6
7	- Python 3.9–3.13
8
9	## How It Works
10
11	```
12	┌─────────────────────────────────────────────────────┐
13	│ Host (Aegis-AI) │
14	│ frame.jpg → /tmp/aegis_detection/ │
15	│ stdin ──→ ┌──────────────────────────────┐ │
16	│ │ Native Python Environment │ │
17	│ │ detect.py │ │
18	│ │ ├─ loads _edgetpu.tflite │ │
19	│ │ ├─ reads frame from disk │ │
20	│ │ └─ runs inference on TPU │ │
21	│ stdout ←── │ → JSONL detections │ │
22	│ └──────────────────────────────┘ │
23	│ USB ──→ Native System USB / edgetpu drivers │
24	└─────────────────────────────────────────────────────┘
25	```
26
27	1. Aegis writes camera frame JPEG to shared `/tmp/aegis_detection/` workspace
28	2. Sends `frame` event via stdin JSONL to the local Python instance
29	3. `detect.py` invokes PyCoral and executes natively on the mapped USB Edge TPU
30	4. Returns `detections` event via stdout JSONL
31
32	## Platform Setup
33
34	### Linux
35	```bash
36	# Uses the official apt-get google-coral packages natively
37	./deploy.sh
38	```
39
40	### macOS
41	```bash
42	# Downloads and installs the libedgetpu OS payload framework inline
43	./deploy.sh
44	```
45
46	> Important Deployment Notice: The updated `deploy.sh` script will natively halt execution and prompt you securely for your OS `sudo` password to securely register the USB drivers (`libedgetpu`) system-wide. If you refuse the prompt, it gracefully outputs the exact terminal instructions for you to configure it manually.
47
48	## Performance
49
50	\| Input Size \| Inference \| On-chip \| Notes \|
51	\|-----------\|-----------\|---------\|-------\|
52	\| 320x320 \| ~4ms \| 100% \| Fully on TPU, best for real-time \|
53	\| 640x640 \| ~20ms \| Partial \| Some layers on CPU (model segmented) \|
54
55	> 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`.
56
57	## Protocol
58
59	Same JSONL as `yolo-detection-2026`:
60
61	### Skill → Aegis (stdout)
62	```jsonl
63	{"event": "ready", "model": "yolo26n_edgetpu", "device": "coral", "format": "edgetpu_tflite", "tpu_count": 1, "classes": 80}
64	{"event": "detections", "frame_id": 42, "camera_id": "front_door", "objects": [{"class": "person", "confidence": 0.85, "bbox": [100, 50, 300, 400]}]}
65	{"event": "perf_stats", "total_frames": 50, "timings_ms": {"inference": {"avg": 4.1, "p50": 3.9, "p95": 5.2}}}
66	```
67
68	### Bounding Box Format
69	`[x_min, y_min, x_max, y_max]` — pixel coordinates (xyxy).
70
71	## Installation
72
73	### Linux / macOS
74	```bash
75	./deploy.sh
76	```
77
78	The deployer builds the local Python virtual environment and installs the Edge TPU runtime. No Docker required.

People who liked this also viewed

6 picks

Type