ModelListedExternal

Zerodefect 1.0

A YOLOv5 Nano object detection model trained to identify surface defects on aircraft skin. Optimized for edge deployment on the Luckfox Pico Max (RV1106 SoC, 0.5 TOPS NPU).

Sourcehuggingface.co/prath0029/Zerodefect-1.0/tree/2a331f070d37ae4c3bf317b8f43d614e32eebc29

KindOtherVersionBestCgrade

Model source

Kind: Other
File size: 3.60–7.17 MB
Version: vBest
Updated: Oct 10, 2026
Source: Hugging Face

Source description

ZeroDefect YOLOv5 Nano — v1.0

Aircraft Skin Defect Detection (Edge-Deployable)

A YOLOv5 Nano object detection model trained to identify surface defects on aircraft skin. Optimized for edge deployment on the Luckfox Pico Max (RV1106 SoC, 0.5 TOPS NPU).

Model Formats

Format	File	Size	Use Case
PyTorch	`best.pt`	~3.8 MB	Training, fine-tuning, desktop inference
ONNX	`best.onnx`	~7.2 MB	Cross-platform CPU/GPU inference
RKNN	`best.rknn`	~2.6 MB	RV1106 NPU hardware-accelerated inference

Classes (7)

ID	Class	Description
0	`crack`	Structural cracks, fatigue lines
1	`dent`	Impact dents, surface deformations
2	`corrosion`	Rust, chemical wear, oxidation
3	`scratch`	Superficial scrapes, paint scratches
4	`paint-peel`	Flaking paint, coating degradation
5	`missing-head`	Missing rivet heads or fasteners
6	`defect`	Generic surface defect anomalies

Evaluation Results

Tested on 2,139 validation images (2,215 with detect.py)

Class	Precision	Recall	[email protected]	[email protected]:0.95
all	0.435	0.355	0.323	0.238
missing-head	0.404	0.640	0.528	0.350
dent	0.576	0.448	0.447	0.372
scratch	0.509	0.397	0.363	0.356
paint-peel	0.395	0.312	0.312	0.250
crack	0.483	0.262	0.283	0.220
corrosion	0.308	0.227	0.172	0.072
defect	0.374	0.199	0.154	0.044

Inference Speed: 2.8 ms/image (RTX 3050, batch 16) | 7.8 ms/image (single image)

Confusion Matrix

Precision-Recall Curve

PR Curve

F1-Confidence Curve

F1 Curve

Sample Detections

See the sample_detections/ folder for annotated detection results on validation images.

Training Details

Architecture: YOLOv5 Nano (1.77M parameters, 4.2 GFLOPs)
Epochs: 150
Image Size: 640x640
Batch Size: 16
Dataset: 22k+ train / 2.2k+ val images merged from 36 COCO-format Roboflow datasets
GPU: NVIDIA RTX 3050 6GB Laptop
Optimizer: SGD with cosine LR schedule
Augmentation: Standard YOLOv5 mosaic, mixup, HSV jitter

Quick Start: ONNX Inference

pip install onnxruntime opencv-python numpy
python infer_onnx.py --model best.onnx --image test.jpg --conf 0.25

Hardware Deployment (RV1106 NPU)

# Push to board
adb push best.rknn /userdata/

# Run on board (after cross-compiling rknn_model_zoo demo)
./rknn_yolov5_demo /userdata/best.rknn test.jpg

License

MIT License

Sources

1 source

Hugging FacePrimaryVersion 2a331f070d37ae4c3bf317b8f43d614e32eebc29

huggingface.co/prath0029/Zerodefect-1.0/tree/2a331f070d37ae4c3bf317b8f43d614e32eebc29

Verified Oct 10

Download files

Model artifacts

2 artifacts

best.onnx

onnx · 7.17 MB · SHA-256 fc2a70634e8d…bf05 · Hugging Face

Download file

best.pt

pt · 3.60 MB · SHA-256 add51aa71cf5…636d · Hugging Face

Download file

Source excerpts

2 excerpts

ReadmeAug 1huggingface.co/prath0029/Zerodefect-1.0

--- license: mit tags: - object-detection - pytorch - yolov5 - onnx - rknn - rv1106 - luckfox - aircraft-inspection - edge-ai metrics: - precision - recall - map model-index: - name: Zerodefect-1.0 results: - task: type: object-detection name: Object Detection dataset: type: custom name: Merged Aircraft Skin Defect & Corrosion Dataset metrics: - type: precision value: 0.435 name: Precision - type: recall value: 0.355 name: Recall - type: map value: 0.323 name: [email protected] - type: map value: 0.238 name: [email protected]:0.95 --- # ZeroDefect YOLOv5 Nano — v1.0 ### Aircraft Skin Defect Detection (Edge-Deployable) A YOLOv5 Nano object detection model trained to identify surface defects on aircraft skin. Optimized for edge deployment on the **Luckfox Pico Max (RV1106 SoC, 0.5 TOPS NPU)**. --- ## Model Formats | Format | File | Size | Use Case | |--------|------|------|----------| | PyTorch | `best.pt` | ~3.8 MB | Training, fine-tuning, desktop inference | | ONNX | `best.onnx` | ~7.2 MB | Cross-platform CPU/GPU inference | | RKNN | `best.rknn` | ~2.6 MB | RV1106 NPU hardware-accelerated inference | --- ## Classes (7) | ID | Class | Description | |----|-------|-------------| | 0 | `crack` | Structural cracks, fatigue lines | | 1 | `dent` | Impact dents, surface deformations | | 2 | `corrosion` | Rust, chemical wear, oxidation | | 3 | `scratch` | Superficial scrapes, paint scratches | | 4 | `paint-peel` | Flaking paint, coating degradation | | 5 | `missing-head` | Missing rivet heads or fasteners | | 6 | `defect` | Generic surface defect anomalies | --- ## Evaluation Results **Tested on 2,139 validation images (2,215 with detect.py)** | Class | Precision | Recall | [email protected] | [email protected]:0.95 | |-------|-----------|--------|---------|---------------| | **all** | **0.435** | **0.355** | **0.323** | **0.238** | | missing-head | 0.404 | 0.640 | 0.528 | 0.350 | | dent | 0.576 | 0.448 | 0.447 | 0.372 | | scratch | 0.509 | 0.397 | 0.363 | 0.356 | | paint-peel | 0.395 | 0.312 | 0.312 | 0.250 | | crack | 0.483 | 0.262 | 0.283 | 0.220 | | corrosion | 0.308 | 0.227 | 0.172 | 0.072 | | defect | 0.374 | 0.199 | 0.154 | 0.044 | **Inference Speed**: 2.8 ms/image (RTX 3050, batch 16) | 7.8 ms/image (single image) ### Confusion Matrix ![Confusion Matrix](evaluation/confusion_matrix.png) ### Precision...

NoteAug 1huggingface.co/prath0029/Zerodefect-1.0

Source context: 0 downloads · 0 likes · Pipeline object-detection · Repo prath0029/Zerodefect-1.0