UNT-DETECCION DE MACIZO ROCOS FRACTURADO

Object Detection

Dataset Versions

v13

2023-07-17 12:16pm

Generated on Jul 17, 2023

Popular Download Formats

Pascal VOC XML
Common XML annotation format for local data munging (pioneered by ImageNet).
PaliGemma
PaliGemma JSONL format used for fine-tuning PaliGemma, Google's open multimodal vision model.
CreateML JSON
CreateML JSON format is used with Apple's CreateML and Turi Create tools.
Other Formats
Choose another format.

Dataset Split

Train Set 87%
1908Images
Valid Set 8%
184Images
Test Set 4%
92Images

Preprocessing

Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -45° and +45°
Shear: ±30° Horizontal, ±20° Vertical
Hue: Between -85° and +85°
Saturation: Between -50% and +50%
Brightness: Between -40% and +40%
Exposure: Between -20% and +20%
Blur: Up to 1.25px
Noise: Up to 10% of pixels
Cutout: 10 boxes with 10% size each
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Bounding Box: Rotation: Between -45° and +45°
Bounding Box: Shear: ±30° Horizontal, ±20° Vertical
Bounding Box: Blur: Up to 1.25px
Bounding Box: Noise: Up to 10% of pixels