Dataset Versions
v2
2024-07-19 12:42pm
Generated on Jul 19, 2024
1396 Total Images
View All Images
Dataset Split
Train Set 87%
1218Images
Valid Set 9%
120Images
Test Set 4%
58Images
Preprocessing
Auto-Orient: Applied
Static Crop: 19-86% Horizontal Region, 14-90% Vertical Region
Resize: Stretch to 1024x1024
Auto-Adjust Contrast: Using Contrast Stretching
Grayscale: Applied
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Rotation: Between -10° and +10°
Shear: ±14° Horizontal, ±14° Vertical
Grayscale: Apply to 24% of images
Hue: Between -24° and +24°
Saturation: Between -33% and +33%
Brightness: Between -24% and +24%
Exposure: Between -15% and +15%
Blur: Up to 2.6px
Noise: Up to 1.88% of pixels
Mosaic: Applied
Bounding Box: Shear: ±7° Horizontal, ±7° Vertical
Bounding Box: Brightness: Between -15% and +15%
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Blur: Up to 2.6px
Bounding Box: Noise: Up to 0.38% of pixels