Dataset Versions
Versions
v1
2024-09-27 6:34pm
Generated on Sep 27, 2024
3126 Total Images
View All Images
Dataset Split
Train Set 88%
2736Images
Valid Set 8%
260Images
Test Set 4%
130Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 40-76% Vertical Region
Resize: Stretch to 224x224
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 1 rows x 2 columns
Augmentations
Outputs per training example: 3
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 21% of images
Hue: Between -22° and +22°
Saturation: Between -32% and +32%
Brightness: Between -21% and +21%
Blur: Up to 1px
Noise: Up to 0.14% of pixels