Dataset Versions
v1
2024-03-23 2:10am
Generated on Mar 22, 2024
496 Total Images
View All Images
Dataset Split
Train Set 92%
456Images
Valid Set 4%
20Images
Test Set 4%
20Images
Preprocessing
Auto-Orient: Applied
Static Crop: 38-77% Horizontal Region, 30-84% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
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, 25% Maximum Zoom
Rotation: Between -12° and +12°
Shear: ±14° Horizontal, ±14° Vertical
Grayscale: Apply to 25% of images
Saturation: Between -24% and +24%
Brightness: Between -24% and +24%
Exposure: Between -14% and +14%
Blur: Up to 3.3px
Noise: Up to 2.75% of pixels
Mosaic: Applied