Dataset Versions
v8
2024-12-15 3:27pm
Generated on Dec 15, 2024
135 Total Images
View All Images
Dataset Split
Train Set 80%
108Images
Valid Set 7%
9Images
Test Set 13%
18Images
Preprocessing
Auto-Orient: Applied
Static Crop: 31-67% Horizontal Region, 36-73% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 3 rows x 3 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±5° Horizontal, ±5° Vertical
Hue: Between -15° and +15°
Exposure: Between -10% and +10%
Bounding Box: Exposure: Between -2% and +2%