Dataset Versions
Versions
v1
2022-12-12 1:47pm
Generated on Dec 12, 2022
1980 Total Images
View All Images
Dataset Split
Train Set 87%
1731Images
Valid Set 8%
166Images
Test Set 4%
83Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x960
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±30° Horizontal, ±30° Vertical
Hue: Between -78° and +78°
Saturation: Between -25% and +25%
Brightness: Between -29% and +29%