Dataset Versions
v2
2024-09-03 5:13am
Generated on Sep 3, 2024
438 Total Images
View All Images
Dataset Split
Train Set 93%
408Images
Valid Set 5%
20Images
Test Set 2%
10Images
Preprocessing
Auto-Orient: Applied
Static Crop: 6-96% Horizontal Region, 29-71% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Modify Classes: 1 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 12% Maximum Zoom
Rotation: Between -15° and +15°
Brightness: Between -22% and +22%
Exposure: Between -10% and +10%
Noise: Up to 1.17% of pixels