Dataset Versions

v4

2023-12-03 1:00am

Generated on Dec 3, 2023

Dataset Split

Train Set 88%
4716Images
Valid Set 8%
448Images
Test Set 4%
224Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Saturation: Between -15% and +15%
Brightness: Between -10% and +10%