Dataset Versions

v10

2023-10-24 8:50am

Generated on Oct 24, 2023

Dataset Split

Train Set 71%
2700Images
Valid Set 22%
837Images
Test Set 7%
261Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 800x1200
Auto-Adjust Contrast: Using Contrast Stretching
Tile: 3 rows x 3 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Brightness: Between -20% and +20%
Exposure: Between -6% and +6%
Mosaic: Applied