Dataset Versions

v16

2024-12-20 10:29am

Generated on Dec 20, 2024

Dataset Split

Train Set 87%
1675Images
Valid Set 7%
132Images
Test Set 7%
126Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1024x1024
Tile: 2 rows x 2 columns
Filter Null: Require at least 95% of images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -10° and +10°
Brightness: Between -5% and +5%

Similar Projects

See More