Dataset Versions

v2

2022-12-14 2:48pm

Generated on Dec 14, 2022

Dataset Split

Train Set 88%
519Images
Valid Set 8%
49Images
Test Set 4%
25Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 14 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 41% Maximum Zoom
Rotation: Between -37° and +37°
Saturation: Between -63% and +63%