Dataset Versions
v3
2024-10-27 5:53pm
Generated on Oct 27, 2024
631 Total Images
View All Images
Dataset Split
Train Set 88%
558Images
Valid Set 8%
49Images
Test Set 4%
24Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require at least 71% of images to contain annotations.
Augmentations
Outputs per training example: 3
Rotation: Between -13° and +13°
Shear: ±10° Horizontal, ±10° Vertical
Exposure: Between -10% and +10%
Blur: Up to 1.3px
Cutout: 3 boxes with 10% size each