Dataset Versions
v3
2024-07-08 3:21pm
Generated on Jul 8, 2024
670 Total Images
View All Images
Dataset Split
Train Set 92%
614Images
Valid Set 5%
32Images
Test Set 4%
24Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require at least 80% of images to contain annotations.
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Brightness: Between -15% and +15%