Dataset Versions
v2
2024-12-05 3:09pm
Generated on Dec 5, 2024
3632 Total Images
View All Images
Dataset Split
Train Set 88%
3180Images
Valid Set 8%
300Images
Test Set 4%
152Images
Preprocessing
Auto-Orient: Applied
Tile: 2 rows x 2 columns
Modify Classes: 0 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -11° and +11°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images