Reflective_types Computer Vision Dataset
636 Total Images
View All Images
Dataset Split
Train Set 95%
606Images
Valid Set 3%
17Images
Test Set 2%
13Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 432x432
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images