Dataset Versions
v2
2024-07-10 6:37am
Generated on Jul 10, 2024
77 Total Images
View All Images
Dataset Split
Train Set 90%
69Images
Valid Set 10%
8Images
Test Set %
0Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Rotation: Between -5° and +5°
Shear: ±8° Horizontal, ±8° Vertical
Saturation: Between -25% and +25%
Blur: Up to 1.1px
Noise: Up to 0.3% of pixels
Cutout: 3 boxes with 9% size each