Dataset Versions
v3
2023-05-06 11:02am
Generated on May 6, 2023
1152 Total Images
View All Images
Dataset Split
Train Set 88%
1008Images
Valid Set 8%
96Images
Test Set 4%
48Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 2 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 15% of images
Noise: Up to 10% of pixels
Cutout: 3 boxes with 15% size each
Mosaic: Applied
Bounding Box: Brightness: Between -15% and +15%
Bounding Box: Exposure: Between -15% and +15%