Dataset Versions
v1
2023-12-04 6:06pm
Generated on Dec 4, 2023
3100 Total Images
View All Images
Dataset Split
Train Set 87%
2709Images
Valid Set 8%
255Images
Test Set 4%
136Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 0 remapped, 1 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
Rotation: Between -19° and +19°
Shear: ±26° Horizontal, ±28° Vertical
Grayscale: Apply to 25% of images
Brightness: Between -33% and +33%
Blur: Up to 4px
Noise: Up to 10% of pixels
Cutout: 17 boxes with 16% size each
Bounding Box: Blur: Up to 5px