Dataset Versions
v2
2023-08-31 10:50am
Generated on Aug 31, 2023
275 Total Images
View All Images
Dataset Split
Train Set 87%
240Images
Valid Set 8%
23Images
Test Set 4%
12Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -37° and +37°
Shear: ±26° Horizontal, ±33° Vertical
Grayscale: Apply to 79% of images
Hue: Between -99° and +99°
Saturation: Between -65% and +65%
Brightness: Between 0% and +42%
Exposure: Between -34% and +34%
Blur: Up to 0.25px
Noise: Up to 5% of pixels
Cutout: 11 boxes with 4% size each
Mosaic: Applied