Dataset Versions
v5
2023-05-22 11:56pm
Generated on May 22, 2023
74 Total Images
View All Images
Dataset Split
Train Set 57%
42Images
Valid Set 22%
16Images
Test Set 22%
16Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Brightness: Between -12% and +12%
Exposure: Between -25% and +25%
Blur: Up to 2.5px