Dataset Versions
v3
2023-01-10 1:24pm
Generated on Jan 10, 2023
720 Total Images
View All Images
Dataset Split
Train Set 88%
630Images
Valid Set 8%
60Images
Test Set 4%
30Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Upside Down
Crop: 0% Minimum Zoom, 5% Maximum Zoom
Rotation: Between -1° and +1°
Shear: ±1° Horizontal, ±1° Vertical
Brightness: Between 0% and +33%
Exposure: Between -20% and +20%
Blur: Up to 1px