Dataset Versions
v1
2024-10-08 9-03am - Lots of augs
Generated on Oct 8, 2024
2600 Total Images
View All Images
Dataset Split
Train Set 92%
2400Images
Valid Set 4%
100Images
Test Set 4%
100Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -10° and +10°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -15% and +15%
Exposure: Between -5% and +5%
Blur: Up to 1px
Noise: Up to 0.5% of pixels