Dataset Versions
Versions
v1
2022-09-12 11:07am
Generated on Sep 12, 2022
734 Total Images
View All Images
Dataset Split
Train Set 92%
678Images
Valid Set 4%
28Images
Test Set 4%
28Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Exposure: Between -8% and +8%
Blur: Up to 2.75px
Noise: Up to 5% of pixels