Dataset Versions
v1
2022-09-20 3:17pm
Generated on Sep 20, 2022
1012 Total Images
View All ImagesDataset Split
Train Set 87%
885Images
Valid Set 8%
84Images
Test Set 4%
43Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Augmentations
Outputs per training example: 3
Rotation: Between -27° and +27°
Shear: ±15° Horizontal, ±15° Vertical
Hue: Between -25° and +25°
Brightness: Between -25% and +25%
Exposure: Between -16% and +16%
Blur: Up to 1.25px
Noise: Up to 4% of pixels