Dataset Versions
v5
2024-06-20 3:12am
Generated on Jun 20, 2024
1248 Total Images
View All Images
Dataset Split
Train Set 88%
1092Images
Valid Set 8%
104Images
Test Set 4%
52Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x640
Augmentations
Outputs per training example: 3
Hue: Between -20° and +20°
Saturation: Between -30% and +30%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%
Blur: Up to 2.5px
Noise: Up to 0.5% of pixels