Dataset Versions
v3
2024-01-14 12:44am
Generated on Jan 13, 2024
1273 Total Images
View All Images
Dataset Split
Train Set 88%
1116Images
Valid Set 6%
77Images
Test Set 6%
80Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 240x240
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require at least 40% of images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Saturation: Between -15% and +15%
Brightness: Between 0% and +25%