Dataset Versions
v4
2023-06-21 1:54am
Generated on Jun 20, 2023
3716 Total Images
View All Images
Dataset Split
Train Set 88%
3255Images
Valid Set 7%
260Images
Test Set 5%
201Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Modify Classes: 0 remapped, 15 dropped
Filter Null: Do not filter any null images.
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Grayscale: Apply to 10% of images
Saturation: Between -10% and +10%
Exposure: Between -10% and +10%
Blur: Up to 1.5px