Dataset Versions
v6
2023-07-07 3:22pm
Generated on Jul 7, 2023
2003 Total Images
View All Images
Dataset Split
Train Set 89%
1776Images
Valid Set 7%
148Images
Test Set 4%
79Images
Preprocessing
Resize: Fit (black edges) in 640x640
Modify Classes: 2 remapped, 0 dropped
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±18° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Exposure: Between -15% and +15%
Blur: Up to 1.5px
Noise: Up to 5% of pixels