Dataset Versions
Versions
v5
2024-07-01 11:09am
Generated on Jul 1, 2024
446 Total Images
View All Images
Dataset Split
Train Set 87%
390Images
Valid Set 8%
37Images
Test Set 4%
19Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 1024x768
Modify Classes: 1 remapped, 0 dropped
Filter Null: Require at least 80% of images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal
Shear: ±6° Horizontal, ±9° Vertical
Exposure: Between -7% and +7%
Noise: Up to 1.01% of pixels
Cutout: 3 boxes with 6% size each