Dataset Versions
v2
2023-06-14 4:13pm
Generated on Jun 14, 2023
2861 Total Images
View All Images
Dataset Split
Train Set 86%
2458Images
Valid Set 10%
277Images
Test Set 4%
126Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Modify Classes: 0 remapped, 15 dropped
Filter Null: Do not filter any null images.
Augmentations
Outputs per training example: 3
Exposure: Between -10% and +10%
Bounding Box: Shear: ±5° Horizontal, ±5° Vertical
Bounding Box: Blur: Up to 0.5px
Bounding Box: Noise: Up to 5% of pixels