Dataset Versions
v4
2023-06-19 3:44pm
Generated on Jun 19, 2023
2835 Total Images
View All Images
Dataset Split
Train Set 89%
2532Images
Valid Set 8%
224Images
Test Set 3%
79Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (white 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: 2
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 10% of images
Exposure: Between -10% and +10%
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Blur: Up to 1px
Bounding Box: Noise: Up to 5% of pixels