Dataset Versions
Versions
v1
2023-10-15 12:11pm
Generated on Oct 15, 2023
1580 Total Images
View All Images
Dataset Split
Train Set 87%
1380Images
Valid Set 9%
136Images
Test Set 4%
64Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-81% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 2 rows x 2 columns
Modify Classes: 0 remapped, 0 dropped
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Cutout: 3 boxes with 10% size each