Dataset Versions
v4
2024-09-29 4:23pm
Generated on Sep 29, 2024
13464 Total Images
View All Images
Dataset Split
Train Set 92%
12348Images
Valid Set 5%
684Images
Test Set 3%
432Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 1024x768
Auto-Adjust Contrast: Using Contrast Stretching
Tile: 4 rows x 3 columns
Modify Classes: 1 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -12% and +12%
Brightness: Between -15% and +15%
Exposure: Between -5% and +5%