Dataset Versions
v3
2024-12-22 12:45pm
Generated on Dec 22, 2024
1920 Total Images
View All Images
Dataset Split
Train Set 88%
1680Images
Valid Set 8%
160Images
Test Set 4%
80Images
Preprocessing
Auto-Orient: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Dynamic Crop: Class: kista
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -9° and +9°
Brightness: Between -20% and +20%
Bounding Box: Flip: Horizontal
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Exposure: Between -10% and +10%