Geolamp2 Dataset

v3

2024-06-26 4:58pm

Generated on Jun 26, 2024

Dataset Split

Train Set 88%
978Images
Valid Set 8%
93Images
Test Set 4%
46Images

Preprocessing

Auto-Orient: Applied
Static Crop: 21-75% Horizontal Region, 0-96% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Brightness: Between -17% and +17%