LLL+NM Merged Segmentation - Stomata 9.13.25

Instance Segmentation

LLL+NM Merged Segmentation - Stomata 9.13.25 Dataset

v1

2024-09-15 2:24am

Generated on Sep 15, 2024

Dataset Split

Train Set 86%
363Images
Valid Set 9%
39Images
Test Set 5%
19Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Grayscale: Apply to 12% of images
Hue: Between -20° and +20°
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 1px