esper

scfive4

Instance Segmentation

scfive4 Image Dataset

v3

2024-05-24 10:05am

Generated on May 24, 2024

Dataset Split

Train Set 87%
651Images
Valid Set 8%
63Images
Test Set 4%
31Images

Preprocessing

Auto-Orient: Applied
Resize: Fit (white edges) in 1024x1024

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Grayscale: Apply to 21% of images
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 0.5px