Dataset Versions

v1

Thick_1193

Generated on Jun 28, 2024

Dataset Split

Train Set 91%
1080Images
Valid Set 9%
113Images
Test Set %
0Images

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 15% of images
Hue: Between -92° and +92°
Saturation: Between -67% and +67%
Brightness: Between -40% and +40%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 1.56% of pixels