GPA

papeador

Instance Segmentation

papeador Image Dataset

v1

2023-11-28 9:59am

Generated on Nov 28, 2023

Dataset Split

Train Set 78%
600Images
Valid Set 22%
173Images
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
Rotation: Between -24° and +24°
Shear: ±19° Horizontal, ±20° Vertical
Saturation: Between -10% and +10%
Brightness: Between -19% and +19%
Exposure: Between -17% and +17%
Blur: Up to 1px
Noise: Up to 13% of pixels
Cutout: 25 boxes with 2% size each