PTIT

documents

Instance Segmentation

documents Image Dataset

v5

2024-03-26 8:58pm

Generated on Mar 26, 2024

Dataset Split

Train Set 92%
696Images
Valid Set 4%
30Images
Test Set 4%
30Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Hue: Between -25° and +25°
Saturation: Between -25% and +25%
Brightness: Between -20% and +20%
Exposure: Between -15% and +15%
Blur: Up to 1.2px
Noise: Up to 0.97% of pixels