korrawiz

train_set

Instance Segmentation

train_set Image Dataset

v5

train_val_aug_32classes

Generated on Jun 30, 2022

Dataset Split

Train Set 82%
69Images
Valid Set 18%
15Images
Test Set %
0Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 1512x800
Auto-Adjust Contrast: Using Histogram Equalization

Augmentations

Outputs per training example: 3
Crop: 0% Minimum Zoom, 13% Maximum Zoom
Rotation: Between -5° and +5°
Shear: ±5° Horizontal, ±5° Vertical
Brightness: Between -10% and +10%
Exposure: Between -6% and +6%
Blur: Up to 1.25px