Dataset Versions

v10

2023-08-13 1:32am

Generated on Aug 12, 2023

Dataset Split

Train Set 83%
92Images
Valid Set %
0Images
Test Set 17%
19Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 224x224

Augmentations

Outputs per training example: 2
Flip: Vertical
90° Rotate: Upside Down
Rotation: Between -13° and +13°
Shear: ±15° Horizontal, ±20° Vertical
Hue: Between -25° and +25°
Saturation: Between -55% and +55%
Brightness: Between 0% and +14%
Exposure: Between -14% and +14%
Noise: Up to 6% of pixels