Dataset_DQPlus Dataset

v1

2023-06-21 4:47pm

Generated on Jun 21, 2023

Dataset Split

Train Set 100%
84Images
Valid Set %
0Images
Test Set %
0Images

Preprocessing

No preprocessing steps were applied.

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 33% Maximum Zoom
Rotation: Between -21° and +21°
Shear: ±19° Horizontal, ±22° Vertical
Grayscale: Apply to 34% of images
Hue: Between -26° and +26°
Saturation: Between -43% and +43%
Brightness: Between -24% and +24%
Exposure: Between -43% and +43%
Blur: Up to 3.5px
Noise: Up to 5% of pixels
Cutout: 7 boxes with 33% size each