target_detect Dataset

v15

2023-07-09 4:49pm

Generated on Jul 9, 2023

Dataset Split

Train Set 92%
2058Images
Valid Set 5%
110Images
Test Set 3%
58Images

Preprocessing

Resize: Stretch to 1920x1080
Modify Classes: 2 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 30% Maximum Zoom
Brightness: Between -25% and +25%
Blur: Up to 2px
Noise: Up to 3% of pixels
Cutout: 10 boxes with 6% size each
Bounding Box: Exposure: Between -5% and +5%