Dataset Versions

v1

2021-12-22 2:55pm

Generated on Dec 22, 2021

Dataset Split

Train Set 87%
480Images
Valid Set 8%
46Images
Test Set 4%
23Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 416x416
Modify Classes: 0 remapped, 0 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Grayscale: Apply to 25% of images
Exposure: Between -25% and +25%
Cutout: 10 boxes with 20% size each
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Brightness: Between -25% and +25%
Bounding Box: Blur: Up to 10px
Bounding Box: Noise: Up to 5% of pixels