Stick detection Dataset

v6

Current training data

Generated on Nov 14, 2023

Dataset Split

Train Set 87%
6663Images
Valid Set 8%
633Images
Test Set 4%
320Images

Preprocessing

Auto-Orient: Applied
Resize: Fill (with center crop) in 848x480
Modify Classes: 0 remapped, 2 dropped

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Exposure: Between -25% and +25%
Cutout: 15 boxes with 15% size each