Dataset Versions
v10
2023-08-04 6:05pm
Generated on Aug 4, 2023
411 Total Images
View All Images
Dataset Split
Train Set 85%
351Images
Valid Set 8%
31Images
Test Set 7%
29Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Do not filter any null images.
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 13% Minimum Zoom, 34% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 43% of images
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -22% and +22%
Blur: Up to 7px
Noise: Up to 5% of pixels
Cutout: 3 boxes with 10% size each
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: 90° Rotate: Clockwise, Counter-Clockwise
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Brightness: Between -25% and +25%
Bounding Box: Exposure: Between -52% and +52%
Bounding Box: Blur: Up to 2.5px
Bounding Box: Noise: Up to 5% of pixels