Dataset Versions
v2
Second Model Bigger
Generated on Sep 14, 2023
124 Total Images
View All Images
Dataset Split
Train Set 87%
108Images
Valid Set 8%
10Images
Test Set 5%
6Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 640x640
Grayscale: Applied
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 12% Minimum Zoom, 29% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±3° Horizontal, ±3° Vertical
Brightness: Between -9% and +9%
Blur: Up to 1px
Noise: Up to 1% of pixels
Cutout: 16 boxes with 5% size each
Bounding Box: Brightness: Between -15% and +15%
Bounding Box: Blur: Up to 1.25px
Bounding Box: Noise: Up to 2% of pixels