Dataset Versions
v12
New-data
Generated on Dec 17, 2024
7774 Total Images
View All ImagesDataset Split
Train Set 87%
6801Images
Valid Set 8%
646Images
Test Set 4%
327Images
Preprocessing
Auto-Orient: Applied
Resize: Fill (with center crop) in 640x362
Modify Classes: 0 remapped, 1 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 25% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -15% and +15%
Blur: Up to 2.4px
Noise: Up to 0.54% of pixels