Dataset Versions
v1
2024-10-26 6:58pm
Generated on Oct 26, 2024
632 Total Images
View All Images
Dataset Split
Train Set 87%
552Images
Valid Set 8%
52Images
Test Set 4%
28Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Grayscale: Apply to 21% of images
Hue: Between -21° and +21°
Brightness: Between -22% and +22%
Blur: Up to 2.5px
Noise: Up to 1.92% of pixels
Cutout: 4 boxes with 34% size each
Mosaic: Applied