Dataset Versions
v1
2024-10-31 3:22pm
Generated on Oct 31, 2024
215 Total Images
View All Images
Dataset Split
Train Set 94%
203Images
Valid Set 4%
8Images
Test Set 2%
4Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 7
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -11° and +11°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Saturation: Between -45% and +45%
Brightness: Between -15% and +0%
Blur: Up to 2.2px
Noise: Up to 1.05% of pixels