Dataset Versions
v1
2023-08-28 7:52pm
Generated on Aug 28, 2023
2536 Total Images
View All Images
Dataset Split
Train Set 88%
2220Images
Valid Set 8%
212Images
Test Set 4%
104Images
Preprocessing
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -6° and +6°
Shear: ±10° Horizontal, ±11° Vertical
Hue: Between -46° and +46°
Saturation: Between -41% and +41%
Blur: Up to 4.75px
Noise: Up to 6% of pixels