Dataset Versions
v1
2023-06-15 11:41pm
Generated on Jun 15, 2023
1836 Total Images
View All Images
Dataset Split
Train Set 88%
1608Images
Valid Set 8%
148Images
Test Set 4%
80Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Saturation: Between -48% and +48%
Blur: Up to 5px
Cutout: 5 boxes with 15% size each
Mosaic: Applied
Bounding Box: Shear: ±15° Horizontal, ±15° Vertical
Bounding Box: Noise: Up to 5% of pixels