Dataset Versions
v4
2022-07-08 6:29pm
Generated on Jul 8, 2022
4064 Total Images
View All Images
Dataset Split
Train Set 70%
2844Images
Valid Set 15%
612Images
Test Set 15%
608Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Tile: 2 rows x 2 columns
Modify Classes: 0 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -14° and +14°
Shear: ±9° Horizontal, ±6° Vertical
Grayscale: Apply to 6% of images
Saturation: Between -38% and +38%
Mosaic: Applied