Dataset Versions
Versions
v1
2022-07-11 12:21pm
Generated on Jul 11, 2022
4280 Total Images
View All Images
Dataset Split
Train Set 87%
3720Images
Valid Set 8%
340Images
Test Set 5%
220Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 416x416
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 2% of images
Saturation: Between -25% and +25%
Brightness: Between -25% and +25%
Exposure: Between -25% and +25%
Blur: Up to 3.25px
Mosaic: Applied