Dataset Versions

v3

2023-05-26 1:25pm

Generated on May 26, 2023

Dataset Split

Train Set 83%
192Images
Valid Set 7%
16Images
Test Set 10%
24Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Contrast Stretching
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Rotation: Between -12° and +12°
Shear: ±19° Horizontal, ±11° Vertical
Brightness: Between -25% and +25%
Exposure: Between -14% and +14%
Blur: Up to 0.75px
Noise: Up to 1% of pixels
Mosaic: Applied

Similar Projects

See More