Dataset Versions

v1

2023-01-04 2:03pm

Generated on Jan 4, 2023

Dataset Split

Train Set 87%
201Images
Valid Set 8%
18Images
Test Set 6%
13Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -14° and +14°
Grayscale: Apply to 23% of images
Hue: Between -148° and +148°
Saturation: Between -81% and +81%
Brightness: Between -27% and +27%
Blur: Up to 2px
Noise: Up to 9% of pixels
Mosaic: Applied

Similar Projects

See More
572 images 2 models