5 PART DIFF Dataset

v1

2023-07-26 4:59pm

Generated on Jul 26, 2023

Dataset Split

Train Set 89%
168Images
Valid Set 7%
14Images
Test Set 4%
7Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -45° and +45°
Grayscale: Apply to 88% of images
Saturation: Between -44% and +44%
Brightness: Between -16% and +16%
Blur: Up to 8px
Noise: Up to 1% of pixels
Mosaic: Applied
Bounding Box: Brightness: Between -15% and +15%

Similar Projects

See More