Dataset Versions

v1

2023-07-13 2:11pm

Generated on Jul 13, 2023

Dataset Split

Train Set 84%
828Images
Valid Set 8%
80Images
Test Set 8%
76Images

Preprocessing

Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Blur: Up to 4.5px
Noise: Up to 6% of pixels
Bounding Box: Brightness: Between -40% and +40%
Bounding Box: Exposure: Between -25% and +25%

Similar Projects

See More