Dataset Versions

v2

2024-05-26 9:50pm

Generated on May 27, 2024

Dataset Split

Train Set 95%
14904Images
Valid Set 3%
472Images
Test Set 2%
240Images

Preprocessing

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

Augmentations

Outputs per training example: 3
Rotation: Between -15° and +15°
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Exposure: Between -15% and +15%
Blur: Up to 2.5px
Noise: Up to 1.92% of pixels

Similar Projects

See More
2.4k images 2 models