Dataset Versions

v2

2024-04-13 4:51pm

Generated on Apr 13, 2024

Dataset Split

Train Set 82%
2664Images
Valid Set 14%
444Images
Test Set 4%
144Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Tile: 2 rows x 2 columns

Augmentations

Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Shear: ±10° Horizontal, ±10° Vertical
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Bounding Box: Exposure: Between -10% and +10%
Bounding Box: Noise: Up to 0.1% of pixels

Similar Projects

See More
1.3k images 1 model