Dataset Versions

v2

2024-01-19 7:50pm

Generated on Jan 19, 2024

Dataset Split

Train Set 90%
6657Images
Valid Set 8%
610Images
Test Set 2%
154Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 640x640
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Noise: Up to 0.1% of pixels

Similar Projects

See More