Dataset Versions

v1

2023-07-08 7:15pm

Generated on Jul 8, 2023

Dataset Split

Train Set 89%
1365Images
Valid Set 8%
123Images
Test Set 3%
40Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 300x300

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Grayscale: Apply to 25% of images
Hue: Between -30° and +30°
Exposure: Between -25% and +25%
Noise: Up to 7% of pixels
Mosaic: Applied
Bounding Box: Crop: 10% Minimum Zoom, 20% Maximum Zoom

Similar Projects

See More