Dataset Versions
v3
2024-03-14 6:41pm
Generated on Mar 14, 2024
4042 Total Images
View All Images
Dataset Split
Train Set 94%
3783Images
Valid Set 4%
157Images
Test Set 3%
102Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Hue: Between -15° and +15°
Saturation: Between -25% and +25%
Brightness: Between -46% and +46%
Exposure: Between -32% and +32%
Blur: Up to 2.5px
Noise: Up to 1.92% of pixels
Cutout: 3 boxes with 10% size each