Dataset Versions
v1
2024-10-09 7:19am
Generated on Oct 9, 2024
1071 Total Images
View All Images
Dataset Split
Train Set 90%
968Images
Valid Set 6%
68Images
Test Set 3%
35Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 4
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Saturation: Between -25% and +25%
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.97% of pixels