Dataset Versions
v5
2023-10-23 10:09am
Generated on Oct 23, 2023
812 Total Images
View All Images
Dataset Split
Train Set 88%
711Images
Valid Set 8%
68Images
Test Set 4%
33Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise
Rotation: Between -15° and +15°
Saturation: Between -30% and +30%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels