Dataset Versions
v4
2024-04-23 3:21am
Generated on Apr 23, 2024
339 Total Images
View All ImagesDataset Split
Train Set 88%
297Images
Valid Set 8%
28Images
Test Set 4%
14Images
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
Saturation: Between -25% and +25%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 0.1% of pixels