Dataset Versions
v2
2024-06-24 4:08am
Generated on Jun 24, 2024
1688 Total Images
View All ImagesDataset Split
Train Set 92%
1555Images
Valid Set 5%
89Images
Test Set 3%
44Images
Preprocessing
Auto-Orient: Applied
Resize: Fit within 640x640
Augmentations
Outputs per training example: 5
Crop: 0% Minimum Zoom, 3% Maximum Zoom
Rotation: Between -1° and +1°
Shear: ±1° Horizontal, ±1° Vertical
Grayscale: Apply to 1% of images
Brightness: Between -1% and +1%
Exposure: Between -1% and +1%