Dataset Versions
v1
2023-06-07 2:03pm
Generated on Jun 7, 2023
10100 Total Images
View All Images
Dataset Split
Train Set 87%
8784Images
Valid Set 9%
872Images
Test Set 4%
444Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Static Crop: 38-66% Horizontal Region, 23-80% Vertical Region
Resize: Stretch to 80x50
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise
Crop: 0% Minimum Zoom, 10% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Mosaic: Applied
Bounding Box: Rotation: Between -15° and +15°
Bounding Box: Exposure: Between -25% and +25%
Bounding Box: Blur: Up to 1.75px