Dataset Versions
v3
2023-08-12 10:11pm
Generated on Aug 12, 2023
324 Total Images
View All Images
Dataset Split
Train Set 89%
288Images
Valid Set 7%
24Images
Test Set 4%
12Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Static Crop: 25-75% Horizontal Region, 25-75% Vertical Region
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 2 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Crop: 0% Minimum Zoom, 21% Maximum Zoom
Rotation: Between -45° and +45°
Grayscale: Apply to 37% of images
Hue: Between -87° and +87°
Saturation: Between -38% and +38%
Exposure: Between -15% and +15%
Blur: Up to 3px
Mosaic: Applied
Bounding Box: Flip: Horizontal, Vertical
Bounding Box: Rotation: Between -26° and +26°