Dataset Versions
Versions
v1
2022-12-12 2:48pm
Generated on Dec 12, 2022
1984 Total Images
View All Images
Dataset Split
Train Set 88%
1737Images
Valid Set 8%
165Images
Test Set 4%
82Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x940
Auto-Adjust Contrast: Using Adaptive Equalization
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 24% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±26° Horizontal, ±26° Vertical
Hue: Between -78° and +78°
Exposure: Between -48% and +48%
Cutout: 22 boxes with 4% size each