Dataset Versions
v4
2023-07-24 3:10pm
Generated on Jul 24, 2023
340 Total Images
View All Images
Dataset Split
Train Set 79%
267Images
Valid Set 14%
47Images
Test Set 8%
26Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Histogram Equalization
Grayscale: Applied
Augmentations
Outputs per training example: 3
Flip: Horizontal
Crop: 0% Minimum Zoom, 15% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±9° Horizontal, ±8° Vertical
Hue: Between -13° and +13°
Brightness: Between -20% and +20%
Exposure: Between -8% and +8%
Blur: Up to 0.25px
Noise: Up to 3% of pixels