Dataset Versions
v2
2023-04-29 3:27am
Generated on Apr 29, 2023
545 Total Images
View All Images
Dataset Split
Train Set 88%
477Images
Valid Set 9%
48Images
Test Set 4%
20Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Auto-Adjust Contrast: Using Adaptive Equalization
Grayscale: Applied
Tile: 2 rows x 2 columns
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 34% Maximum Zoom
Hue: Between -25° and +25°
Cutout: 3 boxes with 10% size each