Dataset Versions
v3
2023-11-28 2:01pm
Generated on Nov 28, 2023
244 Total Images
View All Images
Dataset Split
Train Set 65%
159Images
Valid Set 17%
42Images
Test Set 18%
43Images
Preprocessing
Auto-Orient: Applied
Isolate Objects: Applied
Resize: Stretch to 640x640
Filter Null: Require all images to contain annotations.
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -15° and +15°
Saturation: Between -66% and +66%
Brightness: Between -43% and +43%
Exposure: Between -20% and +20%