Dataset Versions
Versions
v2
V2
Generated on Oct 13, 2023
591 Total Images
View All Images
Dataset Split
Train Set 82%
483Images
Valid Set 4%
26Images
Test Set 14%
82Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Modify Classes: 6 remapped, 25 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
Rotation: Between -30° and +30°
Shear: ±12° Horizontal, ±12° Vertical
Brightness: Between -30% and +0%
Blur: Up to 1.25px
Noise: Up to 5% of pixels