Dataset Versions
v11
Creacion de 24-10-24
Generated on Oct 24, 2024
3774 Total Images
View All Images
Dataset Split
Train Set 86%
3258Images
Valid Set 7%
268Images
Test Set 7%
248Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Tile: 1 rows x 2 columns
Augmentations
Outputs per training example: 3
Flip: Horizontal, Vertical
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Rotation: Between -15° and +15°
Grayscale: Apply to 11% of images
Hue: Between -15° and +15°
Saturation: Between -16% and +16%
Brightness: Between -23% and +23%
Exposure: Between -13% and +13%
Blur: Up to 1.1px
Noise: Up to 0.57% of pixels