Dataset Versions
Versions
2023-09-01 10:44am
v9
· a year ago
2023-09-01 10:43am
v8
· a year ago
2023-09-01 10:41am
v7
· a year ago
2023-09-01 10:40am
v6
· a year ago
2023-09-01 10:39am
v5
· a year ago
2023-09-01 10:39am
v4
· a year ago
2023-09-01 10:38am
v3
· a year ago
2023-09-01 10:37am
v2
· a year ago
2023-09-01 10:36am
v1
· a year ago
v1
2023-09-01 10:36am
Generated on Sep 1, 2023
326 Total Images
View All Images
Dataset Split
Train Set 90%
294Images
Valid Set 8%
26Images
Test Set 2%
6Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Augmentations
Outputs per training example: 3
Flip: Horizontal
90° Rotate: Clockwise, Counter-Clockwise, Upside Down
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -36% and +36%
Exposure: Between -25% and +25%
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Cutout: 8 boxes with 9% size each