Dataset Versions

v15

2024-07-11 EffNetB5

Generated on Jul 11, 2024

Dataset Split

Train Set 88%
1143Images
Valid Set 8%
102Images
Test Set 4%
51Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 456x456
Filter Null: Require all images to contain annotations.

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -15° and +15°
Grayscale: Apply to 15% of images
Brightness: Between -15% and +15%
Exposure: Between -10% and +10%
Blur: Up to 2.5px
Noise: Up to 1.45% of pixels

Similar Projects

See More