Dataset Versions
Versions
2024-10-31 5:51am
v11
· 22 days ago
2024-09-11 8:26am
v10
· 2 months ago
2024-09-11 7:38am
v9
· 2 months ago
2024-09-11 7:36am
v8
· 2 months ago
2024-09-11 7:34am
v7
· 2 months ago
2024-09-11 7:32am
v6
· 2 months ago
2024-09-11 7:22am
v5
· 2 months ago
2024-08-30 4:09am
v4
· 3 months ago
2024-08-23 3:05pm
v3
· 3 months ago
2024-08-23 2:59pm
v2
· 3 months ago
2024-08-23 8:45am
v1
· 3 months ago
v3
2024-08-23 3:05pm
Generated on Aug 23, 2024
2085 Total Images
View All Images
Dataset Split
Train Set 92%
1920Images
Valid Set 5%
110Images
Test Set 3%
55Images
Preprocessing
Auto-Orient: Applied
Resize: Fit (black edges) in 1024x1024
Auto-Adjust Contrast: Using Histogram Equalization
Augmentations
Outputs per training example: 5
Rotation: Between -7° and +7°
Saturation: Between -8% and +8%
Brightness: Between -7% and +7%
Exposure: Between -10% and +10%
Noise: Up to 0.1% of pixels
Cutout: 3 boxes with 10% size each
Mosaic: Applied
Bounding Box: Crop: 0% Minimum Zoom, 20% Maximum Zoom