Letter Classification Dataset
Versions
2023-11-01 4:09pm
v10
· a year ago
2023-11-01 1:26pm
v9
· a year ago
2023-11-01 1:14pm
v8
· a year ago
2023-11-01 1:13pm
v7
· a year ago
2023-11-01 1:11pm
v6
· a year ago
2023-11-01 1:05pm
v5
· a year ago
2023-10-19 2:34pm
v4
· a year ago
2023-10-19 12:15pm
v3
· a year ago
2023-10-19 11:49am
v2
· a year ago
2023-10-19 11:45am
v1
· a year ago
v10
2023-11-01 4:09pm
Generated on Nov 1, 2023
964 Total Images
View All Images
Dataset Split
Train Set 87%
843Images
Valid Set 8%
81Images
Test Set 4%
40Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 640x640
Grayscale: Applied
Augmentations
Outputs per training example: 3
Crop: 0% Minimum Zoom, 20% Maximum Zoom
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Blur: Up to 2.5px
Noise: Up to 5% of pixels
Cutout: 3 boxes with 10% size each