TU Berlin

new3

Classification

new3 Image Dataset

v1

2023-09-24 7:15am

Generated on Sep 23, 2023

Dataset Split

Train Set 88%
1881Images
Valid Set 8%
180Images
Test Set 4%
86Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 320x320

Augmentations

Outputs per training example: 3
Flip: Horizontal, Vertical
Crop: 0% Minimum Zoom, 34% Maximum Zoom
Shear: ±15° Horizontal, ±15° Vertical
Grayscale: Apply to 25% of images
Saturation: Between -25% and +25%
Exposure: Between -25% and +25%
3d printer defects
924 images
3d
924 images
3d-printing-error
745 images
3d-printing-error
741 images
3d
926 images