pt-detect Image Dataset
Versions
2023-03-27 4:43am
v15
Mar 27, 2023
2023-02-09 12:09pm
v14
Feb 9, 2023
2023-02-06 4:03pm
v13
Feb 6, 2023
2023-02-04 9:49am
v12
Feb 4, 2023
2023-01-30 12:15pm
v11
Jan 30, 2023
2023-01-27 11:34am
v10
Jan 27, 2023
2023-01-11 5:19pm
v9
Jan 11, 2023
2023-01-09 5:46pm
v8
Jan 9, 2023
2023-01-09 10:02am
v7
Jan 9, 2023
2023-01-06 12:24pm
v6
Jan 6, 2023
2023-01-06 10:24am
v5
Jan 6, 2023
2023-01-06 10:12am
v4
Jan 6, 2023
2023-01-06 10:00am
v3
Jan 6, 2023
2023-01-04 3:45pm
v2
Jan 4, 2023
2023-01-04 2:03pm
v1
Jan 4, 2023
v8
2023-01-09 5:46pm
Generated on Jan 9, 2023
1113 Total Images
View All ImagesDataset Split
Train Set 86%
957Images
Valid Set 7%
82Images
Test Set 7%
74Images
Preprocessing
Auto-Orient: Applied
Resize: Stretch to 768x768
Modify Classes: 1 remapped, 0 dropped
Augmentations
Outputs per training example: 3
Flip: Horizontal
Rotation: Between -30° and +30°
Grayscale: Apply to 20% of images
Hue: Between -148° and +148°
Saturation: Between -90% and +90%
Brightness: Between -27% and +27%
Blur: Up to 3.25px
Noise: Up to 3% of pixels
Mosaic: Applied
Similar Projects
diag-3x5-2x2-5x6
434 images
tiles
3182 images
majangpae
572 images
Button
1612 images
Domino-Pieces
149 images