PocketSight

Edit Project

DGEN-segment-test

Instance Segmentation

DGEN-segment-test Image Dataset

Try Pre-Trained Model
Versions
2023-05-07 2:14pm
v12
May 7, 2023
2023-05-07 2:08pm
v11
May 7, 2023
2023-05-07 1:52pm
v10
May 7, 2023
2023-05-07 12:26pm
v9
May 7, 2023
2023-05-07 1:48am
v8
May 7, 2023
2023-05-07 12:18am
v7
May 7, 2023
2023-05-06 11:38pm
v6
May 7, 2023
2023-05-06 6:13pm
v5
May 6, 2023
2023-05-06 5:57pm
v4
May 6, 2023
2023-05-06 5:28pm
v3
May 6, 2023
2023-05-06 4:25pm
v2
May 6, 2023
2023-05-06 3:08pm
v1
May 6, 2023
v6

2023-05-06 11:38pm

Generated on May 7, 2023
Download Dataset

85 Total Images

View All Images
Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image Annotation VisualizationDataset Image

Dataset Split

Train Set 85%
72Images
Valid Set 6%
5Images
Test Set 9%
8Images

Preprocessing

Auto-Orient: Applied
Resize: Stretch to 480x640

Augmentations

Outputs per training example: 3
Flip: Horizontal
Rotation: Between -15° and +15°
Shear: ±15° Horizontal, ±15° Vertical
Brightness: Between -25% and +25%
Blur: Up to 0.5px