Spaces:
No application file
No application file
| title: Visual Anomaly Detection | |
| emoji: 🏆 | |
| colorFrom: gray | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: 4.36.1 | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| > Assume that we have a dataset in which the training set contains only normal images, and the test set contains both normal and abnormal images. We want to train an anomaly segmentation model that will be able to detect the abnormal regions in the test set. We only have normal images in our dataset but would like to train a segmentation model. Use the synthetic anomaly generation feature to create abnormal images from normal images, and perform the validation and test steps. | |
| ``` | |
| pip3 install anomalib | |
| anomalib install --option core | |
| cog train --input | |
| ``` | |
| In vr generate photos of normal images of avatar motion. Use to detect abnormal avatar animation. | |