An anomaly detection library comprising state-of-the-art algorithms and features such as experiment management, hyper-parameter optimization, and edge inference.
When attempting to train via CLI using the default normalization method on certain datasets (btech, kolektor, folder, mvtech_3d, folder_3d), the following error occurs:
'IMAGENET' is not a valid InputNormalizationMethod
Dataset
Other (please specify in the text field below)
Model
PatchCore
Steps to reproduce the behavior
After installing the anomalib v1 version, try executing the following command:
Describe the bug
When attempting to train via CLI using the default normalization method on certain datasets (btech, kolektor, folder, mvtech_3d, folder_3d), the following error occurs:
Dataset
Other (please specify in the text field below)
Model
PatchCore
Steps to reproduce the behavior
After installing the anomalib v1 version, try executing the following command:
OS information
OS information:
Expected behavior
the default normalization method should be a valid InputNormalizationMethod
Screenshots
No response
Pip/GitHub
GitHub
What version/branch did you use?
v1
Configuration YAML
Logs
Code of Conduct