Skip to content

Conversation

@shunping
Copy link
Collaborator

@shunping shunping commented Mar 13, 2025

To support offline model scoring with model handler and RunInference, we add a new AnomalyDetector class called CustomDetector for storing model handler and other information. Then we modify our transform to expand the pipeline with RunInference Transform if we see this new type of detctors.

This PR only contains the code change for the new detector. The follow-up PR (#34286) is for the transform change.

@shunping shunping changed the title Add Custom Detector to support model handlers from RunInference [AnomalyDetection] Add Custom Detector to support model handlers from RunInference Mar 13, 2025
@shunping shunping changed the title [AnomalyDetection] Add Custom Detector to support model handlers from RunInference [AnomalyDetection] Add Custom Detector to support custom model handlers Mar 13, 2025
@shunping shunping self-assigned this Mar 13, 2025
@shunping shunping requested a review from damccorm March 13, 2025 19:57
@shunping shunping added this to the 2.64.0 Release milestone Mar 13, 2025
@github-actions
Copy link
Contributor

Checks are failing. Will not request review until checks are succeeding. If you'd like to override that behavior, comment assign set of reviewers

@shunping shunping force-pushed the anomaly-detection-5-2 branch 3 times, most recently from e4b375e to fddbb73 Compare March 14, 2025 01:08
@github-actions
Copy link
Contributor

Assigning reviewers. If you would like to opt out of this review, comment assign to next reviewer:

R: @damccorm for label python.

Available commands:

  • stop reviewer notifications - opt out of the automated review tooling
  • remind me after tests pass - tag the comment author after tests pass
  • waiting on author - shift the attention set back to the author (any comment or push by the author will return the attention set to the reviewers)

The PR bot will only process comments in the main thread (not review comments).

- torch.Tensor(n) gives a nx1-tensor with zeros: i.e. Tensor(0, 0, ... 0).
- torch.tensor(n) gives a 1x1-tensor with value n: i.e. Tensor(n).
@shunping shunping force-pushed the anomaly-detection-5-2 branch from fddbb73 to ce275a6 Compare March 14, 2025 12:43
Copy link
Contributor

@damccorm damccorm left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missed that this was a prereq for #34286 (review) and left some high level comments there instead, PTAL

@shunping
Copy link
Collaborator Author

Missed that this was a prereq for #34286 (review) and left some high level comments there instead, PTAL

This PR has been superseded by #34310 and #34311.

@shunping shunping closed this Mar 17, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants