Uploaded image for project: 'Data Management'
  1. Data Management
  2. DM-36743

Add the real-bogus PipelineTask to ap_verify for the DC2 CI dataset

    XMLWordPrintable

    Details

    • Type: Story
    • Status: Reviewed
    • Resolution: Unresolved
    • Fix Version/s: None
    • Component/s: ap_verify
    • Labels:
      None
    • Story Points:
      4
    • Epic Link:
    • Sprint:
      AP F22-6 (November), AP S23-2 (January), AP S23-3 (February), AP S23-4 (March)
    • Team:
      Alert Production
    • Urgent?:
      No

      Description

      Add the traditional real-bogus classifier PipelineTask to ApVerify.yaml and ApVerifyWithFakes.yaml in the new DC2 CI dataset defined in DM-34845. The real-bogus PipelineTask should be run by default when ap_verify is run with this dataset, on any supported machine.

        Attachments

          Issue Links

          blocks

          Story - Created by Jira Software - do not edit or delete. Issue type for a user story. DM-36744 Add real-bogus CI output to Chronograf

          • To Do
          is blocked by

          Story - Created by Jira Software - do not edit or delete. Issue type for a user story. DM-36742 Add real-bogus trained model to DC2 CI repository

          • In Review
          relates to

          Story - Created by Jira Software - do not edit or delete. Issue type for a user story. DM-37687 Add torchvision to the stack

          • To Do

            Activity

            Ascending order - Click to sort in descending order
            Hide
            Permalink
            nima Nima Sedaghat added a comment -

            I literally plugged rbClassify into the ApVerify.yaml and things worked like a charm.


            dataset types are also created in the output repository:

             

            Let's discuss whether just leaving the rbClassifier as a default part of ap_verify (+ fakse) is desirable, or do we e.g. want to make it optional.

            Show
            nima Nima Sedaghat added a comment - I literally plugged rbClassify into the ApVerify.yaml and things worked like a charm. dataset types are also created in the output repository:   Let's discuss whether just leaving the rbClassifier as a default part of ap_verify (+ fakse) is desirable, or do we e.g. want to make it optional.
            Hide
            Permalink
            sullivan Ian Sullivan added a comment -

            As noted on Github, this ticket will need to wait for the trained model to be available from DM-36742 before it can be merged, rather than using a hard-coded path.

            Show
            sullivan Ian Sullivan added a comment - As noted on Github, this ticket will need to wait for the trained model to be available from DM-36742 before it can be merged, rather than using a hard-coded path.
            Hide
            Permalink
            sullivan Ian Sullivan added a comment -

            We discussed this ticket earlier this week, and add DM-36742 as a blocker for merging. Once the model is available the hard-coded path on the current PR can be updated.

            Show
            sullivan Ian Sullivan added a comment - We discussed this ticket earlier this week, and add DM-36742 as a blocker for merging. Once the model is available the hard-coded path on the current PR can be updated.

              People

              Assignee:
              nima Nima Sedaghat
              Reporter:
              sullivan Ian Sullivan
              Reviewers:
              Ian Sullivan
              Watchers:
              Eric Bellm, Ian Sullivan, John Parejko, Krzysztof Findeisen, Nima Sedaghat
              Votes:
              0 Vote for this issue
              Watchers:
              5 Start watching this issue

                Dates

                Created:
                Updated:

                  Jenkins

                  No builds found.