Conversation
The frames indexes start at 0 and go up to (n_frames - 1)
…im/add_ctd_integration_test
Replaced np.max by np.nanmax, to avoid excluding whole pose if some keypoint is Nan
Contributor
|
Thanks for this.
and everything worked as expected. |
AlexEMG
approved these changes
Sep 10, 2025
2 tasks
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This Pull Request fixes the edge case in the CTD pipeline when the conditions passed to the
CTDInferenceRunner.predict()method are empty. This typically can happen when theFilterLowConfidencePosesprocessing stage filters out all poses.Thus, this Pull Request solves #3001.
The following changes were introduced to fix the edge case:
"model_kwargs"item to the context in theConditionalKeypointsToModelInputspreprocessing stage, even in the case of empty conditions. This parameter is expected in downstream inference stages.CTDInferenceRunnerwhen the received conditions are empty.TopDownCropprocessing stage has been modified to always output images of the cropped shape, even in the case of an emptycontext["bboxes"]list. The first dimension length of the returnedimages(corresponding to the number of bounding boxes) obviously remains 0 in that case.