Open
Conversation
Member
|
visually the pr looks good, do you have any clue where could be the problem? |
liueo
commented
Jun 26, 2020
Comment on lines
+167
to
+168
| eval_metric.update(det_bboxes, det_ids, det_scores, gt_bboxes, gt_ids, gt_difficults) | ||
| return eval_metric.get() |
Author
There was a problem hiding this comment.
I didn't save the errror message. I remember the error message started roughly from these lines and was related to data type. The error message was something like 'float64 is not supported in pycocotools'. I was confused about the error because I didn't think I use the data type mentioned. Maybe can run the code to reproduce the bug.
Member
There was a problem hiding this comment.
it seems to be an issue with latest numpy that breaks pycocotools. Maybe related: facebookresearch/detectron2#580
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Object detector using matrix layers to extract features and heads of CenterNet to predict. Something is wrong with the code cause bug happens during validation.