-
Notifications
You must be signed in to change notification settings - Fork 2.5k
Indexing error in RPNLossComputation.prepare_targets #234
Comments
This is a duplicate of #31 |
@fmassa I've checked and that is not true. All my images have annotations, there must be a transformation that is creating empty BoxLists |
Maybe one of your images have an empty annotation, like |
That is not the case.
This would make a lot more sense, but it should still be verified. |
The error points down to the fact that there is not GT for one image that has been fed, that is kind of clear from the error message and there is BTW and open PR to improve this error message in #37 If you are adding random crops in your transforms, that is probably the culprit. |
Is there an option to not add random crops? I'm not doing it explicitly |
We don't add random crops by default (this option is not even present in the current codebase actually) |
🐛 Bug
I am getting this error and I have no idea why... At some point in
RPNLossComputation.prepare_targets
,matched_targets
is aBoxList
withnum_boxes=0
, resulting in an empty tensor inlabels_per_image
and subsequently in a indexing error down the line.maskrcnn-benchmark/maskrcnn_benchmark/modeling/rpn/loss.py
Lines 50 to 62 in ced10f2
Environment
Docker image
The text was updated successfully, but these errors were encountered: