one line for detection rpn work normally with cuda#1312
Open
Cosin777 wants to merge 2 commits intopytorch:mainfrom
Open
one line for detection rpn work normally with cuda#1312Cosin777 wants to merge 2 commits intopytorch:mainfrom
Cosin777 wants to merge 2 commits intopytorch:mainfrom
Conversation
fmassa
requested changes
Sep 9, 2019
Member
fmassa
left a comment
fmassa
left a comment
There was a problem hiding this comment.
Can you write a full example which shows the error and add a test for it?
I believe the error happens only if you have done a first forward with the model in the CPU, and then you move the model to the GPU and try doing forward again.
But this should indeed be fixed, thanks for the catch!
torchvision/models/detection/rpn.py
Outdated
|
|
||
| def set_cell_anchors(self, device): | ||
| if self.cell_anchors is not None: | ||
| if self.cell_anchors is not None and device == self.cell_anchors[0].devcie: |
Member
There was a problem hiding this comment.
There is a typo here, and the code is not going to work as is (devcie is not an attribute of Tensor).
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The origin code, for example for detection: model.cuda()(torch.tensor([1,3,128,128], dtype = torch.float).cuda()), will raise error because the anchor tensor is still on the "cpu". This fix make the
code work more pytorch way.