-
Notifications
You must be signed in to change notification settings - Fork 2.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[Enhance] Replace data_dict calling 'img' key to support MMDet3D #514
Conversation
Codecov Report
@@ Coverage Diff @@
## master #514 +/- ##
==========================================
+ Coverage 86.56% 86.60% +0.04%
==========================================
Files 99 99
Lines 5164 5160 -4
Branches 836 834 -2
==========================================
- Hits 4470 4469 -1
+ Misses 535 533 -2
+ Partials 159 158 -1
Flags with carried forward coverage won't be shown. Click here to find out more.
Continue to review full report at Codecov.
|
This PR is ready for review @xvjiarui. Thanks! |
@@ -97,7 +97,7 @@ def single_gpu_test(model, | |||
result = np2tmp(result) | |||
results.append(result) | |||
|
|||
batch_size = data['img'][0].size(0) | |||
batch_size = len(result) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Refer to open-mmlab/mmcv#987
…n-mmlab#514) * remove dict calling img key for compatibility * fix unit test * infer batch size using len(result) to be consistent with mmcv
Hi, I am Ziyi, a developer from MMDet3D. In order to train/test 3D seg algorithms, I need to call functions from MMSeg. However, some functions in MMSeg calls
data['img']
, which causesKeyError
because we don't haveimg
. I replace these calling with some workarounds and make it compatibility with MMDet3D. Hope you can approve it. Thanks.