Evaluation batch inference with same image size #2965
Assignees
Comments
|
I agree, I find it quite limiting not being able to run inference on batches since it slows down a lot the processing in production. Would it be possible to remove this assert and let the user deal with it? |
|
Any update on this? |
|
l also feel like this is a big limitation. My workflow involve a validation epoch after each train epoch, and with One workaround is to write my own |
xiexinch
added a commit
that referenced
this issue
Jul 20, 2023
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers. ## Motivation #3181 #2965 #2644 #1645 #1444 #1370 #125 ## Modification Remove the assertion at data_preprocessor ## BC-breaking (Optional) Does the modification introduce changes that break the backward-compatibility of the downstream repos? If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR. ## Use cases (Optional) If this PR introduces a new feature, it is better to list some use cases here, and update the documentation. ## Checklist 1. Pre-commit or other linting tools are used to fix the potential lint issues. 2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness. 3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D. 4. The documentation has been modified accordingly, like docstring or example tutorials.
nahidnazifi87
pushed a commit
to nahidnazifi87/mmsegmentation_playground
that referenced
this issue
Apr 5, 2024
Thanks for your contribution and we appreciate it a lot. The following instructions would make your pull request more healthy and more easily get feedback. If you do not understand some items, don't worry, just make the pull request and seek help from maintainers. ## Motivation open-mmlab#3181 open-mmlab#2965 open-mmlab#2644 open-mmlab#1645 open-mmlab#1444 open-mmlab#1370 open-mmlab#125 ## Modification Remove the assertion at data_preprocessor ## BC-breaking (Optional) Does the modification introduce changes that break the backward-compatibility of the downstream repos? If so, please describe how it breaks the compatibility and how the downstream projects should modify their code to keep compatibility with this PR. ## Use cases (Optional) If this PR introduces a new feature, it is better to list some use cases here, and update the documentation. ## Checklist 1. Pre-commit or other linting tools are used to fix the potential lint issues. 2. The modification is covered by complete unit tests. If not, please add more unit test to ensure the correctness. 3. If the modification has potential influence on downstream projects, this PR should be tested with downstream projects, like MMDet or MMDet3D. 4. The documentation has been modified accordingly, like docstring or example tutorials.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
I understand the problematic of batch inference with different image sizes. But we should be able to do this on a dataset with constant image size. Is there any plan of supporting this feature?
The text was updated successfully, but these errors were encountered: