Batch inference is not support currently, as the image size might be different in a batch #3181
Comments
|
File "D:\mmsegmentation-main\tools\train.py", line 104, in |
|
I read the above existing questions, but none of them can solve my doubts. My dataset potsdam is obtained by using tools\dataset_converters. Size should be consistent. No matter how I adjust the batch_size, this error will be reported |
|
It is clearly stated in the previous issues that it doesn't matter whether your images are all the same size -- batched inference is not currently supported in any case. |
|
@edsml-hmc122 ，How to set it up so that it is not batched?Set up batch size=1? |
|
The test and val dataloaders each need to have batch size 1. Most likely your val dataloader is the issue, but I can't really say without seeing the config |
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.
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.
No description provided.
The text was updated successfully, but these errors were encountered: