Skip to content
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

How to test with multi gpu and increase test batches? #33

Closed
joeythegod opened this issue Oct 12, 2019 · 4 comments
Closed

How to test with multi gpu and increase test batches? #33

joeythegod opened this issue Oct 12, 2019 · 4 comments
Labels
enhancement Improvements or good new features

Comments

@joeythegod
Copy link

Hi, I would like to know how to test with multi gpu and increase test batches?

@ppwwyyxx
Copy link
Contributor

ppwwyyxx commented Oct 12, 2019

tools/train_net.py --num-gpu 8

Evaluation with batch size > 1 is unsupported at the moment, mainly because for most models it will not produce the exact same output due to padding, therefore not very useful for research. However the models can already accept inputs with batch size>1.

@Aswantm

This comment has been minimized.

@asanakoy
Copy link
Member

@joeythegod but if you still want to increase the batch, you can do it by hacking the code here: https://github.com/facebookresearch/detectron2/blob/master/detectron2/data/build.py#L398
Just change the batch size in the BatchSampler.

@ppwwyyxx
Copy link
Contributor

Closing as all the models do support batch size >1 for inference from the beginning.
We probably don't want to support batch size > 1 for evaluation, due to reasons mentioned above.

ppwwyyxx added a commit that referenced this issue Jan 2, 2022
Summary: Pull Request resolved: fairinternal/detectron2#64

Differential Revision: D13578812

Pulled By: ppwwyyxx

fbshipit-source-id: 12b0b18d79870387232e9af56a7b37f9132a891d
niqbal996 pushed a commit to niqbal996/detectron2 that referenced this issue Jun 15, 2023
* refine docs

* refine docs

* refine docs

* add matcher docs

* add neck docs

* refine channel mapper docs

Co-authored-by: ntianhe ren <rentianhe@dgx061.scc.idea>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement Improvements or good new features
Projects
None yet
Development

No branches or pull requests

4 participants