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.

Sign up for GitHub

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

Jump to bottom

Implementation of DeepLabv2 #771

Closed
nakashima-kodai opened this issue Aug 10, 2021 · 3 comments
Closed

Implementation of DeepLabv2 #771

nakashima-kodai opened this issue Aug 10, 2021 · 3 comments
Assignees
@Junjun2016

Comments

@nakashima-kodai
Copy link

Hi,

DeepLabv2 is still widely used. Therefore, I think it would be more convenient if deeplabv2 can be used in mmsegmentation, is there any plan to implement it?

Thanks.
@Junjun2016
Copy link
Collaborator

Hi @nakashima-kodai
Since deeplabv3 is already supported, you can use deeplabv3 or deeplabv3+ instead.

@Junjun2016 Junjun2016 self-assigned this Aug 10, 2021
@fabvio
Copy link

fabvio commented Aug 23, 2021

I jump into the discussion just to say that having DeepLabv2 implemented could be helpful to fairly compare with other methods in research, since it is a widely used baseline for domain adaptation purposes.

@Junjun2016
Copy link
Collaborator

Hi @nakashima-kodai @fabvio
Got it, PR is welcome and we will benchmark it.

wjkim81 pushed a commit to wjkim81/mmsegmentation that referenced this issue Dec 3, 2023
@zengwang430521
Add mesh demo. (open-mmlab#771)
07e9403 
* add mesh demo.
wjkim81 pushed a commit to wjkim81/mmsegmentation that referenced this issue Dec 3, 2023
@ly015
Fix imshow_bbox error when input bboxes is empty (open-mmlab#796)
6188c9f 
* update imshow_bbox to handle empty bboxes
* update unittest
* add trimesh into requirements (related to open-mmlab#771)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@Junjun2016 Junjun2016

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@fabvio @Junjun2016 @nakashima-kodai