The Wayback Machine - https://web.archive.org/web/20220409075314/https://github.com/open-mmlab/mmsegmentation/issues/13
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

Jump to bottom

Roadmap of MMSegmentation #13

Open
6 tasks done
hellock opened this issue Jul 13, 2020 · 40 comments
Open
6 tasks done

Roadmap of MMSegmentation #13

hellock opened this issue Jul 13, 2020 · 40 comments
Labels
good first issue help wanted

Comments

@hellock
Copy link
Member

@hellock hellock commented Jul 13, 2020 •
edited by xvjiarui

We keep this issue open to collect feature requests from users and hear your voice. Our monthly release plan is also available here.

You can either:

  1. Suggest a new feature by leaving a comment.
  2. Vote for a feature request with 👍 or be against with 👎. (Remember that developers are busy and cannot respond to all feature requests, so vote for your most favorable one!)
  3. Tell us that you would like to help implement one of the features in the list or review the PRs. (This is the greatest things to hear about!)

V0.6 (August)

  • ResNeSt. (#47)
  • Semantic FPN. (#35)
  • PointRend. (#35)
  • FastSCNN. (#58)
  • DNL. (#37)
  • ONNX export. (#12)
@hellock hellock added good first issue help wanted labels Jul 13, 2020
@hellock hellock pinned this issue Jul 13, 2020
@xvjiarui
Copy link
Collaborator

@xvjiarui xvjiarui commented Jul 15, 2020 •
edited

@xvjiarui
Copy link
Collaborator

@xvjiarui xvjiarui commented Jul 24, 2020

albumentation in #29

@xvjiarui xvjiarui mentioned this issue Jul 24, 2020
Closed
@zjupx
Copy link

@zjupx zjupx commented Jul 28, 2020

MobileNet v3 backbone support please！

@VincentZ-2020
Copy link

@VincentZ-2020 VincentZ-2020 commented Jul 31, 2020

Add U-net please！

@UESTC-Liuxin UESTC-Liuxin mentioned this issue Aug 2, 2020
Closed
@zhongqiu1245
Copy link

@zhongqiu1245 zhongqiu1245 commented Aug 5, 2020

nnU-net support please！

@xungeer29
Copy link

@xungeer29 xungeer29 commented Aug 10, 2020

tensorboard support please!

@xvjiarui
Copy link
Collaborator

@xvjiarui xvjiarui commented Aug 10, 2020

tensorboard support please!

You may uncomment this line to enable tensorboard.

@JoyLuo
Copy link

@JoyLuo JoyLuo commented Aug 11, 2020

Gans for segment

@advaza
Copy link

@advaza advaza commented Aug 17, 2020

Is there a way to view segmentation results throughout training (like evaluation hook but with visualisation of possibly unlabelled dataset)?
E.g. Tensorboard image writer.

@sandylaker
Copy link

@sandylaker sandylaker commented Aug 17, 2020

UNet, UNet++, and installation on OS X.

@johnzja
Copy link
Contributor

@johnzja johnzja commented Aug 23, 2020

MobileNet v3 backbone support please！

Supporting...

@hhaAndroid
Copy link

@hhaAndroid hhaAndroid commented Aug 24, 2020

support EfficientFCN

@JoyLuo
Copy link

@JoyLuo JoyLuo commented Aug 28, 2020 •
edited

dice loss， focal loss

@caodroid
Copy link

@caodroid caodroid commented Sep 3, 2020

please add Res2net，thank you，

@jianlong-yuan
Copy link

@jianlong-yuan jianlong-yuan commented Sep 3, 2020

please add Panoptic-DeepLab and segfix, thank you

@huang45
Copy link

@huang45 huang45 commented Sep 22, 2020

https://github.com/PingoLH/FCHarDNet please!

@huang45
Copy link

@huang45 huang45 commented Sep 22, 2020

and Bisenetv2, thank you~

@Hr-Song
Copy link

@Hr-Song Hr-Song commented Sep 24, 2020 •
edited

Lovasz hinge loss and Lovasz softmax loss suport please， thank you.

@ywwwer
Copy link

@ywwwer ywwwer commented Oct 7, 2020

Multi-scale attention https://github.com/NVIDIA/semantic-segmentation, thank you!

@zhongqiu1245
Copy link

@zhongqiu1245 zhongqiu1245 commented Oct 10, 2020

HighRes2DNet(2D version of HighRes3DNet) support please!

@zhongqiu1245
Copy link

@zhongqiu1245 zhongqiu1245 commented Oct 12, 2020

support CaNet please，thank you！
https://github.com/icoz69/CaNet?utm_source=wechat_session&utm_medium=social&utm_oi=980147122032807936

@caodroid
Copy link

@caodroid caodroid commented Oct 16, 2020 •
edited

hope the Xception will be supported in backbones, thank you https://arxiv.org/pdf/1610.02357.pdf

@9p15p
Copy link

@9p15p 9p15p commented Nov 3, 2020

support COCO Dataset, please. Thank you.

@JPLAY0
Copy link

@JPLAY0 JPLAY0 commented Nov 18, 2020

Support Mapillary Vistas Dataset ,thank you.

@bkbjsd bkbjsd mentioned this issue Nov 21, 2020
Closed
@zhongqiu1245
Copy link

@zhongqiu1245 zhongqiu1245 commented Nov 21, 2020 •
edited

Support Dice Loss, Generalized Dice Loss, Focal Loss & Tversky Loss please!
Thank you!

@NickChang97
Copy link

@NickChang97 NickChang97 commented Dec 14, 2020

Make it easy to use mixed loss

@lucci17
Copy link

@lucci17 lucci17 commented Jan 4, 2021

please support for temporal structure

@caodroid
Copy link

@caodroid caodroid commented Jan 27, 2021

DenseASPP plz，thank you

@JPLAY0
Copy link

@JPLAY0 JPLAY0 commented Apr 6, 2021

Support CamVid Dataset ,thank you.

@jfzhuang
Copy link

@jfzhuang jfzhuang commented Apr 9, 2021

Xception backbone support please！

@fcakyon
Copy link

@fcakyon fcakyon commented Apr 15, 2021 •
edited

@hellock please support VNet and ResUNet

@aikeyz
Copy link

@aikeyz aikeyz commented May 18, 2021

EMA/SWA and knowledge distillation please

@zhongqiu1245
Copy link

@zhongqiu1245 zhongqiu1245 commented Jun 15, 2021

Hi, thanks for your amazing job！
Is there any plan to support Panoptic-DeepLab？
Thank you！

@hannes09
Copy link

@hannes09 hannes09 commented Jun 23, 2021

Hi,
great project. I would like to see DDRNet.
https://github.com/chenjun2hao/DDRNet.pytorch

@tiwaria9034
Copy link

@tiwaria9034 tiwaria9034 commented Jul 30, 2021

Thanks for your contributions.
Please add EfficientNet family of backbones (v1, v2, tflite, etc.)

@Junjun2016
Copy link
Member

@Junjun2016 Junjun2016 commented Jul 30, 2021

Thanks for your contributions.
Please add EfficientNet family of backbones (v1, v2, tflite, etc.)

Could you please provide some references?

@tiwaria9034
Copy link

@tiwaria9034 tiwaria9034 commented Jul 31, 2021

Thanks for your contributions.
Please add EfficientNet family of backbones (v1, v2, tflite, etc.)

Could you please provide some references?

EfficientNet (v1):

EfficientNet (v2):

@babakbch babakbch mentioned this issue Sep 7, 2021
Closed
@eugenelawrence
Copy link

@eugenelawrence eugenelawrence commented Oct 9, 2021

MaskFormer

@chiba1sonny chiba1sonny mentioned this issue Nov 8, 2021
Closed
@chenhaiwen chenhaiwen mentioned this issue Nov 25, 2021
Closed
@eliabruni
Copy link

@eliabruni eliabruni commented Dec 6, 2021

Hi, great project.
I would like to see Mask2Former

@litaws
Copy link

@litaws litaws commented Dec 17, 2021 •
edited

Add support for Un/Semi-Supervised Loss (-or- partially unlabeled data)

edit:
moved into a separate issue #1147

@dongbo811 dongbo811 mentioned this issue Mar 28, 2022
Open
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
good first issue help wanted
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests