The Wayback Machine - https://web.archive.org/web/20201126061723/https://github.com/open-mmlab/mmclassification/issues/4
Skip to content

/ mmclassification

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鈥檒l occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Roadmap of MMClassification #4

Open
hellock opened this issue Jul 13, 2020 · 11 comments
Open

Roadmap of MMClassification #4

hellock opened this issue Jul 13, 2020 · 11 comments
Labels
good first issue help wanted

Comments

@hellock
Copy link
Contributor

@hellock hellock commented Jul 13, 2020

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 馃憤 or be against with 馃憥. (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!)
@hellock hellock pinned this issue Jul 13, 2020
@GoldenAbel
Copy link

@GoldenAbel GoldenAbel commented Jul 16, 2020

warm up and more pretrained models
@LeeJZh
Copy link
Contributor

@LeeJZh LeeJZh commented Jul 17, 2020

tricks like mix-up, auto-augmentation, and etc..
@Tshzzz
Copy link

@Tshzzz Tshzzz commented Jul 17, 2020

convert model to onnx.
@SilvioGiancola
Copy link

@SilvioGiancola SilvioGiancola commented Jul 20, 2020 •
edited

EfficientNet, that could serve as backbone for mmdetection as well
@Ironteen
Copy link

@Ironteen Ironteen commented Jul 21, 2020

some Nerual Architecture Search algorithms which could be implement on one GPU, like ENAS
@soldier828
Copy link

@soldier828 soldier828 commented Jul 22, 2020

multi-brach for multi-task learning
@LeeJZh
Copy link
Contributor

@LeeJZh LeeJZh commented Jul 23, 2020

convert model to onnx.

I think pytorch 1.5 supports it. torch.onnx
@GoldenAbel
Copy link

@GoldenAbel GoldenAbel commented Jul 28, 2020

darknet networks and data aug, like darknet53, mosaic, cutmix, mixup
@myopengit
Copy link

@myopengit myopengit commented Aug 4, 2020

benchmark on cifar10 and cifar100
@zhongqiu1245
Copy link

@zhongqiu1245 zhongqiu1245 commented Sep 20, 2020

Could you support HRNet?
@ousinkou
Copy link

@ousinkou ousinkou commented Oct 10, 2020

Multi-label classification
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
good first issue help wanted
10 participants
@SilvioGiancola @hellock @GoldenAbel @soldier828 @ousinkou @Tshzzz @myopengit @Ironteen @LeeJZh @zhongqiu1245
You can鈥檛 perform that action at this time.