Coder Social home page Coder Social logo

Comments (6)

Hhhhhhao avatar Hhhhhhao commented on May 28, 2024

We plan to release the imbalanced algorithms in end of Nov, or beginning of Dec. We still have some code tweak to accommodate the imbalanced algorithms and have to run the experiments to get evaluation of these algorithms too.

from semi-supervised-learning.

muziyi19 avatar muziyi19 commented on May 28, 2024

ok, thanks,

from semi-supervised-learning.

Gank0078 avatar Gank0078 commented on May 28, 2024

Hi, thank you for your great job! I also want to know whether imbalanced algorithms be released soon?

from semi-supervised-learning.

Hhhhhhao avatar Hhhhhhao commented on May 28, 2024

Hi, thank you for your great job! I also want to know whether imbalanced algorithms be released soon?

Expected this week along with results and logs.

from semi-supervised-learning.

Hhhhhhao avatar Hhhhhhao commented on May 28, 2024

Updated in 69a2afc

from semi-supervised-learning.

weiliangwuw avatar weiliangwuw commented on May 28, 2024

Traceback (most recent call last):
File "train.py", line 416, in
main(args)
File "train.py", line 320, in main
main_worker(args.gpu, ngpus_per_node, args)
File "train.py", line 399, in main_worker
model.train()
File "/data/gauss/wlw/Semi-supervised-learning-main/semilearn/core/algorithmbase.py", line 349, in train
self.call_hook("before_train_epoch")
File "/data/gauss/wlw/Semi-supervised-learning-main/semilearn/core/algorithmbase.py", line 560, in call_hook
getattr(hook, fn_name)(self, *args, **kwargs)
File "/data/gauss/wlw/Semi-supervised-learning-main/semilearn/imb_algorithms/cossl/cossl.py", line 85, in before_train_epoch
init_teacher, init_ema_teacher = classifier_warmup(algorithm.args, copy.deepcopy(algorithm.ema_model),
File "/data/gauss/wlw/Semi-supervised-learning-main/semilearn/imb_algorithms/cossl/utils.py", line 82, in classifier_warmup
tfe_model = weight_imprint(args, copy.deepcopy(model), train_labeled_set, num_class, gpu)
File "/data/gauss/wlw/Semi-supervised-learning-main/semilearn/imb_algorithms/cossl/utils.py", line 268, in weight_imprint
new_weight = torch.zeros(num_classes, model.module.backbone.num_features)
File "/data/.conda/envs/usb/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1695, in getattr
raise AttributeError(f"'{type(self).name}' object has no attribute '{name}'")
AttributeError: 'CoSSL_Net' object has no attribute 'module'

当我训练到中间的时候出现了这个错误,这是怎么回事呢?已经迭代了81920次了,
我是在freematch的算法,加入了cossl,配置文件如图所示:
image

from semi-supervised-learning.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.