GithubHelp home page GithubHelp logo

famus's People

Contributors

youjiangxu avatar

Stargazers

avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar avatar

Watchers

avatar avatar avatar avatar avatar avatar avatar

famus's Issues

The result you provided cannot be achieve based on this code.

We trained the model with your code and default settings (NL=0.8) but we didn’t achieve the result you provided. The validation log is shown below.

Instructions for updating:
To construct input pipelines, use the `tf.data` module.
INFO:tensorflow:Starting evaluation at 2021-09-02-13:40:44
I0902 21:40:44.409504 139727230316736 evaluation.py:450] Starting evaluation at 2021-09-02-13:40:44
2021-09-02 21:40:44.808432: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2021-09-02 21:40:45.073419: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
INFO:tensorflow:Evaluation [20/200]
I0902 21:40:47.569142 139727230316736 evaluation.py:167] Evaluation [20/200]
INFO:tensorflow:Evaluation [40/200]
I0902 21:40:48.506234 139727230316736 evaluation.py:167] Evaluation [40/200]
INFO:tensorflow:Evaluation [60/200]
I0902 21:40:49.461488 139727230316736 evaluation.py:167] Evaluation [60/200]
INFO:tensorflow:Evaluation [80/200]
I0902 21:40:50.409007 139727230316736 evaluation.py:167] Evaluation [80/200]
INFO:tensorflow:Evaluation [100/200]
I0902 21:40:51.340363 139727230316736 evaluation.py:167] Evaluation [100/200]
INFO:tensorflow:Evaluation [120/200]
I0902 21:40:52.284018 139727230316736 evaluation.py:167] Evaluation [120/200]
INFO:tensorflow:Evaluation [140/200]
I0902 21:40:53.217222 139727230316736 evaluation.py:167] Evaluation [140/200]
INFO:tensorflow:Evaluation [160/200]
I0902 21:40:54.177478 139727230316736 evaluation.py:167] Evaluation [160/200]
INFO:tensorflow:Evaluation [180/200]
I0902 21:40:55.141287 139727230316736 evaluation.py:167] Evaluation [180/200]
INFO:tensorflow:Evaluation [200/200]
I0902 21:40:56.100607 139727230316736 evaluation.py:167] Evaluation [200/200]
INFO:tensorflow:Finished evaluation at 2021-09-02-13:40:56
I0902 21:40:56.101341 139727230316736 evaluation.py:456] Finished evaluation at 2021-09-02-13:40:56
test/accuracy[0.284]
total_loss[3.83895969]
INFO:tensorflow:Waiting for new checkpoint at ./output/mini_imagenet_models/resnet32/red_noise_nl_0.8/mentormix//train
I0902 21:44:35.734614 139937759006912 evaluation.py:189] Waiting for new checkpoint at ./output/mini_imagenet_models/resnet32/red_noise_nl_0.8/mentormix//train

We also trained again but got the similar result. Could you give me some advices about that?
Thank you.

RuntimeError in grad_operator_layer.py

FaMUS/FaMUS/grad_operator_layer.py

Line 57 in 26a7b22

if grad_act > 0.5:

Hi, thanks for your excellent work, it's really impressive. I am trying to reproduce your code, but I noticed some problems. Would you please give some explanations, thanks a lot.
(1) line57 in grad_operator_layer.py
this line of code always caused the "RuntimeError: Boolean value of Tensor with more than one value is ambiguous";
(2) line61 in grad_operator_layer.py
"acts.append(grad_act)", this line of code puzzles me, would you give more explanations ?
(3) the new_grads variable in grad_operator_layer.py
I do not think this updated new_grads will match the parameters in the meta model, it actually causes parameters mismatch error.
Best

About Code Release

Hi, dear author, I am very interested after reading your paper. When will you release the code?

tabular data/ noisy instances

Hi,
thanks for sharing your implementation. I have two questions about it:

  1. Does it also work on tabular data?
  2. Is is possible to identify the noisy instances (return the noisy IDs or the clean set)

Thanks!

About the contrast algorithm MW-Net

I notice that you compared your work with MW-Net on webvision. Can you provide the details about how to construct the meta data for MW-Net when training on webvision?

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.