Skip to content

issues Search Results · repo:bhanML/Co-teaching language:Python

Filter by

11 results
 (61 ms)

11 results

inbhanML/Co-teaching (press backspace or delete to remove)

bhanML/Co-teaching
tabular data/ noisy instances/ new datasets

Hi, thanks for sharing your implementation. I have some questions about it: 1. Does it also work on tabular data? 2. Is the code tailored to the datasets used in the paper or can one apply it to any ...
  • nazaretl
  • Opened 
    on May 9, 2022
  • #13

bhanML/Co-teaching
How to inference given two trained nets?

How to inference given two trained nets (net1 net2)? by using net1 only?
  • qianc62
  • Opened 
    on Oct 12, 2021
  • #12

bhanML/Co-teaching
How to ensure ‘noise rate’ if I use the method on my datasets?

How to ensure ‘noise rate’ if I use the method on my datasets? Is {0.2, 0.45, 0.5} recommended? and how to ensure the parameter from validation set?
  • qianc62
  • Opened 
    on Oct 11, 2021
  • #11

bhanML/Co-teaching
no need to calculate average after F.cross_entropy in loss.py

In line 29 of loss.py, there is no need to do torch.sum(loss_1_update)/num_remember. Because the result of F.cross_entropy with default parameters reduce = True and size_average = True is the average loss. ...
  • Vicky7777
  • Opened 
    on Feb 2, 2021
  • #9

bhanML/Co-teaching
data augmentation makes performance worse

Oddly, if I add the most common standard data augmentation to CIFAR-10 training, namely: transform=transforms.Compose([ transforms.RandomCrop(32, padding=4), transforms.RandomHorizontalFlip(), ...
  • cgnorthcutt
  • 1
  • Opened 
    on Feb 5, 2020
  • #8

bhanML/Co-teaching
cifar10 and cifar100 parameters

Hey guys, thanks for your nice work. I am now trying to re-produce your result presented in the paper. However, I could not reach your result on cifar10 and cifar100. cifar10 is just a bit lower (71.8% ...
  • CandiceUIC
  • 4
  • Opened 
    on Sep 17, 2019
  • #7

bhanML/Co-teaching
Simple CNN

  • hongxin001
  • 4
  • Opened 
    on Jul 1, 2019
  • #6

bhanML/Co-teaching
A question about your loss_coteaching function

Hello, I find that in your class loss_coteaching , the parameters you passed are y_1, y_2, which are already the log_softmax results. But you then used the cross_entropy, which has combined the log_softmax ...
  • nihaomiao
  • 4
  • Opened 
    on Mar 4, 2019
  • #4

bhanML/Co-teaching
Weird test accuracy curve

I tested your original codes and found out that the test accuracy dropped sharply around 40 epochs and fluctuated drastically until the final 20 epochs which does not match the curve in your paper. Can ...
  • howiethepeanut
  • 3
  • Opened 
    on Jan 21, 2019
  • #3

bhanML/Co-teaching
Detail experiment results sharing

In order to compare with co-teaching, i want to cite the figure 3, 4, 5, 6 in your paper. Can you share your detail experiment results with me? It‘s quite useful for me. Thank you very much.
  • huangyangyu
  • Opened 
    on Dec 27, 2018
  • #2
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub