SMP icon indicating copy to clipboard operation
SMP copied to clipboard

Published 20 hours ago • verified publisher icon sarsbug
→

Metadata

Pytorch implementation for Deep Self-Learning From Noisy Labels

Results 4 SMP issues
Sort by recently updated
recently updated
newest added

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 it possible to identify the noisy instances (return...

nazaretl avatar nazaretl

Do you know how to solve the problem of unstable ?

hi, blogger！I also find the unstable problem by using the SMP algorithm, and I think it is caused by random sampling. Do you have any idea ?

Shougong avatar Shougong

According to my research, this paper has been re-implemented by USC---in the paper NoiseRank: Unsupervised label noise...

2 comment

LanXiaoPang613 avatar LanXiaoPang613

batch_y_pseudo = self.y_pseudo[step*batch_size:(step+1)*batch_size].cuda()

Hello, I think there is an error in the code here. In each epoch,the sample of dataset is different.The y_pseudo and the batch_y can not be mapped correctly by the...

momo666666 avatar momo666666

← Metadata

33
Stars
2
Forks
Watchers

Owner

verified publisher icon sarsbug

Metadata

Pytorch implementation for Deep Self-Learning From Noisy Labels

Back