DivideMix

DivideMix copied to clipboard

question about penalty

4

`prior = torch.ones(args.num_class)/args.num_class` `prior = prior.cuda()` `pred_mean = torch.softmax(logits, dim=1).mean(0)` `penalty = torch.sum(prior*torch.log(prior/pred_mean))` entropy=p*log(p) why not penalty = `torch.sum(pred_mean*torch.log(prior/pred_mean))`

hhhhnwl

Need For Kind Help in Paper's Replication

3

Hi li， I got a poor performance in both cifar-10/100 when the noise ratio is high than 80%, which mainly indicating 80% 90% in Table 1. All goes well with...

Christophe-Jia

Lambda_u for CIFAR-100 on 40 asym noise

2

Hi, I haven't been able to find which hyper-parameters you use to train on CIFAR-100 with 40% asymmetric noise. Can you please tell me? Thank you! P.S: Awesome work!

aldakata

Plot Figure 2

3

Dear author Thank you very much for your excellent code. My recent work is also trying to identify noise labels from correct labels. I'm curious where you output the loss...

xiqxin1

Hi, I am impressed and interested in your outstanding work. However, I noticed a question about the batch size while experimenting with the code. When I increase the batch size...

lxysl

At cifar10 0.2 sym noise rate setting, cann't repeat the results reported at paper.

4

The cifar10 0.2 noise rate, I can only get about 91.5% acc useing the code, and I can't find the reason

sillytheif

why change dimension

1

why cahnge (samples, channels, height, width) to (samples, height, width, channels) in cifar-10 and cifar-100? (transpose((0, 2, 3, 1))) I wonder the last dimension is (samples, channels, height, width) or...

IwGrin

IwGrin

I have some issues with the CIFARN dataset, has anyone tested DMix on this dataset

1

I couldn't achieve the accuracy of CIFAR10-N on its dataset's official website, or even much worse.Any recommendations for hyperparameters?

kl258521