unsupervised-data-augmentation

unsupervised-data-augmentation copied to clipboard

Looking Forward to Your Experiments on ImageNet

3

Hi, I am curious whether if you will do experiments on ImageNet. The official repo didn't release the codes on this large dataset. But I see the TODO list in...

semi-supervised-paper

Using mixup in supervised data

1

Inspired by the paper Mixmatch, mixup can be used in supervised data. In this way, we can achieve improved performance, even better than the native UDA. 

mzchtx

I haven't found the Training Signal Annealing(TSA) function, why don't you implement it?

yxyuni

In the paper， the weight of unsup_loss is set to 1 to comput the whole loss，but in your code, the weight of unsup_loss is set as ratio_unsup=5.0. For example， https://github.com/ildoonet/unsupervised-data-augmentation/blob/master/train.py#L71...

feimengjuan

https://github.com/ildoonet/unsupervised-data-augmentation/blob/master/train.py#L231, why a not in first bracket?

getsanjeev