corenel / pytorch-adda

A PyTorch implementation for Adversarial Discriminative Domain Adaptation
MIT License
473 stars 138 forks source link

RNN network invalid #26

Open zhangqingqing24630 opened 3 years ago

zhangqingqing24630 commented 3 years ago

1 I use RNN network as encoder, save the trained model in the source domain and test the USPS data set. The accuracy rate is only 10%, which is not as good as lenet network. Why is this 2 Does ADDA algorithm replace the noise with the target domain data set on the basis of Gan? 3 After using RNN as encoder, There is no obvious change in g_loss during confrontation generation.

onlyonewater commented 3 years ago

我利用他这个代码,实现了一遍,发现也达不到文章中的精度哇