DANN_py3

DANN_py3 copied to clipboard

Size of target domain

1

I have a training set with 50k source images and 1k target images. Is DANN a good approach for this use case? If not, what is your recommendation?

jsetty

您好，我想请问一下，为了使源域和目标域距离拉近，随时训练的加深，域分类器的loss（error）是不是应该越来越大呀，

kikiYa99

The domain classifier loss is not decreasing.

4

As shown in the image above, the domain classifier loss is almost constant throughout the training process. I use a ViT as the feature extractor, a linear layer as label...

zhongpeixiang

救命！帮帮我！

1

我想做可以检测森林火灾烟雾的DAN模型，那我是不是需要更换源域数据集呀，更换源域数据集的话都需要改什么部分呀

yjyjjy