CuthbertCai

公式4.17中的第二个指示函数是否应该为等于1而不是等于0

@jindongwang 可能我没有表达清楚，我的意思是第二个指示函数中是否应该是$\eta(x_i)=1$而不是$\eta(x_i)=0$，对于假设$\eta$来说来自source domain的样本应该判断为0，来自target domain的样本应该判断为1吧

> > Hi, > > I'm not sure if this is an issue, or that's my misunderstanding. You calculated loss as: > > loss = class_loss + params.theta * domain_loss...

> > > > Hi, > > > > I'm not sure if this is an issue, or that's my misunderstanding. You calculated loss as: > > > > loss...

> RuntimeError: output with shape [1, 28, 28] doesn't match the broadcast shape [3, 28, 28] I'm not sure if you meet this error when extracting features of MNIST. If...

@tengerye I run this code several times and find that the results are not stable. The best result I get is about 72% and the worst one is about 67%....

@tengerye After merging your request, maybe I found the reason why our results are so different. In function `get_test_loader()`, I used `transforms.CenterCrop()` while you used `transforms.RandomCrop()` for `MNIST_M`. Thus, I...

@omg777 I tested the original version, ploted the embeddings and founded that the distributions are not mixed. For the newest version, I just recorded the accuracy and did not check...

@omg777 The original version means the first version I pushed, instead of the caffe implemented version. In fact, I don't know why the embedding are not mixed well while the...

@tengerye @omg777 Here is my embedding plot after 100 epochs, and the embeddings seem not mixed well.