Xlearn
Xlearn copied to clipboard
Transfer Learning Library
I have read the paper “Transferable Attention for Domain Adaptation” published in AAAI 2019 and interested a lot. The paper wrote the code and datasets would be available at github.com/thuuml,...
Hi, Thanks for your great jobs! But I have some questions about the MMD/JMMD loss. the unbiased estimate of JMMD in paper is as follow: ![image](https://user-images.githubusercontent.com/48144572/110268524-be87f780-7ffc-11eb-9bab-86b8953881e5.png) while the code is:...
Hi, In the paper "**Transferable Representation Learning with Deep Adaptation Networks**", you use cross-entropy loss (which is corresponding to equation 8 in the paper) to minimize the uncertainty of predicting...
I found that inputs = [data[j][0] for j in range(10)] labels = data[0][1]. labels is a a constant value. How should it be modified?
In " loss.py " about ,"DAN loss ",it use MK-MMD? why i think it only use MMD In a certain layer. who can tell me?
In " loss.py " about ,"DAN loss ", I dont't find bata parameter of multi -guassian_kernels and dont't known how it update? Can someone tell me? Thanks.
Hello, I used caffe implementation. Sometimes MMD backward diff = NaN, and soon the whole network crushed. In my inplementation, the data is sliced into to branches in fc layers,...
I am using the current pytorch implementation for binry classification. I wanted to use a sigmoid function. Will that affect the MMD loss. though according to the paper I feel...
You have done a great job. But I have a question about the MMD Loss. The proposed MMD Loss in the paper are as follows, we can see that source...
.item
{'trade_off': 1.0, 'name': 'JAN'} Traceback (most recent call last): File "train.py", line 288, in transfer_classification(config) File "train.py", line 222, in transfer_classification print image_classification_test(dset_loaders["target"], nn.Sequential(base_network, bottleneck_layer, classifier_layer), test_10crop=prep_dict["target"]["test_10crop"], gpu=use_gpu) File "train.py",...