MDDA
MDDA copied to clipboard
daoyuan98
Implementation of paper multi-source distilling domain adaptation
Dear friend! During the training for S2_adv, the gen_loss and disc_loss are divergency by Wasserstein distance. However, it is fine with cross_entropy loss referenced by the adda project. Can you...
“we preprocess all of these data into a json file ” Thank you for your open source code. May I ask if the processed data set in jison format can...
I saw your paper on arxiv, and I was deeply inspired. I feel that your paper did a very good job, so I hope to see the implementation on the...
