wogong / pytorch-dann

A PyTorch implementation for Unsupervised Domain Adaptation by Backpropagation

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Result interpretation

opened this issue · comments

Hello, I'm working on DANN algorithm and I'm wondering how to interpret my print results from your repo ? I got this after 100 epochs:

tgt -> Avg Loss = 0.019690, Avg Accuracy = 77.73%, 7761.0/9984, Avg Domain Accuracy = 58.553686%
src -> Avg Loss = 0.000233, Avg Accuracy = 99.56%, 59704.0/59968, Avg Domain Accuracy = 68.128002%
``
commented

please inspect the source code for more info.