zhang

Hello! I trained for 40 epochs, batch_size=1, but the loss function of the generator does not seem to converge, why is this? Can you please provide some advice, thanks

please see https://github.com/CuriousAI/mean-teacher/issues/17%20%20 , the answer of tarvaina can help you !

The same, how can I train my own datasets? Thx!!!

@xuhaohao86 Hello, according to the formula of cycle-consistency loss, the loss function of each pixel is calculated by L1 norm, seems to be effective for image segmentation, rather than just...

@Luodian 讲得挺清晰的，非常感谢！Clarified it pretty clear :-)， thank you so much !

”Note that we can also consider a feature-level method Which distinguishes the features or semantics from two image sets as viewed under **_a task network_**. “ I think both f...

@zhangmozhe @msftdata @msftgits @dnfclas Could you please answer my question? thx!