Pre-trained source models

[sudalvxin]

Thanks to the author for contributing the code! Can you provide your pre-trained source models?

[sudalvxin]

The pre-trained source models are consistent with your paper 'Exploiting the intrinsic neighborhood
structure for source-free domain adaptation'?

[Albert0147]

Hi, I think so. Otherwise, you can also directly train it, as it is quite fast.

[sudalvxin]

ok, Thank you!

[LiuMing-Hui]

Thanks to the author for contributing the code! When I run src_pretrain directly, both the loss and feature become ‘nan’ on the second batch. Do you have this problem when running code?

[Albert0147]

Hi, I think the code is correct, which should be the same as our previous work.

[LiuMing-Hui]

Thank you very much!