search

Albert0147 / AaD_SFDA

Code for our NeurIPS 2022 (spotlight) paper 'Attracting and Dispersing: A Simple Approach for Source-free Domain Adaptation'
64 stars 6 forks source link

Pre-trained source models #5

Open sudalvxin opened 1 year ago

sudalvxin commented 1 year ago

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

sudalvxin commented 1 year ago

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

Albert0147 commented 1 year ago

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

sudalvxin commented 1 year ago

ok, Thank you!

LiuMing-Hui commented 1 year ago

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 commented 1 year ago

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

LiuMing-Hui commented 1 year ago

Thank you very much!