result

[Zhudogsi]

Hello, may I ask if the accuracy result in this paper is a good thing of has0 and no-has0? What's the difference between aligned and misaligned results? What method is used to align different modes? thank you for your reply.

[xueyuG]

I'm also trying to reproduce the model. Judging from the code provided by the author, they only calculate non0_acc2 but not has0_acc2.

[hustcselwb]

请问论文中的结果是同一个epoch下的结果吗，还是不同epoch下的最优结果。

[Raymond-Qiancx]

I'm also trying to reproduce the model. Judging from the code provided by the author, they only calculate non0_acc2 but not has0_acc2.

Yes, i have the same question, and my running results is 2% lower than the paper illustrated.

[Issac304]

确实低了一点，解决了吗？

[tbzzzzz]

May I ask if there is a problem with my settings, as the unaligned version of the paper gave 83.5, but I tested and found it to be almost 3%?