Zixin Wang comments

Results 7 comments of


                                            Zixin Wang

Missing key(s) when loading the pre-trained simclr model parameters in stage 3

Same issue here

Missing key(s) when loading the pre-trained simclr model parameters in stage 3

> I have found out the key point to solve the problem. Parameter "bn_clr" should be deleted from the command line code used to generate pseudo labels. I've also tried...

Missing key(s) when loading the pre-trained simclr model parameters in stage 3

> The last two parameters can be deleted at the same time, have a try! > […](#) > ------------------ 原始邮件 ------------------ 发件人: "microsoft/ProDA" ***@***.***>; 发送时间: 2021年10月1日(星期五) 中午1:13 ***@***.***>; ***@***.******@***.***>; 主题: Re: [microsoft/ProDA] Missing key(s)...

Training error: RuntimeError: For non-complex input tensors, argument alpha must not be a complex number.

Same error here, and I've tried to increase num_steps in so_config.yaml but it didn't work. Could you provide the parameter that you use to train source-only model? Thank you!

Training error: RuntimeError: For non-complex input tensors, argument alpha must not be a complex number.

Hi, I just solved that several days ago. The error caused by the fixed max number of steps in adjusting learning rate. You can have a check if it's work....

IndexError: only integers, slices (`:`), ellipsis (`...`), numpy.newaxis (`None`) and integer or boolean arrays are valid indices

> check your python version, it should be use python2 Is there any difference in this case? I solved this problem but is show another problem which is sj will...

Training error: RuntimeError: For non-complex input tensors, argument alpha must not be a complex number.

> > 嗨，我几天前刚刚解决了这个问题。调整学习率时固定的最大步数引起的错误。您可以检查它是否有效。干杯，zx > > I also encountered this problem recently, can you elaborate on how to solve it? Thank you very much Hi there, Sorry for the late reply....