ponykid
ponykid
> i face the same question ,so how to fix this problem? please
I think is_infer should be set to False in the trainning process
Thank you for your sharing. However, I think that there a mistask in the code. var = F.softplus(variance(x)) means that log(1+var(x)**2), however,the gaussiannlloss is 0.5 * log(x**2)+mse/var(x)**2(attention the var(x)**2) ,...
I don't know how to solve 在 2022-08-24 15:00:52,"shirui1122378" ***@***.***> 写道: AttributeError:“DataParallel”对象没有属性“生成器” Have you solved the problem? — Reply to this email directly, view it on GitHub, or unsubscribe. You...
I notice the w_loss decreases to -6.0, so I am so confused about that why w_loss can be negative?