uniBruce
uniBruce
> Hi @uniBruce , the code uses 'batch' settings for testing, so if you want to test on other datasets rather than CelebA or EmotionNet, you'll need to create a...
Hi, it's me again. I noticed that you made the lambda_mask and lambda_tv both 0, could you explain it? Because these two parameters really brought me much trouble when I...
> Hi @uniBruce, from my point of view, these two parameters won't affect too much of the final results, as long as they are not set to some very large...
> > Hi, it's me again. I noticed that you made the lambda_mask and lambda_tv both 0, could you explain it? Because these two parameters really brought me much trouble...
> Hi, what's your test data "*.h5" order? Are you following the test.list? Why did you rename them from "0000.h5" to "1199.h5"? Hi, have you got the answer of this...
> Sorry, I will inform the related staff to check the issue.
> Hi, > > I downloaded part of the datasets and found that the correspondence of the audio snippets are not arranged as what I have expected. > > I...
> Thank you for the reply. > > I have read the supp and realize why there are different numbers of snippets in neutral and other emotions. But there still...
> You can modify the training code's pipeline by first loading the model's checkpont before training. Does the provided "ours_t" checkpoint file share the same experiment setting with the default...