-
i cannot get the evaluate_diy function in eval_metrics_cvae.py. can u provide it for reference ?thanks！
-
Hi,
For the Model Confidence score, is the underlying dialogue model SEQ2SEQ? But I also found loss of dialogwae/hred/transformer/cvae. What's the meaning of these values and how did you use them?
T…
-
https://github.com/OpenTalker/SadTalker/blob/ae0b26359d44c9379450a8e02a38b45eeec15549/src/audio2pose_models/cvae.py#L94C9-L94C42
I think it should be "linear_logvar" !
-
I am attempting to reproduce your work, and I would like to know about the training resources utilized for the CVAE and reinforcement learning components in your work, such as the duration of training…
-
Hi 助教
想問一下每次 batch[0].cuda( )的size是否都固定 [64, 1, 28, 28], 我run到 batch 46900/937, size就會變成 [32, 1, 28, 28], 請問64 和 32的不同?
-
**Describe the bug**
During training, if the model has been running a long time it will occasionally return NaNs. I suspect this is related to the `SMALL_CONSTANT` variable in `CVAE_model.py`.
-
Hi,
I am trying to replicate your chatbot model. I did exactly the same thing as you mentioned in the README. I got more or less similar kl/reconstruction loss for training CVAE. But for emoji clas…
-
Hello,.
I have a question about how the model was trained? I saw two losses in the compile_models function in the _trave.py file. I also saw two outputs in the model, reconstruction_output and mmd_…
-
VAR is indeed impressive, but there’s one issue that’s been bothering me. We reached out to the authors for assistance with the matter, and we appreciate your help.
In the quant.py line 33: self.qu…
-
Can you provide the pre-trained model？
9ime updated
4 months ago