Rejnald Lleshi
Rejnald Lleshi
Could someone please merge this? It's just a single line.
That was the original problem :sweat_smile: Otherwise, the default arg should be changed from `default='.m4a'` to just `m4a`
Is this PR still planned? @jin-s13 kind ping. @ailingzengzzz @ly015
@ttxskk fixed the conflict
@liuhaorandezhanghao did u manage to incorporate the camera parameters so that the character isn't anchored on the mid point anymore?
First, thanks a lot for the great repo. Do you have a rough timeline for when (if at all) this will be available?
> Following the way that CHD explored, I am trying to develop a more concise/compact method to achieve the dynamics smoothness, just like the spirit of ROMP. I mean this.
FYI: These models could yield much better results with a better dataset & some more effort. So the only hindrance would be the GPU(s).
Write a wrapper around the model such that only the prediction of the model is returned: ``` class ModelInferenceGradCam(torch.nn.Module): def __init__(self, model): super().__init__() self.model = model def forward(self, x): return...
This is still an issue.