KevinGoodman

In the demo example , the histroy search can't be deleted , yet there's a "X" aside.

 Thanks for sharing the code. However, I'm quite confused for the code of QGM as the naming of the code is a little different from the original paper(if I...

I am not sure why the implementation only use the tokenizer from hugging face but did not use the pre-trained encoder. I mean why need to retrain the BERT-like transformer?...

Classifier free guidance

1

Thanks for sharing the code, I cannot find the classifer free guidance in this implementation. I wonder if I miss it, if so can you show me where it is?...

Thanks for your great work. I notice that the the root joint position of the predicted 3d kp is fixed. I wonder how I can get the root joint position...

Thanks for sharing your wonderful work! I wonder how you get the specific number, 15360 * 2, as the sampling rate for 60 FPS. Can you elaborate how specific rate...

In-the-wild 3D Face Reconstruction

1

Thanks for sharing the code. I wonder when can we expect the update for EMICA.

Why use 2 time tokens?

2

```python self.to_time_tokens = nn.Sequential( nn.Linear(latent_dim * 4, latent_dim * 2), # 2 time tokens Rearrange("b (r d) -> b r d", r=2), ) ``` In L278-L281 of model/model.py, what is...

dataset naming rule and music genere labels

7

Thanks for releasing the dataset. It would be really nice if extra explanation about the naming system of the dataset can be provided(as well as other useful labels such as...

https://github.com/radekd91/inferno/blob/master/inferno/models/DecaFLAME.py#L222 Could you please clarify what length unit is used for the vertex coordinates obtained from FLAME? Is it in meters? If not, how can I convert it to other...