Taewhan KIM

Hi Thanks for wonderful project. At architecture of body model(19 or 25), before last process of concat, last each layers represent confidence map(Mconv7_stage6_L2), PAF(Mconv7_stage6_L1). But, in the last layer of...

Transformer 모델 학습시 y_hat이 float로 출력

3

좋은 소스를 공유해주셔서 감사합니다! Speech transformer 모델로 학습시 supervised_trainer.py ``` while True: inputs, targets, input_lengths, target_lengths = queue.get() if inputs.shape[0] == 0: break inputs = inputs.to(self.device) targets = targets[:, 1:].to(self.device)...

Is it possible to train KSS dataset in master branch?

2

Thanks for sharing great result. I want to train kss data for training vocoder to use in fastspeech2 with master branch code, is it possible? ``` Avg : g 1.3729...

How to get texture map from image for rendering?

1

Hi, Thanks for sharing great project! I'm wondering, how to extract texture map (ex - `.data/smpl_tex.png in your project`) from image? Already downloaded smplx_uv.png and smplx_uv.obj in [Official smplx site](https://smpl-x.is.tue.mpg.de/)...

Thanks for sharing great repo! I'm wonder how to get UV map with Human image texture (ex - .data/smplx_tex.png) I downloaded **smplx_uv.png** in [Official smplx site](https://smpl-x.is.tue.mpg.de) but don't know how...

How to extract only UV map in Figure 3.(e) ?

2

Thanks for sharing great repo!! I wonder how to get UV map like in Fig 3.(e) In demo.py ` uvmap = self.get_texture(img_tensor, parts)` [ uvmap = self.get_texture(img_tensor, parts)](https://github.com/xuxy09/Texformer/blob/f415da127cce01628da1fbb131dfcac13d18a202/demo.py#L132) When I...

[Inference.py] I've always get error : RuntimeError: Image too big to run face detection on GPU. Please use the --resize_factor argument

15

Hi there, Thanks for sharing wonderful project! If I run inference.py to check how it works, I always get this error ` RuntimeError: Image too big to run face detection...

혹시 FreiHAND+InterHand2.6M+MSCOCO 로 학습된 pretrained-model 도 hand4whole model과 combine시킬 수 있나요?

7

먼저 정말 좋은 프로젝트를 공유해주셔서 감사합니다!! 코드를 따라 혼자 학습을 진행해보려하는데 궁금한점이 있어 이슈에 글을 올립니다. [2nd stage](https://github.com/mks0601/Hand4Whole_RELEASE#2nd-pre-train-hand-only-pose2pose)에 올려준 pretrained hand model 이 아닌 hand-only Pose2Pose trained on FreiHAND+InterHand2.6M+MSCOCO 로...

Different results at CiDER metric in paper

1

Hi there, firstly thanks for sharing wonderful project! Can you share the embedding model and parameter values ​​that produced the best performance in the CiDER metric in table1 and fig3?...