DFRF

DFRF copied to clipboard

我替换成 deepspeech-0.9.2-models.pbmm会报错

4

感觉默认的 deepspeech是v0.1，我就换成 0.9.2或者 0.9.3，都会报错 Traceback (most recent call last): File "/home/tailangjun/Documents/AIGenHuman/NerfLips/DFRF/data_util/deepspeech_features/extract_ds_features.py", line 133, in main() File "/home/tailangjun/Documents/AIGenHuman/NerfLips/DFRF/data_util/deepspeech_features/extract_ds_features.py", line 125, in main extract_features( File "/home/tailangjun/Documents/AIGenHuman/NerfLips/DFRF/data_util/deepspeech_features/extract_ds_features.py", line 82, in extract_features conv_audios_to_deepspeech( File...

tailangjun

我在运行`sh process_data.sh ${id}`时遇到了问题，产生`raise AttributeError(name) from None`的报错。经排查，发现是`data_util/process_data.py`的第101行出现了bug。 `face_alignment.LandmarksType.__2D`语句中，`LandmarksType`这个枚举里并没有成员`__2D`，而是`TWO_D`，修改为`face_alignment.LandmarksType.TWO_D`后代码正常运行。 我的`face_alignment`的版本是1.3.5，和作者在requirements.txt里写的一样。不知道为何看似只有我出现了这个问题。

unknownzjuer

https://github.com/sstzal/DFRF/assets/156503481/14451223-cfca-4ef0-9b3a-9eb901d6ca0a

dousang1999

indices_.reshape(indices_.shape[0], 1024, -1, indices_.shape[2]) error in run_nerf_deform.py

8

Nice work! Thanks your sharing code. When I rendering.sh one video, there is a problem in this line: ``` try: indices_ = indices_.reshape(indices_.shape[0], 1024, -1, indices_.shape[2]) except: pdb.set_trace() ``` I...

aishoot

Anastasia-Zyh

jeminteza08

JunjieLl

训练视频需要一镜到底吗

1

如果没有15s长度的视频可以拼接几个短视频吗

luqianX

poor performance on lip sync for chinese video

3

Thanks for your work! I want to train it with Chinese video,however, the output video having a poor performance on lip sync, is this because the deepspeech model does not...

yxqyyy

Strange artifacts in result

15

I am run script process_data.sh for "cnn", run script rendering.sh with parameters ` iters="french_500000_head.tar" names="french" datasets="cnn" ` and get following images:  What is this body-colored artifacts around head? And...

Vadim2S