GeneFace

GeneFace copied to clipboard

CUDA_VISIBLE_DEVICES=0 data_gen/nerf/process_data.sh $VIDEO_ID (missing files and issues)

4

[INFO] ===== extract audio from data/raw/videos/May.mp4 to data/processed/videos/May/aud.wav ===== ffmpeg version 4.2.2 Copyright (c) 2000-2019 the FFmpeg developers built with gcc 7.3.0 (crosstool-NG 1.23.0.449-a04d0) configuration: --prefix=/tmp/build/80754af9/ffmpeg_1587154242452/_h_env_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placehold_placeho --cc=/tmp/build/80754af9/ffmpeg_1587154242452/_build_env/bin/x86_64-conda_cos6-linux-gnu-cc --disable-doc --enable-avresample --enable-gmp...

wnqw

训练训练PostNet模型时报AttributeError: 'PostnetAdvSyncTask' object has no attribute '_lazy_val_dataloader'

1

Traceback (most recent call last): File "Z:\GeneFace-main\utils\commons\dataset_utils.py", line 158, in _get_data_loader value = getattr(self, attr_name) File "C:\ProgramData\Anaconda3\envs\geneface\lib\site-packages\torch\nn\modules\module.py", line 1185, in __getattr__ raise AttributeError("'{}' object has no attribute '{}'".format( AttributeError: 'PostnetAdvSyncTask'...

Liuling608

My cuda version is 11.3.1,I don't know what cause this happen.

Westbrook077

ModuleNotFoundError: No module named 'utils.commons'

2

执行以下语句export PYTHONPATH=./, 出现这个报错ModuleNotFoundError: No module named 'utils.commons'

zhieie

请问原始数据集目录下的每个文件夹名称分别是什么啊？

1633347510

FileNotFoundError: data/processed/videos/May/ori_imgs/0.lms not found

3

While run "bash scripts/infer_lm3d_radnerf.sh", FileNotFoundError: data/processed/videos/May/ori_imgs/0.lms not found **How to solve this problem? Thanks** In more detail: ================================================================================= (geneface) llm@llm-PowerEdge-R730xd:~/projects/GeneFace$ bash scripts/infer_lm3d_radnerf.sh /home/llm/anaconda3/envs/geneface/lib/python3.9/site-packages/torch/autocast_mode.py:162: UserWarning: User provided device_type of 'cuda', but...

jackyin68

LRS3

2

大佬，可以开放下LRS3的原始数据集吗？官方目前下架了

JJun-Guo

用Chinese Mandarin Lip Reading（CMLR）数据集训练syncnet模型，训练40000步。最终的syncloss停留在0.34，感觉这个loss有点高，对比了下lrs3的训练，在15000步的时候，syncloss 就能到0.25左右。

12

yulj21

我按照docs/prepare_env/install_guide.md中的步骤，执行到下面这个命令的时候，报错，请问是什么原因啊？ sudo apt-get install libasound2-dev portaudio19-dev 报错的完整消息： Reading package lists... Done Building dependency tree Reading state information... Done E: Unable to locate package libasound2-dev E: Unable to locate package portaudio19-dev

SEUlegend

CUDA error: no kernel image is available for execution on the device

1

start extracting 3DMM...: 0%| | 0/189 [00:00

angelandy