配置运行video retalking遇到的问题和注意事项_videoretalking 模型下载

ReadTimeoutError: HTTPSConnectionPool(host=‘download.pytorch.org’, port=443): Read timed out.

pip3 install torch1.10.0+cu113 torchvision0.11.1+cu113 torchaudio===0.10.0+cu113 -f https://download.pytorch.org/whl/cu113/torch_stable.html -i https://pypi.tuna.tsinghua.edu.cn/simple
pip --default-timeout=1688 install 库名称 -i http://pypi.douban.com/simple/ --trusted-host pypi.douban.com
安装cuda11.1:

https://developer.nvidia.com/cuda-toolkit-archive
设置环境变量：运行control system
CUDA_HOME,C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1
pip --default-timeout=1688 install torch1.9.0+cu111 torchvision0.10.0+cu111 -f https://download.pytorch.org/whl/torch_stable.html
python inference.py --face examples/face/1.mp4 --audio examples/audio/1.wav --outfile results/1_1.mp4
pip install opencv-python
pip install scikit-image
pip install face_recognition
pip install kornia
python inference.py --face examples/face/1.mp4 --audio examples/audio/1.wav --outfile results/1_1.mp4
pip install numpy1.23.1
TypeError: mel() takes 0 positional arguments but 5 were given
pip install librosa0.9.1
遇到人脸检测问题：
从另外一个项目中拷过相应文件替换，另外一个项目从网上下载下来后居然要运行密码，假的集成环境，但里面的数据和文件资料是有用的。像模型的checkpoints这些都可以从里面拷到来。还有libs和third_party这些文件夹也可以直接拷过去。
内存不够的问题：
RuntimeError: CUDA out of memory. Tried to allocate 2.44 GiB (GPU 0; 8.00 GiB total capacity; 2.83 GiB already allocated; 0 bytes free; 5.68 GiB reserved in total by PyTorch)
Can this project run on 8GB GPU?
You can try reducing these these two parameters: --face_det_batch_size and --LNet_batch_size.
Or you can run the code in colab: https://colab.research.google.com/github/vinthony/video-retalking/blob/main/quick_demo.ipynb
python3 inference.py
–face examples/face/1.mp4
–audio examples/audio/1.wav
–outfile results/1_1.mp4
–face_det_batch_size 2 --LNet_batch_size 2
python inference.py --face examples/face/1.mp4 --audio examples/audio/1.wav --outfile results/1_1.mp4 --face_det_batch_size 2 --LNet_batch_size 2

也可以修改webUI.py:
def process_segment(video_seg, audio_seg, i):
output_file = f"results/{random.randint(10,100000)}_{i}.mp4"
command = [“python”, “inference.py”, “–face”, video_seg,
“–audio”, audio_seg, “–outfile”, output_file,“–face_det_batch_size”,“2”,“–LNet_batch_size”,“2”]

成功运行起来了。

subprocess.py报错FileNotFoundError:[WinError 2]系统找不到指定的文件
https://blog.csdn.net/m0_60034512/article/details/132815893