Docker file for Wav2Lip

.dockerignore

# Ignore everything
**

# Allow files and directories
!/audio.py
!/Dockerfile
!/hparams.py
!/preprocess.py
!/checkpoints/
!/evaluation/
!/hq_wav2lip_train.py
!/README.md
!/temp/
!/color_syncnet_train.py
!/face_detection/
!/inference.py
!/requirements.txt
!/filelists/
!/models/
!/results/
!/wav2lip_train.py


# Ignore unnecessary files inside allowed directories
# This should go after the allowed directories
**/*~
**/*.log
**/.DS_Store
**/Thumbs.db

Dockerfile.wav2lip

# 1. install a version of docker with gpu support (docker-ce >= 19.03)

# 2.  enter the project directory and build the wav2lip image:
# docker build -t wav2lip .

# 3. allow root user to connect to the display
# xhost +local:root

# 4. instantiate the container
# docker run --rm --gpus all -v /tmp/.X11-unix:/tmp/.X11-unix -v $PWD:/workspace/src -e DISPLAY=$DISPLAY --device /dev/dri -ti wav2lip bash

# NOTES:
# export CUDA_VISIBLE_DEVICES="" ## force cpu only

# Based on https://github.com/1adrianb/face-alignment/blob/master/Dockerfile

FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04

RUN export DEBIAN_FRONTEND=noninteractive RUNLEVEL=1 ; \
     apt-get update && apt-get install -y --no-install-recommends \
          build-essential cmake git curl ca-certificates \
          vim \
          python3-pip python3-dev python3-wheel \
          libglib2.0-0 libxrender1 python3-soundfile \
          ffmpeg && \
	rm -rf /var/lib/apt/lists/* && \
     pip3 install --upgrade setuptools

# RUN curl -o ~/miniconda.sh -O  https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh  && \
#      chmod +x ~/miniconda.sh && \
#      ~/miniconda.sh -b -p /opt/conda && \
#      rm ~/miniconda.sh

# ENV PATH /opt/conda/bin:$PATH

# RUN conda config --set always_yes yes --set changeps1 no && conda update -q conda
# RUN conda install pytorch torchvision cudatoolkit=10.1 -c pytorch

# # Install Wav2Lip package
# # NOTE we use the git clone to install the requirements only once
# # (if we use COPY it will invalidate the cache and  reinstall the dependencies for every change in the sources)
WORKDIR /workspace
RUN chmod -R a+w /workspace
RUN git clone https://github.com/Rudrabha/Wav2Lip
WORKDIR /workspace/Wav2Lip
RUN pip3 install -r requirements.txt

RUN mkdir -p /root/.cache/torch/checkpoints && \
     curl -SL -o /root/.cache/torch/checkpoints/s3fd-619a316812.pth "https://www.adrianbulat.com/downloads/python-fan/s3fd-619a316812.pth"

# !!! NOTE !!! nvidia-driver version must match the version installed on the host(/docker server)
RUN export DEBIAN_FRONTEND=noninteractive RUNLEVEL=1 ; \
	apt-get update && apt-get install -y --no-install-recommends \
          nvidia-driver-450 mesa-utils && \
	rm -rf /var/lib/apt/lists/*

# create the working directory, to be mounted with the bind option
RUN mkdir /workspace/src
WORKDIR /workspace/src

After installing and running everything when I run "docker run --rm --gpus all -v /tmp/.X11-unix:/tmp/.X11-unix -v $PWD:/workspace/src -e DISPLAY=$DISPLAY --device /dev/dri -ti wav2lip bash" it returns "docker: Error response from daemon: could not select device driver "" with capabilities: [[gpu]]." Do you know what the problem might be?

Sorry I never seen that error, maybe a version problem? Are you using a docker-ce >= 19.03?

docker-ce                  5:20.10.3~3-0~debian-buster
docker-ce-cli              5:20.10.3~3-0~debian-buster
docker-ce-rootless-extras  5:20.10.3~3-0~debian-buster

Yep when I run "docker version" it says I'm on docker community edition v 20.10.3

I'm on Ubuntu by the way (Well, actually Kubuntu, but it shouldn't make a difference)

It's been a few months since I tried it and it worked, in the meantime a few versions of the various nvidia components have been updated (I use debian/sid) and now I have some problems to make it work too, but it gives me a different error.

Well, just due to time constraints I ended up installing it normally, without docker to do my tests. So there's no urgency for it to be fixed, but I wish you good luck!

I had to add RUN pip3 install --upgrade pip to the docker file just before RUN pip3 install -r requirements.txt to get it to install the requirements correctly.

I had to add RUN pip3 install --upgrade pip to the docker file just before RUN pip3 install -r requirements.txt to get it to install the requirements correctly.

This is important

Exactly this works for me.

Why doesnot anyone had already created the docker image share to public repo?

Why doesnot anyone had already created the docker image share to public repo?

I haven't used this image for a while, lately when I need some python-ML projects I just use Conda.

I had to add RUN pip3 install --upgrade pip to the docker file just before RUN pip3 install -r requirements.txt to get it to install the requirements correctly.

This is important

Super important, was fun wasting time today

" Do you know what the problem might be?

I have been having problems running with this error python: can't open file
'inference.py': [Errno 2] No such file or directory

The base image FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04 seems to be deprecated. Any pre-built image ready to run available?

The base image FROM nvidia/cuda:10.1-cudnn7-devel-ubuntu18.04 seems to be deprecated. Any pre-built image ready to run available?

Did any find a resolution for this?

I am having some issues trying to use newer base images

Having issues with the regular conda dev too. Maybe some dependency stuff?