如何使用Windows在我的Python上运行deepfacelive

Question

以下是我尝试在 Anaconda 上运行 deepfacelive 后得到的结果。我使用的是 Windows 电脑。

(tudazdeep) C:\Users\owner\Desktop\DeepFaceLive-master>python main.py run DeepFaceLive--userdata-dirC:\Users\owner\Desktop\DeepFaceLive-master
usage: main.py run [-h] {DeepFaceLive} ...
main.py run: error: argument {DeepFaceLive}: invalid choice: 'DeepFaceLive--userdata-dirC:\\Users\\owner\\Desktop\\DeepFaceLive-master' (choose from 'DeepFaceLive')

尝试在我的Python上运行deepfacelive

Answer 1

我可以帮助您使用 Linux/Docker。有总比什么都没有好。

简短回答

cd /root
python main.py run DeepFaceLive --userdata-dir /data/

长答案

cd /root

mkdir -p /root/deepface.04/build/linux
mkdir -p /root/deepface.04/build/linux/data
#create the files below: data; example.sh; start.cpu.02.sh  ; Dockerfile  ; README.md

#run
docker build -t deepfacelive-cpu .

# Allow access to the X server
xhost +




#run
start.cpu.02.sh


#run
docker start deepfacelive-container

sleep 4

docker exec -it deepfacelive-container bash


#inside docker deepfacelive-container  run
root@ce902a8d05f8:/app/DeepFaceLive# python main.py run DeepFaceLive --userdata-dir /data/

#check files
ls /root/deepface.04/build/linux

data
example.sh
start.cpu.02.sh
Dockerfile
README.md

Docker 文件。

# Start with the base image
FROM ubuntu:20.04

# Set the working directory
WORKDIR /app

# Set the ARG for non-interactive installation
ARG DEBIAN_FRONTEND=noninteractive

# Set timezone environment variable (e.g., "Etc/UTC" or your local timezone)
ENV TZ=Etc/UTC

# Update package list and install dependencies
RUN apt update && apt install -y \
    tzdata \
    libgl1-mesa-glx \
    libegl1-mesa \
    libxrandr2 \
    libxss1 \
    libxcursor1 \
    libxcomposite1 \
    libasound2 \
    libxi6 \
    libxtst6 \
    curl \
    ffmpeg \
    git \
    nano \
    gnupg2 \
    libsm6 \
    wget \
    unzip \
    libxcb-icccm4 \
    libxkbcommon-x11-0 \
    libxcb-keysyms1 \
    libxcb-render0 \
    libxcb-render-util0 \
    libxcb-image0 \
    python3 \
    python3-pip

# Install required Qt and X11 libraries
RUN apt update && apt install -y \
    libx11-xcb1 \
    libxcb1 \
    libxcomposite1 \
    libxkbcommon-x11-0 \
    libxkbcommon0 \
    libxcb-cursor0 \
    libxcb-shape0 \
    libxcb-shm0 \
    libxcb-sync1 \
    libxcb-xfixes0 \
    libxcb-xinerama0 \
    libxcb-xinput0 \
    libxcb-xkb1

# Configure timezone data
RUN ln -fs /usr/share/zoneinfo/$TZ /etc/localtime && \
    echo $TZ > /etc/timezone && \
    dpkg-reconfigure --frontend noninteractive tzdata

# Create a symlink for python3
RUN ln -s /usr/bin/python3 /usr/bin/python

# Clone the DeepFaceLive repository
RUN git clone https://github.com/iperov/DeepFaceLive.git

# Upgrade pip and install required Python packages
RUN python -m pip install --upgrade pip
RUN python -m pip install \
    onnxruntime==1.15.1 \
    numpy==1.21.6 \
    h5py \
    numexpr \
    protobuf==3.20.2 \
    opencv-python==4.8.0.74 \
    opencv-contrib-python==4.8.0.74 \
    pyqt6==6.5.1 \
    onnx==1.14.0 \
    torch==1.13.1 \
    torchvision==0.14.1

# Set the working directory for DeepFaceLive
WORKDIR /app/DeepFaceLive

# Copy the example script
COPY example.sh example.sh

# Uncomment the CMD line if you want to run the script by default
# CMD ./example.sh

启动.cpu.02.sh

#!/bin/bash





# Define the data folder path
DATA_FOLDER=$(pwd)/data/

# Declare variables for camera device mappings
declare CAM0 CAM1 CAM2 CAM3

# Check for available camera devices and set them up
test -e /dev/video0 && CAM0="--device=/dev/video0:/dev/video0"
test -e /dev/video1 && CAM1="--device=/dev/video1:/dev/video1"
test -e /dev/video2 && CAM2="--device=/dev/video2:/dev/video2"
test -e /dev/video3 && CAM3="--device=/dev/video3:/dev/video3"

# Output the detected camera devices
echo "Detected camera devices:" $CAM0 $CAM1 $CAM2 $CAM3

# Run the Docker container without GPU support. Only CPU support
docker run --name deepfacelive-container --ipc host -e DISPLAY=$DISPLAY \
    -v /tmp/.X11-unix:/tmp/.X11-unix \
    -v $DATA_FOLDER:/data/ \
    $CAM0 $CAM1 $CAM2 $CAM3 \
    deepfacelive-cpu \
    #bash -c "python main.py run DeepFaceLive --userdata-dir /data/ && tail -f /dev/null"