| 基本信息 | 具体版本 |
|---|---|
| 系统 | Ubuntu 18.04 LTS |
| 用户:密码 | pamirl:qwerty |
| pytorch | 1.10.1 |
| python | 3.8 |
| mujoco | 2.1.0 |
| cuda | 10.0 |
| pytorch—cudatoolkit | 10.2 |
| 强化环境库 | dm_control, mujoco,pybullet |
| 强化算法库 | stable-baselines3 |
| jupyter lab | password, ip, remote_access等配置 |
可在dockerfile中修改对应的版本，但修改前须了解它们彼此的依赖关系，可阅读setup.py
操作： sh build_image.sh ; sh start_container.sh
可能大家会问一个问题：cuda和cudatoolkit有什么关系？
- 这里的cuda:10.0是系统层面的关于CUDA的完整工具包，包括Nvidia驱动、编译程序、工具包、IDE、调试器等一系列程序
- cudatoolkit是为了使用pytorch框架而“事先被编译好的”动态链接库
- 因此如果只为了使用pytorch，只需关心cudatoolkit就好了（如果要写pytorch以外的cuda程序，就需要关心cuda完整工具包的版本）
# build_image.sh
## 使用当前路径.下的Dockerfile，创建名为stable_rl:launch的镜像
docker build -t stable_rl:launch .
# start_container.sh
## mount_dir:挂载主机上的mount_dir路径到容器内的/home/pamirl/rl_dev
## 利用image_name创建容器
jupyter_port=8888
ssh_port=8889
container_nick_name="stable_rl"
image_name="stable_rl:launch"
mount_dir="/home/pami/rl_dev"
nvidia-docker run -itd -p ${jupyter_port}:8888 -p ${ssh_port}:22 -u pamirl -v ${mount_dir}:/home/pamirl/rl_dev --name ${container_nick_name} ${image_name} bash
自行修改端口、名字、挂载路径、容器内的用户名等
# change_apt.txt
deb https://mirrors.ustc.edu.cn/ubuntu/ bionic main restricted universe multiverse
deb-src https://mirrors.ustc.edu.cn/ubuntu/ bionic main restricted universe multiverse
deb https://mirrors.ustc.edu.cn/ubuntu/ bionic-updates main restricted universe multiverse
deb-src https://mirrors.ustc.edu.cn/ubuntu/ bionic-updates main restricted universe multiverse
deb https://mirrors.ustc.edu.cn/ubuntu/ bionic-backports main restricted universe multiverse
deb-src https://mirrors.ustc.edu.cn/ubuntu/ bionic-backports main restricted universe multiverse
deb https://mirrors.ustc.edu.cn/ubuntu/ bionic-security main restricted universe multiverse
deb-src https://mirrors.ustc.edu.cn/ubuntu/ bionic-security main restricted universe multiverse
deb https://mirrors.ustc.edu.cn/ubuntu/ bionic-proposed main restricted universe multiverse
deb-src https://mirrors.ustc.edu.cn/ubuntu/ bionic-proposed main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ xenial main
deb-src http://mirrors.aliyun.com/ubuntu/ xenial main
deb http://mirrors.aliyun.com/ubuntu/ xenial-updates main
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-updates main
deb http://mirrors.aliyun.com/ubuntu/ xenial universe
deb-src http://mirrors.aliyun.com/ubuntu/ xenial universe
deb http://mirrors.aliyun.com/ubuntu/ xenial-updates universe
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-updates universe
deb http://mirrors.aliyun.com/ubuntu/ xenial-security main
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-security main
deb http://mirrors.aliyun.com/ubuntu/ xenial-security universe
deb-src http://mirrors.aliyun.com/ubuntu/ xenial-security universe
#change_conda.txt
channels:
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/r
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/msys2
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch/
- https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/conda-forge/
- defaults
show_channel_urls: true
custom_channels:
conda-forge: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
msys2: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
bioconda: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
menpo: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
pytorch: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
pytorch-lts: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
simpleitk: https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud
- pip的源直接在dockerfile中指定了pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple
- 从github下载的均使用了它的镜像网站github.cnpmjs.org
- 所以如果不熟悉docker挂https_proxy，或者懒的话，国内就根据自己需要换掉apt , pip , conda, github的源
# test_cuda.py
import torch
print(torch.__version__)
print(torch.cuda.is_available()) # cuda是否可用
print(torch.cuda.device_count()) # 返回GPU的数量
print(torch.cuda.get_device_name(0)) # 返回gpu名字，设备索引默认从0开始
# test_mujoco.py
import mujoco_py
import os
mj_path = mujoco_py.utils.discover_mujoco()
xml_path = os.path.join(mj_path, 'model', 'humanoid.xml')
model = mujoco_py.load_model_from_path(xml_path)
sim = mujoco_py.MjSim(model)
print(sim.data.qpos)
sim.step()
print(sim.data.qpos)
# test_pybullet.py
import os
import gym
import pybullet_envs
from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
from stable_baselines3 import PPO
env = DummyVecEnv([lambda: gym.make("HalfCheetahBulletEnv-v0")])
# Automatically normalize the input features and reward
env = VecNormalize(env, norm_obs=True, norm_reward=True,
clip_obs=10.)
model = PPO('MlpPolicy', env)
model.learn(total_timesteps=2000)
print("finish learning")
# Don't forget to save the VecNormalize statistics when saving the agent
log_dir = "/tmp/"
model.save(log_dir + "ppo_halfcheetah")
print("saving model at {0}".format(log_dir))
stats_path = os.path.join(log_dir, "vec_normalize.pkl")
env.save(stats_path)
print("saving env at {}".format(stats_path))
# To demonstrate loading
del model, env
# Load the saved statistics
env = DummyVecEnv([lambda: gym.make("HalfCheetahBulletEnv-v0")])
print("loading env and model")
env = VecNormalize.load(stats_path, env)
# do not update them at test time
env.training = False
# reward normalization is not needed at test time
env.norm_reward = False
# Load the agent
model = PPO.load(log_dir + "ppo_halfcheetah", env=env)
# test_stable_baselines.py
import gym
from stable_baselines3 import PPO
env = gym.make("Ant-v3")
model = PPO("MlpPolicy", env, verbose=1)
model.learn(total_timesteps=1000)
obs = env.reset()
for i in range(1000):
action, _states = model.predict(obs, deterministic=True)
obs, reward, done, info = env.step(action)
#env.render()
if done:
obs = env.reset()
env.close()
这些基本是从各官网copy下来的例子，进行测试。
FROM nvidia/cuda:10.0-base
COPY ./change_apt.txt /
RUN cp /etc/apt/sources.list /etc/apt/sources_init.list \
&& cat /change_apt.txt > /etc/apt/sources.list \
&& rm /change_apt.txt \
&& apt update
RUN apt update && DEBIAN_FRONTEND=noninteractive apt install -y --allow-unauthenticated --no-install-recommends \
build-essential apt-utils cmake git curl vim ca-certificates sudo tmux jq unrar\
libjpeg-dev libpng-dev \
libgtk3.0 libsm6 cmake ffmpeg pkg-config \
qtbase5-dev libqt5opengl5-dev libassimp-dev \
libboost-python-dev libtinyxml-dev bash \
wget unzip libosmesa6-dev software-properties-common \
libopenmpi-dev libglew-dev openssh-server \
libosmesa6-dev libgl1-mesa-glx libgl1-mesa-dev patchelf libglfw3 \
&& rm -rf /var/lib/apt/lists/*
RUN useradd --create-home --shell /bin/bash pamirl \
&& adduser pamirl sudo \
&& echo 'pamirl:qwerty' | chpasswd \
&& su pamirl
USER pamirl
WORKDIR /home/pamirl
# miniconda
RUN wget -q https://mirrors.tuna.tsinghua.edu.cn/anaconda/miniconda/Miniconda3-latest-Linux-x86_64.sh && \
bash Miniconda3-latest-Linux-x86_64.sh -b -p miniconda3 && \
rm Miniconda3-latest-Linux-x86_64.sh
ENV PATH /home/pamirl/miniconda3/bin:$PATH
# mujoco
RUN wget https://github.com.cnpmjs.org/deepmind/mujoco/releases/download/2.1.0/mujoco210-linux-x86_64.tar.gz \
&& mkdir -p .mujoco \
&& whoami \
&& pwd \
&& tar -zxf mujoco210-linux-x86_64.tar.gz -C "$HOME/.mujoco" \
&& rm mujoco210-linux-x86_64.tar.gz
ENV LD_LIBRARY_PATH /home/pamirl/.mujoco/mujoco210/bin:${LD_LIBRARY_PATH}
# conda env
COPY ./change_conda.txt ./
RUN conda config --describe \
&& cat ./change_conda.txt > .condarc \
&& rm change_conda.txt \
&& conda create -y -n deep_rl python=3.8
SHELL ["/bin/bash", "--login", "-c"]
# basis pytorch
RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple \
&& source activate deep_rl \
&& cat .condarc \
&& pip install -q dm_control gym \
&& pip install -U 'mujoco-py<2.2,>=2.1' \
&& conda install -y pytorch=1.10.1 torchvision torchaudio cudatoolkit=10.2 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/cloud/pytorch \
&& pip install glfw Cython imageio lockfile
# stable-baselines3
RUN pip config set global.index-url https://pypi.tuna.tsinghua.edu.cn/simple \
&& source activate deep_rl \
&& pip install -U stable-baselines3[extra] pyglet pybullet
# atari
#RUN source activate deep_rl \
# && wget -q http://www.atarimania.com/roms/Roms.rar \
# && mkdir ~/atari_roms
# && unrar e Roms.rar ~/atari_roms \
# && python -m atari_py.import_roms ~/atari_roms \
# && rm Roms.rar \
# && rm -rf ~/atari_roms
# install jupyerlab
RUN source activate deep_rl \
&& conda install jupyterlab ipykernel \
&& python -m ipykernel install --user --name deep_rl --display-name deep_rl:stable-baselines3
# configure jupyter lab & vscode
RUN source activate deep_rl \
&& jupyter lab --generate-config \
&& cd .jupyter \
#&& echo c.ServerApp.password=$(cat jupyter_server_config.json | jq .ServerApp.password) >> jupyter_lab_config.py \
&& echo "c.ServerApp.password = \"$(python -c "from jupyter_server.auth import passwd;print(passwd('qwerty'))")\"" >> jupyter_lab_config.py \
&& echo "c.ServerApp.ip = '*'" >> jupyter_lab_config.py \
&& echo "c.ServerApp.allow_remote_access=True" >> jupyter_lab_config.py
# Add test scripts
ADD test*.py ./
# Add conda dependency of your code
RUN source activate deep_rl \
&& conda install -y scikit-learn tensorboardX \
&& conda init
系统用户、密码、jupyterlab的配置、端口都可根据自行需要修改
# 容器内程序的权限与host当前用户($UID)一致
ARG UID
# 在build image的时候传入当前主机用户的UID
RUN useradd -u $UID --create-home --shell /bin/bash pamirl \
# 如无必要，可删除用户的sudo权限
&& adduser pamirl sudo \
&& echo 'pamirl:qwerty' | chpasswd \
&& su pamirl
#####################
# 容器内文件权限与host当前用户权限一致
ADD --chown=$UID test*.py ./
build_image.sh制作镜像命令修改如下：( 比如build时希望每个密码不一样，都可以通过定义ARG，在制作镜像时传入，其余同理）
docker build --build-arg UID=$UID -t stable_rl:origin .