$ ssh-copy-id [作成したユーザ名]@192.168.XXX.XXX
/usr/bin/ssh-copy-id: INFO: Source of key(s) to be installed: "/home/[作成したユーザ名]/.ssh/id_rsa.pub"
/usr/bin/ssh-copy-id: INFO: attempting to log in with the new key(s), to filter out any that are already installed
/usr/bin/ssh-copy-id: INFO: 1 key(s) remain to be installed -- if you are prompted now it is to install the new keys
[作成したユーザ名]@192.168.XXX.XXX's password:

$ ssh [作成したユーザ名]@192.168.XXX.XXX -i ~/.ssh/id_rsa

PasswordAuthentication no

# /etc/init.d/ssh restart

$ sudo apt update
$ sudo apt upgrade

$ sudo apt install language-pack-ja
$ sudo update-locale LANG=ja_JP.UTF8
$ sudo apt install fontconfig
$ sudo apt install fonts-ipafont

$ sudo apt install unzip
$ mkdir ~/tmp
$ cd tmp
$ wget https://github.com/yuru7/udev-gothic/releases/download/v1.3.0/UDEVGothic_v1.3.0.zip
$ unzip UDEVGothic_v1.3.0.zip
$ sudo mv UDEVGothic_v1.3.0 /usr/local/share/fonts/
$ fc-cache -fv

$ sudo apt update
$ sudo apt upgrade

$ sudo apt install -y \
  emacs \
  emacs-mozc \
  emacs-mozc-bin \
  tmux \
  git

set-option -g prefix C-c
unbind-key C-b
bind-key C-c send-prefix

set-option -g default-terminal screen-256color
set -g terminal-overrides 'xterm:colors=256'

blacklist nouveau
options nouveau modeset=0

$ sudo update-initramfs -u
$ sudo reboot

$ sudo apt update
$ sudo apt upgrade
$ ubuntu-drivers devices
modalias : pci:v000010DEd00002504sv00001462sd00008E90bc03sc00i00
vendor   : NVIDIA Corporation
model    : GA106 [GeForce RTX 3060 Lite Hash Rate]
driver   : nvidia-driver-535-server - distro non-free
driver   : nvidia-driver-535-server-open - distro non-free recommended
driver   : nvidia-driver-525-open - distro non-free
driver   : nvidia-driver-535-open - distro non-free
driver   : nvidia-driver-470-server - distro non-free
driver   : nvidia-driver-470 - distro non-free
driver   : nvidia-driver-535 - distro non-free
driver   : nvidia-driver-525-server - distro non-free
driver   : nvidia-driver-525 - distro non-free
driver   : xserver-xorg-video-nouveau - distro free builtin

$ sudo apt install -y nvidia-driver-535
$ sudo reboot

$ nvidia-smi 
Thu Jul 20 14:41:28 2023       
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.54.03              Driver Version: 535.54.03    CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 3060        Off | 00000000:01:00.0 Off |                  N/A |
| 36%   39C    P8               8W / 170W |      2MiB / 12288MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+

$ sudo apt install \
  ca-certificates curl gnupg lsb-release

$ sudo mkdir -p /etc/apt/keyrings
$ curl -fsSL https://download.docker.com/linux/ubuntu/gpg \
  | sudo gpg --dearmor -o /etc/apt/keyrings/docker.gpg

$ echo \
  "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] \
  https://download.docker.com/linux/ubuntu $(lsb_release -cs) stable" \
  | sudo tee /etc/apt/sources.list.d/docker.list > /dev/null

$ sudo apt update
$ sudo apt install docker-ce docker-ce-cli containerd.io

$ docker --version
Docker version 24.0.4, build 3713ee1

$ docker compose version
Docker Compose version v2.19.1

$ sudo docker run hello-world
Unable to find image 'hello-world:latest' locally
latest: Pulling from library/hello-world
719385e32844: Pull complete
Digest: sha256:926fac19d22aa2d60f1a276b66a20eb765fbeea2db5dbdaafeb456ad8ce81598
Status: Downloaded newer image for hello-world:latest

Hello from Docker!
This message shows that your installation appears to be working correctly.

To generate this message, Docker took the following steps:
 1. The Docker client contacted the Docker daemon.
 2. The Docker daemon pulled the "hello-world" image from the Docker Hub.
    (amd64)
 3. The Docker daemon created a new container from that image which runs the
    executable that produces the output you are currently reading.
 4. The Docker daemon streamed that output to the Docker client, which sent it
    to your terminal.

To try something more ambitious, you can run an Ubuntu container with:
 $ docker run -it ubuntu bash

Share images, automate workflows, and more with a free Docker ID:
 https://hub.docker.com/

For more examples and ideas, visit:
 https://docs.docker.com/get-started/

$ sudo usermod -aG docker $USER
$ su - ${USER}

$ docker run hello-world

Hello from Docker!
...

$ distribution=$(. /etc/os-release;echo $ID$VERSION_ID) \
      && curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
      && curl -s -L https://nvidia.github.io/libnvidia-container/$distribution/libnvidia-container.list | \
            sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
            sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list

$ sudo apt-get update
$ sudo apt-get install -y nvidia-container-toolkit
$ sudo nvidia-ctk runtime configure --runtime=docker
INFO[0000] Loading docker config from /etc/docker/daemon.json
INFO[0000] Config file does not exist, creating new one
INFO[0000] Wrote updated config to /etc/docker/daemon.json
INFO[0000] It is recommended that the docker daemon be restarted.

$ sudo systemctl restart docker

$ docker run --rm --runtime=nvidia --gpus all nvidia/cuda:12.2.0-base-ubuntu22.04 nvidia-smi
Unable to find image 'nvidia/cuda:12.2.0-base-ubuntu22.04' locally
12.2.0-base-ubuntu22.04: Pulling from nvidia/cuda
6b851dcae6ca: Already exists
8f5f0e71700a: Already exists
fac7ce4a13c3: Already exists
1af9bee222cb: Already exists
d47e0a26d15c: Already exists
Digest: sha256:f8870283bea6a85ba4b4a5e1b65158dd15e8009e433539e7c83c94707e703a1b
Status: Downloaded newer image for nvidia/cuda:12.2.0-base-ubuntu22.04
Mon Jul 24 05:48:04 2023
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.54.03              Driver Version: 535.54.03    CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 3060        Off | 00000000:01:00.0 Off |                  N/A |
| 36%   35C    P8              13W / 170W |    191MiB / 12288MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+

+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
+---------------------------------------------------------------------------------------+

FROM nvidia/cuda:12.2.0-base-ubuntu22.04

RUN apt-get update && apt-get -y upgrade && \
    apt-get install -y locales && \
    localedef -f UTF-8 -i ja_JP ja_JP.UTF-8
ENV LANG ja_JP.UTF-8
ENV LANGUAGE ja_JP:ja
ENV LC_ALL ja_JP.UTF-8
ENV TZ=Asia/Tokyo
RUN ln -snf /usr/share/zoneinfo/$TZ /etc/localtime && \
    echo $TZ  > /etc/timezone

RUN apt-get install -y software-properties-common && \
    add-apt-repository ppa:deadsnakes/ppa && \
    apt-cache policy python3.9

RUN apt-get install -y \
    git \
    wget \
    zip \
    unzip \
    cmake \
    build-essential \
    libboost-dev \
    libboost-system-dev \
    libboost-filesystem-dev \
    libblas-dev \
    liblapack-dev \
    python3.9 \
    python3.9-dev \
    python3-pip \
    python-is-python3 \
    && apt-get clean \
    && rm -rf /var/lib/apt/lists/*

RUN pip install --upgrade setuptools && \
    pip install --no-cache-dir \
        'pycaret[full]>=3.0.4' && \
    pip install --no-cache-dir \
        scikit-learn \
        numpy \
        scipy \
        pandas && \
    pip install --no-cache-dir \
        jupyterlab \
        ipywidgets \
        plotly \
        graphviz \
        shap \
        matplotlib \
        japanize_matplotlib \
        seaborn \
        tqdm && \
    pip install --no-cache-dir \
        lightgbm \
        xgboost \
        catboost && \
    pip install --no-cache-dir \
        torch \
        torchvision \
        torchaudio && \
    pip install --no-cache-dir \
        skl2onnx \
        onnxmltools \
        onnxruntime-gpu && \
    pip install --no-cache-dir \
        pillow \
        opencv-python && \
    pip install --no-cache-dir \
        boto3

version: '12.2'
services:
  python3:
    restart: no
    build: .
    container_name: 'pytorch-base'
    working_dir: '/root/'
    tty: true
    command:
      jupyter-lab --ip=0.0.0.0 --allow-root --ServerApp.open_browser=False
    ports:
      - "8888:8888"
    volumes:
      - ./opt:/root/opt
      - ./root_jupyter:/root/.jupyter
    deploy:
      resources:
        reservations:
          devices:
            - capabilities: [gpu]
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=all

$ docker compose create
$ docker compose start
$ docker ps
...

$ docker logs [CONTAINER ID]
...
   http://(e22198a8202b or 127.0.0.1):8888/?token=xxxxxxxxx

import pycaret
pycaret.__version__

# loading sample dataset from pycaret dataset module
from pycaret.datasets import get_data
data = get_data('diabetes')

# import pycaret classification and init setup
from pycaret.classification import *
s = setup(data, target = 'Class variable', session_id = 123)

# import ClassificationExperiment and init the class
from pycaret.classification import ClassificationExperiment
exp = ClassificationExperiment()

# check the type of exp
type(exp)

# init setup on exp
exp.setup(data, target = 'Class variable', session_id = 123)

# compare baseline models
best = compare_models()

# compare models using OOP
exp.compare_models()

# plot confusion matrix
plot_model(best, plot = 'confusion_matrix')

!nvidia-smi

Mon Jul 24 22:12:15 2023
+---------------------------------------------------------------------------------------+
| NVIDIA-SMI 535.54.03              Driver Version: 535.54.03    CUDA Version: 12.2     |
|-----------------------------------------+----------------------+----------------------+
| GPU  Name                 Persistence-M | Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp   Perf          Pwr:Usage/Cap |         Memory-Usage | GPU-Util  Compute M. |
|                                         |                      |               MIG M. |
|=========================================+======================+======================|
|   0  NVIDIA GeForce RTX 3060        Off | 00000000:01:00.0 Off |                  N/A |
| 37%   35C    P8              13W / 170W |      5MiB / 12288MiB |      0%      Default |
|                                         |                      |                  N/A |
+-----------------------------------------+----------------------+----------------------+
                                                                                         
+---------------------------------------------------------------------------------------+
| Processes:                                                                            |
|  GPU   GI   CI        PID   Type   Process name                            GPU Memory |
|        ID   ID                                                             Usage      |
|=======================================================================================|
|  No running processes found                                                           |
+---------------------------------------------------------------------------------------+

# https://water2litter.net/rum/post/pytorch_tutorial_classifier_gpu/
import torch
import torchvision
import torchvision.transforms as transforms
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim

# ニューラルネットワークの定義
class Net(nn.Module):
    def __init__(self):
        super(Net, self).__init__()
        self.conv1 = nn.Conv2d(3, 6, 5)
        self.pool = nn.MaxPool2d(2, 2)
        self.conv2 = nn.Conv2d(6, 16, 5)
        self.fc1 = nn.Linear(16 * 5 * 5, 120)
        self.fc2 = nn.Linear(120, 84)
        self.fc3 = nn.Linear(84, 10)

    def forward(self, x):
        x = self.pool(F.relu(self.conv1(x)))
        x = self.pool(F.relu(self.conv2(x)))
        x = x.view(-1, 16 * 5 * 5)
        x = F.relu(self.fc1(x))
        x = F.relu(self.fc2(x))
        x = self.fc3(x)
        return x

# データセット読み込み
transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))])

trainset = torchvision.datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
trainloader = torch.utils.data.DataLoader(trainset, batch_size=4, shuffle=True, num_workers=0)

testset = torchvision.datasets.CIFAR10(root='./data', train=False, download=True, transform=transform)
testloader = torch.utils.data.DataLoader(testset, batch_size=4, shuffle=False, num_workers=0)

classes = ('plane', 'car', 'bird', 'cat', 'deer', 'dog', 'frog', 'horse', 'ship', 'truck')

# ネットワークのインスタンス作成
net = Net()

# 損失関数とオプティマイザーの定義
criterion = nn.CrossEntropyLoss()
optimizer = optim.SGD(net.parameters(), lr=0.001, momentum=0.9)
Files already downloaded and verified
Files already downloaded and verified

# GPUを使用する
device_str = "cuda:0" if torch.cuda.is_available() else "cpu"
device = torch.device(device_str)
net.to(device) # モデルの転送

# 学習ループ
for epoch in range(2):  # 総データに対する学習回数

    running_loss = 0.0
    for i, data in enumerate(trainloader, 0):
        # データをリストに格納
        inputs, labels = data[0].to(device), data[1].to(device) # データの転送

        # パラメータを0にリセット
        optimizer.zero_grad()

        # 順方向の計算、損失計算、バックプロパゲーション、パラメータ更新
        outputs = net(inputs)
        loss = criterion(outputs, labels)
        loss.backward()
        optimizer.step()

        # 計算状態の出力
        running_loss += loss.item()
        if i % 2000 == 1999:    # print every 2000 mini-batches
            print('[%d, %5d] loss: %.3f' %
                  (epoch + 1, i + 1, running_loss / 2000))
            running_loss = 0.0

print('Finished Training')

# 計算結果のモデルを保存
torch.save(net.state_dict(), './cifar_net.pth')