n-taku/CIFIR10.ipynb

## CIFIR10.ipynb
{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "CIFIR10.ipynb",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "yHACRBz1ruR8",
        "colab_type": "code",
        "outputId": "7b1af173-60ca-45b4-f128-4c8ade81ce93",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        }
      },
      "source": [
        "import torch\n",
        "import torchvision\n",
        "import torch.nn as nn\n",
        "import torch.optim as optim\n",
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from torchsummary import summary\n",
        "import torch.nn.functional as F\n",
        "\n",
        "BATCH_SIZE = 100\n",
        "WEIGHT_DECAY = 0.005\n",
        "LEARNING_RATE = 0.001\n",
        "EPOCH = 10\n",
        "PATH = \"Dataset\"\n",
        "\n",
        "transform = torchvision.transforms.Compose([torchvision.transforms.Resize((32,32)),torchvision.transforms.ToTensor(),torchvision.transforms.Normalize((0.5,), (0.5,))])\n",
        "\n",
        "trainset = torchvision.datasets.CIFAR10(root = PATH, train = True, download = True, transform = transform)\n",
        "trainloader = torch.utils.data.DataLoader(trainset, batch_size = BATCH_SIZE, shuffle = True, num_workers = 2)\n",
        "\n",
        "testset = torchvision.datasets.CIFAR10(root = PATH, train = False, download = True, transform = transform)\n",
        "testloader = torch.utils.data.DataLoader(testset, batch_size = BATCH_SIZE,\n",
        "                        shuffle = False, num_workers = 2)\n",
        "\n",
        "class Net(nn.Module):\n",
        "    def __init__(self):\n",
        "        super(Net, self).__init__()\n",
        "        self.conv1 = nn.Conv2d(3, 64, 5)\n",
        "        self.pool = nn.MaxPool2d(2, 2)\n",
        "        self.conv2 = nn.Conv2d(64, 128, 5)\n",
        "        self.fc1 = nn.Linear(128 * 5 * 5, 120)\n",
        "        self.fc2 = nn.Linear(120, 10)\n",
        "\n",
        "    def forward(self, x):\n",
        "        x = self.pool(F.relu(self.conv1(x)))\n",
        "        x = self.pool(F.relu(self.conv2(x)))\n",
        "        x = x.view(-1, 128 * 5 * 5)\n",
        "        x = F.relu(self.fc1(x))\n",
        "        x = self.fc2(x)\n",
        "        return x\n",
        "\n",
        "device = torch.device(\"cuda:0\" if torch.cuda.is_available() else \"cpu\")\n",
        "net = Net()\n",
        "net = net.to(device)\n",
        "criterion = nn.CrossEntropyLoss()\n",
        "optimizer = optim.SGD(net.parameters(), lr=LEARNING_RATE, momentum=0.9, weight_decay=WEIGHT_DECAY)\n",
        "\n",
        "train_loss_value=[] #trainingのlossを保持するlist\n",
        "train_acc_value=[] #trainingのaccuracyを保持するlist\n",
        "test_loss_value=[] #testのlossを保持するlist\n",
        "test_acc_value=[] #testのaccuracyを保持するlist \n",
        "\n",
        "summary(net, (3, 32, 32))\n",
        "\n",
        "for epoch in range(EPOCH):\n",
        "    print('epoch', epoch+1)    #epoch数の出力\n",
        "    for (inputs, labels) in trainloader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        optimizer.zero_grad()\n",
        "        outputs = net(inputs)\n",
        "        loss = criterion(outputs, labels)\n",
        "        loss.backward()\n",
        "        optimizer.step()\n",
        "\n",
        "    sum_loss = 0.0   #lossの合計\n",
        "    sum_correct = 0 #正解率の合計\n",
        "    sum_total = 0     #dataの数の合計\n",
        "\n",
        "    #train dataを使ってテストをする(パラメータ更新がないようになっている)\n",
        "    for (inputs, labels) in trainloader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        optimizer.zero_grad()\n",
        "        outputs = net(inputs)\n",
        "        loss = criterion(outputs, labels)\n",
        "        #lossを足していく\n",
        "        sum_loss += loss.item()\n",
        "        #出力の最大値の添字(予想位置)を取得\n",
        "        _, predicted = outputs.max(1)\n",
        "        #labelの数を足していくことでデータの総和を取る                      \n",
        "        sum_total += labels.size(0)\n",
        "        #予想位置と実際の正解を比べ,正解している数だけ足す\n",
        "        sum_correct += (predicted == labels).sum().item()\n",
        "    \n",
        "    #lossとaccuracy出力\n",
        "    print(\"train mean loss={}, accuracy={}\"\n",
        "    .format(sum_loss*BATCH_SIZE/len(trainloader.dataset), float(sum_correct/sum_total)))\n",
        "    #traindataのlossをグラフ描画のためにlistに保持\n",
        "    train_loss_value.append(sum_loss*BATCH_SIZE/len(trainloader.dataset))\n",
        "    #traindataのaccuracyをグラフ描画のためにlistに保持\n",
        "    train_acc_value.append(float(sum_correct/sum_total))\n",
        "\n",
        "    sum_loss = 0.0\n",
        "    sum_correct = 0\n",
        "    sum_total = 0\n",
        "\n",
        "    #test dataを使ってテストをする\n",
        "    for (inputs, labels) in testloader:\n",
        "        inputs, labels = inputs.to(device), labels.to(device)\n",
        "        optimizer.zero_grad()\n",
        "        outputs = net(inputs)\n",
        "        loss = criterion(outputs, labels)\n",
        "        sum_loss += loss.item()\n",
        "        _, predicted = outputs.max(1)\n",
        "        sum_total += labels.size(0)\n",
        "        sum_correct += (predicted == labels).sum().item()\n",
        "    print(\"test  mean loss={}, accuracy={}\"\n",
        "    .format(sum_loss*BATCH_SIZE/len(testloader.dataset), float(sum_correct/sum_total)))\n",
        "    test_loss_value.append(sum_loss*BATCH_SIZE/len(testloader.dataset))\n",
        "    test_acc_value.append(float(sum_correct/sum_total))\n",
        "\n",
        "#グラフ\n",
        "fig, (axL, axR) = plt.subplots(ncols=2, figsize=(12,6))\n",
        "\n",
        "#損失グラフ描画\n",
        "axL.plot(range(EPOCH), train_loss_value)\n",
        "axL.plot(range(EPOCH), test_loss_value, c='#00ff00')\n",
        "axL.set_xlabel('EPOCH')\n",
        "axL.set_ylabel('LOSS')\n",
        "axL.legend(['train loss', 'test loss'])\n",
        "axL.set_title('loss')\n",
        "\n",
        "#正答率グラフ描画\n",
        "axR.plot(range(EPOCH), train_acc_value)\n",
        "axR.plot(range(EPOCH), test_acc_value, c='#00ff00')\n",
        "axR.set_xlabel('EPOCH')\n",
        "axR.set_ylabel('ACCURACY')\n",
        "axR.legend(['train acc', 'test acc'])\n",
        "axR.set_title('accuracy')\n",
        "\n",
        "fig.savefig(\"loss_accuracy_image.png\")\n",
        "fig.show()\n"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Files already downloaded and verified\n",
            "Files already downloaded and verified\n",
            "----------------------------------------------------------------\n",
            "        Layer (type)               Output Shape         Param #\n",
            "================================================================\n",
            "            Conv2d-1           [-1, 64, 28, 28]           4,864\n",
            "         MaxPool2d-2           [-1, 64, 14, 14]               0\n",
            "            Conv2d-3          [-1, 128, 10, 10]         204,928\n",
            "         MaxPool2d-4            [-1, 128, 5, 5]               0\n",
            "            Linear-5                  [-1, 120]         384,120\n",
            "            Linear-6                   [-1, 10]           1,210\n",
            "================================================================\n",
            "Total params: 595,122\n",
            "Trainable params: 595,122\n",
            "Non-trainable params: 0\n",
            "----------------------------------------------------------------\n",
            "Input size (MB): 0.01\n",
            "Forward/backward pass size (MB): 0.60\n",
            "Params size (MB): 2.27\n",
            "Estimated Total Size (MB): 2.88\n",
            "----------------------------------------------------------------\n",
            "epoch 1\n",
            "train mean loss=1.9003137192726136, accuracy=0.31732\n",
            "test  mean loss=1.8944680571556092, accuracy=0.3197\n",
            "epoch 2\n",
            "train mean loss=1.6699165675640106, accuracy=0.40088\n",
            "test  mean loss=1.6637732303142547, accuracy=0.4039\n",
            "epoch 3\n",
            "train mean loss=1.5065160362720489, accuracy=0.45532\n",
            "test  mean loss=1.5074181103706359, accuracy=0.4534\n",
            "epoch 4\n",
            "train mean loss=1.4361625032424927, accuracy=0.48254\n",
            "test  mean loss=1.4433046615123748, accuracy=0.4787\n",
            "epoch 5\n",
            "train mean loss=1.367594486474991, accuracy=0.50936\n",
            "test  mean loss=1.3763530683517455, accuracy=0.5032\n",
            "epoch 6\n",
            "train mean loss=1.335053557395935, accuracy=0.52356\n",
            "test  mean loss=1.3456828105449676, accuracy=0.5131\n",
            "epoch 7\n",
            "train mean loss=1.2771146647930145, accuracy=0.54384\n",
            "test  mean loss=1.2908622443675994, accuracy=0.5365\n",
            "epoch 8\n",
            "train mean loss=1.2266256620883942, accuracy=0.56362\n",
            "test  mean loss=1.2466589391231537, accuracy=0.5537\n",
            "epoch 9\n",
            "train mean loss=1.1873798089027405, accuracy=0.58062\n",
            "test  mean loss=1.212351723909378, accuracy=0.5684\n",
            "epoch 10\n",
            "train mean loss=1.170360258102417, accuracy=0.58402\n",
            "test  mean loss=1.198556705713272, accuracy=0.5678\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAGDCAYAAAACpSdYAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}