{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"# This Python 3 environment comes with many helpful analytics libraries installed\n# It is defined by the kaggle/python docker image: https://github.com/kaggle/docker-python\n# For example, here's several helpful packages to load in \n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n\n# Input data files are available in the \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n\nimport os\nfor dirname, _, filenames in os.walk('/kaggle/input'):\n    for filename in filenames:\n        print(os.path.join(dirname, filename))\n\n# Any results you write to the current directory are saved as output","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# pytorchでcat vs dog"},{"metadata":{},"cell_type":"markdown","source":"## 準備"},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import torch\nimport torchvision\nimport torch.optim as optim\nimport torch.nn as nn\nfrom torchvision import transforms, models\nfrom torch.utils.data import DataLoader, Dataset, ConcatDataset\nimport torch.nn.functional as F\nfrom PIL import Image\nimport matplotlib.pyplot as plt\nimport os\nimport glob\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#GPU設定\ndevice = \"cuda\" if torch.cuda.is_available() else \"cpu\"\ndevice","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#zipファイルを解凍\n!unzip \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/train.zip\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#trainの中身を確認\n!ls train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#test\n!unzip \"/kaggle/input/dogs-vs-cats-redux-kernels-edition/test.zip\"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#中身を確認\n!ls test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dir = 'train'\ntest_dir = 'test'","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#ファイルをリスト化\ntrain_list = glob.glob(os.path.join(train_dir, '*.jpg'))\ntest_list = glob.glob(os.path.join(test_dir, '*jpg'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#件数を確認\nprint('train_list:{}'.format(len(train_list)))\nprint('test_list:{}'.format(len(test_list)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#データセットを確認\nrandom_idx = np.random.randint(1, 25000, size=10)\nfig = plt.figure()\ni = 1\nfigsize = (15, 15)\nfor idx in random_idx:\n    figsize = figsize\n    ax = fig.add_subplot(2,5,i)\n    img = Image.open(train_list[idx])\n    plt.imshow(img)\n    i += 1\n    plt.axis('off')\nplt.show()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#ファイルの名前のtrainとtestの違い\nprint('train_file_name:{}'.format(train_list[0].split('/')[-1].split('.')[0]))\nprint('test_file_name:{}'.format(test_list[0].split('/')[-1].split('.')[0]))\n#trainは写っているのがdogかcatか\n#testは番号のみ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#trainを学習用と検証用に分ける\ntrain_list, val_list = train_test_split(train_list, test_size=0.2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 前処理を定義"},{"metadata":{"trusted":true},"cell_type":"code","source":"#前処理の定義\n#train\ntrain_transform = transforms.Compose([\n    transforms.Resize((224, 224)),\n    transforms.RandomResizedCrop(224),\n    transforms.RandomHorizontalFlip(),\n    transforms.ToTensor()\n])\n\n#validation\nval_transform = transforms.Compose([\n    transforms.Resize((224, 224)),\n    transforms.RandomResizedCrop(224),\n    transforms.RandomHorizontalFlip(),\n    transforms.ToTensor(),\n    \n])\n\n#test\ntest_transform = transforms.Compose([\n    transforms.Resize((224, 224)),\n    #transforms.RandomResizedCrop(224),\n    #transforms.RandomHorizontalFlip(),\n    transforms.ToTensor()\n])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## カスタムデータセットの定義と作成"},{"metadata":{"trusted":true},"cell_type":"code","source":"#カスタムデータセット定義\nclass dataset(Dataset):\n    #初期化\n    def __init__(self, file_list, transform=None):\n        self.file_list = file_list\n        self.transform = transform\n    \n    #特殊メソッド\n    def __len__(self):\n        return len(self.file_list)\n    \n    def __getitem__(self, idx):\n        img_path = self.file_list[idx]\n        img = Image.open(img_path)\n        img_transformed = self.transform(img)\n        \n        #ラベルの定義\n        label = img_path.split('/')[-1].split('.')[0]\n        if label == 'dog':\n            label = 1\n        else:\n            label = 0   \n        return img_transformed, label, img_path","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#データセット作成\ntrain_data = dataset(train_list, transform=train_transform)\nval_data = dataset(val_list, transform=val_transform)\ntest_data = dataset(test_list, transform=test_transform)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#dataloaderを使ってバッチ処理\ntrain_loader = DataLoader(dataset = train_data, batch_size=100, shuffle=True)\ntest_loader = DataLoader(dataset = test_data, shuffle=False)\nval_loader = DataLoader(dataset = val_data, batch_size=100, shuffle=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(train_data), len(train_loader))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(val_data), len(val_loader))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(len(test_data), len(test_loader))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#画像のshapeを確認\ntrain_data[0][0].shape","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## モデル構築(CNN)"},{"metadata":{"trusted":true},"cell_type":"code","source":"class CNN(nn.Module):\n    def __init__(self, num_classes):\n        super().__init__()\n        self.layer1 = nn.Sequential(\n            nn.Conv2d(3, 16, kernel_size=3, padding=0, stride=2),\n            nn.BatchNorm2d(16),\n            nn.ReLU(),\n            nn.MaxPool2d(2)\n        )\n        self.layer2 = nn.Sequential(\n            nn.Conv2d(16, 32, kernel_size=3, padding=0, stride=2),\n            nn.BatchNorm2d(32),\n            nn.ReLU(),\n            nn.MaxPool2d(2)\n        )\n        self.layer3 = nn.Sequential(\n            nn.Conv2d(32, 64, kernel_size=3, padding=0, stride=2),\n            nn.BatchNorm2d(64),\n            nn.ReLU(),\n            nn.MaxPool2d(2)\n        )\n        self.fc1 = nn.Linear(3*3*64, 10)\n        self.dropout = nn.Dropout(0.5)\n        self.fc2 = nn.Linear(10, 2)\n        self.relu = nn.ReLU()\n    \n    #順伝播\n    def forward(self, x):\n        out = self.layer1(x)\n        out = self.layer2(out)\n        out = self.layer3(out)\n        out = out.view(out.size(0), -1)\n        out = self.relu(self.fc1(out))\n        out = self.fc2(out)\n        return out\n        \n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#インスタンス作成\nmodel = CNN(2)\n#GPUに送る\nmodel.to(device)\n#??\nmodel.train()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#損失関数とoptimizerの設定\ncriterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(model.parameters(), lr=0.001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#データが正しく取得できているか確認\ndata_iter = iter(train_loader)\ndata, label, path = data_iter.next()\nlabel","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_iter = iter(test_loader)\ntest_data, _, test_path = test_iter.next()\ntest_path = str(test_path)\ntest = []\nfor test_data, _, test_path in test_loader:\n    test_path = str(test_path)\n    idx = [test_path.split('/')[-1].split('.')[0]]\n    print(idx)\n    test += list(zip(idx, test_data))\ntest","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## 学習"},{"metadata":{"trusted":true},"cell_type":"code","source":"epochs = 15\nlosses = []\nacces = []\nval_losses = []\nval_acces = []\nfor epoch in range(epochs):\n    epoch_loss = 0\n    epoch_acc = 0  \n    for data, label,_ in train_loader:\n        data = data.to(device)\n        label = label.to(device)\n        output = model(data)\n        loss = criterion(output, label)\n        optimizer.zero_grad()\n        loss.backward()\n        optimizer.step()\n        acc = ((output.argmax(dim=1) == label).float().mean())\n        epoch_acc += acc/len(train_loader)\n        epoch_loss += loss/len(train_loader)\n        losses.append(epoch_loss)\n        acces.append(epoch_acc)\n    print('Epoch:{}, train_acc:{}, train_loss:{}'.format(epoch+1, epoch_acc, epoch_loss))\n    \n    #val_loop\n    with torch.no_grad():\n        epoch_val_acc = 0\n        epoch_val_loss = 0\n        for data, label, _ in val_loader:\n            data = data.to(device)\n            label = label.to(device)\n            val_output = model(data)\n            val_loss = criterion(val_output, label)\n            acc = ((val_output.argmax(dim=1)==label).float().mean())\n            epoch_val_acc += acc/len(val_loader)\n            epoch_val_loss += val_loss/ len(val_loader)\n            val_losses.append(epoch_val_loss)\n            val_acces.append(epoch_val_acc)\n    print('Epoch:{}, val_accuracy:{}, val_loss:{}'.format(epoch+1, epoch_val_acc, epoch_val_loss))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.style.use(\"ggplot\")\nplt.plot(losses, label=\"train_loss\")\nplt.plot(val_losses, label=\"validation_loss\")\nplt.legend()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.plot(acces, label=\"train_acc\")\nplt.plot(val_acces, label=\"validation_acc\")\nplt.legend()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#test\n\ndog_probs = []\nmodel.eval()\n\nwith torch.no_grad():\n    for test_data, test_label, test_file in test_loader:\n        data = test_data.to(device)\n        preds = model(data)\n        preds_list = F.softmax(preds, dim=1)[:, 1].tolist()\n        test_file = str(test_file)\n        idx = [test_file.split('/')[-1].split('.')[0]]\n        #print(idx)\n        dog_probs += list(zip(idx, preds_list))\n    dog_probs\n    \n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"dog_probs.sort(key = lambda x : int(x[0]))\ndog_probs","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"idx = list(map(lambda x: x[0], dog_probs))\nprob = list(map(lambda x: x[1], dog_probs))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.DataFrame({'id': idx, 'label':prob})\nsubmission","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.to_csv('result.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#モデルの精度を可視化してして見てみる\nimport random\nid_list = []\nclass_ = {0: 'cat', 1:'dog'}\nfig, axes = plt.subplots(2, 5, figsize=(20, 12), facecolor='w')\nfor ax in axes.ravel():\n    i = random.choice(submission['id'].values)\n    label = submission.loc[submission['id'] == i, 'label'].values[0]\n    if label > 0.5:\n        label = 1\n    else:\n        label = 0\n    img_path = os.path.join(test_dir, '{}.jpg'.format(i))\n    img = Image.open(img_path)\n    \n    ax.set_title(class_[label])\n    ax.imshow(img)\n        ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat":4,"nbformat_minor":4}