{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"name":"python","version":"3.11.11","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"},"kaggle":{"accelerator":"none","dataSources":[{"sourceId":5441,"databundleVersionId":38425,"sourceType":"competition"}],"dockerImageVersionId":31040,"isInternetEnabled":true,"language":"python","sourceType":"notebook","isGpuEnabled":false}},"nbformat_minor":4,"nbformat":4,"cells":[{"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\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 read-only \"../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# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"execution":{"iopub.status.busy":"2025-07-25T06:50:12.961688Z","iopub.execute_input":"2025-07-25T06:50:12.962371Z","iopub.status.idle":"2025-07-25T06:50:12.971131Z","shell.execute_reply.started":"2025-07-25T06:50:12.962342Z","shell.execute_reply":"2025-07-25T06:50:12.970227Z"}},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import glob\nimport os\nimport random\nimport numpy as np\nimport torch\nimport torch.nn as nn\nimport torch.optim as optim\nimport torch.utils.data as data\nimport torchvision.transforms as transforms\nimport torchvision.models as models\nfrom PIL import Image\nfrom sklearn.model_selection import train_test_split\nimport time\nimport copy\nfrom tqdm import tqdm\nimport matplotlib.pyplot as plt\n\n# シード固定（再現性確保）\ndef set_seed(seed=42):\n    random.seed(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed_all(seed)\n    torch.backends.cudnn.deterministic = True\n    torch.backends.cudnn.benchmark = False\n\nset_seed()\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"size = 224\nmean = (0.485, 0.456, 0.406)\nstd = (0.229, 0.224, 0.225)\nbatch_size = 64\ndevice = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\nnum_epochs = 8\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# データを初期化\n!rm -rf ../data","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import zipfile\n\n# データの解凍\nbase_dir = '../input/dogs-vs-cats-redux-kernels-edition'\ntrain_dir = '../data/train'\ntest_dir = '../data/test'\n\nos.makedirs('../data', exist_ok=True)\n\n# 学習データの解凍\nwith zipfile.ZipFile(os.path.join(base_dir, 'train.zip')) as train_zip:\n    train_zip.extractall('../data')\n    \n#推論データの解凍\nwith zipfile.ZipFile(os.path.join(base_dir, 'test.zip')) as test_zip:\n    test_zip.extractall('../data')\n\n\ntrain_list = glob.glob(os.path.join(train_dir, '*.jpg'))\ntest_list = glob.glob(os.path.join(test_dir, '*.jpg'))\n\n# 学習データから検証データを分割(8:2)\ntrain_list, val_list = train_test_split(train_list, test_size=0.2)\n# ★画像数を制限して高速化したい場合（例：学習800枚、検証200枚）\ntrain_list = train_list[:800]\nval_list = val_list[:200]\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ImageTransform:\n    def __init__(self, resize, mean, std):\n        self.transforms_dict = {\n            'train': transforms.Compose([\n                transforms.RandomHorizontalFlip(p=0.5),\n                transforms.RandomVerticalFlip(p=0.2),\n                transforms.RandomRotation(degrees=10),\n                transforms.Resize((resize, resize)),\n                transforms.ToTensor(),\n                transforms.Normalize(mean, std),\n            ]),\n            'val': transforms.Compose([\n                transforms.Resize((resize, resize)),\n                transforms.ToTensor(),\n                transforms.Normalize(mean, std),\n            ])\n        }\n\n    def __call__(self, img, phase):\n        return self.transforms_dict[phase](img)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ImageDataset(data.Dataset):\n    def __init__(self, file_list, transform=None, phase='train'):\n        self.file_list = file_list\n        self.transform = transform\n        self.phase = phase\n\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).convert('RGB')  # RGB変換を追加\n        img = self.transform(img, self.phase)\n\n        label_str = img_path.split('/')[-1].split('.')[0]\n        label = 1 if label_str == 'dog' else 0\n\n        return img, label\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# データの前処理\ntrain_dataset = ImageDataset(train_list, transform=ImageTransform(size, mean, std), phase='train')\nval_dataset = ImageDataset(val_list, transform=ImageTransform(size, mean, std), phase='val')\n\n# データの読み込み\ntrain_dataloader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True)\nval_dataloader = data.DataLoader(val_dataset, batch_size=batch_size, shuffle=False)\n\ndataloader_dict = {'train': train_dataloader, 'val': val_dataloader}","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"use_pretrained = True\n# 事前学習済みのvgg16\nnet = models.vgg16(pretrained=True)\n\n# 全パラメータ更新停止\nfor param in net.parameters():\n    param.requires_grad = False\n\n# classifierの5層目以降は微調整可能に\nfor param in net.classifier[5:].parameters():\n    param.requires_grad = True\n\n# 出力層のクラス数変更（2クラス）\nnet.classifier[6] = nn.Linear(4096, 2)\n\nparams_to_update = [p for p in net.parameters() if p.requires_grad]\nupdate_params_name = ['classifier.6.weight', 'classifier.6.bias']\n\nfor name, param in net.named_parameters():\n    if name in update_params_name: #更新するパラメータの場合\n        param.requires_grad = True #更新する\n        params_to_update.append(param) #更新するパラメータの追加\n    else: #更新しないパラメータの場合\n        param.requires_grad = False #更新しない","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"criterion = nn.CrossEntropyLoss()\noptimizer = optim.Adam(params_to_update, lr=1e-4)\n\n# 検証精度が改善しなければ学習率を下げる\nscheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode='max', factor=0.5, patience=2, verbose=True)\n\ndef train_model(net, dataloader_dict, criterion, optimizer, num_epoch):\n    \n    since = time.time() #学習開始時刻を記録\n    best_model_wts = copy.deepcopy(net.state_dict()) #最良モデルの初期化\n    best_acc = 0.0 #最良精度の初期化\n    \n     # 損失と精度の履歴\n    history = {'train_loss': [], 'val_loss': [], 'train_acc': [], 'val_acc': []}\n    \n    net = net.to(device) #モデルをGPUに転送\n    print('training started')\n    for epoch in range(num_epoch): #各エポックの進捗\n        print('Epoch {}/{}'.format(epoch + 1, num_epoch))\n        print('-'*20)\n        \n        for phase in ['train', 'val']:\n            #学習と検証を交互に行う\n            if phase == 'train':\n                net.train() #学習フェーズ\n            else:\n                net.eval() #検証フェーズ\n                \n            epoch_loss = 0.0\n            epoch_corrects = 0\n            \n            for inputs, labels in tqdm(dataloader_dict[phase]):\n                inputs = inputs.to(device)\n                labels = labels.to(device)\n                optimizer.zero_grad()\n                \n                with torch.set_grad_enabled(phase == 'train'):\n                    outputs = net(inputs) #出力を算出\n                    _, preds = torch.max(outputs, 1) #予測値の取得\n                    loss = criterion(outputs, labels) #損失の計算\n                    \n                    if phase == 'train':\n                        loss.backward() #逆伝播で学習\n                        optimizer.step()\n                        \n                    #バッチごとの損失と精度を累積    \n                    epoch_loss += loss.item() * inputs.size(0) \n                    epoch_corrects += torch.sum(preds == labels.data)\n            \n            #エポックごとの損失と精度の計算\n            epoch_loss = epoch_loss / len(dataloader_dict[phase].dataset)\n            epoch_acc = epoch_corrects.double() / len(dataloader_dict[phase].dataset)\n            \n            print('{} Loss: {:.4f} Acc: {:.4f}'.format(phase, epoch_loss, epoch_acc))\n            \n            # 履歴に保存\n            history[f'{phase}_loss'].append(epoch_loss)\n            history[f'{phase}_acc'].append(epoch_acc.cpu().numpy())\n            \n            # 最良モデルの保存\n            if phase == 'val' and epoch_acc > best_acc:\n                best_acc = epoch_acc\n                best_model_wts = copy.deepcopy(net.state_dict())\n                \n    time_elapsed = time.time() - since #学習の総時間を計算\n    print('Training complete in {:.0f}m {:.0f}s'.format(time_elapsed // 60, time_elapsed % 60))\n    print('Best val Acc: {:4f}'.format(best_acc))\n\n    # 最良の重みを読み込む\n    net.load_state_dict(best_model_wts)\n    return net, history","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"transform = ImageTransform(size, mean, std)\n\n# train_list, val_list は事前に用意されている想定\ntrain_dataset = ImageDataset(train_list, transform=transform, phase='train')\nval_dataset = ImageDataset(val_list, transform=transform, phase='val')\n\ntrain_loader = data.DataLoader(train_dataset, batch_size=batch_size, shuffle=True, num_workers=2)\nval_loader = data.DataLoader(val_dataset, batch_size=batch_size, shuffle=False, num_workers=2)\n\ndataloaders = {'train': train_loader, 'val': val_loader}\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"def train_model(net, dataloaders, criterion, optimizer, scheduler, num_epochs, device):\n    best_acc = 0.0\n    best_weights = copy.deepcopy(net.state_dict())\n    history = {'train_loss': [], 'val_loss': [], 'train_acc': [], 'val_acc': []}\n    net.to(device)\n\n    for epoch in range(num_epochs):\n        print(f'Epoch {epoch+1}/{num_epochs}')\n        for phase in ['train', 'val']:\n            net.train() if phase == 'train' else net.eval()\n\n            running_loss = 0.0\n            running_corrects = 0\n\n            for inputs, labels in tqdm(dataloaders[phase]):\n                inputs = inputs.to(device)\n                labels = labels.to(device)\n\n                optimizer.zero_grad()\n\n                with torch.set_grad_enabled(phase == 'train'):\n                    outputs = net(inputs)\n                    loss = criterion(outputs, labels)\n                    preds = torch.argmax(outputs, dim=1)\n\n                    if phase == 'train':\n                        loss.backward()\n                        optimizer.step()\n\n                running_loss += loss.item() * inputs.size(0)\n                running_corrects += torch.sum(preds == labels.data)\n\n\n            epoch_loss = running_loss / len(dataloaders[phase].dataset)\n            epoch_acc = running_corrects.double() / len(dataloaders[phase].dataset)\n\n            print(f'{phase} Loss: {epoch_loss:.4f} Acc: {epoch_acc:.4f}')\n\n            history[f'{phase}_loss'].append(epoch_loss)\n            history[f'{phase}_acc'].append(epoch_acc.cpu().numpy())\n\n            if phase == 'val':\n                scheduler.step(epoch_acc)\n\n            if phase == 'val' and epoch_acc > best_acc:\n                best_acc = epoch_acc\n                best_weights = copy.deepcopy(net.state_dict())\n\n        # 5エポック以降でval_accが改善しなければ早期終了\n        if epoch > 5 and all(history['val_acc'][-1] <= acc for acc in history['val_acc'][-4:-1]):\n            print(f\"Early stopping at epoch {epoch+1}\")\n            break\n\n    net.load_state_dict(best_weights)\n    return net, history\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"net, history = train_model(net, dataloaders, criterion, optimizer, scheduler, num_epochs, device)\n\ntorch.save(net.state_dict(), 'best_model_v2.pth')","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n# 損失のプロット\nplt.figure(figsize=(12, 5))\nplt.subplot(1, 2, 1)\nplt.plot(history['train_loss'], label='Train Loss')\nplt.plot(history['val_loss'], label='Val Loss')\nplt.xlabel('Epoch')\nplt.ylabel('Loss')\nplt.title('Loss over epochs')\nplt.legend()\n\n# 精度のプロット\nplt.subplot(1, 2, 2)\nplt.plot(history['train_acc'], label='Train Accuracy')\nplt.plot(history['val_acc'], label='Val Accuracy')\nplt.xlabel('Epoch')\nplt.ylabel('Accuracy')\nplt.title('Accuracy over epochs')\nplt.legend()\n\nplt.show()","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"# ハイパーパラメータの定義（推論・学習共通）\nsize = 224  # 入力画像のサイズ\nmean = (0.485, 0.456, 0.406)  # ImageNetの平均\nstd = (0.229, 0.224, 0.225)   # ImageNetの標準偏差\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"class ImageTransform():\n    def __init__(self, resize, mean, std):\n        self.data_transform = {\n            'train': transforms.Compose([\n                transforms.Resize((resize, resize)),\n                transforms.RandomHorizontalFlip(),\n                transforms.RandomVerticalFlip(),\n                transforms.ToTensor(),\n                transforms.Normalize(mean, std)\n            ]),\n            'val': transforms.Compose([\n                transforms.Resize((resize, resize)),\n                transforms.ToTensor(),\n                transforms.Normalize(mean, std)\n            ])\n        }\n\n    def __call__(self, img, phase):\n        return self.data_transform[phase](img)\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"print(len(test_list))       # 画像の数を確認\nprint(test_list[:5])        # 最初の5件を表示（空なら [] になる）\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\nprint(os.listdir('../data/test'))  # 画像ファイル名が出るか？\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import glob\ntest_list = glob.glob('/kaggle/working/data/test/*.jpg')  # 実際に確認できたパスに合わせる\nprint(f\"画像数: {len(test_list)} 枚\")\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import os\n\nfolder = \"../data/test\"\nfilenames = os.listdir(folder)\n\n# 拡張子が .jpg のものだけに絞ってパスを作成\ntest_list = [os.path.join(folder, f) for f in filenames if f.endswith('.jpg')]\n\nprint(f\"画像数: {len(test_list)} 枚\")\nprint(test_list[:5])  # 最初の5件だけ表示\n","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import torch\nimport torch.nn.functional as F\nimport pandas as pd\nfrom PIL import Image\nfrom tqdm import tqdm\n\n# モデルを評価モードにする（1回だけでOK）\nnet.eval()\n\n# 前処理（transform）もループ外で定義\ntransform = ImageTransform(size, mean, std)\n\nid_list = []\npred_list = []\n\nwith torch.no_grad():\n    for test_path in tqdm(test_list):\n        try:\n            img = Image.open(test_path).convert('RGB')  # カラーモード統一\n            _id = int(os.path.basename(test_path).split('.')[0])  # ファイル名からIDを取得\n\n            img = transform(img, phase='val')  # 前処理\n            img = img.unsqueeze(0).to(device)  # バッチ次元追加＋GPU転送\n\n            outputs = net(img)\n            preds = F.softmax(outputs, dim=1)[:, 1].item()  # クラス1(dog)の確率\n\n            id_list.append(_id)\n            pred_list.append(preds)\n\n        except Exception as e:\n            print(f\"❌ Error on {test_path}: {e}\")\n\n# DataFrameにしてCSV出力\nres = pd.DataFrame({'id': id_list, 'label': pred_list})\nres = res.sort_values('id').reset_index(drop=True)\n\n# 確認（Kaggleでは12500件必要）\nprint(f\"✅ 予測件数: {len(res)} 件\")\n\nres.to_csv('/kaggle/working/submission.csv', index=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"if len(res) != 12500:\n    print(f\"⚠️ 行数が不足しています: {len(res)} 行\")\nelse:\n    print(\"✅ 正しい提出形式です（12500行）\")","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"res.to_csv('/kaggle/working/submission.csv', index=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"res.to_csv('submission.csv', index=False)","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"import pandas as pd\n\n# テスト用（resが消えてる場合は仮のデータでも可）\n# res = pd.DataFrame({'id': [1, 2], 'label': [0.9, 0.1]})\n\nres.to_csv('submission.csv', index=False)\n\nimport os\nprint(\"カレントディレクトリのファイル一覧:\")\nprint(os.listdir('.'))","metadata":{"trusted":true},"outputs":[],"execution_count":null},{"cell_type":"code","source":"from google.colab import files\nfiles.download(\"submission.csv\")","metadata":{"trusted":true},"outputs":[],"execution_count":null}]}