{"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\n\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nfrom matplotlib import pyplot as plt\nimport seaborn as sns\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","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import zipfile\n\nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/train.zip\",\"r\") as zip_ref:\n    zip_ref.extractall()\n    \nwith zipfile.ZipFile(\"/kaggle/input/dogs-vs-cats/test1.zip\",\"r\") as zip_ref:\n    zip_ref.extractall()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import csv\nimport pathlib\n\ncsv_columns = ['path', 'label']\ncsv_data = []\ncsv_file = \"trainData.csv\"\n\npy = pathlib.Path(\"./train\").glob(\"*\")\nfor file in py:\n    # print(file.name.split(\".\"))\n    filename = file.name\n    label = 0\n    if file.name.split(\".\")[0] == 'cat':\n        label = 0\n    else:\n        label = 1\n\n    csv_data.append({'path': filename, 'label': label})\n\ntry:\n    with open(csv_file, 'w') as csvfile:\n        writer = csv.DictWriter(csvfile, fieldnames=csv_columns)\n        writer.writeheader()\n        for data in csv_data:\n            writer.writerow(data)\n\nexcept IOError:\n    print(\"I/O error\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df = pd.read_csv(\"./trainData.csv\")\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['label'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class CFG:\n    debug=False\n    apex=False\n    print_freq=100\n    num_workers=4\n    model_name='resnext50_32x4d'\n    size=256\n    scheduler='CosineAnnealingWarmRestarts' \n    epochs=1\n    T_0=10 # CosineAnnealingWarmRestarts\n    lr=1e-4\n    min_lr=1e-6\n    batch_size=64\n    weight_decay=1e-6\n    gradient_accumulation_steps=1\n    max_grad_norm=1000\n    seed=42\n    target_size=2\n    target_col='label'\n    n_fold=5\n    trn_fold=[0, 1, 2, 3, 4]\n    train=True\n    inference=False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport math\nimport time\nimport random\nimport shutil\nfrom pathlib import Path\nfrom contextlib import contextmanager\nfrom collections import defaultdict, Counter\n\nimport scipy as sp\nimport numpy as np\nimport pandas as pd\n\nfrom sklearn import preprocessing\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import KFold\n\nfrom tqdm.auto import tqdm\nfrom functools import partial\n\nimport cv2\nfrom PIL import Image\n\nimport torch\nimport torch.nn as nn\nimport torch.nn.functional as F\nfrom torch.optim import Adam, SGD\nimport torchvision.models as models\nfrom torch.nn.parameter import Parameter\nfrom torch.utils.data import DataLoader, Dataset\nfrom torch.optim.lr_scheduler import CosineAnnealingWarmRestarts\n\nfrom albumentations import (\n    Compose, OneOf, Normalize, Resize, RandomResizedCrop, RandomCrop, HorizontalFlip, VerticalFlip, \n    RandomBrightness, RandomContrast, RandomBrightnessContrast, Rotate, ShiftScaleRotate, Cutout, \n    IAAAdditiveGaussianNoise, Transpose\n    )\nfrom albumentations.pytorch import ToTensorV2\nfrom albumentations import ImageOnlyTransform\n\nimport warnings \nwarnings.filterwarnings('ignore')\n\nif CFG.apex:\n    from apex import amp\n\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!pip install timm\nimport timm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_score(y_true, y_pred):\n    return accuracy_score(y_true, y_pred)\n\n\n@contextmanager\ndef timer(name):\n    t0 = time.time()\n    LOGGER.info(f'[{name}] start')\n    yield\n    LOGGER.info(f'[{name}] done in {time.time() - t0:.0f} s.')\n\n\ndef init_logger(log_file='./train.log'):\n    from logging import getLogger, INFO, FileHandler,  Formatter,  StreamHandler\n    logger = getLogger(__name__)\n    logger.setLevel(INFO)\n    handler1 = StreamHandler()\n    handler1.setFormatter(Formatter(\"%(message)s\"))\n    handler2 = FileHandler(filename=log_file)\n    handler2.setFormatter(Formatter(\"%(message)s\"))\n    logger.addHandler(handler1)\n    logger.addHandler(handler2)\n    return logger\n\nLOGGER = init_logger()\n\n\ndef seed_torch(seed=42):\n    random.seed(seed)\n    os.environ['PYTHONHASHSEED'] = str(seed)\n    np.random.seed(seed)\n    torch.manual_seed(seed)\n    torch.cuda.manual_seed(seed)\n    torch.backends.cudnn.deterministic = True\n\nseed_torch(seed=CFG.seed)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\nfolds = train_df.copy()\nFold = KFold(n_splits=CFG.n_fold, shuffle=True, random_state=CFG.seed)\nfor n, (train_index, val_index) in enumerate(Fold.split(folds, folds[CFG.target_col])):\n    folds.loc[val_index, 'fold'] = int(n)\nfolds['fold'] = folds['fold'].astype(int)\nprint(folds.groupby(['fold', CFG.target_col]).size())\n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_PATH='./train'\nclass TrainDataset(Dataset):\n    def __init__(self, df, transform=None):\n        self.df = df\n        self.file_names = df['path'].values\n        self.labels = df['label'].values\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.df)\n\n    def __getitem__(self, idx):\n        file_name = self.file_names[idx]\n        file_path = f'{TRAIN_PATH}/{file_name}'\n        image = cv2.imread(file_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        if self.transform:\n            augmented = self.transform(image=image)\n            image = augmented['image']\n        label = torch.tensor(self.labels[idx]).long()\n        return image, label","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = TrainDataset(train_df, transform=None)\n\nfor i in range(1):\n    image, label = train_dataset[i]\n    plt.imshow(image)\n    plt.title(f'label: {label}')\n    plt.show() ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def get_transforms(*, data):\n    \n    if data == 'train':\n        return Compose([\n            Resize(CFG.size, CFG.size),\n            RandomResizedCrop(CFG.size, CFG.size),\n#             Transpose(),\n            HorizontalFlip(),\n#             VerticalFlip(),\n#             ShiftScaleRotate(),\n            Normalize(\n                mean=[0.485, 0.456, 0.406],\n                std=[0.229, 0.224, 0.225],\n            ),\n            ToTensorV2(),\n        ])\n\n    elif data == 'valid':\n        return Compose([\n            Resize(CFG.size, CFG.size),\n            Normalize(\n                mean=[0.485, 0.456, 0.406],\n                std=[0.229, 0.224, 0.225],\n            ),\n            ToTensorV2(),\n        ])\n    ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\ntrain_dataset = TrainDataset(train_df, transform=get_transforms(data='train'))\n\nfor i in range(1):\n    image, label = train_dataset[i]\n    plt.imshow(image[0])\n    plt.title(f'label: {label}')\n    plt.show() \n\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class CustomResNext(nn.Module):\n    def __init__(self, model_name='resnext50_32x4d', pretrained=True):\n        super().__init__()\n        self.model = timm.create_model(model_name, pretrained=pretrained)\n        n_features = self.model.fc.in_features\n        self.model.fc = nn.Linear(n_features, CFG.target_size)\n\n    def forward(self, x):\n        x = self.model(x)\n        return x\n    \n    def freeze(self):\n        for name, param in self.model.named_parameters():\n            if \"fc\" in name:\n                param.requires_grad = True\n            else:\n                param.requires_grad = False\n    def unfreeze(self):\n        for name, param in self.model.named_parameters():\n            param.requires_grad = True","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = CustomResNext(model_name=CFG.model_name, pretrained=False)\ntrain_dataset = TrainDataset(train_df, transform=get_transforms(data='train'))\ntrain_loader = DataLoader(train_dataset, batch_size=4, shuffle=True,\n                          num_workers=4, pin_memory=True, drop_last=True)\n\nfor image, label in train_loader:\n    output = model(image)\n    print(output)\n    break","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"class AverageMeter(object):\n    \"\"\"Computes and stores the average and current value\"\"\"\n    def __init__(self):\n        self.reset()\n\n    def reset(self):\n        self.val = 0\n        self.avg = 0\n        self.sum = 0\n        self.count = 0\n\n    def update(self, val, n=1):\n        self.val = val\n        self.sum += val * n\n        self.count += n\n        self.avg = self.sum / self.count\n\n\ndef asMinutes(s):\n    m = math.floor(s / 60)\n    s -= m * 60\n    return '%dm %ds' % (m, s)\n\n\ndef timeSince(since, percent):\n    now = time.time()\n    s = now - since\n    es = s / (percent)\n    rs = es - s\n    return '%s (remain %s)' % (asMinutes(s), asMinutes(rs))\n\n\ndef train_fn(train_loader, model, criterion, optimizer, epoch, scheduler, device):\n    batch_time = AverageMeter()\n    data_time = AverageMeter()\n    losses = AverageMeter()\n    scores = AverageMeter()\n    # switch to train mode\n    model.train()\n    start = end = time.time()\n    global_step = 0\n    for step, (images, labels) in enumerate(train_loader):\n        # measure data loading time\n        data_time.update(time.time() - end)\n        images = images.to(device)\n        labels = labels.to(device)\n        batch_size = labels.size(0)\n        y_preds = model(images)\n        loss = criterion(y_preds, labels)\n        # record loss\n        losses.update(loss.item(), batch_size)\n        if CFG.gradient_accumulation_steps > 1:\n            loss = loss / CFG.gradient_accumulation_steps\n        if CFG.apex:\n            with amp.scale_loss(loss, optimizer) as scaled_loss:\n                scaled_loss.backward()\n        else:\n            loss.backward()\n        grad_norm = torch.nn.utils.clip_grad_norm_(model.parameters(), CFG.max_grad_norm)\n        if (step + 1) % CFG.gradient_accumulation_steps == 0:\n            optimizer.step()\n            optimizer.zero_grad()\n            global_step += 1\n        # measure elapsed time\n        batch_time.update(time.time() - end)\n        end = time.time()\n        if step % CFG.print_freq == 0 or step == (len(train_loader)-1):\n            print('Epoch: [{0}][{1}/{2}] '\n                  'Data {data_time.val:.3f} ({data_time.avg:.3f}) '\n                  'Elapsed {remain:s} '\n                  'Loss: {loss.val:.4f}({loss.avg:.4f}) '\n                  'Grad: {grad_norm:.4f}  '\n                  #'LR: {lr:.6f}  '\n                  .format(\n                   epoch+1, step, len(train_loader), batch_time=batch_time,\n                   data_time=data_time, loss=losses,\n                   remain=timeSince(start, float(step+1)/len(train_loader)),\n                   grad_norm=grad_norm,\n                   #lr=scheduler.get_lr()[0],\n                   ))\n    return losses.avg\n\n\ndef valid_fn(valid_loader, model, criterion, device):\n    batch_time = AverageMeter()\n    data_time = AverageMeter()\n    losses = AverageMeter()\n    scores = AverageMeter()\n    # switch to evaluation mode\n    model.eval()\n    preds = []\n    start = end = time.time()\n    for step, (images, labels) in enumerate(valid_loader):\n        # measure data loading time\n        data_time.update(time.time() - end)\n        images = images.to(device)\n        labels = labels.to(device)\n        batch_size = labels.size(0)\n        # compute loss\n        with torch.no_grad():\n            y_preds = model(images)\n        loss = criterion(y_preds, labels)\n        losses.update(loss.item(), batch_size)\n        # record accuracy\n        preds.append(y_preds.softmax(1).to('cpu').numpy())\n        if CFG.gradient_accumulation_steps > 1:\n            loss = loss / CFG.gradient_accumulation_steps\n        # measure elapsed time\n        batch_time.update(time.time() - end)\n        end = time.time()\n        if step % CFG.print_freq == 0 or step == (len(valid_loader)-1):\n            print('EVAL: [{0}/{1}] '\n                  'Data {data_time.val:.3f} ({data_time.avg:.3f}) '\n                  'Elapsed {remain:s} '\n                  'Loss: {loss.val:.4f}({loss.avg:.4f}) '\n                  .format(\n                   step, len(valid_loader), batch_time=batch_time,\n                   data_time=data_time, loss=losses,\n                   remain=timeSince(start, float(step+1)/len(valid_loader)),\n                   ))\n    predictions = np.concatenate(preds)\n    return losses.avg, predictions\n\n\ndef inference(model, states, test_loader, device):\n    model.to(device)\n    tk0 = tqdm(enumerate(test_loader), total=len(test_loader))\n    probs = []\n    for i, (images) in tk0:\n        images = images.to(device)\n        avg_preds = []\n        for state in states:\n            model.load_state_dict(state['model'])\n            model.eval()\n            with torch.no_grad():\n                y_preds = model(images)\n            avg_preds.append(y_preds.softmax(1).to('cpu').numpy())\n        avg_preds = np.mean(avg_preds, axis=0)\n        probs.append(avg_preds)\n    probs = np.concatenate(probs)\n    return probs","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def train_loop(folds, fold):\n\n    LOGGER.info(f\"========== fold: {fold} training ==========\")\n\n    # ====================================================\n    # loader\n    # ====================================================\n    trn_idx = folds[folds['fold'] != fold].index\n    val_idx = folds[folds['fold'] == fold].index\n\n    train_folds = folds.loc[trn_idx].reset_index(drop=True)\n    valid_folds = folds.loc[val_idx].reset_index(drop=True)\n\n    train_dataset = TrainDataset(train_folds, \n                                 transform=get_transforms(data='train'))\n    valid_dataset = TrainDataset(valid_folds, \n                                 transform=get_transforms(data='valid'))\n\n    train_loader = DataLoader(train_dataset, \n                              batch_size=CFG.batch_size, \n                              shuffle=True, \n                              num_workers=CFG.num_workers, pin_memory=True, drop_last=True)\n    valid_loader = DataLoader(valid_dataset, \n                              batch_size=CFG.batch_size, \n                              shuffle=False, \n                              num_workers=CFG.num_workers, pin_memory=True, drop_last=False)\n    \n    # ====================================================\n    # scheduler \n    # ====================================================\n    def get_scheduler(optimizer):\n        if CFG.scheduler=='ReduceLROnPlateau':\n            scheduler = ReduceLROnPlateau(optimizer, mode='min', factor=CFG.factor, patience=CFG.patience, verbose=True, eps=CFG.eps)\n        elif CFG.scheduler=='CosineAnnealingLR':\n            scheduler = CosineAnnealingLR(optimizer, T_max=CFG.T_max, eta_min=CFG.min_lr, last_epoch=-1)\n        elif CFG.scheduler=='CosineAnnealingWarmRestarts':\n            scheduler = CosineAnnealingWarmRestarts(optimizer, T_0=CFG.T_0, T_mult=1, eta_min=CFG.min_lr, last_epoch=-1)\n        return scheduler\n\n    # ====================================================\n    # model & optimizer\n    # ====================================================\n    model = CustomResNext(CFG.model_name, pretrained=True)\n    model.to(device)\n    model.freeze()\n    optimizer = Adam(model.parameters(), lr=CFG.lr, weight_decay=CFG.weight_decay, amsgrad=False)\n    scheduler = get_scheduler(optimizer)\n\n    # ====================================================\n    # apex\n    # ====================================================\n    if CFG.apex:\n        model, optimizer = amp.initialize(model, optimizer, opt_level='O1', verbosity=0)\n\n    # ====================================================\n    # loop\n    # ====================================================\n    criterion = nn.CrossEntropyLoss()\n\n    best_score = 0.\n    best_loss = np.inf\n    \n    for epoch in range(CFG.epochs):\n        \n        if epoch == 7:\n            print('==== Unfreezing Model ====')\n            model.unfreeze()\n        \n        start_time = time.time()\n        \n        # train\n        avg_loss = train_fn(train_loader, model, criterion, optimizer, epoch, scheduler, device)\n\n        # eval\n        avg_val_loss, preds = valid_fn(valid_loader, model, criterion, device)\n        valid_labels = valid_folds[CFG.target_col].values\n        \n \n        if isinstance(scheduler, CosineAnnealingWarmRestarts):\n            scheduler.step()\n\n        # scoring\n        score = get_score(valid_labels, preds.argmax(1))\n\n        elapsed = time.time() - start_time\n\n        LOGGER.info(f'Epoch {epoch+1} - avg_train_loss: {avg_loss:.4f}  avg_val_loss: {avg_val_loss:.4f}  time: {elapsed:.0f}s')\n        LOGGER.info(f'Epoch {epoch+1} - Accuracy: {score}')\n\n        if score > best_score:\n            best_score = score\n            LOGGER.info(f'Epoch {epoch+1} - Save Best Score: {best_score:.4f} Model')\n            torch.save({'model': model.state_dict(), \n                        'preds': preds},\n                        './'+f'{CFG.model_name}_fold{fold}_best.pth')\n    \n    check_point = torch.load('./'+f'{CFG.model_name}_fold{fold}_best.pth')\n#     print(check_point)\n    valid_folds[[str(c) for c in range(2)]] = check_point['preds']\n#     print(valid_folds)\n    valid_folds['preds'] = check_point['preds'].argmax(1)\n\n    return valid_folds","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def main():\n\n    \"\"\"\n    Prepare: 1.train  2.test  3.submission  4.folds\n    \"\"\"\n\n    def get_result(result_df):\n        preds = result_df['preds'].values\n        labels = result_df[CFG.target_col].values\n        score = get_score(labels, preds)\n        LOGGER.info(f'Score: {score:<.5f}')\n    \n    if CFG.train:\n        # train \n        oof_df = pd.DataFrame()\n        for fold in range(CFG.n_fold):\n            if fold in CFG.trn_fold:\n                _oof_df = train_loop(folds, fold)\n                oof_df = pd.concat([oof_df, _oof_df])\n                LOGGER.info(f\"========== fold: {fold} result ==========\")\n                get_result(_oof_df)\n        # CV result\n        LOGGER.info(f\"========== CV ==========\")\n        get_result(oof_df)\n        # save result\n        oof_df.to_csv('./'+'oof_df.csv', index=False)\n    \n    if CFG.inference:\n        # inference\n        model = CustomResNext(CFG.model_name, pretrained=False)\n        states = [torch.load('./'+f'{CFG.model_name}_fold{fold}_best.pth') for fold in CFG.trn_fold]\n        test_dataset = TestDataset(test, transform=get_transforms(data='valid'))\n        test_loader = DataLoader(test_dataset, batch_size=CFG.batch_size, shuffle=False, \n                                 num_workers=CFG.num_workers, pin_memory=True)\n        predictions = inference(model, states, test_loader, device)\n        # submission\n        test['label'] = predictions.argmax(1)\n        test[['image_id', 'label']].to_csv(OUTPUT_DIR+'submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if __name__ == '__main__':\n    main()","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}