{"cells":[{"metadata":{},"cell_type":"markdown","source":"# About this notebook\n- PyTorch resnext50_32x4d starter code\n- GroupKFold 5 folds\n- training code is [here](https://www.kaggle.com/yasufuminakama/ranzcr-resnext50-32x4d-starter-training)\n\nIf this notebook is helpful, feel free to upvote :)"},{"metadata":{"papermill":{"duration":0.022224,"end_time":"2020-12-14T19:52:41.498163","exception":false,"start_time":"2020-12-14T19:52:41.475939","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Directory settings"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:41.549032Z","iopub.status.busy":"2020-12-14T19:52:41.548343Z","iopub.status.idle":"2020-12-14T19:52:41.553026Z","shell.execute_reply":"2020-12-14T19:52:41.552269Z"},"papermill":{"duration":0.033458,"end_time":"2020-12-14T19:52:41.553131","exception":false,"start_time":"2020-12-14T19:52:41.519673","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# Directory settings\n# ====================================================\nimport os\n\nMODEL_DIR = '../input/ranzcr-resnext50-32x4d-starter-training/'\nOUTPUT_DIR = './'\nif not os.path.exists(OUTPUT_DIR):\n    os.makedirs(OUTPUT_DIR)\n\nTEST_PATH = '../input/ranzcr-clip-catheter-line-classification/test'","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.02073,"end_time":"2020-12-14T19:52:41.594446","exception":false,"start_time":"2020-12-14T19:52:41.573716","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# CFG"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:41.647322Z","iopub.status.busy":"2020-12-14T19:52:41.646482Z","iopub.status.idle":"2020-12-14T19:52:41.650102Z","shell.execute_reply":"2020-12-14T19:52:41.649535Z"},"papermill":{"duration":0.034829,"end_time":"2020-12-14T19:52:41.650216","exception":false,"start_time":"2020-12-14T19:52:41.615387","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# CFG\n# ====================================================\nclass CFG:\n    debug=False\n    num_workers=4\n    model_name='resnext50_32x4d'\n    size=512 #320\n    batch_size=256  #128\n    seed=42\n    target_size=11\n    target_cols=['ETT - Abnormal', 'ETT - Borderline', 'ETT - Normal',\n                 'NGT - Abnormal', 'NGT - Borderline', 'NGT - Incompletely Imaged', 'NGT - Normal', \n                 'CVC - Abnormal', 'CVC - Borderline', 'CVC - Normal',\n                 'Swan Ganz Catheter Present']\n    n_fold=5\n    trn_fold=[0, 1, 2, 3, 4]","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.02152,"end_time":"2020-12-14T19:52:41.693202","exception":false,"start_time":"2020-12-14T19:52:41.671682","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Library"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:41.750878Z","iopub.status.busy":"2020-12-14T19:52:41.750245Z","iopub.status.idle":"2020-12-14T19:52:45.494184Z","shell.execute_reply":"2020-12-14T19:52:45.492665Z"},"papermill":{"duration":3.779959,"end_time":"2020-12-14T19:52:45.49431","exception":false,"start_time":"2020-12-14T19:52:41.714351","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# Library\n# ====================================================\nimport sys\nsys.path.append('../input/pytorch-image-models/pytorch-image-models-master')\n\nimport 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 roc_auc_score\nfrom sklearn.model_selection import StratifiedKFold, GroupKFold, KFold\n\nfrom tqdm.auto import tqdm\nfrom functools import partial\n\nimport cv2\nfrom PIL import Image\n\nfrom matplotlib import pyplot as plt\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, CosineAnnealingLR, ReduceLROnPlateau\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 timm\n\nfrom torch.cuda.amp import autocast, GradScaler\n\nimport warnings \nwarnings.filterwarnings('ignore')\n\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.021243,"end_time":"2020-12-14T19:52:45.536479","exception":false,"start_time":"2020-12-14T19:52:45.515236","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Utils"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:45.59513Z","iopub.status.busy":"2020-12-14T19:52:45.594471Z","iopub.status.idle":"2020-12-14T19:52:45.60117Z","shell.execute_reply":"2020-12-14T19:52:45.60042Z"},"papermill":{"duration":0.040687,"end_time":"2020-12-14T19:52:45.601288","exception":false,"start_time":"2020-12-14T19:52:45.560601","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# Utils\n# ====================================================\ndef get_score(y_true, y_pred):\n    return roc_auc_score(y_true.reshape(-1), y_pred.reshape(-1))\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=OUTPUT_DIR+'inference.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\n#LOGGER = 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":{},"cell_type":"markdown","source":"# Data Loading"},{"metadata":{"trusted":true},"cell_type":"code","source":"test = pd.read_csv('../input/ranzcr-clip-catheter-line-classification/sample_submission.csv')\nprint(test.shape)\ntest.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"if CFG.debug:\n    test = test.head()","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.023234,"end_time":"2020-12-14T19:52:45.910123","exception":false,"start_time":"2020-12-14T19:52:45.886889","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Dataset"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:45.967747Z","iopub.status.busy":"2020-12-14T19:52:45.96573Z","iopub.status.idle":"2020-12-14T19:52:45.968559Z","shell.execute_reply":"2020-12-14T19:52:45.969115Z"},"papermill":{"duration":0.036559,"end_time":"2020-12-14T19:52:45.969232","exception":false,"start_time":"2020-12-14T19:52:45.932673","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# Dataset\n# ====================================================\nclass TestDataset(Dataset):\n    def __init__(self, df, transform=None):\n        self.df = df\n        self.file_names = df['StudyInstanceUID'].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'{TEST_PATH}/{file_name}.jpg'\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        return image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = TestDataset(test, transform=None)\n\nfor i in range(5):\n    image = train_dataset[i]\n    plt.imshow(image)\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.024022,"end_time":"2020-12-14T19:52:46.01618","exception":false,"start_time":"2020-12-14T19:52:45.992158","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Transforms"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:46.071509Z","iopub.status.busy":"2020-12-14T19:52:46.070642Z","iopub.status.idle":"2020-12-14T19:52:46.074136Z","shell.execute_reply":"2020-12-14T19:52:46.073613Z"},"papermill":{"duration":0.035507,"end_time":"2020-12-14T19:52:46.074245","exception":false,"start_time":"2020-12-14T19:52:46.038738","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# Transforms\n# ====================================================\ndef get_transforms(*, data):\n    \n    if data == 'train':\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\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        ])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_dataset = TestDataset(test, transform=get_transforms(data='valid'))\n\nfor i in range(5):\n    image = train_dataset[i]\n    plt.imshow(image[0])\n    plt.show() ","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.022168,"end_time":"2020-12-14T19:52:46.118843","exception":false,"start_time":"2020-12-14T19:52:46.096675","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# MODEL"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:46.17627Z","iopub.status.busy":"2020-12-14T19:52:46.170979Z","iopub.status.idle":"2020-12-14T19:52:46.18312Z","shell.execute_reply":"2020-12-14T19:52:46.183763Z"},"papermill":{"duration":0.042914,"end_time":"2020-12-14T19:52:46.183878","exception":false,"start_time":"2020-12-14T19:52:46.140964","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# MODEL\n# ====================================================\nclass CustomResNext(nn.Module):\n    def __init__(self, model_name='resnext50_32x4d', pretrained=False):\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","execution_count":null,"outputs":[]},{"metadata":{"papermill":{"duration":0.022356,"end_time":"2020-12-14T19:52:46.228883","exception":false,"start_time":"2020-12-14T19:52:46.206527","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# Helper functions"},{"metadata":{"execution":{"iopub.execute_input":"2020-12-14T19:52:46.445205Z","iopub.status.busy":"2020-12-14T19:52:46.443326Z","iopub.status.idle":"2020-12-14T19:52:46.445944Z","shell.execute_reply":"2020-12-14T19:52:46.446449Z"},"papermill":{"duration":0.064625,"end_time":"2020-12-14T19:52:46.446561","exception":false,"start_time":"2020-12-14T19:52:46.381936","status":"completed"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# Helper functions\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.sigmoid().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":{"papermill":{"duration":0.022557,"end_time":"2020-12-14T19:52:46.492442","exception":false,"start_time":"2020-12-14T19:52:46.469885","status":"completed"},"tags":[]},"cell_type":"markdown","source":"# inference"},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","execution":{"iopub.execute_input":"2020-12-14T19:52:46.757077Z","iopub.status.busy":"2020-12-14T19:52:46.755987Z"},"papermill":{"duration":null,"end_time":null,"exception":false,"start_time":"2020-12-14T19:52:46.725364","status":"running"},"tags":[],"trusted":true},"cell_type":"code","source":"# ====================================================\n# inference\n# ====================================================\nmodel = CustomResNext(CFG.model_name, pretrained=False)\nstates = [torch.load(MODEL_DIR+f'{CFG.model_name}_fold{fold}_best.pth') for fold in CFG.trn_fold]\ntest_dataset = TestDataset(test, transform=get_transforms(data='valid'))\ntest_loader = DataLoader(test_dataset, batch_size=CFG.batch_size, shuffle=False, \n                         num_workers=CFG.num_workers, pin_memory=True)\npredictions = inference(model, states, test_loader, device)\n# submission\ntest[CFG.target_cols] = predictions\ntest[['StudyInstanceUID'] + CFG.target_cols].to_csv(OUTPUT_DIR+'submission.csv', index=False)\ntest.head()","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}