{"cells":[{"metadata":{},"cell_type":"markdown","source":"# About this notebook"},{"metadata":{},"cell_type":"markdown","source":"- PyTorch Resnet18 inference code \n- I prepared this inference code because [training code](https://www.kaggle.com/yasufuminakama/imet-2020-pytorch-resnet18-starter/output?scriptVersionId=30968669) faces Notebook Timeout for submission though I set epochs not to exceed 4 hours\n\nIf this notebook is helpful, feel free to upvote :)  "},{"metadata":{},"cell_type":"markdown","source":"# Library"},{"metadata":{"_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","trusted":true},"cell_type":"code","source":"import os\nimport numpy as np \nimport pandas as pd \nimport json","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"os.listdir('../input/imet-2020-fgvc7')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Loading"},{"metadata":{"trusted":true},"cell_type":"code","source":"submission = pd.read_csv('../input/imet-2020-fgvc7/sample_submission.csv')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Library"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Library\n# ====================================================\n\nimport sys\n\nimport gc\nimport os\nimport random\nimport time\nfrom contextlib import contextmanager\nfrom pathlib import Path\nfrom collections import defaultdict, Counter\n\nimport cv2\nfrom PIL import Image\nimport numpy as np\nimport pandas as pd\nimport scipy as sp\n\nimport sklearn.metrics\nfrom sklearn.metrics import accuracy_score\nfrom sklearn.model_selection import StratifiedKFold\n\nfrom functools import partial\nfrom tqdm import tqdm\n\nimport torch\nimport torch.nn as nn\nfrom torch.optim import Adam, SGD\nfrom torch.optim.lr_scheduler import CosineAnnealingLR, ReduceLROnPlateau\nfrom torch.utils.data import DataLoader, Dataset\nimport torchvision.models as models\n\nfrom albumentations import Compose, Normalize, Resize, RandomResizedCrop\nfrom albumentations.pytorch import ToTensorV2\n\n\ndevice = torch.device('cuda' if torch.cuda.is_available() else 'cpu')\ndevice","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Utils"},{"metadata":{"trusted":true},"cell_type":"code","source":"# ====================================================\n# Utils\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, DEBUG, FileHandler,  Formatter,  StreamHandler\n    \n    log_format = '%(asctime)s %(levelname)s %(message)s'\n    \n    stream_handler = StreamHandler()\n    stream_handler.setLevel(DEBUG)\n    stream_handler.setFormatter(Formatter(log_format))\n    \n    file_handler = FileHandler(log_file)\n    file_handler.setFormatter(Formatter(log_format))\n    \n    logger = getLogger('Herbarium')\n    logger.setLevel(DEBUG)\n    logger.addHandler(stream_handler)\n    logger.addHandler(file_handler)\n    \n    return logger\n\nLOG_FILE = 'train.log'\nLOGGER = init_logger(LOG_FILE)\n\n\ndef seed_torch(seed=777):\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 = 777\nseed_torch(SEED)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Dataset"},{"metadata":{"trusted":true},"cell_type":"code","source":"N_CLASSES = 3474\n\n\nclass TrainDataset(Dataset):\n    def __init__(self, df, labels, transform=None):\n        self.df = df\n        self.labels = labels\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.df)\n\n    def __getitem__(self, idx):\n        file_name = self.df['id'].values[idx]\n        file_path = f'../input/imet-2020-fgvc7/train/{file_name}.png'\n        image = cv2.imread(file_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        \n        if self.transform:\n            augmented = self.transform(image=image)\n            image = augmented['image']\n            \n        label = self.labels.values[idx]\n        target = torch.zeros(N_CLASSES)\n        for cls in label.split():\n            target[int(cls)] = 1\n        \n        return image, target\n    \n\nclass TestDataset(Dataset):\n    def __init__(self, df, transform=None):\n        self.df = df\n        self.transform = transform\n        \n    def __len__(self):\n        return len(self.df)\n\n    def __getitem__(self, idx):\n        file_name = self.df['id'].values[idx]\n        file_path = f'../input/imet-2020-fgvc7/test/{file_name}.png'\n        image = cv2.imread(file_path)\n        image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n        \n        if self.transform:\n            augmented = self.transform(image=image)\n            image = augmented['image']\n        \n        return image","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Transforms"},{"metadata":{"trusted":true},"cell_type":"code","source":"HEIGHT = 128\nWIDTH = 128\n\n\ndef get_transforms(*, data):\n    \n    assert data in ('train', 'valid')\n    \n    if data == 'train':\n        return Compose([\n            #Resize(HEIGHT, WIDTH),\n            RandomResizedCrop(HEIGHT, WIDTH),\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(HEIGHT, WIDTH),\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":{},"cell_type":"markdown","source":"# Inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 128\n\ntest_dataset = TestDataset(submission, transform=get_transforms(data='valid'))\ntest_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.resnet18(pretrained=False)\nmodel.avgpool = nn.AdaptiveAvgPool2d(1)\nmodel.fc = nn.Linear(model.fc.in_features, N_CLASSES)\n\nweights_path = '../input/imet-2020-pytorch-resnet18-starter/fold0_best_score.pth'\nmodel.load_state_dict(torch.load(weights_path))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with open('../input/imet-2020-pytorch-resnet18-starter/train.log') as f:\n    s = f.read()\n    print(s)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with timer('inference'):\n    \n    model.to(device) \n    \n    preds = []\n    tk0 = tqdm(enumerate(test_loader), total=len(test_loader))\n\n    for i, images in tk0:\n            \n        images = images.to(device)\n            \n        with torch.no_grad():\n            y_preds = model(images)\n            \n        preds.append(torch.sigmoid(y_preds).to('cpu').numpy())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"threshold = 0.09\npredictions = np.concatenate(preds) > threshold\n\nfor i, row in enumerate(predictions):\n    ids = np.nonzero(row)[0]\n    submission.iloc[i].attribute_ids = ' '.join([str(x) for x in ids])\n    \nsubmission.to_csv('submission.csv', index=False)\nsubmission.head()","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.6"},"widgets":{"application/vnd.jupyter.widget-state+json":{"state":{"3152668ea8b74589b2a7123dccca5cbd":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"ProgressStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":"initial"}},"6fd44a996a19464f99110602a6db08b7":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"79a7f6b8f5914a688c09d843603e8bc8":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"FloatProgressModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"100%","description_tooltip":null,"layout":"IPY_MODEL_b66bcff488cd470c9bb25673405f2d82","max":46827520,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3152668ea8b74589b2a7123dccca5cbd","value":46827520}},"83e67fce80104b5a9383ec9c3196506a":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b66bcff488cd470c9bb25673405f2d82":{"model_module":"@jupyter-widgets/base","model_module_version":"1.2.0","model_name":"LayoutModel","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d5e26b2104c94d3e93c1579f9830e0c5":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HBoxModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_79a7f6b8f5914a688c09d843603e8bc8","IPY_MODEL_f52096278de8485f9182c22905489f44"],"layout":"IPY_MODEL_83e67fce80104b5a9383ec9c3196506a"}},"f52096278de8485f9182c22905489f44":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"HTMLModel","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_6fd44a996a19464f99110602a6db08b7","placeholder":"​","style":"IPY_MODEL_fdc2f0a4a2ad4377affda7d6294960c7","value":" 44.7M/44.7M [00:00<00:00, 70.6MB/s]"}},"fdc2f0a4a2ad4377affda7d6294960c7":{"model_module":"@jupyter-widgets/controls","model_module_version":"1.5.0","model_name":"DescriptionStyleModel","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}},"version_major":2,"version_minor":0}}},"nbformat":4,"nbformat_minor":4}