{"cells":[{"metadata":{},"cell_type":"markdown","source":"# About this notebook\n- PyTorch Resnet18 starter code\n- [train kernel](https://www.kaggle.com/yasufuminakama/herbarium-2020-pytorch-resnet18-train) -> inference kernel\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/herbarium-2020-fgvc7')","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Data Loading"},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\nwith open('../input/herbarium-2020-fgvc7/nybg2020/train/metadata.json', \"r\", encoding=\"ISO-8859-1\") as file:\n    train = json.load(file)\n\ntrain_img = pd.DataFrame(train['images'])\ntrain_ann = pd.DataFrame(train['annotations']).drop(columns='image_id')\ntrain_df = train_img.merge(train_ann, on='id')\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\n\nwith open('../input/herbarium-2020-fgvc7/nybg2020/test/metadata.json', \"r\", encoding=\"ISO-8859-1\") as file:\n    test = json.load(file)\n\ntest_df = pd.DataFrame(test['images'])\ntest_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_submission = pd.read_csv('../input/herbarium-2020-fgvc7/sample_submission.csv')\nsample_submission.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# TARGET (\"category_id\")"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df['category_id'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"- imbalance\n- 32093 targets"},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn import preprocessing\n\nle = preprocessing.LabelEncoder()\nle.fit(train_df['category_id'])\ntrain_df['category_id_le'] = le.transform(train_df['category_id'])\nclass_map = dict(sorted(train_df[['category_id_le', 'category_id']].values.tolist()))","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\n\nimport cv2\nfrom PIL import Image\nimport numpy as np\nimport pandas as pd\nimport scipy as sp\n\nimport sklearn.metrics\n\nfrom functools import partial\n\nimport torch\nimport torch.nn as nn\nfrom torch.optim import Adam, SGD\nfrom torch.optim.lr_scheduler import CosineAnnealingLR\nfrom torch.utils.data import DataLoader, Dataset\n\nfrom albumentations import Compose, Normalize, Resize\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 = 32093\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['file_name'].values[idx]\n        file_path = f'../input/herbarium-2020-fgvc7/nybg2020/test/{file_name}'\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():\n    \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        ])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"batch_size = 512\n\ntest_dataset = TestDataset(test_df, transform=get_transforms())\ntest_loader = DataLoader(test_dataset, batch_size=batch_size, shuffle=False)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"import torchvision.models as models\n\nmodel = models.resnet18(pretrained=False)\nmodel.avgpool = nn.AdaptiveAvgPool2d(1)\nmodel.fc = nn.Linear(model.fc.in_features, N_CLASSES)\n\nweights_path = '../input/herbarium-2020-pytorch-resnet18-train/fold0_best_score.pth'\nmodel.load_state_dict(torch.load(weights_path))","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Inference"},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm\n\nwith timer('inference'):\n    \n    model.to(device) \n    \n    preds = np.zeros((len(test_dataset)))\n\n    for i, images in tqdm(enumerate(test_loader)):\n            \n        images = images.to(device)\n            \n        with torch.no_grad():\n            y_preds = model(images)\n            \n        preds[i * batch_size: (i+1) * batch_size] = y_preds.argmax(1).to('cpu').numpy()\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# Submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['preds'] = preds.astype(int)\nsubmission = sample_submission.merge(test_df.rename(columns={'id': 'Id'})[['Id', 'preds']], on='Id').drop(columns='Predicted')\nsubmission['Predicted'] = submission['preds'].map(class_map)\nsubmission = submission.drop(columns='preds')\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":{"0106678c48224879ba1132331a1cd15f":{"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}},"023370e659304ffcabe5fa7074e4ef34":{"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_cef9441d4b4d4587b281c2622524ea11","IPY_MODEL_13deae7fa1004aa0a74232c8c8146b96"],"layout":"IPY_MODEL_0106678c48224879ba1132331a1cd15f"}},"13deae7fa1004aa0a74232c8c8146b96":{"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_383a09bde2084fd2bafe7927d9a6fbc8","placeholder":"​","style":"IPY_MODEL_4610ea4209d4447ea54fd13baa2f5a35","value":" 44.7M/44.7M [00:14<00:00, 3.31MB/s]"}},"2699f1aa18514de2b53c97ab29ac06e3":{"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}},"383a09bde2084fd2bafe7927d9a6fbc8":{"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}},"3f70667c52244a0cbb8d7a294818a99a":{"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"}},"4610ea4209d4447ea54fd13baa2f5a35":{"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":""}},"cef9441d4b4d4587b281c2622524ea11":{"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_2699f1aa18514de2b53c97ab29ac06e3","max":46827520,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3f70667c52244a0cbb8d7a294818a99a","value":46827520}}},"version_major":2,"version_minor":0}}},"nbformat":4,"nbformat_minor":4}