{"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)\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\n# import os\n# for 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 5GB 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 sys\nsys.path.append('../input/mmtest/mmtest')\nimport torch\nimport pandas as pd\nfrom torch.utils.data import DataLoader\n\nfrom utils import Config\nfrom models import build_classifier\nfrom dataset import LandmarkDataset\nfrom tqdm import tqdm\nimport glob\nimport csv\n\ndef read_train_file(input_path):\n    df = pd.read_csv(input_path)\n    uniques = df['landmark_id'].unique()\n    df['label'] = df['landmark_id'].map(dict(zip(uniques, range(len(uniques)))))\n    return df, dict(zip(range(len(uniques)), uniques))\n\n\ncfg_path = '../input/mmtest/mmtest/configs/regnet80.py'\ncheckpoint_path = '../input/google-landmark-test-model/epoch_100.pth'\nimg_path = '../input/landmark-recognition-2020/test'\n_, mapping = read_train_file('../input/landmark-recognition-2020/train.csv')\n\ncfg = Config.fromfile(cfg_path)\nmodel = build_classifier(cfg.model)\nmodel.load_state_dict(torch.load(checkpoint_path)['state_dict'])\nmodel.eval()\nmodel.cuda()\ndataset = LandmarkDataset(img_path)\ndata_loader = DataLoader(dataset, batch_size=48, \n                          shuffle=False, num_workers=2)\n\nresults = []\nwith torch.no_grad():\n    for img in tqdm(data_loader):\n        img = img.cuda()\n        res = model(img, return_loss=False)\n        results.append(res)\n        # del res,img\n        # torch.cuda.empty_cache()\n\noutputs = torch.cat(results)\n\nsoftmax = torch.nn.Softmax(dim=1)\noutputs = softmax(outputs)\n\nconfs, preds = outputs.max(1)\n\nconfs = confs.cpu().numpy()\npreds = preds.cpu().numpy()\n\nwith open('submission.csv', 'w') as submission_csv:\n    csv_writer = csv.DictWriter(submission_csv, fieldnames=['id', 'landmarks'])\n    csv_writer.writeheader()\n    for image_path, lable, score in zip(dataset.file_path, preds, confs):\n        csv_writer.writerow({'id': image_path.split('/')[-1].split('.')[0], 'landmarks': f'{mapping[lable]} {score}'})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","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}