{"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":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.applications import MobileNetV2\nfrom keras.utils import to_categorical\nfrom keras.layers import Dense\nfrom keras import Model\nfrom keras.callbacks import ModelCheckpoint\nfrom keras.models import load_model","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"train = pd.read_csv(\"/kaggle/input/landmark-recognition-2020/train.csv\")\ntrain[\"filename\"] = train.id.str[0]+\"/\"+train.id.str[1]+\"/\"+train.id.str[2]+\"/\"+train.id+\".jpg\"\ntrain[\"label\"] = train.landmark_id.astype(str)\ntrain","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sub = pd.read_csv(\"/kaggle/input/landmark-recognition-2020/sample_submission.csv\")\nsub[\"filename\"] = sub.id.str[0]+\"/\"+sub.id.str[1]+\"/\"+sub.id.str[2]+\"/\"+sub.id+\".jpg\"\nsub","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y = train.landmark_id.values\nn_classes = np.max(y)\nprint(n_classes)\nplt.hist(y)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from collections import Counter\ncount = Counter(y).most_common(1000)\nprint(len(count), count[-1])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# only keep 10000 classes\nkeep_labels = [c[0] for c in count]\ntrain_keep = train[train.landmark_id.isin(keep_labels)]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_rate = 0.3\nbatch_size = 32","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"gen = ImageDataGenerator(validation_split=val_rate)\n\ntrain_gen = gen.flow_from_dataframe(\n    train_keep,\n    directory=\"/kaggle/input/landmark-recognition-2020/train/\",\n    x_col=\"filename\",\n    y_col=\"label\",\n    weight_col=None,\n    target_size=(256, 256),\n    color_mode=\"rgb\",\n    classes=None,\n    class_mode=\"categorical\",\n    batch_size=batch_size,\n    shuffle=True,\n    subset=\"training\",\n    interpolation=\"nearest\",\n    validate_filenames=False)\n    \nval_gen = gen.flow_from_dataframe(\n    train_keep,\n    directory=\"/kaggle/input/landmark-recognition-2020/train/\",\n    x_col=\"filename\",\n    y_col=\"label\",\n    weight_col=None,\n    target_size=(256, 256),\n    color_mode=\"rgb\",\n    classes=None,\n    class_mode=\"categorical\",\n    batch_size=batch_size,\n    shuffle=True,\n    subset=\"validation\",\n    interpolation=\"nearest\",\n    validate_filenames=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model  = load_model(\"/kaggle/input/common-keras-pretrained-models/MobileNetV2.h5\")\nfor i in range(len(model.layers)-1):\n    model.layers[i].trainable = False\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(optimizer=\"adam\", loss=\"categorical_crossentropy\", metrics=[\"categorical_accuracy\"])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# training parameters\nepochs = 5 # maximum number of epochs\ntrain_steps = int(len(train_keep)*(1-val_rate))//batch_size\nval_steps = int(len(train_keep)*val_rate)//batch_size","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model_checkpoint = ModelCheckpoint(\"best_model.h5\", save_best_only=True, verbose=1)\n\nhistory = model.fit_generator(train_gen, steps_per_epoch=train_steps, epochs=epochs,\n                              validation_data=val_gen, validation_steps=val_steps, callbacks=[model_checkpoint])\n\nmodel.save(\"model.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import load_model\nbest_model = load_model(\"best_model.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_gen = ImageDataGenerator().flow_from_dataframe(\n    sub,\n    directory=\"/kaggle/input/landmark-recognition-2020/test/\",\n    x_col=\"filename\",\n    y_col=None,\n    weight_col=None,\n    target_size=(256, 256),\n    color_mode=\"rgb\",\n    classes=None,\n    class_mode=None,\n    batch_size=1,\n    shuffle=True,\n    subset=None,\n    interpolation=\"nearest\",\n    validate_filenames=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(\"Predicting on all available data...\")\ny_pred_one_hot = best_model.predict_generator(test_gen, verbose=1, steps=len(sub))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_pred = np.argmax(y_pred_one_hot, axis=-1)\ny_prob = np.max(y_pred_one_hot, axis=-1)\nprint(y_pred.shape, y_prob.shape)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"y_uniq = np.unique(train_keep.landmark_id.values)\nprint(y_uniq)\ny_pred = [y_uniq[Y] for Y in y_pred]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for i in range(len(sub)):\n    sub.loc[i, \"landmarks\"] = str(y_pred[i])+\" \"+str(y_prob[i])\nsub = sub.drop(columns=\"filename\")\nsub.to_csv(\"submission.csv\", index=False)\nsub","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}