{"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\nimport os\nfor 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 20GB 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 zipfile\nimport os\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as train_z:\n    train_z.extractall('/kaggle/working/')\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as test_z:\n    test_z.extractall('/kaggle/working/')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir('/kaggle/working/'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#print(os.listdir('/kaggle/working/train'))\n\nfilenames = os.listdir('/kaggle/working/train')\ncategories = [filename.split('.')[0] for filename in filenames]\n\ntrain_df = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})\ntrain_df['label'] = np.where(train_df['category'] == 'cat', 1, 0)\ntrain_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir('/kaggle/working/test1')\ncategories = [filename.split('.')[0] for filename in filenames]\n\ntest_df = pd.DataFrame({\n    'filename': filenames,\n})\ntest_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from sklearn.model_selection import train_test_split\ntrain_df, val_df = train_test_split(train_df, test_size=0.2, random_state=42) \nprint('Train set shape: {}  Test set shape: {}'.format(train_df.shape, val_df.shape))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\n\nIMAGE_SIZE=(128, 128)\ntrain_data_gen = tf.keras.preprocessing.image.ImageDataGenerator(rotation_range=15, rescale=1./255, shear_range=0.1, zoom_range=0.2, horizontal_flip=True, width_shift_range=0.1, height_shift_range=0.1)\ntrain_generator = train_data_gen.flow_from_dataframe(train_df, '/kaggle/working/train/', x_col='filename', y_col='category', class_mode='categorical', target_size=IMAGE_SIZE, batch_size=32)\n\nval_data_gen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)\nval_generator = val_data_gen.flow_from_dataframe(val_df, '/kaggle/working/train/', x_col='filename', y_col='category', class_mode='categorical', target_size=IMAGE_SIZE, batch_size=32)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"network = tf.keras.models.Sequential([\n    tf.keras.layers.Conv2D(32, (3,3), activation=None),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Activation('relu'),\n    tf.keras.layers.MaxPooling2D((2,2)),\n    \n    tf.keras.layers.Conv2D(64, (3,3), activation=None),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Activation('relu'),\n    tf.keras.layers.MaxPooling2D((2,2)),\n    \n    tf.keras.layers.Conv2D(128, (3,3), activation=None),\n    tf.keras.layers.BatchNormalization(),\n    tf.keras.layers.Activation('relu'),\n    tf.keras.layers.MaxPooling2D((2,2)),\n    \n    tf.keras.layers.GlobalAveragePooling2D(),\n    tf.keras.layers.Dense(256, activation='relu'),\n    tf.keras.layers.Dropout(0.3),\n    tf.keras.layers.Dense(2, activation='softmax')\n])\nnetwork.build(input_shape=(None, 128, 128, 3))\nnetwork.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_NUM_EXAMPLES = 20000\nVAL_NUM_EXAMPLES = 5000","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"network.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\nlearning_rate_reduction = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_acc', patience=3, verbose=1, factor=0.5, min_lr=0.00001)\nhistory = network.fit_generator(generator=train_generator, validation_data=val_generator, epochs=10, callbacks=[learning_rate_reduction], steps_per_epoch=TRAIN_NUM_EXAMPLES//32, validation_steps=VAL_NUM_EXAMPLES//32)\nhistory.history","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_data_gen = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1./255)\ntest_generator = train_data_gen.flow_from_dataframe(test_df, '/kaggle/working/test1/', x_col='filename', y_col=None, class_mode=None, target_size=IMAGE_SIZE, batch_size=32)\npredictions = network.predict_generator(test_generator, steps=test_df.shape[0]//10)\ntest_df['category'] = np.argmax(predictions, axis=-1)\ntest_df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir('/kaggle/working/'))","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}