{"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 shutil","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"with zipfile.ZipFile('/kaggle/input/dogs-vs-cats/train.zip', 'r') as zip_ref:\n    zip_ref.extractall('./')\nwith zipfile.ZipFile('/kaggle/input/dogs-vs-cats/test1.zip', 'r') as zip_ref:\n    zip_ref.extractall('./')\n#shutil.rmtree('./dogs-vs-cats')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"try:\n    root_dir = './'\n    source_dir = os.path.join(root_dir, 'train')\n    test_dir = os.path.join(root_dir, 'test1')\n\n    os.mkdir(os.path.join(source_dir, 'train'))\n    os.mkdir(os.path.join(source_dir, 'validate'))\n\n    train_dir = os.path.join(source_dir, 'train')\n    validate_dir = os.path.join(source_dir, 'validate')\n\n\n    os.mkdir(os.path.join(train_dir, 'dogs'))\n    os.mkdir(os.path.join(train_dir, 'cats'))\n    os.mkdir(os.path.join(validate_dir, 'dogs'))\n    os.mkdir(os.path.join(validate_dir, 'cats'))\n\n    train_dogs_dir = os.path.join(train_dir, 'dogs')\n    train_cats_dir = os.path.join(train_dir, 'cats')\n    validate_dogs_dir = os.path.join(validate_dir, 'dogs')\n    validate_cats_dir = os.path.join(validate_dir, 'cats')\nexcept:\n    pass","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"root_dir = './'\nsource_dir = os.path.join(root_dir, 'train')\ntest_dir = os.path.join(root_dir, 'test1')\ntrain_dir = os.path.join(source_dir, 'train')\nvalidate_dir = os.path.join(source_dir, 'validate')\ntrain_dogs_dir = os.path.join(train_dir, 'dogs')\ntrain_cats_dir = os.path.join(train_dir, 'cats')\nvalidate_dogs_dir = os.path.join(validate_dir, 'dogs')\nvalidate_cats_dir = os.path.join(validate_dir, 'cats')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"all_files_in_train = os.listdir(source_dir)\nall_files_in_test = os.listdir(test_dir)\n\nall_cats_in_train = [x for x in all_files_in_train if x[:3]=='cat']\nall_dogs_in_train = [x for x in all_files_in_train if x[:3]=='dog']\n\nprint(len(all_files_in_train), len(all_cats_in_train)+len(all_dogs_in_train))\n\nsplit = 0.9\n\nnp.random.shuffle(all_cats_in_train)\ncats_valid_number = int(len(all_cats_in_train)*split)\ntrain_cats = all_cats_in_train[:cats_valid_number]\nvalid_cats = all_cats_in_train[cats_valid_number:]\nprint(len(all_cats_in_train), len(train_cats)+len(valid_cats), len(train_cats), len(valid_cats))\n\nnp.random.shuffle(all_dogs_in_train)\ndogs_valid_number = int(len(all_dogs_in_train)*split)\ntrain_dogs = all_dogs_in_train[:dogs_valid_number]\nvalid_dogs = all_dogs_in_train[dogs_valid_number:]\nprint(len(all_dogs_in_train), len(train_dogs)+len(valid_dogs), len(train_dogs), len(valid_dogs))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for cat in train_cats:\n    try:\n        os.replace(os.path.join(source_dir, cat), os.path.join(train_cats_dir, cat))\n    except:\n        pass\nprint(len(os.listdir(train_cats_dir)))\n\nfor cat in valid_cats:\n    try:\n        os.replace(os.path.join(source_dir, cat), os.path.join(validate_cats_dir, cat))\n    except:\n        pass\nprint(len(os.listdir(validate_cats_dir)))\n\nfor dog in train_dogs:\n    try:\n        os.replace(os.path.join(source_dir, dog), os.path.join(train_dogs_dir, dog))\n    except:\n        pass\nprint(len(os.listdir(train_dogs_dir)))\n\nfor dog in valid_dogs:\n    try:\n        os.replace(os.path.join(source_dir, dog), os.path.join(validate_dogs_dir, dog))\n    except:\n        pass\nprint(len(os.listdir(validate_dogs_dir)))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras import Sequential\nfrom tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.optimizers import RMSprop","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rescale=1./255)\nvalid_datagen = ImageDataGenerator(rescale=1./255)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator = train_datagen.flow_from_directory(\n    train_dir,\n    target_size=(150,150),\n    batch_size=50,\n    class_mode='binary'\n)\n\nvalid_generator = valid_datagen.flow_from_directory(\n    validate_dir,\n    target_size=(150,150),\n    batch_size=50,\n    class_mode='binary'\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential([\n    Conv2D(16, (3,3), input_shape=(150,150,3), activation='relu'),\n    MaxPooling2D((2,2)),\n    Conv2D(32, (3,3), activation='relu'),\n    MaxPooling2D((2,2)),\n    Conv2D(64, (3,3), activation='relu'),\n    MaxPooling2D((2,2)),\n    Flatten(),\n    Dense(512, activation='relu'),\n    Dense(1, activation='sigmoid')\n])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(\n    optimizer=RMSprop(learning_rate=0.001),\n    loss='binary_crossentropy',\n    metrics=['accuracy']\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit(\n    train_generator,\n    steps_per_epoch=100,\n    epochs=15,\n    validation_steps=50,\n    validation_data=valid_generator\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.preprocessing.image import load_img, img_to_array","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"file = os.listdir(train_dogs_dir)[0]\npath = os.path.join(train_dogs_dir, file)\nimg = load_img(path, target_size=(150,150))\nx = img_to_array(img)\nx = x/255.\nx = x.reshape(1,150,150,3)\nmodel.predict(x)[0][0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tqdm import tqdm","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predicts = []\nids = []\nfor file in tqdm(os.listdir(test_dir)):\n    path = os.path.join(test_dir, file)\n    img = load_img(path, target_size=(150,150))\n    \n    ids.append(file.split('.')[0])\n    \n    x = img_to_array(img)\n    x = x.reshape(1,150,150,3)\n    \n    predict = model.predict(x)[0][0]\n    \n    if predict > 0.5:\n        predicts.append(1)\n    else:\n        predicts.append(0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"d = {'id':ids, 'label':predicts}\nsubmit = pd.DataFrame(d)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submit.to_csv('submission.csv')","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}