{"cells":[{"metadata":{"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 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":"print(os.listdir(\"../input/dogs-vs-cats-redux-kernels-edition/\"))","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import numpy as np\nimport tensorflow as tf\nimport pandas as pd\nimport seaborn as sns\nfrom sklearn.model_selection import train_test_split\nfrom tensorflow import keras\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Activation, Dense, Flatten, BatchNormalization, Conv2D, MaxPool2D\nfrom tensorflow.keras.optimizers import Adam\nfrom tensorflow.keras.metrics import categorical_crossentropy\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.metrics import confusion_matrix\nimport itertools\nimport os\nimport shutil\nimport random\nimport glob\nimport matplotlib.pyplot as plt\nimport warnings\nwarnings.simplefilter(action='ignore', category=FutureWarning)\n%matplotlib inline","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip -q ../input/dogs-vs-cats-redux-kernels-edition/train.zip","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip -q ../input/dogs-vs-cats-redux-kernels-edition/test.zip","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"/kaggle/working/test\")\nfor filename in filenames:\n    test_df = pd.DataFrame({\n    'filename': filenames\n})\n\ntest_df.index = test_df.index + 1\ntest_df.head()","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":"filenames = os.listdir(\"/kaggle/working/train\")\ncategories = []\nfor filename in filenames:\n    category = filename.split('.')[0]\n    if category == 'dog':\n        categories.append(1)\n    else:\n        categories.append(0)\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sns.countplot(df['category'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['category'] = df['category'].astype(str)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df, validate_df = train_test_split(df, test_size=0.1)\ntrain_df = train_df.reset_index()\nvalidate_df = validate_df.reset_index()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"total_train = train_df.shape[0]\ntotal_validate = validate_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(total_train)\nprint(total_validate)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_batches = ImageDataGenerator(\n    rotation_range=15,\n    rescale=1./255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\n    fill_mode='nearest',\n    width_shift_range=0.1,\n    height_shift_range=0.1) \\\n    .flow_from_dataframe(\n    train_df, \n    \"/kaggle/working/train\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary',\n    target_size=(224, 224),\n    batch_size=124)\n\nvalid_batches = ImageDataGenerator(rescale=1./255) \\\n    .flow_from_dataframe(\n    validate_df, \n    \"/kaggle/working/train\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary',\n    target_size=(224, 224),\n    batch_size=124)\n\ntest_batches = ImageDataGenerator(rescale=1./255) \\\n    .flow_from_dataframe(\n    test_df, \n    \"/kaggle/working/test\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    batch_size=124,\n    target_size=(224, 224),\n    shuffle=False\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"assert train_batches.n == 22500\nassert valid_batches.n == 2500","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imgs, labels = next(train_batches)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# This function will plot images in the form of a grid with 1 row and 10 columns where images are placed in each column.\ndef plotImages(images_arr):\n    fig, axes = plt.subplots(1, 10, figsize=(20,20))\n    axes = axes.flatten()\n    for img, ax in zip( images_arr, axes):\n        ax.imshow(img)\n        ax.axis('off')\n    plt.tight_layout()\n    plt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plotImages(imgs)\nprint(labels[0:10])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model= tf.keras.models.Sequential(\n    [tf.keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu', input_shape = (224,224,3)),\n     tf.keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu'),\n     tf.keras.layers.MaxPooling2D(2, 2),\n     tf.keras.layers.Dropout(.25),\n     tf.keras.layers.Conv2D(filters = 64, kernel_size = (3,3), activation = 'relu'),\n     tf.keras.layers.MaxPooling2D(2,2),\n     tf.keras.layers.Flatten(),\n     tf.keras.layers.Dense(128, activation='relu'),\n     tf.keras.layers.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(optimizer=Adam(learning_rate=0.0001),\n              loss='binary_crossentropy',\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x=train_batches,\n          steps_per_epoch=len(train_batches),\n          validation_data=valid_batches,\n          validation_steps=len(valid_batches),\n          epochs=2,\n          verbose=2\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Since accuracy is not that great, we will use a pre-trained model with transfer learning.","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"train_batches1 = ImageDataGenerator(preprocessing_function=tf.keras.applications.vgg16.preprocess_input) \\\n    .flow_from_dataframe(\n    train_df, \n    \"/kaggle/working/train\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary',\n    target_size=(224, 224),\n    batch_size=124)\n\nvalid_batches1 = ImageDataGenerator(preprocessing_function=tf.keras.applications.vgg16.preprocess_input) \\\n    .flow_from_dataframe(\n    validate_df, \n    \"/kaggle/working/train\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary',\n    target_size=(224, 224),\n    batch_size=124)\n\ntest_batches1 = ImageDataGenerator(preprocessing_function=tf.keras.applications.vgg16.preprocess_input) \\\n    .flow_from_dataframe(\n    test_df, \n    \"/kaggle/working/test\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    batch_size=124,\n    target_size=(224, 224),\n    shuffle=False\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"imgs, labels = next(train_batches1)\nplotImages(imgs)\nprint(labels[0:10])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg16_model = tf.keras.applications.vgg16.VGG16()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg16_model.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Removing the Last Layer","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nfor layer in vgg16_model.layers[:-1]:\n    model.add(layer)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for layer in model.layers:\n    layer.trainable = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.add(Dense(units=1, activation='sigmoid'))","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(optimizer=Adam(learning_rate=0.0001),\n              loss='binary_crossentropy',\n              metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.fit(x=train_batches1,\n          steps_per_epoch=len(train_batches1),\n          validation_data=valid_batches1,\n          validation_steps=len(valid_batches1),\n          epochs=3,\n          verbose=2)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Predict","execution_count":null},{"metadata":{"trusted":true},"cell_type":"code","source":"results = model.predict(test_batches)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['category'] = np.where(results > 0.5, 1,0)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"Submission","execution_count":null},{"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)\n","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}