{"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\nimport numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport tensorflow as tf\n\nimport tensorflow.keras as keras\nimport tensorflow.keras.layers as layers\nfrom keras.preprocessing.image import ImageDataGenerator\nimport matplotlib.pyplot as plt\nimport cv2\nfrom random import randint\nimport tensorflow.keras.layers.experimental.preprocessing as preprocessing\nimport os, warnings\nimport matplotlib.pyplot as plt\nfrom matplotlib import gridspec\nfrom PIL import Image\nimport seaborn as sns\n\ndef plotImages( images_arr, n_images=4):\n    fig, axes = plt.subplots(n_images, n_images, figsize=(12,12))\n    axes = axes.flatten()\n    for img, ax in zip( images_arr, axes):\n        if img.ndim != 2:\n            img = img.reshape( (SIZE,SIZE))\n        ax.imshow( img, cmap=\"Greys_r\")\n        ax.set_xticks(())\n        ax.set_yticks(())\n    plt.tight_layout()\n\n\n\ndatagen = ImageDataGenerator(validation_split=0.2)#rescale=1./255,\n\n\n# Set Matplotlib defaults\nplt.rc('figure', autolayout=True)\nplt.rc('axes', labelweight='bold', labelsize='large',\n       titleweight='bold', titlesize=18, titlepad=10)\nplt.rc('image', cmap='magma')\nwarnings.filterwarnings(\"ignore\") # to clean up output cells\n\n\n#Exploring the data \ntrain_path = \"../input/state-farm-distracted-driver-detection/imgs/train/\"\ntest_path = \"../input/state-farm-distracted-driver-detection/imgs/test/\"\n\n# VISUALIZATION\ncategory_names = os.listdir(train_path)\nnb_categories = len(category_names) \ntrain_images = []\n\nfig, axs = plt.subplots(ncols=1)\n\nfor category in category_names:\n    folder = train_path + \"/\" + category\n    train_images.append(len(os.listdir(folder)))\n\nsns.barplot( y=category_names, x=train_images).set_title(\"Number Of Training Images Per Category\");\n\n\n# Load training and validation sets\ntrain_generator = datagen.flow_from_directory(\n    train_path,\n    class_mode='categorical',\n    target_size=(150, 150),\n    interpolation='nearest',\n    batch_size=64,\n    shuffle=True,\n    subset='training'\n)\nvalidation_generator = datagen.flow_from_directory(\n    train_path,\n    class_mode='categorical',\n    target_size=(150, 150),\n    interpolation='nearest',\n    batch_size=64,\n    shuffle=False,\n    subset='validation'\n)\n\ntest_generator = datagen.flow_from_directory(\n    test_path,\n    class_mode='categorical',\n    target_size=(150, 150),\n    interpolation='nearest',\n    batch_size=64,\n    shuffle=False,\n)\n\n\n#model intialise \nmodel = keras.Sequential([\n    layers.InputLayer(input_shape=[150,150, 3]),\n    \n    #preprocessing.RandomContrast(factor=0.5),\n    #preprocessing.RandomFlip(mode='horizontal'), # meaning, left-to-right\n    #preprocessing.RandomContrast(factor=0.5),\n    #preprocessing.RandomTranslation(height_factor=0.1, width_factor=0.1),\n\n    #preprocessing.RandomWidth(factor=0.15), # horizontal stretch\n\n    # Block One\n    layers.BatchNormalization(renorm=True),\n    layers.Conv2D(filters=64, kernel_size=3, activation='relu', padding='same'),\n    layers.Dropout(0.3),\n    layers.MaxPool2D(),\n\n    # Block Two\n    layers.BatchNormalization(renorm=True),\n    layers.Conv2D(filters=128, kernel_size=3, activation='relu', padding='same'),\n    layers.Dropout(0.3),\n    layers.MaxPool2D(),\n\n    # Block Three\n    layers.BatchNormalization(renorm=True),\n    layers.Conv2D(filters=256, kernel_size=3, activation='relu', padding='same'),\n    layers.Dropout(0.3),\n    layers.Conv2D(filters=256, kernel_size=3, activation='relu', padding='same'),\n    layers.MaxPool2D(),\n    \n    # Block Four\n    layers.BatchNormalization(renorm=True),\n    layers.Conv2D(filters=256, kernel_size=3, activation='relu', padding='same'),\n    layers.Dropout(0.3),\n    layers.Conv2D(filters=256, kernel_size=3, activation='relu', padding='same'),\n    layers.MaxPool2D(),\n    # Head\n    layers.BatchNormalization(renorm=True),\n    layers.Flatten(),\n    layers.Dense(10, activation='softmax'),\n])\n\n#compile model\noptimizer = tf.keras.optimizers.Adam(epsilon=0.01)\nmodel.compile(\n    optimizer=optimizer,\n    loss='categorical_crossentropy',\n    metrics=['categorical_accuracy'],\n)\n\nhistory = model.fit(\n    train_generator,\n    validation_data=validation_generator,\n    epochs=3,\n)\n\n\n# Plot learning curves\nimport pandas as pd\nhistory_frame = pd.DataFrame(history.history)\nhistory_frame.loc[:, ['loss', 'val_loss']].plot()\nhistory_frame.loc[:, ['categorical_accuracy', 'val_categorical_accuracy']].plot();\n","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","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}