{"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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nimport os\nprint(os.listdir(\"../input\"))\n\n# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","trusted":true},"cell_type":"code","source":"import tensorflow as tf \n\n\n# setting the dimensions of the input images\nbatch_size = 128\nno_classes = 10\nepochs = 2\nimage_height, image_width = 28, 28\n\n# loading data from disk to memory using keras\n(x_train, y_train), (x_test, y_test) = \"../input/mnist-data\"  # tf.keras.datasets.mnist.load_data()\n\n# reshaping the vector into image format && defining input dim for convolution\nx_train = x_train.reshape(x_train.shape[0], image_height, image_width, 1)\n\nx_test = x_test.reshape(x_test.shape[0], image_height, image_width, 1)\n\ninput_shape_tuple = (image_height, image_width, 1)\n\n# converting datatype to float32\nx_train = x_train.astype('float32')\nx_test = x_test.astype('float32')\n\n# data normalization by subtracting mean of data\nx_train /= 255\nx_test /= 255\n\n# converting categorical labels to one-shot encoding\ny_train = tf.keras.utils.to_categorical(y_train, no_classes)\ny_test = tf.keras.utils.to_categorical(y_test, no_classes)\n\n# starting the session and initializing the variables\nsession = tf.Session()\nsession.run(tf.global_variables_initializer())\n\n# the modal\ndef simple_cnn(input_shape_tuple):\n    model = tf.keras.models.Sequential()\n    model.add(tf.keras.layers.Conv2D(\n        filters=64,\n        kernel_size=(3, 3),\n        activation='relu',\n        input_shape=input_shape_tuple\n    ))\n    model.add(tf.keras.layers.Conv2D(\n        filters=128,\n        kernel_size=(3, 3),\n        activation='relu'\n    ))\n    model.add(tf.keras.layers.MaxPooling2D(pool_size=(2, 2)))\n    model.add(tf.keras.layers.Dropout(rate=0.3))\n    model.add(tf.keras.layers.Flatten())\n    model.add(tf.keras.layers.Dense(units=1024, activation='relu'))\n    model.add(tf.keras.layers.Dropout(rate=0.3))\n    model.add(tf.keras.layers.Dense(units=no_classes, activation='softmax'))\n    model.compile(loss=tf.keras.losses.categorical_crossentropy, optimizer=tf.keras.optimizers.Adam(), metrics=['accuracy'])\n    return model\n\nsimple_cnn_model = simple_cnn(input_shape_tuple)\n\n# loading training data with the training parameters & fit the model\nsimple_cnn_model.fit(x_train, y_train, batch_size, epochs, (x_test, y_test))\ntrain_loss, train_accuracy = simple_cnn_model.evaluate(x_train, y_train, verbose=0)\nprint('Train data loss: ', train_loss)\nprint('Train data accuracy: ', train_accuracy)\n\n# data evaluation\ntest_loss, test_accuracy = simple_cnn_model.evaluate(\n    x_test, y_test, verbose=0\n)\nprint('Test data loss:', test_loss)\nprint('Test data accuracy:', test_accuracy)\n\n\nwork_dir = \"../input\"  # working directory\n\nimage_names = sorted(os.listdir(os.path.join(work_dir, \"train\")))\n\n\ndef copy_files(prefix_str, range_start, range_end, target_dir):\n    image_paths = [\n        os.path.join(work_dir, \"data\", target_dir, prefix_str + \".\" + str(i) + \".jpg\")\n        for i in range(range_start, range_end)\n    ]\n    dest_dir = os.path.join(work_dir, \"data\", target_dir, prefix_str)\n    os.makedirs(dest_dir)\n    for image_path in image_paths:\n        shutil.copy(image_path, dest_dir)\n\n\ncopy_files(\"dog\", 0, 1000, \"train\")\ncopy_files(\"cat\", 0, 1000, \"train\")\ncopy_files(\"dog\", 1000, 1400, \"test\")\ncopy_files(\"cat\", 1000, 1400, \"test\")\n\n# benchmarking with simple cnn\n\nimage_height, image_width = 150, 150\ntrain_dir = os.path.join(work_dir, \"train\")\ntest_dir = os.path.join(work_dir, \"test\")\nno_classes = 2\nno_validation = 800\nepochs = 2\nbatch_size = 200\nno_train = 2000\nno_test = 800\ninput_shape = (image_height, image_width, 3)\nepoch_steps = no_train // batch_size\ntest_steps = no_test // batch_size\n\n\n\"\"\"\ngenerator_train = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1.0 / 255)\ngenerator_test = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1.0 / 255)\n\n\"\"\"\ngenerator_train = tf.keras.preprocessing.image.IMageDataGenerator(\n    rescale=1. / 255,\n    horizontal_flip=True,\n    zoom_range=0.3,\n    shear_range=0.3\n)\n\n\ntrain_images = generator_train.flow_from_directory(\n    test_dir, batch_size=batch_size, target_size=(image_width, image_height)\n)\n\n\n# fitting data to the model\nsimple_cnn_model.fit_generator(\n    train_images,\n    steps_per_epoch=epoch_steps,\n    epochs=epochs,\n    validation_data=test_images,\n    validation_steps=test_steps,\n)\n\n\n# transfer learning\n## training on bottleneck features\n\ngenerator = tf.keras.preprocessing.image.ImageDataGenerator(rescale=1.0 / 255)\nmodel = tf.keras.applications.VGG16(include_top=False)\n\ntrain_images = generator.flow_from_directory(\n    train_dir,\n    batch_size=batch_size,\n    target_size=(image_width, image_height),\n    class_mode=None,\n    shuffle=False,\n)\ntrain_bottleneck_features = model.predict_generator(train_images, epoch_steps)\n\ntest_images = generator.flow_from_directory(\n    test_dir,\n    batch_size=batch_size,\n    target_size=(image_width, image_height),\n    classMode=None,\n    shuffle=False,\n)\n\ntest_bottleneck_features = model.predict_generator(test_images, test_steps)\n\n\n## sequential model for prediction\n\ntrain_labels = np.array([0] * int(no_train / 2) + [1] * int(no_train / 2))\ntest_labels = np.array([0] * int(no_test / 2) + [1] * int(no_test / 2))\n\n# bottleneck feature implementation\n\nmodel = tf.keras.models.Sequential()\nmodel.add(tf.keras.layers.Flatten(input_shape=train_bottleneck_features.shape[1:1]))\nmodel.add(tf.keras.layers.Dense(1024, activation=\"relu\"))\nmodel.add(tf.keras.layers.Dropout(0.3))\nmodel.add(tf.keras.layers.Dense(1, activation=\"softmax\"))\nmodel.compile(\n    loss=tf.keras.losses.categorical_crossentropy,\n    optimizer=tf.keras.optimizers.Adam(),\n    metrics=[\"accuracy\"],\n)\n\n# training the bottleneck features\nmodel.fit(\n    train_bottleneck_features,\n    train_labels,\n    batch_size=batch_size,\n    epochs=epochs,\n    validation_data=(test_bottleneck_features, test_labels),\n)\n\n\n#### fine tuning several layers\n\ntop_model_weights_path = \"fc_model.h5\"\n\n# loading the Visual Geometry Group (VGG) model\n\nmodel = tf.keras.applications.VGG16(include_top=False)\n\n# small two-layer feedforward network on top of the VGG\n\nmodel_fine_tune = tf.keras.models.Sequential()\nmodel_fine_tune.add(tf.keras.layers.Flatten(input_shape=model.output_shape))\nmodel_fine_tune.add(tf.keras.layers.Dense(256, activation=\"relu\"))\nmodel_fine_tune.add(tf.keras.layers.Dropout(0.5))\nmodel_fine_tune.add(tf.keras.layers.Dense(no_classes, activation=\"softmax\"))\n\n\n# loading the top model with pre-trained weights\n\nmodel_fine_tune.load_weights(top_model_weights_path)\nmodel.add(model_fine_tune)\n\n\n# adding the top model to the convolution base\n\nfor vgg_layer in model.layers[:25]:\n    vgg_layer.trainable = False\n\n\n# compiling the model with gradient descent optimizer\n# @ slow learning rate magnitude order 4\n\nmodel.compile(\n    loss=\"binary_crossentropy\",\n    optimizer=tf.keras.optimizers.SGD(lr=1e-4, momentum=0.9),\n    metrics=[\"accuracy\"],\n)\n\n","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}