{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import tensorflow as tf\n\nclass ResnetIdentityBlock(tf.keras.Model):\n  def __init__(self, kernel_size, filters, batch_normalization=True, conv_first=False):\n    super(ResnetIdentityBlock, self).__init__(name='')\n    \n    self.residual_layers = []\n    \n    for i in range(len(filters)):\n        \n        if conv_first:\n            setattr(self, 'conv' + str(i+1), tf.keras.layers.Conv2D(filters[i], kernel_size, padding='same'))\n            self.residual_layers.append('conv' + str(i+1))\n\n            if batch_normalization:\n                setattr(self, 'bn' + str(i+1), tf.keras.layers.BatchNormalization())\n                self.residual_layers.append('bn' + str(i+1))\n        \n        else:\n            if batch_normalization:\n                setattr(self, 'bn' + str(i+1), tf.keras.layers.BatchNormalization())\n                self.residual_layers.append('bn' + str(i+1))\n            \n            setattr(self, 'conv' + str(i+1), tf.keras.layers.Conv2D(filters[i], kernel_size, padding='same'))\n            self.residual_layers.append('conv' + str(i+1))\n\n            \n            \n  def call(self, input_tensor, training=False):\n    \n    x = input_tensor\n    \n    for layer in self.residual_layers:\n        if isinstance(layer, tf.keras.layers.Conv2D):\n            x = getattr(self, layer)(x)\n        else: \n            x = getattr(self, layer)(x, training=False)\n        x = tf.nn.relu(x)\n        \n    x += input_tensor\n    return tf.nn.relu(x)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.datasets import cifar10\n\n(x_train,y_train),(x_test,y_test) = cifar10.load_data() \n\nx_train = x_train /255\nx_test = x_test / 255","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.utils.np_utils import to_categorical   \n\ny_train = to_categorical(y_train, num_classes=10)\ny_test = to_categorical(y_test, num_classes=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\n\nimport tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"datagen = ImageDataGenerator(\n        # set input mean to 0 over the dataset\n        featurewise_center=False,\n        # set each sample mean to 0\n        samplewise_center=False,\n        # divide inputs by std of dataset\n        featurewise_std_normalization=False,\n        # divide each input by its std\n        samplewise_std_normalization=False,\n        # apply ZCA whitening\n        zca_whitening=False,\n        # epsilon for ZCA whitening\n        zca_epsilon=1e-06,\n        # randomly rotate images in the range (deg 0 to 180)\n        rotation_range=5,\n        # randomly shift images horizontally\n        width_shift_range=0.1,\n        # randomly shift images vertically\n        height_shift_range=0.1,\n        # set range for random shear\n        shear_range=0.,\n        # set range for random zoom\n        zoom_range=0.,\n        # set range for random channel shifts\n        channel_shift_range=0.,\n        # set mode for filling points outside the input boundaries\n        fill_mode='nearest',\n        # value used for fill_mode = \"constant\"\n        cval=0.,\n        # randomly flip images\n        horizontal_flip=True,\n        # randomly flip images\n        vertical_flip=False,\n        # set rescaling factor (applied before any other transformation)\n        rescale=None,\n        # set function that will be applied on each input\n        preprocessing_function=None,\n        # image data format, either \"channels_first\" or \"channels_last\"\n        data_format=None,\n        # fraction of images reserved for validation (strictly between 0 and 1)\n        validation_split=0.05)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"NUM_CLASSES = 10\nINPUT_SHAPE = (32, 32, 3)\n\nNUM_EPOCHS = 80\nlearning_rate = 1e-4\nBATCH_SIZE=128","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = tf.keras.Sequential()\nmodel.add(tf.keras.layers.Conv2D(128, (3, 3), activation='relu', input_shape=INPUT_SHAPE))\n\nmodel.add(ResnetIdentityBlock((3,3), filters=(128, 128)))\nmodel.add(ResnetIdentityBlock((3,3), filters=(128, 128)))\nmodel.add(ResnetIdentityBlock((3,3), filters=(128, 128)))\nmodel.add(tf.keras.layers.Conv2D(64, (3, 3), padding='same'))\n\nmodel.add(ResnetIdentityBlock((3,3), filters=(64, 64)))\nmodel.add(ResnetIdentityBlock((3,3), filters=(64, 64)))\nmodel.add(ResnetIdentityBlock((3,3), filters=(64, 64)))\n\nmodel.add(tf.keras.layers.BatchNormalization())\nmodel.add(tf.keras.layers.Activation('relu'))\nmodel.add(tf.keras.layers.AveragePooling2D(pool_size=8))\nmodel.add(tf.keras.layers.Flatten())\n\nmodel.add(tf.keras.layers.Dense(NUM_CLASSES, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.summary()\n\ndatagen.fit(x_train)\n\nsgd = tf.keras.optimizers.Adam(learning_rate)\n\nmodel.compile(optimizer=sgd,\n              loss='categorical_crossentropy',\n              metrics=['accuracy'])\n\nmodel.fit_generator(datagen.flow(x_train, y_train, batch_size=BATCH_SIZE),\n                    validation_data=(x_test, y_test),\n                    epochs=NUM_EPOCHS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history1 = model.history.history\n\n# summarize history for accuracy\nplt.plot(history1['accuracy'])\nplt.plot(history1['val_accuracy'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()\n\n# summarize history for loss\nplt.plot(history1['loss'])\nplt.plot(history1['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mode = tf.keras.Sequential()\nmode.add(tf.keras.layers.Conv2D(256, (3, 3), activation='relu', input_shape=INPUT_SHAPE))\n\nmode.add(ResnetIdentityBlock((3,3), filters=(256, 256)))\nmode.add(ResnetIdentityBlock((3,3), filters=(256, 256)))\nmode.add(ResnetIdentityBlock((3,3), filters=(256, 256)))\nmode.add(tf.keras.layers.Conv2D(128, (3, 3), padding='same'))\n\n\nmode.add(ResnetIdentityBlock((3,3), filters=(128, 128)))\nmode.add(ResnetIdentityBlock((3,3), filters=(128, 128)))\nmode.add(ResnetIdentityBlock((3,3), filters=(128, 128)))\nmode.add(tf.keras.layers.Conv2D(64, (3, 3), padding='same'))\n\nmode.add(ResnetIdentityBlock((3,3), filters=(64, 64)))\nmode.add(ResnetIdentityBlock((3,3), filters=(64, 64)))\nmode.add(ResnetIdentityBlock((3,3), filters=(64, 64)))\n\nmode.add(tf.keras.layers.BatchNormalization())\nmode.add(tf.keras.layers.Activation('relu'))\nmode.add(tf.keras.layers.AveragePooling2D(pool_size=8))\nmode.add(tf.keras.layers.Flatten())\n\nmode.add(tf.keras.layers.Dense(NUM_CLASSES, activation='softmax'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"mode.summary()\n\ndatagen.fit(x_train)\n\nsgd = tf.keras.optimizers.Adam(learning_rate)\n\nmode.compile(optimizer=sgd,\n              loss='categorical_crossentropy',\n              metrics=['accuracy'])\n\nmode.fit_generator(datagen.flow(x_train, y_train, batch_size=BATCH_SIZE),\n                    validation_data=(x_test, y_test),\n                    epochs=NUM_EPOCHS)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = mode.history.history\n\n# summarize history for accuracy\nplt.plot(history['accuracy'])\nplt.plot(history['val_accuracy'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()\n\n# summarize history for loss\nplt.plot(history['loss'])\nplt.plot(history['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"#VGG16 MODEL","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np\nfrom tensorflow.keras.applications.vgg16 import VGG16\nimport tensorflow.keras as k\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Flatten, Dropout\nfrom keras.utils.np_utils import to_categorical\nfrom tensorflow.keras import optimizers\nfrom tensorflow.keras.callbacks import ModelCheckpoint, EarlyStopping\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom sklearn.metrics import accuracy_score\n\nvgg16_model = VGG16(weights='imagenet',\n                    include_top=False, \n                    classes=10,\n                    input_shape=(32,32,3)# input: 32x32 images with 3 channels -> (32, 32, 3) tensors.\n                   )","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model1 = Sequential()\nfor layer in vgg16_model.layers:\n    model1.add(layer)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow.keras.layers import Dense, Flatten, Dropout\nmodel1.add(Flatten())\nmodel1.add(Dense(512, activation='relu', name='hidden1'))\nmodel1.add(Dropout(0.4))\nmodel1.add(Dense(256, activation='relu', name='hidden2'))\nmodel1.add(Dropout(0.4))\nmodel1.add(Dense(10, activation='softmax', name='predictions'))\n\nmodel1.summary()\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sgd = optimizers.SGD(lr=0.001, momentum=0.9)\n\n# For a multi-class classification problem\nmodel1.compile(loss='categorical_crossentropy',optimizer= sgd,metrics=['accuracy'])\n\n\nes = EarlyStopping(patience=10, monitor='val_accuracy', mode='max')\n\n# initialize the number of epochs and batch size\nEPOCHS = 100\nBS = 32\n\n# construct the training image generator for data augmentation\naug = ImageDataGenerator(rotation_range=20, zoom_range=0.15, width_shift_range=0.2, height_shift_range=0.2, shear_range=0.15,\n                        horizontal_flip=True, fill_mode=\"nearest\")\n \n# train the model\nhistory = model1.fit_generator(aug.flow(x_train,y_train, batch_size=BS),validation_data=(x_test,y_test), \n                              steps_per_epoch=len(x_train) // BS ,epochs=EPOCHS ,callbacks=[es])\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\n# summarize history for accuracy\nplt.plot(history.history['accuracy'])\nplt.plot(history.history['val_accuracy'])\nplt.title('model accuracy')\nplt.ylabel('accuracy')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()\n\n# summarize history for loss\nplt.plot(history.history['loss'])\nplt.plot(history.history['val_loss'])\nplt.title('model loss')\nplt.ylabel('loss')\nplt.xlabel('epoch')\nplt.legend(['train', 'test'], loc='upper left')\nplt.show()","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}