{"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":{"trusted":true},"cell_type":"code","source":"!unzip ../input/dogs-vs-cats-redux-kernels-edition/test.zip\n!unzip ../input/dogs-vs-cats-redux-kernels-edition/train.zip\n!ls -ltr train | head","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# Cloud AutoML\nPROJECT_ID = 'automl-exercise-307804'\nfrom google.cloud import automl_v1beta1 as automl\nautoml_client = automl.AutoMlClient()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import os, cv2, re, random\nimport numpy as np\nimport pandas as pd\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras.preprocessing.image import img_to_array, load_img\nfrom keras import layers, models, optimizers\nfrom keras import backend as K\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"TRAIN_DIR = 'train/'\nTEST_DIR = 'test/'\ntrain_dogs = ['./train/{}'.format(i) for i in os.listdir(TRAIN_DIR) if 'dog' in i]\ntrain_cats = ['./train/{}'.format(i) for i in os.listdir(TRAIN_DIR) if 'cat' in i]\ntest_images_dogs_cats = ['./test/{}'.format(i) for i in os.listdir(TEST_DIR)]\nlen(train_dogs), len(train_cats), len(test_images_dogs_cats)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def atoi(text):\n    return int(text) if text.isdigit() else text\n\ndef natural_keys(text):\n    return [ atoi(c) for c in re.split('(\\d+)', text) ]\n\ntrain_dogs.sort(key=natural_keys)\ntrain_cats.sort(key=natural_keys)\ntrain_images_dogs_cats = train_dogs[0:1300] + train_cats[0:1300] \n\ntest_images_dogs_cats.sort(key=natural_keys)\nlen(train_images_dogs_cats), len(test_images_dogs_cats)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_width = 150\nimg_height = 150\ndef prepare_data(list_of_images):\n    \"\"\"\n    Returns two arrays: \n        x is an array of resized images\n        y is an array of labels\n    \"\"\"\n    x = [] # images as arrays\n    y = [] # labels\n    \n    for image in list_of_images:\n        x.append(cv2.resize(cv2.imread(image), (img_width,img_height), interpolation=cv2.INTER_CUBIC))\n    \n    for i in list_of_images:\n        if 'dog' in i:\n            y.append(1)\n        elif 'cat' in i:\n            y.append(0)\n    return x, y\n\nX, Y = prepare_data(train_images_dogs_cats)\nprint(K.image_data_format())\n# Since K.image_data_format() is channel_last, \n# input_shape to the first keras layer will be (img_width, img_height, 3). \n# '3' since it is a color image","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_train, X_val, Y_train, Y_val = train_test_split(X,Y, test_size=0.2, random_state=1)\nnb_train_samples = len(X_train)\nnb_validation_samples = len(X_val)\nbatch_size = 16","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.Sequential()\n\nmodel._name = 'CNN_Exp1'\nmodel.add(layers.Conv2D(32, (3, 3), input_shape=(img_width, img_height, 3)))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Conv2D(32, (3, 3)))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Conv2D(64, (3, 3)))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(64))\nmodel.add(layers.Activation('relu'))\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(1))\nmodel.add(layers.Activation('sigmoid'))\n\nmodel.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_datagen = ImageDataGenerator(\n    rescale=1. / 255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True)\n\nval_datagen = ImageDataGenerator(\n    rescale=1. / 255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True)\n\ntrain_generator = train_datagen.flow(np.array(X_train), Y_train, batch_size=batch_size)\nvalidation_generator = val_datagen.flow(np.array(X_val), Y_val, batch_size=batch_size)\n\n# Show sample from train\nfrom matplotlib import pyplot as plt\nplt.figure(figsize=(12,12))\nfor i in range(0,8):\n    plt.subplot(2, 4, i+1)\n    for x_batch, y_batch in train_generator:\n        img = x_batch[0]\n        print(y_batch[0])\n        plt.imshow(img)\n        break\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nhistory = model.fit_generator(\n    train_generator, \n    steps_per_epoch=nb_train_samples // batch_size,\n    epochs=15,\n    validation_data=validation_generator,\n    validation_steps=nb_validation_samples // batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"X_test, Y_test = prepare_data(test_images_dogs_cats) #Y_test in this case will be []\ntest_generator = val_datagen.flow(np.array(X_test), batch_size=batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"prediction_probabilities = model.predict(test_generator, verbose=1)\ncounter = range(1, len(test_images_dogs_cats) + 1)\nsubmission = pd.DataFrame({\"id\": counter, \"label\":list(prediction_probabilities)})\nprint(submission)\ncols = ['label']\nfor col in cols:\n    submission[col] = submission[col].map(lambda x: str(x).lstrip('[').rstrip(']')).astype(float)\n\nsubmission.to_csv(\"dogsVScats_exp1.csv\", index = False)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Experiment 2"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.Sequential()\n\nmodel._name = 'CNN_Exp2'\nmodel.add(layers.Conv2D(32, (3, 3), activation = 'relu', input_shape = (img_width, img_height, 3)))\nmodel.add(layers.MaxPooling2D((2, 2)))\n\nmodel.add(layers.Conv2D(64, (3, 3), activation = 'relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\n\nmodel.add(layers.Conv2D(128, (3, 3), activation = 'relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\n\nmodel.add(layers.Conv2D(128, (3, 3), activation = 'relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(512, activation = 'relu'))\nmodel.add(layers.Dense(1, activation = 'sigmoid'))\n\nmodel.compile(loss='binary_crossentropy',optimizer='rmsprop',metrics=['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator = train_datagen.flow(np.array(X_train), Y_train, batch_size=batch_size)\nvalidation_generator = val_datagen.flow(np.array(X_val), Y_val, batch_size=batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nhistory = model.fit_generator(\n    train_generator, \n    steps_per_epoch=nb_train_samples // batch_size,\n    epochs=15,\n    validation_data=validation_generator,\n    validation_steps=nb_validation_samples // batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_generator = val_datagen.flow(np.array(X_test), batch_size=batch_size)\nprediction_probabilities = model.predict(test_generator, verbose=1)\ncounter = range(1, len(test_images_dogs_cats) + 1)\nsubmission = pd.DataFrame({\"id\": counter, \"label\":list(prediction_probabilities)})\nprint(submission)\ncols = ['label']\nfor col in cols:\n    submission[col] = submission[col].map(lambda x: str(x).lstrip('[').rstrip(']')).astype(float)\n\nsubmission.to_csv(\"dogsVScats_exp2.csv\", index = False)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Experiment 3"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = models.Sequential()\n\nmodel._name = 'CNN_Exp3'\nmodel.add(layers.Conv2D(32,(3,3),activation='relu',input_shape=(img_width, img_height, 3)))\nmodel.add(layers.BatchNormalization())\nmodel.add(layers.MaxPooling2D(pool_size=(2,2)))\nmodel.add(layers.Dropout(0.25))\n\nmodel.add(layers.Conv2D(64,(3,3),activation='relu'))\nmodel.add(layers.BatchNormalization())\nmodel.add(layers.MaxPooling2D(pool_size=(2,2)))\nmodel.add(layers.Dropout(0.25))\n\nmodel.add(layers.Conv2D(128,(3,3),activation='relu'))\nmodel.add(layers.BatchNormalization())\nmodel.add(layers.MaxPooling2D(pool_size=(2,2)))\nmodel.add(layers.Dropout(0.25))\n\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(512,activation='relu'))\nmodel.add(layers.BatchNormalization())\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(1,activation='sigmoid'))\nmodel.compile(loss='binary_crossentropy',optimizer='rmsprop',metrics=['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau\nearlystop = EarlyStopping(patience = 10)\nlearning_rate_reduction = ReduceLROnPlateau(monitor = 'val_acc',patience = 2,verbose = 1,factor = 0.5,min_lr = 0.00001)\ncallbacks = [earlystop,learning_rate_reduction]\n\ntrain_generator = train_datagen.flow(np.array(X_train), Y_train, batch_size=batch_size)\nvalidation_generator = val_datagen.flow(np.array(X_val), Y_val, batch_size=batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"%%time\nhistory = model.fit_generator(\n    train_generator, \n    steps_per_epoch=nb_train_samples // batch_size,\n    epochs=15,\n    validation_data=validation_generator,\n    validation_steps=nb_validation_samples // batch_size,\n    callbacks=callbacks\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_generator = val_datagen.flow(np.array(X_test), batch_size=batch_size)\nprediction_probabilities = model.predict(test_generator, verbose=1)\ncounter = range(1, len(test_images_dogs_cats) + 1)\nsubmission = pd.DataFrame({\"id\": counter, \"label\":list(prediction_probabilities)})\nprint(submission)\ncols = ['label']\nfor col in cols:\n    submission[col] = submission[col].map(lambda x: str(x).lstrip('[').rstrip(']')).astype(float)\n\nsubmission.to_csv(\"dogsVScats_exp3.csv\", index = False)\nsubmission.head()","execution_count":null,"outputs":[]},{"metadata":{"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}