{"cells":[{"metadata":{},"cell_type":"markdown","source":"# **Data Preprocessing**\n"},{"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)\nimport random as rand\n# Input data files are available in the \"../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# Any results you write to the current directory are saved as output.","execution_count":null,"outputs":[]},{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator, load_img\nfrom keras.utils import to_categorical\nfrom sklearn.model_selection import train_test_split\nimport matplotlib.pyplot as plt\nimport random\n\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip ../input/dogs-vs-cats/train.zip -d train","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip ../input/dogs-vs-cats/test1.zip -d test","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"ld=os.listdir('../working/train/train')\nprint(ld)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"filenames = os.listdir(\"../working/train/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()\ndf['category'] = df['category'].astype(str)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample = random.choice(filenames)\nimage = load_img(\"../working/train/train/\"+sample)\nplt.imshow(image)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Loading and Using Pre-trained Model**"},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras import layers\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation,GlobalMaxPooling2D\nfrom keras import applications\nfrom keras.preprocessing.image import ImageDataGenerator\nfrom keras import optimizers\nfrom keras.applications import VGG16\nfrom keras.models import Model\n\nimage_size = 224\ninput_shape = (image_size, image_size, 3)\n\nepochs = 5\nbatch_size = 16\n\npre_trained_model = VGG16(input_shape=input_shape, include_top=False, weights=\"imagenet\")\n    \nfor layer in pre_trained_model.layers[:15]:\n    layer.trainable = False\n\nfor layer in pre_trained_model.layers[15:]:\n    layer.trainable = True\n    \nlast_layer = pre_trained_model.get_layer('block5_pool')\nlast_output = last_layer.output\n    \n# Flatten the output layer to 1 dimension\nx = GlobalMaxPooling2D()(last_output)\n# Add a fully connected layer with 512 hidden units and ReLU activation\nx = Dense(512, activation='relu')(x)\n# Add a dropout rate of 0.5\nx = Dropout(0.5)(x)\n# Add a final sigmoid layer for classification\nx = layers.Dense(1, activation='sigmoid')(x)\n\nmodel = Model(pre_trained_model.input, x)\n\nmodel.compile(loss='binary_crossentropy',\n              optimizer=optimizers.SGD(lr=1e-4, momentum=0.9),\n              metrics=['accuracy'])\n\nmodel.summary()","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()\n\n# validate_df = validate_df.sample(n=100).reset_index() # use for fast testing code purpose\n# train_df = train_df.sample(n=1800).reset_index() # use for fast testing code purpose\n\ntotal_train = train_df.shape[0]\ntotal_validate = validate_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(train_df)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(total_validate)","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_datagen = 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)\n\ntrain_generator = train_datagen.flow_from_dataframe(\n    train_df, \n    \"../working/train/train/\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary',\n    target_size=(image_size, image_size),\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validation_datagen = ImageDataGenerator(rescale=1./255)\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validate_df, \n    \"../working/train/train/\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary',\n    target_size=(image_size, image_size),\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"example_df = train_df.sample(n=10).reset_index(drop=True)\nexample_generator = train_datagen.flow_from_dataframe(\n    example_df, \n    \"../working/train/train/\", \n    x_col='filename',\n    y_col='category',\n    class_mode='binary'\n)\nplt.figure(figsize=(12, 12))\nfor i in range(0, 9):\n    plt.subplot(3, 3, i+1)\n    for X_batch, Y_batch in example_generator:\n        image = X_batch[0]\n        plt.imshow(image)\n        break\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(\n    train_generator,\n    epochs=epochs,\n    validation_data=validation_generator,\n    validation_steps=total_validate//batch_size,\n    steps_per_epoch=total_train//batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(history.history)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"loss, accuracy = model.evaluate_generator(validation_generator, total_validate//batch_size, workers=12)\nprint(\"Test: accuracy = %f  ;  loss = %f \" % (accuracy, loss))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"# **Analyzing the Results**"},{"metadata":{"trusted":true},"cell_type":"code","source":"def plot_model_history(model_history, accuracy='acc', val_accuracy='val_acc'):\n    fig, axs = plt.subplots(1,2,figsize=(15,5))\n    axs[0].plot(range(1,len(model_history.history['accuracy'])+1),model_history.history['accuracy'])\n    axs[0].plot(range(1,len(model_history.history['val_accuracy'])+1),model_history.history['val_accuracy'])\n    axs[0].set_title('Model Accuracy')\n    axs[0].set_ylabel('Accuracy')\n    axs[0].set_xlabel('Epoch')\n    axs[0].set_xticks(np.arange(1,len(model_history.history['accuracy'])+1),len(model_history.history['accuracy'])/10)\n    axs[0].legend(['train', 'val'], loc='best')\n    axs[1].plot(range(1,len(model_history.history['loss'])+1),model_history.history['loss'])\n    axs[1].plot(range(1,len(model_history.history['val_loss'])+1),model_history.history['val_loss'])\n    axs[1].set_title('Model Loss')\n    axs[1].set_ylabel('Loss')\n    axs[1].set_xlabel('Epoch')\n    axs[1].set_xticks(np.arange(1,len(model_history.history['loss'])+1),len(model_history.history['loss'])/10)\n    axs[1].legend(['train', 'val'], loc='best')\n    plt.show()\n    \nplot_model_history(history)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"Y_val = validate_df['category']\ny_pred =  model.predict_generator(validation_generator)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(y_pred)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_filenames = os.listdir(\"../working/test/test1\")\ntest_df = pd.DataFrame({\n    'filename': test_filenames\n})\nnb_samples = test_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df, \n    \"../working/test/test1/\", \n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    batch_size=batch_size,\n    target_size=(image_size, image_size),\n    shuffle=False\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = model.predict_generator(test_generator, steps=np.ceil(nb_samples/batch_size))\nthreshold = 0.5\ntest_df['category'] = np.where(predict > threshold, 1,0)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_test = test_df.sample(n=9).reset_index()\nsample_test.head()\nplt.figure(figsize=(12, 12))\nfor index, row in sample_test.iterrows():\n    filename = row['filename']\n    category = row['category']\n    img = load_img(\"../working/test/test1/\"+filename, target_size=(256, 256))\n    plt.subplot(3, 3, index+1)\n    plt.imshow(img)\n    plt.xlabel(filename + '(' + \"{}\".format(category) + ')')\nplt.tight_layout()\nplt.show()","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}