{"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":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats/train.zip -d /kaggle/working/","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"!unzip /kaggle/input/dogs-vs-cats/test1.zip -d /kaggle/working/","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Import Libraries\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Dense, Conv2D, Flatten, Dropout, MaxPooling2D\nfrom tensorflow.keras.callbacks import ModelCheckpoint\nfrom tensorflow.keras.optimizers import Adam\nfrom sklearn.model_selection import train_test_split\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau\nfrom matplotlib import pyplot as plt\nfrom tensorflow.keras.applications import VGG16\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Prepare Data\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"Dtrain = os.listdir('./train')\ncategories = []\nfor filename in Dtrain:\n    category = filename.split(\".\")[0]\n    if category == \"dog\":\n        categories.append(\"dog\")\n    else:\n        categories.append(\"cat\")\ndf = pd.DataFrame({\n    \"filename\" : Dtrain,\n    \"category\" : categories\n})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(df.head())","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Split data to train and validation set \n"},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df, validate_df = train_test_split(df, test_size = 0.2, random_state = 42)\ntrain_df = train_df.reset_index(drop=True)\nvalidate_df = validate_df.reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"image_width, image_height = 128, 128\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg_conv = VGG16(weights='imagenet', include_top=False, input_shape=(image_width, image_height, 3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg_conv.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"for layer in (vgg_conv.layers):\n    layer.trainable = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"vgg_conv.summary()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Build Model"},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\n\n# Add the vgg convolutional base model\nmodel.add(vgg_conv)\n\n# Add new layers\nmodel.add(Flatten())\nmodel.add(Dense(128, activation='relu'))\nmodel.add(Dropout(0.4))\nmodel.add(Dense(2, activation='sigmoid'))\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='binary_crossentropy', optimizer=Adam(lr = 0.0001,decay=1e-6), metrics=['accuracy'])","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Callbacks"},{"metadata":{"trusted":true},"cell_type":"code","source":"earlystop = EarlyStopping(patience=10)\n\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=2, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)\n\ncallbacks = [earlystop, learning_rate_reduction]","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Traning Generator\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"\n\ntrain_datagen = ImageDataGenerator(\n    rotation_range=20,\n    rescale=1./255,\n    shear_range=0.2,\n    zoom_range=0.2,\n    horizontal_flip=True,\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    \"./train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(image_width, image_height),\n    class_mode='categorical',\n    batch_size=64,\n    color_mode=\"rgb\",\n    shuffle=True\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Validation Generator"},{"metadata":{"trusted":true},"cell_type":"code","source":"validation_datagen = ImageDataGenerator(rescale=1./255)\n\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validate_df, \n    \"./train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(image_width, image_height),\n    class_mode='categorical',\n    batch_size=64,\n    color_mode=\"rgb\",\n    shuffle=True\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## show example"},{"metadata":{"trusted":true},"cell_type":"code","source":"example_df = train_df.sample(n=1).reset_index(drop=True)\nexample_generator = train_datagen.flow_from_dataframe(\n    example_df, \n    \"./train/\", \n    x_col='filename',\n    y_col='category',\n    target_size=(image_width, image_height),\n    class_mode='categorical',\n    color_mode=\"rgb\",\n    shuffle=True\n)\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 example_generator:\n        img = x_batch[0]\n        plt.imshow(img)\n        break\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Fit model"},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(\n    train_generator,\n    steps_per_epoch=len(train_df)//64,\n    epochs=30,\n    validation_data=validation_generator,\n    validation_steps=len(validate_df)//64,\n    callbacks=callbacks\n)\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"### Save model weights"},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save_weights(\"CatsVsDogs.h5\")\n","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Visualize Training\n"},{"metadata":{"trusted":true},"cell_type":"code","source":"accuracy      = history.history['accuracy']\nval_accuracy  = history.history['val_accuracy']\nloss     = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs   = range(len(accuracy))\n\nplt.plot(epochs, accuracy)\nplt.plot(epochs, val_accuracy)\nplt.title('Training and validation accuracy')\nplt.figure()\n\n# Plot training and validation loss per epoch\nplt.plot(epochs, loss)\nplt.plot(epochs, val_loss)\nplt.title('Training and validation loss')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## prepare test data"},{"metadata":{"trusted":true},"cell_type":"code","source":"Dtest = os.listdir('./test1')\ndf_test = pd.DataFrame({\n    \"filename\" : Dtest\n})","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## Create Testing Generator"},{"metadata":{"trusted":true},"cell_type":"code","source":"test_dataGen = ImageDataGenerator(1./255)\n\ntest_gen = test_dataGen.flow_from_dataframe(\n    df_test,\n    './test1',\n    target_size = (image_width, image_height),\n    x_col = \"filename\",\n    y_col = None,\n    batch_size = 64,\n    class_mode = None,\n    shuffle = True,\n    color_mode=\"rgb\",\n\n)","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## predict"},{"metadata":{"trusted":true},"cell_type":"code","source":"predict = model.predict_generator(test_gen)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test['category'] = np.argmax(predict, axis=-1)\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"df_test[\"category\"] = df_test[\"category\"].replace({1 : \"cat\", 0 : \"dog\"})\ndf_test['category'].value_counts().plot.bar()\nplt.ylabel(len(df_test), fontsize = 14)\nplt.title(str(len(df_test[df_test['category'] == 'dog']))+\" Dogs  |  \"+str((len(df_test[df_test['category'] == 'cat'])))+\" Cats\", fontsize=18)\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator, load_img\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"sample_test = df_test.head(25)\nsample_test.head()\nplt.figure(figsize=(12, 24))\nfor index, row in sample_test.iterrows():\n    filename = row['filename']\n    category = row['category']\n    img = load_img(\"/kaggle/working/test1/\"+filename, target_size=(image_width, image_height))\n    plt.subplot(5, 5, index+1)\n    plt.imshow(img)\n    plt.xlabel(filename + '(' + \"{}\".format(category) + ')' )\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{},"cell_type":"markdown","source":"## submission"},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = df_test.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","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}