{"cells":[{"metadata":{"trusted":true},"cell_type":"code","source":"import numpy as np # linear algebra\nimport pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\nimport matplotlib.pyplot as plt\n\nfrom keras import layers\nfrom keras import models\nfrom keras import optimizers\nfrom keras.preprocessing.image import load_img, img_to_array, ImageDataGenerator\nfrom keras import applications\n\nfrom sklearn.preprocessing import LabelEncoder\nfrom sklearn.model_selection import train_test_split\nfrom sklearn.linear_model import LogisticRegression\nfrom sklearn import metrics\n\nimport glob\nimport os\nprint(os.listdir(\"../input\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import zipfile\n\n\nzip_files = ['test1', 'train']\n# Will unzip the files so that you can see them..\nfor zip_file in zip_files:\n    with zipfile.ZipFile(\"../input/dogs-vs-cats/{}.zip\".format(zip_file),\"r\") as z:\n        z.extractall(\".\")\n        print(\"{} unzipped\".format(zip_file))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print(os.listdir('../input/dogs-vs-cats'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"IMAGE_FOLDER_PATH=\"../working/train/\"\nFILE_NAMES=os.listdir(IMAGE_FOLDER_PATH)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"FAST_RUN = False\nIMAGE_WIDTH=128\nIMAGE_HEIGHT=128\nIMAGE_SIZE=(IMAGE_WIDTH, IMAGE_HEIGHT)\nIMAGE_CHANNELS=3","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"targets=list()\nfull_paths=list()\nfor file_name in FILE_NAMES:\n    target=file_name.split(\".\")[0]\n    full_path=os.path.join(IMAGE_FOLDER_PATH, file_name)\n    full_paths.append(full_path)\n    targets.append(target)\n\ndataset=pd.DataFrame()\ndataset['image_path']=full_paths\ndataset['target']=targets","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"target_counts=dataset['target'].value_counts()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from keras.models import Sequential\nfrom keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, Activation, BatchNormalization\n\nmodel = Sequential()\n\nmodel.add(Conv2D(32, (3, 3), activation='relu', input_shape=(IMAGE_WIDTH, IMAGE_HEIGHT, IMAGE_CHANNELS)))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128, (3, 3), activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Flatten())\nmodel.add(Dense(512, activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(Dropout(0.5))\nmodel.add(Dense(2, activation='softmax')) # 2 because we have cat and dog classes\n\nmodel.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"# from keras.callbacks import EarlyStopping, ReduceLROnPlateau\nfrom tensorflow.keras.callbacks import EarlyStopping,ReduceLROnPlateau","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"earlystop = EarlyStopping(patience=10)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"learning_rate_reduction = ReduceLROnPlateau(monitor='val_acc', \n                                            patience=2, \n                                            verbose=1, \n                                            factor=0.5, \n                                            min_lr=0.00001)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"callbacks = [earlystop, learning_rate_reduction]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_df, validate_df = train_test_split(dataset, test_size=0.20, 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":"train_df['target'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"validate_df['target'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"total_train = train_df.shape[0]\ntotal_validate = validate_df.shape[0]\nbatch_size=15","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=0.1,\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    x_col='image_path',\n    y_col='target',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\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    x_col='image_path',\n    y_col='target',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"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    x_col='image_path',\n    y_col='target',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical'\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"plt.figure(figsize=(12, 12))\nfor i in range(0, 15):\n    plt.subplot(5, 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":"epochs=3 if FAST_RUN else 50\nhistory = model.fit_generator(\n    train_generator, \n    epochs=20,\n    validation_data=validation_generator,\n    validation_steps=total_validate//batch_size,\n    steps_per_epoch=total_train//batch_size,\n    callbacks=callbacks\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.save_weights(\"model.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"fig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 12))\nax1.plot(history.history['loss'], color='b', label=\"Training loss\")\nax1.plot(history.history['val_loss'], color='r', label=\"validation loss\")\nax1.set_xticks(np.arange(1, epochs, 1))\nax1.set_yticks(np.arange(0, 1, 0.1))\n\nax2.plot(history.history['accuracy'], color='b', label=\"Training accuracy\")\nax2.plot(history.history['val_accuracy'], color='r',label=\"Validation accuracy\")\nax2.set_xticks(np.arange(1, epochs, 1))\n\nlegend = plt.legend(loc='best', shadow=True)\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_filenames = os.listdir(\"../working/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_df","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/test1/\",\n    x_col='filename',\n    y_col=None,\n    class_mode=None,\n    target_size=IMAGE_SIZE,\n    batch_size=batch_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))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['target'] = np.argmax(predict, axis=-1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"label_map = dict((v,k) for k,v in train_generator.class_indices.items())\ntest_df['target'] = test_df['target'].replace(label_map)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"test_df['target'] = test_df['target'].replace({ 'dog': 1, 'cat': 0 })","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df = test_df.copy()\nsubmission_df['id'] = submission_df['filename'].str.split('.').str[0]\nsubmission_df['label'] = submission_df['target']\nsubmission_df.drop(['filename', 'target'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"submission_df","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}