{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true,"id":"FDE9HX-Hmlgu","outputId":"49d751a1-2e5a-414a-86c3-0ddd6207bbac"},"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 5GB 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,"id":"g7uwMZqEmlg0"},"cell_type":"code","source":"from keras import layers, models\nfrom keras.preprocessing.image import ImageDataGenerator, load_img\nfrom keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\nfrom keras import optimizers\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split\nimport random\nimport zipfile\nfrom math import ceil\n\nINPUT_PATH = '/kaggle/input/dogs-vs-cats'\nWORKING_PATH = '/kaggle/working'\n\n\n# Extract train and test zip files\nwith zipfile.ZipFile(os.path.join(INPUT_PATH, 'train.zip')) as z:\n    z.extractall('.')\n    \nwith zipfile.ZipFile(os.path.join(INPUT_PATH, 'test1.zip')) as z:\n    z.extractall('.')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"P4nAAP6Imlg4"},"cell_type":"code","source":"IMAGE_SHAPE = (150, 150, 3)\nTRAIN_PATH = os.path.join(WORKING_PATH, 'train')\nTEST_PATH = os.path.join(WORKING_PATH, 'test1')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"G1Lh9LfAmlg7","outputId":"315707a4-5161-4c2c-9685-8ab2a42ddc0c"},"cell_type":"code","source":"files = os.listdir(TRAIN_PATH)\ncategories = []\n\nfor file in files:\n    category = file.split('.')[0]\n    if category == 'dog':\n        categories.append(1)\n    else:\n        categories.append(0)\n\ndf = pd.DataFrame({\n    'filename': files, \n    'category': categories\n})\n\nprint(df.size)\ndf.head()","execution_count":null,"outputs":[]},{"metadata":{"id":"Znnj0tEzmlg_"},"cell_type":"markdown","source":"**Data Distribution Visualization:**"},{"metadata":{"trusted":true,"id":"TfmMWunSmlg_","outputId":"4a1d5e70-a526-435b-dd77-8941bd8e3767"},"cell_type":"code","source":"df['category'].value_counts().plot(kind='bar')","execution_count":null,"outputs":[]},{"metadata":{"id":"z61r8yIrmlhD"},"cell_type":"markdown","source":"Building a Model"},{"metadata":{"trusted":true,"id":"P7afbHwvmlhD"},"cell_type":"code","source":"def build_model():\n    model = models.Sequential()\n    \n    model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=IMAGE_SHAPE))\n    model.add(layers.BatchNormalization())\n    model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n    model.add(layers.Dropout(0.20))\n    \n    model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n    model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n    model.add(layers.BatchNormalization())\n    model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n    model.add(layers.Dropout(0.25))\n    \n    model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n    model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n    model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n    model.add(layers.BatchNormalization())\n    model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n    model.add(layers.Dropout(0.30))\n    \n    model.add(layers.Conv2D(256, (3, 3), activation='relu'))\n    model.add(layers.BatchNormalization())\n    model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n    model.add(layers.Dropout(0.4))\n    \n    model.add(layers.Flatten())\n    model.add(layers.Dense(512, activation='relu'))\n    model.add(layers.BatchNormalization())\n    model.add(layers.Dense(2, activation='softmax'))\n    \n    model.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\n    return model","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"-qXm5E6VmlhG","outputId":"80ff4841-19bb-4552-a97b-23c6299305b3"},"cell_type":"code","source":"model = build_model()\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"aqyOCwS9mlhK"},"cell_type":"code","source":"from keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\nearlystop = EarlyStopping(patience=10)\nlearning_rate_reduction = ReduceLROnPlateau(monitor='val_accuracy',\n                                           patience=2,\n                                           verbose=1,\n                                           factor=0.5,\n                                           min_lr=0.00001)\nfilepath = \"model.h5\"\ncheckpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min')\n\ncallbacks = [earlystop, learning_rate_reduction, checkpoint]","execution_count":null,"outputs":[]},{"metadata":{"id":"B-hmT0lqmlhO"},"cell_type":"markdown","source":"Data Preparation"},{"metadata":{"trusted":true,"id":"2yedIeeamlhO"},"cell_type":"code","source":"df['category'] = df['category'].replace({1:'dog', 0:'cat'})","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"3IshlfGUmlhR"},"cell_type":"code","source":"train_df, valid_df = train_test_split(df, test_size=0.2, random_state=28)\ntrain_df = train_df.reset_index(drop=True)\nvalid_df = valid_df.reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"AzllJT1qmlhU","outputId":"f6de202b-aea2-474b-b906-c2e07fa668b9"},"cell_type":"code","source":"train_df['category'].value_counts().plot.bar()\nplt.title('Data Distribution - Training Dataset')\nplt.show()\nvalid_df['category'].value_counts().plot.bar()\nplt.title('Data Distribution - Validation Dataset')\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"IDTW1kvVmlhX"},"cell_type":"code","source":"train_count = len(train_df)\nvalid_count = len(valid_df)\nbatch_size = 25","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"8gbSgXbYmlha","outputId":"4f5ee70f-fd49-4a80-dae4-fdbdb79fd774"},"cell_type":"code","source":"train_datagen = ImageDataGenerator(rotation_range=20, \n                               rescale=1./255, \n                               width_shift_range=0.2, \n                               height_shift_range=0.2, \n                               shear_range=0.2,\n                               horizontal_flip=True,\n                               fill_mode='nearest')\n\ntrain_gen = train_datagen.flow_from_dataframe(\n    train_df,\n    directory = TRAIN_PATH,\n    x_col = 'filename',\n    y_col = 'category',\n    target_size = IMAGE_SHAPE[:2],\n    class_mode = 'categorical',\n    batch_size = batch_size\n)\n\nvalid_gen = train_datagen.flow_from_dataframe(\n    valid_df,\n    directory = TRAIN_PATH,\n    x_col = 'filename',\n    y_col = 'category',\n    target_size = IMAGE_SHAPE[:2],\n    class_mode = 'categorical',\n    batch_size = batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"Fut7O4E1mlhe","outputId":"13a9de7b-732c-4fdc-ce74-54fb21128945"},"cell_type":"code","source":"epoch = 30\nhistory = model.fit(\n    train_gen,\n    epochs=epoch,\n    steps_per_epoch = train_count // batch_size,\n    validation_data = valid_gen,\n    \n    validation_steps = valid_count // batch_size,\n    callbacks = callbacks\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"Nfn18awGmlhh"},"cell_type":"code","source":"model.save_weights(\"dog_vs_cat_3.h5\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"Xe1Su__smlhk","outputId":"60941361-741b-4c67-d832-b15abf57566a"},"cell_type":"code","source":"epoch_count = range(1, len(history.history['accuracy'])+1)\n\nplt.plot(epoch_count, history.history['accuracy'], 'bo', label='Training Accuracy')\nplt.plot(epoch_count, history.history['val_accuracy'], 'b', label='Validation Accuracy')\nplt.title('Accuracy')\nplt.legend()\nplt.show()\n\nplt.figure()\n\nplt.plot(epoch_count, history.history['loss'], 'bo', label='Training Loss')\nplt.plot(epoch_count, history.history['val_loss'], 'r', label='Validation Loss')\nplt.legend()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"mRlCbSpRmlhn"},"cell_type":"code","source":"test_files = os.listdir(TEST_PATH)\n\ntest_df = pd.DataFrame({\n    'filename': test_files\n})\n\ntest_samples = test_df.shape[0]","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"UJEU0Duwmlhp","outputId":"5ad0e962-92e7-483b-8e9c-1e2188c0a17e"},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=(1./255))\ntest_generator = test_gen.flow_from_dataframe(\n    test_df,\n    shuffle = False,\n    directory = TEST_PATH,\n    x_col = 'filename',\n    y_col = None,\n    target_size=IMAGE_SHAPE[:2],\n    class_mode = None,\n    batch_size = batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"id":"UTIX1uiJzDdl","trusted":true},"cell_type":"code","source":"from math import ceil\npred = model.predict(test_generator, steps=ceil(test_samples/batch_size))\ntest_df['category'] = np.argmax(pred, axis=-1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"CJQ-j336mlhv"},"cell_type":"code","source":"label_map = dict((v,k) for k,v in train_gen.class_indices.items())\ntest_df['category'] = test_df['category'].replace(label_map)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"CdUEcNJwmlhy"},"cell_type":"code","source":"test_df['category'] = test_df['category'].replace({ 'dog': 1, 'cat': 0 })","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"xs4x7ROumlh2","outputId":"ef33ed66-845b-4418-f850-d2252c292c1a"},"cell_type":"code","source":"test_df['category'].value_counts().plot.bar()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"id":"OZGNXfSsmlh5","outputId":"ce73f662-b70c-4edc-e372-70685ffc1bc7"},"cell_type":"code","source":"sample_test = test_df.head(18)\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(os.path.join(TEST_PATH,filename), target_size=IMAGE_SHAPE)\n    plt.subplot(6, 3, index+1)\n    plt.imshow(img)\n    plt.xlabel(filename + '(' + \"{}\".format(category) + ')' )\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"id":"VpPYLcrhyj3I","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['category']\nsubmission_df.drop(['filename', 'category'], axis=1, inplace=True)\nsubmission_df.to_csv('submission.csv', index=False)","execution_count":null,"outputs":[]},{"metadata":{"id":"kPH2iZ2Vzk2m","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}