{"cells":[{"metadata":{"trusted":false},"cell_type":"code","source":"import os\nimport random\nimport pandas as pd\nimport numpy as np\nimport matplotlib.pyplot as plt\nfrom sklearn.model_selection import train_test_split","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"import tensorflow as tf\nfrom tensorflow.keras.models import Sequential\nfrom tensorflow.keras.layers import Activation, BatchNormalization, Conv2D, Dense, Dropout, Flatten, MaxPooling2D\nfrom tensorflow.keras.preprocessing.image import ImageDataGenerator, load_img\nfrom tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# DEFINE CONSTANTS\n\nFAST_RUN = False\nIMAGE_WIDTH = 128\nIMAGE_HEIGHT = 128\nIMAGE_SIZE = (IMAGE_WIDTH, IMAGE_HEIGHT)\nIMAGE_CHANNELS = 3","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# JOIN DIRECTORYS\n\ntrain_dir = os.path.join('../input/train/train/')\nno_of_train_data = len(os.listdir(train_dir))\n\nprint('no of train data: {}'.format(no_of_train_data))","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# CREAT CSV FILES\n\ncategories = list()\nfilenames = os.listdir(train_dir)\nfor filename in filenames:\n    name = filename.split('.')[0]\n    if name=='dog':\n        categories.append(1)\n    else:\n        categories.append(0)\n\ndf = pd.DataFrame({\n    'filename': filenames,\n    'category': categories\n})","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"df.tail()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# PLOT VALUE_COUNT GRAPH\n\ndf['category'].value_counts().plot.bar(color=['r','b'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# CREATE MODEL ARCHITECTURE\n\nmodel = Sequential()\n\nmodel.add(Conv2D(32, (3,3), padding='same', 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), padding='same', activation='relu'))\nmodel.add(BatchNormalization())\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\nmodel.add(Dropout(0.25))\n\nmodel.add(Conv2D(128, (3, 3), padding='same', 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'))\n          \nmodel.compile(loss='categorical_crossentropy', optimizer='rmsprop', metrics=['accuracy'])\nmodel.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"earlystop = EarlyStopping(patience=10)\nlearning_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":false},"cell_type":"code","source":"callbacks = [earlystop, learning_rate_reduction]","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"df['category'] = df['category'].replace({0:'cat', 1:'dog'})","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"df.head()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"train_df, validation_df = train_test_split(df, test_size=0.20, random_state=42)\ntrain_df = train_df.reset_index(drop=True)\nvalidation_df = validation_df.reset_index(drop=True)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"train_df['category'].value_counts().plot.bar(color=['r', 'b'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"validation_df['category'].value_counts().plot.bar(color=['b', 'r'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"total_train = train_df.shape[0]\ntotal_validate = validation_df.shape[0]\nbatch_size = 64","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"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    directory='../input/train/train/', \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"validation_datagen = ImageDataGenerator(rescale=1./255)\nvalidation_generator = validation_datagen.flow_from_dataframe(\n    validation_df, \n    directory='../input/train/train/', \n    x_col='filename',\n    y_col='category',\n    target_size=IMAGE_SIZE,\n    class_mode='categorical',\n    batch_size=batch_size\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"shape = list()\nplt.figure(figsize=(12,12))\nfor i in range(0, 15):\n    plt.subplot(5, 3, i+1)\n    for x_batch, _ in train_generator:\n        img = x_batch[0]\n        shape.append(img.shape)\n        plt.imshow(img)\n        break\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"# FIT MODEL\n\nepochs=3 if FAST_RUN else 50\nhistory = 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,\n    callbacks=callbacks\n)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"model.save_weights('model.h5')","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"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['acc'], color='b', label=\"Training accuracy\")\nax2.plot(history.history['val_acc'], 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":false},"cell_type":"code","source":"test_filenames = os.listdir('../input/test1/test1/')\ntest_df = pd.DataFrame(\n{\n    'filename': test_filenames\n})","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"no_samples = test_df.shape[0]\nprint(no_samples)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_gen = ImageDataGenerator(rescale=1./255)\ntest_generator = test_gen.flow_from_dataframe(\n    test_df,\n    directory='../input/test1/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":false},"cell_type":"code","source":"predict = model.predict_generator(test_generator, steps=np.ceil(no_samples/batch_size))","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"print(predict)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_df['category'] = np.argmax(predict, axis=-1)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"label_map = dict((v,k) for k,v in train_generator.class_indices.items())","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"label_map","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_df['category'] = test_df['category'].replace(label_map)","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_df","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_df['category'] = test_df['category'].replace({ 'dog': 1, 'cat': 0 })","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"test_df['category'].value_counts().plot.bar(color=['r', 'b'])","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"sample_test = test_df.head(18)\nsample_test.head()\nplt.figure(figsize=(12, 15))\nfor index, row in sample_test.iterrows():\n    filename = row['filename']\n    category = row['category']\n    img = load_img(\"../input/test1/test1/\"+filename, target_size=IMAGE_SIZE)\n    plt.subplot(6, 3, index+1)\n    plt.imshow(img)\n    if category == 1:\n        name = 'dog'\n    else:\n        name = 'cat'\n    plt.xlabel(name + '(' + \"{}\".format(category) + ')' )\nplt.tight_layout()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":false},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"codemirror_mode":{"name":"ipython","version":3},"file_extension":".py","mimetype":"text/x-python","name":"python","nbconvert_exporter":"python","pygments_lexer":"ipython3","version":"3.6.9"}},"nbformat":4,"nbformat_minor":1}