{"cells":[{"metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"cell_type":"code","source":"import zipfile, os\n\nwith zipfile.ZipFile(\"../input/dogs-vs-cats/train.zip\",\"r\") as z:\n    z.extractall(\".\")","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"img_width, img_height = 150, 150\ninput_shape = (img_width, img_height, 3)\nbatch_size = 15\nnb_train_samples = 20000\nnb_validation_samples = 5000\n\nnb_images = 25000\nnb_classes = 2\nnb_class_images = nb_images // nb_classes\n\nval_data_portion = 0.2","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"def create_directory(dir_name):\n    if os.path.exists(dir_name):\n        shutil.rmtree(dir_name)\n    os.makedirs(dir_name)\n    os.makedirs(os.path.join(dir_name, \"cats\"))\n    os.makedirs(os.path.join(dir_name, \"dogs\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"data_dir = '/kaggle/working/train'\ntrain_dir = '/kaggle/working/set/train' \nval_dir = '/kaggle/working/set/val' ","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"create_directory(train_dir)\ncreate_directory(val_dir)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import shutil\n\ndef copy_images(start_index, end_index, source_dir, dest_dir):\n    for i in range(start_index, end_index):\n        shutil.copy2(os.path.join(source_dir, \"cat.\" + str(i) + \".jpg\"), os.path.join(dest_dir, \"cats\"))\n        shutil.copy2(os.path.join(source_dir, \"dog.\" + str(i) + \".jpg\"), os.path.join(dest_dir, \"dogs\"))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"start_val_data_idx = int(nb_class_images * (1-val_data_portion))\n\n\ncopy_images(0, start_val_data_idx, data_dir, train_dir)\ncopy_images(start_val_data_idx, 12500, data_dir, val_dir)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"print('Cats in train set: ', len(os.listdir(train_dir + '/cats')))\nprint('Dogs in train set: ', len(os.listdir(train_dir + '/dogs')), '\\n')\n\nprint('Cats in validation set: ', len(os.listdir(val_dir + '/cats')))\nprint('Cats in validation set: ', len(os.listdir(val_dir + '/dogs')), '\\n')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"from tensorflow import keras\nfrom tensorflow.python.keras.preprocessing.image import ImageDataGenerator\nfrom tensorflow.python.keras.models import Sequential\nfrom tensorflow.python.keras.layers import Conv2D, MaxPooling2D, BatchNormalization\nfrom tensorflow.python.keras.layers import Activation, Dropout, Flatten, Dense\nfrom tensorflow.keras.optimizers import Adam","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model = Sequential()\nmodel.add(Conv2D(32, (3, 3), activation='relu' input_shape=input_shape))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(32, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Conv2D(64, (3, 3), activation='relu'))\nmodel.add(MaxPooling2D(pool_size=(2, 2)))\n\nmodel.add(Flatten())\nmodel.add(Dense(64, activation='relu'))\n\nmodel.add(Dropout(0.5))\nmodel.add(Dense(1, activation='sigmoid'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"model.compile(loss='binary_crossentropy',\n optimizer='adam',\n metrics=['accuracy'])","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\ndatagen = ImageDataGenerator(rescale=1./255)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"train_generator = train_datagen.flow_from_directory(\n train_dir,\n target_size=(img_width, img_height),\n batch_size=batch_size,\n class_mode='binary')\n","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"val_generator = datagen.flow_from_directory(\n val_dir,\n target_size=(img_width, img_height),\n batch_size=batch_size,\n class_mode='binary')","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"history = model.fit_generator(\n train_generator,\n steps_per_epoch=nb_train_samples // batch_size,\n epochs=10,\n validation_data=val_generator,\n validation_steps=nb_validation_samples // batch_size)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true},"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nfig, (ax1, ax2) = plt.subplots(2, 1, figsize=(12, 12))\nax1.plot(history.history['loss'], color='b', label=\"Train_loss\")\nax1.plot(history.history['val_loss'], color='r', label=\"Val_loss\")\nax1.set_xticks(np.arange(1, 10, 1))\nax1.set_yticks(np.arange(0, 1, 0.1))\n\nax2.plot(history.history['accuracy'], color='b', label=\"Train_accuracy\")\nax2.plot(history.history['val_accuracy'], color='r',label=\"Val_accuracy\")\nax2.set_xticks(np.arange(1, 10, 1))\n\nlegend = plt.legend(loc='best', shadow=True)\nplt.tight_layout()\nplt.show()","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}