{"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_minor":4,"nbformat":4,"cells":[{"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, shutil\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","metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"## Unzipping the dataset\n# # !unzip /kaggle/input/dogs-vs-cats/test1.zip -d /kaggle/working/\n!unzip /kaggle/input/dogs-vs-cats/train.zip -d /kaggle/working/","metadata":{"_uuid":"d629ff2d2480ee46fbb7e2d37f6b5fab8052498a","_cell_guid":"79c7e3d0-c299-4dcb-8224-4455121ee9b0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# The path to the directory where the original\n# dataset was uncompressed\noriginal_dataset_dir = '/kaggle/working/train'\n\n# The directory where we will\n# store our smaller dataset\nbase_dir = '/kaggle/working/Reduced'\nos.mkdir(base_dir)\n\n# Directories for our training,\n# validation and test splits\ntrain_dir = os.path.join(base_dir, 'train')\nos.mkdir(train_dir)\nvalidation_dir = os.path.join(base_dir, 'validation')\nos.mkdir(validation_dir)\ntest_dir = os.path.join(base_dir, 'test')\nos.mkdir(test_dir)\n\n# Directory with our training cat pictures\ntrain_cats_dir = os.path.join(train_dir, 'cats')\nos.mkdir(train_cats_dir)\n\n# Directory with our training dog pictures\ntrain_dogs_dir = os.path.join(train_dir, 'dogs')\nos.mkdir(train_dogs_dir)\n\n# Directory with our validation cat pictures\nvalidation_cats_dir = os.path.join(validation_dir, 'cats')\nos.mkdir(validation_cats_dir)\n\n# Directory with our validation dog pictures\nvalidation_dogs_dir = os.path.join(validation_dir, 'dogs')\nos.mkdir(validation_dogs_dir)\n\n# Directory with our validation cat pictures\ntest_cats_dir = os.path.join(test_dir, 'cats')\nos.mkdir(test_cats_dir)\n\n# Directory with our validation dog pictures\ntest_dogs_dir = os.path.join(test_dir, 'dogs')\nos.mkdir(test_dogs_dir)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\n# Copy first 1000 cat images to train_cats_dir\nfnames = ['cat.{}.jpg'.format(i) for i in range(1000)]\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(train_cats_dir, fname)\n    shutil.copyfile(src, dst)\n\n# Copy next 500 cat images to validation_cats_dir\nfnames = ['cat.{}.jpg'.format(i) for i in range(1000, 1500)]\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(validation_cats_dir, fname)\n    shutil.copyfile(src, dst)\n    \n# Copy next 500 cat images to test_cats_dir\nfnames = ['cat.{}.jpg'.format(i) for i in range(1500, 2000)]\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(test_cats_dir, fname)\n    shutil.copyfile(src, dst)\n    \n# Copy first 1000 dog images to train_dogs_dir\nfnames = ['dog.{}.jpg'.format(i) for i in range(1000)]\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(train_dogs_dir, fname)\n    shutil.copyfile(src, dst)\n    \n# Copy next 500 dog images to validation_dogs_dir\nfnames = ['dog.{}.jpg'.format(i) for i in range(1000, 1500)]\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(validation_dogs_dir, fname)\n    shutil.copyfile(src, dst)\n    \n# Copy next 500 dog images to test_dogs_dir\nfnames = ['dog.{}.jpg'.format(i) for i in range(1500, 2000)]\nfor fname in fnames:\n    src = os.path.join(original_dataset_dir, fname)\n    dst = os.path.join(test_dogs_dir, fname)\n    shutil.copyfile(src, dst)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras import layers\nfrom keras import models\nfrom keras import optimizers","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"model = models.Sequential()\nmodel.add(layers.Conv2D(32, (3, 3), activation='relu',\n                        input_shape=(150, 150, 3)))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(64, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Conv2D(128, (3, 3), activation='relu'))\nmodel.add(layers.MaxPooling2D((2, 2)))\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(512, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))\n\n\nmodel.compile(loss='binary_crossentropy',\n              optimizer=optimizers.RMSprop(lr=1e-4),\n              metrics=['acc'])\n\nmodel.summary()","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"print('total training cat images:', len(os.listdir(train_cats_dir)))\nprint('total training dog images:', len(os.listdir(train_dogs_dir)))\nprint('total validation cat images:', len(os.listdir(validation_cats_dir)))\nprint('total validation dog images:', len(os.listdir(validation_dogs_dir)))\nprint('total test cat images:', len(os.listdir(test_cats_dir)))\nprint('total test dog images:', len(os.listdir(test_dogs_dir)))","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\n\n# All images will be rescaled by 1./255\ntrain_datagen = ImageDataGenerator(rescale=1./255)\ntest_datagen = ImageDataGenerator(rescale=1./255)\n\ntrain_generator = train_datagen.flow_from_directory(\n        # This is the target directory\n        train_dir,\n        # All images will be resized to 150x150\n        target_size=(150, 150),\n        batch_size=20,\n        # Since we use binary_crossentropy loss, we need binary labels\n        class_mode='binary')\n\nvalidation_generator = test_datagen.flow_from_directory(\n        validation_dir,\n        target_size=(150, 150),\n        batch_size=20,\n        class_mode='binary')","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"for data_batch, labels_batch in train_generator:\n    print('data batch shape:', data_batch.shape)\n    print('labels batch shape:', labels_batch.shape)\n    break","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"history = model.fit_generator(\n      train_generator,\n      steps_per_epoch=100,\n      epochs=30,\n      validation_data=validation_generator,\n      validation_steps=50)","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\n\nacc = history.history['acc']\nval_acc = history.history['val_acc']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\n\nepochs = range(len(acc))\n\nplt.plot(epochs, acc, 'bo', label='Training acc')\nplt.plot(epochs, val_acc, 'b', label='Validation acc')\nplt.title('Training and validation accuracy')\nplt.legend()\n\nplt.figure()\n\nplt.plot(epochs, loss, 'bo', label='Training loss')\nplt.plot(epochs, val_loss, 'b', label='Validation loss')\nplt.title('Training and validation loss')\nplt.legend()\n\nplt.show()","metadata":{"trusted":true},"execution_count":null,"outputs":[]}]}