{"cells":[{"metadata":{"_uuid":"8f2839f25d086af736a60e9eeb907d3b93b6e0e5","_cell_guid":"b1076dfc-b9ad-4769-8c92-a6c4dae69d19","trusted":true},"cell_type":"code","source":"from keras.applications import VGG16\nconv_base = VGG16(weights='imagenet',\n                  include_top=False,\n                  input_shape=(150, 150, 3))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"337d3503df944e2bb864e69ea45fcaf0fb350ba1"},"cell_type":"code","source":"conv_base.summary()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f7e03923a47f74eb99c09066086eeb2c929212b5"},"cell_type":"code","source":"import os, shutil\n\noriginal_dataset_dir = '../input/train/train/'\nbase_dir = '/kaggle/working/cats_and_dogs_small'\nos.mkdir(base_dir)\n\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\ntrain_cats_dir = os.path.join(train_dir, 'cats')\nos.mkdir(train_cats_dir)\n\ntrain_dogs_dir = os.path.join(train_dir, 'dogs')\nos.mkdir(train_dogs_dir)\n\nvalidation_cats_dir = os.path.join(validation_dir, 'cats')\nos.mkdir(validation_cats_dir)\n\nvalidation_dogs_dir = os.path.join(validation_dir, 'dogs')\nos.mkdir(validation_dogs_dir)\n\ntest_cats_dir = os.path.join(test_dir, 'cats')\nos.mkdir(test_cats_dir)\ntest_dogs_dir = os.path.join(test_dir, 'dogs')\nos.mkdir(test_dogs_dir)\n\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\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\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\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\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\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)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"ed453d9c3c64219ea1dc7e40634f8cbdd8db9eb0"},"cell_type":"code","source":"import numpy as np\nfrom keras.preprocessing.image import ImageDataGenerator","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"1f94f7f7398f1a42d8351918b6047248ff9e1e43"},"cell_type":"code","source":"datagen = ImageDataGenerator(rescale=1./255) \nbatch_size = 20","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"6bfddb9340132ccf6e843af3a0a60579143c73dd"},"cell_type":"code","source":"def extract_features(directory, sample_count):\n    features = np.zeros(shape=(sample_count, 4, 4, 512))\n    labels = np.zeros(shape=(sample_count))\n    generator = datagen.flow_from_directory(directory, target_size=(150, 150), batch_size=batch_size, class_mode='binary')\n    i=0\n    for inputs_batch, labels_batch in generator:\n        features_batch = conv_base.predict(inputs_batch)\n        features[i * batch_size : (i + 1) * batch_size] = features_batch\n        labels[i * batch_size : (i + 1) * batch_size] = labels_batch\n        i += 1\n        if i * batch_size >= sample_count:\n            break\n    return features, labels","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"b99fadd2aaf663c03808662bbd5c14a106e14615"},"cell_type":"code","source":"train_features, train_labels = extract_features(train_dir, 2000) \nvalidation_features, validation_labels = extract_features(validation_dir, 1000) \ntest_features, test_labels = extract_features(test_dir, 1000)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"45a04f721257247b924a9a13eb5fa3db8e2e74a5"},"cell_type":"code","source":"train_features = np.reshape(train_features, (2000, 4 * 4 * 512))\nvalidation_features = np.reshape(validation_features, (1000, 4 * 4 * 512))\ntest_features = np.reshape(test_features, (1000, 4 * 4 * 512))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"4027a5ef796ba3d93aaccda8cce58f9191a25562"},"cell_type":"code","source":"from keras import models\nfrom keras import layers\nfrom keras import optimizers\nmodel = models.Sequential()\nmodel.add(layers.Dense(256, activation='relu', input_dim=4 * 4 * 512))\nmodel.add(layers.Dropout(0.5))\nmodel.add(layers.Dense(1, activation='sigmoid'))\nmodel.compile(optimizer=optimizers.RMSprop(lr=2e-5),\n              loss='binary_crossentropy',\n              metrics=['acc'])\nhistory = model.fit(train_features, train_labels,\n                    epochs=30,\n                    batch_size=20,\n                    validation_data=(validation_features, validation_labels))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"7180c826ac9a920a47c7b0293a21b427adbe15d2"},"cell_type":"code","source":"import matplotlib.pyplot as plt\nacc = history.history['acc']\nval_acc = history.history['val_acc']\nloss = history.history['loss']\nval_loss = history.history['val_loss']\nepochs = range(1, len(acc) + 1)\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()\nplt.figure()\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()\nplt.show()","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"37471aca633f5de37e9f254356c43c8867c609b5"},"cell_type":"code","source":"from keras import models\nfrom keras import layers\nmodel = models.Sequential()\nmodel.add(conv_base)\nmodel.add(layers.Flatten())\nmodel.add(layers.Dense(256, activation='relu'))\nmodel.add(layers.Dense(1, activation='sigmoid'))","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"e9f3abfff30cad4d51cde45322cb56e6a2176b6d"},"cell_type":"code","source":"conv_base.trainable = False","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"f04df0c33c27e76526acee78defdf7e535cf7564"},"cell_type":"code","source":"from keras.preprocessing.image import ImageDataGenerator\nfrom keras import optimizers\ntrain_datagen = ImageDataGenerator(\n      rescale=1./255,\n      rotation_range=40,\n      width_shift_range=0.2,\n      height_shift_range=0.2,\n      shear_range=0.2,\n      zoom_range=0.2,\n      horizontal_flip=True,\n      fill_mode='nearest')\ntest_datagen = ImageDataGenerator(rescale=1./255)\ntrain_generator = train_datagen.flow_from_directory(train_dir, target_size=(150, 150),\n                                                    batch_size=20, class_mode='binary')\nvalidation_generator = test_datagen.flow_from_directory(\n        validation_dir,\n        target_size=(150, 150),\n        batch_size=20,\n        class_mode='binary')\nmodel.compile(loss='binary_crossentropy',\n              optimizer=optimizers.RMSprop(lr=2e-5),\n              metrics=['acc'])\nhistory = model.fit_generator(\n      train_generator,\n      steps_per_epoch=100,\n      epochs=30,\n      validation_data=validation_generator,\n      validation_steps=50)","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"91a8518117aa0f87ffcf8bccb907c07ae55f18c9"},"cell_type":"code","source":"","execution_count":null,"outputs":[]},{"metadata":{"trusted":true,"_uuid":"55e7263022e00195ed60b0f9afb240d9e7b89b7b"},"cell_type":"code","source":"","execution_count":null,"outputs":[]}],"metadata":{"kernelspec":{"display_name":"Python 3","language":"python","name":"python3"},"language_info":{"name":"python","version":"3.6.6","mimetype":"text/x-python","codemirror_mode":{"name":"ipython","version":3},"pygments_lexer":"ipython3","nbconvert_exporter":"python","file_extension":".py"}},"nbformat":4,"nbformat_minor":1}