{ "cells": [ { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b2badc36-14dd-2012-4c2c-87707d08cf48" }, "outputs": [], "source": [ "import os, cv2, random\n", "import numpy as np\n", "import pandas as pd\n", "\n", "import matplotlib.pyplot as plt\n", "from matplotlib import ticker\n", "import seaborn as sns\n", "%matplotlib inline \n", "\n", "from keras.models import Sequential\n", "from keras.layers import Input, Dropout, Flatten, Convolution2D, MaxPooling2D, Dense, Activation\n", "from keras.optimizers import RMSprop\n", "from keras.callbacks import ModelCheckpoint, Callback, EarlyStopping\n", "from keras.utils import np_utils" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "801061dc-047c-8ae9-eed2-de934b462669" }, "outputs": [], "source": [ "TRAIN_DIR = '../input/train/'\n", "TEST_DIR = '../input/test/'\n", "\n", "ROWS = 64\n", "COLS = 64\n", "CHANNELS = 3\n", "\n", "train_images = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR)] # use this for full dataset\n", "train_dogs = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'dog' in i]\n", "train_cats = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'cat' in i]\n", "\n", "test_images = [TEST_DIR+i for i in os.listdir(TEST_DIR)]\n", "\n", "\n", "# slice datasets for memory efficiency on Kaggle Kernels, delete if using full dataset\n", "train_images = train_dogs[:1000] + train_cats[:1000]\n", "random.shuffle(train_images)\n", "test_images = test_images[:25]\n", "\n", "def read_image(file_path):\n", " img = cv2.imread(file_path, cv2.IMREAD_COLOR) #cv2.IMREAD_GRAYSCALE\n", " return cv2.resize(img, (ROWS, COLS), interpolation=cv2.INTER_CUBIC)\n", "\n", "\n", "def prep_data(images):\n", " count = len(images)\n", " data = np.ndarray((count, CHANNELS, ROWS, COLS), dtype=np.uint8)\n", "\n", " for i, image_file in enumerate(images):\n", " image = read_image(image_file)\n", " data[i] = image.T\n", " if i%250 == 0: print('Processed {} of {}'.format(i, count))\n", " \n", " return data\n", "\n", "train = prep_data(train_images)\n", "test = prep_data(test_images)\n", "\n", "print(\"Train shape: {}\".format(train.shape))\n", "print(\"Test shape: {}\".format(test.shape))" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "9bd16f75-ee45-b9d5-d301-65af594f12b4" }, "outputs": [], "source": [ "labels = []\n", "for i in train_images:\n", " if 'dog' in i:\n", " labels.append(1)\n", " else:\n", " labels.append(0)\n", "\n", "sns.countplot(labels)\n", "sns.plt.title('Cats and Dogs')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "8289b914-42da-60f7-4645-6e964ac64770" }, "outputs": [], "source": [ "def show_cats_and_dogs(idx):\n", " cat = read_image(train_cats[idx])\n", " dog = read_image(train_dogs[idx])\n", " pair = np.concatenate((cat, dog), axis=1)\n", " plt.figure(figsize=(10,5))\n", " plt.imshow(pair)\n", " plt.show()\n", " \n", "for idx in range(0,5):\n", " show_cats_and_dogs(idx)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "de5d9bc1-1e19-1742-902b-36f292c67b70" }, "outputs": [], "source": [ "dog_avg = np.array([dog[0].T for i, dog in enumerate(train) if labels[i]==1]).mean(axis=0)\n", "plt.imshow(dog_avg)\n", "plt.title('Your Average Dog')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "b1c22d4b-4528-38cc-6a4f-551481dc0ed6" }, "outputs": [], "source": [ "cat_avg = np.array([cat[0].T for i, cat in enumerate(train) if labels[i]==0]).mean(axis=0)\n", "plt.imshow(cat_avg)\n", "plt.title('Your Average Cat')" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "1cdf6726-dcae-4dd6-cea8-f785d8d1a53a" }, "outputs": [], "source": [ "optimizer = RMSprop(lr=1e-4)\n", "objective = 'binary_crossentropy'\n", "\n", "\n", "def catdog():\n", " \n", " model = Sequential()\n", "\n", " model.add(Convolution2D(32, 3, 3, border_mode='same', input_shape=(3, ROWS, COLS), activation='relu'))\n", " model.add(Convolution2D(32, 3, 3, border_mode='same', activation='relu'))\n", " model.add(MaxPooling2D(pool_size=(2, 2)))\n", "\n", " model.add(Convolution2D(64, 3, 3, border_mode='same', activation='relu'))\n", " model.add(Convolution2D(64, 3, 3, border_mode='same', activation='relu'))\n", " model.add(MaxPooling2D(pool_size=(2, 2)))\n", " \n", " model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))\n", " model.add(Convolution2D(128, 3, 3, border_mode='same', activation='relu'))\n", " model.add(MaxPooling2D(pool_size=(2, 2)))\n", " \n", " model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n", " model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n", "# model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n", " model.add(MaxPooling2D(pool_size=(2, 2)))\n", "\n", "# model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n", "# model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n", "# model.add(Convolution2D(256, 3, 3, border_mode='same', activation='relu'))\n", "# model.add(MaxPooling2D(pool_size=(2, 2)))\n", "\n", " model.add(Flatten())\n", " model.add(Dense(256, activation='relu'))\n", " model.add(Dropout(0.5))\n", " \n", " model.add(Dense(256, activation='relu'))\n", " model.add(Dropout(0.5))\n", "\n", " model.add(Dense(1))\n", " model.add(Activation('sigmoid'))\n", "\n", " model.compile(loss=objective, optimizer=optimizer, metrics=['accuracy'])\n", " return model\n", "\n", "\n", "model = catdog()" ] } ], "metadata": { "_change_revision": 0, "_is_fork": false, "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": "3.6.0" } }, "nbformat": 4, "nbformat_minor": 0 }