{ "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": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 0, "cells": [ { "metadata": { "_cell_guid": "d6f08c60-5beb-5e25-bbd5-9b5712a2c935", "_active": false, "collapsed": false }, "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 in \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 \"../input/\" directory.\n# For example, running this (by clicking run or pressing Shift+Enter) will list the files in the input directory\n\nfrom subprocess import check_output\nprint(check_output([\"ls\", \"../input\"]).decode(\"utf8\"))\n\n# Any results you write to the current directory are saved as output.", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "7fd6c09b-fdd2-5385-082b-11d8bf705a61", "_active": false, "collapsed": false }, "source": "# read data", "execution_count": null, "cell_type": "markdown", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "7d9b4824-e38e-4039-ead0-b512fbc25f8f", "_active": false, "collapsed": false }, "source": "import os, cv2, random\nimport numpy as np\nimport pandas as pd\n\nimport matplotlib.pyplot as plt\nfrom matplotlib import ticker\nimport seaborn as sns\n%matplotlib inline \n\nfrom keras.models import Sequential\nfrom keras.layers import Input, Dropout, Flatten, Convolution2D, MaxPooling2D, Dense, Activation\nfrom keras.optimizers import RMSprop\nfrom keras.callbacks import ModelCheckpoint, Callback, EarlyStopping\nfrom keras.utils import np_utils", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "ed011be2-9fe0-887a-8355-e3c62d775337", "_active": false, "collapsed": false }, "source": "TRAIN_DIR = '../input/train/'\nTEST_DIR = '../input/test/'\n\nROWS = 64\nCOLS = 64\nCHANNELS = 3\n\ntrain_images = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR)] # use this for full dataset\ntrain_dogs = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'dog' in i]\ntrain_cats = [TRAIN_DIR+i for i in os.listdir(TRAIN_DIR) if 'cat' in i]\n\ntest_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\ntrain_images = train_dogs[:1000] + train_cats[:1000]\nrandom.shuffle(train_images)\ntest_images = test_images[:25]\n\ndef 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\ndef 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\ntrain = prep_data(train_images)\ntest = prep_data(test_images)\n\nprint(\"Train shape: {}\".format(train.shape))\nprint(\"Test shape: {}\".format(test.shape))", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "bd331ab5-d8d2-207c-7977-fdf99348cff1", "_active": false, "collapsed": false }, "source": "labels = []\nfor i in train_images:\n if 'dog' in i:\n labels.append(1)\n else:\n labels.append(0)\n\nsns.countplot(labels)\nsns.plt.title('Cats and Dogs')", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "b360a3e7-f5a7-a4c3-f481-7d2bead5e86c", "_active": false, "collapsed": false }, "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 \nfor idx in range(0,5):\n show_cats_and_dogs(idx)", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "37a08b64-db2f-04a8-36d0-9beed47b36a3", "_active": false, "collapsed": false }, "source": "dog_avg = np.array([dog[0].T for i, dog in enumerate(train) if labels[i]==1]).mean(axis=0)\nplt.imshow(dog_avg)\nplt.title('Your Average Dog')", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "ece7c44d-aea3-fd47-cf44-cc6f23950854", "_active": false, "collapsed": false }, "source": "train_images_data = []\nfor path in train_images:\n image = read_image(path)\n train_images_data.append(image)", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "0f7e2a01-7b5c-b0e3-d99e-6be6753283e8", "_active": false, "collapsed": false }, "source": "print(np.shape(train_images_data[0]))", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "1009b919-019c-cf6e-1acb-f388428f5f52", "_active": false, "collapsed": false }, "source": "def plt_show_image(image):\n p_image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)\n plt.imshow(p_image)\n plt.show()\n", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "ddfffcbf-0072-7028-0aa2-b801bf136188", "_active": false, "collapsed": false }, "source": "red_channel_image = []\ngreen_channel_image = []\nblue_channel_image = []\nfor image in train_images_data :\n b,g,r = cv2.split(image)\n red_channel_image.append(r)\n green_channel_image.append(g)\n blue_channel_image.append(b)\n \n ", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "1ad22380-6b7b-3108-87c2-fbe7e6ce0225", "_active": true, "collapsed": false }, "source": "print(np.shape(red_channel_image[0]))\nprint(np.average(red_channel_image[0]))\nchannel = red_channel_image[0]\nchannel = (channel - np.average(channel))/255\nprint(channel)", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "a8033123-0b35-d66d-f9fc-62e0c0d811cf", "_active": false, "collapsed": false }, "source": "data pre-process\n1. $P(image)=\\frac{image - image_{average}}{255}$", "execution_count": null, "cell_type": "markdown", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "30dbc39d-076d-7281-458a-5b122af93cd5", "_active": false, "collapsed": false }, "source": "from sklearn.decomposition import PCA\npca = PCA()\nX = red_channel_image.flatten()\npca.fit(X)", "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" }, { "metadata": { "_cell_guid": "8976db66-a187-e054-1d49-e20ad73361bd", "_active": false, "collapsed": false }, "source": null, "execution_count": null, "cell_type": "code", "outputs": [], "execution_state": "idle" } ] }