{ "cells": [ { "cell_type": "markdown", "metadata": { "_cell_guid": "c17988a6-23f6-b9c4-938f-9b2351627c23" }, "source": "" }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "40b9b187-f9c7-3cdb-a6e3-f608cfefc1af" }, "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", "\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": "bb66cce8-71b1-56a4-86ff-402910aa1264" }, "outputs": [], "source": [ "TRAIN_DIR = '../input/train/'\n", "TEST_DIR = '../input/test/'\n", "train_dogs = [(TRAIN_DIR+i, 1) for i in os.listdir(TRAIN_DIR) if 'dog' in i]\n", "train_cats = [(TRAIN_DIR+i, 0) for i in os.listdir(TRAIN_DIR) if 'cat' in i]\n", "#\u53d6\u6d4b\u8bd5\u96c6\uff0c\u8fd9\u4e2a\u5730\u65b9\u9700\u8981\u63d0\u524d\u5360\u4f4d\uff0c-1\u5c31\u662f\u5360\u4f4d\u7b26\u3002\n", "test_images = [(TEST_DIR+i, -1) for i in os.listdir(TEST_DIR)]\n", "print(test_images[0])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "516e95da-b868-27ff-6d61-6c17deb01f6a" }, "outputs": [], "source": [ "TRAIN_NUM = 50\n", "# \u56e0\u4e3a\u8fd0\u884c\u901f\u5ea6\u592a\u6162\uff0c\u9009\u53d6TRAIN_NUM\u4e2a\u6570\u636e\uff0c\u5e76\u968f\u673a\u6563\u5217\n", "\n", "train_images = train_dogs[:TRAIN_NUM]+ train_cats[:TRAIN_NUM]\n", "random.shuffle(train_images)\n", "# \u53d6\u4e2aTEST_NUM\u4e2a\u505a\u6d4b\u8bd5\n", "test_images = test_images" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "eb2e9153-361b-2e9a-124f-e682fcd3ac97" }, "outputs": [], "source": [ "ROWS = 64\n", "COLS = 64\n", "\n", "#\u8fd9\u91cc\u4f20\u5165\u7c7b\u4f3ctrain_dogs\u7684K-V\u683c\u5f0flist\u3002\u5c06\u56fe\u7247\u7edf\u4e00\u5316\n", "# \u8fd4\u56de \u7edf\u4e00\u5316\u540e\u7684\u56fe\u7247 + label \n", "def read_image(tuple_set):\n", " file_path = tuple_set[0]\n", " label = tuple_set[1]\n", " img = cv2.imread(file_path, cv2.IMREAD_COLOR)\n", " # \u8fd9\u91cc\u7684\u53c2\u6570\uff0c\u53ef\u4ee5\u662f\u5f69\u8272\u6216\u8005\u7070\u5ea6(GRAYSCALE)\n", " return cv2.resize(img, (ROWS, COLS), interpolation=cv2.INTER_CUBIC), label\n", " # \u8fd9\u91cc\uff0c\u53ef\u4ee5\u9009\u62e9\u538b\u7f29\u56fe\u7247\u7684\u65b9\u5f0f\uff0czoom\uff08cv2.INTER_CUBIC & cv2.INTER_LINEAR\uff09\u8fd8\u662fshrink\uff08cv2.INTER_AREA\uff09" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "02654c0c-24d8-ef57-133b-ba00f7af05fc" }, "outputs": [], "source": [ "CHANNELS = 3\n", "# \u4ee3\u8868RGB\u4e09\u4e2a\u989c\u8272\u9891\u9053\n", "# \u5c06\u56fe\u7247\u53d8\u4e3anumpy\u6570\u7ec4\n", "# \u8fd4\u56de\u7edf\u4e00\u5316\u540e\u7684numpy\u6570\u7ec4 + label \n", "def prep_data(images):\n", " no_images = len(images)\n", " data = np.ndarray((no_images, CHANNELS, ROWS, COLS), dtype=np.uint8)\n", " labels = []\n", " \n", " for i, image_file in enumerate(images): \n", " image, label = read_image(image_file)\n", " data[i] = image.T\n", " labels.append(label)\n", " return data, labels\n", "\n", "x_train, y_train = prep_data(train_images)\n", "x_test, y_test = prep_data(test_images)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "e2cc4904-aa20-04af-5ac8-4c582dc2f93c" }, "outputs": [], "source": [ "optimizer = RMSprop(lr=1e-4) #\u5b66\u4e60\u65b9\u6cd5\uff0c\u4e00\u6b65\u8de8\u591a\u5927\n", "objective = 'binary_crossentropy' #0-1\u5dee\u8ddd\u71b5\uff0c\u56e0\u4e3a\u8fd9\u91cc\u5c31\u662f0-1\n", "\n", "# \u5efa\u9020\u6a21\u578bVGG-16\u6784\u67b6\u65b9\u5f0f \n", "model = Sequential()\n", "#\u8f93\u5165\u4e00\u4e2a\u77e9\u9635 32\u4e2a\u7279\u5f81\uff0c3*3 \n", "#\u51e0\u5957CNN\u540e\uff0c\u7279\u5f81\u8981\u8d8a\u6765\u8d8a\u591a\uff0c\u4ece\u5927\u5904\u5230\u7ec6\u8282\u770b\u3002\u5982\u679c\u4ece\u7ec6\u8282\u5230\u5927\u770b\u3002feature\u4ece\u5927\u5230\u5c0f\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),dim_ordering=\"th\"))\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),dim_ordering=\"th\"))\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),dim_ordering=\"th\"))\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(MaxPooling2D(pool_size=(2, 2),dim_ordering=\"th\"))\n", "\n", "model.add(Flatten()) ##\u53d8\u6210\u4e00\u6761\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'])" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "70485d9e-c309-3fe6-e0cc-99331eb30200" }, "outputs": [], "source": [ "#\u8fd9\u4e00\u90e8\u5206\u7b97CNN\u505c\u6b62\u70b9\n", "\n", "nb_epoch = 10\n", "batch_size = 10\n", "#\u6ca1\u6709\u51cf\u5c11\u53cd\u800c\u589e\u9ad8\u4e86\uff0c\u6211\u4eec\u7ed9\u4ed63\u6b65\u8010\u5fc3\n", "\n", "early_stopping = EarlyStopping(monitor='val_loss', patience=3, verbose=1, mode='auto') \n", "# \u8dd1\u6a21\u578b\n", "model.fit(x_train, y_train, batch_size=batch_size, nb_epoch=nb_epoch,\n", " validation_split=0.2, verbose=0, shuffle=True, callbacks=[early_stopping])\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "6123dc01-e99e-c245-a146-fd7c6e72d7d1" }, "outputs": [], "source": [ "predictions = model.predict(x_test, verbose=0)\n", "print(predictions)" ] }, { "cell_type": "code", "execution_count": null, "metadata": { "_cell_guid": "a8aa8261-dc4e-a866-94e9-023ccfddaf76" }, "outputs": [], "source": [ "predictions[0]" ] } ], "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": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 0 }