{
 "cells": [
  {
   "cell_type": "heading",
   "metadata": {
    "collapsed": true
   },
   "level": 1,
   "source": [
    "# 数据下载\n",
    "\n",
    "对应的模型在 'vgg16' 可以下载链接: https://pan.baidu.com/s/1qgx5LfTOen9MDlTdfGKFhw 密码: s4m5"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 导入包\n",
    "from keras.models import Sequential\n",
    "from keras.layers.core import Flatten, Dense, Dropout\n",
    "from keras.layers.convolutional import Convolution2D, MaxPooling2D, ZeroPadding2D\n",
    "from keras.optimizers import SGD\n",
    "import cv2, numpy as np"
   ]
  },
  {
   "cell_type": "heading",
   "metadata": {},
   "level": 1,
   "source": [
    "定义模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def VGG_16(weights_path=None):\n",
    "    model = Sequential()\n",
    "    model.add(ZeroPadding2D((1,1),input_shape=(3,224,224)))\n",
    "    model.add(Convolution2D(64, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(64, 3, 3, activation='relu'))\n",
    "    model.add(MaxPooling2D((2,2), strides=(2,2)))\n",
    "    \n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(128, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(128, 3, 3, activation='relu'))\n",
    "    model.add(MaxPooling2D((2,2), strides=(2,2)))\n",
    "    \n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(256, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(256, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(256, 3, 3, activation='relu'))\n",
    "    model.add(MaxPooling2D((2,2), strides=(2,2)))\n",
    "    \n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(512, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(512, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(512, 3, 3, activation='relu'))\n",
    "    model.add(MaxPooling2D((2,2), strides=(2,2)))\n",
    "    \n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(512, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(512, 3, 3, activation='relu'))\n",
    "    model.add(ZeroPadding2D((1,1)))\n",
    "    model.add(Convolution2D(512, 3, 3, activation='relu'))\n",
    "    model.add(MaxPooling2D((2,2), strides=(2,2)))\n",
    "    \n",
    "    model.add(Flatten())\n",
    "    model.add(Dense(4096, activation='relu'))\n",
    "    model.add(Dropout(0.5))\n",
    "    model.add(Dense(4096, activation='relu'))\n",
    "    model.add(Dropout(0.5))\n",
    "    model.add(Dense(1000, activation='softmax'))\n",
    "    \n",
    "    if weights_path:\n",
    "    model.load_weights(weights_path)\n",
    "    \n",
    "    return model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = VGG_16('data/vgg16_weights.h5')  "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)\n",
    "model.compile(optimizer=sgd, loss='categorical_crossentropy')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_image(imageurl):\n",
    "    im = cv2.resize(cv2.imread(imageurl),(224,224)).astype(np.float32)\n",
    "    im[:,:,0] -= 103.939\n",
    "    im[:,:,1] -= 116.779\n",
    "    im[:,:,2] -= 123.68\n",
    "    im = im.transpose((2,0,1))\n",
    "    im = np.expand_dims(im,axis=0)\n",
    "    return im"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = open('synset_words.txt','r')\n",
    "lines = f.readlines()\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "def predict(url):\n",
    "    im = load_image(url)\n",
    "    pre = np.argmax(model.predict(im))\n",
    "    print(lines[pre])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pylab inline\n",
    "from IPython.display import Image\n",
    "Image('cat1.jpg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "predict('cat1.jpg')\n",
    "Image('zebra.jpg')\n",
    "predict('zebra.jpg')\n",
    "Image('airplane.jpg')\n",
    "predict('airplane.jpg')\n",
    "predict('airplane.jpg')"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}