{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "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": "markdown",
   "metadata": {},
   "source": [
    "## 导入数据"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/media/sf_share\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "print(os.getcwd())\n",
    "os.chdir(\"/media/sf_share/linux/ImageIdentification-vgg16\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## 导入包"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "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": "markdown",
   "metadata": {},
   "source": [
    "定义模型"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "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": 6,
   "metadata": {
    "collapsed": true
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/liuyuqi/anaconda3/envs/py36/lib/python3.6/site-packages/ipykernel_launcher.py:4: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation=\"relu\")`\n  after removing the cwd from sys.path.\n/home/liuyuqi/anaconda3/envs/py36/lib/python3.6/site-packages/ipykernel_launcher.py:6: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(64, (3, 3), activation=\"relu\")`\n  \n/home/liuyuqi/anaconda3/envs/py36/lib/python3.6/site-packages/ipykernel_launcher.py:10: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), activation=\"relu\")`\n  # Remove the CWD from sys.path while we load stuff.\n/home/liuyuqi/anaconda3/envs/py36/lib/python3.6/site-packages/ipykernel_launcher.py:12: UserWarning: Update your `Conv2D` call to the Keras 2 API: `Conv2D(128, (3, 3), activation=\"relu\")`\n  if sys.path[0] == '':\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_4/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mInvalidArgumentError\u001b[0m                      Traceback (most recent call last)",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py\u001b[0m in \u001b[0;36m_call_cpp_shape_fn_impl\u001b[0;34m(op, input_tensors_needed, input_tensors_as_shapes_needed, require_shape_fn)\u001b[0m\n\u001b[1;32m    685\u001b[0m           \u001b[0mgraph_def_version\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnode_def_str\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput_shapes\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput_tensors\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 686\u001b[0;31m           input_tensors_as_shapes, status)\n\u001b[0m\u001b[1;32m    687\u001b[0m   \u001b[0;32mexcept\u001b[0m \u001b[0merrors\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mInvalidArgumentError\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0merr\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/errors_impl.py\u001b[0m in \u001b[0;36m__exit__\u001b[0;34m(self, type_arg, value_arg, traceback_arg)\u001b[0m\n\u001b[1;32m    515\u001b[0m             \u001b[0mcompat\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mas_text\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mc_api\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTF_Message\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstatus\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstatus\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 516\u001b[0;31m             c_api.TF_GetCode(self.status.status))\n\u001b[0m\u001b[1;32m    517\u001b[0m     \u001b[0;31m# Delete the underlying status object from memory otherwise it stays alive\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mInvalidArgumentError\u001b[0m: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_4/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128].",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-6-3b57a7001932>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mmodel\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mVGG_16\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'data/vgg16_weights.h5'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m<ipython-input-3-9889470a4e16>\u001b[0m in \u001b[0;36mVGG_16\u001b[0;34m(weights_path)\u001b[0m\n\u001b[1;32m     11\u001b[0m     \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mZeroPadding2D\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     12\u001b[0m     \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mConvolution2D\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m128\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m3\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mactivation\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'relu'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 13\u001b[0;31m     \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mMaxPooling2D\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstrides\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     14\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     15\u001b[0m     \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0madd\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mZeroPadding2D\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;36m1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/keras/models.py\u001b[0m in \u001b[0;36madd\u001b[0;34m(self, layer)\u001b[0m\n\u001b[1;32m    490\u001b[0m                           output_shapes=[self.outputs[0]._keras_shape])\n\u001b[1;32m    491\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 492\u001b[0;31m             \u001b[0moutput_tensor\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mlayer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;36m0\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    493\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moutput_tensor\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mlist\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    494\u001b[0m                 raise TypeError('All layers in a Sequential model '\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/keras/engine/topology.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, inputs, **kwargs)\u001b[0m\n\u001b[1;32m    617\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    618\u001b[0m             \u001b[0;31m# Actually call the layer, collecting output(s), mask(s), and shape(s).\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 619\u001b[0;31m             \u001b[0moutput\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcall\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    620\u001b[0m             \u001b[0moutput_mask\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompute_mask\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mprevious_mask\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    621\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/keras/layers/pooling.py\u001b[0m in \u001b[0;36mcall\u001b[0;34m(self, inputs)\u001b[0m\n\u001b[1;32m    156\u001b[0m                                         \u001b[0mstrides\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstrides\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    157\u001b[0m                                         \u001b[0mpadding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpadding\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 158\u001b[0;31m                                         data_format=self.data_format)\n\u001b[0m\u001b[1;32m    159\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0moutput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    160\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/keras/layers/pooling.py\u001b[0m in \u001b[0;36m_pooling_function\u001b[0;34m(self, inputs, pool_size, strides, padding, data_format)\u001b[0m\n\u001b[1;32m    219\u001b[0m         output = K.pool2d(inputs, pool_size, strides,\n\u001b[1;32m    220\u001b[0m                           \u001b[0mpadding\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata_format\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 221\u001b[0;31m                           pool_mode='max')\n\u001b[0m\u001b[1;32m    222\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0moutput\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    223\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/keras/backend/tensorflow_backend.py\u001b[0m in \u001b[0;36mpool2d\u001b[0;34m(x, pool_size, strides, padding, data_format, pool_mode)\u001b[0m\n\u001b[1;32m   3655\u001b[0m         x = tf.nn.max_pool(x, pool_size, strides,\n\u001b[1;32m   3656\u001b[0m                            \u001b[0mpadding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpadding\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3657\u001b[0;31m                            data_format=tf_data_format)\n\u001b[0m\u001b[1;32m   3658\u001b[0m     \u001b[0;32melif\u001b[0m \u001b[0mpool_mode\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'avg'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3659\u001b[0m         x = tf.nn.avg_pool(x, pool_size, strides,\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py\u001b[0m in \u001b[0;36mmax_pool\u001b[0;34m(value, ksize, strides, padding, data_format, name)\u001b[0m\n\u001b[1;32m   2142\u001b[0m         \u001b[0mpadding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpadding\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2143\u001b[0m         \u001b[0mdata_format\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdata_format\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2144\u001b[0;31m         name=name)\n\u001b[0m\u001b[1;32m   2145\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2146\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/ops/gen_nn_ops.py\u001b[0m in \u001b[0;36mmax_pool\u001b[0;34m(input, ksize, strides, padding, data_format, name)\u001b[0m\n\u001b[1;32m   4585\u001b[0m     _, _, _op = _op_def_lib._apply_op_helper(\n\u001b[1;32m   4586\u001b[0m         \u001b[0;34m\"MaxPool\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0minput\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minput\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mksize\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mksize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mstrides\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mstrides\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpadding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpadding\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 4587\u001b[0;31m         data_format=data_format, name=name)\n\u001b[0m\u001b[1;32m   4588\u001b[0m     \u001b[0m_result\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_op\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0moutputs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   4589\u001b[0m     \u001b[0m_inputs_flat\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_op\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/op_def_library.py\u001b[0m in \u001b[0;36m_apply_op_helper\u001b[0;34m(self, op_type_name, name, **keywords)\u001b[0m\n\u001b[1;32m    785\u001b[0m         op = g.create_op(op_type_name, inputs, output_types, name=scope,\n\u001b[1;32m    786\u001b[0m                          \u001b[0minput_types\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0minput_types\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mattrs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mattr_protos\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 787\u001b[0;31m                          op_def=op_def)\n\u001b[0m\u001b[1;32m    788\u001b[0m       \u001b[0;32mreturn\u001b[0m \u001b[0moutput_structure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mop_def\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_stateful\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mop\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    789\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36mcreate_op\u001b[0;34m(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_shapes, compute_device)\u001b[0m\n\u001b[1;32m   3290\u001b[0m           op_def=op_def)\n\u001b[1;32m   3291\u001b[0m       self._create_op_helper(ret, compute_shapes=compute_shapes,\n\u001b[0;32m-> 3292\u001b[0;31m                              compute_device=compute_device)\n\u001b[0m\u001b[1;32m   3293\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mret\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3294\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36m_create_op_helper\u001b[0;34m(self, op, compute_shapes, compute_device)\u001b[0m\n\u001b[1;32m   3330\u001b[0m     \u001b[0;31m# compute_shapes argument.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3331\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mop\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_c_op\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mcompute_shapes\u001b[0m\u001b[0;34m:\u001b[0m  \u001b[0;31m# pylint: disable=protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3332\u001b[0;31m       \u001b[0mset_shapes_for_outputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3333\u001b[0m     \u001b[0;31m# TODO(b/XXXX): move to Operation.__init__ once _USE_C_API flag is removed.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3334\u001b[0m     \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_add_op\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36mset_shapes_for_outputs\u001b[0;34m(op)\u001b[0m\n\u001b[1;32m   2494\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0m_set_shapes_for_outputs_c_api\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2495\u001b[0m   \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2496\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0m_set_shapes_for_outputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2497\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2498\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36m_set_shapes_for_outputs\u001b[0;34m(op)\u001b[0m\n\u001b[1;32m   2467\u001b[0m       \u001b[0mshape_func\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_call_cpp_shape_fn_and_require_op\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2468\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2469\u001b[0;31m   \u001b[0mshapes\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mshape_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2470\u001b[0m   \u001b[0;32mif\u001b[0m \u001b[0mshapes\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2471\u001b[0m     raise RuntimeError(\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36mcall_with_requiring\u001b[0;34m(op)\u001b[0m\n\u001b[1;32m   2397\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2398\u001b[0m   \u001b[0;32mdef\u001b[0m \u001b[0mcall_with_requiring\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2399\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0mcall_cpp_shape_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mop\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrequire_shape_fn\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2400\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2401\u001b[0m   \u001b[0m_call_cpp_shape_fn_and_require_op\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcall_with_requiring\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py\u001b[0m in \u001b[0;36mcall_cpp_shape_fn\u001b[0;34m(op, require_shape_fn)\u001b[0m\n\u001b[1;32m    625\u001b[0m     res = _call_cpp_shape_fn_impl(op, input_tensors_needed,\n\u001b[1;32m    626\u001b[0m                                   \u001b[0minput_tensors_as_shapes_needed\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 627\u001b[0;31m                                   require_shape_fn)\n\u001b[0m\u001b[1;32m    628\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mres\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdict\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    629\u001b[0m       \u001b[0;31m# Handles the case where _call_cpp_shape_fn_impl calls unknown_shape(op).\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/anaconda3/envs/py36/lib/python3.6/site-packages/tensorflow/python/framework/common_shapes.py\u001b[0m in \u001b[0;36m_call_cpp_shape_fn_impl\u001b[0;34m(op, input_tensors_needed, input_tensors_as_shapes_needed, require_shape_fn)\u001b[0m\n\u001b[1;32m    689\u001b[0m       \u001b[0mmissing_shape_fn\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mTrue\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    690\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 691\u001b[0;31m       \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0merr\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmessage\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    692\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    693\u001b[0m   \u001b[0;32mif\u001b[0m \u001b[0mmissing_shape_fn\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: Negative dimension size caused by subtracting 2 from 1 for 'max_pooling2d_4/MaxPool' (op: 'MaxPool') with input shapes: [?,1,112,128]."
     ],
     "output_type": "error"
    }
   ],
   "source": [
    "model = VGG_16('data/vgg16_weights.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'model' is not defined",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-5-1b3fb0da450c>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[0msgd\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mSGD\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlr\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdecay\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m1e-6\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmomentum\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m0.9\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnesterov\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mTrue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcompile\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0moptimizer\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0msgd\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mloss\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'categorical_crossentropy'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m: name 'model' is not defined"
     ],
     "output_type": "error"
    }
   ],
   "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": 12,
   "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
}