Porting `TensorFlow Mnist.ipynb` by reactivekk to IJulia.

TensorFlow Mnist w Julia.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "_original: [TensorFlow Mnist.ipynb](https://github.com/reactivekk/tensorflow-getting-started/blob/master/TensorFlow%20Mnist.ipynb) at https://github.com/reactivekk/tensorflow-getting-started_"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "using PyCall"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "@pyimport tensorflow as tf"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Import data:\n",
    "\n",
    "![](https://www.tensorflow.org/versions/master/images/MNIST.png)\n",
    "\n",
    "From https://www.tensorflow.org/versions/master/tutorials/mnist/beginners/index.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Extracting MNIST_data/train-images-idx3-ubyte.gz\n",
      "Extracting MNIST_data/train-labels-idx1-ubyte.gz\n",
      "Extracting MNIST_data/t10k-images-idx3-ubyte.gz\n",
      "Extracting MNIST_data/t10k-labels-idx1-ubyte.gz\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "PyObject <tensorflow.examples.tutorials.mnist.input_data.DataSets object at 0x3191f64d0>"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "@pyimport tensorflow.examples.tutorials.mnist.input_data as input_data\n",
    "mnist = input_data.read_data_sets(\"MNIST_data/\", one_hot=true)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "One hot: E.g.\n",
    "\n",
    "3: [0, 0, 0, 1, 0, 0, 0, 0, 0, 0]"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Create the model:\n",
    "    \n",
    "![](https://www.tensorflow.org/versions/master/images/softmax-regression-scalargraph.png)\n",
    "\n",
    "From https://www.tensorflow.org/versions/master/tutorials/mnist/beginners/index.html"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PyObject <tensorflow.python.framework.ops.Tensor object at 0x30b708b10>"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "x = tf.placeholder(tf.float32, [nothing, 784])\n",
    "\n",
    "W = tf.Variable(tf.zeros(Int32[784, 10]))\n",
    "b = tf.Variable(tf.zeros(Int32[10]))\n",
    "\n",
    "# layer = tf.matmul(x, W) + b\n",
    "layer = tf.add(tf.matmul(x, W), b)\n",
    "\n",
    "y = tf.nn[:softmax](layer)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Define loss and optimizer:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PyObject <tensorflow.python.framework.ops.Operation object at 0x30b76e6d0>"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_ = tf.placeholder(tf.float32, [nothing, 10])\n",
    "\n",
    "# cross_entropy = -tf.reduce_sum(y_ * tf.log(y))\n",
    "cross_entropy = tf.neg(tf.reduce_sum(tf.mul(y_, tf.log(y))))\n",
    "\n",
    "optimizer = tf.train[:GradientDescentOptimizer](0.01)\n",
    "train_step = optimizer[:minimize](cross_entropy)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Initialize:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "I tensorflow/core/common_runtime/local_device.cc:40] Local device intra op parallelism threads: 4\n",
      "I tensorflow/core/common_runtime/direct_session.cc:58] Direct session inter op parallelism threads: 4\n"
     ]
    }
   ],
   "source": [
    "init = tf.initialize_all_variables()\n",
    "\n",
    "sess = tf.Session()\n",
    "sess[:run](init)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "Create summary file for TensorBoard:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "PyObject <tensorflow.python.training.summary_io.SummaryWriter object at 0x30b7791d0>"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "writer = tf.train[:SummaryWriter](\"/tmp/mnist_logs\", sess[:graph_def])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Start TensorBoard server in your terminal: \n",
    "```\n",
    "tensorboard --logdir=/tmp/mnist_logs\n",
    "```\n",
    "Then visit http://localhost:6006 in your browser and click on 'GRAPH'. "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "---\n",
    "Train:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "for i in 1:1000\n",
    "    batch_xs, batch_ys = mnist[:train][:next_batch](100)\n",
    "    sess[:run](train_step, feed_dict=Dict(x => batch_xs, y_ => batch_ys))\n",
    "end"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Test:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "accuracy:0.9115999937057495\n"
     ]
    }
   ],
   "source": [
    "correct_prediction = tf.equal(tf.argmax(y,1), tf.argmax(y_,1))\n",
    "accuracy = tf.reduce_mean(tf.cast(correct_prediction, \"float\"))\n",
    "\n",
    "println(\"accuracy:$(sess[:run](accuracy, feed_dict=Dict(x => mnist[:test][:images], y_ => mnist[:test][:labels])))\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "true"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Pkg.add(\"PyPlot\")\n",
    "# Pkg.build(\"PyPlot\")\n",
    "using PyPlot\n",
    "PyPlot.svg(true)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Classified as: 5\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "image/svg+xml": [
       "<?xml version=\"1.0\" encoding=\"utf-8\" standalone=\"no\"?>\n",
       "<!DOCTYPE svg PUBLIC \"-//W3C//DTD SVG 1.1//EN\"\n",
       "  \"http://www.w3.org/Graphics/SVG/1.1/DTD/svg11.dtd\">\n",
       "<!-- Created with matplotlib (http://matplotlib.org/) -->\n",
       "<svg height=\"375pt\" version=\"1.1\" viewBox=\"0 0 379 375\" width=\"379pt\" xmlns=\"http://www.w3.org/2000/svg\" xmlns:xlink=\"http://www.w3.org/1999/xlink\">\n",
       " <defs>\n",
       "  <style type=\"text/css\">\n",
       "*{stroke-linecap:butt;stroke-linejoin:round;stroke-miterlimit:100000;}\n",
       "  </style>\n",
       " </defs>\n",
       " <g id=\"figure_1\">\n",
       "  <g id=\"patch_1\">\n",
       "   <path d=\"M 0 375.61375 \n",
       "L 379.27 375.61375 \n",
       "L 379.27 0 \n",
       "L 0 0 \n",
       "z\n",
       "\" style=\"fill:#ffffff;\"/>\n",
       "  </g>\n",
       "  <g id=\"axes_1\">\n",
       "   <g id=\"patch_2\">\n",
       "    <path d=\"M 26.47 352.8 \n",
       "L 372.07 352.8 \n",
       "L 372.07 7.2 \n",
       "L 26.47 7.2 \n",
       "z\n",
       "\" style=\"fill:#ffffff;\"/>\n",
       "   </g>\n",
       "   <g clip-path=\"url(#p4178fa998b)\">\n",
       "    <image height=\"346.32\" id=\"imageda810c0d66\" width=\"346.32\" x=\"26.47\" xlink:href=\"data:image/png;base64,\n",
       "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\" y=\"6.48\"/>\n",
       "   </g>\n",
       "   <g id=\"patch_3\">\n",
       "    <path d=\"M 26.47 7.2 \n",
       "L 372.07 7.2 \n",
       "\" style=\"fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;\"/>\n",
       "   </g>\n",
       "   <g id=\"patch_4\">\n",
       "    <path d=\"M 372.07 352.8 \n",
       "L 372.07 7.2 \n",
       "\" style=\"fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;\"/>\n",
       "   </g>\n",
       "   <g id=\"patch_5\">\n",
       "    <path d=\"M 26.47 352.8 \n",
       "L 372.07 352.8 \n",
       "\" style=\"fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;\"/>\n",
       "   </g>\n",
       "   <g id=\"patch_6\">\n",
       "    <path d=\"M 26.47 352.8 \n",
       "L 26.47 7.2 \n",
       "\" style=\"fill:none;stroke:#000000;stroke-linecap:square;stroke-linejoin:miter;\"/>\n",
       "   </g>\n",
       "   <g id=\"matplotlib.axis_1\">\n",
       "    <g id=\"xtick_1\">\n",
       "     <g id=\"line2d_1\">\n",
       "      <defs>\n",
       "       <path d=\"M 0 0 \n",
       "L 0 -4 \n",
       "\" id=\"mffc13c70cb\" style=\"stroke:#000000;stroke-width:0.5;\"/>\n",
       "      </defs>\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"32.6414285714\" xlink:href=\"#mffc13c70cb\" y=\"352.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_2\">\n",
       "      <defs>\n",
       "       <path d=\"M 0 0 \n",
       "L 0 4 \n",
       "\" id=\"mb797512127\" style=\"stroke:#000000;stroke-width:0.5;\"/>\n",
       "      </defs>\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"32.6414285714\" xlink:href=\"#mb797512127\" y=\"7.2\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_1\">\n",
       "      <!-- 0 -->\n",
       "      <defs>\n",
       "       <path d=\"M 31.78125 66.40625 \n",
       "Q 24.171875 66.40625 20.328125 58.90625 \n",
       "Q 16.5 51.421875 16.5 36.375 \n",
       "Q 16.5 21.390625 20.328125 13.890625 \n",
       "Q 24.171875 6.390625 31.78125 6.390625 \n",
       "Q 39.453125 6.390625 43.28125 13.890625 \n",
       "Q 47.125 21.390625 47.125 36.375 \n",
       "Q 47.125 51.421875 43.28125 58.90625 \n",
       "Q 39.453125 66.40625 31.78125 66.40625 \n",
       "M 31.78125 74.21875 \n",
       "Q 44.046875 74.21875 50.515625 64.515625 \n",
       "Q 56.984375 54.828125 56.984375 36.375 \n",
       "Q 56.984375 17.96875 50.515625 8.265625 \n",
       "Q 44.046875 -1.421875 31.78125 -1.421875 \n",
       "Q 19.53125 -1.421875 13.0625 8.265625 \n",
       "Q 6.59375 17.96875 6.59375 36.375 \n",
       "Q 6.59375 54.828125 13.0625 64.515625 \n",
       "Q 19.53125 74.21875 31.78125 74.21875 \n",
       "\" id=\"BitstreamVeraSans-Roman-30\"/>\n",
       "      </defs>\n",
       "      <g transform=\"translate(28.8239285714 365.918125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-30\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"xtick_2\">\n",
       "     <g id=\"line2d_3\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"94.3557142857\" xlink:href=\"#mffc13c70cb\" y=\"352.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_4\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"94.3557142857\" xlink:href=\"#mb797512127\" y=\"7.2\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_2\">\n",
       "      <!-- 5 -->\n",
       "      <defs>\n",
       "       <path d=\"M 10.796875 72.90625 \n",
       "L 49.515625 72.90625 \n",
       "L 49.515625 64.59375 \n",
       "L 19.828125 64.59375 \n",
       "L 19.828125 46.734375 \n",
       "Q 21.96875 47.46875 24.109375 47.828125 \n",
       "Q 26.265625 48.1875 28.421875 48.1875 \n",
       "Q 40.625 48.1875 47.75 41.5 \n",
       "Q 54.890625 34.8125 54.890625 23.390625 \n",
       "Q 54.890625 11.625 47.5625 5.09375 \n",
       "Q 40.234375 -1.421875 26.90625 -1.421875 \n",
       "Q 22.3125 -1.421875 17.546875 -0.640625 \n",
       "Q 12.796875 0.140625 7.71875 1.703125 \n",
       "L 7.71875 11.625 \n",
       "Q 12.109375 9.234375 16.796875 8.0625 \n",
       "Q 21.484375 6.890625 26.703125 6.890625 \n",
       "Q 35.15625 6.890625 40.078125 11.328125 \n",
       "Q 45.015625 15.765625 45.015625 23.390625 \n",
       "Q 45.015625 31 40.078125 35.4375 \n",
       "Q 35.15625 39.890625 26.703125 39.890625 \n",
       "Q 22.75 39.890625 18.8125 39.015625 \n",
       "Q 14.890625 38.140625 10.796875 36.28125 \n",
       "z\n",
       "\" id=\"BitstreamVeraSans-Roman-35\"/>\n",
       "      </defs>\n",
       "      <g transform=\"translate(90.5382142857 365.918125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-35\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"xtick_3\">\n",
       "     <g id=\"line2d_5\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"156.07\" xlink:href=\"#mffc13c70cb\" y=\"352.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_6\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"156.07\" xlink:href=\"#mb797512127\" y=\"7.2\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_3\">\n",
       "      <!-- 10 -->\n",
       "      <defs>\n",
       "       <path d=\"M 12.40625 8.296875 \n",
       "L 28.515625 8.296875 \n",
       "L 28.515625 63.921875 \n",
       "L 10.984375 60.40625 \n",
       "L 10.984375 69.390625 \n",
       "L 28.421875 72.90625 \n",
       "L 38.28125 72.90625 \n",
       "L 38.28125 8.296875 \n",
       "L 54.390625 8.296875 \n",
       "L 54.390625 0 \n",
       "L 12.40625 0 \n",
       "z\n",
       "\" id=\"BitstreamVeraSans-Roman-31\"/>\n",
       "      </defs>\n",
       "      <g transform=\"translate(148.435 365.918125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-31\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-30\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"xtick_4\">\n",
       "     <g id=\"line2d_7\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"217.784285714\" xlink:href=\"#mffc13c70cb\" y=\"352.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_8\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"217.784285714\" xlink:href=\"#mb797512127\" y=\"7.2\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_4\">\n",
       "      <!-- 15 -->\n",
       "      <g transform=\"translate(210.149285714 365.918125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-31\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-35\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"xtick_5\">\n",
       "     <g id=\"line2d_9\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"279.498571429\" xlink:href=\"#mffc13c70cb\" y=\"352.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_10\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"279.498571429\" xlink:href=\"#mb797512127\" y=\"7.2\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_5\">\n",
       "      <!-- 20 -->\n",
       "      <defs>\n",
       "       <path d=\"M 19.1875 8.296875 \n",
       "L 53.609375 8.296875 \n",
       "L 53.609375 0 \n",
       "L 7.328125 0 \n",
       "L 7.328125 8.296875 \n",
       "Q 12.9375 14.109375 22.625 23.890625 \n",
       "Q 32.328125 33.6875 34.8125 36.53125 \n",
       "Q 39.546875 41.84375 41.421875 45.53125 \n",
       "Q 43.3125 49.21875 43.3125 52.78125 \n",
       "Q 43.3125 58.59375 39.234375 62.25 \n",
       "Q 35.15625 65.921875 28.609375 65.921875 \n",
       "Q 23.96875 65.921875 18.8125 64.3125 \n",
       "Q 13.671875 62.703125 7.8125 59.421875 \n",
       "L 7.8125 69.390625 \n",
       "Q 13.765625 71.78125 18.9375 73 \n",
       "Q 24.125 74.21875 28.421875 74.21875 \n",
       "Q 39.75 74.21875 46.484375 68.546875 \n",
       "Q 53.21875 62.890625 53.21875 53.421875 \n",
       "Q 53.21875 48.921875 51.53125 44.890625 \n",
       "Q 49.859375 40.875 45.40625 35.40625 \n",
       "Q 44.1875 33.984375 37.640625 27.21875 \n",
       "Q 31.109375 20.453125 19.1875 8.296875 \n",
       "\" id=\"BitstreamVeraSans-Roman-32\"/>\n",
       "      </defs>\n",
       "      <g transform=\"translate(271.863571429 365.918125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-32\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-30\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"xtick_6\">\n",
       "     <g id=\"line2d_11\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"341.212857143\" xlink:href=\"#mffc13c70cb\" y=\"352.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_12\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"341.212857143\" xlink:href=\"#mb797512127\" y=\"7.2\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_6\">\n",
       "      <!-- 25 -->\n",
       "      <g transform=\"translate(333.577857143 365.918125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-32\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-35\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "   </g>\n",
       "   <g id=\"matplotlib.axis_2\">\n",
       "    <g id=\"ytick_1\">\n",
       "     <g id=\"line2d_13\">\n",
       "      <defs>\n",
       "       <path d=\"M 0 0 \n",
       "L 4 0 \n",
       "\" id=\"mb9aab1434f\" style=\"stroke:#000000;stroke-width:0.5;\"/>\n",
       "      </defs>\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"26.47\" xlink:href=\"#mb9aab1434f\" y=\"13.3714285714\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_14\">\n",
       "      <defs>\n",
       "       <path d=\"M 0 0 \n",
       "L -4 0 \n",
       "\" id=\"m1f9bfeebf3\" style=\"stroke:#000000;stroke-width:0.5;\"/>\n",
       "      </defs>\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"372.07\" xlink:href=\"#m1f9bfeebf3\" y=\"13.3714285714\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_7\">\n",
       "      <!-- 0 -->\n",
       "      <g transform=\"translate(14.835 16.6826785714)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-30\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"ytick_2\">\n",
       "     <g id=\"line2d_15\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"26.47\" xlink:href=\"#mb9aab1434f\" y=\"75.0857142857\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_16\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"372.07\" xlink:href=\"#m1f9bfeebf3\" y=\"75.0857142857\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_8\">\n",
       "      <!-- 5 -->\n",
       "      <g transform=\"translate(14.835 78.3969642857)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-35\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"ytick_3\">\n",
       "     <g id=\"line2d_17\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"26.47\" xlink:href=\"#mb9aab1434f\" y=\"136.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_18\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"372.07\" xlink:href=\"#m1f9bfeebf3\" y=\"136.8\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_9\">\n",
       "      <!-- 10 -->\n",
       "      <g transform=\"translate(7.2 140.11125)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-31\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-30\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"ytick_4\">\n",
       "     <g id=\"line2d_19\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"26.47\" xlink:href=\"#mb9aab1434f\" y=\"198.514285714\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_20\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"372.07\" xlink:href=\"#m1f9bfeebf3\" y=\"198.514285714\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_10\">\n",
       "      <!-- 15 -->\n",
       "      <g transform=\"translate(7.2 201.825535714)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-31\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-35\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"ytick_5\">\n",
       "     <g id=\"line2d_21\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"26.47\" xlink:href=\"#mb9aab1434f\" y=\"260.228571429\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_22\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"372.07\" xlink:href=\"#m1f9bfeebf3\" y=\"260.228571429\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_11\">\n",
       "      <!-- 20 -->\n",
       "      <g transform=\"translate(7.2 263.539821429)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-32\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-30\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "    <g id=\"ytick_6\">\n",
       "     <g id=\"line2d_23\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"26.47\" xlink:href=\"#mb9aab1434f\" y=\"321.942857143\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"line2d_24\">\n",
       "      <g>\n",
       "       <use style=\"stroke:#000000;stroke-width:0.5;\" x=\"372.07\" xlink:href=\"#m1f9bfeebf3\" y=\"321.942857143\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "     <g id=\"text_12\">\n",
       "      <!-- 25 -->\n",
       "      <g transform=\"translate(7.2 325.254107143)scale(0.12 -0.12)\">\n",
       "       <use xlink:href=\"#BitstreamVeraSans-Roman-32\"/>\n",
       "       <use x=\"63.623046875\" xlink:href=\"#BitstreamVeraSans-Roman-35\"/>\n",
       "      </g>\n",
       "     </g>\n",
       "    </g>\n",
       "   </g>\n",
       "  </g>\n",
       " </g>\n",
       " <defs>\n",
       "  <clipPath id=\"p4178fa998b\">\n",
       "   <rect height=\"345.6\" width=\"345.6\" x=\"26.47\" y=\"7.2\"/>\n",
       "  </clipPath>\n",
       " </defs>\n",
       "</svg>\n"
      ],
      "text/plain": [
       "PyPlot.Figure(PyObject <matplotlib.figure.Figure object at 0x31c67a7d0>)"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "PyObject <matplotlib.image.AxesImage object at 0x31c6dbb90>"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# n = len(mnist.test.images)\n",
    "n = size(mnist[:test][:images], 1)\n",
    "# i = random.randrange(n)\n",
    "i = rand(1:n)\n",
    "\n",
    "# imageData = mnist.test.images[i]\n",
    "imageData = mnist[:test][:images][i,:]\n",
    "# label = mnist.test.labels[i]\n",
    "label = mnist[:test][:labels][i,:]\n",
    "\n",
    "result = sess[:run](y, feed_dict=Dict(x => imageData, y_ => label))\n",
    "println(\"Classified as: $(indmax(result)-1)\")\n",
    "\n",
    "image = reshape(imageData, 28, 28)'\n",
    "\n",
    "# plt.imshow(image, cmap = cm.Greys)\n",
    "imshow(image, cmap=get_cmap(\"Greys\"))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Julia 0.4.3",
   "language": "julia",
   "name": "julia-0.4"
  },
  "language_info": {
   "file_extension": ".jl",
   "mimetype": "application/julia",
   "name": "julia",
   "version": "0.4.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}