{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "from tensorflow.examples.tutorials.mnist import input_data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "def init_weights(shape):\n",
    "    return tf.Variable(tf.random_normal(shape, stddev=0.01))\n",
    "\n",
    "def model(X, w):\n",
    "    return tf.matmul(X, w) # notice we use the same model as linear regression, this is because there is a baked in cost function which performs softmax and cross entropy\n",
    "\n",
    "mnist = input_data.read_data_sets(\"MNIST_data/\", one_hot=True)\n",
    "trX, trY, teX, teY = mnist.train.images, mnist.train.labels, mnist.test.images, mnist.test.labels"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "X = tf.placeholder(\"float\", [None, 784]) # create symbolic variables\n",
    "Y = tf.placeholder(\"float\", [None, 10])\n",
    "\n",
    "w = init_weights([784, 10]) # like in linear regression, we need a shared variable weight matrix for logistic regression\n",
    "\n",
    "py_x = model(X, w)\n",
    "\n",
    "cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=py_x, labels=Y)) # compute mean cross entropy (softmax is applied internally)\n",
    "train_op = tf.train.GradientDescentOptimizer(0.05).minimize(cost) # construct optimizer\n",
    "predict_op = tf.argmax(py_x, 1) # at predict time, evaluate the argmax of the logistic regression"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [],
   "source": [
    "# Launch the graph in a session\n",
    "with tf.Session() as sess:\n",
    "    # you need to initialize all variables\n",
    "    tf.global_variables_initializer().run()\n",
    "\n",
    "    for i in range(100):\n",
    "        for start, end in zip(range(0, len(trX), 128), range(128, len(trX)+1, 128)):\n",
    "            sess.run(train_op, feed_dict={X: trX[start:end], Y: trY[start:end]})\n",
    "        print(i, np.mean(np.argmax(teY, axis=1) ==\n",
    "                         sess.run(predict_op, feed_dict={X: teX})))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "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": "2.7.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}