{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![book](https://raw.githubusercontent.com/ageron/tensorflow-safari-course/master/images/intro_to_tf_course.png)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Try not to peek at the solutions when you go through the exercises. ;-)**"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "First let's make sure this notebook works well in both Python 2 and Python 3:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from __future__ import absolute_import, division, print_function, unicode_literals"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# TensorFlow basics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "tf.__version__"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Construction Phase"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ">>> a = tf.constant(3)\n",
    ">>> b = tf.constant(5)\n",
    ">>> s = a + b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "a"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "s"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "tf.get_default_graph()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ">>> graph = tf.Graph()\n",
    ">>> with graph.as_default():\n",
    "...     a = tf.constant(3)\n",
    "...     b = tf.constant(5)\n",
    "...     s = a + b\n",
    "..."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Execution Phase"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ">>> with tf.Session(graph=graph) as sess:\n",
    "...     result = s.eval()\n",
    "...\n",
    ">>> result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ">>> with tf.Session(graph=graph) as sess:\n",
    "...     result = sess.run(s)\n",
    "...\n",
    ">>> result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    ">>> with tf.Session(graph=graph) as sess:\n",
    "...     result = sess.run([a,b,s])\n",
    "...\n",
    ">>> result"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exercise 1"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![Exercise](https://c1.staticflickr.com/9/8101/8553474140_c50cf08708_b.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.1) Create a simple graph that calculates $ c = \\exp(\\sqrt 8 + 3) $.\n",
    "\n",
    "**Tip**: TensorFlow's API documentation is available at:\n",
    "https://www.tensorflow.org/versions/master/api_docs/python/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.2) Now create a `Session()` and evaluate the operation that gives you the result of the equation above:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.3) Create a graph that evaluates and prints both $ b = \\sqrt 8 $ and $ c = \\exp(\\sqrt 8 + 3) $. Try to implement this in a way that only evaluates $ \\sqrt 8 $ once."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.4) The following code is needed to display TensorFlow graphs in Jupyter. Just run this cell then visualize your graph by calling `show_graph(`_your graph_`)`:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from IPython.display import display, HTML\n",
    "\n",
    "def strip_consts(graph_def, max_const_size=32):\n",
    "    \"\"\"Strip large constant values from graph_def.\"\"\"\n",
    "    strip_def = tf.GraphDef()\n",
    "    for n0 in graph_def.node:\n",
    "        n = strip_def.node.add() \n",
    "        n.MergeFrom(n0)\n",
    "        if n.op == 'Const':\n",
    "            tensor = n.attr['value'].tensor\n",
    "            size = len(tensor.tensor_content)\n",
    "            if size > max_const_size:\n",
    "                tensor.tensor_content = b\"<stripped %d bytes>\"%size\n",
    "    return strip_def\n",
    "\n",
    "def show_graph(graph_def=None, max_const_size=32):\n",
    "    \"\"\"Visualize TensorFlow graph.\"\"\"\n",
    "    graph_def = graph_def or tf.get_default_graph()\n",
    "    if hasattr(graph_def, 'as_graph_def'):\n",
    "        graph_def = graph_def.as_graph_def()\n",
    "    strip_def = strip_consts(graph_def, max_const_size=max_const_size)\n",
    "    code = \"\"\"\n",
    "        <script>\n",
    "          function load() {{\n",
    "            document.getElementById(\"{id}\").pbtxt = {data};\n",
    "          }}\n",
    "        </script>\n",
    "        <link rel=\"import\" href=\"https://tensorboard.appspot.com/tf-graph-basic.build.html\" onload=load()>\n",
    "        <div style=\"height:600px\">\n",
    "          <tf-graph-basic id=\"{id}\"></tf-graph-basic>\n",
    "        </div>\n",
    "    \"\"\".format(data=repr(str(strip_def)), id='graph'+str(np.random.rand()))\n",
    "\n",
    "    iframe = \"\"\"\n",
    "        <iframe seamless style=\"width:1200px;height:620px;border:0\" srcdoc=\"{}\"></iframe>\n",
    "    \"\"\".format(code.replace('\"', '&quot;'))\n",
    "    display(HTML(iframe))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Try not to peek at the solution below before you have done the exercise! :)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "![thinking](https://upload.wikimedia.org/wikipedia/commons/0/06/Filos_segundo_logo_%28flipped%29.jpg)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exercise 1 - Solution"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "graph = tf.Graph()\n",
    "with graph.as_default():\n",
    "    c = tf.exp(tf.add(tf.sqrt(tf.constant(8.)), tf.constant(3.)))\n",
    "    # or simply...\n",
    "    c = tf.exp(tf.sqrt(8.) + 3.)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with tf.Session(graph=graph):\n",
    "    c_val = c.eval()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c_val"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "graph = tf.Graph()\n",
    "with graph.as_default():\n",
    "    b = tf.sqrt(8.)\n",
    "    c = tf.exp(b + 3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "with tf.Session(graph=graph) as sess:\n",
    "    b_val, c_val = sess.run([b, c])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "c_val"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Important**: the following implementation gives the right result, but it runs the graph twice, once to evaluate `b`, and once to evaluate `c`.  Since `c` depends on `b`, it means that `b` will be evaluated twice. Not what we wanted."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# WRONG!\n",
    "with tf.Session(graph=graph):\n",
    "    b_val = b.eval()  # evaluates b\n",
    "    c_val = c.eval()  # evaluates c, which means evaluating b again!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "b_val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "c_val"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "1.4)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "show_graph(graph)"
   ]
  }
 ],
 "metadata": {
  "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": "3.6.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}