Cleaned and refactored for TF 1.0.

Author: Kyubyong

Control_Flow.ipynb

@@ -15,6 +15,7 @@
    },
    "outputs": [],
    "source": [
+    "from __future__ import print_function\n",
     "import tensorflow as tf\n",
     "import numpy as np"
    ]
@@ -27,17 +28,19 @@
    },
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0.10.0\n",
-      "1.11.1\n"
-     ]
+     "data": {
+      "text/plain": [
+       "datetime.date(2017, 2, 22)"
+      ]
+     },
+     "execution_count": 2,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
    "source": [
-    "print tf.__version__\n",
-    "print np.__version__"
+    "from datetime import date\n",
+    "date.today()"
    ]
   },
   {
@@ -48,44 +51,93 @@
    },
    "outputs": [],
    "source": [
-    "sess = tf.InteractiveSession()"
+    "author = \"kyubyong. https://github.com/Kyubyong/tensorflow-exercises\""
    ]
   },
   {
-   "cell_type": "markdown",
-   "metadata": {},
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "collapsed": false
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'1.0.0'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
-    "Q1. Let x and y be random 0-D tensors. Return x + y \n",
-    "if x < y and x - y otherwise."
+    "tf.__version__"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 5,
    "metadata": {
     "collapsed": false
    },
    "outputs": [
     {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "0.469627\n"
-     ]
+     "data": {
+      "text/plain": [
+       "'1.12.0'"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
     }
    ],
-   "source": []
+   "source": [
+    "np.__version__"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": [
+    "sess = tf.InteractiveSession()"
+   ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q2. Let x and y be 0-D int tensors randomly selected from 0 to 5. Return x + y 2 if x < y, x - y elif x > y, 0 otherwise."
+    "NOTE on notation\n",
+    "* _x, _y, _z, ...: NumPy 0-d or 1-d arrays\n",
+    "* _X, _Y, _Z, ...: NumPy 2-d or higer dimensional arrays\n",
+    "* x, y, z, ...: 0-d or 1-d tensors\n",
+    "* X, Y, Z, ...: 2-d or higher dimensional tensors"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Control Flow Operations"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Q1. Let x and y be random 0-D tensors. Return x + y \n",
+    "if x < y and x - y otherwise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 7,
    "metadata": {
     "collapsed": false
    },
@@ -94,7 +146,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1\n"
+      "1.75876\n",
+      "0.9915587370245782\n"
      ]
     }
    ],
@@ -104,12 +157,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q3. Let x be a tensor [[-1, -2, -3], [0, 1, 2]] and y be a tensor of zeros with the same shape as x. Return a boolean tensor that yields Trues if x equals y elementwise."
+    "Q2. Let x and y be 0-D int32 tensors randomly selected from 0 to 5. Return x + y 2 if x < y, x - y elif x > y, 0 otherwise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 8,
    "metadata": {
     "collapsed": false
    },
@@ -118,8 +171,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[False False False]\n",
-      " [ True False False]]\n"
+      "1\n",
+      "1\n"
      ]
     }
    ],
@@ -129,12 +182,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q4. Let x be a tensor [[-1, -2, -3], [0, 1, 2]] and y be a tensor of zeros with the same shape as x. Return a boolean tensor that yields Trues if x does not equal y elementwise."
+    "Q3. Let X be a tensor [[-1, -2, -3], [0, 1, 2]] and Y be a tensor of zeros with the same shape as X. Return a boolean tensor that yields True if X equals Y elementwise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 45,
+   "execution_count": 9,
    "metadata": {
     "collapsed": false
    },
@@ -143,8 +196,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[ True  True  True]\n",
-      " [False  True  True]]\n"
+      "[[False False False]\n",
+      " [ True False False]]\n"
      ]
     }
    ],
@@ -154,12 +207,19 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q5. Let x be a tensor [[-1, -2, -3], [0, 1, 2]] and y be a tensor of zeros with the same shape as x. Return a boolean tensor that yields Trues if x is greater than or equal to y elementwise."
+    "## Logical Operators"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Q4. Given x and y below, return the truth value x AND/OR/XOR y element-wise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 46,
+   "execution_count": 10,
    "metadata": {
     "collapsed": false
    },
@@ -168,23 +228,25 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[False False False]\n",
-      " [ True  True  True]]\n"
+      "[ True False False] [ True  True False] [False  True False]\n"
      ]
     }
    ],
-   "source": []
+   "source": [
+    "x = tf.constant([True, False, False], tf.bool)\n",
+    "y = tf.constant([True, True, False], tf.bool)\n"
+   ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q6. Let x be a tensor [[-1, -2, -3], [0, 1, 2]] and y be a tensor of zeros with the same shape as x. Return a boolean tensor that yields Trues if x is less than or equal to y elementwise.\n"
+    "Q5. Given x, return the truth value of NOT x element-wise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 47,
+   "execution_count": 11,
    "metadata": {
     "collapsed": false
    },
@@ -193,23 +255,31 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[ True  True  True]\n",
-      " [ True False False]]\n"
+      "[False  True  True]\n"
      ]
     }
    ],
-   "source": []
+   "source": [
+    "x = tf.constant([True, False, False], tf.bool)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Comparison Operators"
+   ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q7. Let x be a 0-D tensor randomly selected from -5 to 5. Return a boolean tensor that yields Trues if x is less than 3 and x is greater than 0.\n"
+    "Q6. Let X be a tensor [[-1, -2, -3], [0, 1, 2]] and Y be a tensor of zeros with the same shape as x. Return a boolean tensor that yields True if X does not equal Y elementwise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 12,
    "metadata": {
     "collapsed": false
    },
@@ -218,7 +288,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "True\n"
+      "[[ True  True  True]\n",
+      " [False  True  True]]\n"
      ]
     }
    ],
@@ -228,12 +299,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q8. Let x be a tensor [[1, 2], [3, 4]], y be a tensor [[5, 6], [7, 8]], and z be a boolean tensor [[True, False], [False, True]]. Create a 2*2 tensor such that each element corresponds to x if True, otherise y."
+    "Q7. Let X be a tensor [[-1, -2, -3], [0, 1, 2]] and Y be a tensor of zeros with the same shape as X. Return a boolean tensor that yields True if X is greater than or equal to Y elementwise."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 51,
+   "execution_count": 13,
    "metadata": {
     "collapsed": false
    },
@@ -242,8 +313,8 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[[1 6]\n",
-      " [7 4]]\n"
+      "[[False False False]\n",
+      " [ True  True  True]]\n"
      ]
     }
    ],
@@ -253,12 +324,12 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Q9. Let x be a tensor [1, 2, 3, ..., 100]. Extract elements of x greater than 30."
+    "Q8. Let X be a tensor [[1, 2], [3, 4]], Y be a tensor [[5, 6], [7, 8]], and Z be a boolean tensor [[True, False], [False, True]]. Create a 2*2 tensor such that each element corresponds to X if Z is True, otherise Y."
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 75,
+   "execution_count": 14,
    "metadata": {
     "collapsed": false
    },
@@ -267,14 +338,14 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "[ 31  32  33  34  35  36  37  38  39  40  41  42  43  44  45  46  47  48\n",
-      "  49  50  51  52  53  54  55  56  57  58  59  60  61  62  63  64  65  66\n",
-      "  67  68  69  70  71  72  73  74  75  76  77  78  79  80  81  82  83  84\n",
-      "  85  86  87  88  89  90  91  92  93  94  95  96  97  98  99 100]\n"
+      "[[1 6]\n",
+      " [7 4]]\n"
      ]
     }
    ],
-   "source": []
+   "source": [
+    "\n"
+   ]
   },
   {
    "cell_type": "code",
@@ -287,22 +358,23 @@
   }
  ],
  "metadata": {
+  "anaconda-cloud": {},
   "kernelspec": {
-   "display_name": "Python 2",
+   "display_name": "Python [conda root]",
    "language": "python",
-   "name": "python2"
+   "name": "conda-root-py"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.6"
+   "pygments_lexer": "ipython3",
+   "version": "3.5.2"
   }
  },
  "nbformat": 4,