ML0120EN-5.1-Review-Autoencoders.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<img src=\"https://cf-courses-data.s3.us.cloud-object-storage.appdomain.cloud/IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork/images/IDSN-logo.png\" width=\"300\" alt=\"cognitiveclass.ai logo\">\n",
    "\n",
    "<h1 align=\"center\"><font size=\"5\">AUTOENCODERS</font></h1>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Estimated time needed: **25** minutes\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<div class=\"alert alert-block alert-info\" style=\"margin-top: 20px\">\n",
    "Welcome to this notebook about autoencoders.\n",
    "<font size=\"3\"><strong>In this notebook you will learn the definition of an autoencoder, how it works, and see an implementation in TensorFlow.</strong></font>\n",
    "<br>\n",
    "<br>\n",
    "<h2>Table of Contents</h2>\n",
    "<ol>\n",
    " <li><a href=\"#ref1\">Introduction</a></li>\n",
    " <li><a href=\"#ref2\">Feature Extraction and Dimensionality Reduction</a></li>\n",
    " <li><a href=\"#ref3\">Autoencoder Structure</a></li>\n",
    " <li><a href=\"#ref4\">Performance</a></li>\n",
    " <li><a href=\"#ref5\">Training: Loss Function</a></li>\n",
    " <li><a href=\"#ref6\">Code</a></li>\n",
    "</ol>\n",
    "</div>\n",
    "<br>\n",
    "By the end of this notebook, you should be able to create simple autoencoders apply them to problems in the field of unsupervised learning.\n",
    "<br>\n",
    "<p></p>\n",
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"ref1\"></a>\n",
    "\n",
    "<h2>Introduction</h2>\n",
    "An autoencoder, also known as autoassociator or Diabolo networks, is an artificial neural network employed to recreate the given input.\n",
    "It takes a set of <b>unlabeled</b> inputs, encodes them and then tries to extract the most valuable information from them.\n",
    "They are used for feature extraction, learning generative models of data, dimensionality reduction and can be used for compression. \n",
    "\n",
    "A 2006 paper named <b><a href=\"https://www.cs.toronto.edu/~hinton/science.pdf?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">Reducing the Dimensionality of Data with Neural Networks</a>, done by G. E. Hinton and R. R. Salakhutdinov</b>, showed better results than years of refining other types of network, and was a breakthrough in the field of Neural Networks, a field that was \"stagnant\" for 10 years.\n",
    "\n",
    "Now, autoencoders, based on Restricted Boltzmann Machines, are employed in some of the largest deep learning applications. They are the building blocks of Deep Belief Networks (DBN).\n",
    "\n",
    "<center><img src=\"https://ibm.box.com/shared/static/xlkv9v7xzxhjww681dq3h1pydxcm4ktp.png\" style=\"width: 350px;\"></center>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"ref2\"></a>\n",
    "\n",
    "<h2>Feature Extraction and Dimensionality Reduction</h2>\n",
    "\n",
    "An example given by Nikhil Buduma in KdNuggets (<a href=\"http://www.kdnuggets.com/2015/03/deep-learning-curse-dimensionality-autoencoders.html?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">link</a>) gives an excellent explanation of the utility of this type of Neural Network.\n",
    "\n",
    "Say that you want to extract the emotion that a person in a photograph is feeling. Take the following 256x256 pixel grayscale picture as an example:\n",
    "\n",
    "<img src=\"https://ibm.box.com/shared/static/r5knpow4bk2farlvxia71e9jp2f2u126.png\">\n",
    "\n",
    "If we just use the raw image, we have too many dimensions to analyze.  This image is 256x256 pixels, which corresponds to an input vector of 65536 dimensions! Conventional cell phones can produce images in the  4000 x 3000 pixels range, which gives us 12 million dimensions to analyze.\n",
    "\n",
    "This is particularly problematic, since the difficulty of a machine learning problem is vastly increased as more dimensions are involved. According to a 1982 study by C.J. Stone (<a href=\"http://www-personal.umich.edu/~jizhu/jizhu/wuke/Stone-AoS82.pdf?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">link</a>), the time to fit a model, is optimal if:\n",
    "\n",
    "<br><br>\n",
    "\n",
    "<div class=\"alert alert-block alert-info\" style=\"margin-top: 20px\">\n",
    "<h3><strong>$$m^{-p/(2p+d)}$$</strong></h3>\n",
    "<br>\n",
    "Where:\n",
    "<br>\n",
    "m: Number of data points\n",
    "<br>\n",
    "d: Dimensionality of the data\n",
    "<br>\n",
    "p: Number of Parameters in the model\n",
    "</div>\n",
    "\n",
    "As you can see, it increases exponentially!\n",
    "\n",
    "Returning to our example, we don't need to use all of the 65,536 dimensions to classify an emotion.\n",
    "A human identifies emotions according to specific facial expressions, and some <b>key features</b>, like the shape of the mouth and eyebrows.\n",
    "\n",
    "<center><img src=\"https://ibm.box.com/shared/static/m8urvuqujkt2vt1ru1fnslzh24pv7hn4.png\" height=\"256\" width=\"256\"></center>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"ref3\"></a>\n",
    "\n",
    "<h2>Autoencoder Structure</h2>\n",
    "\n",
    "<img src=\"https://ibm.box.com/shared/static/no7omt2jhqvv7uuls7ihnzikyl9ysnfp.png\" style=\"width: 400px;\">\n",
    "\n",
    "An autoencoder can be divided in two parts, the <b>encoder</b> and the <b>decoder</b>.\n",
    "\n",
    "The encoder needs to compress the representation of an input. In this case, we are going to reduce the dimensions of the image of the example face from 2000 dimensions to only 30 dimensions.  We will acomplish this by running the data through the layers of our encoder.\n",
    "\n",
    "The decoder works like encoder network in reverse. It works to recreate the input as closely as possible.  The training procedure produces at the center of the network a compressed, low dimensional representation that can be decoded to obtain the higher dimensional representation with minimal loss of information between the input and the output.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"ref4\"></a>\n",
    "\n",
    "<h2>Performance</h2>\n",
    "\n",
    "After training has been completed, you can use the encoded data as a reliable low dimensional representation of the data.  This can be applied to many problems where dimensionality reduction seems appropriate.\n",
    "\n",
    "<img src=\"https://ibm.box.com/shared/static/yt3xyon4g2jyw1w9qup1mvx7cgh28l64.png\">\n",
    "\n",
    "This image was extracted from the G. E. Hinton and R. R. Salakhutdinovcomparing's <a href=\"https://www.cs.toronto.edu/~hinton/science.pdf?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">paper</a>, on the two-dimensional reduction for 500 digits of the MNIST, with PCA (Principal Component Analysis) on the left and autoencoder on the right. We can see that the autoencoder provided us with a better separation of data.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"ref5\"></a>\n",
    "\n",
    "<h2>Training: Loss function</h2>\n",
    "\n",
    "An autoencoder uses the <b>Loss</b> function to properly train the network. The Loss function will calculate the differences between our output and the expected results. After that, we can minimize this error with gradient descent. There are many types of Loss functions, and it is important to consider the type of problem (classification, regression, etc.) when choosing this funtion.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>Binary Values:</h3>\n",
    "$$L(W) = - \\sum_{k} (x_k log(\\hat{x}_k) + (1 - x_k) \\log (1 - \\hat{x}_k) \\ )$$\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For binary values, we can use an equation based on the sum of Bernoulli's cross-entropy.  This loss function is best for binary classification problems.\n",
    "\n",
    "$x_k$ is one of our inputs and $\\hat{x}_k$ is the respective output.  Note that:\n",
    "\n",
    "$$\\hat{x} = f(x,W)$$\n",
    "\n",
    "where $W$ is the full parameter set of the neural network.\n",
    "\n",
    "We use this function so that when $x_k=1$, we want the calculated value of $\\hat{x}_k$ to be very close to one, and likewise if $x_k=0$.\n",
    "\n",
    "If the value is one, we just need to calculate the first part of the formula, that is, $-x_k log(\\hat{x}_k)$. Which, turns out to just calculate $- log(\\hat{x}_k)$.  We explicitly exclude the second term to avoid numerical difficulties when computing the logarithm of very small numbers.\n",
    "\n",
    "Likewise, if the value is zero, we need to calculate just the second part, $(1 - x_k) \\log (1 - \\hat{x}_k))$ - which turns out to be $log (1 - \\hat{x}_k) $.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>Real values:</h3>\n",
    "$$L(W) = - \\frac{1}{2}\\sum_{k} (\\hat{x}_k- x_k \\ )^2$$\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For data where the value (not category) is important to reproduce, we can use the sum of squared errors (SSE) for our Loss function. This function is usually used in regressions.\n",
    "\n",
    "As it was with the above example, $x_k$ is one of our inputs and $\\hat{x}_k$ is the respective output, and we want to make our output as similar as possible to our input.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3>Computing Gradient</h3>\n",
    "\n",
    "The gradient of the loss function is an important and complex function.  It is defined as:\n",
    "    $$\\nabla_{W} L(W)_j = \\frac{\\partial f(x,W)}{\\partial{W_j}}$$\n",
    "\n",
    "Fortunately for us, TensorFlow computes these complex functions automatically when we define our functions that are used to compute loss!  They automatically manage the backpropagation algorithm, which is an efficient way of computing the gradients in complex neural networks.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<a id=\"ref6\"></a>\n",
    "\n",
    "<h2>Code</h2>\n",
    "\n",
    " We are going to use the MNIST dataset for our example.\n",
    "The following code was created by Aymeric Damien. You can find some of his code in <a href=\"https://github.com/aymericdamien\">here</a>. We made some modifications which allow us to import the datasets to Jupyter Notebooks.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's call our imports and make the MNIST data available to use.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "!pip install tensorflow==2.2.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2.2.0\n"
     ]
    },
    {
     "ename": "ValueError",
     "evalue": "please upgrade to TensorFlow 2.2.0-rc0, or restart your Kernel (Kernel->Restart & Clear Output)",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
      "\u001b[0;32m/tmp/ipykernel_385/2576421763.py\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      8\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__version__\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'2.2.0-rc0'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      9\u001b[0m     \u001b[0mprint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__version__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 10\u001b[0;31m     \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'please upgrade to TensorFlow 2.2.0-rc0, or restart your Kernel (Kernel->Restart & Clear Output)'\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     11\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mValueError\u001b[0m: please upgrade to TensorFlow 2.2.0-rc0, or restart your Kernel (Kernel->Restart & Clear Output)"
     ]
    }
   ],
   "source": [
    "#from __future__ import division, print_function, absolute_import\n",
    "\n",
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "if not tf.__version__ == '2.2.0-rc0':\n",
    "    print(tf.__version__)\n",
    "    raise ValueError('please upgrade to TensorFlow 2.2.0-rc0, or restart your Kernel (Kernel->Restart & Clear Output)')\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/mnist.npz\n",
      "11493376/11490434 [==============================] - 0s 0us/step\n"
     ]
    }
   ],
   "source": [
    "# Import MINST data\n",
    "mnist = tf.keras.datasets.mnist\n",
    "(x_train, y_train), (x_test, y_test) = mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "x_train = x_train.astype('float32') / 255.\n",
    "x_test = x_test.astype('float32') / 255."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "y_train = y_train.astype('float32') / 255.\n",
    "y_test = y_test.astype('float32') / 255."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-15 17:10:51.343167: W tensorflow/stream_executor/platform/default/dso_loader.cc:55] Could not load dynamic library 'libcuda.so.1'; dlerror: libcuda.so.1: cannot open shared object file: No such file or directory\n",
      "2023-05-15 17:10:51.343222: E tensorflow/stream_executor/cuda/cuda_driver.cc:313] failed call to cuInit: UNKNOWN ERROR (303)\n",
      "2023-05-15 17:10:51.343255: I tensorflow/stream_executor/cuda/cuda_diagnostics.cc:156] kernel driver does not appear to be running on this host (jupyterlab-pedromgomes): /proc/driver/nvidia/version does not exist\n",
      "2023-05-15 17:10:51.343635: I tensorflow/core/platform/cpu_feature_guard.cc:143] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA\n",
      "2023-05-15 17:10:51.354702: I tensorflow/core/platform/profile_utils/cpu_utils.cc:102] CPU Frequency: 2394285000 Hz\n",
      "2023-05-15 17:10:51.355553: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x7ff07c000b20 initialized for platform Host (this does not guarantee that XLA will be used). Devices:\n",
      "2023-05-15 17:10:51.355599: I tensorflow/compiler/xla/service/service.cc:176]   StreamExecutor device (0): Host, Default Version\n"
     ]
    }
   ],
   "source": [
    "x_image_train = tf.reshape(x_train, [-1,28,28,1])  \n",
    "x_image_train = tf.cast(x_image_train, 'float32') \n",
    "\n",
    "x_image_test = tf.reshape(x_test, [-1,28,28,1]) \n",
    "x_image_test = tf.cast(x_image_test, 'float32') "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We use the tf.keras.layers.Flatten() function to prepare the training data to be compatible with the encoding and decoding layer\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(60000, 28, 28)\n"
     ]
    }
   ],
   "source": [
    "print(x_train.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "flatten_layer = tf.keras.layers.Flatten()\n",
    "x_train = flatten_layer(x_train)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Notice how the <code>x_train.shape</code>  changes from (60000,28,28) to (60000, 784)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(60000, 784)\n"
     ]
    }
   ],
   "source": [
    "print(x_train.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, let's give the parameters that are going to be used by our NN.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "learning_rate = 0.01\n",
    "training_epochs = 20\n",
    "batch_size = 256\n",
    "display_step = 1\n",
    "examples_to_show = 10\n",
    "global_step = tf.Variable(0)\n",
    "total_batch = int(len(x_train) / batch_size)\n",
    "\n",
    "# Network Parameters\n",
    "n_hidden_1 = 256 # 1st layer num features\n",
    "n_hidden_2 = 128 # 2nd layer num features\n",
    "encoding_layer = 32 # final encoding bottleneck features\n",
    "n_input = 784 # MNIST data input (img shape: 28*28)\n",
    "\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3> encoder </h3>\n",
    "Now we need to create our encoder. For this, we are going to use tf.keras.layers.Dense with sigmoidal activation functions. Sigmoidal functions delivers great results with this type of network. This is due to having a good derivative that is well-suited to backpropagation. We can create our encoder using the sigmoidal function like this:\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "\n",
    "enocoding_1 = tf.keras.layers.Dense(n_hidden_1, activation=tf.nn.sigmoid)\n",
    "encoding_2 = tf.keras.layers.Dense(n_hidden_2, activation=tf.nn.sigmoid)\n",
    "encoding_final = tf.keras.layers.Dense(encoding_layer, activation=tf.nn.relu)\n",
    "\n",
    "# Building the encoder\n",
    "def encoder(x):\n",
    "    x_reshaped = flatten_layer(x)\n",
    "    # Encoder first layer with sigmoid activation #1\n",
    "    layer_1 = enocoding_1(x_reshaped)\n",
    "    # Encoder second layer with sigmoid activation #2\n",
    "    layer_2 = encoding_2(layer_1)\n",
    "    code = encoding_final(layer_2)\n",
    "    return code"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<h3> decoder </h3>\n",
    "\n",
    "You can see that the layer_1 in the encoder is the layer_2 in the decoder and vice-versa.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "decoding_1 = tf.keras.layers.Dense(n_hidden_2, activation=tf.nn.sigmoid)\n",
    "decoding_2 = tf.keras.layers.Dense(n_hidden_1, activation=tf.nn.sigmoid)\n",
    "decoding_final = tf.keras.layers.Dense(n_input)\n",
    "# Building the decoder\n",
    "def decoder(x):\n",
    "    # Decoder first layer with sigmoid activation #1\n",
    "    layer_1 = decoding_1(x)\n",
    "    # Decoder second layer with sigmoid activation #2\n",
    "    layer_2 = decoding_2(layer_1)\n",
    "    decode = self.decoding_final(layer_2)\n",
    "    return decode"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's construct our model.\n",
    "We  define a <code>cost</code> function to calculate the loss  and a <code>grad</code> function to calculate gradients that will be used in backpropagation.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "class AutoEncoder(tf.keras.Model):\n",
    "    def __init__(self):\n",
    "        super(AutoEncoder, self).__init__()\n",
    "\n",
    "        self.n_hidden_1 = n_hidden_1 # 1st layer num features\n",
    "        self.n_hidden_2 = n_hidden_2 # 2nd layer num features\n",
    "        self.encoding_layer = encoding_layer\n",
    "        self.n_input = n_input # MNIST data input (img shape: 28*28)\n",
    "\n",
    "        self.flatten_layer = tf.keras.layers.Flatten()\n",
    "        self.enocoding_1 = tf.keras.layers.Dense(self.n_hidden_1, activation=tf.nn.sigmoid)\n",
    "        self.encoding_2 = tf.keras.layers.Dense(self.n_hidden_2, activation=tf.nn.sigmoid)\n",
    "        self.encoding_final = tf.keras.layers.Dense(self.encoding_layer, activation=tf.nn.relu)\n",
    "        self.decoding_1 = tf.keras.layers.Dense(self.n_hidden_2, activation=tf.nn.sigmoid)\n",
    "        self.decoding_2 = tf.keras.layers.Dense(self.n_hidden_1, activation=tf.nn.sigmoid)\n",
    "        self.decoding_final = tf.keras.layers.Dense(self.n_input)\n",
    "\n",
    "\n",
    "    # Building the encoder\n",
    "    def encoder(self,x):\n",
    "        #x = self.flatten_layer(x)\n",
    "        layer_1 = self.enocoding_1(x)\n",
    "        layer_2 = self.encoding_2(layer_1)\n",
    "        code = self.encoding_final(layer_2)\n",
    "        return code\n",
    "        \n",
    "\n",
    "    # Building the decoder\n",
    "    def decoder(self, x):\n",
    "        layer_1 = self.decoding_1(x)\n",
    "        layer_2 = self.decoding_2(layer_1)\n",
    "        decode = self.decoding_final(layer_2)\n",
    "        return decode\n",
    "\n",
    "        \n",
    "    def call(self, x):\n",
    "        encoder_op  = self.encoder(x)\n",
    "        # Reconstructed Images\n",
    "        y_pred = self.decoder(encoder_op)\n",
    "        return y_pred\n",
    "        \n",
    "def cost(y_true, y_pred):\n",
    "    loss = tf.losses.mean_squared_error(y_true, y_pred)\n",
    "    cost = tf.reduce_mean(loss)\n",
    "    return cost\n",
    "\n",
    "def grad(model, inputs, targets):\n",
    "    #print('shape of inputs : ',inputs.shape)\n",
    "    #targets = flatten_layer(targets)\n",
    "    with tf.GradientTape() as tape:    \n",
    "        reconstruction = model(inputs)\n",
    "        loss_value = cost(targets, reconstruction)\n",
    "    return loss_value, tape.gradient(loss_value, model.trainable_variables),reconstruction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For training we will run for 20 epochs.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch: 0001 cost= 0.049763247\n",
      "Epoch: 0002 cost= 0.033494003\n",
      "Epoch: 0003 cost= 0.025581393\n",
      "Epoch: 0004 cost= 0.021141957\n",
      "Epoch: 0005 cost= 0.018737812\n",
      "Epoch: 0006 cost= 0.016268460\n",
      "Epoch: 0007 cost= 0.015390849\n",
      "Epoch: 0008 cost= 0.014105605\n",
      "Epoch: 0009 cost= 0.013134934\n",
      "Epoch: 0010 cost= 0.012040367\n",
      "Epoch: 0011 cost= 0.010677254\n",
      "Epoch: 0012 cost= 0.010184465\n",
      "Epoch: 0013 cost= 0.009154153\n",
      "Epoch: 0014 cost= 0.008717001\n",
      "Epoch: 0015 cost= 0.008633426\n",
      "Epoch: 0016 cost= 0.008132818\n",
      "Epoch: 0017 cost= 0.007782963\n",
      "Epoch: 0018 cost= 0.007419842\n",
      "Epoch: 0019 cost= 0.007256700\n",
      "Epoch: 0020 cost= 0.007264418\n",
      "Optimization Finished!\n"
     ]
    }
   ],
   "source": [
    "model = AutoEncoder()\n",
    "optimizer = tf.keras.optimizers.RMSprop(learning_rate)\n",
    "\n",
    "for epoch in range(training_epochs):\n",
    "    for i in range(total_batch):\n",
    "        x_inp = x_train[i : i + batch_size]\n",
    "        loss_value, grads, reconstruction = grad(model, x_inp, x_inp)\n",
    "        optimizer.apply_gradients(zip(grads, model.trainable_variables))\n",
    "    # Display logs per epoch step\n",
    "    if epoch % display_step == 0:\n",
    "        print(\"Epoch:\", '%04d' % (epoch+1),\n",
    "              \"cost=\", \"{:.9f}\".format(loss_value))\n",
    "\n",
    "print(\"Optimization Finished!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now, let's apply encoder and decoder for our tests.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Applying encode and decode over test set\n",
    "encode_decode = model(flatten_layer(x_image_test[:examples_to_show]))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's simply visualize our graphs!\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 1000x200 with 20 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Compare original images with their reconstructions\n",
    "f, a = plt.subplots(2, 10, figsize=(10, 2))\n",
    "for i in range(examples_to_show):\n",
    "    a[0][i].imshow(np.reshape(x_image_test[i], (28, 28)))\n",
    "    a[1][i].imshow(np.reshape(encode_decode[i], (28, 28)))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "As you can see, the reconstructions were successful. It can be seen that some noise were added to the image.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Want to learn more?\n",
    "\n",
    "Also, you can use **Watson Studio** to run these notebooks faster with bigger datasets.**Watson Studio** is IBM’s leading cloud solution for data scientists, built by data scientists. With Jupyter notebooks, RStudio, Apache Spark and popular libraries pre-packaged in the cloud, **Watson Studio** enables data scientists to collaborate on their projects without having to install anything. Join the fast-growing community of **Watson Studio** users today with a free account at [Watson Studio](https://cocl.us/ML0120EN_DSX).This is the end of this lesson. Thank you for reading this notebook, and good luck on your studies.\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Thanks for completing this lesson!\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Created by <a href=\"https://www.linkedin.com/in/franciscomagioli?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">Francisco Magioli</a>, <a href=\"https://ca.linkedin.com/in/erich-natsubori-sato?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">Erich Natsubori Sato</a>, <a href=\"https://ca.linkedin.com/in/saeedaghabozorgi?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\">Saeed Aghabozorgi</a>\n",
    "\n",
    "Updated to TF 2.X by  <a href=\"https://www.linkedin.com/in/samaya-madhavan?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01\"> Samaya Madhavan </a>\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### References:\n",
    "\n",
    "-   [https://en.wikipedia.org/wiki/Autoencoder](https://en.wikipedia.org/wiki/Autoencoder?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders/](http://ufldl.stanford.edu/tutorial/unsupervised/Autoencoders?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [http://www.slideshare.net/billlangjun/simple-introduction-to-autoencoder](http://www.slideshare.net/billlangjun/simple-introduction-to-autoencoder?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [http://www.slideshare.net/danieljohnlewis/piotr-mirowski-review-autoencoders-deep-learning-ciuuk14](http://www.slideshare.net/danieljohnlewis/piotr-mirowski-review-autoencoders-deep-learning-ciuuk14?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [https://cs.stanford.edu/~quocle/tutorial2.pdf](https://cs.stanford.edu/~quocle/tutorial2.pdf?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   <https://gist.github.com/hussius/1534135a419bb0b957b9>\n",
    "-   [http://www.deeplearningbook.org/contents/autoencoders.html](http://www.deeplearningbook.org/contents/autoencoders.html?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [http://www.kdnuggets.com/2015/03/deep-learning-curse-dimensionality-autoencoders.html/](http://www.kdnuggets.com/2015/03/deep-learning-curse-dimensionality-autoencoders.html?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [https://www.youtube.com/watch?v=xTU79Zs4XKY](https://www.youtube.com/watch?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&v=xTU79Zs4XKY&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n",
    "-   [http://www-personal.umich.edu/~jizhu/jizhu/wuke/Stone-AoS82.pdf](http://www-personal.umich.edu/~jizhu/jizhu/wuke/Stone-AoS82.pdf?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ)\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "<hr>\n",
    "\n",
    "Copyright © 2018 [Cognitive Class](https://cocl.us/DX0108EN_CC). This notebook and its source code are released under the terms of the [MIT License](https://bigdatauniversity.com/mit-license?utm_medium=Exinfluencer&utm_source=Exinfluencer&utm_content=000026UJ&utm_term=10006555&utm_id=NA-SkillsNetwork-Channel-SkillsNetworkCoursesIBMDeveloperSkillsNetworkDL0120ENSkillsNetwork954-2022-01-01&cm_mmc=Email_Newsletter-_-Developer_Ed%2BTech-_-WW_WW-_-SkillsNetwork-Courses-IBMDeveloperSkillsNetwork-DL0120EN-SkillsNetwork-20629446&cm_mmca1=000026UJ&cm_mmca2=10006555&cm_mmca3=M12345678&cvosrc=email.Newsletter.M12345678&cvo_campaign=000026UJ).\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python",
   "language": "python",
   "name": "conda-env-python-py"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}