{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "MHvuWIUHdIpt"
   },
   "source": [
    "Adapted by Tias Guns <Tias.Guns@kuleuven.be>, based (very heavily) on:\n",
    "\n",
    "## Handwritten Digit Recognition\n",
    "- Author = Amitrajit Bose\n",
    "- Dataset = MNIST\n",
    "- [Medium Article Link](https://medium.com/@amitrajit_bose/handwritten-digit-mnist-pytorch-977b5338e627)\n",
    "- Frameworks = PyTorch\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "oGjRmijsaXJ3"
   },
   "source": [
    "### Installation\n",
    "\n",
    "Recommended installation instructions:\n",
    "https://pytorch.org/get-started/locally\n",
    "\n",
    "This typically involves installing python3, python3-numpy, python3-matplotlib through an installer (anaconda) or system manager (apt), then installing torch and torchvision from python through conda or pip."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {},
    "colab_type": "code",
    "id": "TOyGrPT5ASDc"
   },
   "outputs": [],
   "source": [
    "# Import necessary packages\n",
    "%matplotlib inline\n",
    "%config InlineBackend.figure_format = 'retina'\n",
    "\n",
    "import os\n",
    "import numpy as np\n",
    "import torch\n",
    "import torchvision\n",
    "import matplotlib.pyplot as plt\n",
    "from time import time"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "uLdtrS4zaeEs"
   },
   "source": [
    "### Download The Dataset & Define The Transforms\n",
    "\n",
    "It is best to do this before the practical; + it allows you to test whether your setup works!\n",
    "\n",
    "It will download the files into the __same directory as where you stored this notebook__.\n",
    "\n",
    "It will take a minute or two. It will only download it once, so you can rerun this cell over and over."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 119
    },
    "colab_type": "code",
    "id": "sZD2NGz2Ak6w",
    "outputId": "74eec0da-d867-406b-be2c-4013a2162bf1"
   },
   "outputs": [],
   "source": [
    "from torchvision import datasets, transforms\n",
    "\n",
    "# Define a transform to normalize the data (effect: all values between -1 and 1)\n",
    "transform = transforms.Compose([transforms.ToTensor(),\n",
    "                                transforms.Normalize((0.5,), (0.5,))])\n",
    "\n",
    "# Download and load the training data\n",
    "trainset = datasets.MNIST('.', download=True, train=True, transform=transform)\n",
    "testset = datasets.MNIST('.', download=True, train=False, transform=transform)\n",
    "trainloader = torch.utils.data.DataLoader(trainset, batch_size=128, shuffle=True)\n",
    "testloader = torch.utils.data.DataLoader(testset, batch_size=128, shuffle=True)\n",
    "print(\"Data loaded.\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "colab_type": "text",
    "id": "GcAfrn2falkK"
   },
   "source": [
    "### Exploring The Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 68
    },
    "colab_type": "code",
    "id": "xOjlOyjcCezX",
    "outputId": "fde25724-ea30-46f6-cf0f-4a7807c2ee0e"
   },
   "outputs": [],
   "source": [
    "dataiter = iter(trainloader)\n",
    "images, labels = dataiter.next()\n",
    "print(type(images))\n",
    "print(images.shape)\n",
    "print(labels.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The above shows that one batch of training data contains 128 images, and that each image is 28x28 pixels.\n",
    "\n",
    "Let's display one image:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 265
    },
    "colab_type": "code",
    "id": "EuBvOWmGDHOq",
    "outputId": "127e0264-be67-4f12-b03f-dac28b7280af"
   },
   "outputs": [],
   "source": [
    "plt.imshow(images[0].numpy().squeeze(), cmap='gray_r');"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Let's display a grid of images!"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 265
    },
    "colab_type": "code",
    "id": "F9CppCcqDLtB",
    "outputId": "0f59838b-90b6-4370-e23a-0e4a0ba90c2a",
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "def show_grid_img(images):\n",
    "    dim = 9\n",
    "    figure = plt.figure()\n",
    "    num_of_images = dim*dim\n",
    "    for index in range(num_of_images):\n",
    "        plt.subplot(dim, dim, index+1)\n",
    "        plt.axis('off')\n",
    "        plt.imshow(images[index].numpy().squeeze(), cmap='gray_r')\n",
    "\n",
    "dataiter = iter(trainloader)\n",
    "images, labels = dataiter.next()\n",
    "show_grid_img(images)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If you see a grid of images, your system is __ready__ for the practical of Wednesday.\n",
    "\n",
    "__Optional:__ To use the CPMpy modeling environment and _ortools_ CP solver, you should do install them as such:\n",
    "<pre>python3 -m pip install -U --user cpmpy ortools</pre>\n",
    "\n",
    "Test in the following cell."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from cpmpy import *\n",
    "\n",
    "x = IntVar(1,3, name=\"x\") # x \\in {1,2,3}\n",
    "csp = Model([\n",
    "    x > 1,\n",
    "    x != 2,\n",
    "])\n",
    "\n",
    "if csp.solve():\n",
    "    print(\"X =\",x.value())\n",
    "else:\n",
    "    print(\"CSP infeasible\")"
   ]
  }
 ],
 "metadata": {
  "colab": {
   "collapsed_sections": [],
   "name": "handwritten_digit_recognition_CPU.ipynb",
   "provenance": [],
   "version": "0.3.2"
  },
  "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": "3.7.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}