lesson01-Overview/01_tensor_tutorial.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "01-tensor-tutorial.ipynb",
      "version": "0.3.2",
      "provenance": [],
      "collapsed_sections": [],
      "toc_visible": true,
      "include_colab_link": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "view-in-github",
        "colab_type": "text"
      },
      "source": [
        "<a href=\"https://colab.research.google.com/github/Alro10/PyTorch1.0Tutorials/blob/master/lesson01-Overview/01_tensor_tutorial.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fp9hbokQIxWW",
        "colab_type": "text"
      },
      "source": [
        "# A Gentle Introduction to  PyTorch\n",
        "\n",
        "---\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "z6RUp96FLuMd",
        "colab_type": "text"
      },
      "source": [
        "## Google Colaboratory\n",
        "\n",
        "First of all, take a moment to look around and discover Google Colab if you haven't before! You can run the commands below to understand how much resources you're using and are still available. Then consider also that you can also connect your Google Drive for additional space or for easily loading your own files.\n",
        "\n",
        "You can always reset the entire VM with \"*Runtime > Reset all runtime*\" in case of difficulty. Make also sure you're using the GPU or TPU in the same  tab (\"*Runtime > Change runtime type*\")."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pPViRmMBqbJ2",
        "colab_type": "code",
        "outputId": "f45c1a3c-55bc-4810-89a5-ed7f8f784393",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 514
        }
      },
      "source": [
        "!free -m\n",
        "!df -h\n",
        "!nvidia-smi # <Ctrl> + <Return>"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "              total        used        free      shared  buff/cache   available\n",
            "Mem:          13022         416       10844           0        1761       12332\n",
            "Swap:             0           0           0\n",
            "Filesystem      Size  Used Avail Use% Mounted on\n",
            "overlay         359G   23G  318G   7% /\n",
            "tmpfs           6.4G     0  6.4G   0% /dev\n",
            "tmpfs           6.4G     0  6.4G   0% /sys/fs/cgroup\n",
            "/dev/sda1       365G   28G  338G   8% /opt/bin\n",
            "tmpfs           6.4G   12K  6.4G   1% /var/colab\n",
            "shm             6.0G     0  6.0G   0% /dev/shm\n",
            "tmpfs           6.4G     0  6.4G   0% /sys/firmware\n",
            "Fri Apr 26 18:31:56 2019       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 418.56       Driver Version: 410.79       CUDA Version: 10.0     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   55C    P8    16W /  70W |      0MiB / 15079MiB |      0%      Default |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                       GPU Memory |\n",
            "|  GPU       PID   Type   Process name                             Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jt_PxOYPmxp_",
        "colab_type": "text"
      },
      "source": [
        "##  How to connect your G Drive with G Colab?\n",
        "\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UtrFVmecRucu",
        "colab_type": "code",
        "outputId": "f7b41d54-6d05-44b0-8f73-fbaf91bc2951",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 125
        }
      },
      "source": [
        "from google.colab import files\n",
        "# Load the Drive helper and mount\n",
        "from google.colab import drive\n",
        "\n",
        "# This will prompt for authorization.\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "# This is an example for connecting csv file with pandas, see how to invocate the directory: '/content/drive/My Drive/path/file.csv' \n",
        "# df = pd.read_csv('/content/drive/My Drive/path/file.csv', sep=',')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Go to this URL in a browser: https://accounts.google.com/o/oauth2/auth?client_id=947318989803-6bn6qk8qdgf4n4g3pfee6491hc0brc4i.apps.googleusercontent.com&redirect_uri=urn%3Aietf%3Awg%3Aoauth%3A2.0%3Aoob&scope=email%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdocs.test%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive.photos.readonly%20https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fpeopleapi.readonly&response_type=code\n",
            "\n",
            "Enter your authorization code:\n",
            "··········\n",
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DO871S1wjXbJ",
        "colab_type": "text"
      },
      "source": [
        "## Python native data types\n",
        "\n",
        "Python has many native datatypes. Here are the important ones:\n",
        "\n",
        " - **Booleans** are either `True` or `False`.\n",
        " - **Numbers** can be integers (1 and 2), floats (1.1 and 1.2), fractions (1/2 and 2/3), or even complex numbers.\n",
        " - **Strings** are sequences of Unicode characters, e.g. an html document.\n",
        " - **Lists** are ordered sequences of values.\n",
        " - **Tuples** are ordered, immutable sequences of values.\n",
        " - **Sets** are unordered bags of values.\n",
        " - **Dictionaries** are unordered bags of key-value pairs.\n",
        " \n",
        "See [here](http://www.diveintopython3.net/native-datatypes.html) for a complete overview.\n",
        "\n",
        "### More resources\n",
        "\n",
        " 1. Brief Python introduction [here](https://learnxinyminutes.com/docs/python3/).\n",
        " 2. Full Python tutorial [here](https://docs.python.org/3/tutorial/).\n",
        " 3. A Whirlwind Tour of Python [here](https://github.com/jakevdp/WhirlwindTourOfPython).\n",
        " 4. Python Data Science Handbook [here](https://github.com/jakevdp/PythonDataScienceHandbook)."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EiCPaGdjbdlt",
        "colab_type": "text"
      },
      "source": [
        "##What is Pytorch?\n",
        "It's is a famous Python based scientific computing package targeted at two sets of audiences:\n",
        "\n",
        "\n",
        "\n",
        "*   Tensorial library that uses power of Graphics Processing Units (GPU's)\n",
        "*   A Deep Learning research plattform that provides maximum flexitibility and speed\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dxBjm6T06c_M",
        "colab_type": "text"
      },
      "source": [
        "## Important: Pytorch 1.0 is available in G Colab for Python 3.6"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PIaCl2Cr7ZAv",
        "colab_type": "code",
        "outputId": "c35bd33d-3fcc-4ba8-8772-b89299912aa0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        }
      },
      "source": [
        "import torch\n",
        "print(torch.__version__)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "1.0.1.post2\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eaSUr-B3NEZq",
        "colab_type": "text"
      },
      "source": [
        "### See this in case you want to install PyTorch 0.4.0\n",
        "\n",
        "Tensorflow is installed by default in Google Colab (guess why :P). If you want to use another DL toolkit you have to do it by yourself. Run the command below to install it. It should take less than a couple of minutes."
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "herKnlqYGYdx",
        "colab_type": "code",
        "outputId": "e21c2415-61c2-4892-963b-7263812ac79d",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 133
        }
      },
      "source": [
        "# http://pytorch.org/\n",
        "!pip install http://download.pytorch.org/whl/cu80/torch-0.4.0-cp36-cp36m-linux_x86_64.whl \n",
        "!pip install torchvision\n",
        "\n",
        "import torch\n",
        "print('Torch', torch.__version__, 'CUDA', torch.version.cuda)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: torch==0.4.0 from http://download.pytorch.org/whl/cu80/torch-0.4.0-cp36-cp36m-linux_x86_64.whl in /usr/local/lib/python3.6/dist-packages (0.4.0)\n",
            "Requirement already satisfied: torchvision in /usr/local/lib/python3.6/dist-packages (0.2.1)\n",
            "Requirement already satisfied: pillow>=4.1.1 in /usr/local/lib/python3.6/dist-packages (from torchvision) (5.4.1)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from torchvision) (1.16.1)\n",
            "Requirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from torchvision) (1.12.0)\n",
            "Requirement already satisfied: torch in /usr/local/lib/python3.6/dist-packages (from torchvision) (0.4.0)\n",
            "Torch 0.4.0 CUDA 8.0.61\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "i74kZQufNv5d",
        "colab_type": "text"
      },
      "source": [
        "**Ok, torch is installed and imported! Let' see if it can see the GPU:**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "hv7FUJ2Wrd_l",
        "colab_type": "code",
        "outputId": "53dbc0a8-c81e-4945-8b9d-245f48b9a323",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "import torch\n",
        "torch.cuda.is_available()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "True"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 2
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yQmghCXjdPRn",
        "colab_type": "text"
      },
      "source": [
        "**Question to explore:**\n",
        "\n",
        "*   What's new in Pythorch 1.0?\n",
        "\n",
        "Some tips here: https://github.com/pytorch/pytorch/releases/tag/v1.0.0"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "JuSqVkPnN7iT",
        "colab_type": "text"
      },
      "source": [
        "**That's great, let us import then a few libraries, which we'll be using during this tutorial!**"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w7AxhUWe68vT",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "import torch"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ztZAPQNXZ4ll",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# switch to False to use CPU\n",
        "use_cuda = True\n",
        "\n",
        "use_cuda = use_cuda and torch.cuda.is_available()\n",
        "device = torch.device(\"cuda\" if use_cuda else \"cpu\");\n",
        "torch.manual_seed(1);"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "G8g9w49De7j9",
        "colab_type": "text"
      },
      "source": [
        "###Getting help in Jupyter"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wk8s1IY7eV9p",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# What about all `*Tensor`s?\n",
        "# Press <esc> to get out of help\n",
        "torch.*Tensor?"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U4c9Q2OxfI8J",
        "colab_type": "code",
        "outputId": "fe49e4e2-4c2d-4f1a-c3d7-36e57af2c5e1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "torch.nn.Module()  # <Shift>+<Tab>"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Module()"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QGPo7HGMh4u0",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Annotate your functions / classes!\n",
        "torch.nn.Module?"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cOep2gU5h-O6",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "torch.nn.Module??"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pxOe4L3iiQfq",
        "colab_type": "code",
        "outputId": "48317b49-67ae-4b15-ffdb-95d1810134cd",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# List all the files in the current directory\n",
        "!ls -lh"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "total 8.0K\n",
            "drwx------ 3 root root 4.0K Feb 25 15:36 drive\n",
            "drwxr-xr-x 1 root root 4.0K Feb 15 17:21 sample_data\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LXgJ7KRxjlNQ",
        "colab_type": "text"
      },
      "source": [
        "##Torch! \n",
        " Now let's see how to work with Tensors"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_NE48kKjjw5X",
        "colab_type": "code",
        "outputId": "3a8ac0eb-a4f4-461f-ed04-dd08f557dad4",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Generate a tensor of size 3x3x4\n",
        "t = torch.Tensor(3, 3, 4)\n",
        "type(t)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "torch.Tensor"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 5
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "spDkxPyJj9XP",
        "colab_type": "code",
        "outputId": "21edfcd2-e2d3-4184-d6e4-43aa2f64f6f2",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Get the size of the tensor\n",
        "t.size()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "torch.Size([3, 3, 4])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "af0mQK-wkC3v",
        "colab_type": "code",
        "outputId": "95ae87fd-79fc-4497-f0d6-92647c826b11",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# t.size() is a classic tuple =>\n",
        "print('t size:', ' \\u00D7 '.join(map(str, t.size())))"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "t size: 3 × 3 × 4\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "_9fwSNitkFsn",
        "colab_type": "code",
        "outputId": "8a97e52d-adc3-4ccd-a59a-8e5e1876f99b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        }
      },
      "source": [
        "# prints dimensional space and sub-dimensions\n",
        "print(f'point in a {t.numel()} dimensional space')\n",
        "print(f'organised in {t.dim()} sub-dimensions')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "point in a 36 dimensional space\n",
            "organised in 3 sub-dimensions\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "71-8kR3BkYfe",
        "colab_type": "code",
        "outputId": "9966c976-a532-4462-cb82-d2f9599e5a0a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 200
        }
      },
      "source": [
        "t"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[[ 1.0379e-37,  0.0000e+00,  1.2472e-43,  0.0000e+00],\n",
              "         [ 0.0000e+00,  0.0000e+00,  0.0000e+00,  0.0000e+00],\n",
              "         [ 0.0000e+00, -1.5249e+30,  7.0295e+28,  6.1949e-04]],\n",
              "\n",
              "        [[ 2.3328e-18,  6.9776e+22,  6.1972e-04,  7.2443e+22],\n",
              "         [ 7.7052e+31,  1.6533e+19,  7.7140e+31,  3.3806e-18],\n",
              "         [ 1.0900e+27,  2.3364e-18,  4.5447e+30,  3.0750e+29]],\n",
              "\n",
              "        [[ 1.9284e+31,  1.8891e+31,  2.0871e+37,  1.0887e+27],\n",
              "         [ 1.7830e+19,  1.7262e+25,  2.1975e+23,  7.1846e+22],\n",
              "         [ 2.5048e+07,  5.0625e-30, -5.8872e+21,  4.5872e-41]]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "9pSiy_vkkf1u",
        "colab_type": "code",
        "outputId": "7a545e13-17d7-499d-bc70-952eec019e26",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 200
        }
      },
      "source": [
        "# Mind the underscore!\n",
        "# Any operation that mutates a tensor in-place is post-fixed with an _.\n",
        "# For example: x.copy_(y), x.t_(), x.random_(n) will change x.\n",
        "t.random_(10)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[[5., 9., 4., 8.],\n",
              "         [3., 3., 1., 1.],\n",
              "         [9., 2., 8., 9.]],\n",
              "\n",
              "        [[6., 3., 3., 0.],\n",
              "         [2., 1., 2., 6.],\n",
              "         [0., 3., 6., 4.]],\n",
              "\n",
              "        [[3., 6., 4., 2.],\n",
              "         [9., 4., 8., 6.],\n",
              "         [7., 3., 7., 3.]]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GPk27MsoktqX",
        "colab_type": "code",
        "outputId": "1a1ba117-3a95-4304-9cbe-537be8d88257",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# This resizes the tensor permanently \n",
        "r = torch.Tensor(t)\n",
        "r.resize_(3, 8)\n",
        "r"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[5., 9., 4., 8., 3., 3., 1., 1.],\n",
              "        [9., 2., 8., 9., 6., 3., 3., 0.],\n",
              "        [2., 1., 2., 6., 0., 3., 6., 4.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vRNALIiACxOv",
        "colab_type": "code",
        "outputId": "e8e10092-16db-402f-d269-af9f02565bf0",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# As you can see zero_ would replace r with 0's which was originally filled with integers\n",
        "r.zero_()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[0., 0., 0., 0., 0., 0., 0., 0.],\n",
              "        [0., 0., 0., 0., 0., 0., 0., 0.],\n",
              "        [0., 0., 0., 0., 0., 0., 0., 0.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "U48TDvPfC6FN",
        "colab_type": "code",
        "outputId": "f70f6746-88fd-4140-fbe8-eadfedd8a009",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# This *is* important, sigh...\n",
        "s = r.clone()\n",
        "\n",
        "# In-place fill of 1's\n",
        "s.fill_(1)\n",
        "s"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[1., 1., 1., 1., 1., 1., 1., 1.],\n",
              "        [1., 1., 1., 1., 1., 1., 1., 1.],\n",
              "        [1., 1., 1., 1., 1., 1., 1., 1.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "O2dWtBloC_BW",
        "colab_type": "code",
        "outputId": "1583ae8c-f4c8-41e9-d76e-6d2b867b466a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# Because we cloned r, even though we did an in-place operation, this doesn't affect r\n",
        "r"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[0., 0., 0., 0., 0., 0., 0., 0.],\n",
              "        [0., 0., 0., 0., 0., 0., 0., 0.],\n",
              "        [0., 0., 0., 0., 0., 0., 0., 0.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "1c7SMexyDKSH",
        "colab_type": "text"
      },
      "source": [
        "##Vectors (1D Tensors)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "zr6eqe8KDSb6",
        "colab_type": "code",
        "outputId": "419a6978-c3e5-4086-aa65-f31c368860af",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Creates a 1D tensor of integers 1 to 4\n",
        "v = torch.Tensor([1, 2, 3, 4])\n",
        "v"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([1., 2., 3., 4.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XBkhbwt6EiDA",
        "colab_type": "code",
        "outputId": "702ba686-986b-4729-a4f0-6984eb388b51",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Print number of dimensions (1D) and size of tensor\n",
        "print(f'dim: {v.dim()}, size: {v.size()[0]}')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "dim: 1, size: 4\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "q0EPgiGjEqjk",
        "colab_type": "code",
        "outputId": "f4237e45-59b4-441d-9384-916d99ea7b38",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "w = torch.Tensor([1, 0, 2, 0])\n",
        "w"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([1., 0., 2., 0.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8_jSYg-gEvEU",
        "colab_type": "code",
        "outputId": "b6d30aa7-2c5b-4c71-d7e2-1d20b30e46d3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Element-wise multiplication\n",
        "v * w"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([1., 0., 6., 0.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 19
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dO_VZ5eAE3lk",
        "colab_type": "code",
        "outputId": "52ad31b7-1d9d-47c6-a649-11ac7419be45",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Scalar product: 1*1 + 2*0 + 3*2 + 4*0\n",
        "v @ w"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor(7.)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PPZyIIXgFvrM",
        "colab_type": "code",
        "outputId": "2af0c246-1fa8-4f2e-dd3b-7e49e9f4f2d9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# In-place replacement of random number from 0 to 10\n",
        "x = torch.Tensor(5).random_(10)\n",
        "x"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([3., 6., 2., 0., 5.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "KCkb0g5xFxq3",
        "colab_type": "code",
        "outputId": "ba6fff67-7ff1-4157-a98a-b356e943090a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "print(f'first: {x[0]}, last: {x[-1]}')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "first: 3.0, last: 5.0\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "wGEZ9YytGMOV",
        "colab_type": "code",
        "outputId": "7e821b0d-ee76-46b3-db62-55633cf9e546",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Extract sub-Tensor [from:to)\n",
        "x[1:2 + 1]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([6., 2.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 25
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0sHqq86zGbSe",
        "colab_type": "code",
        "outputId": "4de5274b-6a1d-4820-c81c-4a4cc948bea1",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Create a tensor with integers ranging from 1 to 5, excluding 5\n",
        "v = torch.arange(1, 4 + 1)\n",
        "v"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([1, 2, 3, 4])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 26
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dcpb6aurHZKw",
        "colab_type": "code",
        "outputId": "b6e9a2f8-ae0a-456e-8ca2-ab9c34ae487c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Square all elements in the tensor\n",
        "print(v.pow(2), v)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "tensor([ 1,  4,  9, 16]) tensor([1, 2, 3, 4])\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ivpJKWqXITcG",
        "colab_type": "text"
      },
      "source": [
        "##Matrices (2D Tensors)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5RLNdAAlIXnt",
        "colab_type": "code",
        "outputId": "312d1de5-abb1-4bdc-d767-43a4cfa7c640",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        }
      },
      "source": [
        "# Create a 2x4 tensor\n",
        "m = torch.Tensor([[2, 5, 3, 7],\n",
        "                  [4, 2, 1, 9]])\n",
        "m"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[2., 5., 3., 7.],\n",
              "        [4., 2., 1., 9.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 28
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Wc-5FEJpIawG",
        "colab_type": "code",
        "outputId": "8d880666-d96f-4bf5-bc2e-9f135c7c5152",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "m.dim()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 29
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VmwL7QzQIhdj",
        "colab_type": "code",
        "outputId": "25236132-f699-43f8-9c2f-438ddd5a7236",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "print(m.size(0), m.size(1), m.size(), sep=' -- ')"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "2 -- 4 -- torch.Size([2, 4])\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Quh62uBNIntn",
        "colab_type": "code",
        "outputId": "9ef01c65-3062-4dda-8806-bdd4b5c97b26",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Returns the total number of elements, hence num-el (number of elements)\n",
        "m.numel()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "8"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 31
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lujIvMuqIrSs",
        "colab_type": "code",
        "outputId": "cad82235-1b80-4f35-d927-169c6a58099a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Indexing row 0, column 2 (0-indexed)\n",
        "m[0][2]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor(3.)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 32
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "QMyraCpMI7Nr",
        "colab_type": "code",
        "outputId": "42df397b-1ded-4a74-8532-9d2bd473188c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Indexing row 0, column 2 (0-indexed)\n",
        "m[0, 2]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor(3.)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 33
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PkQd9QAsJFJb",
        "colab_type": "code",
        "outputId": "44a73a7a-1907-4299-d82a-0a8b7b91ba9e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Indexing column 1, all rows (returns size 2)\n",
        "m[:, 1]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([5., 2.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 34
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "HnUevCeGJHf-",
        "colab_type": "code",
        "outputId": "2ed315bf-c81b-4473-dd6f-f046f6da1d68",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        }
      },
      "source": [
        "# Indexing column 1, all rows (returns size 2x2)\n",
        "m[:, [1]]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[5.],\n",
              "        [2.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 35
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "OriKEZcNJNJl",
        "colab_type": "code",
        "outputId": "e9c5a966-8508-4f75-d262-f576f483aca5",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Indexes row 0, all columns (returns 1x4)\n",
        "m[[0], :]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[2., 5., 3., 7.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "w6nPl1R2Kyow",
        "colab_type": "code",
        "outputId": "c9871458-34d2-4831-e79c-66df31ed3958",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Indexes row 0, all columns (returns size 4)\n",
        "m[0, :]"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([2., 5., 3., 7.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 37
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "5JmIqsZeMPJ7",
        "colab_type": "code",
        "outputId": "f812a9a7-69f9-4d52-ff49-70f5839a9001",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Create tensor of numbers from 1 to 5 (excluding 5)\n",
        "v = torch.arange(1., 4 + 1)\n",
        "v"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([1., 2., 3., 4.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 39
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "M54n-8rYKz0-",
        "colab_type": "code",
        "outputId": "4ad31a50-6a86-45ec-d807-1eb02ca83b36",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Scalar product\n",
        "m @ v"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([49., 47.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 40
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-nDlqrraMcpA",
        "colab_type": "code",
        "outputId": "1867c22c-c7f4-4c36-8ece-62031dc6be7b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Calculated by 1*2 + 2*5 + 3*3 + 4*7\n",
        "m[[0], :] @ v"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([49.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 41
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bKVK_HZvMimC",
        "colab_type": "code",
        "outputId": "a9e022b6-a76f-4ce1-89c0-6a7f2566f8bb",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        }
      },
      "source": [
        "# Subtract a random tensor of size 2x4 to m\n",
        "m - torch.rand(2, 4)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[1.7115, 4.1250, 2.4941, 6.7634],\n",
              "        [3.2430, 1.7654, 0.3529, 8.6444]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 42
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nlgFgfUwMlFG",
        "colab_type": "code",
        "outputId": "a62d2b26-957a-499e-bcc3-292b2464fe9e",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        }
      },
      "source": [
        "# Multiply a random tensor of size 2x4 to m\n",
        "m * torch.rand(2, 4)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[0.8904, 0.0965, 0.7848, 5.3992],\n",
              "        [1.5138, 1.9960, 0.9008, 4.2893]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 43
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pWtCEP84Mo5H",
        "colab_type": "code",
        "outputId": "19478c3a-d5bc-4dc3-e4f0-630f0342f216",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 50
        }
      },
      "source": [
        "# Divide m by a random tensor of size 2x4\n",
        "m / torch.rand(2, 4)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[12.0295,  6.2152,  4.5789, 39.5950],\n",
              "        [ 4.8498,  2.4890,  1.0599, 40.9612]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VxJZLVraMrLj",
        "colab_type": "code",
        "outputId": "f579daa0-bf02-4e91-b937-69795dfb198b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 100
        }
      },
      "source": [
        "print(m.size())\n",
        "\n",
        "# Transpose tensor m, which is essentially 2x4 to 4x2\n",
        "m.t()"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "torch.Size([2, 4])\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[2., 4.],\n",
              "        [5., 2.],\n",
              "        [3., 1.],\n",
              "        [7., 9.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "o7DqV4mwOjhB",
        "colab_type": "text"
      },
      "source": [
        "##Constructors"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SNT5J5aEOoEV",
        "colab_type": "code",
        "outputId": "55dbe991-5925-4532-f82e-e160670f4e20",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Create tensor from 3 to 8, with each having a space of 1\n",
        "torch.arange(3., 8 + 1)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([3., 4., 5., 6., 7., 8.])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 47
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pQN6Va3sOuhY",
        "colab_type": "code",
        "outputId": "22d18c36-39b0-4293-908d-3ca851505099",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 33
        }
      },
      "source": [
        "# Create tensor from 5.7 to -2.1 with each having a space of -3\n",
        "torch.arange(5.7, -2.1, -3)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([ 5.7000,  2.7000, -0.3000])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 48
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tm-WhtRnOynT",
        "colab_type": "code",
        "outputId": "a9983c9a-48a9-4a42-a947-fefa25b0b5f3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# returns a 1D tensor of steps equally spaced points between start=3, end=8 and steps=20\n",
        "torch.linspace(3, 8, 20).view(1, -1)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[3.0000, 3.2632, 3.5263, 3.7895, 4.0526, 4.3158, 4.5789, 4.8421, 5.1053,\n",
              "         5.3684, 5.6316, 5.8947, 6.1579, 6.4211, 6.6842, 6.9474, 7.2105, 7.4737,\n",
              "         7.7368, 8.0000]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 49
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CHb8BrJ5Oz2w",
        "colab_type": "code",
        "outputId": "6f928f59-e18f-4e47-c66c-63f392d5096a",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# Create a tensor filled with 0's\n",
        "torch.zeros(3, 5)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[0., 0., 0., 0., 0.],\n",
              "        [0., 0., 0., 0., 0.],\n",
              "        [0., 0., 0., 0., 0.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "L24H2ca4O2oJ",
        "colab_type": "code",
        "outputId": "b6e6e228-3a1d-404f-9c21-a7a86401c3a3",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 150
        }
      },
      "source": [
        "# Create a tensor filled with 1's\n",
        "torch.ones(3, 2, 5)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[[1., 1., 1., 1., 1.],\n",
              "         [1., 1., 1., 1., 1.]],\n",
              "\n",
              "        [[1., 1., 1., 1., 1.],\n",
              "         [1., 1., 1., 1., 1.]],\n",
              "\n",
              "        [[1., 1., 1., 1., 1.],\n",
              "         [1., 1., 1., 1., 1.]]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 51
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3q7eN5ZxO7Fr",
        "colab_type": "code",
        "outputId": "6a251cf3-efb5-4a83-bdb2-4f4b52c0bd57",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66
        }
      },
      "source": [
        "# Create a tensor with the diagonal filled with 1\n",
        "torch.eye(3)"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "tensor([[1., 0., 0.],\n",
              "        [0., 1., 0.],\n",
              "        [0., 0., 1.]])"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 52
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LzhyrhXzO9Xt",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "# Set default plots\n",
        "#from plot_lib import set_default\n",
        "from matplotlib import pyplot as plt\n",
        "#set_default()"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UWHwoQe6PKTt",
        "colab_type": "code",
        "outputId": "0b71d707-64a3-4546-e272-192098bd2a6b",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 346
        }
      },
      "source": [
        "# Numpy bridge!\n",
        "plt.hist(torch.randn(1000).numpy(), 100);"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAd8AAAFKCAYAAABcq1WoAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\njFG+AAAYo3wBADD2vxfMyngVo97uAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UUw11xi2PM-m",
        "colab_type": "code",
        "outputId": "6f86ed4e-7d94-4716-a505-8d92e43a8e4c",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 346
        }
      },
      "source": [
        "plt.hist(torch.randn(10**6).numpy(), 100);  # how much does this chart weight?\n",
        "# use rasterized=True for SVG/EPS/PDF!"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe8AAAFKCAYAAAA0WNeQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nRK5CYII=\n",
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kOk1BLMVPRiY",
        "colab_type": "code",
        "outputId": "74f880b4-861a-43d7-f0c1-9da7536c7952",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 346
        }
      },
      "source": [
        "plt.hist(torch.rand(10**6).numpy(), 100);"
      ],
      "execution_count": 0,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAe8AAAFKCAYAAAA0WNeQAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nDVS07vUtSwAAAABJRU5ErkJggg==\n",
            "text/plain": [
              "<Figure size 576x396 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ANJfdFD3s0oT",
        "colab_type": "text"
      },
      "source": [
        "**Questions to explore:**\n",
        "\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OS9gHzZM7HQr",
        "colab_type": "text"
      },
      "source": [
        "\n",
        "\n",
        "See the accompanying LICENSE file in the GitHub repository for terms. \n",
        "\n",
        "Date: 16-04-2019                                                             \n",
        "Author: Alexander Robles                                                  \n",
        "E-mail: alexander.robles20@gmail.com                                           \n",
        "                                             "
      ]
    }
  ]
}