Loading MNIST

Loading MNIST.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Scratch",
      "provenance": [],
      "collapsed_sections": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "metadata": {
        "id": "MhApsB6JmjYZ",
        "colab_type": "code",
        "colab": {}
      },
      "source": [
        "%tensorflow_version 2.x\n",
        "from tensorflow.keras.datasets import mnist\n",
        "import matplotlib.pyplot as plt"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XK5A8E0epBgX",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 85
        },
        "outputId": "05887258-7376-49ce-fa85-c15e23a5da98"
      },
      "source": [
        "(X_train, y_train), (X_test, y_test) = mnist.load_data()\n",
        "print (\"X_train.shape: {}\".format(X_train.shape))\n",
        "print (\"y_train.shape: {}\".format(y_train.shape))\n",
        "print (\"X_test.shape: {}\".format(X_test.shape))\n",
        "print (\"y_test.shape: {}\".format(y_test.shape))"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "X_train.shape: (60000, 28, 28)\n",
            "y_train.shape: (60000,)\n",
            "X_test.shape: (10000, 28, 28)\n",
            "y_test.shape: (10000,)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "MFvRH6QKmw65",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 99
        },
        "outputId": "c96ca192-2eab-4044-f610-e2698619fc3c"
      },
      "source": [
        "plt.subplot(161)\n",
        "plt.imshow(X_train[3], cmap=plt.get_cmap('gray'))\n",
        "plt.subplot(162)\n",
        "plt.imshow(X_train[5], cmap=plt.get_cmap('gray'))\n",
        "plt.subplot(163)\n",
        "plt.imshow(X_train[7], cmap=plt.get_cmap('gray'))\n",
        "plt.subplot(164)\n",
        "plt.imshow(X_train[2], cmap=plt.get_cmap('gray'))\n",
        "plt.subplot(165)\n",
        "plt.imshow(X_train[0], cmap=plt.get_cmap('gray'))\n",
        "plt.subplot(166)\n",
        "plt.imshow(X_train[13], cmap=plt.get_cmap('gray'))\n",
        "\n",
        "plt.show()"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXIAAABSCAYAAABJ/1+LAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nuaIoisf5fyLVBFBfyYuPAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 6 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    }
  ]
}