fork from https://github.com/keras-team/keras/blob/master/examples/mnist_cnn.py

ithome2018_lab0_keras-cnn-mnist.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "keras_cnn_mnist.ipynb",
      "version": "0.3.2",
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU"
  },
  "cells": [
    {
      "metadata": {
        "id": "-eIxxGyvQAbP",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "## Import Library and Use Tensorflow as Keras Backend"
      ]
    },
    {
      "metadata": {
        "id": "bsGpTlf1NMOB",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "e00bc87d-dcfa-490f-a405-b6ad48e14b79"
      },
      "cell_type": "code",
      "source": [
        "from __future__ import print_function\n",
        "import keras\n",
        "from keras.datasets import mnist\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Dense, Dropout, Flatten\n",
        "from keras.layers import Conv2D, MaxPooling2D\n",
        "from keras import backend as K"
      ],
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Using TensorFlow backend.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "metadata": {
        "id": "hfvp3JVuP8dR",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "## Load Data"
      ]
    },
    {
      "metadata": {
        "id": "gv9kobR6PO2N",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        },
        "outputId": "26156e1b-40c5-43c4-87c7-f7f3ad93e515"
      },
      "cell_type": "code",
      "source": [
        "# the data, split between train and test sets\n",
        "(x_train, y_train), (x_test, y_test) = mnist.load_data()"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Downloading data from https://s3.amazonaws.com/img-datasets/mnist.npz\n",
            "11493376/11490434 [==============================] - 1s 0us/step\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "GEJetJ29QH5W",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "## Setup Hyper-parameter"
      ]
    },
    {
      "metadata": {
        "id": "OYc55xjGP2rA",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 68
        },
        "outputId": "0ea7ecf0-ca2d-4c82-c1de-785b5cf7b8e7"
      },
      "cell_type": "code",
      "source": [
        "batch_size = 128\n",
        "num_classes = 10\n",
        "epochs = 12\n",
        "\n",
        "# input image dimensions\n",
        "img_rows, img_cols = 28, 28\n",
        "\n",
        "if K.image_data_format() == 'channels_first':\n",
        "    x_train = x_train.reshape(x_train.shape[0], 1, img_rows, img_cols)\n",
        "    x_test = x_test.reshape(x_test.shape[0], 1, img_rows, img_cols)\n",
        "    input_shape = (1, img_rows, img_cols)\n",
        "else:\n",
        "    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, 1)\n",
        "    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, 1)\n",
        "    input_shape = (img_rows, img_cols, 1)\n",
        "\n",
        "x_train = x_train.astype('float32')\n",
        "x_test = x_test.astype('float32')\n",
        "x_train /= 255\n",
        "x_test /= 255\n",
        "print('x_train shape:', x_train.shape)\n",
        "print(x_train.shape[0], 'train samples')\n",
        "print(x_test.shape[0], 'test samples')\n",
        "\n",
        "# convert class vectors to binary class matrices\n",
        "y_train = keras.utils.to_categorical(y_train, num_classes)\n",
        "y_test = keras.utils.to_categorical(y_test, num_classes)"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "x_train shape: (60000, 28, 28, 1)\n",
            "60000 train samples\n",
            "10000 test samples\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "metadata": {
        "id": "tS7PZjX5QC5X",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "## Build Model"
      ]
    },
    {
      "metadata": {
        "id": "Scdyj8g0Nct1",
        "colab_type": "code",
        "colab": {}
      },
      "cell_type": "code",
      "source": [
        "\n",
        "model = Sequential()\n",
        "model.add(Conv2D(32, kernel_size=(3, 3),\n",
        "                 activation='relu',\n",
        "                 input_shape=input_shape))\n",
        "model.add(Conv2D(64, (3, 3), activation='relu'))\n",
        "model.add(MaxPooling2D(pool_size=(2, 2)))\n",
        "model.add(Dropout(0.25))\n",
        "model.add(Flatten())\n",
        "model.add(Dense(128, activation='relu'))\n",
        "model.add(Dropout(0.5))\n",
        "model.add(Dense(num_classes, activation='softmax'))\n",
        "\n",
        "model.compile(loss=keras.losses.categorical_crossentropy,\n",
        "              optimizer=keras.optimizers.Adadelta(),\n",
        "              metrics=['accuracy'])"
      ],
      "execution_count": 0,
      "outputs": []
    },
    {
      "metadata": {
        "id": "L5oZWDnqQz9V",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "## Train Model"
      ]
    },
    {
      "metadata": {
        "id": "GWyjsuFoQ2Zh",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 459
        },
        "outputId": "2bdc2b0e-1a45-4569-cf4e-f69561728235"
      },
      "cell_type": "code",
      "source": [
        "model.fit(x_train, y_train,\n",
        "          batch_size=batch_size,\n",
        "          epochs=epochs,\n",
        "          verbose=1,\n",
        "          validation_data=(x_test, y_test))"
      ],
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Train on 60000 samples, validate on 10000 samples\n",
            "Epoch 1/12\n",
            "60000/60000 [==============================] - 11s 188us/step - loss: 0.2642 - acc: 0.9186 - val_loss: 0.0615 - val_acc: 0.9793\n",
            "Epoch 2/12\n",
            "60000/60000 [==============================] - 10s 160us/step - loss: 0.0866 - acc: 0.9737 - val_loss: 0.0417 - val_acc: 0.9859\n",
            "Epoch 3/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0654 - acc: 0.9808 - val_loss: 0.0376 - val_acc: 0.9864\n",
            "Epoch 4/12\n",
            "60000/60000 [==============================] - 9s 156us/step - loss: 0.0543 - acc: 0.9840 - val_loss: 0.0456 - val_acc: 0.9852\n",
            "Epoch 5/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0472 - acc: 0.9853 - val_loss: 0.0337 - val_acc: 0.9892\n",
            "Epoch 6/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0401 - acc: 0.9875 - val_loss: 0.0293 - val_acc: 0.9906\n",
            "Epoch 7/12\n",
            "60000/60000 [==============================] - 9s 154us/step - loss: 0.0370 - acc: 0.9890 - val_loss: 0.0256 - val_acc: 0.9915\n",
            "Epoch 8/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0351 - acc: 0.9895 - val_loss: 0.0275 - val_acc: 0.9908\n",
            "Epoch 9/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0302 - acc: 0.9911 - val_loss: 0.0248 - val_acc: 0.9922\n",
            "Epoch 10/12\n",
            "60000/60000 [==============================] - 9s 157us/step - loss: 0.0291 - acc: 0.9914 - val_loss: 0.0287 - val_acc: 0.9908\n",
            "Epoch 11/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0269 - acc: 0.9918 - val_loss: 0.0274 - val_acc: 0.9915\n",
            "Epoch 12/12\n",
            "60000/60000 [==============================] - 9s 155us/step - loss: 0.0259 - acc: 0.9920 - val_loss: 0.0283 - val_acc: 0.9909\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<keras.callbacks.History at 0x7f670edfd048>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 6
        }
      ]
    },
    {
      "metadata": {
        "id": "tvIByE2hQpUk",
        "colab_type": "text"
      },
      "cell_type": "markdown",
      "source": [
        "## Validate Model"
      ]
    },
    {
      "metadata": {
        "id": "PfcHeD7LQfvT",
        "colab_type": "code",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 51
        },
        "outputId": "53d5b3a9-3ab4-4258-d14c-a624835c27e2"
      },
      "cell_type": "code",
      "source": [
        "score = model.evaluate(x_test, y_test, verbose=0)\n",
        "print('Test loss:', score[0])\n",
        "print('Test accuracy:', score[1])\n"
      ],
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Test loss: 0.028276310487868248\n",
            "Test accuracy: 0.9909\n"
          ],
          "name": "stdout"
        }
      ]
    }
  ]
}