Malaria_Parasite_Detection_Using_CNN.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "Malaria_Parasite_Detection_Using_CNN.ipynb",
      "provenance": [],
      "collapsed_sections": [
        "DWNbV9na5v7r"
      ],
      "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/danielsoy/ALOCC-CVPR2018/blob/master/Malaria_Parasite_Detection_Using_CNN.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FrqbZzyNfcyp"
      },
      "source": [
        "## Malaria Parasite Detection Using CNN"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "nGm8Ywe6LBZv"
      },
      "source": [
        "Watch Full Video Here: https://youtu.be/Jdagdil0FIw\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5bFd-gm6zUrN"
      },
      "source": [
        "![alt text](https://ourworldindata.org/uploads/2019/04/Previous-prevalence-of-malaria-world-map.png)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Z6qrKFXYzUyu"
      },
      "source": [
        "Malaria is an infectious disease that causes over 400,000 deaths per year."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "RIGgPoXHzU2s"
      },
      "source": [
        "Mosquitoes are notorious for carrying malaria"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7pnyA0ZizU6q"
      },
      "source": [
        "In 2018, Rajaraman et al. published a paper entitled Pre-trained convolutional neural networks as feature extractors toward improved parasite detection in thin blood smear images."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "-QeOG98ezU-b"
      },
      "source": [
        "Link: https://lhncbc.nlm.nih.gov/publication/pub9932\n",
        "\n",
        "Paper Link: https://lhncbc.nlm.nih.gov/system/files/pub9752.pdf"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EDIo8mVj0D3O"
      },
      "source": [
        "![alt text](https://www.pyimagesearch.com/wp-content/uploads/2018/12/dl_medical_imaging_malaria_dataset.jpg)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "PRd7-zjwfQPI",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "8e31182f-b0a9-4b06-f2b9-c2b9ac14d35c"
      },
      "source": [
        "!pip install tensorflow-gpu==2.7.0  ## -rc0"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting tensorflow-gpu==2.7.0\n",
            "  Downloading tensorflow_gpu-2.7.0-cp37-cp37m-manylinux2010_x86_64.whl (489.6 MB)\n",
            "\u001b[K     |████████████████████████████████| 489.6 MB 24 kB/s \n",
            "\u001b[?25hRequirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.1.0)\n",
            "Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.42.0)\n",
            "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (0.22.0)\n",
            "Requirement already satisfied: keras<2.8,>=2.7.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (2.7.0)\n",
            "Requirement already satisfied: absl-py>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (0.12.0)\n",
            "Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (3.3.0)\n",
            "Requirement already satisfied: wheel<1.0,>=0.32.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (0.37.0)\n",
            "Collecting tensorboard~=2.6\n",
            "  Downloading tensorboard-2.7.0-py3-none-any.whl (5.8 MB)\n",
            "\u001b[K     |████████████████████████████████| 5.8 MB 23.5 MB/s \n",
            "\u001b[?25hCollecting tensorflow-estimator<2.8,~=2.7.0rc0\n",
            "  Downloading tensorflow_estimator-2.7.0-py2.py3-none-any.whl (463 kB)\n",
            "\u001b[K     |████████████████████████████████| 463 kB 38.4 MB/s \n",
            "\u001b[?25hRequirement already satisfied: numpy>=1.14.5 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.19.5)\n",
            "Requirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (12.0.0)\n",
            "Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.6.3)\n",
            "Requirement already satisfied: flatbuffers<3.0,>=1.12 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (2.0)\n",
            "Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (3.1.0)\n",
            "Requirement already satisfied: protobuf>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (3.17.3)\n",
            "Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (0.2.0)\n",
            "Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.1.2)\n",
            "Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.15.0)\n",
            "Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (1.13.3)\n",
            "Requirement already satisfied: gast<0.5.0,>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (0.2.2)\n",
            "Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow-gpu==2.7.0) (3.10.0.2)\n",
            "Requirement already satisfied: cached-property in /usr/local/lib/python3.7/dist-packages (from h5py>=2.9.0->tensorflow-gpu==2.7.0) (1.5.2)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (1.35.0)\n",
            "Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (0.4.6)\n",
            "Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (1.0.1)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (57.4.0)\n",
            "Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (1.8.0)\n",
            "Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (0.6.1)\n",
            "Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (2.23.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard~=2.6->tensorflow-gpu==2.7.0) (3.3.6)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow-gpu==2.7.0) (4.8)\n",
            "Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow-gpu==2.7.0) (4.2.4)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow-gpu==2.7.0) (0.2.8)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.6->tensorflow-gpu==2.7.0) (1.3.0)\n",
            "Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard~=2.6->tensorflow-gpu==2.7.0) (4.8.2)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard~=2.6->tensorflow-gpu==2.7.0) (3.6.0)\n",
            "Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.7/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard~=2.6->tensorflow-gpu==2.7.0) (0.4.8)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow-gpu==2.7.0) (2.10)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow-gpu==2.7.0) (1.24.3)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow-gpu==2.7.0) (3.0.4)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard~=2.6->tensorflow-gpu==2.7.0) (2021.10.8)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard~=2.6->tensorflow-gpu==2.7.0) (3.1.1)\n",
            "Installing collected packages: tensorflow-estimator, tensorboard, tensorflow-gpu\n",
            "  Attempting uninstall: tensorflow-estimator\n",
            "    Found existing installation: tensorflow-estimator 2.0.1\n",
            "    Uninstalling tensorflow-estimator-2.0.1:\n",
            "      Successfully uninstalled tensorflow-estimator-2.0.1\n",
            "  Attempting uninstall: tensorboard\n",
            "    Found existing installation: tensorboard 2.0.2\n",
            "    Uninstalling tensorboard-2.0.2:\n",
            "      Successfully uninstalled tensorboard-2.0.2\n",
            "  Attempting uninstall: tensorflow-gpu\n",
            "    Found existing installation: tensorflow-gpu 2.0.0\n",
            "    Uninstalling tensorflow-gpu-2.0.0:\n",
            "      Successfully uninstalled tensorflow-gpu-2.0.0\n",
            "Successfully installed tensorboard-2.7.0 tensorflow-estimator-2.7.0 tensorflow-gpu-2.7.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IP69j-fjftKz",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "ab0adf7e-0ea5-44ff-a2f3-b8487ce45989"
      },
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow.keras import Sequential\n",
        "from tensorflow.keras.layers import Flatten, Dense, Conv2D, MaxPool2D, Dropout\n",
        "\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "print(tf.__version__)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "2.7.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "n6_k7gqOgNYQ"
      },
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "BowRCrCWiPQT",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "69e324f8-8c9b-4028-ce88-7baaddeac617"
      },
      "source": [
        "!git clone https://github.com/laxmimerit/Malaria-Classification-Using-CNN.git"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Cloning into 'Malaria-Classification-Using-CNN'...\n",
            "remote: Enumerating objects: 27577, done.\u001b[K\n",
            "remote: Total 27577 (delta 0), reused 0 (delta 0), pack-reused 27577\u001b[K\n",
            "Receiving objects: 100% (27577/27577), 331.67 MiB | 35.91 MiB/s, done.\n",
            "Resolving deltas: 100% (3/3), done.\n",
            "Checking out files: 100% (27562/27562), done.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LMKkyU4jiPTl"
      },
      "source": [
        "img_width = 64\n",
        "img_height = 64"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "sHyJJ5quiPWX"
      },
      "source": [
        "datagen = ImageDataGenerator(rescale=1/255.0, validation_split=0.2)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "dFcyZF06_2AN"
      },
      "source": [
        "from google.colab import drive"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "brsdf-pK_1fp",
        "outputId": "d6633c38-5011-42da-f7bb-6693bf20c8c1"
      },
      "source": [
        "drive.mount ('/content/drive')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6SdOmHeSzHMh",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "7fd9480f-e2eb-478d-e2ca-c9d58f6c6818"
      },
      "source": [
        "train_data_generator = datagen.flow_from_directory(directory='/content/Malaria-Classification-Using-CNN/malaria-dataset',\n",
        "                                                   target_size = (img_width, img_height),\n",
        "                                                   class_mode = 'binary',\n",
        "                                                   batch_size = 16,\n",
        "                                                   subset = 'training'\n",
        "                                                   )"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Found 22048 images belonging to 2 classes.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "YQZa11nxC0_L"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gT2kmKKRC1TV"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "254F-VJszHPz",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "72b82160-cb14-4992-a58f-a1968d2f11f8"
      },
      "source": [
        "validation_data_generator = datagen.flow_from_directory(directory='/content/Malaria-Classification-Using-CNN/malaria-dataset',\n",
        "                                                   target_size = (img_width, img_height),\n",
        "                                                   class_mode = 'binary',\n",
        "                                                   batch_size = 16,\n",
        "                                                   subset = 'validation'\n",
        "                                                   )"
      ],
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 5510 images belonging to 2 classes.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "AG-yTDwtzHaP",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 34
        },
        "outputId": "cec5ee99-dfb4-4360-88d1-a2dc7f241e94"
      },
      "source": [
        "train_data_generator.labels"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array([0, 0, 0, ..., 1, 1, 1], dtype=int32)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bSX3p9W7zHdm"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DWNbV9na5v7r"
      },
      "source": [
        "## CNN Model Building"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ib5yNUESzHgH"
      },
      "source": [
        "model = Sequential()\n",
        "\n",
        "model.add(Conv2D(16, (3,3), input_shape = (img_width, img_height, 3), activation='relu'))\n",
        "model.add(MaxPool2D(2,2))\n",
        "model.add(Dropout(0.2))\n",
        "\n",
        "model.add(Conv2D(32, (3,3), activation='relu'))\n",
        "model.add(MaxPool2D(2,2))\n",
        "model.add(Dropout(0.3))\n",
        "\n",
        "model.add(Flatten())\n",
        "model.add(Dense(64, activation='relu'))\n",
        "model.add(Dropout(0.5))\n",
        "\n",
        "model.add(Dense(1, activation='sigmoid'))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0jBf7QUyzHjV",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 487
        },
        "outputId": "b5a4ef74-b405-4ab9-d835-4c650a263166"
      },
      "source": [
        "model.summary()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            "Layer (type)                 Output Shape              Param #   \n",
            "=================================================================\n",
            "conv2d (Conv2D)              (None, 62, 62, 16)        448       \n",
            "_________________________________________________________________\n",
            "max_pooling2d (MaxPooling2D) (None, 31, 31, 16)        0         \n",
            "_________________________________________________________________\n",
            "dropout (Dropout)            (None, 31, 31, 16)        0         \n",
            "_________________________________________________________________\n",
            "conv2d_1 (Conv2D)            (None, 29, 29, 32)        4640      \n",
            "_________________________________________________________________\n",
            "max_pooling2d_1 (MaxPooling2 (None, 14, 14, 32)        0         \n",
            "_________________________________________________________________\n",
            "dropout_1 (Dropout)          (None, 14, 14, 32)        0         \n",
            "_________________________________________________________________\n",
            "flatten (Flatten)            (None, 6272)              0         \n",
            "_________________________________________________________________\n",
            "dense (Dense)                (None, 64)                401472    \n",
            "_________________________________________________________________\n",
            "dropout_2 (Dropout)          (None, 64)                0         \n",
            "_________________________________________________________________\n",
            "dense_1 (Dense)              (None, 1)                 65        \n",
            "=================================================================\n",
            "Total params: 406,625\n",
            "Trainable params: 406,625\n",
            "Non-trainable params: 0\n",
            "_________________________________________________________________\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "CFI_j2lTzHmE"
      },
      "source": [
        "model.compile(optimizer='adam', loss='binary_crossentropy', metrics = ['accuracy'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "aAc-JsA9zHqY",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 272
        },
        "outputId": "b979aaa0-e5f3-4b4f-ae23-492f7424a694"
      },
      "source": [
        "history = model.fit_generator(generator=train_data_generator,\n",
        "                              steps_per_epoch = len(train_data_generator),\n",
        "                              epochs = 5,\n",
        "                              validation_data = validation_data_generator,\n",
        "                              validation_steps = len(validation_data_generator))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "WARNING: Logging before flag parsing goes to stderr.\n",
            "W0906 14:12:46.659580 140276563072896 deprecation.py:323] From /usr/local/lib/python3.6/dist-packages/tensorflow_core/python/ops/math_grad.py:1394: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.\n",
            "Instructions for updating:\n",
            "Use tf.where in 2.0, which has the same broadcast rule as np.where\n"
          ],
          "name": "stderr"
        },
        {
          "output_type": "stream",
          "text": [
            "Epoch 1/5\n",
            "1378/1378 [==============================] - 159s 116ms/step - loss: 0.5148 - accuracy: 0.7516 - val_loss: 0.2932 - val_accuracy: 0.9198\n",
            "Epoch 2/5\n",
            "1378/1378 [==============================] - 157s 114ms/step - loss: 0.2424 - accuracy: 0.9248 - val_loss: 0.2023 - val_accuracy: 0.9330\n",
            "Epoch 3/5\n",
            "1378/1378 [==============================] - 158s 115ms/step - loss: 0.2090 - accuracy: 0.9252 - val_loss: 0.2072 - val_accuracy: 0.9350\n",
            "Epoch 4/5\n",
            "1378/1378 [==============================] - 158s 114ms/step - loss: 0.1879 - accuracy: 0.9415 - val_loss: 0.1777 - val_accuracy: 0.9421\n",
            "Epoch 5/5\n",
            "1378/1378 [==============================] - 159s 115ms/step - loss: 0.1756 - accuracy: 0.9460 - val_loss: 0.1776 - val_accuracy: 0.9359\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "G4uTlLpEzHto",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 218
        },
        "outputId": "d1ae07ec-ab62-4ac2-9490-8fe22039fe0a"
      },
      "source": [
        "history.history"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "{'accuracy': [0.7516328, 0.9247551, 0.92516327, 0.9414913, 0.9459815],\n",
              " 'loss': [0.5148320565721985,\n",
              "  0.24242815816118038,\n",
              "  0.20904136766680936,\n",
              "  0.18788115207257267,\n",
              "  0.17563284345171232],\n",
              " 'val_accuracy': [0.9197822, 0.93303084, 0.93502724, 0.94210523, 0.93593466],\n",
              " 'val_loss': [0.29318461221629294,\n",
              "  0.2022698652593122,\n",
              "  0.20716091553154198,\n",
              "  0.17766353934463383,\n",
              "  0.1776162104573155]}"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "qjmQySABzHyp"
      },
      "source": [
        "def plot_learningCurve(history, epoch):\n",
        "  # Plot training & validation accuracy values\n",
        "  epoch_range = range(1, epoch+1)\n",
        "  plt.plot(epoch_range, history.history['accuracy'])\n",
        "  plt.plot(epoch_range, history.history['val_accuracy'])\n",
        "  plt.title('Model accuracy')\n",
        "  plt.ylabel('Accuracy')\n",
        "  plt.xlabel('Epoch')\n",
        "  plt.legend(['Train', 'Val'], loc='upper left')\n",
        "  plt.show()\n",
        "\n",
        "  # Plot training & validation loss values\n",
        "  plt.plot(epoch_range, history.history['loss'])\n",
        "  plt.plot(epoch_range, history.history['val_loss'])\n",
        "  plt.title('Model loss')\n",
        "  plt.ylabel('Loss')\n",
        "  plt.xlabel('Epoch')\n",
        "  plt.legend(['Train', 'Val'], loc='upper left')\n",
        "  plt.show()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "J743xX1ezH1r",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 573
        },
        "outputId": "0dbb4019-c1cf-4302-aaba-d7a7c6816a14"
      },
      "source": [
        "plot_learningCurve(history, 5)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZIAAAEWCAYAAABMoxE0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n8UTinHOuWzyROOec65b/H31vryDSjKzqAAAAAElFTkSuQmCC\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYsAAAEWCAYAAACXGLsWAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n",
            "text/plain": [
              "<Figure size 432x288 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "vigdwNsrzH4T"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "gGpsjrbJzH7U"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "kKm7geb_zIAw"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "GWcMEs9GzHYY"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pA8t1M3_zHWC"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NivkfZWuzHSN"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jjKiHaoPiPZV"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "fdgfdKQOiPdr"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "pkymTeZsiPgy"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lgry9pEQiPjx"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "IIZHRUa6iPm9"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "1JGIcC1diPpn"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tfslfpSRiPLO"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RSlKRR8nhD3e"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VSPouy_ShD9N"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "JZ8EbCTDhEAN"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}