BrainCancerMulti_Classification.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "gpuClass": "standard"
  },
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "nrBW2gxyU_rC",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "addff182-7092-45f2-f105-5e9f679ad3e9"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/GoogleDrive; to attempt to forcibly remount, call drive.mount(\"/content/GoogleDrive\", force_remount=True).\n"
          ]
        }
      ],
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/GoogleDrive')"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install split-folders"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lshnc8uV3WqP",
        "outputId": "0d11744e-3311-44df-c875-3c808860fb1b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Collecting split-folders\n",
            "  Downloading split_folders-0.5.1-py3-none-any.whl (8.4 kB)\n",
            "Installing collected packages: split-folders\n",
            "Successfully installed split-folders-0.5.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import pandas as pd\n",
        "import tensorflow as tf\n",
        "\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Conv2D, MaxPooling2D, Dropout, Flatten, Dense, BatchNormalization\n",
        "from sklearn.metrics import confusion_matrix, ConfusionMatrixDisplay, zero_one_loss\n",
        "from imutils import paths\n",
        "\n",
        "import matplotlib.pyplot as plt\n",
        "import splitfolders\n",
        "import cv2\n",
        "import random"
      ],
      "metadata": {
        "id": "poZ-XM9XVWlz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "inputFolder = '/content/GoogleDrive/MyDrive/Colab Notebooks/Neural Networks/Selected2 Project/Brain Cancer'\n",
        "outputFolder = '/content/GoogleDrive/MyDrive/Colab Notebooks/Neural Networks/Selected2 Project/dataset'"
      ],
      "metadata": {
        "id": "C_sqJXglBJ6j"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "splitfolders.ratio(inputFolder, outputFolder, seed = 44, ratio = (0.8, 0.0, 0.2))"
      ],
      "metadata": {
        "id": "jH31LV_mV6DS",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "5bc01479-7980-477e-973a-19d1c94da318"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Copying files: 15000 files [08:15, 30.30 files/s]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "imgPaths = list(paths.list_images(outputFolder))\n",
        "print(imgPaths[0].split('/'))\n",
        "\n",
        "random.shuffle(imgPaths)\n",
        "\n",
        "classes = [] # classes = ['brain_tumor', 'brain_menin', 'brain_glioma']\n",
        "for imgPath in imgPaths:\n",
        "  className = imgPath.split('/')[-2]\n",
        "\n",
        "  if className not in classes:\n",
        "    classes.append(className)\n",
        "\n",
        "#print(classes)\n",
        "\n",
        "X_train = []\n",
        "y_train = []\n",
        "\n",
        "X_test = []\n",
        "y_test = []\n",
        "\n",
        "IMGSIZE = 128\n",
        "img_names = []\n",
        "\n",
        "for imgPath in imgPaths:\n",
        "  trainOrTest = imgPath.split('/')[-3]\n",
        "  className = imgPath.split('/')[-2]\n",
        "\n",
        "  img = cv2.imread(imgPath) #cv2.IMREAD_GRAYSCALE\n",
        "  img = cv2.resize(img, (IMGSIZE,IMGSIZE))\n",
        "\n",
        "  if trainOrTest == 'train':\n",
        "    X_train.append(img)\n",
        "    y_train.append(classes.index(className))\n",
        "    img_names.append(imgPath.split('/')[-1])\n",
        "\n",
        "  elif trainOrTest == 'test':\n",
        "    X_test.append(img)\n",
        "    y_test.append(classes.index(className))\n",
        "\n",
        "print(len(X_train), len(y_train))\n",
        "print(len(X_test), len(y_test))"
      ],
      "metadata": {
        "id": "IniMJGp9_IXg",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "75fb521b-3eaf-43ef-9f70-46eba400d2a9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "12000 12000\n",
            "3000 3000\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.DataFrame({\n",
        "    'File Name' : img_names,\n",
        "    'Category' : y_train\n",
        "})\n",
        "\n",
        "# print(classes.index('brain_tumor'))\n",
        "# print(classes.index('brain_glioma'))\n",
        "# print(classes.index('brain_menin'))\n",
        "\n",
        "print(classes)\n",
        "df.head()"
      ],
      "metadata": {
        "id": "0AqGy5iG7qnK",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 223
        },
        "outputId": "84149682-0fd0-4e5f-d96c-a136a16000e0"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['brain_tumor', 'brain_menin', 'brain_glioma']\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "               File Name  Category\n",
              "0   brain_menin_0466.jpg         1\n",
              "1   brain_menin_2933.jpg         1\n",
              "2  brain_glioma_3210.jpg         2\n",
              "3  brain_glioma_2218.jpg         2\n",
              "4  brain_glioma_4257.jpg         2"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-bb5ce910-9b75-4782-828f-d75bd0973f62\">\n",
              "    <div class=\"colab-df-container\">\n",
              "      <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>File Name</th>\n",
              "      <th>Category</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>brain_menin_0466.jpg</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>brain_menin_2933.jpg</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>brain_glioma_3210.jpg</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>brain_glioma_2218.jpg</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>brain_glioma_4257.jpg</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-bb5ce910-9b75-4782-828f-d75bd0973f62')\"\n",
              "              title=\"Convert this dataframe to an interactive table.\"\n",
              "              style=\"display:none;\">\n",
              "        \n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
              "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
              "  </svg>\n",
              "      </button>\n",
              "      \n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      flex-wrap:wrap;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "      <script>\n",
              "        const buttonEl =\n",
              "          document.querySelector('#df-bb5ce910-9b75-4782-828f-d75bd0973f62 button.colab-df-convert');\n",
              "        buttonEl.style.display =\n",
              "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "        async function convertToInteractive(key) {\n",
              "          const element = document.querySelector('#df-bb5ce910-9b75-4782-828f-d75bd0973f62');\n",
              "          const dataTable =\n",
              "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                     [key], {});\n",
              "          if (!dataTable) return;\n",
              "\n",
              "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "            + ' to learn more about interactive tables.';\n",
              "          element.innerHTML = '';\n",
              "          dataTable['output_type'] = 'display_data';\n",
              "          await google.colab.output.renderOutput(dataTable, element);\n",
              "          const docLink = document.createElement('div');\n",
              "          docLink.innerHTML = docLinkHtml;\n",
              "          element.appendChild(docLink);\n",
              "        }\n",
              "      </script>\n",
              "    </div>\n",
              "  </div>\n",
              "  "
            ]
          },
          "metadata": {},
          "execution_count": 86
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "X_train = np.array(X_train)\n",
        "y_train = np.array(y_train)\n",
        "\n",
        "X_test = np.array(X_test)\n",
        "y_test = np.array(y_test)"
      ],
      "metadata": {
        "id": "zPNII54jDPgg"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = Sequential()\n",
        "\n",
        "model.add(Conv2D(filters = 32, kernel_size = (3, 3), activation = 'relu', input_shape = (IMGSIZE, IMGSIZE, 3)))\n",
        "model.add(BatchNormalization())\n",
        "model.add(MaxPooling2D((2,2)))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Conv2D(filters = 64, kernel_size = (3, 3), activation = 'relu'))\n",
        "model.add(MaxPooling2D((2,2)))\n",
        "\n",
        "model.add(Conv2D(filters = 128, kernel_size = (3, 3), activation = 'relu'))\n",
        "model.add(MaxPooling2D((2,2)))\n",
        "\n",
        "model.add(Flatten())\n",
        "model.add(Dense(256, activation = 'relu'))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Dense(128, activation = 'relu'))\n",
        "model.add(Dropout(0.25))\n",
        "\n",
        "model.add(Dense(64, activation = 'relu'))\n",
        "model.add(Dense(3, activation = 'softmax'))\n",
        "\n",
        "model.compile(optimizer = 'adam', loss = 'sparse_categorical_crossentropy', metrics = ['accuracy'])\n",
        "history = model.fit(X_train, y_train, validation_data = (X_test, y_test), epochs = 15)\n",
        "# val_loss, val_acc = model.evaluate(X_test, y_test)\n",
        "\n",
        "y_pred = model.predict(X_test)\n",
        "\n",
        "model.summary()"
      ],
      "metadata": {
        "id": "1hiVsLhx7g53",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "80002195-e18e-4732-8e55-05a576855219"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "375/375 [==============================] - 584s 2s/step - loss: 0.7432 - accuracy: 0.6879 - val_loss: 0.6903 - val_accuracy: 0.6817\n",
            "Epoch 2/15\n",
            "375/375 [==============================] - 593s 2s/step - loss: 0.4689 - accuracy: 0.8142 - val_loss: 0.6275 - val_accuracy: 0.7427\n",
            "Epoch 3/15\n",
            "375/375 [==============================] - 599s 2s/step - loss: 0.3447 - accuracy: 0.8631 - val_loss: 0.2723 - val_accuracy: 0.8957\n",
            "Epoch 4/15\n",
            "375/375 [==============================] - 600s 2s/step - loss: 0.2735 - accuracy: 0.8990 - val_loss: 0.3266 - val_accuracy: 0.8653\n",
            "Epoch 5/15\n",
            "375/375 [==============================] - 591s 2s/step - loss: 0.2251 - accuracy: 0.9153 - val_loss: 0.2367 - val_accuracy: 0.9160\n",
            "Epoch 6/15\n",
            "375/375 [==============================] - 594s 2s/step - loss: 0.1915 - accuracy: 0.9310 - val_loss: 0.3613 - val_accuracy: 0.8940\n",
            "Epoch 7/15\n",
            "375/375 [==============================] - 594s 2s/step - loss: 0.1517 - accuracy: 0.9427 - val_loss: 0.2245 - val_accuracy: 0.9213\n",
            "Epoch 8/15\n",
            "375/375 [==============================] - 599s 2s/step - loss: 0.1180 - accuracy: 0.9573 - val_loss: 0.2478 - val_accuracy: 0.9263\n",
            "Epoch 9/15\n",
            "375/375 [==============================] - 593s 2s/step - loss: 0.1017 - accuracy: 0.9620 - val_loss: 0.2637 - val_accuracy: 0.9237\n",
            "Epoch 10/15\n",
            "375/375 [==============================] - 597s 2s/step - loss: 0.0851 - accuracy: 0.9682 - val_loss: 0.4091 - val_accuracy: 0.8843\n",
            "Epoch 11/15\n",
            "375/375 [==============================] - 600s 2s/step - loss: 0.0752 - accuracy: 0.9725 - val_loss: 0.2158 - val_accuracy: 0.9367\n",
            "Epoch 12/15\n",
            "375/375 [==============================] - 598s 2s/step - loss: 0.0640 - accuracy: 0.9768 - val_loss: 0.2192 - val_accuracy: 0.9437\n",
            "Epoch 13/15\n",
            "375/375 [==============================] - 595s 2s/step - loss: 0.0521 - accuracy: 0.9827 - val_loss: 0.2586 - val_accuracy: 0.9280\n",
            "Epoch 14/15\n",
            "375/375 [==============================] - 600s 2s/step - loss: 0.0551 - accuracy: 0.9802 - val_loss: 0.4129 - val_accuracy: 0.8973\n",
            "Epoch 15/15\n",
            "375/375 [==============================] - 600s 2s/step - loss: 0.0367 - accuracy: 0.9870 - val_loss: 0.2088 - val_accuracy: 0.9540\n",
            "94/94 [==============================] - 34s 365ms/step - loss: 0.2088 - accuracy: 0.9540\n",
            "94/94 [==============================] - 36s 385ms/step\n",
            "Model: \"sequential_4\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " conv2d_9 (Conv2D)           (None, 126, 126, 32)      896       \n",
            "                                                                 \n",
            " batch_normalization_3 (Batc  (None, 126, 126, 32)     128       \n",
            " hNormalization)                                                 \n",
            "                                                                 \n",
            " max_pooling2d_9 (MaxPooling  (None, 63, 63, 32)       0         \n",
            " 2D)                                                             \n",
            "                                                                 \n",
            " dropout_8 (Dropout)         (None, 63, 63, 32)        0         \n",
            "                                                                 \n",
            " conv2d_10 (Conv2D)          (None, 61, 61, 64)        18496     \n",
            "                                                                 \n",
            " max_pooling2d_10 (MaxPoolin  (None, 30, 30, 64)       0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " conv2d_11 (Conv2D)          (None, 28, 28, 128)       73856     \n",
            "                                                                 \n",
            " max_pooling2d_11 (MaxPoolin  (None, 14, 14, 128)      0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " flatten_4 (Flatten)         (None, 25088)             0         \n",
            "                                                                 \n",
            " dense_16 (Dense)            (None, 256)               6422784   \n",
            "                                                                 \n",
            " dropout_9 (Dropout)         (None, 256)               0         \n",
            "                                                                 \n",
            " dense_17 (Dense)            (None, 128)               32896     \n",
            "                                                                 \n",
            " dropout_10 (Dropout)        (None, 128)               0         \n",
            "                                                                 \n",
            " dense_18 (Dense)            (None, 64)                8256      \n",
            "                                                                 \n",
            " dense_19 (Dense)            (None, 3)                 195       \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 6,557,507\n",
            "Trainable params: 6,557,443\n",
            "Non-trainable params: 64\n",
            "_________________________________________________________________\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.save('/content/GoogleDrive/MyDrive/Colab Notebooks/Neural Networks/Selected2 Project/model3.h5')\n",
        "# new_model = model.load_weights('/content/GoogleDrive/MyDrive/Colab Notebooks/Neural Networks/Selected2 Project/model.h5')"
      ],
      "metadata": {
        "id": "aR8gzctW1IkY"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# epochs = range(1,15)\n",
        "plt.plot(history.history['accuracy'], label = 'Training Accuracy')\n",
        "plt.plot(history.history['val_accuracy'], label = 'Testing Accuracy')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Accuracy')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 452
        },
        "id": "cId2mAn6eXWw",
        "outputId": "0cbabc84-be78-4a8e-f65a-9b1096d7c84d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.plot(history.history['loss'], label = 'Training Loss')\n",
        "plt.plot(history.history['val_loss'], label = 'Testing Loss')\n",
        "plt.xlabel('Epochs')\n",
        "plt.ylabel('Loss')\n",
        "plt.legend()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 449
        },
        "id": "uulcHW9Z2lRe",
        "outputId": "1bc356df-e01b-4b7d-ce8a-947d7098d4d6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(classes)\n",
        "print(y_test[:25], '\\n')\n",
        "print(y_pred[:25], '\\n')\n",
        "\n",
        "predict = []\n",
        "for i in range(3000): #len(y_pred)\n",
        "  predict.append(np.argmax(y_pred[i]))\n",
        "\n",
        "print(predict[:25], '\\n')\n",
        "\n",
        "cm = confusion_matrix(y_test, predict)\n",
        "print(cm, '\\n')\n",
        "\n",
        "zol = zero_one_loss(y_test, predict, normalize = False)\n",
        "print(zol)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "95YSmFe598P2",
        "outputId": "4c37f146-7153-495a-ffa9-cadd198d3466"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "['brain_tumor', 'brain_menin', 'brain_glioma']\n",
            "[0 0 2 0 0 1 2 0 0 0 0 2 2 0 0 2 2 0 2 1 2 2 0 0 0] \n",
            "\n",
            "[[9.9992400e-01 7.5901422e-05 2.9794058e-09]\n",
            " [9.9999684e-01 3.0507995e-06 9.0490039e-11]\n",
            " [6.9533474e-13 6.2490763e-11 9.9999994e-01]\n",
            " [9.9999994e-01 7.4280668e-12 2.8352125e-17]\n",
            " [9.9999994e-01 5.3939068e-08 4.1361425e-11]\n",
            " [1.5169085e-04 9.9521255e-01 4.6356926e-03]\n",
            " [6.3160705e-08 3.7380460e-08 9.9999982e-01]\n",
            " [9.4262594e-01 5.7244722e-02 1.2920726e-04]\n",
            " [9.9991912e-01 8.0592858e-05 2.0055425e-07]\n",
            " [9.9999994e-01 2.4570270e-12 6.1827067e-19]\n",
            " [9.9999994e-01 1.7949433e-09 4.2337236e-13]\n",
            " [3.7844119e-15 7.6265730e-12 9.9999994e-01]\n",
            " [2.3165061e-17 5.2599343e-14 9.9999994e-01]\n",
            " [9.9999994e-01 8.5868685e-15 1.2439935e-22]\n",
            " [9.9973774e-01 2.6231236e-04 5.1519994e-10]\n",
            " [5.7318434e-04 2.1256880e-01 7.8685790e-01]\n",
            " [1.8529448e-21 3.8842917e-16 9.9999994e-01]\n",
            " [9.9999207e-01 7.8664234e-06 8.1447444e-09]\n",
            " [8.0888890e-24 1.9546778e-18 9.9999994e-01]\n",
            " [9.0069038e-13 9.9999994e-01 4.6872189e-12]\n",
            " [4.3045342e-19 3.4783535e-15 9.9999994e-01]\n",
            " [5.4754526e-12 5.1192801e-09 9.9999994e-01]\n",
            " [9.9999994e-01 3.1691073e-11 3.1072641e-16]\n",
            " [9.9999994e-01 9.4551283e-11 4.3657793e-15]\n",
            " [9.9997252e-01 2.5521616e-05 1.8710292e-06]] \n",
            "\n",
            "[0, 0, 2, 0, 0, 1, 2, 0, 0, 0, 0, 2, 2, 0, 0, 2, 2, 0, 2, 1, 2, 2, 0, 0, 0] \n",
            "\n",
            "[[969  23   8]\n",
            " [ 44 941  15]\n",
            " [  1  47 952]]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.figure(figsize = (5,5))\n",
        "ConfusionMatrixDisplay(cm).plot()\n",
        "plt.show()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "tyrQBSqkkrE4",
        "outputId": "0f058052-f6e1-4303-a8d7-a490e97a6d46"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 500x500 with 0 Axes>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "test_img_path = '/content/GoogleDrive/MyDrive/Colab Notebooks/Neural Networks/Selected2 Project/dataset/test/brain_menin/brain_menin_0089.jpg'\n",
        "\n",
        "test_img = cv2.imread(test_img_path)\n",
        "test_img = cv2.resize(test_img, (128,128))\n",
        "\n",
        "plt.imshow(test_img)\n",
        "plt.title(test_img_path.split('\\\\')[-1])\n",
        "\n",
        "test_img = test_img[tf.newaxis, ...]\n",
        "\n",
        "print(model.predict(test_img))\n",
        "print(classes)"
      ],
      "metadata": {
        "id": "yFl8coCNNtqk"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}