{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:28:24.809574Z",
          "iopub.status.busy": "2023-03-09T11:28:24.808412Z",
          "iopub.status.idle": "2023-03-09T11:28:24.815326Z",
          "shell.execute_reply": "2023-03-09T11:28:24.814327Z",
          "shell.execute_reply.started": "2023-03-09T11:28:24.809514Z"
        },
        "trusted": true,
        "id": "ZLLl1AD9wdmC"
      },
      "outputs": [],
      "source": [
        "import keras\n",
        "from keras.models import Sequential\n",
        "from keras.layers import Conv2D,Flatten,Dense,MaxPooling2D,Dropout\n",
        "from sklearn.metrics import accuracy_score\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v2XHSE-2wdmC",
        "outputId": "514f6ed7-a546-467b-e6a0-7ced066f82d8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Downloading...\n",
            "From: https://drive.google.com/uc?id=1gbwBMoFv9qyE_Brs4wrPH5hIIm4wXZH-\n",
            "To: /content/dataset.zip\n",
            "100%|██████████| 91.0M/91.0M [00:02<00:00, 32.5MB/s]\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['.config', 'Training', 'dataset.zip', 'Testing', 'sample_data']"
            ]
          },
          "metadata": {},
          "execution_count": 2
        }
      ],
      "source": [
        "# Import the library to download files\n",
        "import gdown\n",
        "\n",
        "# Define the Google Drive file ID from the shared link\n",
        "file_id = '1gbwBMoFv9qyE_Brs4wrPH5hIIm4wXZH-'\n",
        "\n",
        "# Define the destination directory where you want to save the dataset\n",
        "output_dir = '/content/'\n",
        "\n",
        "# Construct the download URL\n",
        "url = f'https://drive.google.com/uc?id={file_id}'\n",
        "\n",
        "# Download the file to the specified directory\n",
        "gdown.download(url, output_dir + 'dataset.zip', quiet=False)\n",
        "\n",
        "# Unzip the downloaded dataset\n",
        "import zipfile\n",
        "with zipfile.ZipFile(output_dir + 'dataset.zip', 'r') as zip_ref:\n",
        "     zip_ref.extractall(output_dir)\n",
        "\n",
        "# List the files in the directory to verify the extraction\n",
        "import os\n",
        "os.listdir(output_dir)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:28:24.817226Z",
          "iopub.status.busy": "2023-03-09T11:28:24.816730Z",
          "iopub.status.idle": "2023-03-09T11:28:24.827544Z",
          "shell.execute_reply": "2023-03-09T11:28:24.826387Z",
          "shell.execute_reply.started": "2023-03-09T11:28:24.817188Z"
        },
        "trusted": true,
        "id": "iGZ1ucqcwdmC"
      },
      "outputs": [],
      "source": [
        "import ipywidgets as widgets #required for classification\n",
        "import io #for input n output\n",
        "from PIL import Image #PIL is Public Image Library\n",
        "import tqdm\n",
        "from sklearn.model_selection import train_test_split\n",
        "import cv2\n",
        "from sklearn.utils import shuffle #for spliting train n test data..\n",
        "import tensorflow as tf\n",
        "import numpy as np\n",
        "from tensorflow.keras import Sequential\n",
        "from tensorflow.keras import layers"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "E7z_5UKFwdmD"
      },
      "source": [
        "FolderPaths"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:28:24.831016Z",
          "iopub.status.busy": "2023-03-09T11:28:24.830634Z",
          "iopub.status.idle": "2023-03-09T11:28:35.758595Z",
          "shell.execute_reply": "2023-03-09T11:28:35.757538Z",
          "shell.execute_reply.started": "2023-03-09T11:28:24.830976Z"
        },
        "trusted": true,
        "id": "59vlJ7OdwdmD"
      },
      "outputs": [],
      "source": [
        "X_train = []\n",
        "Y_train = []\n",
        "image_size = 150\n",
        "labels = ['glioma_tumor','meningioma_tumor','no_tumor','pituitary_tumor']\n",
        "for i in labels:\n",
        "    folderPath = os.path.join('/content/Training',i) #os.path.join joins two path to create a new.\n",
        "    for j in os.listdir(folderPath):\n",
        "        img = cv2.imread(os.path.join(folderPath,j))\n",
        "        img = cv2.resize(img,(image_size,image_size))\n",
        "        X_train.append(img)\n",
        "        Y_train.append(i)\n",
        "\n",
        "for i in labels:\n",
        "    folderPath = os.path.join('/content/Testing',i)\n",
        "    for j in os.listdir(folderPath):\n",
        "        img = cv2.imread(os.path.join(folderPath,j))\n",
        "        img = cv2.resize(img,(image_size,image_size))\n",
        "        X_train.append(img)\n",
        "        Y_train.append(i)\n",
        "\n",
        "X_train = np.array(X_train)\n",
        "Y_train = np.array(Y_train)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:28:35.760593Z",
          "iopub.status.busy": "2023-03-09T11:28:35.759897Z",
          "iopub.status.idle": "2023-03-09T11:28:35.836739Z",
          "shell.execute_reply": "2023-03-09T11:28:35.835560Z",
          "shell.execute_reply.started": "2023-03-09T11:28:35.760552Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "lBRbft9CwdmE",
        "outputId": "52f30d5c-b36a-4972-dc89-e02fe4c96c07"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(3264, 150, 150, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 5
        }
      ],
      "source": [
        "X_train, Y_train = shuffle(X_train, Y_train, random_state=101)\n",
        "X_train.shape\n",
        "#3264 images, 150 height, 150 width, 3 color channels\n"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "7Wp33nT1wdmE"
      },
      "source": [
        "TRAIN TEST SPLIT"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:30:02.652234Z",
          "iopub.status.busy": "2023-03-09T11:30:02.651024Z",
          "iopub.status.idle": "2023-03-09T11:30:02.678179Z",
          "shell.execute_reply": "2023-03-09T11:30:02.676443Z",
          "shell.execute_reply.started": "2023-03-09T11:30:02.652179Z"
        },
        "trusted": true,
        "id": "BFWy0APjwdmE"
      },
      "outputs": [],
      "source": [
        "X_train,X_test,y_train,y_test = train_test_split(X_train,Y_train,test_size=0.1,random_state=101)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:34:00.115635Z",
          "iopub.status.busy": "2023-03-09T11:34:00.114375Z",
          "iopub.status.idle": "2023-03-09T11:34:00.126671Z",
          "shell.execute_reply": "2023-03-09T11:34:00.125625Z",
          "shell.execute_reply.started": "2023-03-09T11:34:00.115591Z"
        },
        "trusted": true,
        "id": "BEe9hfHWwdmE"
      },
      "outputs": [],
      "source": [
        "y_train_new = []\n",
        "for i in y_train:\n",
        "    y_train_new.append(labels.index(i))\n",
        "y_train=y_train_new\n",
        "y_train = tf.keras.utils.to_categorical(y_train) #convert label indexes to categorical\n",
        "\n",
        "y_test_new = []\n",
        "for i in y_test:\n",
        "    y_test_new.append(labels.index(i))\n",
        "y_test=y_test_new\n",
        "y_test = tf.keras.utils.to_categorical(y_test)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "w_hU3kU3wdmE"
      },
      "source": [
        "Convolutional Neural Network"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:44:34.614035Z",
          "iopub.status.busy": "2023-03-09T11:44:34.613642Z",
          "iopub.status.idle": "2023-03-09T11:44:37.366867Z",
          "shell.execute_reply": "2023-03-09T11:44:37.365887Z",
          "shell.execute_reply.started": "2023-03-09T11:44:34.614000Z"
        },
        "trusted": true,
        "id": "z5FaXoy_wdmE"
      },
      "outputs": [],
      "source": [
        "import tensorflow as tf\n",
        "from tensorflow import keras\n",
        "from tensorflow.keras import layers\n",
        "from tensorflow.keras.layers import *\n",
        "\n",
        "\n",
        "model = Sequential()\n",
        "model.add(Conv2D(32,(3,3),activation = 'relu',input_shape=(150,150,3)))\n",
        "model.add(Conv2D(64,(3,3),activation='relu'))\n",
        "model.add(MaxPooling2D(2,2))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Conv2D(64,(3,3),activation='relu'))\n",
        "model.add(Conv2D(64,(3,3),activation='relu'))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(MaxPooling2D(2,2))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Conv2D(128,(3,3),activation='relu'))\n",
        "model.add(Conv2D(128,(3,3),activation='relu'))\n",
        "model.add(Conv2D(128,(3,3),activation='relu'))\n",
        "model.add(MaxPooling2D(2,2))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Conv2D(128,(3,3),activation='relu'))\n",
        "model.add(Conv2D(256,(3,3),activation='relu'))\n",
        "model.add(MaxPooling2D(2,2))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Flatten())\n",
        "model.add(Dense(512,activation = 'relu'))\n",
        "model.add(Dense(512,activation = 'relu'))\n",
        "model.add(Dropout(0.3))\n",
        "model.add(Dense(4,activation='softmax')) #softmax we used b'coz we will be dealing with probaility, YES or NO\n",
        "\n",
        "#we added this much layers coz we have 4 categories."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:44:51.756237Z",
          "iopub.status.busy": "2023-03-09T11:44:51.755839Z",
          "iopub.status.idle": "2023-03-09T11:44:51.810542Z",
          "shell.execute_reply": "2023-03-09T11:44:51.809733Z",
          "shell.execute_reply.started": "2023-03-09T11:44:51.756204Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "q93EWqSmwdmF",
        "outputId": "7ab4daa8-074c-405b-a47e-66bca79580a8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Model: \"sequential\"\n",
            "_________________________________________________________________\n",
            " Layer (type)                Output Shape              Param #   \n",
            "=================================================================\n",
            " conv2d (Conv2D)             (None, 148, 148, 32)      896       \n",
            "                                                                 \n",
            " conv2d_1 (Conv2D)           (None, 146, 146, 64)      18496     \n",
            "                                                                 \n",
            " max_pooling2d (MaxPooling2  (None, 73, 73, 64)        0         \n",
            " D)                                                              \n",
            "                                                                 \n",
            " dropout (Dropout)           (None, 73, 73, 64)        0         \n",
            "                                                                 \n",
            " conv2d_2 (Conv2D)           (None, 71, 71, 64)        36928     \n",
            "                                                                 \n",
            " conv2d_3 (Conv2D)           (None, 69, 69, 64)        36928     \n",
            "                                                                 \n",
            " dropout_1 (Dropout)         (None, 69, 69, 64)        0         \n",
            "                                                                 \n",
            " max_pooling2d_1 (MaxPoolin  (None, 34, 34, 64)        0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " dropout_2 (Dropout)         (None, 34, 34, 64)        0         \n",
            "                                                                 \n",
            " conv2d_4 (Conv2D)           (None, 32, 32, 128)       73856     \n",
            "                                                                 \n",
            " conv2d_5 (Conv2D)           (None, 30, 30, 128)       147584    \n",
            "                                                                 \n",
            " conv2d_6 (Conv2D)           (None, 28, 28, 128)       147584    \n",
            "                                                                 \n",
            " max_pooling2d_2 (MaxPoolin  (None, 14, 14, 128)       0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " dropout_3 (Dropout)         (None, 14, 14, 128)       0         \n",
            "                                                                 \n",
            " conv2d_7 (Conv2D)           (None, 12, 12, 128)       147584    \n",
            "                                                                 \n",
            " conv2d_8 (Conv2D)           (None, 10, 10, 256)       295168    \n",
            "                                                                 \n",
            " max_pooling2d_3 (MaxPoolin  (None, 5, 5, 256)         0         \n",
            " g2D)                                                            \n",
            "                                                                 \n",
            " dropout_4 (Dropout)         (None, 5, 5, 256)         0         \n",
            "                                                                 \n",
            " flatten (Flatten)           (None, 6400)              0         \n",
            "                                                                 \n",
            " dense (Dense)               (None, 512)               3277312   \n",
            "                                                                 \n",
            " dense_1 (Dense)             (None, 512)               262656    \n",
            "                                                                 \n",
            " dropout_5 (Dropout)         (None, 512)               0         \n",
            "                                                                 \n",
            " dense_2 (Dense)             (None, 4)                 2052      \n",
            "                                                                 \n",
            "=================================================================\n",
            "Total params: 4447044 (16.96 MB)\n",
            "Trainable params: 4447044 (16.96 MB)\n",
            "Non-trainable params: 0 (0.00 Byte)\n",
            "_________________________________________________________________\n"
          ]
        }
      ],
      "source": [
        "model.summary()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:47:06.856783Z",
          "iopub.status.busy": "2023-03-09T11:47:06.855807Z",
          "iopub.status.idle": "2023-03-09T11:47:06.876356Z",
          "shell.execute_reply": "2023-03-09T11:47:06.875442Z",
          "shell.execute_reply.started": "2023-03-09T11:47:06.856743Z"
        },
        "trusted": true,
        "id": "reovYVjXwdmF"
      },
      "outputs": [],
      "source": [
        "model.compile(loss=\"categorical_crossentropy\", optimizer=\"Adam\", metrics=[\"accuracy\"])\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "history = model.fit(X_train,y_train,epochs=10,validation_split=0.1)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xcihuima1mpK",
        "outputId": "c9513654-d2b3-4965-b8f6-ca98a98454a9"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/10\n",
            "83/83 [==============================] - 27s 126ms/step - loss: 2.0661 - accuracy: 0.3148 - val_loss: 1.3551 - val_accuracy: 0.3027\n",
            "Epoch 2/10\n",
            "83/83 [==============================] - 8s 97ms/step - loss: 1.2339 - accuracy: 0.4408 - val_loss: 1.1637 - val_accuracy: 0.5034\n",
            "Epoch 3/10\n",
            "83/83 [==============================] - 8s 99ms/step - loss: 1.0115 - accuracy: 0.5573 - val_loss: 0.9309 - val_accuracy: 0.5986\n",
            "Epoch 4/10\n",
            "83/83 [==============================] - 8s 99ms/step - loss: 0.8723 - accuracy: 0.6186 - val_loss: 0.9028 - val_accuracy: 0.5952\n",
            "Epoch 5/10\n",
            "83/83 [==============================] - 8s 98ms/step - loss: 0.7562 - accuracy: 0.6814 - val_loss: 0.7056 - val_accuracy: 0.6905\n",
            "Epoch 6/10\n",
            "83/83 [==============================] - 8s 98ms/step - loss: 0.6755 - accuracy: 0.7246 - val_loss: 0.6138 - val_accuracy: 0.7245\n",
            "Epoch 7/10\n",
            "83/83 [==============================] - 8s 100ms/step - loss: 0.5313 - accuracy: 0.7817 - val_loss: 0.5720 - val_accuracy: 0.7517\n",
            "Epoch 8/10\n",
            "83/83 [==============================] - 8s 98ms/step - loss: 0.4710 - accuracy: 0.8157 - val_loss: 0.5534 - val_accuracy: 0.7925\n",
            "Epoch 9/10\n",
            "83/83 [==============================] - 8s 99ms/step - loss: 0.4209 - accuracy: 0.8275 - val_loss: 0.4872 - val_accuracy: 0.8163\n",
            "Epoch 10/10\n",
            "83/83 [==============================] - 8s 100ms/step - loss: 0.3521 - accuracy: 0.8630 - val_loss: 0.5633 - val_accuracy: 0.7789\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:52:27.320099Z",
          "iopub.status.busy": "2023-03-09T11:52:27.319462Z",
          "iopub.status.idle": "2023-03-09T11:52:27.538292Z",
          "shell.execute_reply": "2023-03-09T11:52:27.537183Z",
          "shell.execute_reply.started": "2023-03-09T11:52:27.320041Z"
        },
        "trusted": true,
        "id": "_yt_3AFbwdmF"
      },
      "outputs": [],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "import seaborn as sns"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:55:52.571512Z",
          "iopub.status.busy": "2023-03-09T11:55:52.570787Z",
          "iopub.status.idle": "2023-03-09T11:55:52.987038Z",
          "shell.execute_reply": "2023-03-09T11:55:52.985836Z",
          "shell.execute_reply.started": "2023-03-09T11:55:52.571474Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 457
        },
        "id": "eAA7qv1BwdmF",
        "outputId": "4bcc8da4-7d76-4795-c6be-4969e93b42f4"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x700 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "model.save('braintumor.h5')\n",
        "\n",
        "acc = history.history['accuracy']\n",
        "val_acc = history.history['val_accuracy']\n",
        "epochs=range(len(acc))\n",
        "fig = plt.figure(figsize=(14, 7))\n",
        "plt.plot(epochs,acc,'r',label=\"Training Accuracy\")\n",
        "plt.plot(epochs,val_acc,'b',label=\"Validation Accuracy\")\n",
        "plt.legend(loc=\"upper left\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T11:57:50.642761Z",
          "iopub.status.busy": "2023-03-09T11:57:50.642142Z",
          "iopub.status.idle": "2023-03-09T11:57:50.879916Z",
          "shell.execute_reply": "2023-03-09T11:57:50.878807Z",
          "shell.execute_reply.started": "2023-03-09T11:57:50.642721Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 453
        },
        "id": "zuOGHQ-1wdmF",
        "outputId": "9712c3bf-d1c5-4a59-ebbe-a1be96b1573b"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 1400x700 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "loss = history.history['loss']\n",
        "val_loss = history.history['val_loss']\n",
        "epochs=range(len(loss))\n",
        "fig = plt.figure(figsize=(14, 7))\n",
        "plt.plot(epochs,loss,'r',label=\"Training loss\")\n",
        "plt.plot(epochs,val_loss,'b',label=\"Validation loss\")\n",
        "plt.legend(loc=\"upper left\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VwDZ0Ay3wdmF"
      },
      "source": [
        "Prediction of the model"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 28,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T12:00:26.577322Z",
          "iopub.status.busy": "2023-03-09T12:00:26.576368Z",
          "iopub.status.idle": "2023-03-09T12:00:26.590363Z",
          "shell.execute_reply": "2023-03-09T12:00:26.588929Z",
          "shell.execute_reply.started": "2023-03-09T12:00:26.577266Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0N6l8cKGwdmF",
        "outputId": "d7350cfc-4ac5-4b69-b7dc-3f044500064d"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(150, 150, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 28
        }
      ],
      "source": [
        "img = cv2.imread('/content/Testing/no_tumor/image(1).jpg')\n",
        "img = cv2.resize(img,(150,150))\n",
        "img_array = np.array(img)\n",
        "img_array.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 29,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T12:01:25.391347Z",
          "iopub.status.busy": "2023-03-09T12:01:25.390840Z",
          "iopub.status.idle": "2023-03-09T12:01:25.399122Z",
          "shell.execute_reply": "2023-03-09T12:01:25.397867Z",
          "shell.execute_reply.started": "2023-03-09T12:01:25.391303Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "llzqyyLQwdmG",
        "outputId": "173495d8-6970-4c90-c739-8809b7193e06"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(1, 150, 150, 3)"
            ]
          },
          "metadata": {},
          "execution_count": 29
        }
      ],
      "source": [
        "img_array = img_array.reshape(1, 150, 150, 3)\n",
        "img_array.shape"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 30,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T12:02:57.493932Z",
          "iopub.status.busy": "2023-03-09T12:02:57.493551Z",
          "iopub.status.idle": "2023-03-09T12:02:57.733304Z",
          "shell.execute_reply": "2023-03-09T12:02:57.732233Z",
          "shell.execute_reply.started": "2023-03-09T12:02:57.493895Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 435
        },
        "id": "7b9s8gs7wdmG",
        "outputId": "496dcc69-96be-43dc-8377-4e1850d66a8c"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "from tensorflow.keras.preprocessing import image\n",
        "img = image.load_img('/content/Testing/no_tumor/image(1).jpg')\n",
        "plt.imshow(img,interpolation='nearest')\n",
        "plt.show()\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 31,
      "metadata": {
        "execution": {
          "iopub.execute_input": "2023-03-09T12:04:14.571513Z",
          "iopub.status.busy": "2023-03-09T12:04:14.570758Z",
          "iopub.status.idle": "2023-03-09T12:04:14.862892Z",
          "shell.execute_reply": "2023-03-09T12:04:14.861917Z",
          "shell.execute_reply.started": "2023-03-09T12:04:14.571472Z"
        },
        "trusted": true,
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "UTiyF4NPwdmG",
        "outputId": "256b868c-2f95-4545-9edc-0fff2bec69b1"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1/1 [==============================] - 0s 19ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2"
            ]
          },
          "metadata": {},
          "execution_count": 31
        }
      ],
      "source": [
        "a=model.predict(img_array)\n",
        "indices = a.argmax() #argmax() will return the largest value....\n",
        "indices"
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "####DISCLAIMER:\n",
        "\n",
        "0-glioma_tumor,\n",
        "\n",
        "1-meningioma_tumor,\n",
        "\n",
        "2-No_tumor,\n",
        "\n",
        "3-pituitary_tumor"
      ],
      "metadata": {
        "id": "ArFqzThz7XEE"
      }
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FhX9sVN8wdmG"
      },
      "source": [
        "Here, we seen that we can predict which  type of tumor it is.."
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.6.4"
    },
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "accelerator": "GPU"
  },
  "nbformat": 4,
  "nbformat_minor": 0
}