brain_tumour.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "b05540d3",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-03-01 10:29:17.550984: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n",
      "2023-03-01 10:29:17.648974: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:17.648996: I tensorflow/compiler/xla/stream_executor/cuda/cudart_stub.cc:29] Ignore above cudart dlerror if you do not have a GPU set up on your machine.\n",
      "2023-03-01 10:29:18.187224: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer.so.7'; dlerror: libnvinfer.so.7: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:18.187288: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libnvinfer_plugin.so.7'; dlerror: libnvinfer_plugin.so.7: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:18.187296: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Cannot dlopen some TensorRT libraries. If you would like to use Nvidia GPU with TensorRT, please make sure the missing libraries mentioned above are installed properly.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "import tensorflow as tf \n",
    "from tensorflow import keras\n",
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Activation, Dense, Flatten, Conv2D, MaxPool2D, Dropout,Input\n",
    "from tensorflow.keras.models import Model\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "from tensorflow.keras.metrics import categorical_crossentropy\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from sklearn.metrics import confusion_matrix\n",
    "import datetime, os\n",
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "from sklearn.metrics import confusion_matrix\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "67353293",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_path = '/home/murali/DeepLearning/dataset/BrainTumour/Training'\n",
    "test_path = '/home/murali/DeepLearning/dataset/BrainTumour/Testing'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "ec9bc225",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_datagen = ImageDataGenerator(validation_split=0.2,rescale=1./255)\n",
    "test_datagen = ImageDataGenerator(rescale=1./255)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "73d4afbb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2297 images belonging to 4 classes.\n",
      "Found 573 images belonging to 4 classes.\n",
      "Found 394 images belonging to 4 classes.\n"
     ]
    }
   ],
   "source": [
    "train_batches = train_datagen.flow_from_directory(\n",
    "        train_path,\n",
    "        target_size=(64, 64),\n",
    "        batch_size=32,\n",
    "        subset='training',\n",
    "        class_mode='categorical')\n",
    "\n",
    "validation_batches = train_datagen.flow_from_directory(\n",
    "        train_path,\n",
    "        target_size=(64, 64),\n",
    "        batch_size=32,\n",
    "        subset='validation',\n",
    "        class_mode='categorical')\n",
    "\n",
    "\n",
    "test_batches = test_datagen.flow_from_directory(\n",
    "         test_path,\n",
    "         target_size=(64, 64),\n",
    "        batch_size=32,\n",
    "        class_mode='categorical')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "215392a0",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-03-01 10:29:21.706182: I tensorflow/compiler/xla/stream_executor/cuda/cuda_gpu_executor.cc:981] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero\n",
      "2023-03-01 10:29:21.706430: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudart.so.11.0'; dlerror: libcudart.so.11.0: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706492: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublas.so.11'; dlerror: libcublas.so.11: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706562: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcublasLt.so.11'; dlerror: libcublasLt.so.11: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706634: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcufft.so.10'; dlerror: libcufft.so.10: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706703: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcurand.so.10'; dlerror: libcurand.so.10: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706766: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusolver.so.11'; dlerror: libcusolver.so.11: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706830: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcusparse.so.11'; dlerror: libcusparse.so.11: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706895: W tensorflow/compiler/xla/stream_executor/platform/default/dso_loader.cc:64] Could not load dynamic library 'libcudnn.so.8'; dlerror: libcudnn.so.8: cannot open shared object file: No such file or directory\n",
      "2023-03-01 10:29:21.706909: W tensorflow/core/common_runtime/gpu/gpu_device.cc:1934] Cannot dlopen some GPU libraries. Please make sure the missing libraries mentioned above are installed properly if you would like to use GPU. Follow the guide at https://www.tensorflow.org/install/gpu for how to download and setup the required libraries for your platform.\n",
      "Skipping registering GPU devices...\n",
      "2023-03-01 10:29:21.707225: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  AVX2 FMA\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "model = Sequential()\n",
    "model.add(Conv2D(32, 3, activation='relu' , input_shape=(64,64,3)))\n",
    "model.add(MaxPool2D())\n",
    "model.add(Dropout(0.25))\n",
    "model.add(Conv2D(64, 3, activation='relu'))\n",
    "model.add(MaxPool2D())\n",
    "model.add(Flatten())\n",
    "\n",
    "#hidden layer 1\n",
    "model.add(Dense(128 , activation = 'relu'))\n",
    "model.add(Dropout(0.25))\n",
    "\n",
    "#hidden layer 2\n",
    "model.add(Dense(64 , activation = 'relu'))\n",
    "model.add(Dropout(0.25))\n",
    "\n",
    "#hidden layer 3\n",
    "model.add(Dense(32 , activation = 'relu'))\n",
    "model.add(Dropout(0.25))\n",
    "\n",
    "# output layer\n",
    "model.add(Dense(4 , activation = 'softmax'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "e1a2210f",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"sequential\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " conv2d (Conv2D)             (None, 62, 62, 32)        896       \n",
      "                                                                 \n",
      " max_pooling2d (MaxPooling2D  (None, 31, 31, 32)       0         \n",
      " )                                                               \n",
      "                                                                 \n",
      " dropout (Dropout)           (None, 31, 31, 32)        0         \n",
      "                                                                 \n",
      " conv2d_1 (Conv2D)           (None, 29, 29, 64)        18496     \n",
      "                                                                 \n",
      " max_pooling2d_1 (MaxPooling  (None, 14, 14, 64)       0         \n",
      " 2D)                                                             \n",
      "                                                                 \n",
      " flatten (Flatten)           (None, 12544)             0         \n",
      "                                                                 \n",
      " dense (Dense)               (None, 128)               1605760   \n",
      "                                                                 \n",
      " dropout_1 (Dropout)         (None, 128)               0         \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 64)                8256      \n",
      "                                                                 \n",
      " dropout_2 (Dropout)         (None, 64)                0         \n",
      "                                                                 \n",
      " dense_2 (Dense)             (None, 32)                2080      \n",
      "                                                                 \n",
      " dropout_3 (Dropout)         (None, 32)                0         \n",
      "                                                                 \n",
      " dense_3 (Dense)             (None, 4)                 132       \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 1,635,620\n",
      "Trainable params: 1,635,620\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    }
   ],
   "source": [
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "d9cf3b69",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/7\n",
      "72/72 - 7s - loss: 1.2746 - accuracy: 0.4057 - val_loss: 1.2186 - val_accuracy: 0.3298 - 7s/epoch - 100ms/step\n",
      "Epoch 2/7\n",
      "72/72 - 6s - loss: 0.9416 - accuracy: 0.5973 - val_loss: 1.1296 - val_accuracy: 0.4101 - 6s/epoch - 86ms/step\n",
      "Epoch 3/7\n",
      "72/72 - 6s - loss: 0.7624 - accuracy: 0.6670 - val_loss: 1.1256 - val_accuracy: 0.4817 - 6s/epoch - 89ms/step\n",
      "Epoch 4/7\n",
      "72/72 - 7s - loss: 0.6559 - accuracy: 0.7231 - val_loss: 1.0173 - val_accuracy: 0.5305 - 7s/epoch - 94ms/step\n",
      "Epoch 5/7\n",
      "72/72 - 7s - loss: 0.5356 - accuracy: 0.7719 - val_loss: 0.9995 - val_accuracy: 0.6283 - 7s/epoch - 94ms/step\n",
      "Epoch 6/7\n",
      "72/72 - 6s - loss: 0.5014 - accuracy: 0.7989 - val_loss: 0.8831 - val_accuracy: 0.6754 - 6s/epoch - 82ms/step\n",
      "Epoch 7/7\n",
      "72/72 - 7s - loss: 0.3989 - accuracy: 0.8346 - val_loss: 1.0420 - val_accuracy: 0.6702 - 7s/epoch - 96ms/step\n"
     ]
    }
   ],
   "source": [
    "# model compiling\n",
    "model.compile('adam' , loss = 'categorical_crossentropy' , metrics = ['accuracy'])\n",
    "\n",
    "# training model\n",
    "history= model.fit(x=train_batches,\n",
    "    validation_data=validation_batches,\n",
    "    epochs=7,\n",
    "    verbose=2\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "e3bfd6e8",
   "metadata": {},
   "outputs": [],
   "source": [
    "predictions = model.predict(x=test_batches, verbose=0)\n",
    "predictions=np.round(predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "a71723bb",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "13/13 [==============================] - 2s 128ms/step - loss: 1.9991 - accuracy: 0.5431\n",
      "[1.9991201162338257, 0.5431472063064575]\n"
     ]
    }
   ],
   "source": [
    "print(model.evaluate(x=test_batches))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a9482b28",
   "metadata": {},
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "5b4aa012",
   "metadata": {},
   "outputs": [],
   "source": [
    "cm = confusion_matrix(y_true=test_batches.classes,y_pred=np.argmax(predictions,axis=1))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "989c0a0b",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "ax = sns.heatmap(cm, annot=True, xticklabels=[\"pituitary_tumor\",'no_tumor',\"meningioma_tumor\",\"glioma_tumor\"], yticklabels=[\"pituitary_tumor\",'no_tumor',\"meningioma_tumor\",\"glioma_tumor\"],\n",
    "                cbar=False,cmap='Blues')\n",
    "ax.set_xlabel('Prediction')\n",
    "ax.set_ylabel('Actual')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99231c1d",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}