{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Brain Tumor MRI Detection"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "pip install tensorflow"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from tensorflow.keras.models import load_model\n",
    "from tensorflow.keras.preprocessing import image\n",
    "import os\n",
    "import numpy as np\n",
    "from PIL import Image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Current Directory: e:\\Github Projects\\BrainTumorMRIDetection\n"
     ]
    }
   ],
   "source": [
    "current_dir = os.getcwd()\n",
    "print (\"Current Directory: \" + current_dir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "train_dir = os.path.join(current_dir, 'Testing')\n",
    "val_dir = os.path.join(current_dir, 'Training')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the target size and batch size\n",
    "target_size = (1250, 1250)\n",
    "batch_size = 32\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 394 images belonging to 4 classes.\n",
      "Found 2870 images belonging to 4 classes.\n"
     ]
    }
   ],
   "source": [
    "# Define the training and validation data generators\n",
    "train_datagen = ImageDataGenerator(rescale=1./255)\n",
    "train_generator = train_datagen.flow_from_directory(\n",
    "    train_dir,\n",
    "    target_size=target_size,\n",
    "    batch_size=batch_size,\n",
    "    class_mode='categorical')\n",
    "\n",
    "val_datagen = ImageDataGenerator(rescale=1./255)\n",
    "val_generator = val_datagen.flow_from_directory(\n",
    "    val_dir,\n",
    "    target_size=target_size,\n",
    "    batch_size=batch_size,\n",
    "    class_mode='categorical')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Define the model\n",
    "model = tf.keras.models.Sequential([\n",
    "    tf.keras.layers.Conv2D(32, (3, 3), activation='relu',\n",
    "                           input_shape=(target_size[0], target_size[1], 3)),\n",
    "    tf.keras.layers.MaxPooling2D((2, 2)),\n",
    "    tf.keras.layers.Conv2D(64, (3, 3), activation='relu'),\n",
    "    tf.keras.layers.MaxPooling2D((2, 2)),\n",
    "    tf.keras.layers.Conv2D(128, (3, 3), activation='relu'),\n",
    "    tf.keras.layers.MaxPooling2D((2, 2)),\n",
    "    tf.keras.layers.Flatten(),\n",
    "    tf.keras.layers.Dense(128, activation='relu'),\n",
    "    tf.keras.layers.Dropout(0.5),\n",
    "    tf.keras.layers.Dense(train_generator.num_classes, activation='softmax')\n",
    "])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Compile the model\n",
    "model.compile(optimizer='adam',\n",
    "              loss='categorical_crossentropy',\n",
    "              metrics=['accuracy'])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/15\n",
      "12/12 [==============================] - 753s 64s/step - loss: 17.4665 - accuracy: 0.2431 - val_loss: 1.4717 - val_accuracy: 0.2883\n",
      "Epoch 2/15\n",
      "12/12 [==============================] - 694s 60s/step - loss: 1.1907 - accuracy: 0.4779 - val_loss: 1.4602 - val_accuracy: 0.2798\n",
      "Epoch 3/15\n",
      "12/12 [==============================] - 704s 61s/step - loss: 0.8829 - accuracy: 0.6575 - val_loss: 1.5343 - val_accuracy: 0.2791\n",
      "Epoch 4/15\n",
      "12/12 [==============================] - 697s 61s/step - loss: 0.4633 - accuracy: 0.8398 - val_loss: 1.7458 - val_accuracy: 0.3206\n",
      "Epoch 5/15\n",
      "12/12 [==============================] - 690s 60s/step - loss: 0.2428 - accuracy: 0.9309 - val_loss: 2.3506 - val_accuracy: 0.3536\n",
      "Epoch 6/15\n",
      "12/12 [==============================] - 698s 61s/step - loss: 0.1575 - accuracy: 0.9558 - val_loss: 2.2596 - val_accuracy: 0.3588\n",
      "Epoch 7/15\n",
      "12/12 [==============================] - 694s 61s/step - loss: 0.1069 - accuracy: 0.9696 - val_loss: 1.9421 - val_accuracy: 0.3272\n",
      "Epoch 8/15\n",
      "12/12 [==============================] - 694s 61s/step - loss: 0.0688 - accuracy: 0.9807 - val_loss: 3.2596 - val_accuracy: 0.3711\n",
      "Epoch 9/15\n",
      "12/12 [==============================] - 685s 61s/step - loss: 0.1024 - accuracy: 0.9696 - val_loss: 2.0157 - val_accuracy: 0.3722\n",
      "Epoch 10/15\n",
      "12/12 [==============================] - 699s 61s/step - loss: 0.0556 - accuracy: 0.9890 - val_loss: 2.7399 - val_accuracy: 0.3430\n",
      "Epoch 11/15\n",
      "12/12 [==============================] - 696s 61s/step - loss: 0.0561 - accuracy: 0.9862 - val_loss: 2.4300 - val_accuracy: 0.3831\n",
      "Epoch 12/15\n",
      "12/12 [==============================] - 684s 60s/step - loss: 0.0320 - accuracy: 0.9917 - val_loss: 2.5653 - val_accuracy: 0.3511\n",
      "Epoch 13/15\n",
      "12/12 [==============================] - 681s 61s/step - loss: 0.0493 - accuracy: 0.9890 - val_loss: 2.8736 - val_accuracy: 0.3515\n",
      "Epoch 14/15\n",
      "12/12 [==============================] - 689s 60s/step - loss: 0.0213 - accuracy: 0.9917 - val_loss: 3.0044 - val_accuracy: 0.3704\n",
      "Epoch 15/15\n",
      "12/12 [==============================] - 692s 62s/step - loss: 0.0407 - accuracy: 0.9917 - val_loss: 2.8754 - val_accuracy: 0.3838\n"
     ]
    }
   ],
   "source": [
    "# Train the model\n",
    "history = model.fit(\n",
    "    train_generator,\n",
    "    steps_per_epoch=train_generator.samples//batch_size,\n",
    "    epochs=15,\n",
    "    validation_data=val_generator,\n",
    "    validation_steps=val_generator.samples//batch_size)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Saving The Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Save the trained model in the current directory\n",
    "model.save(os.path.join(current_dir, 'model.h5'))"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "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": "3.8.8"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}