{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "from keras.layers import Conv2D,MaxPooling2D,Dense,Flatten,Dropout\n",
    "from keras import Sequential\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "from tensorflow.keras.preprocessing import image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Zip file extracted successfully.\n"
     ]
    }
   ],
   "source": [
    "from zipfile import ZipFile\n",
    "\n",
    "zip_file_path = 'bone_frac.zip'\n",
    "\n",
    "with ZipFile(zip_file_path, 'r') as zip_ref:\n",
    "    zip_ref.extractall()\n",
    "\n",
    "print(\"Zip file extracted successfully.\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "Training = 'archive (6)/train'\n",
    "Validation = 'archive (6)/val'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "img_width, img_height = 224, 224\n",
    "batch_size = 32"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 8863 images belonging to 2 classes.\n",
      "Found 600 images belonging to 2 classes.\n"
     ]
    }
   ],
   "source": [
    "#Data Augmentation\n",
    "\n",
    "train_datagen = ImageDataGenerator(\n",
    "    rescale=1.0/255,\n",
    "    rotation_range=20,\n",
    "    width_shift_range=0.2,\n",
    "    height_shift_range=0.2,\n",
    "    shear_range=0.2,\n",
    "    zoom_range=0.2,\n",
    "    horizontal_flip=True,\n",
    "    fill_mode='nearest'\n",
    ")\n",
    "\n",
    "#Rescale validation images \n",
    "validation_datagen = ImageDataGenerator(rescale=1.0/255)\n",
    "\n",
    "#loading train n val data:\n",
    "\n",
    "train_generator = train_datagen.flow_from_directory(\n",
    "    Training,\n",
    "    target_size=(img_width, img_height),\n",
    "    batch_size=batch_size,\n",
    "    class_mode='binary'\n",
    ")\n",
    "\n",
    "validation_generator = validation_datagen.flow_from_directory(\n",
    "    Validation,\n",
    "    target_size=(img_width, img_height),\n",
    "    batch_size=batch_size,\n",
    "    class_mode='binary'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "#building CNN model\n",
    "\n",
    "model = Sequential()\n",
    "\n",
    "model.add(Conv2D(32, (3,3), activation='relu', input_shape=(img_width, img_height, 3)))\n",
    "model.add(MaxPooling2D((2,2)))\n",
    "\n",
    "model.add(Conv2D(64, (3,3), activation='relu'))\n",
    "model.add(MaxPooling2D((2,2)))\n",
    "\n",
    "model.add(Conv2D(128, (3,3), activation='relu'))\n",
    "model.add(MaxPooling2D((2,2)))\n",
    "\n",
    "model.add(Flatten())\n",
    "\n",
    "model.add(Dense(128, activation='relu'))\n",
    "model.add(Dropout(0.5))\n",
    "\n",
    "model.add(Dense(1, activation='sigmoid'))\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(optimizer='Adam', loss='binary_crossentropy', metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "276/276 [==============================] - 450s 2s/step - loss: 0.6812 - accuracy: 0.5570 - val_loss: 0.6559 - val_accuracy: 0.5533\n",
      "Epoch 2/5\n",
      "276/276 [==============================] - 457s 2s/step - loss: 0.6691 - accuracy: 0.5919 - val_loss: 0.6212 - val_accuracy: 0.6000\n",
      "Epoch 3/5\n",
      "276/276 [==============================] - 301s 1s/step - loss: 0.6513 - accuracy: 0.5942 - val_loss: 0.5682 - val_accuracy: 0.6800\n",
      "Epoch 4/5\n",
      "276/276 [==============================] - 302s 1s/step - loss: 0.6283 - accuracy: 0.6159 - val_loss: 0.6609 - val_accuracy: 0.5000\n",
      "Epoch 5/5\n",
      "276/276 [==============================] - 303s 1s/step - loss: 0.6163 - accuracy: 0.6440 - val_loss: 0.5883 - val_accuracy: 0.6767\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(\n",
    "    train_generator,\n",
    "    steps_per_epoch=train_generator.samples / batch_size,\n",
    "    validation_data=validation_generator,\n",
    "    validation_steps=(validation_generator.samples / batch_size),\n",
    "    epochs=5)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "19/19 [==============================] - 4s 203ms/step - loss: 0.5883 - accuracy: 0.6767\n",
      "Test accuracy:  67.67%\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_acc = model.evaluate(validation_generator)\n",
    "print(f'Test accuracy: {test_acc * 100: .2f}%') #.2f means float no. upto 2 decimals"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save('bone_model.h5')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = tf.keras.models.load_model('bone_model.h5')\n",
    "\n",
    "img_path = 'archive (6)/val/fractured\\9.jpg'\n",
    "img = image.load_img(img_path, target_size=(224,224))\n",
    "img_array = image.img_to_array(img)\n",
    "img_array = np.expand_dims(img_array, axis=0)\n",
    "img_array /= 255.0"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1/1 [==============================] - 0s 76ms/step\n"
     ]
    }
   ],
   "source": [
    "#making prediction\n",
    "\n",
    "prediction = model.predict(img_array)\n",
    "predicted_class=int(np.round(prediction)[0][0]) #[0][0]\n",
    "\n",
    "class_labels = ['Not Fractured', 'Fractured']\n",
    "\n",
    "\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Predicted class: Fractured (Confidence: 57.78%)\n"
     ]
    }
   ],
   "source": [
    "print(f\"Predicted class: {class_labels[predicted_class]} (Confidence: {prediction[0][0] * 100:.2f}%)\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.7"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}