{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "85dcc51c",
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import os\n",
    "import cv2\n",
    "import imghdr\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "945cdd4c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#To create augmented dataset and store it locally\n",
    "#DONOT RUN THIS NOW THAT THE AUGMENTED DATASET HAS ALREADY BEEN CREATED\n",
    "ans=input(\"Are you sure you want to run this(y/n): \")\n",
    "if(ans==\"y\"): \n",
    "    from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "    datagen = ImageDataGenerator(\n",
    "            rotation_range=45,     \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",
    "    i = 0\n",
    "    for batch in datagen.flow_from_directory(directory=\"pepe_folder\", \n",
    "                                             batch_size=20,  \n",
    "                                             target_size=(256, 256),\n",
    "                                             color_mode=\"rgb\",\n",
    "                                             save_to_dir=r'data\\aug_pepe', \n",
    "                                             save_prefix='aug', \n",
    "                                             save_format='png'):\n",
    "        i += 1\n",
    "        if i > 60:\n",
    "            break\n",
    "\n",
    "    i = 0\n",
    "    for batch in datagen.flow_from_directory(directory=\"notpepe_folder\", \n",
    "                                             batch_size=20,  \n",
    "                                             target_size=(256, 256),\n",
    "                                             color_mode=\"rgb\",\n",
    "                                             save_to_dir=r'data\\aug_notpepe', \n",
    "                                             save_prefix='aug', \n",
    "                                             save_format='png'):\n",
    "        i += 1\n",
    "        if i > 60:\n",
    "            break"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b27e514f",
   "metadata": {},
   "outputs": [],
   "source": [
    "#to retrieve augmented dataset and remove corrupted files from it\n",
    "data_dir = 'data' \n",
    "image_exts = ['jpeg','jpg', 'bmp', 'png']\n",
    "for image_class in os.listdir(data_dir): \n",
    "    for image in os.listdir(os.path.join(data_dir, image_class)):\n",
    "        image_path = os.path.join(data_dir, image_class, image)\n",
    "        try: \n",
    "            img = cv2.imread(image_path)\n",
    "            tip = imghdr.what(image_path)\n",
    "            if tip not in image_exts: \n",
    "                print('Image not in ext list {}'.format(image_path))\n",
    "                os.remove(image_path)\n",
    "        except Exception as e: \n",
    "            print('Issue with image {}'.format(image_path))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "75b52f06",
   "metadata": {},
   "outputs": [],
   "source": [
    "predata = tf.keras.utils.image_dataset_from_directory('data')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e1d8486d",
   "metadata": {},
   "outputs": [],
   "source": [
    "data_iterator = predata.as_numpy_iterator()\n",
    "batch = data_iterator.next()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "81675bd7",
   "metadata": {},
   "outputs": [],
   "source": [
    "#to view a sample batch and verify the labels\n",
    "fig, ax = plt.subplots(ncols=4, figsize=(20,20))\n",
    "for idx, img in enumerate(batch[0][:4]):\n",
    "    ax[idx].imshow(img.astype(int))\n",
    "    ax[idx].title.set_text(batch[1][idx])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e55af779",
   "metadata": {},
   "outputs": [],
   "source": [
    "#scaling the images\n",
    "data = predata.map(lambda x,y: (x/255, y))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "91ca596a",
   "metadata": {},
   "outputs": [],
   "source": [
    "#splitting the dataset into training, validation and testing\n",
    "train_size = int(len(data)*.7)\n",
    "val_size = int(len(data)*.2)+1\n",
    "test_size = int(len(data)*.1)\n",
    "train = data.take(train_size)\n",
    "val = data.skip(train_size).take(val_size)\n",
    "test = data.skip(train_size+val_size).take(test_size)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "75fd8b96",
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.models import Sequential\n",
    "from tensorflow.keras.layers import Conv2D, MaxPooling2D, Dense, Flatten,BatchNormalization,Input"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f2eb4c6d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#building the model architecture\n",
    "model = Sequential()\n",
    "model.add(Input(shape=(256, 256, 3)))\n",
    "model.add(Conv2D(16, (3, 3), strides=1, activation='relu'))\n",
    "model.add(BatchNormalization())\n",
    "model.add(MaxPooling2D())\n",
    "\n",
    "model.add(Conv2D(32, (3, 3), strides=1, activation='relu'))\n",
    "model.add(BatchNormalization())\n",
    "model.add(MaxPooling2D())\n",
    "\n",
    "model.add(Conv2D(16, (3, 3), strides=1, activation='relu'))\n",
    "model.add(MaxPooling2D())\n",
    "\n",
    "model.add(Flatten())\n",
    "model.add(Dense(256, activation='relu'))\n",
    "model.add(Dense(1, activation='sigmoid'))\n",
    "\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "\n",
    "learning_rate = 0.0006\n",
    "optimizer = Adam(learning_rate=learning_rate)\n",
    "\n",
    "model.compile(optimizer=optimizer, loss=tf.losses.BinaryCrossentropy(), metrics=['accuracy'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7c639b2c",
   "metadata": {},
   "outputs": [],
   "source": [
    "#to view the model summary\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "99a49621",
   "metadata": {},
   "outputs": [],
   "source": [
    "#saving logs\n",
    "logdir='logs'\n",
    "tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir=logdir)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5c550f6f",
   "metadata": {},
   "outputs": [],
   "source": [
    "hist = model.fit(train, epochs=10, validation_data=val, callbacks=[tensorboard_callback])\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d19ccb13",
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.metrics import Precision, Recall, BinaryAccuracy"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "d6237387",
   "metadata": {},
   "outputs": [],
   "source": [
    "#calculating precision, recall and binary accuracy\n",
    "pre = Precision()\n",
    "re = Recall()\n",
    "acc = BinaryAccuracy()\n",
    "for batch in test.as_numpy_iterator(): \n",
    "    X, y = batch\n",
    "    yhat = model.predict(X)\n",
    "    pre.update_state(y, yhat)\n",
    "    re.update_state(y, yhat)\n",
    "    acc.update_state(y, yhat)\n",
    "print(pre.result(), re.result(), acc.result())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2db17093",
   "metadata": {},
   "outputs": [],
   "source": [
    "#calculating the F1 score and test accuracy\n",
    "from sklearn.metrics import f1_score\n",
    "test_images = []\n",
    "test_labels = []\n",
    "\n",
    "for image, label in test:\n",
    "    test_images.append(image)\n",
    "    test_labels.append(label)\n",
    "\n",
    "test_images = tf.concat(test_images, axis=0)\n",
    "test_labels = tf.concat(test_labels, axis=0)\n",
    "\n",
    "\n",
    "y_pred = model.predict(test_images)\n",
    "y_pred_binary = (y_pred > 0.5).astype(int)  \n",
    "y_true = test_labels  \n",
    "\n",
    "\n",
    "f1 = f1_score(y_true, y_pred_binary)\n",
    "\n",
    "print(\"F1 Score:\", f1)\n",
    "test_loss = model.evaluate(test)\n",
    "print(\"Test Loss:\", test_loss)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b937369d",
   "metadata": {},
   "outputs": [],
   "source": [
    "#plotting the losses\n",
    "fig = plt.figure()\n",
    "plt.plot(hist.history['loss'], color='teal', label='Training Loss')\n",
    "plt.plot(hist.history['val_loss'], color='orange', label='Validation Loss')\n",
    "\n",
    "\n",
    "plt.axhline(y=test_loss[0], color='red', linestyle='--', label='Test Loss')\n",
    "\n",
    "fig.suptitle('Loss', fontsize=20)\n",
    "plt.legend(loc=\"upper left\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "618e8ed4",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in range(13):\n",
    "    img = cv2.imread(f\"C:/Users/91896/Desktop/not/OIP ({i}).jpeg\")\n",
    "    plt.imshow(img)\n",
    "    resize = tf.image.resize(img, (256,256))\n",
    "    plt.imshow(resize.numpy().astype(int))\n",
    "    plt.show()\n",
    "    yhat = model.predict(np.expand_dims(resize/255, 0))\n",
    "    yhat\n",
    "    if yhat > 0.5: \n",
    "        print(f'Pepe Found')\n",
    "    else:\n",
    "        print(f'Pepe Not Found')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "a453a1ec",
   "metadata": {},
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'model' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[1], line 4\u001b[0m\n\u001b[0;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtensorflow\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mkeras\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmodels\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m load_model\n\u001b[0;32m      3\u001b[0m \u001b[38;5;66;03m# Saving the model\u001b[39;00m\n\u001b[1;32m----> 4\u001b[0m model\u001b[38;5;241m.\u001b[39msave(\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mimageclassifier.keras\u001b[39m\u001b[38;5;124m'\u001b[39m)\n",
      "\u001b[1;31mNameError\u001b[0m: name 'model' is not defined"
     ]
    }
   ],
   "source": [
    "from tensorflow.keras.models import load_model\n",
    "\n",
    "# Saving the model\n",
    "model.save('imageclassifier.keras')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9df6180d",
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aaac6285",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}