{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "57037210",
   "metadata": {},
   "source": [
    "#### Import Libraries"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "93086509",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import tensorflow as tf\n",
    "\n",
    "from tensorflow.keras.models import Sequential\n",
    "\n",
    "from tensorflow.keras.layers import (\n",
    "\n",
    "    Input,\n",
    "    Conv2D,\n",
    "    MaxPooling2D,\n",
    "    Flatten,\n",
    "    Dense,\n",
    "    Dropout,\n",
    "    BatchNormalization\n",
    "\n",
    ")\n",
    "\n",
    "from tensorflow.keras.preprocessing.image import (\n",
    "    ImageDataGenerator\n",
    ")\n",
    "\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "\n",
    "from tensorflow.keras.optimizers.schedules import (\n",
    "    CosineDecay\n",
    ")\n",
    "\n",
    "from tensorflow.keras.callbacks import (\n",
    "\n",
    "    EarlyStopping,\n",
    "    ModelCheckpoint\n",
    "\n",
    ")\n",
    "\n",
    "from tensorflow.keras.regularizers import l2\n",
    "\n",
    "from sklearn.utils.class_weight import (\n",
    "    compute_class_weight\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "647fb1dc",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Natalia\\AppData\\Local\\Temp\\ipykernel_6492\\929672231.py:27: FutureWarning: \n",
      "\n",
      "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `y` variable to `hue` and set `legend=False` for the same effect.\n",
      "\n",
      "  ax = sns.barplot(\n"
     ]
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Original Class Distribution\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "class_df = pd.DataFrame({\n",
    "\n",
    "    'Class': [\n",
    "        'Scab',\n",
    "        'Healthy',\n",
    "        'Frog Eye Leaf Spot',\n",
    "        'Rust',\n",
    "        'Powdery Mildew'\n",
    "    ],\n",
    "\n",
    "    'Images': [\n",
    "        3378,\n",
    "        3236,\n",
    "        2226,\n",
    "        1302,\n",
    "        828\n",
    "    ]\n",
    "})\n",
    "\n",
    "plt.figure(figsize=(10,6))\n",
    "\n",
    "ax = sns.barplot(\n",
    "    data=class_df,\n",
    "    y='Class',\n",
    "    x='Images',\n",
    "    palette='viridis'\n",
    ")\n",
    "\n",
    "for p in ax.patches:\n",
    "    ax.annotate(\n",
    "        f'{int(p.get_width())}',\n",
    "        (p.get_width(), p.get_y()+p.get_height()/2),\n",
    "        ha='left',\n",
    "        va='center',\n",
    "        fontweight='bold'\n",
    "    )\n",
    "\n",
    "plt.title('Original Training Dataset Distribution')\n",
    "plt.xlabel('Number of Images')\n",
    "plt.ylabel('Disease Class')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5a72e0c8",
   "metadata": {},
   "source": [
    "#### Data Augumentation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "1b1df22b",
   "metadata": {},
   "outputs": [],
   "source": [
    "train_datagen = ImageDataGenerator(\n",
    "\n",
    "    rescale=1./255,\n",
    "\n",
    "    rotation_range=20,\n",
    "\n",
    "    width_shift_range=0.10,\n",
    "\n",
    "    height_shift_range=0.10,\n",
    "\n",
    "    zoom_range=0.15,\n",
    "\n",
    "    horizontal_flip=True,\n",
    "\n",
    "    brightness_range=[0.8,1.2]\n",
    "\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1e2352ad",
   "metadata": {},
   "source": [
    "#### Validation Generator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "72fa432a",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2352 images belonging to 5 classes.\n"
     ]
    }
   ],
   "source": [
    "val_datagen = ImageDataGenerator(\n",
    "    rescale=1./255\n",
    ")\n",
    "\n",
    "validation_generator = val_datagen.flow_from_directory(\n",
    "\n",
    "    \"plant_split_dataset/validation\",\n",
    "\n",
    "    target_size=(160,160),\n",
    "\n",
    "    batch_size=64,\n",
    "\n",
    "    class_mode='categorical',\n",
    "\n",
    "    shuffle=False\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "818ff8a9",
   "metadata": {},
   "source": [
    "#### Test Generator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f8479950",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2353 images belonging to 5 classes.\n"
     ]
    }
   ],
   "source": [
    "test_datagen = ImageDataGenerator(\n",
    "    rescale=1./255\n",
    ")\n",
    "\n",
    "test_generator = test_datagen.flow_from_directory(\n",
    "\n",
    "    \"plant_split_dataset/test\",\n",
    "\n",
    "    target_size=(160,160),\n",
    "\n",
    "    batch_size=64,\n",
    "\n",
    "    class_mode='categorical',\n",
    "\n",
    "    shuffle=False\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c1d9155",
   "metadata": {},
   "source": [
    "#### Training Generator"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "266752a6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 13855 images belonging to 5 classes.\n"
     ]
    }
   ],
   "source": [
    "train_generator = train_datagen.flow_from_directory(\n",
    "\n",
    "    \"plant_split_dataset/train\",\n",
    "\n",
    "    target_size=(160,160),\n",
    "\n",
    "    batch_size=64,\n",
    "\n",
    "    class_mode='categorical'\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "9c039af4",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "['frog_eye_leaf_spot', 'healthy', 'powdery_mildew', 'rust', 'scab']\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "# Count Images Per Class\n",
    "train_dir = \"plant_split_dataset/train\"\n",
    "\n",
    "class_names = []\n",
    "labels = []\n",
    "\n",
    "for idx, class_name in enumerate(sorted(os.listdir(train_dir))):\n",
    "\n",
    "    class_path = os.path.join(\n",
    "        train_dir,\n",
    "        class_name\n",
    "    )\n",
    "\n",
    "    if os.path.isdir(class_path):\n",
    "\n",
    "        image_count = len(os.listdir(class_path))\n",
    "\n",
    "        class_names.append(class_name)\n",
    "\n",
    "        labels.extend(\n",
    "            [idx] * image_count\n",
    "        )\n",
    "\n",
    "print(class_names)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5e841e0c",
   "metadata": {},
   "source": [
    "#### Compute Class Weights"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "15be9d2c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{0: np.float64(1.2448337825696316), 1: np.float64(0.8563040791100124), 2: np.float64(0.9187665782493368), 3: np.float64(1.386193096548274), 4: np.float64(0.820307874481942)}\n"
     ]
    }
   ],
   "source": [
    "weights = compute_class_weight(\n",
    "\n",
    "    class_weight='balanced',\n",
    "\n",
    "    classes=np.unique(\n",
    "        train_generator.classes\n",
    "    ),\n",
    "\n",
    "    y=train_generator.classes\n",
    ")\n",
    "\n",
    "class_weights = dict(\n",
    "    enumerate(weights)\n",
    ")\n",
    "\n",
    "print(class_weights)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "9a892d17",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Class</th>\n",
       "      <th>Weight</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>frog_eye_leaf_spot</td>\n",
       "      <td>1.244834</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>healthy</td>\n",
       "      <td>0.856304</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>powdery_mildew</td>\n",
       "      <td>0.918767</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>rust</td>\n",
       "      <td>1.386193</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>scab</td>\n",
       "      <td>0.820308</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                Class    Weight\n",
       "0  frog_eye_leaf_spot  1.244834\n",
       "1             healthy  0.856304\n",
       "2      powdery_mildew  0.918767\n",
       "3                rust  1.386193\n",
       "4                scab  0.820308"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "weight_df = pd.DataFrame({\n",
    "\n",
    "    \"Class\": class_names,\n",
    "\n",
    "    \"Weight\": weights\n",
    "\n",
    "})\n",
    "\n",
    "weight_df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "7d9db20e",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Natalia\\AppData\\Local\\Temp\\ipykernel_6492\\4247672820.py:3: FutureWarning: \n",
      "\n",
      "Passing `palette` without assigning `hue` is deprecated and will be removed in v0.14.0. Assign the `x` variable to `hue` and set `legend=False` for the same effect.\n",
      "\n",
      "  sns.barplot(\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA04AAAIjCAYAAAA0vUuxAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAZktJREFUeJzt3Xd4FFX//vF70xtJCCUECASQqhgQ6SgBIgERQURQUAIKohRRBBV9pFjAgggqSnkURAVUmiJNQEPvEB/EEFroCVUSiiaQnN8f/Jiva4KTCGGBvF/XtRe7M+fMfGZ32N07M3PWYYwxAgAAAABclpurCwAAAACA6x3BCQAAAABsEJwAAAAAwAbBCQAAAABsEJwAAAAAwAbBCQAAAABsEJwAAAAAwAbBCQAAAABsEJwAAAAAwAbBCQBwQ4iIiFDXrl2v6jKHDh0qh8NxVZd5o4iLi5PD4VBcXNy/7jtjxoyrXxgAXKcITgBwjezevVs9e/ZU+fLl5ePjo8DAQDVs2FBjxozRH3/84eryror58+dr6NChri5Df/75p95//33VrVtXQUFB8vHxUaVKldSnTx/t2LHD1eVdVmZmpgIDA9WmTZts895//305HA7FxsZmmzd48GA5HI7rctumTp2q0aNHu7oMALhiHq4uAAAKgnnz5umhhx6St7e3unTpottuu00ZGRlauXKlBg4cqG3btmnChAmuLvOKzZ8/X2PHjnVpeDp+/LhatGihTZs26b777lOnTp0UEBCgxMRETZ8+XRMmTFBGRobL6vsn7u7uqlevnlavXp1t3qpVq+Th4aFVq1blOK948eKqVKlSrtd19913648//pCXl9cV1Wxn6tSp+vXXX/Xss8/m63oAIL8RnAAgnyUlJenhhx9W2bJl9dNPPyksLMya17t3b+3atUvz5s1zYYU3l65du2rLli2aMWOGHnzwQad5r7/+ul555RUXVZY7jRo10uLFi5WQkKCqVata01etWqUOHTpo6tSpSklJUYkSJSRJFy5c0Lp169S8efM8rcfNzU0+Pj5XtXYAuJlxqh4A5LN33nlHZ86c0aeffuoUmi655ZZb1K9fP+vxhQsX9Prrr6tChQry9vZWRESEXn75ZaWnpzv1i4iI0H333ae4uDjdeeed8vX1VfXq1a1rVmbNmqXq1avLx8dHtWrV0pYtW5z6d+3aVQEBAdqzZ49iYmLk7++vkiVL6rXXXpMxxmp3uWth9u7dK4fDocmTJ1vLGzt2rCTJ4XBYt0uysrI0evRo3XrrrfLx8VFoaKh69uyp33//3Wm5xhi98cYbKl26tPz8/NSkSRNt27YtV8/1unXrNG/ePD3xxBPZQpMkeXt7a+TIkf+4jEmTJqlp06YqXry4vL29Va1aNX3yySfZ2m3cuFExMTEqWrSofH19Va5cOT3++ONObaZPn65atWqpUKFCCgwMVPXq1TVmzJh/XH+jRo0kyenI0p49e5SSkqI+ffrIx8fHaV58fLzOnj1r9ZOk7du3q3379goJCZGPj4/uvPNOff/9907rudzrOnbsWJUvX16+vr6qU6eOVqxYoaioKEVFRWWrNSsrS2+++aZKly4tHx8fNWvWTLt27bLmR0VFad68edq3b5+1P0RERFjzP/zwQ916663y8/NT4cKFdeedd2rq1Kn/+PwAgKtwxAkA8tncuXNVvnx5NWjQIFftu3fvrs8//1zt27fX888/r3Xr1mnEiBFKSEjQ7Nmzndru2rVLnTp1Us+ePfXoo49q5MiRat26tcaNG6eXX35ZvXr1kiSNGDFCHTp0UGJiotzc/u9vZpmZmWrRooXq1aund955RwsXLtSQIUN04cIFvfbaa3nazp49e+rw4cNavHixvvjiixznT548Wd26ddMzzzyjpKQkffTRR9qyZYtWrVolT09PSRev13njjTd077336t5779XmzZvVvHnzXJ1edykcPPbYY3mq/a8++eQT3Xrrrbr//vvl4eGhuXPnqlevXsrKylLv3r0lSUePHlXz5s1VrFgxvfTSSwoODtbevXs1a9YsazmLFy/WI488ombNmuntt9+WJCUkJGjVqlVOQfnv6tWrJw8PD61cuVLdu3eXdDFE+fv7q3bt2rrzzju1atUqKxheClGXgtO2bdvUsGFDlSpVSi+99JL8/f31zTffqG3btpo5c6YeeOCBf9z2Pn366K677tJzzz2nvXv3qm3btipcuLBKly6drf1bb70lNzc3DRgwQKmpqXrnnXfUuXNnrVu3TpL0yiuvKDU1VQcPHtT7778vSQoICJAkTZw4Uc8884zat2+vfv366c8//9T//vc/rVu3Tp06dcrFKwUA15gBAOSb1NRUI8m0adMmV+3j4+ONJNO9e3en6QMGDDCSzE8//WRNK1u2rJFkVq9ebU1btGiRkWR8fX3Nvn37rOnjx483kszPP/9sTYuNjTWSTN++fa1pWVlZplWrVsbLy8scO3bMGGPMzz//nK2vMcYkJSUZSWbSpEnWtN69e5ucPlpWrFhhJJmvvvrKafrChQudph89etR4eXmZVq1amaysLKvdyy+/bCSZ2NjYyzxzFz3wwANGkvn999//sd0lQ4YMyVbvuXPnsrWLiYkx5cuXtx7Pnj3bSDIbNmy47LL79etnAgMDzYULF3JVy1/Vrl3bVKhQwXrcs2dP06RJE2OMMS+88IKpXbu2Na99+/bGz8/PnD9/3hhjTLNmzUz16tXNn3/+abXJysoyDRo0MBUrVrSm/f11TU9PN0WKFDG1a9e2lmWMMZMnTzaSTOPGjbP1rVq1qklPT7emjxkzxkgyW7dutaa1atXKlC1bNts2tmnTxtx66615fGYAwHU4VQ8A8lFaWpokqVChQrlqP3/+fElS//79naY///zzkpTtWqhq1aqpfv361uO6detKkpo2baoyZcpkm75nz55s6+zTp4913+FwqE+fPsrIyNCSJUtyVXNufPvttwoKCtI999yj48ePW7datWopICBAP//8syRpyZIlysjIUN++fZ1O88vtwAJ5fb5z4uvra91PTU3V8ePH1bhxY+3Zs0epqamSpODgYEnSDz/8oPPnz+e4nODgYJ09e1aLFy/Ocw2NGjXS7t27lZKSIuniUaVLRywbNmyoLVu26Ny5c9a8unXrysPDQydPntRPP/2kDh066PTp09bzfOLECcXExGjnzp06dOhQjuvcuHGjTpw4oR49esjD4/9OSOncubMKFy6cY59u3bo5DS5x1113Scp5P/u74OBgHTx4UBs2bMjFMwIArkdwAoB8FBgYKEk6ffp0rtrv27dPbm5uuuWWW5ymlyhRQsHBwdq3b5/T9L+GI0kKCgqSJIWHh+c4/e/XE7m5ual8+fJO0y6NzLZ3795c1ZwbO3fuVGpqqooXL65ixYo53c6cOaOjR49KkrV9FStWdOpfrFixy355/6u8Pt85WbVqlaKjo+Xv76/g4GAVK1ZML7/8siRZwalx48Z68MEHNWzYMBUtWlRt2rTRpEmTnK5D69WrlypVqqSWLVuqdOnSevzxx7Vw4cJc1fDX65xOnTplnX4nSQ0aNNCFCxe0fv16JSUlKTk52Wq/a9cuGWP06quvZnuehwwZIknWc/13l577v+97Hh4eTtcl/dXf979Lr9Hf97OcvPjiiwoICFCdOnVUsWJF9e7dO8cRAwHgesE1TgCQjwIDA1WyZEn9+uuveeqX2x9ldXd3z9N085dBH660lszMzFwvIysrS8WLF9dXX32V4/xixYrlua6cVKlSRZK0detW6+hHXuzevVvNmjVTlSpVNGrUKIWHh8vLy0vz58/X+++/r6ysLEmyfvx17dq1mjt3rhYtWqTHH39c7733ntauXauAgAAVL15c8fHxWrRokRYsWKAFCxZo0qRJ6tKliz7//PN/rONSEFq5cqX8/PwkyTqyWLRoUVWsWFErV67UgQMHnNpfqm/AgAGKiYnJcdl/D0ZX4kr2s6pVqyoxMVE//PCDFi5cqJkzZ+rjjz/W4MGDNWzYsKtWIwBcLQQnAMhn9913nyZMmKA1a9Y4nVaXk7JlyyorK0s7d+50Gor6yJEjOnXqlMqWLXtVa8vKytKePXucfv/n0o+oXjrKcOkowqlTp5z6/v3ol3T5kFWhQgUtWbJEDRs2dDoV7u8ubd/OnTudjoQdO3YsV0cxWrdurREjRujLL7/8V8Fp7ty5Sk9P1/fff+90NOXSqYR/V69ePdWrV09vvvmmpk6dqs6dO2v69OnWoA5eXl5q3bq1WrduraysLPXq1Uvjx4/Xq6+++o8Bpnjx4lY48vf3V7Vq1azTA6WLR51WrVqlgwcPyt3d3dqvLj1nnp6eio6OztO2X3rud+3apSZNmljTL1y4oL179+r222/P0/Iu+ac/Avj7+6tjx47q2LGjMjIy1K5dO7355psaNGgQQ6UDuO5wqh4A5LMXXnhB/v7+6t69u44cOZJt/u7du60hqu+9915J0ujRo53ajBo1SpLUqlWrq17fRx99ZN03xuijjz6Sp6enmjVrJuniF2p3d3ctX77cqd/HH3+cbVn+/v6SsoesDh06KDMzU6+//nq2PhcuXLDaR0dHy9PTUx9++KHTUYu/Px+XU79+fbVo0UL//e9/NWfOnGzzMzIyNGDAgMv2v3QE5a/rTk1N1aRJk5za/f7779mOqtSoUUOSrNP1Tpw44TTfzc3NCh9/H1o+J40aNVJ8fLx+/PHHbCMyNmjQQGvWrNGKFSt0++23W9d0FS9eXFFRURo/frySk5OzLfPYsWOXXd+dd96pIkWKaOLEibpw4YI1/auvvspVaL0cf39/6xTHv/r78+Pl5aVq1arJGHPZ68YAwJU44gQA+axChQqaOnWqOnbsqKpVq6pLly667bbblJGRodWrV+vbb79V165dJUmRkZGKjY3VhAkTdOrUKTVu3Fjr16/X559/rrZt2zodCbgafHx8tHDhQsXGxqpu3bpasGCB5s2bp5dfftk6fS4oKEgPPfSQPvzwQzkcDlWoUEE//PBDjtfK1KpVS5L0zDPPKCYmRu7u7nr44YfVuHFj9ezZUyNGjFB8fLyaN28uT09P7dy5U99++63GjBmj9u3bq1ixYhowYIBGjBih++67T/fee6+2bNmiBQsWqGjRornapilTpqh58+Zq166dWrdurWbNmsnf3187d+7U9OnTlZycfNnfcmrevLl1lKhnz546c+aMJk6cqOLFizsFkc8//1wff/yxHnjgAVWoUEGnT5/WxIkTFRgYaIXf7t276+TJk2ratKlKly6tffv26cMPP1SNGjWcjiZeTqNGjTRp0iRt2LDBGgb9kgYNGig1NVWpqanq27ev07yxY8eqUaNGql69unr06KHy5cvryJEjWrNmjQ4ePKhffvklx/V5eXlp6NCh6tu3r5o2baoOHTpo7969mjx5sipUqJDr00f/rlatWvr666/Vv39/1a5dWwEBAWrdurWaN2+uEiVKqGHDhgoNDVVCQoI++ugjtWrV6ooG9wCAfOO6Af0AoGDZsWOH6dGjh4mIiDBeXl6mUKFCpmHDhubDDz90Gjr6/PnzZtiwYaZcuXLG09PThIeHm0GDBjm1MebicOStWrXKth5Jpnfv3k7TLg0d/u6771rTYmNjjb+/v9m9e7dp3ry58fPzM6GhoWbIkCEmMzPTqf+xY8fMgw8+aPz8/EzhwoVNz549za+//pptOPILFy6Yvn37mmLFihmHw5FtqO8JEyaYWrVqGV9fX1OoUCFTvXp188ILL5jDhw9bbTIzM82wYcNMWFiY8fX1NVFRUebXX381ZcuWtR2O/JJz586ZkSNHmtq1a5uAgADj5eVlKlasaPr27Wt27dpltctpOPLvv//e3H777cbHx8dERESYt99+23z22WdGkklKSjLGGLN582bzyCOPmDJlyhhvb29TvHhxc99995mNGzday5kxY4Zp3ry5KV68uPHy8jJlypQxPXv2NMnJybnahsTERCPJSDI7duxwmpeVlWWCg4ONJPP1119n67t7927TpUsXU6JECePp6WlKlSpl7rvvPjNjxgyrzeWGmf/ggw9M2bJljbe3t6lTp45ZtWqVqVWrlmnRokW2vt9++61T35yGqD9z5ozp1KmTVe+locnHjx9v7r77blOkSBHj7e1tKlSoYAYOHGhSU1Nz9fwAwLXmMOZfXCkMALjhde3aVTNmzNCZM2dcXQquY1lZWSpWrJjatWuniRMnurocAHAZrnECAACSpD///DPbtVtTpkzRyZMnFRUV5ZqiAOA6wTVOAABAkrR27Vo999xzeuihh1SkSBFt3rxZn376qW677TY99NBDri4PAFyK4AQAACRdHII+PDxcH3zwgU6ePKmQkBB16dJFb731lry8vFxdHgC4FNc4AQAAAIANrnECAAAAABsEJwAAAACwUeCuccrKytLhw4dVqFChf/1jfgAAAABufMYYnT59WiVLlpSb2z8fUypwwenw4cMKDw93dRkAAAAArhMHDhxQ6dKl/7FNgQtOhQoVknTxyQkMDHRxNQAAAABcJS0tTeHh4VZG+CcFLjhdOj0vMDCQ4AQAAAAgV5fwMDgEAACAjeXLl+vee+9VsWLF5HA45HA4NG7cONt+o0ePVmRkpIKDg+Xt7a3SpUvroYce0v/+9z+ndlu3btWDDz6oUqVKycfHR7fffrsmTZqUX5sD4F8gOAEAANjYvHmzFi9erJCQkDz1W7ZsmY4dO6by5curQoUKSk5O1owZM9SkSROdPXtWkvTbb7+pXr16mjVrlv78809VrFhRW7du1eOPP67Ro0fnw9YA+DcITgAAADYee+wxpaWladGiRXnqN23aNB0+fFibN2/Wb7/9ppdfflmSdPLkSW3fvl2SNHnyZJ07d07e3t7auXOntm7darUbOnSo/vjjj6u7MQD+FYITAACAjSJFisjX1zfP/Xx8fDR79mzVq1dP1apV0/DhwyVJxYoVU6VKlSRd/KmUSy5dZ3FpWOTU1FRt2LDhSssHcBUUuMEhAAAArqUjR45o3bp11uNy5cpp7ty51ihe7dq10+jRo5Wenq6KFSuqZMmS+vXXX632hw4duuY1A8iOI04AAAD56KmnnlJWVpb27dunjh07KikpSR07dtTp06clSQ0aNNB3332nunXrKj09XSdOnFCXLl2s/p6enq4qHcBfEJwAAADymcPhUJkyZaxrl7Zt26Zp06ZZ81u1aqW1a9fq9OnTOnTokGJiYqx5lStXvub1AsiO4AQAAHAVNGvWTFWqVNGgQYMkSSdOnNAXX3yhjIwMq838+fOt+5dG1ZMujr53yYEDBzR06FBJ0q233qrbbrstnysHkBsOY4xxdRHXUlpamoKCgpSamsoP4AIAgFyZNWuWXnjhBV24cEH79u2TdHGAh8DAQNWtW1dfffWVIiIitG/fPsXGxmry5Mnau3evypUrJ19fX1WoUEGpqak6cOCAJKlQoULaunWrypYtK0kKCAiQn5+fQkNDtXPnTqWnp8vPz09LlixR/fr1XbbdwM0uL9mAI04AAAA20tLStHv3bis0SdKxY8e0e/fuyw7eEBwcrIcfflhhYWHavXu3kpOTFR4erkcffVTr1q2zQpMktW7dWh4eHkpMTJS/v7/atWunNWvWEJqA64hLjzgtX75c7777rjZt2qTk5GTNnj1bbdu2zVXfVatWqXHjxrrtttsUHx+f63VyxAkAAACAdAMdcTp79qwiIyM1duzYPPU7deqUunTpombNmuVTZQAAAADwf1z6O04tW7ZUy5Yt89zvqaeeUqdOneTu7q45c+Zc/cIAAAAA4C9uuGucJk2apD179mjIkCG5ap+enq60tDSnGwAAAADkxQ0VnHbu3KmXXnpJX375pTw8cnewbMSIEQoKCrJu4eHh+VwlAAAAgJvNDROcMjMz1alTJw0bNkyVKlXKdb9BgwYpNTXVul0aBhQAAAAAcsul1zjlxenTp7Vx40Zt2bJFffr0kSRlZWXJGCMPDw/9+OOPatq0abZ+3t7e8vb2vtblAgAAALiJ3DDBKTAwUFu3bnWa9vHHH+unn37SjBkzVK5cORdVBgAAAOBm59LgdObMGe3atct6nJSUpPj4eIWEhKhMmTIaNGiQDh06pClTpsjNzU233XabU//ixYvLx8cn23QAAAAAuJpcGpw2btyoJk2aWI/79+8vSYqNjdXkyZOVnJys/fv3u6o8AABwlSU9/5yrS8A1VO69911dAnDVOIwxxtVFXEt5+XVgAABwdRGcChaCE653eckGN8yoegAAAADgKgQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcAIAAAAAGwQnAAAAALBBcCpAli9frnvvvVfFihWTw+GQw+HQuHHjbPu99957ioqKUlhYmLy9vVW2bFnFxsZqz549ObY/ffq0KlSokKd1AAAAANczglMBsnnzZi1evFghISF56vfhhx9q+fLlCg4OVqlSpbR//35NmTJFDRs2VFpaWrb2ffr0uWyoAgAAAG5EBKcC5LHHHlNaWpoWLVqUp349evTQ3r17lZCQoD179ujZZ5+VJKWkpGjp0qVObb/55htNmTJFHTp0uFplAwAAAC5HcCpAihQpIl9f3zz3e+WVV1SmTBnr8V133WXd9/b2tu4fOHBAPXv2VK1atfTGG29cWbEAAADAdYTghDzJzMzUhAkTJEnly5dXs2bNJElZWVl67LHHdP78eU2dOlWenp6uLBMAAAC4qghOyLWzZ8/qgQce0KJFi1SiRAnNnTvXOuI0ZswYLVu2TGPGjFGlSpVcXCkAAABwdRGckCspKSlq3Lix5s6dq0qVKmnVqlWqVq2aNf+XX36RJPXr108BAQG69dZbrXnPPvusGjRocM1rBgAAAK4WghOcNGvWTFWqVNGgQYOsadu2bVO9evW0adMm3XXXXVqzZo3Kly+fY/+zZ8/q7NmzOnfunDUtPT3d6TEAAABwoyE4FSCzZs3SLbfcoqioKGva4MGDdcstt6hz586SpN27dysxMVHJyclWm3bt2mnfvn2SLv5G07333qt69eqpXr16+u9//ytJmjx5sowx1i0pKcnq/8knnyg+Pj7/NxAAAADIJx6uLgDXTlpamnbv3u007dixYzp27JhKly592X7p6enW/b8HoBYtWlzVGgEAAIDrEcGpAOnatau6du36j2327t2bq2l2IiIiZIzJcz8AAADgesSpegAAAABgg+AEAAAAADYITgAAAABgg+AEAAAAADYITgAAAABgg+AEAAAAADYITgAAAABgg99x+hdqlO7g6hJwDcUf/MbVJQAAAMDFOOIEAAAAADYITgAAAABgg+AEAAAAADYITgAAAABgg+AEAAAAADYITgAAAABgg+AEAAAAADYITgAAAABgg+AEAAAAADYITgAAAABgw6XBafny5WrdurVKliwph8OhOXPm/GP7WbNm6Z577lGxYsUUGBio+vXra9GiRdemWAAAAAAFlkuD09mzZxUZGamxY8fmqv3y5ct1zz33aP78+dq0aZOaNGmi1q1ba8uWLflcKQAAAICCzMOVK2/ZsqVatmyZ6/ajR492ejx8+HB99913mjt3rmrWrHmVqwMAAACAi1wanK5UVlaWTp8+rZCQkMu2SU9PV3p6uvU4LS3tWpQGAAAA4CZyQw8OMXLkSJ05c0YdOnS4bJsRI0YoKCjIuoWHh1/DCgEAAADcDG7Y4DR16lQNGzZM33zzjYoXL37ZdoMGDVJqaqp1O3DgwDWsEgAAAMDN4IY8VW/69Onq3r27vv32W0VHR/9jW29vb3l7e1+jygAAAADcjG64I07Tpk1Tt27dNG3aNLVq1crV5QAAAAAoAFx6xOnMmTPatWuX9TgpKUnx8fEKCQlRmTJlNGjQIB06dEhTpkyRdPH0vNjYWI0ZM0Z169ZVSkqKJMnX11dBQUEu2QYAAAAANz+XHnHauHGjatasaQ0l3r9/f9WsWVODBw+WJCUnJ2v//v1W+wkTJujChQvq3bu3wsLCrFu/fv1cUj8AAACAgsGlR5yioqJkjLns/MmTJzs9jouLy9+CAAAAACAHN9w1TgAAAABwrRGcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMAGwQkAAAAAbBCcAAAAAMCGS4PT8uXL1bp1a5UsWVIOh0Nz5syx7RMXF6c77rhD3t7euuWWWzR58uR8rxMAAABAwebS4HT27FlFRkZq7NixuWqflJSkVq1aqUmTJoqPj9ezzz6r7t27a9GiRflcKQAAAICCzMOVK2/ZsqVatmyZ6/bjxo1TuXLl9N5770mSqlatqpUrV+r9999XTExMfpUJAAAAoIC7oa5xWrNmjaKjo52mxcTEaM2aNZftk56errS0NKcbAAAAAOTFDRWcUlJSFBoa6jQtNDRUaWlp+uOPP3LsM2LECAUFBVm38PDwa1EqAAAAgJvIDRWc/o1BgwYpNTXVuh04cMDVJQEAAAC4wbj0Gqe8KlGihI4cOeI07ciRIwoMDJSvr2+Ofby9veXt7X0tygMAAABwk7qhjjjVr19fS5cudZq2ePFi1a9f30UVAQAAACgIXBqczpw5o/j4eMXHx0u6ONx4fHy89u/fL+niaXZdunSx2j/11FPas2ePXnjhBW3fvl0ff/yxvvnmGz333HOuKB8AAABAAeHS4LRx40bVrFlTNWvWlCT1799fNWvW1ODBgyVJycnJVoiSpHLlymnevHlavHixIiMj9d577+m///0vQ5EDAAAAyFcuvcYpKipKxpjLzp88eXKOfbZs2ZKPVQEAAACAsxvqGicAAP5u+vTpuuOOO+Tr66uQkBC1b99eu3fv/sc+x44dU79+/VShQgX5+PgoIiJCgwYNUnp6utVm27Zt6tq1q6pUqaLAwEAFBQWpVq1a+vTTT/N7kwAA1yGCEwDghvXpp5/qkUce0ZYtWxQWFqbMzEzNnDlTDRo0UEpKSo590tPTddddd+mDDz7QoUOHVKVKFR05ckRvvfWWHn74Yavdhg0b9Pnnn+vo0aMqX768zp8/r82bN6t79+565513rtUmAgCuEwQnAMANKSMjQy+99JIk6cEHH9SePXuUkJCgQoUK6ejRoxo+fHiO/ZYuXarExERJ0syZMxUfH6/vv/9ekjRnzhytXr1aklSmTBl9++23OnbsmOLj45WQkKCgoCBJ0ldffZXfmwcAuM4QnAAAN6QNGzbo+PHjki4GJ0kqWbKk6tWrJ0lauHBhjv2ysrKs+25ubk7/StKSJUskSU2bNlX79u3l7u4uSSpbtqzKlCkjSfw+IAAUQDfUD+ACAHDJgQMHrPvFixe37oeGhkqS06isf9WoUSOFhYUpOTlZ7dq1U5UqVawjUJJ06NChHPstX75c27ZtkyT16NHjiusHANxYOOIEALip/NNorZIUHBysJUuWqHXr1vL399fevXvVtm1bBQcHS5I8PT2z9Zk/f75atWqlrKwsPfPMMwQnACiAOOIEALghhYeHW/ePHj2a7f6l0+pyUq1aNeu6Jkk6fPiwpk2bJkmqXLmyU9tPPvlEffv2VWZmpl577TW9+uqrV6V+AMCNhSNOAIAbUu3atVWkSBFJFwd5kC4GoLVr10qSWrRoIUmqUqWKqlSpoo8++sjqu3btWmvo8T/++EN9+/aVdPFoU7t27SRdPHL1wgsvqFevXnJ3d9eXX35JaAKAAozgBAC4IXl5eVkj582cOVPly5dX1apVdfr0aRUtWtQacS8xMVGJiYnWQBKS9MYbb6ho0aK6/fbbFRYWplmzZkmS3n33XZUqVUrSxd+HevfddyVJgYGB+vDDD1WvXj3rBgAoWDhVDwBww3ryySfl7++vkSNHKiEhQT4+PmrXrp3eeustlSxZ8rL9GjdurMTERO3cuVPu7u5q1KiRnn/+ebVt29Zq89cfwz1+/LhT8AIAFDwOY3cV7U0mLS1NQUFBSk1NVWBg4L9aRo3SHa5yVbiexR/8xtUlAMBNI+n551xdAq6hcu+97+oSgH+Ul2zAqXoAAAAAYIPgBAAAAAA2CE4AAAAAYIPgBAAAAAA2CE4AAAAAYIPgBAAAAAA2CE4AAAAAYIPgBAAAAAA2PFxdAADA9aa3eNnVJeAaenjhcFeXAAA3HI44AcgX06dP1x133CFfX1+FhISoffv22r179z/2OXr0qJ5++mlFRETIx8dHhQsXVp06dfTZZ59la7t8+XK1aNFChQsXlo+PjyIiItSvX7/82hwAAFDAEZwAXHWffvqpHnnkEW3ZskVhYWHKzMzUzJkz1aBBA6WkpFy2X4cOHTRu3DgdPHhQVapUkZeXlzZs2KAnnnhCc+fOtdp98803atq0qRYtWiR3d3dVq1ZNDodD8+fPvxabBwAACiCCE4CrKiMjQy+99JIk6cEHH9SePXuUkJCgQoUK6ejRoxo+POdThIwxWr16tSSpR48eio+P19q1a635+/btkySdPXtWTz/9tDIzM/XCCy8oJSVFmzdvVlJSkjZv3pzPWwcAAAoqghOAq2rDhg06fvy4pIvBSZJKliypevXqSZIWLlyYYz+Hw6GGDRtKkiZOnKgaNWqoXr16cjgcuv/++9W1a1dJ0pIlS3Ty5ElJ0pEjR1S6dGkVKVJE999/v44cOZKfmwYAAAowghOAq+rAgQPW/eLFi1v3Q0NDJUn79++/bN/Zs2crJiZGmZmZ+uWXX3T06FEFBASoZs2a8vPzkyQlJiZa7adMmaKiRYvqjz/+0Ny5cxUVFaXU1NSrvUkAAAAEJwDXhjHGts2gQYO0aNEitW/fXqmpqVqxYoXS09M1bNgwffDBB5KkCxcuWO1fe+01/frrr1q0aJEk6dChQ5o9e3b+bAAAACjQCE4Arqrw8HDr/tGjR7PdL1OmTI79du7cqXHjxkmSOnXqpMDAQDVq1EhVqlSRdPEUPUkqVaqU1ad27dqSpDp16ljT9u7dexW2AgAAwBnBCcBVVbt2bRUpUkSSNHPmTEnS4cOHrYEeWrRoIUmqUqWKqlSpoo8++kiSnE6x27hxoyTpxIkTVhDy9/eXJDVt2lRubm5O7S79K0kVK1bMl+0CAAAFG8EJwFXl5eVljZw3c+ZMlS9fXlWrVtXp06dVtGhRa8S9xMREJSYmWgNJREZGqkKFCpKk4cOHq1q1aqpYsaLS0tIkSV26dJF08YhWnz59JEmvvvqqqlevrubNm0uSqlWrpvbt21+7jQUAAAUGwQnAVffkk0/qyy+/VI0aNXT48GE5HA61a9dOq1evVsmSJXPs4+npqbi4OD311FMqV66ckpKS5OHhoaioKM2fP1+tWrWy2r7//vt66623VKFCBe3YsUOhoaHq06ePVq5cKW9v72u1mQAAoADxcHUBAG5OnTt3VufOnS87P6fBIkqXLq1PPvnEdtlubm568cUX9eKLL15RjQAAALnFEScAAADgOjJ9+nTdcccd8vX1VUhIiNq3b6/du3f/Y5+jR4/q6aefVkREhHx8fFS4cGHVqVNHn332mdXm4MGDeuqpp1S9enUVLlxYAQEBuu222zRy5EidP38+vzfrhkdwAgAAAK4Tn376qR555BFt2bJFYWFhyszM1MyZM9WgQQOlpKRctl+HDh00btw4HTx4UFWqVJGXl5c2bNigJ554QnPnzpUk7dq1S+PHj9fevXsVEREhd3d3bdu2TQMHDlS/fv2u1SbesAhOAAAAwHUgIyPDGkTpwQcf1J49e5SQkKBChQrp6NGj1uBLf2eM0erVqyVJPXr0UHx8vDWarSTt27dPkhQSEqKJEyfq+PHj2rJli/bu3aty5cpJkr766qv83LSbAsEJAAAAuA5s2LDBGm32wQcflCSVLFlS9erVkyQtXLgwx34Oh0MNGzaUJE2cOFE1atRQvXr15HA4dP/996tr166SpNtvv13du3e3BlIqXLiwbrvtNklicKVcIDgBAAAA14EDBw5Y94sXL27dDw0NlSTt37//sn1nz56tmJgYZWZm6pdfftHRo0cVEBCgmjVrys/PL8c+iYmJ+umnnyRdPFKFf0ZwAgAAAK5jOY1E+3eDBg3SokWL1L59e6WmpmrFihVKT0/XsGHD9MEHH2Rrv2HDBjVu3Fhnz55Vu3btNGzYsPwo/aZCcAIAAACuA+Hh4db9o0ePZrtfpkyZHPvt3LlT48aNkyR16tRJgYGBatSokapUqSJJWrJkiVP77777TlFRUTpy5IiefPJJffPNN/Lw4FeK7BCcAAAAgOtA7dq1VaRIEUnSzJkzJUmHDx+2Bnpo0aKFJKlKlSqqUqWKPvroI0lSamqqtYyNGzdKkk6cOKG9e/dKkvz9/a35Y8aMUbt27fTHH3/o7bff1vjx4+Xu7p6/G3aTIFoC17Fe1V9wdQm4hj7e+o6rSwAAuJCXl5eGDx+unj17aubMmSpfvrxOnDih06dPq2jRotaIe4mJiZJkDSQRGRmpChUqaPfu3Ro+fLhmz56tlJQUpaWlSZK6dOkiSVqzZo2effZZSVKhQoU0a9YszZo1y1r/7NmzFRYWdq0294bDEScAAADgOvHkk0/qyy+/VI0aNXT48GE5HA61a9dOq1evVsmSJXPs4+npqbi4OD311FMqV66ckpKS5OHhoaioKM2fP1+tWrWSJKWnp1t9Tp8+rXXr1jnd/jof2XHECQAAALiOdO7cWZ07d77s/JwGiyhdurQ++eSTf1xuVFRUrgaaQM444gQAAAAANghOAAAAAGCD4AQAAAAANghOAAAAAGCD4AQAAAAANghOAAAAAGCD4AQAAAAANghOAAAAAGCDH8AFAADATef3H95xdQm4hgrf90K+r4MjTgAAAABgg+AEAAAAADZcHpzGjh2riIgI+fj4qG7dulq/fv0/th89erQqV64sX19fhYeH67nnntOff/55jaoFAAAAUBC5NDh9/fXX6t+/v4YMGaLNmzcrMjJSMTExOnr0aI7tp06dqpdeeklDhgxRQkKCPv30U3399dd6+eWXr3HlAAAAAAoSlwanUaNGqUePHurWrZuqVaumcePGyc/PT5999lmO7VevXq2GDRuqU6dOioiIUPPmzfXII4/YHqUCAAAAgCvhsuCUkZGhTZs2KTo6+v+KcXNTdHS01qxZk2OfBg0aaNOmTVZQ2rNnj+bPn6977733sutJT09XWlqa0w0AAAAA8sJlw5EfP35cmZmZCg0NdZoeGhqq7du359inU6dOOn78uBo1aiRjjC5cuKCnnnrqH0/VGzFihIYNG3ZVawcAAABQsOT5iNP+/ftljMk23Rij/fv3X5WiLicuLk7Dhw/Xxx9/rM2bN2vWrFmaN2+eXn/99cv2GTRokFJTU63bgQMH8rVGAAAAADefPB9xKleunJKTk1W8eHGn6SdPnlS5cuWUmZmZq+UULVpU7u7uOnLkiNP0I0eOqESJEjn2efXVV/XYY4+pe/fukqTq1avr7NmzevLJJ/XKK6/IzS17DvT29pa3t3euagIAAACAnOT5iJMxRg6HI9v0M2fOyMfHJ9fL8fLyUq1atbR06VJrWlZWlpYuXar69evn2OfcuXPZwpG7u7tVFwAAAADkh1wfcerfv78kyeFw6NVXX5Wfn581LzMzU+vWrVONGjXytPL+/fsrNjZWd955p+rUqaPRo0fr7Nmz6tatmySpS5cuKlWqlEaMGCFJat26tUaNGqWaNWuqbt262rVrl1599VW1bt3aClAAAAAAcLXlOjht2bJF0sUjO1u3bpWXl5c1z8vLS5GRkRowYECeVt6xY0cdO3ZMgwcPVkpKimrUqKGFCxdaA0bs37/f6QjTf/7zHzkcDv3nP//RoUOHVKxYMbVu3VpvvvlmntYLAAAAAHmR6+D0888/S5K6deumMWPGKDAw8KoU0KdPH/Xp0yfHeXFxcU6PPTw8NGTIEA0ZMuSqrBsAAAAAciPPg0NMmjQpP+oAAAAAgOtWnoPT2bNn9dZbb2np0qU6evSosrKynObv2bPnqhUHAAAAANeDPAen7t27a9myZXrssccUFhaW4wh7AAAAAHAzyXNwWrBggebNm6eGDRvmRz0AAAAAcN3J8+84FS5cWCEhIflRCwAAAABcl/IcnF5//XUNHjxY586dy496AAAAAOC6k6tT9WrWrOl0LdOuXbsUGhqqiIgIeXp6OrXdvHnz1a0QAAAAAFwsV8Gpbdu2+VwGAAAAAFy/chWc+MFZAAAAAAVZnq9xAgAAAICCJs/DkRcuXDjH325yOBzy8fHRLbfcoq5du6pbt25XpUAAAAAAcLU8B6fBgwfrzTffVMuWLVWnTh1J0vr167Vw4UL17t1bSUlJevrpp3XhwgX16NHjqhcMAAAAANdanoPTypUr9cYbb+ipp55ymj5+/Hj9+OOPmjlzpm6//XZ98MEHBCcAAAAAN4U8X+O0aNEiRUdHZ5verFkzLVq0SJJ07733as+ePVdeHQAAAABcB/IcnEJCQjR37txs0+fOnauQkBBJ0tmzZ1WoUKErrw4AAAAArgN5PlXv1Vdf1dNPP62ff/7ZusZpw4YNmj9/vsaNGydJWrx4sRo3bnx1KwUAAAAAF8lzcOrRo4eqVaumjz76SLNmzZIkVa5cWcuWLVODBg0kSc8///zVrRIAAAAAXCjPwUmSGjZsqIYNG17tWgAAAADgupSr4JSWlqbAwEDr/j+51A4AAAAAbha5Ck6FCxdWcnKyihcvruDg4Bx/ANcYI4fDoczMzKteJAAAAAC4Uq6C008//WSNmPfzzz/na0EAAAAAcL3JVXD66wh5jJYHAAAAoKDJ8+84SdKKFSv06KOPqkGDBjp06JAk6YsvvtDKlSuvanEAAAAAcD3Ic3CaOXOmYmJi5Ovrq82bNys9PV2SlJqaquHDh1/1AgEAAADA1fIcnN544w2NGzdOEydOlKenpzW9YcOG2rx581UtDgAAAACuB3kOTomJibr77ruzTQ8KCtKpU6euRk0AAAAAcF3Jc3AqUaKEdu3alW36ypUrVb58+atSFAAAAABcT/IcnHr06KF+/fpp3bp1cjgcOnz4sL766isNGDBATz/9dH7UCAAAAAAulavhyCUpKSlJ5cqV00svvaSsrCw1a9ZM586d09133y1vb28NGDBAffv2zc9aAQAAAMAlch2cKlSooLJly6pJkyZq0qSJEhISdPr0aZ05c0bVqlVTQEBAftYJAAAAAC6T6+D0008/KS4uTnFxcZo2bZoyMjJUvnx5NW3aVE2bNlVUVJRCQ0Pzs1YAAAAAcIlcB6eoqChFRUVJkv7880+tXr3aClKff/65zp8/rypVqmjbtm35VSsAAAAAuESug9Nf+fj4qGnTpmrUqJGaNGmiBQsWaPz48dq+ffvVrg8AAAAAXC5PwSkjI0Nr167Vzz//rLi4OK1bt07h4eG6++679dFHH6lx48b5VScAAAAAuEyug1PTpk21bt06lStXTo0bN1bPnj01depUhYWF5Wd9AAAAAOByuQ5OK1asUFhYmDUQROPGjVWkSJH8rA0AAAAArgu5/gHcU6dOacKECfLz89Pbb7+tkiVLqnr16urTp49mzJihY8eO5WedAAAAAOAyuT7i5O/vrxYtWqhFixaSpNOnT2vlypX6+eef9c4776hz586qWLGifv3113wrFgAAAABcIddHnP7O399fISEhCgkJUeHCheXh4aGEhISrWRsAAAAAXBdyfcQpKytLGzduVFxcnH7++WetWrVKZ8+eValSpdSkSRONHTtWTZo0yc9aAQAAAMAlch2cgoODdfbsWZUoUUJNmjTR+++/r6ioKFWoUCE/6wMAAAAAl8t1cHr33XfVpEkTVapUKT/rAQAAAIDrTq6DU8+ePfOzDgAAAAC4bv3rwSEAAAAAoKAgOAEAAACADYITAAAAANggOAEAAACADYITAAAAANggOAEAAACADYITAAAAANggOAEAAACADYITAAAAANhweXAaO3asIiIi5OPjo7p162r9+vX/2P7UqVPq3bu3wsLC5O3trUqVKmn+/PnXqFoAAAAABZGHK1f+9ddfq3///ho3bpzq1q2r0aNHKyYmRomJiSpevHi29hkZGbrnnntUvHhxzZgxQ6VKldK+ffsUHBx87YsHAAAAUGC4NDiNGjVKPXr0ULdu3SRJ48aN07x58/TZZ5/ppZdeytb+s88+08mTJ7V69Wp5enpKkiIiIq5lyQAAAAAKIJedqpeRkaFNmzYpOjr6/4pxc1N0dLTWrFmTY5/vv/9e9evXV+/evRUaGqrbbrtNw4cPV2Zm5mXXk56errS0NKcbAAAAAOSFy4LT8ePHlZmZqdDQUKfpoaGhSklJybHPnj17NGPGDGVmZmr+/Pl69dVX9d577+mNN9647HpGjBihoKAg6xYeHn5VtwMAAADAzc/lg0PkRVZWlooXL64JEyaoVq1a6tixo1555RWNGzfusn0GDRqk1NRU63bgwIFrWDEAAACAm4HLrnEqWrSo3N3ddeTIEafpR44cUYkSJXLsExYWJk9PT7m7u1vTqlatqpSUFGVkZMjLyytbH29vb3l7e1/d4gEAAAAUKC474uTl5aVatWpp6dKl1rSsrCwtXbpU9evXz7FPw4YNtWvXLmVlZVnTduzYobCwsBxDEwAAAABcDS49Va9///6aOHGiPv/8cyUkJOjpp5/W2bNnrVH2unTpokGDBlntn376aZ08eVL9+vXTjh07NG/ePA0fPly9e/d21SYAAAAAKABcOhx5x44ddezYMQ0ePFgpKSmqUaOGFi5caA0YsX//frm5/V+2Cw8P16JFi/Tcc8/p9ttvV6lSpdSvXz+9+OKLrtoEAAAAAAWAS4OTJPXp00d9+vTJcV5cXFy2afXr19fatWvzuSoAAAAA+D831Kh6AAAAAOAKBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgAAAAAb10VwGjt2rCIiIuTj46O6detq/fr1ueo3ffp0ORwOtW3bNn8LBAAAAFCguTw4ff311+rfv7+GDBmizZs3KzIyUjExMTp69Og/9tu7d68GDBigu+666xpVCgAAAKCgcnlwGjVqlHr06KFu3bqpWrVqGjdunPz8/PTZZ59dtk9mZqY6d+6sYcOGqXz58tewWgAAAAAFkUuDU0ZGhjZt2qTo6Ghrmpubm6Kjo7VmzZrL9nvttddUvHhxPfHEE7brSE9PV1pamtMNAAAAAPLCpcHp+PHjyszMVGhoqNP00NBQpaSk5Nhn5cqV+vTTTzVx4sRcrWPEiBEKCgqybuHh4VdcNwAAAICCxeWn6uXF6dOn9dhjj2nixIkqWrRorvoMGjRIqamp1u3AgQP5XCUAAACAm42HK1detGhRubu768iRI07Tjxw5ohIlSmRrv3v3bu3du1etW7e2pmVlZUmSPDw8lJiYqAoVKjj18fb2lre3dz5UDwAAAKCgcOkRJy8vL9WqVUtLly61pmVlZWnp0qWqX79+tvZVqlTR1q1bFR8fb93uv/9+NWnSRPHx8ZyGBwAAACBfuPSIkyT1799fsbGxuvPOO1WnTh2NHj1aZ8+eVbdu3SRJXbp0UalSpTRixAj5+Pjotttuc+ofHBwsSdmmAwAAAMDV4vLg1LFjRx07dkyDBw9WSkqKatSooYULF1oDRuzfv19ubjfUpVgAAAAAbjIuD06S1KdPH/Xp0yfHeXFxcf/Yd/LkyVe/IAAAAAD4Cw7lAAAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2LgugtPYsWMVEREhHx8f1a1bV+vXr79s24kTJ+quu+5S4cKFVbhwYUVHR/9jewAAAAC4Ui4PTl9//bX69++vIUOGaPPmzYqMjFRMTIyOHj2aY/u4uDg98sgj+vnnn7VmzRqFh4erefPmOnTo0DWuHAAAAEBB4fLgNGrUKPXo0UPdunVTtWrVNG7cOPn5+emzzz7Lsf1XX32lXr16qUaNGqpSpYr++9//KisrS0uXLr3GlQMAAAAoKFwanDIyMrRp0yZFR0db09zc3BQdHa01a9bkahnnzp3T+fPnFRISkuP89PR0paWlOd0AAAAAIC9cGpyOHz+uzMxMhYaGOk0PDQ1VSkpKrpbx4osvqmTJkk7h669GjBihoKAg6xYeHn7FdQMAAAAoWFx+qt6VeOuttzR9+nTNnj1bPj4+ObYZNGiQUlNTrduBAweucZUAAAAAbnQerlx50aJF5e7uriNHjjhNP3LkiEqUKPGPfUeOHKm33npLS5Ys0e23337Zdt7e3vL29r4q9QIAAAAomFx6xMnLy0u1atVyGtjh0kAP9evXv2y/d955R6+//roWLlyoO++881qUCgAAAKAAc+kRJ0nq37+/YmNjdeedd6pOnToaPXq0zp49q27dukmSunTpolKlSmnEiBGSpLfffluDBw/W1KlTFRERYV0LFRAQoICAAJdtBwAAAICbl8uDU8eOHXXs2DENHjxYKSkpqlGjhhYuXGgNGLF//365uf3fgbFPPvlEGRkZat++vdNyhgwZoqFDh17L0gEAAAAUEC4PTpLUp08f9enTJ8d5cXFxTo/37t2b/wUBAAAAwF/c0KPqAQAAAMC1QHACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwQXACAAAAABsEJwAAAACwcV0Ep7FjxyoiIkI+Pj6qW7eu1q9f/4/tv/32W1WpUkU+Pj6qXr265s+ff40qBQAAAFAQuTw4ff311+rfv7+GDBmizZs3KzIyUjExMTp69GiO7VevXq1HHnlETzzxhLZs2aK2bduqbdu2+vXXX69x5QAAAAAKCpcHp1GjRqlHjx7q1q2bqlWrpnHjxsnPz0+fffZZju3HjBmjFi1aaODAgapatapef/113XHHHfroo4+uceUAAAAACgoPV648IyNDmzZt0qBBg6xpbm5uio6O1po1a3Lss2bNGvXv399pWkxMjObMmZNj+/T0dKWnp1uPU1NTJUlpaWn/uu7MrPP/ui9uPFeyr1ypjMx0+0a4abhyXzt3gX2tIHHlvnY6nX2tIHHlvpZ27k+XrRvXnvu/3Ncu7aPGGNu2Lg1Ox48fV2ZmpkJDQ52mh4aGavv27Tn2SUlJybF9SkpKju1HjBihYcOGZZseHh7+L6tGQRMUFOTqElBAfBr0gatLQAHxRNAoV5eAgmLsJ66uAAXGkCvqffr0advvfC4NTtfCoEGDnI5QZWVl6eTJkypSpIgcDocLK7uxpKWlKTw8XAcOHFBgYKCry8FNjH0N1wr7Gq4V9jVcK+xreWeM0enTp1WyZEnbti4NTkWLFpW7u7uOHDniNP3IkSMqUaJEjn1KlCiRp/be3t7y9vZ2mhYcHPzviy7gAgMD+Y+Ia4J9DdcK+xquFfY1XCvsa3mT27OLXDo4hJeXl2rVqqWlS5da07KysrR06VLVr18/xz7169d3ai9Jixcvvmx7AAAAALhSLj9Vr3///oqNjdWdd96pOnXqaPTo0Tp79qy6desmSerSpYtKlSqlESNGSJL69eunxo0b67333lOrVq00ffp0bdy4URMmTHDlZgAAAAC4ibk8OHXs2FHHjh3T4MGDlZKSoho1amjhwoXWABD79++Xm9v/HRhr0KCBpk6dqv/85z96+eWXVbFiRc2ZM0e33XabqzahQPD29taQIUOynfYIXG3sa7hW2NdwrbCv4VphX8tfDpObsfcAAAAAoABz+Q/gAgAAAMD1juAEAAAAADYITgAAAABgg+CUB8YYPfnkkwoJCZHD4VB8fLyrS3KJrl27qm3btld9uUOHDlVoaKgcDofmzJlz1ZePqyMqKkrPPvtsvq4jIiJCo0eP/sc2Q4cOVY0aNfK1DrjWjfpesHfvXqfPiLi4ODkcDp06deqyfSZPnsxvDALId7zXXBmCUx4sXLhQkydP1g8//KDk5GRG8ruKEhISNGzYMI0fP17Jyclq2bKlS+v5+xcfuNaN+gUaBVN4eDifEcgTPnOAG4PLhyO/kezevVthYWFq0KBBjvMzMjLk5eV1jau6OezevVuS1KZNGzkcDhdXA+Bm4Kr3ZHd3d5UoUeKarxeuw+c/UDBwxCmXunbtqr59+2r//v1yOByKiIhQVFSU+vTpo2effVZFixZVTEyMJGnZsmWqU6eOvL29FRYWppdeekkXLlywlnX69Gl17txZ/v7+CgsL0/vvv5+n05/S09M1YMAAlSpVSv7+/qpbt67i4uIkSWfPnlVgYKBmzJjh1GfOnDny9/fX6dOnJUkHDhxQhw4dFBwcrJCQELVp00Z79+79V89NVlaWRowYoXLlysnX11eRkZFO68/MzNQTTzxhza9cubLGjBljzR86dKhat24tSXJzc8tVcIqLi1OdOnXk7++v4OBgNWzYUPv27bOWV6NGDY0fP17h4eHy8/NThw4dlJqa6lTza6+9ptKlS8vb29v6/bBLypUrJ0mqWbOmHA6HoqKi/tVzc7PKysrSCy+8oJCQEJUoUUJDhw615p06dUrdu3dXsWLFFBgYqKZNm+qXX36x5u/evVtt2rRRaGioAgICVLt2bS1ZsuSy64qIiJAkPfDAA9b/vb/64osvFBERoaCgID388MPWPj5lyhQVKVJE6enpTu3btm2rxx577MqegALg0vtbnz59FBQUpKJFi+rVV1/VpV+w+P3339WlSxcVLlxYfn5+atmypXbu3Cnp4mnNxYoVc3ofqFGjhsLCwqzHK1eulLe3t86dOydJ2rlzp+6++275+PioWrVqWrx4cbaa7N63Lp1G/Oabb6pkyZKqXLmyXnvttRyP/NSoUUOvvvqq7fNwaZnDhw9XaGiogoOD9dprr+nChQsaOHCgQkJCVLp0aU2aNMnqk5ujB5MnT1aZMmXk5+enBx54QCdOnMjW5rvvvtMdd9whHx8flS9fXsOGDbM+SwYMGKD77rvPajt69Gg5HA6n97FbbrlF//3vf223EXmX0+f/31/zU6dOyeFwWJ/Pv//+uzp37qxixYrJ19dXFStWtPYbPnPwdzNmzFD16tXl6+urIkWKKDo6WmfPnpUkffbZZ7r11lut75l9+vSx+o0aNUrVq1eXv7+/wsPD1atXL505cybb8ufMmaOKFSvKx8dHMTExOnDgwDXbthuaQa6cOnXKvPbaa6Z06dImOTnZHD161DRu3NgEBASYgQMHmu3bt5vt27ebgwcPGj8/P9OrVy+TkJBgZs+ebYoWLWqGDBliLat79+6mbNmyZsmSJWbr1q3mgQceMIUKFTL9+vXLVS3du3c3DRo0MMuXLze7du0y7777rvH29jY7duwwxhjTo0cPc++99zr1uf/++02XLl2MMcZkZGSYqlWrmscff9z873//M7/99pvp1KmTqVy5sklPT7ddf2xsrGnTpo31+I033jBVqlQxCxcuNLt37zaTJk0y3t7eJi4uzlrf4MGDzYYNG8yePXvMl19+afz8/MzXX39tjDHm9OnTZtKkSUaSSU5ONsnJyf+4/vPnz5ugoCAzYMAAs2vXLvPbb7+ZyZMnm3379hljjBkyZIjx9/c3TZs2NVu2bDHLli0zt9xyi+nUqZO1jFGjRpnAwEAzbdo0s337dvPCCy8YT09P6zlcv369kWSWLFlikpOTzYkTJ2yfl4KicePGJjAw0AwdOtTs2LHDfP7558bhcJgff/zRGGNMdHS0ad26tdmwYYPZsWOHef75502RIkWs5zA+Pt6MGzfObN261ezYscP85z//MT4+PtbrZ4wxZcuWNe+//74xxpijR48aSWbSpEnW/z1jLr7OAQEBpl27dmbr1q1m+fLlpkSJEubll182xhhz7tw5ExQUZL755htruUeOHDEeHh7mp59+uhZP1Q3t0vtbv379zPbt263/txMmTDDGXHxPqVq1qlm+fLmJj483MTEx5pZbbjEZGRnGGGPatWtnevfubYwx5uTJk8bLy8sEBQWZhIQEY8zF942GDRsaY4zJzMw0t912m2nWrJmJj483y5YtMzVr1jSSzOzZs40xuXvfio2NNQEBAeaxxx4zv/76q/n111/NgQMHjJubm1m/fr21bZs3bzYOh8Ps3r3b9nmIjY01hQoVMr179zbbt283n376qZFkYmJizJtvvml27NhhXn/9dePp6WkOHDhgjDEmKSnJSDJbtmwxxhjz888/G0nm999/N8YYs3btWuPm5mbefvttk5iYaMaMGWOCg4NNUFCQtd7ly5ebwMBAM3nyZLN7927z448/moiICDN06FBjjDHff/+9CQoKMhcuXDDGGNO2bVtTtGhR8+KLLxpjjDl48KCRZHbu3Jn7Fx25ltPn/19fc2OM+f33340k8/PPPxtjjOndu7epUaOG2bBhg0lKSjKLFy8233//vTGGzxw4O3z4sPHw8DCjRo0ySUlJ5n//+58ZO3asOX36tPn444+Nj4+PGT16tElMTDTr16+3Pi+NMeb99983P/30k0lKSjJLly41lStXNk8//bQ1f9KkScbT09PceeedZvXq1Wbjxo2mTp06pkGDBi7Y0hsPwSkP3n//fVO2bFnrcePGjU3NmjWd2rz88sumcuXKJisry5o2duxYExAQYDIzM01aWprx9PQ03377rTX/1KlTxs/PL1fBad++fcbd3d0cOnTIaXqzZs3MoEGDjDHGrFu3zri7u5vDhw8bY/7vy+KlIPPFF19kqzE9Pd34+vqaRYsW2dbw1+D0559/Gj8/P7N69WqnNk888YR55JFHLruM3r17mwcffNB6PHv2bJPbHH/ixAkjydqevxsyZIhxd3c3Bw8etKYtWLDAuLm5WaGsZMmS5s0333TqV7t2bdOrVy9jTPYvPvg/jRs3No0aNXKaVrt2bfPiiy+aFStWmMDAQPPnn386za9QoYIZP378ZZd56623mg8//NB6/NfgZIxx+gJ9yZAhQ4yfn59JS0uzpg0cONDUrVvXevz000+bli1bWo/fe+89U758ead9Hzlr3LixqVq1qtNz9eKLL5qqVauaHTt2GElm1apV1rzjx48bX19fK6h+8MEH5tZbbzXGGDNnzhxTt25d06ZNG/PJJ58YYy4G7Eshd9GiRcbDw8PpfW3BggVOr3tu3rdiY2NNaGhotj8AtWzZ0umLQ9++fU1UVFSunofY2FhTtmxZk5mZaU2rXLmyueuuu6zHFy5cMP7+/mbatGnGGPvg9Mgjj2T741bHjh2dglOzZs3M8OHDndp88cUXJiwszBhz8Uu5m5ub2bBhg8nKyjIhISFmxIgR1v7/5ZdfmlKlSuVqG5F3f//8z+kz4+/BqXXr1qZbt245Lo/PHPzVpk2bjCSzd+/ebPNKlixpXnnllVwv69tvvzVFihSxHl/6Q/XatWutaQkJCUaSWbdu3ZUVXgBwqt4VqlWrltPjhIQE1a9f3+l0s4YNG+rMmTM6ePCg9uzZo/Pnz6tOnTrW/KCgIFWuXDlX69u6dasyMzNVqVIlBQQEWLdly5ZZ1wnVqVNHt956qz7//HNJ0pdffqmyZcvq7rvvliT98ssv2rVrlwoVKmT1DwkJ0Z9//mktI7d27dqlc+fO6Z577nGqZ8qUKU7LGjt2rGrVqqVixYopICBAEyZM0P79+/O0rktCQkLUtWtXxcTEqHXr1hozZoySk5Od2pQpU0alSpWyHtevX19ZWVlKTExUWlqaDh8+rIYNGzr1adiwoRISEv5VTQXN7bff7vQ4LCxMR48e1S+//KIzZ86oSJEiTvtDUlKStT+cOXNGAwYMUNWqVRUcHKyAgAAlJCT8q/0hIiJChQoVylbHJT169NCPP/6oQ4cOSbp4elTXrl25ji6X6tWr5/Rc1a9fXzt37tRvv/0mDw8P1a1b15pXpEgRVa5c2fo/1LhxY/322286duyYli1bpqioKEVFRSkuLk7nz5/X6tWrrdOREhISFB4erpIlSzqt669y+75VvXr1bNea9OjRQ9OmTdOff/6pjIwMTZ06VY8//niun4dbb71Vbm7/93EZGhqq6tWrW4/d3d1VpEgRp33vnyQkJDg9d5fb3tdee83p/1GPHj2UnJysc+fOKTg4WJGRkYqLi9PWrVvl5eWlJ598Ulu2bNGZM2e0bNkyNW7cONfbiLz7++e/naefflrTp09XjRo19MILL2j16tX5VBludJGRkWrWrJmqV6+uhx56SBMnTtTvv/+uo0eP6vDhw2rWrNll+y5ZskTNmjVTqVKlVKhQIT322GM6ceKEdVq0JHl4eKh27drW4ypVqig4OJjvQLnA4BBXyN/f/5qu78yZM3J3d9emTZvk7u7uNC8gIMC63717d40dO1YvvfSSJk2apG7dullfgM6cOaNatWrpq6++yrb8YsWK5bkeSZo3b55TUJEkb29vSdL06dM1YMAAvffee6pfv74KFSqkd999V+vWrcvTuv5q0qRJeuaZZ7Rw4UJ9/fXX+s9//qPFixerXr16/3qZyD1PT0+nxw6HQ1lZWTpz5ozCwsKsc/r/6tLwpwMGDNDixYs1cuRI3XLLLfL19VX79u2VkZFx1eq4pGbNmoqMjNSUKVPUvHlzbdu2TfPmzcvzepB31atXV0hIiJYtW6Zly5bpzTffVIkSJfT2229rw4YNOn/+/GUH2slJbt+3cnpPbt26tby9vTV79mx5eXnp/Pnzat++fa7XndN+ZrfvXakzZ85o2LBhateuXbZ5Pj4+kmQFUW9vbzVu3FghISGqWrWqVq5cqWXLlun555+/avUgu7/ua5eCtfn/1wBK0vnz553at2zZUvv27dP8+fO1ePFiNWvWTL1799bIkSOvTcG4Ybi7u2vx4sVavXq1fvzxR3344Yd65ZVXtHTp0n/st3fvXt133316+umn9eabbyokJEQrV67UE088oYyMDPn5+V2jLbh5EZyusqpVq2rmzJkyxlhBZdWqVSpUqJBKly6twoULy9PTUxs2bFCZMmUkSampqdqxY4d1ROif1KxZU5mZmTp69Kjuuuuuy7Z79NFH9cILL+iDDz7Qb7/9ptjYWGveHXfcoa+//lrFixdXYGDgFW1vtWrV5O3trf3791/2r5urVq1SgwYN1KtXL2taXo9s5aRmzZqqWbOmBg0apPr162vq1KlWcNq/f78OHz5s/QV77dq1cnNzU+XKlRUYGKiSJUtq1apVTjWvWrXKOhJ46S/WmZmZV1xnQXLHHXcoJSVFHh4e2QZxuGTVqlXq2rWrHnjgAUkXvyDaDUzi6en5r1+L7t27a/To0Tp06JCio6MVHh7+r5ZTEP39jxtr165VxYoVVa1aNV24cEHr1q2zws+JEyeUmJioatWqSboYJO666y5999132rZtmxo1aiQ/Pz+lp6dr/PjxuvPOO60vnlWrVtWBAweUnJxsDSCxdu1ap3VfyfuWh4eHYmNjNWnSJHl5eenhhx+Wr6/vv3pOroaqVavm+Nz+1R133KHExETdcsstl11O48aN9dlnn8nDw0MtWrSQdDFMTZs2TTt27GCAgWvoUnhPTk5WzZo1JSnHwUGKFSum2NhYxcbG6q677tLAgQM1cuRIPnOQjcPhUMOGDdWwYUMNHjxYZcuW1eLFixUREaGlS5eqSZMm2fps2rRJWVlZeu+996ww/80332Rrd+HCBW3cuNH6zpOYmKhTp06patWq+btRNwFO1bvKevXqpQMHDqhv377avn27vvvuOw0ZMkT9+/eXm5ubChUqpNjYWA0cOFA///yztm3bpieeeCLXo8lVqlRJnTt3VpcuXTRr1iwlJSVp/fr1GjFihNNf0gsXLqx27dpp4MCBat68uUqXLm3N69y5s4oWLao2bdpoxYoVSkpKUlxcnJ555hkdPHgwT9tbqFAhDRgwQM8995w+//xz7d69W5s3b9aHH35onSpYsWJFbdy4UYsWLdKOHTv06quvasOGDXlaz18lJSVp0KBBWrNmjfbt26cff/xRO3fudPoP7+Pjo9jYWP3yyy9asWKFnnnmGXXo0MEaInjgwIF6++239fXXXysxMVEvvfSS4uPj1a9fP0lS8eLF5evrq4ULF+rIkSNOI/Lh8qKjo1W/fn21bdtWP/74o/bu3avVq1frlVde0caNGyVd3B9mzZql+Ph4/fLLL+rUqZPtX+ovfVCkpKTo999/z1NNnTp10sGDBzVx4sQ8nZ6Fi3+A6N+/vxITEzVt2jR9+OGH6tevnypWrKg2bdqoR48eWrlypX755Rc9+uijKlWqlNq0aWP1v/QlvkaNGgoICJCbm5vuvvtuffXVV05/tIiOjlalSpWc/s++8sorTrVc6ftW9+7d9dNPP2nhwoUu3w8uHS0fOXKkdu7cqY8++shpNDxJGjx4sKZMmaJhw4Zp27ZtSkhI0PTp0/Wf//zHanP33Xfr9OnT+uGHH6yQFBUVpa+++kphYWGqVKnStdysAs3X11f16tXTW2+9pYSEBC1btszptZIuvqbfffeddu3apW3btumHH36wPrf4zMFfrVu3TsOHD9fGjRu1f/9+zZo1S8eOHVPVqlU1dOhQvffee/rggw+0c+dO6zuXdHEkzfPnz+vDDz/Unj179MUXX2jcuHHZlu/p6am+fftq3bp12rRpk7p27ap69eo5XUaCy3D1RVY3kpwGh8hpQIe4uDhTu3Zt4+XlZUqUKGFefPFFc/78eWt+Wlqa6dSpk/Hz8zMlSpQwo0aNMnXq1DEvvfRSruq4NEpdRESE8fT0NGFhYeaBBx4w//vf/5zaLV261EhyGlXskuTkZNOlSxdTtGhR4+3tbcqXL2969OhhUlNTbdf/91H1srKyzOjRo03lypWNp6enKVasmImJiTHLli0zxlwcQKJr164mKCjIBAcHm6efftq89NJLJjIy0lpGXgaHSElJMW3btjVhYWHGy8vLlC1b1gwePNi6eHvIkCEmMjLSfPzxx6ZkyZLGx8fHtG/f3pw8edJaRmZmphk6dKgpVaqU8fT0NJGRkWbBggVO65k4caIJDw83bm5upnHjxrmqrSDIab9v06aNiY2NNcZc3L/79u1rSpYsaTw9PU14eLjp3Lmz2b9/vzHm4kXQTZo0Mb6+viY8PNx89NFH2Zb598Ehvv/+e3PLLbcYDw8P6//gpdf5r/7+f/SSxx57zISEhGQbtAKX17hxY9OrVy/z1FNPmcDAQFO4cGHz8ssvW4MznDx50jz22GMmKCjI+Pr6mpiYGGtUyku2bNliJFkjvRlz8TWSZBYuXOjUNjEx0TRq1Mh4eXmZSpUqmYULF2YbFMTufevv701/d9ddd1kDVuRWTsvM6f/AX/dZu8EhjDHm008/NaVLlza+vr6mdevWZuTIkU6DQxhjzMKFC02DBg2Mr6+vCQwMNHXq1LFGNbwkMjLSlChRwnp84sQJ43A4zMMPP5yn7UTe5LQP/Pbbb6Z+/frG19fX1KhRw/z4449Og0O8/vrrpmrVqsbX19eEhISYNm3amD179lj9+czBJb/99puJiYkxxYoVM97e3qZSpUpOAyiNGzfO+s4VFhZm+vbta80bNWqUCQsLs96Xp0yZ4vT+M2nSJBMUFGRmzpxpypcvb7y9vU10dLTTyLa4PIcxfzkhFy5x9uxZlSpVSu+9956eeOKJq7bcL774Qs8995wOHz5coH6Yb+jQoZozZw6/wA5Ls2bNdOutt+qDDz5wdSk3jKioKNWoUUOjR492dSlXhTFGFStWVK9evdS/f39XlwMAuAFxjZMLbNmyRdu3b1edOnWUmpqq1157TZKcTnG5EufOnVNycrLeeust9ezZs0CFJuCvfv/9d8XFxSkuLk4ff/yxq8uBixw7dkzTp09XSkqKunXr5upyAAA3KIKTi4wcOVKJiYny8vJSrVq1tGLFChUtWlQrVqxQy5YtL9svp19//rt33nlHb775pu6++24NGjQoz7X9dXS+v1uwYME/DkpxtVwPNeDGV7NmTf3+++96++23cz3kP24+xYsXV9GiRTVhwgQVLlzYaR7vNQCA3OJUvevMH3/8Yf3mTE7+aYSlq2XXrl2XnVeqVKlrMhrV9VADgJsf7zUAgNwiOAEAAACADYYjBwAAAAAbBCcAAAAAsEFwAgAAAAAbBCcAAAAAsEFwAgBcMw6HQ3PmzHF1Gflq7969cjgc/Ag3ANxkCE4AgCvStWtXORwOORwOeXp6KjQ0VPfcc48+++wzZWVlObVNTk7+x9+quxHs2rVL3bp1U+nSpeXt7a1y5crpkUce0caNG11dGgAgHxGcAABXrEWLFkpOTtbevXu1YMECNWnSRP369dN9992nCxcuWO1KlCghb29vF1Z6ZTZu3KhatWppx44dGj9+vH777TfNnj1bVapU0fPPP+/q8gAA+YjgBAC4Yt7e3ipRooRKlSqlO+64Qy+//LK+++47LViwQJMnT7ba/fVUvYyMDPXp00dhYWHy8fFR2bJlNWLECKvtqVOn1L17dxUrVkyBgYFq2rSpfvnlF2v+7t271aZNG4WGhiogIEC1a9fWkiVLnOr6+OOPVbFiRfn4+Cg0NFTt27e35mVlZWnEiBEqV66cfH19FRkZqRkzZlx2G40x6tq1qypWrKgVK1aoVatWqlChgmrUqKEhQ4bou+++y7FfZmamnnjiCWs9lStX1pgxY5zaxMXFqU6dOvL391dwcLAaNmyoffv2SZJ++eUXNWnSRIUKFVJgYKBq1arF0S0AcAEPVxcAALg5NW3aVJGRkZo1a5a6d++ebf4HH3yg77//Xt98843KlCmjAwcO6MCBA9b8hx56SL6+vlqwYIGCgoI0fvx4NWvWTDt27FBISIjOnDmje++9V2+++aa8vb01ZcoUtW7dWomJiSpTpow2btyoZ555Rl988YUaNGigkydPasWKFdbyR4wYoS+//FLjxo1TxYoVtXz5cj366KMqVqyYGjdunK3e+Ph4bdu2TVOnTpWbW/a/OwYHB+f4PGRlZal06dL69ttvVaRIEa1evVpPPvmkwsLC1KFDB124cEFt27ZVjx49NG3aNGVkZGj9+vVyOBySpM6dO6tmzZr65JNP5O7urvj4eHl6eub15QAAXCGCEwAg31SpUkX/+9//cpy3f/9+VaxYUY0aNZLD4VDZsmWteStXrtT69et19OhR69S+kSNHas6cOZoxY4aefPJJRUZGKjIy0urz+uuva/bs2fr+++/Vp08f7d+/X/7+/rrvvvtUqFAhlS1bVjVr1pQkpaena/jw4VqyZInq168vSSpfvrxWrlyp8ePH5xicdu7caW1TXnh6emrYsGHW43LlymnNmjX65ptv1KFDB6WlpSk1NVX33XefKlSoIEmqWrWq0/M0cOBAa70VK1bM0/oBAFcHp+oBAPKNMcY6cvJ3Xbt2VXx8vCpXrqxnnnlGP/74ozXvl19+0ZkzZ1SkSBEFBARYt6SkJO3evVuSdObMGQ0YMEBVq1ZVcHCwAgIClJCQoP3790uS7rnnHpUtW1bly5fXY489pq+++krnzp2TdHGAh3Pnzumee+5xWv6UKVOs5ee0Lf/W2LFjVatWLRUrVkwBAQGaMGGCVWdISIi6du2qmJgYtW7dWmPGjFFycrLVt3///urevbuio6P11ltvXbY+AED+IjgBAPJNQkKCypUrl+O8O+64Q0lJSXr99df1xx9/qEOHDtY1SGfOnFFYWJji4+OdbomJiRo4cKAkacCAAZo9e7aGDx+uFStWKD4+XtWrV1dGRoYkqVChQtq8ebOmTZumsLAwDR48WJGRkTp16pTOnDkjSZo3b57T8n/77bfLXudUqVIlSdL27dvz9BxMnz5dAwYM0BNPPKEff/xR8fHx6tatm1WnJE2aNElr1qxRgwYN9PXXX6tSpUpau3atJGno0KHatm2bWrVqpZ9++knVqlXT7Nmz81QDAODKcaoeACBf/PTTT9q6dauee+65y7YJDAxUx44d1bFjR7Vv314tWrTQyZMndccddyglJUUeHh6KiIjIse+qVavUtWtXPfDAA5Iuhq29e/c6tfHw8FB0dLSio6M1ZMgQBQcH66efftI999wjb29v7d+/P8fT8nJSo0YNVatWTe+99546duyY7TqnU6dO5Xid06pVq9SgQQP16tXLmpbTUaOaNWuqZs2aGjRokOrXr6+pU6eqXr16ki6GtkqVKum5557TI488okmTJlnbDQC4NghOAIArlp6erpSUFGVmZurIkSNauHChRowYofvuu09dunTJsc+oUaMUFhammjVrys3NTd9++61KlCih4OBgRUdHq379+mrbtq3eeecdVapUSYcPH9a8efP0wAMP6M4771TFihU1a9YstW7dWg6HQ6+++qrT70b98MMP2rNnj+6++24VLlxY8+fPV1ZWlipXrqxChQppwIABeu6555SVlaVGjRopNTVVq1atUmBgoGJjY7PV63A4NGnSJEVHR+uuu+7SK6+8oipVqujMmTOaO3eufvzxRy1btixbv4oVK2rKlClatGiRypUrpy+++EIbNmywjsQlJSVpwoQJuv/++1WyZEklJiZq586d6tKli/744w8NHDhQ7du3V7ly5XTw4EFt2LBBDz744FV65QAAuUVwAgBcsYULFyosLEweHh4qXLiwIiMj9cEHHyg2NjbHEeiki6fSvfPOO9q5c6fc3d1Vu3ZtzZ8/32o/f/58vfLKK+rWrZuOHTumEiVK6O6771ZoaKiki8Hr8ccfV4MGDVS0aFG9+OKLSktLs5YfHBysWbNmaejQofrzzz9VsWJFTZs2Tbfeequki4NJFCtWTCNGjNCePXsUHBxsDaV+OXXq1NHGjRv15ptvqkePHjp+/LjCwsLUoEEDjR49Osc+PXv21JYtW9SxY0c5HA498sgj6tWrlxYsWCBJ8vPz0/bt2/X555/rxIkTCgsLU+/evdWzZ09duHBBJ06cUJcuXXTkyBEVLVpU7dq1cxpsAgBwbTjMlVztCgAAAAAFAINDAAAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAIANghMAAAAA2CA4AQAAAICN/we6tr/QjEG+3wAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,6))\n",
    "\n",
    "sns.barplot(\n",
    "\n",
    "    data=weight_df,\n",
    "\n",
    "    x=\"Class\",\n",
    "\n",
    "    y=\"Weight\",\n",
    "\n",
    "    palette=\"magma\"\n",
    ")\n",
    "\n",
    "plt.title(\n",
    "    \"Computed Class Weights\"\n",
    ")\n",
    "\n",
    "plt.xlabel(\n",
    "    \"Disease Class\"\n",
    ")\n",
    "\n",
    "plt.ylabel(\n",
    "    \"Weight\"\n",
    ")\n",
    "\n",
    "for i, weight in enumerate(weight_df[\"Weight\"]):\n",
    "\n",
    "    plt.text(\n",
    "\n",
    "        i,\n",
    "\n",
    "        weight + 0.03,\n",
    "\n",
    "        f\"{weight:.2f}\",\n",
    "\n",
    "        ha='center',\n",
    "\n",
    "        fontweight='bold'\n",
    "    )\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3830f342",
   "metadata": {},
   "source": [
    "#### Cosine Learning-Rate Decay"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "6f4dd64f",
   "metadata": {},
   "outputs": [],
   "source": [
    "lr_schedule = CosineDecay(\n",
    "\n",
    "    initial_learning_rate=0.001,\n",
    "\n",
    "    decay_steps=12000,\n",
    "\n",
    "    alpha=0.0001\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fcede162",
   "metadata": {},
   "source": [
    "#### CNN Model 4 Architecture"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "e159e7e3",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_1\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ conv2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">158</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">158</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_4           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">158</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">158</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">79</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">79</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">77</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">77</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_5           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">77</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">77</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │           <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_5 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">38</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">38</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">36</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">36</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_6           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">36</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">36</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_6 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">18</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">18</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_7           │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,024</span> │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">BatchNormalization</span>)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>)  │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">16384</span>)          │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │     <span style=\"color: #00af00; text-decoration-color: #00af00\">4,194,560</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5</span>)              │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,285</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m158\u001b[0m, \u001b[38;5;34m158\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_4           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m158\u001b[0m, \u001b[38;5;34m158\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m128\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m79\u001b[0m, \u001b[38;5;34m79\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_5 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m77\u001b[0m, \u001b[38;5;34m77\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_5           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m77\u001b[0m, \u001b[38;5;34m77\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │           \u001b[38;5;34m256\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_5 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m38\u001b[0m, \u001b[38;5;34m38\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_6           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m36\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │           \u001b[38;5;34m512\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_6 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m18\u001b[0m, \u001b[38;5;34m18\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │       \u001b[38;5;34m295,168\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ batch_normalization_7           │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m)    │         \u001b[38;5;34m1,024\u001b[0m │\n",
       "│ (\u001b[38;5;33mBatchNormalization\u001b[0m)            │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_7 (\u001b[38;5;33mMaxPooling2D\u001b[0m)  │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16384\u001b[0m)          │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │     \u001b[38;5;34m4,194,560\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m)              │         \u001b[38;5;34m1,285\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,586,181</span> (17.49 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,586,181\u001b[0m (17.49 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">4,585,221</span> (17.49 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m4,585,221\u001b[0m (17.49 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">960</span> (3.75 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m960\u001b[0m (3.75 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "model4 = Sequential([\n",
    "\n",
    "    Input(shape=(160,160,3)),\n",
    "\n",
    "    Conv2D(32,(3,3),activation='relu'), \n",
    "    BatchNormalization(),\n",
    "\n",
    "    MaxPooling2D(2,2),\n",
    "\n",
    "    Conv2D(64,(3,3), activation='relu'),\n",
    "\n",
    "    BatchNormalization(),\n",
    "\n",
    "    MaxPooling2D(2,2),\n",
    "\n",
    "    Conv2D(128,(3,3),activation='relu'),\n",
    "\n",
    "    BatchNormalization(),\n",
    "\n",
    "    MaxPooling2D(2,2),\n",
    "\n",
    "    Conv2D(256,(3,3),activation='relu'),\n",
    "\n",
    "    BatchNormalization(),\n",
    "\n",
    "    MaxPooling2D(2,2),\n",
    "\n",
    "    Flatten(),\n",
    "\n",
    "    Dense(256,activation='relu', kernel_regularizer=l2(0.0001)),\n",
    "\n",
    "    Dropout(0.4),\n",
    "\n",
    "    Dense(5,activation='softmax')\n",
    "])\n",
    "model4.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1449f7b7",
   "metadata": {},
   "source": [
    "#### Compile Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "a7fbe7b1",
   "metadata": {},
   "outputs": [],
   "source": [
    "model4.compile(\n",
    "\n",
    "    optimizer=Adam(\n",
    "        learning_rate=lr_schedule\n",
    "    ),\n",
    "\n",
    "    loss='categorical_crossentropy',\n",
    "\n",
    "    metrics=['accuracy']\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e7058235",
   "metadata": {},
   "source": [
    "#### Early Stopping"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "36a06d5b",
   "metadata": {},
   "outputs": [],
   "source": [
    "early_stop = EarlyStopping(\n",
    "\n",
    "    monitor='val_loss',\n",
    "\n",
    "    patience=4,\n",
    "\n",
    "    restore_best_weights=True,\n",
    "\n",
    "    verbose=1\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "888ce321",
   "metadata": {},
   "source": [
    "#### Checkpoint"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "ffb8cc66",
   "metadata": {},
   "outputs": [],
   "source": [
    "checkpoint = ModelCheckpoint(\n",
    "\n",
    "    \"4plant_disease_optimised_cnn.keras\",\n",
    "\n",
    "    monitor='val_accuracy',\n",
    "\n",
    "    save_best_only=True,\n",
    "\n",
    "    verbose=1\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "cbf33468",
   "metadata": {},
   "source": [
    "#### Train the Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "045dcb68",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.4409 - loss: 1.8271\n",
      "Epoch 1: val_accuracy improved from None to 0.32228, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 1: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m630s\u001b[0m 3s/step - accuracy: 0.4409 - loss: 1.8271 - val_accuracy: 0.3223 - val_loss: 3.7398\n",
      "Epoch 2/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.5272 - loss: 1.1848\n",
      "Epoch 2: val_accuracy did not improve from 0.32228\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m662s\u001b[0m 3s/step - accuracy: 0.5272 - loss: 1.1848 - val_accuracy: 0.3197 - val_loss: 1.8619\n",
      "Epoch 3/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4s/step - accuracy: 0.6104 - loss: 1.0061\n",
      "Epoch 3: val_accuracy improved from 0.32228 to 0.48044, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 3: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m997s\u001b[0m 5s/step - accuracy: 0.6104 - loss: 1.0061 - val_accuracy: 0.4804 - val_loss: 1.6210\n",
      "Epoch 4/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4s/step - accuracy: 0.6773 - loss: 0.8165\n",
      "Epoch 4: val_accuracy did not improve from 0.48044\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m968s\u001b[0m 4s/step - accuracy: 0.6773 - loss: 0.8165 - val_accuracy: 0.2645 - val_loss: 4.2952\n",
      "Epoch 5/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4s/step - accuracy: 0.7223 - loss: 0.7392\n",
      "Epoch 5: val_accuracy improved from 0.48044 to 0.60332, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 5: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m927s\u001b[0m 4s/step - accuracy: 0.7223 - loss: 0.7392 - val_accuracy: 0.6033 - val_loss: 1.1541\n",
      "Epoch 6/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4s/step - accuracy: 0.7328 - loss: 0.7068\n",
      "Epoch 6: val_accuracy did not improve from 0.60332\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m940s\u001b[0m 4s/step - accuracy: 0.7328 - loss: 0.7068 - val_accuracy: 0.3537 - val_loss: 2.6127\n",
      "Epoch 7/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.7486 - loss: 0.6565\n",
      "Epoch 7: val_accuracy improved from 0.60332 to 0.61947, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 7: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m714s\u001b[0m 3s/step - accuracy: 0.7486 - loss: 0.6565 - val_accuracy: 0.6195 - val_loss: 0.9387\n",
      "Epoch 8/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.7868 - loss: 0.5969\n",
      "Epoch 8: val_accuracy improved from 0.61947 to 0.75128, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 8: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m667s\u001b[0m 3s/step - accuracy: 0.7868 - loss: 0.5969 - val_accuracy: 0.7513 - val_loss: 0.6514\n",
      "Epoch 9/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.8356 - loss: 0.5076\n",
      "Epoch 9: val_accuracy did not improve from 0.75128\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m633s\u001b[0m 3s/step - accuracy: 0.8356 - loss: 0.5076 - val_accuracy: 0.5599 - val_loss: 2.4398\n",
      "Epoch 10/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.8609 - loss: 0.4668\n",
      "Epoch 10: val_accuracy did not improve from 0.75128\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m586s\u001b[0m 3s/step - accuracy: 0.8609 - loss: 0.4668 - val_accuracy: 0.6752 - val_loss: 0.9944\n",
      "Epoch 11/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.8764 - loss: 0.4246\n",
      "Epoch 11: val_accuracy improved from 0.75128 to 0.81718, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 11: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m662s\u001b[0m 3s/step - accuracy: 0.8764 - loss: 0.4246 - val_accuracy: 0.8172 - val_loss: 0.5933\n",
      "Epoch 12/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.8930 - loss: 0.3845\n",
      "Epoch 12: val_accuracy did not improve from 0.81718\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m573s\u001b[0m 3s/step - accuracy: 0.8930 - loss: 0.3845 - val_accuracy: 0.8146 - val_loss: 0.7431\n",
      "Epoch 13/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.9086 - loss: 0.3484\n",
      "Epoch 13: val_accuracy did not improve from 0.81718\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m579s\u001b[0m 3s/step - accuracy: 0.9086 - loss: 0.3484 - val_accuracy: 0.6548 - val_loss: 1.9112\n",
      "Epoch 14/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.9140 - loss: 0.3332\n",
      "Epoch 14: val_accuracy improved from 0.81718 to 0.82100, saving model to 4plant_disease_optimised_cnn.keras\n",
      "\n",
      "Epoch 14: finished saving model to 4plant_disease_optimised_cnn.keras\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m581s\u001b[0m 3s/step - accuracy: 0.9140 - loss: 0.3332 - val_accuracy: 0.8210 - val_loss: 0.7203\n",
      "Epoch 15/25\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3s/step - accuracy: 0.9215 - loss: 0.3038\n",
      "Epoch 15: val_accuracy did not improve from 0.82100\n",
      "\u001b[1m217/217\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m585s\u001b[0m 3s/step - accuracy: 0.9215 - loss: 0.3038 - val_accuracy: 0.7853 - val_loss: 0.7480\n",
      "Epoch 15: early stopping\n",
      "Restoring model weights from the end of the best epoch: 11.\n"
     ]
    }
   ],
   "source": [
    "history4 = model4.fit(\n",
    "\n",
    "    train_generator,\n",
    "\n",
    "    validation_data=validation_generator,\n",
    "\n",
    "    epochs=25,\n",
    "\n",
    "    class_weight=class_weights,\n",
    "\n",
    "    callbacks=[\n",
    "\n",
    "        early_stop,\n",
    "        checkpoint\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c1c2c6cb",
   "metadata": {},
   "source": [
    "#### Accuracy Visualisation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "d388097c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "\n",
    "plt.figure(figsize=(10,6))\n",
    "\n",
    "plt.plot(\n",
    "\n",
    "    history4.history['accuracy'],\n",
    "\n",
    "    label='Training Accuracy'\n",
    ")\n",
    "\n",
    "plt.plot(\n",
    "\n",
    "    history4.history['val_accuracy'],\n",
    "\n",
    "    label='Validation Accuracy'\n",
    ")\n",
    "\n",
    "plt.title(\n",
    "    \"CNN Model 4 Training and Validation Accuracy\"\n",
    ")\n",
    "\n",
    "plt.xlabel(\"Epoch\")\n",
    "plt.ylabel(\"Accuracy\")\n",
    "\n",
    "plt.legend()\n",
    "\n",
    "plt.grid(True)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "36155c94",
   "metadata": {},
   "source": [
    "#### Loss Visualisation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "b1baa5e1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1000x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10,6))\n",
    "\n",
    "plt.plot(\n",
    "\n",
    "    history4.history['loss'],\n",
    "\n",
    "    label='Training Loss'\n",
    ")\n",
    "\n",
    "plt.plot(\n",
    "\n",
    "    history4.history['val_loss'],\n",
    "\n",
    "    label='Validation Loss'\n",
    ")\n",
    "\n",
    "plt.title(\n",
    "    \"CNN Model 4 Training and Validation Loss \"\n",
    ")\n",
    "\n",
    "plt.xlabel(\"Epoch\")\n",
    "plt.ylabel(\"Loss\")\n",
    "\n",
    "plt.legend()\n",
    "\n",
    "plt.grid(True)\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "83620874",
   "metadata": {},
   "source": [
    "#### Test Model"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "d6899d38",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m37/37\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m28s\u001b[0m 741ms/step - accuracy: 0.8177 - loss: 0.5835\n",
      "Test Accuracy: 0.8177\n",
      "Test Loss: 0.5835\n"
     ]
    }
   ],
   "source": [
    "test_loss, test_accuracy = model4.evaluate(\n",
    "    test_generator\n",
    ")\n",
    "\n",
    "print(\n",
    "    f\"Test Accuracy: {test_accuracy:.4f}\"\n",
    ")\n",
    "\n",
    "print(\n",
    "    f\"Test Loss: {test_loss:.4f}\"\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "65718892",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m37/37\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m23s\u001b[0m 613ms/step\n"
     ]
    }
   ],
   "source": [
    "# Generate Predictions\n",
    "import numpy as np\n",
    "\n",
    "predictions = model4.predict(\n",
    "    test_generator\n",
    ")\n",
    "\n",
    "y_pred = np.argmax(\n",
    "    predictions,\n",
    "    axis=1\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "ea267c90",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                    precision    recall  f1-score   support\n",
      "\n",
      "frog_eye_leaf_spot       0.95      0.88      0.91       478\n",
      "           healthy       0.67      0.99      0.80       694\n",
      "    powdery_mildew       0.75      0.82      0.78       178\n",
      "              rust       0.98      0.91      0.94       279\n",
      "              scab       0.96      0.58      0.73       724\n",
      "\n",
      "          accuracy                           0.82      2353\n",
      "         macro avg       0.86      0.83      0.83      2353\n",
      "      weighted avg       0.86      0.82      0.81      2353\n",
      "\n"
     ]
    }
   ],
   "source": [
    "#Classification Report\n",
    "from sklearn.metrics import classification_report\n",
    "\n",
    "print(\n",
    "\n",
    "    classification_report(\n",
    "\n",
    "        test_generator.classes,\n",
    "\n",
    "        y_pred,\n",
    "\n",
    "        target_names=list(\n",
    "            test_generator.class_indices.keys()\n",
    "        )\n",
    "    )\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "f1938cdc",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 800x600 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "#Confusion Matrix\n",
    "from sklearn.metrics import confusion_matrix\n",
    "import seaborn as sns\n",
    "\n",
    "cm = confusion_matrix(\n",
    "\n",
    "    test_generator.classes,\n",
    "\n",
    "    y_pred\n",
    ")\n",
    "\n",
    "plt.figure(figsize=(8,6))\n",
    "\n",
    "sns.heatmap(\n",
    "\n",
    "    cm,\n",
    "\n",
    "    annot=True,\n",
    "\n",
    "    fmt='d',\n",
    "\n",
    "    cmap='Blues',\n",
    "\n",
    "    xticklabels=list(\n",
    "        test_generator.class_indices.keys()\n",
    "    ),\n",
    "\n",
    "    yticklabels=list(\n",
    "        test_generator.class_indices.keys()\n",
    "    )\n",
    ")\n",
    "\n",
    "plt.xlabel(\"Predicted\")\n",
    "\n",
    "plt.ylabel(\"Actual\")\n",
    "\n",
    "plt.title(\n",
    "    \"Confusion Matrix CNN Model 4\"\n",
    ")\n",
    "\n",
    "plt.show()"
   ]
  }
 ],
 "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": "3.13.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}