ArtStudies/M2/Deep Learning/TP1 - Dense/TP1 - Starter.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Séance 1 - Réseau de neurones dense\n",
    "\n",
    "On se propose de classifier les chiffres manuscrit du dataset [MNIST](https://yann.lecun.com/exdb/mnist/) en définissant ses propres réseaux de neurones denses. L'objectif est de découvrir la manière d'entraîner ces algorithmes et observer en pratique les bases théoriques discutées en cours.\n",
    "\n",
    "## Exploration des données\n",
    "\n",
    "Commençons par importer les données."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "sns.set(style=\"whitegrid\")\n",
    "\n",
    "from tensorflow import keras\n",
    "\n",
    "(X_train_full, y_train_full), (X_test, y_test) = keras.datasets.mnist.load_data()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne** : À l'aide de la fonction [`train_test_split`](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html), séparer le jeu d'entraînement complet en un dataset d'entraînement et un dataset de validation. Afficher les tailles des datasets respectifs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(48000, 28, 28) (48000,)\n",
      "(12000, 28, 28) (12000,)\n"
     ]
    }
   ],
   "source": [
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "X_train, X_valid, y_train, y_valid = train_test_split(\n",
    "    X_train_full, y_train_full, test_size=0.2, random_state=42\n",
    ")\n",
    "print(X_train.shape, y_train.shape)\n",
    "print(X_valid.shape, y_valid.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne** : Afficher plusieurs images du dataset d'entraînement aléatoirement. On pourra utiliser la fonction [`imshow`](https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAxoAAAMqCAYAAAAFOjf/AAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQAAaH9JREFUeJzt3Qm4TdX/+PF1cQ2ZyeySKaJryHhFSIYbShnL8C0JqcgcUSQNkluZSlQyD4WQKZkzVK66hFR0yTxmdnH/zz7/Rz/7fHb2dqxz9j3nvF/P03O/6/Oss8+n73d99zmfs/dnr4jk5ORkBQAAAAAapdJ5MAAAAAAwUGgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGiXxsmk+Ph4ZWy3ERkZqT8DBKWkpCQVERGhKlSo4Pf3Yv3BzfVnYA3iRqw/uI3PYATL+nNUaBgLjH39cKNArgfWH7wFej2wBnEj1h/cxmcw3HQr68FRoXG9io2OjvY9K4SUhISEgL0X6w9urj8DaxA3Yv3BbXwGI1jWHz0aAAAAALSj0AAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGiXRv8hAQAAgk/Pnj1FLC4uTsS6dOliGo8bN86veQHBiisaAAAAALSj0AAAAACgHYUGAAAAAO0oNAAAAABoRzM4AOC2LF68WMQaNWrk07G++eYbEWvYsKFPxwJuZvLkySI2ZswYEYuIiBCxJUuWmMarV68Wc2rVqnXbOQLBjisaAAAAALSj0AAAAACgHYUGAAAAAO0oNAAAAABoRzN4CnPy5EkRS0xMDGgOOXPmFLGCBQsGNAcAwS116tQ+vc6q8RbQwftBA5999pmYk5SUJGJ33HGH7bGLFi16m9khWOXJk0fEjhw5ImKNGzc2jbt27SrmxMbGqlDDFQ0AAAAA2lFoAAAAANCOQgMAAACAdiHZo/HPP/+YxvHx8do20lmzZo2ILVy4UMTWrVvn0/GPHz8uYrt371Zu32948ODBgOYQjt555x0R+/vvv03j/v37izn58uXza16AnWeffdan17Vr107EatasqSEjhLs///xTxDp27GgaHzp0yFE/xty5c217GaOionzMFMHE6rvQtWvXRCxt2rQitn//ftN4wYIFYg49GgAAAADgAIUGAAAAAO0oNAAAAABoR6EBAAAAQLuQbAbv16+fbYO1VTP4xo0bRaxp06am8YkTJ8ScK1euOGqozpIli/JFiRIllC5PPPGEiP3000+mcbly5bS9H6ytXr1axIYPH267ZnLnzi3mWG36Y7XmnWwO+dFHHyknvDenatWqlZhTuHBhRw1yCH4HDhzwacO+bNmy+bQ5GmDX1F2sWDHb11l9Jls9PIbN+HDd2LFjHX3eWn0HjLdYW+GAKxoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGgX9M3gVs2rEyZMMI0fe+wxMefYsWMi9uijj4rY0aNHTeOqVauKOb169RKx6tWri1j+/PlFDKHvjTfeELEPPvhAxKwavd9//33TODEx0dGDDbZt22abl1Wzdvbs2R3tsPvPP/+YxoMGDbJ9KINh6NChIhYZGWmbK1KOV1991e0UEMasHmJh9UCMiIgIEbv77rtv+l3BQOM3oBdXNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAACO9m8KSkJBGbOHGiiF29etV2p1mrptft27fb5pA5c2YRS5cune3rED5WrVplGn/44YeOdkTu2LGjiDVr1sw0PnfunKMcatasKWL169c3jZ966ikxp2DBgiL2448/itjGjRtN41mzZjlqeE9OThaxN99885Z3lIZ7rNaD1f+u3udhQ6ZMmUzjkiVLas4OoebSpUu2D19ZsmSJiFl97o8ZM8Y0rlGjhpYcAfw3rmgAAAAA0I5CAwAAAIB2FBoAAAAAwrtHw+o+zJ9++sl2Y7x3331XzLG6D/zOO++87RwRXvbv3y9iLVq0sN0cskKFCiJmtU69ezIefPBBMWfgwIEiVqdOHaVLpUqVbGMvvPCCmNOwYUMRGz58uIgVKVLENO7SpYuPmSIQUqVK5WhzNKtzbIECBUzjzp07a84Ooeazzz4zjT///HNH/Rhz584Vsbp162rODoAdrmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAABDezeCLFy92NO/o0aOmcZUqVRy9rlChQiI2YMAA2ybbtGnTOjo+gtuFCxdErHfv3iLm3fzdpk0bMSdXrlwitmzZMhH7+uuvbRusIyMjVUo0depUEbv77rtFbPDgwaYxzeApy6lTp0zj8+fP+3ysfPnyacgIoWr27Nki9txzz9m+bujQoSJWr149bXkhfCUmJprGI0aMcPS6ypUr+ymj4MMVDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAwrsZPG/evI7mJSUlmcZ//fWXo9dZzYuNjTWNq1evLuY0atRIxPr37+/oPRE81qxZI2IzZ84UsRw5cpjG/fr1c7Sj+Pvvvy9i99xzT1A0flvJmTOnowcn5MmTJ0AZwReTJ082jdeuXevzsT755BMNGSEUbNq0ScTat28vYlmyZDGNK1asKOa0bdtWc3bA/5ecnGwaX7p0ydHrOnXq5KeMgg9XNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAACO9m8L59+4rYwoULRSxjxoymcbly5XzeefzPP/80jb///nsxxyoWHx8vYtOmTTON06QJqv/6w96iRYtELFu2bCI2f/580zg6OtrRDtkrV64UsaxZs6pg1bNnTxE7cuSIiI0dOzZAGSGQrHZ4Z2fw8GT1//tmzZqJmFWjbdmyZW3PwxkyZLjtHAH4B1c0AAAAAGhHoQEAAABAOwoNAAAAANoFVZNA+vTpRWzz5s3ajm+1YdoPP/xgGjds2FDMOXnypIjNmTNHxBISEkzjbdu2iTmpU6d2nC/85/Lly7ZrwZArVy4Rq1Gjhu3x06VLJ2K1a9dWwWrHjh0iNmnSJBHr3LmziDVt2tRveeHWnDt3zvZ/26tXr9puamUoWbKkiN1xxx23nSNSvgMHDthuqOc9x1CvXj0R+/zzz237MS5cuODoM9ib1eZ/pUuXtn0dwodVr6GTzaTZiPb/cEUDAAAAgHYUGgAAAAC0o9AAAAAAoB2FBgAAAIDwbgZ3Q+XKlW0bgrt16yZi33zzjYjt2rXLNB46dKiYM3jwYB8zhU5Lly4VsY0bN4pYx44dVTjyXstWjexWDZpWzZ4RERGas4OvXn31VRH75JNPbB9YYdUgjvBg1dQ9ZMgQ281IS5UqZdv4bTh27Jhp3L17dzFn9uzZyheFCxd2tNlu9uzZfTo+gt/Zs2dt5zz00EO23x3DGVc0AAAAAGhHoQEAAABAOwoNAAAAANpRaAAAAADQjmbwW1S0aFER+/rrr0WsT58+IhYXF2cajxo1Ssyx2kG1ePHiPmSK27F8+XJH8+6//34VSpKSkhw1Rw4bNsw0/ueffxztFn7XXXfddo7Q4+jRoyI2d+5cn46VKVMmEcuWLZtPx0JwsdqBe/z48aZxxowZxZy3335bxNKnTy9ir7zyimm8cOFCMad8+fKOPktnzJhhGv/yyy9izqJFixwdC7huxIgRbqeQonFFAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAACA8G4G3717t4iVKFFCuS1VqlSOdvj23i3ce3fl/9pllWbwwLNq1Ldqbg3mZvDDhw+LWKdOnRw97KBWrVqm8eLFi8UcGr9TNu+GfsO+fft8Ota7774rYjTQhp7jx4872k3e28svvyxiFStWFLEKFSrYnqdWrVrlaBfmDBky2DaDWz38wslO0AhNVg8aWLt2rSu5hBKuaAAAAADQjkIDAAAAgHYUGgAAAADCu0ejbNmyIrZmzRpH92sGWubMmUWsW7dupvHzzz8fwIxwu6w2k0oJPUJWrl69arupkNW9zkuWLBGxOnXqiNisWbNM4zvvvNPHTBEIP/zwg6PeG1917txZ27GQcv32228iZrVZZ8uWLU3junXrijktWrQQscjISBGbPHmyafzAAw+IORcuXLB9neHHH380jXPkyCHmsNFk+LJaRxcvXnQll1DCFQ0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAAMK7GdyqKefKlSsqWKRNm9btFHAbTp06JWLLly8XsXr16vkth40bN4qY1aZTr7/+uoh9++23ts3tcXFxItamTRsRo/k7uFSpUkXEIiIiXMkFweuPP/4QseTkZNtNzmJiYhydy2rUqCFizZs3t81r4sSJIvbiiy/avq5Hjx4i1rp1a9vXITRZrWXcPq5oAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAAAQ3s3gVlLqro1WTXPDhw93JRfcuiJFiojYnj17RGzQoEF+fUDBuHHjTOOlS5eKOZcvXxaxVKlS2e7E269fPzGnYsWKPmaKlMyq8Tt16tQ+HatLly4aMkIwKleunIiVKlVKxHbu3Gka9+zZU8zJmDGjiJUpU0bE2rZtaxqvWLFCzDlx4oSIWe36PWrUKNOYxm/ciAdk+AdXNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAACO9m8IIFC4pYhw4dROyFF14wjZ9++mlHjWJWvHddXr16tZiTkJAgYh9++KGI/fXXX6ZxpkyZxJxs2bI5ygv+tXLlSkc7fm/atEnEHn74Yb/lVaJECRGrUKGCiL3yyisiVrZsWb/lhfDRuHFjt1OAS6Kjo0Vs9OjRItakSRPbh7acP39exMaPH2+7W7NVw+5TTz3l6KEFVapUETHgOnYG9w+uaAAAAADQjkIDAAAAgHYUGgAAAADCu0dj2bJlIhYbGytiffr0MY3ff/99MSdDhgyO3vPq1au2m7Y5FRkZaRpPmzZNzOE++pShcOHCIrZ+/XoRs/rf0Lu/48KFC2JOgQIFfNog68knnxRzcuXK5ehYAKBb3bp1RWz+/Pmm8dSpU8Wcb7/9VsSKFi1qu3lq8+bNxZzatWuLWObMmW+SNaBvw77vvvtOxNgM8v9wRQMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAgPBuBr/nnntEbMWKFSL23nvv2W6+tmvXLm15lS9f3lEzcd++fU3jmJgYbTnA/6yarrt37y5iXbt2NY2vXbsm5qRLl05zdoB/eG++VrFiRddyQXDw3tzUarNTIKWxWqfVqlUzjTdu3Oho416awf8PVzQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAAAjvZnArxYoVE7GxY8eaxqdOnRJzEhMTteVw9913i1j69Om1HR/BxXsHeMBtVg8kAAD8n2zZsonYoEGDbvr90tC/f3+/5hXsuKIBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2Qd8M7muDj1UMAAAAMMTGxt50DHtc0QAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAuzROJiUlJank5GSVkJCgPwMEpcuXL6uIiIiAvBfrD26uPwNrEDdi/cFtfAYjWNafo0IjkCdUBAdjTQRqXbD+4Ob6u/5+wHWsP7iNz2AEy/qLSDbKVAAAAADQiB4NAAAAANpRaAAAAADQjkIDAAAAgHYUGgAAAAC0o9Bw4NKlS6pMmTKqZMmSpn8qVKjgdmoII+vWrVPNmjVT5cqVUw8++KCaOHGi55GDQCAdOnRIVapUSW3atMntVBBGtm7dqtq1a6fKly+vqlevrvr166eOHz/udloIQ5wDb42jx9uGu99++01duXJFvfvuu6pQoUL/xlOlok5D4D5ku3TpomJjY1X37t3VTz/95FmPV69eVZ06dXI7PYSJgwcPqmeeeUadOXPG7VQQRrZt26bat2/vKTBGjx6tjhw5okaOHKmef/55NWPGDLfTQxjhHHjrKDQc2Llzp0qTJo1q2LChSps2rdvpIAyNGjVK3XPPPZ7iwvDAAw94it+PPvrI8wGcPn16t1NECLt27ZqaN2+eeuedd9xOBWHIOO+VLl1ajR079t8f+DJlyqSGDRum9u3bp6KiotxOESGOc6Dv+EnegR07dqiiRYtSZMC1HTiNS7T16tUzxRs0aKDOnTvnuboB+NOuXbvUa6+9ppo2baqGDx/udjoIIydPnlSbN29WTzzxhOkugvr166vVq1dTZCAgOAf6jkLDYaGROnVq1aFDB8/9oVWqVFGvvvqqOnv2rNupIQwYv9glJSWpu+66yxQvXLiw5++ePXtcygzhIl++fGr58uWqf//+XD1DwL/gGb8m58iRQ/Xq1cvTG2n807dvX/XPP/+4nR7CBOdA33HrlA2j2dY40Rl/W7RooZ577jmVkJDguU/0999/V1OmTKFXA351/V5Q41aBG2XMmNHzl4IX/pYtWza3U0CYOnHihOfvgAEDPLeMGrdP7d2719OjYfwIM23aNBUREeF2mghxnAN9R6Fhwygwxo0b5/k1pUSJEp5Y5cqV1Z133qn69Omj1q5dq2rVquV2mghhxq95N0OhCyBUGVdzDcaTH42eDENMTIzKkiWL6tmzp1q/fr2qUaOGy1kC+C98Q7FhfImrWrXqv0XGdbVr1/b8Na52AP6UOXNmz1+jH+NG169keF/pAIBQcf3KbZ06dUzxmjVrev7++uuvruQFwBkKDRuHDx9Ws2bNUgcOHDDFL1686PmbPXt2lzJDuDAeqWz0CP3111+meGJioudvsWLFXMoMAPzrem+a8VCMGxlP3TNwvzyQslFo2DD2KRg0aJCaOXOmKf7NN994vvwZm7YA/pQuXTrPOjMa0W7coG/p0qWeqx1ly5Z1NT8A8Bfjh5QCBQqoRYsWmc5/K1as8PzlMxhI2ejRsJE/f371+OOPe3ZhNr7wGU+7MB4nauxf0KZNG1WkSBG3U0QYMB5C8PTTT3s26zN2B4+Pj/esSeMpLBkyZHA7PQDwC6PR23jC1EsvvaR69OihWrZs6XkQS1xcnOcR38b+GgBSLgoNB4YMGeJ5Vvf8+fM9jeF58+ZV3bp1Ux07dnQ7NYQJo/nR2LTvww8/9OyGmydPHs+Hr/HIZQAIZcZmucZn75gxY1Tnzp1V1qxZVevWrT2FB4CULSL5xmuRAAAAAKABPRoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAOwoNAAAAANpRaAAAAABwZ8M+YxdiY7uNyMhI/RkgKCUlJXl2bDV2Svc31h/cXH8G1iBuxPqD2/gMRrCsP0eFhrHA2NcPNwrkemD9wVug1wNrEDdi/cFtfAbDTbeyHhwVGter2OjoaN+zQkhJSEgI2Hux/uDm+jOwBnEj1h/cxmcwgmX90aMBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAOwoNAAAAANpRaAAAAADQjkIDAAAAgHYUGgAAAAC0o9AAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEC7NPoPCQAIRjt27BCxPXv2mMZffvmlmPPpp5+KWPPmzUUsS5YspnHHjh3FnJiYGMf5AgBSNq5oAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgHc3gABDijh07JmIJCQki1q1bNxHbvn27T+9p1TTubdq0aSJWv359EZs5c6aIpU+f3qe8AB3Onz9vGh8/flzMiYqKCmBGuBV79+4VsSVLlojY1KlTTePs2bOLOd9++62ItWjRQsSSk5NtH5iRNWtWEatVq5YKZlzRAAAAAKAdhQYAAAAA7Sg0AAAAAGhHjwYQ5P755x9H975/9dVXpvHy5ct9fs9y5cqZxu+8846Y06BBA5+Pj9vTv39/0/jtt98WcyIiIpTbLl26JGILFiwQsccee0zEZs+ebRpnypRJc3YIR1ZrcujQoSK2YsUK03jfvn1izv79+zVnB198+OGHIjZo0CARO3PmjO1n3dmzZ8WckiVLitiaNWts+0KmTJki5qROnVrEWrdubfvvZNU7klJwRQMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAAO1oBr9Fp0+fFrFdu3aJ2IwZM0Tss88+M43z5csn5jRs2NBRHk8++aRpnCdPHjGHzYKCv6nbe81YbZ62bNkyEUtMTLR9P6tm4GzZsolYiRIlROyHH34wjT/++GMxh2Zw/ayaFVu1aiVi3333nbb3TJcunWlcpEgR242oDNOnT7c9V1qtm1WrVjnaSGvevHmmcdu2bcUc4FbFxMSI2NatW21f9+yzz/opI9yqCRMmmMZ9+vRxtDGe1UNNunTp4lMOJ0+eFLF9Xg8MsNrU1Oqc6L1poCEpKcn2O2dKwRUNAAAAANpRaAAAAADQjkIDAAAAgHYUGgAAAAC0oxn8BleuXLFtaD1w4ICYs3PnTp/e79SpUyK2Y8cOR6+Ni4uzbeKdNWuWiNWrV++WcoR/bNu2TcTq168vYufPnzeNH3zwQTFn8ODBItajRw8Ry5gx403XkKFu3boi9uuvv4rYAw88IGLQ6+LFiyLWsmVLEVu6dKlPx0+fPr2IvfzyyyLWpEkT07hChQrKV+XLl7d9IEbt2rV93sEZuBnvBxR88803Yk58fLyIFShQwHZn6Y4dO2rJEbdv0qRJN22cNkyePNmvDzCx2qk7u1fM6oE93rnfyvFTKq5oAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgHc3gN3j11Vd92mE3MjJSxKpXr27baHvXXXeJObGxsY52xe3evbtpfOLECTFnypQpIkYzeOB5N3T/V1Ov1a7wTz/9tGlcs2ZNMefvv/8Wsddff13EnnrqKdM4c+bMytcdy+F/Vk2BVucCJ6yavK1iVrvlBprVLuNW8uTJ4/dcELwSEhJEbNq0aabxwoULxZxUqeTvrx999JGINW7c+LZzhH+sW7fO9nuVzsZvXyUmJorYX3/95ej7gtVu5ykVVzQAAAAAaEehAQAAAEA7Cg0AAAAA2tGjcYNWrVqJmPdGeKVKlRJzrO51r1Onjk85WN0zOnv2bNvNqqzyatasmU85QK+YmBgRy5Ili4iNGDFCxHLkyGF7fKvNpF588UXli99++03Ejhw5ImLevSJdunTx6f3w36zuC4+IiHD02iFDhtx0czHdrDYfteq1aN26tWm8ZcsWR/+OVj1vVhtcIjy99dZbIjZu3DgR279/v2n8yCOPiDnPPvusiNGPkTJYbbzXs2dPnzY//eyzz0SsefPmIua0l9HbyZMnbd9z9+7dYs7EiRNFrG3btiKWNm1aFSy4ogEAAABAOwoNAAAAANpRaAAAAADQjkIDAAAAgHY0g9+gXLlyjmK+unDhgmm8a9cuMWfYsGEitnHjRttNAq2aca0a3eB/hw8fNo2LFy8u5vTo0UO5LVeuXCKWM2dO243+rDY7ojFXv8qVK4vYzz//7NNGUFabQBUuXFjEDh48KGKbN2+2bWC0asbNnz+/iG3fvv0mWf93Xt4brQVbMyT0sXpgxYABAxw9VCAqKsr28/bee++97RzhH1ZN3YsWLbJ93apVqxzFrB580q9fP9vjnzt3TsQefvhh2+9yd1ls2my1cXSwn+u4ogEAAABAOwoNAAAAANpRaAAAAADQjkIDAAAAgHY0g2uwZs0aEZs3b56ILVmyxDTesWOHo+OXKVPGdudnmnFTjvTp05vG33zzjZgzd+5c212TDVOmTDGNU6Xy/bcB793knTQR/1cj8euvv+5zHnCmYsWKIjZhwgRHr/XeXXbmzJliTqVKlUTs2LFjIrZt2zbb97PaBdxqZ1wnsmbN6qgBOEuWLLbHypYtm085IOVYuHChadyuXTtHr+vUqZOIeTd/Wz38AimX1S7dVg/C+fjjj03jPXv2ODp+//79Rcz7e1rHjh0dfZ5v2rRJxAoUKGAaL168WMzJly+fCjVc0QAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQLugbwa3akJMSkoyjePj4x016ljx3j3SqoF7586djo7l3cj72GOPiTlNmzZ1FHPSCAl3eDezWj0YoGXLliI2Y8YMEXv00UdN41atWok5x48fF7EVK1aIWFxcnO3rrHZgtmpSh/+1adNGxL766itHDfy7du0yjc+cOeNoZ9yU4JdffhGx5s2bi1iePHlM40KFCok5CxYssH1YA9xx5coVEduyZYuIPfvss6bx1atXxZxSpUqJWM+ePUWM5u/Q07dvX9vYTz/9JOa8++67jj43J02adNPxrdi/f78KR1zRAAAAAKAdhQYAAAAA7Sg0AAAAAGgX9D0aH3zwgYj16NEjoDnkzp1bxI4cOSJitWrVMo0/++wzR5tVIbg1aNBAxNq3by9iY8aMEbHevXvbbuYzfvx4R70WUVFRtpsFPfjggyIGd2TKlEnEli5d6ui1NWrUMI2PHj3qaBM8f/fP+er06dO2Mat/ny+++MLRRm4IvLNnzzo6Lx4+fPimn6OGlStXas4Oob75qVVPpFWPUOfOnW37PawUK1bslnIMZVzRAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAu6BvBh82bJi2Y3lvqGfo0KGDafz444+LORkyZBCxOnXq2Dasff/992JObGys43wRvEaOHOloo7K1a9eaxrVr17bduMxqcz5Du3btTOMcOXI4zhcp1xtvvCFiW7duNY3PnTsn5kRERPj0flYb3lk1PjZu3Nin43/55Zci9tdff9luWmq1AWX37t1FrHLlyiJWoUIFFaqsHhYR6IZ4q0b9ESNGOJpXt25d23MboEPatGlF7I8//rCdY3VO9H6dYejQoepGAwYMUN5Sp06tQg1XNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0C7om8F///132wbxgwcPijlVqlQRsdatW4tYrly5bHP49ddfRcxqB+dr167ZNjgiPEydOlXErNaDk92VrZqBn3nmmdvIDinBpUuXHDX2Wj0Qw+q13tKlS2e7C67VbvGFChUSc8qXL690ee6550QsMTFRxEqVKmUa586d29F/DwsWLAirZvCUsBP6o48+KmI7d+509IAC7wbae++9V3N2CEcXLlwQsd69e4vYyZMnTeMxY8aIOTExMY52I3/11VdN43r16ok51apVU6GGKxoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGgX9M3gWbNmFbHhw4cHNAerBiKrBnTvJp8uXbr4NS+44+LFi6Zxy5YtxZzly5c72l00Y8aMpnFUVJS2HZiRspw/f9407tChg5gza9Ysn4797LPPiljz5s1FrH79+sptVs3mVrGzZ8+axoULF3b0gIV9+/bddo64ecP9iy++aNv4bfXZPW7cuLBojoX7rJq6ly5dKmL/+9//TOOuXbs6aiy3avRetmyZaTx79uywWO9c0QAAAACgHYUGAAAAAO0oNAAAAABoF/Q9GoG+//SFF14QcxYvXuzoWEOGDNGWF1KG/fv3i9gjjzxiGsfHx4s5JUuWFLEvvvhCxDZv3mwad+vWTcxZtGiRiFnd34+UbcuWLVr6MQy9evUyjd99910Vat5++22fNkAtUaKEnzIKT1bnnwkTJthuxNezZ08Re+KJJzRnB1j3UHz//fciliNHDhHr27ev7fEzZMggYnFxcSJWpkwZ03j06NGONtstXbq0CmZc0QAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAIHSbwdesWWMa33///WJO6tSpVaB9/fXXN21y+y81atQQMat/JwSPbdu2iZjVwwG2bt1qu1ma1YMB8uXLJ2LR0dG26+/06dM3yRrBYt26daZxcnKyo9cNHDhQxIYOHapSoh07dpjGe/bssW3yNqxdu9an9/Pe8NIQGxvr07Fg/b9D586dbV/36quvOooB/jBv3jxHsfbt22trxLZ6XUuvzXutNuy7cuWKCjVc0QAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAIDSawb0bYgzz5883jRs1aiTmlC9fXlsOBw8etM3BcOrUKdtjjRgxwlGTcLp06W4pR6Qso0aNsn2IgdWu3+PHj/f5Pb0bvQ8fPizmfPXVVyLWo0cPn98T7ti9e7ftbspWunTpoi2HS5cuidiZM2dsd4L+5ZdfROz3338XsVWrVt302LciTZo0tp8PgwYNsn3AApybO3euiB0/flzEmjRpYvu/AxAo8fHxKiV4xmvXb6tm8FDEFQ0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAAEKjGbxt27Yi9uuvv9o2nVnFdLJqvsyfP79p3K1bN0eNt6lSUcOFGqtGbKvdmydOnKjtPfPmzWsaFytWTMzJlSuXtveDewoVKuTT6xo2bChixYsXt12nVue7Q4cOidimTZtsc3B6fF81bdpUxCpWrGi7Qzp8N2TIEBH79NNPRWzq1Kki9sQTT/gtL+BWxcTEODpnWe18f+DAgZt+J7wdyRY5hCK+DQMAAADQjkIDAAAAgHYUGgAAAABCo0fjkUceEbHatWubxvPmzRNzfv75Z7/mZXVfqfd901myZBFz6McID2XLlhWxr7/+WsR++OEH07h69eracrC67/2hhx7Sdny4p2PHjqbxtGnTbDf1M2zfvt025u8eiowZMzrqOSlcuLBp3K9fP0cb6uXMmfO2c8TNeW+8l5iYaPs5baAfAyld48aNRax9+/YiNnnyZNue4qVLl4o5kZGRInby5EkRa926td/OwSkZ35ABAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAAAiNZnAr3k3WVo06gJu6du0qYmfPnrXdwPHy5ctiznPPPSdimTJlss0hKipKxNatW+coV6RsBQoUMI2/+eYbMeftt992tGHaxYsXbd+vefPmIpY1a1bbc3OzZs3EnMyZMztq6kbKNX36dNO4Vq1aYg6fywhGVs3aQ4cOFbETJ06I2MKFC03j++67T8xJkyaNo2bwk16x8uXLizklSpRQoYYrGgAAAAC0o9AAAAAAoB2FBgAAAADtKDQAAAAAhG4zOJDS5c2bV8QGDhwoYufOnTON33zzTTHnrbfeErGGDRuK2KBBg0zj9OnTizmNGjW6SdYIVsWKFROxTz75xFEMuFUvvPCC2ykAAVOoUCER69evn4hdunTJNP7222+1PfBjutcDGAwZMmRQoYYrGgAAAAC0o9AAAAAAoB2FBgAAAADtKDQAAAAAaEczOHAbcuTIIWIff/yxadynTx8x5/333xexsWPHitiqVatM4/j4eDEnT548jvMFAABSjRo1RGzZsmWu5BJKuKIBAAAAQDsKDQAAAADaUWgAAAAA0I4eDcDPihcvLmKjR492FAMAAAhWXNEAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAANzZsC8pKUklJyerhIQE/RkgKF2+fFlFREQE5L1Yf3Bz/RlYg7gR6w9u4zMYwbL+HBUagTyhIjgYayJQ64L1BzfX3/X3A65j/cFtfAYjWNZfRLJRpgIAAACARvRoAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgHYWGA9euXVMTJ05U9evXV2XLllWPPPKI+vrrr91OC2Fm1qxZqlGjRqp8+fIqNjZWTZ061fPIQSAQWH9IKQ4dOqQqVaqkNm3a5HYqCCOcA33j6PG24e6DDz7wFBrdunVT0dHRavXq1apPnz4qVapUqnHjxm6nhzAwe/ZsNWjQINWuXTtVt25d9eOPP6qhQ4eqS5cuqQ4dOridHkIc6w8pxcGDB9Uzzzyjzpw543YqCCOcA33H421tXLhwQVWvXl21bt1a9evX79+4sdiMDUtmzpzpan4ID8b6MwrbadOm/Rvr2bOn2rp1q/ruu+9czQ2hj/WHlHBnwbx589Q777zjGZ86dUp98cUXqmrVqm6nhjDAOdB33DplI23atGr69OmiYo2MjPRUskAgGGstU6ZMpli2bNk8H7aAv7H+4LZdu3ap1157TTVt2lQNHz7c7XQQZjgH+o5Cw0bq1KlVqVKlVK5cuTz34h07dkyNHz9eff/99+rJJ590Oz2Eifbt26t169ap+fPne24ZWLt2rZo7d6569NFH3U4NYYD1B7fly5dPLV++XPXv31+lT5/e7XQQZjgH+o4ejVuwaNEi1atXL89/rl27tqcpHAgEowFt8+bNqm/fvv/GatSooQYMGOBqXggPrD+4zfj1GHAL50DfcUXjFhhPnJoyZYqnIWjLli2qY8eOPHEAAdG1a1e1ZMkSz0MIJk+e7FmD27ZtU927d2cNwu9YfwDCGedA33FF4xYUKlTI80/lypU99+oZzeHGkweMMeAvRlFrXKZ94403VIsWLTyxKlWqqKioKNWpUye1atUqVadOHbfTRIhi/QEIZ5wDbw9XNGycOHHC86SL48ePm+KlS5f2/D1y5IhLmSFcHDhwwPP3vvvuM8WN58gbdu/e7UpeCA+sPwDhjHPg7aHQsHHx4kXPlYs5c+aY4uvXr/f8LVmypEuZIVwULVrU89e4eub9K4vB+FUF8BfWH4Bwxjnw9nDrlI38+fOrZs2aqTFjxqg0adJ4rmQYi8148lTz5s1V8eLF3U4RIc5Ycw0aNFBvv/22On36tCpXrpz6/fff1ahRo1SZMmVUvXr13E4RIYz1ByCccQ68PWzY54CxMZ+xM7hxC9Xff//tecxey5YtPbuTGhu4AIFYg+PGjfM8Ws+4Xc8ogB966CH1/PPPq4wZM7qdHkIc6w8pyaZNmzyPG2XDPgQK50DfUWgAAAAA0I6f4wEAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAA3NmwLz4+XhlPwY2MjNSfAYJSUlKSioiIUBUqVPD7e7H+4Ob6M7AGcSPWH9zGZzCCZf05KjSMBcZ2G7hRINcD6w/eAr0eWIO4EesPbuMzGG66lfXgqNC4XsVGR0f7nhVCSkJCQsDei/UHN9efgTWIG7H+4DY+g+GmW1l/9GgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAOwoNAAAAANpRaAAAAADQjkIDAAAAgHYUGgAAAAC0o9AAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAANAujf5DAgAA3L5Tp06Zxl27dhVztmzZImIbN24UsWzZsmnODoAdrmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdzeAAEIbOnDkjYvPnzxexzZs32x5r/PjxInbp0iXb12XKlEnEBg4cKGIvvfSSiKVLl872+Ah+M2bMMI1nzpzp6HW7d+8WscqVK2vLC7hVH3zwge15zcrEiRNFrEOHDipYcEUDAAAAgHYUGgAAAAC0o9AAAAAAoF1I9mgcO3bMNN63b5+YU65cORFLlcq/dVfp0qVN4zRp5H/9K1euFLGcOXP6NS8AoWXHjh2mcY8ePcScQ4cOidgvv/yiLYeIiAjbOefOnROx/v37i9jevXtFbMyYMQE9f8Mdv/32m0+vs9rEjx4NBMrBgwdF7JNPPrnlc+StzEupODMDAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKBdSDaDnzhxwjS+7777xJzHHntMxN58800RK1WqlE85XLlyRcSSk5NN44SEBEeNkFabYSHlbnpWpUoV03jXrl1izvPPPy9i7du3F7E33njDNF6wYIHtunLaPFa9enURa9y4sYi1bNlSxLJly2Ya58iRw/b9cPuszivDhw8XsREjRpjGp06d8vk9vddSZGSkmNOpUyefNtSz+v+P1fnu448/FrGnn376pv+/Q2iIj4/36XWNGjXSngvg1OzZs0Xs119/VeGIKxoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGgXks3gy5Yts50zd+5cEevYsaO2ZvCvv/5axHbu3OnTsZByvffee7Y72Vo1Zo8dO9ZRzJvOnUQ3bNjgKPbKK6+IWIkSJXz6/8nAgQNFrFKlSo5eG26smvzbtGnjqOnQiSJFiohYrVq1RKxJkya2D9Lw1f79+31++EXatGm15YGUy/tcs3r1atdyAZzuAu7rQ3wKFy4sYk8++aQKZlzRAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAu6BvBj9+/LiIjR49WrltyZIlbqcAzb788ksRGzZsWEBzaNWqlYhlypTJp2bwSZMmiVhSUpKjPHbv3n3T8X8pWrSoiNEMbu2tt97yufE7TRrzqf3999931FieNWtWFUh//vmno3nR0dGOYgg9EyZM8OmBGEAw7gJeuXJlEUuXLp0KZlzRAAAAAKAdhQYAAAAA7Sg0AAAAAGgX9D0a06dPF7Fdu3b5tCmKr/f8/vLLL47u53ci0PdIw9rly5dF7PXXXxexa9eu+XT8jBkzitijjz5qu8Gd9+ZVhlSpfPu9IC4uTsSefvppEZszZ45Px7faUC1z5sw+HSscffLJJ9pe+7///U8F2tWrV0Wsb9++N73//r8kJCSI2MSJE03jTp063XKOSPlat25tGs+cOdO1XIBx48aJ2Msvv+zTsYoVKyZin376qQo1XNEAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEC7oG8Gj4+P9+l1HTp0ELGoqCifjpWYmChiJ06csH1dlixZRKxHjx4+5QC91q5dK2Lbtm3z6Vj33nuviI0fP17EqlatqgLphx9+ELHNmzf7dKw77rjD0b/jE0884dPxw1Hu3LlF7K+//nL02mPHjqlAOnDggIi9++67IvbBBx9oe89z585pOxZSroMHD7qdAsKY9/r78MMPxZyLFy/6dOxevXo52oA32HFFAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAACA8G4GP3nypIitXLnSp2OVLVtWua1p06Yilj9/fldygdns2bO1HSslNH4b/vjjD9O4YcOGjnZEtxIZGWm7i7X3jr64Nd67wv/X7vFWvHeqXb9+vZjTu3dvEatevbqIHT9+3DQePXq0o91s9+3bp3xRo0YNEatfv76ItWzZ0qfjI7isWrXKNI6IiHAtF4SfGTNmmMa7du3y+VglS5YMy4ejcEUDAAAAgHYUGgAAAAC0o9AAAAAAoB2FBgAAAIDwbga32n1xz549Whpj/6vJx7t5x8qhQ4d8ygEpV+HChUUsderUIpacnCxiXbt2NY3vu+8+FWi7d+8WsQYNGvjU+F2mTBkRa968uWlM47d+jRs3FrEuXbqI2JQpU0Ts7NmzpvG8efPEnMWLF4tYlixZRCwpKck0PnXqlHIiTZo0tg9BaNKkiZjTvXt3EUuXLp2j90To8W7+phkc/rJ69WoRe/XVV7Udv7vXuS1r1qwqHHBFAwAAAIB2FBoAAAAAtKPQAAAAABDePRrem4QZcufOLWJHjhyxPZbVZlVvvPGGiMXExNgea8OGDbZzEFz69+/vqF/Hqm/oySefVIG0c+dOEYuNjRWxxMRE22NVqVJFxN566y0Rq1279i3liFtndS/62LFjbTfnMzz11FM33fTMcOnSJRE7evSo0mXQoEGOYgCQEmzZskXEzp0759OxSpUqJWItw3STUa5oAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAAAQ3s3gd955p6NNrT799FOfjm+1EZXVpla6tGnTxm/Hhn6PP/642ymob7/9VsSeeeYZEdu/f7/tsdKmTStiw4cPF7GaNWveUo4IrEKFConY8uXLbc9jHTt29OlBGk5ZNZafOHHCNM6RI4e29wMAp44dO+boYRtOWG10arXRX44wPd9xRQMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAgPBuBrfSpUsXEdu3b59pfObMGTFn48aNym1FihRxOwWkcH/++aftruNWTW1Wu0p7+/nnn0Xs7rvvvuUckfKkTp3a9kEa3o3Z/7VucuXKZRpfvHhRzPnnn39EbPTo0SI2adIk03jq1KmOHvCB8JWcnOx2CghBU6ZMEbE//vjDp2OVLVtWxFq3bu3TsUIRVzQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAANAu6JvBK1euLGLLli0zjc+fPy/mJCQkiNiMGTNE7PfffzeNv//+e0dNlVbq1atnGkdFRTl6HcLDunXrROyBBx7wqVkyffr0Ivb555+bxjR+hy7vhm2rhwhcuXJFxEqXLi1i27ZtM4337t0r5jz11FMitmbNGhHzfjBH165dxRyawXGzBxQ4edAFYOfjjz/26XWZM2cWsWeffVZDRqGLKxoAAAAAtKPQAAAAAKAdhQYAAAAA7YK+R8OJO+64Q8SqVq3qKOatVq1aju5FtpIzZ07b++gRHnbv3i1i7dq1EzEn9yNbraMJEyaIWMuWLW8pRwSvq1ev2vZVWGnWrJntnLvuukvEli9fLmJNmjSx7Z87cuSImPPdd9+J2IMPPmibF0JTxYoVTeMtW7a4lguC0+nTp0Xs0qVLPh0rNjbW0Wc3/g9XNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0C4smsFTis6dO7udAlwwf/58EevRo4eIJSYm2h7r3nvvFbFXXnlFxGj8Dm/jxo3z6XUxMTE+vS4yMlLEsmXLZvu6y5cvO2rcRPj66aefTGM27IMd741B27ZtK+Y4fUCGt27duvmcV7jiigYAAAAA7Sg0AAAAAGhHoQEAAABAOwoNAAAAANrRDB5Ad955p9spQLNr166JWEJCgmn8wgsviDkHDhxwdPy0adOaxnPnzhVzihYt6uhYCB9XrlyxnVOjRg0Rq1Onjk/vt3TpUhH7/vvvbV+XLl06EcuVK5dPOSA0JScnu50CgsysWbNM40WLFvl8rOjoaNO4ePHiPh8rXHFFAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7WgGB26Dd+O34b777vPpWHfccYeIjR8/3jSm8Ru6FChQwFFz9uHDh20fSNC7d28RO3/+vG0OVs3nVk3qCF/e6/TgwYOu5YLQZnX+836YS+7cuQOYUWjgigYAAAAA7Sg0AAAAAGhHoQEAAABAO3o0AIfmz58vYlab8TlRpkwZERswYICItW7d2qfjA7e6qZUhe/bsIrZ27VrTePv27T6/Z7169Wz7PYAbtWzZ0jT+4IMPXMsFoe3RRx8VsWeffdaVXEIJVzQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAANCOZvBb1KtXLxFbs2aNK7nAf3bv3i1iPXr0ELEDBw7YHqtcuXIi9s4779g2ygK+aty4se2DBpKTk0Xso48+0pZDw4YNRWz69Om2G2QBN6pVq5ZpvHjxYkevy5w5s58yQkqXOnVq0zgiIkLMKVu2rIiNGjXKr3mFK65oAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgHc3gt+iee+4RsXz58onYwYMHRWzdunWm8b333qs5O/jq6NGjpnH9+vXFnMTEREfHKlSokGk8adIkMSc6OvqWcwScKlGihO0O8zNmzHB0rDx58tx0p2ZD1apVRaxJkyYiRoMubne3Zqvdm4EbPfXUU6bx999/L+ZYxa5du+bXvMIVVzQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAANCOZvDbbLI0tG3bVsTeffddEatRo4bf8sLtGTJkiE+N39myZROxjRs33rSZFvA37x23p02bJuZYxQAg1IwfP97tFMIaVzQAAAAAaEehAQAAAEA7Cg0AAAAA2tGjocHw4cMdxZBy3X333bZzrDZYfO2110SMngwAAACuaAAAAADwAwoNAAAAANpRaAAAAADQjkIDAAAAgHY0gwNKqW7dut10DAAAgFvDFQ0AAAAA2lFoAAAAANCOQgMAAACAOz0aSUlJKjk5WSUkJOjPAEHp8uXLKiIiIiDvxfqDm+vPwBrEjVh/cBufwQiW9eeo0AjkCRXBwVgTgVoXrD+4uf6uvx9wHesPbuMzGMGy/iKSjTIVAAAAADSiRwMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAAO0oNHzwwgsvqAcffNDtNBAmNm3apEqWLPmf/4wePdrtFBEGZs2apRo1aqTKly+vYmNj1dSpUz2PvAQC7dChQ6pSpUqecyMQaKy/W+Po8bb4P/Pnz1fLly9XBQoUcDsVhIkyZcqomTNnivj777/vea658eUP8KfZs2erQYMGqXbt2qm6deuqH3/8UQ0dOlRdunRJdejQwe30EEYOHjyonnnmGXXmzBm3U0EYYv3dOgqNW3D48GE1bNgwlTdvXrdTQRjJlCmT51fkG61YsUJt2LBBffDBB6pIkSKu5Ybw8OWXX6qKFSuqgQMHesYxMTFqz549asqUKRQaCIhr166pefPmqXfeecftVBCGWH++49apW2B8yN5///2eD1nALRcvXlRvvPGGql27tmrYsKHb6SAMGFcujIL3RtmyZVOnTp1yLSeEl127dqnXXntNNW3aVA0fPtztdBBmWH++o9C4hVsHtm/f7rl9AHDTF1984bm6NmDAALdTQZho3769WrdunefWUeOWgbVr16q5c+eqRx991O3UECby5cvnuW25f//+Kn369G6ngzDD+vMdt0458Pfff6u33nrL80+OHDncTgdh7PLly55C4+GHH1aFCxd2Ox2ECaMPaPPmzapv377/xmrUqEGxi4AxrqABbmH9+Y4rGjaMp6oYH6a1atVSDRo0cDsdhLmlS5eqo0ePqo4dO7qdCsJI165d1ZIlS1SfPn3U5MmTPVd2t23bprp3786TpwAA/4krGjaMRzga9+YtWLBAXblyxRO7/sFqjFOlSuX5BwhUoVGiRAlVqlQpt1NBmNiyZYvnVimjL6hFixaeWJUqVVRUVJTq1KmTWrVqlapTp47baQIAUiC+ITv4Ynfy5EnPbQLGY0aNf4wnDxi3Uxn/ecyYMW6niDCRlJTkuU+eBnAE0oEDBzx/77vvPlPceI68Yffu3a7kBQBI+biiYWPIkCHq3LlzpphRXBi3DYwbN07lzp3btdwQXn777Td14cIFz2NGgUApWrSo56+xd0axYsVMVzoMxpUNAACsUGg4/JD1bgpKmzatio6OdiUnhG+hYbjxyx7gb6VLl/b0p7399tvq9OnTqly5cur3339Xo0aN8lzVrVevntspAgBSKAoNIEgcO3bM8zdr1qxup4IwM2LECM8V3BkzZqgPP/xQ5c+fXz3++OPq+eefV2nS8DECALAWkcwjQwAAAABoRjM4AAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2jh6AHh8fr4yn4EZGRurPAEEpKSlJRUREqAoVKvj9vVh/cHP9GViDuBHrD27jMxjBsv4cFRrGAmO7DdwokOuB9QdvgV4PrEHciPUHt/EZDDfdynpwVGhcr2Kjo6N9zwohJSEhIWDvxfqDm+vPwBrEjVh/cBufwQiW9UePBgAAAADtKDQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADapdF/SADBYNu2bSLWrl07ETtx4oSIbd++3TTOlCmT5uwAAECw44oGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADa0QyuwaxZs0QsJibG9nVRUVF+ygiQtmzZYhr37t1bzNm6dauIpUolf4+4dOmSaUwzOAAA7ti7d6+IPf744yKWO3duEVuyZInyJ65oAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgXdg2g1s1cM+ZM0fEZs+erQLpvffeE7GePXsGNAcEv5UrV9quI6vG77Rp04rYxIkTRSxnzpy3nSNCW6FChUSsWbNmpvFzzz0n5tx9991+zQsAgt2xY8dM41q1aok5R48eFbFXXnlFBRpXNAAAAABoR6EBAAAAQDsKDQAAAADahWSPxr59+0zjli1bijkbN25UKVGvXr1ErGDBgiJm9e+E8HTu3DlHfT3ePRmRkZFiTqNGjUSsbdu2t50jQttvv/0mYhcvXhSxDz/80DS+//77xRx6NMLXhg0bRCwuLs62b7JatWoi1qNHDxHjcxPB6MyZMyL2yCOPmMb79+8XcwYPHmzbJxcIXNEAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEC7NKHW+P1fG0U5YdU85t1kdjvNZN6Nbq1atXL072M1LyYmxjSOioryOS8Ej9OnT4vYY489JmJWm/F5a9eunaPN+QA7Y8eOFbHjx4+7kguCd9Ncq886J6we7mJ1LO/PSe/PUSAlmmjxuez9fXLGjBna/v+kG1c0AAAAAGhHoQEAAABAOwoNAAAAANpRaAAAAADQLuibwa120vZm1Si9fv16R/N08m48S0xMdNTIbtUg7v3vbdVYh9DjvRuoYc2aNY5e27t3b9N46NCh2vJCePPe8dsQEREhYlWqVLHd0RmhR2fjt9VDW+bMmePoc9N7V3GawZHSjBo1SsQGDRokYt26dTONGzdurFIqrmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKBd0DeDW/Fu6h4xYoTtnJTipZdectTw7t3UhtD00Ucf+dT43aRJExEbPHiwaZw+ffrbzA7haP78+Y7mlS9fXsS++uor0zhfvnza8kLK4d2I7f0gilsxc+ZM07hly5aOGsStHqwSFxdnGo8cOdLnvIBblZycbBqfP39ezJkwYYKI3XnnnSL2wQcfqGDBFQ0AAAAA2lFoAAAAANCOQgMAAACAdmlCcSMg7/tDU2o/hpWCBQu6nQJS0KZnVvcee8uePbuIvfnmmyKWMWPG28gO4erMmTOm8fvvv29777GhRIkSIkZPRnjw7iu02jzPST/Gf/VkeNu/f7/S9f3ByfshuCxZskTEvv/+exF7/fXX/ZrH2bNnTeOKFSuKObt37xaxiRMnqmDGFQ0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAALQL+mZwK8HU/B1KucO57777zlHj97Vr12wbvxcvXixi9957723nCBhWr15tu2lkRESEiJUrV86veSFl2LBhg08bylqd73xtxGYDW9zM8OHDHTVdV6lSRcQaN26sLY8LFy7Y5lCkSBERa9OmjQpmXNEAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEC7kGwGB1KS3377TcSeeuop28ZvKytXrhSxtGnTithPP/2kfBEZGSliZcuW9elYCA2TJ0+2nZM/f34R69ixo58yQkoSFxfn0+usmsGteO8qbvV+vuaA4JecnCxiP/zwg2m8fv16MSdHjhwi9tBDD2nL6/LlyyJWtWpV0zhjxoxizowZM0QsXbp0KphxRQMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAAO1oBg+CXVattGjRwu+5wDfeTd0vv/yybYOjU1ZN5Dt37hSxixcv+nT8NGnkKaF3794i9tprr5nG6dOn9+n9kPIfXLBp0ybb13Xq1EnEcuXKpS0vBLdq1aqJWFRUlIj17NlTxObMmaPl3InQdOXKFRFr0qSJaVyuXDkxZ9WqVSKm83PslVdeEbHDhw+bxuvWrRNz7rvvPhVquKIBAAAAQDsKDQAAAADaUWgAAAAA0C4kezRmzZplO8f7vk/d958WLFhQxFq2bGl7rF69evn8nkgZ+vXrZxrPnTtX27G3bt3qaF6NGjVs55w8eVLEtm/fLmJvv/227TqlRyM0HD9+XMSc3BP/6quv+ikjhIKNGzeKWEREhLbjW/V7OFm3Vq9DcBk6dKjtnEaNGonYHXfcofxp165dIpbe63OycOHCKhxwRQMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAgPBuBrdq8rbaTCzQG/rMnj3b0TzvXG+noZsN+1IG7w14DB999JFPx7JqjqxYsaJp/MADD4g5zZo1E7Hq1avbvt+5c+dErHjx4iJ26NAh2zX/3HPP2b4fUj6rDdOSk5NdyQXB4b333rNt/r6dz+QePXrcdPxfG922atXK9tgxMTE+54XAi4+PF7FRo0aJ2NmzZ03jmjVr+m1DXsOKFStEbPHixSLWrVs30zhnzpwqHHBFAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAACA0G0GHzlypGn8/vvvizm+NpRZNU473c3byY7iVnlZ7YTqPc/pv49V/uxomjJ8+umnto1oTr355psi9vLLLyt/2b17t4idOnXK0WtPnz7th4zgNqsHEnjHypcvH8CMkNJZfRYlJiYGNIf9+/cH9P3gfwcOHBCxhx9+2NFnVtOmTU3jtGnTijnr1q1zlMdvv/1mGi9cuFDMmTt3rqNjVapUSYUjrmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAABAazeBWO3z36tXL9nVWDdxWu4S2bNlS+YvTYxcqVEhbM7vVzuPe/x36898Z/2369Ok+Ndi2adNGxPr27asCac+ePSJ28eJFR6994okn/JARAslqN9tff/1VxNKlS+fqOgXsxMXFuZ0CNDtz5oyIHTp0yNFr582bd9NxIFidJ1uG6fc0rmgAAAAA0I5CAwAAAIB2FBoAAAAAQqNHo1WrVrZzZs6cmSLvb9uwYYOI9ezZU1s/hq//HVr9d5oSNlIKdU425+vYsaOIjR8/XgXatm3bTOOuXbs6el3evHlFLHv27NrygjtOnDjh6L7o6OjoWz5/A8DtKFGihIhNmzZNxF5//XXbz+VixYqJObGxsY7ymDJlyk0/Rw2VK1d2tAFv6tSpVTjiigYAAAAA7Sg0AAAAAGhHoQEAAABAOwoNAAAAAKHRDO6EG43fVg3c3hsB3c7GQC1atLDduNCq2dzqPZs3b247x/v94A6rpnydkpOTRezTTz8VsYEDB9pufpQ5c2YRW758uYhlyZLFh0wRjMqVK+d2CkghrD4j/X1+0ymYcg13qVKlcrRRrM7NY60ehuH9nezKlStizvDhw0UsXBu/rXBFAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAACA8GkGj4mJcRSrVq2a7bHmzJnjqKlt48aNt5TjzXKwavR20ojm9N87Je6aDmtWjdl79uwRsUyZMolYQkKC7fGvXbsmYmvWrPFpx+8BAwaI2L333mt7LAQfq4cIWMVWrVoVoIwA/3LyfQHhISkpScSefPJJEVu4cKFpPHPmTDGndu3amrMLLVzRAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAAAgNJrBrZppWrVqZduY7Wuz9u3wbuB+6aWXxJyePXsGMCOkJP369ROxvn37msZ79+4Vcz777DO/5lWwYEERGzVqlGkcGxsr5qRLl86veSHliIiIcBSz2qEX4SnYd9a2eggMwtPcuXNFbPny5bbfO6tUqeLXvEIRnyAAAAAAtKPQAAAAAKAdhQYAAACA0OjRsNpczvvez7i4OEc9Gk7uubTapMfqXtPmzZs7yhW4rnPnziJWvHhx07h3795iztatW316v6efftrRuq1cubKI5cqVy6f3RGjKmTOniGXJkkXELl68aBofPHhQzMmXL5/m7AD93OjzhPtmzJjh6LPUqm+xatWqfssrXHBFAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAACA0GgGtxITE3PTMRAs6tataxrHx8e7lgvwXx588EERGzlypIh1797dNG7UqJGYs2XLFs3ZAYAe48ePF7Hy5cuL2Oeffx6gjMILVzQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAAAjdZnAAgLusdstdsmSJaZyUlBTAjADg9nz33XdupxDWuKIBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2NIMDAP7TzJkz3U4BuKkePXqI2MaNG0WsWrVqAcoIwHVc0QAAAACgHYUGAAAAAO0oNAAAAABoR48GAAAIWjExMSKWmJjoSi4AzLiiAQAAAEA7Cg0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAALSj0AAAAACgHYUGAAAAAO0oNAAAAAC4s2FfUlKSSk5OVgkJCfozQFC6fPmyioiICMh7sf7g5vozsAZxI9Yf3MZnMIJl/TkqNAJ5QkVwMNZEoNYF6w9urr/r7wdcx/qD2/gMRrCsv4hko0wFAAAAAI3o0QAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQeuXbumpk+frpo0aaIqVKig6tatq95880119uxZt1NDGNm6datq166dKl++vKpevbrq16+fOn78uNtpIcwcOnRIVapUSW3atMntVBBGn8ETJ05U9erVU9HR0So2NlZNmTLF7bQQpl544QX14IMPup1G0KDQcGDChAlq6NChqnbt2mrMmDGqQ4cOav78+erFF1/0PFsa8Ldt27ap9u3bq4wZM6rRo0er3r17q/Xr16vnn3/e7dQQRg4ePOg5/505c8btVBBG3n77bTV8+HDPDyzjxo3z/OAyatQoTxwIJOO73/Lly91OI6g42kcj3H9J+eSTT1SrVq1Ur169PDHjZJc9e3bVo0cPzxdA4xcWwJ/effddVbp0aTV27FiVKtX//30gU6ZMatiwYWrfvn0qKirK7RQR4ufBefPmqXfeecftVBBmTpw44bl60aJFCzVkyJB/4/ny5VNdu3b1xIsVK+ZqjggPhw8f9nzm5s2b1+1UggpXNGwYt0c9+uijqnHjxqZ40aJFPX+NL3mAP508eVJt3rxZPfHEE/8WGYb69eur1atXU2TA73bt2qVee+011bRpU88vy0Cg7N27V129elXVqVPHFK9ataqnAF67dq1ruSG8DBw4UN1///0qJibG7VSCCoWGjSxZsngWV8WKFU3xb7/91vO3ePHiLmWGcPqSZ3yg5siRw3NVzegTMv7p27ev+ueff9xOD2HA+PXYuF2gf//+Kn369G6ngzBi3D1gOHDggCmemJjo+bt//35X8kJ4mT17ttq+fbsaNGiQ26kEHW6d8sHPP/+sxo8f7/mF5e6773Y7HYTBrQOGAQMGqAceeMBz+5TxK9/IkSM9V9SmTZumIiIi3E4TISxbtmxup4AwVaRIEc8PfUZPhnHLSrVq1TznPeMLX9q0adX58+fdThEh7u+//1ZvvfWW5x/jBz/cGgqNW/TTTz+pLl26qIIFC3oWHeBvSUlJnr9lypTx3B9qMC7dGlfbevbs6WkKr1GjhstZAoB/fPjhh+rVV1/1PO3HYJz7+vTp4yk+MmTI4HZ6CGHGA3+MH/lq1aqlGjRo4HY6QYlC4xZ888036uWXX1Z33XWX50lU1y/pAv5kPGnK4H2Pcs2aNT1/f/31VwoNACHrzjvv9FzJNW4VPXLkiCpUqJCnX83oG8qaNavb6SGETZ061XP78oIFC9SVK1c8setPGzXGxjq8sXcSEoWGQ8YzvI0n/1SpUsXziNvMmTO7nRLChFHYGi5fvmyKXz/pcc88gFC2aNEiz5OlSpUq5bmaYUhISPD0rhlP4wP8ZenSpZ4Hslj9mGfcZWBcZTO2OsB/o9BwYMaMGZ4nrTz88MOexzsa94UCgWJ8wBYoUMDzYdu2bdt/+zFWrFjh+WtsngYAocrYO8PohzT60q77/PPPPT/4GU+fAvzFeKTyuXPnTDHjx2ZjawNjXebOndu13IIFhYaNo0ePenoxjC96bdq08dymciPjEi7NQfAno7AwnjD10ksvefZuadmypfr9999VXFyc555RftEDEMqMDfqM26RKlCjheeKecRvzwoUL1eDBg7m7AH51fSsD74djGD84s4eaMxQaNox9Ci5evOh56oBRaHgzipDHH3/cldwQPho2bOj59cT4JaVz586e+5Jbt27tKTwAIJQZG+Yan8PGxn0ff/yx50lU7733ntjfCkDKE5F8vasFAAAAADShVR4AAACAdhQaAAAAALSj0AAAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADubNgXHx+vjO02IiMj9WeAoJSUlOTZsdrYpdXfWH9wc/0ZWIO4EesPbuMzGMGy/hwVGsYCY18/3CiQ64H1B2+BXg+sQdyI9Qe38RkMN93KenBUaFyvYqOjo33PCiElISEhYO/F+oOb68/AGsSNWH9wG5/BCJb1R48GAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAAGhHoQEAAABAuzT6DwkAgNS2bVvTOCEhQcz5+eefA5gRAMCfuKIBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2NIMDALTbsmWLiH311VemcY0aNQKYEQAg0LiiAQAAAEA7Cg0AAAAA2lFoAAAAANCOQgMAAACAdmHRDP7tt9+KWJMmTUQsb968IjZgwADTuHXr1mJO5syZfcrrypUrIvbjjz+KWHx8vIjdf//9pnHZsmV9ygHuSEpKErGLFy+K2HvvvWcaDxkyRMyJiIhw9J558uQxjZ955hkxp2PHjiJ21113OTo+wtcvv/wiYrGxsbZrcM6cOX7NCwCszJo1S8Ti4uJE7O+//zaNq1WrJuY0b95cxFq2bHnbOYYKrmgAAAAA0I5CAwAAAIB2FBoAAAAAtAuLHo3Ro0c7uh9+7969Ita3b1/TuG7dutp6NKw2tPLuvTBcu3ZNxAoXLmwa9+vXT8zp1KmTiKVOndqHTKHbRx99JGIvvfSS7eus+jGc9mgcOXLENH7rrbfEnJo1a4oYPRq4UWJioog99NBDInb06FERGzhwoGmcJUsWzdkhHNWpU0fEVq1aJWK1a9c2jVeuXOnXvJAy+i969+4t5uzbt8+nYzt9HT0a/4crGgAAAAC0o9AAAAAAoB2FBgAAAADtKDQAAAAAaBeSzeDz5883ja9evWq7cZShdOnSIlavXj3TuGjRokqXKlWqiNjUqVNF7KmnnhKxv/76yzTu2rWrmFOqVClHTXPwrzNnzojYyJEjVUr0zjvv2DZQGtKlSxegjOC2Xbt2mcY9evRw1PhttYlo//79NWeHUOfd1G21aalV47eTY1k9SMOqQdzqHIjAs2rE7tWrl4jNnj3b9lhRUVGONt7z3qBv//79Yk6LFi1s3y+ccUUDAAAAgHYUGgAAAAC0o9AAAAAAoB2FBgAAAADtQrIZ/JtvvjGNd+/eLeZcunRJxBo1aiRizz33nPIXq93JrZrNc+TIIWIHDx60Pf7PP/8sYjSDB96SJUsc7a6sU6FChUQsQ4YMN23yNaxevVrEduzYIWLly5e/7RwRHBYsWGAaL168WMzJmDGjiC1btkzE7rjjDs3ZIVhZNXCnhM8nJzuKw53G7/vvv9/RPO9G7xEjRgTNzt37LP594uLiRGzDhg2m8caNGx01vPv7u4cVrmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKBdSDaDDx8+/Ka7e1vtrG2YNGmSiMXGxtruHu6rsWPHOtrl0leHDh3Sdiz4rmbNmiK2aNEiEfvxxx9F7NtvvzWNa9WqJebExMSIWHR0tIh572jarl07MefkyZMililTJhFDaFq4cKGI9evXz7bxe/LkySKWJ08ezdkhWKXUxm8rVg/EQOD52vhtWL9+ve0cN+zzyt+qId2qqdtXBQoUUCkBVzQAAAAAaEehAQAAAEA7Cg0AAAAA2oVkj8bMmTNv2mfxX/fDp06d2vaeOp09GlY5OOV9T/TZs2fFnKefftrn40OfvHnziljDhg0dxQYOHOjTe547d07EnnzySdP4jz/+EHOmTp0qYsWLF/cpB6RsVpt+9unTR8SuXbtm2//z2GOPac4OwWzw4MGm8ZAhQ/z6fq+99pqjef7OA76bNWuWbT+GlebNm4tYSujJGDlypLYe3CiLfx/vf+8WLVo46t90A1c0AAAAAGhHoQEAAABAOwoNAAAAANpRaAAAAADQLiSbwbNmzWoad+7c2dHrtm7dKmIvvfSSabxjxw5Hx/r9999tm4OcNoO//vrrItagQQPTOFeuXI6OhfAwbNgwEVu3bp3tmilfvrxf80LKYXVe2blzp+2mT59//rlf80Lwb8ans+m6du3ato3f3nOsGtJv59/H6li+Hh/WvDevmzNnjpgze/ZsEYuLixMx79daNYz36NFDWxO51cZ7Vrk6eb8RI0Y4On4w4YoGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADahWQzuPcOiVZN3u+//76IXbx40af3O3TokO3O3YZx48b5dHyrpqhBgwb5dCwEt59++knE3nvvPRFbvHixiOXMmdO2Wa1UqVK3nSNSnn79+onYRx99JGJp0qSx3Z2+ZMmSmrNDsLBqlK5Tp462469cudJRo7eTHKxyRfDuFP5fMatm8I0bN9rOsYpZNYh7x6xe56Tx2+q7qdVnd0rY1Vw3rmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKBdSDaDp0plrp/69Okj5hw8eFDEJk2aJGIlSpSwfT+rXVCtGi29RUZGitiTTz4pYn379rU9FoLLF198IWLfffediC1btsw0Pnv2rJhz7tw5R+/5yCOPmMb58+d39DoEH+818fXXXzt6XceOHUWsS5cu2vLyfuCG1YMujh07JmJZs2YVsXbt2tk2skMvfzdYWzV+e7+nzuZzBBerHbKtYhs2bPBpR3GnMSesGr179uypwhFXNAAAAABoR6EBAAAAQDsKDQAAAADahcVNrTly5PB5U5SFCxeaxvfee6+Ys337dp/yeuGFF0Rs5MiRPh0LKUeDBg1M41OnTok5e/bsEbHjx4/bHjs5OVnEIiIiHOVVpEgR07hYsWKOXofgM3fuXNN4586dYk7ZsmVFrH///tpysNrItF69eqbxtm3bfD7+33//fdONBRF8nJ7LAt0nMnjwYFdygW9iYmJuOv6vzfms+j28N/9zshFfOPdjWOGKBgAAAADtKDQAAAAAaEehAQAAAEA7Cg0AAAAA2oVFM7iVq1evOprn3XzrtPHbavOoZ5991jTu0KGDo2MhuNbRmTNnTOMffvhB2/ulTZtWxNKlS2e7MZph+vTpthux3X333bedIwJr7969Ima1Sam3CRMmiFihQoV8ysFqQ8BXXnlFxG6n+dvbvn37tB0LuK5WrVpupwCXOGn8dvo6q/NTlMOHEIUarmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKBd2DaDf/bZZ349/pQpU0SsVatWfn1PBN6PP/4oYvHx8dp2u61fv75pPHToUDGnUqVKIta9e3cRGz16tGmckJAg5tAMHnzGjh1ruyt3bGysmFOxYkWf3u/LL78UsXbt2onYhQsXbI9VokQJEdu9e7ejhyDcc889tseH/3fNHjJkiOs5WFm1apVfj4/g1qtXL0fzqlWrZtvQPXv2bBG7//77RWz9+vW2xwpFXNEAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEC7kGwGP3XqlGk8btw4MadFixYiNmrUKBHLnj27ady6dWsxx+r4hQsXdpwvgpf3+jBky5bNND5y5IiYkyVLFhGzavSuXr26aXzfffc5yqtIkSK2c/78809Hx0LKFhcXZzunW7duIpYqlbPfmTZt2mQaP/HEE2JOUlKS8oVV43f58uVFbOLEiSLm9P8L0MeqUXrlypUiVqdOHW3v6X18qxx0vh/N4KFnw4YNjhq4rYwcOdI0LliwoKPXWR2/l1cD+qxZs1Q44IoGAAAAAO0oNAAAAABoR6EBAAAAQLuQ7NHwvqdz3rx5ju4pLlmypIgdOHDANJ45c6ajHL744gvbjV8Q/HLkyOGo18fbXXfd5WjjPSes1vLq1attXxcdHe3T+yH4rFu3zlHfQ/HixUVs0aJFWvoxrPo7BgwY4CiH9OnT+/ye8C+rnobk5GTbzfN09kKwOR9uZt++fY7mWX1Hi4mJsX1djx49HPVozPaKWfWOOHm/YMMVDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAtAv6ZvAXX3xRxCZPnmwanz59WgWaVQP62LFjA54H/OvOO+8UsebNm/vt/a5evSpigwYNErGvv/7atsm2YsWKmrODG5xsvDds2DC/5mC1iZ/Vudn7gQeRkZF+zQspQ0ptuq5Vq5bbKSAANm7c6GheVFSUT8e3auC22hR6tlczuNVmqzSDAwAAAIADFBoAAAAAtKPQAAAAAKAdhQYAAACA8G4Gv3jxooh9+eWXIpYtWzbbZvCXX35ZxHbu3Cli//vf/0zj/v37O3pd06ZNRQyh54cffrBtus6ePbu299u2bZuIvfvuu45emylTJtM4V65c2vKCe6x2gfd+GMVPP/3k6Ly1f/9+EcudO7dp3KdPHzGnd+/ejvMF3NgF3MrgwYO1HQspl9V5LaU0oIcDrmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAABDezeCpU6cWsejoaBErVqyYaTxu3DhHTeS//fabiG3ZssU0PnPmjKNcT506JWIrVqwwjevWrevoWEgZrHZ7f/rpp0VswYIFpnGNGjUcHd/7dYaVK1eaxtOnT3d0rAYNGoiY1S6kCH7VqlVzFPPWtWtXEbM6V8bGxprGNH7DTUOGDHE7BQSZ5s2b2+7SfTtGjhwpYvv27bN9XcGCBVU44IoGAAAAAO0oNAAAAABoR6EBAAAAILx7NCIjI0Vs6dKlIubknvjExEQRq1OnjoitWbPGNL527ZqDTK3vpS9btqxpTI9GcLH63/Sff/4RsTZt2pjG5cuXF3MOHz4sYvHx8SJ25coV0zg5OdnR/fgDBgwQsZIlS4oYcKNKlSqJ2HvvvedKLoDVpno6N+wD7DbZmzVrlmk8Z84cn/s9qnl9Vlv1doQirmgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAABDezeBOjRgxwjQeNmyYmLN582YR83eTmdWGgAgeFStWFDGrxrD9+/ffdHwrKleubBr369fP0eZ8d9xxh8/vifAwduxYt1MAAL9r2bKlow1srZrBW7Vq5dN7Wj2kZZZXY3m44IoGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADahWQzuHcTzoIFC8QcqwbdV155RcRWr15tGs+cOVPM2bVrl4iVKlVKxKpUqXKTrJHStW3bVsQmTJggYn/88YeWxm/DihUrTOOMGTP6dGwACEa1a9c2jYcMGeLzsV577TUNGSEUWDVmWzWNezeIR0VF2T6A6L+OFa64ogEAAABAOwoNAAAAANpRaAAAAADQjkIDAAAAgHYh2QzuRMGCBUVs0qRJPh2ratWqGjJCSpc/f34RY7d3AAhcM7hVQ7dVg7jVPO9jIXxZNXVv2LDBlVxCHVc0AAAAAGhHoQEAAABAOwoNAAAAANqFbY8GAAAILoMHD3YUA5AycEUDAAAAgHYUGgAAAAC0o9AAAAAAoB2FBgAAAADtKDQAAAAAaEehAQAAAEA7Cg0AAAAA2lFoAAAAAHBnw76kpCSVnJysEhIS9GeAoHT58mUVERERkPdi/cHN9WdgDeJGrD+4jc9gBMv6c1RoBPKEiuBgrIlArQvWH9xcf9ffD7iO9Qe38RmMYFl/EclGmQoAAAAAGtGjAQAAAEA7Cg0AAAAA2lFoAAAAANCOQgMAAACAdhQaAAAAALSj0HBo1qxZqlGjRqp8+fIqNjZWTZ061fNcaSAQrl27piZOnKjq16+vypYtqx555BH19ddfu50WwsjWrVtVu3btPOfA6tWrq379+qnjx4+7nRbC6PxXr149FR0d7fkMnjJlittpIczwPdA3jvbRCHezZ89WgwYN8nzI1q1bV/34449q6NCh6tKlS6pDhw5up4cw8MEHH3g+aLt16+b5oF29erXq06ePSpUqlWrcuLHb6SHEbdu2TbVv395TYIwePVodOXJEjRw5Uj3//PNqxowZbqeHEPf222+rSZMmqdatW3uKjcTERM85cf/+/erll192Oz2EAb4H+o59NBwwTm7GF7pp06b9G+vZs6fnF77vvvvO1dwQ+i5cuOD5gmesQ+NX5OuME56xO+fMmTNdzQ+h73//+5/nA9U4BxrnQsOyZcvUsGHDPL8sR0VFuZ0iQtSJEydUjRo11OOPP67eeOONf+MrV65UXbt2VQsXLlTFihVzNUeEPr4H+o4rGg4YH7C5cuUyxbJly6ZOnTrlWk4IH2nTplXTp09XOXPmNMUjIyPVmTNnXMsL4eHkyZNq8+bNnl+VrxcZBuM2PuMfwJ/27t2rrl69qurUqWOKV61a1XNL1dq1ayk04Hd8D/QdPRoOGLcMrFu3Ts2fP9/zxc44sc2dO1c9+uijbqeGMJA6dWpVqlQpz0nOuAB57NgxNX78ePX999+rJ5980u30EOJ27drl+UKXI0cO1atXL1WhQgXPP3379lX//POP2+khxGXPnt3z98CBA6a4cfuUwbh9CvA3vgf6jisaDhjNP8YvesYH63XGpdwBAwa4mhfCz6JFizxf9gy1a9f2NIUD/r51xWCc7x544AE1duxYz6/MRo/Gvn37PLcSREREuJ0mQlSRIkVUxYoV1ahRo1TevHlVtWrVPOvOuF/euNp7/vx5t1NEGOB7oO+4ouGAcR/okiVLPM23kydP9pzgjObI7t2788QBBJTxxCnjnnhjDW7ZskV17NiRNQi/SkpK8vwtU6aMpycjJiZGPfHEE2rw4MGeNbh+/Xq3U0SI+/DDD1WlSpXUCy+84Plr9Ay1atXKc+tKhgwZ3E4PYYDvgb7jioYN44PUuERmNKG1aNHCE6tSpYqn+bFTp05q1apV4t5RwF8KFSrk+ady5coqU6ZMnuZw4+kXxhjwh4wZM3r+ep/natas6fn766+/en7ZA/zlzjvv9FxJM27VM554ZpwDjX6h1157TWXNmtXt9BDi+B54e7iiYeP6faH33XefKW78qmLYvXu3K3khvG5dmTdvntizoHTp0p6/xgcv4C933XWX56/xhLMbXblyxfM3ffr0ruSF8LpldOfOnSpLliyqePHinlumduzY4ekdun4eBPyF74G3h0LDRtGiRT1/jV+NvStcA491hL9dvHjRc+Vizpw5pvj1W1ZKlizpUmYIB8YTfQoUKOD5snfjLQIrVqwwfdgC/jJu3DjPAzBu9Pnnn6vMmTN7nj4F+BPfA28Pt07ZMH4tadCggefRjqdPn1blypVTv//+u6cxzbhn2dg8CPCn/Pnzq2bNmqkxY8aoNGnSeNakccIzPnibN2/u+YUP8Bej0dtogHzppZdUjx49VMuWLT3nwLi4OM+5kV+U4W/GnkHGbVIlSpTwPPHsm2++8eyfYfQJGcUG4E98D7w9bNjngHHLgPGLivFYM+M2FeOL30MPPeTZFff6/cuAv9egsTO4cQvV33//rfLly+f5wvfMM8+Y9jYA/MXYIM0odo3H3Rr3xTdp0sRTeBi3sQD+ZuwMbjwI4+jRo54nURnnvsaNG7udFsIE3wN9R6EBAAAAQDt+CgUAAACgHYUGAAAAAO0oNAAAAABoR6EBAAAAQDsKDQAAAADaUWgAAAAA0I5CAwAAAIB2FBoAAAAAtKPQAAAAAKAdhQYAAAAA7Sg0AAAAACjd/h+bOAx5GpBC4AAAAABJRU5ErkJggg==",
      "text/plain": [
       "<Figure size 1000x1000 with 25 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(10, 10))\n",
    "for i in range(25):\n",
    "    plt.subplot(5, 5, i + 1)\n",
    "    plt.xticks([])\n",
    "    plt.yticks([])\n",
    "    plt.grid(False)\n",
    "    plt.imshow(X_train[i], cmap=plt.cm.binary)\n",
    "    plt.xlabel(y_train[i])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Les images sont en niveau de gris, donc de valeurs entre 0 et 255. Pour entraîner correctement un réseau de neurones, il est préférable que les inputs soit standardisés.\n",
    "\n",
    "**Consigne** : Standardiser les données en utilisant la classe [`StandardScaler`](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html). On commencera par applatir les images en utilisant la méthode [`reshape`](https://numpy.org/doc/stable/reference/generated/numpy.reshape.html), puis on applique le pré-processing et on termine par reformer la matrice."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "from sklearn.preprocessing import StandardScaler\n",
    "\n",
    "scaler = StandardScaler()\n",
    "X_train_flat = X_train.reshape(X_train.shape[0], -1).astype(np.float32)\n",
    "X_valid_flat = X_valid.reshape(X_valid.shape[0], -1).astype(np.float32)\n",
    "X_test_flat = X_test.reshape(X_test.shape[0], -1).astype(np.float32)\n",
    "\n",
    "X_train = scaler.fit_transform(X_train_flat).reshape(X_train.shape)\n",
    "X_valid = scaler.transform(X_valid_flat).reshape(X_valid.shape)\n",
    "X_test = scaler.transform(X_test_flat).reshape(X_test.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Modélisation du réseau de neurones\n",
    "\n",
    "Pour le moment, nous travaillons avec des images de tailles $28\\times28$, mais nous ne savons pas définir (pour le moment) de réseau de neurones capable de travailler directement avec une image. Nous allons utiliser une couche nommée [`Flatten`](https://keras.io/api/layers/reshaping_layers/flatten/) dont le but est *d'applatir* une matrice de dimension *(height, width, channel)* en un vecteur de taille *height $\\times$ width $\\times$ channel*. Dans le cadre des données MNIST, *channel*=1 puisque nous sommes en niveau de gris, et *height=width=28*. On aura un vecteur de 784 dimensions.\n",
    "\n",
    "Une fois que nous aurons décrit l'ensemble du réseau, nous devrons terminer le réseau par une couche avec dix neurones : un pour chaque classe. Pour s'assurer que l'on aura une estimation de probabilité d'appartenance à la classe, on utilisera la fonction softmax. Pour un vecteur $x = (x_0, x_1, \\ldots, x_n)$ on a:\n",
    "\n",
    "$$\\text{softmax}(x)_j = \\frac{e^{x_j}}{\\displaystyle \\sum_{i=0}^n e^{x_i}}$$\n",
    "\n",
    "On veut définir le réseau suivant:\n",
    "* **Couche cachée 1** : 256 neurones avec fonction d'activation ReLU\n",
    "* **Couche cachée 2** : 128 neurones avec fonction d'activation ReLU\n",
    "\n",
    "On peut définir de plusieurs manières un réseau de neurones. La première est de la même manière qu'une liste à laquelle on ajoute des couches en utilisation le template de modèle *Sequential* :"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.models.Sequential()\n",
    "model.add(keras.layers.Input(shape=[28, 28]))\n",
    "model.add(keras.layers.Flatten())\n",
    "model.add(keras.layers.Dense(256, activation=\"relu\"))\n",
    "model.add(keras.layers.Dense(128, activation=\"relu\"))\n",
    "model.add(keras.layers.Dense(10, activation=\"softmax\"))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "En début de réseau de neurones on doit définir la dimension de l'input: ici (28, 28). Le reste des dimensions pour l'ensemble des couches qui lui succède sont calculées automatiquement.\n",
    "\n",
    "La deuxième manière est directement sous le format d'une liste:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "model = keras.models.Sequential(\n",
    "    [\n",
    "        keras.layers.Input(shape=[28, 28]),\n",
    "        keras.layers.Flatten(),\n",
    "        keras.layers.Dense(256, activation=\"relu\"),\n",
    "        keras.layers.Dense(128, activation=\"relu\"),\n",
    "        keras.layers.Dense(10, activation=\"softmax\"),\n",
    "    ]\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne** : Calculer à la main le nombre de neurones du modèle, couche par couche. Puis utiliser la méthode [`summary`](https://keras.io/api/models/model/#summary-method) pour vérifier les calculs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "784\n",
      "256\n",
      "128\n",
      "10\n",
      "235146\n"
     ]
    },
    {
     "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",
       "│ 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\">784</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\">256</span>)            │       <span style=\"color: #00af00; text-decoration-color: #00af00\">200,960</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_4 (<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\">128</span>)            │        <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_5 (<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\">10</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</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",
       "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m784\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;34m256\u001b[0m)            │       \u001b[38;5;34m200,960\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_4 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │        \u001b[38;5;34m32,896\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_5 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)             │         \u001b[38;5;34m1,290\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\">235,146</span> (918.54 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m235,146\u001b[0m (918.54 KB)\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\">235,146</span> (918.54 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m235,146\u001b[0m (918.54 KB)\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\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "print(28 * 28)\n",
    "print(256)\n",
    "print(128)\n",
    "print(10)\n",
    "\n",
    "print(28 * 28 * 256 + 256 + 256 * 128 + 128 + 128 * 10 + 10)\n",
    "\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Nous avons décrit l'architecture du réseau de neurones. Il faut maintenant définir comment il va s'entraîner. Nous devons spécifier:\n",
    "\n",
    "* **Loss** : Quelle fonction de perte est à minimiser ?\n",
    "* **Optimizer** Quel schéma de descente de gradient est à utiliser ?\n",
    "* **Metrics** : Quelles métrique de performance souhaite-on observer pendant l'entraînement ?\n",
    "\n",
    "Puisque nous travaillons sur un problème de classification avec plusieurs classes, la fonction de perte [`sparse_categorical_crossentropy`](https://keras.io/api/losses/probabilistic_losses/#sparsecategoricalcrossentropy-class) est celle qu'il nous faut.\n",
    "\n",
    "Concernant l'*optimizer* il y a plusieurs possibilités que nous verrons dans une prochaine séance. Pour le moment nous travaillerons avec une descente de gradient stochastique par mini-batch [`SGD`](https://keras.io/api/optimizers/sgd/). Pour la définir, nous devons statuer sur:\n",
    "* **Learning rate** : pas de descente, on décide de choisir la valeur 0.001\n",
    "* **Batch size** : nombre d'observations à considérer pour chacune des passes. On décide de prendre 32 images par batch. Cette valeur sera à renseigner un peu plus tard.\n",
    "\n",
    "Pour les métriques, nous suivrons l'accuracy parce que la distribution des catégories à prédire n'est pas déséquilibrées."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.compile(\n",
    "    loss=\"sparse_categorical_crossentropy\",\n",
    "    optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n",
    "    metrics=[\"accuracy\"],\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Entraînement\n",
    "\n",
    "Le modèle est maintenant prêt à être entraîné, il nous reste à lui indiquer:\n",
    "* **Données** : jeu d'entraînement et jeu de validation\n",
    "* **Époques** : le nombre de passes à réaliser sur l'ensemble du dataset\n",
    "* **Batch size** : le nombre d'observations pour chaque batch, nous avions décidé juste avant que ce serait 32"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.6391 - loss: 1.2957 - val_accuracy: 0.8216 - val_loss: 0.7425\n",
      "Epoch 2/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 855us/step - accuracy: 0.8513 - loss: 0.5829 - val_accuracy: 0.8708 - val_loss: 0.4937\n",
      "Epoch 3/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 856us/step - accuracy: 0.8828 - loss: 0.4307 - val_accuracy: 0.8915 - val_loss: 0.4044\n",
      "Epoch 4/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 847us/step - accuracy: 0.8984 - loss: 0.3613 - val_accuracy: 0.9036 - val_loss: 0.3565\n",
      "Epoch 5/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 836us/step - accuracy: 0.9091 - loss: 0.3192 - val_accuracy: 0.9107 - val_loss: 0.3250\n"
     ]
    }
   ],
   "source": [
    "epochs = 5\n",
    "batch_size = 32\n",
    "\n",
    "history = model.fit(\n",
    "    X_train,\n",
    "    y_train,\n",
    "    epochs=epochs,\n",
    "    batch_size=batch_size,\n",
    "    validation_data=(X_valid, y_valid),\n",
    ")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Nous avons des informations disponible dans l'objet *history*, plus précisement dans *history.history*\n",
    "\n",
    "**Consigne** : Créer un [`DataFrame`](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html) à partir de *history.history* puis inspecter-le."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "   accuracy      loss  val_accuracy  val_loss\n",
      "0  0.639125  1.295723      0.821583  0.742507\n",
      "1  0.851313  0.582944      0.870750  0.493708\n",
      "2  0.882833  0.430686      0.891500  0.404362\n",
      "3  0.898396  0.361310      0.903583  0.356492\n",
      "4  0.909104  0.319176      0.910667  0.324995\n"
     ]
    }
   ],
   "source": [
    "history_df = pd.DataFrame(history.history)\n",
    "\n",
    "print(history_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne**: Définir une fonction `plot_learning_curves` qui prend en paramètre l'objet *history* et qui renvoie un graphique. Le graphique correspondra à deux graphiques côte à côte :\n",
    "1. Le premier montre l'évolution de la fonction de perte en fonction des époques\n",
    "2. Le second montre l'évolution de l'accuracy en fonction des époques\n",
    "Dans les deux cas, les valeurs de performance sur le dataset de validation doivent être en pointillé. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "def plot_learning_curves(history_df: pd.DataFrame) -> None:\n",
    "    plt.figure(figsize=(12, 4))\n",
    "\n",
    "    plt.subplot(1, 2, 1)\n",
    "    plt.plot(history_df[\"loss\"], label=\"Training Loss\")\n",
    "    plt.plot(history_df[\"val_loss\"], label=\"Validation Loss\")\n",
    "    plt.xlabel(\"Epochs\")\n",
    "    plt.ylabel(\"Loss\")\n",
    "    plt.legend()\n",
    "\n",
    "    plt.subplot(1, 2, 2)\n",
    "    plt.plot(history_df[\"accuracy\"], label=\"Accuracy\")\n",
    "    plt.plot(history_df[\"val_accuracy\"], label=\"Validation Accuracy\")\n",
    "    plt.xlabel(\"Epochs\")\n",
    "    plt.ylabel(\"Accuracy\")\n",
    "    plt.legend()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne** : Exploiter la fonction précédente pour observer les courbes d'apprentissage du l'entraînement précédent."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+0AAAF3CAYAAADQJaofAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQAArO1JREFUeJzs3QdY0+f2B/AvCXvvLYrg3ntva23drd122/Z23u7d3v67977de9j21jpbbW3de9dRcaCAbJC9V/J/zhuDgKiAwC8J38/z5EkIIZxETHJ+57zntTMajUYQERERERERkcXRaR0AEREREREREdWPSTsRERERERGRhWLSTkRERERERGShmLQTERERERERWSgm7UREREREREQWikk7ERERERERkYVi0k5ERERERERkoezRxu3evRuyVb2Dg4PWoRARESkVFRWws7NDv379tA7FJvC9noiIrPm9vs1X2uVNXE7NdV/l5eXNdn+tjfFri/Frz9ofA+O3nfib872Jmv/55N+qthi/thi/thh/23yvb/OVdvNR9169ep33fRUXFyMmJgbR0dFwdXWFtWH82mL82rP2x8D4bSf+ffv2NVtc1Lzv9YJ/q9pi/Npi/Npi/G3zvb7NV9qJiIiIiIiILBWTdiIiIiIiIiILxaSdiIiIiIiIyEIxaSciIiIiIiKyUEzaiYiIiIiIiCxUm58eT0RUV1lZGXQ6nVXGbT5n/JYbv0wy1+v1rRgZERERWTMm7UREJ/fKPHHihEq2UlJSrDJpNBgMsLe3Z/xWEL+3tzeCg4NhZ2fXavERERGRdWLSTkQEIC0tDYWFhQgKCoKnp6dKvqxNVVWVqvI6OTlZZSW3LcQvB4dkj9eMjAz1dUhISCtHSURERNbG+j6VEhG1QLKVm5uLgIAAuLq6wtnZ2WqTRsH4LTt+FxcXdS6Je2BgoFU+ViIiImo91td/SETUzCoqKmolU0QtTQ4O1fzbIyIiIjoTJu1ERCdxfTG1Fv6tERERUUOxPb4Z7T58AovWncC/w0qrqyhERERERERkuYyGKhhKClFVUgBDSQGqivNPXi5Ul03XFaCiKA9OHu2Abt1aNT4m7c1ox8EMHEwqxc+rjuG+q321DoeIiIiIiKhNMVZVmhLu4gJ1XlWSX31ZJd81v6cS8kIYSgsbfP+ObtlobUzam9GYvqH4a3sy1v6dguumlMDPi+tjiaj1PP7441i0aNFZb3Po0KEm3fe1116LsLAwvPzyyw26/fjx4zFr1izcfffdaAlJSUmYMGECvvnmGwwZMqRFfgcRERFpy1BZXjvhrlH1PnWdORmX6nghjGXFTf59RkdXVNm7oUznjBI4o6DKEbkVDsgqtUdWmT2KDE4oQjheQOti0t6MOkd4o32gIxIyyrFo7VHcPL2n1iERURvy2GOP4Y477qjecmzkyJEqkb/44ovP+77fe++9Rk05nz9/voqDiIiISLY8NVaUoSr/BPR5aShLqITBUF4n+TZVvU2V8JMJeEVpE3+jHXQu7tC7ekDn4gGjozvKdS4ohhMKq5xMiXiZPTKKdUgptENqPlSCbjjHyDcnRz36BbR+YZZJezMb2d0DCRlZ+GNLPC6f2Bkero5ah0REbYSHhwccHBxqbTkm18lWdufL29u7Ubf39eUSISIiIptNwMtLTraXn14Br1n1NtRYG26sLFc/7wkgpzG/0E5XnXzrXTygc/U0nauk3BMGB1cUGpyQW+6AbEnES/RIKzAiM68MmTklOJFQgrJy07asZ6PX2SHQyxkBPq7w93JBgI8L/L1dEOB96rLOWIGDBw+itTFpb2bRIc5oH+yOhLRCLNsYhysu6KJ1SER0Hm9KDXmRbwlyJLclJowvWLAAH374IcaMGYOFCxeq1vIPPvgAf/31Fz7++GMcOXJE7TfeqVMn3HfffRg1atRp7fHm+7j99tvVeWpqKjp37ownnngCAwYMOK09Xqr0O3fuxPDhw/Hdd98hJycHffr0wf/93/8hKipK3T47OxvPPvss1q9fD3t7e1x22WXYu3cvBg0a1OQW+9LSUnz00UdYunSp2hO9Y8eOqhPhwgsvVN+Xx/nmm2/i119/RVZWFsLDw3H99dfjqquuUt+X6yTGrVu3oqSkBN27d8f999+PwYMHN9O/BhERkbaMRgMMpcV11nrn17vu+9Ta8ELpW2/aL9Tbw2DvDEcPH9i7SfLteTIZd69OxqsTdFdPGB3dkFOqw4m8UpzILUFmbonpPO3keW4xCoqlHf7cLfHeHk6nknDvkwl5jcTc28NZJe5nU1zcxMd9npi0NzP5kD1jVCTe/Xkflqw/hhljouDsyKeZyBoT9kfe34CY+NYfNiK6dfDFK3eNbJHE/fjx4yqJlfXvktju379fJcaPPPKIWideWFiIN954Aw8//DDWrl0LR8fTO4YkUf/xxx/x2muvwc3NDc888wweffRRrFixot6Yd+zYodrlP/nkE7U3udy3JMSyJt1gMOC2225DZWUl3n//fbi7u+OVV15RPyNJe1NJgn3gwAEVW/v27VVy/u9//1v9jokTJ2LevHn4/fff8dZbbyEoKAirV69Wt5UDFgMHDlSXy8vL1YEGeQ7kAIAk/evWreMOIUREZJkT0EuL6km4ayfk5ono5go4jIYm/T47e8fq5Lpm0m2ugJsr4zWr4yWVBlWp7tatG1xcXJBXWF6dfEtCnpluSsZP5KYhMzcOOfmlMBjPHYuLk71KwKuT8VoJuSv8vJzh6NDwZX6WhtlkCxjaIxD/W+WKtKxi/Ln1OKaN6qh1SEREtUjy2a5dO3U5JiYGTz31FK6++urq71933XW45ZZbVLU5JCTktJ+XxFuSbnnTFTfeeCPuvPNOZGZmIjAw8LTbS0L+6quvwsvLS3195ZVXqoRfbNu2TVXVf/vtN/W7pL3/7bffVtX6pjp69ChWrlypEu2xY8eq6+TAhHxQkOskaZeDF5J8S4VdYp4zZ46qxkdGRqrby/elg0CeJ4lJOgmmTZvWqLX9bYUceJGDIT///DMKCgrUwZann366+m+srvj4eLz44ovYtWuX+jeYPXu2+puULguz77//Hl988YX6m+rZsyeefPJJ1e1ARNTWiggy2bwyNwMVuRkoyUyCS2Ic8o6vR355sakF3VwZLymSn2jS77FzdD6ZcHtC7+p+qgJeqy39ZBJ+MiHXOZx9dk1xaUV1ZfzE8WJk5mQhLasACSnZKP09C1n5ZaioPPcBA3u9Dv7ezir5VufSvl6nYu7m4gBbxqS9Bej1OlwyrhM+mL8HC9fG4qLhHdQfGxFZD6kWS6Xb1trjzTp06FB9WRJvSaalCn7s2DEkJCRUr9eSFvIzMbe2m9fOm5P5+vj7+1cn7Obbm28r1XD5niTLUvk3396cPDeFeUq+uV3fTJJJaYkX11xzjVoWIEsF5DkYMWIEpkyZAj8/P/X9u+66Cw899BD++OMPdT8y2G/q1KkcsFcPWWIhnQuyfCI4OFgdkJk7d65amlC3UyMvL08993KA5Ouvv1ZLD+SgUVpamkrkhSzdkIM8zz33nErU5W9TDgwtX76c8xKIyOYYKspQmZeJytx0VOSkozLPlKCbEvX006ahOwMoOcv96Zxcqyvg9Ve9T55XV8k9YGffuKRXku2MrCJTdVzWjZvb1s3nOcUoKj13K7l81PHxcK63Xd38tZebE3TnaFu3dUzaW8iEge0w74+D6o943e4kjB8YoXVIRNRIkjQ7O9nmy6RUjs2k0n3zzTerirQkp1JNlkRKKudnU1/bvFQEGnpbM6lcS6W2NUh85mquHLiQdn55/Bs3bsSaNWvw6aef4qWXXlLr8S+44AK1xl5OmzZtwpdffqmqyf/73/9UCz2ZyBICqYg/+OCD1V0NsuRA5iHI8ysHOmqShLy4uBjvvPNOdQL+/PPPq04PqbZL54N0Q0jnw/Tp09X3JZmX7gip5MtSCiIia2tbr8zPMiXlJ5NxlZhLgp6bjqqi3HPeh97NG/begbBz90NumQH+Ye3h7OVbJwk3tanb6c/vs4vBYERuYdnJ5NuUiEv7uvlrOZfvn+EtvxZ3F4daybiXqz3Ki7LRq3tHtAv2ga+nMxzsWdw8F9v8NGoBZM3EjNFR+Pq3A5i/KhZj+7dr80eIiMgyScIlA+lkYJzZt99+e9YkvDl17dpVtVRLlT80NFRdJ8PqpOLfVF26mIaAygC8cePGVV8v6+Sjo6PVZVlPL1V1qa5LlV3W2Us1d9myZeo6Wdc/Y8YMtWWenKQLQG4nyT2T9lOkK6OoqAjDhg2rvs7T01NVyLdv335a0i7/rlJlr1kxN7e9y7+PrHGU9vma9ycHWmTOgNwfk3YissgW9uJ8VRU3V8dVYm5O0vNPAIazd+7ZObrAwTtIJeYO3oGwr75sOje3ostBz9SYGLh369ak+SoSq1TApRJeqzJeIyHPyitBZdW53/8d7aVtvfbacfPX5kq5rDWvSeKPiSlFtw4+nA/TCEzaW9DFwztg/srDSEwvwPYDaRjS8/R1oUREWpN15NImLgmTtDbLtHSpgpqrqC1NDhjINHkZZCfVWkn4pIVdqv3nWiIga+HLyspqXSdD5SRpl2Rd1t3LfcggOlkzL+vcZb28eWL9f//7X9V1IAcO5KCBrO+X9fzSGbBv3z71nEjrtrTrywA6+bDRr1+/Fn0+rI20tYu6sw9kToD5e3Wvl0GIsvTCPB8gOTlZncsMhbPd3/lssyMfVOXfrznI32bNc2vD+LXF+K0zfoNscZaXiar8TNN59eUMtfe47EF+Vnp76D38ofcKgN4zQJ3b17hs5+xe73ueNJhXVlQBFcUNir+8ogpZ+aXIypNKuZyXqsnrcm6+XNqApX8SilTB/byc4OfprNaSyzA3f69T5x6uDmd9nzZWlaO4uPbniLb693Om96WGLoVk0t6CXJ0dcPGISPy88gh+XnUEg3sEt+gaVSKiprjnnntw4sQJ/Otf/1JfSyVa2pFlPbckrjXXrrcUqfJLgi0xSBItrdKSRMu+82fz+uuvn3adtLbL2mpJ/OUkA+Ty8/PVUDn5PdL2bl6zLuvqpTVbhp3Jfvay3Zu5kist3tIqL1vbSSeAVIfl90nFl04xf3CpuwRC1v7L+vW6LrroIrUGXp5bmfAvibT8G0g1Xf49znZ/dQ/QNIbctxyUaU7SEWDNGL+2GL+FxW+ogq4k7+QpF/riXHWuTnK54uxJmtSljc4eqHLxhkGdvGBwNV2ucvWG0cnDlAnXJLlzThmQk9TgJK+w1ICcwkrsTziAvOIq5BVVIb+4Up3L18VlDVtu5uqkg6erHl5ueni56uHpaq/OzV+7u+jrbH8mwcqguyKU5QHJp7+8t+2/nyY62/LBmpi0tzCZHL947VEcSsjB/mNZ6BXlr3VIRNRGmIex1XTJJZeoU00+Pj61WuPNJk2adFq7/JnuQ6rlNX/fqlWrqi/L1Pa6e63XvA+peMswOkmwpfoqSbucf/XVV6pqXh9Z91zf46tJ2u5k4ric6iNJohyYkFN95Hebq/J07vkI0pVRc1aCJNjS6l6XzBKQTg6ZLi8T4uXfSf4+YmNj1YDCmvdX05nur6HkAJB5acT5kgML8oFNHsv5xKQVxq8txq/hfuRFeSjOSETGsYPwdbKDrjgHlScr54bCbLnRWe9DquGmyrg/7L0Cq6vk6uTh3+hhbmeOVdaUlyMxoxBJGUVIqnHekOFuMsz2VHXcqVZ1XM7le3IbLVjr309LxC/vew3FpL2FyTTEiYMjsGxTPOavOsKknYionuT5vvvuw+WXX66q5DqdTiXscvR59OjRWodH52BuY5eW94iIU0NX5WvzbIG6ZDs/OcltvL291ZaA0h0hW8TVvL+aXR7y9ZkO4jSEdLo19/pJ+cBmzWsyGb+2GH/zk+3P1JryPPOa8pPD3tTXmTBWmXYtcZMDgWfYd7zmOnJ12SsI9j5Bap25TGVvTpKc5xSU4XhaPo6nF+B4mukkS2sLS+rfjUWK9VIJD/b3QJCv+6n15CfXkQec3P7M0rt7LfHvp7Xjb8y/EZP2VjBrbDR+35KAXQczcDQpF1Hh3lqHRERkMWQNu0wLl6q2TAeXpL1///5qUBy397J8Mg/A3d1dzUIwJ+2yHEG6J2QCfF0yJ0Aq7TKNX9apCxn+Jx+A5N9d7ku2+5P7Mw+jk6Refk6WTRBR22WoLD+VjNcd+paXAUOptG+fhZ0Oeg9flNq7wTOkPZz9w2ol6DKhvSWSXVU5V8l5ARLS85GYXmhK1NPOnJxLZ3qIvxsigj3RLsgDEXIK9oCvux6xRw6prUqtOemlxmHS3gqC/dwwqk8Y1u5Owi+rY/HwtVwPSURU09ChQ1WrtExol/Zo84AysnzSESHJuaz3l4MsYWFhap92GWooSyxkqYMsgTC3vstsAFna8Morr6ihf3JZ1rTLLAFJ2MVNN92EF154QQ0Q7NWrl9qnXf42Zs+erfXDJaKW3hqtIOuMiXlVYc4570Pv5nVq8rqXaQq7msbuEwR7Dz+UlJWr+RbtWiDprU7OzVVzdS5JegEKis+cnEuuIAm5JOjm5DwswF3tRlVXcw3UJOvCpL2VzJ7QSSXtG/ckI+Wirgj1N30wISIisoVhhlINl/kBklwPGjQIn3/+uVpHnpSUhAkTJqjBczLHQBJ76ayQdnjZDk4GAMpQwBtuuKH6/mSphAz/k+6L3Nxc9OzZU1Xm2XlBZCtbo9Xep1xdVtfJ1miVDdgazVQZNyXkNbZJ8wqEzvHUbI36lTfTmvOyWu3s5gT9XMm5qpqfTNDbnyU5J6qJSXsr6RDiiYHdgrAjJh0LVsfirsv6ah0SERFRs5DOiDMN9atvaKC0wf/vf/87633efPPN6kRE1sVQXlqjOn5yn/Ia1XJjRenZ70BnD3svfzhIZdwr6LQEXedS/9ZoLcGcnKuk/GSCbq6iF9TZyszMzlw5Nyfn6twTYYHucGJyTk3EpL0VzR7fSSXtK7cn4uoLu6q9D4mIiIiIrIWxqlJNXS9L2I/K0rzT2tilkn52dtB7+JxaS+4VaErQTw6A07v7wE7X+smtqa09H4lq3fmpJP2sybmvua3dlJxLFT08yIPJOTU7Ju2tqEdHP3SP9MWBuGy1DdyN03poHRIRERER0RlV5mehNPkQypIOoTT5MMrSjsGrqhJnW12uc3avNYXdVC03J+kB0Nk3bG/qlpBfVI649FIcz09EanZpdRVdrj9Xcl7d2s7knFoZk3YNqu3Pfr4VyzfH4bIJneDuqt2LFhERERGRmbGyAmXpcShNOoSy5EMoTTqMqoKs028nLezegXD0Ca5OyGsm6Dpn2VRNW3nmNecn15ofPy05P3Fach7k64qIIM/q6rmqnAe6w9mRKRNpi3+BrUzWtcv69vjUfLV3++UTO2sdEhERERG12Sr64eoEvTztWPVe5tXsdHAMbA/n8C5wCusMo18EjqRkoVv37hax5ZhKzqvb2U9up5aej7zCM1fOvd30iAzzQWSot2liezCTc7Js/MtsZTI449LxnfDG9zuxZP1RTB/dkS8QRNQsZPq27I+9YMGCer8vk723b9+OP/7446z3895772HhwoVYtWqV+rpLly7Vk7/r8+ijjyI5ORnffvttg+KsqKhQ27uZp4Wbf9+ff/6JlnLttdeqrchkYjkRUVskyXhZWhzKkg+rSrok61X5tavNQufqCeewznAK6wLn8M5wComuNZFdbTmWmq1Zcl57KNyZk3OhKufVw+Dk3BO+HnrEHT3Mfc7JqlhUtvjxxx9jw4YNZ/3gd+TIEbX/6549e6DT6dS2MvKBMTQ0FNZiVJ9QfLc8BunZxVi57TimjOyodUhEZAMkqZbXw2PHjqFTp061vldWVobff/9d7YXdWPK6LHtsN5dff/1VHQQwJ+2yJ/c111zTbPdPRERAZUH2ybXoh9V5eepZquiSpId3hnNYF9j7BLfadPb6SPu6uZ1dhsKZq+gyxf1sybm0sssWaubkXFXOnU5PdbjPOVkji0napeoi+7EOHDjwjLfJycnBjTfeqLaKkcS+vLxcVU3mzp2rqjROTk6wBnq9DpeMi8aHv+zFgjWxuHBYB9jrdVqHRURWbtKkSXj++edVUnzffffV+t5ff/2FkpISzJw5s9H3K/toN/cWOjW5ubmpU1VVVbP+HiKitlVFjze1uUu7e9IhVNZXRXfxOJmgdzGdh0oV3UWz5NxUNc8/tfY8vUBNcT+TQLXmvEblXNadB3rUm5wT2RLN/8LT09Pxn//8B1u3bkWHDh3Oelv50ClHx1599VU4O5vadKTqPnbsWOzatQvDhg2DtZgwKAI//HEIGTklWP93MsYNaKd1SERUT3JprDjzh4eWZOfg1OhKh7wuTp48Gb/99ttpSbsc2BwzZoxKwA8fPow33nhDvW5KIh8UFKQq3VLxrk/N9nh5Tj788EP8+OOPqhX/oosuUlX8mnbs2IF3330X+/fvVwdX27Vrh3/961+YMWOGat1/7LHHqu/3m2++wbZt22q1x6empqqDuJs3b0ZRUREGDBig9v/u2rWr+r50EwgfHx8sWrRIvS8MHToUzz77rHosTbVmzRp88MEHqqNLDiJMmTJFPY/m95u1a9finXfewdGjR1VLpTyf8li8vLzU97/44gv1vMj7WmBgIC699FLccccdmlasiMg2VRbknEzQa6xFryw/vYoeEFFdQZdWd3ufkFZ/TZIt08zrzavXnp8rOfdxMa01P5mcSxVdTi5MzqmN0vwv/59//oGDgwOWLFmC//73v2pd5JlIUi4fqMwfoIS0yAv58GhNZIsIWc/+zbIYzF91BGP6hUOn4wc7IkshyWnKN0+oaoUWnMK7IvS65xv94UoS4/nz52P37t3o16+fui4zMxObNm1Sr7GSpEtyPmLECJVg6vV6/Pzzz3jllVfUa6ys8TubTz75BJ999plKkLt3746ffvpJJeKDBw9W35eE9eabb8acOXPw3HPPqfXrn376KZ544gn1Oy+++GIUFBTgxRdfVG33kvBK0m4mSbocQIiIiFAHBxwdHdWad7m/xYsXq3XpQroJpk2bhu+++w5ZWVm4//77VaIvBxeaQg4Y3HPPPbj77rvVcyFLDJ555hkkJiaq953s7Gzcdddd6oCBHChOS0vDww8/rA4iv/DCC2r9vzw30v3VuXNn7Nu3T30/PDxc/ZsQEZ3Pvujl6fGqgl6adFCtSa/MyzztdjoXd5Wcy7A4NTRO1qI7ubR+cl6jei6V9JxzJOembdRqJ+hMzolq0/x/xPjx49WpIeTDj5xqkg9JksTL2vbz+XDeHOtb5MNwzfNzGdcvCD+vPKJe1DbuOY4BXZq3BbWl47c0jF9b1hy/VIoNBoN6LZAkWc61b9U2xdCYpF3i7tGjh0oa5UBo79691fVSjfbz81NJc15enhrKdtVVV6lqsrjzzjtVIn7w4EH1s+bnouZzINdVVlaqpUny81JhF5KYbtmypfr28loq9ycHBsyxyxImiUEq1LIEyvx7fX19q+9bdTUYjVi2bBlyc3PVgQfz9yUxvvDCC1WC/uCDD6rbyRp76dKSg77SpSXxrFu37oz/bub7P9P3ZabKxIkTq9f8y0GDp556SiXxhw4dUgcfpGsgODi4+iQHQeT+5JSQkKAOMMh8lZCQEHXu7++vLtf3O+U6edzy/0XO64uXFXqitqmyMLdWm3tZ6tEzVNHbnRoWF9YFDr6tU0UvLq1AQkYZkgqTkJ5TVp2gny05D5DKeXVy7q7OZc25q7NDi8dLZAs0T9rPh3x4lA9xMhHZ/OGuKeTDWExMTLPFFR8f3+Db9o9ywcYDBfjh9wNwqQqwiA9pjYnfEjF+bVlr/Pb29iopk9kY5nZvr0sfB+p+UGq1gBxPaztvKKlAS6v2vffeqx6XJMzS6i2vddLWPWvWLHWdJKNSSZZ2eVFaWqpOkpxL0iiXzeRnpbosVXtpa6/5vV69eqnKtFwnbeFSTf/yyy8RGxtb7/3LfZm/FubfJ49XfkYSZomz5u+QgxFyUEGuk4RXKu7mhFnIwVv596v5MzVJYiy3PdP3pSVeZgLU/L75oId0hMlBA1l6IO3ukoxLO/6oUaMwbtw49TMXXHCBOtAgMwM6duyIIUOGqIMA8t5U3++UxyqPW563M5GDAETUBqroGQkn90U3DYyrzM2ot4ruFGqqoJvWondq9Sr65n2paknn3tgTMBhkNklmvcm5qpxXD4Vjck7UZpN2+XAn6wqldfL2229XVZ/zIZWa6Ojo845LKiaSsEjVx8WlYS+kIeFl2HZ4AxJPlMPONQTdOvhAK02J35Iwfm1Zc/ySQKWkpFQnSZK4nzqAZj2PxZz4SlIua8p37typ1rBLhVtazCWxlaRbquxSeZeEc/To0ejZs6fqeJLXQrmNJPry+GsuRZLvmf9dpaW+5vfk+ZKlSnKdJN3Syi5J9vDhw1WyK4nrFVdcoZ5fuY3clzDfh/n3yf2YK8w171+Yvy/Xm39/zdvIfdS8z7okvrpx133uzI/fzJxsywEEuf7NN99Ulff169er5QZywFgGo8oBCqmoy7p82VJPThs3bsQPP/ygWuol0a+PxCwHKOoboirPIxHZnqqiPJQe2wuXQ1uRte8XVKbHnV5Fhx0cAtqdStDDpYoe2uqFncKSCmzdb0rU/z6ciSqVqJt4uurRMcwbHWSf8xpt7UzOiVqG1SXtUqGRwT+ynlHOzVsGnQ95EWzOfRrlg21D709uN3FQBJZvjsevmxIxoLtpvaaWGhO/JWL82rLG+CWhk5P5A5GcS4JnbcxVZ0mSJQmX/dilKizLh6T6K5YvX65a5FesWFGdPEvFvebjNj8XNZ8DuU4SfUlO//77b5WM151NYl4fL7/zq6++qv6+eb93832a79d8bv59cpKt6uT1XVrk5fcJORAhQ+2kii0/Y75t3fjO9u9W38/UJN0DMgdAdigxk6+FxCS/Xwb8Pf744+ogr9xOliDIgDyJVZJ0eV5lWJ9U4aXLQZJ6eb4l0a/L/DzL/5f6DiRYQtcVEZ0fo6EK5ekJpm3XTu6NXpmbrr4n/+vNm6/pnN1OVtFP7o0uE92dTcuIWpu0vm/9Jw0b/k7BrkMZqKw6tXwnMtQTI/uEYWAXX+RkJHCfc6JWZHVJu6yflIFBMvlY2j1twayx0fhjSzx2xKQjLiUPkaGmScRERE01e/Zstf7b09OzVtIoa7GlK0L2bJep7NKebR7eJu3l53LLLbeoQW1yEEDWp8twuL1796r7Mt+/tNHLpHVJbiWhl23oat6/+UOeJMJ1u5ykBV0q15L0SkIs1XlZOy5r5aVafz5kSJ6se69Lug1k3f2///1vNXRO1sdL14gM0pNuhKioKNWtMG/ePHVw4vLLL1cHEmT9vXSWyBR7+Vp2M5F4ZaBfRkaGqrifbRtTIrLBKrqsQz850b0sNbaeHUjsYO8XiiKXAAR0GwjPjr3g4CdVdO22/i0pq8T2A2nYsCdFfRatqDyVqEsFXRL1kX1CVSVdyOtxzukd/ETUVpN2qRrJxF4ZOCSVCJlQLB+SJHGXScXS5mlmvo01CvF3Uy+I6/5OVpPkH5rDD3lEdH5GjhypkmOpAtesiktSLIm0TDkvLCxUa8Mvu+wyrFy5Uk08l9b5s5HJ7rI+XJYnnThxQq3rlgMEcXFx6vvXXXedOhAgr9OSpEtSK5PdpV1f7l8SZKlE9+nTB1deeaVKdGuS1/Kvv/5aXW/upJIDAtJqLlvHnQ9paZdTXdJpIM+RtL/L45LEXboVpk6dqibKC0ncZYnB+++/r5J3qZLL45DJ+HJZnsOcnBz1tRykkKn4cp9y4ISIbLSKrtain0zSZaJ7Ttppt9M5uZqmuctUd9l6LbQTSg12yIyJgWu3bnDUqFJdWl6JnTEZqvV9e0w6yitODcwMC3DDyL5hGNU3DO2DPTWJj4hqszPKQj4LIVvpyJZvMmBOJCUlYcKECdX7A8s0YmlBrI/5No0lHyLNg5TOlxx5lIF2TWkXkgr7PW+sgez69vFjExHs1/ptUecTvyVg/Nqy5vhl7bIknbK+WJjXTVsb86A1xm/58Zv/5iIjI+s94Nyc703U/M+nNb/eCcbfeFXF+bWGxZWlHIWx4vQhkw7+4acSdJno7h92WhVdq+dfEvOdBzOw4e9kbDuQhtLyU4l6iJ8k6qEqUe8Q4nnWJTr8+9EW47ed+Bvz3mRRlXap/NQk27uZ11oKmYZsq6QlfkDXQPViumB1LO6Y3UfrkIiIiIjaaBX9eHUFXa1FP2MVvZNpHboMjAvrDL1Ga9HPpKKyCrsPZ6qK+tb9aaoV3izQ1xWj+oSqbs+ocC/O0iCyYBaVtLd1s8d3Ukn7X9uP46pJXeDjaZ3t/kRERETWQlXRT+6Jrs5TYs9SRT85LC68s/pay7XoZyLD4/YcMSXqW/aloqj0VKLu7+Vc3freqZ03E3UiK8Gk3YL06OiHbh18EROfjSXrj+H6Kd21DomIiIjItqromYmnEvTkQ6jITj3tdnZOrmr9uVqPHt5F7Yuud3GHpaqqMqj902WY3OZ9KSgoNs+mB3w9nTCiTxhG9QlDl/Y+0MlaTCKyKkzaLYgc7ZRq+3NfbMWyTXHqspsL97skIiIiaoqq4oLqdeimKvoRGMvrqaL7hVVX0KvXousse7aG7Jv+z7ETWP93CjbtTUF+0akdQLzdnTC8d4iqqHeP9GOiTmTlmLRbmIHdgtT2GsfTClTiftmEzlqHRERERGQ9VXSVpJ+somelnHY7O0cXOKu16CenuodJFd20nZmlMxiMqiNTWt837k1BbsGpLeU8XB2rE/WeUf7QM1EnshlM2i2MHAmVCvub83apFvnpo6Pg5GDZR3qJbIVspsH1fdQaLGjjFiKrZSgtQnHKQdM0d5WoSxW95LTbyT7o5mFx0uqu1qJbeBW9bqJ++HiOStSl/T07/1SngLuLA4b1ClHr1HtH+8Neb3lr7Ino/DFpt0ByhPS75THIyCnByu3HcfHwSK1DIrJpDg6mZSglJSVWuf0IwSq3jKn5t0dEDVN+Igl5mxbB89heZPyeddr37RydT65FN7W6O4V2ht7VOqrodQ/sHUnMrU7UT+SeOhjh5myPIT1NFfU+nQLgYM9EncjWMWm3QHKUdNbYaHy8cJ/a/u3CIe2h55FTohYje2p7e3sjMzNTncuHJXt7e6vcJ7yszNQqaa37nNt6/PK3JQl7RkaG+luzxsdJpIWKvAzkrPsfCvetlT54mP/nOPiGVu+JLu3ujgHtrKqKXvf14WhyntpHXRL19GzTwT3h4qTHkB6mRL1fF0nUrfMxElHTWN+n0jZi4uAI/PjnIfWCvX5PCsb2D9c6JCKbFhwcjIqKCqSnpyMnJwc6nfUdKDMYDKisrFQHHBi/ZccvCbv8zRHR2VUV5SFn43zk71oBVJm2LnOKGoAsr47oOHgc3P2CYM0kUY9Pza+uqKeeKKr+npOjHoO7B2NU31D07xrE5ZJEbRiTdgvl7GiPaaM64rvlB/HLqiMY0y+Ma22JWpD8//L391fV9tDQULi4uMDaSHv/sWPHEBERwfgtOH5piWeFnejc69Vzty5B3tZfq/dMd27fE77jroHBJxxpMTHQWcnwuPpk5FVg38qj2HogA0kZhdXXO9rrMLB7kKqoy3Bi+TxIRMRXAgs2ZXikStjlCOzOgxnqxZuIWp6TkxOcnZ1hjZVewfi1Ye3xE1kCQ0UZ8nf+jtxNC2AoMSWzTiFR8Bl7DVwie6sDrOaZENYmObNQVdTX7UpCYo1EXdakD+gaiJF9wjC4RzBcnPjxnIhq46uCBXN3dcRFwyKxYE0sfl55mEk7ERER2SRjVSUK9qxCzoafUVWQXb13us/Yq+DWZajVdhtKu/uGPckqWY9Lya++XlbQ9O3kjzH9IzC0ZzBcnTmUkojOjEm7hZs+uqPa+u1AXDb+OZaFHh39tA6JiIiIqFkYjQYUHdiEnHU/oiI7VV1n7+kPn9FXwL3XGKscKifziDaeTNRjk/Kqr5d90/t0DsDgbv7w0ueif58e3LGEiBqESbuF8/NywYRB7fDHlgT8svoIk3YiIiKyejKAreToLmSv+QHl6XHqOp2rJ3xGXArP/hfCzt66Ks+ZOSXYuDcZG/5OwaHjOdXX6+yA3tEBah912U/d081RtffHxJyquhMRnQuTditwybho/Lk1AdsPpKv17R1CPLUOiYiIiKhJShNjkL36e3Uu7Jxc4T1kOrwGT4XOyXqGUGblSaKeohL1mHhTS7+QTv6eHf3V1PdhvULh7eGkaZxEZP2YtFuBUH93DO8dqrYCkcF0D1wzQOuQiIiIiBqlLD0eOWvmoTh2p/razt4RngMnw3vYJdC7Wsck+JyCUmzam6pa3w/EZcFoPPW97pG+aur7iN6h8PHkMEoiaj5M2q3E7PGdVNK+7u9kXDO5K4L93LQOiYiIiOicZK169rofUfTPBtMVdjp49BkPn1GXw97T8pf95RWWYfM+U6K+/+gJGGok6l3b+6jW95F9QtWSRiKilsCk3UpEhXujf5dA7DqUgYVrYnH7pX20DomIiIjojCoLspGz/mcU7FkJGKrUdW7dR8Bn9JVw9AuFJSsoLleJ+oa/k7En9gQMNTL1Tu28qyvqgb4cJEdELY9Ju5VV2yVp/2vbcVw5qQt8PNh6RURERJalqqQAuZsWIn/Hchgry9V1LlH94Dv2ajgFd4SlKiqpwJb9qaqzcfehDFTVSNQ7hnmpRF0q6ux2JKLWxqTdivSM8kOX9j44lJCDpeuP4bqLu2sdEhEREZFiKC9B3rbfkLtlMYxlxeo6p/Cu8B13DVwiLPMzS3FpBbb9k6YS9Z0HM1BZZaj+ngz+Hdk3FCP7hCEswF3TOImobWPSbkXs7OxUtf2FL7dh2cY4ddnV2bq2RCEiIiLbYqysQP7uP5G7cT6qikz7kjsGtofv2GvgEt1ffX6xJKVllWpHnvV7krEjJh0VlacS9XZB7hjVJ0ytU28XZB3D8YjI9jFptzKDuwerN5HE9AIs3xSPS8d30jokIiIiaoOMhioU7l+HnHU/oTIvU11n7xMM3zFXqrXrdnY6WIrS8kpVSZdhcpKwl1eY1tiLUH831foup4hgD4s7yEBExKTdyuh0Um2Pxls/7MbidUcxbVRHODrotQ6LiIiI2gij0YjiQ9uQvXYeKk4kqev07j5qGrxMhbfTW8bHS0nMZRaQJOrSAl9afipRD/ZzVW3vkqhHhnoyUScii2YZr6rUKKP7hePb5QdxIrcEK3ck4qJhHbQOiYiIiNqAkri9yF4zD2UpR9TXOmd3eA+fBc+BF0Hn4KR1eKrVfffhDDX1fes/aSguraz+XqCPi0rUZZ16dLg3E3UishpM2q2QvV6HWWOj8Omi/Viw+ggmDY6AXm85LWhERNS2GAwGvP/++/j5559RUFCAQYMG4emnn0a7du3qvX1WVhZefPFFbNy4UVVthw8fjkcffRRBQUHVt5k0aRISEhJq/dysWbPw8ssvt/jjodOVpsQiZ/V3KInfp762c3CC1+Cp8Bo6A3pnbaepy/C4PUcyseHvFGzen6qmwJv5eTlXJ+pdInyYqBORVWLSbqUmDWmPn/48jLSsYmzam4pR/cK0DomIiNqoDz74APPmzVMJdXBwMF577TXMnTsXS5cuhaOj42m3v/fee1FZWYkvv/xSJe3/93//hzvvvBPz589X3y8uLkZiYiI+/vhj9OjRo/rnnJ251WlrK89MRPbaH1B8aKvpCp09PPtPgveIS2Hv7q1ZXLId296jWdgecxib96WgoPhUou7j4YQRfUJV63vX9r5qaSERkTVj0m6lnB3t1Xr2738/iJ9XHVZHkHn0mIiIWlt5eTm++OILPPjggxg7dqy67q233sKoUaOwYsUKTJ06tdbt8/PzsW3bNnz44Yfo1q2buu7WW2/FHXfcgdzcXHh7eyM2NlZV7/v16wcvLy9NHldbV5GXgZx1/0PhvrUycU5q63DvPQY+o66Ag3egdnFVVuGb5YewemcqisuSq6/3cnfE8N6mRL17pB/0TNSJyIYwabdiU0ZEqvb4uJR8NWhlQNdTbYVERESt4eDBgygqKsKwYcOqr/P09ET37t2xffv205J2qZa7ublh0aJFGDx4sLpu8eLFiIyMVD8nDh06BH9/fybsGpAt23I2zkf+rhVAlWk9uGvnwfAdexUcAyK0Dg+L1h7Fb5uOq8serg6mRL1PGHpG+XGpIBHZLCbtVszD1REXDu2g3sB+XnmESTsREbW6tLQ0dR4SElLr+sDAwOrv1STt8tJGL2veBw4cqLrE5LbfffcddDpdddLu6uqKe+65B7t27YKPjw8uvfRSXHfdddW3adLE8+JiNIeSkpJa59amvvgNZcUo2rkMxbt+h7GiTF3n2K473EdcBseQaEj6XtlMz9/5rF1fuv6YunxBXy9ccWEPeLib1tOXlZXCWtji3481YfzaYvy135ca2inNpN3KzRwThV83HMM/x7IQE5eNbpG+WodERERtiPmDS921605OTsjLy6v3Q0pMTIxqfZd171VVVaqdXtrjf/jhB7i7u+PIkSOqjf7CCy9Ua9137typ1snL/f373/9uUpwVFRXq9zan+Ph4WDMVf1UFnI7vhPOxzdBVmP4tKz1DUNJ5LCr9I5GeWwHkNu/z1lR744uRU1AGd2cdhnRxR1KiqeJurWzi78eKMX5tMX6T+ua+1IdJu5Xz83LBuAHt8Oe24/hl9RE8GTlE65CIiKgNMQ+Hk7XtNQfFlZWVwcXF5bTbL1++XFXVV69erRJ08dFHH2HcuHFqEN0NN9yATz/9VP28h4eH+n6XLl1QWFio1sHffffdTaq2Ozg4IDo6Gs11oEI+sHXo0KHex2jpVPzHjiKkNAnlO5fBUJSjrtf7hsJj+Gw4RZs6ICyJHOz5Zu02dfmCweGw1xus+/m39r8fxq8Zxm878cv8loZi0m4DLh3fCX9tP672I01IzUf7ENOaQCIiopZmbovPyMhARMSpNc/ytSTbde3YsUOtXzcn7ELWrst15i3epPJQt/rQuXNn1d4u1XZpl28sSUKl5b45yQe25r7PlmY0GlBycDM8N/yA0mJTsm7v6Q+f0VfAvdcY2On0sEQH4rJwLDkfDvY6XDw8EsnHj1rl818T49cW49cW40ejDo5yYocNCAtwx/BeoeqyVNuJiIhaS9euXVUCvnXr1loT4g8cOKD2a69LtoST5Fwq6WaSjCclJanKhVRUJ06cqPZ9r2nfvn0ICAhoUsJOJ9f0x+5E8mcPIW/5B9AX50Dn4gG/STeh3e3vw6PPeItN2MWSdaa17GP7h8PTrWHtpEREtoJJu42YPb6TOl+7OxkZ2doOiiEiorZDKuJz5szB66+/jpUrV6pp8vfdd59KzidNmqTWrGdmZqK01DQobObMmdV7tctt5XT//ferNfCXXHKJqjxccMEF+Pzzz7Fs2TIcP34cP/30Ez777DM1mI4arzQxBqnfPoW0n15EeUY87BxdUBI9Gv43vQGvQVNgZ+8ASyafa2QvdjFjdJTW4RARtTq2x9uI6Hbe6Ns5AH8fzsTCNbG47ZLeWodERERthCTTlZWVePLJJ1VyLhV2SbplHblU0CdMmICXXnpJJeUyKX7evHlqsNz111+v1qfLFHm5zryG/YEHHlDV+zfffFNNoA8PD8cTTzyByy+/XOuHalXK0uKQvWYeSo7uUl/b2TvCc+BkOPWdjEPxSdA5Wsd60qUbjsFgBPp2ClBLAJtrFwAiImvBpN3Gqu2StK/YmoArLugCbw8nrUMiIqI2QK/X46GHHlKnuiThli3caoqKilLD587E3t5eTY2XEzVeRXYqstf+gKIDG01X2Ong0XcCfEZeBntPP6tKeotLK/DnVtOsg+mjO2odDhGRJpi025De0f7o1M4bRxJz1TZwcy7qpnVIRERE1Eoq87OQs2E+Cv7+CzAa1HVu3UfAd8yVcPA1zb6xNiu3J6KotBJhAW4Y0DVI63CIiDTBpN2GyDrAyyZ0wotfbcevG+NwybhouDpb9jo1IiIiOj9VxQXI3bwQ+TuWw1hZrq5zieoH37FXwynYeqvTBoMRS9ebBtBNGxUFnc6ytqEjImotTNptzJAeIWqafHJmIX7fnKASdyIiIrI9hvIS5G37DblbFsNYZmp5dwrvCt9x18Alojus3Y6YdKRmFcHNxQETBrbTOhwiIs0wabcxchR69vhovPPT31i8LhbTRkXCwd5yt3AhIiKixjFWViB/9wrkbvwFVUV56jrHwPbwHXsNXKL7N2rvX0u2eN1RdT55aHs4O/EjKxG1XXwFtEFj+rfD978fxIm8UqzakYgLh3bQOiQiIiI6T0ZDFQr3rUXO+v+hMi9TXWfvE6zWrMvadTs729nJNy4lD3tjT6hixJQR1tviT0TUHJi02yAHex1mjo3GZ4v345fVsZg4uD30XAdGRERklYxGI4oPbVUT4StOJKnr9O6+8Bl1GTz6jIed3vY+zpmr7CN6hyLAxzq2piMiaim29ypPyqQh7fHTn4eQeqIIm/elYGSfMK1DIiIiokYqiduL7NXfoyw1Vn2tc3aH9/BZ8Bx4EXQOtrm1a05BKdbuSlaXuc0bERGTdpvl4mSPaSM7Yt6KQ/h55RF1pNpW1rgRERHZutLkI8hZ8z1K4vepr+0cnOE1eCq8h06HztkNtmz5pnhUVhnQpb0Purb31TocIiLNMWm3YVNGdsSCNbE4lpyH3Ycz0b9LoNYhERER0VmUZyaqNnhph1d09vDsPwneIy6Fvbs3bF15RZVK2sWMUVFah0NEZBGYtNswTzdHNYRO1oX9suoIk3YiIiILVZGbgZz1P6Fw3zqZOAfY6eDeazR8Rl0BB++28/69bncycgvL4O/tguG9Q7QOh4jIIlhU0v7xxx9jw4YN+Pbbb894m5ycHDz//PNYt26daveeMmUKHn74Ybi4cEhJfWaOicJvG4+pCayHErLRhW1mREREFqOyMFdt3Za/awVgqFTXuXYZAt8xV8ExoF2bG7hnHkA3dUQk9HrbmYZPRGQTSfv333+Pt99+GwMHDjzr7e655x6UlJTgq6++Qn5+Pp544gkUFxfjlVdeabVYrYkcqR7bvx3+2n4c81cdwRM3DtE6JCIiojbPUFqE3C1LkLftVxgrStV1Lh16wWfsNXAO64S2aN/RE4hPzYeTox4XDm2vdThERBZD86Q9PT0d//nPf7B161Z06HD2/cR3796Nbdu2YdmyZYiKMq1zevbZZzF37lzcf//9CAoKaqWorcsl46KxcsdxbNmfhsT0ArQL8tA6JCIiojbJUFGG/B3Lkbt5IQwlheo6p5Bo+Iy7Gq6RfdCWLV57TJ1PGNgO7q6OWodDRGQxNO87+ueff+Dg4IAlS5agT5+zv1nt2LEDAQEB1Qm7GDx4sGqT37lzZytEa50kSR/a07QuTKrtRERE1LqMVZWqBT7xg7uQvepblbA7+Icj6NKHEHrjy20+YU/JLMT2mDR1edoobvNGRGRRlfbx48erU0Or8iEhtYeSODo6wtvbG6mpqee1hkpa7M+XtO3XPLckU4e3w+Z9qVi7KwmXjmmv2uatKf6GYPzasvb4beExMH7biV/el7hNp20wGg0oOrAR2Wt/RGWOKSm19/SHz+gr4N5rDOx0eq1DtAhLNxyD0QgM7BaE8EB2BBIRWVTS3hjyQUiS9LqcnJxQVlbW5PutqKhATEwMmkt8vGmrEksTGeSEuPQyfLP0b1w00Nvq4m8oxq8ta4/fFh4D47eN+Ot7vyPrIQdeSmJ3IXvNPJRnmP4mdK6e8Bk5G579JsHO3kHrEC1GYUkF/tp2XF2eMZpVdiIiq07anZ2dUV5eftr1krC7uro2+X6lPT86OrpZDirIhzVZm2+J0+yvdgzEC1/twu64Ysy9ZIDaEs6a4j8Xxq8ta4/fFh4D47ed+GNjY5stLmp9JccPIGfNPJQmmgoCdk6u8B46A16Dp0DnaH1/2y3tz60JKC2vQvtgD/TpFKB1OEREFseqkvbg4GD89ddfta6TJD43NxeBgU3fw1RaEM8n6a9LPqw15/01lyE9XRAdfhSxSXlYuTMN10zualXxNxTj15a1x28Lj4HxW3/8bI23TmVpcaqyXnJ0l/razt4RngMvgvewWdC7suW7PlVVBtUaL6aPjuLfPhGRJQ6ia4xBgwYhLS0NCQkJ1dfJNHkxYMAADSOzDvJGOHtCZ3X51w3HUFxaoXVIREREVq8iOwXpC99E8ucPmhJ2Ox08+k1Cu9vfh9+E65iwn4XsbJOZU6K6/8b0D9c6HCIii2TRlfaqqipkZ2fDw8NDtcbLdPn+/fvjvvvuwzPPPKOGxz399NOYOXMmt3trIJkiHxbghuTMIqzYmoCZY85/WQAREVFbVFWYjcw136Dg75WA0aCuc+s+Ar5jroSDb6jW4VmFxeuOqvOLhneAkwOH8hERWV2lXSbCjxw5Uu3Lbq4Uv//++wgPD8f111+Pe++9F6NHj1YJPDWMXmeHS8Z1UpcXrjmKisoqrUMiIiKyKoaSArgcXInMLx5Ewe4/VcLuEtUfYTe/jqBZ9zNhb6DDx3MQE58Ne70dLh4eqXU4REQWy6Iq7S+//HKtryU5P3ToUK3r/Pz88O6777ZyZLZl3IBwzPvjILLySrF6ZxImDWmvdUhERERWoTwzEZlfPw7nMtNWsc7tusFn7NVwieiudWhWZ8k601r20f3C4evprHU4REQWy6Ir7dQyHOz1mDkmSl1esPoIqgxGrUMiIiKyClUl+TCWl6DSIxA+Mx9AyLXPMWFvgqy8EmzYk6wuTxvFbd6IiM6GSXsbJdV1dxcHtbZ9y/5UrcMhIiKyCi4RPRB4+0coGH4znCL7ctp5E/22MU4VDXp09EN0uLfW4RARWTQm7W2Uq7MDpo40Hdmev/IwjEZW24mIiBpC5+Qqg3a0DsNqlZZX4vfN8eryjNGmzj8iIjozJu1t2NSRkXB00Kt92/ccydQ6HCIiImoDZJ5OQXEFgv1cMbhHsNbhEBFZPCbtbZiXuxMuHGoaQjd/1RGtwyEiIiIbZzAYseTkNm/TRnZUu9oQEdHZMWlv42Qgnbxh7jlyQlXciYiIiFrK7sMZSMoohIuTPSYOjtA6HCIiq8CkvY0L9HHFmP7h6vLi9ab1ZUREREQtuc3bBUMi1HwdIiI6NybthEvHRavz7TEZyMyr0DocIiIiskHH0/Kx61AGpCNeWuOJiKhhmLQTIoI9MbRnMGSA/MaYAq3DISIiIhu0ZL2pyj6kZwiC/dy0DoeIyGowaSfl0vGd1Pne+GKcyCvVOhwiIiKyIflF5Vi9I1Fd5jZvRESNw6SdlK7tfdE90gcGA7BsU4LW4RAREZENkX3ZyysNiAr3QvdIX63DISKyKkzaqdrM0ZHq/K8dyeqIOBEREdH5qqg04LeNcery9FFRsLPjNm9ERI3BpJ2q9Y7yRbCPA8rKq/DbBtO6MyIiIqLzsXFPMrLzS+Hj4YRRfcO0DoeIyOowaadqcuR7ZHcPdXnphmMoKavUOiQiIiKyYkajEYtPDqCbMiISDvb86ElE1Fh85aRaurdzQbCvCwqKK7BiK9e2ExERUdPFxGcjNjEXjvY6TB7WQetwiIisEpN2qkWns8P0UaY31UVrYtU6NCIisi1lZWVah0BtxOJ1R9X52AHt4OXupHU4RERWiUk7nWZ031D4ejqprd/W7jJtz0JERLZjxIgR+M9//oO9e/dqHQrZsPTsYmzZl6ouTx/dUetwiIisFpN2Oo2sN5sxOlpdnr8qFgaDUeuQiIioGd10003YsmULrrjiClx88cX47LPPkJmZqXVYZGN+3XAM8hGib+cAtA/21DocIiKrxaSd6jV5WHu4uTggObMQW/8xHSUnIiLbcMcdd+CPP/7A999/jwEDBuDjjz/GuHHjcOutt6rrKyoqGnV/BoMB7777LkaNGoW+ffvilltuQWLimTu1srKy8MADD2Do0KEYMmQI7rvvPqSnp9e6zfLly9UBhd69e2PmzJnYvHlzkx8vtb7i0lOzcWaMjtI6HCIiq8aknerl6uyAqSNM+7b/vPKImv5KRES2pX///njuueewceNGvPPOOygpKcG9996LkSNH4pVXXkFycnKD7ueDDz7AvHnz1H39+OOPKomfO3cuysvL6729/I6UlBR8+eWX6iSX77zzzurvSxfAQw89hCuvvBILFy7EsGHD1AGFo0dN66PJ8q3cnoji0kqEBbijf5dArcMhIrJqTNrpjKaN6ghHBz2OJOZib+wJrcMhIqIWkJqaii+++EJVyrdv344OHTrgkksuwbp161Sle9myZWf9eUnM5efvuecejB07Fl27dsVbb72FtLQ0rFix4rTb5+fnY9u2baoa361bN3Tv3l0l5Pv27UNubq66zaeffoqJEyfiuuuuQ1RUFB555BH06NEDX3/9dYs9D9R8qgxGLD25zZusZZcht0RE1HT25/GzZONkyuukwRH4dWMc5q86gj6dArQOiYiImkFhYaFqg1+0aBF27twJZ2dnTJ48WQ2nk+q7kET5tttuw4svvqiS9zM5ePAgioqKVDXczNPTUyXjchBg6tSptW4vv8vNzU397sGDB6vrFi9ejMjISPVzUqXftWsXHn300Vo/J2309R0EaCjpGCsuLkZzkI6EmufWpqXj3xGTgdSsIri52GNod/9me97N+Pxri/Fri/HbTvzyvmRn17CDmkza6axmjY3Gss3x+PtwptpnNbqdt9YhERFRM0yPl23fZP35s88+q5JyV1fX027Xq1cvHDhw4Kz3JRV1ERISUuv6wMDA6u/V5OjoiJdffhlPP/00Bg4cqD6wyG2/++476HQ6VW2XJC84OLhB99dQsk4/JiYGzSk+Ph7WrKXi//kv01DDvpEuiDt6GC2Fz7+2GL+2GL9txC/viQ3BpJ3OKtDXFWP6hWH1ziRVbX/0+kFah0REROfpmmuuwezZs9Gx49m34brxxhtx++23n/U25mpD3Q8eTk5OyMvLq7eyIMlzv3791Lr3qqoq1U4vw/F++OEHlJaWnvH+zmd/eQcHB0RHm3ZGOV/ymOUDmywlcHFxgbVpyfjjUwsQn5GkWuKvvrgv/L2c0dz4/GuL8WuL8dtO/LGxsQ2+LZN2OqdLx3dSSfumfSlqmrwMlSEiIuv18MMPq7b4//73v9UD4KSiLlPkZa15z5491XXSxn4u0u5uXttuviwkwa7vA41MhZeq+urVq+Hubno/+eijj9T0+vnz52PGjBnV91fTme6voaSiX183wfmQeJr7PltTS8T/x7aD6nxk71BEhPiiJfH51xbj1xbjt/74G9oaLziIjs5J9lYd0iMYMkD+l1VHtA6HiIjO09q1a3H99ddjw4YNtT48SPXg6quvxo4dOxp8X+a2+IyMjFrXy9dBQUGn3V7uW9avmxN24eXlpa5LSEiAt7e3+iDU0Psjy5GTX4p1u5OrB9AREVHzYNJODTJ7fCd1vnpnIrLyrHNwBBERmbz33nuYMmWK2qbNTCa5y0C4iy66CG+++WaD70umxUsCvnXr1loT4qVyP2jQ6UuqZK26JOc1W91lDXtSUpJqN5SDBzIMTybM1yT3L2vgyXIt3xyPyioDurb3QZf2LVtlJyJqS5i0U4N07eCLHh39UFllxKK13CeXiMiayX7nM2fOrLc1T66XifANJWvP58yZg9dffx0rV65UP3vfffep5HzSpElqzXpmZmb1WnW5f/Ne7XJbOd1///1qzbpsNWdeS//bb7+pPdwl1ldffVWtg5fuALJM5RVVWLYpTl2ePjpK63CIiGwKk3ZqsMsmmKrtv2+OR0Fx7bWGRERkPTw8PBAXZ0qw6kpMTGz0Oj3Zo10G2z355JO46qqroNfr8fnnn6vhb7IP/MiRI6v3e5cp8FLhl4F0koRLgi63k+skLiG3l63mZDDdrFmzsGXLFrXuXfZsJ8u0bncS8grL4e/tguG9au8kQERE54eD6KjB+ncJRGSoJ+JS8vHbxjhceUEXrUMiIqImuOCCC/DOO++o9egyAM5s/fr16nqpkDeGJOkPPfSQOtUVHh6OQ4cO1bpOkm9Jws9GKvLmqjxZNjkAs3jdMXV52shI6PWsCRERNScm7dRg0kYpa9tf+24nlqw7hpmjo+DsxD8hIiJrI+3r+/btU9u5SZVbhr/J/uiVlZXo06cPHnjgAa1DJCuyN/YE4lPz4eSox6Qh7bUOh4jI5jDjokYZ0TsU3/kdRGpWEVZsS8D0UWxVJCKyNjI47scff1RT5GXrN9lPXVrTZdDb2LFjodOxUkoNJwfyxcRBEXB3ddQ6HCIim8OknRpFWt5mjYvGB/P3YOGao7h4eCTs2QZHRGR1JDGX1via7fE1250bs38stV0pmYXYHpOmLk8bxW3eiIhaApN2arQJA9vhhz8O4kRuiRo8M35ghNYhERFRI8lgONlWrby8XCXpQs5l+7W///4b69at0zpEsgJL1x+D/PkM6h6EsAB3rcMhIrJJTNqp0Rwd9JgxOgpf/XYA81cdwdj+7aDTsSJDRGQt3n//fXWSlnhZxy7r2u3t7ZGdna0q8JdddpnWIZIVKCypwF/bj6vLM7hcjoioxTRbX/P+/fuxYsUK5OfnN9ddkgW7aHgHuDnbIzG9ENsOmNriiIjIOixcuFBNZpdK+w033KBa5Ddt2oT58+eroXSdOpm2+CQ6mxVbElBaXoUOIZ7o3clf63CIiGxWk5L2jIwMXHvttfjggw/U19999506Ki/7tMo2MUeOHGnuOMnCuDo74OIRkery/JVHqlsriYjI8qWnp2PatGlq3Xq3bt2we/dudX3Pnj3xr3/9Cz///LPWIZKFq6oy4NeNpgF000d15AwEIiJLS9pfe+01xMXFoVevXjAYDGqv1eHDh2PRokWIjo7GG2+80fyRksWRgTOO9jocOp6D/UeztA6HiIgayNXVtTrJat++PZKSklBaWqq+liReviY6m837U5GZUwIvd0eM6R+udThERDatSUn7hg0b8Mgjj2DUqFHYtWsXTpw4geuuuw5du3bF3LlzsWPHjuaPlCyOj4czJg42DaGTte1ERGQd5KC7HGgXkZGR0Ov12Lx5s/r66NGjcHTktl3UsG3eLhoWqWbdEBGRhSXtMlk2ODhYXZbpsvLmPnToUPW1XGardNsxa2y0GkK361AGYpNytQ6HiIgaQFrgZXq8nMv79vTp09XB+LvvvhuvvPIKRo4cqXWIZMEOH89BTHw27PV2uHh4B63DISKyeU1K2jt06KCq6RUVFfjjjz8wePBgODk5qe8tWbJEfZ/ahmA/N4zuG6Yu/8JqOxGRVRg0aJAaOnfRRRepr59++mlceOGFOHbsGCZPnownn3xS6xDJgi1ed1Sdj+4XDh9PZ63DISKyeU3a8u2WW25RR+Q///xzVXWXN3sxe/ZsHDhwAK+//npzx0kW7NLxnbBmVxI27U1BSmYhQrlPKxGRRZNBspKkz5gxQ30tB96fe+45rcMiK3AitwQb96RUD6AjIiILTdqnTp2KkJAQ7Ny5U1XZ+/btW33kXibIjx49urnjJAsmW70M7BaEHTHpWLAmFnddZvp7ICIiy/Txxx+jR48eiIri3trUOL9tjEOVwYieUX6ICvfWOhwiojahyfu0DxgwALfeemt1wl5ZWYnbbruNCXsbddkE056+K7cnIiuvROtwiIjoLGSnF9kFhqgxSssr8fvmeHV5xmge8CEisuhKuyToss2bbBMj+7xu3bpVVdjz8/NV5f3dd9+Fl5dX80dLFqt7pB+6R/riQFy2mih747QeWodERERnMG7cOLz55ptYv349unTporaAq0m2g7vzzjs1i48s0+odiSgsqUCwnysGdTcNJCYiIgtN2iUpl/Xsjz/+uPr6+eefh7e3t3qD//LLL9U+7c8++2xzx0oW7rIJnfF/n23B8s1xqvLu7sotg4iILNH777+vzjdu3KhOdTFpp7oMBiOWrDdt8zZtZEfodXZah0RE1GY0KWn/7bffcP/99+Oaa65R+7keOXIEL7/8MmbOnKmS91dffbXBSbvBYFAfHn7++WcUFBSodfEy2K5du3b13j4rKwsvvvii+pAhW8sNHz4cjz76KIKCgpryUKgZDegaqNa3x6fm47dNcbhiYhetQyIionocPHhQ6xDIysjWrkkZhXB1tsfEwRFah0NE1KY0aU17RkYG+vTpoy6vWbMGOp2uei277N8uyXdjJtjOmzdPTa398ccfVRI/d+5clJeX13v7e++9FykpKaqiLye5zGqAZZDKjEySF0vXH1Nr34iIiMj6LTm5zdsFg9vD1dlB63CIiNqUJlXaAwMDkZSUhIEDB2LVqlXo1q0bfH191fd2796tEveGkMT8iy++wIMPPoixY8eq69566y2MGjUKK1asUFPqa5I189u2bcOHH36ofqeQYXh33HEHcnNzVZWftDWqTyi+Wx6D9Oxi/LXtOKaO5HYwRESW5rHHHjvnbV566aVWiYUsX0JaPnYfzoR0xE8dGal1OEREbU6Tt3yTN/OlS5eqbd/M+7S/8MIL+OGHH/Cvf/2rwe15RUVFGDZsWPV1np6e6N69O7Zv335a0u7s7Aw3NzcsWrRIDbwTixcvRmRkpPq5ppI2e9lv/nyVlJTUOrc2zRX/1BER+HzpQSxYfQSj+wTCXt/kTQoahc+/tqw9flt4DIzfduKX9yXpXmopMkC2LnkfNB8A79WrV4v9brI+0j0nhvQMQbCfm9bhEBG1OU1K2qVFXSbNSmL9wAMP4Oqrr1bX79u3DzfddJOqfDdEWlqaOpc93+tW8s3fq8nR0VGtnZeDBFLllw80ctvvvvtOteg3VUVFBWJiYtBc4uNN26FYq/ONP9jFCDdnHTJzSzH/j13oE9m6b/Bt/fnXmrXHbwuPgfHbRvzyntdSpEuuPjKn5q677lIzaohEXmGZmhovuM0bEZEVJe2SLMue7HKqSdakN4a5GlH3g4mTkxPy8vLqrTxIct2vXz+17r2qqkq108tBAqnwu7u7N+XhwMHBQe1Ze77k8ciHtQ4dOsDFxQXWpjnjn57jgh/+jMX2o+W4fPIA6Fphyiyff21Ze/y28BgYv+3EHxsbCy1ERUXh7rvvxnvvvYcpU6ZoEgNZlt+3xKO80oDocC+1tSsREVlJ0i6ys7PVenRZYy5rzX18fFT1+4YbboCfn1+D7kPa3c1r282XRVlZWb0feJYvX66q6qtXr65O0GW/eNlvdv78+ep3N/UgRN09as+HxN6c99famiP+GWM6Y/H6eCRlFOFAQgEG92i9/Vz5/GvL2uO3hcfA+K0//pZsjT8XeX9NTk7W7PeT5aioNGDZxjh1efroKE3/LomI2rIm9ZRL6/qsWbPw9ddfq6q4rEG3t7dX09ylpS49Pb1B92Nui5dp9DXJ1/Vt4bZjxw61fr1mRd3Ly0tdl5CQ0JSHQi3EzcUBFw3roC7/vPKw6pIgIiLLIDuv1D0lJiaq99l3331XVdyJNu5JRnZ+GXw9nTCyT5jW4RARtVlNqrS/9tprKklftmxZrf3U5Q1f1rRLy7qsPT+Xrl27qgRcBuJERJj2/JSq/YEDBzBnzpzTbi9T6WWPeKnEy8EC8+AcmWQ/ffr0pjwUakGy9m3J+mM4mJCDf45loWeUv9YhERERgPHjx9dbNZUDrNL59v7772sSF1kO+VtYfHKbt4tHRMLBvnWGyhIRUTMl7Rs2bMDjjz9eK2EX8rXsmf7qq6826H5kLbsk56+//rraMi4sLEwdEJDkfNKkSWrNurThe3h4qA8RUsX//PPP1SC8f//73+o+3n77bZXAX3LJJU15KNSCfDydMXFQBJZvjsf8VUeYtBMRWYgXX3zxtKRdvpYD6UOGDFHvu9S2HYjLRmxSHhztdZg81NQ5R0REVpS0SzIta9jrI8l3YWFhg+/rnnvuQWVlJZ588kmUlpZi0KBBKjGX4XBSQZ8wYYLaXk6ScpkUP2/ePJXYX3/99WpivKyjl+v4AcMyzRobjT+2xGPnwQwcS85DxzAvrUMiImrz5D3VYDDg8OHDqutNZGZmqk43axwCSM3PXGUfN7AdvNxN3Y1ERGRFSXuXLl3UHu2jR48+7Xuyb3rnzp0bfF96vR4PPfSQOtUVHh6OQ4cO1bpO1tnJ8DmyDiH+bhjZNwzrdifjl1VH8NC1A7UOiYiozZPZM7ILi0y8/+uvv9R1krDLrjB9+/ZV77OyXzu1TWlZRdi6P1Vdnjaqo9bhEBG1eU1aoCRbrEnSfuutt2LRokXYuHGjOr/lllvUOve6W8FR2zZ7fCd1vmFPMlJPFGkdDhFRmyfL2GTnFlmeZjZmzBgsWLAAubm5eOONNzSNj7T128Y4GIxAv84BaB/sqXU4RERtXpMq7SNGjFCD5uTNft26ddXX+/v7q1b2Cy64oDljJCsXGeqFAV0DVYv8gjWxuHN2H61DIiJq0zZt2oRnn31WVdVrkt1gZGbMCy+8oFlspK3i0gqs2JpQvc0bERFpr8mjQGUo3Pr169U0d1lTLufytWzV9tRTTzVvlGT1LptgWjLx17bjyM4v1TocIqI2TarssjytPrKmvaiIXVFt1V/bj6O4tBLhge7o3yVQ63CIiOh8knbzpFlZY96/f391Ll/LUJv58+c3X4RkE7pH+qJbB19UVhmw5ORwGyIi0kafPn3w5ZdfoqKiotb1Mhj2m2++Qe/evTWLjbRTZTBi6fpj6vL0UR2h052+LSAREVlJezxRY8kBHVnb/twXW7FsUzxmT+gMdxcHrcMiImqTZOeWa6+9Vu3QIkNl/fz81BarMqMmKysL3377rdYhkga2H0hDWlaxen8eN6D2tr5ERGSllXaixhjYLQjtgz1QUlaJ5ZvitA6HiKjNkrXsP/30kzpfs2aN2mpVpsj36NEDP/74IyvtbXybt8nDOsDZiXUdIiJLwVdkajXSZnfp+E54c94uLFl3TA24cXKof00lERG1LBk699Zbb1WvbZft36Q93sPDQ+vQSANHk3Kx/2gW9Do7TBkRqXU4RERUAyvtzchoNMKuvFjrMCzaqL5hCPRxQW5hmRpKR0RErU/Wsv/nP//B5ZdfXn3d7t27MWzYMLzyyiswGAyaxketb8nJtewj+oTC39tF63CIiKgplfbrrruuQbdLS0tDW1W4aT68ty1BfvYkuFx4E+zsuWa7Lnu9DpeMjcZHC/ep7d8mD20PvZ7HjoiIWtN7772HJUuW4O67765VeX/wwQfV93x8fHDrrbdqGiO1npz8Uqzbnawuz+A2b0REFkfXmCpyQ06y5dvAgQPRFum9g9R58d8rkPz146jITtU6JIs0YXAEvNwdkZFdjPV7UrQOh4iozVm6dCkeeeQR3HTTTdXXeXt744YbbsB9993HXWDaGBkQK7u7yC4vnSN8tA6HiIiaWmnnJNlzc+0xGskn8uB5YBnK044h6fOHEDDldrh3H6F1aBbF2dEe00Z1xHfLD+KXVUcwpl+Ymi5PREStIycnB+3a1T8dvGPHjm26a66tKa+owvLNpuGw00d31DocIiKqB/uSm1llYDT857wA53bdYCwvQcbCN5G57CMYKsq0Ds2iTBnRES5O9ohPzceOmHStwyEialMkMf/jjz/q/d6qVavQvn37Rt2frIF/9913MWrUKDWR/pZbbkFiYmK9t5X2+y5dutR7euyxx6pvd+ONN572fdmmjprX2l1JyCssR4CPC4b1DNE6HCIiqgenx7cAvYcvQub8H3LW/YTcjQtQsPtPlCUfQuCsB+DoH651eBZB9oC9aFgHta59/qojGNQ9WOuQiIjaDJlT8+ijjyI3NxcTJ06s3qd99erVWL58OV566aVG3d8HH3yAefPm4eWXX0ZwcDBee+01zJ07V7XhOzo61rqttORfeeWVta778ssv8cMPP6j2fLNDhw7hmWeeUfGZOThwVkxzkmWN5gF0U0d05IwZIiILxaS9hdjp9PAdezWcI3ogc8k7KM84juQvHob/5Fvh0Xus1uFZBGnDkw8LB+Ky8c+xLPTo6Kd1SEREbcLMmTNRVFSkku0VK1ZUXy8D6J5++mnMmDGjwfdVXl6OL774Qg2xGzvW9P4mW8lJ1V3ue+rUqbVu7+bmpk5mBw4cwDfffIPnnntOVdNFVlaWOvXp0wcBAQHN8IipPvuPZauON2dHPSYNbVx3BRERtR4eUm1hrh37IGzuG3Du0AvGijJkLn0PGUvfg6G8BG2dn5cLJgwyramUajsREbWea665Bhs2bMCyZctUlfzXX3/FokWLVLI8fvz4Bt/PwYMH1QEA2S7OzNPTU02j3759+zl//tlnn1UDbGfNmlWryi6zTiIjuV94S1q22bT16sRBEaoDjoiILBMr7a3A3t0HIVc9hdxNC1XLfOHeNShLPoLAWffDKagD2rJLxkXjz60Jal17XEoeIkO9tA6JiKjNkMRY1revX78en3/+OdauXYvKykqEhzd8KZd5aF1ISO310IGBgeccaCft+LI/vBwsqOnw4cPw8PBQCf3GjRvh6uqKyZMn44477jit3b4xreDFxcVoDiUlJbXOrY3EfSK/ArsOnVBfTxwU0mzPTWuwhee/5rm1YfzaYvy2E7+8LzV0GDeT9lZsl/cZORvOEd2QsfBtVGQlI+Wrx+B3wY3w6HdBm52eHurvjhF9wrD+72T8sioWD84ZoHVIRERtgqxhl63d/ve//yE5ORnu7u6q2i2t8Y3ZutX8waVuMu3k5IS8vLyz/qysZR83bhy6det2WtJeVlaG3r17q4F0MTExePXVV5GSkqLOm6KiokLdT3OKj4+Htdp6qFCddw51Rm7GceRmwOpY8/MvGL+2GL+2GL9JQw9EM2lvZS4RPRA+93XVIl9ydDdOLP8YJQn7EXDxv6BzckVbdOm4aJW0r/87CXMu6opgv1NrHYmIqHlt2bIFP/30E/766y9UVVVhwIABKmn/73//i8GDBzf6/pydnavXtpsvC0m6XVxczvhzkoBv3boVn3zyyWnfkwq77CPv5WXqvurcubMaQid7yD/88MPw9/dvdJzy89HR0WgOcqBCPrB16NDhrI/RUp3ILsDfx5LV5Ssu7IFuHX1hTaz9+Wf82mL82mL8p8TGxqKhmLRrQO/mheArHkfe1qXIXv09ig5sRFnqUQRJu3xIFNqaqHBv9O8SiF2HMtQ0+Tsu7aN1SERENuerr75SyXpcXJza0k1azaWyLq3nkqw3tePL3BafkZGBiIiI6uvla/NgufrIQQNfX1+MGDHitO/Z29tXJ+xmnTp1UufSct+UpF0enzzW5iQf2Jr7PlvDpg3xqKgyIiLIHYN6hFltt5+1Pv9mjF9bjF9bjB+Neu3lIDqN2Nnp4D10BkKvex72XgGozElD8lePI2/7b2p9Q1sze4Lpw9hf244jp6BU63CIiGyObMcmbXgyqV32aL/99tvV9mznm7B17dpVtdZL1dwsPz9fTYUfNGjQGX9ux44d6mCBJOh1yX7sNfdsF/v27VPVcqluUNNVVRnw+5ZEdfni4RFWm7ATEbUlTNo15hzWGWE3vw7XzoMBQyWyVnyB9PmvoqrEtNasrejZ0Q9d2vugotKApSf3jCUiouYzZcoUJCQk4LbbblNV9j///FMNnTtfciBgzpw5eP3117Fy5Uo1TV7a2OWAwKRJk1QLfmZmJkpLax+QlaReEv76XHjhhVi8eLHauz0xMVFNuJe17DfffLM6QEBNt2lfKrLySuHqpMOIXsFah0NERA3A9ngLoHdxR9Dsh5G/YzmyVn6N4sPbkPx5nJouL0l9WyBH+meP74QXvtyG3zbG4dJxneDG7WeIiJrNG2+8gcLCQixduhQLFizA3XffrfZlnzhxonoNPp+K6z333KMOADz55JMqOZcKu0yjl8p4UlISJkyYgJdeegmXXHJJ9c9IIu/t7V3v/clBAInn22+/xYsvvqj2ar/hhhtw6623NjlGMlmy7qg6H9TJDY4Oeq3DISKiBmDSbiHkw4nXoIvhHN4F6QvfVO3yKd88Cd+xV8Nr6HTVTm/rBncPRrsgDySmF2D55niVxBMRUfORKvVVV12lTkeOHMEvv/yiknhZlvX444+rarycGjuwTa/X46GHHlKnumT7ONl3va49e/accx95OVHzOZSQjYMJObDX22FgJ3YsEBFZC9vPBK2MDKILv/k1uHUfARiqkL3qW6T99CKqis6+bY4t0Omk2m76oLh43VGUV1RpHRIRkc2SwW6PPvqo2pv9vffeU/u1f/rpp5g2bRqmT5+udXjUApasMy0/G9E7GB4urLITEVkLJu0WSLZ+C5x5H/wv/hfs7B3V1nBJnz2IkuP/wNaN7heOAB8X5BaUYeX241qHQ0Rk82QQ3AUXXICPPvoIa9aswf33398sa93JspzILcGGvSnq8sXD2msdDhERNQKTdgtul/fsdwHCbnwZDn5hqCrMRup3zyBnw3wYDbZbgbbX6zBrjKnaLtu/yZRbIiJqHbKV2i233KIGv5Ft+XXDMRgMRvSK8keHEA+twyEiokZg0m7hHAPbI+ymV+HeexxgNCBn7Q9I++E5VBbmwFZdMCQCnm6OSMsqxsaTVQEiIiJqmtKySvyxJUFdnjG6o9bhEBFRIzFptwI6R2cETrsLAdPuhp2DE0ri9yH5swdQfOzsQ3yslbOjPaaNMn2omL/qSJvct56IiKi5rNqZiMKSCoT4uWFgd27zRkRkbZi0WxGP3mNV1d0xMEINppOKe/bq722yXX7qiEi4OOkRl5KPnQcztA6HiIjIKklLvHkA3dRRkdDrmr61HxERaYNJu5Vx9A9H6A0vw6PfJABG5G5agNTv/oPK/CzYEndXR1w4tEN1tZ2IiIgab9ehDCRnFsLV2R4TB0VoHQ4RETUBk3YrpHNwQsDFtyFw1v2wc3RBaWIMkqRd/shO2JKZY6LUXrL/HMtCTFy21uEQERFZHdlCVUwa0h6uzg5ah0NERE3ApN2KuXcfgfC5r8MxOAqGkgKk/e9FZP31NYxVFbAFfl4uGD/QVBVgtZ2IiKhxEtLy8ffhTEhH/NSRHEBHRGStmLRbOQefYIRd/wI8B01RX+dtXYKUb55CRW46bMEl46JhZwdsO5CGhNR8rcMhIiKyGua17EN7hSDI11XrcIiIqImYtNsAO3sH+E+6CUGzH4bO2Q1lKUeQ/NmDKDq4BdYuLMAdw3uFqsvzV7PaTkRE1BB5hWVYvTNRXZ4+KkrrcIiI6Dwwabchbl2GIGzu63AK6wJDWTHSf3kNJ/74DIbKcliz2eM7qfN1u5ORnl2sdThEREQW7/ct8aioNCC6nTe6R/pqHQ4REZ0HJu02xsErEKHXPguvYTPV1/k7liPlq8dRkZ0CayUfOPp2DlDb1ixaE6t1OERERBZNkvVlG+PU5RmjOsJO1pkREZHVYtJug+z09vAbfy2Cr3wSOldPlKfHIenzh1C4fz2svdq+YmsCcgvKtA6HiIjIYm3Yk4zs/DL4ejpjRJ8wrcMhIqLzxKTdhrlG9UP4za/DOaI7jOWlyFj8NjJ//QCGCutLentH+6NzhDfKKw1YusE0WIeIiIhqMxqN1du8TRkRCQd7ftQjIrJ2fCW3cfaefgi55hl4j7xMavAo2LMSyV8+gvJM03AaayGtfeZq+28b41Bcahvb2hERETWnA3HZOJqUB0d7HS4c2l7rcIiIqBkwaW8D7HR6+I65EiHX/Ad6N29UZCYi+YuHUbBnlToiby2G9AhBeKA7ikoq8PvmeK3DISIisjjmKvu4ge3g5e6kdThERNQMmLS3IS4deiFs7htwiewDY2U5Mn/9LzKXvAtDWQmsgU5nh0vHmarti9YeRXlFldYhERERWYy0rCJs3Z+qLk8f1VHrcIiIqJkwaW9j7N29EXzVk/AZe42U4FG4f52qupelmabMWrox/cPh7+WMnIIyrNphXS3+RERELenXDXEwGIH+XQIREeypdThERNRMmLS3QXZ2OviMuERtDaf38FPbwaV89RiK9/wlE2xgyWSgzsyx0erygtWxqJJPJ0RERG2czHqRHVbE9NGsshMR2RIm7W2Yc7tuCJ/7BlyjB8BYVYH8VV/Dbc9CGMqKYckuHNIeHq4OSM0qwqa91rv/PBERUXP5a9txlJRVol2Qu6q0ExGR7WDS3sbpXT0QdPlj8J14A6DTwzHtILK+exKlKbGwVM5O9pg20lRFmL/yiFUN0yMiImpu0nW2ZL1pO9Rpo6LUjitERGQ7NE/aDQYD3n33XYwaNQp9+/bFLbfcgsTEM69VrqiowBtvvFF9+zlz5iAmJqZVY7Y18ubuPWQafK94ClUuXqjKz0TK108gd+tSi02Ip4zsCGdHPY6l5GH3oUytwyEiItLMtn/SkJ5drLrQxg0I1zocIiKytaT9gw8+wLx58/Dcc8/hxx9/VEn83LlzUV5eXu/tn3nmGSxYsAAvvvgifvnlF/j6+qpEv6CgoNVjtzWOwVEoGH4znKIHAYZKZP/1FdJ/fhlVJZb33Hq6OeLCoR3U5fmrjmgdDhERkWaWrDdt8zZ5WAc4O9prHQ4REdlS0i6J+RdffIF77rkHY8eORdeuXfHWW28hLS0NK1asOO32UoGXRP2FF15QlfaoqCg8//zzcHR0xP79+zV5DLbG6OAM76l3w+/CWwC9PYqP7EDSZw+iNPEgLM3MMVGw19th39ETOJiQrXU4REREre5oUi72H82CXmeHKSMitQ6HiIhsLWk/ePAgioqKMGzYsOrrPD090b17d2zfvv2022/cuBEeHh4YPXp0rduvWrWq1n3Q+bfLew2cjLAbXoaDbwiq8k8g5dunkLtpAYxGAyyFv7cLxg1oV722nYiIqK0xr2Uf2ScMfl4uWodDREQtQNMeKqmoi5CQkFrXBwYGVn+vpri4OLRr105V4T/55BOkp6erBP/RRx9VVfemknXbxcXnPzG9pKSk1rm1OS1+zyD4XPV/yF/5FUoPbkL26u9ReGwvvCbfBr2rFyzBRUPD8df249j6Txpij4fa1vNvZaw9flt4DIzfduKX9yUOE6Nzyc4vxbrdSeoyt3kjIrJdmibt5g820t5ek5OTE/Ly8k67fWFhIRISEtQ6+IcfflhV2T/88ENcffXVWLZsGfz8/JoUhwy3a85hdvHx8bBmp8Xffgwc7X3geuAPlCfsQ/pXj6Co9wxU+pnWlGuta7gLYhJL8L+/DmLWMF/be/6tjLXHbwuPgfHbRvx13xuJ6lq2KQ6VVUZ06+CLzhE+WodDRES2mLQ7OztXr203XxZlZWVwcTm9xcve3l4l7rLu3VxZl8tjxozBwoUL1QC7pnBwcEB0dDSa4yCEfFjr0KFDvfFburPG3707KvqNRN5v76MyOxkeO36A+5CZcBsyE3Y6becZzvHIwxMfb8P+hBKM612Jvj2ibe/5twLWHr8tPAbGbzvxx8Za7rabZBnKK6qwfJPpANGM0U3vNiQiIsunadJubovPyMhARERE9fXydZcuXU67fXBwsErca7bCS7IvLfNJSab2sKaQFkRXV1c0F/mw1pz319rOGH9EZ3jMfQ1Zf3yOgj0rUbhlISpTDyNwxr2w9/CFVnp3dkWfTv7Yc+QENscUYthAG33+rYS1x28Lj4HxW3/8bI2nc1mzKwn5ReUI9HHB0J7BWodDREQtSNMSqUyLd3d3x9atW6uvy8/Px4EDBzBo0KDTbi/XVVZWYt++fdXXlZaWqqny7du3b7W42zKdgxMCpt6BgBn/hp2jM0oT/kHSZw+g+OhuTeOaPb6TOt95tEit8SMiIrJVMvNgyTrTNm9TR3aEXq/5Dr5ERNSCNH2Vl/V6c+bMweuvv46VK1eqafL33XefqqhPmjQJVVVVyMzMVIm5GDhwIIYPH45HHnkEO3bsUO2DsrZdr9djxowZWj6UNsej52iE3fQaHAM7wFCcj7Qfn0fWqm9hrKrUJJ4+nQLQMcxTre3799sb8dGCvUjLKtIkFiIiopa050gmEtIK4OyoxwVDWLQgIrJ1mh+alT3aZ8+ejSeffBJXXXWVSsA///xztc48NTUVI0eOVEPmzN577z0MHjwYd911l/o5WeP+zTffwNdXu/bstsrRLxShN74EzwGT1dd5mxch5bunUZmX2eqxSCvp7bN6INjHAeUVBvy2MQ63vfQXXv56Ow5xD3ciIrIhi9eZtnmbODgC7i4OWodDRES2vKZdSJL+0EMPqVNd4eHhOHToUK3rpJ3+mWeeUSfSns7eEf6Tb4Fz+57I/O0DlCUdQtJnDyJg2l1w63z6EoeWFBHkjtsmB8LgHIxlmxOx82AGNu5NUaceHf0wa0wUBnUPhk7HtaJERGSdkjMLsSMmHTL2YNpIbvNGRNQWaJ60k21w7zYMTsGRyFj4FspSY5H+88vwHDwVfuPnwE7v0KoV954dfTG4ZzgSUvOxcG0s1u5Kwj/HstQpLMAds8ZGYdyAdnB00LdaXERERM3BvJZ9ULdghAa4ax0OERG1hfZ4sh0OPsEIvf55eA2Zpr7O3/YrUr5+AhU5aZrE0z7EE/de2R+fPXEBLh0XDTdne1WheP/nPbj5+T/x45+H1ORdIiIia1BYXI6VOxLV5RljWGUnImormLRTs5Kqut/EGxB02aPQubijLPUokj5/CIUxmzSLyc/LBTdM7YEvnpqEuTN6IsDHBbmFZfj+94O48bkVamhd6gkOrSMiIsv2x5YElJVXoUOIJ3pF+WsdDhERtRIm7dQiZD17+Nw34BTeFcayYmQseAMnln8CQ6V2lW1XZwfMGB2FTx6biAevGYCOYV4or6hSQ+v+9TKH1hERkeWqrDLg1w2mAXTyXibLwYiIqG3gmnZqMfae/gi99lnkrP0RuZsWIn/XHyhNOojASx6Ao1+YdnHpdRjTPxyj+4Vhb+wJLFwTW2toXfdIX1wyNppD64iIyGJs3peKE3ml8HZ3Uu9fRETUdjBppxZlp9PDd9w1cG7fA5lL3kV5RgKSP38Y/hfdAo9eY7WNzc5O7e8up5pD6w7EZeNA3DaEBbhh5phojB/IoXVERKStxScH0F00vAPfk4iI2hi2x1OrcO3YF2E3v6G2hjNWlCJzyXvIWPo+DOWlsAQ1h9bNHt/p5NC6Ivx3/qmhdXmFZVqHSURkkQwGA959912MGjUKffv2xS233ILERNPAtLree+89dOnSpd7TY489Vn27zZs345JLLkGfPn0wefJk/Pbbb2irDiZk41BCjuoUk6SdiIjaFibt1GrsPXwQcvXT8Bl9hZTgUbh3NZK/fATlGcdhKWRo3fVTutc7tO6m5//k0Doionp88MEHmDdvHp577jn8+OOPKomfO3cuystPn2Ny0003YcOGDbVON998M1xdXXHDDTeo2xw9ehS33XabOgiwYMECXHbZZXj44YdVIt8WLVlnWss+pn8YfDyctQ6HiIhaGdvjqdXb5X1GXQ7niO7IWPQ2Kk4kqcTdb9LN8Og7wWIG65iH1k0dEYkNe1KwYE0sjiXnqaF1yzbFYVivEMwaG42u7X21DpWISFOSmH/xxRd48MEHMXasadnTW2+9pRLuFStWYOrUqbVu7+bmpk5mBw4cwDfffKMSfqm2i6+//lpdvu+++9TXUVFR6nafffYZhg0bhrYkM6dEzVsR8r5ERERtD5N20oRL+55qunzGkvdQcmw3Tiz7ECUJ+xBw0W3QObnCUuhrDK3bd/QEFqw2Da3btDdVnWRonSTvgzm0jojaqIMHD6KoqKhWMu3p6Ynu3btj+/btpyXtdT377LMYOHAgZs2aVX3djh07MHHixFq3Gzp0KF544QUYjcYmHeCVnysuLkZzKCkpqXXekhatOQKDwYgekT4I8nZolsfQmvG3BMavLcavLcZvO/E35v2MSTtpRu/mheArH0feliXIXv09iv7ZgLKUWATNegBOIR1hSeQ/VO/oAHWSoXWL1h7Fml2Jpw2tGzewHZw4IIiI2pC0tDR1HhISUuv6wMDA6u+dyerVq7F7924sWrTotPsMDg4+7f7kQ1JOTg58fRvf5VRRUYGYmBg0p/j4eLSk8koDVmxNVZd7tdNZXfwtjfFri/Fri/HbRvyOjo4Nuh2TdtKUnZ0O3sNmwrldN2QsfBOVOWlI/vox+E24Hp4DL7KYdvm6Q+v+fWU/zLmoK37dEIflm+Kqh9Z993sMpo7siIuGdYCXu5PWoRIRtThztaHuBw8nJyfk5eWd9We//PJLjBs3Dt26dat1fWlp6Wn3Z/66vnXyDeHg4IDo6Gg012OWD2wdOnSAi4sLWsqKbYkorUhBkK8LZkzo12wdXa0Vf0th/Npi/Npi/LYTf2xsbINvy6SdLIJzeBeEzX0dmb/+F8WHtyNrxecoSdiPgKl3Qu98au2jJTEPrbtsQif8ue242o5H1h7K0LqfVx7BxEHtMGNMFEL93bUOlYioxTg7O1cn0+bLoqys7KwfaFJSUrB161Z88sknp31PEv66ybn566Z+SJKDwDLsrjlJLM19n2bSEv/7FtME/hmjo+Hu3vzvhS0Zf2tg/Npi/Npi/NYff2OKk5weTxZD7+KBoNkylO4mQGeP4kNbkfzZgyhNPgxLZh5a9+ljE/HQnAGICvdCeUUVlm2Kx79eXomXvt6mtushIrJF5rb4jIyMWtfL10FBQWf8ub/++ku1uY8YMaLe+6zv/uQDkoeHB9qCXYcyVBeXbEE6cXCE1uEQEZGGmLSTRZEjTl6DpiDs+hdg7x2EyrwMpHzzJHK3LIbRaIAlk6F1o/uF4617x+CF24djYLcgGI1QA+seenc9Hnl/PbbsT1XVEyIiW9G1a1e4u7urqrlZfn6+mvY+aNCgM/6cDJsbPHgw7O1Pb/qTwXTbtm2rdd2WLVvQv39/6HRt46PL4rVH1fkFQ9rDxYmNkUREbRnfBcgiOYVGI/zm15C57CMUxWxC9spvUJrwDwKm3QW9qycsWa2hdWn5WLTm9KF1M8ZEYzyH1hGRDZC15nPmzMHrr7+uKudhYWF47bXX1CC5SZMmoaqqCtnZ2apCXrN9XpL6Sy+9tN77vPbaa9U0eblPOV+7di1+//13teVbWyADT/8+kglZwj5tpGUNZiUiotbXNg5Xk1XSObshcNb98L/oNtjpHVAcuxNJnz2AkuMHYC3aB5uG1n32xAWYPb6TanOUdscP5u/Bzc+vwA8rDiGvsEzrMImIzss999yD2bNn48knn8RVV10FvV6Pzz//XA1/S01NxciRI7Fs2bJaP5OZmQlvb+96769Tp0744IMPVLI+c+ZM/Pzzz+pAQFvZo33J+mPqfFivUAT6Wu+aTyIiah6stJPFV609+0+CU1hnZCx8AxVZKUj97j/wGX0FvIfPgp3OOirVNYfW/XVyaF1GTgnm/XEQ81eZhtZdODhM6zCJiJpEkvSHHnpIneoKDw/HoUOHTrt+z549Z73P0aNHq1NbIwdyV+80DaCbPppVdiIiYqWdrIRTUAeE3fQq3HuNBYwG5Kz9AWk/Po/KwhxYExlaN310FD6pZ2jdve9sxE/rs3A4MVfrMImISCO/b45HRaUBndp5o1uHxu9HT0REtodJO1kNnaMLAqffrda12zk4oSRur5ouL+fW5kxD62ISS/DUJ9vx8HvrsXkfh9YREbUlFZVV+G1jnLosB3gbsx0QERHZLrbHk9Xx6D0OTqGdkL7gDVRkHkfqvGfhPfJSOA2YCmtTc2jdobgMfL9sD/YllCAmPhsxX21DqL8bZo7l0DoiorZg/d8pyCkog6+nM0b2CdU6HCIishCstJNVcvQPR9iNL8Oj3wUAjMjdMB/Z81+CXWkBrFW7IHfMGOqL9x8Ypda+u7k4IOUEh9YREbUFRqNRzTsRU0dGwl7Pj2hERGTCSjtZLZ2DEwIu/hdc2vdUW8NVJB+CZ8Zx5OccgDF6AJw79ITe2Q3WxsfDCddd3F1Nmz/T0LoZY6IQ6u+udahERNRM/jmWhWPJeXB00OPCoR20DoeIiCwIk3ayeu49RsIpJAqpv7yOyox4FO9ZqU6w06nrXSJ7q5NzWBfY2TvA2obWTRkRiU17U7FgzRHEJuWpoXXLN8djaM8QXDI2Gl05qIiIyGa2eZPlUJ5ujlqHQ0REFoRJO9kEB98Q+F35Hxxd/xsCjXmoSPxHbQ9XlnJEnXI3/qKG1zm3616dxDsGRsDOTmcVQ+tG9QvDyL6h2H80CwvWxGJHTLoaVCcnmS48a2w0hvQIhk7HoUVERNYmLasIW/anqsvTR3GbNyIiqo1JO9kMO709KoI6w7NbN7i6uqIy/4SaLF8Sv0+dVxXlouTYbnUSejcvOHfoBZcOveEa2Rv2XgGw9KF1vaL91SkhLR+L1x7F6p1JHFpHRGTllm44pnYQ6d81EO2CPLQOh4iILAyTdrJZ9p7+8OgzXp1kwI9Mmi+WJD5uL0qPH0BVUR6K/tmgTsLBN9RUhe/Q2+LXw7cP9sQ9V/TDnIu64dcNx1TLvHlo3XfLYzB1RCQuHhEJL3cnrUMlIqKzKC6twJ9bj6vLM0ZFaR0OERFZICbt1CZIldoxsL06eQ+ZBmNVBUqTD5sq8XH7VAt9RXaKOuXv/N1q1sPLtkAytO6yCZ3x57YELF53DBnZxZi34hDmr47FhEHtMHN0FEIDOLSOiMgS/bntOErKKtUOIv26WHbHFxERaYNJO7VJdnoHuET0UCeMuQqG0iKUJPyDknhTJb4iK9mq1sO7ONlj+qgoTBlee2jd8k3x+J1D64iILFKVwYilJwfQyWu4HGAmIiKqi0k7kWwf5+wGty6D1UlY63r4hg6tG9wjGHoOrSMi0tS2f1KRnl0MD1cHjB0QrnU4RERkoZi0E9ngeviaQ+uOp+VjUX1D68ZEYfygCA6tIyLSiCxpEpOHdYCzIz+SERFR/fgOQWTj6+EjzjS07pe9+O73gxxaR0SkgdikXPxzLEt1PU0ZEal1OESakMJIVVUVKisrW+13lpWVVZ/rdJaz1LGhGL91xO/g4AC9vvkKY0zaiVp6Pby9I5wjZD18H03Xw591aN2qI5gwOIJD64iIWsmSdUfV+ai+YfDzctE6HKJWT9Zzc3ORmZmpkvbWZDAYYG9vj5SUFKtMGhm/9cTv7e2N4ODgZplXwqSdqFXWw/+tTur2rp7VrfRarIfn0DoiIm1l55di/d/J6vL00R21Doeo1aWlpamk3dPTU50kCWqtQYxykECqpE5OTs1aCW0tjN/y45eDUsXFxcjIyFBfh4SEnPfvZdJO1Mrr4Q3F+XXWw4eoKrwutAvsKvTaDK07loUFq+sbWheFwT1COLSOiKgZLdsYh8oqo3qd7dTOR+twiFo96cnLy0NAQAD8/f01+f3C2dnZapNGwfgtO34XF1MHlSTugYGB5/1YmbQTab4ePlWdsPN3eMEOWf9EojSqX6uth1dD66L81en0oXXZHFpHRNSMyiqqsHxzvLo8Y0yU1uEQtbqKigpV1HBz03ZoL1FLc3V1rf6bZ9JOZCPr4YuO7UGVDLRLO4ZcOWmwHr7u0LrldYbWybAkOXFoHRFR06zZmYT8onIE+rhgaI9grcMh0kxrtcMT2cLfOJN2IgtZD+9aXIyDu7YiwqkMhpRDZ14PL/vDR/Zp0fXwZxpa98OKQ/hFhtYNilDVdw6tIyJqOKkuLllvGkA3bVRHtUyJiIjoXJi0E1kQo4snXLt1g+ugySfXwyeiOG5P7fXwBzaqU/V6+A6ytVwfOLfvAb2Le8sNrdsnQ+tiEZuYq1o7f99iGlo3a0w0ukVyaB0R0bnsOZKJ42kFcHHS44LB7bUOh4iIrASTdiKLXg8foU7nWg+fv+uPU/vDSyW+Y59mXQ+vhtb1DcPIPqahdQvXxGL7gVND67q298GU4RFwMxqb5fcREdki6VoS0q3k5tKy80qIqHUVFhZixIgRaq3+2rVr1T7dRM2FSTuRLe4Pv2lBjfXwpkp8c6yHP9PQuoMJOerk467HoGN26N4xAJ3aeSMs0IOT54mIACRlFKgdOmSJo7TGE5Ft+e233+Dn56f2nv/zzz9x8cUXax0S2RAm7UQ2sz98Fkqklf5s+8Or9fCyP3yf814Pbx5ad+1F3bB0wzEs2xSHnMJKrNiWpE5CWkCjwr3VlkaSxMspyNeVw2eIqM1Zst5UZR/cPRih/pwHQmRrfvnlF4waNQopKSn48ccfmbRTs2LSTmQj7D396uwP39D18L3h3L5nk9fD+5wcWjd1WDiWrt6DEqM74tOKcDQpFyVlVdh/NEudzDxcHdEpwpTAdz6ZzMt9EBHZqoLicqzakaguzxjNbd6IzkQ+v5SVm/bBbilVhiqUyu/QVUKvO7Wsz8lR3+SiwtGjR7Fnzx7MnTtX7UH/5JNPIi4uDpGRkdVbfn3wwQdYtGgRsrOzERUVhQceeEC104uEhAS8/PLL2LZtG+zt7dX1TzzxhKrcP/roo0hOTsa3335b/fv+85//IC0tDd999x2SkpIwYcIE3H///fjmm2/U/uGLFy9WBw/eeOMN7Nq1CyUlJQgKCsI111yDm266qfp+1q9fj/fffx8HDx6El5cXZs2ahXvuuUfd79tvv41NmzZV7zduMBgwduxY3Hbbbep+qHUxaSeyQee1Hl6S+PCujV4P7+xkj57tXdGtWxe1L2WVwYik9AIcSczB4cRcHEnMRXxKnvrwuutghjqZ+Xs5o1PEqWp8dDsfuHO9JxHZiBVbElQiEhnqiZ5RflqHQ2SxCfsj729ATHy2Jr+/WwdfvHLXyCYl7vPnz1effUaPHo3S0lL83//9n6q2P/bYY+r7L7zwAv744w+VbHfv3l1V5f/1r3+p5Nrf318lwV26dMHXX38NnU6Hp59+Gvfee2+tRP1cFi5cqH5eEnTZE1ySc0n+JQ75+ueff8Yrr7yCYcOGoVu3bti9ezduvfVW3HjjjXjxxRfVgYGHHnpIHTSQeF577TWsWLECM2bMUPcvCXxOTg6mTp3a6OeHzh+TdqI24LzWw3foDceg9o1eDy9r2duHeKrTxJNTkisqqxCXkq8SeEnm5TwxvQAn8kpx4uRQO7NQfzdTW/3JqnzHMC84O/Ili4isS2WVAb9uMLXGy24cXB5EZFsqKyuxZMkSjB8/XlW55TRy5EhVVZfqt1TZJal/6qmnMHnyZPUz9913nzpIIcPrpLpeVFSEN998U1W7xfPPP6/WyJeXlzc4jquvvhrR0dHqslTzr7vuOpV8y2A8IRX0zz77DIcOHVJJuxwQ6NOnDx5++GH1fan+P/vss8jKyoKvr696PPK4zEm7HBSQ68wxUuvS/BOwtFpIW4Yc/SkoKMCgQYPU0aV27dqd82flD0mOCK1cuRLh4eGtEi+RLdBqPbyDvR6dI3zUCTC1jJWUVapWelMib0rm07KKkXKiSJ3W7jatj9fp7BAR5GGqxp+syncI8YQ99zkmIgu2eW+qOjDp7e6EMf3DtA6HyGLJAS2pdLdKe3xpGZydnaDX6c+7PV4mxZ84cQJTpkypvk4ur169GsuXL1fJsCTukiDXJAm9kOS+Q4cOtZLhrl27qlNjtG9/ahtJSbolif/1119x4MABHD9+XLXAm3Mvcfjw4er2fLMLL7yw+vKll16K22+/HRkZGaqL4K+//sK7777bqJjIhpJ2Wd8xb948tY4jODhYtWLIepClS5fC0dHxjD8nLRxyNIiIrHc9vHkv+J5R/upkll9UrvaDN1fj5Tw7vwzxqfnq9Oe246Y47HXoGOp1MpE3DbwLC3BXCT4RkSVYvO6oOr94eAd14JKIzkySZllu15KqquwAQ6Xq3pO28fO1YMECdX7XXXed9j1pTX/mmWfO+vPSjt6U6n5dUuE3kwn2V1xxRXXFXCr/vXr1wpgxYxr8e+VnpHVfEn9vb294enqq66gNJu3S8vHFF1/gwQcfVIMNxFtvvaUmL8oaijOtmZAjRFJh79GjB7Zs2dLKURO1xfXwR0yV+LOsh7cP7wZ7oxuqikNhdHE5rxZQTzdH9O8aqE5mWXklOHy8ZiKfi6KSChw6nqNO2HjqIEC0mlh/KpEP9Dm/eIiImuJgQrZ6fZKOoIuGm7qLiMh2SCu5VNovueQStTa8pq+++kqtXReyZ/u+fftqVc8vv/xyNWFeWtrNHcceHh7qe//8848qYkpLuvystNHXlJiYWD0grj6SaOfm5qp19Ob94qUtXkhxRkgHgMRUk6yJl5+VeOSAxsyZM9X2dZKwS5t8cxzkICtM2qVNQ9ZwyEAEM/mjkAEN27dvP2PS/tFHH6k2EzmixaSdqDXWw3dXp+r18McPnEzia6+Hl7eazO0/4ISTKxx8glVF/tR5iDqXVvumJNB+Xi4Y1ktOIdVvOqlZRTiiEnlTMn80OU+12+87ekKdah4EMA25O7VG3seDE+uJqGUtXmuqso/tHw5vDyetwyGiZiZLdaXqfcstt6Bjx461vieD5iTp/t///oc5c+bgnXfeUZXvTp06qTXu0p4uncYhISGq81gKkjJ8Tu5PqvOdO3dWXch9+/ZVt5ff1a9fPzW8LjY2VlXOz0R+TgbS/f777xgwYACOHTuGl156SX3PvE5eDgpIC7zEJQm5TLCXOGQtvJkcjJB18JKsm9e+UxtM2mWrAiF/rDUFBgZWf6+uvXv3quq8/PGmp6c3Sxzy4b+4uPi870f+c9Q8tzaMX1vWE78d7MJ7wFVOo65GVUE2yo//o9rpSxMPQl+aD2NZMcrTjqnTaT/t6AK9dxDsvYNOngerc71PEHQujUvovV11GNTVV51EVZUByZlFOJqcf/KUh4T0QtVuv/NghjqZ+Xk5IyrMs/rUMdQTOlRayb+Btf8N1Y/x135fYneIdcvIKcamk8M1p4+u/WGeiGyDtMYPHz78tIRdREREYOLEiSrZlvXtkvjK9HipqEvF/ZNPPqn+uc8//1wl1VdeeaVqc5cO5EceeUR9b/r06YiJiVHD6SShl2F2V111Ffbv33/GuOQ2Uq2XgwJSpQ8LC8Nll12m5oBJdV1+XobR/fe//1Xr1D/99FOVf0nCLuvYzWStvazFly5nqcxTG03azR9s6q5dd3JyUnsc1iWJtbTSy0n+iJoraZeqvfxnaC7x8fGwZoxfW1YZv84fiJpgOlVVQleSA31RDnTFOdAXZ6tzXVE2dKX5QHkJKjPi1akuo70Tqlx9YHD1MZ27+Z782hdGR1fp3W9QOMGuQHAnYEQnL1RUeSI9pwIp2eVIzipX55l5lcjKK1WnbQdqJPIe9gj1c0TYwQJ1HuzjAEd76xt0Z5V/QzUwfpOzzXUhy7dsYxwMBiN6R/sjMpTTlolskczgOpv33nuv+rJU0uVUH0mIpaJdH2lvl33f5SSqqmSQXmn1GnYZxm1ufTeTg77mnKmmui3848aNU6ezHUCWQXTSNUBtOGk3/7FJm0bN4QllZWX1rtOQI0yRkZHqKFRzkv8M5i0SzvcghHxYkwMKZ1tnYqkYv7ZsJv6o6DPGb6wsR1VeJipz01CVm47KnHTTeW4aDAXZsKssg31+GiCnFqzQSwu9bD13qiKfj4ycEmQVVKrTvpM5lwy0axfohqgwr+qKfLsgd4udWG8zf0OMX7U+kvWS15jftySoyzNGszpFRNZFCpqrVq1Sy5ClaFpzMj61waTd3BYvR3CkhcRMvu7Spctpt5dhDlJ5kPUc5iNNQta+yxGgph4Fkg/7spVBc5EPa815f62N8WvLtuN3BTy9gXadTvuOobJcJfFqyF1OmjqvzDENvJMt6YxnqdDbNXINvYTn5+OJgT1OXZdXWIZ/jqZjy+6jyC93xLGUAuQUlCEhrVCdVu1MVreTyntkmNepNfLtvC1uYr1t/w21jfjZGm/dVu1IVIMyQ/zdMLBbkNbhEBE1uqApxVIhO3tZ83uyrdA0aZf1HO7u7ti6dWt10p6fn6/2E5SBDXXJRPma9uzZo9pMZE2IDGsgIuuls3eEY0A7dWp0Qn+2NfQNTOi93J3Qt5M/nCoz1TovSbykfb56Wr0MvEs6ObE+IUedgDj1s67ONSbWn0zkAzixnqhNkpb4JSe3eZs+qqNFHdAjImqo9evXax0CWUrSLlVzSc5ff/11NU1RhiTI0RyZeDhp0iRVSc/OzlbbH0j7fPv27Wv9vHlYXWhoqNo/kIhsU2sl9EY3P+jzStS2dXBxgb+36TSsV6jpdxmMSMsqwuHjp7adk2F3xaWV2Bt7Qp3MvNwdqxN4czLP6dFEtm/nwXSknCiCm7M9Jgw61UVIRERklUm7uOeee9QkRBmuIEMVBg0apCYoSltGUlISJkyYoKYpypYDREQtndB7yrZ1W7+tf9s63xAE+YQgpH84xg5oVz2x/nh6Qa095BNS85FXWI4dMenqZCbV95rVeKnOu7mY9k8lItuwZJ3p9WTS0A5wcdL8YxYREdkAzd9NZPuDM01TrG8aYk1Dhgw56/eJqG1rbEJfdiIZJZmJ0JcWNKpC7+8bgpDwEEzsFala7isqDTiWkndyD3lTIp+cWYjMnBJ12rTXtA2UkPXw5r3jO7fzUevlnRz0Lf7cEFHzi0/Nx99HMiEd8VNHRGodDhER2QjNk3YiIktJ6GVCqmz/2LVTFBzKCs6r5d7HNwQjfIIxtmcIHEaHocLVH3FZBhxJzDvZWp+jJtZLMi+nNTuT1M/rdXZoH+xZnchLVT4i2MNiJ9YTCdnD9/3338fPP/+s9iCWrrmnn34a7dqdfsDMPJlY9gZetGiRun3Pnj3xxBNPqHkSNbcm2rRpU62fGzx4ML799ltYKvNa9mG9QxHoy8FNRETUPJi0ExHVYScJvWfzr6H3cHLFEJ9gjJQK/chgVLgGILXcDUdyHXEgtQKxSXnILSxTVXo5/XFyyyiZWN9RJtZHnFojH+pvWRPrqW374IMPMG/ePLz88stqLo3Mp5k7d67aw7i+/eafeeYZrFmzRt1e5tK88847uOWWW7B8+XI1x0ZIJ53cbuLEidU/J0vnLFVuQRnW7DIdfJsxitu8ERFR82HSTkSk8Rr6AQAGSoU+IhgG9wDk2HkjpdQVh3OdsCfdDpml9jiYkKNOZrUm1p9M5t0cja32PBCZlZeX44svvsCDDz6IsWPHquveeustjBo1Su36Ituy1pSYmKi2cP3oo4/UbYRsLTRz5kzs378fw4YNQ1ZWljr16dMHAQEBsAa/b4lXS2M6R3ijawcfrcMhIiIbwqSdiEijhL4iJxWVdRJ64Bikztjl5GmadNh6uaDMxQ858EJSqRti8xyRWuGOY0cLsDc2U3oD1O/wdHOAl6sd2u+vRGigJ4J8XRHk46radGUKvoM9W+yp+R08eBBFRUUq2Tbz9PRE9+7dsX379tOS9o0bN6pq+ujRo2vdftWqVdVfS5VdtkyMjLSOdeEVlVVYttG0BeT0UVHc7pGoDbj22mvVa9+CBQvq/b4M2ZbXwD/++OOs9/Pee+9h4cKF1a+BXbp0OesQ7scff1wd/GzoUiFZjvT999/jhhtuqPf3taQrr7wSu3fvxuLFi9VW39R0TNqJiCw8oUdFCZwqkhAMOQEDXQC4nHwz1jkh2+iJ5DI3ZFZ5IC/fFfm5Lkg64IJ8gzMKDC6ogD0kh/DzdEaQnxsCfVxUIm9O6INOJvVcN09NYd5+NSQkpNb1gYGB1d+rKS4uTq11lyr8J598gvT0dJXgP/roo4iKMrWVHz58WCX2zz77rEryXV1dMXnyZNxxxx31tts3hNFoVHMrmkNJSUmt87W7U5BTUAZfTyf06+TdbL+npdSN39owfuuOv6ysTM3BkK2d5dTa5LXAfH4+v1+SanndOnLkCDp27HjaY/z9999x6623nvN3yHNRM5a1a9eq178z/Vxj41+yZIk6CCAHGcT111+vkumWfu7j4+NVwt6hQwe1fOo///lPk+K3NMZGxC/fl39f+b8i5/XdV0MP8jJpJyKy4oTewVCGIGQiyFEq7vUrMTog3yBJvAsK0l2Qn+aCLIMz4uQ6o4tK7AuNLnDy8kaAj7upQu/rikCfk+eS1Hs5Q8+knuph/uBeN5l2cnJCXl7eabcvLCxEQkKCWgf/8MMPqyr7hx9+iKuvvhrLli2Dn5+fStrlQ2/v3r3VQDoZEPnqq68iJSVFnTeFVJvkfpr7Q6l86FqwOkN93S/SCUcOW8+uNhK/NWP81hu/vb29+j+upfP9/dIt5O7urgZqygHFmqS6Lq+NF154odrS+mxk62t5HTHfzjzX40w/Z07+Ghq/LGGqeX+yc5ccCD1XXOfrf//7n0rYp0+frrbzvvvuu9XvNdP63/98NSR+uY38+x47dvqcI7OGHohm0k5EZCMJfUlmEvLSEuGmN8BYnI+qwhwYqyrgYlcBF30FgvT5Z/1dBqMdCrOdkH/ClMhnGl1wzOCskv1CuMLO1QvOXn5w8/WDn58PAqVqfzLB9/NyUZPvqe1xdnau/mBovmz+sOLicrIlpM6HdUncZd27ubIul8eMGaNaNmWAnVTYH3nkEXh5eanvd+7cWQ2hu++++1Si7+/v3+g45eejo6PRHOTDuCQs8oE0Lq0EaTnJcHTQ4eqL+8Pd1XKH5dUXf33/RpaO8Vt3/PLaIAfg5MBezdcMIcmrsaJlkzn5HfJ6JclSzSqnnYNTo5a2SOxTpkxRCfr9999f63u//fabSupl+2qpxL/55puq6ixdODKs86qrrlIHJM2vifJ7zc+FdB698MILmDVrlor1448/xk8//YT8/Hx1EECSQCHPn/zcjh078N///lfNBJHHJZ1MUuGXZFleU2Wgp+jfvz+++uorbNu2TR1o+Ouvv9T1qamp6jV48+bNKj65ncwokTZ9czu+8Pb2VlV7uY1su/1///d/qqPqTBVmOQh7wQUX4KKLLlK7hcjvu/zyy9Vjkr8Bif/XX39VM1Hk70nml0g3gLkjQJYeSFzSlVVUVIQePXqo9wU5l8clO44cOHCg+nfWvU6GmE6aNAnr1q1Ddna2Gngq7yVvvPFG9XVy0Hj8+PF47LHHqv+W5aCyHByWpQ1ygGPEiBHq+5mZmaq74uuvv0avXr2qn395ruTf5O233673uZB/34iICHX7umJjYxv898aknYjIRhJ6x+JipMTEIKJbN3U0W334KStGZVEuqgpzUaXOc1BZmHPysukk3zcU5UFnZ4SnXSk8dXL0/dTQu1ok788HyuP0KrHPMDrjqFTwjS6ocvKEztUbjp4+cPXxh1dAAPyDgxDo7wVfqdQzqbdJ5rb4jIwM9cHETL42f+irST6wyocYc8Iu5MOqfNBMSjJNX5fvmxN2s06dOqlzablvStIuH65qVnmag3zI+2Ob6UPXhIER6m/dmkj8zf2ctCbGb53x63Q6dZKESE5m8p6V8s0TKEvSplvFKbwrQq97vlGJ++zZs1VCvXfvXvTr109dJ8mdJMCSSEsSLQciJfH78ccf1eOVrTFlhw25Tra5lOdCfmfN58L8/EjCLlVqOZApybz8Lkm8BwwYoH7mxIkTKkGfM2cOnnvuOdVR9Omnn+Kpp55Sgz5lpogkvC+++CI2bNigXlclyTf/PjmAKj8rr78yHFQOZMia9+uuu06tQw8LC1O3leR62rRp+O6779SQUDlIIYm4tN3XZ/369eo94OKLL1ZLByTRlsctByvMLeWyfECSYUl6J0yYgH/++UctN5BEWpLjBx54QCXzsstIRESEik+eyz///FM9P6Luc1bzOolb2vLlOZTuBXk/+ve//62WZMkWpdLVtWvXLnVQQt5fZM2/HBiRxy63leRc7lO2L5VYZIaA/BvIgQtJ2uX+5QDGypUr1XNWMxYzuU7uQ/6v1D1AZY6xoZi0ExHZKHkzsHN2g6OzG+AXdtbbGg1VqFLV+VPJvZxXSlJfmIOyvGxUFOYAxXnQVZbC0a4KfvpC+KGw9h0VnzzJUuaTncjpBkfEGl1QondDlaMH7Fy84eDpAxdvX3j4BcA3KEidjDq+JVkjGS4kLaJbt26tTtrlg49UO+TDYF2yh7tUJfbt26c++Ahp05TBSlK1ElJpkQpVzQ+Ecnuplkt1z1KkZRdj6z+mdfvTRtVe00pETWFdB3dlCY9Ub2V7S3PSLkmdJIRSaZclQpIEXnPNNXBzc1Pfv+eee/DZZ5+pgZuStJ+JHMSQRFF+3jzQU5LcLVu2VN9GKtbSdn7zzTdXJ4CSxEslXRLegQMHVrfb17cTh8Sak5Ojhun5+vqq66QSLVVqGV4nnU3CPGNEXoPlgKsk47L2/kzk/uQArRxcEBL/K6+8og5uSAIvvvnmG3U/EruQ13Y5wCDJrbSTSzVcDliMHDlSfV86BiShl3gbSjq4hg8fXv21HCiR9yDzAWV5n5EDEbIkS0h3gMQgnRHmA8eyu4l0TsgBmEsvvVRV1OVAg8Qp25RKTOYYWxI/IREREex0eti7+6jTuRgqympV6iWZL8w6geKcEygvyIGhKBe6snw4VRZBjyq46srhCllTlwd1dvIiEk33V3TyZIAdHOCCg6s8ABcvFYuzly/c/fxVcm/v4a2u07v5wM7RmRO6LYRUZiQ5f/3119WHPqnMSBVJPrBJa6JUVaQNUT70yYcc+RApH6KkzVE+BErLpVRspCIxY8YMdZ/SAiqVIflALB+GJGGXdkX5cCcHCCzF71sSITOJBnQNRLsg0wdjImoaeU2XSndLt8fLa5K5PbtmdbSx7fFmkshJNVcqttIlJAmztLbLfctroszrkEq1HMg8fvy42nFD1DeYrCZJTqVqbz64ada3b1/Vci/kQKlUpSUBlsSz5v03ZMib/Iwky+aEXcjrtLz2mhNZ8++RhN1MXs+lql8feb2XyfTyvmB+PiU5l9dw6TaQjgDz7667u4i0z5ur8ObHaubk5KQOWgipkDdE+/bta30t/xYSm7TSy0ENaU+XDi/zIEHz81Gz00sOTJsn30u3gRx8WLNmjXq/kvuR8/qq7M2NSTsRETWKzsEJOu8gOHgHVV/nfYYqgaG0CBUFOcjOSEdeRgaKsk+gNC9HVfLtSvPhUFkAV0Mx3OxKVXu+u5Tpy+WUbkrskwFp1q87LqdK5wCjtOO7ecPJy1cl9yqhd/eG3s0benUAQi57wU5v+WuMrZ1UjqR6LlscSdVcKhlSIZEPefKBSFofa25hJK2EkuTfdddd6vayhlI+dJo/OJo/7EmVSZJ3qRBJ66JUkCxFaYUBa3alqsvTR59q9Sei8+wQczy9jbg5GauqYGcAdI7O0DVDsiVrx+X1THa6kNcqSail/VpI0n3FFVeo1zZZOy0HISUJlwrwuZgTXvO0cjM5MGAmSackolK9loOhcqDUx8cHl112WYNir3vfZnJAoebvacyuHdJ1IAm9tJfL63rN3yWVbKney3tDzYMAddX83Q1VVc9Bipot6fKYbrvtNvXvIwcL5ECCPG+ylKChv1eSeXk/k8chXQQyp0Aq8a2BSTsREbUItWbOxV2dQgPbIfQMt6uqMuBEdiGSEhJxJCYGrno7VBTkqdZ8lOTBoaIA7nYl8NTJqRTOdhXQGyqAkix1qjhxFBVni8PZ3ZTASyJ/MqE/ldx7w97N9LXOxR12dpyQ3xRSZXjooYfUqS5pP5Q20JqkWi6tjuYBSfWRdlI5WardR4tQUlalKuz9Op/edkpEbYM5IZdETuZtyEFLc4VXKuy5ublqWJ05STW/Hp4pYTaT5FtmhuzcuVO1q5vJ2m/z+m2pXEsr/pdffln9ffP+6+b7P1v3gLSJS2eArFOX+xHShSBD7WbOnNmk50Na480D32qSxyGv+dKSL90J0mYvXVQ1ycFdGYwnQ0eFfH/YsGHqshwYloMS5qRfyJp8c/fVuXYzkN1DpOVeptr36dNHXScHF6Q7Qdb0CxlWKmvvCwoKqpcVyPMta+mlqi4dZHLw+c4771TPm3Qk1JzP0pKYtBMRkaZkK7mgAE94uEUCdqVqjV/N4UaVktTnliAjpxgp2cXIzMxDflamqR0/Xyr2efCwK1EnSeoluTddLoHezghjaSEq5HTCNOTsjHR6VZmX9nv7Gkl97cq96Tqdo/VNfKbmYzAYsfWQaZ7DjNEduVSDqI2TgXSyzlnWN8saczNJ8mTavrR7S2VW1mqbZ3WYt2I7m1tuuUW1Y0v7tiwtkuFwsi7c3DYu9y/DOWV9uSSckmCaK7/m+ze/n0oiXncHDWn3ltb+e++9Vx10lYq6DNCTAWvSIdBY8vulPV+WPkniXpP8bunAkqRZknZJhGUwnCS+0nmwZ88e/PDDD+pnIyMjVYIuE+ol0Q8KCsInn3yiDigMHjxYrTuX113p2pIZKJLcS1J9NnJARSrpsg5dDrTIwRQZbifdEObnSp4P2Y5Ungt5TuRAgfx+eSzyXAs5iCA/L1PvZXBea2HSTkREFs1er0Own5s61aei0oCsvBKkZxerU5Kc5xQjI6sIBTkyLT/XlNSrSn3t5N7z5PXuujJAhvEVZKvTuT5KSfumJPCmNfamRN7g7Ak7h1NLBsh2bY/JQG5RFTxcHTB2wOnbMRJR2yJt75IcSyIoMznMJk+erBJZmYAuVWGZ+SGt6zJxXBJNmaZ+NtJtJG3dH374oZoULxPhJeE9evSo+r4MqZMDAVJ9lsRT1mObJ7vL/cswvKFDh6rK8pVXXqnmjdQk1WQZxCbxyRIkIQcXJHk2V58bW2WXAxeyZKAu6Q64/vrr1UEFaSsfN26cStBl2r0cmJDnRtasmyv8sjRK1sFLYl9eXq4egyT9kjDLSRJ6OeAgE+IlZnkOZFbKmUjiL49TEn0ZsidLGcaOHaset7k7Qaa8y++QAyvyfEl7vdym5v3K45ChqfK8mYentgY747l6M2ycuS2j7pCHppCjUtJ6UbdKZC0Yv7YYv/as/TEwfpwxqc/MLUaGSupNFXvTZdMpO79UDcxzV9vdmRJ6leDXSPS99KXw1peqhN/eeOZm/NKIAehw6b3nHX9zvjdR8z+fD727FgcTcjFrTCRumt4b1oavFdpq6/HLHIu4uDhVTa1vG6yWJmufJQb53a0xQKy5MX7t45ckXlLouksAGvu33pj3JlbaiYjIpjnY6xDq765O9SmvqFLt9+YkXpJ6OT9+8nJ2fu1Jxo6oOJncS9XelOj7OpTCx9kIR5cesJwNyaglHE3KVQm7zg6YNDhc63CIiKiVyLBBGWQnMwpqDtlrDUzaiYioTXN00CM0wF2d6lNWUYVMVZ0vMbXdSzJ/MsFPyClGbkEZIHl9ITA8wB0TWv0RUGuSzgzRp6MrfD1bv0pIRETa+OWXX9R2bzKFXtbityYm7URERGfh5KBHeKCHOtWntLwSmTklyMjKR0WBaQswsl0DuwXh5duHoDD7HIMNiYjIprz55pvV7f2tjXvbEBERnQdnR3u17Ve3Dj5wsOcUcVsnE4sjQz1hr+e/NRERtQ4m7UREREREREQWikk7ERERERG1qja+gRW1AcZm/Btn0k5ERERERK3CwcFBLTMpKirSOhSiFt8e0fw3f744iI6IiIiIiFqF7M3t5eWFzMxMlJWVwdPTE/b29iqRbw0ySEx+rzkWa8P4LT9+qbBLwp6RkQFvb+9meZxM2omIiIiIqNUEBwfDxcVFJTX5+fmt+rsNBgMqKyvVgQKdzvqajhm/9cQvCbv8rTcHJu1ERERERNRqpKouCY1U3KVyKUlQaykpKcGxY8cQERGhDhxYG8ZvHfFLS3xzdhIwaSciIiIiIk2Sd6lYyqk1K6XCyckJzs7OsDaMv23Gb309CURERERERERtBJN2IiIiIiIiIgvFpJ2IiIiIiIjIQtkZm3PXdyu0a9cuNZbf0dHxvO9L7qeioqJ6/0lrw/i1xfi1Z+2PgfHbTvzl5eXqPvr3799s8bVlzfleL/i3qi3Gry3Gry3G3zbf69v8ILrm/GOR+2quDwRaYPzaYvzas/bHwPhtJ365L2v8MGOpmvu55N+qthi/thi/thh/23yvb/OVdiIiIiIiIiJLxTXtRERERERERBaKSTsRERERERGRhWLSTkRERERERGShmLQTERERERERWSgm7UREREREREQWikk7ERERERERkYVi0k5ERERERERkoZi0ExEREREREVkoJu1EREREREREFopJOxEREREREZGFYtJOREREREREZKGYtBMRERERERFZKCbtjWAwGPDuu+9i1KhR6Nu3L2655RYkJiae8fY5OTl44IEHMGjQIAwePBj/93//h5KSElhL/EuWLEGXLl1OOyUlJUFrH3/8Ma699tqz3sbSnv+mPAZL+jfIzc3F008/jdGjR6N///646qqrsGPHjjPeXmK87bbb1G1HjhyJt99+G1VVVdBKY+P/8MMP633utZSVlYWHHnoIQ4cORb9+/XDrrbfi6NGjVvN/oLHxW9Lff01xcXEq/gULFljNc0+Nw/d7y/i/Zgvv99b2Xi/4fq/t+z3f6y3n9SfOgt7v7Zv9Hm3YBx98gHnz5uHll19GcHAwXnvtNcydOxdLly6Fo6Pjabe/55571D/aV199hfz8fDzxxBMoLi7GK6+8YhXxHzp0SP3xvfnmm7Wu9/X1hZa+//579YYwcODAs97O0p7/pjwGS/o3uP/++5GZmali8fPzw7fffoubb74ZCxcuRMeOHWvdtqKiQn2vQ4cO+PHHH3H8+HH1/Ot0OvXvooXGxG9+7mfMmKHeeCzFnXfeqT6Mf/LJJ3Bzc8M777yDG264AStWrICLi4vF/x9obPyW9Pdf82/7wQcfVM/j2Vjac0+Nw/d7E77ft733esH3e23xvd4yXn8qLO393kgNUlZWZuzXr5/x+++/r74uLy/P2Lt3b+PSpUtPu/2uXbuMnTt3NsbGxlZft379emOXLl2MaWlpRkuPX8ydO9f43HPPGS2FPG+33XabsW/fvsbJkycb58yZc8bbWtrz35THYEn/BvHx8er53LFjR/V1BoPBOHHiROPbb7992u3lb6pnz57G3Nzc6ut+/PFHY//+/dXfoqXHLy666CLjl19+abQU8lzef//9xkOHDlVfFxMTox7Xnj17LP7/QGPjt6S//5reeOMN43XXXafi/uWXX+q9jaU999Q4fL/XnrW/31vre73g+722+F5vOd6wsPd7tsc30MGDB1FUVIRhw4ZVX+fp6Ynu3btj+/btp91e2nACAgIQFRVVfZ0cRbKzs8POnTth6fGbj3zVjF9r//zzDxwcHFQbTZ8+fc56W0t7/pvyGCzp38DHx0cdMe3Vq1f1dfJcykmOKtb3/Pfo0QNeXl7V10mbVGFhIWJiYmDp8ZeXlyM+Pr7eI/JakefyjTfeQOfOndXX2dnZ6qiuVNGio6Mt/v9AY+O3pL9/M3mt/Omnn1T18mws7bmnxuH7vfas/f3eWt/rBd/vtcX3esuw3QLf75m0N1BaWpo6DwkJqXV9YGBg9fdqSk9PP+220pLm7e2N1NRUWHr8eXl56jHIH+O0adPUGqU77rhDre3Qyvjx4/Hee++hXbt257ytpT3/TXkMlvRvIB/4xowZU6ut8o8//kBCQoJaM1mX/E3JC3TdvzWhxfPf2PhjY2PVejy5zYUXXoixY8eqtrmMjAxYgqeeekp9IP/tt9/wwgsvwNXV1Wr+DzQ0fkv6+xfyYe/hhx/Gk08+edrzak3PPZ0b3+/5ft9W3+sF3+8t5/2e7/XayLfQ93sm7Q1kHihQdy2Yk5MTysrK6r19fevGznR7S4v/yJEj6txoNOKll15Sa7LkdldffTVOnDgBS2dpz39TWPK/wa5du/DYY49h0qRJ6g2urtLS0nr/1oQlPP/niv/w4cPqXNZeyVosebM5duwYrrvuOvXYtHb99f/f3p3GxvT1ARw/ePyV2JeIhBBRRS2ltJaGVPBCJFpvWutDa6+RILSNrRSJBrU0Kl6Q4KWlrwithoRuYukSEqJBtZKqrYitdZ/8zpOZdGo8nelD58z0+0mmnd57p3PmzLnzu+fOub/zb3XhwgU1Z84cfe2YfKvjS/uAO+U3rf2npKToZDRyUNEUk+seTSPemxNr3GFa/XvK9Pon3nsPsd477T/F0HhPIjo3BQQEOIbR2O8LeUNcJVWQbWTbxmR7V2eaTCu/JE3Jz8/Xw4xkiIfIyMjQH3iSQVEyQZrMtPpvDlPfg5ycHJ2YQzKyHjhwwO36t394ebv+3Sl/VFSUzjrbMAlKYGCgXpabm6tmz56tvMk+xEwOLoqLi9W5c+d0sPOVfcCd8pvU/rOysvS3AJLEyx0m1z2aRrw3I9a4y7T695TJ9U+89268J9a3fPvPMjje8027m+xDHxoPl5G/+/bt+8v2MlSo8bbypso0FPZhQyaXX8gHmH0HEhLs+/fvr4eCmM60+m8u094D+cC12WwqMjJSnThxwnE23Z36t//9u/ZmUvldZS2VdiPDnVwNL20Jcl2YDDGrq6tzLJPsvBIUXQ3jM20f8LT8JrV/+aZAprCRgwg5+y43sXPnTp2R2/S6h2eI996PNZ4wrf6bw8T6J957J94T673b/i8YHO/ptLtp2LBhqnPnzqqwsNDpmoeHDx/qefkak2Wys8s1NHZFRUX6d2hoqDK9/JJ8ITw83GmaA0kqIsk6fpdIwiSm1X9zmPYeyPRBqampauHChXpaDlfDgRrWv7QtKa9dQUGBnvpD2qI3eFL+9PR0fW2bDNeyk/lCZS5Ob7V/GSYm09jIGemG05FIPbtK4GLaPuBp+U1q//INzeXLl/UZePvNPs2LfINget3DM8R74n1LMrH+iffei/fEeu+2/wMmx/s/movezx06dMgKCwuzcnJy9PQFcXFx1qxZs6zv379bdXV1VnV1tfXlyxfH9BKxsbFWdHS0nuIgPz/fioyMtJKSknyi/FVVVdb48eOthIQE6/Hjx1ZJSYm1dOlSPWXG169fLW9LTEx0mkLFF+rf09dg0ntQXl5uBQcH67JIGRveamtr9bQuct8+vYuUT8oZHx+v21p2drZue8eOHWvRcje3/KWlpXr7HTt26McWFRVZUVFRuk1J2/IWmRZF9lkpj0ynItOqTJgwwaqsrPSJfcCT8pvU/l1pOAWML9Q9PEO8N2df8/V470uxXhDvvR/vifXmfP6YFO/ptHtA3qi0tDRr4sSJeu7NFStWWBUVFXqd/G48j19NTY1ls9n0tuHh4dbOnTu92gA9LX9ZWZm1bNkyKzQ0VM+3Ka9Fdi4Tg6Av1H9zXoMp70FmZqYum6ubvI6CggJ9X343nCtVyj5q1CgrIiJCz49aX1/f4mVvbvnz8vKsmJgY3X7kACQ5OdlpHlpvkAMOacdTpkzRcy7LgbgEOV/ZBzwtvynt35WGZfWFuodniPfm7Gu+Hu99KdYL4r334z2x3pzPH5PifRv58We/uwcAAAAAAH8C17QDAAAAAGAoOu0AAAAAABiKTjsAAAAAAIai0w4AAAAAgKHotAMAAAAAYCg67QAAAAAAGIpOOwAAAAAAhqLTDgAAAACAof7l7QIA+PuSkpLUpUuXfru+d+/e6vbt2y1apqCgILVu3Tpls9la9HkBAPBHxHrAf9FpB1qJPn36qIyMDJfr2rdv3+LlAQAAfxaxHvBPdNqBVuKff/5RISEh3i4GAAD4S4j1gH/imnYADosXL9bD606cOKEmT56sQkND1dq1a1VlZaXTdqWlpSo+Pl6Fh4ercePGqdWrV6snT544bVNdXa0SExPVpEmT1NixY9WiRYvU/fv3nbb59OmT2rp1qwoLC9PbrF+/XtXU1DjWv3jxQv9veZ4xY8aomJgYdfPmzb9cCwAA+C9iPeB76LQDrUhdXZ3Lm2VZjm2uX7+uLl68qLZt26Z27dqlHj16pAP8ly9f9PqCggI1f/58fX/fvn1qz5496tWrVyo2NlY9ffpUL//8+bPeprCwUG3evFkP1evQoYOKi4tTz549czzXmTNn1I8fP9SRI0fUpk2bVG5urtq9e7de9/PnT7Vq1Sr9vGlpaer48eOqe/fuas2aNer58+ctXHMAAPgGYj3gfxgeD7QScgY9ODjY5botW7bos+lCAqcE8gEDBui/Bw8erKKjo1VWVpYOzgcPHlQDBw5UJ0+eVO3atdPbREREqJkzZ6qjR4/qoCyJcOT55Pfw4cP1NnKWPioqSt25c0cNGjRILxs1apQO0kLO0hcXFzvOrr9580aVl5frs//Tpk3Ty0aPHq0PCr5///7X6wsAAF9DrAf8E512oBUlp8nMzHS5rl+/fo77EnDtQVyMGDFC/y0BeO7cuXq4nGSCtQdx0bVrVxUZGekIwnfv3lX9+/d3BHHRsWNHdfXqVafnlSF5DcljamtrHVluhwwZorZv365u3bqlDxamTp2qkpOT/++6AADAHxHrAf9Epx1oRclp5Gx3U/r27fvLsl69eqkPHz6ojx8/6uF1EmQbk2WyXrx//14/pimdOnVy+rtt27aO4Xtt2rRRp06d0gcf2dnZ+uy/ZL6dMWOGHsrXrVu3Jv8/AACtCbEe8E9c0w7Aybt3735ZJgljevbsqbp06aIDbMMEMnavX7/W16EJ2e7t27e/bHPv3j3HtXDukIOKlJQUffZdArkM67t27Zo6fPiwx68LAAD8F7Ee8C102gE4keFuDYN5WVmZevnypb4OTc6Wjxw5Ul25ckXV19c7tpGz7jdu3HAMgRs/fryqqKhwyjL77ds3ZbPZ1Pnz590qh2Sflay2JSUl+uBBht9t2LBBDR06VFVVVf3R1wwAQGtCrAd8C8PjgVZCEro8ePDgt+uDgoIcyWmWL1+uM7dKZtj09HQdPOfMmaPXS+ZXOQu+cuVKtWDBAp0RVhLVyP9PSEjQ28ybN0+dPXtW/w+Z2qVHjx6O7LHyGHfI9XUBAQE6cY4cAMiQvLy8PJ3hdsmSJX+kTgAA8CfEesA/0WkHWgkZ0iZzn/6ODEmznzmfOHGinlNVTJ8+XQdTuU5OyFn406dP6+yxGzdu1MvlMfv371eBgYF6m86dO6tz587pbLGpqal6SpeQkBAdzBsmvvlfZNoYuc5NMtju3btXJ62RTLQyTYwcKAAAAGfEesA/tbEaTtoIoFWTOVqFnDkHAAD+h1gP+B6uaQcAAAAAwFB02gEAAAAAMBTD4wEAAAAAMBTftAMAAAAAYCg67QAAAAAAGIpOOwAAAAAAhqLTDgAAAACAoei0AwAAAABgKDrtAAAAAAAYik47AAAAAACGotMOAAAAAIAy038AFfQK8k20posAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_learning_curves(history_df)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Exploitation des prédictions\n",
    "\n",
    "On souhaite à présent utiliser le modèle pour prédire le chiffre présent dans une image.\n",
    "\n",
    "**Consigne** : Prédire sur le jeu de test à l'aide de la méthode [`predict`](https://keras.io/api/models/model_training_apis/#predict-method), puis observer le résultat sur la première image."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 427us/step\n",
      "[6.0739734e-05 4.0368459e-04 9.8676115e-01 3.0002455e-04 2.9265425e-07\n",
      " 7.8633835e-04 1.1406293e-02 1.2295802e-06 2.7377973e-04 6.4694455e-06]\n"
     ]
    }
   ],
   "source": [
    "predictions = model.predict(X_test)\n",
    "\n",
    "print(predictions[1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne** : Après avoir vérifier que si l'on somme les chiffres affichés pour la première image vaut bien 1, identifier la classe prédite par le modèle. Vérifier visuellement."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1.0\n",
      "2\n",
      "2\n"
     ]
    }
   ],
   "source": [
    "print(np.sum(predictions[1]))\n",
    "print(np.argmax(predictions[1]))\n",
    "print(y_test[1])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Quel est l'impact du learning rate ?\n",
    "\n",
    "On s'intéresse à présent à l'importance du choix du learning rate. On se propose de tester plusieurs valeurs pour obtenir les meilleurs performances.\n",
    "\n",
    "**Consigne** : Définir une fonction `get_model` qui prend en paramètre un `float` qui correspond à un learning rate. La fonction renvoie un modèle compilé avec les mêmes paramètres que précédemment, sauf la valeur du learning rate qui est renseignée par l'utilisateur."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "def get_model(learning_rate: float) -> keras.Model:\n",
    "    model = keras.models.Sequential(\n",
    "        [\n",
    "            keras.layers.Input(shape=[28, 28]),\n",
    "            keras.layers.Flatten(),\n",
    "            keras.layers.Dense(256, activation=\"relu\"),\n",
    "            keras.layers.Dense(128, activation=\"relu\"),\n",
    "            keras.layers.Dense(10, activation=\"softmax\"),\n",
    "        ]\n",
    "    )\n",
    "    model.compile(\n",
    "        loss=\"sparse_categorical_crossentropy\",\n",
    "        optimizer=keras.optimizers.SGD(learning_rate=learning_rate),\n",
    "        metrics=[\"accuracy\"],\n",
    "    )\n",
    "\n",
    "    return model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Avant de lancer sur plusieurs époques, commençons par écrire une ébauche de la boucle de comparaison avec 5 époques."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Learning rate: 0.1 - époques: 5\n",
      "Epoch 1/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 923us/step - accuracy: 0.9294 - loss: 0.2604 - val_accuracy: 0.9551 - val_loss: 0.2009\n",
      "Epoch 2/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 844us/step - accuracy: 0.9674 - loss: 0.1181 - val_accuracy: 0.9597 - val_loss: 0.2333\n",
      "Epoch 3/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 846us/step - accuracy: 0.9787 - loss: 0.0740 - val_accuracy: 0.9691 - val_loss: 0.1443\n",
      "Epoch 4/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 862us/step - accuracy: 0.9871 - loss: 0.0469 - val_accuracy: 0.9673 - val_loss: 0.2344\n",
      "Epoch 5/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 894us/step - accuracy: 0.9915 - loss: 0.0333 - val_accuracy: 0.9688 - val_loss: 0.1642\n",
      "Learning rate: 0.01 - époques: 5\n",
      "Epoch 1/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m3s\u001b[0m 2ms/step - accuracy: 0.8728 - loss: 0.4616 - val_accuracy: 0.9284 - val_loss: 0.2625\n",
      "Epoch 2/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9428 - loss: 0.1983 - val_accuracy: 0.9450 - val_loss: 0.2082\n",
      "Epoch 3/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9572 - loss: 0.1477 - val_accuracy: 0.9517 - val_loss: 0.1845\n",
      "Epoch 4/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9659 - loss: 0.1174 - val_accuracy: 0.9580 - val_loss: 0.1667\n",
      "Epoch 5/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 979us/step - accuracy: 0.9725 - loss: 0.0971 - val_accuracy: 0.9612 - val_loss: 0.1587\n",
      "Learning rate: 0.001 - époques: 5\n",
      "Epoch 1/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 917us/step - accuracy: 0.6303 - loss: 1.3171 - val_accuracy: 0.8044 - val_loss: 0.7800\n",
      "Epoch 2/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 840us/step - accuracy: 0.8430 - loss: 0.6094 - val_accuracy: 0.8692 - val_loss: 0.5088\n",
      "Epoch 3/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 835us/step - accuracy: 0.8806 - loss: 0.4418 - val_accuracy: 0.8893 - val_loss: 0.4054\n",
      "Epoch 4/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 932us/step - accuracy: 0.8979 - loss: 0.3657 - val_accuracy: 0.9027 - val_loss: 0.3520\n",
      "Epoch 5/5\n",
      "\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 861us/step - accuracy: 0.9093 - loss: 0.3207 - val_accuracy: 0.9101 - val_loss: 0.3175\n"
     ]
    }
   ],
   "source": [
    "n_epochs = 5\n",
    "batch_size = 32\n",
    "learning_rates = [10 ** (-power) for power in range(1, 4)]\n",
    "\n",
    "results = []\n",
    "for learning_rate in learning_rates:\n",
    "    print(f\"Learning rate: {learning_rate} - époques: {n_epochs}\")\n",
    "    model = get_model(learning_rate=learning_rate)\n",
    "    history = model.fit(\n",
    "        X_train,\n",
    "        y_train,\n",
    "        epochs=n_epochs,\n",
    "        batch_size=batch_size,\n",
    "        validation_data=(X_valid, y_valid),\n",
    "    )\n",
    "    result = {\n",
    "        \"learning_rate\": learning_rate,\n",
    "        \"n_epochs\": n_epochs,\n",
    "        \"history\": pd.DataFrame(history.history),\n",
    "    }\n",
    "    results.append(result)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne** : Définir une fonction `show_results` qui prend en paramètre l'objet *results* construit précédemment et qui renvoie un graphique similaire à celui renvoyé par `plot_learning_curves`. Cependant, les différentes itérations doivent être présente sur chaque graphique, ici les courbes d'entraînement pour chaque learning rate, avec la bonne légende pour chaque graphique."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "def show_results(results: list) -> None:\n",
    "    plt.figure(figsize=(12, 4))\n",
    "    colors = sns.color_palette(\"husl\", len(results))\n",
    "    for _, result in enumerate(results):\n",
    "        history_df = result[\"history\"]\n",
    "        learning_rate = result[\"learning_rate\"]\n",
    "\n",
    "        plt.subplot(1, 2, 1)\n",
    "        plt.plot(history_df[\"val_loss\"], linestyle=\"--\", color=colors[_])\n",
    "        plt.plot(\n",
    "            history_df[\"loss\"], label=f\"LR={learning_rate}\", alpha=0.5, color=colors[_]\n",
    "        )\n",
    "        plt.xlabel(\"Epochs\")\n",
    "        plt.ylabel(\"Loss\")\n",
    "        plt.legend()\n",
    "\n",
    "        plt.subplot(1, 2, 2)\n",
    "        plt.plot(history_df[\"val_accuracy\"], linestyle=\"--\", color=colors[_])\n",
    "        plt.plot(\n",
    "            history_df[\"accuracy\"],\n",
    "            label=f\"LR={learning_rate}\",\n",
    "            alpha=0.5,\n",
    "            color=colors[_],\n",
    "        )\n",
    "        plt.xlabel(\"Epochs\")\n",
    "        plt.ylabel(\"Accuracy\")\n",
    "        plt.legend()\n",
    "\n",
    "    plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "**Consigne**: Lancer l'entraînement pour plus d'époques afin de comparer avec la fonction `show_results` les différences d'entraînement. Commenter.\n",
    "\n",
    "Pour gagner du temps, on pourra augmenter le batch_size à 256 voire 528. Pour éviter de surcharger l'affichage, on peut utiliser le paramètre *verbose* de la méthode `fit` : s'il vaut 0 alors il n'y a aucun affichage."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA+0AAAF3CAYAAADQJaofAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQAA99tJREFUeJzsnQd4HNX19t/tK2nVe7Et2ZZtufcCptoQ08EQAqF3PgIkdEgICSSUAAkECKGXBAgdAgH+OJRQ3XuRu2VbvbftOzPfc+7srFbySpbllXZXOj8/88zs7Ozo7mqtmfeec96jUxRFAcMwDMMwDMMwDMMwUYc+0gNgGIZhGIZhGIZhGCY0LNoZhmEYhmEYhmEYJkph0c4wDMMwDMMwDMMwUQqLdoZhGIZhGIZhGIaJUli0MwzDMAzDMAzDMEyUwqKdYRiGYRiGYRiGYaIUFu0MwzAMwzAMwzAME6UYMcRZu3YtqFW9yWSK9FAYhmEYRuD1eqHT6TBt2rRID2VQwNd6hmEYJpav9UM+0k4XcVrCdS6PxxO28w00PP7IwuOPPLH+Hnj8g2f84bw2MeH/PPm7Gll4/JGFxx9ZePxD81o/5CPt2qz7pEmTDvtcDocDpaWlGD16NOLj4xFr8PgjC48/8sT6e+DxD57xb9y4MWzjYsJ7rSf4uxpZePyRhccfWXj8Q/NaP+Qj7QzDMAzDMAzDMAwTrbBoZxiGYRgmbDz77LO46KKLejymqakJt9xyC2bNmoXZs2fj3nvvhdPp7HTMZ599hpNPPhmTJ0/GmWeeiaVLl/bzyBmGYRgmOmHRzjAMwzBMWHj99dfx+OOPH/S4G2+8EXv37sUrr7yCv/71r/jmm2/w+9//PvD8smXLcNttt+G8887DBx98gHnz5uHqq6/Grl27+vkdMAzDMEz0waKdYRiGYZjDoqamBtdeey0effRRFBYWHtTJfcWKFfjTn/6ECRMmCEF+33334d///rc4D/H8889j4cKFuPjiizFq1Cjccccd4thXX311gN4RwzAMw0QPLNoZhmEYhjksNm/eLMzePvroI0yZMqXHY1etWoXMzEwhxjUoRZ7a3qxevRqyLGPNmjVCzAczZ84crFy5st/eA8MwDMNEK0PePZ5hGCZaoTYgkiTB5/P16ni32x1Y6/WxNyc7VMZP4tZgMGAwcfzxx4ulN1A0PTc3t9M+s9mMlJQUVFVVobW1Vbjz5uTkdDomKysL1dXVh/X/ic4bDrT6+651+LECjz+y8PgjC48/svD4O1+XaMK6N7BoZxiGiTLoj3hzczPq6uqEaO8tFKE0Go2orKyMSdE7lMZPApVEaW8v1oMJutEhkd4Vi8UiJjxcLpd43PUY7fm+4vV6RZuecFJWVoZYhscfWXj8kYXHH1l4/CqhroehYNHOMAwTZVA0kUR7UlKSWEgI9kbckcAnUUPiJhYjuUNh/Fq0t7a2VjzuGnEeClitVng8ngP202dHPW/p8yO6HkPPx8XF9fnnUoYD9dUN18QD3bBR/f7hjClS8PgjC48/svD4IwuPv4OdO3eit7BoZxiGiTLh19LSImp+MzIyDvm1miiKVdE7FMavXeRJuFPKdyy+18OBMgy++OKLTvtIoNNEFX0elIVA4l2b2NCgx9nZ2X3+uTTxRecNJ/S7DPc5BxIef2Th8UcWHn9k4fHjkLLtYi//kGEYZhBDKbwUjU1ISIj0UJh+RLvQ0+97qEG92SmbhFq+aZCbPDFjxgxxEzN9+vTAPo3ly5dj5syZAz5ehmEYhok0LNoZhmGikKFY6zyUGEq/X8pAIH8GrVad3OVJlN90003YsGGD6Ml+zz334MwzzwxE0i+77DJ88sknePnll0Vv9ocffljUo19yySURfjcMwzAMM/BwenwYqWiXsaY1HsO9CmI32YNhGIZhwgc5wi9YsAAPPvggFi9eLCYsnnrqKdx7771ChFMN+6JFi3DXXXcFXjN//nw88MADePrpp/HYY4+JWvRnnnmmU5s4hmEYhukORVbIIZZmjgHaFmt6LEPxrxFirYQ4vtPrXC7EOVqBEgwoLNrDSHmbghq3GUurJJyW1HsLf4ZhGIYZLDz00EOdHhcUFGDbtm2d9qWnp+OJJ57o8TwUeaeFYRiGiW2o7C8ggF0eGNxeoN0BxaMKY6UbAU3CWelGQCPk6zoEt/iZ/YDO64W1vR0DDYv2MFKSpsdSnYLKdgV7WiSMTOGPl2GYoQv17T7rrLNwww03HPDc+++/3ymySlCbNKrlnzhxIm6//XaMHz/+kH4epU/ff//92LRpE9LS0nDppZfi4osv7tVrV69ejQsvvDDsLcEYhmEYJtoQEeNuos0HRqElQCLRLfUgrnvxuiDRm1ZfD12DEz6TaUDer47asBr0dKNxwFpHZrB6HSDWQc+L5w58jZeMU6srkIOBhVVlGEmy6DAqzoUmAMsqvchPNMBi4Gg7wzBMd3z//fedHMQpIkvp0FdccYVwGO+tIV9TU5Oog6aJAkq7XrdunVjT688+++yDCvbrrrtO9FlnGIZhmGhARJh9PsCrLop/jfZ2xNU2A9YKSCR6u03z7iycOwnsfopC9+p96XRQ9HooZhN0VgugNwCkl3oS0IbuRHTH8UKYdye+aX+4cDig1FdjoGHRHmaK4t2QLTo4vApWV3lxRIE50kNiGIaJWqi1XbBhGbX7uvvuu0WEnAzKqBa6N7z99tuiD/d9990n+tpT7TO5kz/33HPdinafz4dHHnkEr7/+OsaMGSNajjEMwzBMuBDi2CepYtsXJLyDhXgoYU7btD8EFKm21TdC59NDDkOkWhXCmnCmdYcw7jlCHfy6EAK6m9d5XS7Ul5Yis6QExhhu+TbQsGgPM/S9nZOjx9eVwNZGH0anGpCVMLR68DIM048X/6AUswOep1ounwSFlnBPotPFe4B8OsxmdbKTxDdx55134oMPPgh5LKXfUw31qlWrMHv27MBriLlz5+LZZ59FfX19yJ73DocDK1euxAsvvIDKysoD0vUZhmEYJnDt7YPwFscf5gVZR9c1kwEwGaEzmaDIElySC0p+FvRxcX6RfCjR6c5Ravbgig1YtPcDOQl6FKcZsaPRhx8qvDh9tB6GcKZlMAwz5KCLvrR8I5Tm1h6P0fl8kI1GkX4WTnSpSTDMntTvF/eKigr8+c9/Rl5enujnTfzmN7/BLbfcEvJ4q9Uq1tT3m6LlwWRlZQXcy0OJ9qSkJFFbT2hrhmEYZnAi0sW9XsDuhMnuAuqaIBvb/ULb2xER93qheDu2xWT4YZZPibRvIbxNqvg2ht6mY3TatthvVKPWwTgcaDP6gHFFMHCkesjAor2fmJ1rwv5WCY1OGZvrfZicNTBGCwzDDGIG4dzftGnTAtter1ekuB955JEieh7vvxlJTEwUS09QD3AtQq9BrcQIt9vdL2NnGIZhoqTO+4AouFdknQWEt5fM0KRAenkKGaG1eNSa8F4ixHOw2A4S4bRf163wNqnRboY5DFi09xNWo04I92/3e7C2xouiFAMSzfwflmGYvkERbop095QeTzXhissFvdUKA83qx0B6/IcffijWDQ0NePzxx1FXV4df/vKXok2Yxj333IOPP/445OtPO+00UcdOEXcysgtGE+ua+GcYhmGirM47lLgOinAHouD+yHd3dd69ha5jiskIyWyCkmSDPiHeL7RJYJMQ92/7F/FYpKcbB7RMjGG6wqK9H6F69h1NelS1y1ha4cUJhWb+z84wTJ8Rfz9o1r7b5+mvukGk2olUvBhgxIgRgfXTTz+Nc889F1deeaUQ86mpqeI5EvHkJh8Km80m1jk5Oaitre30nPY4Ozu7n98FwzDMEMMvvBWn+5CFd/jqvLuJavv3h0w/p22nE42lpcguKeH0ciZmYNHezzfYR+Sb8eF2l0iVL2uRUMS92xmGYUISFxcn+qxTv3SKnlPrNyI9PV0sPUH172+++abINtCyDMh9vqio6KCvZRiGYfyp5ySuPV4obg/g9m97grZpv92OzMoq6KraDqvPtlrnHTqq3SnCrT0OjoizVxQzxGAF2c+kWPWinp1S5LXe7Wbu3c4wzBCB2q59++23Ic3jQkFmchRpf+aZZ0TqO/Vd7w3U1o1c4Mm0jl6/YcMGvPLKK6JXu0ZbW5uom09LSzuMd8QwDBPDQtzjFQL8ACHu8W/3IgJONeFQguq8u4rtYCHek/DmOm+G6TUs2geAyVlG7Gr2odWtYHW1F/PyuXc7wzBDA6pF71qPnp+fj+uvv77b11x77bVYsmSJENzUxk1Lge8JiqaTaKdIPbWBo/7vt99+u9jWoOdWrFiBr7766jDfFcMwTOQQwloT2UKEqwI8sN01On4IqeiiDItEtcUMndkk1jCboLOYqB+n2PbKPjTs2Y2M8eNhSLRx6SfDDAAs2gcAo15Nk/+/3W6UNvhQnGpERjzPLjIMM7g5mDhevHhxyP3kAv/ZZ58d8s+bPHky3nrrrW6fJ0f6nsbS3XgYhmEiIsRFFPzwhTihCXCx1raFEFfFeKftg6WeOxyQNcd0FuwMMyCwaB8gKC2ejOl2Nkn4vtyD04st0PMfOoZhGIZhmEGJENZkvOb2+IU4CW4P0NqGxP11gFsP4YWupayHQ4iLdVchbjqw1zfDMIcE/f+UFB9cPsdhGyn2BRbtA8isXDP2tbrQ4JSxpd6HiZncu51hGIZhGCbWhXhgW9vvj4qHurmnmnBrUxt0BguULkZumgDX+dPSA9uWEPtZiDPMQZEUCT7JA6/shU/2wiur27T2BW2rj33qtkTbHfu11yqKLLxxvA5gPMZjIGHRPoDEm3SYlWvCD+UerKHe7ckGJHDvdoZhGIZhmMgL8W5d0z1qmnoPQrwnREsyS4fgpht/u1FGRvFIGJITWYgzTBfo/1hXge0VoloT2/59UpfHge2O/ZIs8lnCh04Hqz4OAw2L9gFmbBqlyOtRY5eFm/yCQkukh8QwDMMwDDO4hXiwa7q/ZlwV4n6BLst9EuLB0e+AWRsJ9GATt65C3OGAQ3IAeZnQR3mfcHKfV5pbAbsDit0l1mhuRVp1NdDihZSbBUPJyMDx0tpSIWrEQu7w9N7927qEOOjzswPHypW1qgu9wX8MHavXBRzpdbaOz0ZkL1Ctvf98XEsfvenjwYK5Q1x3iO92Zxv2uHbDXlsHvUnXOeodJMLDjUFvhElvhlFnhFFngklvgglGmIxWmEwW8ZxB1sHkhbpfZ4IBBpgU2lYfm5KT4YUBW7duxUDDon2AoT8yRxaovdupb/u+FgnDk9WewgzDMAzDMEz3CDHudMHU7gRqGiDrmoPS0YNT1sMsxLXt7oR4DKH4JMjbywC7E4rDCcXuVLf9a92oYTAtmq8e7PXC88dnO72e3nmu2NoBaeLoTqLd+/onQDefu37MCJiv/VngseepfwEud8hjdYV5sNx4YeCx+4HngFZ70MloYkCvTgbkZXY+9qk3oDS1qr8jTehrEwJpycDPftIx3nc+h9LYChj856Pj/Ns0yWBavDBwrO+blf5jOyYixAQCvcZigvHY2YFjpU07oLS2d4wxaPKCfoZh8phOkxeKw6UaAAaNVdvWZaUHzAHF76jdDqPDDTS3QXZ51c+b/l/ICnSZaYFj5YZmoN0h9kOR1fZ/YpvWMvTFI6AzGkT6uGd/Obx1dQHRLBbFKx77FA/k4gL4jIoQ2O7KSvVYhUS5D16FjvXBp3ghKzL0hfnqpBWNoa4JSn2j+jNpgkZRIEsy3C4XPPvNMI4pgi5ebQMr1zRAKa+hg8Rx9BK9AhhlPUyyAZapE2HOSBfiWl9WA/26nTDJehglvXqMpPNv6xB35omwjhoJk8EM3bqdwDtfQC/rxOegtSvUMF18OgxTx6m/t3Vb4f3HRyG/k+Jrd95J0E0chUjAoj0CpFr1mJhpxIZaH5ZWepBrs8LEvdsZhmEYhmEOQIiN5lbItY1Qahuha2lFSn09dK1eSF1qwkMKcb8522AR4mIywukWwkaLRtNkhfT9GiH+tKi4EHh+UW6YOBqmcxepJ5AkeF94r9vz6+OCskDps6PHZHIXHwddghWSxYyWtjYkJyYKgdbptaOHAZJfIJJAkmRVVJKgTEvpdKwuKQEKudD7nw+IT3qNoUtAi54/4LEk3gt8UufnmtuAptau2kyFsi+CT7OnAkp1fegPIiWxk2iX1m6Fsq8q9LFx1s6i/bvVkHfsC32swQDDI7cEHvo++w7y5l2hjwVgeeRW+rTU4b//X+jXbsUYKPDpvkGzXoZPL8FLa50M/S0XwGeEEN3OL76Fe/su8Tw959WO1dFahrJoDnwmnUgfl0p3Q9nfzXujISfNgC5OFddSeRmUsopuj0VuFkxxCTCSuG5rhH5nqxDXJLyNCq1JWMeL7fgpU2HOzVPFdcUW6Dau9D+vHmtQdKB/hGn+QhiGjxDbvr1r4dtdh+4wIRUGa7rYlmCC1ydmDEIfHFzuomVwaJNCYvKkY1tHky4RgkV7hJiWbcKeFgltbgVra7yYnce92xmGYRiGYbRosNLQDIWib/VNagRde06vh2QxQUlNgt6W0E37Mr8Qj+BNdm9QSHQ6OgQ2iT99bqb6nNMN34dfdo6Gkyin4xTAMHsSTOedFDiX7z/fdP9z2hwdD+hzGZGnTmIkkBBXF5Aot8VBl57SKUPUev8vO53L4XCgorQUSSUlMHZJ7w+OpB8My51X9v7Y31zdIewDiyImMLpOtpguP0sV5/7jxSSH9lqTkaR+AOMpR6uff9A5A+f3R4s1DLMnQike0ennB7Zp8iEIXVEB9FZr6GODxkuC2ZVigSsvDh54xeKGV/zzwCceK9VfwCN74JFccJhXwz28Cl691FEmIBbxU2Go+kJEz8W54/ZDyW7tKFfQaaKUov56GCQXdAb1PdKEjD41VU0Lh1H8EynhtKUzwpo8HiZbEkwGE/QtBTA6azrSzMViFCKdUs6txXOhT0kS55WVfZAN+zsJX4/Ph5q6WmTn5CAufxJ0STb12PEJUJKG+0slOkohtMwDfV5mx+9i4mjoczI6ju0isHVp6s8n9JPHwDI61Hn9n0vQxB8da/3L7T1/GR1B/5cGEBbtEezdPi/PjCV73Nhc78OoVCPS46L7wsIwDMMwDNNfKC43FEqnrW2A0tgChSKuQRFzXWYqdFlp8MZb0LhjO7JLSmCIoppwxefzp5mTCHcExLguIwWGMYXqMfT42XcwurkVuve+g9vl6XQOw6yJ0J9/sv+BHtLKTd3/PCoJ8EPpyPRaiooLAU5CPN6/piUxoeNYnQ6WX3akk8cCYoIh1P4Q+/R5Wb0WXYYJo3s9BuMR07o3TVN8sHvb4JHc6nJkHjxSGtzaY5nWrsDz7l2vicfCJG0CgAkkHLvJGmnb3bE9ZQS84/NQV1+PzIwMmMxqLTaJZSPVaFPNNq0NZphml6h129o+cYw5cLxYG9TnjGNNMOh6Wa5LAew5vTtUP3q4WILxOBxoLC0V/391Qf9/xWSVf8LqYOjIwDE5sXfHiu4LvQuORrNXQlSJ9meffRbff/89/vnPf3Z7zI4dO/DII49g/fr10Ov1mDVrFu68807k5eUh1hiWZEBRigF7miXhKH/qaO7dzjAMwzDMEKpPb3dAqWuEXNMIpaWt0/NU6yrqebPSoEtJCtTqDkSkS0ReW+1CfGsGbCLKTeN1uKAfngPDDFJbELXL7gefV2vpQ6CfNTEg2oXBWnkNDrAhjrOKKDeJ7GAhbjzlGIA+By0aHoiKW6HrkkJu0sQ+0+fvI6WVayLbHSSyPXLQNonuLo9lpUuK/iFAQtGst8BsoHJZs9i2GKwwG2ifJfAcbVsMFkhuGbtdezChaBISExKjWmgyg1C0v/7663j88ccxc+bMbo9pamrCZZddhunTpwth7/F48NBDD+HKK6/EBx98AIsl9pzY5+aZUdHmQp1DxrYGCSUZUfMrYRiGOSyOP/54nHXWWbjhhhsOeO7999/HXXfd1WkfTcQmJCRg4sSJuP322zF+/KH1QC0tLcX999+PTZs2IS0tDZdeeikuvvjiHl/z2Wef4cknn0R5eTlGjhyJO+64A/PmzTvgOFmWcfXVV2PKlCkh3w/DMIfmRk616SKiTkI4CIqe6bPThKEWbPFhFSSUYi/vLg+YrlHaebABm75kJIzHzlIPbrXDfd/fuz8XCXG/aIfV0iHYabwiym0NCOxgx3QS4vIFp6CsthqF48chLj1VFezdpPEbF/QypMkEIDM0rxDWHaJaRLn9j1sdLdjj3I3Gqv2AUQl63iPa8fUVnU7fSWxb9EHCW4jvoOfoOCHG1Uj5oXzPHYpDnMuoN7JgD/P3hrIlOtrKqT3btcfJljTkJgxDpIi4QqypqcHvfvc7LF++HIWF/lnIbvjiiy9EHc3DDz8MK9WJACLqfuyxx2LNmjUhb7RioXf7jBwjllZ4saraixHJBrGPYRhmKEDZVRo0Ebtt2zY89thjuOKKK8TffBLxvUGb1KWJgnvvvRfr1q0Ta3r92WefHfI1y5Ytw2233SYmCI488ki8++67Qph/+OGHGDVqVKdx3XPPPfjuu++EaGcY5tDTxpX6ZlWoU/q7tyMiTWKVHL1FRJ3S30kAh4rIk9mYv4UbfB1p4YrTBWnFxpDRcIqSG2ZOhOnUY9SDHS54n3un+4Emq7W1Aopmk5AW5msd6ebatn5YTsd7MJtgvusq9TmrpSMjoDtKiuCEC6D3G0Xp/dGGcDUPIboDEfCAKFcfayKdBHtPeL1e1HnrITtcMIUwMqTWYBTZtvhFtbp0iGxLl8fa81TjzSIaPZYQUFu3Nk8r2qRmOH0OxEP9/ju87djXtqtTb/bg3uujk8ejMFl13K931mDJ3vfFubSe7MH92+flLsCR+SeKY6vs+/GX1b9W28n5jwsW5ScX/QwXlPxCHFvrqMT/+/L0bt/DSYXn4urJd2LIivbNmzeL/zAfffQR/va3v6Gions3QhLlTz/9dECwa5EZorW1FbHKuHQjdjZJItq+rNKD40fEXsYAwzBMX8jM7KhfkyQJKSkpuPvuu0WEnET1ggULenWet99+W1xL7rvvPhiNRiG69+7di+eee65b0f78889j4cKFgWg8RdnXrl2LV199VZyHoAlhEuwulwtJSR3GNgzDBLmYe32qEBeiWt0W0WsStBIZyrWIenWZ2jmJOnVFCF3hHE4trfZVQT+xGEa/EKZ6dmrbJc4nFm8n42fd3EnAKH/dsscL37+/7n6M1HZLg4R3bqaahh4sxjVBnp3W8TNMRlgevqXXIkyfmXqoH9+QgURSR5p517TzINHd5fHh9urWUs0Dotufaq74gMS2KozJHIukhOTA8yTGtfrvWIc+43ZPaycxGyxuRyQVI9mSGhC2mxtWw0ft3qiNm+QRAlt73VH5i1CUPFYcu71pI/6967VOEWgSv5qAPnfM1ZiXp16319Uuw8Orbuu27/olyTfhzKSLxPbulm347Y9Xdft+Liy5ISDaW9wNeGf7890em2cbgSOhinbyDNjZvLmHz0n9O0Vov3dyq9e+B8E+ATZzMiJJxEU7RUVo6Q0FBQViCYZuyEjEU2374cz+UAT/cHE6nZ3Wh8L0dAWftvqwvc6LYXFe5NsG3pTucMYfDfD4I0usjz9a3oPb7Rap2CRgaQk1U90d4nlxc6SHjvqRhpG+RBBoPNp76QrtJ4KfE9E0utHyRz5oUpae//Wvfy2i36E488wz8cADD2DlypXiOkBj1M5Jj8krhTK6MjIyDvj5q1evFkI9eAyzZ8/Gf//738C+//3vf5g/fz6uu+46nHHGGd2+n+Dx07q7YzToeToXfde0z6LruThiwxwq4juoCV2qnfa7X1PUWa6o6Xiu3Y7U/eVAoxs+nU70a9aPyAv0Svb93/cBsaz4hbi2bTxuNoxHzVDPW14Dz+Pd+xDpRhZ0mFAZDFB2drTACm6+RNud2oFRQIbadoWCotjBL6ao97Rx0CXE+2u/40VbMvjXwWZVQojfdlmvP0/+P3jg94tEdbO7AU2+OpS3W6D36LsV3ZooF2ZrfYR+B6bgiPZB6r2Da8O7M1aje35DTSkKk8YgPgKZDsF/35tc9ahxVMDps4vIM60dPjtc/u1FhT9FVrz6f/O7is/x0a7X4PC0w+5uh64O/ug1iXEP7p77JKZkquUU/9v/Hzyz4YFux3DnrD9jTu5xASH+t3XqRHUoSOBror3J1YAfK//b7bGtnqbANr1Heg+hIGEc7AMQZ4xHTnxBQCSTS71wpifBbDAh2/8ZEMmWdBH17hDURr+5niqui1P9ZSsAMuJy8OvZj3cx4wsW4h2T8enWLLx76gqRaRGNROeoegnVtb/22msiKkP1i32F0mSoFjJclJWV9el18e1WlDmt+KhJxlGprYhU6/a+jj9a4PFHllgffzS8B4oUk3jvepH/puoTNLhqIzKmDGs2js49+ZBuYsUkgs8notSh/u4SXZ+jbKtHH30UOTk5mDRpknj+pptuEqI5FORlQsdUVVWJmvTg81HUnti3bx9stqC0V5qpb2kRgjk9Pb3Ta1JTU8W5tH3XXHNNr95PMF1/d90dQ+favTvIFbgLZmpZxQwuIU0RaUrvDhLE1LZIc/amPuRy6S7/cf4Is4hiq2nhxiOnBUSwtGMvfO8uCTwX+Bl+jD89EcZ5U9XzllfD+8zbgecoLKDeAm8DvcJ4uiEg2ilyLq/f1v378UfQxbbW5kp0kTKo6eQkuP1rEsyGMSNE6rtqOmdX2yvR62hSQfRQV7e1NmeCxHiYb7oocCyJbdF+i7YNBjXQ4r9v0xmNMF/UfUor03tIXNt97XB6STi2w+5tF2uHt82/tqvRVUovd9SjqiYjZHp5d/XeHcI6dK13sOgOFuXRMHmiRa6DxbW2JoE9P/8nAQG4tPJLfF+5BE5ve8exkiOw/dD8VzAqpUQc+9X+j/Ba6VPd/tzpWUcGRHu7p6Vz1LjL3DBFtDVIlOp1hgNd5f0O8jTxoZEZl4OZ2UeFOE59nG/rKF8uTCrGVZNuF+cQoprc56k1nFibMCxxZODYcamT8fTxHwae0471un3YtnU7SoarnwFBn8ffF37Uq99FRlx2r9PUrcY4zMo5ulfH0vfMoIteaRy9I+sB+sP/17/+FX//+9/x//7f/8NFF6mpFX2F/uCMHt37lg/dQTeAdLNPtflxcR3un71ltKzgo10S7F4FnowcTM/qZeuFMHG44480PP7IEuvjj5b3QGKusrJSiNHgUiD6u2cymWH09fBnm0SlJMFIjsJhvskxmkxiPIdy80TH0gRE8PvQ0G70qJZcg0Qs7T/iiCOEySgJaCLU60N9bhQxCT42MTEx8Nl1PUdzc7NYU8178HP0mGrYQ/3Mnt6P9nNoHPS7683nROcaPnx4SBPVnTt3HvT1TATZXY78HzdDt34vPNR/uUtE2njOiTBQP2e6r165Cb43P+v2VKaLToNhmnrzqlTV9ZjqLY8t6ohcS7KoD++WIAGvI6Oz7HRVLJMRml6HNpcLiWkpMIrnOjJRdOnJMJ610B+pJ0GtCmshnGnbFg+5ul7Up9Mkg+GEeYG/N2p9eorq9k5LUJsloet/1tFTvCdImOuG5fbqWKZ30N8nl+RQhbgmxoUQVxcS625f77LMLIY4JOgTRRTTFpfkj34fWPsdbLhGAnCgxLfmAt9VXNN6UkaH4fW6+qXY0bYx6PnOx/5u3t8Cgvmtbc/hg52vdPszx6ZNDoj2ivayHqPR9HvQSLGkIzu+QESa1SUhaJ2AVGtGJwH/69mPQeczoHJ/FUaPHIPE+MSAuE4yd2SrHDfsNBw/vHeTWePTp4ulN2Qn5OPkovN6dazFGIdcW+d2b4TkiUyf81gn5kQ7ze6R4/B//vMfsSZ34MOF/oiEMz2Gbvb7er5jCiX8t8yNHa3AhBwrUq0DnyZ/OOOPBnj8kSXWxx/p90Ap4bQYDAaxBHPCiDN7TI+nlGu3ywWL1XrAayORHk/Ha++lK5ofyb///W+xbmhoEB1E6urq8Ktf/UqIWQ2qKf/4449D/ozTTjtN1J/T74yuD8E/iyYBCIqydx2D9vulY4Kfo3PQuUKNuaf3Q2gp8WK2/iCfPz1P56Kf1d0EQSxBKf5PPfUU3nnnHbS1tYnSBPq9DRsW2mmXJseorIE8A+h3cc4554hsCprI0D7LadOmHZC1cP3110eHe39jK1L2VIvNkF7TQY7oQuxqUATaL34D0WN/Crs4Ni0Z+uklHQJZS3H3P9YXdqSI6ofnwnz9+R2Ra7P/nNr5g9zIyTTNcscVHcNzOLC/tBQlJSUwdflbR1F/41HTD+yfTiZyNQ1QSnerteza8RazcHoXIj09BTrjwAYcGBWv5BHC29EpOm4PCHKKnvemLRmlBieYbIg32hBvShRr7XGcKQHxxgR4XF6UOktRklcStmslmc6pKeGqaKborl6nfoe3NKxBWeuOTpHtYIF968w/IcGkTtK+tOnP+HTPW5C6uVY+s+BjJOrUCeEtTWvxyd43uh0TTXBokJCmyHVnYR2POEMCrMZ4MVmhMTVr3gHiO/h1KUFCfMHwM8TSW8FMC/3/1VF6f2Jxt59/rF1DmEEo2snll+oN//znP+OUU07BYGN4skE4yO9tUXu3nzIqOtKCGIaJPKK2T9d9KqJe0UPSSyKtzUCpqjHAiBEjAmsyGj333HNFG0+qYdci7b/85S+Fm3wotLR3Sqevre1cOqA9zs7uaLcUnDpPNzuhXhPqeKZn6Hf3xhtviAwJ+l1QZxf6PdJkS9c0fypNuOCCC0Q5A5n+UYbLb3/7W1RXVwshr4l6Euw0qUMlDBpRMyFYkIXqqaORVZAHc3z8ARFpSgfX0E8qhuWBXx4gpENB4tp84Wm9GoLoYT5yWP/2T69pgFxH/dPbO/9sMm7LSoOe2rIF909n+gVN0FI7Kk2Ud6Su09p+UMd07RpCwjFeE+VCmHeIctruTTq6B161vl1yB9y/ib2tO1HnrOoUrXYFieurJ90ZqBd+rfRJ/Fj5ZUCAu4IMwYh/LvpfIHL9Tfmnwi28O+hz0UQ7Cf1gwU6R/mDRLAdNs41PnQajURXi1i7CWtRYJ3T4aC0uvgznFF/Rq3vy0SnjxcIwQ0a000x7Y2OjSHGkSAT19f3000+FcCezIIrIaGjHDAbm5plQ2S6hxi5jW6Mk3OUZhmEGOxR1pj7rF154oYieU+s3gkRbsHALBUV233zzTXHd0KLc5D5fVFQU8rV04zV9+nSsWLECP/3pTwP7qf3ozJkd6ZPMwaFygpdeegm33nqraMFK0O/uqKOOwpIlS3Dqqad2Ov6DDz4QkSIqc9P8aP74xz/i5z//uYi2k+Estf6jCZlx48YhKsnJQMOEEcgqKYHxIBMJVHMNfwZBNEPRc6VJ65/eKFqpaQihQv3T/WnvwnGdAwphQZTVSK4gAd6Rrq6lrlM6tWZ02RMU7RUi3C/ASYAGC3J6TKKWRK42AUCCutpORmiq+CchfurI8wPnfG/HS9jcsMZf504CXJ0woNcplTLePW1lwPCNHL1/6CEt/OLxvxRp9USrpxlV9g5jQg2qKaZx0mdigyraR6WMxzxPS0BUU2Q7WIjbTB1mYotHXyrGL44zxIU0FdPMp6dmzMMRw3vXoaQ7UzuGGSii+ipCZkDU7ufBBx/E4sWLRUo8QX3aaQlGO2YwYDPrMT3bhOWVXqys8mJ4EvduZxgmNqG2a99++22nfT1NsI4ZM0ZEaJ955hmR+t7b7iLU1u2FF17Ab37zG/H6DRs24JVXXhG92jUobZvS3zWhSH3dqS/7+PHjcfTRR+O9994TpqQ0ccD0nq1bt8Jut4u2rBrUHo8+V3L17yra6TtBUfZgA1k6lli1alVAtFPbvnASrk4x0dJpIizjb2sHahqA+iagvgU6f0kJoVAJS1oykJkCpKcAQfXpiPD7jqXPn4zbNEdwtY7cjhZHE/Y7yrBr1zp4de6Dpq0r9E9RhAAl8UgLGYGNTZmspq0b47G67gfUOPajStrnj2w74JTUOm167QNzX4bLq07E/GnNbdjYuKLbn3ds9mmB1PQdjVuwtvbHbo9tamsQYyAyLXkoShyrimoDRa/jYTWoUWtau51u6Lyq+D0x7xzMy1yoPh90LNVmiwkhpUNcz89cJJZu8VKfb/VYIyxioX1uLxmzdZizxeL3JxQ8/sEz/kPpFBNVop3S6oLRLtwaNJM/VBifofZub3DKWFnlwTHDuXc7wzCxB6VHd61Hz8/PF7XJ3XHttdeKCC0Jbsqq6ur8HgqKppNoJ8F91llnif7vlJVF2xr0HEXWv/rqK/GYWrlROjaldlNkmAxJabIg3GJxsENp7URubmfjsKysrMBzXfdTGUJwVgR1DdC8DYjt27cLvwEqi6BJASpZuOSSS0TbvWjpFBMNnSb6gt7rg7nVgeRWO+wb98AeFMGVDQZ4kuLhToqH1xYHxSABLQ3qEoVE+vNXFBkexQ2X7IRbccLtX7tkB9yKC06pXTw26jomPJp99fAoLpHCLdl9oH+0rUAWx81KOA4WfZxYvm55H5WevfDiwNR3iy4Ot+U9ARdaKW6Nr+o/wm73lm5GqsOWLZuFgzvhc0jiZ1l0VrGQezudz0Iu7ro4bC7dJNy+idHSVGSljBDP0THqsdprrCjbvi8gOiZiPiYmzT/wx9NckA/Ys2NvlyfMcMAHh/89DLXvz+HC4x8c4+9tp5ioEu1MB3qdDvMLzPhop0uI99GpEvITOTWHYZjYQRPH3dFddhRdwD77rHu37e6YPHky3nrrrV5PDGt93mkJx/sZqmjRhq43HuSKT/XrXTnppJPERAllyN18880imkbp8WRCp7UC3LFjhzC3u/HGG0WN/DfffCPMZ+l5Mq2LZKeYaOk00Wv89emobxYRdV2rA16fD81tTuHtYEyyAZmpQEYqQNsxUJ8+EJ9/o6sOLZ4GNHka0OpuEv2n27wtaPe2ihrzosQxoo0XCfc19T+izdMsHMt9ihde0TfbK4Q4GZWdVnihMHCjiPT7u19Ctas85M+k58+ecXHg8ao1X8Lb2CHYhRGaiFyr56LyEU0wH1N+MsY6JgWeV9PDOxzJi5NLAtHzXyuPBbYPRgk62nLF5Pc/BDz+yMLj71unGBbtUUxGvB4l6UZsqffhxwoPzhpjhTEGLqYMwzDM0EErd+jaKo+M5ELd0NCNDtWzk7v866+/LszlyBGebl60Nn1UDkeReGrBR5A4oVaIL774Yp9Fe7g7xURzt4we69PNZijJiWi36pExcyriM3v2i4hmtM9fmKLJ7qC6a3UhkTs+fVrg+Pd3vIIGV43oN07u6u1abbevXbTL+tnYqwMGb29ufRZtXrU1ZFdIMBckjRAmZjqdCe3eFjS4a0IeS+L4/AnXBB7vtpdif8tu+JwSslJzYLMkId5EIpsM4RI7fZ+um3a3eG8k+El8U816d6m0p4/5OQaaaP3+9xYef2Th8eOQvEFYtEc5M3JMKGuR0OpWsKHWh+k53TtHMwzDMMxAo6XFU8p7cKs+ejx27NiQryGvAlroGIr2Uio8ZUJoLeJC+R6Q38FHH33Ub+8j1lF8PtG3XYj0+ia1b3xw3/P0ZOFqr6OouuSDk0oFEqI7ykWCtdndgBpHBart5ahxlIs2ZAtyOrJjrv9qsXguVIuvAlsRbp/1SECYf7z7dXG+UJAp267mjvIJ0WdcUvuOUw9yEbU2xSPBmIhUayYWjjhLmLxRz/LRKROEWZwqrtUouCrEVdO0YK6ZfJfILin1t9zr6aY/N6F/ugMwDBN7sGiPcswGnXCT/2qvBxtqvRiZYkBKBHq3MwzDMEwoKApOvgPkvK+J9tbWVmzZskV0AugKmc1RpP3ll18W9e0EdYahqAU5+tNrFy5ciDvvvLNTCcXGjRtRXFw8gO8s+lGc/v7p1JatsaVz/3Tq205u79RDPSNFCPcAjtA9rCMBuZVTynmaNTOw7y+rfy3ah5FIJxfxYEYkjsYxWafALrWhmp73OTsJdjIyM+pNoiabDNx+qFjS6bV5CcOFiRu1xqR2YDZzMhLNyUi1pGNEUnGgHdrJI88TIpzOdTBmZB8Zts+DYRgmFCzaY4DCZAOGJRmwv1USafInjeTe7QzDMEx0QLXsJM4fffRR4QhPRoPUp51q0U888cQD2reSczyZzP7pT3/CxRdfLLappv2aa64JmA7OnTtXmAOSweCIESOEMSFF2Z999lkMZUTbrzY7ZC3tvbVr//R4tX86tWVLToyq/uk7m7egsn1vIGJe7ahAjb0Cja5aIZYfO/bNwLEk2Pe1qbWeOuiQEZeN7IQCZMblChH9cdnrqLHXYG9VBubkHu93UzfBqDeK48XrdDrRe1trf0ZCfHr2fLW23N8Wrad0c4ZhmGiCRXsMQBeUefkmVLVLqGqXhTFdcRr/6hiGYZjogAzjKMX97rvvhsvlwqxZs0T9OZm/lZeXd2rfSsKeXPopHZ7awZHTP3UTuPTSSwPnI1f/J598Er/73e+Eozw5+j/xxBOi9/tQI1CfXtOgRtSdHcZkQnCm+PunU0TdFpn6UK/kQa2zSohxEuIkzMmE7fKJtwaOeWLtPdjftjvk61vcjZ0eXzz+RvHecuKHITM+V4hyEv2b61eJyDsZElIkPdmShpT4tIAoD+5JTmnp3FubYZjBAiu/GCHRrMe0bJPo276iyisi71Yjzw4zDMMwkYdat912221i6UrX9q0EpcG//fbb3Z6PIu7kFk/LUITq0UVdenf16ZTuTiI9MxW64P7p/TUeRRHu6E3uBoxI6nDgf3Lt77GxfgXqnTUiFT0YEs+XTbglEMkekzoJieYU5MQXICehANnx+f51gTCBC2ZG9vzAz62y78e6uqXCwZ1IsqRiXMY0NHnaUFLQc004wzDMYIFFewwxIcOIXc0SGp2yEO5HD+v/CzXDMAzDMANYn17boNanB/VPD9Sn05LepT49zGxtXI+y1h2otu8XBnAUOac1GbmREH/tpG8CQrzF04g6Z7XYpvrw7E6CPB8yZBigjvX6qb87pHE0uxuxrvZHEbXXzj8pczZGJo+Dy+lCEzpM4xiGYQY7LNpjCINehyPyTfhklxs7Gn0oTjUg18apXwzDMAwT2/XpDVBa7QfWp2enQZ8Znvp0+nlk+EYCfF/TLmxqW4fvt3wEu9SCX895PHDcO9tfwJraH0Kew2qMEy7p5IpOnDf2WpxTfIWInlOqejjqw10+JzbWr8TullIxZmrbRlF6at1Gju4MwzBDERbtMUZ2ggFj04zY2qD2bj+jmHu3MwzDMEzM1KdTFF1zfA9Zn56uRtT70I7NJ3tFqnqtoxKTM2cH9j+/8U/43/5PRLS8E63qqt3TCps5SWyPT58Og96InPh8ETnPTqB1PrLi80S0O5jRKeMRLiTZh21NG1HauFbUyBPDEkdiSubcwNgYhmGGKizaY5CZuSbsbZXQ7FKwsc4nat0ZhmEYhonS+nTqn04inda+EPXpJNIzDq0+fUvDGmxt3NBh/uYoF6nqsiKJ5ymNPcGUKLZlRQ4I9lRLBjKtubB4ElCcU4JhKUWd2pqdXXwZBhKKppNB3fq6ZaKfOkHt36ZlHSFM6BiGYRgW7TGJxd+7/eu9Hqz3925PtnDvdoZhoovjjz8eZ511Fm644YYDnnv//fcPMBnT6/VISEjAxIkTcfvtt2P8+EOL4pWWluL+++/Hpk2bhEM5uZFTS7Ge+Oyzz4RLOTmcUyuyO+64A/PmzQs839TUJNqRffvttyISesopp4ixUU/xrqxZs0b8PPr5zNBGcbr89emNB9anW8yqgRxF1NOTD6hPp4hzg6tW1HKTEFdryqlNWgXunfeMcEYnvqv4HP9X9s4BP5v6lFNkvM3TEhDtZ4y6CCcX/QxZcbmwGOPgcDjE/5eSUZE1cmtw1mJt7Y+o99fFx5lsmJwxG4VJxdyKjWEYJggW7TFKUbIB2xMNqGij3u1eLCoy8wWOYZiY4/vvvw9sezwe4TJO/bmvuOIKfPHFF0LE9wYS15dddpmYKLj33nuxbt06sabXn3322SFfs2zZMuF2TiL8yCOPxLvvvourr74aH374oWgxprUyczqdeOWVV9Da2orf/OY3QvBQj/FgVq9ejV/84heQZfmwPg8mNhGivLVdrU+niHrX+nSb1j89HUi2wemzCxFeXbMW07OPDKSdv176N3yw81VISkc0PpgaRyWKkseI7fFp08R5SKCrBnDqOtWaAb2u80Q+mcNFExRR31C3Antbd4jHlI5fkjYN49Imd4r6MwzDMCos2mMUEuhkSvf+dgmVbZJwlR+dyr9OhmFiC+rRrSFJElJSUkSvb4pYk6im/t69gdqHUU/w++67D0ajUYjuvXv34rnnnutWtD///PNYuHBhIBpPUfa1a9fi1VdfFeeh7RUrVuDTTz8NiHjaf+WVV+Lmm29Gdna26E3+yCOP4PXXX0dxcTFaWlrC8rkwMYCsAA3NkMqq1Ii6q0t9emqSMJHbai7HmtYfUdNWgZpqNY2d2qdpPHbMmyj0C/F4Y4IQ7BQtpxrynKCa8pyEYcgKShc/qmCRWGIJr+xFacNabGvaIDIK6HMqTBqDSRmzAhkEDMMwzIGwyothkixq7/ZV1Lu90othiQZYuHc7wwzqaJ6vh0CuJCnwygoMkgK5S8/kw8Wo9wuRAcBsVut6SXwTd955Jz744IOQx1L6/UMPPYRVq1Zh9uzZgdcQc+fOxbPPPov6+npkZGR0eh1FxCmdnc4dzJw5c7BkyRKxTeekSQVNsBP0M+hzoMj6ySefLKLuK1euxAsvvCBS7CkSzwxuFI8X2LwLti3bsa9qGxqMzahRGlCra0SNf/vOWY9ieNpYcXzpjiV4b8dLB5wnyZwqIuC+oKj6guFn4KiCk0RNd9doeSxDNfVlrduxsW6lyA4gqF6d6tbpvTIMwzA9w6I9xpmYYcTOJjKlk7Gy2ov5Bdy7nWEGq2Cndo819u5Vu6LIIvJrNLqgC/MNf3aCHqeMsvS7cK+oqMCf//xn5OXlYdasWWIfCeFbbrkl5PFWq5pWXF1djTFj1GilRlZWllhXVVUdINop1Z0Ed05OzgGvoXMRNTU1yM3NPWBCgbIB6JxEUlKSqM8nKL2eGfxQjfqnVe/h9dSP1B3Bmez+7WpPNYZDFe0laVOwqPCnImqu9TCn6LnWNi2YJEsqBhtUk7+2bimaXfXisc2cjCmZc1BgK+KyPoZhmF7Con0Q9G4/0t+7fVuDD6NTDchJ4N7tDMPEBtOmTQtse71ekeJO9eUUPdcMshITE8XSEy6XKxCh17BY1J7Obrc75PFEqNdox1Mte9fnux7DDD3IQC512BhgP2AzJSM3YVhQCnuBEOdFyapg11qo0TLUaPU0Y33dclS07RGPTQYLJqRPR3HqRBh0fJ/CMAxzKLBoHwTk2NTe7dsaffix3IszivVCzDMMM3gQzuWjLAdJj5fgcrtgtVhh6OJIHa3p8WT6RjQ0NODxxx9HXV0dfvnLX6KgoMM465577sHHH38c8vWnnXaaqDOniDsZ2QWjCetQ7tiaoA/1Gs0ZPtQ5tWMi6bjNRBadXofpoxfhVt8wTJswg78LXXBLLmxuWI0dTZtF9g9l/VA/94npM4RzPcMwDHPosGgfZL3bm1wyNtX7MCWL3VcZZrBBotnUgxbXQwdJT8foYDDExsTdiBEjAuunn34a5557rjB6IzGfmqqmCpOIJzf5UNhsqnkVpbnX1tZ2ek57TIZxXaEUdxJboV6jHU/nJAf7YEjENzc3B1LvmaEJub1b9SzWg5EUMsXdgk31q+GR1EyWXNtwTM2ch+RBmPbPMAwzkAwel5MhjtWow+w8Vaivq/Gi1c1thxiGiS0owk191sk4jqLnGunp6ULUh1roOYLq38kcjrINNMh9vqioKHBM1wmQ6dOnC3f4YJYvX46ZM2cGzkn17eRCr6EdP2PGjH74BBgmNv02Ktr34vOyd7Cm5gch2JMtaThm2Ck4puBkFuwMwzBhgCPtg4jRKQbsbNSjsl3G0govTuTe7QzDRBgSvN9++21I87hQkJkcRdqfeeYZkfpOfdd7A7V1Iwd3Mq2j12/YsEH0Vqde7RptbW2ibj4tLU08pr7u1Jd9/PjxOProo/Hee++htLRUTBwQU6ZMEcL+pptuwu9//3thXEep+meeeWbI6D3DDDWaXQ3CZK7GXi4eU/r75IxZKEoeN6jc7xmGYSINi/ZBBAn0eflmfLjdhfI2CXtaJIxM4V8xwzCRg2rRu9aj5+fn4/rrr+/2Nddee61ou0aCm1qsaSnwPUHRdBLtJLipDRy1arv99tvFtgY9R5Hyr776SjyeP38+HnjgAZGW/9hjj2H06NFiskBr8UZ/U5966ikxjksuuUTUwS9atAh33XXXYXwiDBP7OH0ObKxfiT0tW0Wk3aA3YkzqJIxPmwaTgbvYMAzDhBtWdIOMFKsek7NMWFvjxbJKL/Kpd3uM1LYyDDO40MRxdyxevDjkfnJs/+yzzw75502ePBlvvfVWt8+TI31XKGpOS0+TAU888USvfj5NEJx00km9HC3DxB4+2YvtTRuxpWGt2CaGJY3ClIw5sJmTIj08hmGYQQuL9kHI5Cwjdjf70OJWsKbaK6LvDMMwDMMwfYGi6fvadmFD3XLYvW1iX1pcFqZnHYGMuJxID49hGGbQw6J9EGLU63BEgRmf7XKj1N+7PTOee6IyDMMwDHNo1DtrsLb2RzQ4a8TjOJMNUzJmY0RSMfvmMAzDDBAs2gcpeTaDEOs7myT8UO7F6cV66PniyjAMwzBML6CI+oa6FdjbukM8NupNKEmfirGpk8U2wzAMM3CwaB/EzM4zY3+bCw1OGVvqfZiYyRdZhmEYhmG6xyt5UNq4FtuaNkKSfSKaXpg0FpMzZyHOmBDp4TEMwwxJWLQPYuKMOszKMeH7cg9WV3tRmGyAzcwtWBgmVmpImcEL/36ZaENWZOxp2SZc4V0+h9iXFZ+HqVnzkGbNjPTwGIZhhjQs2gc5Y9IM2NmsR7W/d/sJRZZID4lhmB4wmUwismW32xEXFxfp4TD9BPV8137fDBNpqu3lWFe7FM3uBvHYZk7G1My5yLcVct06wzBMFMCifZBDF9sj8s3493YX9rVK2NsiYUQym9IxTLRiMBiQnJyMuro6uN1uJCUlwWg09urGWZIk8RrtPLHGUBg/RdhJsNfW1iIlJSUm3yczeGjzNGN147eoaC8Tj00GCyamz8Do1Akw6Pi7yTDM0MAjKbB7FbR5FNg9Ctq9Mtpp26tgbLoRxamqZC5r8eGNjW78JAIxFRbtQ4BUq17Us6+v9WJphQe5NivM3LudYaKWnJwcEWUnYdfa2trr18myDJ/PJ0S+Xh97pTBDafwk2On3zDCRwCO5sdO1EaXly2A0GqDT6TE6ZQImpk+HxcgZPgzDxA6SrIprk0EnSoOJeoeMldVetHtkvwhXhAinNR17ZrEFxwxXs4+pPfaNX3R/r3VCoRkzc01wehXsb5Xw5T4Z6TkJKMHAwqJ9iDA124jdLT60Ue/2Gi/m5nHvdoaJViiqTqKOIu4UvSUh2BucTid2796N4cOHx2Rq/VAZP6XEc4SdiQSSImFn02asq16GCk8FMpUM5NtGYUrmHCRZUiM9PIZhhhiUfeb0QYhrTVgHIt5eBdOyjShMVuVqab0PL25wiP2aAKfX0euJW2cn4MwxVrG9t1XC/T+2d/tzUyw6cR6nTxFZyBomvbpYDDqYDBBBTq+kiDJjwmLUYWqWHgbdwPvSRJVof/bZZ/H999/jn//8Z7fHNDU14Y9//CO+/fZbcWN7yimn4Pbbb4/JG7yB7t1+ZL4Z/7fbLZzkR6cYkREfe5EshhlK0N84itrS0ttIL2GxWGC1qheuWILHzzD9d2Ncad+LdbXLREq8V/LCpk/CUbmLUJhRHOnhMQwTo39XPBKV2ShIMHdEuSvbJayq8nYS4SLi7X98brEeWh+Kb/d78JtvuxfXJMQ10W73KlhW6e322I11XpgNEEK8ql1Gnk0vHpv1OnVt8K/1OtjMOnEMkWjW4YLxViHU4006xNFiDFpMqrm3tiheYNc21ZdmSIr2119/HY8//jhmzpzZ43E33nijiGa88sorIm30N7/5jagP/NOf/jRgY41V8hMNGJliwO5mCT9UeHDaaAv3bmcYhmHCMmHx1FNP4Z133kFbWxtmzZqFe+65B8OGDQt5fFlZGR544AGsWbMG8fHxOOecc3Ddddd1mqCi+4KXXnpJ+DtMnDgRd999N8aPHz+A72pw0OSqx9rapah1VIjHVmM8JqVMgtPtQ1Z8fqSHxzBMhPDJB0a2tYg3pZQfUWBGQaKaFUYi/J+bHUEiXI10+1Tdi3vn27CgUE03397ow8PL7d3+3KPzTBjl3yaRTFDVboJfHFv9i0mvQ41dwme7XHD4IFpYzy8wgRphkQCndPhgUU6aRhPidJ6fFJHO6TinEORiW93X8ViHeKN6jt74BzlkHSIhnyIu2mtqavC73/0Oy5cvR2FhYY/Hrl27FitWrMCnn36KUaPUX/d9992HK6+8EjfffDOys7MHaNSxy5w8M8rbXKLWo7TBhwkZ7FzMMAzDHB5PP/003njjDTz00EOiVv+RRx4R1+aPP/4YZnPncqyWlhZccMEFGDlyJF599VUxEf/b3/4W1dXVQsgTH3zwAR5++GH84Q9/EEL9ueeew2WXXYbPPvsMaWlpEXqXsYXTZ8eGupUoa90mImIGvRFjUyehJG0avG4fSnWlkR4iwzB9RFYopVxBqywhxaoXwlMzSltd7esU2Q6OeP9iejwmZ6n3/pR9+9Cy7sV1erw+INrbPLI4byjoJ7ukjnTxnAQDjsgziog1iWuKYJOwpqowo57G7sOK5gTs2OWDVwdcNMEq9qtnOpBKvxA36CAM4UiI0/vVhLe6HRQND4qUW3opxGOBiIv2zZs3i/q+jz76CH/7299QUaHOBIdi1apVyMzMDAh2Yvbs2eKXsXr1apx88sl9GoPm5nu40I1H8DpamZQqY1mVhGX7vcgyGZHgn+WKlfF3B48/ssT6+AfDe+DxD57x03UpVm40PB6PiIjfeuutOPbYY8W+xx57DEcddRSWLFmCU089tdPxJMjpmvvXv/41IMCp7O3nP/+5iLYXFBTgmWeewYUXXojTTz9dPE9ifuHChSKSf80110TgXcYOPtmLbU0bUNqwTmwTw5NGi7r1BFOieOxF73wyGIYZWOhvP0W9SYhqptFra7xYsseNWocsgm61DgntnhFQtrpILuMvxyditt+ramOtD4+t7F6I1zn9oXHR2lE9Pwle0gI2sx42k06kutM6I66jjHZ8hhG/PSJBRL+NJL51gF6vAx0hKwpcEvDZbrcwa6P09HEZJijdlH03u4EGrwk6twLqekolvMFCvEN4dwhxa1BkfDAJ8ZgS7ccff7xYehuVz83N7bSPZvDJsKmqqqrPY/B6vSgtDd+MM6X9RTP0n8jXbEO9z4h/N3swLckRU+M/GDz+yBLr4x8M74HHPzjG3zVCHa1s3boVdrsd8+bNC+yjVoUUIV+5cuUBon3v3r0iyh4cMdfS3mlynjxq6DMMPh+lzVP5HJ2PRXv3N/v72nZifd1yOLxqjWh6XDamZc1DRhx3KmCYaILMz1ZVe1HnkFDnkMWiiXISwI8vSBKO5URFm4SPd6rtRDtQRSulirs7fNQwLMmAY4ebO4lvbU2ifHx6h/SbX2DGV+enwifrhNB2+RQ4fIoQ3rTd7JKFEHdp+ySlWyEeCtLVWuq5Fg0n4a3zSah02zFhRDbSEq1qOvwQFeIxJdoPBYpehLqJIdMfrTduX6BI/+jRo8MyPrrRoDT/aDfGy3Up+GSPDz4FSCwwoCBRH1PjDwWPP7LE+vgHw3vg8Q+e8e/cuROxAqW1E10n1bOysgLPdd1P7QypM4Lmoq9l2TU0NPR4Ppog6CvhyqqLxqyQBlcN1jcsR5OrTjyON9owIX0mhiWMhE7RHfC+o238hwqPP7Lw+EPT6lGwt1VGvVNRF5d/LRbgtpkmTM1U/+atrvDhsTXdm6pVtTjhSFafL0qQcXGJEelxOmTG6WDTedBSsw/jioYj2UbXGh8cVPQNYEwicOcMvRDyLh+VyaiTACTKyWV9TYVbiG/apn103CELcYMWFadtrUbcXztu0GrIyYGd6szpVZ1/gNPpgc7qRYreDYush+IBYumb5IxQVl1MiXZy46U0vK6QYCcjm75CH9bhvL4rdLMWzvP1BzS8aW4PNtT6sLZRh6IMa0yNvyd4/JEl1sc/GN4Djz/2xx9LEQftxqXrpDpNqFP9eldOOukkUQP/4IMPCj8aEpSUHk/RdMp86+l8hzNBH+6sumjICnHJDux2b0Gdt1I8NugMGG4uRr55JOwOD7Zia1SP/3Dh8UeWoTJ+l6RDs8+IZq9BrFt8BjR71fWJGc0ojFO1ybJmG/5VldHtedbvrIClXk1dV5xmTE5MRopRQorJh2RaG31IMUlIMkow2xUE/7maQa9xAK52HeolA1yyAT9sq4Jb1sEt6+FR/GvxmK4fh3INUWDWK7DoFZh1slhb9LJ/n/pY2zZBgZ4i+7R0+XPs9i8H/tUf2t+fcGXVxZRoJ3ObL774otM+EvHNzc1iBp45NKZmmbCnWRK1M+tqvZiQHOkRMQzDMLGG1t6OrsfBre5IYIfKOKBMBKpnJ3d5coinCY4bbrhBZBckJiZ2Ol8w3Z1voLPqoiErxCt7sK1pPcpaNgNWCZm6TBQmjsGE1OnCHT7ax3+48Pgjy2AZ//ARhfDorWhwKahzKmhwqutjCwwoSlbruZfs9eHR1d1HxE8am4ySEaqcctVK+KbVi4w4XSAqnm71r+N0GGYbFqgjL6HXhjgf1Ye3e9U2au0eoM3v7N7m3yat7JN9aG5rFuXBwR03LP6FnCto3pci3RQJFxHxgFlbcHRc3adGxAduoniwfH8KBzirLqZEO7WQefTRR0U93IgRI8Q+cpMnZsygOSjmUKBWCXPzzfjvHjc21fmQZzmE/BiGYRiGCUpjp5T34cOHB/bT47Fjx/boZ0PH0I2nz+cTzvPUIi74fMHGs/T4cLrEhDurLhJZIbIiY0/LVmyoXwm3zwmDUY/c+GGibj3V2n2Erzs4qyWy8Pj7t51ZvVOtFaelJN2IXJuamr68SsJjO/PRto0mwMjMrTNFaRZMyFUnD/OSafLQK2rCM+P1ByzTs02Ij1fPe2ShuvRmbKoQV9Dqlv1rBa3Ubs2jOsOHipTryQDOqPYVN9i9GJluRkqCJVA3TuZtJMhVR/WBFeKD7fsTjVl1US3aqd6tsbExMPM+ZcoUTJ8+HTfddBN+//vfi5Q6mqk/88wzud1bHxmeZEBhigFlzZJwlB/Bup1hGIY5BMaNGwebzSZat2qivbW1FVu2bBEO8F0hszmKtL/88suBLDlq5Uo3QHSNp3MVFRWJ82lmdCTq6XXkMD9UqbLvx7rapWhxN4rHieYUTM2ai7yEETFVTsEwhwvVYtfZZaRYdUiyqBHxTXVevL7ZGTBza3QpnSqp75qXgFP8ot2gBxq9qskb/c9Js+qQEa9HVrxerLU2Z8S0bBOW/Cwt0E+8t3glvyj3yH5BrqDNLYs1tV7rqY6cxpdk1iPJohMCPXibIvUupxOlXjtK8g2Ij48Nw1Lm8Ilq0U6O8AsWLBB1b4sXLxYXpaeeegr33nsvLrnkElHftmjRItx1112RHmpMMzfXhMo2WaQE6V1mqB6+DMMwDNO7ejwS55QJR47w+fn5ok87lbSdeOKJB0zAk3P8tm3b8Kc//QkXX3yx2KaadnKFJ8FOXH755bj//vtFVt2kSZNEn3aXy4VzzjkHQ40WdxPW1S1FVfs+8dhssGJixgyMShkvatgZZrBAplwUZTao7mXY1yqJbFDNWV1EzZ0UjVY6hPgoa0DIf1feOY2den9nxqkRcYqUa5Sk6fGrEVWYWVKIgrQE0XKsp6xUUzf/zdwkzN2dhTlFzmlNbus9QeckMZ5oIVHeIcxpWzis80QcE82inVLjgqFerXQxDyY9PR1PPPHEAI9scJNg1mN6jhHflXmwzR6Ho30KYjdZhWEYhhlobrzxRhENv/vuu4W4pnK2F198UdSRl5eXd5qAJ2FPfdjpmk/t4DIzM3H99dfj0ksvDZzv3HPPRVtbGx5//HHhWzNx4kQRmQ9uEzfYofT3TQ2rsbN5CxRFhk6nR3HqBExInwGLocM7gGFiiSaXjA213k4tzoIF+c2zEnDqaPX7XWOX8PLG0A7dVItN7ugao1KMuGV2ghDoFDGndbKF+n8fKH6pJ3lRvFsc15Ngp0kEcl7XhLgm0NW12hatJyxGvyAXYjxIoFv03OKMiW3RzkQOqvXZUqNDvaLDyhoZi5IiPSKGYRgmVqDWbbfddptYuhJqAp7S4N9+++0ez3nFFVeIZaghKRJ2NG3C5oY18EqqPXO+rRBTsuYiyZwS6eExTMhU8Npg8R28OGX8rMSKBSPIIg3Y2eTDb75t7/ZcJOKDe46fUWxRo+UJ+kDUnMQ2BZyCSYvT46wx1r61gvRqUXK/KPdv09oj9SzMqY5cE+KdBLpZJ0Q7w4QLFu2MgGYi5+YYsG2/grIWGRVtEvKDanoYhmEYhuk/SDyUt+/B+rrlaPeoTZNSrBmYljkP2Qn5kR4eM8S/m+SsvqfFh7IWCbsaPBjmswoHdGJ9rQ+/+rK129fvayHPcxUyg5uQYexs6BanR1aCHhl+Ua6Rk2DAbXPUkpnDQTiy+43faKltlbCtJQE7dvngghNSxzzBAVAwnCLzJMgTQwhzSp9nmIGARTsTgNpRUK9Jmv/8ocKDxWOsPaYNMQzDMAxz+DS66oTJXK1D7bdObdsmZcxCUfJY6HWdI4oMMxBQ8OYfm5xCpNNC5mnBnJShRs4JinxT27BgER4cGR+d2iE3yOTt2UXh7zEsBTuy+2vMNXd2EuzBAXOvV0a9xwTJrcBkosAVhMFbV/O3RP823wsz0QCLdqYTxfFObDNB1Ousq/FhZq7qrskwDMMwTHhx+uzYULcCZa3bRTTToDdibOpklKRNhcnArtBM/0AtxyrbZb8g92Fvi4Q9LRJOKLTg/PFq32kyhPtkl1qeQVBAOc+mFx2H8uMUZLk7WqUNS9Lji/PS+r1GW2uVpqWxB7uyt/fCkT2RRDmlrUNCvcuBScMNyE62iki6Zn7HMNEKi3bmAKfN2TkG/FCtts8YlWpAqpVn+RmGYRgmXPhkL7Y2bkBp41pIsuqmNSKpGJMzZyPBlBjp4TGDBKrHJrM0rS1anUPCLV+1YX+rBG+IlPARSR3Obrk2PS6fHIcRyQYUJRtEhNzsTwWnlsulpR2CPpxiPdiRvatAp9rzQ3FkFyLdv03CXBunwyGhtNGDfJse8f7PhmGiHRbtzAEMT9Rjv8MgWm38UO7BKaMs7HDJMAzDMIcJRdPLWndgQ/0KOL2qGVdGXA6mZs1DRlx2pIfHxCjU7ozqxrVU9rJWH8qaJRFN/0mRBb8+Qq0LT7HoRVSdUsXJvZwEeaFYjGI9OrXDy4hSwi+fHN8v/wfcQY7sahp7Rzo7vZeeoIkDTYhr5m+qSNcLR3m+X2UGKyzamZDMyzehyi6hxi5je6OEsen8VWEYhmGYvlLnqMLa2h9F/TpBEfXJmXMwPHEUCw2mV7R71JR2Sl2fnGUKRKYXvdXYqWY7mBpHhwkcmaY9tiBJRNGzE/Qh26GFS5g7fSGEuX/7oI7s1CpNqy3vYv7GjuzMUIWVGBMSG/VuzzZheaUXK6u9GJ5sEH9EGYZhGIbpPe2eVqyvW4b9bbvFY6pVL0mbhrGpk0QNO8OEYl2NtyNy7q89r3eqYndKlhF/O1E1c7MYdMJ53elV/FHzztFzMhkOZnpOeLyKaOKADN6aJMlvANdRY05i3deDIzshHNlD9C8noa6l4TMM0wFfLZhuGZ9hxM4mCQ1OGSsqPThmeIdTKMMwDMMw3eOR3NjSsBbbmzZCViQRTR+ZPA4TM2Yhzhj+tGMmtiDTNBLhNS0eIcrp8bklqgkcce8P7aLPeVfIjT09rnMd9qunpCDe1L9Cl9qm0XiodHJ3gw+76pORBh9Mpo7a9mB0wY7swW3S2JGdYfoEi3amWyht6sgCEz7e6RbivThNQp6Ne7czDMMwTHfIiozdLVuxsX4l3D6n2JedUCD6radY0yM9PCaCfLjdhS0NPuxp8mBP83C4tpIDu+rCnhGn6yTaZ+WY0OyWMSLJIBzbKWpO25QJ2ZX+EuxeSUFFu4R9rbIwryNTO7Hfq0CGTrRKS7F2NnzTtm3syM4wYYVFO9MjmfEGlKQbsaXehx/LPTiTe7czDMMwTEiq2vdhXd0ytLgbxeMkSwqmZM5DXsJwrlsfCm3U2mTsoRZqrZIwgqM2ZA8flxQ45osyN9bVag7tVFNOfcv1gVR2imZrdeaaedxAY/fI2N+mRtQr2yVIQcF+Slun9m6ZJhmNciumjcuBLaFjooFhmP6DRTtzUKj+iVK3WtwKNtT6wlYPxTAMwzCDgRZ3kzCZq7bvF4/NBismZszEqJQSGHScoTbYxHlw8OL5dQ58u9+D/W1SyDpuckPXPIEWjbSIe6g8qwRf/R4cNXkUkm0JiCRkGtfoUoRIp6W+S0o+pbNThH9YkgHZ8XoRPaeWaa5Kud+M7BiGORAW7cxBIZOTOXkmfL3Xgw21XoxMMSCFe7czDMMwQxyX5MSWmtXY1VwKRSERY0Bx6gSMT58Oi8Ea6eExhwGJbWqPRkELde3Dnha1q87nP0sLmKXVOym6rjq0h2qjFpyceOpoa0ef8zYvTBHKXKSJh2q7LNrE0WQDGcppkA7PitcLkT48yYAUS0d/c4ZhIgeLdqZXFCUbsDPJIGqallZ4xGwx/xFnGIZhhiKS7MN+907s2L8K0KuCJz+xCFMy5yDJnBLp4TGHALmekygfl24MRND/usqOd0S9eWjK2ySMTFFvoc8aY8Wxw83iPolc3KM1+kz16CTQKZpe0SbB29EJDkY9fX9VkU5inbsFMUz0waKd6RUk0OfmmVDVTjVOMnY2SyhO5a8PwzAMM7Swe9vw3/IPUObejUwpA1nxuZiWdQSy4vMiPTSmB6gN2a7mjsj5Hn/0vMHfRu2N01OEaCXS/NmEqVZdwAiORPmIpAPbqJHYj1Za3GptOi2UIUAO9cHmdVo0Pc+mZ78iholyovcvDRN1UP/MqdkmrKryYkWlF8MSDbDybCzDMAwzhGh2N8LubYVFZ8WMrKMxLmsS9DouGYsGFH9bMjKCI1F+QqEFqX4BTpHzlzeqbv5doXRwEriAKtrPKLbgtNGWmCsFJCO7WnuHUCcvomCoVRyJdFpo4oEzJhkmdmDRzhwSEzOM2NUkocklC/E+f5g50kNiGIZhmAEj3zYCCwvOwn53BQoTi1mwR5B9bTLW7HGK6HkZOba3SHB4O4QqBRfm5av3KeTHQxFltd68Y6FIekKXNmoUpIgVPNSWzZ/2Xt4mB9qyEVR2n2Mjka7WqFM7NoZhYhMW7cwhQa6h1Lv9Pzvd2Nbow+hUg7ggMAzDMMxQIdmShkpdTaSHMeSgdmQmvwEcsb1JxtNr3Z2OoacLElVBHty//LgRFrEMBtqpLVurGlGnskUpKKBuMeowLFEV6fQ5aIZ5DMPENizamUMmO8GAselGbGvw4YcKL84sVluAMAzDMAzDhBu3T8F72114fbMTl0yKw6nD1f3FKXosGGHuFDknoRos7AdL2j/V3mtp7w3Ozm3Zkvxt2SjtPZrN8BiG6Tss2pk+MSvHJFqFNLtkbKr3YUoW925nGIZhGCZ8eCUF/9nlxisbHQHDuG/3eXDKMPX2dUSSHvceFY/BCLVlq2pXo+nUucfuPbAtm1afnsxt2Rhm0MOinekTlH41O8+Eb/Z5sLbGK1xVY6kGjGEYhmGY6ESSFSwp8+ClDQ4hXImcBD0unxyHE4ss8LhCG8oNht7w5f5oekV757ZsJgP5KagivYDbsjHMkINFO9NnRqUYsKPJgMo2CT9WePGTIjPP9DIMwzAMc1hQn/T3t6u16mlWHS6ZFC/c3LX6bA8GT9o7Gftq0fRaR+e2bAkmnRpNTzaISQtuy8YwQxcW7UyfIYF+ZL4J72+XhHMptVcZmcJfKYZhGIZhDk28emUERPlpxVZ8udeD88fH4eyx1kEVVaa2bNV2GaXtVmzdJcGluDo9z23ZGIYJBSss5rCglHiqZ19T7cWySi/yEw2wDDIDGIZhGIZh+ocNtV48t86BwhQDbp1tE/uKU414/6xUUYo3GHD727JRNH1/m4x2p4R6pxUZCQqsZiDXn/Y+LEkPG7dlYxgmBCzamcNmUqYRu5t9aHYponf7kQXcu51hGIZhmO7Z3ujD8+scWFrpFY+pjey1U+MDojXWBXubR0t7l1HdpS2b1QjkWz2YW2DAqMw4bsvGMMxBYdHOHDZUY3VEvhmf7nJja4Pau53awjEMwzAMwwSzt0XCC+sd+HqfWplOevWUURZcOikupqPMlOJf7yShror1xi5t2VKsan069U+3QcG2rQ7hfs+CnWGY3sCinQkLlNo1Js0oZs7JlO700dy7nWEYhmGYDr7c68a937dDVgC6Q1hYaMYVU+JFb/VYbctW6W/LRouzS1u27ITgtmwdExIOB98fMQxzaLBoZ8LGrFxTYHZ5c70Pk7l3O8MwDMMMaSgCrZmpzcg2CVO56dlGXDklHqNSY+821OFVUN7mb8vWJsEnd27LRhMQFE0flmiANcZT/BmGiR5i768lE7XQxWl2rgnf7vf3bk8xIDGGU90YhmGY3iHLMp566im88847aGtrw6xZs3DPPfdg2LBhIY9vaGjAAw88gB9++EGIuiOOOAJ33nknsrOzA8eceOKJ2Lt3b6fXnXXWWXjooYf6/f0wh0+rW8YbW5zY0yzhT8cliX0pVj3eOD1FOKTHCvT9bHYrajS9RUKds3NbNpvZ35YtiUoDuS0bwzD9A4t2JqxQPfuOJj2q2mUsrfDihELu3c4wDDPYefrpp/HGG28IQZ2Tk4NHHnkEV155JT7++GOYzQeak/7qV7+Cz+fDyy+/LETRvffei1/84hd49913xfMOhwP79+/Hs88+iwkTJgReZ7VaB/R9MX2LRL+91Yk3t7jQ7k8X31TnxcRMNfsuFgS7JCuocXSkvbe5g1Q6gIz4jrR36iPP9zkMw/Q3LNqZsEIXLjKl+3C7S7Q2KWuRUMS92xmGYaIKt9sNi8USlnN5PB689NJLuPXWW3HssceKfY899hiOOuooLFmyBKeeemqn41tbW7FixQr8/e9/R0lJidh39dVX47rrrkNzczNSUlKwc+dOEb2fNm0akpOTwzJOpv/bmv17uwv/2OQUkWliVIoBV02Nx4QMY8y0ZdMc3z1Bdu8GPZCntWVL1COBswgZhhlgjIMxpY6JLJT+RvXslCKv9W5nd1SGYZjo4cgjj8Qpp5yCs88+G5MnTz6sc23duhV2ux3z5s0L7EtKSsL48eOxcuXKA0Q7RcsTEhLw4YcfYvbs2WLfv//9bxQVFYnXEdu2bUNGRgYL9hiB0sZ/9WUrah1qgXdBol7UrB8/wgx9FEehKYVfFekSqu2yMMjToNp7qk0noZ5n08PE9zEMwwxl0R7ulDomOpicZcSuZh9a3QpWV3sxL597tzMMw0QLl19+uRDKb7/9thDLixcvxhlnnIHMzMxDPld1dbVY5+bmdtqflZUVeC4YurbTNZ8m6GfOnCkytOjY1157DXq9PiDa4+PjceONN2LNmjVITU0VEwwXX3xx4JhDhe4ZKO0+HDidzk7rWCPc408xKDDpFWTE6XDROCNOGGGAUS/B1U+fT1/Hr7ZlA8rbZexvU2vVg0mx6FCQqEOBTSfei15Hz/vgdQPeKBh/tMDjjyw8/sEz/mCjzqgW7f2RUsdEV+/2/9vtRqm/d3tmfGy2dGEYhhls0HWTFhLEH3zwgagdf/zxx0X2Gonj448/HiZT7zqAaDcuXSfaKf2+paUl5E1KaWmpSH2nSXpJksS1n8bzr3/9CzabDTt27BDX/J/85CdiYn716tViUp/O98tf/rJP79nr9YqfG07KysoQy/Rl/GTCtrk9Dj82J+Ly/FoY/XMol2SZkGbyweRSsGMbomb8lOVe7zGi1mNCnccEt9wx6aODglSThCyzF1kWLxI8MtBAWZ1i1e8Mxe9PNMHjjyw8fpVQQeqoE+39kVLHRA+UFk9ifWeThB/KvTi9WB/VaXIMwzBDjenTp4vlt7/9Lb777ju88sorIqONrqkUfb/wwguRn5/f4zk0cziaiA82iqO6+bi4uAOO/+yzz0RU/euvvxYCnXjmmWdw3HHHiay5Sy+9FM8//7x4fWJionh+7NixaG9vF5P2N9xwQ5+i7TQJMXr0aIQDmqigG7bCwsKQ7zHa6ev419ZKeHmzF1ub1Aj1HmsxTh+l3kqqoZToGL9oy9ZOi4wquwKJ7onNAH2b0gxAvk2PYTYd8mw6WCKQ9j5Uvz/RAo8/svD4OyD/lt4SUdHeHyl1kUyZ43SPA5mYomB3gw/VrcDaCh9K0vrPvIU//8gS6+MfDO+Bxz80U+YOl6qqKjEBTmKa0tJpIpyy37799ltRvvbggw/i5JNP7vb12jW8trYWw4cPD+ynxyS2u7Jq1SrxMzTBTlDtOu3TWrzR9b5r9GHMmDHiWk3RdkqXP1To86SU+3BCN2zhPudA0tvxb6734rl1TlHuRlgNwE/HxeHkMVbEW/QRHz/9f2ly+duytUqoE7X19P9HD70BSI7rqE/PSdDDECVt2YbK9yda4fFHFh4/Duk6H1HR3h8pddGQMsfpHp1JdZqxqT0eSxoUOFNbEWfoXEMWbvjzjyyxPv7B8B54/EMrZa4vUNT6888/F5lrlHpOEfJFixbhd7/7nYi8E3fccQeuueYaYf7ak2gfN26cuP4uX748INoptX3Lli0iUt8V8q/55JNPOjnYkxgvLy/H6aefLq71J5xwAs4880xcf/31gddt3LhR1Nz3RbAzfXdU/913bfi+XBXrlAp/ZrEVF02Mi3jrNjKNq7LLqG3yCCO5Nk/ne4vMoLZsqdyWjWGYGCeior0/Uur6QrhS5jjdIzTjFAXyXgm1DgUtiVmYPqx/vnb8+UeWWB//YHgPPP6hmTLXV/d4utZOnToV9913nxDloSIGkyZNEuL7YJMLJM4fffRRpKWliXR6qj8ncX7iiSeKCfbGxkaR6k7XehLjL774okjD1+rTqZ6eBDyl5JO4ItFOx4wcORITJ07E0qVL8cILL+A3v/lNv30mzIFQ6rhPBigwfdJICy6bFIccmyHiEwk/VEpY3ZCMFEgwmXyBtmz5NkMgoh5vYpHOMMzgIaKivT9S6vpCuFPmON3jQI4bKYve7dUuoM5rwYjk/rvo8+cfWWJ9/IPhPfD4h1bKXF+44IILcM455whR3BOXXXYZ/t//+38HPR+5vFNnl7vvvhsul0u0byXRTZPiFEFfsGCBSLMnUU5lbZR2T8L+kksuEeVtVPJG+7Qa9ltuuUVc6//yl7+IcrmCggIh2M8999ywfQbMgdTaJfxjsxOXToxHRrwaSb9xRgIoht2f1+1DYWWVF7uaZfgUHeKMwKg0o9qWLVEvTHAZhmEGIxEV7eFOqYsGGjxGlLfJGBO795v9QqpVj4mZRmyo9WFZpQd5Niv3PGUYhokQt99+u0iL/9vf/ibc2Qm69pKL/FVXXSWi2wSZv/YGg8GA2267TSxdIcFNtfLBjBo1SmTKdYfRaBTj0sbG9C9NLhmvbXLig+0ukIG6QafDTbPU3/3wKBHrRL1DxvZGNbI+LcmOY4tzkJDALWUZhhn8RLQgKTil7ssvvxRu8jfddFOnlLq6ujoxa09QSh1BKXV0LC0333xzIKUu0lAd3lvV6bjmSzdeXO8QKVxMB9OyTUi06NDuUbCmJpwdTxmGYZhD4ZtvvhFR7u+//75TdJ/S+3/+85+LzDZm8EPX4+fXOXDuh014a6sq2KdmGbFgRPQJYbrHokl/ajlXmKxHjsXLdeoMwwwZIusi4k+poxQ9Sqk7//zzxWy9llJHjrbz58/Hp59+Ko7VUuroDzfdbFDaHh0XnFIXSZw++kAVeGXg5Y1OXPKfZqyo9ER6WFEDpa3Ny1NvBLbU+8SMOcMwDDPwPPnkkzjllFPE9VOjpKREuMifdNJJIi2dGdz8rzEJl3zuwqubnOL+ZWyaAX85PhFPnpCEyVkmRBt7WiTU2GVhhjcjK+K3rwzDMEMnPb4/UuoiCZmeXDOsFvVJY/DMRq9Ik7/5qzYxY33DjIRAfdhQhgxiilIM2NMs4ccKD04dbeHe7QzDMAPMrl27RN14qEglZbVxWvrgp8lrQJuXotYGXDUlDkcPM0dt5NorKVhRqWbo0YRCgomz9RiGGVqwigwzdL07usCA109LwU/HWYXj6pd7Pbjg42ZsbVDrsIY6c/PMMBt0oo8qfyYMwzADD2Wn7dmzJ+Rz+/fvj2kjQOZAfLKCT3e5Ol1zT0hvwW0zTHj1lGQcM9wStYKd2FDng92rINGsw6TMiMebGIZhBhwW7f1EglmPX85MwAsnJaMk3YiMOD1GpUSPmUukMxJm5qipd6urfXB4ufafYRhmIKGWan/9619FC9VgvvvuO7GfnmdiH1lR8PVeNy75TwseWGrHM2sdgedsRhknjDDCEOWO661uGRvr1Mj6rFwTO8QzDDMk4enKfmZMmhHP/CQJDU454JZOM96vbXbinLFW2MxDc95kbLoBO5r0ItpOxjLHj1C7ATAMwzD9D5m+bty4UbRzI2+YlJQUNDc3i7ZtU6ZMEanzTOyimrZ58fx6B7Y3SmJfklmH2XkmIeRjCWrxJslAnk0vUvkZhmGGIizaBwCaxc5K6LjQvF3qwgvrnfhgmwvXz0jAwsLorSPrL6iO/cgCMz7a4RL17ftTJVHvzjAMw/Q/1G71zTffFC7y1PqtpaVFpMxTv/Rjjz1W9E5nYpNNdV48vcYhUsq17LafjbPivBKryAKMJSrbJZS1SKL0cE7e0LtXYhiG0WDRHgHGphsxLFGP/W0y7v2hHZ/sMuGW2QlDTrSmx+kxIcOIjXU+LK3wINdm5bQ3hmGYAYKE+XHHHSeWUJFaFkixyc4mSQh2swE4e4wVF0yIQ4o1tsQ6QRkByyrUtHgqM0yLi733wDAMEy5YtEeAGTkmvHpqCt7Y7MQ/Njmxqtor2sNdODFOXFwt/jT6odK7ndq4tHkUrK3xYlZu9PWGZRiGGYxQO9UVK1bA46He12rKNK0dDgfWrVuHb7/9NtJDZHrBnmYfmt2KuJ4S1JWFWqMtHmtBZnzsBgPINK/JJcNi1GG6/70xDMMMVVi0RwhyT790cjwWFlnwlxV2rKjy4qUNTlS1y/jNETYMFajOn3q3/7fMjU11PoxONSI1BiMCDMMwscRTTz0lFkqJpzp2qms3Go1obGwUEfif/vSnkR4i04vUcbpvWLLHjZwEPd44PUVkq9FyzbTYdv93+RRhVEvMyDYJ4c4wDDOUCZs62rRpE5YsWYLW1tZwnXJIUJBowJ+PT8R9R9nERfeCCVYMNYYnG4S5jKwAP5R3RHwYhmGY/uGDDz4Q/dgp0n7ppZeKFPkff/wR7777rjClKy4ujvQQmW6od8h4dEU7fv5RM/5vt1tcO2nCmzLWBgurq73wSIpIiSfjWoZhmKFOn0R7bW0tLrroIjz99NPi8WuvvSZm5W+88UaceOKJ2LFjR7jHOaihukFyT3/zjBQUJnckPzy3zoH3tjkh0RV5kDM3zwSTASKlb5vf6ZZhGIbpH2pqanDaaaeJ609JSQnWrl0r9k+cOBHXXnst3nnnnUgPkelCi1vG02vsOPffTfhwuxs+GZida8Lzi5LxwDGJgyZLjbrtbGv0Be4NyLiWYRhmqNOnv/CPPPII9uzZg0mTJkGWZTzzzDM44ogj8OGHH2L06NH485//HP6RDgGCTdh2NflEW7jHVjpw9f+1iNquwQw52mo1a9TehXu3MwzD9B/x8fEBo7kRI0agvLwcLpdLPCYRT4+Z6GJXk4Q3trjgkYBJmUY8sTAJf1mQhJIM4yBrVUcZd0BRigG5No6yMwzD9Fm0f//997jjjjtw1FFHYc2aNaivr8fFF1+McePG4corr8SqVav40z1MKF38plkJsJl0IvJ81WcteGylHe0eGYOV8RlG4ShPKXErqzyRHg7DMMyghSbdaaKdKCoqgsFgwNKlS8XjXbt2wWxmU9BI4/Yp2FCruqcT03NMOGesFY8cl4inT0wSjwcbZExb3S7DoAdm5Q6+98cwDNNX+jQ9S86yOTk5YpvcZeniPnfuXPGYtrkmOTy93c8aY8XRw8x4arUd/y3z4L1tLvxvrxs3zEzAghGDr18ppcDNp97tO12iZc3oVAn5iTzLzjAME24oBf6yyy4TPjSULXf66aeLyfg5c+aIifmFCxdGeohDFp+s4D873XhlowN2r4K3z0wNpL7/alYCBvP7pkw7YnKmCYkx1lOeYRimP+nTX8TCwkIRTfd6vfj8888xe/ZsWCwW8dxHH30knmfCA0Wefzc/EY8vSBK93RtcCh5dbkfrIDKcCSYjXi/6sRI/VnjERZxhGIYJL7NmzRKmcyeddJJ4fM899+AnP/kJdu/ejUWLFuHuu++O9BCHHORf8/lutzCYe3SFHfVOBUkWPSrahobPy4ZaH9o9CmxmHSZnDZ6Uf4ZhmHDQp7+KV111lZiRf/HFF0XUnS72xDnnnIMtW7bg0UcfDcvgmA5m5nb0didhm2zpmG8hYRtcDz8Y+tiXtUhodStYX+sTjxmGYZjwQUayJNLPOOMM8Zgm3v/whz9EelhDEspO/Ha/By+sd4r0cCLVqsMlE+NwerFVtIgd7LR5ZGyoU6PslBY/mO5pGIZhIibaTz31VOTm5mL16tUiyj516tTAzD05yB999NFhGRwTurd7MNQi7cnVdtwyOwGzcs2D5n2SY+xXez3YWOvFyBTDoHHFZRiGiQaeffZZTJgwAaNGjYr0UIY89U4Zv/u+XbjBU5T5gvFxOGecFXFDqDf5iiovJBnItelRlMxlcQzDMF3pc/7RjBkzxKLh8/lwzTXXiP6uzMBBDvPlbTJu+rJN1LnfMCNBROIHgxHfsCQD9rdKIk3+5JGWQVfDzzAMEymo0wt1gTnmmGMiPZQhyb5WCcOTVHGaGW/AeSVW4ety/njrkKvlrmyXUNYsgS7xc/MGn18PwzBMxEQ7CXQyrqE2MdTndfny5SLCToY2FHl/4oknkJycHJYBMj3z6HGJeH69E+9vd+HLvR4sq/Ti6qlxOLPYKszsYhW6aM/LN6GqXXWS3dEkYUwa17gxDMOEg+OOOw5/+ctf8N1332Hs2LGiBVzXv8G/+MUvIja+wcqOJh+eX+fAjxVevHBSMsb5PVyunTZ4DeZ6QlYULK9U0+LHpRmRFje0JiwYhmF6S59UEIlyqmf/9a9/LR7/8Y9/FBF2usC//PLLok/7fffd15dTM33ob05usieNtOCR5e3Y2iiJ3u6f7nLjjrm2mBa6FG2Ylm0SbrK0UFTCOoTSBRmGYfqLp556Sqx/+OEHsXSFRXv4I+svrneIyXWCytQ31XkDon2osq1BQqNThsWoG5Qt7BiGYcJFn64Wn3zyCW6++WZccMEFop/rjh078NBDD+HMM88U4v3hhx9m0T7AjE034tlFyfj3DjeeXecQvd3rHDLGpCGmmZBhxK5m9aJONW/UAo9hGIY5PLZu3RrpIQwJqu0SXtngxGe73ZD8zVColO2KKfGB9PihisunYHWNGmWfnm3kSXmGYZhwi/ba2lpMmTJFbP/vf/+DXq8PmM9R//a2tra+nJY5TCgdfvFYK44ZbsaXZW4cWdAhcKllTJ5NH3O1YvSejsw34T+73NjR6ENxqgG5tqF9o8MwDMPERgu3G5a0osoui8d0LbtyajyKU4d2dF1jTbUXbp8iUuKHesYBwzDMwejTX8msrCyUl5dj5syZ+Oqrr1BSUoK0NDWku3btWiHcmcj2dj+3JC7wmKLUV3zagvEZRtw8OwEFibElerMSDKLWrbTBJ0zpzii2cjsYhmGYw+Cuu+466DEPPvjggIxlsLUuSzDphKkcTTqfPz4OX+9z45qp8ZiYyenfwfclWxt9YntOnkl8XgzDMEw/tHyji/nHH38s2r5pfdrvv/9+/Otf/8K1117bl9My/cTmeh88kiLSyy/+uBkXTYzDBRPiYqr364xcE8paJTS7FGys84lad4ZhGKZvkIFsVxwOB5qbm0WZ26RJkyIyrljF4VXw7jYn3tjiwq2zE7Cw0CL2nznGgrPGcPeTrn3pl1V6oChAYYoBeZw9xzAM0z+i/Ve/+pVwml25ciVuueUW/PznPxf7N27ciMsvvxzXXXddX07L9BNHDTPjH6el4C8r7EK4v7jBic/3uGOqt7vF37v9670erPf3bk+2sMsswzBMX6AsuVCQT831118vPGqYg0MT4p9sdeIfm5xocqlF61/udQdEO0eQD6SsRUJVuwyDHpidyxPwDMMw/SbaacaYerLTEsybb77Zl9MxAwClxP/5+ER8tdeDJ1bbA73df1Jkxm+OsMXEjUVRsgE7Eg0ob6Pe7V4sKuJ+rgzDMOFk1KhRuOGGG/Dkk0/ilFNOifRworpefWmzDX9c4kadUxXr+Ta9MJgjozkmND5ZzfojJmeahlxPeoZhmL7S57+WjY2NePTRR3Huuedi0aJFOP/880Wrt4aGhj4PhulfSOAuKLTg9dNScM5YK6gsnC6YsSDYg3u30+x8ZZskXOUZhmGY8GKz2VBRUXFIr5FlWbSDPeqoozB16lRcddVV2L9/f7fH070CZerNnTsXc+bMwU033YSamppOx3z22Wc4+eSTMXnyZBH5X7p0KaKFP63y4s2qDCHYM+P1uG1OAl4/PQUnFllELTsTmg21PrR7FNjMOkzOYvM5hmGYfhXt1dXVOOuss/Dqq6/CYrFg/PjxMBqNokc7XVi7XniZ6MLm7+3+3KJkXDWlw7Cuol3Gfmd0RwiSLGrvdmJFpeo8yzAMwxwalZWVBywksletWiXEN0XcD4Wnn34ab7zxBv7whz+IrDsS8VdeeSU8HrUveagyO/qZdN9AC20H94VftmwZbrvtNpx33nn44IMPMG/ePFx99dUifT8aWFRoQIJBwjWTTHjzjBQ2SO0F7R4ZG+vUKPusXBN/XgzDMIdAn6Y5H3nkESHSP/30UwwbNiywny74VNP+2GOPib7tTHQT3GKFjGEeX+PFhvpc7DB48P9mWIW4j0YmZhixs4lM6WSsrPZiflBrO4ZhGObgHH/88SHLi+haYLVa8dRTT/X6XCTMX3rpJdx666049thjxT66D6Co+5IlS4R5bTCtra1YsWIF/v73v4vuMwQJcvLD0Yzwnn/+eSxcuBAXX3yxeP6OO+4Q3WkoWHDfffch0kzL1ON3o8sxtXic8FxhDg6lxftkIMemF+VuDMMwTD+L9u+//x6//vWvOwl2gh7TTPnDDz/cl9MyEcQtAWlWHRTo8O9dEr6vbMaNMxNw/PDoqxsXvdsLTPhkpxvbGnwYnWpATgLfADAMw/SWBx544IC/7fSYUuMpXT0xMbHX59q6dSvsdruIhmskJSWJLDwyrO0q2mlSICEhAR9++CFmz54t9v373/9GUVGReB1F6desWYM777yz0+toXDQJEA3QZ2XRc6ZXb6lql7CnWQJ95ebmRd99BcMwzKAU7ZIkITU1NeRz1K+9vb39cMfFDDBWow53zTajRL8H/27MRUW7gt99145Pck1R2dudRPrYNCO2NfrwY7kXZxRHZ1YAwzBMNLJ48WIhjrdv345x48aJfXV1ddiyZQvi4jrKpnpbMkfk5uZ22p+VlRV4Lhiz2Syy8ahd7MyZM4WAo2Nfe+016PV6EW2n9nM5OTm9Ol9voSwCOm84cDqdndaxxkCOX1YUfFsmwetVMCZVjzjFhcP9NfDnH1l4/JGFxz94xk/Xpd5OYvZJtI8dO1b0aD/66KMPeI5my8eMGdOX0zJRwNgEF56dZsH7e3R4bZMz0Nv9ryckYVJmdLVmoZq4fa0SmlwyNtX7UGyL9IgYhmFiA/KeoZpzuun44osvxD4S7NQVhozknnnmGZGm3hu0GxcS48GQ501LS0vIm5TS0lJMmzZNjIECAZROT+nx//rXv+Byubo9n9vt7vN79nq94ueGk7KyMsQyAzH+vU4zdrTHw6hTEKe0orQ5fBkK/PlHFh5/ZOHxD47xd73WhVW004X1iiuuEBdjcnbNzMwUM/SffPKJSJ0nExsmdjEbdLh8cjxOKLTgLyvtaHDKKAmqf48WLEYdZuWZ8O0+D9bWeJFj5lRFhmGY3kBlbFSLTl1gNI455hi8//77uPnmm0U3GDKV6w2U7k7Q+bRtggR2qKg9ucJTVP3rr78W6fgETRIcd9xxePfdd3HGGWcEzhdMd+frLSaTCaNHj0Y4oIkKumErLCw8rDFFioEav1tSsGGnDxlWYFaOASVpeWE5L3/+kYXHH1l4/INn/Dt37uz1sX1SYkceeaRIbaOL/bfffhvYn5GRgQcffBAnnHBCX07LRBnDkgz4y/GJaHErAZdXr6TguXUOnDc+DulxkU9JH51iwM5GPSrbZSyvlpDHup1hGOag/Pjjj8LQjaLqwVAd+i9/+Uvcf//9vT6XlhZfW1uL4cOHB/bTY8rM6wo51FP9uibYieTkZLFv7969IsIfHx8vXh8MPc7OzkZfoRREOm84oRu2cJ9zIOnv8a+v8EDW65AVr8e0fEvYW8zy5x9ZePyRhccf++M/FH+PPqsuau323Xffieg6tXmhNT2mC+pvf/vbfuvtSultFAHQjr/wwgvDnu7GdP4ypVg7vib/KnXiX6UuXPBRM97f5oIkKxEf3xEFZpB5b2W7gmpPdKXwMwzDRCMUxTYYDN3eiJCxXG+hmngS4MuXL+/kEE/p9rNmzTrgeKpVJ3EenOpOtebl5eUickF/16dPny4c5oOh81MNPBMbUOna1gaf2J6TZwq7YGcYhhlKHFaolC6s1MuVLq60psdkakPpbf3V2/X3v/+9SN8j59v33ntPGN+R0G9razuct8L0ktm5ZoxNM6Ddq4jU+Ws/bxEO7pEk2aLH5CxVrJe2x6Hdw+F2hmGYnpgyZYroj04T4cH4fD784x//wOTJkw+pHo8m0Cn77ssvvxRu8jfddJMQ5yeeeKKoWacSOq1WnSb9tV7tdCwtlJJPNetkkEdcdtllIhhAY6Te7JTOTxP0l1xySVg/B6Z/IN+CZRRlV4DCZAPyo8zMlmEYJtaIaH6z1tv1xhtvFL1dabaezGjIHTZUWxeKwJNQp7Q9irTTRMEf//hHccOwadOmiLyHodjb/blFybhpVgISTDqUNki46v9a8PhKO+weOWLjmpxlRJJFB7esxwe7fPi/3W7savLBF+FMAIZhmGiErrvr1q3DggULcPfdd4trL2XJkchevXo1brnllkM+3znnnCPOdf7554so/osvvijqyKuqqjB//nx8+umnARd4mqwnYUcinAQ6HUf7tFZzdDxNzpMx3VlnnYVly5aJune67jPRz95WSZStGfSqaSzDMAxzeETUXexQe7v+8MMP4oIe7FpPx3/11VcDOu6hDvVJP3usFccMM+PJ1XZ8udeDd7e50OKW8bv5ve/tG06o5v6YfANaar1QFKCiTRILmeqNSjGgOM2AjDg994ZlGIYBRHnZW2+9JYTw//73P9Fmja6vlH5OZrMlJSWHdD4S6bfddptYulJQUIBt27Z12kfim352T1BEXovKM7EDTZavqFQzOKjrTJIl8v43DMMwsU5ERfuh9nbds2cPhg0bJqLwzz33nGhZQwL/zjvvPKzZ93D1bh1qfQfJeuGOGQYsLDDj2Y1e/HyMLmw9cPuCVXFhdoodGfk+VLr12NmswO5SsKEaYkmx6DA6RYeiZD3ijNEn3ofa9ycaifX3wOMfmr1b+wpdPynCrtW207gpPV6LdjNMX9hY50ObRxHZeJMzo6/zDMMwTCwS0b+mh9rbtb29XZjXUB387bffLqLsf//73/Hzn/9cpN2lp6dHRe/WodZ3kMT7r/KA1v1Aq3/f+zWpSNDLWJDeAuMAT7LXV5SBvlElCtDgNaLcZUaNx4R6RYedFYAOCrLMPuRb3cg0++A3xo8ahtr3JxqJ9ffA4x9avVv7et2j8jIqLaOyM2Lt2rW4+uqrcdFFF4mIuV7PEVLm0Gj3yNhQq0bZKS3eRC6xDMMwzMCJ9osvvrhXx4WKkIert6vRaBTCnSIDWmSdtqm37AcffCAM7CLZu5X7DqqUtcr4ttQNqibf4ErDDVNNmJZliOj4PZKCslYFO5tl1DsVSAD2AagzQkTeR6foRSQ+kvD3J/LE+nvg8Q/N3q194cknn8RHH32EG264oVPk/dZbbxXPpaamCgHPMIfCyiovfDKQnaDHyBQ2n2MYhhlw0U6per2BWr71to/qofZ2JSdaEu7BqfAk9illnlrFREvv1qHed7AkTsHv5pvw5Co7ytsV3PG9BycWmnH9jASkDUBv91Djp0dTE4Gp+Wobmh2NPuxskuD0KdjRCrFQH9niNCOKUgywRDA6MNS/P9FArL8HHv/Q6t3aFz7++GPccccdOO+88wL7qD/6pZdeKq6z5CDPop05FKrbJexulkBf3bl5ZvaQYRiGiYRo/+c//4lwE9zbVRPtWm9Xah/TFer3SvV2GzduxKRJk8Q+aiFDrvKnnHJK2MfH9A26UC8stGBungnPr3eKfu5Lyjz4scKLa6bF4/TRFmFmFylSrXrMzjNjRo6C8jYZO5p82N8qodYho9bhwfJKtUUNCfjcBDavYxhm8NHU1CQmvEMxcuTIQ8qaYxiZWrz5zefGpBmREc+lFQzDMOEkon9VD7W3K7naHnHEESI6sGrVKpE+SLXtZKJzxhlnRPKtMCGwmfWiNdzzJyUHers/v84h1tEATRyMSDaICYaflcRhdp4JKVa9SO2jKPxnu9x4Z6sLa6q9aItgOzuGYZhwQ8L8888/D/kcdWQZMWLEgI+JiV22N0pocMqiY8uMHG7xxjAME24ibutJvV0pek69XUmcUzRd6+1KKe/UQ/bBBx/E4sWLxfFUa0ci//rrrxfHT58+XaTxpaWlRfqtMAfp7f7hDhdsJj2S/e1fqOTCJSEqnNzjTTrRmmZihhH1TlncgFCaHzngrq3xiiUv0YDiVIOIwlOLOYZhmFiFfGqo8wq1elu4cKEwcm1sbMTXX3+Nzz77TFx3GaY3uH0KVlerUfZp2caouKYzDMMMNiIu2g+1tyul0//+978XCxNrvd07GzN9u9+Dx1bacePMBBw3PDrq32gMmfEGsczJU7C3RcL2JgmVbR3LUoNOGOyM4d7vDMPEKNT/3G63i24s1EZVgwzo7rnnHs5eY3rNmhovXD5FZKqVpEf8tpJhGGZQwn9dmYjx3jaXcHK/57t2zMkz4eZZCchPjB63WYqmj0o1ioXS43c0StjZpPaf3drgEwvdpJB4H5ViFNF6hmGYWOGCCy4QLVP37NkjIu7URpV6tL/zzjs4/vjjRdSdYXqCjF3pWkiQj00k/WoYhmEGMyzamYjxyPFJeG2TE69tdmJ5pRcX/acZF0+Mw8/Hx4m6uGgi0azH9By9SP2rsqvu82UtEppdMlZUylhV5UVBIkXfjShI1PONC8MwMQFlClF9+3fffSdK07755htRskaZbgzTE4rffE5WIPxhomnSnWEYZrDBop2JGNRW7Yop8TihyIK/rLBjVbUXL6x3YskeN+6Ya8OULFNU3uDm2QximSsp2NMsCQFPzvP7WiWxUD3fqFRVwJNTPcMwTDRCNezvvvsu3n77bVRUVIjys7POOkukxpPxK8P0xL5WWZSMGfTA7Nzou14zDMMMJli0MxFneJIBjy1IxBdlHjy52i5uBMjYJhYmHchkjxZKEaTU+R3U+92rYFOdTyyZ8ZQ+H/ne7wzDMBrLli3DW2+9hS+++EJ0aZkxY4YQ7X/7298we/bsSA+PiQF8soLlVR6xPTHDhCS/wSzDMAzTP7BoZ6Imgk0R97n5JnyzzyP6qGvsbvYJx3Z9FBu+UUR9Vq4Z07MVVLTJ2O7v/V7nkFHn8GCZ1vs91Yg8G5vXMQwz8LzyyitCrFMNO7V0u+6660RkPT4+Xoh1/rvE9BaalG5zK8LLZUoW30oyDMP0N/yXlom62vFTR1sDj+sdMq79vBUjkgy4bU6CiFpHM1TLPjzZIBanT8GuJp9oH0eR+F1NklgSzTqMTjVidKqBoxMMwwwYDz30EMaOHSvapAZH1Nva2iI6Lia2sHtkrK9VW7zNyjXBxFlkDMMw/Q4rBiaq2dmsutKWNvhw5Wct+Osqu7hhiAWotn1ipglnjbHgjGKraIVDBnta7/d3trrw2S4XdjT5RKohwzBMf3LKKadg7969uOaaa0SU/b///a8wnWOYQ2FltRc+GchO0GNUCpvPMQzDDATRHbZkhjxz88x447QUUev+5V6PELpf73VHVW/3g0FjzIinxYzZ/t7vVPte2U6LjMp2D5YZdMiLkwCvQTjyMgzDhJs///nPaG9vx8cff4z3338fN9xwg+jLvnDhQvF3Khb+njKRpdquZozRV4Wuz/ydYRiGGRg40s5EPRnxetx7VCL+cnwi8m36QG/3O/7XBjnGBK7W+33RSAvOHWfF9BwTEi06eCQFO5pkLG1OxEe7JWyo9cLhja33xjBM9EMO8eeff77oxU7inZziv/rqKzFZ+Otf/xp//etfsXPnzkgPk4lC6Hq7rEJNix+TahTXZoZhGGZg4L+4TMxA5nT/OC0Fl02Kg0mvus5HszndwbCZqe+7CT8da8XJoywYmayHQaegxa1gZZUXb5Wq7e/KWnyQOH2eYZgwU1xcjDvvvFP0Zn/yySdFv/bnn38ep512Gk4//fRID4+JMsifpcEpizKvGdzijWEYZkDh9HgmZnu7Z8TpOznMV7dIsCD2oPTCXJsByfkGJDe3wJqbg/1OPWrssnCgp8VqJPM61X0+Leh9MwzDHC5GoxEnnHCCWOrr6/HBBx+IhWE03JKC1dVqlH1atlF4tjAMwzADB4t2JiahKHtwyt4jy+3YWOfDjKQMLE6VMKNAFpHsWMOoB4pT9ZiSb0WzSxYmdV17v1NKIqUmjqTe73zjxDBMGMnIyMBVV10lFobRIPNUl09BilUnTFUZhmGYgYX/8jIxj1cmoWsQgnZ1qw2rf/RABw9GpRowOdOIeflmscQaKf7e7zNyFJS3ydjR6MO+Vkm0wat3eLC8CqIVHrXBy7XpY7pUgGEYholOqGVpab3aZYDM56i1KcMwDDOwsGhnBkXK/M2zbTguD/jn2gaU+xJRaVews0kSi92rBEQ7ReX/s9ONiZlGFCbHRk08jZEyC2jRer9T9L3RKWN3syQWm7/3O01ecO93hmEYJhyQQeHySi/IVoWuQfmJ3OKNYRgmErBoZwYNY9P0uCCvHiUlmXDAio11Xmyo82FqVsfXfE+zhIeX28V2olmHSZlGTM4yiYj8OH8f9Vjo/T4hw4gGJznO+8TERLtHwboar1go6l6cZkRhkgGmKH8/DMMwTPSyr1VGRZsEupTMyWPzOYZhmEjBop0ZlFDd93EjLGIJxiMBM3KM2FznQ5tHwY8VXrEQVAL/q1kJOL3Yiljq/T4rVxFp8+TsS73fq9plVPl7vxclG1CcZkBWvJ776TIMwzC9xicrWF7lEdsTMo2cxcUwDBNBWLQzQ4qSDCP+ujBZ3IzsaJSwgaLxtT6xbnIpyEnouCn5odyD59Y5MCnLiMmZJkzOMiInwRCVvd9HppAxnRHtHllE3ikC3+pWsK3RJxYyD1LT542IN7F4ZxiGYXpmc70PbW5FXDOmZHGUnWEYJpKwaGeGJCR0ScDT8rMStW6PzN4oIq2xvtaLXc2SWD7c7hb76PnJfhF//AizMIuLJsgxf2q2HlOyjKJl3PYmCXuafWh2KVhV5RUtewoSqXWcWiPPhkIMwzBMV+weWVwDiZm5pqgvHWMYhhnssGhnGH+6+bCgNnLE+ePjRO24Fomn9PNah4wvyjximZVrQoo/k35rg0/0saW6eDLGi4b3k2MziGVunknU8lP0vWvvd3LYp+h7Ovd+ZxiGYfysqvbCKwHZCXqMTom+DDOGYZihBot2humGVKsexwy3iIUg5/Yt9T5s8EfgCxI7hO7rm534ep8HJj2EcA82uIt0HSBFSMamG8Wi9X6nFHqHVxG1/bSQaB+TZsCoFCP3fmcY5pCRZRlPPfUU3nnnHbS1tWHWrFm45557MGzYsAOOffLJJ8WxoVi8eDEefPBBsX3ZZZfhxx9/7PT87Nmz8c9//rOf3gVD1NjVzitkg0It3tgPhWEYJvKwaGeYQ3Bun5FjEktXqGY83apDg0vBxjqfWN7Y4hLPUSr6CyclR0UqenDv94o2Sp/3YX+LhAanjKUVMlZUejE8We39nse93xmG6SVPP/003njjDTz00EPIycnBI488giuvvBIff/wxzGa15abG5ZdfjvPOO6/Tvpdffhn/+te/cOmllwb2bdu2Db///e+xcOHCwD6TiWur+xMqFVtWqabFUxYWmboyDMMwkYdFe5gvdm5ZFWrM0OKW2TbcPEtBZbssIvHUao7S6ve2SqJ+Pliw3/m/VpFCr9XGj0wZ+Npyvb8cgBYX9X5v9gljPhLvlEpPS4JJNa+jCHykswUYholePB4PXnrpJdx666049thjxb7HHnsMRx11FJYsWYJTTz210/EJCQli0diyZQv+8Y9/4A9/+APGjh0r9jU0NIhlypQpyMzMHOB3NHShMrB6hywytEJNUDMMwzCRgUV7GNncuArL2r+Cs7oRc4cdiwRTYqSHxAwglEKYn2gQy0mj1H1NLlksGpSSvrTCC0kBvtyrttIhZ96JZIqXqiDNaUHJAI+batsnZFDvd5O4WaP0eUr/t3sVYURES45NjzGpRhQmc+93hmE6s3XrVtjtdsybNy+wLykpCePHj8fKlSsPEO1due+++zBz5kycddZZnaLs9De1qKgorBPrDocjLOdyOp2d1rFGqPF7JAVL9/vg9QGT0/SA1wmHGnSPOgbj5x9L8PgjC49/8Iyfrku9LUFi0R5Gksyp0EGHSnsZPt3zFsanT8O41Ckw6PljHsp18bRomA3A4wuThBCmSPymep8Q8iuqvFhRBUxLSsJJQf+Rf6jwCkE/UC71lAoZ3Pudou8V7RKq22VUt3uwtBIoSjaK3u/Z3PudYRgA1dXVYp2bm9tpf1ZWVuC57vj666+xdu1afPjhh532b9++HYmJiULQ//DDD4iPj8eiRYtw3XXXHZBu31u8Xi9KS0sRTsrKyhDLBI+/tN2KcqcVCQYJQBtKaxH1DKbPPxbh8UcWHv/gGH9vr2msJsPI8MTRmJFwDOxx9WjxNWBj3UrsadmO6VlHIs82PNLDY6IASpWflm0SCyHJCnY3q/3i11S5MUzuiALtb5Vx5//axPaIJIM/nV41uKN68/4UzMG936n1z85mCdsb1d7vtKYl2aJDcZpROAsnmDl9nmGGKlq0oeuNh8ViQUtLS4+vpVr24447DiUlJQeIdrfbjcmTJwtDOhLbDz/8MCorK8W6L1A9/OjRoxGu90w3bIWFhYiLi0Os0XX8LW4Fq3f7kJEALBhuQL4tuv+mD7bPP9bg8UcWHv/gGf/OnTt7fSyL9jCTYEjCjNzZqJcqsa52Gdo9Lfi2/FPkJxZhetYRnDLPdIJq2Un40nLSMAWlpfbAc81uWaSjl7VIojaelo93qv3i0+N0+MX0BJxYpDrb9yckyKdk6cWEAbWM20G931t84iYvuPd7QZws0v4ZhhlaWK3WQG27tk2Q6O7phoYE+PLly/Hcc88d8BxF2O+44w4kJyeLx2PGjBGi+6abbsLtt9+OjIyMQx4nTXRSxD6c0PsL9zkHEho/Ld9Ve2Aw6lCYZEBxVv9fV8LFYPj8efyRg8cfWXj8OKQAHIv2foB+ASOSipGXMAKbG1ZjW9NGVLTtQbV9P0rSpqEkjVPmmYNDEfXXTktBi1sWbvRkcEfr0gYfGpwKbKaO/+gknF/b7AxE4sdnGIXbfb/2fm9Ro+9a7/fdDRJaGpJQvc+H7CSPvzRAhxSLnuvgGWYQo6XF19bWYvjwjqwyeqwZy4Xiiy++QFpaGo488sgDnjMajQHBrlFcXCzWlHLfF9HOhIayusrbJNCf6Tl5bD7HMAwTjbBy7EdMBjOmZs1DUfI4rK75HrWOCmyqX4k9rdtEyny+bUSkh8jEAMkWPeYXmMVCuH0Ktjb6RDueYNG+skpdAKe4+SLXd3Knp7R6avNGhnfhgkQ4tYWjhSYVqPZ9S60X9Yoele0K6ty+wLE0iZho1gXq+0nI0zrJ3NlVn2GY2GTcuHGw2Wwiaq6J9tbWVuEKf+GFF3b7ulWrVom+6yTQu3LRRRehoKAg0LOd2Lhxo4i2U0oiEx6oRGt5lWqKOiHTKK43DMMwTPTBon0ASLak4rhhp2J/226srVsKu6cV35V/hjzbCCHebeakSA+RiSEsRh2mZHWOhpw00oKMOL2ojSeDu1qHjNIGSSxvbQX+cWqyqE8n9rZIIK1ckBieuni6yZuZq8e4JCOWO9uQkZsNp86IJic55ytw+hRRC9/qlsTP1qCJBWolp4n4NKte9Lsngc8GdwwTO1AtO4nzRx99VETO8/PzRZ926td+4oknQpIkNDY2CmO54PR5EvVnn312yHP+5Cc/wQMPPCBq2ufPny8EO9WyX3HFFWKCgAkPpY0yWt06xJkOvK4wDMMw0QOL9gGCRMjwpFHItQ3HloY12Na4AZXte1HjqMC4tCkoSZsKo54vmEzf0HquLx6r3hBX2yUh3knE72qSRG28xisbHfhvGaWv6wKReFqTIzwZ0B1O7/cUk4TiVD3i4zsMqUi0a63vSMQ3+9fUXkjdR0d1iHmjvsN1XxP0tMQZD632h2GYgePGG2+Ez+fD3XffDZfLhVmzZuHFF18UkfHy8nIsWLBARM0XL14ceE1dXR1SUlJCno8mAej/+z//+U8h3qlX+6WXXoqrr756AN/V4MYl6bC1XgYMBszKNYne7AzDMEx0wqJ9gDHpTZiSOQdFSWOwuvYH1NjLsbl+NcpatmNa1hHItxWyMGEOm5wEA3KKDCGN6mQFILN3Es7f7PeIhbAagElZJjx6XGJY09aptj7OZkCerWPigNrZUR94GkMnQe+W4ZOBOocslq4ZBkLEW/RIi1Oj8rRN+xmGiSwGgwG33XabWLpCae7Ud70r69ev7/GcF1xwgViY/mGbPQ7eRCA/US+6gDAMwzDRC4v2CJFkScWxBaegvH0P1tb+CLu3Dd9XfC4i8STek8yhow8Mc7jce1Qi3JKCbQ0Uie8wuGvzKGhxyZ0E+0NL20XapGZwlx4XnnpHmpiymWlRswQ0ZEVNpddEfJNbFpF5cqqnWv7qdlo6i/kEk+6AqDwJ+sPJGmAYhhnM1DkUVLrNyEgE5uabOFjAMAwT5URctMuyjKeeegrvvPMO2traRErdPffcg2HDhh30tR999JGY1f/yyy/FTH6sQRfJYYkjkZMwDKUNa7C1cQOq2vehxk4p85NRkj5dROYZJtxYDDohwmnBhDghlqm1XLuno2cbieT/2+MWke93tqr7qA5eS6mfmm0Srd7CiUixJ8d5qx5FQft9siKEe3BUntY0XorY270SytWW9geY32m18mx+xzAMo2Y6raxRS5JGpeiRGc9RdoZhmGgn4qL96aefxhtvvIGHHnpImNaQec2VV16Jjz/+WJjbdEdFRYXo4zoYIGE+OXMOCpPHYk3ND6I13JaGtShr3SGi7gW2Ip4FZ/oVEsuaUV0AHXD3ETYRiaeIPNXGl7dRayA3Pt3txjHDzLj/mMTATeC2Rhm+furTTlFz6k3fNdJPGQPNQSKethtdClw9mN8lB0flLWx+xzDM0GJHk4R6pwKjTsH0LHaLZxiGiQUiKto9Hg9eeukl3HrrrTj22GPFvsceewxHHXUUlixZglNPPbXb6DxF2CdMmIBly5ZhsEAp8ccUnIyK9rJAyvwPFUuQk1AgXOYppZ5hBjIav7DQIhai3SNjUz2l06sp9TNyOrJAKttl3PA/N0y64cipcCHX5kNOgh45Nr2ory9JN3ZKgw/nGLMTDMhO6LyfzO8ahXs9CXl/hN4twytB7G900lEdYt5kgOgnn6CT0Oy0IMUuI9eksPkdwzCDCjIAXVVNrUGB0fEu4TnCMAzDRD8RFe1bt26F3W7HvHnzAvuSkpIwfvx4rFy5slvR/swzz8Dr9eL6668Pi2inKKHD4Tjs8zidzk7rvpJmyMYx2adhW/MGbG/egP3Ne1DRsg/FyRMwLrX/XObDNf5IwePvXygeMzlFXTCGvoNy4P9NWYOERBPQ5tVjf5uC/W3qTaHGpeON+Pk49Xtb0S7jsTVeZMXrkB2vC6xpyYzThc3BONUApJKYTwg2vwOa3Yp/6dj2egGHC8L9urk9DlW73DAaJViNJOZ1QYv6OFpdlqP9O3QwePwd0PeVJ4yYcLOuxgunV0GSRYcRcEd6OAzDMEwsiPbq6mqxzs3N7bQ/Kysr8FxXNmzYIKLz7777LmpqasIyDpoAKC0tRbgoKysLy3n0iMMIeSJ2uTahzleDmroarNT9iFHWCcgw5vXbDV24xh8pePwDDzWau28U0Og1BpamwLYBxtZWlJaqQmZzexw21Gd3e64zsxpxXHqr2G7xGrChLR5pJh9STT6xthoOPwefYv7p/oXc9B2SHm2SAe0+AywWPdrbGtAs0TSFDuWh3q9eRqJRgs0g+dcybEZJpN9HA7H4HQqGx6/SU4kYwxwqVD60pd4ntmdl69G6P9IjYhiGYWJCtGvRiK43JhaLBS0tLQccT1E9SqWnpbCwMGyinfrIjh49Oizvh27WaGxxcXEIF9MxE5X2fdjQsEykzNdhL3RxXkzJmIskc/hS5vtr/AMFjz/y49eXlWHmmIIQ408LbGU5FaTlSKhxKKh1KKixK6hxqttuCRgzPBslw/PFsSuqJby7U21Jp0ERfYrO03LaSCNmZhsC9e1OH5Bs7ntKe/DvwGSxoiUoGk9Lk1uBw59EQFMH5H3X1sX8TovGa0uSWfUMGAgGw3eIx6+yc+fOsI2LYYgVVV5IitqxI98GqFOjDMMwTCwQUdFutVoDte3aNuF2u0Pe8Pzxj39EUVERzjvvvLCOg27w4+Pjw3Y+Gns4z0eMjh+HwvRR2Nq4HqWN69Dkq8M3NZ9gbOokTEifAZPBHNXjH0h4/NE9fnpqGIW4Q6QDkzCmOvV4kypy02xeHDVMQU27jCq7LNrSUeZ9W4uCXS0KFhaZER+v1tyvr/Dgtq/bRL95tc5d36munhzvaX0o7yHJBnTtY0GTA51q5f3md+S275RJuAFVQdnRFH1P8ZvfqWt122bqP/O7wf4dGgrj59R4Jpzsa5Wwv1XNBpqTZwKkDk8PhmEYJvqJqGjX0uJra2sxfPjwwH56PHbs2AOOf++990RUftq0aeKx5L/oUO37tddeK5bBDNWyT8yYicKkMcKojgzrSMTvbd2JqVlzMTxxNN/oMTELfXdJzAYTaEvnx+FVUG2XRK/2aruMiZkdf8JIPBMuCdjbKoklmN8eYUPOSEOgrvPFDQ4h4knYk8DPtRmQrD+4Az5NKqiv6zzhQFH+ri3pmv3mdw1OGQ1dzO+oLp4i8VpfedGeLk7PxlAMw4QVSVawolLNWBqfYUSyRY8w2PgwDMMwQ0W0jxs3DjabDcuXLw+I9tbWVmzZsgUXXnjhAceTo3ww69evFy7yzz33HMaMGYOhgs2chKMKFqGyfR/W1P6Adk8LllZ+iV3xpZiePR8plo5UZIYZTFAEnlrTjSQzvC6cPMqKBYUW1NpJ0EuoEWv/0i5heJB7PfWkX1tDtZ1qfWcwZM/0myQJi/x/Uva1SFhd4w2IexLsWiZAp2wdE43PgPyg3vUk5ik7QETl3R2CvsUlCxdnKgmodaiTDRok2rtG5WkdreZ3DMNEN5vrfWhxK4gz6TA1u3+MbBmGYZhBLNopak7i/NFHH0VaWhry8/NFn3bq137iiSeKSHpjYyMSExNF+vyIESM6vV4zq8vLy0NKSoi7+EFOnm04suPzsLVpvejrXuuoxOdl72JM6kRMTJ8Z1pR5hokFKApO9ZoHay83O8+Ee460dYraqyJfglsiwdxx7JoaL/68wt7p9UlmirbrkW3T45KJ8RiXrv4ptXvUSD09T0KeFnJpTrIAw4X9XUfkq9Wjpdd3pNmTwKd2dc52RbTRC8Zm9veW9wv6NKseyRad6GHPMAwTCspOWl/rN5/LMfHkH8MwTIwSUdFO3HjjjaLN0t133w2Xy4VZs2bhxRdfFOZw5eXlWLBgAR588EEsXrw40kONSgx6o6hp11Lmy9v2YFvjBjVlPnMuRiQVc8o8w3Qhz2YQS1eoBeWqTdsxLrUjcycjXo/5BaZA1L7dowruVo+E7U0SfjauI5/+v2UePLrCLvq7U129qKkXEXp1e2auSQhvg16NptN2MD7ZH5XvkmZv9yri57Z7qC6143j6r03CXUTlLXpYIaPZaxDHWxVlwAzwGIaJTqgnO2X1ZMbrMZr6YDIMwzAxScRFu8FgECnutHSloKAA27Zt6/a1c+bM6fH5oUSCKRHz83+CKpEy/yPaPM1YVvUVdrWUYkbWfKRYQzh/MQzTCZrgshnlTtGo+QVmsWhQNJ3EOxnj1dglFKV03AhTDTtB9e2Ugk9LME+dkBQQ6l/udeOjHS7VNC++wzCPxH1hsgHFaR1/nsnkTqTXO/2CXqTaq+Z3JPKbXRLKIMHrlVDfnIgdO3wwm52wGnWIp8XkX/zbCdpjk04Y9/HEHsMMPmrtEnY0qlH2uXkm/n/OMAwTw0RctDPhJdc2HIvi87CtaQM2N6xBnaMKn+99D6NTJmBSxkyYDarTNsMwfSPBrMcoWkJ0W7x0UjzOHx8XqKvXUu+1Gvs8W0dkfWejhNXV3dXVA3//SRImZqr1p7uafdjeKPkN8/SYlmMSYrur+V1tqw/tehmUMa8ogNOriEU1wQsNHRss6LsKfG3bzOKeYWIG8tNYVqn2p6QIe1YvO2cwDMMw0QmL9kGaMj8+fbpIjV9XuxT723ZjR9NG7GtTU+YplZ5vvhkmsnX1PxlpFhH1qmDTvHbqX08mdUBGXIfA/26/F//c3Fl5U1q8Zoz3i+nxmJhpgMPhw7I2O/Lz9UhJtIj0eZdPrWsVi0/ptO3yKZAV+FPve7bNN+rRraAP3jZxzSzDRJydTRLqHDJMBmBWLvvbMAzDxDos2gd5yvyR+Seiyr4fa2t/QKu7Gcurvsau5lLMyJ6PVGtGpIfIMEOWwmSjWEJFyChqTm3gNIYn6XFEvikg7qlmndygW9ySiMDfMKOjJ/g3TUn4cie1d/KIKDqZ4lHNO4l8avV044x45Pjr+Xc2ebGvVYbFQKJcB+o2Rwn+FMEPFveUhu+TgVa3IpaeoNIC4aTfQ+SeHPLZQI9h+geqYV9ZrUbZp2aZDuh2wTAMw8QeLNqHALkJw5BV+FNsb9yIzQ2rUe+sxhJ/yjz1fbcYgqyyGYaJKJQFkxbX+Sb7pFFWsWi0++vqVdd7SZhMBRNvBBw+iCh6s1tBs7ujtp5Eu8aSPR68scV1QERdmNtZ9PjD0YmiVR4Z5K2s8qK03guLSJXXgQLqpLt10MErq+KeetKTYKBMgWb0LO5FvX0XMa/3yahxm5DpVJBhUmA10s9gwcEwh8L6Wq8oi6HOFdSXnWEYhol9+K/5EMGgM6AkfSpGJI3Gurpl2Ne6EzuaNmFf2y5MyZyDoqSxkR4iwzC9xGbWYzQtIerqT89qwh3H5MBkifNH42WxJvO6FpeC1KC0e2obNybNoB7nkuGSyMEeaHBSHbwk6tgJioqvrfEeIPA1qL7+2UXJoiSAovPf7feIVnkWI2ChCL5epwp8v/4269W0fUrPbww6jzDSa03Avj0+mExOcTxF5XtMyWczPYYJQP/fN9epPhlz8syc0cIwDDNIYNE+xIg32XBE3kKMSi7B6trv0epuwoqq/4mU+fFJMyI9PIZhwgTVlmfE09I5Ch/MeePjxKJBIloT+bROD2pJNzLFiOOGmwPPN/vXJPJJ7FMfeYrA07KvVRLt77qDTPbybQYRnf9ijxtLKzywmHQwKjKcLhMcbTJMRkmk7afF6eHw9iw8KOofp4l5c/cCnyYLWNwzg5nllV5IClCQaMCwxO7/7zMMwzCxBYv2IUp2Qj5+UniOiLZvql+FBmcNvmr7CCZnPEZJIxGPjhRahmGGBpSybjUakJ1w4HOLRlrE0rX+niLrlIKfHhTBp370FOHThH1A6Ltk0eM+K14vxHgatdDzKtjcENwaLwFop8p6VfQ/dnyiaItHAv+zXS58s9+jjtMAmCiKb1DN/2jfsESDWBOy6FNPW7qDmukldHnM0UkmFtnfKomFvr5zuMUbwzDMoIJF+xBPmR+XNkVNma9dhp0NW1Dp3YvP97+LmXlHYmRyCV/0GYbpFvr7kGCmpfN+SsulJRQkpoP/qiwstGBEskEI//p2D/bVNkEXl4x2n16I/cIUAzLj1Tz9L8p0qHdSrXzoevn7j7aI+n6HF/h0l0tE++MoRV9kAGiTEjrxeFy6AQkmfSDDgOr26TkS9maDPkjcd++ab2Bxz0QJkqxgeaU60TUhwyjMJxmGYZjBA4t2BnHGBMzLW4A8SyH+r/EDeCQXVlZ/i10tWzEjaz7S47IiPUSGYQYJXY3lxqYbxUI4HApKSxtQUpKF+PgDs33OHWfFkQVqin6zq3MqP4n+SZkmEcEnllZ6hLQnQz6K0qt0iP3Tiy2ipp+e++8eN77Zr7ptkw6nKL4m7skMb1q2STjvE20eGW0eVeCTYR+dI8miFyLeKEuQJBbyzMCzpcEn/i+QB8SUbFOkh8MwzCEiSRK8XvU6dDDcbndgrdfH3gTdUBm/yWSCwdBz+99DgUU7EyAzLhfTE46BOUPBzvZNaHTW4ot9H2Bk8jhMzpgNi7Gj9pVhGGagyUowiKU3XDM1HueVWIWYJwM+Vdh3iP15+eaAEN/VJOHHCi+8suq43yH0VZF/1hgDkq164ci9tcGHpZWdb6woI5/EfYFNh6NtVkzrh/fOMN1BJSrranyB0hSabGIYJjagMrPq6mo0Nzf3+jWyLMNoNKKysjImRe9QGn9KSgpycnLCkrnMop3phF6nR3FyCcZkTsT6umUoa9kuTOr2t+3B5MzZQsDTMQzDMNEMGeJRWn1mL+w5rpgSj8snx4n+9J2M9vwC/8Qii3DsJ9ySgqp2yX+c2tee9H27F6I2foRVnYFnmIFidbVXtFok08ni1PBFdRiG6X80wZ6VpWaY9UbcUVSeorwWiyWskdyBYiiMXyHPH4cDtbW14nFubu5h/1wW7UxI4ozxmJt7vOoyX/M9mt0NWEUp881bMCP7KGTEZUd6iAzDMGGDbpTiTVS/bkCurfvjzh4bJxatPp+M9DSTPaPkhr2CZDzDDAx1DgnbG9Uo+1w2n2OYmBN/mmBPT08/pNcRVqs1ZkXvUBh/XJx6r0DCnX7Hh/teOWTK9EhmfC5OLDwb07OPhMlgQZOrHl/s/QDLq/4Hl88Z6eExDMNEtD4/0awX7bUmZpowPIkvqczAQZGcZRVqqcboVOr6EHs3vwwzlNFq2EN5uDCDg3j/77a3fgU9wXcYzEGhdPgxqZNwctHPUJQ8Vuzb07IVn+x5E9ubNkFWOLLEMAwzlKEavyeeeAJHHXUUpk6diquuugr79+8PeeyTTz6JsWPHhlzuuuuuwHFLly7F4sWLMWXKFCxatAiffPLJAL6j6Gdns4RahwyTAZiVG7pbA8Mw0Q9nyAxedGH83bJoZw4pZX5O7nFYOOJMpFoz4JXcWFPzPZbsfR/1zupID49hGIaJEE8//TTeeOMN/OEPf8Cbb74pRPyVV14Jj0dtQxbM5Zdfju+//77TcsUVV4iIxKWXXiqO2bVrF6655hoxCfD+++/jpz/9KW6//XYh5BmIGvZVVWrkZkqWSbQhZBiGYQYvLNqZQyYjLgcnjFgsatspZb5ZpMx/iOVVX8Ppc0R6eAzDMMwAQsL8pZdewo033ohjjz0W48aNw2OPPSYMlpYsWXLA8QkJCcjMzAwsdXV1+Mc//oF77rlHRNuJV199VWzfdNNNGDVqlBD1FG1/4YUXIvAOo4/1tV7hGp9k0Ym+7AzDMMzghkU703eX+dQJOKXoPIxMKRH79rRsw6ciZX4jp8wzDMMMEbZu3Qq73Y558+YF9iUlJWH8+PFYuXLlQV9/3333YebMmTjrrLMC+1atWtXpfP+/vfMAc6M89/1fXdrem8uue+8VMAYMOIRAMPjmkEJLaCf0auBACCUGTDdwMSGBkEC4Jgkl4QQCISTUuBtsx2sb97W396auuc/7jkYrabXr3fXaGu2+v+eZlTTzjfRpdjTf/L+3EfPnz8fGjRs5lnsw0+wO4D81avK5eYVWmI1iZRcEIb4sWrSIQ59iQd5S4WFQNDbQNZ+u6T/+8Y+xffv2Xn9eaWkpLrroIg7Hos+mid+eQuPIhAmqdkkkZHpWOCrsZgfmFpzCpeDIVb7eVYNNVV9gb+MOTl6Xl1QU7y4KgiAIxxCyqMcqaUPZcrVtXfHPf/4TmzdvxjvvvNPpPam2bfT7OZ1ONDQ0ICsrq9f91Erw9AfUj/DH48lnZT64PAqKUgzINtN3MiRU//sD6X98kf73D1Q2jEKJKBu5lpG8J2gTl/TYm/2OJdQX7btEQ+uJTz75JNSWjj3VOV+xYgV7Un3wwQfshdUTGhsbWeyfdtpp7KH19ddfc2gWZWunPCjdsWnTJlx77bVd9rWn31V7PNJ70Hb6LPq+2nGIfq+exr2LaBf6BSoBd0bx+djbtANbatZxibiPD/4FxWljMD1vPhzmnv0QBUEQhMRCu/G1WiOToVEN26ampm73/c1vfsM3XtFWD5fL1en9tNex4uR7AmXvJetMf7J//34cT2o8ZmxuSoEBCib4W7CjLZBQ/e9vpP/xRfp/9JjNZhbvfaGv+x0LSHz6fD6+dkejZU5PTU2N8MbKz8/H7bffzolLKbfJKaec0qPPev311/m43Xnnnfw4ZMgQzoPyq1/9CmeffXbMfahvK1euxBtvvIHRo0fz2BSrr/19/KkNffbevXu7bBM91nWFiHahX13mR2dMxLCUEdhSu44F/IHmb1DedgCTsmdhTOZkmAxSkkYQBGEgQbVqNTGtPdduVrQ6tbEgK8vatWvx4osvdtpGgj9anGuvu3vP7rBYLHyz1l8TFXTDX1JS0uf+9Ba/omDXXj9yLAomZhsxO78oofrfn0j/44v0v3+gayRdB+l6F37tZEuuv+sJOdrucbthtdn6P/O8ydin96R9SECHf4/way+hbaP+03en760Jefo/0Pb/+Z//6eR5pbFkyRI89NBDbFmfO3cuUlJSQttOOukkngRubW1FTk5Op32bm5vx1VdfsbCnY3733XfH7GtPCO9/T44VHZfhw4dz+2h2797d488V0S70OzazA3MKTsGojInYUPUZ6p3V+Kr63xzzPit/gbjMC4IgDCA0t/jq6mq+MdGg11piuVh89NFH7OZON1ux3pP2D4deU4b5cGtNb6Cbq/6uh0w3mserxvK2Gi/aA16kOQyYN9wOm8mQUP0/Fkj/44v0/+gwGo28mEwmXkIu12u3Qmls7nI/dqn2+aCYzXRh69c+GTLTYJw7pdfCndpr3yUaWk9o2zSX8sOHD+PJJ59EUVER5s2bx9vvuece3HbbbTE/w263c5uqqioeW8I/K3wcIgt+NJmZmRxbT2iPsfraE7T+03c+0nvQdvr+2qRENL05ziLa+xOfHxvq/4aPt7yBwvRhyHMUITepkEUqZVy3mfo2o5OoZNlzceZwzWV+LZrc9ewyPzxtNKbnzkeSpWOGTBAEQUhMKFs8WTzIaq6JdrJqUHIhShTUFZRsjqwlZIWIhpIUrVu3LmLdmjVrMHPmzNAN4GDC6VOwuUpNPjerwNIvgl0QBJ0yQH/eM2bMiHClJwv8ggUL8PDDD4cmT2hS9kgTs64Y4VOaFVtPIQP9jYj2/mTvIRxq2oJtzm+ASAMBk2HLxv9d9HZIrG6v2wynr41Ffa6jkJO6DTRoBmlUxgQMTR2BrbXrsadxOw4270Z5q+oyPzZrirjMC4IgJDB080Ti/PHHH2fLOcUXPvbYY5xIbvHixWyVqK+v5xuxcEsDifqlS5fGfM+LL76Ys8nTe9IjJTD629/+NmhLvm2s8HJt9myHEWOyZMwUhIEKW2/nTunWPZ6uqYrLBWPQ8qwH9/ieoLm9U5lPKgtKSUVvuukmDB06NNSGEsu9++67Mfc/99xzudoIjSPR4VOaWE9kz48jIaK9P8nJwEk75mKqdRzqjE2oUepRA1oa4FJccPnaIxKyvbPnd1hfqWZSJNKsGSzeNRF/0cTrYTGqcSC+gBfm4PNEhLwMZuefzFnmN1Z9jjpnFb6uWYN9zTswM28BCpI7frCCIAhCYkE12slyQq6NZAWZM2cOXnrpJbakHDp0CKeffjpbU8Iz+9KNW0ZGRsz3GzNmDJ5//nkW/1SznW7q6Hl0GbjBQG17ALsaVCv7/CEWGI/RDbUgCPqARbO5azHOlwCzCQZa+lu0H0OKi4v5ka7nlBTu0ksv5czxb7/9NruvEzfeeCOvi0VKMIadJoRjhU8RsVzjBwoi2vuTrHTkjj4FC4cVw9bcDqWqDkprO7uBtKEdjWhBYMN/YMjLhiE/CwVJQ1GSNhY1zgq0eVvQ7GnkZU9TKewmBy6bdHPorR/dsAzb6zaFudwXRgh8EsPHamasv13mzxi+BPuad+LrmrVodjfiX2X/i2FpozAj9wRxmRcEQUhAyNpDWYBpiYZu0Hbu3NlpPSUT6o6FCxfyMpih+4c15R5QXqrRmSYUJCfODbogCEJXUIz3o48+igsvvJCt52R5J7Kzs3npjjlz5mD16tXscaB5GlD41IgRI464byIjor2/IeGcmgxTfi4wplgV7VV1SK2qQ0pzMgJ1jQAtpXtwScaZMBZ/H4b8bLRbvKhpr0C1s4If3X5XhAindSTs93l3suCNtmL/v7O/CL3+465fo8FVqwp6EviOIn5Olnw9CHvqA00yDE0hl/kN2N24DWXNe0Iu8+OyporLvCAIgjDo2dPoR1VbABYTMLsgcb3tBEEY+Bw4cACffvppxLruMrRTPpQrrrgCq1atYtf3RYsW9ehzli5dyqFSlAGe9t+yZQteeeUV3H///aE2LS0tXGqOQrYGCiLajzGGlCRejKOGQWl3sYAPkAW+sZkXP2WH3LkPtrQUDM/PRnH+HBgKOsdjPLTgZRbuZJWvbi+PeDQbrRFi/N/l/+gk7AmryY7hqSPx2MLXQuvIem80mFjUW5XjG1NvNdkwK/8kjEwfh43Vn6O2vZIT1lGW+Zn5J6Ewedhx7Y8gCIIg6AWvX8H6CrW+8bQ8C5Ktgy8BnyAIiQPFokfHo1OOk+uuu67Lfa655hp88MEHLLijy7h1RXZ2Nov25cuXc86T3NxcLFu2jJ9r0DZKZvrxxx9joCCi/ThiSLLDMGIIjCOGQHG5oVTVQ6mug1LfBKW5Ff7mVuCbA6rQz8+GMT+brfYkyB3mJAxPG8XLkfjuqB/hUOs+VJPIZ+t9OVvePX6Kq3dGtP311sdCAt9itCLVkIEiZzEKUoZiaEoJzht9cWSJiWNgqc+05+D0Yedhf/M3HOfe4mnEJ2V/5eR1M/JORLKlcxZJrmFJx7DNCbS5oLQ7gYYmGMxdJ+4QhIEITQYGDlVCKauE4XAV8jwuwGWAMn86DCa5yReEROXrah/avQpSbQZMypHbNUEQ9MuRxHF4PpPoRKbvv/9+rz9v6tSpeOONN7rc/sgjj3Tbl676o2dkFIgTBrsNhuJCoLgQitsDpaZejYGva1Jd6lvbEdhTpgp9FvA5QHpKj0TzqcPO6bTO6/eg1lkJlz9StGc78tDibeJa6t6AB/WoRn19NbbVr8eQKNF+x2eXcsx9blJB0OWe4upV1/v8oCt+X1C8PqDNieK2DBT4T8B/Gjfhm9adOOg5hMPeTzBp3hJMyJsJk9EM718/hX/tFoBEekCJeB+SJ6YlHfV+/eu3qcdwWAGMQ/NhKMqDwSKnvDAw8P7lnwhs+wZKbWNoHV0dcuk3taccOFEtrUL4PviCJ7joWmLIy4qYEBQEQX80uwNcl52YV2iF2Si/VUEQhMGMKBgdYLBZYRhaAAwtYAEbEvC1japL/b7DCOw7rAr9vCwYCnJgyEiDoReDuMVkRWGKWj83nLvnrQxlpz/UcAAbd65DUp4Vzf462MMy3RMVbQfR6m1GVfuhTu9DAv+5RW+FXv9+wxOA04XcQAZyvanIcacgp90GU7uPBbflJxfw9+bPfvPv8K/bqh4LAJMpcZEF+Cq7FrX2Nmwt/jf2t+/BzLyTkOv3A63tHR9stQA0sZHsQICOI1ngg/i370Hg651A8L1hNMJQmAPj0AIYhuXDNHsyDLS/IOgQxeOFUl6DQFkFAmWVfE2w3nhx6HevNLWGBLshO4PPaV92BhoPHuIsrOGC3P/VDt4/AodNnRAckg/L0jOPuUeNIAg9Z12FF34FGJJqwvA08ZgRBEEY7Iho1xlkCSaLMIryoPj8UGobVAFf06C61B+sAA5WsNhkAZ+fA0N2OgzGoxvUqZwcWc9LbOMwoXA8HCYzQBMGYTfwjw1ZgZrDO1DtrkK1txq1/mBJO1MTCuv97DGgCfG/HX4LrYZIq77BCmTCgQmePNzafjYQbLsrqRKO5BbkGLNhS0oFkhzISrJjUfJslCU1YqvFiVZPEz499B6GjMvH9OnfQ0p6DrcLt5y3t7fDW1oaem06YTofI6Wsit2HSewrh6vhP1wNbDCqdTCD+Df8hydMjMMK1EmRbkptCMKxwl+6F4Etu1R394paIBAZ7qHU1nP1CcK8cBaUuZPVSahkNR+Fr70dFaUpyJgwIWI/8+nzEaioUa8ltNQ3AU43lP3lCLhVa56GZ+VrgNfHFS7os8gqzxb63CzxVBGE48DhFj8ONPlB83PziiwyiSYIgiDEX7QHAgE899xz+OMf/8iZ/iiN/7333othw2InIfvmm2+4ViuVijEajdz+zjvvRFFREQYaXH+xIAcoyIHiD0Cpa1Rj4CkWnqxwh6qAQ1Wq0KcbarqxzsmIqNlIwp8s22SxJxd0ejROHh26CfB9sRmBnfs5JtzQ2o6xza0weP8Jt18VC7aHbwqJ6+zt9chYV4Ux/CovuIRxnovbBpQAvmtdjOravaixtaLG0oIaYyO8Bh/qbU60DU9jK5/GCsvv0DKniZ9n2LLZ7V4rbUdZ5r9TcBq21W3AroZtOKxUodL1D0xImoEJpmnoTlqbxhbzwseBLPCNLWyxZAHvdMNg7jj9fZ9uUI8nQce9MFcV8ORaTwtNpAhCP8C/5eo61XpeVgnz4hNhSFW9WgL7D6vhHxqUxHJ4AXvi8PmY3pHfwVjc82ueafakiN+K6tHTwP1QC74G1wcCbN2HzweloobX+bWNBsA4dgSsV38v1D5QXq16/SR1nR1WEISe4w9QiTd1Im1CjhmZdrGyC4IgCDoQ7c8//zxef/11ThhQUFDAgpzS91P2QUpOEE5DQwN+/OMfY+bMmXj11Vfh8Xh4P2r/9ttvw2brEIIDDoOBE9TxDXZyEkDivbKW3WMDTheMFBdON9AmE/wHyqGQMHV5AE+kFY2wPXQjYFePFbWjuFj+CHKjD29I1manOyTajaOHg6f+ycJNlr2gW7ohyQHQ6zRVeBgNRnzv2z+P+EwSzU2eBs54bzIY2dVfi7XPsOdwPD3F2ze663ghgU5Q7fYFQ77FCelGpI/Hzf/6Pvfz00Pvs8CfkDUdYzIncVx9CjK7OXwGIDMNJlqmju203ThhJBSHPSToSUz5yyrVfbMzYLv7qghrqCEjVZ0kOUoPB2HgozS1ILD7oDphREKdPD3Cfpd07pkmqgkmTeNH0o+Freck0kHn2TGwsqkePbkALREbDLAu+zGU6mCIDlW74InCOvVaEBZOQr9pz7O/B8hSn5oMI3v+BK3yZKEvzIEh7chZYAVB6KC0zodGVwB2swEz8iV8SxAEQdCBaCfR/fLLL+O2227DqaeeyuueeuopnHzyyfjwww9xzjmRCdU++ugjdoF+9NFHQ3X/SOTTvps2bcIJJ5yARCJAli4q+cYW8I4s6GwVb3fB8pPzQzfs3t/9md1mu8K4cDaUhiYodGPd1AI0t3WOXyXRTwKbBH5QNBtnTmRrMglvt8mAfZUVGDFpAhzZmXyDHi4Y2Fo3e1Kfviu9T4Yti5foWPtnTvsjCwBKiFfTXq5mveeSdhWcwT68Hn2ju5afN7hrOUM+WeA1pmTNxXmOK/k5vd89X1zB+zgsKUgyJ8NhTg49Dkktwez8k0P7VpxUBPspo2A3JcHe5IXpcK0qsMiTITsj1E4JKPC++i5nrufjMyQvJLD4OOZmipAfpNA5pzQ0q1nch+bDGDxv/Dv3w7c6KjOqzdJhPc9MC62myhK0xAv6nRpyMgFaghMJIU+VljY1aaQGXafoOkKivaUNgZY2YE9ZaLNx4ihYr1ga2t//r/X83ux2n50pme0FIQqnT8HmKvU3NqvAAptJ3OIFQRAEHYj2HTt2oK2tLUJsp6WlYeLEiVi/fn0n0U7tyDKvCXaCXOSJ5uZm6IGU8jqgbjO8Xr8qxp1Bt3QqTeb2wHr3VR2u6f/7CQJbuxbi1F4T1wZH8DuTpYut2/aghVt9NI4pBuxWgErHZaZDqayB4vfDYLGo7t6UhC0rHYaC7AhrmYn2o4Vob4fL06pa94LW9eMFHZM0awYvozImxmxjNVrx5Cmr2Vpf2VaGHfVfs3Cn5HjtvjaYjWb4FfWGxxNwY3v95i4/b27BqRGi/dZPf8jJ+Do+ywaHNRlJ45IxJWcOfoqz1A1OF34/8T8wtjjhcBth91jg2GVBUqkFDp8ZmcPHYtRl/x16H39NPYwkUCTz74BDoXAL8lShyZ2DwbAL+p3ThXXJ6TAunBVyYzeUFKmTO8MLg5M7WQl1TvA1Ky2FvVxC65IdsP/8GjXXRtAyHyDrfNAyTyEmIVrb4Xv3Xx2vTcaggA9a5ccMV69FgjCI2VjphcevINthxNgsyasiCIIg6ES0V1aq7seFhZGlwvLy8kLbwhk6dCgv4bz44oss4im2va+QFYgs+EeL0+lE5u7DMJbVdMSBRrdpaFLFNd30picDuZnsZs4LCfMkO5Tgc6fLBQSC77R4PvDtk1SX9Rh4FT91gEzXwJRRwOSRqoCoaQCq6zleHZU1vCh0A56eAuRlqZ8fnBig/oc/6pF8y1Dkpw/FlPS5OLNoKdd0/6r231yL3uP1YH3zx6gvO4xUexouHHU1FCicN8EPHzx+N9wBJ5y+doxIHRf6n5NYTzKnwOlrYzd9TfR7PG40eepR6CjuOD8MwN/Sv4YvrXPYATFBOYh72i9RX7Q5cc0n58Jj9MMBGxxkxbemwGFPh8OehmEpI7F01OWhff918K+oaa9B0+FKpCdlcnvyCnCY1UeL8fhOpPSWRDh/+vwd6LdElQs0d++DFTC++Gan/RWyHudnw2MEPNo5k+oArrgg8prgcg6s/0FOurpMGhlaRd/Xqx2DllYYKCyltoGvSQaKqQ+632sJ9JQhudxvo9uLwMtvw0m5POj6lBu8TgWT7emZ/jz+ksV/cFHbHsCuenXSef4QC4zyvxcEQRD0Itq1G5vo2HWKTW9qUhOTdQfFtb/22mu45557kJUV6XbdG7xeL0rDso4fDVl5mQiYjPDbLPBbLfzoo+fB164933DpMaY4S126Ys/ufukT0sww2RywNbXB1twGc7sbqKkBdu/jzT6HDe70ZF7IbXf//v1IJLKVYig+K/a4tsGtuLC9/OuY7Ywwwma0I8uQAZfHh/fq34LN6IDd6MBPsu7hRyiAFx4W9/Re9Gg12ELnB91In5ByFjy83Q2P4oQ74IJbccITcMFuLgi1ddQ0od3sgdcYgBMk8lsBbzV9ANAC1FXsw0TPiWrnFAWvVz6HtkAL0NC57/mWYbgy797Q6z/UPQdnoB02gx1Wox02g4O/Gz2mmTIxLbmjXn2V9xAMMHBb+r5Wg53zDhwrEu38icbo8aJmzSY46pphr2uGo74F1jYX6sYNReXscdzG4PNjvNEAT1oynFmpcGan8eLOSFGFO9FP15QB8z+YQslFh/G5bmlzwdbcztcka3MbWi0KWrTfDV2j9h4G9h6OsOzTddSdloT6sUPRXFKgrtRKPOpM4PTX8Y8eG4WBCY0ra8o9fDqPyjShIFms7IIgCIKORLvm5k6x7eEu7263Gw6Ho9sBbuXKlVi1ahV++tOf4uKLLz6qflgsFowePRr9MQlBt2olJScjrZv+xx2Kxw5a4NHUqtY29wHeqhbUutqROW4UbFQ3nixbOrsZ7pqJmNE2B1/t2YCsggz4TT44fa1sVW+nR397xw0+5ROAC05eIhWy2WhlyzZZ3tPYyp0DhzkYE29SY+InGu/oWZcmAE+3vwlXTQWclYfhrK2Es74KruZ6OA1upM6YhQlaaa6ySkzZmo1GexrcDgNcFh+cRg9cAScn6MtMzu5oS0L80zL2AojF8JRR+P6EK0KvX/ryAVS0d8QaEyTwObY/uQT/M2tlaP2be17i3AKahZ9i/Pm5KRmp1jSMy5gWakteCWZDR94DPv/370dJSUm3v19dEVDU5IpaOMr/XQ1jfexQmyyrA5nhpdTGj4fVYgbJqnTog4T8H1DViLD+H3LuhPvsk2BtbFWvU2SZb2yB2e2FuaYJjnnTMET7P1DOiZfeVi3xuZlQKBY/L2idz0rv0jMpEY7/7t39NGkr6J69jX5UtQVgNgJzCiT5nCAIgqAz0a65xVdXV2P48OGh9fR63DjVohXLKn7XXXfhf//3f/nxsssuO+p+kOhISkpCf0E3a/35fv0O9S0rExg3kmurh8rIVdbA3OiB/XANzNWNHCtPMfBGqgudnpIQrpo5lkJMyJvQ6fj7FT9cJOC9rSzi27wk6Nv4dRuJem8r3H4XTQnBpbTB5W1DfWwPeNjMDiSbU4IJ7lKQbElhYZscfG03J4Us2UlJxUBOMQt4Dco1QJn/qXyXIdhPX3Ujbtw6v/OH0cTJ0Dwok2bDEfadbpm1HK3eFvU7+Nrg9NKjOkmRacuO+P6ptnS0+Vr4u/qCMf/sHeBxIcOeFdF2bc0/cbg1tpUw11GIF8/8a+j1sk//G3uaSoOTHMlsxVc8BmQ4M5GTlI+bZv4i1PbDA2+hwVULu8nByQGtJjvsZvU57T8xe2aobZu3BUaDCVaTDSZD/4kuLnN2uDpU9o8TxmWlh5Kl0e/CSSUSqS1VGSguVGugU8k/egwrU6h3dH8N6gby/LHMnBBxvvN1qkaNmzcML4IxuM3f3A4vV86o4SXiCmU0wPx/vgXz/Knqe1BukbpGGCjLfTAkSM/HPxGut8LR4/UrWF+hDjbT8ixItkqCRkEQEo9Fixbh/PPPx/XXX99p21tvvcWaLRzKSZaSkoLJkyfj9ttv53xmvaG0tBTLly/Htm3b2Nua9OAllwTDU7vg/fffx7PPPotDhw5h5MiRuOOOO2ImMaew2quuugrTpk2L+X0GpWgfP348/8PWrl0bEu2UUG779u246KKLYu6zbNky/P3vf8cTTzyB73znO8e5xwMPSjhnGFYI0NLUjJZ1m5CTksEx8JzJfu8hBPYeYsHCCaPyswGqy5xASbQIEn/JllReuoJi21VRrwrg0HNvS0jo+wM+uH1OXuBS61hHYzAYVSEbFPG8BDPY0yMJfmtRXmRm/hOmwlOQhcqNW1AYMMJYUQulolaNpd55ALYzg270JFS27ML4tWXBGvIlMA7Nj6jfHc2Kk38Xek4l9kJC3xdVYQDAOSN/iHpXdXBCQ22jtc+05US0pWMSUPwssmnROFwP5DiD7stBPjrwDr5pVMv4RZNiScOr3+5IUvbo+tuxpXZdKCEgCXxbUOTT5MhjC18NtX13z+9xsGUv7Ga1jS04KaA9Xzj02/D/+Z8I7ClDdf1+eAxe2PxmWANm2PwmWFtaI2KHlYvOwc7qCoydPhXWBBW9A/Y6Rd4/tIRhnDEB1uGFoeR3nAiPk+HVs+eEgXJ3BAns2q9WfiAyUtUSdXlaibqshJuYEQYGW2p8aPMqSLUaMDk37lV4BUEQjhmff/45P/r9fs4VVV5ejhUrVuDyyy/nCmHJyWrp6CPRECwBThMF999/P7766it+pP2XLg0aYqJYs2YNTw6QjjzppJPwpz/9iYX5O++8g1GjOqrlkPf3vffei88++4xFu56I6whB8Xokzh9//HGeJRkyZAiXcKN67YsXL+Z/an19PVJTU9l9nmZq3nvvPT7gc+fORQ3FZQfR2ghHgcUMV1YqMGEsTFYrFCpJRzfAtQ1cSk45UI7AgXL1BlqryUwZ6QdIiTOz0YI0WyYvseC61AF3yFpPorZD3HeIfEUJqM+9rV1+lsloDhPz9JgMY6oZ5SMsSBo3FdlpeTD7DVAqatgybBiSH9qXBGigdC9QurcjuVlaMpcPI+FhOnE6DKmxL3xUYo+Wrr7jWSX/p8fH6/GFvw9a91WB39BWh937dyG3MAcOe6Rr8AlFp2NE+ji4/U72aOCJD3r0Ux6ASHGsejygIyFgwI1Wr5rjgo5VOJuqv8BXNWti9o/i+E8ZejYCh6rYwv7apE1Yl3uoUzvbe6tZ5L94xl+5brm/qRZ/2f8qdjVvVScLTI6IiQN6PGfED9jjgtjftAuN7jp1wsAcOXFA+9J5JVbTYwOVjaNrESfVnDwmskRdU6ua4FNbRxZ5+l1QaTrK/N/YAuw6ENpOJTZNwfdgb4zdBzvqzmemDZjrnKAfmt0BbK1RrexziywwJ9hkuCAIQm/IzVWrypC+c7lcKC4uZoFMWpBE9emnn96j9/nDH/7Aoc0PPPAAzGYzi+4DBw5wcvKuRPuvfvUrnHHGGSFrPFnZN2/ejN/+9rf8PgSVD6f+UN+ompneiPu07g033ACfz8fJ5OggURb4l156if8Z5L5A/8CHH34YF1xwAbvEE1SnnZZwtDZC/2Awm9WSTYW5qjt3baMq4MlFlVxVyyo5DptKyqkCfuDXXibhpYmxTERanTUCSoCFKVnlQ2JeE/RBUU9u+mSxp8z3tISHftS016KybDef/yQU2TpfnIKkxlb1Obnfz8iHI+tE2MsbgbJqNQN3cxsC/9nDiynoDkz4N5fypEuoJnhK/1mPScDSAqgX4XZbO0xVyZhQ2Dk84fzRl/b4fR9a8DK8fjdcLOo7xD099werKfhL9yKwcx9OqcvBGOc0eBQP3CY/3EYfPCY/vJOLETCqFnTzonnAwtlwtNchpaGF30erEkBo728x2eCHOmGwv+UbbK7+sss+frvkv0LP/7pvNT46+E6XbX995t+Q7cjj53/c9Wt8dviDkKDXQgW0CYELx12NDJuanHJn/RaUte4NTQLYQ23V17lJhbAYJf41FjxJkhHpfWKeO4UXpd3FlvkOq7waHkTiXCOwYx98738WtrMZhly1RB15G5nmTYUh6v0FobeQW7w/ABSlmlCcJsnnBEHomHjWwhljQfdC5B3qDZgQMAT69bPNBvNxNTRQ8nH+XLMqSe+88068/fbbMduef/75eOSRR7BhwwY23mr7EPPnz8cvf/lL1NbWIicnp5O7Owlyeu9w5s2bhw8//DD0+pNPPsHJJ5+Ma6+9Ft/97nehN+Iu2k0mE7sr0BINlXfbuXNn6PXLL798nHsnEAaTSb2hzc+GEghAqWsKuaMqHi+Uw1XA4SoYqB481Z8myxTVYD7OSaD0AMWyq0nckgFHh3U8HBLsmns6i3uON29DY1s92o1utoRTbL3H7+KFrLidyAcMBQbY5yTBYSiBo9kPR70bjiYv0ow1SHI62Ypv3PgfKNv3duyXmabWCycBT5b50cN1N9FCx5Cs2CRQlQYjlLIWBMpqYP72Aj4XicDXO+FftxXzQZb3CVz1gLwRjEMLVY+DiaPYI4QwTVTdnm7CiogcB3Rs3T5tQsAVkVH/W8OWYm7hKdyGEgFqkwZaWxLNGln2XJSkjQmbXFA9CbQBV53YUKlxVqCsZU+X3/2C0R05Or4s/wh/2ftal22fOe1PGJY6MjQZ8M7u33E4QcCvwF5v5/OIcgPQAHzzrOWhtjRp8M+ydzlkxGQww2w086Mp+EgTLEUparjSjvqvsbHq8442tI9R3cdoMGN2/gLkOFSX9aq2w9jXvDPsPdW26n5mfk8tPMXlc7L3RMR7Gsx8E8JW8mOIIckOQ8kQGEuGdN2GxPn08aGJSvh87PXCni90jk4dGxLtvrVbENj6jXqNLIo9mScI0Rxu8WN/k5/zYM4vEm8cQRBUaAz8x8E/o9bZufS1RoBEvc/HorW/y0PmJBXg9GHnHZdrEhlnycO6qKgoVLr77rvvxq233hqzvT3oUU1lwceOHdupXDhRUVHRSbRT6DW545Mnd3clxm+++WbombiLdiGxIBdRg5apecIoKI3NoXrLisvNN7WoqFHdVkm4U8woWaisYhHUIIGSak3nJRy6oGQ1DsOEkgmw2MyhBHlaPH24Sz4JfhL/HHOONoB04ZDgcrhj1hAjamBPc8JR54GjwY0knwWO/fuRtNsCh9GBzHtv5pJxdHH2/2c3lVKAcVg+DI7jH2qitLRx+AW5JpMnBz1yTH8Q0/TxMAxVJ0KMk0YDVuprAQzDC9VzrBfuyyQUQ5MrMaAs+T1NJPaD8T/lJRoSoB6/O+Izloy6FAuKvtVpEkAT+ilh58SQ1BLMyl/A23jyIDjB4IkxcRDy6qCygjRARZUJ9wU6ZuwrWg9260Vw+vDvogiqaN/ZsBV/+ualLtsWzH8+JNq/qvk3XtjyUJdt75zzBOYVnsbP11b+E09vuqfLttdk3YszRy7h5zRp8Mzmn3dMBIRNMNC6/xp7Zeh99zSW4vUdz0dMBPDEBbU3mrGgaDGm5s7jttXt5fjo4J+5badJiTQzxpw3mUM6aKKytfowth38DMYmJ0wNbbAadsNcV8b7KPvXIn13OTK3O2CYNAqYXtLl9xIE7YZ7bbnqFj8+24xMu74mTgVBiDMDdA5vxowZHZ4EPh97lS5YsIC9pbV7Lgp3pqU7XC5XzHLhWgWyWO2JWPvEaq9XRLQLfYaS0VFMO5VWUsaP4BhS1eW0VnVBJbdtyvZsMMCQnRFK+KRZQIWuIStphikr5CodDV3wSLipgr4lKhN+Gz+6KL5+SC5cQ8BO3/U+P5TmVqC5VX00tMG057f8WSQsrZ9ugKPeA4fPguTULCTnDUFy0TAkDxsBy7Cifs24rbS2sygPd9n3r90K33ufRjakyZ/CXG5HORdCq6eM4UXPUCw7LeGQtVmzYh+JxcUX8NITlo75Cc4svgBNbQ3YvfcbDC8eDrPNxBM7ZPEvSO6wKs8tOIWFNiURpG3Uxh98pNdUJUBjRNpYfGfE91n0cxvFH2pHj5n2DpfydFsWxmdO42383mHvS4+UnDH8/KVjQ9sUdLash1cNIE+HZk9kacZwWr0dJfrIK4XyHHRFceqYMNFegT/u+lWXbS+acD2LdpoMqrK34NHKx9UNNFey7pWOhg5g6enn4MKWmfDm0+/12HoKCIlPaZ0PDa4A7GYDZubLhLYgCB3QPTNZurt1j/f74Xa5YLPb2WM5UdzjKekbQTnJnnrqKU4od9NNN7FntQbFlL/7bjBpbBTnnnsux5+TxZ0SxoWjie9YBhdN0MfaJ5HK44poF/o1htSUkQplbDEne2IBX13PFlSKqwbFVm83qC7aWoKnY1x6aSAfby2mnNyzYxGzzF1u5zJ3lFHe4/MgkO2DYm4HnCTxq4D6UoBKwW8D7EkZSD3jFCRZUjmu3tHoQVJ2AVKSM0Nl7rpCcboQKKsKWs8rVAt6gyq0LJd8ly3o/J2KC0MCXc2MXwBDUS7nVxC6J8WaxkuGMQftVh/GZHTOK6BRkj6Wl54wNXcuLz1hfuEiXnrCqcO+w4uWB0KbCGhta0HpzlJMzenI2Do9dz6ePvUNPp95IoAnAfw8EUCvi9M6sr4Wp43B9dPvi5xcCD6n9mMzp4TaZtpzcPaIC8MmFzrekyYdhqQUh9pS2AHtG5rgiJiU8CN15FhYRp0Bb3s71aHp0TEQBidOn4JNlerN+KwCC2zmAWpSEwThqO7xLIauJ/SMihF+o5/z2piMiROKSonnCBLpK1euxKWXXsqZ4ymGPTNTTZB844038rpYpKSoyYjJzZ3Kg4ejvc7P7xyampGRwfdEsfaJ1V6vyN2wcGwEfFoKTGkpwJhitqqGEj9RRuf6Jvjrmzj7OcWFqgI+h2NNhTiWuSs6VRX0rfVoqy5HW10l2ppq4GtugjvDCp+rlmutk5XU/481lNkDSE7islrGtFRYUzLR5PShoWw/UtOyuM66+WAtDO9+AWvApC7+4KPRBEtOrvoeWn/HFMN0+4+P09ER9ALlEjBSVQNYoViAZFMqnzsaRzqHw8lx5GPR8J4ljyFRfuWUO3rUdnjaKKw4+bc9aisI3bGpksJmFGQ7jBiblTg324IgCP0JWbgpqfiFF17I1nOyvBPZ2dm8dMecOXOwevVq9jjQPA0o+/yIESNi7ku6ZObMmVi3bh2+973vhdZTyfHZs2cjURDRLhxzyP2ZFuPIYWx11eopU9klpbEFfiq9tHM/DFS2jGLgC3KAZIck5olXmTvK31ESWeauzdUEp+LkmPq2hio0+ffB6W5Gu88LZ2sN/OXVoDBqCnyocNahdrTqAq6YXPBnlwMOO4t7Q2oKkO6AIS0FBrMfFtNaWPd+BRvXY7dxBneyatrokbOlq68jHk02jiWW80MQhESizhnAznrVyk7J5/o7gZQgCEI8obJrn34aGebYXTnu8ePH44orrsCqVavY9Z3qrveEpUuX4te//jUnraP9t2zZgldeeYVrtWu0tLRwVSYqKU5QXXeqyz5x4kQsXLgQb775JkpLS7F8+XIkCiLaheMKJTjTMjdz4jpynycLfH0TlOY2+JvbAKqPTBZcyuBckM21lUWgxbnMXXLYRTdzEnDjIjVxXFkl/AfL4Sw/hJbyMrhcTXDnFsOQO4eTsPFyzmh4zKr4pyRqVG6NXPIJKu1GS1sv+0XJwkjEUzw+iXibMSjwg4tFE/4s9Du2WYyUUV2SPgmCcHyhCdA15R5QcYSRGSYUpIiVXRCEgQXFokfHow8ZMgTXXXddl/tcc801+OCDD1hwUxk3zQW+O7Kzs1m0k+CmMnBU/33ZsmX8XIO2kWX9448/5teU8O6hhx7C888/z1b90aNH44UXXuAa74mCiHYhblA8O2X+xvBCtXQcC/hataRcWzuUve0I7C1ThX6wPjLFzYuA1weG1GQup0YLWdgt7e3YsXUbxk+ZfMTM6xQTzLH0lA094IY7KN5VYa++1rZxuwBlTFe3KcEYaGcwe35vYWs+C31N5NtZzJPID3iBSk850tuSkIb0COt+dFI5QRCEnrKvyY/K1gDMRmBOoVxLBEEYWGjiuCsuuCB2Yl3K6P7+++/3+vOmTp2KN954o8vtVM89miVLlvDSH98nHohoF3QBlYTjcl5D86F4fVBqGlQBX9uoutTvP4zA/sMw2K1qGTmKg89M5wz2gn5QzD2zHnFprWAivV69P5UJoVJqQXHPS9CCr4l6b7jwD26j17Tfkaz75EpV46pFfeUhLkUS0Wex7guC0Ae8fgXrK9Trz9Q8C1Kscj0QBEEQeoeIdkF3GCxmzhqOolwofr8q3CtrVSHv8kA5WAEcrFCFPpWQIwGflRHvbgvHK6MqJS0zWXucnKw76360yG91NsPfaEQ2ZeQ3B/rFuk99NhutXVr3u4vdF+u+ICQ+W2t8aPUoSLUaMCVXbrsEQRCE3iOjh6BrDCYTi3LkZ0PxB6DUN6ox8ORKTy71h6qAQ1VqWbD0JNio/jiVmDOZAYtFLPFCr6z77e3tSKnLw4QhHSXTjta6T/sfbey+mqTP2sm6b+XX1pB13+8NcCiB9rkSSiIcLwKBAJ577jn88Y9/5ARAlN2X6u0OGzYsZnvyannmmWe4bi+1nzx5MicVmjBhQqgNJQ768ssvI/ajmMdXX30ViUKLJ4AtNaqVndzizTImCYIgCH1ARLuQMBhMRhhys4DcLCgBBUpDU1DA17EF3lBZh7TaWhjaA/CRYCfBYrMCNgsM/GhVH+1WCqJhV3veThZ7ETdCnKz7/Rm7z+79rbXYvW8Tu/eTpT60GMzB5+ao9ZbI9aF2HYsluJ4mESRzvxALSu7z+uuvcxwh1dB97LHHOKsvJSWimMVo7rvvPvzrX//i9kVFRVyz98orr+TYxtRU9Xe2c+dObnfGGWeE9osOW9E76yq88AeAohQjStIl+ZwgCILQN0S0CwkJWdAN2RlAdgaUCSO5fJz34GH42pqhkEhXDGxphMvNi9Lde3Un7rXnIu6FPnC8Y/fb/G0IP0PpPbRY/v5CdfePIfZjCn5zWLtYbTqe07ESEhOPx4OXX34Zt912G0499VReR9l5Tz75ZHz44Yc455xzItqXlZVxuR3K3EttiF/84hecIGjbtm044YQTUFdXx8u0adM4M3AiUt7qx/5GP2jYmFdklfFDEARB6DMi2oWEh2+EMtMAmxkNvnYUTJgAk91Bd5KA2wPFHXx0qY9we0PrQC72vRb3JOQtIu4F3Vn3yb1/u3M7xo4YC6vdEhLtPsULb/A5We99iq9jW6Bjm7ae29B6paMNrSNUd38PvFDL9vUXRoMJil9BbUsdysq2I8mW1Mnir04CHMFTIGpiQJIAHnt27NiBtrY2FtsaaWlpXA93/fr1nUT7F198wdZ0qpUb3j48Wy9Z2el3MGLECCQiASrxdlidMJuQbUaWQ85DQRAEoe+IaBcGJBzLbrfx0p18Jjf7Yyru2RU/aMEXcS8cB1RLuDlo3e+dhb87AkF3fZoA8AVFfcekQFDkawI/YlIgbFvUJADtp00GBDiUwAu34kKLpxEupffl/GJhiiH0ycWfXf47if0jTBCETQrIb7eDyspKfiwsLIxYn5eXF9oWzr59+zjWnazwL774Iqqqqljg33nnnaGaubt27WJh/8ADD7DIpxwTZ511Ftf0jeVu3xPoGk4TW/2B0+mMeIxmR30A1S1+2EzA+DT6XPU81wtH6r/ekf7HF+l//+B2uzkfiN/v56Wn8P1o8LE3++mFwdR/v9/P/2M61+gx1nv19H5CRLswqOm1uKfs9Z5ocU+C3xtb3Df1QtxDQVJVA5BejUB6moh7QVeQxdpI1n/0TTB1F/evWfZb2ppR6izFiKISWGxBT4Ewoa+K/6A3QJS3gOpN0LGOcgLw+wd88MMHt9/Vr/3myQAt5j8o9hUfYPYnY7Ch3fhGi2mbzYamps4XwdbWVhw4cIDj4JctW8ZW9lWrVuGHP/wh3nvvPWRnZ7NopxtaqsVLCelKS0vx6KOPory8nB/7AuV8oPfpT/bv399pnSdgwKf1qfAqRkxMacfeXf3rlXKs+59ISP/ji/T/6DGbzXyt6wt93U8vDIb+u91u+Hw+7N27t8s2PZ2IFtEuCDoR9wavF8m1DTD498Eflmypk7gPWevDXPRF3AuJHPdvMnE2fFiNSDVlINdRGMre3xfot0WW+44wgDCBHzEJENtzQPMKUCcTfBH7aTPsPBkQ8MENZ4QotHnTMNiw2+2h2HbtuXaz4nA4Yt6kknCnuHfNsk7PTznlFLz99tucwI4s7HfccQfS09N5+9ixYzkJ3c0338xCPycnp9f9pP1Hjx6N/pqooBv+kpKSTt9xbYUf6YYAMu0GLB5hglGH1+Xu+p8ISP/ji/S/f6BrJE1E0gRn+LXzSNA4RPvSfol43zfY+m82mzF8+HBuH83u3bt7/Lki2gUhLuI+wMKdxT2LeA+8TS1wBdxQsjPUfUngH43lPlzQhyXZE3EvDHTo/CYXeBPMsJl6fiN0JNgVjicCwicBOp63O9vR4G7BYENzi6+uruYbEw16PW7cuE7tKbs83cRogp2gG1ZymT906BC/pu2aYNcYM2YMP5LLfV9EO50XRzMZFAu64Q9/zzpnAPvaXLBYTFhYYkNKsr4TLEb3P9GQ/scX6f/RYTQaeaGJa1p6iuaSzWNdL/Y7lixatAjnn38+rr/++k7b3nrrLdx1110R6+h7p6SkcLnP22+/nUOkekNpaSmWL1/OyUuzsrJw2WWX4ZJLLul2H6pO8uyzz/I4M3LkSJ4YDs/F0tDQwElRP/30Uz623/nOd3iSOHpih47/V199xRPMR/Leov8PfVd6j1gTM725HxfRLghxwGA0dhb32elooRv+CeNg1mqExxD3kZZ7T9/EfVTZOxH3gtDDfAFBV/hY+QLaTe1oMfSv+3UiMH78eL75Wrt2bUi0Nzc3Y/v27bjooos6taca7uQuuHXrVkyZMoXXuVwuzipPN0nExRdfjKFDh+Lhhx8O7UftyVpO1jE9QtfgteUe0KV4RIYJhSn6uJkWBEHQA59//nlI9FJ+EfIyWLFiBS6//HJ89NFHSE7uWXhZQ0MDh03RRMH999/PApoeaf+lS5fG3GfNmjU8OUAi/KSTTsKf/vQnXHXVVXjnnXdCE8g33HADe2G88sorPIbdfffd3E/qYzibNm1ir69YMerHEhHtgpBo4j4GncR9WGK90HMS+16fKu6dbl56JO7DRH2HuO/IoC/iXhAGNxSPR+L88ccfZ4vHkCFDuE47WdQXL17MN2j19fWcWI4sDbNnz8aJJ57IVg5yg8/IyMAzzzzDFonzzjuP3/Nb3/oWHnroIY5pX7BgAQt2imWnmzuaINAj+5r8qGgNwGQE5hQmVj15QRCEY41WvpPGBJqoLS4uxr333svjB4nq008/vUfv84c//IEncGn80Ly2KE8KJTbtSrT/6le/whlnnBGyxtP4s3nzZvz2t7/l96Hn69at47wqmoin9WRNv+WWW5Cfn8+TzTS2vfbaaxxqFStny7FERLsgDACOubg/0meTgDcAaTXVlH4K/uRkGMwm8nEFLNqjWV1nMauvzSYR+4IwQCALBd3Q3HPPPXwzRtb0l156iW+syBWRbsbIan7BBRdwe3JRJJF/3XXXcfuZM2fid7/7HYt+gm7i6Prw6quvsninmz1yfyTLiB7xBRSsr1BLvE3NtSDVKiXeBEHoG3T/5evGiOv3K/AGFJj8CgLd3qH1HrOxdy7bR4sW503im6AqIpTbJBbnn38+HnnkEWzYsAFz584N7UPMnz8fv/zlL1FbW9spfIos4mQdp/cOZ968eVzFhKD3pHEmPGyLPoOOxcaNG3H22Wez1Z3KmNIEAE0S3HfffTieiGgXhEFEf4t7hdzyqa3TzYn0bM3tMJTXIGBpPHJfaFBgYR8l6oPPWdSHCfyY2+n7CIIQd8hKTq6HtERDbu5Udz0cspbTDU93Nz0/+tGPeEkEtlT70OpRkGI1YGqe3FoJgtB3wf7XPW5UtXWt2qk6Ck2Sms0uGAz9ex+Un2zEd0YdnwRxNKFLluuioiKe6CXIJf3WW2+N2d4ejAmnvCaUnDS6xChRUVHRSbSTqzsJbvL+6qosKZUejS5bSl5k5AlG70lQpROKzydPARLtxxsZWQRB6Bdx721qRstOIGfoMBhJWHt9gM+vWu19PsDrB/zqo+L3q5Z8akML1LIZvZ0vjhDxJhL54aLeHPXaBEPYBABvJz9WQRCEo6DFE8CWGtXKTm7xZkpIKgiCIEQwY8aMDk8Cn489sSj8ibywtISAFEZFS3e4XK6YJUa7KsNG7YlY+2jtKZY9Vum18DbxRkS7IAj9Iu5hNcFVmwaUFMF0hGysij8A+KJEffA5Paoiv6vt9FrNnMqPtLj6KPpJtLOQD7rx+/1Iq6oCDHbVxV8T/cHt0aKfglfFxV8QBjfkFk+XtMIUI0akS/I5QRD6DmctH2U7gnu8Hy63C3abvd+zxx9L93hK+kbU1NRwmU9KKHfTTTexN5YGxbi/++67Mfc/99xzOc6cLO5UYjQcTVjHqgagCfpY+2iZ4WO9p9ZGLxUSRLQLgnDcYbFsooR2wde93F8JKB2in0R8mMCPeB2xPWjtD+5HM708eeAPuv1TP8jFv6kNhsPVCFiOnEiKBzZLlKgPWvXZkh8u8CO2a20krl8QEpnKtgD2NdK1AJhfZJXfsyAIRw1dR8hm0BVGGOA3Uhsq+ZY41xxKPEeQSF+5ciUuvfRSTi5KMeyZmZm87cYbb+R1sUgJJiElN3cqKRqO9poSxkVDLu4kvGPto7Wn96QM9uGQiG9sbAy53scbEe2CICQcBnI/tVrUpS+in1zzg4I+3JrvbWlD624FOUOHwmgyB4V+uPU/uE8wUR+/D4UH0NIXS38orr8jYV9EHH94XH+sOH9qL664ghAXaO5wfRWZw4wYn2VGlkPCbQRBEHoCWbipIsiFF17I1nOyvBPZ2dm8dMecOXOwevVq9jjQPA0o+/yIESNi7kv3WpTslLLDf+973wutpzKlVM1Ee09Kjkqx6trkArUnZs2aBT0gol0QhEFHyEJOi7aO/qQ44GysAUYM6dbFn8W65uKvifqQdV+z9vtjbA+bJAgEIuP6ncH3Ppq4/oAf6ZRUxWOEn1y+KHyBRD09kneD0aiGNGgLzdBHvNa2R62n18H9yaQo1kRBAMpcVjRAQYrDgJkFUuJNEITBDQneTz/9NGbyuFiMHz+eS6qtWrWKXd+p7npPWLp0KX79619z0jraf8uWLVxbnWq1a7S0tMDr9YYqklBdd6o+MnHiRCxcuBBvvvkmSktLsXz5ct4+bdo0FvZUf50SpFLiOnLVX7JkSUzrfTwQ0S4IgtBLIjLfUzx/X6z9MUV/h7CPFP1hkwC+jmR+0XH95N5vbXXCUNuIgKXt2H33rkQ/TQqwuA9vowr9mBMH0ft73LC0OoGmVigU0Be2T/gEhEwaCPHG7VfwTZsd6XZgZr4ZdrOck4IgDG4oFj06Hn3IkCFc2rMrrrnmGnzwwQcsuKnEmuYC3x3Z2dks2klwUxk4KtW2bNkyfq5B28hS/vHHH/NrSnhH5UOff/55tupTnfUXXnghVOKN7iuee+457ge57VMc/FlnnYW77roLekFEuyAIQlzj+q19jOsPdErO521pRfNuA3JKSmCy2Kg4KS/clhaaKODnSmgbPVcitoW3Vdvx9ggvA6oEQJ8do19Hc0y8XmTU1sLQ7IWvm5wChlgeAN15C0QJfz72hl54G0R9hoQkCF/XBOBVjMi0GzA+W26lBEEY3GjiuCsuuOCCmOspY/v777/f68+bOnUq3njjjS63Uz33aMhqTkt3kwHPPPNMjz7/u9/9Lv7rv/4LxxMZaQRBEBIQFpZWY2Rcv8MKd10qUJQHYz9mO2Wh3pXo9wfd/KNFP28LE/3d7a9NLrjc8Lc0QXHYVbf/4P68jT5D64+2b1f9xbGFLf0hIR8m7gN+WAL6KA0jHDsaXAHsbFDPv9n5RhjF80MQBEE4xohoFwRBEHogUk3qEmt7P32Op70d9aUm5E+YAHPYpAML9oiJg0jRHzExEIieQDjCxMER9w+bmAjvD5cd9EceBwpPMMRwPxAGFK0eSkIJFNo8KEyW5HOCIAjCsUdEuyAIgqD/SQMtLr6LUetY2zq5zGCEJ0FnbwGv04W2irJj3BMh3gxNNeI7I8yo3Nce764IgiAIgwQR7YIgCIJwBDiO3UieBt14G7S3A1VieR0Mk0jZDgOqxSteEARBOE7E/e4iEAhw0P/JJ5+M6dOn48orr0RZWdeWioaGBtx6661cT4+yDFKWP6czWCtJEARBEARBEARBEAYQcRftlHr/9ddfx4MPPojVq1eziKeaex6PJ2b7G264gesAUj2+lStX4pNPPuF6eoIgCIIgCIIgCIlEeM4UYWCh9OP/Nq6inYT5yy+/zEL81FNPxfjx47l2XmVlJT788MNO7Tdv3sw191asWIFJkybhhBNOwAMPPIA///nPqKqqist3EARBEARBEARB6A2WYGnTdgqtEgYk7cH/rfa/TtiY9h07dqCtrY3Ft0ZaWhomTpyI9evX45xzzolov2HDBuTm5mLUqFGhdeQiT/FlGzduxNlnn31c+y8IgiAIgiAIgtBbTCYTMjIyUF1dza+TkpLUxKtHwO/3w+12h94j0RgM/VcUhQU7/W/pf9wf3zOuop0s6kRhYWHE+ry8vNC2cMiaHt3WarXywaioqOhzP7QDe7RosfWJGmMv/Y8v0v/4k+jfQfo/cPpP41JPbt4EQRCExKWgoIAfNeHeEyiU2OfzwWw2w0hVVRKMwdT/jIyM0P84oUW7dmNDwjscm82GpqammO2j22rttRmPvuD1elFaWor+Yv/+/UhkpP/xRfoffxL9O0j/B0b/Y413giAIwsCBJmfJIEkGS9IjPYH00N69ezF8+HA4HA4kGoOl/xaLpV89CeIq2u12eyi2XXtOkACPdRCoTawEddSeXEr6Ch3U0aNHoz/+iXSzVlJSkrAnofQ/fkj/40+ifwfp/8Dp/+7du/utX4IgCIK+IXHXU4FHll7NaBmunxIF6X8CinbN1Z1cQmi2QoNejxs3rlN7ci/46KOPItaRiG9sbOQZqqOZ5Toa0R8N3az15/sdb6T/8UX6H38S/TtI/xO//+IaLwiCIAiCRlwDCShbfEpKCtauXRta19zcjO3bt3Md9mhoHcW6U8k3DcomT8yaNes49VoQBEEQBEEQBEEQBoGlneL1LrroIjz++OPIysrCkCFD8Nhjj7FFffHixZydr76+Hqmpqex+MG3aNMycORM333wz12an5HH33nsvlixZgvz8/Hh+FUEQBEEQBEEQBEHodwxKf1Z97wMkzJ988km89dZbcLlcbE0nIT506FAcOnQIp59+Oh5++GFccMEF3L6urg73338/PvvsM44lOOuss3DXXXfx876wadMmztLbHwl/6H0oiQTFyCeia6P0P75I/+NPon8H6f/A6T+FftF70ES1cPT051hPyLkaX6T/8UX6H1+k/4NzrI+7aI83mzdv5oPfH0XvBUEQBKE/oBsCGshnzJgR764MCGSsFwRBEBJ5rB/0ol0QBEEQBEEQBEEQ9EriVbQXBEEQBEEQBEEQhEGCiHZBEARBEARBEARB0Cki2gVBEARBEARBEARBp4hoFwRBEARBEARBEASdIqJdEARBEARBEARBEHSKiHZBEARBEARBEARB0Cki2gVBEARBEARBEARBp4hoFwRBEARBEARBEASdIqJdEARBEARBEARBEHSKiHZBEARBEARBEARB0Cki2gVBEARBEARBEARBp4hoFwRBEARBEARBEASdIqK9FwQCATzzzDM4+eSTMX36dFx55ZUoKyvrsn1DQwNuvfVWzJkzB3PnzsX9998Pp9OJROn/X/7yF4wbN67TcujQIcSbX/7yl7j44ou7baO349+X76Cn/0FjYyPuvfdeLFy4EDNnzsQPfvADbNiwocv21Merr76a2y5YsABPP/00/H4/4kVv+79q1aqYxz6e1NXV4fbbb8f8+fMxY8YMXHXVVdizZ0/C/AZ62389nf/h7Nu3j/v/1ltvJcyxF3qHjPf6+K0NhPE+0cZ6Qsb7+I73Mtbr5/qzT0fjvbnf33EA8/zzz+P111/HI488goKCAjz22GO44oor8O6778JqtXZqf8MNN/A/7ZVXXkFzczPuvvtutLe3Y8WKFQnR/507d/LJ9+STT0asz8rKQjz5/e9/zwPC7Nmzu22nt+Pfl++gp//BLbfcgpqaGu5LdnY2Xn31VVx++eV4++23MXLkyIi2Xq+Xt5WUlGD16tU4ePAgH3+j0cj/l3jQm/5rx/68887jgUcvXHvttXwz/uKLLyI5ORkrV67EZZddhg8//BAOh0P3v4He9l9P53/4uX3bbbfxcewOvR17oXfIeK8i4/3gG+sJGe/ji4z1+rj+ePU23itCj3C73cqMGTOU3//+96F1TU1NytSpU5V33323U/tNmzYpY8eOVXbv3h1a99lnnynjxo1TKisrFb33n7jiiiuUBx98UNELdNyuvvpqZfr06cpZZ52lXHTRRV221dvx78t30NP/YP/+/Xw8N2zYEFoXCASUM844Q3n66ac7tadzavLkyUpjY2No3erVq5WZM2fyuaj3/hPf/va3ld/85jeKXqBjecsttyg7d+4MrSstLeXv9fXXX+v+N9Db/uvp/A/niSeeUC655BLu95tvvhmzjd6OvdA7ZLyPP4k+3ifqWE/IeB9fZKzXD0/obLwX9/gesmPHDrS1teGEE04IrUtLS8PEiROxfv36Tu3JDSc3NxejRo0KraNZJIPBgI0bN0Lv/ddmvsL7H2/+85//wGKxsBvNtGnTum2rt+Pfl++gp/9BZmYmz5hOmTIltI6OJS00qxjr+E+aNAnp6emhdeQm1draitLSUui9/x6PB/v37485Ix8v6Fg+8cQTGDt2LL+ur6/nWV2yoo0ePVr3v4He9l9P578GXSvfeOMNtl52h96OvdA7ZLyPP4k+3ifqWE/IeB9fZKzXB+t1ON6LaO8hlZWV/FhYWBixPi8vL7QtnKqqqk5tySUtIyMDFRUV0Hv/m5qa+DvQyXjuuedyjNI111zDsR3xYtGiRXj22WcxbNiwI7bV2/Hvy3fQ0/+AbvhOOeWUCLfKDz74AAcOHOCYyWjonKILdPS5RsTj+Pe2/7t37+Z4PGrzrW99C6eeeiq7zVVXV0MP/OxnP+Mb8r/+9a9Yvnw5kpKSEuY30NP+6+n8J+hmb9myZbjnnns6HddEOvbCkZHxXsb7wTrWEzLe62e8l7E+PjTrdLwX0d5DtIQC0bFgNpsNbrc7ZvtYcWNdtddb/7/55ht+VBQFDz/8MMdkUbsf/vCHqK2thd7R2/HvC3r+H2zatAl33XUXFi9ezANcNC6XK+a5Rujh+B+p/7t27eJHir2iWCwabPbu3YtLLrmEv1u8ufTSS/Hmm2/inHPO4dgxsuok0m+gJ/3X2/l/3333cTIauqk4Eno+9sKRkfFeP2NNT9Db8e8tej/+Mt7HDxnr43P+36fT8V4S0fUQu90ecqPRnhP0D4mVVIHaUNtoqH2smSa99Z+Spvz73/9mNyNy8SCee+45vuBRBkXKBKln9Hb8+4Je/wcfffQRJ+agjKyPP/54j4+/dvGK9/HvSf+XLFnCWWfDk6CMGTOG13388cc4++yzEU80FzO6ufj666/x2muv8WCXKL+BnvRfT+f/O++8w1YASuLVE/R87IUjI+O9PsaanqK3499b9Hz8ZbyP73gvY/3xP//f0fF4L5b2HqK5PkS7y9Dr/Pz8Tu3JVSi6Lf1TqQyF5jak5/4TdAHTfkAEDfZDhw5lVxC9o7fj31f09j+gC+7111+P0047DS+88EJoNr0nx1973dX5pqf+x8paSucNuTvFci89HlBcGLmY+Xy+0DrKzkuDYiw3Pr39Bnrbfz2d/2QpoBI2dBNBs++0ED//+c85I7fej73QO2S8j/9Y0xv0dvz7gh6Pv4z38RnvZayP7/n/po7HexHtPWT8+PFISUnB2rVrI2Ietm/fznX5oqF19GOnGBqNdevW8eOsWbOg9/5T8oV58+ZFlDmgpCKUrKOrRBJ6Qm/Hvy/o7X9A5YMefPBB/OhHP+KyHLHcgcKPP51b1F+NNWvWcOkPOhfjQW/6/9RTT3FsG7lraVC9UKrFGa/zn9zEqIwNzUiHlyOh4xwrgYvefgO97b+ezn+y0Lz33ns8A68tWpkXsiDo/dgLvUPGexnvjyd6PP4y3sdvvJexPr7n/+N6Hu/7NRf9AOfJJ59U5s6dq3z00UdcvuAnP/mJsnjxYsXj8Sg+n0+prq5WnE5nqLzE97//feX888/nEgf//ve/ldNOO0258847E6L/5eXlyuzZs5Vrr71W2bVrl7Jlyxblsssu45IZLpdLiTd33HFHRAmVRDj+vf0Oevof7N27V5k0aRL3hfoYvjQ3N3NZF3qulXeh/lE/L7/8cj7X/v73v/O59+yzzx7Xfve1/1u3buX29957L++7bt06ZcmSJXxO0bkVL6gsCv1mqT9UToXKqsyZM0c5fPhwQvwGetN/PZ3/sQgvAZMIx17oHTLe6+e3lujjfSKN9YSM9/Ef72Ws18/1R0/jvYj2XkD/qEcffVSZP38+19688sorlbKyMt5Gj9F1/Gpra5Xrr7+e286bN0/5+c9/HtcTsLf937Ztm/LjH/9YmTVrFtfbpO9CPy49DoKJcPz78h308j9YtWoV9y3WQt9jzZo1/Jwew2ulUt+nTJmiLFiwgOuj+v3+4973vvb/yy+/VC688EI+f+gG5K677oqoQxsP6IaDzuOTTjqJay7TjTgNconyG+ht//Vy/scivK+JcOyF3iHjvX5+a4k+3ifSWE/IeB//8V7Gev1cf/Q03hvoT//a7gVBEARBEARBEARB6A8kpl0QBEEQBEEQBEEQdIqIdkEQBEEQBEEQBEHQKSLaBUEQBEEQBEEQBEGniGgXBEEQBEEQBEEQBJ0iol0QBEEQBEEQBEEQdIqIdkEQBEEQBEEQBEHQKSLaBUEQBEEQBEEQBEGniGgXBEEQBEEQBEEQBJ1ijncHBEE49tx55514++23u9yek5ODL7744rj2ady4cbjuuutw/fXXH9fPFQRBEISBiIz1gjBwEdEuCIOE3NxcPPfcczG3WSyW494fQRAEQRD6FxnrBWFgIqJdEAYJVqsV06dPj3c3BEEQBEE4RshYLwgDE4lpFwQhxMUXX8zudS+88AJOPPFEzJo1C9dccw0OHz4c0W7r1q24/PLLMW/ePMycORP//d//jW+++SaiTXV1Ne644w6ccMIJmDFjBi666CJs3rw5ok1rayvuvvtuzJ07l9vccMMNqK2tDW0/ePAgvzd9zrRp03DhhRfik08+OcZHQRAEQRAGLjLWC0LiIaJdEAYRPp8v5qIoSqjNP/7xD7z11lu45557cP/996O0tJQHeKfTydvXrFmDH/zgB/z8oYcewi9+8QtUVFTg+9//Pvbs2cPr29rauM3atWtx++23s6uezWbDT37yE+zfvz/0Wb/73e/g9XqxcuVK3Hrrrfj444/xwAMP8LZAIICrr76aP/fRRx/F888/j4yMDPz0pz/FgQMHjvOREwRBEITEQMZ6QRh4iHu8IAwSaAZ90qRJMbctW7aMZ9MJGjhpIB82bBi/HjlyJM4//3y88847PDg/8cQTKC4uxosvvgiTycRtFixYgDPPPBPPPPMMD8qUCIc+jx4nTJjAbWiWfsmSJVi/fj1KSkp43ZQpU3iQJmiW/uuvvw7NrtfV1WHv3r08+3/KKafwuqlTp/JNgcfjOebHSxAEQRASDRnrBWFgIqJdEAZRcppVq1bF3FZYWBh6TgOuNogTEydO5Nc0AJ933nnsLkeZYLVBnEhLS8Npp50WGoQ3btyIoUOHhgZxwuFw4IMPPoj4XHLJC4f2aW5uDmW5HT16NH72s5/h888/55uFhQsX4q677jrqYyEIgiAIAxEZ6wVhYCKiXRAGUXIamu0+Evn5+Z3WZWdno6mpCS0tLexeR4NsNLSOthONjY28z5FISkqKeG00GkPuewaDAS+//DLffPz973/n2X/KfHvGGWewK196evoR318QBEEQBhMy1gvCwERi2gVBiKChoaHTOkoYk5WVhdTUVB5gwxPIaNTU1HAcGkHt6uvrO7XZtGlTKBauJ9BNxX333cez7zSQk1vfhx9+iKeffrrX30sQBEEQBBUZ6wUhsRDRLghCBOTuFj6Yb9u2DYcOHeI4NJotnzx5Mt5//334/f5QG5p1/9e//hVygZs9ezbKysoissy63W5cf/31+NOf/tSjflD2Wcpqu2XLFr55IPe7m2++GWPHjkV5eXm/fmdBEARBGEzIWC8IiYW4xwvCIIESunz11Vddbh83blwoOc0VV1zBmVspM+xTTz3Fg+c555zD2ynzK82CX3XVVfjhD3/IGWEpUQ29/7XXXsttLrjgArz66qv8HlTaJTMzM5Q9lvbpCRRfZ7fbOXEO3QCQS96XX37JGW4vueSSfjkmgiAIgjCQkLFeEAYmItoFYZBALm1U+7QryCVNmzmfP38+11QlFi1axIMpxckRNAv/m9/8hrPH3nLLLbye9lmxYgXGjBnDbVJSUvDaa69xttgHH3yQS7pMnz6dB/PwxDfdQWVjKM6NMtguX76ck9ZQJloqE0M3CoIgCIIgRCJjvSAMTAxKeNFGQRAGNVSjlaCZc0EQBEEQBh4y1gtC4iEx7YIgCIIgCIIgCIKgU0S0C4IgCIIgCIIgCIJOEfd4QRAEQRAEQRAEQdApYmkXBEEQBEEQBEEQBJ0iol0QBEEQBEEQBEEQdIqIdkEQBEEQBEEQBEHQKSLaBUEQBEEQBEEQBEGniGgXBEEQBEEQBEEQBJ0iol0QBEEQBEEQBEEQdIqIdkEQBEEQBEEQBEHQKSLaBUEQBEEQBEEQBAH65P8Dujbr9Av3qQMAAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_results(results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Learning rate: 0.1 - époques: 50\n",
      "Learning rate: 0.01 - époques: 50\n",
      "Learning rate: 0.001 - époques: 50\n"
     ]
    }
   ],
   "source": [
    "n_epochs = 50\n",
    "batch_size = 256\n",
    "learning_rates = [10 ** (-power) for power in range(1, 4)]\n",
    "\n",
    "results = []\n",
    "for learning_rate in learning_rates:\n",
    "    print(f\"Learning rate: {learning_rate} - époques: {n_epochs}\")\n",
    "    model = get_model(learning_rate=learning_rate)\n",
    "    history = model.fit(\n",
    "        X_train,\n",
    "        y_train,\n",
    "        epochs=n_epochs,\n",
    "        batch_size=batch_size,\n",
    "        validation_data=(X_valid, y_valid),\n",
    "        verbose=0,\n",
    "    )\n",
    "    result = {\n",
    "        \"learning_rate\": learning_rate,\n",
    "        \"n_epochs\": n_epochs,\n",
    "        \"history\": pd.DataFrame(history.history),\n",
    "    }\n",
    "    results.append(result)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "show_results(results)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Pour continuer\n",
    "\n",
    "Choisir une ou plusieurs pistes de recherche parmi les suivantes. Il est possible de choisir une autre direction, mais elle doit être validé auparavant.\n",
    "\n",
    "1. L'initialisation des réseaux de neurones étant aléatoire, et la mise à jour des poids étant réalisées avec SGD, on ne peut pas considérer un exemple comme une généralité. Reproduire l'étude précédente en lançant plusieurs fois le même modèle pour être capable de générer un graphique avec des intervalles de confiance.\n",
    "2. Nous avons vu en cours que l'initialisation des poids peut avoir un impact fort sur la suite de l'entraînement. En exploitant le paramètre `kernel_initializer` présent dans la définition de la couche [`Dense`](https://keras.io/api/layers/core_layers/dense/), proposer et réaliser une étude pour vérifier ou infirmer cela.\n",
    "3. Les réseaux de neurones peuvent sur-apprendre. Il est important de pouvoir les régulariser. En exploitant le paramètre `kernel_regularizer` présent dans la définition de la couche [`Dense`](https://keras.io/api/layers/core_layers/dense/), proposer une étude pour visualiser son impact sur l'apprentissage."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "studies",
   "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": "3.13.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}