{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-08 14:10:55.450897: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1 SSE4.2\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "import numpy as np\n",
    "from tensorflow import keras\n",
    "from tensorflow.keras import backend as K\n",
    "from tensorflow.keras.models import Model, Sequential\n",
    "from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D, Input\n",
    "from tensorflow.keras.datasets import fashion_mnist"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n",
      "29515/29515 [==============================] - 0s 1us/step\n",
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n",
      "26421880/26421880 [==============================] - 13s 1us/step\n",
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n",
      "5148/5148 [==============================] - 0s 0us/step\n",
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n",
      "4422102/4422102 [==============================] - 2s 1us/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "((60000, 28, 28), (10000, 28, 28), (60000,), (10000,))"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(x_train, y_train), (x_test, y_test) = fashion_mnist.load_data()\n",
    "x_train = x_train.astype('float32') / 255.0\n",
    "x_test = x_test.astype('float32') / 255.0\n",
    "\n",
    "x_train.shape, x_test.shape, y_train.shape, y_test.shape"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Fashion-MNIST is a dataset of Zalando's article images—consisting of a training set of 60,000 examples and a test set of 10,000 examples. Each example is a 28x28 grayscale image, associated with a label from 10 classes. Zalando intends Fashion-MNIST to serve as a direct drop-in replacement for the original MNIST dataset for benchmarking machine learning algorithms. It shares the same image size and structure of training and testing splits.\n",
    "\n",
    "Each training and test example is assigned to one of the following labels:\n",
    "\n",
    "0 T-shirt/top\n",
    "1 Trouser\n",
    "2 Pullover\n",
    "3 Dress\n",
    "4 Coat\n",
    "5 Sandal\n",
    "6 Shirt\n",
    "7 Sneaker\n",
    "8 Bag\n",
    "9 Ankle boot"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_shape = (x_train.shape[1:] + (1,)) # (28, 28, 1)\n",
    "num_classes = len(np.unique(y_train)) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_train = keras.utils.to_categorical(y_train, num_classes)\n",
    "y_test = keras.utils.to_categorical(y_test, num_classes)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model: \"model\"\n",
      "_________________________________________________________________\n",
      " Layer (type)                Output Shape              Param #   \n",
      "=================================================================\n",
      " input_1 (InputLayer)        [(None, 28, 28, 1)]       0         \n",
      "                                                                 \n",
      " conv2d (Conv2D)             (None, 26, 26, 32)        320       \n",
      "                                                                 \n",
      " conv2d_1 (Conv2D)           (None, 24, 24, 64)        18496     \n",
      "                                                                 \n",
      " max_pooling2d (MaxPooling2D  (None, 12, 12, 64)       0         \n",
      " )                                                               \n",
      "                                                                 \n",
      " dropout (Dropout)           (None, 12, 12, 64)        0         \n",
      "                                                                 \n",
      " flatten (Flatten)           (None, 9216)              0         \n",
      "                                                                 \n",
      " dense (Dense)               (None, 128)               1179776   \n",
      "                                                                 \n",
      " dropout_1 (Dropout)         (None, 128)               0         \n",
      "                                                                 \n",
      " dense_1 (Dense)             (None, 10)                1290      \n",
      "                                                                 \n",
      "=================================================================\n",
      "Total params: 1,199,882\n",
      "Trainable params: 1,199,882\n",
      "Non-trainable params: 0\n",
      "_________________________________________________________________\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2023-05-08 14:11:15.843391: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations:  SSE4.1 SSE4.2\n",
      "To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags.\n"
     ]
    }
   ],
   "source": [
    "inp = Input(shape=input_shape)\n",
    "_ = Conv2D(filters=32, kernel_size=(3, 3), activation='relu')(inp)\n",
    "_ = Conv2D(filters=64, kernel_size=(3, 3), activation='relu')(_)\n",
    "_ = MaxPool2D(pool_size=(2, 2))(_)\n",
    "_ = Dropout(0.25)(_)\n",
    "_ = Flatten()(_)\n",
    "_ = Dense(units=128, activation='relu')(_)\n",
    "_ = Dropout(0.2)(_)\n",
    "_ = Dense(units=num_classes, activation='softmax')(_)\n",
    "model = Model(inputs=inp, outputs=_)\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/12\n",
      "329/329 [==============================] - 29s 88ms/step - loss: 0.5025 - accuracy: 0.8219 - val_loss: 0.3268 - val_accuracy: 0.8839\n",
      "Epoch 2/12\n",
      "329/329 [==============================] - 29s 88ms/step - loss: 0.3146 - accuracy: 0.8887 - val_loss: 0.2758 - val_accuracy: 0.9008\n",
      "Epoch 3/12\n",
      "329/329 [==============================] - 29s 89ms/step - loss: 0.2667 - accuracy: 0.9014 - val_loss: 0.2561 - val_accuracy: 0.9054\n",
      "Epoch 4/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.2347 - accuracy: 0.9141 - val_loss: 0.2435 - val_accuracy: 0.9114\n",
      "Epoch 5/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.2082 - accuracy: 0.9220 - val_loss: 0.2275 - val_accuracy: 0.9162\n",
      "Epoch 6/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.1851 - accuracy: 0.9323 - val_loss: 0.2309 - val_accuracy: 0.9212\n",
      "Epoch 7/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.1664 - accuracy: 0.9368 - val_loss: 0.2298 - val_accuracy: 0.9177\n",
      "Epoch 8/12\n",
      "329/329 [==============================] - 29s 88ms/step - loss: 0.1456 - accuracy: 0.9450 - val_loss: 0.2275 - val_accuracy: 0.9220\n",
      "Epoch 9/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.1319 - accuracy: 0.9513 - val_loss: 0.2328 - val_accuracy: 0.9236\n",
      "Epoch 10/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.1176 - accuracy: 0.9564 - val_loss: 0.2300 - val_accuracy: 0.9248\n",
      "Epoch 11/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.1034 - accuracy: 0.9613 - val_loss: 0.2351 - val_accuracy: 0.9263\n",
      "Epoch 12/12\n",
      "329/329 [==============================] - 28s 86ms/step - loss: 0.0963 - accuracy: 0.9637 - val_loss: 0.2446 - val_accuracy: 0.9269\n"
     ]
    }
   ],
   "source": [
    "model.compile(loss=keras.losses.categorical_crossentropy,\n",
    "              optimizer=keras.optimizers.Adam(), metrics=['accuracy'])\n",
    "history = model.fit(np.expand_dims(x_train, -1), y_train, batch_size=128, epochs=12, validation_split=0.3)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "0.2570808231830597 0.925000011920929\n"
     ]
    }
   ],
   "source": [
    "loss, accuracy = model.evaluate(np.expand_dims(x_test, -1), y_test, verbose=0)\n",
    "print(loss, accuracy)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x7fb5d3d97ac0>"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAABHkAAAGsCAYAAABJp3vjAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAC8eElEQVR4nOzdeVxU9f7H8dcw7MgmKKIigvuaigqIZpZpVl61zTbNtMVbVua93bKysrrZZtmi/rJcskXN1OqWlVi5b0lqlrugKIIIKKtsw/z+ODiKaIECw/J+Ph7zEM45c87niDjMm+/38zVZrVYrIiIiIiIiIiJSoznYuwAREREREREREbl8CnlERERERERERGoBhTwiIiIiIiIiIrWAQh4RERERERERkVpAIY+IiIiIiIiISC2gkEdEREREREREpBZQyCMiIiIiIiIiUgs42ruAilJUVMSxY8fw9PTEZDLZuxwRERG5CKvVSmZmJo0bN8bBQb9vsif9/CQiIlIzlPXnp1oT8hw7doygoCB7lyEiIiJldOTIEZo2bWrvMuo0/fwkIiJSs/zdz0+1JuTx9PQEjBv28vKyczUiIiJyMRkZGQQFBdleu8V+9POTiIhIzVDWn59qTchzZoixl5eXfkgRERGpATQ9yP7085OIiEjN8nc/P2kivIiIiIiIiIhILaCQR0RERERERESkFlDIIyIiIiIiIiJSC9SanjwiIlKzFRUVkZ+fb+8ypAI4OTlhNpvtXYZUEIvFQkFBgb3LkFpC/z+IiFQuhTwiImJ3+fn5xMXFUVRUZO9SpIL4+PjQqFEjNVeuwaxWK0lJSZw6dcrepUgto/8fREQqj0IeERGxK6vVSmJiImazmaCgIBwcNJO4JrNareTk5JCcnAxAYGCgnSuSS3Um4GnYsCHu7u56Qy6XTf8/iIhUPoU8IiJiV4WFheTk5NC4cWPc3d3tXY5UADc3NwCSk5Np2LChpmbUQBaLxRbw+Pn52bscqUX0/4OISOXSr0tFRMSuLBYLAM7OznauRCrSmcBOvVxqpjNfNwWvUhn0/4OISOVRyCMiItWCpoLULvp61g76Okpl0L8rEZHKo5BHRERERERERKQWUMgjIiIiIiIiIlILKOQRERGpJq666irGjx9v7zJE5Dz63hQRkZpCIY+IiEg5mUymv3yMGjXqks67dOlSXnrppcuqbdSoUQwdOvSyziFSU1Xn780zNmzYgNls5rrrrquQ84mIiJzrkkKeGTNmEBISgqurK2FhYaxdu/aix65ateqCL7J79uwpcdySJUto3749Li4utG/fnmXLll1KaRXKarVyKCWbJTFHsVqt9i5HRESqicTERNtj2rRpeHl5ldj2zjvvlDi+rCvI1K9fH09Pz8ooWaROqAnfm3PmzOGRRx5h3bp1xMfHV8g5L5VWtxIRqTh5hRYOJGcSves4KVl5dquj3CHPokWLGD9+PM888wzbtm2jT58+DBo06G9fpPbu3VviRbZVq1a2fRs3bmT48OGMGDGCHTt2MGLECG677TY2b95c/juqQHmFRQx4ew3/WryDw6k5dq1FRKSusFqt5OQX2uVR1kC/UaNGtoe3tzcmk8n2eW5uLj4+PnzxxRdcddVVuLq68umnn5Kamsodd9xB06ZNcXd3p1OnTixYsKDEec+fEtK8eXNeeeUVRo8ejaenJ82aNWPWrFmX9fe7evVqevbsiYuLC4GBgTz11FMUFhba9n/55Zd06tQJNzc3/Pz86N+/P9nZ2YDxi5uePXvi4eGBj48PUVFRHD58+LLqkZpD35vjbZ9f6vdmdnY2X3zxBf/85z+58cYbmTdvXqljvvnmG7p3746rqyv+/v7cdNNNtn15eXn85z//ISgoCBcXF1q1asXs2bMBmDdvHj4+PiXO9dVXX5VYyeqFF16gS5cuzJkzh9DQUFxcXLBarfzwww/07t0bHx8f/Pz8uPHGGzl48GCJcx09epTbb7+d+vXr4+HhQffu3dm8eTOHDh3CwcGBrVu3ljj+vffeIzg4WL8oFZFapdBSxKGUbH7Zm8ycdXE89/UfjJi9md6v/Uy7ST/Q/6013D9/K1sPnbRbjY7lfcJbb73FmDFjuO+++wCYNm0aP/74IzNnzmTKlCkXfV7Dhg1LvfCcMW3aNK699lomTpwIwMSJE1m9ejXTpk0r9SJblVydzHQJ8mHLoTQ2xqbS3N/DbrWIiNQVpwsstH/uR7tce9eLA3F3LvdL4wU9+eSTTJ06lblz5+Li4kJubi5hYWE8+eSTeHl58d133zFixAhCQ0MJDw+/6HmmTp3KSy+9xNNPP82XX37JP//5T6688kratm1b7poSEhK4/vrrGTVqFPPnz2fPnj3cf//9uLq68sILL5CYmMgdd9zB66+/zrBhw8jMzGTt2rVYrVYKCwsZOnQo999/PwsWLCA/P58tW7ZoKeQ6RN+bJV3K9+aiRYto06YNbdq04e677+aRRx5h0qRJtu+j7777jptuuolnnnmGTz75hPz8fL777jvb80eOHMnGjRt59913ueKKK4iLiyMlJaVc93/gwAG++OILlixZgtlsBozwacKECXTq1Ins7Gyee+45hg0bxvbt23FwcCArK4u+ffvSpEkTvvnmGxo1asRvv/1GUVERzZs3p3///sydO5fu3bvbrjN37lxGjRql/yNEpMaxFFk5duo0h1KzOZSSTVxKDnEpWRxKzeFIWg6FRRcPrz2czTT398DsYL//+8r1apmfn09MTAxPPfVUie0DBgxgw4YNf/ncrl27kpubS/v27Xn22Wfp16+fbd/GjRt5/PHHSxw/cOBApk2bdtHz5eXlkZd3dghURkZGOe6k7CJa+LHlUBqbYlO5o2ezSrmGiIjUPuPHjy/xG3iAf//737aPH3nkEX744QcWL178l28kr7/+eh566CHAeHP69ttvs2rVqksKeWbMmEFQUBDvv/8+JpOJtm3bcuzYMZ588kmee+45EhMTKSws5KabbiI4OBiATp06AZCWlkZ6ejo33ngjLVq0AKBdu3blrkHE3uz5vTl79mzuvvtuAK677jqysrL46aef6N+/PwD//e9/uf3225k8ebLtOVdccQUA+/bt44svviA6Otp2fGhoaHluHTB+nv/kk09o0KCBbdvNN99cqs6GDRuya9cuOnbsyOeff86JEyf49ddfqV+/PgAtW7a0HX/fffcxduxY3nrrLVxcXNixYwfbt29n6dKl5a5PRKQqWK1WjmfkEZeSzaHUbOJSjMehlGwOp+WQX1h00ee6ODoQ4u9Bcz8Pmvt7EOLvToh/PZr7u9Ognovdw+1yhTwpKSlYLBYCAgJKbA8ICCApKemCzwkMDGTWrFmEhYWRl5fHJ598wjXXXMOqVau48sorAUhKSirXOQGmTJlS4gWwskSE1ufdn2DjwVSsVqvdv2AiIrWdm5OZXS8OtNu1K8q5v9EGsFgsvPrqqyxatIiEhATbLys8PP56lGjnzp1tH5+ZepKcnHxJNe3evZvIyMgSr2VRUVFkZWVx9OhRrrjiCq655ho6derEwIEDGTBgALfccgu+vr7Ur1+fUaNGMXDgQK699lr69+/PbbfdRmBg4CXVIjWPvjdLKu/35t69e9myZYst+HB0dGT48OHMmTPHFtps376d+++//4LP3759O2azmb59+5bpPi8mODi4RMADcPDgQSZNmsSmTZtISUmhqMh4cxMfH0/Hjh3Zvn07Xbt2tQU85xs6dCjjxo1j2bJl3H777cyZM4d+/frRvHnzy6pVRORyWK1WUrPzi0fjZJ8T6ORwKCWb0wWWiz7XyWyiWX13W5gT0sCDkOJQp5GXKw52HKnzdy5p3Ov5QcdfhR9nhqSeERkZyZEjR3jzzTdtIU95zwnGlK4JEybYPs/IyCAoKKhc91EW3Zr54uzoQHKmkfKFNqhX4dcQEZGzTCZThU3LsKfz3yBOnTqVt99+m2nTptGpUyc8PDwYP348+fn5f3keJyenEp+bTCbbG7DyutBr65l+GSaTCbPZTHR0NBs2bGDFihW89957PPPMM2zevJmQkBDmzp3Lo48+yg8//MCiRYt49tlniY6OJiIi4pLqkZpF35sllfd7c/bs2RQWFtKkSRPbNqvVipOTEydPnsTX1xc3N7eLPv+v9gE4ODiU6n9zocbKFwqvBg8eTFBQEB9++CGNGzemqKiIjh072v4O/u7azs7OjBgxgrlz53LTTTfx+eef/+WIfBGRipSeU0BcajZxKVm2AOdQajZxJ7LJzCu86PPMDiaa+roZIY6/8Wjub4Q5jX1ccTTXzMXIy/VK7e/vj9lsLjXCJjk5udRInL8SERHBp59+avu8UaNG5T6ni4sLLi4uZb7mpXJ1MtM1yIfNcUZfHoU8IiJyKdauXcuQIUNsUzWKiorYv39/lU55at++PUuWLCkR9mzYsAFPT0/bG0+TyURUVBRRUVE899xzBAcHs2zZMtsvVrp27UrXrl2ZOHEikZGRfP755wp5pEariu/NwsJC5s+fz9SpUxkwYECJfTfffDOfffYZ48aNo3Pnzvz000/ce++9pc7RqVMnioqKWL16tW3kz7kaNGhAZmYm2dnZtiBn+/btf1tbamoqu3fv5oMPPqBPnz4ArFu3rsQxnTt35qOPPiItLe2io3nuu+8+OnbsyIwZMygoKCg1JU5E5HKlZeezKTaVg8lZxaGOMb3qZM7FVwo0maCxt1txgONeItBp6uuOs2PNDHL+SrlCHmdnZ8LCwoiOjmbYsGG27dHR0QwZMqTM59m2bVuJ4d2RkZFER0eX6MuzYsUKevXqVZ7yKk1kCz82x6WxKTaNu8KD7V2OiIjUQC1btmTJkiVs2LABX19f3nrrLZKSkiol5ElPTy/15q5+/fo89NBDTJs2jUceeYRx48axd+9enn/+eSZMmICDgwObN2/mp59+YsCAATRs2JDNmzdz4sQJ2rVrR1xcHLNmzeIf//gHjRs3Zu/evezbt4+RI0dWeP211YwZM3jjjTdITEykQ4cOTJs2zfam+kKmT5/O+++/z6FDh2jWrBnPPPNMqb/vU6dO8cwzz7B06VJOnjxJSEgIU6dO5frrr6/s26k1quJ789tvv+XkyZOMGTMGb2/vEvtuueUWZs+ezbhx43j++ee55ppraNGiBbfffjuFhYV8//33/Oc//6F58+bcc889jB492tZ4+fDhwyQnJ3PbbbcRHh6Ou7s7Tz/9NI888ghbtmy54Opd5/P19cXPz49Zs2YRGBhIfHx8qf6bd9xxB6+88gpDhw5lypQpBAYGsm3bNho3bkxkZCRg9OiKiIjgySefZPTo0X87+kdE5O9YrVb2J2fx0+5kftp9nN/iT3KxnscBXi62AKe5/9kgp1l9d1wrcMpvTVDuMbcTJkxgxIgRdO/encjISGbNmkV8fDxjx44FjGlUCQkJzJ8/HzBWzmrevDkdOnQgPz+fTz/9lCVLlrBkyRLbOR977DGuvPJKXnvtNYYMGcLXX3/NypUrS/0WwV4iQv2A/WyKVV8eERG5NJMmTSIuLo6BAwfi7u7OAw88wNChQ0lPT6/wa61atYquXbuW2HbPPfcwb948li9fzhNPPMEVV1xB/fr1GTNmDM8++ywAXl5erFmzhmnTppGRkUFwcDBTp05l0KBBHD9+nD179vDxxx+TmppKYGAg48aN48EHH6zw+mujRYsWMX78eGbMmEFUVBQffPABgwYNYteuXTRrVnphh5kzZzJx4kQ+/PBDevTowZYtW7j//vvx9fVl8ODBgNFA99prr6Vhw4Z8+eWXNG3alCNHjuDp6VnVt1ejVcX35uzZs+nfv3+pgAeMkTyvvPIKv/32G1dddRWLFy/mpZde4tVXX8XLy6tEe4OZM2fy9NNP89BDD5GamkqzZs14+umnASPI/fTTT3niiSeYNWsW/fv354UXXuCBBx74y9ocHBxYuHAhjz76KB07dqRNmza8++67XHXVVbZjnJ2dWbFiBf/617+4/vrrKSwspH379kyfPr3EucaMGcOGDRsYPXr0ZfxtiUhdll9YxJa4NFbuPs5Pe45zJO10if1tG3nSobE3oQ3OND42Rud4uNT86cQVxWQ9f/JuGcyYMYPXX3+dxMREOnbsyNtvv217ARo1ahSHDh1i1apVALz++uvMmjWLhIQE3Nzc6NChAxMnTiz1G6Yvv/ySZ599ltjYWFq0aMF///vfcg3zzMjIwNvbm/T0dLy8vMp7S38pt8BC58kryC8sYuWEvrRsqClbIiIVJTc3l7i4OEJCQnB1dbV3OVJB/urrWpmv2dVVeHg43bp1Y+bMmbZt7dq1s42MOF+vXr2IiorijTfesG0bP348W7dutf0S7P/+7/9444032LNnT6n+MGV1sa+Fvi/lUvz3v/9l4cKF7Ny58y+P078vETlXWnY+v+xJ5qc9x1mzL4Wsc/roODs60KuFH9e0C+Catg1p7FN3RwmW9eenS4q7HnroIduSkec7f1jof/7zH/7zn//87TlvueUWbrnllkspp9K5OpkJa+bLxthUNsWmKuQRERGRMsvPzycmJqbUFJgBAwawYcOGCz4nLy+v1JtfNzc3tmzZQkFBAU5OTnzzzTdERkby8MMP8/XXX9OgQQPuvPNOnnzySczmCw9NP7Ny1BkZGRmXeXcikJWVxe7du3nvvfd46aWX7F2OiFRzZ6Zhrdx9nJ92J/Nb/EnOHXriX8+Fa9o25Jp2Dendyr9WNP2vSvrbKqOIUD82xqayMTaVuyPUl0dERETKJiUlBYvFUmpBiYCAgFILT5wxcOBAPvroI4YOHUq3bt2IiYlhzpw5FBQUkJKSQmBgILGxsfz888/cddddLF++nP379/Pwww9TWFjIc889d8HzTpkyhcmTJ1f4PUrdNm7cOBYsWMDQoUM1VUtELii/sIjNcalGf50LTMNqH+hF/3YNubpdAJ2beFfrJcqrO4U8ZRTZwo+3V8Jm9eURERGRS3Ch5esv9vPEpEmTSEpKIiIiAqvVSkBAAKNGjeL111+3jdIpKiqiYcOGzJo1C7PZTFhYGMeOHeONN964aMgzceJE20ppYIzkCQoKqqA7lLpq3rx5ZWryLCJ1S2pWHr/sPcHPF5mGFVU8DevqOj4Nq6Ip5CmjK4K8cXF0ICUrnwPJWbQKUFNDERER+Xv+/v6YzeZSo3aSk5NLje45w83NjTlz5vDBBx9w/PhxAgMDmTVrFp6envj7+wMQGBiIk5NTialZ7dq1Iykpifz8fJydnUud18XFBRcXlwq8OxEREYPVamXf8Sx+2nPhaVgNPI1pWFe31TSsyqS/1TJycTTTvbkv6w8YfXkU8oiIiEhZODs7ExYWRnR0NMOGDbNtj46OZsiQIX/5XCcnJ5o2bQrAwoULufHGG3FwcAAgKiqKzz//nKKiItu2ffv2ERgYeMGAR0REpKLlFVrYHJvGz3uSWbn7OEdPlpyG1aGxV3F/nQA6aRpWlVDIUw4RIX7FIU8aIyKb27scERERqSEmTJjAiBEj6N69O5GRkcyaNYv4+HjGjh0LGNOoEhISmD9/PmCENVu2bCE8PJyTJ0/y1ltv8ccff/Dxxx/bzvnPf/6T9957j8cee4xHHnmE/fv388orr/Doo4/a5R5FRKRuODMN66fdx1mz7wTZ+RbbvnOnYV3TriGB3pqGVdUU8pRDRAs/iIZN6ssjIiIi5TB8+HBSU1N58cUXSUxMpGPHjixfvpzgYGMxh8TEROLj423HWywWpk6dyt69e3FycqJfv35s2LCB5s2b244JCgpixYoVPP7443Tu3JkmTZrw2GOP8eSTT1b17YmISC12ZhqWsRrWcbYdOXXBaVjXtAsgqqWfpmHZmf72y+GKpj64OjmQmp3P/uQsWmvKloiIiJTRQw89xEMPPXTBfec3rW3Xrh3btm3723NGRkayadOmiihPRETE5sw0rJ92H+enPckXnobVLoD+7RrSsbGmYVUnCnnKwdnRge7B9Vl3IIWNB1MV8oiIyGW56qqr6NKlC9OmTbN3KSJyDn1vikhdlJqVx897kvlpdzJr95echuXi6EBUS3+uaWc0TtY0rOpLIU85RbbwY92BFDbFpnJPr+b2LkdEROxg8ODBnD59mpUrV5bat3HjRnr16kVMTAzdunW7rOvMmzeP8ePHc+rUqcs6j0hdUVXfm2ecPn2axo0bYzKZSEhIwM1Nb3pEpOawWq0cPJFN9K7jrNx9vNRqWA09XYpDnQB6t/THzdl88ZNJtaGQp5wiQusDRl+eoiKrhqWJiNRBY8aM4aabbuLw4cO2nipnzJkzhy5dulTYm0gRKbuq/t5csmQJHTt2xGq1snTpUu66664KO3d5Wa1WLBYLjo768V5ELq7QUkTM4ZOs3H2clbuTiUvJLrFf07BqPgd7F1DTdG7qg5uTmZM5BexLzrR3OSIiYgc33ngjDRs2LNVHJScnh0WLFjFmzBhSU1O54447aNq0Ke7u7nTq1IkFCxZUaB3x8fEMGTKEevXq4eXlxW233cbx48dt+3fs2EG/fv3w9PTEy8uLsLAwtm7dCsDhw4cZPHgwvr6+eHh40KFDB5YvX16h9YlUtar+3pw9ezZ33303d999N7Nnzy61/88//+SGG27Ay8sLT09P+vTpw8GDB23758yZQ4cOHXBxcSEwMJBx48YBcOjQIUwmE9u3b7cde+rUKUwmE6tWrQJg1apVmEwmfvzxR7p3746Liwtr167l4MGDDBkyhICAAOrVq0ePHj1KjWzKy8vjP//5D0FBQbi4uNCqVStmz56N1WqlZcuWvPnmmyWO/+OPP3BwcChRu4jUHFl5hXy/M5EJX2ynx39XMnzWJj5cG0dcSjbOZgf6tm7AS0M7snHi1Xz3aB8mXNuazk19FPDUUIr6y8nJ7ED35r6s3W/05WnbyMveJYmI1C5WKxTk2OfaTu5QhpUTHR0dGTlyJPPmzeO5556zrba4ePFi8vPzueuuu8jJySEsLIwnn3wSLy8vvvvuO0aMGEFoaCjh4eGXXarVamXo0KF4eHiwevVqCgsLeeihhxg+fLjtTeBdd91F165dmTlzJmazme3bt+Pk5ATAww8/TH5+PmvWrMHDw4Ndu3ZRr169y65LajF9b5Zw8OBBNm7cyNKlS7FarYwfP57Y2FhCQ0MBSEhI4Morr+Sqq67i559/xsvLi/Xr11NYWAjAzJkzmTBhAq+++iqDBg0iPT2d9evXl/uv5j//+Q9vvvkmoaGh+Pj4cPToUa6//npefvllXF1d+fjjjxk8eDB79+6lWbNmAIwcOZKNGzfy7rvvcsUVVxAXF0dKSgomk4nRo0czd+5c/v3vf9uuMWfOHPr06UOLFi3KXZ+I2EdSei4rdx8netdxNh5MJd9SZNvn4+7E1W0a0r99AFe2bkA9F8UCtYm+mpcgItSPtfuNvjz3RoXYuxwRkdqlIAdeaWyfaz99DJw9ynTo6NGjeeONN1i1ahX9+vUDjDdCN910E76+vvj6+pZ4k/TII4/www8/sHjx4goJeVauXMnvv/9OXFwcQUFBAHzyySd06NCBX3/9lR49ehAfH88TTzxB27ZtAWjVqpXt+fHx8dx888106tQJwPbGVOSi9L1Zwpw5cxg0aBC+vr4AXHfddcyZM4eXX34ZgOnTp+Pt7c3ChQtt4Wrr1q1tz3/55Zf517/+xWOPPWbb1qNHjzJf/4wXX3yRa6+91va5n58fV1xxRYnrLFu2jG+++YZx48axb98+vvjiC6Kjo+nfvz9Q8vv/3nvv5bnnnmPLli307NmTgoICPv30U954441y1yYiVcdqtbI7MdPWX2dnQnqJ/c393Lm2fQD92wUQFuyLo1mTemorhTyXILKFHwCb49LUl0dEpI5q27YtvXr1Ys6cOfTr14+DBw+ydu1aVqxYAYDFYuHVV19l0aJFJCQkkJeXR15eHh4eZXuj+nd2795NUFCQLeABaN++PT4+PuzevZsePXowYcIE7rvvPj755BP69+/PrbfeavtN/KOPPso///lPVqxYQf/+/bn55pvp3LlzhdQmYk9V8b1psVj4+OOPeeedd2zb7r77bh5//HEmT55sGznXp08fW8BzruTkZI4dO8Y111xz2ffbvXv3Ep9nZ2czefJkvv32W44dO0ZhYSGnT58mPj4egO3bt2M2m+nbt+8FzxcYGMgNN9zAnDlz6NmzJ99++y25ubnceuutl12riFSs/MIiNselsnKX0V8n4dTZZc5NJuga5MO17RtxbfuGtGhQzza6UWo3hTyXoFMTb9ydzZzKKWBPUibtG2vKlohIhXFyN35rb69rl8OYMWMYN24c06dPZ+7cuQQHB9vetE2dOpW3336badOm0alTJzw8PBg/fjz5+fkVUqrVar3gD2vnbn/hhRe48847+e677/j+++95/vnnWbhwIcOGDeO+++5j4MCBfPfdd6xYsYIpU6YwdepUHnnkkQqpT2ohfW/a/PjjjyQkJDB8+PAS2y0WCytWrGDQoEF/udLW363C5eBg/Ibdes4yNwUFBRc89vxw6oknnuDHH3/kzTffpGXLlri5uXHLLbfY7q8sK4Ddd999jBgxgrfffpu5c+cyfPhw3N3L9zUQkcqRnlPAqn3JRO86zuq9J8jMK7Ttc3VyoE+rBlzbLoB+bRvSwNPFjpWKvSjkuQROZgd6NK/P6n0n2BSbqpBHRKQimUxlnpZhb7fddhuPPfYYn3/+OR9//DH333+/LWBZu3YtQ4YM4e677wagqKiI/fv3065duwq5dvv27YmPj+fIkSO20Ty7du0iPT29xDVat25N69atefzxx7njjjuYO3cuw4YNAyAoKIixY8cyduxYJk6cyIcffqiQRy5O35s2s2fP5vbbb+eZZ54psf3VV19l9uzZDBo0iM6dO/Pxxx9TUFBQajSPp6cnzZs356effrJNKTtXgwYNAEhMTKRr164AJZow/5W1a9cyatQo2/d5VlYWhw4dsu3v1KkTRUVFrF692jZd63zXX389Hh4ezJw5k++//541a9aU6doiUjniU3Ns/XW2HErDUnQ2APav50L/dg3p3y6A3q38cXXSMud1nUKeSxQR6sfqfSfYGJvK6N7qyyMiUhfVq1eP4cOH8/TTT5Oens6oUaNs+1q2bMmSJUvYsGEDvr6+vPXWWyQlJZU75LFYLKXe3Dk7O9O/f386d+7MXXfdxbRp02yNl/v27Uv37t05ffo0TzzxBLfccgshISEcPXqUX3/9lZtvvhmA8ePHM2jQIFq3bs3Jkyf5+eefKyyAErG3yvzePHHiBP/73//45ptv6NixY4l999xzDzfccAMnTpxg3LhxvPfee9x+++1MnDgRb29vNm3aRM+ePWnTpg0vvPACY8eOpWHDhgwaNIjMzEzWr1/PI488gpubGxEREbz66qs0b96clJQUnn322TLV17JlS5YuXcrgwYMxmUxMmjSJoqKzDVebN2/OPffcw+jRo22Nlw8fPkxycjK33XYbAGazmVGjRjFx4kRatmxJZGRkma4tIhWjqMjK7wnpRO9KYuWuZPYeL7mqc+uAevRvF8C17QO4QqtgyXkU8lyiM315tqgvj4hInTZmzBhmz57NgAEDbCvXAEyaNIm4uDgGDhyIu7s7DzzwAEOHDiU9Pf0vzlZaVlaW7Tf5ZwQHB3Po0CG++uorHnnkEa688kocHBy47rrreO+99wDjTVpqaiojR47k+PHj+Pv7c9NNNzF58mTACI8efvhhjh49ipeXF9dddx1vv/32Zf5tiFQflfW9OX/+fDw8PC7YT6dfv354enryySefMGHCBH7++WeeeOIJ+vbti9lspkuXLkRFRQFGIJSbm8vbb7/Nv//9b/z9/bnlllts55ozZw6jR4+me/futGnThtdff50BAwb8bX1vv/02o0ePplevXvj7+/Pkk0+SkZFR4piZM2fy9NNP89BDD5GamkqzZs14+umnS/39vfLKK4wePbpMfy8icnlyCyysP5DCyt1Gf50TmXm2fWYHEz2a+3Jt+0b0b9eQYL+aMapS7MNkPXeybw2WkZGBt7c36enpeHlV/vSpQksRV0xeQXa+hW8f6U3HJt6Vfk0RkdooNzeXuLg4QkJCcHV1tXc5UkH+6uta1a/ZcnEX+1ro+1LWr1/PVVddxdGjRwkICKjQc+vfl4ghJSuPn/cks3LXcdbuT+F0gcW2r56LI33bGP11rmrTAB93ZztWKtVBWX9+0kieS+RodqBHSH1W7TX68ijkEREREZGaLi8vjyNHjjBp0iRuu+22Cg94ROoyq9XKwRPZtmXOf4s/yblDLhp7u9K/eJnziFA/nB21zLmUn0KeyxAZ6lcc8qRxX59Qe5cjIiIiInJZFixYwJgxY+jSpQuffPKJvcsRqRUOJGfxZcxRfvwzibiU7BL7OjbxsvXXaR/opWXO5bIp5LkMEaFGX57NcalYiqyY1ZdHRERERGqwUaNGlWhULSKXJjO3gG9/T+SLrUfYFn/Ktt3JbCKyhT/Xtg/gmrYNaezjZr8ipVZSyHMZOjT2wtPFkczcQnYnZmjKloiIiIiISB1VVGRlU2wqi2OO8v0fieQWGCvbmR1MXNW6AcO6NaFv6wZ4ujrZuVKpzRTyXIYzfXl+3pPMxoPqyyMiIiIiIlLXHEnL4cuYo3wZc5SEU6dt21s2rMetYU0Z1rUJDb3UZFyqhkKeyxQZ6sfPe5LZFJvK/VeqL4+IyKWqJYs9SrGioiJ7lyAVQF9HqQz6dyW1wel8C9//kcjirUfZGJtq2+7p4sjgLo25NawpXYJ81GNHqpxCnst0pi/Plrg0Ci1FOJrVAV1EpDycnJwwmUycOHGCBg0a6IehGs5qtZKfn8+JEydwcHDA2VlLvtZEzs7OODg4cOzYMRo0aICzs7O+N+Wy6f8HqemsViu/xZ9k8dajfPt7Ill5hQCYTBDVwp9buzdlYIdGuDqZ7Vyp1GUKeS5T+8ZeeLoafXl2JWbQuamPvUsSEalRzGYzTZs25ejRoxw6dMje5UgFcXd3p1mzZjg46JcfNZGDgwMhISEkJiZy7Ngxe5cjtYz+f5Ca5nhGLkt+M6ZjxZ44uzpWs/ru3BLWlJvDmtJEDZSlmlDIc5nMDibCQ+qzcrcxZUshj4hI+dWrV49WrVpRUFBg71KkApjNZhwdHTXyo4ZzdnamWbNmFBYWYrFY7F2O1BL6/0FqirxCCyt3JbM45ghr9p2gqHhWuZuTmes7BXJr96b0bF4fB62wLNWMQp4KEBHqx8rdRvPlB65sYe9yRERqJLPZjNms4c0i1YnJZMLJyQknJ60EIyK1n9Vq5c9jGSzeeoSvdxzjVM7ZXz71aO7LrWFBXN85kHouehst1Zf+dVaAM315fj10Un15REREREREapDUrDy+2n6MxVuPsCcp07a9kZcrN4c14ZawIEL8PexYoUjZKeSpAO0CvfBydSQjt5A/jmXQJcjH3iWJiIiIiIjIRRRaili19wSLY47w855kCizGfCxnRwcGtA/glrCm9GnVALOmY0kNo5CnApgdTISH+hG96zibYlMV8oiIiIiIiFRD+49nsjjmKEt/SyAlK8+2vVMTb27t3pR/XNEYH3et/CY11yXNK5oxYwYhISG4uroSFhbG2rVry/S89evX4+joSJcuXUpsnzdvHiaTqdQjNzf3UsqzizNTtjYeTLVzJSIiIiIiInJG+ukCPt10mCHT13Pt22uYtSaWlKw8/DycGdM7hB/G9+F/j/RmZGRzBTxS45V7JM+iRYsYP348M2bMICoqig8++IBBgwaxa9cumjVrdtHnpaenM3LkSK655hqOHz9ear+Xlxd79+4tsc3V1bW85dlNZHHIs/VQGgWWIpzUl0dERERERMQuioqsrD+YwuKtR/nxzyTyCosAYxZGvzYNubV7U65u21Dv26TWKXfI89ZbbzFmzBjuu+8+AKZNm8aPP/7IzJkzmTJlykWf9+CDD3LnnXdiNpv56quvSu03mUw0atSovOVUG20beeLt5kT66QJ2JqTTrZmvvUsSERERERGpUw6nZvNlzFGWxBzlWPrZmSGtA+pxa1gQQ7s2oYGnix0rFKlc5Qp58vPziYmJ4amnniqxfcCAAWzYsOGiz5s7dy4HDx7k008/5eWXX77gMVlZWQQHB2OxWOjSpQsvvfQSXbt2veg58/LyyMs7O4cyIyOjPLdS4RwcTISH1GdFcV8ehTwiIiIiIiKV73S+he92JrJ46xE2x6XZtnu5OvKPLo25NSyIzk29MZnURFlqv3KFPCkpKVgsFgICAkpsDwgIICkp6YLP2b9/P0899RRr167F0fHCl2vbti3z5s2jU6dOZGRk8M477xAVFcWOHTto1arVBZ8zZcoUJk+eXJ7yK11kC7/ikCeNh66ydzUiIiIiIiK11+l8C59uOswHaw6SkpUPgMkEvVv6c2v3IAa0D8DVyWznKkWq1iWtrnV+Amq1Wi+YilosFu68804mT55M69atL3q+iIgIIiIibJ9HRUXRrVs33nvvPd59990LPmfixIlMmDDB9nlGRgZBQUHlvZUKFaG+PCIiIiIiIpXqdL6FzzYf5v9Wnw13mvq6cXuPIG7q1pTGPm52rlDEfsoV8vj7+2M2m0uN2klOTi41ugcgMzOTrVu3sm3bNsaNGwdAUVERVqsVR0dHVqxYwdVXX13qeQ4ODvTo0YP9+/dftBYXFxdcXKrXXMo2AZ74ujtxMqeA34+mExasKVsiIiIiIiIV4Wy4E2tb/jyovhuP9GvFsG5N9Et2EcoZ8jg7OxMWFkZ0dDTDhg2zbY+OjmbIkCGljvfy8mLnzp0lts2YMYOff/6ZL7/8kpCQkAtex2q1sn37djp16lSe8uzO6Mvjxw9/JrEpNlUhj4iIiIiIyGXKLTCmZZ0b7jT1deORq1tyU7emCndEzlHu6VoTJkxgxIgRdO/encjISGbNmkV8fDxjx44FjGlUCQkJzJ8/HwcHBzp27Fji+Q0bNsTV1bXE9smTJxMREUGrVq3IyMjg3XffZfv27UyfPv0yb6/qRbY4G/I83K+lvcsRERERERGpkXILLHy2OZ7/W32QE5lGuNPExwh3bg5TuCNyIeUOeYYPH05qaiovvvgiiYmJdOzYkeXLlxMcHAxAYmIi8fHx5TrnqVOneOCBB0hKSsLb25uuXbuyZs0aevbsWd7y7O5sX56T5BcW4eyo/3hERERERETKKrfAwueb45l5gXDnpm5N9R5L5C+YrFar1d5FVISMjAy8vb1JT0/Hy8vLbnUUFVnp/t+VpGXn8+XYSLo3r2+3WkRERKqj6vKaLfpaiEj1kltgYcGWeGauOkjyOeHOuKtbcrPCHanjyvqafUmra8nFOTiYiAitz/KdxpQthTwiIiIiIiIXl1tgYeGWeGacF+483K8lt4Qp3BEpD4U8lSAi1I/lO5PYGJvKuKtb2bscERERERGRaudMuDNz9UGOZxjhTmNvVx6+uiW3hgUp3BG5BAp5KkFkcV+emMMnySu04OJotnNFIiIiIiIi1UNugYVFvx5hxqoDpcKdW8Ka6v2TyGVQNFoJWjash389Z3ILithxJN3e5YiIiEg1MGPGDEJCQnB1dSUsLIy1a9f+5fHTp0+nXbt2uLm50aZNG+bPn3/RYxcuXIjJZGLo0KEVXLWISMXJLbAwf+MhrnpjFc9/8yfHM/II9Hbl5aEd+eWJq7grPFgBj8hl0kieSmAymQgP9eO73xPZFJtKzxD15REREanLFi1axPjx45kxYwZRUVF88MEHDBo0iF27dtGsWbNSx8+cOZOJEyfy4Ycf0qNHD7Zs2cL999+Pr68vgwcPLnHs4cOH+fe//02fPn2q6nZERMolr9DCF78eYfovB0nKyAUg0NuVh/q15LbuGrkjUpG0ulYl+WTTYSZ99QeRoX4seCDC3uWIiIhUG9XtNbsqhIeH061bN2bOnGnb1q5dO4YOHcqUKVNKHd+rVy+ioqJ44403bNvGjx/P1q1bWbdunW2bxWKhb9++3Hvvvaxdu5ZTp07x1VdfXbSOvLw88vLybJ9nZGQQFBRUp74WIlJ1zoQ7M1YdJDHdCHcaebnycL8W3NYjSOGOSDlodS07iww1Ru/8Fn+S3AILrk76D0xERKQuys/PJyYmhqeeeqrE9gEDBrBhw4YLPicvLw9XV9cS29zc3NiyZQsFBQU4OTkB8OKLL9KgQQPGjBnzt9O/AKZMmcLkyZMv8U5ERMomr9DCF1uPMuOXAyXCnYf6tWC4wh2RSqWQp5K0aFAP/3oupGTlsePIKcKLmzGLiIhI3ZKSkoLFYiEgIKDE9oCAAJKSki74nIEDB/LRRx8xdOhQunXrRkxMDHPmzKGgoICUlBQCAwNZv349s2fPZvv27WWuZeLEiUyYMMH2+ZmRPCIiFSGv0MLi4nDnWHG4E+DlwsP9WnJb9yD94lukCijkqSQmk4mI0Pp8+3siG2NTFfKIiIjUcSaTqcTnVqu11LYzJk2aRFJSEhEREVitVgICAhg1ahSvv/46ZrOZzMxM7r77bj788EP8/f3LXIOLiwsuLi6XdR8iIufLLyxiccwRpv9cMtx56KqWDO+hcEekKinkqUSRLfz4trj5soiIiNRN/v7+mM3mUqN2kpOTS43uOcPNzY05c+bwwQcfcPz4cQIDA5k1axaenp74+/vz+++/c+jQoRJNmIuKigBwdHRk7969tGjRovJuSkQEI9z5MuYo0385QMKp0wA09HThoatacHvPZgp3ROxAIU8liigevfNb/Cn15REREamjnJ2dCQsLIzo6mmHDhtm2R0dHM2TIkL98rpOTE02bNgWMZdJvvPFGHBwcaNu2LTt37ixx7LPPPktmZibvvPOOpmCJSKW6WLjzz6tacIfCHRG7UshTiUL9PWjo6UJyZh7b4k8R2UJTtkREROqiCRMmMGLECLp3705kZCSzZs0iPj6esWPHAkavnISEBObPnw/Avn372LJlC+Hh4Zw8eZK33nqLP/74g48//hgAV1dXOnbsWOIaPj4+AKW2i4hUlPzCIpb8dpT3fz4b7jQoHrmjcEekelDIU4mMvjx+fLPjGBtjUxXyiIiI1FHDhw8nNTWVF198kcTERDp27Mjy5csJDg4GIDExkfj4eNvxFouFqVOnsnfvXpycnOjXrx8bNmygefPmdroDEanLCixFLIk5yvu/HODoybPhzj/7tuDOcIU7ItWJyWq1Wu1dREUo65rxVe3zzfE8vWwnPUPq88WDkfYuR0RExO6q62t2XaSvhYhcTG6BhZjDJ1mz/wTf/Z5oC3f86xnTsu5SuCNSpcr6mq2RPJXszOid7erLIyIiIiIi1ZTVamVPUibr9qewZv8JtsSlkVdYZNvvX8+FsX1DuSs8GDdnvacRqa4U8lSy5n7uBHi5cDwjj98On6RXy7IvcyoiIiIiIlJZkjNyWbs/hXUHjMeJzLwS+xt6utC7lT9XtmrAwA6NFO6I1AAKeSqZyWQiMtSPr7YfY1NsqkIeERERERGxi9P5FjbHpRrBzv4U9h7PLLHfzclMeGh9erf058rWDWjVsB4mk8lO1YrIpVDIUwUiikOejbGp9i5FRERERETqiKIiK38ey2DtgROs25/C1kMnybecnYJlMkHHxt70aeVP71b+hAX74uKo0ToiNZlCnipg68tz5BSn8y0a5igiIiIiIpXi2KnTtr46Gw6mkpadX2J/Ex83erf0p09rf3q18Ke+h7OdKhWRyqCQpwo0q+9OoLcriem5xBw+Se9WmrIlIiIiIiKXLyuvkE0HU1l3wAh2Yk9kl9hfz8WRiFA/+rTyp08rf0L8PTQFS6QWU8hTBUwmExGhfizblsCm2FSFPCIiIiIickksRVZ+P3rK1lfnt/iTFBZZbfsdTHBFkA99WjWgTyt/ugT54GR2sGPFIlKVFPJUkcjikEd9eUREREREpDziU3NYe+AEa/elsOFgChm5hSX2B/u5G1OwWjUgsoUf3m5OdqpUROxNIU8ViQg1+vLsOHKKnPxC3J31Vy8iIiIiIqWlny5g48EU2/Lmh1NzSuz3cnUkqqXRLLlPywY083O3U6UiUt0oaagiQfXdaOLjRsKp08QcPkmfVg3sXZKIiIiIiFQDBZYith85xdp9J1h7IIUdR05xzgwsHB1MdGvma1sFq3NTH8wO6qsjIqUp5KkiJpOJ8ND6LP0tgY0HUxXyiIiIiIjUcQeSs3grei9r9qWQlVdyClaLBh62vjrhoX7Uc9FbNxH5e/qfogpFhvqx9Dej+bKIiIiIiNRNuQUWZqw6yMxVByiwGEN2fN2d6N2qAX2Kp2E19nGzc5UiUhMp5KlCZ/ry/H40ney8QjyUxouIiIiI1CkbDqbw7LI/iE0xljrv16YBj1/bmo6NvXHQFCwRuUxKGapQUH13W1+erYdP0re1pmyJiIiIiNQFadn5/Pe73Sz57SgADT1deOEfHRjUsREmk8IdEakYDvYuoK6JbGGM5tl4UFO2RERERERqO6vVyuKtR7hm6iqW/HYUkwlGRASz8l99ub5ToAIeEalQGslTxSJC/fgy5qj68oiIiIiI1HIHT2Tx9NKdbI5LA6BtI0+m3NSJrs187VyZiNRWCnmqWERofQB2JqSTlVeoLvkiIiIiIrVMXqGFGb8cZOaqg+RbinB1cuDx/q0Z3TsEJ7MmU4hI5VHCUMWa+roTVN+NI2mn+fVQGv3aNLR3SSIiIiIiUkE2HkzlmWU7bY2Vr2rTgJeGdCSovrudKxORuuCSYuQZM2YQEhKCq6srYWFhrF27tkzPW79+PY6OjnTp0qXUviVLltC+fXtcXFxo3749y5Ytu5TSaoTI4lW2NGVLRERERKR2SMvO59+Ld3DHh5uITcmmgacL0+/sxtxRPRTwiEiVKXfIs2jRIsaPH88zzzzDtm3b6NOnD4MGDSI+Pv4vn5eens7IkSO55pprSu3buHEjw4cPZ8SIEezYsYMRI0Zw2223sXnz5vKWVyOcWUp9k5ovi4iIiIjUaFarlS9jjnLN1FV8GXNOY+UJfbmhsxori0jVMlmtVmt5nhAeHk63bt2YOXOmbVu7du0YOnQoU6ZMuejzbr/9dlq1aoXZbOarr75i+/bttn3Dhw8nIyOD77//3rbtuuuuw9fXlwULFpSproyMDLy9vUlPT8fLy6s8t1Tljp06Ta9Xf8bBBDueH4Cnq5O9SxIREakyNek1u7bT10Lk8hw8kcUzy3ayKfZsY+VXbupENzVWFpEKVtbX7HKN5MnPzycmJoYBAwaU2D5gwAA2bNhw0efNnTuXgwcP8vzzz19w/8aNG0udc+DAgX95zry8PDIyMko8aorGPm4E+7lTZIVfD6XZuxwRERERESmHvEIL76zcz6Bpa9kUm4arkwNPDWrL/x7prYBHROyqXI2XU1JSsFgsBAQElNgeEBBAUlLSBZ+zf/9+nnrqKdauXYuj44Uvl5SUVK5zAkyZMoXJkyeXp/xqJSLEj8OpOWyKTePqtgF//wQREREREbG7TbGpPL1sJ7EnjMbKfVs34OWhaqwsItXDJa2udf68UqvVesG5phaLhTvvvJPJkyfTunXrCjnnGRMnTmTChAm2zzMyMggKCipL+dVCZAs/Fm09wkb15RERERERqfZOZufzyvLdLI45CoB/PReeH9yeG9V3R6R2slrBkg8FOZCfAwWnjY9tj9PF28/syy7+8zRccTs06mSXsssV8vj7+2M2m0uNsElOTi41EgcgMzOTrVu3sm3bNsaNGwdAUVERVqsVR0dHVqxYwdVXX02jRo3KfM4zXFxccHFxKU/51cqZ5st/Hksn/XQB3m7qyyMiIiIiUt1YrVaW/pbAf5fvJi07H4C7wpvxn+va6md4EXuyFJwTwJwfwpyG/HNCF1sAc35g8zfPsRZdWm2Nu9aMkMfZ2ZmwsDCio6MZNmyYbXt0dDRDhgwpdbyXlxc7d+4ssW3GjBn8/PPPfPnll4SEhAAQGRlJdHQ0jz/+uO24FStW0KtXr3LdTE3SyNuVEH8P4lKy2XoojWvaacqWiIiIiEh1Ensii2e/+oMNxaPv2wQYjZXDgtV3R6RCFRXB6TTIOg5ZyZB9wvgz6/jZj7OTITu1OIjJhqLCqqvPwQmc3cHJHZzcwMmj+E83cD7n4zPb/VtVXW3nKfd0rQkTJjBixAi6d+9OZGQks2bNIj4+nrFjxwLGNKqEhATmz5+Pg4MDHTt2LPH8hg0b4urqWmL7Y489xpVXXslrr73GkCFD+Prrr1m5ciXr1q27zNur3iJC6xOXks3Gg6kKeUREREREqom8QgsfrI7l/V8OkF9YhKuTA49d05r7+oTgZC7X2jUidVeRBXLSjHAmK/lsUGMLcY5D1oni8CYFrJZLu47JwQhXnM8EMOeGMe7nhTPnfHyhcMZ2/HnHmmvOqL1yhzzDhw8nNTWVF198kcTERDp27Mjy5csJDg4GIDExkfj4+HKds1evXixcuJBnn32WSZMm0aJFCxYtWkR4eHh5y6tRIkL9WLDlCJvi1JdHRERERKQ62FzcWPlgcWPlK1s34OUhHWnmp8bKIrbgJut4cWBTHNKcG9jYgpsT5Z/u5O4HHg2hXoPiPwPO+bghePiDi1fJcMbsBOqLZWOyWq1WexdREcq6Znx1cjwjl/BXfsJkgu2TBuDtXnPSQRERkUtVE1+zayt9LUTOOpmdz5Tvd/PF1rONlZ8b3J7BaqwstV3BaSO4OZ12zjSp5LOBzblTpnJSLi+4qRdw8RDHw79GjZipamV9zb6k1bWkYgR4uRLq70FsSjZbDqVxbXtN2RIRERERqUpWq5Vl2xJ4+buzjZXvDG/Gk2qsLDVNkQVy088GNn/556mzHxeeLueFTOBe/+zomnoNLx7iKLipcgp57CyihR+xxX15FPKIiIiIiFSduJRsnv1qJ+sPGO0TWgfUY8pNnQgLrm/nyqTOy8+5SEBz0vjz9MnS+06fAi5xoo6DI7j5gkcD42ELbi4Q4rj7g1lRQnWlr4ydRYT68fnmeDbFqi+PiIiIiEhVyCu0MGt1LO8VN1Z2cXTgsf6tuK93KM6OaqwsFSwvq3jKU4oRzlx0dM05wU1h7qVfz9kT3H3Brb4x4ubcP918z9l2zjEuXuprU0so5LGziFDjtwS7kzI4lZOPj7uznSsSEREREam9tsSl8fSynRxIzgKgTyt/Xh7akWA/DztXJjWKpeCcFaLONB4+5+PMcz4vyL60azg4nhPQ+JYOZi4W4jjqPWVdppDHzhp6utKigQcHT2SzOS6NgR0a2bskEREREZFa51ROPlOW72HR1iMA+NdzZtKN7fnHFY3VWFkMVqsxmsYW2lwgvMlKhqwkyCnnTAwnd6M/zV8FNOcHOC6eGl0j5aaQpxqIbOHHwRPZbIpNVcgjIiIiIlKBrFYrX28/xkvf7iK1uLHyHT2b8dR1bbW6bV1RcPq8wOb80OacPy35ZT+vyXy2Z029gHP+PP/jAHCpV3n3J3IOhTzVQESoH59uimfjQfXlERERERGpKHEp2Uz66g/WHUgBoFVDo7Fy9+ZqrFxrFBVB8i5I+h0yky4c3uSll++crt5Qr9FFQptztrn7gYN6OEn1opCnGggP8QNgT1ImJ7Pz8fXQHEoRERERkUt1IDmTGasO8vX2Y1iKrLg4OvDoNa24v48aK9cKaXEQtxpiV0PcGshJ+fvnmF3AM+CvQ5szq0g5uVb+PYhUEoU81UADTxdaNazH/uQsNselcl3HQHuXJCIiIiJS4+w8ms70Xw7w464krMUrSV/VpgEvDO5Ac/9q2FjZUgDHtoGrD/i11KiQi8k6YYQ6cashdhWcii+538kdmnYHr6YXD29cvdXfRuoEhTzVRESoH/uTs9gUm6aQR0REpBaaMWMGb7zxBomJiXTo0IFp06bRp0+fix4/ffp03n//fQ4dOkSzZs145plnGDlypG3/hx9+yPz58/njjz8ACAsL45VXXqFnz56Vfi8i1YnVamVLXBrTVx1kzb4Ttu0DOwTw0FUtuSLIx37FXcjpk7B/JexdDgd+OjuVyMUbmnSFJmHFj+7GyJO6KC8TDm8wAp3Y1ZD8Z8n9Do7QtAeE9IXQvsbflVaUEgEU8lQbkS38+GTTYTbFqi+PiIhIbbNo0SLGjx/PjBkziIqK4oMPPmDQoEHs2rWLZs2alTp+5syZTJw4kQ8//JAePXqwZcsW7r//fnx9fRk8eDAAq1at4o477qBXr164urry+uuvM2DAAP7880+aNGlS1bcoUuWsViur9p5g+i8H2Hr4JABmBxP/uKIx/7yqBa0DPO1c4TlSD8Le72HfD0Z4YbWc3edWHwpyjLAndpXxOMOrKTTpZoQ+TbtDYJfa2cC3MA+O/lo8/Wo1JMRAUWHJYwI6GYFOSF8I7lU7/x5EKoDJaj0zkLFmy8jIwNvbm/T0dLy8vOxdTrmlZuUR9vJKAGKe7Y9fPRc7VyQiIlI5avpr9qUIDw+nW7duzJw507atXbt2DB06lClTppQ6vlevXkRFRfHGG2/Yto0fP56tW7eybt26C17DYrHg6+vL+++/X2LEz1+pi18LqfksRVa+/yOR6b8cZHdiBgDOZgdu7d6UB69sQTM/dztXCBRZ4MgW2Pe9Ee6k7Cu5v2F7aH0dtLneCHCsFkjebYQbCVsh4Tfjc857q2ZygAZti4Of7sZzG7YHcw373X1RkdEo+cz0q8MbofB0yWN8m0PoVUaoE3Klsfy4SB1W1tfsGva/Qe3lV8+FNgGe7D2eyZa4NAZ10pQtERGR2iA/P5+YmBieeuqpEtsHDBjAhg0bLvicvLw8XF1LNv50c3Njy5YtFBQU4ORUetnnnJwcCgoKqF//4qsG5eXlkZeXZ/s8IyOjPLciYlf5hUV8tT2B/1t1kNiUbADcnc3cHRHMfb1DaOhl52a5eZlw8Gcj1Nm/AnLOGaHv4AjBUUao0+Y6I8AowQECOxuP7veePV/iDji6tTj8+Q0yjhorSSXvgm2fGsc5ukHgFcZInzOjfnyCq1f/GavVGM0Ut8oYrXNorTFt7VweDc5OvwrpC77BdilVpKZTyFONRITWZ+/xTDbGpirkERERqSVSUlKwWCwEBJTsrREQEEBSUtIFnzNw4EA++ugjhg4dSrdu3YiJiWHOnDkUFBSQkpJCYGDpnxOeeuopmjRpQv/+/S9ay5QpU5g8efLl3ZBIFTudb2HRr/HMWhPLsfRcALzdnLg3qjn3RDa378q0p44YU7D2fm8EF5b8s/tcfaDVACPUadnfaPxbHi6e0Ly38TgjM6k48Ik5G/zkZcCRTcbjDHf/c3r7hBnhj3sVLxufmXR2+lXsaiOgOpezJzSPOjtap2G76hVMidRQCnmqkYhQPz7eqL48IiIitZHpvDcvVqu11LYzJk2aRFJSEhEREVitVgICAhg1ahSvv/46ZrO51PGvv/46CxYsYNWqVaVGAJ1r4sSJTJgwwfZ5RkYGQUFBl3hHIpUrI7eATzYeZs66OFKzjfCkgacLD/QJ5Y7wZtRzscNbmaIiSNwGe4uDneM7S+6v3wLaDDIeQREVP43KsxG0vcF4nKkn9UDJ4Cdpp7Gk+P4fjYetttCSwU+jTuDkVnG1nT4Fh9adDXVS9pbcb3aGoPCzo3Uad6t508xEagB9V1Uj4aF+AOw7nkVKVh7+6ssjIiJS4/n7+2M2m0uN2klOTi41uucMNzc35syZwwcffMDx48cJDAxk1qxZeHp64u9fsi/Fm2++ySuvvMLKlSvp3LnzX9bi4uKCi4t+vpDqLTUrjznr45i/4TCZeUbz3aa+bozt24Jbwpri6lQ66KxUBaeN0GLvctj3I2Sd871scjCCizaDjKlY/q2qtjYHB2jQ2nh0uaO43lw4/sfZ0OfoVkg7CGmxxmPn4uLnOkJAx5LBj3/rsi/jXpBrjB46M1rn2DawFp1zgMmYRnZm+lWzSHCuBv2SRGo5hTzVSH0PZ9o28mRPUiabY9O4obOmbImIiNR0zs7OhIWFER0dzbBhw2zbo6OjGTJkyF8+18nJiaZNmwKwcOFCbrzxRhzOeQP2xhtv8PLLL/Pjjz/SvXv3yrkBkSpy7NRpPlwby4It8eQWGGFBq4b1eKhfCwZ3boyjuYzhQ0XIPG5Mw9r3Axz8pWRTYOd60PIaaD3ImI7l4Vd1dZWFk6vRn6fpOf8n5KQZIUzCb0Zj56NbjdE+iduNx9bZxnHOnqWXcfcqfk9SZIFj2yH2FyPUid8MlryS1/ZreXb6VfPeVT9FTEQU8lQ3EaF+7EnKZGNsikIeERGRWmLChAmMGDGC7t27ExkZyaxZs4iPj2fs2LGAMY0qISGB+fPnA7Bv3z62bNlCeHg4J0+e5K233uKPP/7g448/tp3z9ddfZ9KkSXz++ec0b97cNlKoXr161KunpYWl5ohLyeb/Vh1k6bajFFiM1aQ6N/Xm4X4tubZdAA4OVdCnxWqF43+eXQ0rIabkfu8gY7RO6+uM8MKxho2Ic69vBFMtrzE+t1oh/cjZkT4JvxlhT34mxK0xHmd4Nga/FpD4u7HM+7k8A0s2S/ZuUmW3JCIXppCnmokI9WPehkNsik2zdykiIiJSQYYPH05qaiovvvgiiYmJdOzYkeXLlxMcbKwek5iYSHx8vO14i8XC1KlT2bt3L05OTvTr148NGzbQvHlz2zEzZswgPz+fW265pcS1nn/+eV544YWquC2Ry7LrWAYzVh1g+c5EiopXCo8Irc+4fq2Iaul30Z5VFaYwHw6vM0KdvT9AenzJ/U3CjNE6bQZBQIfa1RTYZAKfZsajQ/EIQ0shnNhTvIR7cVPn5F2Qecx4gNE8unmfs6N1/FvVrr8XkVrAZLVarfYuoiKUdc346u5UTj5dX4rGaoVfn+lPA88a9lsCERGRv1FbXrNrA30txB5iDqcx/ZeD/Lwn2bbtmrYNeahfC8KCK3l6T06asbz53uVw4Gdj5MoZjm5GeNFmELQeaDQ5ruvys40pWqkHoFFHCOwCDlXcE0lEgLK/ZmskTzXj4+5M20Ze7E7MYFNsKoOvaGzvkkRERERELovVamXdgRTe//kAm+OMEesOJrihc2P+2bcF7RtXYsiYsr94tM73RqPgc5sD1wswpmC1GWSMTFFj4JKcPYxlzptH2bsSESkjhTzVUERofYU8IiIiIlLjFRVZWbHrODNWHeD3o0Y/FyeziZu7NeXBvi0I8feo+IsW5MLh9bA/2hi1k3aw5P6ATtCmONgJ7Fr21aRERGoAhTzVUGSoH3PXH2JjbKq9SxERERERKbcCSxH/23GMGasOciA5CwBXJwfu7BnM/VeGEOjtVrEXPHXECHT2RxsrPxXknN3n4AQhfYwlzlsPNPrQiIjUUgp5qqHwED9MJog9kU1yRi4NvVztXZKIiIiIyN/KLbCwOOYoH6w+yNGTxrLjnq6O3BPZnHujmuNXr4L6TVoKIH7T2WDnxO6S+z0DodW1xhLnIX3BVT2nRKRuUMhTDXm7O9E+0Is/j2WwMTaVIV20FKGIiIiIVF9ZeYV8vvkwH66N40RmHgB+Hs6M6RPC3RHBeLk6Xf5FMpPOTsGKXQV5GWf3mRwgKPxssBPQUas+iUidpJCnmooI9ePPYxlsik1TyCMiIiIi1dLJ7HzmbTjEvA2HSD9dAEBjb1ce7NuC27oH4eZ8GSsxFVng6Nbi0TorIOn3kvvd/YtDnWshtB+4V/LKXCIiNYBCnmoqMtSP2evi2Ky+PCIiIiJSzRQVWZm5+iDTfzlATr4FgFB/D/55VQuGdGmCs+MlNjPOToEDP8GBaDiwEk6fPGenCZp0M0bqtLpWTZNFRC5AIU811SOkvtGXJyWb4xm5BKgvj4iIiIhUA2nZ+YxftJ01+04A0KGxFw/3a8nADo0wO5RzilRRESTtMKZh7fsREmIA69n9rt7Qsr8R7LS4Buo1qLgbERGphRTyVFPebk50aOzFHwnGUuqasiUiIiIi9rYt/iQPf/Ybx9JzcXVy4KUhHbklrCmm8vS/OX0KYn8p7q8TDdnJJfcHdILWA4xgp0l3MOsti4hIWel/zGosMtSPPxIy2HhQIY+IiIiI2I/VauXjDYf47/LdFFishPh7MPPubrRtVIZVq6xWSN51diWs+E1gtZzd71wPQq86Ow3Lq3Gl3YeISG2nkKcaiwj148O1cWxSXx4RERERsZOsvEKeWvI73/6eCMD1nRrx2s2d8fyrFbPysiBu9dlgJyOh5H7/NmdXwmoWCY7OlXgHIiJ1h0KeaqxHSH0cTHAoNYfE9NMEervZuyQRERERqUP2Hc9k7KcxxJ7IxtHBxNPXt+PeqOalp2dZrZB64OxKWIc3gCX/7H5HNwi58uxqWL7Nq/Q+RETqiktqRz9jxgxCQkJwdXUlLCyMtWvXXvTYdevWERUVhZ+fH25ubrRt25a33367xDHz5s3DZDKVeuTm5l5KebWGl6sTHZt4A2g0j4iIiIhUqWXbjjLk/fXEnsgm0NuVRQ9GMrp3yNmApyDXGKWz/Al4twu83x1+fBpiVxkBj29z6Pkg3LUEnoyDu76Anvcr4BERqUTlHsmzaNEixo8fz4wZM4iKiuKDDz5g0KBB7Nq1i2bNmpU63sPDg3HjxtG5c2c8PDxYt24dDz74IB4eHjzwwAO247y8vNi7d2+J57q6akWpyFA/fj+azsaDqQzr2tTe5YiIiIhILZdbYOHFb3fx+eZ4APq08mfa8C741XMxVsOK3wC/L4I/v4a89LNPNDtDcFRxb50B4NcCytOQWURELlu5Q5633nqLMWPGcN999wEwbdo0fvzxR2bOnMmUKVNKHd+1a1e6du1q+7x58+YsXbqUtWvXlgh5TCYTjRo1upR7qNUiQv34YE0sm2LT7F2KiIiIiNRyR9JyeOiz39iZkI7JBI9e3YpHr2mFOWUPbFoEvy+GjKNnn+AZCK0HQquBxnQsl3r2K15ERMoX8uTn5xMTE8NTTz1VYvuAAQPYsGFDmc6xbds2NmzYwMsvv1xie1ZWFsHBwVgsFrp06cJLL71UIhw6X15eHnl5ebbPMzIyynEnNUf35r6YHUzEp+WQcOo0TXzUl0dEREREKt7KXceZ8MV2MnIL8XV3YsY/GhOZ8yPMGg1JO88e6OIF7YdA5+HGyB2HS+oAISIilaBcIU9KSgoWi4WAgIAS2wMCAkhKSvrL5zZt2pQTJ05QWFjICy+8YBsJBNC2bVvmzZtHp06dyMjI4J133iEqKoodO3bQqlWrC55vypQpTJ48uTzl10iexX15dhw5xaaDqdwcpilbIiIiIlJxCi1FTI3ex8xVB/HgNOMb7GKs71Zcv14L1iLjIAcnYwpW59ug9XXgpLYKIiLV0SWtrnV+N32r1Vq6w/551q5dS1ZWFps2beKpp56iZcuW3HHHHQBEREQQERFhOzYqKopu3brx3nvv8e67717wfBMnTmTChAm2zzMyMggKCrqU26n2IkLrGyFPrEIeEREREak4yZm5PP75rzgdXs07Tuu53jEGp8w8yCw+ICjcGLHTYRi417drrSIi8vfKFfL4+/tjNptLjdpJTk4uNbrnfCEhIQB06tSJ48eP88ILL9hCnvM5ODjQo0cP9u/ff9Hzubi44OLiUp7ya6zIUD8+WB3LRq2wJSIiIiIVwWrlj19/4c8fPuQdyzr8nYtbH1gBv5ZGsNPpVqgfYtcyRUSkfMoV8jg7OxMWFkZ0dDTDhg2zbY+OjmbIkCFlPo/Vai3RT+dC+7dv306nTp3KU16t1b15fcwOJo6ePM2RtByC6rvbuyQRERERqYnS4rD+/gXpmz+j4+nDdAQwQaGbH46dbzWmYzXuplWxRERqqHJP15owYQIjRoyge/fuREZGMmvWLOLj4xk7dixgTKNKSEhg/vz5AEyfPp1mzZrRtm1bANatW8ebb77JI488Yjvn5MmTiYiIoFWrVmRkZPDuu++yfft2pk+fXhH3WOPVc3Gkc1NvtsUbU7YU8oiIiIhImeWkwZ9L4fcv4MhmTIAPcNrqzC7vK+kw6H5cW18DZic7FyoiIper3CHP8OHDSU1N5cUXXyQxMZGOHTuyfPlygoODAUhMTCQ+Pt52fFFRERMnTiQuLg5HR0datGjBq6++yoMPPmg75tSpUzzwwAMkJSXh7e1N165dWbNmDT179qyAW6wdIkL9ikOeNG7tXjt7D4mIiIhIBSnIhX0/wO+LYH80FBUAYMGB9ZYOfGvtQ/dBI7m1V9u/7a0pIiI1h8lqtVrtXURFyMjIwNvbm/T0dLy8vOxdToVbve8E98zZQhMfN9Y/dbW9yxEREblktf01uybR16KWKSqCw+uNYGfX15CXYduV5tWOD052Z1lBBM6+jZl5VxidmnrbsVgRESmPsr5mX9LqWlL1ugf74uhgIuGU+vKIiIiIyDmO7zKCnZ2LISPh7HbvIAo63MLbSV2YscuYinVN24ZMve0KfNyd7VSsiIhUJoU8NYRHcV+e3+JPsVF9eURERETqtoxE+ONL2LEIju88u93FGzoMgc7DiXXvzEOfb2dPUiYOJvj3wDaMvbIFDg6aniUiUlsp5KlBIlv48Vv8KTYdTOU29eURERERqVvyMmH3/4xRO7GrMdY7BxycoPVAY2WsVgPByZXlOxP5z9yNZOUV4l/Phffu6EpkCz+7li8iIpVPIU8NEhHqx/RfDrIpNhWr1aomeSIiIiK1naUADv5sBDt7lkPh6bP7mkUawU77oeBeH4ACSxGvfruL2eviAOgZUp/37+hKQy9XOxQvIiJVTSFPDRIW7IuT2cSx9Fzi03II9vOwd0kiIiIiUtEK8yB+I+z5Dv5YCjkpZ/f5tYLOw6HTLVA/pMTTEtNPM+7zbcQcPgnAg31DeWJAGxzNDlVZvYiI2JFCnhrE3dmRK5r6sPXwSTbFpirkEREREakt0uLgwErjEbcGCnLO7vNoAB1vMUbtNO4KFxjNvXb/CR5buJ207Hw8XR2ZeusVDOjQqApvQEREqgOFPDVMZAu/4pAnjeE9mtm7HBERERG5FPk5xnLnB1bC/mhIO1hyf70AaNkfOtwEoVeB+cI/thcVWXnv5wNM+2kfViu0D/Ri5t3d9MtAEZE6SiFPDRMR6sd7Px9g40H15RERERGpMaxWSNl/drTO4fVQmHt2v4MjBEVAy2ug1bUQ0PGCI3bOlZadz/hF21mz7wQAd/QM4vnBHXB1MlfmnYiISDWmkKeG6dbM6MuTlJHL4dQcmvvrtzQiIiIi1VJepjH16kywcyq+5H6vptCqvzFiJ6QvuHqV+dTb4k/y8Ge/cSw9F1cnB14e2olbwppW8A2IiEhNo5CnhnFzNtM1yJcth9LYGJuqkEdERESkurBa4fifZ0Od+E1QVHB2v9kZgqOMUKfVteDf+m9H65S+hJWPNxziv8t3U2CxEuLvwYy7utEusOwBkYiI1F4KeWqgiND6bDmUxqbYVO7oqb48IiIiInZz+hTE/lIc7PwEmYkl9/uGGIFOy/7QvDc4X/ov6LLyCpm4dCf/23EMgOs7NeK1mzvj6ep0GTcgIiK1iUKev2O1Qm46uPnYuxKbiBZ+vKu+PCIiIiJVr6gIknbA/uLROkd/Bavl7H5HNwjpAy2vNfrr+LWokMvuO57JPz+N4eCJbBwdTEy8vh2jo5rr50ARESlBIc9fKbLAt+Ph6FYY9R2417d3RYDRl8fZ7EByZh5xKdmENqhn75JEREREaq/sFDj489nROjkpJff7tymegtUfmvUCJ9cKvfxX2xKYuHQnpwssNPJyZfpdXQkLrh4/l4qISPWikOevZCXDvhWQlQSf3wYjv76sIbYVxdXJTNdmPmyOM/ryKOQRERERqUBFFkiIMZY2P7ASjm0DrGf3O9czljVveY0R7vhUzvT53AILL327i882Gw2be7f0Z9rtXfCv51Ip1xMRkZpPIc9f8QqEEctg7iBjKO7Cu+DOReBo/xfWiFA/NselsSk2jbvCg+1djoiIiEjNlplkjNI5EA0Hf4HcUyX3B3Q6u7x5057g6Fyp5RxJy+Ghz35jZ0I6JhM8cnUrHrumFWYHTc8SEZGLc7B3AdVeQHu460tw8jCa6i19wPjtjp1FhPoBsCnW6MsjIiIi1duMGTMICQnB1dWVsLAw1q5d+5fHT58+nXbt2uHm5kabNm2YP39+qWOWLFlC+/btcXFxoX379ixbtqyyyq99LAVwaB2sfAFm9oapbeDrh+DPZUbA4+oNHYbBkOkwYQ/8cx1cO9lonlzJAc/Pe45z43vr2JmQjo+7E3NH9WDCta0V8IiIyN/SSJ6yCOoBt38Kn90Gu76Cb71h8DvlXvKyInVt5oOzowMnMvM4eCKblg01ZUtERKS6WrRoEePHj2fGjBlERUXxwQcfMGjQIHbt2kWzZqWn+sycOZOJEyfy4Ycf0qNHD7Zs2cL999+Pr68vgwcPBmDjxo0MHz6cl156iWHDhrFs2TJuu+021q1bR3h4eFXfYs1yaD18MQJyUs/ZaILGXY3pVy37Q5MwMFftj8qWIitvR+/j/V8OAHBFkA8z7upGEx+3Kq1DRERqLpO1lgwDycjIwNvbm/T0dLy8vCrnIn9+BV/eC9YiiBpv/DbHjm6ftZFNsWm8PLQjd0doypaIiNQMVfKaXc2Eh4fTrVs3Zs6cadvWrl07hg4dypQpU0od36tXL6KionjjjTds28aPH8/WrVtZt24dAMOHDycjI4Pvv//edsx1112Hr68vCxYsKFNddfFrQfwm+OQmKMgGd/+zfXVaXA0e/nYrKyUrj8cWbmP9ASN4GhkZzDM3tMPF0Wy3mkREpPoo62u2pmuVR4ehcOM04+P102DdNPvVAkSGGj+IbIxN/ZsjRURExF7y8/OJiYlhwIABJbYPGDCADRs2XPA5eXl5uLqWXKHJzc2NLVu2UFBQABgjec4/58CBAy96zjPnzcjIKPGoU478Cp/ebAQ8oVfB43/ATbOg8212DXhiDqdx47vrWH8gFTcnM+/c3oUXh3RUwCMiIuWmkKe8wu6Ba180Pl75PMTMs1spEaHG0pmb1ZdHRESk2kpJScFisRAQEFBie0BAAElJSRd8zsCBA/noo4+IiYnBarWydetW5syZQ0FBASkpxvLdSUlJ5TonwJQpU/D29rY9goKCLvPuapCEGPj0JsjPguZ94PYF4GTfaVBWq5XZ6+IY/sEmkjJyadHAg2/GRTGkSxO71iUiIjWXQp5LEfWYMV0L4NvHjWlcdtClmQ8ujg6kZOVzIDnLLjWIiIhI2ZjO6+VntVpLbTtj0qRJDBo0iIiICJycnBgyZAijRo0CwGw+O7qjPOcEmDhxIunp6bbHkSNHLvFuaphj2+GTYZCXAc16GaulOrvbtaTM3AIe/vw3Xvp2F4VFVm7sHMjX43rTKsDTrnWJiEjNppDnUvV/AbrdY/TnWXIfHPy5yktwcTQTFuwLGKtsiYiISPXj7++P2WwuNcImOTm51EicM9zc3JgzZw45OTkcOnSI+Ph4mjdvjqenJ/7+xrSiRo0aleucAC4uLnh5eZV41HpJO+GToZCbDkHhcNcX4Oxh15L2JmUy5P31LN+ZhJPZxAuD2/PeHV2p56I1UURE5PIo5LlUJhPc+Da0HwpFBbDwLmOedxU7u5R6WpVfW0RERP6es7MzYWFhREdHl9geHR1Nr169/vK5Tk5ONG3aFLPZzMKFC7nxxhtxcDB+fIuMjCx1zhUrVvztOeuU47tg/hA4fRKadIe7vgQX+46UWbbtKEOnryc2JZtAb1cWPRjJqKiQvxyBJSIiUlb6dcHlcDAbzfryMoyRPJ/dAvd+DwHtq6yEyBZ+EA2/7E1m+5FTdAnyqbJri4iISNlMmDCBESNG0L17dyIjI5k1axbx8fGMHTsWMKZRJSQkMH/+fAD27dvHli1bCA8P5+TJk7z11lv88ccffPzxx7ZzPvbYY1x55ZW89tprDBkyhK+//pqVK1faVt+q807shfn/MJZJb9wV7l4CrvYbuZRXaOHF/+3is83xAPRp5c+04V3wq+dit5pERKT20Uiey+XoAsM/haY9IfeUMd87La7KLt+tmS8RofXJybcwYvZmfj96qsquLSIiImUzfPhwpk2bxosvvkiXLl1Ys2YNy5cvJzg4GIDExETi4+Ntx1ssFqZOncoVV1zBtddeS25uLhs2bKB58+a2Y3r16sXChQuZO3cunTt3Zt68eSxatIjw8PCqvr3qJ2U/fDwYsk9Ao05w91Jw87FbOUfScrj1/zby2eZ4TCZ49JpWzLu3pwIeERGpcCZrLVmWqaxrxleanDSYdwMk7wLf5jD6R/BsVCWXzs4r5J45W9h6+CRero58fn8EHZt4V8m1RUREysvur9liUyu/FqkHjZ/JMhOhYQcY9S2417dbOb/sSWb8ou2kny7Ax92JacO7cFWbhnarR0REaqayvmZrJE9Fca8PI5YZAc/JQ/DJTcb87yrg4eLIvNE96dbMh4zcQu6evZldxzKq5NoiIiIi1UZanDGCJzMRGrSFkV/bLeCxFFmZumIv9877lfTTBVzR1JtvH+mtgEdERCqVQp6K5NkIRnwF9QIg+U/47DbIz66SS9dzceTj0T3pEuTDqZwC7vpoE7sTFfSIiIhIHXEq3gh4MhLAvzXc8z+o18AupaRm5XHPnC289/MBAEZEBPPF2Eia+tp32XYREan9FPJUtPohxogeV284ugUWjYDC/Cq5tKerE/PH9OSKpt6czCngro82szcps0quLSIiImI36Udh3o2QfgTqtygOeOwzYibm8ElueHcd6w6k4OZk5p3bu/DS0I64OJrtUo+IiNQtCnkqQ0AHY4lOJ3c4+BMsewCKLFVyaS9XJ+aPCadTE2/SsvO566NN7D+uoEdERERqqYxjxgieU4eNafP3/K/K+iKey2q1MmddHMM/2EhSRi6hDTz4elwUQ7o0qfJaRESk7lLIU1mCesLwT8DBCf5cBt/9C6qox7W3mxOfjOlJ+0AvUrLyuePDzRxIzqqSa4uIiIhUmczjRsCTFgs+zeCeb8G76kOVrLxCxi3Yxovf7qKwyMoNnQP5ZlxvWgd4VnktIiJStynkqUwt+8PNHwImiJkLP71YZZf2cXfms/vCaRfoRUpWHnd+uInYEwp6REREpJbIOmEEPKkHwDvICHh8gqq8jH3HM/nH++v47vdEHB1MPD+4Pe/f0ZV6Lo5VXouIiIhCnsrWYRgMnmZ8vO4tWP9ulV3a18MIeto28iQ5M487PtzEoZSqaQQtIiIiUmmyU2H+PyBlL3g2hnu+Ad/gKi/jq20JDHl/PbEnsmnk5cqiByO5NyoEk8lU5bWIiIjAJYY8M2bMICQkBFdXV8LCwli7du1Fj123bh1RUVH4+fnh5uZG27Ztefvtt0sdt2TJEtq3b4+Liwvt27dn2bJll1Ja9RQ2Cvq/YHwcPQl+m19ll65fHPS0DqjH8Qwj6DmcqqBHREREaqicNJg/BJJ3Qb1GMOpbqB9apSXkFVp49qudjF+0ndMFFnq39Oe7R3sTFuxbpXWIiIicr9whz6JFixg/fjzPPPMM27Zto0+fPgwaNIj4+PgLHu/h4cG4ceNYs2YNu3fv5tlnn+XZZ59l1qxZtmM2btzI8OHDGTFiBDt27GDEiBHcdtttbN68+dLvrLrp/Tj0etT4+H+Pwa5vquzSfvVc+Oy+CFo2rEdiei53zNrEkbScKru+iIiISIU4fRI+GQrHd4JHQ6PJsl+LKi3h6Mkcbvu/jXy6yfjZ99GrW/Lx6J741XOp0jpEREQuxGS1lq8bcHh4ON26dWPmzJm2be3atWPo0KFMmTKlTOe46aab8PDw4JNPPgFg+PDhZGRk8P3339uOue666/D19WXBggUXPEdeXh55eXm2zzMyMggKCiI9PR0vL6/y3FLVsVrhm0dg2ydgdoY7v4AW/ars8smZudw+axOxJ7Jp4uPGogcjaOrrXmXXFxERAeM129vbu3q/ZtcRNeprkZsO84fCsd/A3d8YwdOwXZWW8MveZB5ftJ1TOQX4uDvx9vAu9Gtjn6XaRUSkbinra3a5RvLk5+cTExPDgAEDSmwfMGAAGzZsKNM5tm3bxoYNG+jbt69t28aNG0udc+DAgX95zilTpuDt7W17BAVVfaO9cjOZYPA70H4IWPJh4V1wdGuVXb6hpysL7o8gxN+DhFOnuePDTSScOl1l1xcRERG5JLkZ8OnNRsDjVh9Gfl2lAY+lyMpbK/Yyet6vnMopoHNTb759pLcCHhERqXbKFfKkpKRgsVgICAgosT0gIICkpKS/fG7Tpk1xcXGhe/fuPPzww9x33322fUlJSeU+58SJE0lPT7c9jhw5Up5bsR8HM9z0IYT2g4Js+OwWSN5dZZcP8DKCnmA/d46kneaOWZtITFfQIyIiItVUXhZ8disc/RVcfYyAp1HHKrt8alYeo+Zu4d2fD2C1wt0RzVg8NlKjoUVEpFq6pMbL568YYLVa/3YVgbVr17J161b+7//+j2nTppWahlXec7q4uODl5VXiUWM4usDwT6FJ9+K55cPg5KEqu3wjbyPoaVbfnfi0HO6YtYnjGblVdn0RERGRMsnPhs+Hw5FN4OINI7+CwM5VdvmYwye58b11rN2fgpuTmWnDu/Dy0E64OJqrrAYREZHyKFfI4+/vj9lsLjXCJjk5udRInPOFhITQqVMn7r//fh5//HFeeOEF275GjRpd0jlrNJd6cNdiaNAOMhONOeaZx6vs8o193FjwQARNfd04lGoEPckKekRERKS6KDgNC26Hw+vA2RNGLIXGXavk0larlbnr4xj+wUYS03MJbeDBVw9HMbRrkyq5voiIyKUqV8jj7OxMWFgY0dHRJbZHR0fTq1evMp/HarWWaJocGRlZ6pwrVqwo1zlrJPf6MGIZ+DSDk3Hw6U1w+lSVXb6JjxsL7o+giY8bsSnZ3PHhJpIzFfSIiIiInRXkwsI7IW4NONeDu5dA0+5VcumsvEIeWbCNyf/bRWGRlRs6BfLNuN60aeRZJdcXERG5HOWerjVhwgQ++ugj5syZw+7du3n88ceJj49n7NixgNErZ+TIkbbjp0+fzv/+9z/279/P/v37mTt3Lm+++SZ333237ZjHHnuMFStW8Nprr7Fnzx5ee+01Vq5cyfjx4y//Dqs7r0AY8ZWxDOjxP4whyflVt7x5UH13FtwfQWNvVw6eyOauDzeTkpX3908UERERqQyFebDobjj4Mzi5GyOfm4VXyaX3Hc9kyPvr+Pb3RBwdTDx3Y3vev7Mr9Vwcq+T6IiIil6vcr1jDhw8nNTWVF198kcTERDp27Mjy5csJDg4GIDExkfj4eNvxRUVFTJw4kbi4OBwdHWnRogWvvvoqDz74oO2YXr16sXDhQp599lkmTZpEixYtWLRoEeHhVfOCbnd+LYwRPfOuN+acfzESbv8cHJ2r5PLN/NxZ8EAEwz/YxP7kLO76cDOf3x+OXz2XKrm+iIiICACF+fDFPXAgGhzd4M4vILhqRnZ/vT2Bp5bs5HSBhUZerky/qythwfWr5NoiIiIVxWS1Wq32LqIilHXN+GotfjPMHwKFp6HjzcYqXA5V19gvLiWb22dt5HhGHm0befL5/RHU96iaoElEROqOWvGaXUtUq6+FpQAWj4I934KjK9yxEFr0q/TL5hVaePnb3Xyy6TAAUS39eOf2rvjrl10iIlKNlPU1+5JW15JK0izcWHXLwQn+WALLn4AqzOBC/D34/P4IGni6sCcpk7s/2sypnPwqu76IiIjUUZZCWHKfEfCYneH2z6ok4Dl6MofbPthkC3geubol80eHK+AREZEaSyFPddOqP9z0AWCCrbPh55er9PItGtRjwf3GDze7EjO4e/Zm0nMKqrQGERERqUOKLLDsQdj1lfGLruGfQsv+lX7ZVXuTufG9dew4cgpvNyfmjurBvwa0wexgqvRri4iIVBaFPNVRx5vhxreMj9e+CRver9LLt2zoyYL7w/HzcOaPhAxGzNlM+mkFPSIiIlLBiizw1UPwx5fg4Ai3zYfWAyv9sn8kpHPvvF85lVNApybefPtIb/q1bVjp1xUREalsCnmqq+6j4ZrnjI9XPAPbPq3Sy7cKONuT5/ej6Yycs4WMXAU9IiIiUkGKiuCbR+H3hWAywy1zoO31VXLpH/9Mwmo1+u8sHhtJUH33KrmuiIhIZVPIU531ngC9HjE+/uYR2P2/Kr18m0aefDomHB93J3YcOcU9c7aQqaBHRERELldREXz3OGz/FEwOcPOH0H5IlV1+c2waAIM7N8bVqeoWuRAREalsCnmqM5MJrn0Jut4N1iL4cjTErqrSEto39uKz+8LxdnNiW/wpRs39lay8wiqtQURERGoRqxW+fwJi5hkBz7BZxlT1KpJbYGH7kVMARIT6Vdl1RUREqoJCnurOZIIb34F2g8GSDwvvgoSYKi2hQ2NvPrsvHC9XR2IOn2T03F/JVtAjIiIi5WW1wg9Pwa8fASYYMgM631qlJfwWf5J8SxEBXi4E+2maloiI1C4KeWoCsyPcPBtC+kJ+Fnx6CyTvqdISOjbx5tP7wvF0dWTLoTRGz/uVnHwFPSIiIlJGViuseBY2/5/x+T/egy53VHkZZ6ZqhYf4YTJpJS0REaldFPLUFI4ucPtn0CQMTqfBJ8Pg5OEqLaFzUx/mj+6Jp4sjm+PSGDNvK6fzLVVag4iIiNRAViv8NBk2Fq8YeuPb0G2EXUrZHJcKaKqWiIjUTgp5ahIXT7jrS2jQFjKPwSdDISu5Skvo2syXeaN74uFsZmNsKvfP30pugYIeERER+Qu/vALr3jY+vv5NYxVRO8gtsLAt/hQA4aH17VKDiIhIZVLIU9O414cRy8C7GaTFwqc3welTVVpCWLAvH4/uibuzmXUHUhT0iIiIyMWteg3WvG58PHAK9LzfbqXsOHKKvMIi/Ou5EOrvYbc6REREKotCnprIqzGM/Ao8GkLSTlhwO+TnVGkJ3ZvXZ969PXFzMrN2fwpjP40hr1BBj4iIiJxj7VRY9Yrx8bUvQeRDdi1nc1xxP57Q+urHIyIitZJCnprKrwWMWAou3hC/EebdALu+BktBlZXQM6Q+c0b1wNXJgVV7T/DQp78p6BERERHD+nfhpxeNj695DqIetW89qB+PiIjUfgp5arJGneDOReDkDsd+gy9GwrROxrDozKQqKSGyhR9z7umBi6MDP+1J5uHPtpFfWFQl1xYREZFqauMMiJ5kfHzV09DnX/atB8gvLCLm8EkAIkLUj0dERGonhTw1XXAkjPvV+OHJ3R8yE41h0W93gMWj4NA6Y0WLStSrpT+zi4OelbuP88iC3yiwKOgRERGpk2JXwY8TjY+v/A9c9aRdyznj96OnyC0ows/DmZYN69m7HBERkUqhkKc28G5qDIOesAtung1BEVBUCH8uM6ZxzYiELR9CXmalldC7lT8fjuyOs6MDP/55nEcXbFPQIyIiUhc1vxK63QO9H4d+T9u7Gpsz/Xh6hqgfj4iI1F4KeWoTRxfodAuM+RHGroOwUcZUrhO7Yfm/YWpb+O5fkLy7Ui5/ZesGfDAiDGezA9//kcT4RdspVNAjIiJStzg4wOB34JrnoRqFKZti1Y9HRERqP4U8tVWjTsYPWP/aA9e9Bn6tID8Lfv0IZkTA3BuMkT4V3Ki5X5uGzLy7G05mE9/9nsiEL3Yo6BEREalrTKZqFfAUWM724wkPVT8eERGpvRTy1Hau3hAx1ujbM/JraDcYTGY4vM7o2fN2R/jlFcg4VmGXvKZdADPuCsPRwcQ3O47xxJe/Yymq3L5AIiIiIhezMyGdnHwLPu5OtG7oae9yREREKo1CnrrCZILQq2D4pzB+p9EI0aMhZCXB6teMsOeLkRC3pkIaNV/bPoD37+yGo4OJZdsS+I+CHhEREbGTzbFGP57wkPo4OFSfEUYiIiIVTSFPXeTdBK5+Bh7/E26ZA816gdUCu76GjwfD9HDYPAtyMy7rMtd1bMR7d3TF7GBiyW9HefCTGE5k5lXQTYiIiIiUzZl+POEh6scjIiK1m0KeuszRGTreDKO/h39ugO6jwckDUvbC908YjZq/fRyO/3nJlxjUKZB3bu+Ck9nEyt3HGfD2ar77PbECb0JERKRmmDFjBiEhIbi6uhIWFsbatWv/8vjPPvuMK664And3dwIDA7n33ntJTU0tccy0adNo06YNbm5uBAUF8fjjj5Obm1uZt1HjFFqK2HqoeCSP+vGIiEgtp5BHDAEd4Ma3jUbNg94A/zZQkA1b58DMXjBnEOz8Egrzy33qGzs35uuHe9Mu0IuTOQU8/PlvjPv8N9Kyy38uERGRmmjRokWMHz+eZ555hm3bttGnTx8GDRpEfHz8BY9ft24dI0eOZMyYMfz5558sXryYX3/9lfvuu892zGeffcZTTz3F888/z+7du5k9ezaLFi1i4sSJVXVbNcKfxzLIzrfg5epI20Ze9i5HRESkUinkkZJcvSD8AXh4M9zzP2g/xGjUHL8BloyBtzvAzy9DekK5Ttu+sRdfPxzFo1e3xOxg4tvfExnw9mpW/JlUSTciIiJSfbz11luMGTOG++67j3bt2jFt2jSCgoKYOXPmBY/ftGkTzZs359FHHyUkJITevXvz4IMPsnXrVtsxGzduJCoqijvvvJPmzZszYMAA7rjjjhLHnC8vL4+MjIwSj9puc5wx+qlniB9m9eMREZFaTiGPXJjJBCFXwm3z4fE/oO9TUK8RZCfDmjdgWidYeBcc/KXMjZqdHR2YMKANyx7qRauG9UjJyueBT2KYsGg76TkVu5S7iIhIdZGfn09MTAwDBgwosX3AgAFs2LDhgs/p1asXR48eZfny5VitVo4fP86XX37JDTfcYDumd+/exMTEsGXLFgBiY2NZvnx5iWPON2XKFLy9vW2PoKCgCrjD6m1TcdPlCE3VEhGROkAhj/w9r8bQb6IR9tw6D5r3MRo17/kWPhkK7/eATTPh9Kkyna5zUx/+90hvxvZtgYMJlm5LYMC01fyyN7ky70JERMQuUlJSsFgsBAQElNgeEBBAUtKFR7T26tWLzz77jOHDh+Ps7EyjRo3w8fHhvffesx1z++2389JLL9G7d2+cnJxo0aIF/fr146mnnrpoLRMnTiQ9Pd32OHLkSMXcZDVlKbLya9yZlbXUdFlERGo/hTxSdmYn6DAMRn0LD22CHveDcz1I3Q8/PAVvtYNvHoWknX97KlcnM08Nasvisb0I9ffgeEYe9879lSe//J3MXI3qERGR2sdkKjlVyGq1ltp2xq5du3j00Ud57rnniImJ4YcffiAuLo6xY8fajlm1ahX//e9/mTFjBr/99htLly7l22+/5aWXXrpoDS4uLnh5eZV41Ga7EzPIzCvE08WR9o1r972KiIgAmKzWMs61qeYyMjLw9vYmPT291v/AUq3kZcKOhfDrbDix++z2oHAjBGr/D3B0+ctTnM638OaKvcxZH4fVCk183Hj9ls5EtfSv5OJFRMQe6tprdn5+Pu7u7ixevJhhw4bZtj/22GNs376d1atXl3rOiBEjyM3NZfHixbZt69ato0+fPhw7dozAwED69OlDREQEb7zxhu2YTz/9lAceeICsrCwcHP7+d3m1/Wvx0dpYXv5uN1e3bcicUT3sXY6IiMglK+trtkbyyOVx8YSe98NDG2HUcmOkj4MjHNkMS+8zGjX/9CKcuvhwcDdnM5NubM/C+yNoVt+dhFOnueujzTz71U6y8wqr8GZEREQqnrOzM2FhYURHR5fYHh0dTa9evS74nJycnFIhjdlsBowRQH91jNVqpZb8Du+ynenHEx6ifjwiIlI3KOSRimEyQfMoo2fP43/CVU+DZyBkn4C1U+GdzjB7IPwyBeI3gaX0lKzwUD++f6wPIyKCAfh0UzyD3lnL5tjUKr4ZERGRijVhwgQ++ugj5syZw+7du3n88ceJj4+3Tb+aOHEiI0eOtB0/ePBgli5dysyZM4mNjWX9+vU8+uij9OzZk8aNG9uOmTlzJgsXLiQuLo7o6GgmTZrEP/7xD1sgVJcVFVn59VBxyBOqfjwiIlI3ONq7AKmFPBvBVU9Cnwmwdzn8+hHErYEjm4zH6lfB2ROa94bQq4xHgzZgMuHh4shLQzsysEMjnlzyO/FpOdz+4Sbu7RXCEwPb4OasH1pFRKTmGT58OKmpqbz44oskJibSsWNHli9fTnCw8YuNxMRE4uPjbcePGjWKzMxM3n//ff71r3/h4+PD1VdfzWuvvWY75tlnn8VkMvHss8+SkJBAgwYNGDx4MP/973+r/P6qoz1JmaSfLsDD2UxH9eMREZE6Qj15pGqcPAyxv0DsKohdDafTSu73DDwb+IReBZ6NyMwt4OVvd7NoqzHVK9TfgzduvYKwYN8qLl5ERCqSXrOrj9r8tZizLo4Xv91F39YN+Hh0T3uXIyIiclkqtSfPjBkzCAkJwdXVlbCwMNauXXvRY5cuXcq1115LgwYN8PLyIjIykh9//LHEMfPmzcNkMpV65ObmXkp5Uh35BkPYKGM61xMH4YHV0H+yEeiYXSAzEXYsgGUPwtQ2MD0Cz1XP8VrnRObf3Y4ALxdiU7K59f82MOX73eQWWOx8QyIiIlKdbY4zpnuHh6ofj4iI1B3lnq61aNEixo8fz4wZM4iKiuKDDz5g0KBB7Nq1i2bNmpU6fs2aNVx77bW88sor+Pj4MHfuXAYPHszmzZvp2rWr7TgvLy/27t1b4rmurq6XcEtS7Tk4QOMuxqP3eCg4bTRqPlg80idxh7FS14ndsGkGVzo4sr5xd1Z6tWNWQjAfrbbw8+5k3rqtC52aetv3XkRERKTaKSqysiXuTNNl9eMREZG6o9zTtcLDw+nWrRszZ860bWvXrh1Dhw5lypQpZTpHhw4dGD58OM899xxgjOQZP348p06dKnMdeXl55OXl2T7PyMggKCioVg43rnNy0iButRH4HPwFTh0usTsLNzZa2rPB2pFm3W/grhv64+ykXj0iIjVFbZ4iVNPU1q/FnqQMrpu2FjcnM7+/MAAns9YaERGRmq2sr9nlGsmTn59PTEwMTz31VIntAwYMYMOGDWU6R1FREZmZmdSvX3LobFZWFsHBwVgsFrp06cJLL71UYqTP+aZMmcLkyZPLU77UFO71jaXYOwwzPk+LK+7l8wvErqZe7imuNcdwLTGw/WNSdvjh2KofPh0HQkhf8Aywa/kiIiJiX5uLl07v3txXAY+IiNQp5Qp5UlJSsFgsBASUfBMdEBBAUlJSmc4xdepUsrOzue2222zb2rZty7x58+jUqRMZGRm88847REVFsWPHDlq1anXB80ycOJEJEybYPj8zkkdqofohxqP7vVBkgaTf4eAvnPj9R7xOxOBvTYV9XxoPgIYdzjZwDu4FLvXsWb2IiIhUMVs/nhD14xERkbrlkpZQN5lMJT63Wq2ltl3IggULeOGFF/j6669p2LChbXtERAQRERG2z6OioujWrRvvvfce77777gXP5eLigouLy6WULzWZgxkad4XGXWnQZwIn0k7xyRcLcT+6jiiHnXRyOATJfxqPTdPBwQmCehaHPv2M55ov6Z+9iIiI1ABWq9U2kiciVP14RESkbinXu11/f3/MZnOpUTvJycmlRvecb9GiRYwZM4bFixfTv3//vzzWwcGBHj16sH///vKUJ3VQg/o+PP7gg3y1/Ubu+vpPzLlpXOm0m7FN42l7OgbTqXg4vN54/PJfcPGC5n2gRT8j+PFrCWUIKEVE6qTMJCMs99AbZak5DiRnkZqdj6uTA52b+ti7HBERkSpVrpDH2dmZsLAwoqOjGTZsmG17dHQ0Q4YMuejzFixYwOjRo1mwYAE33HDD317HarWyfft2OnXqVJ7ypI4ymUwM69qUyFB/nlr6O1/v9eLruHC6Bd3HtLt9aHZys9HTJ24N5J6Cvd8ZDwCvpmendoX2hXoNL34hEZHaLCsZjm2HY9vOPrKS4NqXIOpRe1cnUmabilfV6tbMF2dH9eMREZG6pdzzViZMmMCIESPo3r07kZGRzJo1i/j4eMaOHQsYvXISEhKYP38+YAQ8I0eO5J133iEiIsI2CsjNzQ1vb2P568mTJxMREUGrVq3IyMjg3XffZfv27UyfPr2i7lPqgEberswd1YMvth7hpW9389uRdAZ8nMl/Bl7NqFtH40ARJG4vbuK8CuI3QcZR2P6p8QBoFmk0fG4/BDwb2fFuREQqUXaKEegkbjsb7GQklD7O5ABZx6u6OpHLsjn2TD8ejUATEZG6p9whz/Dhw0lNTeXFF18kMTGRjh07snz5coKDgwFITEwkPj7edvwHH3xAYWEhDz/8MA8//LBt+z333MO8efMAOHXqFA888ABJSUl4e3vTtWtX1qxZQ8+ePS/z9qSuMZlMDO/RjN6tGvDkl7+z7kAKL367ix//TOKNW66gWZMwaBIGff4F+TkQv/Hsyl1JO43P4zfC909CcBR0GGoEPhrhIyI1VU6aEXAfOxPobIf0+AscaAL/1sV9z7oYfzbqBM4eVVquyOWwWq1sjjvTj0dNl0VEpO4xWa1Wq72LqAhlXTNe6g6r1cqnm+OZsnw3OfkW3J3NPH19O+4Kb3bhRuHpCbDra/hzKRz99ex2kwM0722M8Gn3D/Dwr7qbEBEpj9OnIHHH2elWidvh5KELH+vX0tbInsAuENgZXDyrpEy9Zlcfte1rcfBEFtdMXY2zowO/Pz8AVyezvUsSERGpEGV9zVbII7VefGoO//5yB1uKf7PXu6U/r93SmSY+bhd/0qn44sBnGSTEnN1uMkPIlcWBz2Bw128JRcROcjOMQMc2SmcbpMVe+Nj6oUaQYwt1OoOrd1VWW4Jes6uP2va1+HxzPE8v20l4SH0WPRhp73JEREQqjEIekXMUFVmZu+EQr/+wh7zCIjxdHJl0Y3tu7d70wqN6znXyEPz5lRH4JG4/u93B0WjY3GEYtL0B3Hwr7wZEpG7Ly4Kk38+ZcrUNUi+yAqVPcMkpV4FXVLv/n/SaXX3Utq/FYwu38fX2Yzx2TSsev7a1vcsRERGpMAp5RC7g4Iks/r14B9viTwHQr00DXr25MwFermU7QepB2PWVEfgk7Ty73cEJWlxdHPhcb9ffkItIDZefY/z/cu6UqxN7gQu8XHsHnRPmFP9ZA0YY6jW7+qhNXwur1UrElJ84npHH5/eH06uFpleLiEjtoZBH5CIsRVY+XBvLWyv2kW8pwsvVkclDOjC0S5O/H9VzrpQDRtjz5zJI/vPsdrMztLgGOt4Era8DV/17FJGLKDgNSX+UnHJ1Yg9Yi0of69Wk5JSrxl1qbI8wvWZXH7Xpa3EoJZur3lyFs9mB319QPx4REaldyvqaXe7VtURqOrODibF9W3B124b864sd7ExI5/FFO/h+ZxKTh3Qg0PsvevWcy78l9H3CeJzYa4Q9fyyFlL2w73vjYXaBVtcaI3xaXwcu9Sr35kSk+rBa4fRJyEyEjGPGIzPRWKo8IxHSj0LKPrBaSj+3XgA07lZylI5nQFXfgUiNsjnOWDr9iiBvBTwiIlJnKeSROqt1gCdLH+rFzFUHefen/azYdZw1+0/wQJ9QHuzbAg+Xcnx7NGgDVz1lPJJ3nw18UvfDnm+Nh6MrtBpgjPBpNUDLEovUZEUWyEouDm6OnQ1xzg9yCk///bk8GpwzOqc40PEKrPRbEKltNseeWTrdz86ViIiI2I+ma4kAfx5L5/mv/2Tr4ZMANPB04d8DWnNLWBBmh3JM4TqX1QrH/yye0rW05Ko3Tu7QeqAxwqfVAHAq4+ghkapSmG+EF+kJRmCRfrQ4xCj+OD/LWG7bxcvoQeXiZUxNPPO57WMvcPEuuc+pjD2w7KUg95zgpjiwOX80TmbShUfgXIi7H3g2Bq/GRnjj1QQ8A42PG7QztpdnqmgtoNfs6qO2fC2sVitRr/7MsfRcPh0TTu9WNXMqo4iIyMWoJ49IOVmtVn74I4kp3+8hPi0HgLaNPHn2hvaX/8Oi1WqsjHOmh8/JQ2f3OXlAm0FG4NOyf/V/A3whBbnGtJTTJ6GowOhLZHYGs5PRlPrMx+bijx00jN6uLAVGSGELbxKM8OLMx+kJkJ1cedc3O58XCp350+cC284Njs4Jkxxdyn9dqxVy088bfXOBEOd0WtnOZzKDZyMjpPEsDm9KhDjF22vi93Ql02t29VFbvhZH0nLo8/ovODqY+P2FAbg7a7C6iIjULurJI1JOJpOJQZ0CubpdQz7ZeJh3f9rPnqRM7p69mX5tGvD09e1oFeB5qSc3ljEOvAKued5orvrnMmNp9vR4+ONL4+HsaazO1WGYsVrXpbyRvVRWK+Rnnw1r/vJxquTnZZmSci6Tw4XDn1Kh0PnhkOM5AdI5H5fY/lfnK/7YyR2c6xk9kpzrGVPnnOsZ56zpiizFAc4xyDh6diTOmfAmIwGyjl+4se/5zC5GUOHdtDjAaAzeTcCrqRG45GVCXoYRnJz5Mzej+ONz/jyzPy8TsIIlH3JSjMelMrv8/cihwtzSIU5BTtnO7+hWPPKm8QVCnMbGyJx6DRVYilQTm2KNfjydm3or4BERkTpNr4Ii53FxNHNfn9D/b+/Ow6K40raB390N3c3ayNbsm6KABEUQBMRdjDG+mkkiSUYdJ2beZGKihEwm8prVJDKazYxGMvolcTLjNhqzOCEa3EUFFUWNIi4gm+xbsygI9PdHQytBlKWhaLh/11UXdnVV9VPVXtThqXOeg8dHOeGzfVfw76QsHEgvxuErJXg6yBlRU4bC2rQbyReRCHAcpVmmLgfyUu708FHlAee2aRaZAvCaoUn4eEwADKQdO75arfmD+kEJmtqytu813e7GeYk1PTEkUs1xGm9r/phvvN12WIu6CWis0yx9iYH8TtJHZnbXv1uSQfd4LWtJEpm1fc9AptthOE1Nmh42dydsWg2jak5mdGQYkdiwOYHh2Jy4cWxO5jjc+bexle7jr6+6dwJI+/Ne7921rr5Kc6zGOqCmWLN0ltGgdoZP3ZXEkVsMuCFURPosifV4iIiIAHC4FtEDZRRXI/bnS0i4WAgAMJMZ4MWJQ/DHMDfdzt7R1ATknbrTw6fqxp335BaA96OAS6imFsqDetl0tFbIvYgNAWNLzR/CbRaLdtYP0iQ5xOJ2zq1Rk+xplfxpTgC1vP5tYqin1jfUaaatrq/W9CyprwaaGrp+ve57LQ3ukQBq57Xs7h5FhkBV4V09cZp75ajyO5aIE0nuJGvu7n2jaH5t7qQp9tve99WXNTVqvrd7JYC0vYma35NI71yHu4dPSY2FPosBj/fsvqO/fBdjV+5HbvlN/PPZIIwfaiN0OERERDrHmjxEOnb8Wine/+kiLtxQAQAcLYzw+nQvzPSzh0jXT/ybmoCcZE3C5+L3muE1nWVg1DZB027y5q7F0Hjg9WBoqNMMVaur0vysr25OAjX/fOB71XfW19d0fEhQV4jEgKndnd439+qJY6rkMCLq03jP7jv6w3eRV3ETYX/bD4lYhLNvR8C0M7NjEhER6QnW5CHSsZDBVtj10lh8dyYPH+5JR17FTSzecgZfH83EGzN8EOA6SHcfJhYDriGa5eFYIPu4JuFTelXTq+dBiRojC87Y1RkGMs1ibKmb4zU1tp8AqqvWDDlq971qTc8jU1tNj5vf9sQxtesftYOIiHQkubkez0OOCiZ4iIhowOOdkKgTxGIRHg9wwiMP2WPDkQx8cegazmRX4PG4Y5jhZ4+lD3vB2VLHQ0HEEsBtrGYh/SCW3JkNioiIelRL0eVgDx0l6omIiPSYHhZkIBKekVSCxZM9cfAvExAZ6AyRCPjpXD4mf3wIsfFpqLzZjQLGRERE1GHJmc1Fl91ZdJmIiIhJHqJusDWXY+UTfvjp5XCEDbFCfWMT/nE4AxM+PIBvjl/H7cYOTFNNREREXZJfeRNZpbUQi4BANx0OmyYiItJTTPIQ6YCPgzn+vTAYXy0IxGAbE5TX3sZbP1zAtNWHsS+tEP2kvjkREVGfktw8dbqvowJmckOBoyEiIhIekzxEOiISiTDJS4ndUePw3qzhsDSRIqO4Bgv/eQpzv0zGxeZZuYiIiEg3kjOb6/G4sx4PERERwCQPkc4ZSsSYF+KGg69NwPPjPSCViHH0ailmrDmC17afRaHqltAhEhER9QstPXmCWY+HiIgIAJM8RD3GXG6ImOne2PfqeDzqZw+1GtiekosJHx7EZ3uvoLa+QegQiYiI9FaR6hYySmogEgGj2ZOHiIgIAJM8RD3O2dIYa58ZhW//HAp/FwvcvN2IT/dexsSPDmJHSi6amlivh4iIqLOSmmfV8rE3h8KI9XiIiIgAJnmIek2A6yDs/HMo1j7jD6dBRihU1eEv289i5tpEHLtWInR4REREeiU5o6UeD4dqERERtWCSh6gXiUQiPOrngL3R4xEz3QtmMgNcuKHCMxuS8dw/T+FacbXQIRIREemF5OaePMEeHKpFRETUgkkeIgHIDSV4fvxgHHxtAuaHuEIiFmFvWiGmfXoY7/x4AeU19UKHSERE1GcVV9XhalE1RCLOrEVERHQ3JnmIBGRlKsPyWb7YExWOyV62aGhSY+Ox6xj/4QFsOJyBuoZGoUMkIiLqc0409+IZpjSDhbFU4GiIiIj6DiZ5iPqAIbZm+HLBaGx6Lhje9uZQ3WrAB/FpmPrJYcSfz4dazeLMRERELZIzNfV4xniwHg8REdHdmOQh6kPChljjvy+Pxaon/GBrJkN2WS1e3HQaT35xHKk5FUKHR0RE1CckZzTX4+FQLSIiolaY5CHqYyRiEeYEOuPAXyZgyWRPGBlKcCqrHLM/P4qXt5zB1SIWZyYi0kfr1q2Du7s75HI5AgICcOTIkftuv2nTJowYMQLGxsawt7fHH//4R5SWlrbapqKiAosWLYK9vT3kcjm8vb0RHx/fk6chuLKaeqQXVgEAgpjkISIiaoVJHqI+ykRmgFemDsWBv0zAEwFOEImAXWdvYOqnh/DS5tNIL6gSOkQiIuqgbdu2ISoqCsuWLcOZM2cQHh6O6dOnIzs7+57bJyYmYv78+Vi4cCEuXLiA7du34+TJk3juuee029TX12Pq1Km4fv06duzYgfT0dGzYsAGOjo69dVqCONE8VGuo0hRWpjKBoyEiIupbDIQOgIjuz04hx0dPjsAfw9zw2d4r+OViIf57Lh//PZePacOVeHmSJ3wdFUKHSURE9/HJJ59g4cKF2iTN6tWrsWfPHsTFxSE2NrbN9klJSXBzc8PixYsBAO7u7nj++eexatUq7TZfffUVysrKcOzYMRgaGgIAXF1de+FshJWkHarFejxERES/xZ48RHpiuIMC6+cH4ucl4ZjxkD1EImDPhUI8uiYRz248iTPZ5UKHSERE91BfX4+UlBRERES0Wh8REYFjx47dc5/Q0FDk5uYiPj4earUahYWF2LFjB2bMmKHd5scff0RISAgWLVoEpVIJX19frFixAo2N7c/MWFdXB5VK1WrRN0kZLLpMRETUHiZ5iPSMt705Pv/9KPwSNQ6zRzpALAL2XyrCY+uOYd6XyTh5vUzoEImI6C4lJSVobGyEUqlstV6pVKKgoOCe+4SGhmLTpk2IjIyEVCqFnZ0dLCwssGbNGu02GRkZ2LFjBxobGxEfH4833ngDH3/8MT744IN2Y4mNjYVCodAuzs7OujnJXlJRy3o8RERE99OlJE9nCgfu3LkTU6dOhY2NDczNzRESEoI9e/a02e7bb7+Fj48PZDIZfHx88N1333UlNKIBw1NphtVP+WPfq5qaPRKxCEeulODJL47jqfXHcexaCadeJyLqQ0QiUavXarW6zboWFy9exOLFi/HWW28hJSUFu3fvRmZmJl544QXtNk1NTbC1tcX69esREBCAp556CsuWLUNcXFy7McTExKCyslK75OTk6ObkesmJzDKo1cBgGxPYmLEeDxER0W91OsnT2cKBhw8fxtSpUxEfH4+UlBRMnDgRM2fOxJkzZ7TbHD9+HJGRkZg3bx7Onj2LefPmYc6cOUhOTu76mRENEO7WJvjoyRE4+JcJeDrIBYYSEZIyyvDMhmQ8+cVxHLpczGQPEZGArK2tIZFI2vTaKSoqatO7p0VsbCzCwsLw2muvwc/PD9OmTcO6devw1VdfIT8/HwBgb2+PoUOHQiKRaPfz9vZGQUEB6uvr73lcmUwGc3PzVos+Sc5srsfDoVpERET31Okkz92FA729vbF69Wo4Ozu3+9Ro9erV+Otf/4rRo0fD09MTK1asgKenJ3bt2tVqm6lTpyImJgZeXl6IiYnB5MmTsXr16nbj6A9jyol0ydnSGLG/ewiHXpuI+SGukBqIcSqrHH/46gRmrzuGfWmFTPYQEQlAKpUiICAACQkJrdYnJCQgNDT0nvvU1tZCLG7dTGtJ5rT8Lg8LC8PVq1fR1NSk3eby5cuwt7eHVCrV5Sn0GazHQ0REdH+dSvJ0pXDgbzU1NaGqqgqWlnfGUR8/frzNMadNm3bfY+r7mHKinuJgYYTls3xx5K8TsXCsO+SGYpzNqcDCf57Co2sSsfvXfDQ1MdlDRNSboqOj8f/+3//DV199hbS0NLzyyivIzs7WDr+KiYnB/PnztdvPnDkTO3fuRFxcHDIyMnD06FEsXrwYQUFBcHBwAAD8+c9/RmlpKZYsWYLLly/jp59+wooVK7Bo0SJBzrGnVd68jYv5mod6Y1iPh4iI6J46NYV6VwoH/tbHH3+MmpoazJkzR7uuoKCg08eMiYlBdHS09rVKpWKih+guSnM53nzUB3+eMBgbjmTgX8ezcOGGCi/8+zSGKc3w0qQheOQhe0jE964HQUREuhMZGYnS0lIsX74c+fn58PX1RXx8vHbK8/z8/FZD3xcsWICqqiqsXbsWr776KiwsLDBp0iSsXLlSu42zszN++eUXvPLKK/Dz84OjoyOWLFmC119/vdfPrzecuq6px+NubQJbc7nQ4RAREfVJnUrytOhM4cC7bdmyBe+88w5++OEH2NraduuYMpkMMhkL7hE9iLWpDDHTvfHCuMH46mgmNh69jvTCKry85Qw+3XsZL00cgv8Z4QADCSfbIyLqSS+++CJefPHFe763cePGNutefvllvPzyy/c9ZkhICJKSknQRXp93Z6gWe/EQERG1p1N/1XWlcGCLbdu2YeHChfjPf/6DKVOmtHrPzs6uS8ckoo4bZCLFqxHDkLh0El6ZMhQKI0NkFNcg+j9nMfmTQ9h2Mhv1DU0PPhAREZEAtEWX3VmPh4iIqD2dSvJ0pXAgoOnBs2DBAmzevBkzZsxo835ISEibY/7yyy/3PSYRdY3CyBBLpngi8fWJ+OvDw2BpIkVWaS1e//Y8Jn50EP9OykJdQ6PQYRIREWlV3bqNX/MqAQDB7MlDRETUrk4P14qOjsa8efMQGBiIkJAQrF+/vk3hwLy8PHzzzTcANAme+fPn47PPPsOYMWO0PXaMjIygUCgAAEuWLMG4ceOwcuVKzJo1Cz/88AP27t2LxMREXZ0nEf2GmdwQL04YggWhbticnI0vDmUgr+Im3vj+V6zdfxXPj/fA00EukBtKHnwwIiKiHnQqqxxNasDF0hj2CiOhwyEiIuqzOl2EIzIyEqtXr8by5csxcuRIHD58+L6FA//xj3+goaEBixYtgr29vXZZsmSJdpvQ0FBs3boVX3/9Nfz8/LBx40Zs27YNwcHBOjhFIrofY6kBngv3QOLrE/HOTB/YmctRoLqFd3ddxNiVB7DhcAZq6xuEDpOIiAYw1uMhIiLqGJFare4XcymrVCooFApUVlbC3Nxc6HCI9FZdQyO2n8pF3MFryKu4CQCwNJFi4Vh3zA9xhZncUOAIiUjf8Z7dd+jLdzH786NIzanAx0+OwOMBTkKHQ0RE1Os6es/mdDpE1IrMQIK5Y1xx8LUJWPW4H1ytjFFWU48P96Rj7MoD+GzvFVTevC10mERENEDU1DXgPOvxEBERdQiTPER0T4YSMeaMdsa+6PH4NHIEPGxMUHnzNj7dexlj/7YfH+1JR3lNvdBhEhFRP5eSVY7GJjUcLYzgNMhY6HCIiIj6NCZ5iOi+DCRiPObvhIRXxmPN0/4YpjRDVV0D1h64irCV+xH7cxpKquuEDpOIiPqpO/V4OHU6ERHRgzDJQ0QdIhGLMHOEA35eEo4v5gZguIM5ausb8Y9DGRi7cj+W77qIQtUtocMkIqJ+JjmzDACHahEREXVEp6dQJ6KBTSwW4WFfO0wbrsT+S0X4+/6rOJtTga+OZuLfyVl4fJQjnglyxUNOCqFDJSIiPVdb34BzuRUAgDHu7MlDRET0IEzyEFGXiEQiTPZWYpKXLY5cKcGa/Vdw8no5tpzIwZYTORjuYI6nRjtjlr8jzDkjFxERdcHprArcblTDQSGHs6WR0OEQERH1eUzyEFG3iEQijBtqg3BPa5zILMOm5Gzs/rUAF26o8OYPF/BBfBpmPOSAp4OcEeA6CCKRSOiQiYhITyRnaurxBHtY8f5BRETUAUzyEJFOiEQiBHtYIdjDCuU19dh5Jg9bT2TjSlE1vj2di29P58LT1hSRo53x+CgnDDKRCh0yERH1cckZzfV43FmPh4iIqCOY5CEinRtkIsXCse54NswNp7M1Q7j+e+4GrhRV4/2f0rBqdzqm+drh6dHOGONhBbGYT2eJiKi1W7cbkZpTAUDTk4eIiIgejEkeIuoxIpEIAa6WCHC1xFszffBD6g1sPZGNCzdU2HX2BnadvQFXK2NEjnbGEwFOsDWTCx0yERH1Eaezy1Hf2ASluQxuVsZCh0NERKQXmOQhol5hLjfEvDGumDfGFb/mVWLLiWz8kHoDWaW1WLU7HZ/8chmTvW3xVJALxnnaQMLePUREA9qdoVqsx0NERNRRTPIQUa/zdVTgg8cewrIZ3vjvuXxsPZGN09kV2HOhEHsuFMLRwghPBjphTqAzHCw4mwoR0UB0p+gy6/EQERF1FJM8RCQYY6kB5gQ6Y06gM9ILqrD1ZDZ2ns5DXsVNrN57BX/fdwXjh9rgqSAXTPKyhaFELHTIRETUC27dbsTp7AoAwBjW4yEiIuowJnmIqE8YZmeGt2cOx+sPe2HPhQJsOZGNpIwyHEgvxoH0YtiYyfBEgBOeGu0MVysTocMlIqIedDanAvUNTbA2lcHDmr/ziYiIOopJHiLqU+SGEswa6YhZIx2RWVKDbSdzsCMlB8VVdYg7eA1xB68hdLAVngpywbThSsgMJEKHTEREOpac2VyPx8OS9XiIiIg6gUkeIuqz3K1NsHS6F16NGIp9aYXYciIHh68U49i1Uhy7VopBxob43SgnPB3kjCG2ZkKHS0REOtJSj2eMO+vxEBERdQaTPETU5xlKxHjY1x4P+9ojt7wW/zmVi+2ncpBfeQtfJmbiy8RMBLoOwlNBLpjxkD2MpOzdQ0Skr+obmpCSVQ6A9XiIiIg6i0keItIrToOMET11KJZM9sShy0XYciIH+y8V4VRWOU5llePdXRcwe6QjngpyxnAHhdDhEhFRJ53LrcCt202wMpFiiK2p0OEQERHpFSZ5iEgvScQiTPJSYpKXEoWqW9iRkoutJ7ORU3YT/0rKwr+SsuDnpMBTo13wPyMdYCrjrzsiIn3QUo8nyJ31eIiIiDqLf/UQkd5TmsuxaOIQ/Hn8YBy7VoqtJ7Ox50IBzuVW4lzuebz/00XM9HNAZJAz/J0t+EcDEVEflpTRXI+HQ7WIiIg6jUkeIuo3xGIRxnpaY6ynNcpq6rHzdC62nMjGteIabDuVg22ncjBMaYa5Ia54fJQjjKX8FUhE1JfcbrxTjyfYg0WXiYiIOkssdABERD3B0kSK58I9sDd6PLa/EILfjXKEzECM9MIqvPn9rwiJ3Y+//XwJ+ZU3hQ6ViIianc+rRG19IyyMDTGUsyYSERF1Gh9jE1G/JhKJMNrNEqPdLPH2zOHYeToXG49dR1ZpLb44dA0bjmTgkYfssXCsO0Y6WwgdLhHRgJac0VyPx80SYjGH1hIREXUWkzxENGAojAzxxzB3zA9xw/5LRfgyMQNJGWXYdfYGdp29gVEuFlg41gPThithIGFHRyKi3sZ6PERERN3DJA8RDTgSsQhTfZSY6qPEhRuV+CrxOnadvYHT2RU4vfk0HC2M8IdQV0SOdoHCyFDocImIBoSGxiacuq7pycN6PERERF3DR9VENKANd1Dg4zkjkLh0IhZP9oSViRR5FTexIv4SQmL34e0ffkVmSY3QYRIR9XsXbqhQU98Ic7kBvOzMhQ6HiIhILzHJQ0QEwNZMjuipQ3F06SSsetwPXnZmqK1vxD+PZ2HSxwexcONJHLtaArVaLXSoRET9UstQrSB3S0hYj4eIiKhLOFyLiOguckMJ5ox2xpOBTjh2rRRfJWZi36Ui7eJlZ4Znx7rjf0Y4QG4oETpcIqJ+IzlTM1SL9XiIiIi6jkkeIqJ7EIlECBtijbAh1sgorsbGY9ex/VQuLhVU4a87zmHV7kv4fbAr5o5xhY2ZTOhwiYj0WmOTGiebkzzB7kzyEBERdRWHaxERPYCHjSmWz/JFUsxkxEz3goNCjpLqeny27wrC/rYff9l+FhdvqIQOk4hIb6Xlq1BV1wAzmQF8HFiPh4iIqKvYk4eIqIMUxoZ4fvxgPDvWHXsuFODLxEycya7AjpRc7EjJRYiHFZ4d647JXrYQs54EEVGHtdTjGc16PERERN3CJA8RUScZSsR41M8Bj/o54HR2Ob5KzMTPvxbgeEYpjmeUws3KGAtC3fBkoDNMZPw1S0T0IEkZLUO1OHU6ERFRd3RpuNa6devg7u4OuVyOgIAAHDlypN1t8/Pz8cwzz2DYsGEQi8WIiopqs83GjRshEonaLLdu3epKeEREvWaUyyCsfWYUjvx1Ip4f7wFzuQGul9binV0XMSZ2H1bEpyG3vFboMImI+qymJjVOXm9O8rDoMhERUbd0Osmzbds2REVFYdmyZThz5gzCw8Mxffp0ZGdn33P7uro62NjYYNmyZRgxYkS7xzU3N0d+fn6rRS6XdzY8IiJBOFgYIWa6N5L+bzLemzUcHtYmqLrVgPWHMzBu1QG8uCkFKVllnIKdaADrzEMyANi0aRNGjBgBY2Nj2Nvb449//CNKS0vvue3WrVshEokwe/bsHoi8Z6UVqFB58zZMpBL4sh4PERFRt3Q6yfPJJ59g4cKFeO655+Dt7Y3Vq1fD2dkZcXFx99zezc0Nn332GebPnw+FQtHucUUiEezs7FotRET6xlhqgHkhbtgbPR5fLQjE2CHWaFID8ecL8Hjcccz+/Ch+SM3D7cYmoUMlol7U2YdkiYmJmD9/PhYuXIgLFy5g+/btOHnyJJ577rk222ZlZeEvf/kLwsPDe/o0ekRy81CtQDdLGEg4JwgREVF3dOpOWl9fj5SUFERERLRaHxERgWPHjnUrkOrqari6usLJyQmPPvoozpw5c9/t6+rqoFKpWi1ERH2FWCzCJC8l/v1cMHZHhSMy0BlSAzHO5lZiydZUhK88gHUHr6Kitl7oUImoF3T2IVlSUhLc3NywePFiuLu7Y+zYsXj++edx6tSpVts1Njbi97//Pd599114eHj0xqnoXHKmpndSsAfr8RAREXVXp5I8JSUlaGxshFKpbLVeqVSioKCgy0F4eXlh48aN+PHHH7FlyxbI5XKEhYXhypUr7e4TGxsLhUKhXZydnbv8+UREPcnLzhwrn/DDsaWTED11KKxNZShQ3cKq3ekYE7sPy747j6tF1UKHSUQ9pCsPyUJDQ5Gbm4v4+Hio1WoUFhZix44dmDFjRqvtli9fDhsbGyxcuLBDsfS1h2RNTWqcyGwpusx6PERERN3VpT6xIlHrqS3VanWbdZ0xZswYzJ07FyNGjEB4eDj+85//YOjQoVizZk27+8TExKCyslK75OTkdPnziYh6g7WpDIsne+Lo0on4+MkR8LE3x63bTdiUnI0pnxzCgq9P4PDlYtbtIepnuvKQLDQ0FJs2bUJkZCSkUins7OxgYWHRqm109OhRfPnll9iwYUOHY+lrD8kuF1WhvPY2jAwl8HNqf1g/ERERdUynkjzW1taQSCRtGiRFRUVtGi7dCkosxujRo+/bk0cmk8Hc3LzVQkSkD2QGEjwe4ISfFo/F1v8dg6k+SohEwMH0Ysz/6gQiPj2M1Xsv42xOBZqamPAh6i8685Ds4sWLWLx4Md566y2kpKRg9+7dyMzMxAsvvAAAqKqqwty5c7FhwwZYW1t3OIa+9pDsTj2eQTBkPR4iIqJuM+jMxlKpFAEBAUhISMBjjz2mXZ+QkIBZs2bpLCi1Wo3U1FQ89NBDOjsmEVFfIxKJMMbDCmM8rJBVWoOvj17H9lM5uFJUjdV7r2D13iuwNpVi/FBbTPSyQbinDRRGhkKHTUSd1JWHZLGxsQgLC8Nrr70GAPDz84OJiQnCw8Px/vvvo7CwENevX8fMmTO1+zQ1aQq6GxgYID09HYMHD25zXJlMBplMpqtT6zZtPR531uMhIiLShU4leQAgOjoa8+bNQ2BgIEJCQrB+/XpkZ2drnyzFxMQgLy8P33zzjXaf1NRUAJriysXFxUhNTYVUKoWPjw8A4N1338WYMWPg6ekJlUqFv//970hNTcXnn3+ug1MkIur7XK1M8M7/DEd0xFDsPl+AA+lFOHKlBCXV9fj2dC6+PZ0LiViEANdBmDhMk/QZpjTr1lBZIuodXXlIVltbCwOD1s00iUQCQPMwzMvLC+fPn2/1/htvvIGqqip89tlngg/D6gi1Wq3tyRPswXo8REREutDpJE9kZCRKS0uxfPly5Ofnw9fXF/Hx8XB1dQUA5Ofnt5kO1N/fX/vvlJQUbN68Ga6urrh+/ToAoKKiAv/7v/+LgoICKBQK+Pv74/DhwwgKCurGqRER6R9zuSHmjHbGnNHOqG9owqmsMhxML8aBS0W4UlSNE5llOJFZhpW7L8FBIccEL1tMHGaL0MFWMJF1+lc6EfWSzj4kmzlzJv70pz8hLi4O06ZNQ35+PqKiohAUFAQHBwcAgK+vb6vPsLCwuOf6vupqUTVKa+ohNxSzHg8REZGOiNT9pMKnSqWCQqFAZWUl6/MQUb+UU1aLg+lFOJBejGPXSnDrdpP2PalEjGAPy+ZePrZwtzYRMFKi+xuo9+x169Zh1apV2odkn376KcaNGwcAWLBgAa5fv46DBw9qt1+zZg2++OILZGZmwsLCApMmTcLKlSvh6Oh4z+MvWLAAFRUV+P777zsck5Dfxb+SsvDm978idLAVNv9pTK9+NhERkb7p6D2bSR4iIj1063YjjmeU4uClIuxPL0JO2c1W77tZGWNicy+fIHdLyA0lAkVK1Bbv2X2HkN/FS5tP47/n8vHKlKFYMsWzVz+biIhI33T0ns2+/UREekhuKNH02hlmi3fUalwrrmnu5VOEE5lluF5ai6+PXsfXR6/DyFCCsCHWmOhlgwnDbOFoYSR0+EQ0wKnVaiRp6/Gw6DIREZGuMMlDRKTnRCIRhtiaYoitKZ4L90B1XQMSr5Rokz6FqjrsTSvE3rRCAMAwpVlzLx8bjHLltMVE1PsySmpQUl0HqYEYI50thA6HiIio32CSh4ionzGVGeBhXzs87GsHtVqNi/kqbfHm09nlSC+sQnphFb44dA1mcgOM87TBRC9bjB9qAxuzvjO1MhH1Xy2zavk7W3A4KRERkQ4xyUNE1I+JRCIMd1BguIMCiyYOQUVtPQ5dLsbB9GIculyMspp6/HQ+Hz+dzwcA+DkptMWb/RwVEIs5RTsR6V5yZikATp1ORESka0zyEBENIBbGUswa6YhZIx3R2KTGudwKHLikmbHrfF4lzuVqls/2XYGViRTjh9lg4jBbjPO0gcLYUOjwiagf0NTj0SR5xrAeDxERkU4xyUNENEBJxCL4uwyCv8sgREcMQ1HVLRxML8bB9CIcuVyC0pp67Dydh52n8yARizDKxUI7Y5eXnRlEIvbyIaLOyyqtRaGqDlKJGKNcBgkdDhERUb/CJA8REQEAbM3kmBPojDmBzrjd2ISUrPLmXj5FuFxYjZPXy3HyejlW7U6HvUKOSV62mOKtRMhgK9bUIKIOaxmqNcJZwd8dREREOsYkDxERtWEoEWOMhxXGeFgh5hFv5JbXaos3H71WgvzKW9iUnI1Nydkwlkowdog1pngrMdHLlsWbiei+tFOnu7MeDxERka4xyUNERA/kNMgYc8e4Yu4YV9y63YjjGaXYl1aIvReLUKC6hV8uFuKXi4UQiYCRzhaY4q3EZG9bDFNyWBcR3aFWq5GsrcfDJA8REZGuMclDRESdIjeUaGbgGmaL92apceGGCvvSirDvUiHO5VbiTHYFzmRX4MM96XAaZITJXraY4qNEsLsVpAZiocMnIgHllt/EjcpbMBCLMMrVQuhwiIiI+h0meYiIqMtEIhF8HRXwdVRgyRRPFKpuaRI+aYVIvFqC3PKb+OfxLPzzeBZMZQYYN9Qak700w7osTaRCh09EvaxlVi0/JwWMpWyGEhER6RrvrkREpDNKczmeCXbBM8EuuFnfiMSrJdiXVoh9l4pQXFWH+PMFiD9fALEICHAdhMneSkzxtsVgG1MO6yIaAFrq8XCoFhERUc9gkoeIiHqEkVSCqT5KTPVRoqlJjXN5lZo6PmlFSMtXaWfr+tvPl+BqZayt4zPazRKGEg7rIuqPWmbWCmaSh4iIqEcwyUNERD1OLBZhpLMFRjpb4NWIYciruIn9aYVISCtC0rVSZJXW4svETHyZmAlzuQHGD7PFFG9bTBhqC4WxodDhE5EO5JbXIrf8JiRiEQJcBwkdDhERUb/EJA8REfU6RwsjzAtxw7wQN1TXNSDxSjH2phVh/6UilNXUY9fZG9h19gYkYhFGuw1q7uWjhLu1idChE1EXJTcP1fJ1VMBUxiYoERFRT+AdloiIBGUqM8DDvvZ42NcejU1qpOaUY29z8ebLhdVIyihDUkYZ3v8pDYNtTLQJn1EuFjDgsC4ivdEyVGuMh6XAkRAREfVfTPIQEVGfoRnGYYkAV0u8/rAXsktrsTetEPsuFSI5owzXimtwrTgD/zicAQtjQ0wcZosp3kqMG2oNMzmHdRH1ZcmZzUWX3VmPh4iIqKcwyUNERH2Wi5Uxnh3rjmfHukN16zYOpRdjX1ohDqQXo6L2Nr47k4fvzuTBUCJCsLsVJntrkj7OlsZCh05Ed8mvvIms0lqIRUCgG+vxEBER9RQmeYiISC+Yyw0xc4QDZo5wQENjE1KyyjW9fNKKkFFSg8SrJUi8WoJ3d13EMKUZJnvbYrK3EiOdLSARc3p2IiG11OMZ7qBgrzsiIqIexCQPERHpHQOJGMEeVgj2sMKyGT7IKK7GvrQiJKQVIiWrHOmFVUgvrMK6g9dgbSrFxGGahE+4pzVMWPCVqNexHg8REVHvYEuXiIj0noeNKTxsTPGncR6oqK3HwfRi7E0rxKH0YpRU12N7Si62p+RCaiBG6GArTPZWYrKXLRwsjIQOnWhAaOnJE8x6PERERD2KSR4iIupXLIylmO3viNn+jqhvaMLJ62XaYV3ZZbU4mF6Mg+nFeBOAj705pvgoMcXbFr4OCog5rItI54pUt5BRUgORCBjtzp48REREPYlJHiIi6rekBmKEDbFG2BBrvPWoD64WVSOhOeFzOrscF/NVuJivwt/3XYGtmUxbuDlsiDXkhhKhwyfqF5KaZ9XysTeHwoj1eIiIiHoSkzxERDQgiEQieCrN4Kk0w4sThqC0ug4H0oux92IhjlwpRlFVHbacyMGWEzmQG4oxdoi1dliXrblc6PCJ9FZyhqYeD4dqERER9TwmeYiIaECyMpXhiQAnPBHghLqGRiRllGFfWiH2XizEjcpb2JtWhL1pRQCAEU4KTcLH2xY+9uYQiTisi6ijkpt78gSz6DIREVGPY5KHiIgGPJmBBOOH2mD8UBu8+z/DkZZfpUn4XCrC2ZwKnM2txNncSnyScBkOCrk24RMy2AoyAw7rImpPcVUdrhZVAwCC3JjkISIi6mlM8hAREd1FJBLBx8EcPg7meHmyJ4pUt7D/kqZXT+LVYtyovIV/JWXhX0lZMJZKEO5pjSneSkzysoWVqUzo8In6lBPNvXi87MwwyEQqcDRERET9H5M8RERE92FrLsdTQS54KsgFt2434ujVEuxNK8L+S4UoVNVhz4VC7LlQCJEI8He2aJ6tSwlPW1MO66IBLzlTU49njAfr8RAREfUGJnmIiIg6SG4oaR6qpYRa7Ytf81TYm1aIvWmFuHBDhdPZFTidXYFVu9PhbGmEyV6ahE+QuyWkBmKhwyfqdUnaosscqkVERNQbmOQhIiLqApFIhIecFHjISYFXpg5FfuVN7Esrwr60Qhy9VoqcspvYeOw6Nh67DjOZAcYNs8EUb1tMHGYLC2MOW6H+r6ymHpcLm+vxMMlDRETUK5jkISIi0gF7hRHmjnHF3DGuqK1vwJErJdiXVoj9l4pQUl2Pn87l46dz+ZCIRQhwHYQp3rbwdxkEd2sTWJlIObSL+p0TzUO1hipNWa+KiIiol3QpybNu3Tp8+OGHyM/Px/Dhw7F69WqEh4ffc9v8/Hy8+uqrSElJwZUrV7B48WKsXr26zXbffvst3nzzTVy7dg2DBw/GBx98gMcee6wr4REREQnKWGqAacPtMG24HZqa1EjNrcC+tELsSyvCpYIqnMgs0xakBQBzuQHcbUzhYW0C998sJjI+jyH9lJTRPHW6O+vxEBER9ZZOtxy3bduGqKgorFu3DmFhYfjHP/6B6dOn4+LFi3BxcWmzfV1dHWxsbLBs2TJ8+umn9zzm8ePHERkZiffeew+PPfYYvvvuO8yZMweJiYkIDg7u/FkRERH1EWKxCKNcBmGUyyC8Ns0LOWW12H+pCAfTi3C5sBo3Km9CdatBM1V7TkWb/ZXmMnhYm8LdxqRVEsjZ0hiGEtb5ob5LW4/Hg0O1iIiIeotIrVarO7NDcHAwRo0ahbi4OO06b29vzJ49G7Gxsffdd8KECRg5cmSbnjyRkZFQqVT4+eeftesefvhhDBo0CFu2bOlQXCqVCgqFApWVlTA3N+/4CREREQno1u1GZJXWIrOkGhklNcgorkFmiWYpq6lvdz+JWAQXS+M7iR8bzU8Pa1MozWV9evgX79l9R099FxW19fB/LwFqNXBy2RTYmHG4FhERUXd09J7dqZ489fX1SElJwdKlS1utj4iIwLFjx7oWKTQ9eV555ZVW66ZNm3bPYV0t6urqUFdXp32tUqm6/PlERERCkRtKMMzODMPszNq8V1Fbr034ZJbUIKOkBpnNSaCbtxu163/LWCqBm5UJPFp6/9iYwN3aFO7WJlAYGfbGadEAdyKzDGo1MNjGhAkeIiKiXtSpJE9JSQkaGxuhVCpbrVcqlSgoKOhyEAUFBZ0+ZmxsLN59990ufyYREVFfZ2Eshb+LFP4ug1qtb2pSo7DqFjKLmxM/dy3ZZbWorW/ExXwVLua3fQBiZSLV9Pi5K/HjYWMCF0tjyA0lvXVq1M9p6/F4sB4PERFRb+pSNcffdgFXq9Xd7hbe2WPGxMQgOjpa+1qlUsHZ2blbMRAREekDsVgEe4UR7BVGCB1i3eq9241NyC6r1fb40SSBqpFZUoNCVR1Ka+pRWlOPU1nlrfYTiQBHCyO4W5tgsI2ptvbPMDszKM3lvXl61A8kN8+sFcyp04mIiHpVp5I81tbWkEgkbXrYFBUVtemJ0xl2dnadPqZMJoNMxu6/REREdzOUiDHYxhSDbUzbvFdd14DrrYZ9aZI/GcU1qKprQG75TeSW38SRKyXafeaNccV7s3178xRIz1XevK3tRTaGPXmIiIh6VaeSPFKpFAEBAUhISGg1vXlCQgJmzZrV5SBCQkKQkJDQqi7PL7/8gtDQ0C4fk4iIiFozlRnA11EBX0dFq/VqtRqlNc31f5qHgGUUaxJAQ+9RK4jofspr6hHiYYXy2tvsBUZERNTLOj1cKzo6GvPmzUNgYCBCQkKwfv16ZGdn44UXXgCgGUaVl5eHb775RrtPamoqAKC6uhrFxcVITU2FVCqFj48PAGDJkiUYN24cVq5ciVmzZuGHH37A3r17kZiYqINTJCIiovsRiUSwNpXB2lSG0W4cXtNT1q1bhw8//BD5+fkYPnw4Vq9ejfDw8Ha337RpE1atWoUrV65AoVDg4YcfxkcffQQrK03vmA0bNuCbb77Br7/+CgAICAjAihUrEBQU1Cvn0x43axNs/tMYdHICVyIiItIBcWd3iIyMxOrVq7F8+XKMHDkShw8fRnx8PFxdXQEA+fn5yM7ObrWPv78//P39kZKSgs2bN8Pf3x+PPPKI9v3Q0FBs3boVX3/9Nfz8/LBx40Zs27YNwcHB3Tw9IiIiIuFt27YNUVFRWLZsGc6cOYPw8HBMnz69TZupRWJiIubPn4+FCxfiwoUL2L59O06ePInnnntOu83Bgwfx9NNP48CBAzh+/DhcXFwQERGBvLy83jqt++puvUYiIiLqPJG6nzxm6eic8URERCSsgXjPDg4OxqhRoxAXF6dd5+3tjdmzZyM2NrbN9h999BHi4uJw7do17bo1a9Zg1apVyMnJuednNDY2YtCgQVi7di3mz59/z23q6upQV1enfd0yccVA+i6IiIj0UUfbT53uyUNEREREHVdfX4+UlBRERES0Wh8REYFjx47dc5/Q0FDk5uYiPj4earUahYWF2LFjB2bMmNHu59TW1uL27duwtGx/yF1sbCwUCoV24cykRERE/QuTPEREREQ9qKSkBI2NjW1mDVUqlW1mF20RGhqKTZs2ITIyElKpFHZ2drCwsMCaNWva/ZylS5fC0dERU6ZMaXebmJgYVFZWapf2egURERGRfmKSh4iIiKgX/LZGjVqtbrduzcWLF7F48WK89dZbSElJwe7du5GZmamd6OK3Vq1ahS1btmDnzp2Qy9uf0Uomk8Hc3LzVQkRERP1Hp2fXIiIiIqKOs7a2hkQiadNrp6ioqE3vnhaxsbEICwvDa6+9BgDw8/ODiYkJwsPD8f7778Pe3l677UcffYQVK1Zg79698PPz67kTISIioj6PPXmIiIiIepBUKkVAQAASEhJarU9ISEBoaOg996mtrYVY3LqZJpFIAKDV1OQffvgh3nvvPezevRuBgYE6jpyIiIj0DXvyEBEREfWw6OhozJs3D4GBgQgJCcH69euRnZ2tHX4VExODvLw8fPPNNwCAmTNn4k9/+hPi4uIwbdo05OfnIyoqCkFBQXBwcACgGaL15ptvYvPmzXBzc9P2FDI1NYWpqakwJ0pERESCYpKHiIiIqIdFRkaitLQUy5cvR35+Pnx9fREfHw9XV1cAQH5+PrKzs7XbL1iwAFVVVVi7di1effVVWFhYYNKkSVi5cqV2m3Xr1qG+vh5PPPFEq896++238c477/TKeREREVHfIlLf3edXj3V0zngiIiISFu/ZfQe/CyIiIv3Q0Xs2a/IQEREREREREfUDTPIQEREREREREfUDTPIQEREREREREfUDTPIQEREREREREfUD/WZ2rZb60SqVSuBIiIiI6H5a7tX9ZO4Hvcb2ExERkX7oaPup3yR5qqqqAADOzs4CR0JEREQdUVVVBYVCIXQYAxrbT0RERPrlQe2nfjOFelNTE27cuAEzMzOIRCKdHVelUsHZ2Rk5OTmcWrQbeB27j9dQN3gdu4/XUDcG8nVUq9WoqqqCg4MDxGKOHBcS2099F6+hbvA66gavY/fxGurGQL6OHW0/9ZuePGKxGE5OTj12fHNz8wH3n6gn8Dp2H6+hbvA6dh+voW4M1OvIHjx9A9tPfR+voW7wOuoGr2P38RrqxkC9jh1pP/HxGRERERERERFRP8AkDxERERERERFRP8AkzwPIZDK8/fbbkMlkQoei13gdu4/XUDd4HbuP11A3eB2pP+P/7+7jNdQNXkfd4HXsPl5D3eB1fLB+U3iZiIiIiIiIiGggY08eIiIiIiIiIqJ+gEkeIiIiIiIiIqJ+gEkeIiIiIiIiIqJ+gEkeIiIiIiIiIqJ+gEkeIiIiIiIiIqJ+gEmeB1i3bh3c3d0hl8sREBCAI0eOCB2S3oiNjcXo0aNhZmYGW1tbzJ49G+np6UKHpddiY2MhEokQFRUldCh6Jy8vD3PnzoWVlRWMjY0xcuRIpKSkCB2WXmloaMAbb7wBd3d3GBkZwcPDA8uXL0dTU5PQofVZhw8fxsyZM+Hg4ACRSITvv/++1ftqtRrvvPMOHBwcYGRkhAkTJuDChQvCBEukI2w7dQ/bT7rH9lPXsf3UfWw/dR7bT93DJM99bNu2DVFRUVi2bBnOnDmD8PBwTJ8+HdnZ2UKHphcOHTqERYsWISkpCQkJCWhoaEBERARqamqEDk0vnTx5EuvXr4efn5/Qoeid8vJyhIWFwdDQED///DMuXryIjz/+GBYWFkKHpldWrlyJL774AmvXrkVaWhpWrVqFDz/8EGvWrBE6tD6rpqYGI0aMwNq1a+/5/qpVq/DJJ59g7dq1OHnyJOzs7DB16lRUVVX1cqREusG2U/ex/aRbbD91HdtPusH2U+ex/dRNampXUFCQ+oUXXmi1zsvLS7106VKBItJvRUVFagDqQ4cOCR2K3qmqqlJ7enqqExIS1OPHj1cvWbJE6JD0yuuvv64eO3as0GHovRkzZqifffbZVut+97vfqefOnStQRPoFgPq7777Tvm5qalLb2dmp//a3v2nX3bp1S61QKNRffPGFABESdR/bTrrH9lPXsf3UPWw/6QbbT93D9lPnsSdPO+rr65GSkoKIiIhW6yMiInDs2DGBotJvlZWVAABLS0uBI9E/ixYtwowZMzBlyhShQ9FLP/74IwIDA/Hkk0/C1tYW/v7+2LBhg9Bh6Z2xY8di3759uHz5MgDg7NmzSExMxCOPPCJwZPopMzMTBQUFre4zMpkM48eP532G9BLbTj2D7aeuY/upe9h+0g22n3SL7acHMxA6gL6qpKQEjY2NUCqVrdYrlUoUFBQIFJX+UqvViI6OxtixY+Hr6yt0OHpl69atOH36NE6ePCl0KHorIyMDcXFxiI6Oxv/93//hxIkTWLx4MWQyGebPny90eHrj9ddfR2VlJby8vCCRSNDY2IgPPvgATz/9tNCh6aWWe8m97jNZWVlChETULWw76R7bT13H9lP3sf2kG2w/6RbbTw/GJM8DiESiVq/VanWbdfRgL730Es6dO4fExEShQ9ErOTk5WLJkCX755RfI5XKhw9FbTU1NCAwMxIoVKwAA/v7+uHDhAuLi4thI6YRt27bh3//+NzZv3ozhw4cjNTUVUVFRcHBwwB/+8Aehw9NbvM9Qf8P/07rD9lPXsP2kG2w/6QbbTz2D95r2McnTDmtra0gkkjZPnoqKitpkDen+Xn75Zfz44484fPgwnJychA5Hr6SkpKCoqAgBAQHadY2NjTh8+DDWrl2Luro6SCQSASPUD/b29vDx8Wm1ztvbG99++61AEemn1157DUuXLsVTTz0FAHjooYeQlZWF2NhYNlK6wM7ODoDmiZS9vb12Pe8zpK/YdtIttp+6ju0n3WD7STfYftIttp8ejDV52iGVShEQEICEhIRW6xMSEhAaGipQVPpFrVbjpZdews6dO7F//364u7sLHZLemTx5Ms6fP4/U1FTtEhgYiN///vdITU1lA6WDwsLC2kw/e/nyZbi6ugoUkX6qra2FWNz6tiGRSDgFaBe5u7vDzs6u1X2mvr4ehw4d4n2G9BLbTrrB9lP3sf2kG2w/6QbbT7rF9tODsSfPfURHR2PevHkIDAxESEgI1q9fj+zsbLzwwgtCh6YXFi1ahM2bN+OHH36AmZmZ9smeQqGAkZGRwNHpBzMzszZj8E1MTGBlZcWx+Z3wyiuvIDQ0FCtWrMCcOXNw4sQJrF+/HuvXrxc6NL0yc+ZMfPDBB3BxccHw4cNx5swZfPLJJ3j22WeFDq3Pqq6uxtWrV7WvMzMzkZqaCktLS7i4uCAqKgorVqyAp6cnPD09sWLFChgbG+OZZ54RMGqirmPbqfvYfuo+tp90g+0n3WD7qfPYfuom4Sb20g+ff/652tXVVS2VStWjRo3i9JWdAOCey9dffy10aHqNU4B2za5du9S+vr5qmUym9vLyUq9fv17okPSOSqVSL1myRO3i4qKWy+VqDw8P9bJly9R1dXVCh9ZnHThw4J6/B//whz+o1WrNNKBvv/222s7OTi2TydTjxo1Tnz9/XtigibqJbafuYfupZ7D91DVsP3Uf20+dx/ZT94jUarW6N5NKRERERERERESke6zJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUDzDJQ0RERERERETUD/x/LEGanq3RIw4AAAAASUVORK5CYII=",
      "text/plain": [
       "<Figure size 1400x500 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "%matplotlib inline\n",
    "\n",
    "fig, (ax1, ax2) = plt.subplots(nrows=1, ncols=2, figsize=(14, 5))\n",
    "ax1.plot(history.history['loss'], label='Train Loss')\n",
    "ax1.plot(history.history['val_loss'], label='Val Loss')\n",
    "ax1.legend()\n",
    "ax2.plot(history.history['accuracy'], label='Train Accuracy')\n",
    "ax2.plot(history.history['val_accuracy'], label='Val Accuracy')\n",
    "ax2.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}