diff --git a/notebooks/examples/deep_learning.ipynb b/notebooks/examples/deep_learning.ipynb
index e7982f4e5a858b9bc377a25891aadaefa7a05be4..6fad11dc2bc2d93481a9a6ada5dcfdf06e31eb99 100644
--- a/notebooks/examples/deep_learning.ipynb
+++ b/notebooks/examples/deep_learning.ipynb
@@ -23,14 +23,16 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "import pandas as pd\n",
     "import numpy as np\n",
     "import matplotlib.pyplot as plt\n",
     "import tensorflow as tf\n",
-    "from keras.models import Sequential\n",
+    "from keras.models import Sequential, load_model\n",
     "from keras.layers.core import Dense\n",
     "from keras.layers import Dropout, Conv2D, MaxPooling2D, Flatten, Layer, Lambda\n",
     "from keras.utils import np_utils\n",
     "from keras.datasets import mnist\n",
+    "from keras.callbacks import CSVLogger\n",
     "from mpl_toolkits.axes_grid1 import ImageGrid"
    ]
   },
@@ -294,47 +296,64 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/10\n",
-      "1875/1875 [==============================] - 18s 9ms/step - loss: 0.0291 - accuracy: 0.7815 - val_loss: 0.0081 - val_accuracy: 0.9500\n",
+      "1875/1875 [==============================] - 18s 9ms/step - loss: 0.0261 - accuracy: 0.8132 - val_loss: 0.0086 - val_accuracy: 0.9442\n",
       "Epoch 2/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0076 - accuracy: 0.9524 - val_loss: 0.0079 - val_accuracy: 0.9510\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0084 - accuracy: 0.9472 - val_loss: 0.0077 - val_accuracy: 0.9523\n",
       "Epoch 3/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0059 - accuracy: 0.9622 - val_loss: 0.0066 - val_accuracy: 0.9583\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0065 - accuracy: 0.9593 - val_loss: 0.0065 - val_accuracy: 0.9582\n",
       "Epoch 4/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0051 - accuracy: 0.9678 - val_loss: 0.0062 - val_accuracy: 0.9614\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0055 - accuracy: 0.9653 - val_loss: 0.0053 - val_accuracy: 0.9670\n",
       "Epoch 5/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0045 - accuracy: 0.9715 - val_loss: 0.0056 - val_accuracy: 0.9649\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0048 - accuracy: 0.9705 - val_loss: 0.0065 - val_accuracy: 0.9598\n",
       "Epoch 6/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0041 - accuracy: 0.9745 - val_loss: 0.0049 - val_accuracy: 0.9698\n",
+      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0043 - accuracy: 0.9736 - val_loss: 0.0052 - val_accuracy: 0.9680\n",
       "Epoch 7/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0037 - accuracy: 0.9773 - val_loss: 0.0059 - val_accuracy: 0.9647\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0039 - accuracy: 0.9756 - val_loss: 0.0047 - val_accuracy: 0.9715\n",
       "Epoch 8/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0034 - accuracy: 0.9794 - val_loss: 0.0049 - val_accuracy: 0.9697\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0037 - accuracy: 0.9775 - val_loss: 0.0047 - val_accuracy: 0.9704\n",
       "Epoch 9/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0032 - accuracy: 0.9809 - val_loss: 0.0054 - val_accuracy: 0.9676\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0033 - accuracy: 0.9797 - val_loss: 0.0046 - val_accuracy: 0.9705\n",
       "Epoch 10/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0031 - accuracy: 0.9811 - val_loss: 0.0045 - val_accuracy: 0.9717\n"
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0031 - accuracy: 0.9808 - val_loss: 0.0042 - val_accuracy: 0.9738\n"
      ]
     }
    ],
    "source": [
-    "model_One = Sequential() # A sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor.\n",
+    "BASE_PATH = \"./saved_models/\"\n",
     "\n",
-    "model_One.add(Lambda(preprocess_image)) # in this first layer we normalize the image\n",
+    "# Switch this to True or False to enable/disable loading of the model from disk\n",
+    "# Make sure to run the entire notebook at least once before setting this to True.\n",
+    "LOAD_MODEL1 = False\n",
     "\n",
-    "model_One.add(Dense(90, input_dim=784, activation='relu')) # actual input layer\n",
-    "model_One.add(Dense(50, activation='relu')) # hidden layer 1\n",
-    "model_One.add(Dense(50, activation='relu')) # hidden layer 2\n",
-    "model_One.add(Dense(50, activation='relu')) # hidden layer 3\n",
-    "model_One.add(Dense(50, activation='relu')) # hidden layer 4\n",
-    "model_One.add(Dense(50, activation='relu')) # hidden layer 5\n",
-    "model_One.add(Dense(50, activation='relu')) # hidden layer 6\n",
-    "model_One.add(Dense(10, activation='sigmoid')) # output layer\n",
+    "model_One = None\n",
     "\n",
-    "model_One.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])\n",
+    "if LOAD_MODEL1:\n",
+    "    model_One = load_model(BASE_PATH + 'deep_learning_model_One.h5')\n",
+    "else:\n",
+    "    model_One = Sequential() # A sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor.\n",
     "\n",
+    "    model_One.add(Lambda(preprocess_image)) # in this first layer we normalize the image\n",
+    "\n",
+    "    model_One.add(Dense(90, input_dim=784, activation='relu')) # actual input layer\n",
+    "    model_One.add(Dense(50, activation='relu')) # hidden layer 1\n",
+    "    model_One.add(Dense(50, activation='relu')) # hidden layer 2\n",
+    "    model_One.add(Dense(50, activation='relu')) # hidden layer 3\n",
+    "    model_One.add(Dense(50, activation='relu')) # hidden layer 4\n",
+    "    model_One.add(Dense(50, activation='relu')) # hidden layer 5\n",
+    "    model_One.add(Dense(50, activation='relu')) # hidden layer 6\n",
+    "    model_One.add(Dense(10, activation='sigmoid')) # output layer\n",
+    "\n",
+    "    model_One.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])\n",
+    "    \n",
+    "history1 = None\n",
     "amount_epochs = 10 # amount of the epochs\n",
     "\n",
-    "history1 = model_One.fit(XTrain, YTrain, epochs=amount_epochs, validation_data = (XTest, YTest)) # Train the neural network"
+    "if LOAD_MODEL1:\n",
+    "    history1 = pd.read_csv(BASE_PATH+'deep_learning_traing_model_One.log', sep=',', engine='python')\n",
+    "else:\n",
+    "    csv_logger = CSVLogger(BASE_PATH+'deep_learning_traing_model_One.log', separator=',', append=False)\n",
+    "    history1 = model_One.fit(XTrain, YTrain, epochs=amount_epochs, validation_data = (XTest, YTest), callbacks=[csv_logger]).history # Train the neural network\n",
+    "    model_One.save(BASE_PATH+'deep_learning_model_One.h5')"
    ]
   },
   {
@@ -353,7 +372,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAABbIAAAG5CAYAAABbbcJdAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAACHOElEQVR4nOzdeXxV9Z3/8VcSCGFHFgUSBLVRQKuiBru5UsWlFCuOBq1gh8GqpdVa+1NHO4hdmWmttnXUQVGgFYpbxVKKreAyOmqAgAuLQYImAWSVfQ3398e5N8nNRgK5OTfJ6/l4fB93O+fcz0kinrzzvZ9vChBBkiRJkiRJkqQklRp2AZIkSZIkSZIk1cYgW5IkSZIkSZKU1AyyJUmSJEmSJElJzSBbkiRJkiRJkpTUDLIlSZIkSZIkSUnNIFuSJEmSJEmSlNQMsiWpCejbty+RSIS0tLRDbjt69GjeeOONRqhKkiRJatm8TpekxmOQLUkNrLCwkL1799KtW7e45xctWkQkEqFv374hVVa/C21JkiSpOUnm6/SY9u3bs337dv72t7+FXYokJR2DbElKgMLCQkaOHFn2+JRTTqFdu3YhViRJkiQp2a/TR4wYwd69e7nooos45phjGvW9newiKdkZZEtSAkybNo1Ro0aVPR49ejRTp06N26ZTp05MmTKF9evXs3r1au655x5SUlIASE1N5b/+67/YsGEDH3/8MZdffnmVfR9//HHWrFlDcXExP/3pT0lNPbJ/0nv16sWLL77Ipk2bKCgo4N/+7d/KXsvJySEvL4+tW7eybt06fvOb3wDQpk0bpk2bxsaNG9myZQvvvvsuRx999BHVIUmSJCVKsl+njx49mkcffZT33nuPb3/723GvffWrX+XNN99ky5YtfPrpp4wePRqAjIwMfv3rX7N69Wo+//xz3njjDTIyMjjvvPMoKiqKO0ZhYSFDhgwBYPz48TzzzDNMmzaNrVu3csMNN5CTk8Nbb73Fli1bWLNmDb///e9p3bp12f4DBw7k5ZdfZtOmTaxbt467776bY445hp07d9K1a9ey7QYNGsT69etp1apVnc9dkuoi4nA4HI6GG4WFhZEhQ4ZEli9fHunfv38kNTU1UlRUFDn22GMjkUgk0rdv3wgQmTJlSuQvf/lLpEOHDpG+fftGVqxYEfnXf/3XCBD57ne/G1m2bFkkKysrctRRR0XmzZsXiUQikbS0tAgQef755yOPPvpopF27dpEePXpE3nnnnciNN94YASKjR4+OvPHGG9XW1rdv37jjVByvvfZa5OGHH460adMmctppp0XWr18fueCCCyJA5K233op8+9vfjgCR9u3bR84+++wIELnxxhsjs2bNirRt2zaSmpoaOeOMMyIdO3YM/XvgcDgcDofD4XBUHsl8nQ5Ejj322EhpaWlkwIABkdtvvz2yZMmSuNe2bdsWyc3NjbRq1SrStWvXyGmnnRYBIn/4wx8i8+fPj/Tu3TuSmpoa+fKXvxxJT0+PnHfeeZGioqJqvwZAZPz48ZF9+/ZFhg8fHklJSYlkZGREzjjjjMjZZ58dSUtLi/Tt2zeydOnSyK233hoBIh06dIisWbMmcvvtt0fatGkT6dChQ2Tw4MERIDJ79uzITTfdVPY+DzzwQOR3v/td6N9zh8PR7EboBTgcDkezGrGLw3vuuSfyi1/8IjJ06NDIyy+/HElLSyu7QE5NTY3s3bs3MmDAgLL9brzxxsj8+fMjQOSVV16JfPe73y177aKLLiq7QD766KMje/bsiWRkZJS9npubG5k3b14EDi/IzsrKihw4cCDSoUOHsud+8YtfRJ588skIBCH3fffdF+nWrVvcft/5zncib775ZuSLX/xi6F93h8PhcDgcDoejtpHM1+lA5J577onk5+dHgEjv3r0jBw4ciJx++ukRIHLXXXdFnn/++Sr7pKSkRHbt2hU59dRTq7xWlyD7tddeq/Vrduutt5a9b25ubmTRokXVbnf11VdH/vd//zcCRFJTUyNr166N5OTkhP49dzgczWv4GQ9JSpBp06bx+uuvc9xxx1X5uGL37t1JT0/nk08+KXvuk08+ITMzE4DevXvHfQyw4nZ9+/aldevWrF27tuy51NTUKh8brI/evXuzefNmduzYEfeeZ511FgBjxozh/vvvZ/ny5RQWFjJhwgRmz57NtGnT6NOnDzNmzKBLly788Y9/5J577uHAgQOHXYskSZKUSMl6nT5q1CgmTZoEwJo1a3jttdcYPXo0ixcvpk+fPnz88cdV9unevTtt27at9rW6qFxbdnY2DzzwAGeddRbt2rWjVatWLFy4EKDGGgBefPFFHn30Ufr168dJJ53E1q1bycvLO6yaJKkm9siWpAT59NNPKSws5LLLLuP555+Pe23jxo3s27cvbmX0Y489lpKSEgDWrl1Lnz594l6LKSoqYu/evXTv3p2jjjqKo446is6dO3PKKaccdq1r1qyha9eudOjQodp6Vq5cybXXXsvRRx/NxIkTefbZZ2nXrh0HDhzg/vvv5+STT+YrX/kK3/jGN+J6DkqSJEnJJhmv07/85S9z4okncvfdd7N27VrWrl3L2WefzbXXXktaWhpFRUWccMIJVfbbuHEju3fvrva1nTt3xi1kmZqaSo8ePeK2iUQicY8feeQRli9fTnZ2Np07d+bf//3fy/qDFxUVcfzxx1db/969e5k5cybf/va3uf7665k2bdohz1mS6ssgW5ISaMyYMVx44YXs2rUr7vmDBw8yc+ZMfv7zn9OhQweOPfZYbr/9dv74xz8CMHPmTH7wgx+QmZlJly5duOuuu8r2XbduHS+//DK/+c1v6NixIykpKRx//PGce+65da6rTZs2caOkpIS33nqLX/7yl7Rp04YvfvGLjBkzpqye6667ju7duxOJRPj888/LzuH888/nlFNOITU1lW3btrF//34OHjx4hF81SZIkKbGS7Tp99OjRvPzyywwcOJDTTz+d008/nVNOOYW2bdty6aWX8qc//Ymvf/3r/Mu//AtpaWl07dqV0047jUgkwuTJk3nggQfo1asXqampfOlLXyI9PZ2PPvqIjIwMLrvsMlq1asW9995LmzZtaq2jY8eObNu2jR07dnDSSSdx8803l73217/+lV69enHrrbeSnp5Ohw4dGDx4cNnrU6dO5YYbbuCb3/ymQbakhDDIlqQEWrVqVdlH8Sr7/ve/z86dO1m1ahX/+7//y9NPP83kyZMBmDRpEnPnzmXJkiUsWrSoykyRUaNGkZ6eztKlS9myZQvPPvssvXr1qnNdO3fuZM+ePWXjwgsvZOTIkfTr1481a9bwwgsvMH78eF555RUALrnkEj788EO2b9/OQw89RG5uLnv27KFnz548++yzbNu2jWXLlvHaa6950SpJkqSkl0zX6W3atOHqq6/m97//PZ999lnZWL16NdOmTWP06NEUFRVx2WWX8aMf/YjNmzezePFiTjvtNADuuOMO3n//ffLy8ti8eTMTJ04sm2hyyy238Pjjj1NSUsLOnTspLi6utZY77riDa6+9lu3btzNp0iT+/Oc/l722Y8cOLrroIoYNG8a6desoKCjgggsuKHv9rbfe4uDBgyxatIhPP/201veRpMORQtAsW5IkSZIkSTpsr7zyCk8//TRPPPFE2KVIaoYMsiVJkiRJknREzjrrLP7xj3/Qp0+fuEXkJamh2FpEkiRJkiRJh+2pp57in//8J7fddpshtqSEcUa2JEmSJEmSJCmpOSNbkiRJkiRJkpTUWoVdQGNYv349n3zySdhlSJIkqYH17duXo48+OuwyFAKv8SVJkpqnmq7xW0SQ/cknn5CTkxN2GZIkSWpgeXl5YZegkHiNL0mS1DzVdI2f0NYiQ4cOZfny5RQUFHDnnXdWeT09PZ0ZM2ZQUFDA22+/Td++fQHIyckhPz+f/Px8Fi9ezBVXXFHnY0qSJEmSJEmSmpeEBdmpqak8/PDDXHrppQwcOJCRI0cyYMCAuG3GjBnDli1byM7O5re//S0TJ04E4IMPPuCss85i0KBBXHLJJTz22GOkpaXV6ZiSJEmSJEmSpOYlYUH24MGDWblyJYWFhezfv58ZM2YwfPjwuG2GDx/OlClTAHj22WcZMmQIALt376a0tBSAjIwMIpFInY8pSZIkSZIkSWpeEtYjOzMzk6KiorLHxcXFnH322TVuU1paytatW+nWrRubNm1i8ODBTJ48mb59+3L99ddTWlpap2PGjB07lhtvvBGA7t27N/TpSZIk1eioo47itttuo1+/fqSkpIRdTpMXiURYvXo1Dz74IFu2bAm7HEmSJEkhSNrFHt99911OOeUU+vfvz5QpU5gzZ0699p80aRKTJk0CXARIkiQ1rttuu40FCxZw//33l33KTIcvLS2Nyy+/nNtuu43x48eHXY4kSZKkECSstUhJSQl9+vQpe5yVlUVJSUmN26SlpdG5c2c2bdoUt83y5cvZsWMHp5xySp2OKUmSFLZ+/frxt7/9zRC7gZSWljJ79mz69esXdimSJEmSQpKwIDsvL4/s7Gz69etH69atyc3NZdasWXHbzJo1i9GjRwNw1VVXMW/ePCD45S8tLQ2AY489lv79+7N69eo6HVOSJClsKSkphtgNrLS01DYtkiRJUguWsNYipaWljBs3jrlz55KWlsbkyZNZunQpEyZMYMGCBbz00ks88cQTTJs2jYKCAjZv3kxubi4AX/va17jrrrvYv38/Bw8e5JZbbimbqV3dMSVJkiRJkiRJzVdCe2TPmTOnSm/rin0N9+7dy9VXX11lvz/+8Y/88Y9/rPMxJUmSVK5r16688sorAPTs2ZPS0lI2bNgAwODBg9m/f3+N+5555pmMGjWKW2+9tdb3ePPNN/nqV7/acEVLkiRJUi2SdrFHSZIkHZ7NmzczaNAgIJhEsGPHDn7zm9+UvZ6WllZj65OFCxeycOHCQ76HIbYkSZKkxpSwHtmSJElKHk8++SSPPPIIb7/9Nv/5n/9JTk4Ob731FosWLeLNN9/kxBNPBOC8887jpZdeAoIQ/IknnmD+/Pl8/PHHfP/73y873vbt28u2nz9/Ps888wzLli2L+1TdpZdeyrJly1iwYAEPPfRQ2XElSZIkqb6ckS1JkpRIlwA9G/iY64C/13+3rKwsvvKVr3Dw4EE6duzIOeecQ2lpKUOGDOEXv/gFV111VZV9+vfvzwUXXEDHjh1ZsWIFjzzyCAcOHIjbZtCgQZx88smsWbOmrOXIggULeOyxxzj33HNZvXo1Tz/99GGerCRJkiQZZEuSJLUYzzzzDAcPHgSgc+fOTJkyhezsbCKRCK1bt652n9mzZ7Nv3z42bdrE+vXrOeaYYygpKYnb5t133y17bvHixfTr148dO3awatUqVq9eDcD06dO58cYbE3dykiRJkpo1g2xJkqREOoyZ04myc+fOsvs//elPmT9/PldeeSV9+/bl1VdfrXafvXv3lt0vLS2lVauql4912UaSJEmSjoS/ZTS0VOBoYBOwP+RaJEmSatC5c+eyWdQ33HBDgx9/xYoVHH/88fTt25dPPvmEa665psHfQ5IkSUoKKdXcby7P7QG2kRQMshtaP2AUMA34ONxSJEmSavKf//mfTJkyhXvvvZfZs2c3+PH37NnDLbfcwt///nd27txJXl5eg7+HJEmSRArQOjrS63m/LtulVnif6m6bu8XAX0KuISoFiIRdRKLl5eWRk5PTOG/WBrgLeBV4rXHeUpIkJZepU6cyatSosMsIXfv27cvamTz88MMUFBTw4IMPHvbxqvu6Nup1npKK33tJkpqIFOofHtcniK5+qZfa7SPopLC/DvcPRveJVLptjOca871qeu5zYA2NqqbrPGdkN7S9wHqgT9iFSJIkhWvs2LGMHj2a9PR08vPzeeyxx8IuSZIkSTVJI5igWXmkc2RBdH3TxwhVQ+XY4x3VvFbf+7YCbrIMshOhCDiFFjLfXZIkqXoPPvjgEc3AliRJUh2kUn0AnVHP5+s6szlCzSHx9lpeq+v9A4fxNVCLYJCdCMXAWUB3YEPItUiSJEmSJCn5pNAwAXR6Hd7rIEEXgdjYQzC7eVM1z++tNGJBc+zWoFkhMchOhKLobR8MsiVJkiRJkpqTWM/nIw2g29ThvSJUDZl3AVs4dABd8XnbaagZMMhOhE0E/6hkAYtCrkWSJEmSJElVpQHtoqNthfvtKj1fXRCdUofjVw6Y9wBbqXv4HAugbVsrAQbZiVOMCz5KkiRJkiQ1hlZUH0bX9lxtM6L3ALsJJiruIej9XNfwOdaOwwBaalAG2YlSBJxI8I/j7pBrkSRJLcq8efP41a9+xcsvv1z23K233spJJ53ELbfcUmX7+fPnc8cdd7Bw4UJmz57Ntddey9atW+O2GT9+PDt27OA3v/lNje87fPhwPvroI5YtWwbAhAkTeP3113nllVca6MyUDIYOHcpDDz1EWloajz/+OBMnTox7/dhjj2Xy5Mn06NGDzZs38+1vf5uSkhLOP/98fvvb35Zt179/f3Jzc3nxxRd58sknOe+888p+7m644QaWLFnSqOclSUoirahbEF1x1NYneg9BIL0L2EnQBnZXpbG70v3SBj4nSUfMIDtRiqO3mcDKMAuRJEktzfTp08nNzY0LsnNzc/l//+//HXLfyy+//LDf94orruCvf/1rWZA9fvz4wz6WklNqaioPP/wwF110EcXFxeTl5TFr1qyy7znAr3/9a6ZOncrUqVO54IIL+OUvf8moUaN49dVXGTRoEABHHXUUK1eujPsZ/fGPf8xzzz3X6OckSUqwiqF0Xdp41CeU3gGsJz6ErhxOG0pLzYZBdqKUEKwI2weDbEmS1KieffZZfvazn9G6dWv2799P37596d27NyNHjuSBBx6gbdu2PPvss9x3331V9i0sLOSss85i06ZN/Pu//zujR49m/fr1FBUVsXDhQgD+7d/+jRtvvJH09HRWrlzJ9ddfz+mnn843v/lNzjvvPO69915GjBjBT37yE/7617/y3HPPceGFF/LrX/+aVq1akZeXx80338y+ffsoLCxkypQpDBs2jNatW/Mv//IvrFixopG/YqqrwYMHs3LlSgoLCwGYMWMGw4cPjwuyBw4cyO233w4Es/3/8pe/VDnOVVddxZw5c9i9248uSlKT0pq6BdEVR+tajhcLoHcTtO74jJpnScceH2zgc5LUZBhkJ8o+gn+As8IuRJIkhem3wOkNfMzFwA9reX3Lli28++67XHrppcyaNYvc3FxmzpzJL37xC7Zs2UJqaiqvvPIKX/ziF3n//ferPcYZZ5xBbm4up59+Oq1atWLRokVlQfbzzz/P448/DsBPf/pTxowZwx/+8AdmzZpVFlxX1KZNG5566imGDBlCQUEBU6ZM4eabb+ahhx4CYOPGjZx55pncfPPN3HHHHYwdO/ZIv0RKkMzMTIqKisoeFxcXc/bZZ8dts2TJEq688kp+97vf8a1vfYtOnTrRtWtXNm/eXLZNbm4uDzzwQNx+P//5z/mP//gPXnnlFe666y727dtX5f3Hjh3LjTfeCED37t0b8tQkqeVJJT54bl/D/fqG0ruAbVQNpSuH04bSkurJIDuRioFTCVaytcG/JElqRLH2IrEge8yYMVx99dXceOONtGrVil69ejFw4MAag+xzzjmHF154oWzG7KxZs8peO+WUU/jZz35Gly5d6NChA3Pnzq21lpNOOonCwkIKCgoAmDJlCt/73vfKguznn38egIULF3LllVce8bkrXHfccQd/+MMfuOGGG3j99dcpLi6mtLT8M909e/bki1/8YtzPzd133826detIT0/nf/7nf7jzzjv56U9/WuXYkyZNYtKkSQDk5eUl/mQkqSlpTdUAurZwui1BXlGdWPuOnQSh9DpqniUdWwzRUFpSghlkJ1IRkAMcTfCXSEmS1OLUNnM6kV588UV++9vfMmjQINq1a8fmzZu54447yMnJ4fPPP+fJJ58kIyPjsI791FNPccUVV/Dee+8xevRozj///COqde/evQCUlpbSqpWXp8mspKSEPn36lD3OysqipKQkbpu1a9cyYsQIANq3b8+IESPiFg+9+uqreeGFFzhw4EDZc+vWrQNg3759PPnkk9xxxx2JPA1JSn4p1H22dOxxTbOlS4kPnddVeryz0n17SktKUv6mkEixBR+zMMiWJEmNaufOncyfP5/Jkyczffp0OnXqxM6dO9m6dStHH300l156Ka+++mqN+7/++us89dRT/PKXv6RVq1YMGzaMxx57DICOHTuydu1aWrVqxXXXXVcWZG7fvp2OHTtWOdaKFSvo168fJ5xwAh9//DHXX389r732WkLOW4mVl5dHdnY2/fr1o6SkhNzcXK699tq4bbp168bmzZuJRCLcfffdTJ48Oe71kSNHcvfdd8c917Nnz7Iw+4orruCDDz5I7IlIUmNrRf1nS6fWcKy9lIfPscUOK4bRlcPpPYk4IUlqfAbZibSZ4H8efYCFIdciSZJanOnTp/OXv/yF3NxcVqxYQX5+PsuXL6eoqIg333yz1n3z8/P585//zJIlS1i/fn1cG4ef/OQnvPPOO2zYsIF33nmnLLyeMWMGkyZN4gc/+AFXXXVV2fZ79+7lO9/5Ds8880zZYo+PPvpoYk5aCVVaWsq4ceOYO3cuaWlpTJ48maVLlzJhwgQWLFjASy+9xPnnn88vf/lLIpEIr7/+Ot/73vfK9u/bty99+vSp8oeMP/3pT/To0YOUlBQWL17MTTfd1NinJkl1lwJkUL/Z0uk1HOsg8QH0eqoPoyvOlj5Q7ZEkKSFSSZ7OQS2ie3NeXh45OTnhvHku0B34QzhvL0mSGt/UqVMZNWpU2GU0O9V9XUO9zlOo/N5LanBtgI41jMoBdU2zpfdR++zoyq/toQWkMpKSVTuCRhJ9Kt1WvP8s8N1Grqum6zxnZCdaMdCf4CdjV8i1SJIkSZLU0rSm5oC64qhu1vQegvYdO4CNHDqcdra0pCTRjuqD6Yq3R1Wz33qCOLMQeANIpoaABtmJVhS9zQI+CrMQSZIkSZKakTSgA4cOqNtWs+9+YHt0rCX4fX1bhee2E4TX+xJ6BpJ0WNpTc0B9qJC6iPKQuoggtI7dlhC04U9WBtmJtoagkYxBtiRJLUYkEiEtLY3S0tKwS2k20tLSiET87LUktQgp1C2gbl/NvqWUB9EbCdKa7dUMF0CsVhpBfHF8hXEssAn4ODpWAqsx42/OOhN8708Ajos+t5Xgbz3V3W4neXooNwexkLq2dh+HCqlfJwimm1JIXRcG2Ym2H1hH8JMmSZJahNWrV3P55Zcze/Zsw+wGkJaWxuWXX87q1avDLkWSdCRSCGZHHyqg7kDVHtQHCVp4bCdIzoopD6UrzqTejT2nDyEWUlY3+hJ0YonZTxB+dSP41sQcJAjHVhIfcMfu70joGehIpQCZBEH1CZSH1rHbbodxzNh/mjWF3bHb2l7bfbgn1IS059DtPrpUs99nBP/sfUzQ6qNiQF1EMI+2qYfUdWGQ3RiKgEEk1zKfkiQpYR588EFuu+02RowYQUpKStjlNHmRSITVq1fz4IMPhl2KJKkmGdStD3VaNfvGAurtBGlNdTOod+Lv03XUimAWdXVB9XFA10rbbwBWAXnAn6P3Y6OEYJI7QA/gC5SHn7H7VwBHVzrmZ1QfcK8kmCivxMug/PteObA+jmBt05j9wCcE3/OZBN+rVdHbQoL/9DoR/BEkdtu5mucq3nYh+MNI7LnqPkBR2X4OHYQfKhjfRnit6iuG1DXNpu5SzX6VQ+pYQN3SQuq6MMhuDMXA2QT/sq8LuRZJkpRwW7ZsYfz48WGXIUnSkUslSF5qCqY7RW9bV7PvHsqD6E+oGk5vI5i664eX6q0rNc+qPpb4vxfsJWgFsgp4m/igOtZ5pS42RMf/VfNaR6oG3CcA5wHXET/BfhvVB9wfE8QnTqivux5UH1SfAPSutG3s6/4B8CLlQfUq4FMO/Z/hToJ28ocrjeCfi/oG4lnAyRWeq+6fmsp2UfdZ4DUF45U/VdCBmtt8xG67VFPLZwRh9MfAq1Tf7sM2PXVnkN0YYgs+9sEgW5IkSZKUfDoA3Ql6ClQcR1F1FnVs2uR2ghSmuhnU26Pb6bCkE8xmPY7qw+rOlbZfRxBIvgX8kfiwOrZ0VyJtBxZHR2VtgH5Unc19KjCc4Fxj9hCE65WD7tjM4Jb2IxWbXV9dUH088e1eoHxW71zKv26xwHpT45Rco1JgS3QciQyqD70PFYj3rvS4LvXG/t4Wm2Fe2TqCr/lKYD7xAbUhdWIYZDeGzwl++rMIPqsjSZIkSVJja0PVoDo2KvYZOECQeq0HlkXvV+xD7UKJDSI2m7a6kUX8LOY9lAfTbxAfVK8mmC2brPYCK6KjslSCOX+VZ3J/ATif4O8rMaXU3pc7mb8GtYnNZq9uZvWxxAd3FX8OXqVqC5CW0H5iT3R8dgTHSCX42aot/K54fxvV96Q2pG58BtmNpRgXfJQkSZIkJVYawSzqykF1d+JTwQjBpKtNBKnMJoLmxbHQ2v4ORyw2E7mmsLpDpe3XUB5Qrqo01tE8vyUHCbrOfALMq+b1o6m+L/eVBH8IqGgdNfflDnM2cgrBbOCaWoB0r7R9rGf528CfiG8Bsobm+XPQ2A5S3k9bTYtBdmMpAgYQdH5vqn8mlCRJkiSFL4VgGmfloLobweffK07l3UmQ4n0UvY2NLYS3Iloz0pOqiylWnFVd0U7K+1LPo+qs6t2NUnHTsj463qrmtU5U35f7AmBUpW23UnNf7hKOPBzOIPijReWgOvYz0bbCtgcIelJ/DDxLfFC9CsNVqTYG2Y2lOHqbRfWfp5EkSZIkqaIM4kPq2OhKfGPhfQTh9BrgfeIDa9uAHJGuBLNp+1F1RvVxQLtK2xcRhJH/oOqs6vWNUnHLsQ3Ij47K2hB8fyrP5j4d+BbxCwbG2nVUN5t7NeV9ubtRcwuQyn+02B7dfzkwm/gWIJ/i35Ckw2WQ3VjWEDR06oNBtiRJkiQp0IogLa2ub3X7CtsdJJhFvYlgSm/FsNopnPWSQTCTOjZ61fD4GOL/XgBBQLmKYIL734kPqj+hZfQobgr2EoTIy6t5LY3yvtyVZ3NfSPx/dqUE8xK7UHWBzRKC7/s/iQ+qPybo0iOp4RlkN5YDwFqq/plOkiRJktS8pRCkYNWF1V2ir8dsJwinl1MeVG8k6Gdd2lgFNz0pBBPXDxVO9yT4kld2kGDG9Lro+JDgV/jY49UEQaUBZdNXSvD9XA28Us3rxxAfcB9H8J9fLKSOtYexFYzU+AyyG1MxcCZBv7KDIdciSZIkSWpY7ag+rO5G/G/fewkC6mJgMeWB9Wac0ltJOw4dTMdmT1cXcGynPIx+D3i5wuOKQfUG/DuBAp9FR3V9uSWFyyC7MRUBXyL4v+yakGuRJEmSJNVfa6q2Aon1sK64olspQTC9iaDpbsVWIDsasd4klAocTd3ae3SsZv9SgqAxFkQvpmowHRs7E3cakqRGZpDdmIqit1kYZEuSJElSsmtL0FegH+VhdeVGuVsJwukPiA+rP6fFfRK3I3Vr7dGDoE9xZVspD6MXUjWcjt3fRIv70kqSMMhuXNuiow/wbsi1SJIkSZLitaJ8FbjjCdLXFIJ2HxsImupW7Fu9GdgfRqGNJ50geO7JoWdQt6tm//2UB9FFBL8KV5wxHQunP8Oew5Kk2hlkN7YiXPBRkiRJkpJBCkFz5eMJwutjCVqHlBL0r55PsLLbGprNFOBWBMF0D4L2Hoe6rTwBPWYz5UH021Tfd3pddLtIYk5FktTCGGQ3tmLgZKADLb4vmiRJkiQ1us6UB9fHAe2jz68n6GfxMfAJsC+U6uotjaDrSV2D6aNqOM4Bgknm6wkmny+I3sYeVwyqP6PJfHkkSc2IQXZji/XJ7gMsC7MQSZIkSWoBMgh6XMfC627R57cTLMK4Kjq2h1FcVakEJdYURld+rlv1h6GUoANKLIheTHwwXfl2C86cliQlN4PsxraW4E/dWRhkS5IkSVJDSyP4fev46MgkSIf3EfS4ziOYdb2hccpJAbpSt9nSPQiC6dRqjnOQIJiOhc8fUHMovZ4gmG4m3VAkSQIMshtfKUGY3SfsQiRJkiSpmTia8uC6H8EKhQeBEuANghnXxQS/jx2hFKALdQ+muxNk69WpGEwvA16j5mB6c8OUL0lSk2WQHYYiYDDB1YxXIpIkSZJUPx0pD66Pjz6GoMnzYoLgejWw5/AOnwJkA2cAZwKnAj0pb+1R0y/SWygPnz8C3qTmWdObCD6sK0mS6sYgOwzFwFcIroRKQq5FkiRJkpJdOuV9ro8nmO4MsJPyHtergK31P3QqcBJBYB0LrgdRno3vIWjjsQp4h5qD6Y3A/vq/vSRJqiOD7DBUXPDRIFuSJEmS4qUCvQkWZzyeoOd1GkFS/Anls64/o14rFKYBA4gPrU8H2kdf3wUsAaYAC4FFwFKcOS1JUjIwyA7DduBzgosxSZIkSVKwyuHxBOF1PyCDIKReC7xFEFwXUedUuRVwMvGh9WlA2+jrOwjy8McpD62XY/dHSZKSlUF2WIpxwUdJkiRJLVd74DjKw+vO0ee3UN7LoxDYfehDpQOnEB9anwq0ib6+jSCofoTy0PojgvUgJUlS02CQHZYigiutTgRXVZIkSZLUnLUGjqU8uO4ZfX43QWD9OkF4vaX2w2QAXyQ+tD6FIMwmuvsi4HeUh9YrqVcHEkmSlIQMssNSHL3NImi6JkmSJEnNSQrQi/IFGo8l+A30AMHEnleAjwlah9SQMrclaAdSMbQ+mfJfZDcRhNUPRG8XEmTikiSp+THIDss6goVK+mCQLUmSJKl5OIry4Po4oF30+XXAuwTB9acEvwtV0p5g4cUzKQ+uBxAs0AiwniCo/ivlofWniTgHSZKUlAyyw1IKrMEFHyVJkiQ1XW0p73N9PNA1+vxWYAVBq5BVwM743TpRNbQ+CUiNvr6WIKh+jqA1yEKgJFHnIEmSmgSD7DAVA1+i/ON1kiRJkpTM0gg+VXoCQXDdm6CFyF6Cnh5vE8y63lS+SxdgEPGh9YkVDllMEFRPpzy0XpfIc5AkSU2SQXaYioCvEvSNKwq5FkmSJEmqThqQA3wB6EuwaGMpQQL9KsGM6xLgYDAhu2I/6zMIMu+YTwiC6ikEofUigpYhkiRJh2KQHaaKCz4aZEuSJElKRicClwAbCFLoVcBq6LGvamjdr8JuHxME1ZMoD60rTNSWJEmql9RDb6KE2QFsIfhoniRJktQEDB06lOXLl1NQUMCdd95Z5fVjjz2Wf/7znyxZsoT58+eTmZlZ9tqBAwfIz88nPz+fF198sez5fv368fbbb1NQUMCMGTNo3bp1o5yLDi0d6NgTMjfD5Y/AT/4Of/kIPt0XzKSeA/wcOIWgq8iPgSEEaz5+AbgamAj8A0NsSZJ0ZBI6I3vo0KE89NBDpKWl8fjjjzNx4sS419PT05k6dSpnnnkmmzZt4pprruGTTz7h61//Or/61a9IT09n3759/PjHP2b+/PkAzJ8/n169erF7924ALr74YjZs2JDI00isIuKnLUiSJElJKjU1lYcffpiLLrqI4uJi8vLymDVrFsuWLSvb5te//jVTp05l6tSpXHDBBfzyl79k1KhRAOzevZtBgwZVOe7EiRP57W9/y5///GceeeQRxowZw6OPPtpo55UsWgNt6jjS67HtkewPwPzoAA4SrOH4OsHk7IXAYmBbQ34hJEmSqpGwILsuF7ljxoxhy5YtZGdnc8011zBx4kRyc3PZuHEjw4YNY+3atZx88snMnTuXrKyssv2uu+46Fi5cmKjSG1cxcCrQmWBlb0mSJClJDR48mJUrV1JYWAjAjBkzGD58eNw1/sCBA7n99tuBYBLKX/7yl0Me98ILL+Taa68FYMqUKdx3331JFWRnAV8jsWFyRgPWe5Bg7cVDjc+reW5f5edSYO+FsHMtfLg0CK13NGCtkiRJdZWwILsuF7nDhw/nvvvuA+DZZ5/lD3/4AwCLFy8u2+bDDz+kbdu2ZbOzm51Yb+w+GGRLkiQpqWVmZlJUVL64S3FxMWeffXbcNkuWLOHKK6/kd7/7Hd/61rfo1KkTXbt2ZfPmzWRkZJCXl8eBAwf41a9+xYsvvki3bt34/PPPKS0tLTtmxXYkFY0dO5Ybb7wRgO7duyfoLKvKAabX8FpdQ+OtddzukMFyHUZpA503AMcA5wDPNuRBJUmS6i9hQXZdLnIrblNaWsrWrVvp1q0bmzaVd08bMWIEixYtiguxn3zySUpLS3nuuef42c9+Vu37h3WRW2+fEVydZgEfhFyLJEmSdITuuOMO/vCHP3DDDTfw+uuvU1xcXBZS9+3blzVr1nDccccxb9483n//fbZurftsjkmTJjFp0iQA8vLyElJ/df4JnET1ofKBRqsiJLEPxhbXupUkSVLCJbRH9pEaOHAgEydO5OKLLy577rrrrmPNmjV06NCB5557juuvv55p06ZV2Tesi9x6OwiswQUfJUmSlPRKSkro06f8wjUrK4uSkpK4bdauXcuIESMAaN++PSNGjCgLq9esWQNAYWEhr776KoMGDeK5556jS5cupKWlUVpaWu0xw7Y9OlqkLGAnQR8SSZKkEKUm6sB1ucituE1aWhqdO3cum42dmZnJCy+8wKhRo1i1alXZPrGL3x07dvD0008zePDgRJ1C4ykCepLkf1aQJElSS5eXl0d2djb9+vWjdevW5ObmMmvWrLhtunXrRkpKCgB33303kydPBqBLly6kp6eXbfPVr36VpUuXAkEv7auuugqA0aNH8+KLLzbWKelQMnE2tiRJSgoJC7LrcpE7a9YsRo8eDcBVV13FvHnzAOjcuTOzZ8/mrrvu4q233irbPi0tjW7dugHQqlUrvvGNb/DBB82gH0cxkAb0DrsQSZIkqWalpaWMGzeOuXPnsmzZMmbOnMnSpUuZMGECw4YNA+D8889nxYoVrFixgmOOOYaf//znAAwYMIAFCxawePFi5s+fz69+9auy9XPuvPNObr/9dgoKCujWrRtPPPFEaOeoCjKAHhhkS5KkpBFJ1Lj00ksjK1asiKxcuTLy7//+7xEgMmHChMiwYcMiQKRNmzaRmTNnRgoKCiLvvPNO5LjjjosAkXvuuSeyY8eOSH5+ftno0aNHpF27dpEFCxZElixZEvnggw8iDz74YCQ1NfWQdeTl5SXsHBtktCPCfUT4ahLU4nA4HA6Hw9GERtJf5zn83jflcQLB7ynHJ0EtDofD4XA4Wsyo6TovJXqnWcvLyyMnJyfsMmr3fWA98OewC5EkSWo6msR1nhLC730jOBe4APgVwcqWkiRJjaCm67yEtRZRPRXjgo+SJEmSkkcWsAFDbEmSlBQMspNFEdABOCrsQiRJkiSJIMguCbsISZKkgEF2siiK3maFWoUkSZIkBRNs2uFCj5IkKWkYZCeL9QQf2bO9iCRJkqSwxSbYGGRLkqQkYZCdLCIEH9tzRrYkSZKksGUB+wh6ZEuSJCUBg+xkUgz0BFqHXYgkSZKkFi0LWAMcDLsQSZKkgEF2Miki+I5khl2IJEmSpBarFcEEG9uKSJKkJGKQnUxiF4q2F5EkSZIUlp5AGkHrQ0mSpCRhkJ1MdgMbccFHSZIkSeFxoUdJkpSEDLKTTRHOyJYkSZIUnkxgK7A97EIkSZLKGWQnm2KgPdA17EIkSZIktUhZOBtbkiQlHYPsZFMUvbW9iCRJkqTG1h44CvtjS5KkpGOQnWw2AHuwvYgkSZKkxpcZvXVGtiRJSjIG2ckmQjD7wRnZkiRJkhpbFnAQWBt2IZIkSfEMspNREXA0kB52IZIkSZJalCzgM2B/2IVIkiTFM8hORsUE35nMQ20oSZIkSQ0kheB3ENuKSJKkJGSQnYxiF462F5EkSZLUWLoDbTDIliRJSckgOxntAdbjgo+SJEmSGk/s94+SUKuQJEmqlkF2siommJGdEnYhkiRJklqETIJJNZvCLkSSJKkqg+xkVQS0BbqFXYgkSZKkFiGLYEJNJOxCJEmSqjLITlZF0Vvbi0iSJElKtHTgaGwrIkmSkpZBdrLaBOzGBR8lSZIkJV4vgt8OXehRkiQlKYPsZBUhuIh0RrYkSZKkRHOhR0mSlOQMspNZMcHH+9qEXYgkSZKkZi0L2AzsCrsQSZKk6hlkJ7MiIAVnZUuSJElKrNhCj5IkSUnKIDuZlRC0GDHIliRJkpQonYCOGGRLkqSkZpCdzPYC63HBR0mSJEmJY39sSZLUBBhkJ7siggvLlLALkSRJktQsZQEHgHVhFyJJklQzg+xkVwxkAN3DLkSSJElSs5QJrAVKwy5EkiSpZgbZya4oemt7EUmSJEkNLRXojW1FJElS0jPITnabgF244KMkSZKkhncM0BoXepQkSUnPILspKMYZ2ZIkSZIaXmb01iBbkiQlOYPspqAI6AG0DbsQSZIkSc1KFrAT+DzkOiRJkg7BILspiPXJzqx1K0mSJEmqnyycjS1JkpoEg+ymYA1wENuLSJIkKXRDhw5l+fLlFBQUcOedd1Z5/dhjj+Wf//wnS5YsYf78+WRmBrMxTjvtNN566y0++OADlixZwtVXX122z5NPPsmqVavIz88nPz+f0047rdHOp0XLALpjkC1JkpqEVmEXoDrYB3yGCz5KkiQpVKmpqTz88MNcdNFFFBcXk5eXx6xZs1i2bFnZNr/+9a+ZOnUqU6dO5YILLuCXv/wlo0aNYteuXYwaNYqVK1fSq1cvFi5cyNy5c9m6dSsAP/7xj3nuuefCOrWWyf7YkiSpCXFGdlNRTBBkp4RdiCRJklqqwYMHs3LlSgoLC9m/fz8zZsxg+PDhcdsMHDiQefPmATB//vyy1wsKCli5ciUAa9euZf369fTo0aNxT0DxsoAIwSdAJUmSkpxBdlNRBLQBjg67EEmSJLVUmZmZFBUVlT0uLi4uax0Ss2TJEq688koAvvWtb9GpUye6du0at01OTg7p6el8/PHHZc/9/Oc/Z8mSJTzwwAOkp6dX+/5jx44lLy+PvLw8unfv3lCn1XJlAhuAvWEXIkmSdGgG2U1F7PcF24tIkiQpid1xxx2cd955LFq0iPPOO4/i4mJKS0vLXu/ZsyfTpk3jO9/5DpFIBIC7776b/v37k5OTQ9euXavtvQ0wadIkcnJyyMnJYePGjY1yPs2aCz1KkqQmxCC7qdgC7MQFHyVJkhSakpIS+vQpvyDNysqipKQkbpu1a9cyYsQIzjjjDO655x6Asj7YHTt2ZPbs2dxzzz288847ZfusW7cOgH379vHkk08yePDgRJ+KugLtgJJDbShJkpQcDLKbkiKckS1JkqTQ5OXlkZ2dTb9+/WjdujW5ubnMmjUrbptu3bqRkhIs7HL33XczefJkAFq3bs0LL7zA1KlTqyzq2LNnz7L7V1xxBR988EGCz0Qu9ChJkpoag+ympBjoTjBzQpIkSWpkpaWljBs3jrlz57Js2TJmzpzJ0qVLmTBhAsOGDQPg/PPPZ8WKFaxYsYJjjjmGn//85wBcffXVnHvuudxwww3k5+eTn5/PaaedBsCf/vQn3nvvPd5//326d+/Oz372s9DOscXIAvYR9MiWJElqAlII1qlu1vLy8sjJyQm7jCPXF/gO8DTwUci1SJIkJYFmc52nevN7f4TGAvuBp0KuQ5IkqZKarvOckd2UrAFKsb2IJEmSpMPXCuiJbUUkSVKTYpDdlOwHPsMFHyVJkiQdvp5AGgbZkiSpSTHIbmqKCBZm8TsnSZIk6XDEPuFZEmoVkiRJ9WIc2tQUA+nA0WEXIkmSJKlJygS2AtvDLkSSJKnuDLKbmqLore1FJEmSJB2OLGwrIkmSmhyD7Kbmc4KZEy74KEmSJKm+2gNHYVsRSZLU5BhkN0XFOCNbkiRJUv1lRm+dkS1JkpoYg+ymqAjoSjCbQpIkSZLqKgs4CKwNuxBJkqT6MchuimJ9sm0vIkmSJKk+soDPgP1hFyJJklQ/BtlN0VqgFNuLSJIkSaq7FILWIrYVkSRJTZBBdlN0gCDMdka2JEmSpLrqDrTBIFuSJDVJBtlNVTHBbAq/g5IkSZLqIjYRpiTUKiRJkg6LMWhTVQS0BnqGXYgkSZKkJiEL2A1sCrsQSZKk+jPIbqpc8FGSJElSfWQSzMaOhF2IJElS/SU0yB46dCjLly+noKCAO++8s8rr6enpzJgxg4KCAt5++2369u0LwNe//nUWLFjAe++9x4IFC7jgggvK9jnjjDN47733KCgo4KGHHkpk+cltW3S44KMkSZKkQ0kHjsa2IpIkqclKWJCdmprKww8/zKWXXsrAgQMZOXIkAwYMiNtmzJgxbNmyhezsbH77298yceJEADZu3MiwYcM49dRTGT16NNOmTSvb55FHHmHs2LFkZ2eTnZ3NJZdckqhTSH5FOCNbkiRJ0qH1Jvjtz4UeJUlSE5WwIHvw4MGsXLmSwsJC9u/fz4wZMxg+fHjcNsOHD2fKlCkAPPvsswwZMgSAxYsXs3btWgA+/PBD2rZtS3p6Oj179qRTp0688847AEydOpUrrrgiUaeQ/IqBo4AOYRciSZIkKallRm+dkS1JkpqohAXZmZmZFBUVlT0uLi4mMzOzxm1KS0vZunUr3bp1i9tmxIgRLFq0iH379pGZmUlxcXGtx4wZO3YseXl55OXl0b1794Y6reQS+/LaXkSSJElSbbIIFnncFXYhkiRJhyepF3scOHAgEydO5Lvf/W699500aRI5OTnk5OSwcePGBFSXBNYCB7C9iCRJkqTaZeFsbEmS1KQlLMguKSmhT5/yqcJZWVmUlJTUuE1aWhqdO3dm06ZNQDBb+4UXXmDUqFGsWrWqbPusrKxaj9milBKE2c7IliRJklSTTkBH7I8tSZKatIQF2Xl5eWRnZ9OvXz9at25Nbm4us2bNittm1qxZjB49GoCrrrqKefPmAdC5c2dmz57NXXfdxVtvvVW2/bp169i2bRtnn302AKNGjeLFF19M1Ck0DUUEC7ekhV2IJEmSpKQUmwtkkC1JkpqwhAXZpaWljBs3jrlz57Js2TJmzpzJ0qVLmTBhAsOGDQPgiSeeoFu3bhQUFHD77bdz1113ATBu3Di+8IUv8B//8R/k5+eTn59Pjx49ALjlllt4/PHHWblyJR9//DFz5sxJ1Ck0DUVAK6Bn2IVIkiRJSkpZBC0JPwu7EEmSpMOXAkTCLiLR8vLyyMnJCbuMxOgI/Aj4O/B2yLVIkiQ1smZ9nada+b2vh+8QTGF6IuxCJEmSDq2m67ykXuxRdbAd+BwXfJQkSZJUVSpBK0LbikiSpCbOILs5KMYFHyVJkiRVdQzQGigJuxBJkqQjY5DdHBQBnQlWI5ckSZKkmMzorTOyJUlSE2eQ3RwURW9tLyJJkiSpoixgB0E7QkmSpCbMILs5+AzYj+1FJEmSJMXLwrYikiSpWTDIbg5KgTU4I1uSJElSuQygO7YVkSRJzYJBdnNRTLAaeauwC5EkSZKUFOyPLUmSmhGD7OaiCEgDeoVdiCRJkqSkkAVECD69KUmS1MQZZDcXLvgoSZIkqaIsYAOwN+xCJEmSjpxBdnOxE9iCCz5KkiRJCmRiWxFJktRsGGQ3J0UYZEuSJEmCrkA7oCTsQiRJkhqGQXZzUgx0BDqHXYgkSZKaq6FDh7J8+XIKCgq48847q7x+7LHH8s9//pMlS5Ywf/58MjMzy14bNWoUH330ER999BGjRo0qe/6MM87gvffeo6CggIceeqhRzqPZi7UcdEa2JElqJgyym5NYn2xnZUuSJCkBUlNTefjhh7n00ksZOHAgI0eOZMCAAXHb/PrXv2bq1Kmcdtpp3H///fzyl78E4KijjmL8+PGcffbZDB48mPHjx9OlSxcAHnnkEcaOHUt2djbZ2dlccskljX1qzU8msA9YH3YhkiRJDcMguzn5jOBi1QUfJUmSlACDBw9m5cqVFBYWsn//fmbMmMHw4cPjthk4cCDz5s0DYP78+WWvDx06lH/84x9s2bKFzz//nH/84x9ccskl9OzZk06dOvHOO+8AMHXqVK644opGPa9mKQtYA0TCLkSSJKlhGGQ3JwcJLladkS1JkqQEyMzMpKioqOxxcXFxXOsQgCVLlnDllVcC8K1vfYtOnTrRtWvXGvfNzMykuLi41mPGjB07lry8PPLy8ujevXtDnlrz0groiW1FJElSs2KQ3dwUEVy0tgq7EEmSJLVEd9xxB+eddx6LFi3ivPPOo7i4mNLS0gY59qRJk8jJySEnJ4eNGzc2yDGbpZ5AGgbZkiSpWTHIbm6KCC5ae4ddiCRJkpqbkpIS+vQp//hfVlYWJSUlcdusXbuWESNGcMYZZ3DPPfcAsHXr1hr3LSkpISsrq9Zjqp5iX06/jJIkqRkxyG5uYrMubC8iSZKkBpaXl0d2djb9+vWjdevW5ObmMmvWrLhtunXrRkpKCgB33303kydPBmDu3LlcfPHFdOnShS5dunDxxRczd+5c1q1bx7Zt2zj77LMBGDVqFC+++GLjnlhzkwVsBbaHXYgkSVLDMchubnYBm3DBR0mSJDW40tJSxo0bx9y5c1m2bBkzZ85k6dKlTJgwgWHDhgFw/vnns2LFClasWMExxxzDz3/+cwC2bNnCT3/607Ie1/fffz9btmwB4JZbbuHxxx9n5cqVfPzxx8yZMye0c2wWMrGtiCRJanZSaAHrWOfl5ZGTkxN2GY3nW8AJwK/DLkSSJCmxWtx1nsr4va9Be+DHwFzg/0KuRZIk6TDUdJ3njOzmqAjoABwVdiGSJEmSGpX9sSVJUjNlkN0cFUVvbS8iSZIktSyZwEFgbdiFSJIkNSyD7OZoPbAXF3yUJEmSWposYB2wP+xCJEmSGpZBdnMUIfgooTOyJUmSpJYjhWBGtm1FJElSM2SQ3VwVAz2B1mEXIkmSJKlRdAfaEPwuIEmS1MwYZDdXRQTf3cywC5EkSZLUKGKfyDTIliRJzZBBdnMVu3i1vYgkSZIq+cY3vkFKSkrYZaihZQG7gc1hFyJJktTwDLKbq93ARlzwUZIkSVVcc801FBQUMHHiRE466aSwy1FDifXHjoRdiCRJUsMzyG7OinBGtiRJkqq4/vrrGTRoEB9//DFPPfUUb731FmPHjqVDhw5hl6bDlQ4cjW1FJElSs2WQ3ZwVAe2BrmEXIkmSpGSzfft2nn32WWbMmEGvXr341re+xaJFixg3blzYpelw9Cb47a4k7EIkSZISwyC7OYvNxrC9iCRJkioYNmwYzz//PK+++iqtW7dm8ODBXHbZZZx22mn86Ec/Crs8HY7YIu/OyJYkSc1Uq7ALUAJtAPYQtBdZEnItkiRJShojRozgt7/9LW+88Ubc87t372bMmDEhVaUjkgVsIlgrR5IkqRkyyG7OIgQfLXRGtiRJkiq47777WLt2bdnjjIwMjjnmGD755BPmzZsXYmU6bFlAYdhFSJIkJY6tRZq7IoJFX9LDLkSSJEnJ4plnnuHgwYNlj0tLS3nmmWdCrEhHpDPQEduKSJKkZs0gu7krIvguZx5qQ0mSJLUUrVq1Yv/+/WWP9+/fT3q6Mx+aLPtjS5KkFsAgu7mLrVpuexFJkiRFbdiwgWHDhpU9/uY3v8nGjRtDrEhHJAs4AHwWdiGSJEmJY4/s5m4PsJ7g4laSJEkCbrrpJv70pz/xhz/8gZSUFIqKihg1alTYZelwZQFrgdKwC5EkSUocg+yWoBgYAKQQLAApSZKkFm3VqlV8+ctfpn379gDs3Lkz5Ip02FKBXsCCsAuRJElKrDoF2e3atWP37t1EIhGys7Pp378/c+bM4cCBA4muTw2hCDgD6Ab4iVFJkiQBl112GSeffDIZGRllz/30pz8NsSIdlmOA1pS3FJQkSWqm6tQj+/XXXycjI4PevXvz8ssvc/311/PUU08luDQ1mKLore1FJEmSBDzyyCNcc801fP/73yclJYV/+Zd/oW/fvmGXpcMRu8Z3oUdJktTM1SnITklJYffu3Vx55ZX893//N1dffTUnn3xyomtTQ9kE7MYFHyVJkgTAV77yFUaPHs2WLVu4//77+fKXv8yJJ54Ydlk6HJnADuDzkOuQJElKsDoH2V/60pe47rrrmD17NgBpaWkJLUwNKEIwQ8MZ2ZIkSQL27NkDwK5du+jVqxf79++nV69eIVelw5KFbUUkSVKLUKcg+7bbbuPuu+/mhRdeYOnSpRx33HHMnz8/0bWpIRUDRwNtwi5EkiRJYXvppZfo3Lkz//Vf/8WiRYtYvXo1Tz/9dNhlqb4ygO7YVkSSJLUIdVrs8fXXX+f1118HgtnZGzdu5NZbb01oYWpgRUAKwYyNj0OuRZIkSaFJSUnhlVdeYevWrTz//PP89a9/JSMjg23btoVdmuorM3prkC1JklqAOs3I/tOf/kTHjh1p164dH3zwAUuXLuWOO+5IdG1qSCUELUZsLyJJktSiRSIRHn744bLH+/btM8RuqrIIrvHXhF2IJElS4tUpyB44cCDbt2/niiuuYM6cORx33HFcf/31ia5NDWkvsB4XfJQkSRKvvPIKV155Zdhl6EhlARsIrvUlSZKauToF2a1bt6ZVq1ZcccUVzJo1iwMHDhCJRBJdmxpaEcHFbkrYhUiSJClM3/3ud3nmmWfYu3cvW7duZdu2bWzdujXsslRfmdhWRJIktRh1CrIfe+wxVq9eTfv27Xn99dc59thj/fhhU1RE+YIwkiRJarE6depEWloabdq0oXPnznTq1InOnTuHXZbqoyvQDoNsSZLUYtRpscff//73/P73vy97/Omnn3LBBRckrCglSOwitw/BRxAlSZLUIp1zzjnVPv/GG280ciU6bLG1b0pCrUKSJKnR1CnI7tSpE+PHj+fcc88F4LXXXuP+++93VnZTswnYRXDRuyjkWiRJkhSaH//4x2X3MzIyGDx4MAsXLmTIkCEhVqV6yQT2EayDI0mS1ALUKciePHkyH3zwAVdffTUA119/PU8++SQjRoxIaHFKgGJc8FGSJKmF++Y3vxn3OCsriwcffDCcYnR4sghmY7t0kSRJaiHqFGSfcMIJXHXVVWWP77//fvLz8xNWlBKoCDgRaAvsDrkWSZIkJYXi4mIGDBgQdhmqq1ZAT+D/wi5EkiSp8dQpyN69ezdf/epXefPNNwH4yle+wu7dpqBNUlH0NhNYGWYhkiRJCsvvfvc7IpFgKm9qaiqnn346ixbZe67J6Amk4UKPkiSpRalTkH3TTTcxderUspXMt2zZwujRoxNamBJkDXCQoL2IQbYkSVKLtGDBgrL7Bw4cYPr06bz11lshVqR6caFHSZLUAtUpyH7vvfc4/fTT6dixIwDbt2/n1ltv5f33309ocUqAfcBnlF/8SpIkqcV59tln2bNnDwcPHgSCWdlt27at06cuhw4dykMPPURaWhqPP/44EydOjHu9T58+TJkyhS5dupCWlsZdd93FnDlzuPbaa+MWmTz11FM544wzWLJkCfPnz6dXr15l73/xxRezYcOGBjzjZiYL2ApsD7sQSZKkxhU5nPHJJ58c1n5hjLy8vNBrSKpxORHuJkJKEtTicDgcDofDcQTD67zDG//3f/8Xad++fdnj9u3bR958881D7peamhpZuXJl5Ljjjou0bt06snjx4siAAQPitnnsscciN910UwSIDBgwIFJYWFjlOKecckpk5cqVZY/nz58fOfPMM/3e13XcRoR/SYI6HA6Hw+FwOBIwarrOS+UwpaSkHO6uClsR0AY4OuxCJEmSFIaMjAx27txZ9njnzp20a9fukPsNHjyYlStXUlhYyP79+5kxYwbDhw+P2yYSidCpUycAOnfuzJo1a6ocZ+TIkcyYMeMIz6KFag90wf7YkiSpxTnsIDu2OIyaoNiCj7YXkSRJapF27tzJoEGDyh6fccYZdWorkpmZSVFRUdnj4uJiMjMz47a57777+Pa3v01RURF/+9vf+P73v1/lONdccw3Tp0+Pe+7JJ58kPz+fe++9t8b3Hzt2LHl5eeTl5dG9e/dD1tss2R9bkiS1ULUG2du2bWPr1q1VxrZt2+jdu/chDz506FCWL19OQUEBd955Z5XX09PTmTFjBgUFBbz99tv07dsXgK5duzJv3jy2b9/O73//+7h95s+fz/Lly8nPzyc/P58ePXrU53wFsAXYSbDgoyRJklqc2267jWeeeYbXX3+dN954gz//+c+MGzeuQY49cuRInnrqKfr06cNll13GtGnT4j7NOXjwYHbt2sWHH35Y9tx1113HqaeeyjnnnMM555zD9ddfX+2xJ02aRE5ODjk5OWzcuLFB6m1ysoBSYG3YhUiSJDWuWhd7jH0k8HCkpqby8MMPc9FFF1FcXExeXh6zZs1i2bJlZduMGTOGLVu2kJ2dzTXXXMPEiRPJzc1lz549/OQnP+GUU07hlFNOqXLs6667joULFx52bSKYle2MbEmSpBZpwYIF9O/fn5NOOgmAFStWcODAgUPuV1JSQp8+5bMhsrKyKCmJnxo8ZswYLrnkEgDefvttMjIy6N69e9nijbm5uVVmY8faj+zYsYOnn36awYMHM23atMM/weYsk2Dx9v1hFyJJktS4Dru1yKHUpX/e8OHDmTJlChCsnD5kyBAAdu3axZtvvsmePXsSVZ6Kge7AoVshSpIkqZm55ZZbaN++PR9++CEffvghHTp04Oabbz7kfnl5eWRnZ9OvXz9at25Nbm4us2bNitvm008/Lbuu79+/PxkZGWUhdkpKCldffXVcf+y0tDS6desGQKtWrfjGN77BBx980FCn2rykEATZthWRJEktUMKC7Lr0z6u4TWlpKVu3bi27iK2N/fMagH2yJUmSWqyxY8eydevWsseff/45Y8eOPeR+paWljBs3jrlz57Js2TJmzpzJ0qVLmTBhAsOGDQPgRz/6EWPHjmXx4sVMnz6dG264oWz/c889l6KiIgoLC8uea9OmDXPnzmXJkiUsXryYkpISJk2a1HAn25z0IFi03YUeJUlSC1Rra5FkdN1117FmzRo6dOjAc889x/XXX1/txw4nTZpUdgGcl5fX2GUmvzUEvfWygI9CrkWSJEmNKi0tLe5xamoq6enpddp3zpw5zJkzJ+658ePHl91ftmwZX/va16rd97XXXuPLX/5y3HO7du3irLPOqtN7t3ixeUEG2ZIkqQVK2IzsuvTPq7hNWloanTt3ZtOmTbUet7r+eToM+wl667ngoyRJUovz97//nT//+c9ceOGFXHjhhUyfPr1KOK0klAXsBjaHXYgkSVLjS1iQXZf+ebNmzWL06NEAXHXVVcybN6/WY9o/r4EVEczqSNhPgSRJkpLRnXfeybx587jpppu46aabeP/992nbtm3YZelQsgj6Y0fCLkSSJKnxJay1SMX+eWlpaUyePLmsf96CBQt46aWXeOKJJ5g2bRoFBQVs3ryZ3Nzcsv0LCwvp1KkT6enpXHHFFVx88cV88sknzJ07l9atW5OWlsY///lP++cdiSLgbOBoYF3ItUiSJKnRRCIR3nnnHU444QSuvvpqunfvznPPPRd2WapNOkGP7GVhFyJJkhSOhPbIPlT/vL1793L11VdXu+9xxx1X7fP2z2tAsd56fTDIliRJagGys7MZOXIkI0eOZOPGjfz5z38G4MILLwy5Mh1Sb4JPUtofW5IktVBNbrFHNaDPge0EH1F0PUxJkqRmb/ny5bzxxht84xvf4OOPPwbghz/8YchVqU6yorcltW4lSZLUbNkduaUrxgUfJUmSWogrr7yStWvXMn/+fP7nf/6HCy+8kJSUlLDLUl1kApsIFnuUJElqgQyyW7oioCvQPuxCJEmSlGgvvvgiI0eOpH///syfP5/bbruNo48+mv/+7//moosuCrs81SYL24pIkqQWzSC7pSuK3mbVupUkSZKakV27djF9+nS++c1vkpWVRX5+PnfeeWfYZakmnYGO2FZEkiS1aAbZLd1aoBTbi0iSJLVQn3/+OZMmTeLrX/962KWoJpnRW2dkS5KkFswgu6U7QBBmOyNbkiRJSk5ZBNftn4VdiCRJUngMshXM7MjEnwZJkiQpGWVR/klKSZKkFsroUkGf7NZAz7ALkSRJkhQnFeiFbUUkSVKLZ5AtF3yUJEmSktUxBJNODLIlSVILZ5At2BYdLvgoSZIkJZfYZJOSUKuQJEkKnUG2AkUYZEuSJEnJJhPYAXwech2SJEkhM8hWoAjoAnQIuQ5JkiRJ5bKwrYgkSRIG2YqJXRw7K1uSJElKDm2B7thWRJIkCYNsxawFDuCCj5IkSVKyyIzeOiNbkiTJIFtRpQRhtjOyJUmSpOSQCUSANWEXIkmSFD6DbJUrAnoDaWEXIkmSJIksYAOwN+xCJEmSwmeQrXJFQCugZ9iFSJIkSSIT24pIkiRFGWSrnAs+SpIkScmhK9AOg2xJkqQog2yV2w58jgs+SpIkSWGLXZOXhFqFJElS0jDIVrxinJEtSZIkhS0L2AesD7sQSZKk5GCQrXhFQGegU9iFSJIkSS1YJsFs7EjYhUiSJCUHg2zFK4re2l5EkiRJCkdsAXbbikiSJJUxyFa8z4D92F5EkiRJCksvIA0XepQkSarAIFvxSoE1OCNbkiRJCktm9NYgW5IkqYxBtqoqBnoTfKRRkiRJUuPKAj4HdoRchyRJUhIxyFZVRQQfZewVdiGSJElSC5SF/bElSZIqMchWVS74KEmSJIWjA9AF24pIkiRVYpCtqnYCW3DBR0mSJKmx2R9bkiSpWgbZql4RBtmSJElSY8siWIB9bdiFSJIkJReDbFWvCOgIdA67EEmSJKkFyQQ+Aw6EXYgkSVJyMchW9WIfZXRWtiRJktQ4UgiCbNuKSJIkVWGQrep9BuzDBR8lSZIUZ+jQoSxfvpyCggLuvPPOKq/36dOHefPmsWjRIpYsWcKll14KQN++fdm1axf5+fnk5+fzyCOPlO1zxhln8N5771FQUMBDDz3UaOeSdHoAbYCSsAuRJElKPgbZqt5BYA3OyJYkSVKZ1NRUHn74YS699FIGDhzIyJEjGTBgQNw29957LzNnzuSMM84gNzeX//7v/y577eOPP2bQoEEMGjSIm2++uez5Rx55hLFjx5KdnU12djaXXHJJo51TUnGhR0mSpBoZZKtmRUBPoFXYhUiSJCkZDB48mJUrV1JYWMj+/fuZMWMGw4cPj9smEonQqVMnADp37syaNWtqPWbPnj3p1KkT77zzDgBTp07liiuuSEj9SS8L2A1sDrsQSZKk5GOQrZoVAWlA77ALkSRJUjLIzMykqKio7HFxcTGZmZlx29x33318+9vfpqioiL/97W98//vfL3vtuOOOY9GiRbz66qt87WtfKztmcXFxrceMGTt2LHl5eeTl5dG9e/eGPLXkkEXQViQSdiGSJEnJxyBbNXPBR0mSJNXTyJEjeeqpp+jTpw+XXXYZ06ZNIyUlhbVr13LsscdyxhlncPvtt/P000/TsWPHeh170qRJ5OTkkJOTw8aNGxN0BiFJB47GtiKSJEk1MMhWzXYBm3DBR0mSJAFQUlJCnz7lsxyysrIoKYlfmXDMmDHMnDkTgLfffpuMjAy6d+/Ovn372Lw56JmxaNEiPv74Y0488URKSkrIysqq9ZgtQm8gBYNsSZKkGhhkq3bFOCNbkiRJAOTl5ZGdnU2/fv1o3bo1ubm5zJo1K26bTz/9lCFDhgDQv39/MjIy2LBhA927dyc1Nfj147jjjiM7O5tVq1axbt06tm3bxtlnnw3AqFGjePHFFxv3xJJBLMtvgRm+JElSXbiMn2pXBJwGHAVsCbkWSZIkhaq0tJRx48Yxd+5c0tLSmDx5MkuXLmXChAksWLCAl156iR/96EdMmjSJH/7wh0QiEW644QYAzj33XO6//37279/PwYMHuemmm9iyJbjAvOWWW3jqqado27Ytc+bMYc6cOSGeZUiyCD4NuTvsQiRJkpJTCi1gKZG8vDxycnLCLqNpOga4GXgOeD/kWiRJkirxOq/lanbf+x8Bq4AXwi5EkiQpXDVd59laRLVbD+zF9iKSJElSonQGOmJbEUmSpFoYZKt2EYILahd8lCRJkhIjdq3tQo+SJEk1MsjWoRUBPYHWYRciSZIkNUOZwAHgs7ALkSRJSl4G2Tq0YoKflMywC5EkSZKaoSxgLVAadiGSJEnJyyBbhxb7iKPtRSRJkqSGlQr0wrYikiRJh2CQrUPbDWzEBR8lSZKkhnYMQQs/g2xJkqRaGWSrbopwRrYkSZLU0GLX2CWhViFJkpT0DLJVN0VAe6Br2IVIkiRJzUgWsAP4POQ6JEmSkpxBtuom9lFH24tIkiRJDScT24pIkiTVgUG26mYDsAfbi0iSJEkNpS3QHYNsSZKkOjDIVt1ECPr2OSNbkiRJahiZ0Vv7Y0uSJB2SQbbqrgg4GkgPuxBJkiSpGcgkmDCyJuxCJEmSkp9BtuquiOAnJvNQG0qSJEk6pCxgPbA37EIkSZKSn0G26i72kUfbi0iSJElHLhPbikiSJNWRQbbqbg/BjBEXfJQkSZKOTFegHS70KEmSVEcG2aqfYoIZ2SlhFyJJkiQ1YbHJIQbZkiRJdWKQrfopAtoC3cIuRJIkSWrCsgh6Y28IuxBJkqSmIaFB9tChQ1m+fDkFBQXceeedVV5PT09nxowZFBQU8Pbbb9O3b18Aunbtyrx589i+fTu///3v4/Y544wzeO+99ygoKOChhx5KZPmqTlH01vYikiRJ0uHLBNYAkbALkSRJahoSFmSnpqby8MMPc+mllzJw4EBGjhzJgAED4rYZM2YMW7ZsITs7m9/+9rdMnDgRgD179vCTn/yEO+64o8pxH3nkEcaOHUt2djbZ2dlccskliToFVWcTsBsXfJQkSZIOVyugJ7YVkSRJqoeEBdmDBw9m5cqVFBYWsn//fmbMmMHw4cPjthk+fDhTpkwB4Nlnn2XIkCEA7Nq1izfffJM9e/bEbd+zZ086derEO++8A8DUqVO54oorEnUKqk6E4ILbGdmSJEnS4ekFpAElYRciSZLUdCQsyM7MzKSoqKjscXFxMZmZmTVuU1paytatW+nWrebmy5mZmRQXl09bqO6YagRFwNFAm7ALkSRJkpogF3qUJEmqt2a72OPYsWPJy8sjLy+P7t27h11O81IMpOCsbEmSJOlwZAKfAztCrkOSJKkJSViQXVJSQp8+5Y2Us7KyKCkpqXGbtLQ0OnfuzKZNm2o9ZlZWeXpa3TFjJk2aRE5ODjk5OWzcuPFITkWVlRC0GDHIliRJkuovC9uKSJIk1VPCguy8vDyys7Pp168frVu3Jjc3l1mzZsVtM2vWLEaPHg3AVVddxbx582o95rp169i2bRtnn302AKNGjeLFF19MzAmoZnuB9bjgoyRJklRfHYAu2FZEkiSpnlol6sClpaWMGzeOuXPnkpaWxuTJk1m6dCkTJkxgwYIFvPTSSzzxxBNMmzaNgoICNm/eTG5ubtn+hYWFdOrUifT0dK644gouvvhili1bxi233MJTTz1F27ZtmTNnDnPmzEnUKag2RcApBC1GIiHXIkmSJDUVsSV+DLIlSZLqJWFBNlBt0Dx+/Piy+3v37uXqq6+udt/jjjuu2ucXLlzIF7/4xYYrUoenCDgL6A5sCLkWSZIkqanIAkqBtWEXIkmS1LQ028UelWCxGSS2F5EkSZLqLgv4DDgQdiGSJElNi0G2Ds8mYBcu+ChJkiTVVQrQG9uKSJIkHQaDbB2+YpyRLUmSJNVVD6ANUBJ2IZIkSU2PQbYOXxHBxXjbsAuRJEmSmoDYpxmdkS1JklRvBtk6fEXR28xat5IkSZIEwXXzboI2fZIkSaoXg2wdvjXAQWwvIkmSJNVFFrYVkSRJOkwG2Tp8+whWXHfBR0mSJKl26cDR2FZEkiTpMBlk68gUEQTZKWEXIkmSJCWx3gTXzAbZkiRJh8UgW0emmGDl9aPDLkSSJEmNYejQoSxfvpyCggLuvPPOKq/36dOHefPmsWjRIpYsWcKll14KwNe//nUWLFjAe++9x4IFC7jgggvK9pk/fz7Lly8nPz+f/Px8evTo0Wjn02hin2K0tYgkSdJhaRV2AWriYgs+ZhG0GZEkSVKzlZqaysMPP8xFF11EcXExeXl5zJo1i2XLlpVtc++99zJz5kweffRRBgwYwN/+9jeOO+44Nm7cyLBhw1i7di0nn3wyc+fOJSurvEfdddddx8KFC8M4rcaRRbDI4+6wC5EkSWqanJGtI7MF2IkLPkqSJLUAgwcPZuXKlRQWFrJ//35mzJjB8OHD47aJRCJ06tQJgM6dO7NmzRoAFi9ezNq1awH48MMPadu2Lenp6Y17AmHKxLYikiRJR8AgW0euCINsSZKkFiAzM5OioqKyx8XFxWRmZsZtc9999/Htb3+boqIi/va3v/H973+/ynFGjBjBokWL2LdvX9lzTz75JPn5+dx77701vv/YsWPJy8sjLy+P7t27N8AZNZLOQEcMsiVJko6AQbaOXBHQDWgXdiGSJEkK28iRI3nqqafo06cPl112GdOmTSMlpXxl8IEDBzJx4kS++93vlj133XXXceqpp3LOOedwzjnncP3111d77EmTJpGTk0NOTg4bN25M+Lk0GPtjS5IkHTGDbB252MySrFq3kiRJUhNXUlJCnz7lH8XLysqipCQ+nR0zZgwzZ84E4O233yYjI6Ns9nRmZiYvvPACo0aNYtWqVWX7xNqP7Nixg6effprBgwcn+lQaVyZwANeUkSRJOgIG2Tpya4BSDLIlSZKauby8PLKzs+nXrx+tW7cmNzeXWbNmxW3z6aefMmTIEAD69+9PRkYGGzZsoHPnzsyePZu77rqLt956q2z7tLQ0unXrBkCrVq34xje+wQcffNB4J9UYsii/ZpYkSdJhMcjWkdtPMLvEPtmSJEnNWmlpKePGjWPu3LksW7aMmTNnsnTpUiZMmMCwYcMA+NGPfsTYsWNZvHgx06dP54YbbgBg3LhxfOELX+A//uM/yM/PJz8/nx49etCmTRvmzp3LkiVLWLx4MSUlJUyaNCnEs2xgqUAvbCsiSZJ0hFKASNhFJFpeXh45OTlhl9G8XQoMAn4FHAy5FkmS1GJ4nddyNZnvfS/gu8AzwIch1yJJktQE1HSd54xsNYwiIB04OuxCJEmSpCQSa79XXOtWkiRJOgSDbDWM2IW57UUkSZKkclnADmBr2IVIkiQ1ba3CLqC5GQD8nuBadXt07Kh0W91zsdudNNFeL58TnEAWkBduKZIkSVLSyMLZ2JIkSQ3AILuBtSbosNEX6Ah0iN62q8cxagq56xuKx+4fOMJzqrNinJEtSZIkxbQFugH5YRciSZLU9BlkN7D3gHOreT6VINSOBdsVQ+7Kt9U9dwxwQqXn6toXZg+HF4DX9Nyemt6oiGBKenuCqeWSJElSS5YZvS0JtQpJkqRmwSC7kRwEtkVHQ2nL4YXiHYFOBNfVFV9rU8f3PUAQalcJuRfBju3weeugu8gr+ClKSZIktWBZBH0DDbIlSZKOmEF2E7Y7OtY30PFaU/9QvOJrx+6BjsXQfQd8L3rMj4B5BKH2q8DGBqpVkiRJSnqZBBfr+8IuRJIkqekzyFaZ/cDm6DhsIyBlP5w8BYYAFwLXAjdFX15MebD9OsFMbkmSJKlZygKWhV2EJElS82CQrYZVBJGz4INU+OAgPASkAWdSHmzfAtxO0KLkXYJQex7wf8DecKqWJEmSGlY3gl6A9tqTJElqEHVdL1Cqm2KCHiWDKWu6XUoQWP8SuAjoQhBo/wpIAe4G5gNbgH8Ad0V3T2vMuiVJkqSGFFvo0SBbkiSpQTgjWw1rFUEfwEuArwMrgQ+BFZT1BtxLEFzPB35C0F/7XIJwewhB4A2wFXiN8hnbHzTOGUiSJElHLovgwndD2IVIkiQ1DwbZali7gf8mmIFyCnAy0J+gAXcBQaj9UfRx1HZgdnQA9ADOp7wVyTejz39GEH7Hgu1VCTwNSZIk6YhkAWuASNiFSJIkNQ8G2UqMkuh4meAi/hRgYHTsIwizPyQItw/E77oBeCY6APpQPlt7CJAbfX415aH2PGBdYs5EkiRJqp9WwDHAW2EXIkmS1HwYZCuxIkBRdPwdOJbyUPsUgo9briAItVcSNNSupAiYEh0AJ1EebH8LGBN9finlwfarwOcNfS6SJElSXfQiWPClJOxCJEmSmg+DbDWeCPBJdMwB+hKE2QOAU4E9wHKCUHsV1YbaEOTeK4BHCFYrPY3yYPtfge9Hd11EEGq/ArwJ7ErEOUmSJEmVZUVvXehRkiSpwRhkKxwHgcLomA0cRxBq9wdOJ+i1vYwg1C6Mbl/DYfKj4zdAa2Aw5f21fwjcSdDN5P8oD7bfJa5NtyRJktRwMgk+Hrgj5DokSZKaEYNshe8g8HF0/BU4nvKFIs8gmEq9lCDUXk2tC+bsJ5h9/SZwP9AO+CrlwfZ4YALB7xRvUB5sL6HGrFySJEmqnyycjS1JktTADLKVXEoJFoAsIPjpPIEg1D4VOIsggY6F2p9yyFXgdwH/iA6ALsB5lAfb/xV9fjMwn/Jge0WDnIwkSZJanA4EF53vhFyHJElSM2OQreR1gPKG2K2BLxCE2oMI+odsJwi0PySY8XKIUBuCT3i+GB0APYELCILtIcCI6PMllIfa8wgWnJQkSZIOKTN664xsSZKkBmWQraZhP0HP7GVAOnAiQeuRs4AvAVspD7XrsTr8OmB6dEDQqjs2W/ti4Pro8wWUB9vzgY1HcCqSJElqxrIIPmW4NuxCJEmSmheDbDU9+4APoqMNcBJBqH028BVgC+Whdj1/gSgEHo8OooeNBdu5wHejzy+hPNh+nWByuCRJkkQW8BnBpwslSZLUYAyy1bTtBd6LjgygP0H6/GXga8AmykPtz+p/+NiuvwPSCNaejAXbNwE/JPgdJY/yNiRvRcuSJElSC5MC9CaY9SBJkqQGZZCt5mMPsDg62gIDCELtrwHnAhsoT6Y31P/wpQSBdR7wK4LJ4F8mCLWHAHcB9xKE2MUEbUtqG58RdEyRJElSM9GD4CLR/tiSJEkNziBbzdNuYFF0tAMGEoTa5wHnE6TIsVB70+G9xV7g1ej4D4IF6s+NjiyChST7R9+uWw3H2MShA+910e3qsJalJEmSwpQVva3Hmi2SJEmqG4NsNX+7gAXR0YHyUPvC6FhH0G/7Q4L+2odpB/C36KgsHTiaINyuaXwpetu+mv0PEGTvn3Ho0Nt+3ZIkSSHJIphQcZgTJSRJklQzg2y1LDuAd6OjI0GgfTLw9ehYQ3movbXh3nYfwSdM6/Ip0w7AMdQeep8a3aZ1Nfvvom6zvD+L1iVJkqQGkoltRSRJkhLEIFst13bg7ejoTHmofXF0FBOE2kuBbY1X1o7o+PgQ26UAXak98D6RoNVJ9xqOsZnyULu20HsjcPBwT0iSJKkliH0Eb1nYhUiSJDVPBtkSBLOv34qOoygPtS+Jjk8pD7V3hFRjJRGCT61uIphAXpvWBL9X1TbT+6zobcdq9i8F1lO3md6NmPlLkiQlj0yCmQbOyJYkSUoIg2ypsi3A/0ZHN8pD7cuAS4HVBMnxMmBnOCXW136CNYfqsu5Qew7d2uSU6Dbp1ey/G1hb4f2qG2uwrYkkSWpmMqO3LvQoSZKUEAbZUm02Aa9HRw/KQ+1vEATbhZSH2rtDqrGB7QRWRUdtUggmr1cOvXsBvQl+lzsT+CbQrpr9N1B72F1C0PpEkiSpScgiuHZsJteEkiRJycYgW6qrDcCr0XE0wbTkkwmS2ssJkt8PgeXAnlAqbFQRgqB5M4duBdmFINiuaZxFEIhXtptg9vahZnfvP6IzkSRJagBZHHqRE0mSJB02g2zpcKwH5kVHrNfGycAVBA2lN0a3iY0NBC1LIiHUmgQ+j47aenm3JpjNXVPYnUPw5W1bzb7rOfTs7i1HehLSIXQGBhH8rH8AHAi1GklSo+oMdMD+2JIkSQlkkC0dqdgqh/8k6KkxgGB6cR/gixW2208QaG8gPuDeSosNuCvaT7Cm5qeH2O4oap/dPZhgwnxluzj07O61OLtbddMOOIPg0wQ50ZFd4fXdwGIgLzoWACvwP3VJarayorf2x5YkSUoYg2ypIa2Jjpg2BL21exCkq0cDxwGnVdhmL9UH3Nsaod4maEt0fFDLNunUPrv77OhtRqX9DlK33t2fN8iZqKlIB04lCKtjwfVAIC36ehFBWD0ZWETwx5ZYuP2vwA+i220DFlIebucBnzTKGUiSEi6L4K/hn4VdiCRJUvNlkC0l0l6Cj5hW/phpBkGoXTHgziboSxCzh/hgO3Z/Z2JLbg72EQSEhwoJu1Jz2N0H+BLBt6iyndQ8u7sYWEmw1pOanjSCkLriTOtTCcJsCP5TzAOep3ymdXWZxZ+jt6kEH9KoeLxbCf7GVfF4sWPl1XA8SUomQ4cO5aGHHiItLY3HH3+ciRMnxr3ep08fpkyZQpcuXUhLS+Ouu+5izpw5ANx1112MGTOG0tJSfvCDH/Dyyy/X6ZhJL5Pgo12lYRciSZLUfBlkS2HYQ/V9NNpRNeAeGH0+ZhfVB9y7E1tycxRbrPL9WrZJJ+gYU1Pg/eXo65Vnd28kWPdzWfQ2NlYTzPxW+FKAL1AeMJ9F8Lek9tHXtxKEyw9QHjIfqvVNZQcJesN/CEyJPpdO0HUop8IYStUZ3hUD7q31fF9JSpTU1FQefvhhLrroIoqLi8nLy2PWrFksW1a+9PO9997LzJkzefTRRxkwYAB/+9vfOO644xgwYAC5ubmcfPLJ9O7dm3/+85+ceOKJAIc8ZlJLI7gYyAu7EEmSpObNIFtKJrsIks7VlZ7vQNWA+1Ti09MdVF1gcj3BrHAdtn1U/y2prBtBsJ1FMLm+f3R8ExhbYbs9wEfEh9vLos/tariyVY1jiZ8ZfSbQJfraLoK2IJMoD5BXkpie1vsIWowsBB6NPteOIESvGG5fWWGfj4iftZ2PPy+SwjF48GBWrlxJYWEhADNmzGD48OFxoXMkEqFTp04AdO7cmTVrgr5rw4cPZ8aMGezbt4/Vq1ezcuVKBg8eDHDIYya1Ywh+q3KhR0mSpIQyyJaagh3RsarS852oGnCfQXkfBAimclbuv72BIE1Tg9kUHe9V89pRwEmUh9sDgNOBEZTPwoWgFUrFcDt231YT9Xc08TOtcyhfBHQfwfdpOuXh8FLC/TT4LuDN6IjpQnzwfi5wXfS1UoJZ3hVnbr+Pi5VKSrzMzEyKiorKHhcXF3P22WfHbXPffffx8ssv8/3vf5/27dvz9a9/vWzft99+O27fzMxMgEMeM2bs2LHceOONAHTv3r1hTupIZUZvDbIlSZISyiBbasq2RcfKCs+lAJ0pD7ZjIfdg4v+L30L1AfeBhFfd4mwB3o6OitKBEwiC7f4Vxr8CHSts9znVtylZhd8uCALfM4mfzdwn+lopQUg9m/LA9z2axt9xPgf+GR0xPYkPt4cDY6Kv7QWWEB9uL8dWNomQQvBPa+9qxnaC78MSgq+/f1xQSzRy5EieeuopHnjgAb70pS8xbdo0TjnllAY59qRJk5g0aRIAeXlJ0ssji2DCgX2gJEmSEsogW2puIgQJ2OcE/QhiUgimBlcOuE+gfFrwQYLUtXL/7U24eFEC7CMIp6v74HQm8eF2f+Bi4DuV9l9JfLgdG9sTVnW42hF86KDiTOvsCq8XAG9QPtM6n+a1Puo64K/REdOP+HD7euB70de2E7RMqdhvu/IHOxSvC1XD6cxKj3sBravZdz3BB2ViXZ/2EfwhZUml4WKwaspKSkro06dP2eOsrCxKSkrithkzZgyXXHIJAG+//TYZGRl079691n0PdcykloWzsSVJkhqBQbbUUkQoX91weYXnU4GuVA24T4q+BkHAvYmqAfdmnO6ZICXR8Uql5ztS3qak4kzuYcQHayVU36akCcUCpAOnER/SDqD87y6fEgSzkwlC2oUEf79paVZHx7PRxykEPyMVZ6iPozxc3UR5r+3YWNto1YanHYcOqHsTv7ZuzBZgDeX/Xa2pMEqit58RzL5OI/j6n1ZhXAyMrnC8EqqG2wX490I1DXl5eWRnZ9OvXz9KSkrIzc3l2muvjdvm008/ZciQIUyZMoX+/fuTkZHBhg0bmDVrFk8//TQPPPAAvXv3Jjs7m3fffZeUlJRDHjNptSVYKCM/7EIkSZKav4QG2UOHDuWhhx4iLS2Nxx9/nIkTJ8a9np6eztSpUznzzDPZtGkT11xzDZ988gkAd911F2PGjKG0tJQf/OAHvPzyywAUFhayfft2SktLOXDgADk5OYk8Ban5OwhsjI6lFZ5PI/jFrGLA3RMYSJCUQZC6bKRqwL0VE5kE2U4QQi6o9Hwr4Diqtim5jvIFDWP7r6Bqm5KVhNtuI43gR6viTOtTKW/3vp4gcH2W8hB2feOX2SREKP++Tos+1xo4mfhw+y7KLwJKiJ+1nUcQ3jYFrQlmSNcWTmcSdFyqbCflQfS7VA2n1xCE/LvrUU+snc1Sgj7sMT2ID7dPAy6i/A9Qu4EPiA+338NOBUo+paWljBs3jrlz55KWlsbkyZNZunQpEyZMYMGCBbz00kv86Ec/YtKkSfzwhz8kEolwww03ALB06VJmzpzJ0qVLOXDgAN/73vc4eDD4i3h1x2wS7I8tSZLUaFIIfudtcKmpqXz00UdcdNFFFBcXk5eXx8iRI+NWH7/55ps59dRTufnmm7nmmmv41re+RW5uLgMGDGD69OkMHjyY3r17889//pMTTzyRgwcPUlhYyFlnncWmTXX/YG5eXp6Bt9RQWgHdKQ+4YyH3URW2iRAkplujY1uF+7Gxq/FKbumOIT7cjoXdfStsc4Cg5UTFcDsWdn/ewPWkAF8gPlQdRPlM2K3EzxheQDD7Wg2rLcGioxUXxexf4fWPiZ+1vYjGbdOSSvDPS20BdW/KF/GsaB/xs6arC6jXEPzTFKZ0gv8eTyU+4O5RYZvVVJ29vYoEXbw1UV7ntVxJ8b0/HzgP+CVNYwEGSZKkJqCm67yEzcgePHgwK1eupLCwEIAZM2YwfPjwuCB7+PDh3HfffQA8++yz/OEPfyh7fsaMGezbt4/Vq1ezcuVKBg8eHLfKuaSQHCBo1Luu0vPpBOlLD4Kpj7HRk+Bz9pUbyu6narhdOfh2JcMG8Vl0vFbp+XbAiVRtU3Ix5W0oYvtX16bkU+oWph1L/EzrMymfJb6LICB9jPLwemUdj6sjsxv4v+iI6UT8wplfBnKjr5USfP8rztpewuHlNl059AzqnpS3kYkpJfh5XEPw8/c21QfUm2gaP0P7KA+np1V4vhdVZ29/g/Kvx3bgfeLD7fdpXv3gpSYjk+AjQobYkiRJCZewIDszM5OioqKyx8XFxZx99tk1blNaWsrWrVvp1q0bmZmZcaF1cXExmZnB5/YikQgvv/wykUiExx57rGzV8srGjh3LjTfeCED37t0b9NwkVWMf5Y2dq9OO+IC74sgGOlDesiRmJzWH3VujrzeFtCpJ7QIWR0dFqQQLCFZebHIEwWT8ivt/RHy4XUAQRFac5RubMRsL7aZTPst3GXahSSbbgPnREdOD+O/nZZQvOrqPoP1FxZnb+6g9oO4NtKnmvTdSHkR/QNVwOtaHuiX8vKyNjr9XeC6DoD1MxXB7JHBz9PWDBLPoK8/e9tMMUoJlEd+aTZIkSQnT5BZ7/NrXvsaaNWvo0aMH//jHP1i+fDlvvPFGle0mTZpUFnLn5eU1dpmSKtsVHTWtKpdGsJJhdUF3N+B4qqZfpVTftqTicIZUvR0kaF2wCvhbpde6UbVNyWDgGsrXBoXyPsF/pXz27nv47WiKNhD8HFT8WehDfGuYaykPVCvbRnkQ/SbVB9Rrgb0JqL052UOwoOnCSs8fS9XZ21dVeH0LwX9771Eebn8QPZ6kI9SNoE9TU1pJWZIkqQlLWJBdUlJCnz59yh5nZWVRUlJS7TYlJSWkpaXRuXNnNm3aVOu+a9asAWDDhg288MILDB48uNogW1ITU0rQjPnzWrbJID7g7lThft/o49RK++ym5tYlWwk+o3+wYU6hJdhEEEa+Wen5NgQT608kmDW7GNscNGdF0fF89HEKwff/zOj9iiH1jjAKbEE+jY6XKjzXHvgi8eH2dwg++ALBP7cfUXX29prGKVlqPlzoUZIkqVElLMjOy8sjOzubfv36UVJSQm5uLtdee23cNrNmzWL06NG8/fbbXHXVVcybN6/s+aeffpoHHniA3r17k52dzbvvvku7du1ITU1lx44dtGvXjosvvpj7778/UacgKdnsiY7Pang9lSCpqamFSR/KVxSMOUj8wpTVDacuHtJeglmeH4RdiEIRIQhGPwq7EAHBH5Hejo6YFIIPtlQMt79EeQ90CNq7VA63lxIsaSCpGlkE/wPcEHYhkiRJLUPCguzS0lLGjRvH3LlzSUtLY/LkySxdupQJEyawYMECXnrpJZ544gmmTZtGQUEBmzdvJjc3+HVq6dKlzJw5k6VLl3LgwAG+973vcfDgQY455hheeOGFoPBWrXj66aeZO3duok5BUlNzkGC29TaC6aLVSSd+JnfFkUnQK6Pyv4z7qD3o3kbLaNwrqcmKEPTQ/pjymfQQ/NN3KvEB980E3RIgCLGXUTXgNreTCILsNbhehyRJUiNJoQVceuXl5ZGTkxN2GZKaghSCz+VX174kNjpUs19sVve26P3tBD0VKg4Xp5TUBKQRtIqp3Hs7s8I2a6kabq8gnL/peZ3XcoX6vW8F3A28BbwSTgmSJKlxHXXUUdx2223069ePlJSUsMtp8iKRCKtXr+bBBx9ky5Ytca/VdJ3X5BZ7lKSEilAePNe0eFMrap7VfTTB5/czqtnvIEGYXTng3kHV4NtVESWFpBRYHh1/rvB8N6qG2xcSfNAFgi5MM4HRjVapFKJeBH/1sT+2JEktxm233caCBQu4//77KS31Y9lHKi0tjcsvv5zbbruN8ePH12kfg2xJqq8DwOboqElrgpndHQlmcFceHYFjotukVbP/PqoPuCsH37twsUpJjWITMC86YloD/SkPtl0wUi1GVvS2pj96S5KkZqdfv36G2A2otLSU2bNnM2LEiDrvY5AtSYmwH/g8OmqTQtCMtnLIXfFxbJZ322r2P0gQZtc0s7vi887yltTA9gPvR8cfQ65FalRZBP+P3xFyHZIkqdGkpKQYYjew0tLSerVpMciWpDBFCILoXcD6Q2zbippnd8fu94je1jbLu7aWJrFe3s7yliSpZpnYVkSSJKmRGWRLUlNxgLrP8s6g+tndFQPv46h+lneEuvfy3nv4pyNJUpPUAegCvBNyHZIkqUXp2rUrr7wSrDLds2dPSktL2bBhAwCDBw9m//79Ne575plnMmrUKG699dZa3+PNN9/kq1/9asMV3cAMsiWpuYkAu6NjwyG2TaP2tiYdgO7R2+r+j7GfqgH3rgpjd6X7tjeRJDV1sf7YzsiWJEmNaPPmzQwaNAiA8ePHs2PHDn7zm9+UvZ6WllZj65OFCxeycOHCQ75HMofYYJAtSS1bKbA1Og6lci/vyuF3d6Af0K6WYxyg+oC78v2Kz+0lCOclSUoGmQT//1wbdiGSJCk0lwA9G/iY64C/12+XJ598kj179jBo0CDefPNNZsyYwUMPPURGRga7d+/mO9/5Dh999BHnnXced9xxB8OGDWP8+PEce+yxHH/88Rx77LE8+OCD/P73vwdg+/btdOzYkfPOO4/77ruPjRs3csopp7Bw4UK+/e1vA3DppZfywAMPsHPnTt58802OP/54hg0b1sBfjOoZZEuS6qaus7xTCVqbtCMIv9vVcv/oCvdTazjeQaoPuGu7vxv7fEuSEiML+Izgj7OSJEkhy8rK4itf+QoHDx6kY8eOnHPOOZSWljJkyBB+8YtfcNVVV1XZp3///lxwwQV07NiRFStW8Mgjj3DgQPzFzaBBgzj55JNZs2ZNWcuRBQsW8Nhjj3HuueeyevVqnn766cY6TcAgW5LU0A5SHirXRwaHDr7bEfQl7R29X9v/xWKBdl2C79itoYQkqTYpBP8PWhJ2IZIkKVT1nDmdSM888wwHDwYzuTp37syUKVPIzs4mEonQunXraveZPXs2+/btY9OmTaxfv55jjjmGkpKSuG3efffdsucWL15Mv3792LFjB6tWrWL16tUATJ8+nRtvvDFxJ1eJQbYkKTnsiY4t9dinNYcOvmMtUWKzv9vUcrx91N7mpLr79v2WpJajB8H/R+yPLUmSksTOnTvL7v/0pz9l/vz5XHnllfTt25dXX3212n327t1bdr+0tJRWrapGxHXZprGFX4EkSYdrP3Xv8R2TRt3ansRmf8eeq8kBqm9tsucQ9+39LUlNT2yhx5Jat5IkSQpF586dy2ZR33DDDQ1+/BUrVnD88cfTt29fPvnkE6655poGf4/aGGRLklqWUmB7dNRVffp+d4/eb0vt/5c9SPks9OoC79rC8P31qF2S1HCyCP4d3hR2IZIkSVX953/+J1OmTOHee+9l9uzZDX78PXv2cMstt/D3v/+dnTt3kpeX1+DvUZsUWsB8sLy8PHJycsIuQ5LU0rSiPNTOqMP9io9rWvwSgjC+LoF3da+VNuD5SUnA67yWK5Tv/c3ANuBPjfu2kiQpfFOnTmXUqFFhlxG69u3bl7UzefjhhykoKODBBx887ONV93Wt6TrPGdmSJCXKAeo/+zumDXULvGM9wHtUeL42+6jf7O/Y4z20gD99S1It2hCst7As7EIkSZLCM3bsWEaPHk16ejr5+fk89thjjfbeBtmSJCWjvdFRn/7fEMzkbkPdZ393rXA/vZbjRqhbK5S9BK1P9hOE5vurGQfreU6SlAx6E3ye1YUeJUlSC/bggw8e0QzsI2GQLUlSc3KQ8mC5vtI49Ozvivc7VbifVo/3OUDVcLu60PtwnzuAs8clNbzM6K0LPUqSJIXCIFuSJAVKgR3RUV/pBCF3G6B1pZFej+faV/NcfULymJpmgzdUYG6vcanlyQI2cnh/KJQkSdIRM8iWJElHbl90JEIqhx+MV36uXQ3bpdSzpoPUPBu8tA6jrtvVd9i2RUqcLODjsIuQJElquQyyJUlScjtIec/wRGnFkc0kj91vRfks8tpGK+ofntdFhPBC9FJgJ7A+Aeclha0zwcK69seWJEkKjUG2JEnSgehozJYBKRw68D5UGH4k+7cmaAdTl23rqgD4U/2+DFKTkBW9NciWJEkhmTdvHr/61a94+eWXy5679dZbOemkk7jllluqbD9//nzuuOMOFi5cyOzZs7n22mvZunVr3Dbjx49nx44d/OY3v6nxfYcPH85HH33EsmXLAJgwYQKvv/46r7zySgOdWd0ZZEuSJIUhQnmAnsxSCNq71CXwTuSseSlMK4E/Ap+FXYgkSWqppk+fTm5ublyQnZuby//7f//vkPtefvnlh/2+V1xxBX/961/Lguzx48cf9rGOVGpo7yxJkqTkF2tXso9gxvoOYCuwGdgArANKgE8x5FPztZcgzLYPvSRJAn4LzG/g8dtDvOezzz7L5ZdfTuvWrQHo27cvvXv3ZuTIkeTl5fHBBx9w3333VbtvYWEh3bp1A+Df//3fWbFiBW+88QYnnXRS2Tb/9m//xrvvvsvixYt59tlnadu2LV/+8pf55je/yX/913+Rn5/P8ccfz5NPPsmIESMAuPDCC1m0aBHvvfceTzzxBOnp6WXvd99997Fw4ULee++9uPc5EgbZkiRJkiRJkpTEtmzZwrvvvsull14KBLOxZ86cyT333ENOTg6nnnoq5513Hl/84hdrPMYZZ5xBbm4up59+Opdddhk5OTllrz3//PMMHjyY008/nWXLljFmzBj+7//+j1mzZvHjH/+YQYMGsWrVqrLt27Rpw1NPPcU111zDqaeeSqtWrbj55pvLXt+4cSNnnnkmjzzyCHfccUeDfA1sLSJJkiRJkiRJdfTDkN431l5k1qxZ5ObmMmbMGK6++mpuvPFGWrVqRa9evRg4cCDvv/9+tfufc845vPDCC+zeHSwONGvWrLLXTjnlFH72s5/RpUsXOnTowNy5c2ut5aSTTqKwsJCCggIApkyZwve+9z0eeughIAjGARYuXMiVV155xOcOzsiWJEmSJEmSpKT34osvMmTIEAYNGkS7du3YvHkzd9xxB0OGDOG0005j9uzZZGRkHNaxn3rqKcaNG8epp57KhAkTDvs4MXv3BgvolJaW0qpVw8ylNsiWJEmSJEmSpCS3c+dO5s+fz+TJk5k+fTqdOnVi586dbN26laOPPrqs7UhNXn/9da644goyMjLo0KEDw4YNK3utY8eOrF27llatWnHdddeVPb99+3Y6duxY5VgrVqygX79+nHDCCQBcf/31vPbaaw10ptUzyJYkSZIkSZKkJmD69OmcfvrpTJ8+nffee4/8/HyWL1/O008/zZtvvlnrvvn5+fz5z39myZIlzJkzh7y8vLLXfvKTn/DOO+/w5ptvsnz58rLnZ8yYwY9//GMWLVrE8ccfX/b83r17+c53vsMzzzzDe++9x8GDB3n00Ucb/oQrSCFYi75Zy8vLi2teLkmSpObB67yWy++9JElqTFOnTmXUqFFhl9HsVPd1rek6zxnZkiRJkups6NChLF++nIKCAu68884qrz/wwAPk5+eTn5/PihUr2LJlCwDnn39+2fP5+fns3r2b4cOHA/Dkk0+yatWqstdOO+20Rj0nSZIkJb+G6bQtSZIkqdlLTU3l4Ycf5qKLLqK4uJi8vDxmzZrFsmXLyra5/fbby+6PGzeOQYMGAfDqq6+W3T/qqKNYuXIlL7/8ctm2P/7xj3nuueca6UwkSZLU1DgjW5IkSVKdDB48mJUrV1JYWMj+/fuZMWNG2azq6owcOZLp06dXef6qq65izpw57N69O5HlSpIkNZhIJML/b+9eQ6LK/ziOf3RGy4ouUCGN0zQsFkG1KRVdYB+0C/tAqCCoWaIiIii6rAuVWz2IiB4EUdKFhbFyIyaMrCAflOwmSFDUhJcy7UbjppapsUlFVNr5P4gGQtt18fzP79h5v+BDztEZv8NvJj78Op3x+Xymx/iq+Hw+WVbfr3rNRjYAAACAPgkEAmpqakrebm5uViAQ6PVnx48fr3A4rIqKih7fi0QiPTa49+zZo9raWu3fv1/p6em9PuaaNWsUj8cVj8c1evTofjwTAACA/6axsVF5eXlsZtvE5/MpLy9PjY2Nfb4PlxYBAAAAYLtIJKLS0lJ9+PDhs+OZmZmaOnWqysvLk8e2bdum1tZWpaenKxqNqqCgQLt37+7xmEVFRSoqKpL08UOAAAAAnFJYWKj8/HwtXrxYKSkppscZ8CzLUmNjowoLC/t8HzayAQAAAPRJS0uLgsFg8nZWVpZaWlp6/dlIJKL169f3OL5kyRKdP39eXV1dyWOtra2SpHfv3qm4uFibN2+2eXIAAID++fvvv7Vz507TY3galxYBAAAA0CfxeFzZ2dmaMGGC0tLSFIlEdOHChR4/N2nSJI0aNUrXrl3r8b3erpudmZmZ/HrRokWqq6uzf3gAAAAMaJyRDQAAAKBPuru7tWHDBpWXl8vn8+n48eOqr6/Xrl27dPPmTZWVlUn6eDZ2SUlJj/uHQiEFg0FVVlZ+djwWi2nMmDFKSUlRTU2N1q5d68jzAQAAwMCRIqnvHw05QMXjcc2cOdP0GAAAALAZPc+7WHsAAICv05d6nic2stva2vTXX385+jtHjx6tjo4OR38n3IP19zbW39tYf29j/Z0XCoU0duxY02PAAKc7Pu9v8BrwNtbf21h/b2P9nfdPHd8i9icejxufgbD+hPUnrD9h/Qkh9oT3N+E14O2w/t4O6+/tsP7uCR/2CAAAAAAAAABwNTayAQAAAAAAAACuxkb2/0k0GjU9Agxi/b2N9fc21t/bWH/g68X7G7wGvI319zbW39tYf/fwxIc9AgAAAAAAAAAGLs7IBgAAAAAAAAC4GhvZAAAAAAAAAABXYyPbZj/++KPu3r2rBw8eqKCgwPQ4cFBWVpYqKip0584d1dXVadOmTaZHggGpqamqqqpSWVmZ6VHgsBEjRujMmTNqaGhQfX29Zs+ebXokOCg/P191dXW6ffu2Tp06pUGDBpkeCYCN6PjeRceHRMf3Mjq+t9Hx3cki9iQ1NdV6+PChFQ6HrbS0NKumpsaaPHmy8bmIM8nMzLRycnIsSdawYcOse/fusf4ezC+//GLFYjGrrKzM+CzE2fz+++/W6tWrLUlWWlqaNWLECOMzEWcybtw469GjR9bgwYMtSdbp06etlStXGp+LEGJP6PjeDh2fSHR8L4eO793Q8d0Zzsi20axZs/Tw4UMlEgm9f/9eJSUlWrhwoemx4JDW1lZVV1dLkl69eqWGhgYFAgHDU8FJgUBAeXl5Onr0qOlR4LDhw4fru+++07FjxyRJ79+/V2dnp+Gp4CS/36+MjAz5fD4NGTJET548MT0SAJvQ8b2Njg86vnfR8UHHdx82sm0UCATU1NSUvN3c3EzJ8ahQKKScnBxdv37d9ChwUGFhobZu3aoPHz6YHgUOC4fDam9vV3FxsaqqqlRUVKQhQ4aYHgsOefLkifbt26fHjx/r6dOn6uzs1B9//GF6LAA2oePjEzq+N9HxvYuO7210fHdiIxuw2dChQ3X27Fnl5+fr5cuXpseBQ/Ly8tTW1qaqqirTo8AAv9+v3Nxc/fbbb8rNzdXr16/166+/mh4LDhk5cqQWLlyocDiscePGaejQoVq2bJnpsQAANqLjexMd39vo+N5Gx3cnNrJt1NLSomAwmLydlZWllpYWgxPBaX6/X2fPnlUsFtP58+dNjwMHzZs3TwsWLFAikVBJSYnmz5+vkydPmh4LDmlublZzc7Nu3LghSSotLVVubq7hqeCUH374QYlEQh0dHerq6tK5c+c0d+5c02MBsAkdH3R876Ljexsd39vo+O7ERraN4vG4srOzNWHCBKWlpSkSiejChQumx4KDjh07poaGBh04cMD0KHDY9u3bFQwGFQ6HFYlEVFFRoeXLl5seCw559uyZmpqaNHHiREnS999/r/r6esNTwSmPHz/W7NmzlZGRIenj+jc0NBieCoBd6Pig43sXHd/b6PjeRsd3J7/pAb4m3d3d2rBhg8rLy+Xz+XT8+HH+kvOQefPmacWKFbp161byA2G2b9+uixcvGp4MgBM2btyoWCym9PR0PXr0SKtWrTI9Ehxy48YNlZaWqqqqSl1dXaqurlY0GjU9FgCb0PG9jY4PeBsd37vo+O6UIskyPQQAAAAAAAAAAF/CpUUAAAAAAAAAAK7GRjYAAAAAAAAAwNXYyAYAAAAAAAAAuBob2QAAAAAAAAAAV2MjGwAAAAAAAADgamxkA4BLdXV1qbq6OpmCggLbHjsUCun27du2PR4AAACAf0a/B4D+8ZseAADQuzdv3ignJ8f0GAAAAABsQL8HgP7hjGwAGGASiYT27t2rW7du6fr16/rmm28kfTwL4/Lly6qtrdWff/6pYDAoSRo7dqzOnTunmpoa1dTUaM6cOZIkn8+naDSquro6lZeXa/DgwcaeEwAAAOBV9HsA6Bs2sgHApTIyMj77r4dLlixJfq+zs1PTpk3T4cOHVVhYKEk6dOiQTpw4oW+//VaxWEwHDx6UJB08eFCVlZWaPn26cnNzdefOHUlSdna2jhw5oilTpujFixdavHix488RAAAA8Ar6PQD0n0UIIcR9efnyZa/HE4mEFQ6HLUmW3++3Ojo6LElWe3u75ff7k8fb29stSVZbW5uVnp7+2WOEQiHr/v37ydtbt261duzYYfw5E0IIIYQQ8rWGfk8IIf0LZ2QDwABkWVavX/8Xb9++TX7d3d0tv5+PTQAAAABMoN8DwL9jIxsABqClS5cm/7x27Zok6erVq4pEIpKkZcuW6cqVK5Kky5cva926dZKk1NRUDR8+3MDEAAAAAL6Efg8A/45/ngMAl/p0Db1PLl26pG3btkmSRo0apdraWr19+1Y//fSTJGnjxo0qLi7Wli1b1N7erlWrVkmSfv75Z0WjUa1evVrd3d1at26dnj596vwTAgAAADyMfg8A/ZOij9cYAQAMEIlEQjNmzNDz589NjwIAAACgn+j3ANA3XFoEAAAAAAAAAOBqnJENAAAAAAAAAHA1zsgGAAAAAAAAALgaG9kAAAAAAAAAAFdjIxsAAAAAAAAA4GpsZAMAAAAAAAAAXI2NbAAAAAAAAACAq/0PiShEZCZHHtIAAAAASUVORK5CYII=\n",
+      "image/png": "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\n",
       "text/plain": [
        "<Figure size 1800x504 with 2 Axes>"
       ]
@@ -363,10 +382,10 @@
     }
    ],
    "source": [
-    "loss_train = history1.history['loss'] # save the loss into variable to call it for the plot\n",
-    "loss_val = history1.history['val_loss']  # save the val_loss into variable to call it for the plot\n",
-    "acc_train = history1.history['accuracy']  # save the accuracy into variable to call it for the plot\n",
-    "acc_val = history1.history['val_accuracy']  # save the val_accuracy into variable to call it for the plot\n",
+    "loss_train = history1['loss'] # save the loss into variable to call it for the plot\n",
+    "loss_val = history1['val_loss']  # save the val_loss into variable to call it for the plot\n",
+    "acc_train = history1['accuracy']  # save the accuracy into variable to call it for the plot\n",
+    "acc_val = history1['val_accuracy']  # save the val_accuracy into variable to call it for the plot\n",
     "\n",
     "plt.figure(\"Training Graph 1\" , figsize = (25 ,7))  # unique identifier for the figure, figsize(Width, height)\n",
     "\n",
@@ -409,10 +428,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1875/1875 [==============================] - 10s 5ms/step - loss: 0.0024 - accuracy: 0.9854\n",
-      "313/313 [==============================] - 1s 4ms/step - loss: 0.0045 - accuracy: 0.9717\n",
-      "Training accuracy: 98.54%\n",
-      "Test accuracy: 97.17%\n"
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 0.0023 - accuracy: 0.9860\n",
+      "313/313 [==============================] - 1s 4ms/step - loss: 0.0042 - accuracy: 0.9738\n",
+      "Training accuracy: 98.6%\n",
+      "Test accuracy: 97.38%\n"
      ]
     }
    ],
@@ -495,49 +514,64 @@
      "output_type": "stream",
      "text": [
       "Epoch 1/10\n",
-      "1875/1875 [==============================] - 17s 8ms/step - loss: 0.0373 - accuracy: 0.7256 - val_loss: 0.0139 - val_accuracy: 0.9116\n",
+      "1875/1875 [==============================] - 17s 8ms/step - loss: 0.0539 - accuracy: 0.5418 - val_loss: 0.0392 - val_accuracy: 0.6486\n",
       "Epoch 2/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0124 - accuracy: 0.9217 - val_loss: 0.0120 - val_accuracy: 0.9246\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0380 - accuracy: 0.6554 - val_loss: 0.0375 - val_accuracy: 0.6563\n",
       "Epoch 3/10\n",
-      "1875/1875 [==============================] - 16s 8ms/step - loss: 0.0091 - accuracy: 0.9427 - val_loss: 0.0084 - val_accuracy: 0.9486\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0363 - accuracy: 0.6659 - val_loss: 0.0269 - val_accuracy: 0.7678\n",
       "Epoch 4/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0074 - accuracy: 0.9541 - val_loss: 0.0067 - val_accuracy: 0.9582\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0220 - accuracy: 0.8141 - val_loss: 0.0091 - val_accuracy: 0.9430\n",
       "Epoch 5/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0061 - accuracy: 0.9627 - val_loss: 0.0064 - val_accuracy: 0.9593\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0071 - accuracy: 0.9565 - val_loss: 0.0076 - val_accuracy: 0.9515\n",
       "Epoch 6/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0055 - accuracy: 0.9666 - val_loss: 0.0060 - val_accuracy: 0.9632\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0059 - accuracy: 0.9639 - val_loss: 0.0078 - val_accuracy: 0.9523\n",
       "Epoch 7/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0049 - accuracy: 0.9698 - val_loss: 0.0055 - val_accuracy: 0.9664\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0053 - accuracy: 0.9680 - val_loss: 0.0057 - val_accuracy: 0.9643\n",
       "Epoch 8/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0046 - accuracy: 0.9721 - val_loss: 0.0054 - val_accuracy: 0.9665\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0047 - accuracy: 0.9712 - val_loss: 0.0060 - val_accuracy: 0.9626\n",
       "Epoch 9/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0042 - accuracy: 0.9747 - val_loss: 0.0052 - val_accuracy: 0.9681\n",
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0044 - accuracy: 0.9732 - val_loss: 0.0053 - val_accuracy: 0.9667\n",
       "Epoch 10/10\n",
-      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0039 - accuracy: 0.9765 - val_loss: 0.0053 - val_accuracy: 0.9668\n"
+      "1875/1875 [==============================] - 15s 8ms/step - loss: 0.0041 - accuracy: 0.9749 - val_loss: 0.0054 - val_accuracy: 0.9665\n"
      ]
     }
    ],
    "source": [
-    "model_Two = Sequential() # A sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor.\n",
+    "# Switch this to True or False to enable/disable loading of the model from disk\n",
+    "# Make sure to run the entire notebook at least once before setting this to True.\n",
+    "LOAD_MODEL2 = False\n",
+    "\n",
+    "model_Two = None\n",
     "\n",
-    "model_Two.add(Lambda(preprocess_image)) # in this first layer we normalize the image\n",
+    "if LOAD_MODEL2:\n",
+    "    model_Two = load_model(BASE_PATH + 'deep_learning_model_Two.h5')\n",
+    "else:\n",
+    "    model_Two = Sequential() # A sequential model is appropriate for a plain stack of layers where each layer has exactly one input tensor and one output tensor.\n",
     "\n",
-    "model_Two.add(Dense(80, input_dim=784, activation='relu')) # actual input layer\n",
-    "model_Two.add(Dense(50, activation='relu')) # hidden layer 1\n",
-    "model_Two.add(Dense(20, activation='relu')) # hidden layer 2\n",
-    "model_Two.add(Dense(10, activation='relu')) # hidden layer 3\n",
-    "model_Two.add(Dense(50, activation='relu')) # hidden layer 4\n",
-    "model_Two.add(Dense(20, activation='relu')) # hidden layer 5\n",
-    "model_Two.add(Dense(10, activation='relu')) # hidden layer 6\n",
-    "model_Two.add(Dense(50, activation='relu')) # hidden layer 7\n",
-    "model_Two.add(Dense(20, activation='relu')) # hidden layer 8\n",
-    "model_Two.add(Dense(10, activation='sigmoid')) # output layer\n",
+    "    model_Two.add(Lambda(preprocess_image)) # in this first layer we normalize the image\n",
     "\n",
-    "model_Two.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])\n",
+    "    model_Two.add(Dense(80, input_dim=784, activation='relu')) # actual input layer\n",
+    "    model_Two.add(Dense(50, activation='relu')) # hidden layer 1\n",
+    "    model_Two.add(Dense(20, activation='relu')) # hidden layer 2\n",
+    "    model_Two.add(Dense(10, activation='relu')) # hidden layer 3\n",
+    "    model_Two.add(Dense(50, activation='relu')) # hidden layer 4\n",
+    "    model_Two.add(Dense(20, activation='relu')) # hidden layer 5\n",
+    "    model_Two.add(Dense(10, activation='relu')) # hidden layer 6\n",
+    "    model_Two.add(Dense(50, activation='relu')) # hidden layer 7\n",
+    "    model_Two.add(Dense(20, activation='relu')) # hidden layer 8\n",
+    "    model_Two.add(Dense(10, activation='sigmoid')) # output layer\n",
     "\n",
+    "    model_Two.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy'])\n",
+    "\n",
+    "history2 = None\n",
     "amount_epochs = 10 # amount of the epochs\n",
     "\n",
-    "history2 = model_Two.fit(XTrain, YTrain, epochs=amount_epochs, validation_data = (XTest, YTest)) # Train the neural network"
+    "if LOAD_MODEL2:\n",
+    "    history2 = pd.read_csv(BASE_PATH+'deep_learning_traing_model_Two.log', sep=',', engine='python')\n",
+    "else:\n",
+    "    csv_logger = CSVLogger(BASE_PATH+'deep_learning_traing_model_Two.log', separator=',', append=False)\n",
+    "    history2 = model_Two.fit(XTrain, YTrain, epochs=amount_epochs, validation_data = (XTest, YTest), callbacks=[csv_logger]).history # Train the neural network\n",
+    "    model_Two.save(BASE_PATH+'deep_learning_model_Two.h5')"
    ]
   },
   {
@@ -556,7 +590,7 @@
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABawAAAG5CAYAAABiCnMGAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAACA4UlEQVR4nOzdeXjU1aH/8XcS9lUBV1a1qOCKGtzqBiJFRaxaBWvF1mLVq9Wf1aqtvYh2uda61Vr1UuvWCkWutShFVMB9i2wuLIKCQsAi+76F+f1xkpBAgCwzOTOT9+t5zpPMzHdmPkMUZj4533NygASSJEmSJEmSJEWWGzuAJEmSJEmSJElgYS1JkiRJkiRJShMW1pIkSZIkSZKktGBhLUmSJEmSJElKCxbWkiRJkiRJkqS0YGEtSZIkSZIkSUoLFtaSlCY6duxIIpEgLy9vl8cOHDiQN998sxZSSZIkSfK9uiTVHgtrSaqGOXPmsGHDBlq3bl3u+kmTJpFIJOjYsWOkZFV7My1JkiRlm3R+r16iadOmrFq1in//+9+xo0hS2rGwlqRqmjNnDgMGDCi9fOihh9KkSZOIiSRJkiRB+r9XP//889mwYQO9evVir732qtXndmKLpHRnYS1J1fT0009z6aWXll4eOHAgTz31VLljWrRowZNPPsmiRYuYO3cuv/zlL8nJyQEgNzeXu+++m2+++YbPP/+cs846a7v7/uUvf2HBggXMnz+fO++8k9zcmv21vc8++/Cvf/2LJUuWMGvWLH784x+X3pafn09BQQErVqzg66+/5p577gGgYcOGPP300yxevJhly5bxwQcfsOeee9YohyRJkpRK6f5efeDAgTzyyCN89NFHXHLJJeVuO/HEE3n77bdZtmwZX331FQMHDgSgUaNG/OEPf2Du3LksX76cN998k0aNGnHKKacwb968co8xZ84cevbsCcDgwYN59tlnefrpp1mxYgWXXXYZ+fn5vPPOOyxbtowFCxbw4IMPUr9+/dL7d+3alZdffpklS5bw9ddfc+utt7LXXnuxZs0aWrVqVXpct27dWLRoEfXq1av0a5ekykg4HA6Ho2pjzpw5iZ49eyZmzJiROPjggxO5ubmJefPmJTp06JBIJBKJjh07JoDEk08+mXj++ecTzZo1S3Ts2DExc+bMxI9+9KMEkPjJT36SmD59eqJdu3aJ3XffPTF+/PhEIpFI5OXlJYDEc889l3jkkUcSTZo0Seyxxx6J999/P3HFFVckgMTAgQMTb775ZoXZOnbsWO5xyo7XX3898dBDDyUaNmyYOOKIIxKLFi1KnHbaaQkg8c477yQuueSSBJBo2rRp4thjj00AiSuuuCIxatSoROPGjRO5ubmJo446KtG8efPoPwOHw+FwOBwOh6Oikc7v1YFEhw4dEkVFRYkuXbokbrjhhsTUqVPL3bZy5cpE//79E/Xq1Uu0atUqccQRRySAxJ/+9KfEhAkTEvvuu28iNzc3cfzxxycaNGiQOOWUUxLz5s2r8M8ASAwePDixcePGRL9+/RI5OTmJRo0aJY466qjEsccem8jLy0t07NgxMW3atMR1112XABLNmjVLLFiwIHHDDTckGjZsmGjWrFmie/fuCSAxevToxJVXXln6PPfee2/ij3/8Y/SfucPhyLoRPYDD4XBk3Ch5A/jLX/4y8dvf/jbRu3fvxMsvv5zIy8srfROcm5ub2LBhQ6JLly6l97viiisSEyZMSACJcePGJX7yk5+U3tarV6/SN8F77rlnYv369YlGjRqV3t6/f//E+PHjE1C9wrpdu3aJzZs3J5o1a1Z63W9/+9vE448/noBQZt9+++2J1q1bl7vfD3/4w8Tbb7+dOOyww6L/uTscDofD4XA4HLsa6fxeHUj88pe/TEyePDkBJPbdd9/E5s2bE0ceeWQCSNxyyy2J5557brv75OTkJNauXZs4/PDDt7utMoX166+/vtM/s+uuu670efv375+YNGlShcddeOGFibfeeisBJHJzcxMLFy5M5OfnR/+ZOxyO7BqesyFJNfD000/zxhtvsN9++213imGbNm1o0KABX375Zel1X375JW3btgVg3333LXfqXtnjOnbsSP369Vm4cGHpdbm5udud6lcV++67L0uXLmX16tXlnvOYY44B4PLLL+eOO+5gxowZzJkzhyFDhjB69Giefvpp2rdvz/Dhw9ltt93429/+xi9/+Us2b95c7SySJElSqqXre/VLL72UoUOHArBgwQJef/11Bg4cyJQpU2jfvj2ff/75dvdp06YNjRs3rvC2ytg2W+fOnbn33ns55phjaNKkCfXq1WPixIkAO8wA8K9//YtHHnmETp06cdBBB7FixQoKCgqqlUmSdsQ1rCWpBr766ivmzJnDmWeeyXPPPVfutsWLF7Nx48Zyu5B36NCBwsJCABYuXEj79u3L3VZi3rx5bNiwgTZt2rD77ruz++6707JlSw499NBqZ12wYAGtWrWiWbNmFeaZPXs2F198MXvuuSd33XUXI0eOpEmTJmzevJk77riDQw45hBNOOIGzzz673HqAkiRJUjpKx/fqxx9/PAceeCC33norCxcuZOHChRx77LFcfPHF5OXlMW/ePA444IDt7rd48WLWrVtX4W1r1qwpt6Fkbm4ue+yxR7ljEolEucsPP/wwM2bMoHPnzrRs2ZJf/OIXpet3z5s3j/3337/C/Bs2bGDEiBFccskl/OAHP+Dpp5/e5WuWpKqysJakGrr88svp0aMHa9euLXf9li1bGDFiBL/5zW9o1qwZHTp04IYbbuBvf/sbACNGjOCnP/0pbdu2ZbfdduOWW24pve/XX3/Nyy+/zD333EPz5s3Jyclh//335+STT650roYNG5YbhYWFvPPOO/zud7+jYcOGHHbYYVx++eWleb7//e/Tpk0bEokEy5cvL30Np556Koceeii5ubmsXLmSTZs2sWXLlhr+qUmSJEmpl27v1QcOHMjLL79M165dOfLIIznyyCM59NBDady4MX369OHvf/87p59+Ot/73vfIy8ujVatWHHHEESQSCf76179y7733ss8++5Cbm8txxx1HgwYN+Oyzz2jUqBFnnnkm9erV47bbbqNhw4Y7zdG8eXNWrlzJ6tWrOeigg7jqqqtKb3vxxRfZZ599uO6662jQoAHNmjWje/fupbc/9dRTXHbZZZxzzjkW1pJSwsJakmroiy++KD19blvXXnsta9as4YsvvuCtt97imWee4a9//SsAQ4cOZezYsUydOpVJkyZtN+vj0ksvpUGDBkybNo1ly5YxcuRI9tlnn0rnWrNmDevXry8dPXr0YMCAAXTq1IkFCxbwz3/+k8GDBzNu3DgAvvOd7/Dpp5+yatUqHnjgAfr378/69evZe++9GTlyJCtXrmT69Om8/vrrvjGVJElSRkin9+oNGzbkwgsv5MEHH+Q///lP6Zg7dy5PP/00AwcOZN68eZx55pn87Gc/Y+nSpUyZMoUjjjgCgBtvvJGPP/6YgoICli5dyl133VU6qeTqq6/mL3/5C4WFhaxZs4b58+fvNMuNN97IxRdfzKpVqxg6dCj/+Mc/Sm9bvXo1vXr1om/fvnz99dfMmjWL0047rfT2d955hy1btjBp0iS++uqrnT6PJFVHDmExa0mSJEmSJGmXxo0bxzPPPMNjjz0WO4qkLGRhLUmSJEmSpEo55phjeOWVV2jfvn25Dd0lKVlcEkSSJEmSJEm79MQTT/Dqq69y/fXXW1ZLShlnWEuSJEmSJEmS0oIzrCVJkiRJkiRJaaFe7ADJsmjRIr788svYMSRJkpRkHTt2ZM8994wdQxH4Hl+SJCk77ew9ftYU1l9++SX5+fmxY0iSJCnJCgoKYkdQJL7HlyRJyk47e4/vkiCSJEmSJEmSpLRgYS1JkiRJkiRJSgsW1pIkSZIkSZKktJA1a1hLkiTVtt13353rr7+eTp06kZOTEztORkskEsydO5f777+fZcuWxY4jSZIkKRILa0mSpGq6/vrr+fDDD7njjjsoKiqKHSej5eXlcdZZZ3H99dczePDg2HEkSZIkReKSIJIkSdXUqVMn/v3vf1tWJ0FRURGjR4+mU6dOsaNIkiRJisjCWpIkqZpycnIsq5OoqKjIpVUkSZKkOs7CWpIkSZIkSZKUFiysJUmSMlSrVq2YPHkykydPZuHChcyfP7/0cv369Xd636OPPpoHHnhgl8/x9ttvJyuuJEmSJO2Smy5KkiRlqKVLl9KtWzcABg8ezOrVq7nnnntKb8/Ly9vhkiUTJ05k4sSJu3yOE088MTlhJUmSJKkSnGEtSZKURR5//HEefvhh3nvvPX7/+9+Tn5/PO++8w6RJk3j77bc58MADATjllFN44YUXgFB2P/bYY0yYMIHPP/+ca6+9tvTxVq1aVXr8hAkTePbZZ5k+fTp/+9vfSo/p06cP06dP58MPP+SBBx4ofVxJkiRJqipnWEuSJCXDd4C9k/yYXwMvVf1u7dq144QTTmDLli00b96ck046iaKiInr27Mlvf/tbLrjggu3uc/DBB3PaaafRvHlzZs6cycMPP8zmzZvLHdOtWzcOOeQQFixYwNtvv82JJ57Ihx9+yKOPPsrJJ5/M3LlzeeaZZ6r5YiVJkiTJwlqSJCnrPPvss2zZsgWAli1b8uSTT9K5c2cSicQO17YePXo0GzduZMmSJSxatIi99tqLwsLCcsd88MEHpddNmTKFTp06sXr1ar744gvmzp0LwLBhw7jiiitS9+IkSZIkZTULa0mSpGSoxkzoVFmzZk3p93feeScTJkzgvPPOo2PHjrz22msV3mfDhg2l3xcVFVGv3vZvEytzjCRJkiTVhGtYV1d9YJ/YISRJknauZcuWpbOiL7vssqQ//syZM9l///3p2LEjABdddFHSn0OSJElSDeQAeUADoDHQDGgB7A60AfYqvi1NOC2muvoB+wF/BDbs4lhJkqRIfv/73/Pkk09y2223MXr06KQ//vr167n66qt56aWXWLNmDQUFBUl/DkmSJCkt5BKK35Kxs8tVOTbVlyszZfkJYG5V/0BSIwdIxA6RDAUFBeTn59feE+4DXAG8C7xce08rSZLSx1NPPcWll14aO0Z0TZs2LV2G5KGHHmLWrFncf//91Xqsiv5Ma/19ntKGP3tJkuqAHLaWq/UoX7pWNCpzTHUfa1clcCptAYrKfC2qxOWqHLury18BW1cWTLmdvc9zhnV1LQQmA8cCE4ElceNIkiTFMmjQIAYOHEiDBg2YPHkyjz76aOxIkiRJqkguYZnbikaySt/qHJdsZYvYzZQvabcdmyq4LplFcGWPzYopxclhYV0T44CuQG/gmchZJEmSIrn//vurPaNakiRJxXIoXyA3YMfl8q5u39FtyWgCt7DrErikKN64i9sr8xjVOcbyN6NZWNfEGuB1QmHdGZgVN44kSZIkSZJSYNsyORXFcnVaus2EGcJlx8bisaaC20pur+j6ypbElsFKMQvrmvoAOIZQWn9B+B9XkiRJkiRJceQSiuCGZb7u6vuSsbPiuaqK2HE5vG4nt+2qWC65bTNhtrOUZSysa6oIeAn4PtCdsAmjJEmSJEmSKi+PqhXM235f9rrKlsslS1ZsYOus5JIyuarlcUXXWyZHkws0A5rvZLQo830TwiT6ksnjZb/W5Pt0eYzKPN4IYB7pwcI6GWYVj1OAj6jVHTUlSZIkSZKiKFnSojoF87Zlc2Ubqk2EgrmkZN4ArCzzfdnrK7qu7PeeJZ9WGlH5gnlXxzWt5HMWAasJVd4WQmmdU3zbzr6v6e01OTa3kq+tqj7Ewjr7jAWuAnoAL0TOIkmS6oTx48fzP//zP7z88sul11133XUcdNBBXH311dsdP2HCBG688UYmTpzI6NGjufjii1mxYkW5YwYPHszq1au55557dvi8/fr147PPPmP69OkADBkyhDfeeINx48Yl6ZVJkqSUyyVMK21WPJpQ9dnMlW3OKiqN1+7g+p0VzxtJyqzlXKADcBBwYPFoR/kVPLb9WtF1lbmtKvfPtP48l+QVzM2pfEm5Fli1zfiaMJe07HUrKzhu27G2ei89rSSrKF+fwoxVZWGdLIsJ61kfR/iVxMK4cSRJUvYbNmwY/fv3L1dY9+/fn5///Oe7vO9ZZ51V7ec999xzefHFF0sL68GDB1f7sSRJUhLlsLWEbsrWMrqiyyVrIFRkCxUXyCsruG5X328i2iZ9bQhldNli+iDgW4S+vcRK4EtCAbvtPogNtvmaaiV/ZMkuw3d1zBbCfyKVKZlLjmlSyde0mYrL4gU7uH5HYyVhNnSmFfuptu1yH9nAwjqZXgcOB74DPB45iyRJynojR47k17/+NfXr12fTpk107NiRfffdlwEDBnDvvffSuHFjRo4cye23377dfefMmcMxxxzDkiVL+MUvfsHAgQNZtGgR8+bNY+LEiQD8+Mc/5oorrqBBgwbMnj2bH/zgBxx55JGcc845nHLKKdx2222cf/75/OpXv+LFF1/k//7v/+jRowd/+MMfqFevHgUFBVx11VVs3LiROXPm8OSTT9K3b1/q16/P9773PWbOnFnLf2KSJGWgHKAxuy6gmxaPimY9byI0fauBZYTz/leXGWuKR0nZvDllrybpmhAK6G1L6QOB3csctxH4HPgMGF389TNgJrCoCs9Xdg/Gbcvsiq6r7m2VOb4B4UdfmccqW9BXxmq2L4wLK7iuMrOZ02nmrjKDhXUyrQfGAecAhwKfxI0jSZJqz33AkUl+zCnA/9vJ7cuWLeODDz6gT58+jBo1iv79+zNixAh++9vfsmzZMnJzcxk3bhyHHXYYH3/8cYWPcdRRR9G/f3+OPPJI6tWrx6RJk0oL6+eee46//OUvANx5551cfvnl/OlPf2LUqFGlBXVZDRs25IknnqBnz57MmjWLJ598kquuuooHHngAgMWLF3P00Udz1VVXceONNzJo0KCa/hFJkpS5GrHz8rns93kV3H8zW8vmFYQ2seTytmX0hhS+jlqQB3Sk4tnS7bc5dh6hiB7G1lL6M2AuyZmZWzIjORPlsePyO4+tJfVq3C9ScVlYJ9tkIB/oRfg1Xab+LSZJkjJCybIgJYX15ZdfzoUXXsgVV1xBvXr12GeffejatesOC+uTTjqJf/7zn6xbtw6AUaNGld526KGH8utf/5rddtuNZs2aMXbs2J1mOeigg5gzZw6zZs0C4Mknn+S//uu/Sgvr5557DoCJEydy3nnn1fi1S5KUdhpSueU4mlJxI1NE+cL5ayouoFeTldNW92T7WdIHEmZQNyhz3HJC5fJa8deSUnoW2bEmcaoUAeuKh5TOLKyTLQGMAX4EnEj421OSJGW9nc2ETqV//etf3HfffXTr1o0mTZqwdOlSbrzxRvLz81m+fDmPP/44jRo1qtZjP/HEE5x77rl89NFHDBw4kFNPPbVGWTdsCNO7ioqKqFfPt6GSpAxRn12XzyXfV7TI8Ra2lsxrgG/YvnwuGevJroVoK9AU6Mz2pfSBwG5ljtsAzCYU0qMov4TH4tqLKykCPymkwleE5UBOJMy4XhE3jiRJyl5r1qxhwoQJ/PWvf2XYsGG0aNGCNWvWsGLFCvbcc0/69OnDa6+9tsP7v/HGGzzxxBP87ne/o169evTt25dHH30UgObNm7Nw4ULq1avH97//fQoLCwFYtWoVzZs33+6xZs6cSadOnTjggAP4/PPP+cEPfsDrr7+ektctSVJSNQWOJuwkt20h3aCC4xOEqbwlRfNX7Hg5jrVkfQm9rTxgPyqeLd1um2O/JBTRf6f8bOkvcVkKqa6ysE6VVwh/I/cCRkbOIkmSstqwYcN4/vnn6d+/PzNnzmTy5MnMmDGDefPm8fbbb+/0vpMnT+Yf//gHU6dOZdGiRRQUFJTe9qtf/Yr333+fb775hvfff7+0pB4+fDhDhw7lpz/9KRdccEHp8Rs2bOCHP/whzz77bOmmi4888khqXrQkScl0HnAA5UvoQipeimN18XG2qexN+RnSJcX0AZSfbL6UUEaPo3wpPRuXp5C0vRyy5Pd8BQUF5Ofnx45R3qnF43HCrwYlSVJWeeqpp7j00ktjx8gqFf2ZpuX7PNUKf/aSakVn4PuE5T3fj5wlDTWj4lL6QKBFmePWE9aQLlm2o+yGh0tqMa+kzLCz93nOsE6lt4FuwHeA/yVLfjUgSZIkSVKWyAXOICyKXLCLYzNUXvHI3cXXHRXT+5Z5rC1sXcLjScoX0/Nw0rmk5LCwTqVNwMvA94CjgIlx40iSJEmSpKAN0LYLtFsKbcdD6y2VL3dLvqbzsTUpfL4hlNBj2X4Jjw01eFxJqgwL61T7FOgO9Cj+fn3cOJIkKXkSiQR5eXkUFRXFjpIV8vLySCQ8JU2SVDMNCLOC25YZ7ba5vC/QEMLn9E8rfpzNhBnDRcVjSyW/VuXYjUl+vJocu5ZQSH8GLNv1H7MkpYyFdW0YA/wEOIXw60lJkpQV5s6dy1lnncXo0aMtrWsoLy+Ps846i7lz58aOIklKY7tTvniuqJDeo4L7rSXsoTifsHpnIVB4EBQeDoXjoHBpmFW8mVDgSpLisbCuDV8DkwgzrScS1saSJEkZ7/777+f666/n/PPPJycnJ3acjJZIJJg7dy73339/7CiSpAjqAXuz/UzobUeTCu67iK1l9PvFXwu3Gcu3vdPuwIXAVGBpMl+JJKmmLKxry3jgEMIGjH+LnEWSJCXFsmXLGDx4cOwYkiSltebsfHmOtsBehHWXy9rA1sJ5IjCqzOWSUnohYVmNKutFmEo9oTp3liSlkoV1bVkDvA70BjoDs+LGkSRJkiSpJnIJRfPOludoSyist7WUrcXzFLafET0fWJKq4B2AroSJZatS9SSSpOpKaWHdu3dvHnjgAfLy8vjLX/7CXXfdVe72Bg0a8NRTT3H00UezZMkSLrroIr788ks6duzI9OnTmTlzJgDvvfceV111VSqj1o4PgKMJs6y/wIWxJEmSJElpqQk7XpajpJDem+1LhU2EWc+FwCeEbZy2XaJjAbAu5a9gB3IIE8lWAO/GCiFJ2pmUFda5ubk89NBD9OrVi/nz51NQUMCoUaOYPn166TGXX345y5Yto3Pnzlx00UXcdddd9O/fH4DPP/+cbt26pSpeHEXAS8AlwLHAO3HjSJIkSZIEYculIWwto3ev4JgVbC2dp7P9jOhCwnrSiVrIW22HEV7gc4R2XZKUdlJWWHfv3p3Zs2czZ84cAIYPH06/fv3KFdb9+vXj9ttvB2DkyJH86U9/SlWc9DEb+Aw4hbC5w5q4cSRJkiRJGgrsA7wFvMb2S3QUAqtjhUuW+kBPwov5OHIWSdIObbunQdK0bduWefPmlV6eP38+bdu23eExRUVFrFixgtatWwOw3377MWnSJF577TW+/e1vV/gcgwYNoqCggIKCAtq0aZOiV5ICYwm/KugZO4gkSZIkqa7rDRwO3AScB1wL/A/wNGGZ55lkQVkNcDzQkvCZPK2ngUtS3ZaWmy4uXLiQDh06sHTpUo466iief/55DjnkEFatKr8bwtChQxk6dCgABQUFMaJWzxLgfcI/lgWEBb4kSZIkSYrgJsKk42diB0ml5sC3gWnAV5GzSJJ2KmUzrAsLC2nfvn3p5Xbt2lFYWLjDY/Ly8mjZsiVLlixh48aNLF26FIBJkybx+eefc+CBB6YqahyvA2uBPrGDSJIkSZLqqm6Ek38fIMuXdD4NyANeiR1EkrQrKSusCwoK6Ny5M506daJ+/fr079+fUaNGlTtm1KhRDBw4EIALLriA8ePHA9CmTRtyc0O0/fbbj86dO/PFF1+kKmocG4BxQAfg0MhZJEmSJEl10k3ASuDR2EFSaW9CM/8+sCxyFknSLqVsSZCioiKuueYaxo4dS15eHn/961+ZNm0aQ4YM4cMPP+SFF17gscce4+mnn2bWrFksXbqU/v37A3DyySdzxx13sGnTJrZs2cKVV17JsmVZ+K/KZOAY4AzComBZ/etsSZIkSVI66Qh8D7ifUFpnrTOAdcAbsYNIkiojhyzZaqCgoID8/PzYMaquA/AjwhIhEyJnkSRJSkMZ+z5PNebPXkqt+4Grgf0Ia1hnpYOAAcBowh5SkqS0sLP3eSlbEkSV9BXwMXACsFvcKJIkSZKkuqEV8GPCRotZW1bnEWZXfwNMjJxFklRpFtbpoGTTh15RU0iSJEmS6oirgKbAH2IHSaVjgNbAy8CWyFkkSZVmYZ0OVgJvAYcAneJGkSRJkiRlt4bAtcAY4JPIWVKmMXAq8DkwK24USVLVWFini3eA5cB3CCuLS5IkSZKUApcCewF3xw6SSicTmvmXYweRJFWVhXW62ET4h3Rv4KjIWSRJkiRJWSkX+BnwITAhcpaUaQV0ByYD/4mcRZJUZRbW6WQaMBfoCTSKG0WSJEmSlH3OAQ4iy2dX9wI2k8WNvCRlNwvrdPMSW9fakiRJkiQpiW4C5gD/FztIqnQCuhD2iVodN4okqXosrNPN18BEwulLe0TOIkmSJEnKGicUj3uBoshZUiIH6A2sAN6NnEWSVG0W1uloPLCR8A+tJEmSJElJcBOwBPhr7CCpcjiwD/AqYUkQSVJGsrBOR2uB14BvAQfGjSJJkiRJynwHEtavfojwkTPr1CfsBzUf+CRyFklSjVhYp6sPgG8Is6zzImeRJEmSJGW0nwEbgD/FDpIqJwAtgLFAInIWSVKNWFinqy2EDRhbA8dGziJJkiRJylh7AQOBJwnzorJOc+BEwszqeZGzSJJqzMI6nX0OzAROAZpFziJJkiRJykjXElbMuCd2kFTpSWg3Xo0dRJKUDBbW6W4sUI/wD7AkSZIkSVXQFLgKeB6YHTdKauwDHAm8ByyPmkSSlCQW1uluKeEf3m7AvpGzSJIkSZIyyuVAK+Du2EFSpTewBngzdhBJUrJYWGeCN4DVQJ/YQSRJkiRJmaIecAOhy30vcpaUOBjoBEwg7CgpScoKFtaZYAMwDmgPHBY5iyRJkiQpI3wP6EiWzq7OA3oBi4BJkbNIkpLKwjpTTAEWEP5BbhA3iiRJkiQp/d0ETAdejB0kFfKB1sDLwJbIWSRJSWVhnSkSwBigBXBi5CySJEmSpLTWk7AV0j2Ej5NZpTFwCmEXyazcSVKS6jYL60wyD/iIUFjvFjeKJEmSJCl93QR8DfwtdpBUOAVoSJhdLUnKOhbWmeZVwulOZ8QOIkmSJElKR4cDvYEHyMK9CFsTlgOZRFi/WpKUdSysM81K4C2gK2E3ZEmSJEmSyrgRWA08EjtIKvQCNgMTYgeRJKWKhXUmegdYDvTBn6AkSZIkqVR7YAAwlPCxMavsBxwMvAGsiZxFkpQy1p2ZaDNhra69gKMiZ5EkSZIkpY3ri7/eHzFDSuQQ1jlZDrwfN4okKbUsrDPVNGAO0IOwQ7IkSZIUUe/evZkxYwazZs3i5ptv3u72Dh068OqrrzJ16lQmTJhA27ZtI6SUsltLYBDwD+CryFmS7khgb+AVwiQuSVLWsrDOZC8BjYBTI+eQJElSnZabm8tDDz1Enz596Nq1KwMGDKBLly7ljvnDH/7AU089xRFHHMEdd9zB7373u0hppex1JdAcuDt2kGRrQJisNQ/4NHIWSVLKWVhnsv8AEwk7JO8ROYskSZLqrO7duzN79mzmzJnDpk2bGD58OP369St3TNeuXRk/fjwAEyZM2O52STXTALiOsHrk1MhZku5EQhM/NnYQSVJtsLDOdBOADcB3YgeRJElSXdW2bVvmzZtXenn+/PnbLfkxdepUzjvvPAC++93v0qJFC1q1arXdYw0aNIiCggIKCgpo06ZNaoNLWeQSYB+ycHZ1C+AE4GNgfuQskqRaYWGd6dYCrwEHAAfFjSJJkiTtyI033sgpp5zCpEmTOOWUU5g/fz5FRUXbHTd06FDy8/PJz89n8eLFEZJKmScHuBGYDLwaOUvS9SS8wKx7YZKkHakXO4CSoAA4hrBj8mxg+/f9kiRJUsoUFhbSvn370svt2rWjsLCw3DELFy7k/PPPB6Bp06acf/75rFixolZzStnqLKAL8P3YQZJtX+AI4E3Avy4kqc5whnU22ELYgLEVcFzkLJIkSapzCgoK6Ny5M506daJ+/fr079+fUaNGlTumdevW5OTkAHDrrbfy17/+NUZUKSvdBHwJjIgdJNl6A6uBt2IHkSTVJgvrbPE5MAM4GWgWOYskSZLqlKKiIq655hrGjh3L9OnTGTFiBNOmTWPIkCH07dsXgFNPPZWZM2cyc+ZM9tprL37zm99ETi1lh+6Ej4H3AZsjZ0mqLkBHtu7bJEmqM3KAROwQyVBQUEB+fn7sGHG1Av6LsBnF83GjSJIkJYvv8+ouf/bSrj1LWOa5PbAmcpakySN8tt0EPEo4q1iSlFV29j7PGdbZZCnwLnAk0Hbnh0qSJEmSMtu3gPOAh8mishrgWMKErJexrJakOsjCOtu8AawC+hDmz0uSJEmSstINhEnID8YOkkxNCGucfEZY+lKSVOdYWGebjcA4oB1wWOQskiRJkqSU2AO4DHga+DpulOQ6FWgAvBI5hyQpGgvrbDQVKAROJ/xDL0mSJEnKKv8FNAb+EDtIMrUBjgE+BL6JnEWSFI2FdTZKAGOAFsC3I2eRJEmSJCVVE0Jh/S9gZuQsSXUG4azh1yLnkCRFZWGdreYTZlqfAOweOYskSZIkKWl+SJiMfHfsIMm0P3AgYV+mtZGzSJKisrDOZq8SdlQ+I3YQSZIkSVIy5BE2W3wXeDtylqTJAXoDy4D3I2eRJEVnYZ3NVgFvAl2A/SJnkSRJkiTV2HmEychZNbu6G7AXYaPFoshZJEnRWVhnu3cJv6X+Dv60JUmSJCnD3QR8Rli/Ois0AHoAXwHTImeRJKUFK8xstxl4mfDb6qMjZ5EkSZIkVdspQD5wD2H1x6zwbaAZMDZ2EElSurCwrgumA3MIv7VuHDmLJEmSJKlabgIWAU/FDpIsLYETgI+AwshZJElpw8K6rhgDNAROjZxDkiRJklRlhwBnAQ8C6yNnSZrTgQQwLnYQSVI6sbCuKxYBHxLOH9szchZJkiRJUpXcCKwB/hw7SLK0Aw4j7Lu0InIWSVJasbCuSyYAGwgbMEqSJEmSMsK+wMXAY8DSyFmSpjewCngrdhBJUrqxsK5L1hFK6/2BgyNnkSRJkiRVynVAHnBf7CDJcgjQHhgPbIycRZKUdiys65oPCcuDnAHUi5xFkiRJkrRTLYCfAM8Cc+NGSY56hLWrvwamxI0iSUpPFtZ1zRbgJaAVcFzkLJIkSZKknboCaAncHTtIshwL7A68TNhwUZKkbVhY10VfANOBk4HmkbNIkiRJkipUn7AcyHhgUuQsSdGU8Dl0JuFzqSRJFbCwrqteJvz0e8YOIkmSJEmqyACgHVk0u/pUwpIgr0TOIUlKaxbWddUy4F3gSKBt3CiSJEmSpO3dCHxMWNUx4+0BHE3YV2lx5CySpLRmYV2XvQmsAvoAOZGzSJIkSZJKfQc4jCyaXX0GsAF4LXIOSVLas7CuyzYCrxLOMTs8chZJkiRJUqmbgPnA8NhBkuFbQGfgDWBd5CySpLRnYV3XfUR4F3Q60CByFkmSJEkSRwM9gPuBTXGj1FwuYXb1UuCDyFkkSRnBwrquSwBjgObASZGzSJIkSZK4CVgB/G/sIMlwFLAnYaPFoshZJEkZwcJaUAhMAY4Hdo8bRZIkSZLqsv2AC4BHCFsOZbSGwGnAXGB63CiSpMxhYa1gHLCFcKqWJEmSJCmK/0eYiPxA7CDJcBLQFBgbO4gkKZNYWCtYRdgAowuwf+QskiRJklQHtQYuB/4OLIycpcZ2A44jnM2b8S9GklSbLKy11XuEjTC+g/9lSJIkSVItuxpoAvwhdpBkOJ2wZ9L42EEkSZkmpbVk7969mTFjBrNmzeLmm2/e7vYGDRowfPhwZs2axXvvvUfHjh3L3d6+fXtWrVrFz372s1TGVInNwMuEDTGOiZxFkiRJkuqQRsA1wGhgWuQsNdYeOBR4G1gZOYskKeOkrLDOzc3loYceok+fPnTt2pUBAwbQpUuXcsdcfvnlLFu2jM6dO3Pfffdx1113lbv93nvvZcyYMamKqIrMAL4gbIzROHIWSZIkSaojBhLmDv0+dpCaygF6E5adfCdyFklSRkpZYd29e3dmz57NnDlz2LRpE8OHD6dfv37ljunXrx9PPvkkACNHjqRnz57lbpszZw6ffvppqiJqR15i627OkiRJkqSUygV+BnxA2Fooox0CtAPGARsjZ5EkZaSUFdZt27Zl3rx5pZfnz59P27Ztd3hMUVERK1asoHXr1jRt2pSbb76ZIUOG7PQ5Bg0aREFBAQUFBbRp0yb5L6KuWgQUEJYF2TNyFkmSJEnKcv2AzsDdsYPUVD3C2tULgamRs0iSMlZabq13++23c99997FmzZqdHjd06FDy8/PJz89n8eLFtZSujngNWA/0iZxDkiRJkrLcz4HPgediB6mp44DdgLGEDRclSaqGeql64MLCQtq3b196uV27dhQWFlZ4TGFhIXl5ebRs2ZIlS5Zw7LHHcsEFF/D73/+e3XbbjS1btrB+/XoeeuihVMXVttYBE4CzgC7A9LhxJEmSJCkbfZvQ8/4XsCVylhppCpxE2BdpbtwokqTMlrLCuqCggM6dO9OpUycKCwvp378/F198cbljRo0axcCBA3nvvfe44IILGD9+PAAnn3xy6TGDBw9m9erVltUxTCQsC3IGMAvYHDeOJEmSJGWbm4DFwOOxg9RUD0LD8ErsIJKkTJeyJUGKioq45pprGDt2LNOnT2fEiBFMmzaNIUOG0LdvXwAee+wxWrduzaxZs7jhhhu45ZZbUhUn6fYEmscOkWpbCBsw7g4cHzmLJEmSJGWZg4FzgD8RTnLNWHsB3Qh7IS2JnEWSlPFyyJKVpQoKCsjPz6+15/szcBVhnbGp24y5tZaillwEHAA8CKyKnEWSJNU5tf0+T+nDn72y3VDg+0AHwizrjPUDYF/gj2R48y5Jqi07e5+XsiVBst3fgPnAEcXjXLZOV18OfMTWAnsK8ClhD8OM9DJhQbXTgX9GziJJkiRJWWBvQs/7GBleVncmTHAag2W1JCkpLKyr6Z3iUaIJcBhbC+wjgB8CzYpvLwJmsrXALimzv66duDWzjPBiTyac4jU/bhxJkiRJynQ/BeoD98YOUhO5hD2PlgAfRs4iScoaFtZJshZ4v3iUyAH2Z2uBfSRwAjCgzDGL2L7EnkEa7m/4FuEF9AH+QpYsJCNJkiRJta8ZYYnJ5wjLTGaso4E9gGGEWVqSJCWBhXUKJQhvPj4nvBEpsRtwOFtL7COAa4FGxbdvICwhsu3a2MtqIfMObQReBc4jBJ4SM4wkSZIkZa4fEz4X3h05R400Ak4D5hBOJ5YkKUksrCNYDrxRPErkAQdRvsTuQ1hWpMRXlF8XeyqhDK+1yc4fA/mEtaynE5p1SZIkSVKl1QP+H/A68EHkLDVyEtCYsOeRJElJZGGdJoqAacVjWJnr96L8utglRXbJD241oUcuW2J/DKxJRcgE8BIwiPDm5NVUPIkkSZIkZa8LgQ7A1bGD1MTuwLGED6EL40aRJGUfC+s09x/CL6zL/tK6IXAI5Uvsi4Ari2/fQph5PYXyS4rMS0agwuIHPg6YBCxNxoNKkiRJUt1wE2Gi0r9jB6mJ0wkfPMfHDiJJykYW1hloA6ErnrTN9R0oX2J3A75X5valbL8u9qeE5amr5FWgC/Dd4hD/IewemXY7RUqSJElS+uhFWALyR2TwPvYdCDOoJgCrImeRJGUlC+ss8lXxeKHMdc2Aw9haYh9JWNGjafHtm4AZbL829jc7e6LVhKVBvgP0K75uC7AE+Lp4/Kf46+qavCJJkiRJyh43AQuAv8cOUl05QG9gJfBO5CySpKxlYZ3lVgPvFo8SucABlN/g8RTgkjLHLKR8gT0V+Iyw1jYAk4tv3J2w0PbexV/bExryEmsoX2D/h9CGb0nCi5MkSZKkDHEkYYb1zVTjLNd0cRjQFvgnYfaTJEkpYGFdB20BZhWPkWWubwUcztYS+wjgBqBB8e3rCEuITCEU2OMSMH0pYa2R6WUeqBGhvC4psvcGurP1v7YiQmldtsj+uvgJJEmSJCkL3UhYQePR2EGqqz7QkzBF/KPIWSRJWc3CWqWWAq8VjxL1gIMpX2KfA/yYMCvgDOD1bR9oPfBl8SiRC7Sm/GzsA4ofuMRKtp+NvYQMXtxNkiRJksKyzxcBDwArImeptuOBlsBz+BlNkpRSFtbaqc3AJ8Xjb2Wu7wCMIZwJdgJhHeyd2kKYVf1N8YOVaEr5EntvQpGdV3z7JsKGjmXXxv4PYedJSZIkScoA/4/Q8d4fOUe1NQO+DUyj/MQkSZJSwMJa1fIVcCbwHqG4Po7QI1fZGuCL4lEiD9iD8kV2F+DoMscsY/vZ2MuqE0CSJEmSUmc3whmqw4D5caNUXw/C57RXYweRJNUFFtaqti+BswlLgrxI2LhxbTIeuIitM6qnlrm+BdvPxj6YsFM1hFnXZQvsrwmzs90MRJIkSVIkVxEmKP8hdpDq2hvoBrxLWEdSkqQUs7BWjUwkrMX2L2A48F1C35wSK4vHrDLX1Qf2pPwGj0cADYtv30J4U7XtbOyVqQopSZIkSUFD4KfAS8DHkbNU2xnAOuCN2EEkSXWFhbVqbDRwLfBnwiYi19Tmk28CCotHiRzCeXdlZ2O3BQ4tc8xatp+N/Q0pbNslSZIk1TWXED6S3B07SHUdCOwP/BtYHzmLJKnOsLBWUjwMdAJ+DswB7okZJkFYz3oZ5XeDbEgor8vOxj6GMEsbQlm9mO1nY6+pldSSJEmSskgOcCMwCRgfOUu15BJmVy8GPoycRZJUp1hYK2luAToS1mb7EhgZN872NhB2i/yqzHU5QGvKz8bej7CsSIlVbD8bewlhuRFJkiRJqkBfwpY7A2IHqa5jgDbAM/jZR5JUqyyslTQJYCBh9Y2ngQXAO1ETVUKCMGNgMfBpmeubsP0Gj8cTdsYG2Ax8Djxb/L0kSZIklXETMJfwkSHjNAJOBb4APosbRZJU91hYK6k2AP0IG0iPInS8s3Z6jzS1lrC2yZwy1+URZhjsBbQDugMnARNqPZ0kSZKkNHYc8G3ChosZuU3OKUBjYGzsIJKkuig3dgBln6VAH8IbszGEjjcrFBGWBPmIsOnIVMK70L1ihpIkSZKUbm4ifC76a+wg1dGKMDlnMuHzjyRJtczCWinxBXAOsC9hpnWjuHFS4yXCTtnnENbCliRJklTndQbOBf5Mhu7f3oswWScjd4qUJGUDC2ulzPvAxcCxwN/Iwv/Y1hGmkLclnPMnSZIkqc77GbAReDB2kOroCHQB3gJWR84iSaqzsq5DVHp5HrgBOB+4O26U1PgEmAn0AHaPnEWSJElSVHsSNqJ/ElgUOUuV5QC9gRXAO5GzSJLqNAtrpdwDwP2E4vrauFFSYzSwBTg7dhBJkiRJMV0DNADuiR2kOg4nrOn4KrA5chZJUp1mYa1a8TPgOUJx3S9ulORbSXhTdwBwZNwokiRJkuJoAlwN/AuYFTlLldUjnDVaSDiLVJKkiCysVSu2AJcAHwDPAPlx4yTfh8CXhFPomkbOIkmSJKnW/QhoTYYuhdgdaAm8AiQiZ5Ek1XkW1qo164BzgIXAi8B+ceMkVwJ4AagPnBk5iyRJkqRalUdYAvFt4N3IWaqsEXASYVr43LhRJEkCC2vVsm8IfW4eMAZoFTdOci0GXgcOAQ6KnEWSJElSrbmAMCHn97GDVMdJhNL61dhBJEkKLKxV6z4jrGPdEXgeaBg1TZK9DfwHOIsse2GSJEmSduQmYAbhpMuM0gI4FviI8DlGkqQ0YGGtKN4GBhJ+mf8EkBM1TRJtIeyy0gzoFTmLJEmSpJQ7DTgauIcMXP75tOKv46OmkCSpHAtrRTMC+DnQH/ht5CxJtQB4DziGMI1ckiRJUta6CfgaeDp2kKraEzgS+ABYETeKJEllWVgrqruBh4FbgJ9EzpJUE4BlhF0m60XOIkmSJCklDgP6AA8CGyJnqbLTCaHfjB1EkqTyLKwV3bXAi8BDhA0Zs8ImwgJ2rYFTImeRJEmqBb1792bGjBnMmjWLm2++ebvb27dvz/jx45k0aRJTp06lT58+EVJKyXUjsJowCSejdAQOJJTV6yJnkSRpGxbWiq6IsCzIFOAfwFFR0yTRF8Bk4ERg78hZJEmSUig3N5eHHnqIPn360LVrVwYMGECXLl3KHXPbbbcxYsQIjjrqKPr378+f//znSGml5GgHDAD+Qji5MqP0AlYC78cOIknS9iyslRbWAGcDSwizrTvEjZM8LwNrCUuD+H+bJEnKUt27d2f27NnMmTOHTZs2MXz4cPr161fumEQiQYsWLQBo2bIlCxYsiBFVSprrCJvH3xc7SFV1JbTtE4DNkbNIklQBKzSlja8JS4I0Bv4NtIwbJznWEV7MvsBxkbNIkiSlSNu2bZk3b17p5fnz59O2bdtyx9x+++1ccsklzJs3j3//+99ce+21FT7WoEGDKCgooKCggDZt2qQ0t1RdLYArCBvJfxU5S5XkAj2BRcDUyFkkSdoBC2ullWnAd4HOwHNA/bhxkmMaMAM4DWgVOYskSVIkAwYM4IknnqB9+/aceeaZPP300+Tk5Gx33NChQ8nPzyc/P5/FixdHSCrt2k8IpfXdsYNU1VGEfXZeBbZEziJJ0g5YWCvtvAZcDvQgrAeXFUYTFuvuGzuIJElS8hUWFtK+ffvSy+3ataOwsLDcMZdffjkjRowA4L333qNRo0bOoFZGakBYDuRVwj48GaMBcCrwJfBZ3CiSJO2MhbXS0t+A24BLgSGRsyTFKuAVYD+yaFdJSZKkoKCggM6dO9OpUyfq169P//79GTVqVLljvvrqK3r27AnAwQcfTKNGjfjmm29ixJVq5GKgLfD72EGq6nigGeFziSRJaczCWmnrN4QZ1v8N/DBylqSYBMwFzgCax40iSZKUTEVFRVxzzTWMHTuW6dOnM2LECKZNm8aQIUPo2zecYvazn/2MQYMGMWXKFIYNG8Zll10WN7RUDTnAjYSZ1RnV+zYFTgCmA/MjZ5EkaRfqxQ4g7cxVQHvgUcL7qox6U7itBDAKuBroQ9ihRZIkKUuMGTOGMWPGlLtu8ODBpd9Pnz6db3/727UdS0qqPsAhwCWxg1TVyYQNgl6NHUSSpF1zhrXS2mbge4R9C0cCh8eNU3NLCYt0dwW6xI0iSZIkqWpuAr4C/hE7SFW0Ao4hnPG5JHIWSZIqwcJaaW8VcBawkrB3Ydu4cWruHWAhcCbQKHIWSZIkSZWST9iz8H7CxJqM0YOwAfxrkXNIklRJFtbKCIWEfrcFobTO6CWgtxCWBmlKWM9akiRJUtq7CVgODI2co0r2BQ4F3gVWR84iSVIlWVgrY3wMXEBYM+5ZMnwB9oWEmdZHAftFziJJkiRpp/YHzgMeJsN6317AGsJnD0mSMoSFtTLKK8AVQG/Cm8WM9hphTeu+hA1QJEmSJKWlGwjLgPwxdpCq+BZhcswbwIbIWSRJqgILa2Wcx4E7gR8Dv4ycpUY2E5YGaUVYDE+SJElS2mkN/BD4G/B15CyVlgOcDiwDPoycRZKkKrKwVkb6b+Ap4NfA9yNnqZG5wETgeGCfuFEkSZIkbe+/gCbAH2IHqYrDgL2BcYQNFyVJyiAW1spYPwbGA38lwycov0JYV64f/h8pSZKiOvvss8nJyYkdQ0objYFrCCdGzoicpdLqAT2ABcCnkbNIklQN1mPKWJsIG5/MAv4JdI0bp/rWA6MJMyBOiJxFkiTVaRdddBGzZs3irrvu4qCDDoodR4ruMmAP4O7IOaokH9gNeBVIxI0iSVJ1WFgro60AzgTWAf8mdL4ZaQYwjTBVvHXcKJIkqe76wQ9+QLdu3fj888954okneOeddxg0aBDNmjWLHU2qdbmEzRbfA96KnKXSGgEnAbOBLyJnkSSpmiyslfG+As4G2gAvAk3jxqm+fxOmjfclbJIiSZIUwapVqxg5ciTDhw9nn3324bvf/S6TJk3immuuiR1NqlXfBb5Fhs2uPpGw4ParsYNIklR9FtbKCpOAC4EjgeFAXtQ01bQaeBnoBBwVN4okSaqb+vbty3PPPcdrr71G/fr16d69O2eeeSZHHHEEP/vZz2LHk2rVTYTlB5+PnKPSWgDHAR8BX0fOIklSDdSLHUBKln8TdvB+BPhj8fcZZzJhR+9ewGfAqrhxJElS3XL++edz33338eabb5a7ft26dVx++eWRUkm17yTgWOAqYEvkLJV2KuFMzfGRc0iSVEPOsFZWeRS4C7gauDFylmp7gTBF/KzYQSRJUl1z++2388EHH5RebtSoER07dgRg/HhbMNUdPwcWAU9EzlFpexBONy0AlkdNIklSjVlYK+vcSlgW5G7CMiEZZxkwATgYOCRyFkmSVKc8++yzbNmydT5pUVERzz77bMREUu3rQtgj50/A+shZKq0nsBF4c1cHSpKU/iyslXUSwGWE92pPEfYdyTjvAQuAPkDjyFkkSVKdUa9ePTZt2lR6edOmTTRo0CBiIqn23QisBf4cO0hldSBMdnmbEFySpAxnYa2stAE4F5gL/As4MGaY6thCCN4EOCNyFkmSVGd888039O3bt/TyOeecw+LFiyMmkmrXPsAlwF+BJZGzVFovwt4378UOIklScrjporLWUsIE5fcIGzIeD3wTNVEV/YcwS+Ik4GPgi7hxJElS9rvyyiv5+9//zp/+9CdycnKYN28el156aexYUq35KWE7mXtjB6msg4H2wChg0y6OlSQpQ6R0hnXv3r2ZMWMGs2bN4uabb97u9gYNGjB8+HBmzZrFe++9V7qhS35+PpMnT2by5MlMmTKFc889N5UxlcXmAH0JMyVeIANX13gdWEx4EfUjZ5EkSVnviy++4Pjjj6dr16506dKFE088kc8//zx2LKlWNAeuBEYSPkekvVzgdMKsnClxo0iSlEyVmmHdpEkT1q1bRyKRoHPnzhx88MGMGTOGzZs37/A+ubm5PPTQQ/Tq1Yv58+dTUFDAqFGjmD59eukxl19+OcuWLaNz585cdNFF3HXXXfTv359PPvmEY445hqKiIvbee2+mTp3KCy+8QFFRUc1fseqcD4CLgeeAvwMXEFbcyAibCU37D4EewNi4cSRJUvY788wzOeSQQ2jUqFHpdXfeeWfERFLtuBrYjbB5e0boBrQh7DifMR9wJEnatUrNsH7jjTdo1KgR++67Ly+//DI/+MEPeOKJJ3Z6n+7duzN79mzmzJnDpk2bGD58OP369St3TL9+/XjyyScBGDlyJD179gRg3bp1peV0o0aNSCQSVX1dUjn/Aq4HvgvcEzdK1X0JFADHAm0jZ5EkSVnt4Ycf5qKLLuLaa68lJyeH733ve6VnQUrZ7BDgdsLKGhPjRqmc+sCpwFfAjLhRJElKtkoV1jk5Oaxbt47zzjuPP//5z1x44YUccsghO71P27ZtmTdvXunl+fPn07Zt2x0eU1RUxIoVK2jdujUQCu9PPvmEjz/+mCuvvLLC2dWDBg2ioKCAgoIC2rRpU5mXojrsQeA+QnH907hRqu5VYDVwDmFRPUmSpBQ44YQTGDhwIMuWLeOOO+7g+OOP58ADM277aqlKGgHDgOXAj+NGqbzjCGuYvBI7iCRJyVfpwvq4447j+9//PqNHjwYgLy+1rdkHH3zAoYceSn5+PrfeeisNGzbc7pihQ4eSn59Pfn6+u5erUm4kLA1yH3Bu3ChVswEYDewFnBg5iyRJylrr168HYO3ateyzzz5s2rSJffbZJ3IqKbV+DxwGXEaGbNLeBPg2YWb1vF0cK0lSBqpUYX399ddz66238s9//pNp06ax3377MWHChJ3ep7CwkPbt25debteuHYWFhTs8Ji8vj5YtW7JkyZJyx8yYMYPVq1dz6KGHVuoFSTuzBbiEsK71M4RVNjLGTOAT4GTCWnWSJElJ9sILL9CyZUvuvvtuJk2axNy5c3nmmWdix5JS5izgWuBeMmi7mJMJS4K8GjuIJEmpk6jKyMnJSTRv3nyXx+Xl5SU+//zzRKdOnRL169dPTJkyJdG1a9dyx1x99dWJhx9+OAEkLrroosQ//vGPBJDo1KlTIi8vLwEkOnTokCgsLEy0bt16p89XUFBQpdfhqNtjD0jMhsQiSOyfBnkqPZqS4GYS/IgEOWmQx+FwOByOWhi+z6udkZOTkzj++ONLLzdo0CDRokULf/aOrB17Ez4PTIZEgzTIU6mxOwl+RYK+aZDF4XA4HI4ajJ29z6vUDOu///3vNG/enCZNmvDJJ58wbdo0brzxxp3ep6ioiGuuuYaxY8cyffp0RowYwbRp0xgyZAh9+/YF4LHHHqN169bMmjWLG264gVtuuQWAb3/720ydOpXJkyfzz3/+k6uvvnq7mddSTXwD9CGcYjAGaBU3TuWtAV4COgDHRM4iSZKySiKR4KGHHiq9vHHjRlauXBkxkZQ6OcCTQFNgALAxbpzK60E4bfS1yDkkSUqxXTbekydPTgCJiy++OPGHP/whUa9evcTUqVOjN/Flh7MvHNUZJ0BiHSTehETDNMhT6XEJCW4lQcs0yOJwOBwOR4qH7/Nqb9x9992J8847L3oOf/aOVI+fQSIBiUFpkKXSYx8S3E6CnmmQxeFwOByOGo4az7CuX78+9erV49xzz2XUqFFs3ryZRCJRmbtKae0d4AeEPUueIsy0yAgvEsKeFTuIJEnKJj/5yU949tln2bBhAytWrGDlypWsWLEidiwpqY4CfkvYjH1o5CxVcjqwFngrdhBJklKrUoX1o48+yty5c2natClvvPEGHTp08PRAZY2RwE3AhcD/RM5SacuB8cCBgPuRSpKkJGnRogV5eXk0bNiQli1b0qJFC1q2bBk7lpQ0TYFhwCJgUOQsVbI/cADwBrAhchZJklKsXmUOevDBB3nwwQdLL3/11VecdtppKQsl1bY/APsBPwfmAI/EjVM57xPK6j7AF4TZFpIkSTVw0kknVXj9m2++WctJpNS4H/gWYSnopXGjVF4O0IswaaUgbhRJkmpDpQrrFi1aMHjwYE4++WQAXn/9de644w5nWSur/BRoD/wJmAeMjhtn1xLAKOAnQG/gn3HjSJKkzHfTTTeVft+oUSO6d+/OxIkT6dmzZ8RUUnJcAPwY+A3weuQsVXIosA9hDZOiyFkkSaoFlVoS5K9//SurVq3iwgsv5MILL2TlypU8/vjjqc4m1aoioD8wGfgHcHTcOJWziLCG3RGEqSKSJEk1cM4555SOM844g0MPPZRly5bFjiXVWHvgfwknKd4eN0rV5BGmgy8EPo6cRZKkWlKpGdYHHHAAF1xwQenlO+64g8mTJ6cslBTLWuBs4D3CvobHAV9GTVQJbwBdCcH/DGyMG0eSJGWP+fPn06VLl9gxpBrJBf5G+PB7MbA5bpyqOQbYHXiacIalJEl1QKUK63Xr1nHiiSfy9ttvA3DCCSewbt26lAaTYvkPcCbwDvBv4ETCcnFpq4iwNMiPCLMvXoobR5IkZa4//vGPJBKhFcvNzeXII49k0qRJkVNJNfML4GTgB4StXzJGQ+AUQujPI2eRJKkWVaqwvvLKK3nqqadKdwhftmwZAwcOTGkwKabpwHeBsYSl4r5Dmk9cnkfYgOVY4BNgftw4kiQpM3344Yel32/evJlhw4bxzjvvREwk1czxwGDg74RZ1hnlRKAJ8ErsIJIk1a5KFdYfffQRRx55JM2bNwdg1apVXHfddXz8sYtoKXu9BvyQ8Ob2L8ClUdNUwqvAQcA5wKO4IYskSaqykSNHsn79erZs2QKEWdaNGzf27EplpBaE9/LzgKsjZ6my5oS2/WPC+tWSJNUhldp0scSqVatYtWoVADfccENKAknp5Bngl4TTB++InGWXNhIW3t4TOClyFkmSlJHGjRtH48aNSy83btyYV199NWIiqfoeJmy2eDGwMnKWKjuV8Gl9fOQckiRFUKXCuqycnJxk5pDS1m+BocCvgMsjZ9mlWcBHhMJ6j8hZJElSxmnUqBFr1qwpvbxmzRqaNGkSMZFUPZcQiurbCRuqZ5Q2QDfgQ2BZ5CySJEVQ7cK6ZDMWqS64mrCX4SPAGZGz7NJLwAagH+DvlSRJUhWsWbOGbt26lV4+6qijXA5EGWd/4M/AG8DvImeplp7AJuD12EEkSYpjp2tYr1y5ssJiOicnp9ypglK22wxcCLwJjAS+TZjInJbWAmOA84HuwPtx40iSpMxx/fXX8+yzz7JgwQJycnLYe++9ueiii2LHkiqtHmFZv82EWdZb4sapuvZAF8JSIGsjZ5EkKZKdFtYtWrSorRxS2lsFnEk4pXA0cBxQGDXRTnwMHE6YnTEDWBE3jiRJygwffvghBx98MAcddBAAM2fOZPPmzZFTSZV3O3AscAFhs8WM04vwwePd2EEkSYqn2kuCSHXRAuAswo7jL7KL3/jE9mLx175RU0iSpAxy9dVX07RpUz799FM+/fRTmjVrxlVXXRU7llQppwK3An8B/i9ulOo5COgAvEZYEkSSpDrKwlqqoo+BHwJHApfGjbJzK4BXgW8RZltLkiTtwqBBg1ixYuupWcuXL2fQoEERE0mV0wp4mrAH+fVxo1RPLnA6sBiYHDmLJEmRWVhL1fAcYWno/wYaRM6yUwWEcyG/AzSNnEWSJKW9vLy8cpdzc3Np0CCt3+1IAAwF9gQGAGsiZ6mWI4E9gHFk4MLbkiQll4W1VE23AR2BtJ5zlABGEVr170TOIkmS0t5LL73EP/7xD3r06EGPHj0YNmwYY8aMiR1L2qlBwHmE5UAycnJyfcJ6JvOA6XGjSJKUDiyspWp6FXgd+CXQOHKWnfoGeBM4DDgwchZJkpTWbr75ZsaPH8+VV17JlVdeyccff0zjxmn9Tkd13MHA/cDLwH1xo1TfsYRNcl6JHUSSpPRgYS3VwK+AfYCrYwfZlbeARYQdIxtGziJJktJWIpHg/fffZ+7cuXTv3p0ePXowfbpTPpWeGgDDCEuADCScXJhxGgPfBmYCX0XOIklSmqgXO4CUyd4ExgK3AI8Cq+PG2bEiwtIglwM9gX/HjSNJktJL586dGTBgAAMGDGDx4sX84x//AKBHjx6Rk0k79jvC0s9nA1/HjVJ9JxOa91djB5EkKX04w1qqoduANmTAbuTzCTtFdgc6RM4iSZLSyowZM+jRowdnn302J510En/6058oKiqKHUvaod7ADcCDwOjIWaptNyAfmEJYxk+SJAEW1lKNfQg8D9wI7B43yq6NB5YD5+D5FZIkqdR5553HwoULmTBhAv/7v/9Ljx49yMnJiR1LqtCewJPAx8DPI2epkdMI65i8FjmHJElpxsJaSoL/BloCP4sdZFc2Ai8QpoSfFDmLJElKG//6178YMGAABx98MBMmTOD6669nzz335M9//jO9evWKHU8qlQM8QXjvPQBYHzVNDewNHE44A3Jl5CySJKUZC2spCT4GhgPXAXtEzrJLnwNTCZu77BU5iyRJSitr165l2LBhnHPOObRr147Jkydz8803x44llboW6EOYKPJp5Cw1cjqhbX8rdhBJktKPhbWUJLcTNvnOiI90LxHeIJ9DmKYiSZK0jeXLlzN06FBOP/302FEkIExI/j1hL/E/R85SI/sB3wLeIIOniEuSlDoW1lKSzASeAq4G9o2cZZfWAWOAtsBxkbNIkiRJu9AYGAYsAX4UOUuN5AC9CPvKFMSNIklSurKwlpLoDsJehr+MHaQyPiG07D3IgN0iJUmSVJfdA3QFLiWU1hnrEMLslgnA5shZJElKUxbWUhLNBf4C/BjoFDVJJY0GtgBnxw4iSZIkVawfcBVhOZBxkbPUSB5hssjXwEeRs0iSlMYsrKUk+w2hA/5V7CCVsRJ4BTgAODJuFEmSJGlb+wKPAROB2yJnqbGjgVbAq0AichZJktKYhbWUZIXAw8BAoHPkLJUyEfgS6A00jZxFkiRJKpYLPA00AgYAm+LGqZmGwCnAHGB25CySJKU5C2spBX5H2PD79sg5KiUBvADUB86MnEWSJEkqdhNhBY1rgVmRs9TYCYTJIa/EDiJJUvqzsJZS4BvgAaA/cGjkLJWyGHidsAnMQZGzSJIkqc7LB+4ERgCPR85SY82A4wmbni+InEWSpAxgYS2lyB+AVcAdsYNU1tuEDWDOIpyyKEmSJEXQDHiG0O3+JHKWpDiFsOHi+NhBJEnKDBbWUoosA+4BvkvYXyXtbQFGET4h9IqcRZIkSXXWg8B+wCXA8rhRaq414cPARGBp5CySJGUIC2sphe4nrLZxZ+QclbYAeA84BugYOYskSZLqnP7AZcCvgbfiRkmOnoTdIl+PHUSSpMxhYS2l0CrgLqAPcGLkLJU2gTA9/BygXuQskiRJqjM6Ao8A75BBEz52ph3QlfCC1kTOIklSBrGwllLsIcLS0L+OHaSyNgEvEE5fPCVyFkmSJNUJeYR1qwG+DxRFzJI0vYDVwLuxg0iSlFksrKUUWwf8BjiVcEZgRvgCmEyYFr535CySJEnKer8CTgCuBObGjZIcBxKmjL8ObIycRZKkDGNhLdWC/wW+IoNmWQOMBdYSlgbxbwpJkiSlyLeB24AngeGRsyRFDnA6sISw2aIkSaoSayipFmwkrMN3HHBW5CyVth74N7AvcHzkLJIkScpKuwF/B+YA18SNkjxHAHsC44AtkbNIkpSBLKylWvIEMJtQXOfEjVJ504DphPVMWsWNIkmSpOzzCLAPcDFhueeMVw84DZhPeC8tSZKqzMJaqiWbgduBbsB5caNUzb8Ju970jR1EkiRJ2eQy4CLC+tUFcaMkz7FAS+DV2EEkScpcFtZSLRpGmGhxBxn0P98q4BVgP+CoyFkkSZKUFToDDwLjgbsjZ0maxoQFuT8jS3aOlCQpjozpzKRssAX4b6Ar4bTHjDGJ8Kb7DKB53CiSJCk99e7dmxkzZjBr1ixuvvnm7W6/9957mTx5MpMnT2bmzJksW7YsQkqlg/rAM8AG4FKyaJnnbwONcHa1JEk1VC92AKmueQ6YTFgeZDhhqZC0lwBGAVcBZwL/iBtHkiSll9zcXB566CF69erF/PnzKSgoYNSoUUyfPr30mBtuuKH0+2uuuYZu3brFiKo08GvgGOC7QGHkLEnTkrAcyFRgUeQskiRlOGdYS7UsQVin7wDCun0ZYynwGtCleEiSJBXr3r07s2fPZs6cOWzatInhw4fTr1+/HR4/YMAAhg0bVosJlS56Aj8nbLb4fNwoyXVa8dcJUVNIkpQVLKylCEYD7xKWB2kYOUuVvAssJMyybhQ5iyRJShtt27Zl3rx5pZfnz59P27ZtKzy2Q4cO7LfffowfP77C2wcNGkRBQQEFBQW0adMmJXkVRxvgKcKeLjfs4tiMshdwBPA+sCJyFkmSsoCFtRTJbUB7YFDsIFWxhbA0SFPCetaSJElV1L9/f0aOHMmWLRWvXDx06FDy8/PJz89n8eLFtZxOqfQY0BoYAKyLnCWpegLrgbdiB5EkKTtYWEuRjCecMfhLoEnkLFWyEHgHOAroGDmLJElKC4WFhbRv3770crt27SgsrHh14v79+7scSB10FXAOYTmQjyJnSapOwIGEsjqrWnhJkuKxsJYi+hWwN/BfsYNU1evAMuBsIC9yFkmSFF1BQQGdO3emU6dO1K9fn/79+zNq1KjtjjvooIPYfffdeffddyOkVCyHAPcA/wb+GDlL0vUiLAPyfuwgkiRlDwtrKaK3gTHAzUDzyFmqZBPhE8cewPGRs0iSpOiKioq45pprGDt2LNOnT2fEiBFMmzaNIUOG0Ldv39Lj+vfvz/DhwyMmVW1rBAwDVgI/jJwl6boCbQmnTW6OnEWSpCxSL3YAqa67DZgIXA/cGTdK1cwi7JhzCvApYca1JEmqs8aMGcOYMWPKXTd48OByl4cMGVKbkZQG7gIOA74DLIqcJalyCWtX/weYGjmLJElZxhnWUmSTgOeAnwG7R85SZS8RNmI8M3YQSZIkpZuzgJ8C9wFjI2dJuqMJO0i+CiQiZ5EkKctYWEtpYDBhSZCbYgepqpWEUyA7A10iZ5EkSVLa2Bt4HJgC3BI3SvI1IJxlOJdw1qEkSUoqC2spDXwCDCfMQNkzcpYq+wBYCPQhvHmXJElSnZYDPAk0BQYAG+PGSb7jgWbAK7GDSJKUnSyspTRxO9CQDJyBsgV4kTBF/LTIWSRJkhTd/wPOIOzRMiNulORrCpxI2MulMHIWSZKylIW1lCZmEWaiXEXYbDyjFAIfAscSzv+UJElSndQN+B1hj5ahkbOkxClAPWBc7CCSJGUvC2spjdxJ+J/yl7GDVMc4YC3Ql3AeqCRJkuqUJsAwYBEwKHKWlGhF2GxxIrAkchZJkrKYhbWURr4kzET5MbBf5CxVtp6w/Xtbwht5SZIk1Sn3E/bi/gGwNG6U1OgBFAGvxw4iSVJ2S2lh3bt3b2bMmMGsWbO4+eabt7u9QYMGDB8+nFmzZvHee+/RsWNHAE4//XQ+/PBDPvroIz788ENOO82FcVV3/AbYDPx37CDV8THwBXA6YSMaSZIk1QnnE2ZV/w/wWtwoqbEvcCjwDrA6chZJkrJcygrr3NxcHnroIfr06UPXrl0ZMGAAXbp0KXfM5ZdfzrJly+jcuTP33Xcfd911FwCLFy+mb9++HH744QwcOJCnn346VTGltLMQ+DNhZspBkbNUy2jCun5nxA4iSZKk2tCecJbgB8DgyFlSphewhlBYS5KklEpZYd29e3dmz57NnDlz2LRpE8OHD6dfv37ljunXrx9PPvkkACNHjqRnz54ATJkyhYULFwLw6aef0rhxYxo0aJCqqFLa+R9gHXB75BzVsgR4Czgc2D9yFkmSJKVULvA3wnyFAYQzBbPOtwjr9b0ObIycRZKkOiBlhXXbtm2ZN29e6eX58+fTtm3bHR5TVFTEihUraN26dbljzj//fCZNmsTGjdu/Mxg0aBAFBQUUFBTQpk2bFLwKKY7FhDUA+wOHxY1SPW8RiuuzCJ9eJEmSlJVuBU4GriasDJd1cgizq5cSNluUJEkpl9abLnbt2pW77rqLn/zkJxXePnToUPLz88nPz2fx4sW1nE5KrXuA5cAdkXNUy2bC0iCtgRMjZ5EkSVJKHEc4I/DvhFnWWelwYC9gHGHDRUmSlHIpK6wLCwtp37596eV27dpRWFi4w2Py8vJo2bIlS5YsAcLs63/+859ceumlfPFFVv6uXtqp5cAfgHOB/KhJqukLwiaMJwGtImeRJElSUrUAngHmEWZXZ6V6wGnAAmBa5CySJNUhKSusCwoK6Ny5M506daJ+/fr079+fUaNGlTtm1KhRDBw4EIALLriA8ePHA9CyZUtGjx7NLbfcwjvvuKuF6q4HCMuD3Bk7SHWNJcy2Pit2EEmSJCXTQ4TNFi8GVkbOkjL5wG7AK0AibhRJkuqSlBXWRUVFXHPNNYwdO5bp06czYsQIpk2bxpAhQ+jbty8Ajz32GK1bt2bWrFnccMMN3HLLLQBcc801fOtb3+K///u/mTx5MpMnT2aPPfZIVVQpba0mbMDYmzBROeOsJpw+eQBwaOQskiRJSorvA5cAQ4D3ImdJmUaExblnAXMiZ5EkqY7JIUt+V1xQUEB+fkYunCDtVGNgdvE4JXKWaskBfgy0BP4ErI8bR5KUeXyfV3f5s08/+wNTgMmE1TK2RE2TQqcT9mJ5BPhP5CySJGWhnb3PS+tNFyXBOuA3hAkep0fOUi0J4EWgCdAjchZJkiRVWz3CutVFhBnWWVtWtwCOBT7CslqSpAgsrKUM8BfgS0JxnZEWAh8Q1gFsGzmLJEmSquV2Qo87iLDZYtY6lXCW4ITIOSRJqqMsrKUMsBG4A+gO9I2cpdomAKuAs/FvHkmSpAxzCnArYSLFyMhZUmoP4EjCZIvlUZNIklRnWRtJGeIpwp4vdxImfGScDcBLwD6EmdaSJEnKCLsDfyO8F70+bpTUO50wW+TN2EEkSaq7LKylDLEZGAwcAVwQOUu1TSN80ukBNI+cRZIkSZUyFNgTuBhYEzlLSjQE9iZMqjgIeIuwkYwkSYqiXuwAkirvH8AvCMuDPEfY8Cbj/Bu4GvgO8GzkLJIkSdqpHwPnAzcCkyJnqbY8oCWwG2G6+LajcZljlwDv13I+SZJUjoW1lEG2AP9NKKsvBp6OG6d6lgFvAD2BKYQZ15IkSUo7BwEPAK8A90bOsktN2VpA70b5QroF5c8t3kxYn3o5UEh4f1oyFhffLkmSorGwljLMPwmzW24HhgOboqappneAw4EzgT+ToS9CkiQpezUAhhGWALkUSMSNA/XZvogue7nBNsevIhTQXxKK6bKl9CrS4AVJkqQdsbCWMtBthJU1fgj8b+Qs1VIEvEh4AScB4+PGkSRJUnm/A7oBfYGva+MJcwh7nFS0ZMdubL//yUa2FtBfUL6UXo4TIiRJymAW1lIGGgO8DfwKeBLYEDdO9XxJWBLkROBj4JuoaSRJklSsN3AD8CBhjkHSNGLH60jvRlhrusQWYCWhgJ5F+TJ6GVm6+6MkSQILaylj3QZMAH4C/DFylmp7mbA44tnA45GzSJIkiT0JEyI+Bn5e1TuXbG5Y0TrS225uCLCWUEB/DUyn/LIdK8nQHcYlSVJNWVhLGeo1YBzwC+AvhPf7GWctYRefc4AjCTOuJUmSFM3jhM65J7C+ogPKbm64bTG9o80Nl7H95obLd/QEkiSprrOwljLYrwj7F14L3BU5S7VNJpTVZwAzgXVR00iSJGW1HKAVsE/x2LvM14MIe2L/VzP4dF8qLqbd3FCSJKWYhbWUwd4FRhNO13yYcOZkxkkQFke8EugFjIobR5IkKRM1IJTOZQvoikrpvYH6Fdx/FbCwCdx/GPz5O4RmG7bf3LDsOtLLcXNDSZKUdBbWUob7FTAJ+H/AkMhZqm0RoX0/kbAsyFdR00iSJKWNlmxfOldURLeu4L5bCPtaLyQsE/1Jme+3/bqmK3Ah8BHwf2wtpN3cUJIk1TILaynDTQZGsnUn96Vx41Tfa8AhhA0YHyF8wpIkScpCeYTNDXdWQJd83XafQghLPy8sHjMIb6MqKqIXUcl9C1sAfQnrTD+P78MkSVJUFtZSFhgMnAfcBNwaOUu1bQLGAAOA44G348aRJEmqqqbsuoDeB9iD8nsTlljC1sL5LbYvoEu+X5HM0DnAuYQW/TksqyVJUnQW1lIWmAY8A/wUuB/4T9Q0NTCTME3oVOBTwmmokiRJEeUAbdh5EV3yffMK7r+JrYXzV8D7bF9ALyS8f9uYwtexQ8cB+xP2EVkSI4AkSVJ5FtZSlhgC9CfMsL4+bpSaGQP8F9AHGBY5iyRJqlN+ROhvyxbRe1Hxh6YVbC2bJ7J9AV3ydSlhj+m0tBfQkzBhYFLkLJIkScUsrKUsMRt4ArgS+AMwP2qaGlhBWIjxDOBgwgcoSZKkWnAGcDJby+aPqLiI/hpYGylj0tQDzgfWEWZXS5IkpQkLaymL3AH8ALiNUFxnrPeAIwizrL8g0vmxkiSprukfO0BtOp2w8+PfyIL2XZIkZZOK9vqQlKHmAf9LOJ11/8hZamQL8CLQkrCetSRJkpLnAMLaJ+8TTtOTJElKIxbWUpb5LbAZ+O/YQWpqHmFByOMI6ytKkiSp5poA5wKLgFfiRpEkSaqIhbWUZb4G/gRcQlgCOqO9SlhX8WwgJ3IWSZKkbNCXUFo/R5jlIEmSlGYsrKUsdBdhKcIhsYPU1DrgZaA9cFTkLJIkSZmuG9AFGEeY5SBJkpSGLKylLLQEuA+4kLB3YUabCswlbAzUNG4USZKkjNWKsKH1HODdyFkkSZJ2wsJaylL3AsuAO2IHSYYXgQbAGbGDSJIkZaBc4DygCPgnkIgbR5IkaWcsrKUstQK4GzgH6B45S40tBt4mTBfvFDeKJElSxjkZaEeYBLAychZJkqRdsLCWstgfgW+AO2MHSYY3gKWEDRjzImeRJEnKFO0JhfVU4NPIWSRJkirBwlrKYmuA3xFW0jg5cpYa2wz8G2gDnBg5iyRJUiZoSFgKZAXhfZQkSVIGsLCWstzDQCHw69hBkmE2YWbQyYSNgyRJkrRj3wFaAs8BGyJnkSRJqiQLaynLrSeU1SeRJXsWvkTYMOjM2EEkSZLSWFegG/AmMC9yFkmSpCqwsJbqgMeAuWTJLOtVwHjgW8AhkbNIkiSloxZAX8Jpdq9HziJJklRFFtZSHbAJGALkA+dEzpIUBcACwmmuDSNnkSRJSic5wLmETaqfA7ZETSNJklRlFtZSHfE0MBO4k/A5JqNtAV4EmgE9ImeRJElKJ8cB+xOWUVsSOYskSVI1WFhLdUQRMBg4HLgwcpakWECYaZ0P7Bs5iyRJUjrYC+gJzAAmRc4iSZJUTRbWUh0yAviYsDxIXuQsSTEOWAOcTRZMG5ckSaqBesD5wDpgVOQskiRJNWBhLdUhCeBXwEHAJZGzJMUGYCxhhnV+5CySJEkxnQ7sCfwLWBs5iyRJUg1YWEt1zL+ADwnLg9SPnCUpPgFmE05/bR45iyRJUgwHENaufp/wvkiSJCmDWVhLddBtwH7Aj2IHSZZ/E9Y46R07iCRJUi1rApwLLAJeiRtFkiQpGSyspTpoLPAWYXmQRpGzJMVS4A3gUMIMI0mSpLqiL6G0fg7YHDmLJElSElhYS3XUL4G2wJWxgyTL28Bi4CzCpkOSJEnZrhvQhbAR9deRs0iSJCWJhbVUR71BOGv0VqBp5CxJUQSMBloBJ0XOIkmSlGqtgD7AHODdyFkkSZKSyMJaqsN+RdhM/trYQZJlDjAV+DbQJnIWSZKkVMkFziP8wv6fQCJuHEmSpGSysJbqsPeBF4CfAy0jZ0mal4GNhKVBJEmSstHJQDvgRWBl5CySJElJZmEt1XG/AnYHbogdJFnWAK8C+wGHR84iSZKUbO0JhfUU4NO4USRJklLBwlqq46YCI4D/B7SOnCVpJgHzgN5Ao8hZJEmSkqUhYSmQFcCYyFkkSZJSxMJaEoOBJoSlQbJCgnCKbGPg9MhZJEmSkqUPYR2354ANkbNIkiSliIW1JGYAfweuAfaOnCVp/gO8BxxDWONRkiQpk3UFjgTeJJxJJkmSlKUsrCUBMARoANwaO0gyvUY4ZfZs/NtOkiRlrhZAX6AQeD1yFkmSpBSzwpEEwBfAX4GfEPbyyQobCes77g0cGzmLJElSdeQA5wJ5hKVAtkRNI0mSlHIW1pJK3Vn89VdRUyTZDGAmcBphdpIkSVImOQ7YH3gJWBI5iyRJUi2wsJZUaj7wCPBD4IDIWZJqDGF2Up/YQSRJkqpgL6An4RfwkyJnkSRJqiUW1pLK+R1hJY3BsYMk03LCetZdgAOjJpEkSaqcesD5wDpgVOQskiRJtcjCWlI5/wEeBL5P6HezxrvAIuBMoH7kLJIkSbtyOrAn8C9gbeQskiRJtcjCWtJ2fg+sBobEDpJMW4AXgd2AU+JGkSQpG/Xu3ZsZM2Ywa9Ysbr755gqP+d73vsenn37KJ598wt///vdaTphBDiCsXf0+MDtyFkmSpFpWL3YASelnKXAvcDtwJDAlYpak+oqw/uPxwEeEGdeSJKnGcnNzeeihh+jVqxfz58+noKCAUaNGMX369NJjvvWtb3Hrrbdy4oknsnz5cvbYY4+IidNYE+BcwvuUV+JGkSRJisEZ1pIqdB+huL4zdpBkexXYAJxF2IhRkiTVWPfu3Zk9ezZz5sxh06ZNDB8+nH79+pU7ZtCgQTz00EMsX74cgG+++SZC0gzQl1BaPwdsjpxFkiQpAgtrSRVaSVga5GzCGalZYy3wMtCRMH1ckiTVWNu2bZk3b17p5fnz59O2bdtyxxx44IEceOCBvPXWW7z77rv07t27wscaNGgQBQUFFBQU0KZNm5TmTjtHETYRGQd8HTmLJElSJBbWknboQcImjFk3y3oq8CXQizCDSZIkpVy9evXo3Lkzp556KgMGDGDo0KG0bNlyu+OGDh1Kfn4++fn5LF68OELSSFoB3wG+IGwWLUmSVEdZWEvaobXA7wib1J8aN0pyJQgbMDYklNaSJKlGCgsLad++fenldu3aUVhYWO6Y+fPnM2rUKDZv3szcuXP57LPP6Ny5c21HTU+5wHlAEfA84b2KJElSHZXSwnpXO4U3aNCA4cOHM2vWLN577z06duwIQKtWrRg/fjyrVq3iwQcfTGVESbvwCDAf+HXsIMn2DfAO0I2wPIgkSaq2goICOnfuTKdOnahfvz79+/dn1KhR5Y55/vnnOfXUUwFo3bo1Bx54IF988UWEtGnoFKAd4RfqKyNnkSRJiixlhXXJTuF9+vSha9euDBgwgC5dupQ75vLLL2fZsmV07tyZ++67j7vuuguA9evX86tf/Yobb7wxVfEkVdIGwpIgJxLOUs0qbwDLCBsw5kXOIklSBisqKuKaa65h7NixTJ8+nREjRjBt2jSGDBlC3759ARg7dixLlizh008/ZcKECdx0000sXbo0cvI00B44CZgCfBo3iiRJUrpIpGIcd9xxiZdeeqn08i233JK45ZZbyh3z0ksvJY477rgEkMjLy0t888035W4fOHBg4sEHH6zU8xUUFKTkdTgcDhL1IfE5JD5MgyxJH51JcDsJvp0GWRwOh8NR4fB9Xt0dWf+zb0iC64pHwzTI43A4HA6Hw1FLY2fv81I2w7oyO4WXPaaoqIgVK1bQunXrSj9Hnd5BXKpFm4AhwNHAuXGjJN8sYBrhVNzd4kaRJEl1TB+gJfAc4bQ2SZIkZfami3V2B3Epgr8DMwjLg2T0XxwVeQnYApwZO4gkSaozugJHAm8C83Z+qCRJUl2Sst6pMjuFlz0mLy+Pli1bsmTJklRFklQDRcBg4FDgwshZkm4lMAE4EOiyi2MlSZJqqgXQl7Cz9euRs0iSJKWZlBXWldkpfNSoUQwcOBCACy64gPHjx6cqjqQkeBaYSlgeJOv2KPwA+Jpwam6DyFkkSVL2yiGssZZHWApkS9Q0kiRJaSdlhXVldgp/7LHHaN26NbNmzeKGG27glltuKb3/nDlzuPfee7nsssuYN28eXbo47VGKLQH8ijAR+dLIWZJuC/AC0Bw4LXIWSZKUvY4D9icsSbY0chZJkqQ0VC+VDz5mzBjGjBlT7rrBgweXfr9hwwYuvLDixQX222+/VEaTVE0vECYj3wUcC3xaZvwnYq6kKAQ+JLywqYQZ15IkScmyF9CTsDHIpMhZJEmS0lRKC2tJ2ekK4D7gfOAnZa5fQvkCu2R8U9sBa2IcYR3rs4HHCNPKJUmSaqoe4c3TOmDULo6VJEmqwyysJVXZVKBH8fd7AocUj0OLv/YHdi9z/DeE4voTyhfZaXkW7HpgLOED5dGEGdeSJEk1dTrhjdPfgLWRs0iSJKUxC2tJNbKoeEzY5vp92Fpkl4wfAC3LHPM1Fc/IXp7SxJXwMdCN8MFyOrAmbhxJkpThDiCsXf0+MDtyFkmSpDRnYS0pJRYWj1e3ub4t5UvsQ4EfEvY6LLGAiovslamNXN5o4CqgN/BcbT6xJEnKKk2Acwm/4X8lbhRJkqRMYGEtqVYVFo+Xt7m+A9vPyB4ENC1zzHy2X1ZkGrA6FUGXAG8BpwKTgTmpeBJJkpT1+gKNCUuBbI6cRZIkKQNYWEtKC18VjzFlrssBOrJ9kX014XNfiS/Zfjb2NJKwPORbwOGEDRgfxg+ZkiSpao4ibOb8MvCfyFkkSZIyhIW1pLSVAOYWj9Flrs8F9mP7IrsH0KjMcXPYvsieDqyrbIDNxU/8A+BE4PXqvApJklQntQK+A3wBvBs5iyRJUgaxsJaUcbYAnxePUWWuzwP2Z/si+wygQZn7fsH2RfYMYENFT/Y5YRPGk4q/Lk3qS5EkSdkoFzgPKAKeJ/wWXpIkSZViYS0paxQBs4rH82Wurwd8i+2L7DOB+mXu+znbF9kzgY1jgc7AWcDTKX4RKZRDeL31CQV+ydcG1bhuMzCJsKZ4UW2+CEmSMsEpQDtgBLW8a7QkSVLms7CWlPU2E2ZQzwD+r8z19Qk99LZFdl+2/uW4GZi9Gj59FD49DD5tD5/OC+V2LjUrfVN13Y5uKynnk2k18AHhTOd3gfcI+1VKklRntSecmTWFsKmGJEmSqsTCWlKdtYnwOXIa8GyZ6xsABxLK60OLvx62DM59E/Jq4ZTeTcDGMl837uS6DcCqKt6nMrfv6romQD5wfPH4OVsL8c8IxXVJie0sbElSndGQsBTICsrvJC1JkqRKs7CWpG1sJJSsnwD/KHN9w73g4HPgkPeh49Qw+7omBXBFt29K+atLns+B4cXfNwaOZmuBfQZwafFtzsKWJNUZfYCWwOPsYHMMSZIk7YqFtSRV0oavYepXMPVc4BtgQeRAaWQd8FbxKNGJrQX28cDNbP1H5zO2Ftgls7C31FJWSZJSoitwJPA6MC9uFEmSpExmYS1JVTGBsEbIdwm7Di4Dlhd/dSZVOXOLx7Diy42BY9haYH8HGFh82yq2n4W9tPaiSpJUMy0Im2DMJxTWkiRJqjYLa0mqig3AKEJh3Xub29axtcBeTvkyezlhDZE6bB3wZvEosR/lZ2HfwtZ/mGZSfhb2pzgLW5KUhnKAc4E84Dn8x0qSpAy3++67c/3119OpUydycnJix8loiUSCuXPncv/997Ns2bJK38/CWpKqahbwe8KU4d2A3bf5ugfQma27EJZYzfYldsnXFdTJD7hzisczxZebUH4W9pnAZcW3rWT7WdiV/+dOkqQUOQ7Yn/ALbU8PkiQp411//fV8+OGH3HHHHRQVFcWOk9Hy8vI466yzuP766xk8eHCl72dhLUnVta54LKzgthygKduX2bsB7QjLiuSWOX4LoZFdTsWl9mogkdz46Wgt8EbxKLHtLOxb2fqP1wxCce0sbElSFHsBPQn/IE2KnEWSJCVFp06dLKuTpKioiNGjR3P++edX6X4W1pKUCglCybyaijdeyiWsd7kb5cvs3YEDim8razNhFvaOZmivTWL2NOMsbElSWqoHnE/45fWoyFkkSVLS5OTkWFYnUVFRUZWXVrGwlqQYtrB1reu5FdxeD2hJxTO09yW0tmVtYMdrZy8nqzaErGgW9v7sfBZ22bWwp+EsbElSEpwO7Ak8TVb/4liSJKm2WVhLUjraDCwpHhVpSPlZ2WW/71R8e1lr2XGZvZyM3xDyi+Lx9+LLTSk/C/ts4IfFt60E3qf8LOzltZhVkpQFDiCsXf0+8HnkLJIkKau0atWKcePGAbD33ntTVFTEN998A0D37t3ZtGnTDu979NFHc+mll3Ldddft9DnefvttTjzxxOSFTjILa0nKRBuA/xSPijSh4jJ7L+Agtv/bfxUVl9nLCA1vhk1JXgO8XjxKHED5Wdi/BPKKb5vO9rOw68CS4UBYbr0RYQ/RktFkm8vbXlef8J/GYuCb4rEYi39JdUQT4FxgEfBK3CiSJCn7LF26lG7dugEwePBgVq9ezT333FN6e15e3g6XLJk4cSITJ07c5XOkc1kNFtaSlJ3WFo8FFdyWAzRj+zJ7N6ADcCjbbwi5gvJl9grCmp3rtxkbk/oqkurz4vG34stNgXy2FtjnAD8qvm0FYdJcyYaOtT0LuyFVK5Are8yOrkuWTWwtsbctsyv6fgkZP7lfUl3Ul/CX59/wLzFJkrLdd4C9k/yYXwMvVe0ujz/+OOvXr6dbt268/fbbDB8+nAceeIBGjRqxbt06fvjDH/LZZ59xyimncOONN9K3b18GDx5Mhw4d2H///enQoQP3338/Dz74IACrVq2iefPmnHLKKdx+++0sXryYQw89lIkTJ3LJJZcA0KdPH+69917WrFnD22+/zf7770/fvn2T/IdRMQtrSaprEoQZ1auAryq4PZewfvZubF9qdwaa7+SxtxCK6w1sX2ZvOyo6ZgO1NrV5DfBa8SjxLSo3C3sSofevaVlc0TGNKf/7gqpYT/g9QslYW+b7ZYTfX6zd5phtj6vo8rbXbSL857AH0Kb46x4VXD6i+GvrnWRexs5L7W0vu0yspKiOAroAY9nxWU6SJEkp0K5dO0444QS2bNlC8+bNOemkkygqKqJnz5789re/5YILLtjuPgcffDCnnXYazZs3Z+bMmTz88MNs3lz+N+7dunXjkEMOYcGCBaVLhXz44Yc8+uijnHzyycydO5dnnnmmtl4mYGEtSdrWFkKLuAyYU8Ht9YAWhHUkdjYaFn9ttc11u1KZYntnx9Rg+ZLZxePp4svN2PEs7MrYyI6L31WEs8krUyBXplSu4UuvstXAvEoem0f4z2BHxXbJ950Ia4/vATTYwWOtY9czt8t+v4y6s7yLpBRrRZhl9QXh1BtJkpT9qjgTOpWeffZZtmwJn/patmzJk08+SefOnUkkEtSvX7/C+4wePZqNGzeyZMkSFi1axF577UVhYWG5Yz744IPS66ZMmUKnTp1YvXo1X3zxBXPnzgVg2LBhXHHFFal7cduwsJYkVc1mYGk175vL1iK70Tbf72i0APYsczlnF8+xkarN6t52lFkKbDUwoXiU6ExYNWUTuy6VK15VrO4pYmuBXFkt2HGxXfb7zsVfdzTxv4iw9MiuZm6XXcokjVe2kRRLLnAe4S+V5/E3YZIkqdatWbOm9Ps777yTCRMmcN5559GxY0dee+21Cu+zYcOG0u+LioqoV2/7Krgyx9S2+AkkSXXHFra2udWRQ5h6u6PZ3BWNZoR2s+SYvO0etbzN7LTQnlU8dlh+73jDZlXByuLxeSWPb8jWEntHJfceQFe2LlOyo6VXVrLzUnsJoavKK36MvG2+3/ZrMm9Ll8f6EfDPHfz5SVnpFKAdMILwl4QkSVJELVu2LJ0VfdlllyX98WfOnMn+++9Px44d+fLLL7nooouS/hw7Y2EtScocCUJRvIGwM2J11GfXy5hsO3Yr8/2u/uUsonKzuXd0+0acuVcNG4DC4lEZuWxdh3tna3G3Zeta3I2SG3k7RYTf6RRt8/22X2ty2+YkPdbc1PwRSOmpPXASMAWYFjeKJEkSwO9//3uefPJJbrvtNkaPHp30x1+/fj1XX301L730EmvWrKGgoCDpz7EzOWTJx+KCggLy8/Njx5AkZbt67Lzc3tUyJztanLlEgpoV3huo3cWs65CSyfqtii8ns0jOijdjKeT7vLor+s++IXBl8fePEP6OlSRJWe2pp57i0ksvjR0juqZNm5YuQ/LQQw8xa9Ys7r///mo9VkV/pjt7n+cMa0mSqmIzYXHr1dW8/7breFem9N5tm9t2tY53SZld3dLbxbcrVPJjnxs5h6Ra1AdoCTyOZbUkSapTBg0axMCBA2nQoAGTJ0/m0UcfrbXntrCWJKk2pWod750V3iVTg0su72jx5hKb2PUs7k2E8r7sqOi6bW9z9rekTNEVOBJ4HZgXN4okSVJtu//++6s9o7qmLKwlScokqV7He0fLmuxW5vuavHvYws4L7V0V3jW5r2W5pMpqAfQF5hMKa0mSJNUaC2tJkuqaTcVjVTXvn0d4B1G/+OuOxs5u39Ft9YEmO7mtJpJdlm+qxPclw0WqpcyRA5xL+LvuOfxllyRJUi2zsJYkSVVTslNgjPVc86heEV6Zgr0BqSvLK1NsV6YAr8p9XItcqp7jgP2BUcDSyFkkSZLqIAtrSZKUOUrK8tqWw9aZ5RUV4Dv6vrLHNdrJbdWVoPrF+K6O+wZYU4NsUrraC+gJTAcmRc4iSZJUR1lYS5Ik7UpJ+bu5lp83h53PEq9MGb6j+zQAmu7guLxd5BoJfJKclyillT6ETXFfiB1EkiTVVePHj+d//ud/ePnll0uvu+666zjooIO4+uqrtzt+woQJ3HjjjUycOJHRo0dz8cUXs2JF+Q2PBg8ezOrVq7nnnnt2+Lz9+vXjs88+Y/r06QAMGTKEN954g3HjxiXplVWehbUkSVK6SrB1zfHalMvOi/FvajmPVFv+D2gJrI0dRJIk1VXDhg2jf//+5Qrr/v378/Of/3yX9z3rrLOq/bznnnsuL774YmlhPXjw4Go/Vk3lRntmSZIkpactwEZCabcSWAL8BygE5uJyIMpeq4D5sUNIkqR0cR8wIcnjvl0858iRIznrrLOoXz9spNOxY0f23XdfBgwYQEFBAZ988gm33357hfedM2cOrVu3BuAXv/gFM2fO5M033+Sggw4qPebHP/4xH3zwAVOmTGHkyJE0btyY448/nnPOOYe7776byZMns//++/P4449z/vnnA9CjRw8mTZrERx99xGOPPUaDBg1Kn+/2229n4sSJfPTRR+WepyYsrCVJkiRJkiQpDSxbtowPPviAPn36AGF29YgRI/jlL39Jfn4+/7+9+w+tqv7jOP7a7pluc04FGeUc8yYWhc7dW4klFbQgaJSRoFeGxhgIQ60JTsuICPonCFpWGCt1FnMTddIkbPgjNEzm6N790jt/sLt0utrWj7GGDDfP9w/x8u37Nc3tdj5Hz/MBL9zu9Z77Pr43efP2eJaXl6dnnnlG8+bN+9tjBINBhUIh5efn64UXXtDjjz8ef66urk4LFixQfn6+otGoSkpKdOLECdXX16u8vFyBQECdnZ3x3z9x4kRVVVVp2bJlysvLk2VZKi0tjT/f39+vRx99VFu2bNH69esT8mfALUEAAAAAAAAA4H+sM/S+N24LUl9fr1AopJKSEi1dulSrVq2SZVm6//779cgjj6itre2mr3/qqae0b98+XblyRZJUX18ff27u3Ll67733NHXqVGVkZKihoeGWtTz00EOKxWI6d+6cJGnHjh1avXq1PvroI0nXF+CS9OOPP+qVV14Z97lLXGENAAAAAAAAAK7x9ddfq6CgQIFAQOnp6frtt9+0fv16FRQUaP78+frmm2+Umpo6pmNXVVVpzZo1ysvL07vvvjvm49wwPDwsSRodHZVlJebaaBbWAAAAAAAAAOASQ0ND+u6777Rt2zbV1NQoMzNTQ0NDGhgYUFZWVvx2IX/n2LFjevnll5WamqqMjAy9+OKL8ecmT56snp4eWZaloqKi+OODg4OaPHny/x3rzJkzmjVrlmbPni1JWrFihY4ePZqgM705FtYAAAAAAAAA4CI1NTXKz89XTU2NWltbFYlE1NHRoZ07d+r48eO3fG0kEtGuXbvU0tKiAwcOqKmpKf7c22+/rcbGRh0/flwdHR3xx2tra1VeXq5wOKwHHngg/vjw8LCKi4u1e/dutba26tq1a/rss88Sf8L/JUmS/a++g0Oampr+cgNxAAAA3BuY87yL3gMAAKd9+eWXWrlypeky7ik3+zO91ZzHFdYAAAAAAAAAAFdgYQ0AAAAAAAAAcAUW1gAAAAAAAAAgybZt+Xw+02XcM3w+n2z7zu5IzcIaAAAAAAAAACR1dXWpsLCQpXUC+Hw+FRYWqqur645eZ/075QAAAAAAAADA3aWiokJlZWVasmSJkpKSTJdzV7NtW11dXaqoqLij17GwBgAAAAAAAABJv//+u9555x3TZXgatwQBAAAAAAAAALgCC2sAAAAAAAAAgCuwsAYAAAAAAAAAuEKSJNt0EYnQ29urn376ydH3nD59uvr7+x19T7gH/fc2+u9t9B98DTgrNzdXWVlZpsuAAcz4cBr99zb6723039vov/NuN+PbZGxpamoyXgOh/4T+E/pP+BoghCQufH97O/Tf26H/3g7993bov7vCLUEAAAAAAAAAAK7AwhoAAAAAAAAA4AosrMehsrLSdAkwiP57G/33NvoPvgaAexff395G/72N/nsb/fc2+u8u98wPXQQAAAAAAAAA3N24whoAAAAAAAAA4AosrAEAAAAAAAAArsDCeoyef/55dXR06Ny5c9q4caPpcuCgmTNn6siRIzp16pTa29v12muvmS4JBiQnJyscDmv//v2mS4HDpkyZot27dysajer06dNauHCh6ZLgoLKyMrW3t6utrU07d+7UxIkTTZcEIIGY8b2LGR8SM76XMeN7GzO+O9nkzpKcnGyfP3/e9vv9dkpKit3c3Gw//PDDxusizuS+++6zA4GALcnOyMiwz5w5Q/89mHXr1tnV1dX2/v37jddCnE1VVZVdUlJiS7JTUlLsKVOmGK+JOJMZM2bYnZ2ddmpqqi3J3rVrl/3qq68ar4sQkpgw43s7zPhEYsb3cpjxvRtmfHeGK6zHYMGCBTp//rxisZiuXr2q2tpaLV682HRZcMjPP/+sSCQiSfrzzz8VjUaVnZ1tuCo4KTs7W4WFhfriiy9MlwKHZWZm6umnn9bWrVslSVevXtXAwIDhquAky7KUlpYmn8+n9PR0Xb582XRJABKEGd/bmPHBjO9dzPhgxncfFtZjkJ2drYsXL8Y/7+7uZpjxqNzcXAUCATU2NpouBQ6qqKjQhg0bdO3aNdOlwGF+v199fX3avn27wuGwPv/8c6Wnp5suCw65fPmyPvjgA124cEE9PT0aGBjQwYMHTZcFIEGY8XEDM743MeN7FzO+tzHjuxMLa2CMJk2apL1796qsrEyDg4Omy4FDCgsL1dvbq3A4bLoUGGBZloLBoLZs2aJgMKihoSG98cYbpsuCQ6ZOnarFixfL7/drxowZmjRpkoqKikyXBQBIIGZ8b2LG9zZmfG9jxncnFtZjcOnSJeXk5MQ/nzlzpi5dumSwIjjNsizt3btX1dXV2rdvn+ly4KBFixbppZdeUiwWU21trZ599ll99dVXpsuCQ7q7u9Xd3a2TJ09Kkvbs2aNgMGi4KjjlueeeUywWU39/v0ZGRlRXV6cnn3zSdFkAEoQZH8z43sWM723M+N7GjO9OLKzHoKmpSXPmzNGsWbOUkpKiUCik+vp602XBQVu3blU0GtWHH35ouhQ4bNOmTcrJyZHf71coFNKRI0e0YsUK02XBIb/88osuXryoBx98UJJUUFCg06dPG64KTrlw4YIWLlyotLQ0Sdf7H41GDVcFIFGY8cGM713M+N7GjO9tzPjuZJku4G40OjqqNWvWqKGhQT6fT9u2beMvMw9ZtGiRVq5cqdbW1vgPZtm0aZMOHDhguDIATli7dq2qq6s1YcIEdXZ2qri42HRJcMjJkye1Z88ehcNhjYyMKBKJqLKy0nRZABKEGd/bmPEBb2PG9y5mfHdKkmSbLgIAAAAAAAAAAG4JAgAAAAAAAABwBRbWAAAAAAAAAABXYGENAAAAAAAAAHAFFtYAAAAAAAAAAFdgYQ0AAAAAAAAAcAUW1gBg0MjIiCKRSDwbN25M2LFzc3PV1taWsOMBAAAAuD1mfAAYH8t0AQDgZVeuXFEgEDBdBgAAAIAEYcYHgPHhCmsAcKFYLKb3339fra2tamxs1OzZsyVdv6Li8OHDamlp0aFDh5STkyNJysrKUl1dnZqbm9Xc3KwnnnhCkuTz+VRZWan29nY1NDQoNTXV2DkBAAAAXsaMDwD/DAtrADAoLS3tL/9dcOnSpfHnBgYGlJeXp08++UQVFRWSpI8//lg7duzQ/PnzVV1drc2bN0uSNm/erKNHjyo/P1/BYFCnTp2SJM2ZM0effvqp5s6dqz/++ENLlixx/BwBAAAAL2HGB4DxswkhhJjJ4ODgTR+PxWK23++3JdmWZdn9/f22JLuvr8+2LCv+eF9fny3J7u3ttSdMmPCXY+Tm5tpnz56Nf75hwwb7rbfeMn7OhBBCCCGE3MthxieEkPGFK6wBwKVs277px3dieHg4/vHo6Kgsix9dAAAAAJjCjA8At8fCGgBcatmyZfFfT5w4IUn64YcfFAqFJElFRUX6/vvvJUmHDx9WaWmpJCk5OVmZmZkGKgYAAABwK8z4AHB7/DMcABh04/52N3z77bd68803JUnTpk1TS0uLhoeHtXz5cknS2rVrtX37dpWXl6uvr0/FxcWSpNdff12VlZUqKSnR6OioSktL1dPT4/wJAQAAAB7HjA8A45Ok6/cGAQC4SCwW02OPPaZff/3VdCkAAAAAEoAZHwD+GW4JAgAAAAAAAABwBa6wBgAAAAAAAAC4AldYAwAAAAAAAABcgYU1AAAAAAAAAMAVWFgDAAAAAAAAAFyBhTUAAAAAAAAAwBVYWAMAAAAAAAAAXOE//ZEKteTojTwAAAAASUVORK5CYII=\n",
       "text/plain": [
        "<Figure size 1800x504 with 2 Axes>"
       ]
@@ -566,10 +600,10 @@
     }
    ],
    "source": [
-    "loss_train = history2.history['loss'] # save the loss into variable to call it for the plot\n",
-    "loss_val = history2.history['val_loss'] # save the val_loss into variable to call it for the plot\n",
-    "acc_train = history2.history['accuracy'] # save the accuracy into variable to call it for the plot\n",
-    "acc_val = history2.history['val_accuracy'] # save the val_accuracy into variable to call it for the plot\n",
+    "loss_train = history2['loss'] # save the loss into variable to call it for the plot\n",
+    "loss_val = history2['val_loss'] # save the val_loss into variable to call it for the plot\n",
+    "acc_train = history2['accuracy'] # save the accuracy into variable to call it for the plot\n",
+    "acc_val = history2['val_accuracy'] # save the val_accuracy into variable to call it for the plot\n",
     "\n",
     "plt.figure(\"Training Graph\" , figsize = (25 ,7))  # unique identifier for the figure, figsize(Width, height)\n",
     "\n",
@@ -612,10 +646,10 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1875/1875 [==============================] - 10s 5ms/step - loss: 0.0036 - accuracy: 0.9780\n",
-      "313/313 [==============================] - 1s 4ms/step - loss: 0.0053 - accuracy: 0.9668\n",
-      "Training accuracy: 97.8%\n",
-      "Test accuracy: 96.68%\n"
+      "1875/1875 [==============================] - 9s 5ms/step - loss: 0.0036 - accuracy: 0.9782\n",
+      "313/313 [==============================] - 1s 4ms/step - loss: 0.0054 - accuracy: 0.9665\n",
+      "Training accuracy: 97.82%\n",
+      "Test accuracy: 96.65%\n"
      ]
     }
    ],
@@ -683,14 +717,6 @@
    "source": [
     "print(model_Two.summary())"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "e1fa4b4d-90b8-4305-88bb-46ac71d668f4",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {