Weather-Project/Project Final/Evaluation/Evalutation.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Using TensorFlow backend.\n"
     ]
    }
   ],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "from six.moves import cPickle\n",
    "import matplotlib\n",
    "matplotlib.use('Agg')\n",
    "import matplotlib.pyplot as plt\n",
    "import matplotlib.gridspec as gridspec\n",
    "%matplotlib inline\n",
    "from keras import backend as K\n",
    "from keras.models import Model, model_from_json\n",
    "from keras.layers import Input, Dense, Flatten\n",
    "\n",
    "from prednet import PredNet\n",
    "from data_utils import SequenceGenerator\n",
    "\n",
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "n_plot = 40\n",
    "batch_size = 10\n",
    "nt = 24"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "WEIGHTS_DIR = '../Training/weights/'\n",
    "DATA_DIR = '../data/'\n",
    "RESULTS_SAVE_DIR = './weather_results/'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "weights_file = os.path.join(WEIGHTS_DIR, 'prednet_weather_weights.hdf5')\n",
    "json_file = os.path.join(WEIGHTS_DIR, 'prednet_weather_model.json')\n",
    "test_file = os.path.join(DATA_DIR, 'x_test.hkl')\n",
    "test_sources = os.path.join(DATA_DIR, 'sources_test.hkl')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Load trained model\n",
    "f = open(json_file, 'r')\n",
    "json_string = f.read()\n",
    "f.close()\n",
    "train_model = model_from_json(json_string, custom_objects = {'PredNet': PredNet})\n",
    "train_model.load_weights(weights_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create testing model (to output predictions)\n",
    "layer_config = train_model.layers[1].get_config()\n",
    "layer_config['output_mode'] = 'prediction'\n",
    "data_format = layer_config['data_format'] if 'data_format' in layer_config else layer_config['dim_ordering']\n",
    "test_prednet = PredNet(weights=train_model.layers[1].get_weights(), **layer_config)\n",
    "input_shape = list(train_model.layers[0].batch_input_shape[1:])\n",
    "input_shape[0] = nt\n",
    "inputs = Input(shape=tuple(input_shape))\n",
    "predictions = test_prednet(inputs)\n",
    "test_model = Model(inputs=inputs, outputs=predictions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_generator = SequenceGenerator(test_file, test_sources, nt, sequence_start_mode='unique', data_format=data_format)\n",
    "X_test = test_generator.create_all()\n",
    "X_hat = test_model.predict(X_test, batch_size)\n",
    "if data_format == 'channels_first':\n",
    "    X_test = np.transpose(X_test, (0, 1, 3, 4, 2))\n",
    "    X_hat = np.transpose(X_hat, (0, 1, 3, 4, 2))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Compare MSE of PredNet predictions vs. using last frame.  Write results to prediction_scores.txt\n",
    "mse_model = np.nanmean( (X_test[:, 1:] - X_hat[:, 1:])**2 )  # look at all timesteps except the first\n",
    "mse_prev = np.nanmean( (X_test[:, :-1] - X_test[:, 1:])**2 )\n",
    "if not os.path.exists(RESULTS_SAVE_DIR): os.mkdir(RESULTS_SAVE_DIR)\n",
    "f = open(RESULTS_SAVE_DIR + 'prediction_scores.txt', 'w')\n",
    "f.write(\"Model MSE: %f\\n\" % mse_model)\n",
    "f.write(\"Previous Frame MSE: %f\" % mse_prev)\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "def getAverage(test_frames):\n",
    "    blank = np.zeros((20,40,7))\n",
    "    window = [blank * 5]\n",
    "    average = []\n",
    "    for day in range(test_frames.shape[0]):\n",
    "        day_average = []\n",
    "        for hour in range(test_frames.shape[1]):\n",
    "            day_average.append(np.mean(window[-5:], axis=0))\n",
    "            window.append(test_frames[day,hour])\n",
    "        average.append(np.array(day_average))\n",
    "    return np.array(average)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Naive Case 5 frame average\n",
    "X_test_naive = getAverage(X_test)\n",
    "mse_naive = np.nanmean((X_test[:, 1:] - X_test_naive[:,1:])**2)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model MSE:\t 2.3059108400502737e-07\n",
      "Prev Frame MSE:\t 1.0880363277010474e-08\n",
      "Naive MSE:\t 4.413529927867206e-08\n"
     ]
    }
   ],
   "source": [
    "print(\"Model MSE:\\t {}\\nPrev Frame MSE:\\t {}\\nNaive MSE:\\t {}\".format(mse_model,mse_prev, mse_naive))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [],
   "source": [
    "y_labels = [\n",
    " 'VISIBILITY',\n",
    " 'DB TEMP C',\n",
    " 'WB TEMP C',\n",
    " 'Dew Point',\n",
    " 'Humidity',\n",
    " 'WindSpeed',\n",
    " 'Pressure',\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAuYAAAJQCAYAAADCCqE7AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4xLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvAOZPmwAAIABJREFUeJzsnXmYHFd19t/b6+y7NFpG8mizLO8btiFm84YEAQPfZxMTkpCQOCGBAAY+zBYgIUDAbAFC4gRjk7BvYfUOGAO2bNl4tzbLsvZlNKPZl17u98eM6pxT6m7NjKZnulvv73n06FTdU1W3eqpO36771jnOew9CCCGEEELI3BKZ6w4QQgghhBBCODAnhBBCCCGkJODAnBBCCCGEkBKAA3NCCCGEEEJKAA7MCSGEEEIIKQE4MCeEEEIIIaQE4MCcEEIIIYSQEmBOBubOubXOuU3Oua3Ouevnog+EkMqDsYUQUgwYW8hs4Wa7wJBzLgpgM4DLAewC8CCAa7z3T81qRwghFQVjCyGkGDC2kNkkNgfHvADAVu/9NgBwzn0LwJUA8l7gbS1R37kknrsxfrrYqSdmsJuFOZBJBPahsdrAbkkMGr/6yEjO7WtcgckKdU5bHt8Z2KvOWGL9Zvp89WdZAmx+aFvO9SMYxJgfdbPcHVL6TDm2JFzSV6E2XzM5wWBsIXmYcmyJJ2p9VVUzACB8QZ188oLA3rR535Q7E0ll8rb5mIwtvLNHjqSzspBW+4hF7T4iuW+BfOsBYLU6p81P7wnsk9csMn7TOd9C6OOWAjMxbpmLgfliADvV8i4AFxbaoHNJHA/cviRnW2TBhsDO7ls1A92bHF/oOSmwv7Hj/MB+3dKHjN8ltRtzbn9moirvvvU5rVt2XWDfuuEzxm+mz1cftxS4PHJVzvXr/d2z3BNSJkw5tlShFhe6S4vaKVI+MLaQPEw9tlQ147yL3gIAiKStMuEXv3hvYL/kik9MuTNVewfytqWaqwM7U2UH3Mmu4cCOHDwc2Nl5TcYvU5P7QWi6Jv+Q8Vd3iLrnivM+HNh3bPiw8ZvO+RZCH7cUmIlxy1wMzHP9YjhKT+OcuxbAtQCwaHEUm1PjT6I7ovaCqZnFwXg+Lpz/XGCfktxr2loiaWXLU/bIgi3GTw+yz/7pBwK7raM1p89U0McqtI/J7j/c92IRW95pltPbts/KcUnZMuXYUoWaYveJEFL+TD22JBsRGxr//s8m7QB5OoNTp46WbrAP9nxUuhcejOfDN9XLNqGBuI+qp+5q3+FBsD6PS1/8scCO5vGZCvpYhfbx0stVWwFl9i/vKq0BfCHm4uXPXQD04+8OAHvCTt77G73353vvz29uYfIYQsgxmXJsiSM5a50jhJQtU48tMUrkyPSYixHvgwBWOeeWOecSAP4IwI/noB+EkMqCsYUQUgwYW8isMetSFu992jn3FgC3Y3zG4ybv/ZOz3Q9CSGXB2EIIKQaMLWQ2mQuNObz3Pwfw88n6H0zX4d+6XgwAuG7er0zbUqXbnk3e2iy68mdS+e/PjlhdzvVhPffHulYHdiojCq07vnvzNHuY/1j5+FxPZ2C/vXl7YJ923x8bv6dfc3z96fzyDZPy2771U2b5kks/Pm48eN/xdYBULFONLYQQMhmmGltcOoP4vl4AwNgi+3Kli8h3vFfqdRfWSOtl5Zeund7QbbRNXgyNplSGlkx+cXY2JgcOa72jo2ofSn8x1po/ucVMExtMBXZaaeUTh4Zm9DhXJK6ZlN+d2e+a5XwvgxaC4m1CCCGEEEJKAA7MCSGEEEIIKQHmRMoyVRqiw1jb+DgAYGkeachcsiKev0/5UguG5SXt8d7ATqUml+5optGpHl/4d38d2Ke9c6vxu/B2STu0/mVTT4VUvcue33CHKnSQzp9///J/vRcAsPnq/ikfkxBCCJktfDSKTOt4SkJd9Aew8pVC64tZ6SoTlz650JAjX2rBsJTFZUTKEu0ZlX0vkIw04RzuWhpTiHwpEsNyn8jQWGBX7exSfWg2fmtPkXO6bePUxy0+aw/sVLGl6OKF+Tc8IlvKXxPq6E2m0jFCCCGEEEJIccg7MHfO/dw51zl7XSGEnAgwthBCigFjC6kECklZbgZwh3PuFgCf9N6nCvjOGj0Z+6Ztc7S0K/dNNiPKmxr3iX3xfxerO4bVX3mzWV738gcD+94v/UdgP//R/2P8XqrkOZ9/+rLAvnmbrVDc97RULa1b3RPYSy63UpTe/5K6Dcleme/JXmU/u7Oqx4vBVEfGQMqam1GCsYUQUvbcjFKJLREgM1HC3kemJ0rJJ3mZaXzoEe1kq3Wma2QIGR2Sj9qpZC2Tla6E0ZIVp2Qk8e5h4+ejosMZXiOSkqodh+3+hkYCe93yd8r2iVDV02rJ9KclSLGF7cYvvVvqS2WbRM4cZI+bIDFvfBzkuiavHM/r6b3/jnPuZwD+AcAG59x/A8iq9s9M+iiEEDIBYwshpBgwtpBK4FhD+BSAQQBJAPVQFzghhBwHjC2EkGLA2ELKmrwDc+fcWgCfwXjZ2XO99zObrZ0QckLC2EIIKQaMLaQSKPTE/AMAriqFsrONydPw8uUbAAD/+MQrTdsH2jbORZdMGsTJ6siLyW1DycBeWzNawFP4/DU35W1b9as3ir3wgGn75gOiJX/2lf8Z2N+InW/8Wh8TXVhXh1QC+/3zvmUPlqcQ6M19883yy2ufBQDURKaQd4iUIiUTWwghFUXJxJaTVy/E3b98HwDgsos/atq0Nns2+dUdkjJwsjryyZJqlu945+W7308z6aPW1/uoLKQbQlVF1bESh2Xs4watFh1O9uH7B8ReaMcZWleeTaq/08IW4xdpawzsTI3o0qPDaeOXXTquTfd9VsteiELpEutK4eImhFQcjC2EkGLA2ELKnkIDc+qyCCHFgLGFEFIMGFtI2eO897kbnNuFca1WTmbz7eaa+Uv8qtddBwCofeU+0/abM38Q2KUmL6kUwukSW/5cpoEyi9sC+7affN34vfivrw3sfRdISqNNb/rycfXngpftxIZHR2YpkRSZaUoptjS4Fn+hu3S2DkdKnPX+bvT5bsaWMqWUYktjcoF/weI/BoCgAugRxpTsY6blJZPdX7iCZj5mK2XjTJDolVTKY40J0xb/xSOB7VSKxUhttfFLn9opC0r+kq4+vorsD93/RfT37ZrUp1lI6BQFUIfiVoUlhJx4MLYQQooBYwspewoNzPd67/9x1npCCDlRYGwhhBQDxhZS9hQamJfML85IUyqQsFyz9MG8flq+omUthZhpyUv4uOUkqcmX2eW+s75vHR8W84qr3hjY69ZdY9zuufXGGe0fqRhKJrYQQiqKkoktPhYJJCw+al/ni46KFF5nbPnVbz4wqX0XkqhMVg6jJSpa/jKVfWg5zFxJXqIjkqUtU5V/SBttliwqaGkKTL/voPGbq4w5mkI9uMI515Kv0XvfXYT+EEIqH8YWQkgxYGwhZU+hgfkDADxy/wL1AJYXpUeEkEqHsYUQUgwYW0jZk3dg7r1flq/NObe4ON0hhFQ6jC2EkGLA2EIqgbzpEgtu5NwO7/3SIvQnJ+efVeUfuH3Jce1jrjTnxSTfOU33HIaykmqoJiKphrT2HACeGpH49q5Tbz/u406WI+frnHvIe3/+MdxJGTLbsYXpEomG6RIrl9mOLfUNHf68i96Ssy15cCiwM7XyXRvWN4e13/mYTprFmUiXGBsWffdk0wnmO6fppop0KnO9L1CZJzYoFTnv+q1o+We6AmqYI+c7lXFLoQJDhWDgIoQUA8YWQkgxYGwhZcF0B+ZTf8xOCCHHhrGFEFIMGFtIWZBXY+6c+wJyX8gOQFOO9UUjhSwOZAYBAPOjtaYtn/wizFxJVGayGunPhqrM8itm+Jz056c/17U11m9tzbbAfvVv/jawf7Dy+PswWckRKV9KKbYQQiqHcoktqRapNpmN5n+QX0yZxS/vzF8hVMtNXnq5tIVlLZnkseUr0VTWLM/0ORWSr2iyVcdXubMQk5UcTZZCWVk2TLONEEIKwdhCCCkGjC2k7CmUleWW2ewIIeTEgLGFEFIMGFtIJZA3K4tz7icooMny3r+q4I6duwnAHwI44L0/fWJdC4BvA+gEsB3A1d77nmN18owz4/4HP2sDAGxJtZo2XaHyROOC9745sN/1/m8E9tV1vXPRnWkzVfkKs7KUN6UUW5iVhWiYlaW8KaXYUigrS6ljMrZoO3xn6Mqfk5SUVG87FNhjS5oDOxOf7iuPkyNxaESOVSey3UxyesedqnxlKuOWQlKWG6Z01KO5GcAXAXxNrbsewN3e+084566fWH7PcR6HEFJeMLYQQooBYwspewpJWe45nh1773/tnOsMrb4SwEsm7FsA/Aq8wAk5oWBsIYQUA8YWUgnkfYbvnFvlnPuqc+4zzrkO59ytzrkB59yjzrnpygjavfd7AWDi//kFjn+tc26Dc25Dd3c2nxshpMwopdiSwokrhSOk0iip2JIanObhyIlOISnLVzE+ndMAYD2AtwN4DYAXAvgSgAuL2THv/Y0AbgSAVWdU+yPa8lXxQ8bv/hFJO/SOTVcH9n1nfb+Y3SsJHvj4lwP77Xsl5lxdx5fPSUlTMrGlwbUwtzEhlUPJxJb6ho68sSWSkaZYv6QmHmuyVbYPnC/L8zfM3kMEnRZR682PqgKqlrXmulBKxOHl8p6g/hyKzVhr1bGdSoRCqvc67/2N3vsbAAx777/rvR/x3t8JIFlgu0Lsd84tBICJ/w9Mcz+EkPKFsYUQUgwYW0jZU2hgrvUjfQXapsKPAfzZhP1nAH40zf0QQsoXxhZCSDFgbCFlT6F0iUMAtmJ8smLFhI2J5eXe+9qcG8r238T4CxNtAPYD+BCA/wXwHQBLAewAcJX3vvtYnTz//PP9hg255Rk/33Z6YJ/IqRMfGpXpsIOZetNW6p8L0yWeWJRSbGG6RKJhusTyppRiS6Fxy6Uv/Vhg6zSBv/jaV4zfJX/6pmMdpii4PAqTo6Qsx4mRsoSOmY2V9m04V+kS10zpqCG899fkaeK3ICEnNowthJBiwNhCyp5C6RKfm82OEEJODBhbCCHFgLGFVAJ5B+bOuX7krqDlAHjvfUPRekUIqVgYWwghxYCxhVQChZ6Y1+drKyUmq5/WOubsvlXF6s6MMJ2+vmWjzMCdCKkiSflSLrGFEFJelEtsyVd+fq405WGmoyWfbLpETbxnJLBH26oLeJ5YFHpiXgMg5b1PTSyvBvByANu99z+cpf4RQioMxhZCSDFgbCGVQKF0ibcB6AQA59xKAPcBWA7gLc65yf0cIoSQo2FsIYQUA8YWUvYUysrS7L0/oqn4MwDf9N6/1TmXAPAQgKnlipljJisJKQXJy3SOq+UrD4ymTNsFyfhx9+l4mWpKRFLRVFRsIYSUDCdkbJmOjGSmmc5xtXwlkravBpRCusSppkScKQo9Mdef0iUA7gQA7/0Ypp+onxBCGFsIIcWAsYWUPYWemD/mnLsBwG4AKwHcAQDOuabZ6BghpGJhbCGEFAPGFlL2FBqY/xWAt2Fcr3WF935oYv2pAG4ocr8mTSlIT0qNUpCuAJSvkLyURWwhhJQdZRFbSkF6UmqUgnQFmDv5iqZQusRhAEddMd773wH4XTE7RQipXBhbCCHFgLGFVAKF0iU+jtyJ+gEA3vszi9IjQkhFw9hCCCkGjC2kEigkZdkB4GMY12rlvdAJIWSKMLYQQooBYwspewoNzO/AuCZrIYBvYzzt0COz0qtpQk1zbp5JDQT2injdce8vn66fnz+ZJGUXWwghZUHZxZZS0DTPJk7lxvEF8gJO1m+y5NP1l+Lnn/d0vfef994/H8CLAXQD+Kpz7mnn3D84506etR4SQioKxhZCSDFgbCGVwDF/h3jvn/Pe/4v3/hwArwfwGgBPF71nhJCKhrGFEFIMGFtIOVNIygIAcM7FAawF8EcALgVwD4CPFLlfJcF0pBlzlbKxJzMU2B858CLT9rmFG2b0WExLSWaCEzm2EEKKx4kcW6YjzZjNlI1aluLUWwDRkYzxS1dHZ/S45ZSWslBWlssBXAPgFQAeAPAtANd67wdnqW+EkAqEsYUQUgwYW0glUOiJ+fsAfAPAu7z33bPUH0JI5cPYQggpBowtpOwpVGDopbPZkUqhkPxlOhKQjJdXkw9lh03b/GhtYDdHawI7LF15bGwksM9MVE25D5MlfH7M0kJywdhCCCkGjC3To5D8ZToSEC1RiaSzpi0TFy2LV8U+w9KVSEZ2ko0Wrypo+PxKIUvLDCShIYQQQgghhBwvHJgTQgghhBBSAnBgTgghhBBCSAlwzHSJZObIVzGzEKM+Hdh1Lh5qSwV2MtSm0bryckoBSQghhJC5I1/FzIIojXk2ap//Traip9aVl3oKyJmGT8wJIYQQQggpATgwJ4QQQgghpARw3vtje80xzrmDAAYBdM11XwC0Ye77caL34STv/bw5OjapIBhb2IcQjC1kRmBsYR9CTDq2lMXAHACccxu89+ezH+wDITNJqVzLpdAP9oGQmaNUruVS6Af7MHkoZSGEEEIIIaQE4MCcEEIIIYSQEqCcBuY3znUHJiiFfrAPhMwcpXItl0I/2AdCZo5SuZZLoR/swyQpG405IYQQQgghlUw5PTEnhBBCCCGkYuHAnBBCCCGEkBKgLAbmzrm1zrlNzrmtzrmp12ad3jFvcs4dcM49oda1OOfudM5tmfi/uch9WOKc+6Vz7mnn3JPOubfNdj+cc1XOuQecc49O9OEjE+uXOefWT/Th2865RLH6QEixYGxhbCGkGDC2MLZMl5IfmDvnogC+BGAdgFMBXOOcO3UWDn0zgLWhddcDuNt7vwrA3RPLxSQN4J3e+zUALgLwdxPnPpv9GAVwiff+LABnA1jrnLsIwL8A+OxEH3oAvKmIfSBkxmFsYWwhpBgwtjC2HA8lPzAHcAGArd77bd77MQDfAnBlsQ/qvf81gO7Q6isB3DJh3wLg1UXuw17v/cMTdj+ApwEsns1++HEGJhbjE/88gEsAfG82+kBIkWBsAWMLIUWAsQWMLdOlHAbmiwHsVMu7JtbNBe3e+73A+MUHYP5sHdg51wngHADrZ7sfzrmoc+4RAAcA3AngGQCHvffpCZe5/JsQMl0YW8DYQkgRYGwBY8t0mZOB+RS1Vy7HuhMqx6Nzrg7A9wG83XvfN9vH995nvPdnA+jA+JOANbncZrdXhBwNY8vUYGwhZHIwtkwNxpbpM+sD82lor3YBWKKWOwDsKV4PC7LfObcQACb+P1DsAzrn4hi/uL/uvf/BXPUDALz3hwH8CuO6sSbnXGyiaS7/JoQAYGyZKowthEwOxpapwdhyfMx6gSHn3PMBfNh7/7KJ5fcCgPf+43n8Y9FkTSpZ2wIAyMZse6IvHdjZRDSwfdT+YHVpdZ7q50gmnuuH7dFkqgs06o8waj/PZDIl+8hGctoAgGFZbmgaCuyRjJxwU3zYbFIfGQnsQ5m6wO4ZqDF+icO5u51J2HM/9aT23I5zxKbN+3KuHxnpQWpscHJ/OHLCMJ3YEkvUpJI1LRNr7L0bHckEto/mf4bhsrKdj4mfD2+SL9SGrmTvXM62bDTkF1oONsmEltVxw/EzXx90XyNp5ZaxJxFRcVX3O9w3l82zj9D3j+6rjuHmMwl1V+/Bhb/P1KLL6E7Y/R051sjIYYylGFuIZVrjlqqaVKIh97gl2a3GLUk1bonYSy8yls3ZlmrIf4k6GXIgG8o5Yu5DZYf7V107GthjGelfJmODmhtR8a5K33vKToUCYSS3W2zIuun+adJVdvn0RZU3bskXpotJLu3VhWEn59y1AK4FgGgsidNe8XYAwHCr/SMvvutQYA8tbQjsdK31SxyWGyFTJRfaYHuebzfARP/uM/J/gUBf4LX2W/HklXtlH8MyYO4fShq/yKP1gX3Jqx8K7C198wL7VQsfNdtcUrMpsG/ueUFgf+f+C4xf5//mvsL7O+JmecN/XpfTb6546eWfyLl+w/ovznJPSJkw5dgSiSZw1qVvG1+ftfd43ZbewE43hL4NFNFh+SZMNYtfutrGFv1F41Vs8TEbq7Ox3APckUYb0/SXs95ffCD0A2NM7OF5eb4XQqv14L7qkOyvqsfGt2S3evCQlP6la+25R0dlH/E+6VBkNG389KA9Uyujikwy9FmqAbgesERGbf8iY7IcHZDBho/b/WXqxuPxA4/8GwjJwdRjSzyJlX80/p06Ms/ek8u/2RXYgyska2AmaW/E2p0yWk3Xy/2w87L8Wf6q98s+BpfY7/7YgNyj8UFZP7TA+p1x3rNyrL7GwD58uNb4JbbKE8vRFfKg0KkBkttnY2e2Wh0rI31te9iee2Ig97jl0Gn23t3w4Xfk9JsrZmLcMhcD80lpr7z3NwK4EQBq2pf4kZbxCyptrwuMLpAnxQOL5HSqu+0fdaxJ2uLqD96y0T6F1k9VnA7yrsH49ZwmXY6Oyikleu1gd8fupYGdrlHbLB8wfq+7+leB/c1N5wX22Yt3B/bTg4vMNp+99RWBveLsXYEd77UXbvV2eUn7wMUy0A//JS56/afVeYQeuyl+/bP/l7fteHnRKz4Z2Mn+MdOmAxMhOZhybKlrWeKPPNmODodcx2TQGUnJfe3SNrbop+SxwzL4c6HHVdEBdT2rXYy12i8uX6eeoKlTqjpsjxsflrZ0ldijzfZjGFIxM9GvD6S6E7q16nfKscJP6jX6x0xG/RBJV9kfEclu+VyiQ+qRXugJdzYpcTo8GNeka6QtPiCD+9iAjRnZKvUVp44V/hvGugdzridkginHluqFS3xq4nlbJGU3H1sgD+IGFqlredDucniRDHyjI9I27+FQLBiS5eRBNZN+Zp3xG1DiGv3ju26HvV+f2bcisNNKLeBOtuOl0y7bHNgPP7wysM1ZxO05tf9OPfmvzj/L1rhBVCbb/kw6nui1fi9+uYwZqvbacZXm9t//Y96240UPxmODKdOWro2H3Y/JXLz8WUraK0JI5cDYQggpBowtZNaYi4H5gwBWTVRgSgD4IwA/noN+EEIqC8YWQkgxYGwhs8asS1m892nn3FsA3A4gCuAm7/2Ts90PQkhlwdhCCCkGjC1kNpkLjTm89z8H8PNJ+7v8GQj2Pl9eotSaqWzCTga0PC0aR61PjG3ebfz8kLxs4To7Arttg03DOf9/JdPPwB8sC+zhZttRk9FAaRy7vdV+3dzzB4FdvUM0Sb/fvDqwU/VWq9X6hOizDjwjWvZ4o3HD1jeKrrxpo6zP2PdPkeyRzuoXqsIvxR0vLzvzg3nbou0iiB0NaW9rHtwGAIgMj4KQXEw1trisD15MzIayFA2tag1s3RYbsO9fJHpE0wmVSSS+x4ohXb+8beUbRWMafnOiepv4ZZrlfshUW61iROmhx5rkZo6kbFiPGY253MtZlZEqPjS5bCthxhq19l6/JBp6qVP11aXyv7/i1IcRUe/7jNXbc9ffB/q4kd5B4xdRf4JsrYhlw9lb3OiELnSWs5SR8mFa45Y8moTdL5LvNqdulXStvdfi2+V6TCs9dtODe40fRuXdiswCiVvNm0aMW+tjcrCBk2z2No0et0RS0ofDh216ut/vF1159cGIstW7J6EXWqvUC+O+VenrQ+/43PrsZwL7D/7PDYE92hBO7JF7PBB+wft4WXty/nfrovN14hEbq6o2jWdpiYxY7Xkh8kpZnHNVzrl5OdbPd87lT1FACCEFYGwhhBQDxhZSCRTSmP8rgBfmWH85gM8WpzuEkBMAxhZCSDFgbCFlTyEpy8Xe+2vDK733X3fOva+IfToKHwFSE7Mu6brQlOsKSY8zdlCmZoY7jBuyMfmx3LJJpdRqa7L7GxK/wU6Znqh5NpSjR1H3pOQkjS9tzuv3yzuliu8LrrrBtA3Nkz/FqNpF+/MkWf2ujTaR/pjKY7zstc8E9mNPdBo/r3KKNm6T6ZSw3Ce5R+Q6o4vk3BOHbIokPaVz2+ZPYqq4MTul4xMy9RNTKRJHl9qpNlc7sdw7F+8skxmkhGKLC1INhouSjSxUci4VdhI19vqLqNzbiX2SjzB8nSMm93i6VfQl8b2hCmBKOhLpFWldZMBOzXqVWtDVyT3U8Ky9X1NKbpJS+cVTJvWsPfeYmgEfWCznm+i1fjotbd1mFSNjoc9ISUz0/R6WjkQPqCojLRKDovH8n7mZIs6G0h2mRTYT0bnPa0IpKiP55TqkrCiZ2AIHZJLj11yqMXRdNijZqLoFhjP2OswkRdu16NdKphUukNUg0tjhDrmxk135ZZ8NWyRWheVqGSXHuPvX7w/sS1/0z8Yv0afymLfI+l5RuBgpDABE0hK3hhbIcWv2Wr8XXC1jpIaNkvK5LiRR0bEltUg6Ed/bY/zWtv9tYN+2f+r1ClzaSvB8TEmiu2Qcml5qx5R+eCIe+8mnYi00wikUqTgyIoRMF8YWQkgxYGwhZU+hC/WAc+6C8Ern3PMAHCxelwghFQ5jCyGkGDC2kLKnkJTl3QC+45y7GcCRGvHnA/hTjOfwnDWcl3LWLjQbUH+rTOH0S3IUU60KAAaXyDRJ01b5UT203E471GyRKZPqXz0V2N2vOcP4Nf6PVLzqfZlUyWq961njl1nYFtiXvvRjgd1wwFaoahySueP9l4kOp//HCwO7ynYV/efJNjt6pXHhCht/en+1ILCjAzLtkzhgp3pGVsuxEvdL+ha3cL7x01la1q55b2Bna2yaF6+mn/Ub0tFEKLuEylaRaZCpqMYHbf0GPzgxzR2eriblRsnEFo0PPWtreE6mm4fmq4qU8VD2lnaZbo53K3nJSOi5h8oyEn10a2Cnzlxp3GIHRVKWWiAplqLrnzJ+0SVSCbi6W5X0DN1f8QNy7w2tkPvLZaR/unIoYOUruoxfOP7GhnS2Ffm8XFe/dVRT5U7Zvt9mUYGauo8MiCSnasxmeTEZF7QWIBrKxGCOpWLusM1WEVR5TefPGEPKgpKJLS4LxCaq8/qQFKt6m3xXDrerzCu19gYbWijLKZWZKB5KyqLvgdp75Lu7/7I1xq12p0jFBjtl7FT9vw8Yv3iTxJ11y98Z2ImM7V/bwzJe2v03Z8v+DqooJN80AAAgAElEQVT7PXRL9bxA7j2vYlC4UnKNKIThVCzwh62sOL2mU/zue1T85tl3gF1UjqXP6ShZW0JiuI4zkZiNLW5EZLfZbhlLVR3sNn6BlCUzA1IW7/0DAC7A+NTQGyf+OQAXeu/XT/oIhBCiYGwhhBQDxhZSCRTMY+69PwDgQ7PUF0LICQJjCyGkGDC2kHKHL0MQQgghhBBSAsxJ5c+pko0Bo63j+pyqLvtboqYrrWxZPxKqwNm3LPfL2smfPWiW3UlLZGGRpCds/J/7jd+d2e8G9trTJAtTavkC4xdJaQ2m0hiF0hNlu0SXNO9BSXfUv0q0XoMd9twb14s26vDJos8KJV9DncoO2b9SdGV1SfsZJXcobZSqeuoGhoyfr1JacqVtiwzZ1EwjS6Tv8QFV7SuU7iij06Ip7S1abOpJVzVxvo6/J8nM4B2QjY3fi5GQFjJxWG6cRK/Y6RobNtN1cj37iHqvoid0J8aVflppOLNKFwkAvlbu/8Soum9Wddr9DSrd5bDYLqQx1xVHq3dLW6Ze4sfAklCV3f0Sq7IqjWRs1KY009VDs2p/UVWJEIDVbg+pvkbz38s67mTbW2yj1pVrOxP6IyrNeRA/APih4ZDfRD+YNZHMENkoMNYwfm0m+uyFVbdHpRlVr1KFq1r2rUBuwu9CaP1zh4xBan5oteN3ZL4T2C87VyYV9r3lBcav/bdKx63u/0i/fTfDjUisWvRreTdmqENSHR9aY+Nly70yfhhtUfsOhYzoqHxGg6fL+28122ysiu0+JAtq/OaHQu+RqPdXdMxwoUriKZXKNjognTLjHgBOacYj86TaKkJpct2R7Q5OvhJpwRGOc26ec+5851xTIT9CCJkKjC2EkGLA2ELKnbwDc+fcXwJ4EsAXAGx0zr1q1npFCKlYGFsIIcWAsYVUAoWkLG8HcJr3/qBzbjmArwP48ex0y+KSGSQ6x1NdZXsbTFvykExDRB5SKf4uPdP49S2TKVyd7i+20EpPfJ2qNqnSf0WbraxCV5FCo8hDwhKV4QWStzE2JNNP0cFQ6p1qNc367O7Abth9ILDrdiw222RVCqb4oPQ7G5oxGZNZc6RU1cLYzi7jl5mfu2ppJDwlpKZ0hpfJNgOL7BR66yMytdV1rvzdWr9yn92/mrrXnwOOqsbnzH+kbCmZ2OKjUkG3qidUhXJQTXGqezK6YonxyyZNCU0hGZr6TCRyukXbWu0KPRWatmkCNbqCZrZTpnqjew5ZR1VxFFt3BGZ8gaRBbdpvb6r0fLlfdVXMsSZ7DpE88jwfTi2mF7R8JSx5Udtl5skDz8iI9fNaoqL3Ea7Op2KXkfiE5T5HPiPK5MqdkoktLplFZNm4jCz7ZJ1pS3bLPV61QeSb/ZecYvz6Vsj1ONok93FVqx0HDS+WGPTrn0hl7nUnvcP4rVt2XWCnOyWVc90ee9/0nVwf2Ik+abMiEsBVK3neMxIja5+S2Fn31EKzjU53PLxS+pDcbyWzOp1jVbdKTfjMdtuHUyTdrFP7zu47YPwiapw2ulSkcQOLbUxr3SDjov414ld/19P2PFpl7KNjsW+uR056Jq8cLxSFxrz3BwHAe78NQLKALyGETBbGFkJIMWBsIWVPoSF8h3PuX/Mte+//vnjdIoRUMIwthJBiwNhCyp5jVf7UPJTTazbwDpmJClFx+8IrhttlcqXulOWBXXX3Y8Zv00//J7DXnv5+2XW9nYbWb+j6Pqle50Jv5GZVW0RVjrrr3vcbv3P/+jOyj7RMv857dLs9kXkyZaIr3mXUdEykx1YLHevUVfxkfcTOyJs3wHWFPz9iJSo6q4obUZ9Do52G0yS7lV/UToe7zdsDuw2dsr429Jkr+YqrVVKicKWsAhkcSFlRMrHFO7knvLM3TqZW7vl4i8gq/K79xq96i5JLqGxGaGk0ftCxpVfFlmbrp+OOH1MyjbBMbrnc/8lDqpreoJ0Sdg15plaVBEQfEwAi9XIfZupUZdMBK62JDmnZjcpAFbp3fbdkqAmfr/FTU8IupYJayh43Mhr6IpggG86EoyuBKlmQS4ZkRfEjUhbq5MqckoktkUgWtdXj9/ww7Hfo8Hy5zhMrRRpX/4uNxu+33/uvwH7hlZ8K7IHl9p5O9Mq1/bIzPxjYfoGVp0a7RF4a3y33yt2//KTxW/P+zwb2vMfkPowM2gwmWlKmpaeRVpVFqc+OW7Jt0qe4znbVaMdYtTslm1Q2kT+jia4cbqorz2szfjpjVqJbVRWusfv2z4kkp77bVhk1qDESmuTv4cJVihNTT36Ydwvv/S1T3hshhBwDxhZCSDFgbCGVQN6BuXOu4AsT3nu+7UwImTKMLYSQYsDYQiqBQs/Ynw9gJ4BvAlgP5sIghMwMjC2EkGLA2ELKnkID8wUALgdwDYDXA/gZgG9675+cjY5pfDqCVNd42sHMmVY/Gfu9nEK2WnRb0U6b0iwvobReWneZWSnpCWPPhVLvtImGyiu94otfbrVadSosVP1CdO9bP3yu8Vv56c2yP7U+qlPyRG1fs0nRTNXvEr1TYmeP8RtRWvRsQqVfOnuZ8UvuFM2Z0am2Wp3a2EJJ1bTjZaILW/ZemwbRqTRwbsfewM4MDhq/aFxdhjpVXCil2a3Pjuv1nfvs3L3vQGaCkoktLgvEhsfvuN7l9h2GpsdFh5hV76JEQvdhpkvSE0Z96AUPha+V1KlOVwgNpQVNr5bYFeuWeyXdYJOV6WqkkcPiN/z8k41f9fotclyd1kvdaxH9bgcA9Mr+IoPqXZRQvNT6Sa0JPypdYr3S2OqUhuEKyI3SD6+aoqGKnv6gVCl24b5rP6XRN1VG4za2ZCZSnPn9fI+lzCmZ2JLNRjA4PP79uPDiPabNrRf9s7n/54VSp+YhkrJxZnChXM+j6h2OeL+9b0ZWSerCRL/osc+99jPGr1p1yat7VFfFBIChhfL936QqEWda5H6P7LBjJ6feF4nvEM17+P0Qt1hSWeu70i3tMH66krBX47dwXMg2SPzdsU7GMEv+eb3dn9rOq4rDbm8oDa3u04iuEGrfX7n94Y+M+7h/nPS4JW8U8t5nvPe3ee//DMBFALYC+JVz7q2T3TkhhIRhbCGEFAPGFlIJFHxd1DmXBPAKjP/67ATwrwB+UPxuEUIqGcYWQkgxYGwh5U6hlz9vAXA6gFsBfMR7/8Ss9eooPHx0fOomuq3atOx6qdirvipTIQdeNM/4XXHehwM7qtKWZVpt2qH9L5Uppnm/t5IL0yMlvxhcLdNP0WE7dXTPHdcHtpa5LP9On/Ebep6keoyOyRRT4n6VPklNqwBAzSapUOX3qumiTjvVkzis0iCqlGZjrfazhEppptM3ulDlz+SzBwM73i/T7pFQGkSvpphcjaqAusT2L71zV2Df2f1fIJVNScUWB2Tj41O1Dc/ZFH/d58g90LRZYsFR980iSaUY2yUSi3C6z0y7qmSp5BzZeitRie+V+zDVLtPS0WGbIlCnJ9WV7Kr22biVXaHuNyWhiWzfpw5qpR26al6kXcXSfrtvI43RKWVDkh6TcvWgktqFUrFGBiTWZOtUNeS4lcZEdFVVNX0dCaWGNDGoUaavs6HqfJmGienno6oNk3KilGKLcx6x2Ph9/ty2+bbxNWKu+bTcU1v/ot24nfJBlbZQ3VLZRCh1apvc17X7JO70Lw1JtpKy3fr/eWdgh6UsD/+HVAg9/V3Sh0zSDhmru6RT+y5fFNjt98rYJLPMVlePHVRjHx2PGm01U+hqvykV+0Kpq3XaZ1elYkY4Baxa3vjAVwJ77b//rfFzqvp7RsUd32H/hpFdEiNve+YGzCSFnpj/CYBBACcD+HsnOiMHwHvvG/JtSAghBWBsIYQUA8YWUvYU0phHvPf1E/8a1L/6yVzczrmbnHMHnHNPqHUtzrk7nXNbJv5vLrQPQkjlwdhCCCkGjC2kEnA+TxYB59wl3vtfTNjLvPfPqrbXeu8Laraccy8CMADga9770yfWfRJAt/f+E8656wE0e+/fc6xOJpcu8Yve9XYAQLbOVlVqni/TEytbZPqk7612+qT7TLkn592+Le+xMgtFyjI6X6asa7Z0Gb/0tu2BHV29UtaH3loebZVpF69+Bo022KnZ+LCaflosbdWHZH3DM8Nmm6HFqurps6q6Vqhgpq7o2XeGyG5q9liJymiL9LVmu0w3haeRD58m08DNTyi/JzYbvzvGvhnYL3qlyHgSPWPG767ffABTwTn3kPf+/CltREqGUootNfOX+FVXj0/bpsMFblVoTNXLwsLf2RjkstJW/aTNvqBJ75a2yJmnyGFCWV50FhSnq3P22Cp0qXNWBPZYvUxZh6tzRlISEEbaJGNA8rBMD+sqgADgayQWOF0ReNhW/jsqq9WR7etsRgQthzMZWyL22VBWHTfao6aiR23M8A3yx0q3SMwNy33S9WraW8ffZjvFf6Ry8iP3fB79h3dRz1KmlFJsSS5f7Ds+Ni6TaGqw2eTm1cr39ZsW/yawP3jLG4zfSLtI3pbeHvpiV1TvlHtlcLmMdYZb7P2ZrpFLu2a/7DvZayW4B8+UODGwSt1T3t4aNc+J6CJzjvQhsV7GCLV7bb+zSoKns8kln+s2fiYzXKOqrBmKQToLihtQ24Sq+x5+nmSkafz9gbx+tz3+0cB+4auk2mo4rv7iF+/FVJjKuKVQbigtmvl+qO2YIynv/a8BdIdWXwngSGWuWwC8+lj7IYRUHIwthJBiwNhCyp5CA3OXx861PFnavfd7AWDi//nH8CeEVB6MLYSQYsDYQsqeQgNzn8fOtTzjOOeudc5tcM5tyAzkz45CCCk7Sia2pIcZWwipIEomtmT7GVvI9CiUlWW5c+7HGP+VecTGxPKy/JsVZL9zbqH3fq9zbiGAA/kcvfc3ArgRAJKdHf6Itjxem8q3CTZ1yQ/Z4avtex7pGrkn+08SbWbnj622cmCFaBfrtqsbK6RxjJ62WhZUJavY0zuMX/drRUs6PF9+sFcfsDFioEO0YM1bRO/VdbVopgYetim+mraKX7RLtN6Z+U3GT+s2Gx6X6lWu16YTGlrUKQsxVZnw97ZoWvNm0XS6DtFtuXrbv7Wnv18Wlknat4GloXRz5ESjZGJL9YIlPjPxqkY2FA0jSlKY7JZ79+BZVp/cuE3uw9EXSPrQxjs3Gr9Yh1QS9rpKZugdDq3v1mT6bIrVVK10OF0j92uqzmomx2ql71W9ovfsWSXvqLQNhlKdqvsfNbK/WChu6djnR5T2M1S111T41O81HbDV9KK6Wl9a/QFioT+OqgSqdeWj8622Xevr0zXyOTsrqUVscGJFfhkvKQ9KJrbUrlroj2jLaxN2/NCSlO/1jz798sBOnzFg/NobZQyyo0G+10/6pn3475PqflO3V7oqVFVY3R5j9XKPN92/2/glVOX0uvnSh8E+m9q1/oWi+nlg7ccD+4zEP0h3vttotomqqqVjjXJfj5xjU0XW7pTPKHZA3q/JdtvK5li5NDB1Bc70czuNW6OqTOpUFWakrP7/xev+JbDjoxIQhueFYloRKTQwv1LZ4SSN003a+GMAfwbgExP//2ia+yGElC+MLYSQYsDYQsqeQgPzP/fev3G6O3bOfRPASwC0Oed2AfgQxi/s7zjn3gRgB4Crprt/QkjZwthCCCkGjC2k7Ck0MD/zeHbsvb8mT9OlU93XGW0LsOEvcmcnOudnIpeoq1IVPVfbad/XLBM5xiPdUgnv4O4lxq/9LqlCmVos1fSyJ9lKotHHJeXiwdedLtvfaaesEoMybTOalmmlsUY7xRS7UKZnDqgpq/RBmXsK/7H0NNVYp6R5jAyH0qWpqWOnpp7D1f4aHpEZurEOSdWaaGs1fmiVNl+lKv+ttBU9I30yddS9WvyqDhVd6kdKm5KJLS4DJPrGr8dIKBfD0AK5v/pOlvumYYu9Ew+cJ1PCmXqZ+qzuWmH84g9sCmz9ck/E2ViQVdPSQ6qqcG3IL6aqDI+otGipGuuXqpPlTDJ3esOhDisBiQ3JeVTtFslbptlKXiL9KrWjijO+O5R+UUtRVHrJsOTF10s/TBrJ0NtQbrfEqqFTJDZH0iGJ4CKR4Yw2K3leaH/ejfcv/TgzJZY5JRNb1jQuxoaX/3POttf+9s2B/Rcr7wvse3tWGr/rFt0R2H1KevbWXX9p/Op2yn1Uc1DFoENWm3VooVzfg6fLeKl2/0Ljd6QaMgAM7BV5b9U8m7I5GpH9n3/r+2TfQxInhk+z91R0VJbrdoidGLB9HW2T842MiFwtkrLjGxyQsVNWVffUKWkBYLRVYktEV2XO2JhR85RURN55lchkdEXVYlNoYF7jnDsHed5k9t4/XJwuEUIqHMYWQkgxYGwhZU+hgfliAJ9G7gvcA7ikKD0ihFQ6jC2EkGLA2ELKnkID863ee17EhJCZhrGFEFIMGFtI2VNoYF4WRNTv4oERSTP2/MXbjd+nzvpuYJ/8vX8M7LEzrb6o/S6xo32iwRpcadMvDildeURlcNzxOqtZH1gmeiin0gShIVTWu1/0VM++57rAXvltKQ+LnVbf2fJgV2CPdkhKomy9TZeW3Kn0nirNGKIhoaXSdCb2K11pl01pFtMpzbpEmLv39VbTVb9L/Jq2yfkeXl72lx2pEKIpj7o949fmwEJ7Xabq5X6t2SVtQwtszIivUPfKHrlHD55pU4st/r3av9Jjj82vM36ZKrkPvZJZ955p3/VIV8v9m1aHSoc05lkVDpySSep0kD5it0kcFC1pplZ2EBkL5RmMyzn5RjkPrTcHAD+itOh1Ko5FbAzKqhjkduyR9StsXMWSBdLXw/Jez8AS+5lrXblTWlKtoQWA4XnjbX72MqKRE5gFVRIzbj1wWmCvadhn/Pqycj33ZyXF3zkv3WT8tnxN0jePqjSIh86292G2QQ1WRuVee+4PQzrwAdmuuUNSFS6otymWY0pj/tMXfkH6p97966m36V9bnpJjjTbq9z5sLNDxbWievNfWuN2mW44fkBST2ZMkZXam2sZznZqxfqOMWwZXNhu/dJ3o7Vs2yeel35MrNoUKDOV+25IQQo4PxhZCSDFgbCFlT96Buff+jnxthBAyXRhbCCHFgLGFVAJlrykYS8t0jE6XeO9zy41f5wapLfDmF/9O/NpXGb+fPivTMSv/5TOBnUmGpmaTMoXjq2V6N1Fr0yXGnpVp28wCaUvUWL9kQuaVO78ofa3pkPVDi+008v6XSJqwpq2yv0xV/okQ3yPTUlg437Q5VblPVw/tf91Fxm9wgexfp2NqfNbKc3qXyeX12OffkbdPhMwVkbEsqveMV7aL99sp11SDTJmOKSVbbNBO+9b9VCrejlwi91D/cus3eLGabtZTuNFQdT5dlK42f/q+5GElzYiJXzY04+p10U0ljfEqnIw02ZgRaxcZWvKgVMbLJmy6xeioTPW6HpWiNmnldKY/qure0Em2KmBsRHVqnqSOix+01fkyjTLFP7RI7IEOex76fPUHkeyx8bxxQu23dwSEFJ1tAyJLa0jIRffMgE3L/IF9rw7sB84ROe6piZ8av9O+/B+BffGd/y+wz6u1aaOXVEtqwS0DqlJ62gaNrgEZt5zXLimkB9P2vs6qd2xff/9fBXZvnyqy2mirtR9WaR/rdsh9mEmG5DRK+hsbFXuo3cbpKiXJHZ4v59EfigUpVZi8d5kaO22z4xZ9Tvf+6N2YCwpJWQghhBBCCCGzRN6BuXOuzTn3Iefc3zvn6pxzX3bOPeGc+5FzbmW+7QghpBCMLYSQYsDYQiqBQlKWbwDYAGAVgAcAfBXA5wG8EMB/Ybxs7Zzz+Kskw4rJtjJkp1yal8oUzv/uOiuwX93x6KSOo6tVAQAWydTqJ8/7QWDf8MwVxq13tUyTeDWVms3a/Q2orCyRsdx+0cHQ1Iya5u7tlPNN9ttp2r4zpCpoVFUSrHtsr/HLNklWha6zxW57ZMD4NT0hspm+NSJ5GQ1Nh1O+QvJQOrElm4UbGM9A0neGlVXoCrW6embEzszisEpGFNulplmXWfmFU+lRdNXeqFW1mWMNdohULNETlmmoGKLDSahAnd5/oldVIm5SVfdssgWMNIsGJDoq5xQbsCefblLV9GpU9pZ+qwlxKuPC0BLRBdVuOmiP2ynxySt5zugim7lGk1XfYpHQZzm0UM5Xfw7ZhI2/R6SKGTtLTsqP0oktBbjtxZ8P7Ffd+5bA7k/ZC/CyRZJ95XM9nYH99ubtkzrOvkGbTW5RtUhZP9v5vcD+t64XGb/DKvNaWpXJjTg7thjLSJx4ZO/iwG5pkjHDwf02rqZUdeTRFpU1KRS3RlTmJKfGTrV7raT38CqJO0OqsmnzRrvDMRVXdeX1cJa4J26Y+3FLoYF5u/f+fc45B+A57/2nJtZvdM793Sz0jRBSmTC2EEKKAWMLKXsKacwzAOC99wC6Qm3Zo90JIWRSMLYQQooBYwspewo9MV/unPsxxidJj9iYWF6WfzNCCCkIYwshpBgwtpCyp9DA/Epl3xBqCy+XBJv/7z/M2rHmNQ3kXH/N0gfN8u5RqSr1UPfSwO4dtRXqBqPyY351507ZZktnYLt6+4PfH1KVOlWlLh+aB+k7SfzGGlV6opcsNn7Lvy/V/up2iTZ+tNX29Z718jmvPeMDgX3b4x8FIZOgZGKLj0WRaRnXLzc+YzXhB8+RlGFauzy4MiQyz4hesWGBiLX7e22FupEWuQ91Nc5sKLNgSsmpsyot66gt/In0sBw3NqLeS4laHWiiV9pG2nTuRH1Mq7mOpKUxrSqRZuM2uDjtVy+pygZPtdrW5o0SL5NdEmfSbfXGL6Oq/UVG5dxHWm06N/1+zWiz2P2rbOozqM8iOyjnEbdZ5CStYv7slKQ8KJnYMll+/MIvztqx2uK5xy2XND5lljeNLArsLhWQRrN2yLipvz2wT26X90X6x0QrX7/0gNlmm1fVOQ9J8AtrzL0OnypW9T/PvkjS/GsZnyRUkfPhNhurHv1X0Y6fe62kwn74xutQauQdmHvv7zliO+fmTaw7mM+fEEImA2MLIaQYMLaQSqBQukQ3kXaoC8BGAJudcwedc7P3WJoQUnEwthBCigFjC6kECklZ3g7gYgDP894/CwDOueUAvuyce4f3/rOz0cG5ZOt7JjvF8S+Bdf2j/8e07BqRdILNVTJVnozZKdfRpPwpHtnZEdh/e8EvA/vff29TGn3ub74W2H/1878M7HBaxTop3IV0jczV1uy187Z9y2XuKNEv80rZuPU75UPypx99bw0ImSIlE1vSNREceN64nKK6y86luqySaYiqBZGqUKW4QZFZLKhXUpadVs5R1S1pvkYbZZuRkERldL6qJNwt8gtvi26atI3ZuK6gZ6UsKZ1yVWUxTNcrPxeKBSvEbtwssSkRSsWaGFCfmWqqPmQ/o6FFEluqDkp11HAl0bF6WR7ulM9IS2sAWyVwaJH0oX6BzfuoU9SmGpWkL2LjVrwvctQ5kLKkZGLLXPGbyz855W1+9NTLzPKQ0tdp+Ut7vNf4LUjK8h37Tw3sNU37A/u+PZ1mm3c9//bA/kzissD2PVbT17hR7led9jS23UprdaxKHlINIVla55dEydT66h6UMoWysvwpgGuOXNwA4L3fBuANE22EEDIdGFsIIcWAsYWUPYUG5nHvfTjd0BG9VjyHPyGETAbGFkJIMWBsIWVPISnL2DTbTmg+cdb387b94b1vDeylNXYq5TUtGwL7S/FLAvvRviWB/cylXzXbRBZsCeztqnTCux+9yvh9Z/0Fgd30hPzJk73507qmVXaEw6vs77fR1ZJVITsi002dX7YvvW9/87vy7p+c0JRMbPENGaQuHZ+OPdxrp0irt0pmgcX3iPxicLOtzte/RO6PLaMiQ6vqsvfNWIPMrVb1yL3noyE/lWVkbL5IQlwilJVpSFXnVBlH4O0c7uhC0bwkDsr9r6Uxw6cP602QHZXG/mVKUjJm9123U/xqDmj5Gyxqs1SDTFmn6uy560wKkZTKqBKS0+kMDvo8fOjcG6pFu1NVL5/l9jH71ZdyiaP2RcqSkokt5cS7Tr09b9t/b7kosJuig6btD2tFJ/tQ70mBPZqR++urZ95itjn3pB2B/VZVNflND77R+N2VOE2O+5jsb3Bpfr2Zrtw7uNRWCG1dJmOu/iFx7PzaJ4zf9j+9Pu/+Z4tCA/OznHN9OdY7AFU51hNCyGRgbCGEFAPGFlL2FEqXyGcHhJAZh7GFEFIMGFtIJVBIY04IIYQQQgiZJQpJWcgM89MXfiGw73z2FNN23+CqwD63SSp/Lkvmr42Q3SfbvGf/2Xn9rr7wgcD+1LXfnVxnFcu+8TF7XKUrd6N8QEHKl3g0g8WN4xrznqSVoB70jYHdNSCaxIwt6ImhJaJdjjeLFn0kZmfO97eo6px1on90oeOeunRvYM+rklRlz/bZvIr7e6VqZrZV9p1Ohe7JfhF8j7Uo3WVMtJrJhE1vOJaWZzaZGqUdj4VTrMry8Hw57mhrKPVkSvzig2K7cKFO+fgQUccKa9Z1BePG5aIdvXzJJuN3TdP6wD47KX/DS/Eq47d3Y0fO/hByovMnq+4P7J49HabthwOiK1/b+kRgH87kT6P88HNSAf1LBy7J63fZOU8G9leuvXlSfdWc9/P3m2WtKx8bSoTdSwo+MSeEEEIIIaQE4MCcEEIIIYSQEsB5X/qlzpxzBwEMAjgqP+kc0Ia578eJ3oeTvPfz5ujYpIJgbGEfQjC2kBmBsYV9CDHp2FIWA3MAcM5t8N6fz36wD4TMJKVyLZdCP9gHQmaOUrmWS6Ef7MPkoZSFEEIIIYSQEoADc0IIIYQQQkqAchqY3zjXHZigFPrBPhAyc5TKtVwK/WAfCJk5SuVaLoV+sA+TpGw05oQQQgghhFQy5fTEnBBCCCGEkIqFA3NCCCGEEEJKgLIYmDvn1jrnNjnntjrnrnQYuhgAACAASURBVJ+lY97knDvgnHtCrWtxzt3pnNsy8X9zkfuwxDn3S+fc0865J51zb5vtfjjnqpxzDzjnHp3ow0cm1i9zzq2f6MO3nXOlXeOWkBwwtjC2EFIMGFsYW6ZLyQ/MnXNRAF8CsA7AqQCucc6dOguHvhnA2tC66wHc7b1fBeDuieVikgbwTu/9GgAXAfi7iXOfzX6MArjEe38WgLMBrHXOXQTgXwB8dqIPPQDeVMQ+EDLjMLYwthBSDBhbGFuOh5IfmAO4AMBW7/027/0YgG8BuLLYB/Xe/xpAd2j1lQBumbBvAfDqIvdhr/f+4Qm7H8DTABbPZj/8OAMTi/GJfx7AJQC+Nxt9IKRIMLaAsYWQIsDYAsaW6TInA/MpTvEsBrBTLe+aWDcXtHvv9wLjFx+A+bN1YOdcJ4BzAKyf7X4456LOuUcAHABwJ4BnABz23qcnXObyb0JIAGPL1GFsIeTYMLZMHcaW6THrA/NpTPG4HOtOqByPzrk6AN8H8Hbvfd9sH997n/Henw2gA+NPAtbkcpvdXhFiYWyZOowthBwbxpapw9gyfWY9j7lz7vkAPuy9f9nE8nsBwHv/8Xz+8Wj176rjjQCA0eaYaT99UXtgb964N7B91N4X2Xiu+wRIV+fva6JPPpvI4Gh+R0WqucosL17QJW1e+r5vpN74JZ9LB/ayUw8Hdn82HtjNSXtdbX5omyyo0xtbUGv84oO5/8aRoTGzvOqspTn95ootj+3MuX4404exzHDuPyg5YZlWbEHid1WozdVMTkBGMIgxP8rYQgzHO24ZWRA17We0LgjszU/vkYaofVaaVeMYr5pcayp/Z7tkzBDpGQx3LOcm6bYas7xm4YHAHlZjxG1DbcYvsU3GRfVrMuowss2CqlVmGzNuUWTabByOjmRz+mFw2CyefO7y3H5zxJZHnsu5fjjbj7HsyKRiS+zYLjNOrimeCwv4P1gdb8TzV/wFAGD7a+yFseGf3hHYl1380cBO18WN32C7XT5C1zn5f5gsvV0Gy9XrtxToonDgtfZH9Effc1Ng707JS8iffvIy49f55v2B/fWf/yiwfzEsN/BVKzeYbS6PXBXYLiZ/yueuvcD4tT+Y+yau2bDdLN+24d9y+s0V65a+Pef63+375iz3hJQJU44tVajFhe7S4vaKlA3r/d1z3QVSmkxv3NL5RgDAxvc1mMYNf/LewL7igo8EdrreJgkZbZZxSzopY7r4G/cjH9kbRSFS+0M7ZnBR9QMhIvvbf/V5xu/+938xsB8fk/HD6x+y70ou/WMZF1387d7ATkZkm/ecepvZ5vLo1Tn73X3lRWa56ZmRnH7R3z5ulu/YUFrjgbUtf5lz/X19P8q5PhdzMTCf1BSPc+5aANcCwFhmqNh9IoSUP1OOLSlMbiaMEHJCM/VxS5rjFjI95mJgvgvAErXcAWBP2Ml7fyOAGwGgvqnDD3WOTwltVE/IAeAFV90Q2A298gsr2me/cIfmN+XsTNvv7f1W3a2ekm+Tl5tdrZ1m8YNqisjJHNP8H2wyfu+pkV+YI/PkPv6TV/3S+H3g0Y2BfcZ6+cX19XPkifsVyT8226TvEunJuztvD+yPv+Nc43foNPnVveSW/E/+1y16iyzE8l8at+74XN62GSU0rYdMnqktQsaZcmxpcC0lqTEkhJQUU44tdS1LfO9Z4zP82//kncbv4td+KrDrDstYItFrB/O9nSLVjY5JqOq9baHxq90r343ND+yS/jTaJ/XZATmWU7KWBTc9bPzOTcpYYLhdjvu+V3/f+L3xWZG8LL/zLwL7BatErhJ+Qr75388P7EitjLdWfNlKVA6cJ/KaBf/2gDRErSxobZN6ip/IrYwAgNsO/Hvethkl1D9kMrn9CjAXWVkeBLBqItF7AsAfAfjxHPSDEFJZMLYQQooBYwuZNWb9ibn3Pu2cewuA2wFEAdzkvX9ytvtBCKksGFsIIcWAsYXMJnkH5s65eQDmee+fCq0/DcAB7/3B6R7Ue/9zAD+f7vaEkPKFsYUQUgwYW0glUOiJ+RcAfDnH+g4A7wfw+qL0KAeRsSyqd48Xcbro9Z82bVElOx6bLzrwdLXV+Tjl55WsvO03u+3BlO7Kx2Qf6cWtxm14YUdg1+wS3VZ0d5fx6/j2M4G95W2S1ud3L7YasRUffIkct0XeaL7+vJcHdqTWapWS14gm61/9xYFd67cav9rfiEZsVKUWSj62w/gdpY0qEuuWXZe/UenIw1r2dSveNW7kSflEyoaSiS2EkIqiZGJLdDiNxid7AAAX/rEdt2gldGqhvP+WqrdDMj1u0SmfF3/Dfse7iFIlK5312FnLjN+h0yWdc+sT8k5e/CH77tnirzwR2NveeXpgfyu0v3/6+GsDO7JA9nfoMknFHKm2OalPuU79ZtLpukPf64/de3NgX/E7yVzjngqlW8w3bpnhVOBr2/82f2NWxma3HfyP3NtNYdxSSGN+hvf+nvBK7/3tAM6c9BEIIcTC2EIIKQaMLaTsKTQwz/96a+E2QggpBGMLIaQYMLaQsqeQlGWLc+7lE7qqAOfcOgC5SzcViXR1FIdPG0+XuP8KWyzn5C/I9InLyNTFgXNsesT4gLTV75YUPb46afzc0IhqkymYyFj+lDcupdrioXs/K3NRW98jEo7LfvJR47byO5ImKbpV5DV+WPrT/4MFZpvdz4m85ntXfCmw/2nHK41fIirn614n1VERC00B6WWdmjA0BaOlKLc++xnMJL5GptrWLXmbaRs+bREAINs1F1k+yQxSMrGFEFJRlExsSdfE0H3OeFHBgdf2m7alH0zn2gR7X2Als/EBsZu3iDzEhcYZfkSNW+ZLIcPYgK3uDcj3a6xXUkq7KluxHGnp3+YPSorqK/73w8Zt1X/LebmnRbbr1fa9PznJbLNPjVsuPEMkOQ/vWGL8Or8kqbBPeUZJjpN2zGZSOytJCSKhtIoL/y6wb9v7Jcwkrk5k1GtbrzVt6VPG01r7Ryf/u7DQCOcdAH7qnLsawEMT684H8HwAfzjpIxBCiIWxhRBSDBhbSNmTV8rivd8M4AwA9wDonPh3D4AzJ9oIIWTKMLYQQooBYwupBJyf4TdXi0FD7SJ/0anj0wN9q+pNW3RUSVQ2Hw7sgVWNxq+/QyYHmjfL9E5swEpjIsMyBRM9LPNI2UZb+TPSK5lYdPYWN2b3h7SaWtGSkHBVS50NRslXDKEKUn50LGfbmx99xPi97c43BPapH1NTQoUqa2pZS+gayTbL36B3tVQWqzpkzz2akv15dX7xw/b8Iupz1n0YPN1mrkn0je//gUf+DX39u5mahRw3Da7FX+gunetukBJhvb8bfb6bsYUcN43VC/3zV45Xpew6v8W0pVWikgV37w/s/tPnGb/DK+R7eP7DIj1J7u61B1Pf/25AZLFZJWsBgEi3ktTo8UjKfnd7PRbwYrsCFcGzh3vzthm/kdzjG13JHAD23CuZ75Z9USqjH1WVXMlmClUsR5OMVfpPEzlN1UEr93FpOd+IkilH+mxlUvT0yTZqvDR2sh23xA6Nb3f/1q+gd2jPpGLLXFT+JIQQQgghhITgwJwQQgghhJASoGB6C+fcOQBWAHjSe//07HSJEFLpMLYQQooBYwspd/IOzJ1z/wDgDRh/s/mTzrmPe+//c9Z6pjh5zSLc8eCHAQAvvfwTps1HRbIzsli0z5GU1UVHxnJr6aMDo2a5X2nT63bIhMLQIlu96jc/lEpULzv7g6pD9jhGUJTNX+VKL7tEIrAz7ZL2cff7s2aTwd1yvqd8QDRYH9vycuOXbBNt1Na/ER3X0tut1iuxXVUr1hqzkBY9mxA9VWxUacIXJoxf2y+eC+zhNaK7OnSW1f/Pu1u0aWPL5gd21UGr6QqOW/qvRZAClFJsIYRUDqUUW1adthi3bRhPi/yiV3zStPmYfN8PntIW2JF0aNySO6uiScMMAEjKd6+Py7BudEGdcfvVI/8U2GtPf39gp1rtO3SJHaqCuX5PLnxchU4ZiHY5p+0fsWkChw/JWGr13z8W2M/tt6kifbMc65nrVgd2508GjZ9OL23GWBE7xvJV0o/4gJxT/0k2/WLLT+W3XPrUzsAeOLPN+DX8skf23SBjmiOa8qCtevy4fgqVPws9MX8dgLO990POuVYAtwHglych5HhhbCGEFAPGFlL2FNKYj3jvhwDAe3/oGL6EEDJZGFsIIcWAsYWUPXnTJTrnDgP49ZFFAC9Uy/Dev6rovZugoW6xv+CsNwMA0vV2WiRVJ7KK337vXYF9zt/kr0ipK38mD1kpS/SQpO5zSs6RabVpGrMxud+jg6qC1nAo9Y7ah1dTK3r9UeRLYRnaZudVIkvp+LpU0DLTOYBJd4SofF5d61YYt6z6aNtv3SEL4Qqhqn+7XiPVujq+9YxxO7h2eWC33SptPZcsN37VByVVU9VelToxnbva6n3bb0bv8F6mNCtTSiq2MF0iUTBdYnlTUrGldpG/6JTxNM9j86wUdqRFxAr3f+OdgX3GdZ/Nu7+mZ2TcUruxy7TpNM26GvfaMz5g/Lwat5iK5SmrmXH6u1engC4gZfH52kJpnve/9uTAbv/Wk9IQlp6o8Y5Tctq+S08xfkPzpW3BdzZJQzh1ourH7jeINGbRVx43bgevPj2w531LpDZjF9njJneIlAVKPpStsZLeI9z/5H+gb3By6RILSVmuDC3fkNOLEEKmBmMLIaQYMLaQsifvwNx7f89sdoQQcmLA2EIIKQaMLaQSKJSV5bF8bQDgvT9z5ruTm1R9BLtfMv7GbyJUXGpMJfi44E8/Hdi//9o7MRnWrn6PWTYSEzU1Exm0kpexRSJtie+TiqO3PmN/oK9b+W61c5fbBpCtq5Jj6epcagqn/9xFZhuvFCab3y3ykNU3PGv80p2SEeWZq2oCu/1+O/WUrlJyPN2/kISm6yUiX6nqFlnL9j+30ph5j8gUmK4Ylui3+0scVp+tnkILTW0dJdEhZUkpxRZCSOVQSrFlrCmK7a8ZrzaZ7LHfZSOt8l12/p+L9OTxr143qX2vWx4a36jv6HWL3hLYrspmHPFNkqXFdctg6tY9X7T7X/I2WdASlZDM1tfJeAKHpRKmlsyOnXGS2cap3e36S5GNdNz0pPVbKuOdna+QjC1NW6w0JtmbZ1yQtvKcnitEQpNQ2zz7rjOMX9tjqoqq+vyiQ6EUOUrim60WHbCuHApY+dBkKSRlyWI8Md03APwEwHABX0IImSyMLYSQYsDYQsqevEN57/3ZAK4BUIfxi/yfAZwGYLf3/rl82xFCSCEYWwghxYCxhVQCBZ+xe+83eu8/5L0/F+O/Pr8G4B2z0jNCSMXC2EIIKQaMLaTcyZsuEQCcc4sB/BGA1wDoAfAdAD/03g/k3agIVK1Y7Ds+Np4usbbGar0jP28O7JoDou2p2WtnsO783QcxGcKa8yNkG2vMcrRL9FRZpduK9NqqVFarLdqlzDxb/bLrHNGst9+2M7CHV7cHdvXGfXbfan+37v5CYIdTRdbvVGmWHpMqWTte32n8Wp8UTXjtk+pYIW231pg/eIto4v7g/1p9fSYh5548rM49afV2ycNy3FiP/N3cqNV03fb0x8fXO/eQ9/58kLKlVGIL0yUSDdMllj8lE1tWt/sL//31AID2mj7T9uTNpwV2zUEZt1TvtdW47/qtTXeYD6M5V2M6H9KYu4EhaatWbf2hcYveJqIqoJ/ZYdpiI/K9Ht8oY4vsonmBHdl1wO5Qab9vO3RjYL/gajt+qNkjn0Vs867APnDlycaveav4xZ9UaZ5DY9veS1YF9n3fltTa4XGLU+Od2m3yd8vU2s8yMibnoVNP+rhNL32kav1Uxi2FXv68B0A9xi/qNwLonmhKOOdavPfd+bYlhJB8MLYQQooBYwupBAq9/HkSxl+i+GsA16r1bmL98lwbEULIMWBsIYQUA8YWUvYUymPeOYv9KMxIBO6ZcSnJ4UW28mdtk8w6tj0qMoh9F9UZv0su/XhgJ7fsl4Z46CNQ0zs6Bc5QR0jK0iaVvGo2qamaUAWtW3d8LrBfds4/BHY4pU7bIzLLlm2Wvo81Sv+SLbb6aKRHtll3kkjoqi5abPyG22QftWpayoUKa9Y+tiewfaP0Yc+lrcYvMiZTPaf84COBveyhUC5LJeNJLRLJUSxqX20YbZHP+e5fvg+ksimp2EIIqRhKKbaMDiew5anx7+KuTjt+GFoo342tj4kUY8+La43f5Rf9Y2DHdqhxRriqZUK+Q3WF8WydlV9kW2X/d/1GZDJrW681flpicsXzPhzYyUNWaqNTAY6eLhLXeJ+qgN5kxy1OyWZ0aseqNXbckq6Tc4o5OU5s1EpU4o9tl303NQT2/ktseunYSG7Zdv2922z/dKVzJQUylVIBpJvkb3rXhFxlpsj78qdz7g3K/oNQ21uO3oIQQo4NYwshpBgwtpBKoFBWFp3p/guhtr841o6dczc55w44555Q61qcc3c657ZM/N9caB+EkIqEsYUQUgwYW0jZU0hj7vLYuZZzcTOAL2I8VdERrgdwt/f+E8656yeWc6dBUUTSQPX+8UMu+5HNypKNSUaPjs/JlETmvfbN3Uwiz2+QkPTEjcn+hk6WN5BTNXb7npWy3Ib5gV3zyA7jd9nFH5V9K2lMZGjM+LmUspXMpW6byFVcJlR1qyoR2JlmmaIabbJ9jQ+q7dQb0Uu+E0rrmidDz+LvbzfLT79XpqzWvE29SxOzbyPfuk0qsepsNz6ZMH5330P5yglGycQWQkhFUTKxJZICanaNfyfOu8lKcBGVbB9/9Y0fB/aNb7jSuI3Ok4rgMT20CFW19MMi402vlu9nF8qolk3Kd/TlL/gn6U5IGnPpi/5Z+tAhY4uqLjtuSdXJdtXP9kh/akQCklpkM9Altsk+skqem66x4weXVn33MiZquW2L8TuqQvgE83+w0Sxv/sDqwF4776/lOAk7HtEZ7tYtfbv4Za38+K4nP5bzuDNBoSfmPo+da/nojb3/NeSN6CNcCeCWCfsWAK8+1n4IIRUHYwshpBgwtpCyp9AT81Occ49h/FfmigkbE8vTfbO53Xu/FwC893udc/PzOTrnrsXEW9Xxes4cEVJBlExsqUJNPjdCSPlRMrEl1sBxC5kehQbma2atFznw3t8I4EYAqGlfcsxfuoSQsqFkYkuDa2FsIaRyKJnYUr2Q4xYyPQoNzP/Te3/FDB9vv3Nu4cSvzoUADhxzCwCxgSwW3N8PAPAhOdH2K+WJV2agJbDTtfbUEodF1+RrRLfVe1ab8dt7sRygcZMofYxOG0D9LtEb6T7tf6X9Ud7ylGi/ov2SasgNW628T4Y0aEf8tK4ppAFPz5fUQJEREak3b7YpjeJ7VdWxRO7jAABGlX5Mae3D2vE1n5K0iqayaUjPtm7lu3Puw4V0/eSEo2RiCyGkoiiZ2BLvy6DjjokUwiHR8KY3ybjll73yW6JnjU3z3LRVVTCvlnFLakGT7eBFogNveVq+u6MjoZzICq/SFh9au9K0tTwuqY9H/j975x0m11nd/+87fWartq+k9a66ZUtyx71QXCEYTDUQIBBMAuEHmOYYgwsmOGAMCSWJIQ4OxMG0EAcMtjG4V8lNkq3epZV2V9unl/f3x4zuOed6ZovQ7O6szud59Ojcuefe+9679z3zzn2/95xm0ov790qVj4+NJ36/4RbHvmT53zt2YFAWXM220UyCZ5BSJ2bCtcKv7mmqJMrTQ76qWn2SjaXibOzj0s0v/Tq9g2j8bBzk2h/XlYvxzRQylsa8eYx1h8s9AD5QsD8A4H/LcAxFUWY2GlsURSkHGluUimesJ+Z1xpgrSq201v5qrB0bY/4bwAUAmowxewBcD+AWAD8zxnwYwC4A75h0ixVFqXQ0tiiKUg40tigVz5gDcwBvQvEUQxbAmDe4tfbKEqteP7GmEUuXt+P+p79cdN1Jv/2iY+/opgqVS3ePyPawipeJLppKGV4gZRqRbrKj82mKw0o3LP3ObsdOH0NyGE+rvKTJBkrF40mShMPjknPYANuOp0VkdqpFTnPF2mjfkQN0ft5oWvgJKUqaTZK40v+ATe+YGE0JHXztMcKt8XF2kby0b+tOW8SuuWhD1nVc5WhjxsQWRVFmFTMmtixdPhf3r76h6LqPrXHqIGFPjGQpTc/0SUf2HTqyqtWxR+fKAUnLapK8DHeR5CUblOOR1t9TzsXoSqqMWdUt0yAmWklqU7Wb5CbiOx0QUo9LVtBYjMtD4kvlu7JDXTTOqNlDba3aExd+tobaYIZY2mjXuMUGSWpjWRrJXFe78PN2MxkOl6i45Sp8/7wyvHu8VEbGGpjvtNaOm5BfURRlkmhsURSlHGhsUSqesTTm06N6VxRltqOxRVGUcqCxRal4xhqY/+WUtUJRlKMJjS2KopQDjS1KxVNSymKtXTeVDTlcUhk6hXktg479gZ89JPzes+QZxz7jPVQqvman1A0NL6DfKp40/fhuflamHYof2+bYvjitq90h0yCm6tklZrorO0bawvteolK5F598vWMPLA0Kv5q9pKdKs/SQgX3Dwo9royxPW5h1PVww5JdrpNRFgRF5jTLNtI6ngHyVVotrybntHev3oDLbqZTYoihKZVGJseXMBkrj94Z714t11/3F+x27+0z67m5ZU1rvHIiydTJTIWLHk+6aj1u8CfnOW85Px/LEWKppv2vIyN4r+/26rzr2Jcdf69gHTpEl7/2sTck6Ok7VBte4hacx5MfNyLGYGHWwlJImJc8ptZA0+l52Tt4+13E9TL/PdeVufX0Z0RGSoiiKoiiKoswAdGCuKIqiKIqiKDOAklIWY8wSAF8E0A/gNgA/AHAegC0A/tpa++yUtHAc5kQoxU5LhFIkfvXlS4Xfj957o2PX8hSEzWHh99R/f8GxLzn2GsfO1UWEX7qGpmd8fTQ3E1s4R/hVbyJ5DU/ZCK9L9sGmbS4+iVJD8m1anhoQmxh2HgMn0HH97bKCVmAvtUHIadySEjYtZdI0XVT9siuFE5tWinVRqqdQr0x3xKfA+DSXcnRTKbFFUZTKolJiS0eIUvc1+Wjccs/wScLPBklWsfgu+v4/eJIcZzz4MElHeMXt6DJZb2lwEY1b5v6eKnjHF8sK6KHtLLUgH7e4UyKzat8iXSKTtXb+ylUolY1B9l5G8pLQEtmGyKZeFMVVibxU6kPPgNTxBEZJdjt4KkmRqwJyGOzfR+f+u+23FW9DmRnrifl/AHgCwD4ATwO4A0AjgM8C+G75m6YoyixFY4uiKOVAY4tS8Yw1MK+21t5urb0VQNxa+3NrbcJa+wCA4BjbKYqijIXGFkVRyoHGFqXiGavAEH/td3iMddPKYxd+3bGP/1/KYIIn64XfwZU0fdL4Ep1OwCW/KIVnKCaWbR1NCe16C1W2ansmIfxiC+poH2lWDatJXvr6l5jcxEN+hr+Z7Mp6kmyrou3X0fbxeTWy8fPoWnjS9Kfz9bj+rN4SbyO7jmt99HsueJDON+GSBT3y2+uhKEWoiNiiKErFURGx5e+Pv9exv7T2LY591+/PE35VZ9F3b/uj9B3f+LyUtZaiaqOUg2RDJB3Z8iHK0NLxoMwmF19EVdQ9KbpsyQY5bql9iclcxxircBLH0Hhk3r0HHHt4pZSyxJeQDMc3QtXM/d2uc+fSFn5cl+RlZBWN00IHaX/RDjluefLx6ZGvcMYamB9rjHkJ+Ww0iwo2CssLy94yRVFmKxpbFEUpBxpblIpnrIH58ilrhaIoRxMaWxRFKQcaW5SKZ6yB+VsBPA7geWttZgw/RVGUyaCxRVGUcqCxRal4xhqYzwfwT6CpoSeQv+GftNb2j7HdtLH+ckqJiMvLe6x0bfFLF2+WVa5qNw459sarKI1h1Q7Xe7d/SZqnJfWkC+v5WAdt/7dVYpNjvzeCYgwtkFVFg0OktZrzIunUtr+3Tfg1vExassAwpUv0RWV846mZLj7xS479yG+/DEWZABUXWxRFqQgqLrZ8ZeWvmV3eY2UDxbXf0XY5bpnz/EHHfuWTlJqxdoPUbe/7C3qHzuun8cOSm+mdvE3XV4ttln7FLf3Pc3Cl3HfdZmprA0vfuPmj84RfeD/51e7m4xZZIfSxX1EayXOu+IZjP/nTzxRtz3RScmBurf0sABhjAgBOBXAWgA8B+IExZtBae9zUNFFRlNmExhZFUcqBxhZlNjDWE/NDhAHUAqgr/NsHYG05G6UoylGBxhZFUcqBxhalYhmr8uftAI4HMIJ8ov4nANxmrZ1Ynp5ZwO833DLpbXjVTgDoOZ1SA7U9QumEarZLGcq2RkrlU/dLqjKai9D0TqhBpmLMRWj6Kd4WcuzBE9PC79jvscqkXSSnqdsss0elqmlKKMmkOqk6KY1Z8jVKJ5T6mKwyqijjobFFUZRyoLEF+N2Wb4zv5OKS468Vyz3nUOrCuQ/SOKFmy5Dwi86j7//FP6ZLzMcmbQ1SumIDlE4+dgyldk7OkeORhmdJ0htbQukbq3fJtseYIrefjZdyfimNWfDP36SFt8kx0kxjrAJDxyCfkH8/gL0A9gAYHMNfURRlImhsURSlHGhsUSqesTTmlxhjDPK/Ps8C8BkAK4wx/ci/SKHVYxRFmTQaWxRFKQcaW5TZgLG8WlMpJ2PmAzgb+Rv9TQAarbX1Y2915Dj11FPt6tWrp+pwZePCM25y7C1XygwrX3/jXY79b391hWPH2mnaJ9Itq3P94dEvFj3ORa+5USwPL6a3outeoamovlNK/wkzIZK1xObJeyTVSG87mwz5mbR843v7J8vztrMxZo219tSy7FyZUqY7ttSaBnu6ef1UHU6Z4TxtH8Sw7S9dtlCpGKY7tsyWcctFp9zg2Js+JDOs/PRN33XsL7/jrxw7egyNb6p2RcU29z9T/LfRxau+JJZHl1DGl5r1VGF023tbUQrD1DApWXilAgAAIABJREFUlzQGjTR+yqWYzCUthSM7r/ocysFkxi1jacz/H/I39NkA0iikHAJwB/QlCkVRDhONLYqilAONLcpsYKysLF0AfgHg09ba7qlpjqIoRwFd0NiiKMqRpwsaW5QKZyyN+dVT2RBFUY4ONLYoilIONLYos4GJ5DFXjhAPPEWpFH++5RSx7nMPXEkL7yFz8V1SV855w7lfdWxPsnT14dotlC7xvudvKulXis7bZfqlsXTliqIoiqLMDu5fc4NjP7WzS6x7130fp4W/JnPZD6WunMPfgTOJ0uOW6s30PtzhpK5e8F//IJbH0pXPNGZ26xRFURRFURTlKEEH5oqiKIqiKIoyA5hQusTpxhjTCyAKoG883ymgCdPfjqO9DZ3W2uZpOrYyi9DYom1wobFFOSJobNE2uJhwbKmIgTkAGGNWz4Tc1TOhHdoGRTlyzJR7eSa0Q9ugKEeOmXIvz4R2aBsmjkpZFEVRFEVRFGUGoANzRVEURVEURZkBVNLA/PbpbkCBmdAObYOiHDlmyr08E9qhbVCUI8dMuZdnQju0DROkYjTmiqIoiqIoijKbqaQn5oqiKIqiKIoya6mIgbkx5hJjzEZjzBZjzDVTdMw7jDE9xph17LMGY8wDxpjNhf/nlLkNHcaYPxljXjHGrDfGfHKq22GMCRljnjHGvFhow42FzxcYY54utOFuY0ygXG1QlHKhsUVji6KUA40tGlsOlxk/MDfGeAF8D8ClAI4DcKUx5rgpOPSPAFzi+uwaAA9aa5cAeLCwXE4yAD5jrV0O4AwAHy+c+1S2IwngddbaEwCcCOASY8wZAP4RwLcKbRgA8OEytkFRjjgaWzS2KEo50NiiseXPYcYPzAG8BsAWa+02a20KwE8BXF7ug1prHwHQ7/r4cgB3Fuw7AbylzG3ottY+V7BHALwCYN5UtsPmGS0s+gv/LIDXAfjFVLRBUcqExhZobFGUMqCxBRpbDpdKGJjPA7CbLe8pfDYdtFpru4H8zQegZaoObIzpAnASgKenuh3GGK8x5gUAPQAeALAVwKC1NlNwmc6/iaIcLhpboLFFUcqAxhZobDlcpmVgPkntlSny2VGVSsYYUw3glwA+Za0dnurjW2uz1toTAcxH/knA8mJuU9sqRXk1Glsmh8YWRZkYGlsmh8aWw2fKB+aHob3aA6CDLc8HsK98LRyTA8aYdgAo/N9T7gMaY/zI39z/Za391XS1AwCstYMAHkJeN1ZvjPEVVk3n30RRAGhsmSwaWxRlYmhsmRwaW/48pjyPuTHmTAA3WGsvLiz/PQBYa79Wwt/nN6F02FcDAMiF5Eu0y5a2OfamDd2lD+yhH7Amk3PsZIO3dFuzZNtIrqSfbK+8nnOCMcfOWDpWLOMXfpkoLTfUjzh2Kudz7K6qLnmwtPPiNfpztO+hTFi4jSZCxRvr+tOvbGor7jdNvLLzQNHPkyP9yCSixZ5IKEcxhxNbfP5IOhTJJwewrjvKm6Q+b1n8eNWzMBEaqFPlgq7Ywrdj21j34xHmJ9rk8nvVdiXgcYyFE4EnI5dzPDyN8RXB9234dXC1zZPm25TeocmxdYZO3r2FscX9kHXFaVM8TOT87s/zy8lYP9JJjS2K5HBiizcUSQdqGgC8ut+tmNvq2GLc4nHdernifSXdVroP5ZIUdwKRtFiXzVHHzOXoWAGfDAAdwQHHTrFxy1A2IvyG4jTWCAboWD4P9cOFVZ1im/3xzbTATjeWlWO7dK742CzgyYrlBa79Tzfr9xQft6SH+5GJTSy2lAjTZaWY9ur0Us7W2kxdoAVnNb8LABA/XkqCHrqfZpQuPOsrtJ3rBs8F6I/sH0w49tZ31pVsaGCY9pE6IVrSD2wwHg7JjvCWBS859kCabuoXDs4Xfj1P06D4XZc/4ti74g2Ofedr7hDb5PYvceyfjdJ5/ObgCcLvsU2LizbbJuWNv/qvP1/Ub7o45a9vK/r5hv/91hS3RKkQJh1baurn48TzP5lfdg0mq7bS7Gu2NkgrXIM9T4p9UbAf/aMLq4UfHwx6kxQzMiG5P75sWYTOhKVfuootsFXuQbZ/mI6VaGb7ZtuEDsptEs1sgY+BXeNePz1DgC9GjlnXOVXtpw0DQ9RA13MMeON0La2PtdUVz70J8sv56Q/nG0kKP+unGMf3kWgJSr/C3/TFP/4TFKUIk44tkZYOLHvbpwEA8RZ5/66+8dOO/YZzbnZsPk4BXLGFsfczmaKfA0Bye41jd5wgH1YOxmggHY3TQHhBs3xf9NuLfubY2zI0BvndgBxb/HbtSsde3EkD0ubQqGP/9ExZbPNr6y9zbA8LKGuG5AC7Ny7j5yHaI1IVc9cZPyjqN10c/4Xi45NtdxYfzxRjOgbmE9JeGWOuAnAVAATD9Rg5/RgAQM9JssmXLvqsY3sj9GR4cKVMkTnnabpBM821jl27XR43OEg3Ss02urm6k3IAH38NDdTTUbrBM73yafWP957j2J76lGOfsUAe+EPvfNyxf7CDtnnj3PWO/exOeeP+zfr3OfbprTuprTHZVl+AOnd6hP0qdf0lln+Rbqj6raVnCJ786WdKrjuSVB2QwSfaOh23q1JBTDq2BCJzkKrOD+w8Gelq0nT/edmDjlSjfGrkjVK/zobpUbM3Jffni1Of8o/Qvkc75CAxVcdm91g39KRd+4uRX5ZNiqVqpF+Cvlfho2cSyHnJL+p6BSo4wAaxjeTnHvR7Uuy61JPtcz3HyLIn8O7zEH5B9kSP2fxzAOAPvLNhGsxkQ3JgExhMsnUUP3wxGd886fyyZ4yn+cpRzaRji69uDmLthZmYZjnAvnTx52ibJhpIJ+bK2e3IXtqOzxLZF+R3fPgAretYQwPXXQOyYwdfQwPwbJr6yqYdcrb8Lw58zLGb6mkc9N7OZ4Xf+1/7mGN/euO7HPuApXO67ZULxTZ/6KHBfHtkyLE9rsvZO0pPHla10Phtb1Se+7KbaNzS/ELpHyyP/epzJdcdScK98jzizRN6SC6Yjpc/J6S9stbebq091Vp7qi9Y5V6tKIriZvKxJaSxRVGUcZl0bPFWaWxRDo/pGJg/C2BJoQJTAMC7AdwzDe1QFGV2obFFUZRyoLFFmTKmXBtgrc0YY/4OwH0AvADusNauH2czRVGUMdHYoihKOdDYokwl0yLatdbeC+DeCW9gDDIFjeGcjVIbOLKK3m4O9ZCesGZHTPglOxsdm7/8GeqX+wsdpJc3Yx00FVW9R2rE/MOkM421MU2oS3UWHKAP4i2kP38xMlf4re8ljdfw1nrH/sE+Eoj+0He22Mbro7b/IbbUsdvnyJcjguyF1AzTldmUnDDxxVGcI5y5h7+k6ybZQHrbR34jX0a96JQbAADeWPEXYhRl8rGFXsoMDsr7KjWX3kXxRqkP+YflC4b8hS2uA/VF5f4O6ZgBIFNFoTcw4tY7s5coA8X15nnIL13FY5DrxXcmu/aTXFT4pWogYbvwj/KXMKVbhsntAyQXFVlYAMDPXgwV+3C91Gky/NzJMe168TXnY6J1ds0jAymUwsMytljXNTKH/jZTnKVMqRwmG1usATKh/P1Us0W++9B7brtjV+2nzsLHHwDgSTHNtIf6Q8PLMrbwdyb4uKV2p2u8lKPxhGmgez3o+u73sffm+ppJ93635xTh9xs/6cX37aYxFpeL/9OON4htli7Y79gZFpx6E/Jlz3VvvsmxV97zZcfmmWUAwDeKomRflXnpz4O/pOsm3kbXaPUvPivWnffGrwMAdsUnHlsqofKnoiiKoiiKosx6dGCuKIqiKIqiKDOAcaUsxpigtTY53mflJOsHou353xBZV62cltU09WO9LF3XQEL48aIWqQaSlLhTpA0ulqnLDuGPlp6GqNnN8gQ3uHISsynYjddT7lJ3rstYHdt/NdkXrSAZ24ObjxXbmF10HjddcZdj/8vOC4TfksZex167mXKaZ8NymqtuB02b5VgOYXdSqHPf/A3HfvSeyacgyvlduVrTNC3H/x6vef83hV+9/oycVcyE2AKQtCI5x3Vf9lD/8LB71tsvcwFaL5OHiZR8clqaT3d6UqXjCa+fEepmMrSIbB+PLeF+Ni09JNyQjrAUhCxbaqq29FSvhylCYnNZmsdhuQ2XufhHqQ2BEXl+PD0kl6/wvOUAYJjcxMelLFXy3LkcJtTP44eMabyYnGHHtaXyRauSZVYwU2LLIRJN7v5AdrKeYkb1LpemhMlXcj6yeR0EAEg00v2cCdJ97hlD9dmyhvYRa5FfrqymELZdTemReUplAOhuZv2NjSca5g9Se7Kyr23aTDLeuy/+nmP/oOcC4Xfq76517OH9lP7aJGVb23fRcdNhVtPAdY3ecO5XHfsPj34Rk2WsHPP+YYpvJ/2NzFfe3JOXVZtM6RTUbiYy1Hlygp8piqJMBo0tiqKUA40tSsVS8om5MaYN+WpXYWPMSaDXgWoBREptpyiKMhYaWxRFKQcaW5TZwFhSlosBfBD5RPr82fwIgGuLbVAurBdIFYo91W6X0xOBIZpz9fbQ9EmuRib398TIL8CkE9YjK3VWMymFf4imkQ+8RvbpppdoRqxvFclfIj1yuqL/OJpWOv19JM2od72hG2BTIfvOYZlJfnuSY2fnyanxRadRheDf9a9y7EvaXhZ+P1xL2VyC/dSeqn1ywiTFJDReNpXtrpLHy2Gf9Y5bHdtdWjxVw6bU2Ex2sC0g/IIDbGWO2lCzQ8qRPIm8n8npfHOFM2NiC8cfdWVo2jng2CbDYkZI3r8mx+QSceqjOVYFFAD8w6yMfID3PXk/B0epP/DMJO77nvdRnskl6MpaFGISjpFjqO0+Js8zWdl3E808uwyty7m+MQzv18NMyjIk28CrePrZ+bnPiU8P++LkF5IVw2WFUJZ9gVf3BGQmHB5bvDF39ots0fYoFcfMiS0GsP78/VS9Xfav1t9sc2zLMgHlOlrkLlhWFk+GpBT+UZe0y0f3fY5J67IuZe68h0iGN9JFY5+a3bK/7n0d2ad9gC5j44grtjxM46DNH6Z4NzBAGVaMR/apvzn7T479y8HTHLshICWCaXa+viGyG9YJNyRZRiku3anZJccPlsXB0z5I55SYUzr2hXtoXc0cVzyPUgwKb+ljjWgSft6B/Hlxmd54lByYW2vvBHCnMeZt1tpfTniPiqIoY6CxRVGUcqCxRZkNTCSP+W+MMe8B0MX9rbU3ldxCURRlfDS2KIpSDjS2KBXLRAbm/wtgCMAaANPyRrOiKLMSjS2KopQDjS1KxTKRgfl8a+0lZW/JGKyY24rVhVSDJ18lU9F4otTnbBVppkzSVQEuIPVBhwhv6RXLQ6dSRa5kLaU387k04Q/df41jn/Ee0o67NZi1W8n2shRpmbA7VRlPmcTSLzaWTmm2/ekOx97a2Uxti8q0inOPOejYvXUsVWTalfqMpXDyM125z6VZTdeS3otXKnOnmrQs5WKKSfR9CXncnlNpu+o9dNya3VKTdUizaz2lr4lSUUx7bPFkLCK9eR3nq+4rP/VJ3vtNXH7PWx5b2DbIypjB+wMvPOk+bo6lfeVpXnN++U4IrwTqTbCqll65P55CMHyQ+nKyjvaXcFXJi+yj5Qx/DceVx4u3IVnHq5RKDayfaVOz7Dx8vLIhgCzT5RuuD3dJv3k6N54O0u3H2+EfoVhlUi69Z27i+k+lIpj22LKytRWrP51PNXjS38pxC8I0tuA9z3tgUPqxeJKto/fmfEMyBqWryY+PM3Kufv2Hx69zbD6WirXJjl23gewQewcs3iT7dTpMwaF2HYsnLD2kXSS147e/cI5jGy/5eTyyD66at8+xn59HxxmOy/cCw/tpH6Gh0v040Uzv11TvofHh6Dw5bslUsWrtNKxC/Va5795VtL95vfS3Ce6XpUhztYXBj2fi+Z4n4vmEMWbl+G6KoiiTQmOLoijlQGOLUrFM5In5OQA+aIzZjvyUkAFgrbWrxt5MURRlTDS2KIpSDjS2KBXLRAbml5a9FeOw9uB+dP34awCAuoCr9KehqZrfr73ZsS9ZeR1KYaKURic9r0Gsi+yjdX0nkP7CPT3MqzuZKloXa5N+fKoXpvSUa5RNJdVvo6mjCMvCU7ddTnAcXEHHWvDe5x170+2nCb99e+kcvewvnq4RbvDGaX+jbTRlFfHJc+LpEweW0TSQdc2/8EqAiU7aR88CefJ1r5DNUyR64zKlmTLrmPbYkgkb9K3Iyydqd8ipShtgKche3uTY3iUL5U5YDAJPq1gl0yr6B2n6OTWH+k0u6JKylEgFmKoqPcHJ/dz90DAlmj9KCzy1qz8mp6izAdpf7Vaaiu47sbqkn4hpVvbxDGu7J8MkL+7shGw5V8Wm8cMuGQ87p0QjTykpdxccpFjqjTJ5o1u6okqW2ca0x5b1g/tw3K9vAACY2jqxLttIX773P3O9Y1+6uHQlbU+SVQGuk3KOyK5hx370ha849sqrZaXOEz9G45ZUE/XDaKeUlHF9TaKJyWRcan0edyLdTFLCxi3+52Vbu8+hbRZ96inH3vyfJwu/NZu6HNszRG1I1cnOytM0Z8MUxxKuaxRg6WF7Type4R0Agv0UT0KnkQy4G3Ks2LiOpcllKbhNqsS4ZRKpWMcqMFRrrR1GPv+noijKEUFji6Io5UBjizIbGOuJ+V0A3oT8W80W8h0FC2BhsY0URVHGQWOLoijlQGOLUvGMVWDoTYX/F0xdc0qQMfD05KcePBk5HTCytN6xX3/eVx37QSZrGYuLV31JLI8uoSmnlMgyILcLsNkK7rfhK58Wfm957GOO/fJDix276SW5w5Eumj7Zex7ZwQGy5z4qK1n54jRts+W2Mxw7vFtO+2Yi7A1ptip8wFV1j53TMAtf1iv352OSl+Ag7WN4gauSKJu9Sy6itjc8IqeRQoMsY0NITqlzVNoyO5hJscXkAH9BqcGzGQBAsoWkbJ4LaJrV8+xGuY8Q3c/Rs6iPh/fIbATZWpK2ZCLsPnclg+EZW7JsqjjR4OrXrLgx78v+uFtGQvuIs32EB3jmJVcGJNbnD65g8hV3HByhY2VZcpqxJCqZEO3bnZHGwzNKMJlMqnpiGQ08rkw4HpZ9xTLJkTGui+6Z+DSzMnOZSbEll/EgOpCXU9S4+s3AcSRlueCiWxz7oS3fmNC+LzrlBrE8fCyNg5bdSPIVO0duF9lPtpcNJ3Z+VEpo9u6h7HTnPvoJ2t9WKSVONrMsT0tZ1eM4DS077pV9LbyfYt/WW9m45RXZx5ONrO+ykap/SPr5WZiNt1A/TkdcfbyHTA9TtcVbXTGjk3Y4OEBBtq5b7s+ymOGJ0cW0ftew2k4+tkxEYw5jzJsBnFdYfMha+5tJH0lRFMWFxhZFUcqBxhalUhn3MYQx5hYAnwTwcuHfJ40xXyt3wxRFmd1obFEUpRxobFEqmYk8Mb8MwInW2hwAGGPuBPA8gL8vZ8MURZn1aGxRFKUcaGxRKhZjx9G/GGNeAnCBtba/sNyA/LTQlOUDDbd32AV/dXW+PS6tVsPLlOYnWU8TAMlaORnw4nel9rsUly78jGOnOhsde8/5MvVOupalymHpv2yH1IFnmQ7cM0K/g1531lrh9+AzK8gvSfsL9dF5pGrl3yowTH4v/wOd39KbZZWxUC/5+WIshWGzWzNFNr/OgUF53DhLCbnxy3Rcrm0DZCVRXgmMtxsAqvayNEsDpFnzJmTF0UPVVo0xa6y1p0KpaGZCbIk0d9hj35q/h/1ReZ9Hekgzma6hfpysle9BcE348CKyG152pwUdcuwMqyo80infueC6clHhsqZ0xVv+foir6Cb8rM9zjXiApTN16+tTNRQMeBXgnCt1qjdZ/PtDpFGErIjM9efWdUp8//zdHZ56FZCVmHms8kflF4R/lL4ffFFW+TMtY4v15c/3qfX/huHovtIXWqkIZkJsCXZ02PmfzMcW63qHoe1JWo62U4eNtUm/zddePaFjXfSaGx072URjlV0Xy2BgWijfYXaEXgo5/tjdwi/iIxH26i1djv365RuE35+2LC3aHr5v9/sbgQMUDDZ/kc6v6/u3yjbs5lV76fPRY+T+ROVU9v5bzif9smFa3nY1jfO6viePW8WOG29m45YhGRbqtlGsqdpH1yu4q1/4/a7w3sBkxi0TeWL+NQDPG2P+hPw1OA/6q1NRlD8fjS2KopQDjS1KxTLuwNxa+9/GmIcAnIb8Df4Fa+3+sbdSFEUZG40tiqKUA40tSiUzVoGhFgDXAlgMYC2ArxUS908Lh2QW7qnPvlV0CoFB+jzWLqcx+HSFDdIURNtDcqqnIUlTEgOLabrZd9Kg8Ettr3Xs5hMoD491NfCZK+l9k847KS3S03efIPxCTClTu5PaF2uhz8O9ct/hXvJbeNs3Hbu6T8p4anfTdC5PGZaqk+c+eiLJcHx7aHo9dUJM+GX66LqsuOfLjp3oqBJ+vk2UHq52G32eqhVuiM6jNj17Z+nKZ8rsYMbGFter8KPz6P41rGpbqtatvyCTy7KCA65qeiyVX6qOpnrjTe5SnWRmQsU/B4BMFZtmHSyewhSQEh231OMQ7rSFgVGeZpA+9yXk9oEhOsccq46cbfQLv0yY7YQXC3WnH2BNT1IGOJHeDJAp0vg5Wdc3Gk+/6o2RlCXFUmECgH+4cAB3GkWlophRscUA2VD+3vTG5I2+/yyyvUyWlWqWMePE31AF85bqUcc+8MtO4Td3T69j911AerrzzpSS2af30HYbrrzWsT/zwjuF3zdP/JljX5T6lGO/MtAq/HL9FCPr19M5xluL93cACLG0hYu+QbLb8JAcj9RtI7lZYg7t2y2FDZ5B1TkH9lGO5urWUeE3ul9WLT6EjUhZW9VeLofhqV3ldkML6YOnf3JkJ2PGysrynwCiAL4DoBrAPx/RIyuKcrSisUVRlHKgsUWpeMYamLdZa79orb3PWvsJAJN6acIYc4cxpscYs4591mCMecAYs7nw/5yx9qEoyqxEY4uiKOVAY4tS8YylMTeFG/DQc30vXz70tvMY/AjAd5H/BXuIawA8aK29xRhzTWH5C+M10ho23ezKOMArSiZ7aFolF3RVc2KZTrIsCcL+C+Q0xuASKnnJ3+qdWy2r+P3VZfc79ve3XUD7zsnfOhc9RNNAkVqamx1dKC993ct0YnPW0cxb9Ryay07OkdPDB49n26yntmZkAhlRNc+drYZTu5qONdrJpqz3yh365sUdO7qDpo6M6+3r9bdQxpaTr2JTVn3S79kfTezNc2XWMGNiC0BZQjIhOUWabGSVIlnmpcCQvH9zvOIl6zaJRtnHk/XU/1Msw0qqXrghw7IH8Cq7bhkfl32k6liGlYRL8naQGhXqoawMhmXkclf3Tc6hWOpJM6mIp7TUwzIpi7tCsyddPP6mq+T+eMaWIFMPemSYFvIVnr3JXXGUZ9NJ19OBMxF5vjlffp31qZSlwpk5scUAKNx+2TapxTpmLskvdm4hveqcdqm6SWWKD9Fa37ZTLG/sYuMWJs04s26r8Pt8232O/c4n99E2tkH4fWntWxy7N3q8Y6ezcgAW7KPlmj0kw4kw2W26Sva1wSVkhw+wysbNsvNy+UqOZapK17iyrTxP2fMwj65zMimvnQnTdVl2A2WQCwTkuOqZH9N4ZNWnyM/jylz1wvfLN24Za2BeB2ANpELoucL/FsDCV23BsNY+Yozpcn18OYALCvadAB7CBL88FUWZNWhsURSlHGhsUSqekgNza21XGY7Xaq3tLuy/u/CihqIoRxEaWxRFKQcaW5TZwFga82nFGHOVMWa1MWZ1NhYdfwNFUZQJwGNLJqGxRVGUI4MYt4yOjr+BohRhIgWGjiQHjDHthV+d7QB6Sjlaa28HcDsAhOZ22EPa8mSDTNcV3Eq66CzTlXtSUitYv5HsbIhOu/+0tPDLHktf1B4vHWt5/QHh91y0y7FXNnY79jPdxwi/j8x/1LH/2/8ax041HRR++15Y4Nimu8+xg0Ok7/YPyHSE1lPj2Fwf2/L77cIPIdJWxhc1OfbAUllxMNFMdqCf6dIb5TVPj5D+1B9jOtysvOYnfpx05ZFB2odbf6ooR4DDii2Rlg57qEolT4kIAJH9tJxm2fVCQ7I/8PuZpwxMNMjnHunq4jrrTMStWadllmER3pjsX2mmK/cwXbk7rZd/lFXTHWEa8xyr6BkJiG18MaYlZYcN9MrBhsnQPlKtlI4sl5KN4Np7XqWUVyIGgCyLYz6W5jE84LrmTPfupDoEAJcGPlVHsT4boDYlXKliD1U3HUtDrxy1HFZsCS6Yb1GV111HamVF8F2bWNrBKtJmj8bkd7L3FepTm5rIXnTcPuG34OQ9jt0apjKZaddLeU8nuhx7Vc1ex/6fXTJ9888WPujY7X562WOuf0D43XDfBxz70Xso1fEbzr6ZziEux1j8XZt4K/XxJd/bJfwSS9scO8f6brJBasITLSy+DdC63JBLY84uRZbFXF4tFABO/RCNW+oO0r55NeRyM9VPzO8BcOgv+QEA/zvFx1cUZXaisUVRlHKgsUWZUsYdmBtjbjLGXGiMqRrP17XdfwN4EsAyY8weY8yHAdwC4EJjzGYAFxaWFUU5CtHYoihKOdDYolQyE5Gy7ABwJYB/NsaMAHgUwCPW2jF/NVprryyx6vWTaiGAFXNbsfr6Txddt/LTlM6mcT1NaYZ2D0lHH81j7HgLpdeZ0zIi3Hh6ooCPppj2xGROszPmkFwkFKQMTPEWOc3yr7vPd+yDUZoPj69pFH4LnmTSlhRN/eTaSXpiUrIqWN3jlDIp10rpjmx9jfADm6LnU8o1++T+gsP0O224i1XaGpK/37Js2rx6N33uiws3NN9H1yg7l843NScERcEMiC0AYAp6kZCrYqZhOpLabSQB8bvkHLkIk4rNo3FAsk5OkeYCxW3rSjPKUzNmAyyloavdgQHql7zvVe2Xsg9EGSJoAAAgAElEQVQu9TBp6vOGxRnj87i2QVFMOlt8BQBPktYFXLIgWdGTVdNzpSf0jJBjVQ/b37CcDveyc7JBVw5dflh2WjxtW0YW/kQ2lF+Xm2pxp1IudmCaY8vKxjasfv81Rdct/jrJJVofpJuuandS+PWdyKr2jtB9vvD0PuH3/qbHHft3wyRL2ZWU44wku8GvmLPasY9btlf43dx3rGMnWD7YW1+4UPgtfJGqgl/S/FHH9nS1O3Y2IsdEzS9SsMqwyrzJxbKqqH+YrsXIAoqr9ZtkfIsO0z54ysX0HFfKVlZ9tfUZlm41KfcXOsDSQbNq5qWqJpeDcZ+YW2vvsNZ+CMBrAfwEwDsK/yuKohw2GlsURSkHGluUSmbc5wPGmB8COA7AAeR/db4dlBdUURTlsNDYoihKOdDYolQyE3n5sxH5+lWDAPoB9FlrM2NvoiiKMi4aWxRFKQcaW5SKZdwn5tbatwKAMWY5gIsB/MkY47XWzi934yaCf5R0RN1nk9az+jT5m2PNZZS+502PfsKx173QJfwiHaQ5DwdI1xjwyD793FCHY3tYHeg1O2S6RPRSm5qeIz1lwx6ZPsnEaPl3B2937EvqP0w+DVLnznXbns0k9jaNc1CK0HbSpnnb5P6CfaxMeDWlaUzVu0p8s2RRbX+gNJKZZqltTy+kdEe+XrquMjGbcrQyI2KLpfcuIgdk2exULYXHkS56LyJ+qhQotz1FmvN4E+kdAyNS45jk/Yitcqd25ZgkTx8o/bxMjlq7k/TYoX6px+a68EwDaSZ9fdQnPUMyn3u2qZbWjbIUiwmpgbV+ukbeKNN9B+RXS4DJM62XNKdeV1pFX4wcg/10LG9MnhNYqkewJmXqZLq5LCvlza9/0hXTDmnRVWM+O5gRsWUMfKN0/3W/nfpNZ6t8uaP5UzTuiH6TbvSHti8RflxjviDY69gb4u3Cr5oFjcdGlzn2UwMLhF9vjOJE/2qqp9Sw1XUiljTmv+/9N8e+pOVvHNvT3CA2SbZTbAkMUHt8u2QWyix7vy7UT9chE5bvlMzZQvGtl+nZPWnpV7udvTP0Ahu3NLnGLbUUQwLDdFz+fVBuJiJleROAcwGcB2AOgD8iPzWkKIpy2GhsURSlHGhsUSqZifwEuBTAIwD+yVq7bzxnRVGUCaKxRVGUcqCxRalYJiJl+bgxphP5Fyn2GWPCAHzW2pFxNp0SovNpSihdQ9ObyT82Cb9lz1JaxfkPksQicJGc0nz5Ezc49uK7Sf4yFAsLPy5zGY3T1Ic9KKdS5z9EbQr10ZSVd0hKWXhFzkuWfYH2t5DNvO2QKY08UUrrk1tC0hqTzJb0g2Xpl/YPCr9kJ0ljanfSFM7+ufI2aXuKpp8SnSSbERX4AFiWgu33GzT1qyKZKbHlkJSlb6VM48krT/K3cfxRKVHpW0XTvk0vkSRkpFNKXiI9FAsGltI0q7tiLpe5MJUc/FJtguq91M/DPdT3PK6UhtbL0ioy+YoNkqiMp1EEAO8AHSw7h87P43W9liTSL7J9ZOU14pPKgSE630yVnG72RantnhTZ1uu6Rl7aLsuqlo7Ol0K5eCO1N1VHnyfaXKli+wr708Kfs4KZEltKkVpO38k+P92L23a0CD//ddSv275PEhB7uuw3576DNCY/evaDjl3lk9Izv6U+9cxAl2PvGaoTfskn2VjgAPXloKvqcd+JFOMuOZZSQ+Y6aIzl7ZfyHP8A9dFsFUlPMl0yXSIfx3hjLM64Yguv1lu1j9aF3rNf+OEFKm0+fAIdK7xfjsV8o3TNH3jqy5gOJlJg6CMAfgHgkIBoPoBfl7NRiqLMfjS2KIpSDjS2KJXMRLKyfBzA2QCGAcBauxlAy5hbKIqijI/GFkVRyoHGFqVimYjGPGmtTRmTny4wxvjw6iJ008ZGVhF0xWdJrpKVihJEuqnJQ4tJltJxv6tc5XXFj5NKykvl8dCUTkMNTfv2DVcLv+CgK5tAgWSbrBScZRWwzGisqJ1dIjO+5Pz0uyrZQCfsScvppvBuWjYJljkhLC9ScCNJ8XIrSUKz8J83yeOyaSo+FZWuldPID91fvOqZohSY9tiSrclh4Pz8VKbNubIPbSBpS4AVEvZkZBMjvdS/Yu0UWyI9UtoVay2ej8i4CsrxapXc9sXlcQNDNL3rSZKdC8tYZXh7A9RfeeXPXL2MW1yGlg3TNjlXthXvCMvYkmUylJicHrYsi4qH7TvcHxN+uRA/FouJ7kqiDL4u56okmmKJp7JBVgG5SkpZ0ol8m+xEHlUplcC0x5ax2HbltY7decc/OrYJuILBDhon9K2ie7vt6Yllfoxm5Hd8ykP9d0Udfd+/uLlD+DWz8ZJhyrhUtewgiSbW34ZIJeRNsnFGSLbB8nFLI8VELmMDgECGxYwEl7LIa8THHaKy+Ufl/mLH8jhBn8fbpITx8V9+FtPNRMLQw8aYawGEjTEXAvg5gP8rb7MURTkK0NiiKEo50NiiVCwTGZhfA6AXwFoAHwVwL0o+V1YURZkwGlsURSkHGluUimUiWVlyxphfA/i1tbZ3PH9FUZSJoLFFUZRyoLFFqWRKDsxNXpx1PYC/Qz6JlDHGZAF8x1p70xS1b1Ksu/XT4zuVGeuXy7FW0lfVP7rDsfsul5W2Es2k1dp3Lq2b/yfSVvGqggBQu4308Wmm/Yrsl/qz2AJKhVS1nipeGZcOlFcSDfaQ9jOzVBZL+8Nj9ODholNucOwHH/kiFGU8ZlRssQa5QoW45tYhsWroROpH9iXSYM//o9RFZ6oojAb30/sm8U5ZUS7Hui9Pg2hdylehOeepE12yUg9LG8ZTC8bmyTSNOVb90rRTPAr3Mh2ox1VVNE4HywYptgQSshGZetJn+gfY+zpJqa/PNdD188aZtj0kA2amOsD8SqdI47rSdDVd2Gi7PI9kE9OZ8msel199/lhBi+yS+CqVxYyKLRNk54e+ML7TEcJdwdzB9X4N7wdV3dSXhxbK92Sa1tL+0kvm0nF2H6Rd10gNN38fxhdnOvKMu49TrAru6meNk23l76LU7qIxTXxxs/B7+N7PO/b5l33dsR+953OYaYwlZfkU8m81n2atbbTWNgA4HcDZxpjpHwErilKpaGxRFKUcaGxRKp6xBubvB3CltXb7oQ+stdsAvK+wTlEU5XDQ2KIoSjnQ2KJUPGNpzP3W2j73h9baXmOMv9gGs40t75r8uyJn3vFNsVy1m6Z3h8/odOxkg5yOiXfQ9G5wP/1ZdryTpndq1snfUYERmuoJDNOU7cHjQi4/VrmrhWQtvLofAHj7Rx073U55xkY7ZNXTc674Bm3TItcpygSYObElY+Dtz/e33pysflf/PJNVJKkPuatQJhqpyfvObXDsqr1yatbDMqcmGrlGRTYp1EcfhHrJLzwg03/xNIjpOdTnk3UyTqSraH885eIoS+0Y7pMajsgBtk2UTVfXyKlskaqQpVX0pGVc8AyzKsVV1Fbrl/I8vj9xndPyWkbb6FiDS+l80wtl+ttFc+k229VHVYqzWXmNMolQ4ZhQKpuZE1umiX8/7UeT3uaB224Ty4FRigc8vnlc2Z+7z6QO07CO+vzBv6VK5pHnZCxo2EA78Q9TbEk2yD8PT33qH6a0kcYlp+MSukw9HStXJfv4a99A1cf9iYmlm5wuxnpinjrMdYqiKGOhsUVRlHKgsUWpeMZ6Yn6CMWa4yOcGQKjI54qiKBNBY4uiKOVAY4tS8ZQcmFurk3qHw5M//UzJdcuvo8qkiebSr/+HTxhw7PRWkpSk6uV07mP/U/xt4otPvl4sjyym7BCDyyg7QtNjxeJXHuulyRRfUrbVy96k5tklLrjoFuGnlT+VYsyo2OLPAXPzb/J/ZMWTYtWd+1/n2OlaPrUrs56E+rgshexUrSt7AJupzVaTLMUa2a9TSbo8njTtI1Xvquh5DC37mVwtE5HH5VWQeZt4NdNs0F0xk/YdYhlf/AOuTE6s8m+qnmVRSEvZDU89Y4N0fu5sMDy7DCdd56pgyM4j2UzT0h0tg8KvNUzVCEdZJpdkWl7LoR4ds80GZlRsqSCe/dHVJded8mGSuYx2uGMaxUX7bsrEYtaSlCUtk1Phkf/7PIpx6SJZcTOxgPYx2klSltoNso+XwptwjVuYfIXHndef/w/C78GHr8V0owWIFUVRFEVRFGUGoANzRVEURVEURZkB6MBcURRFURRFUWYAY738qRxhXrmZ6ht0/vDrYp2vmlIIjUZJ75hjWlSMyj/X0ptJ+7XgV7JqIadmC+ks73vuxok3uMD5l/6jWBaS2JyrbKGiVBDGAJ7CDX1t00ax7k3ve9Gxv3Pg9Y79x01LhV96F/XXTJhpzOtK9w1fI6vaOyz107x6cKKB9uGLufIqssVsiC24Xl/hGnNe0S9TxZzc1fR8rNrnoLekH09pONJBGu6BZfKcON4UnVOkR2rKRfU/ZvLqpQCQrKdlbx3FzmhKplwbTrPUjJa2GRqW7wlUb8+frydZstmKclSy5t9Jf77g2zIdtG2iRDd9B0lMbhtZdc+9sk8uu4netVt4596Sxw1tp6yXf/rDrZNocZ43nHOzbCt/n8UVx2Ya+sRcURRFURRFUWYAOjBXFEVRFEVRlBmAsXbmSxGMMb0AogBeVdFrGmjC9LfjaG9Dp7W2eZqOrcwiNLZoG1xobFGOCBpbtA0uJhxbKmJgDgDGmNXW2lO1HdoGRTmSzJR7eSa0Q9ugKEeOmXIvz4R2aBsmjkpZFEVRFEVRFGUGoANzRVEURVEURZkBVNLA/PbpbkCBmdAObYOiHDlmyr08E9qhbVCUI8dMuZdnQju0DROkYjTmiqIoiqIoijKbqaQn5oqiKIqiKIoya9GBuaIoiqIoiqLMACpiYG6MucQYs9EYs8UYc80UHfMOY0yPMWYd+6zBGPOAMWZz4f85ZW5DhzHmT8aYV4wx640xn5zqdhhjQsaYZ4wxLxbacGPh8wXGmKcLbbjbGBMYb1+KMtPQ2KKxRVHKgcYWjS2Hy4wfmBtjvAC+B+BSAMcBuNIYc9wUHPpHAC5xfXYNgAettUsAPFhYLicZAJ+x1i4HcAaAjxfOfSrbkQTwOmvtCQBOBHCJMeYMAP8I4FuFNgwA+HAZ26AoRxyNLRpbFKUcaGzR2PLnMOMH5gBeA2CLtXabtTYF4KcALi/3Qa21jwDod318OYA7C/adAN5S5jZ0W2ufK9gjAF4BMG8q22HzjBYW/YV/FsDrAPxiKtqgKGVCYws0tihKGdDYAo0th0slDMznAdjNlvcUPpsOWq213UD+5gPQMlUHNsZ0ATgJwNNT3Q5jjNcY8wKAHgAPANgKYNBamym4TOffRFEOF40t0NiiKGVAYws0thwu0zIwn6T2yhT57KjK8WiMqQbwSwCfstYOT/XxrbVZa+2JAOYj/yRgeTG3qW2VorwajS2TQ2OLokwMjS2TQ2PL4TPlecwL2qtNAC5E/hfLswCutNa+XML/TF9t+IlAax0AIOTNiPULqjod+0BiE23n2k+VJ+nYI7kQ8yt9/mnrc+waT1ysy7HfNDl2NC9ywi9jPUW34e0BgCpTrB8DCUv7CwVWiXXDSef9DrHvgUyV8BtNBIvuOxhIi+WlNR1F/aaLgeQrRT/v3ZvEcH+m+AVTjloOJ7Z4a8JP+FvqAQAeI2NBJkt9yuulde6Y4fNSH83l2G3pukN5qM3m2L49MmbkLG1ome3xyON6Ta7oNu7zCHiy1CS2LsPakMz6xDZe5pdl+86mpF/J8Ol1reCXhe3b4zp3fr48JIrrCnktuZ/76yzgp3PP5sYKGfl1qQODyAzHNLYogsOJLdVzfE80zct/9/L7GgCaQssce3dsm2P7WV8FgFo27ohbek8xZOR3N2c4GyY/j/TjcYKPW9wxwwPe/ylOBF3HDbH+62djkKSl8wgGThDb7IjuKNqGaHJi72GGXeOWxdXHTGi7qaI3sbHo5wf3JjA6kJ5QbPGN73LEcbRXAGCMOaS9KnqDA3g20FqHFd/5AABgUd1BsfKuM37g2Le9cqFje13fGGdFNjv2H6P0w8lvZEfgdKfqHfu8mg1iXSJHN1HC+h3bPeAezEYcO5qjAfIZ4a3C75Rg8ZtyUzrq2Md2rBbrHth+bNF9/6z3NcLviU2Liu57SccBub/Xfquo33Tx8y2nFP38mrduKPq5ctQz6djib6lH1zeuAgBUhVJi5cGBaseuraEvSL9PxoyWqlHHHk1RP3QPuNNZr2P3Ryku1EXkj/5EmsJyhm0TCcr21QYo1kTTFD+q/NJvftWgYwfZg42+JP2A39LfJPcdon0Psx/2g7vrhZ9JFf+eydXLL0/DBurBMK2LhGS8TKYplvq9dJ2jcRkfc+y6+AN0Tum0V/h1tpDcdjBOD2TcA6VDy5uv/nf3qSgKcBixpWleEDf9agUAIJHzi5UfWfaoY3/6+Xc5dltwSPhdWEW7X5+a69hLAvtLNvQPIysce1moW6yLsnFLjI0ZarwJ4ccH/nwMsyjQI/yOC4w4douX4snWNMXEJa5xy4ef/SC1J0PteXZnp/Ar9Zt/1fy9YvnX53y/hOf08K8bzy/6+dfe9tyE9zEdUpYJaa+MMVcZY1YDeCozFJuqtimKUrlMPrYMa2xRFGVcJh1bRvpLP9VWlLGYjifmE9JeWWtvB3A7AMw7vt6+cd56AMB1TfJp6TUvvs2x1/TTL8XfHPu/wu9dW9/o2O9spV9w6+Lzhd/eBD0RWtfX7tjRVikHeW0dySzqvfRUu94jv+gjhp4I7U43OvYfRo8XfjWeFxybTx1vy9A2333uPWKbnD3Vsa9sfNKxh9Mh4RfcQW0/5txdjm1c01f8l957arahFLVzd5dcdyRxy4dGcuESnooC4DBiS92yVtvZMAAAWFgtZ+MeSS907GiM+tCKefuE34aeVsdurycpJX8qDgAjo3T/5vrZk6sa2V+r6tjTefbUmD89B4CBRJitY9PIGZcshT2557KWeIae4g301sh9J+sc2zAJiCcpL3Gwj44bO4bJDDPymU+kjuLi4sY+xw755OBl9wjF34FRun6ZpDwnm6RrEQrTDEF9tYy/fIq+tZqe4vXH5d8m7Vy/GSk5VaafSceWY1cF7SJ//gnzGSHZdz/34jsce/0Qje9PmLtL+P3P8MmO3eKn2PK7YSkP2RVvcOyX+ujJ+mmtMlX4GTVbHJvLXNwSXC737ctQbOjPSplsxEPjsX0ZGuv0ZOm4n3j4k2KbrT00g5/N0HVxy9rMTuqjK86idieycvbh5nVvcuy31j6PUhx/zN6S644kta5xy/BhjFum44n5HgBczDwfwL4SvoqiKBNFY4uiKOVAY4syZUzHwPxZAEsKFZgCAN4N4J5paIeiKLMLjS2KopQDjS3KlDHlUhZrbcYY83cA7gPgBXCHtXb9VLdDUZTZhcYWRVHKgcYWZSqZDo05rLX3Arh3ov4eYxHx5HWE1/WsFOt2xEiD3Rsl/dNbN79J+H1nwc8d+16WlYVvDwD1ftIHJZn+6d71K4Tf43MWOPa58yjDymX1Lwm/M0OUEeHlJGnJdicahN9zAdK6LwlQtpQRlvroA42Pi20++MIHHfvJ/fRGc8qlMX39G9c49tMHyK+ZZZMAgKFscS1UwrpSOBX1mji5/Usm5HfJws1i+Ykdec2v32SKuSvKpGNL0JtxtOVr+uT7JimWGjDTT5rL50e7hF9nZ69jR1OkHU9lpK40y3TRXLft3y0zjsQGmIaymXSbzQ0jwq8qQNrq/UOkA027Uhr6mE69MUwa7GGWQWbePFkssHsD1f7gCUz8I3KSNbaQdKqeETq/XI2MGVznznXlPiN1pZw5TC9+wHVO2TgtV7PMLkvqe4Vf2EvHGkqX1nrGClltvEY15kpxJhtbfLBoKGQ7+faAfKesO0HfogdGqO/evuM84Xdmy3bH3psj3fZgRr4jsStK6/i7Yw/tXCz80h3URxeE6V2PhUGZbYVnfXlmhN612ROTWZk6/BQ3Tg7tcewXo5TC8C1tL4htvraRjc2CFCdyRsaWHZ+/2rGX/88Njj23XqZET1sZZ8tFvLur5LreLMWg9yyRmXD+b1t+zBqYxLilEip/KoqiKIqiKMqsRwfmiqIoiqIoijIDmBYpy2SJmCRODu8AABzMVot1dz18tmPbCJsWeUBKVN5+0Ycce9EcSovG03MBcqo3+wxND3lWlM53fP82KvTzUr1MbXpKI6U/+tZJdzv29zdcIPyy7DfS/ixNc9V4SVrDUxgBwFdW0LsnfxwieU7Oyt9b+xM0VcaLl2ztkUVF3t3+jGMP5mjaZXWyTfgd3HiuY/NCCRPllZS8lssDNC23J0Pymvkuyct8X/5aBFB6+ltRJkPGetCfyt9/vO8DQO/6ZscODVGfCvXJ/rUrTukSfS3UX7MuKUuohqY7Q2tYgTIZqmCyTE6xn+QmB0ZkmrDWTppG5gVzwmFZYCjko77Mq31G/KXzLDcuoRjZu59SJyaC8tw9o3SO1sdLm8rsclzKwqsP7hqV6dz4VrVBKnqSqJFfVaOs2qqP7XswJaf4ayMDjj2coviZsyXapzU/lSNEBga9BXnokEt68sxuJj2NU7/2PC77wy9OJ8nr6cdSCmO3BOxt7VS85tu/eDPtu0sW8OL8cielXKxyVdO8Yj6lHfzXU37s2Dw9NQB4WDtiOeqjJ4Ro3BOzMtX0defTuOXmx/6C9lUl27Dslzc5dipB8XKfS0zb1C4lfodYm2oXyzFWwOi0zp1FtxmLPRl5Lef76Lz62bn37ZSVSI8txNmQSlkURVEURVEUpbLQgbmiKIqiKIqizAAmJGUxxnitdaXmmEJqPMAF4fyUyVs2nynWedjsgHc/nU6iWb5d73+EZBvrTmfTyPtlJavq5VQz4CPvpRewf/KtS4XfSR+hjCHP/2CVY7d8UNYc+M0WyuZyWT1JXrKYK/xChqZxBll1rS4/ZRlYm+gQ2yQsTYGdXE1TM6/EXfv2UjaCORGaam9pklNA8/w07fux7W937MtbXijp950Nr3Nst4RmV5Km4doDQ45d7ZVvir+cIvnK25hS6fGEnK7rrAjhlTIZpju2eGAR9OaDyMadrWJdsJ/u5wBLBJDzS71D3UaScwwZlvnDJYtIGoo7yeV0yg3Py34zHKYNa1kB3oOny/4wuJqkNoFVgygFl3pwycuh8wZkFVFAVhLt7KDsDbv2Sd1NzsPibIb27a2Vcppaljnl2c1djt3WJttdzTLNjKbkFDjHy6Qswwnyi6dlkOAVPlsiFO+29ksZX0tNPgYZrfw5a5ju2BI2FicU7ufvjcrYkhwiWVXgAN2zo/IrHjUvU8xYW0/SjJZamVHtzqEzHNu/kr5rPWukVPeZWpJZxF+hdcdfIDM/fv8eGu+MZklusi0mxxZnVFNFzh2sSnk0x2QeGSk/Tlg63y+cTWOsH+86XfgNxSgmeX3U309qlxU8m30UnP92E1VH/+aSn6EU16+93LF7U7Lq8cZhykh1UevLjr0yJGPfjgzFz9ODVP397pFO4XdBZAsmy0SfmG8xxnzDGHPcpI+gKIpSGo0tiqKUA40tSkUy0YH5KgCbAPzQGPOUMeYqY8yfm85aURRFY4uiKOVAY4tSkUxoYG6tHbHW/sBaexaAzwO4HkC3MeZOY8zicTZXFEUpisYWRVHKgcYWpVKZsMYcwBsB/BWALgDfBPBfAM5FvhLW0jK1L49/BTxtqwEAZx68TKx6eR5pt7g60LNB6pqyMtOgw8/f+B2x/MvBUx37X9ZRFa7MBQnh9++n/cixO1/8umMPPikvRdtKquLJdeS/65GVRA8yLeSqRtKpJ2pIR74ytFtssz9DGrFGL2nO3lotUwGd8eRVjn3KPNpHKifTuX1vL+nFr2il9Etcw5U/LqVPOzdCWvtbuy8SfitrSAv2wghVVTy5dpfw+8mu1zv2tYOk9/rQcU8Kvx2BfHq4EVs8PZJSeUx3bEnlvNgTzfejSESmwxptpqCRqif9dNUeKR7P8cKdrKKnt1nGDF6RL7eX9JPR+XJ/fnZ7j7JipHUvyQqh0Xm0v3iMNJ3ZAanNHg7ROyv+KtJwN9RSekiezhAAonHaR9BPWsoF82VlzR1rSXPK0yXyypwAsHMv6TOr6+k9F3elzaEEXfOuOkoH+eKgTEPrYdr2GDt399+wfzfFyL0e0pVXtUSF3/7hfNxJZ6emiqBSfqY7tnj9q1A7Nz9uWdEvK5E/X886NpOB21fkuCXN5M/8KWpXjazUu2GAdNGxKPWHtnP2C78nL/pH2seeWx17/X/IyqTp02msctcmGhMZV3+9rpe02osb6F2Uk+tpnLEgKGPG06yS6KnVVNn0ovYNwu/ORygtc00HjUH2jErd/D04ybHfPf9ZlGJ9kmLVm2rpvbnPb3278POwc7z/AKmg3r74ReH3ie3vcOz6AMW0U+t2CL/fFyrND+VWl2ybm4m+TrcZwJ8AfMNa+wT7/BfGmPNKbKMoijIeGlsURSkHGluUimSiA/P3W2sf4x8YY8621j5urf1/ZWiXoihHBxpbFEUpBxpblIrEWDt+eihjzHPW2pPH+6xcHLsqaH9wT37qZyQn03rxtDzvWLyGtrn+WyX3N+dsmt45q2W7WPfgHprdGt5I6f6yVa6sS166biZFk0zhfXIqlEtoeGrH+AKZTswzSL+RzjuLUhc1+GnK9eK6tWKb6zdTha8PdD7l2P/TfZLw66qhKn5+Vqnrt2tXCr9zl29CMdxpEC9tpHakLZ3vB2t7hN+NvTQNtDhEkp6v/uRdwi9+DE2bHb9kj2MHPMUrZT3017/A4IYerdE3C5ju2NKwvNm+4Y4rAACDSRlbsuy+38JSKVZtkpISXtAt2kH9yy1lyQzTduHd1N89rtDCYwaXtQSGZaw2JRLBxdpk1/DRLCuGV1Dc8Ueo34Vc1UJH99I7coFmkgSQHEAAACAASURBVLwkD8pr5K2lfWRZHPQdkNcoW82kMjW0jfHKc6qupmtWw1Is8lSHAPD8FkpJFmDyHLtVpr/lpOfQBfNUu6qeFi7Zvuu+h+S2vRpbZgHTHVsWr4zYW3+dr1491rjlb5Y97NjLbio9bkkvpX7Y1iDlpb1DJIHZ/I4vOXbn7d+QOwlQPwztYvFov+yHHtY90jXUHeKt0s+bpHWhk0he01FPaVA/Ou8hsc2nnnm3Y79x2TrHvmftCcLv2M5uagOT3W59WaZsbFpIx13ZSNvsisoqqu+YS+NDL6sefkX1NuH39o3Uvu5BioOJbhlbvI0Un3gl0dFM8TSvj33k7gmPW8Z8Ym6MORPAWQCajTFXs1W1AFSMpyjKYaGxRVGUcqCxRal0xpOyBABUF/x4FvZhAG8vuoWiKMr4aGxRFKUcaGxRKpoxB+bW2ocBPGyM+ZG1dudYvuVkJBvGn0bzsoiloW6xLpGjrCUv7KKyWRtulBlMSnHF438rlkejNI/Mp4p9I/KHdqaFpk+9A3QZX/nqp4XfJcdf69hDK0gagxPkNHeqn6aiHn6GJCA808F7Ln1KbHNKE8k+nhha5NjvnSf9nhqhzFA+Nm9e3yirh3EeXbfMsTs75VvV9xl6g/uyBpK1fKr7VOH3fw+zt7mzNINTc6p8oxysWt+BUYqj9eG4cKvxy2umVC4zJbYkMj5sLlSBbIrExLocq5K5tJPkb9t6ZHk+/yi7tzup6t5wt6wo5x+gGOJjt7JHqkiQY1GZy2SCgzJzSt16qsCbmE9TrrFWKSNhpyFkONZLduhsee6ZVpLQpZIUY6taZTaTeIz24WXT5Nb1XNL6aV1gN031puvkOQ2nSQ6TqqYL0d1bJ/zqn6Pj5nxku6fas2EmOQxT7MulZAM9gWkrEKkcYWZKbBnOhnH/YF4uurxKVgSPsVROD+1Y4tgbv7wZE6HrP2+RH4xSX+FymHBWDvHi80mjkmyge37jlz8r/C6d+3eOPXD+AraNVGJ4WRxLPU3jm21Zste9b6vY5pROysr2Yj9lW/rASTIL2wPdVCld9OoaKXGtCZKk5LGdlPGltkqOF3YlKTOUl0l6b+yZL/wOPEDLqWYmTZwr9+cPUDsaAhQ/Pa7MNcPpEikBx2A8Kcu3rbWfAvBd486TA8Ba++YimymKooyJxhZFUcqBxhal0hlPyvLjwv+3jumlKIoyOTS2KIpSDjS2KBXNeFKWNYX/Hx7LT1EUZTJobFEUpRxobFEqnTHTJRpj1sIl7+FYa1eVo1Fu5h1fbz96d74K1DMDXWLdXYt+7dgf2vFGx37OVYFz22euxkS4fi1VsvqvV0gj7dkkU+UEhkhrxfWUdVulVtF6yW9gKeknF/xQ6q42fYq0UbkAXXJPirbPtsuqdm9dQdWrvnXS3bTvu/5B+F11AqVyPT1Cx72j5xzh9+IB0nuNjpIuamWH1MftGyU96+pL6VgLvv1N4eebxyoLriMNfXyu1IgFG0lLHmC6raBPXss1l30VAGCMWWOtlYJ2paKYKbElsmSuXXLbhwEA0bjUZi9to3crXn6R0vO1SSkkDh5PfTRTTacU6pVpRpONpFf0j9C6qr3yMtTspj6QriY//6jUY3vStBxvIh14/boB4ddzFuk9k6yCqZeFk3iLbEO6g1baDLXBjMpnOZEOSmPYWkv29g3tws87Svvg6SEz4dLfP9ZP62q2Sk04r4joixX/HABS9XSNciGyTVjGIE9BA7/32u9rusQKZ6bEljnHNtvX3/E2AMD2wUax7rcn/Idjv3/zOx17x6Odwm/Tl+Q7a6XgaRENGzPUbpb9ppbFllgze+cl7k6DSMuZEEsHfVD2m1Qt7SPaxvo4Tw3dLNvaeDq9r8MrkbrHD8tOIi36wmpK+fzHnUuEXyZNbTCsIrDfL8cPXNW0/vIbad/fkseNLKL3hOwTlHIx1i7jb7CD3tGbN4e2WeZKG/39U35SOP7Exy3jSVkO1ZH9eOH/Q1NE7wUQe7W7oijKhNDYoihKOdDYolQ040lZdgJOtayz2aprjDGPA7ipnI1TFGV2orFFUZRyoLFFqXTGe2J+iCpjzDmHytsaY84CULrE2hHGgqrwXT3/frHuugMkx+DyFeuqKHfyVbc59kgXW7FEpv9KDTB5h4+mLlo3yf0lWNqg5qfpR/jQYlnha/UdJKE54z00ZbL9I4uEX4hlEEzWk509hqXoycoZ1iRLFbno63R+i0+T6Q3Pqdro2L1ZkqE0B2S6xMwzNG1jVtA5bb5PtjXRRNfl9SE6v5odMo3csDfi2ClW3dM3IG+7JOiabfro56AcVUxrbDGw8Hnz9/OpHTLF6urddD83r2GSMr9ww9zH6N4eOcbPbFelzjTrv2xWtHqvnB42GVpZu5alROysF379yyntYNML1F+jC2VqQf8oawczo/NKKzYsSycY2kPnlOiScrp5dTSFO5CgfhxslQ8mg5tIY8LjW9VBVxvYYprUb6+qesolgrwwsVdmWEWArcxUsb9hRh43GypMe+dUxTKLmN7YYgBfIS3fZR3rxboPbnmHY3P5SkAW9MQbzv2qYyeaSGrXfbYrHymXyfVSf21ZI8c3mQh99z73K/quPfkjtwm/Z/7zM4599tvpHVr/sKyYm6xjMhKmHIm1UX91p049cJDi09Kb6biexTId4clzKB6v7j/GsZtq5Dn1PUqyuXgHtc+zTwbqZGPxlKjBg1JyGGunuOpjd0tgyCVNBAWoB6+4vui+D5eJDsw/DOAOY8yhKzoI4ENHtCWKohyNaGxRFKUcaGxRKpIJDcwLbzmfYIypRf6F0aHxtjHG3IG81qvHWrui8FkDgLsBdAHYAeCd1tqBUvtQFGV2o7FFUZRyoLFFqVTGKzD0PmvtT4wxV7s+BwBYa28rumGeHwH4LoD/ZJ9dA+BBa+0txphrCstfGK+RAZNBZ7APAPDw6LFi3YV16xz7uVU09Rz7eZvwC/fTVM9IF5uS2CxntupXUn8b3kZzru6qezW7aUp3pCvEbDkVev5lX6c2pFgVqaS89MOdbL6H7cLsp2kV68pg8PT3T3bs7AXUntaInA/71QC9CHzFnNWO3ZuqFn6f/EvKcHPLs5c4dnyZq+JViKbet+xodexwrXDDjk/QdNjy66gaWapOnsdOla8cdcyU2AID+Lz5Kc61PTKTSHM9Sb16VlCc6Lhflur0xag/WA9Nn0b2y1gwdBxNpfpZJWF/VEpZvFGajo13UQyKtsup2cZ11C/9B1if90opS6Ke4pM/yrIWsIqlmbBsa91LTL7SzKpnuiSCORasAl46v8RwUPilTyeNiX8zSV6s6xsox8JgjlU9TlfJ9vnYebAifkjXSL80y3CVqWZT2XJWWplFzJTY4jdZtITymYr2xOeIdec3UYXPV1qo0uQxrtjiSXDpCElZ2h+Xsow9b+NjC5Z5aVRKz/zdg4593htpbBKolXoTPm6p2UW/Z3JBGYOMpdgS6aE2ZMPUwbIyFCDyR9pmmCVYyYzIfT97kCQ+jSGSr2za0yr85p5DWV72baUUMClXVeEVJ1AR2LPupz9fzi/Hitve/UXHPvZLNG7J1MjYt/2Tn0G5GC88Hfo2qinxryTW2kcAuGqv43IAdxbsOwG8ZTKNVRRl1qCxRVGUcqCxRaloxsvK8m+F/28cy28StFpruwv77DbGtJRyNMZcBeAqAGicGyjlpihKBTJTYkugpbaUm6IoFchMiS01bZFSbooyJhPSmBtjFgD4BPIaK2cba+2by9MswFp7O4DbAaBrRXXpKhSKolQs0x1bqpa2a2xRlFnIdMeW1uMaNLYoh8VEs7L8GsC/A/g/iERfk+aAMaa98KuzHUDPuFsASFkfdiabAADtgUGx7l/2vNax51aTFurgZplaLM5SDVWzrGgDK+TpDA3Sr9zACGm1cn6pXcyESJPF9ec126Vf+HnSNZkwaasC1fLXdDpC7c2dT3rR4G9JLxqdL5VHo6xIGE9vlslJvdj2KKs6xqRurxyU2iqePrG1ma7l4NNS08X/BOmTSOeaaJe6t0W3kpTPMDm7N6EpyRSHaY0t2awHg6P5vhjwS633vl3Ub0wLaT8DA/Kdi1yItJFVB6gPDCyW4TXYS/2Sp0XLBmV/NWmuF2Vp0GLyez64o4/thPx8AzJnYJWf4kbviST4rNpP2wwulX0yF6DlMNPKpxqkDnRvhOITr36HlIxVPDJYpv10pyCr3k3r0hE6brJBuIl0iTxNm1f+aZCuYbcUq/wZqZPXKJksnJdHx1KziOmNLdaDkXT+O78hIFP8/XTbKY596akvOfaO7xwj/DJ1LAXpIOnNDy4PCb/wBoo11XtYqkK/jC02wsYgQxTTBpbKd+3mPEZVN22COpXHyDgRqad48scH/96xT38fpYbef4EcF3jjFEOqd7K2Lh8Rfjv6qNMvW3SA/OLynAb/P3tnHiZXWeX/76mtq/c9S2cnCSEQ9gAB3AARUEYQ3NBxX3+4gTgOOuMgruiojBuOzAyLCoqIOo6CgCjKIgkJa0LISkg6ezq9r7W8vz+qcs/7XvpWVzdd3VWd7+d58uTcuufe+97quqdO3fd7z+mznlmJ6Z85NOD6bXzwCAxHqsK95hd9Q/OWxDz9Tojtyzddfvnke6QBY8z3xuF4vwPwHgDXZf//33HYJyGkdGFsIYQUAsYWUpLkm5h/V0SuAXAfAO8xX2PME0EbiMjPAbwGQJOItAK4BpkP9i9F5AMAtgN4S9D2hJDDAsYWQkghYGwhJUm+ifmxAN4F4GzolJDJLg+LMeaygFXn5D26LC3li3DtscP/SP3Bhn/z7IHnVA5SP8/1K9+vUxLTHrHLmbpljIZq4patUxydR7jTItPW6LRSxbrdnh0+2i25lpqnMhC79FHvguCHzvo36/RwxJpS9pf/CU3XKaaWBp0bb+1xZTxL67Wc0J3tp3q2vxtZm1U+sbFcO/ftmeV2+4paZY0iu6xyjr4OX2859xHPvuv32hnZRDhdTDwmNbYAQDrb7TGRdD/A4S5dbn5C7YHprvyifLtOwVYdUDmYpFz9xWCtbjdYo3bvDFceUr/OKi24Va/d2H73ujYx3U4SrgzH8YvosewOmrYEJNLrTlHbJQh75+g2oX733Pu79frf2t+k4653NSWphL5/JmbXRHTHGh7SY6UjwZK33lM1PtX/Saeyk3FfWcU+q/OntSrS4B54WnOmTO7+6PDdAUlJMqmxZX7lfNx86s3Drluy5Uue/ehPtexx9RL381e1SXMVSetntsEnKYntV6lM11KrxOpctyRy9TqVv0We2+bZMwdnO36pFpXxhfdb5RJrXcnLQKPGoBM+ZnXxtMqvxne68c3OEzosKbHZ7eZEFc16Tvdt1TLZTbPccvTdfRqDpEzfv8pW97ghK43pWGbFyzL3PX/t0c979mO/Ot6zBxsnLm/JNzF/E4AjjDFDI3oSQkj+MLYQQgoBYwspSfJts/A0gLoRvQghZHQwthBCCgFjCylJ8r1jPh3A8yLyOFytVsHKDhFCDgsYWwghhYCxhZQk+Sbm1xR0FC+D3h7VhC89Y5tnv+lNTzp+H1rykGefX/cBz66b7mqm9p2keqVYp+qkGte5OuvwgGqU0nXaTCza5WupO6T6pe4jVTueLHM1Yrb+dOtVV3r2sVdpS9hQwt1m02tu8exLNp/r2Tu6XN181BKMVoSCZ/Wunv6AZ7/hiQ/piqR73J55ek6fPOdez/7PX73e8fv5yhWeXW6VQkqtz9l8jRxeTGpsMUnBUHsmhlRN73HWRbv0mtx3geq+Tdq9Ho66ztIoduizHpVbXc16Yplel+UH9Zqs2u6W7pOEtb8yLfMqfa5u28R1XbJBY0vaV34xVTa8VtsuASs+aXX1eapt712r/VSM/xvDKotoenSlaXRbgc+0yq/u3q/7szXlANDXrPvrepWltX/eLS8b2aTLnYt1HzVb3f1Feuxz133XV7jveW0s896G5eVU1SNFRtHmLQMHrbzlzZs8uyrqXje7Pr/Is6Or1a9soNHxM+Wat5Tv1+/4SJsvtiStC71K9eehHve4pkyv5eQMnXRIVri6bTtuPPXDT3v2CZer3jzSB4dL/vGvnn37va9SvwVu/O1r12dHIgf1uO2z3fh2wpxWz37ycX2/0r5YNWCVlX/raas8+86nT3b8HlivenYs05hbudYtUVlI8krMjTF/HdmLEEJGB2MLIaQQMLaQUiXfzp/dyDzNDAAxAFEAvcYY9rMmhIwZxhZCSCFgbCGlSr53zB3tgYhcDODUAPcJZelsnXJtKNPyOrduP93xS5jXeHbyWJV9lG1vd/zW3f8Nzz7/mM9bO3DLkcmgK23xCLnliQ6crNPXIWsX/tKC1Tt15YLvatesmCVxcadlgaWPvMuzv3K8lpP8a8USxy9tdB/HVOz07Ac7jnL83rLuPRiO6Y+4zwh3z9XlG/73As9OLnCn2ste0Kmf5z9ctLOKZBKZ7NhSWTGI04/NTBGn4V5fKxfoVGo0YnWkHHDD5rYv6zTy/M/r6Uib26U43q7r4ts07siQL5ZYscbuuicVrpxjaLruz4TEst3dRfp17GVddplGK7b4OmbuseQr1Yv1PLq6yl3HXp1ijk3XOeuhfnfKe9denQ63m2va3UcBYKBOx1S5Ss+3b6YrUYnasdAyBxrdv2HUaiYoKV3XOxRz/FoPZMbXP+SOm5Qukx1bcnHi0m2enbSSga2dTY7fmd/RkuvPvMv6vu50ZR9/3Pzvnn3+9Mt1RcKVrqatWCOVKuOViJuQJJvcPOYQ/thSvkcDx4rLNG/pPU6vNV+zdvzsGf0TnHamliZct9/tRD4AjavJZus8Otxr92loqceQJbud9oQrzzm4VPf3h1+c4dlyrCv3MUk9yW3v+hwmg3yrsjgYY36LHLVACSFkLDC2EEIKAWMLKRXylbJcYi2GACyHThERQsiYYGwhhBQCxhZSquRbleUfLDsJYBuAi8Z9NGPg7ld9z7Nfcf9nPXtJ3T7H7xuPqeRC3qqnveiXeR4o6nurenX6I7lb5TShhqXuZn0aB+xpoP46d7KirEunYOzqK/ZUbM/x7nzzUU1tnr0/qbN2Z9eud/z+e+crPXvVPr1hcFTDXsfvg/O1U+e3fqEx7dRPPO34bejQae7WTWpHWsscv41fuBKEjMCkxpaIpNFUlpkW/l7L4866q+Lake83z57o2WFfpzi7ytDu16p8teVuXyWnfms7q4sfjJsrmEGdgk21HdSxVrvTy2Jtlw7ZHYLdWGVXPulv0LgTHrRen+ZKQNJlui5ldF1Dfa/j1xlRacvgQbWlwpX+hSwpUPkeHcPOi9zp5sq1GkMi1gxz+V53fAPNVgdT61CJave9tLuHhq1DtXe5sqBUX/Y9Sw9fwYaUJEWbt/z2FTd49hn3/bNnt1S5XS1/+ZjKPqLvULnJwtvzPFDUlX0gpddhav9+z45Uz3fcjH0Z2F1GQ+71EbKq0/VN0+s6bqVfCZ8qJt2v8WkgpfaM6m7Hr9fq6JluszqMV7rxV7Zr3KnZrK93Xenur+8pfS9sKVz5s64877mvT37ekq/G/H2FHggh5PCDsYUQUggYW0ipkjMxF5HvI8fUjzHmk+M+IkLIlIexhRBSCBhbSKkz0h3z1ZZ9LYq4YD8hpKRgbCGEFALGFlLS5EzMjTG3HrJF5Ap7uRh5+NxvBq88JeD1T4ztWCaZGvb10AFXI1azWXVX+5er/rTzGFeD2XKJdq9KD2qZwV2tDZ49o9ndd8+Q6q4uqd7o2bd3HeP42d3ENq9e4NmPVLvdwz71pj959jkXrvHsbb0Njp/9Pr8Cnx32dUJyUSyxpT8VxbPtLQCA78SPcNb938ZjPTu+Ra+1ylb3ZtxQra1j1nVdJ810/KI9GjOconwhX3EsM/zNPtPrlvWKtOtyYo7q3DsXuKXPBpp0f6Gk2uFBSy/qO2TIWtdgdcnc0+Hr2iuW1juu51exzu2SFztTn4fpPN46rq/0Wf8Mq0vxbqurqO8tsht0pq1diO88BmZacdoqpeYvRyb92feMGvOSp1hiS748+rpvBK88I+D1q8d4sNTweQsG3bKKdmfzoQa9lrvmueVEU0fqxWeXgA4PWM+/+DoPRw5q2rm7V3OiVNq9KmuqNO609+k2tU+5MWPupVs9e+2MWTqe1jrH78XPa2fSxV/TzqSbrNeLhdGUS+TTzISQQsDYQggpBIwtpOQYUx1zQgghhBBCyPgy0sOfdkvbChHpOrQKgJnqrW3/uO5ro97mdad80Vnum63dtVLWlE6s3i19uLRGSy4mrDmhtFW3qLG8z9lm98/ne/YbEvoA+uvnrHP83j5tlWc/sUS7ZFXG3XJun93yZs9+/xwtnfjVma2O33tWadexHVvd8pCE5EOxxJZEMow9HZlD/WDnWc66+GaVrww2qHZiqMZXWrDZqsPXpSG17jn3voc06fKBY1XmUrPNnV6u3qDlu8JNlozM352vXv0G6nTdUJ17kzDVouMzYV03NGDtL+GOdfrDurwroWNNz3XjVrU13dx5QMfT1+J29Ozfoh2Qy+dpGbPaJleet2ubdj5MVugYElXuOSWrrffM+nOE+9zzCNXpFL2tEGqqczsndkYz+5OoO25SehRLbJks/rj3hpGdfLzu1Gud5VRc41iiUuPEYJ0b+3qOUMlLqF+vvcYlKl3r8ZUmrXpIc6K95c2eLQ1u6dRLjnnKs3/VpqVrO49x85Zn18/17OY52lF5bo3b1X3+T7/u2fF+V2pXbIykMa/OtZ4QQsYCYwshpBAwtpBSh1IWQgghhBBCioB8O3+SPLnv8S8Grlt855c9u7bKrbDw2/XHe/a3T7vTsw9VjACAF+5b4Gyz/kfDd6g68f99x1n+05u0w+c3T/61Z3//xbMRxMGktuu6ovV1zroHn7TkKxGdH7anigBg27s+F7h/QoqC/hDkqcwNtv947y3Oqk+Zyzx70VxtZffq5k2O300PvdqzQ4N6ryMV91X4sBb7rc6VqZhPohLXagIV+3WqeKDBDddd8/VYaatYQrLClWPIAa1iULNIp3fbrYoIdc/4vgqM7qP5CbXTz7jdffcv1+Xy+SpRGdwarBbo69Fteg+6Xffiu3QcdpUH/yN80Xqd9k7068mnk+57biy5jlh29Ux32jwWzkhZdoYDqlYQMoW5b1VwRclj/vl6zx6qdS/E+F69Xs95g1Zy++PGoz07tt69xp/+wfB5y8kfdPOWXyVO9uw3n6D7/tWqoBJ7QP+QxoInts511sU3qnwlaUnj5v/gW47fto9/JnD/EwXvmBNCCCGEEFIEMDEnhBBCCCGkCGBiTgghhBBCSBFAjfkEsuktX/DsBbe7pRhPnr/ds2/fe5pnd/S5+iybpf+q2q94W3AfhYHfTPfsS370pNoLRxhwlnk//nf3BUtXLjFqMknpYiLAwIzMZ7g77V5r/3DsM549P67lv/58YInjJwnVNadqrI55vVGfn72gZv9M9xqStGqhTdjST7tSdEfvaXfGdDp6AkhM0wO379eCFV63SwBpVzqOwVrdYbzd0qz7ZPN1z+sLB8v0uRRT7YsLMWsfSWvfrW4XP2PFFqejp7s3JLpiGI5wv3uvyVjvha3Dt8vQEkKCWfcN1YQv+dL1zrrUUVp29L4tGhfF34LX4qh/031U7gr2a3pYL9hvv/eXap8wwoAPHecL7lhtXXmysrjLovKOOSGEEEIIIUUAE3NCCCGEEEKKADEmeCqhWBCR/QB6ARyY7LEAaMLkj+NwH8M8Y0zzyG6E5IaxhWPwwdhCxgXGFo7BR96xpSQScwAQkdXGmOUcB8dAyHhSLJ/lYhgHx0DI+FEsn+ViGAfHkD+UshBCCCGEEFIEMDEnhBBCCCGkCCilxPzGyR5AlmIYB8dAyPhRLJ/lYhgHx0DI+FEsn+ViGAfHkCclozEnhBBCCCFkKlNKd8wJIYQQQgiZspREYi4i54vIBhHZLCJXT9AxbxKRfSKy1nqtQUTuF5FN2f/rCzyGOSLyFxFZLyLrRORTEz0OEYmLyCoReTo7hmuzry8QkZXZMdwhIsO34iOkiGFsYWwhpBAwtjC2jJWiT8xFJAzghwAuAHA0gMtE5OgJOPQtAM73vXY1gAeMMYsBPJBdLiRJAFcZY5YCWAHgY9lzn8hxDAI42xhzPIATAJwvIisAfAPA9dkxtAP4QAHHQMi4w9jC2EJIIWBsYWx5ORR9Yg7gVACbjTFbjTFDAH4B4KJCH9QY8zcAB30vXwTg1qx9K4CLCzyG3caYJ7J2N4D1AGZN5DhMhp7sYjT7zwA4G8CvJmIMhBQIxhYwthBSABhbwNgyVkohMZ8FYIe13Jp9bTKYbozZDWQ+fACmTdSBRWQ+gBMBrJzocYhIWESeArAPwP0AtgDoMMYksy6T+TchZKwwtoCxhZACwNgCxpaxMimJ+Si1VzLMa4dVKRkRqQJwF4ArjDFdE318Y0zKGHMCgNnI3AlYOpzbxI6KkJfC2DI6GFsIyQ/GltHB2DJ2JjwxH4P2qhXAHGt5NoBdhRthTvaKyEwAyP6/r9AHFJEoMh/u24wxv56scQCAMaYDwIPI6MbqRCSSXTWZfxNCADC2jBbGFkLyg7FldDC2vDwmvI65iJwO4IvGmPOyy58DAGPM1wP8I+HyikS0pgEAYHw/JWK7ez07Mb3Ss03Y59eR8ux0zNqJDPfDNkMqqna0332fBmt1u7pqHUPXwUrHL7pX10l53LOTFe4A7fFG9uk2qChXu68/cKw2Ei9zlhNVkWH90lF3eVnL9Lz2P1HsG9g47OsHdw6gp30o+A9HDkvGEluiiCXiqBxuNTkMGUAvhswgYwtxGFPeUlaRiFVn8xZ/PnJAv8sHZ5QjiLL9Q56dqtQCIsmK4LEa69Mb63bzlqFatadV603s/R21jl9ZW9KzTUTz91Fi/gAAIABJREFUpXTEvTRCQ7p/GUroNmWaXMjAoDvAkO7PJDUvkzK3QEo66nvTsiTL3TEcM6e48pauwbXDvr53ZwKdB1N5xZbhM7bCMpz26rQgZ2NMsnzGHBzxnk8DeOkHcu61j3r2nnee4dkDje4HcsFd+iHsm6dfxOlw8PvUPVs/GM3PDDjrtr1BP0QXnbXKs//0sxWO34zrdXyhRUd59oFT3EpBiSodx/Tv6zay7FjPNo8/GzhWm/D8Rc7yvlc2D+vXO8s999XXXJnX/ieK7z9/9rCv//ubV0/wSEiJMOrYUiMNOE3OKfjASGmw0jww2UMgxcmoY0tF8xwsuTTznTpU637XzvmxJm+bP3GMtaG7n8U/0kN2nqpy6H0nB4sdUnHdyey/pJ1129+g9qdeeZ9n/+i3Fzh+C29r8+xEgyZdg41u8lyxS39ghLbv1TEsmOHZ4ee2OdtIpe4vdUCfUw0tnO/4DbRUYzjajnFvPK6+vrjylvtfOGrY1z/2xm1572MyEvO8tFci8mEAHwaAcEMdeudlflnFpvU5fr2X6rXx7Lf1D/SLzcsdv6/veqdnNz5nJdm+0bQt1bva4XP0w7mrutE3Qv3A//rpkzy7zvfjsPvtmqhLSk+zrMu9YCDWhXaqlYyvyi8ZDy3TD4P0unfWq3foL9k9K/TCivlUX2e85Vs6vvYkgvjLnwpX5ei8477g2VvecaGz7lMX/75gxyVTglHHljhy3HoihJAMo89b6uvQviz7Pe+7+bvhS6qCKWvTXX//vT92/D4++BHPbnpG7y7XbHH313mk2pe8ZqVn3xU5NXDI/73hTM8OD7int/80zXeifcay3bzlwAlVnl1foenkYL3eMS9/zE00Bl+5xLP7GxZ4duNjex2/+JMvePbOf9T8Jjzkvu2nvfPbgeOzefg3/xS47uVyzllf8+zN73qfs+6/z7p51PubjIc/89JeGWNuNMYsN8YsD1dV+VcTQoifUceWKMr8qwkhxA/zFjJhTEZi/jiAxdkOTDEAbwfwu0kYByFkasHYQggpBIwtZMKYcCmLMSYpIh8HcC8yEzw3GWPWTfQ4CCFTC8YWQkghYGwhE8mEV2UZC+WLWszC73wQAND7gvv0sCRVG5VqVC11dJ9bcmTxj1o9u+8ofYp3oMH9bVL3bIdn7zqnwbN75vu0S80qJg/vUF16+V5Xq5WwCj6Utasd63Hf9/L9qumOdeqT2OEuPU6ou9fZZmh+k26z7YBnp6vdKhPptc979uDrT/Hs3hnuudu697KDOp5EjSuQe/jXL0+rdX7DBwPXpRfM9mxJpJx1L16U+Xts+5/vYGDXDlZOIC+bGmkwfPiTHGKleQBd5iBjC3nZzDym3rzn9kwBgzvWnuysk30qoUtV6vdupMP9rm15WL8De2bpOn91usZn9bmy7edrlRd/5bX659QerNOPedJXmMqu7FKzzcp9fFdGZEDzGLtiS/2Dqg9PznerpoQ379TjzNIeQ6G9bsPSe3b9wLNfc/43PLtrrntS0d7hNfCJCvdNWnnbVXg5nN/8kcB1/cuP8OzIgJu3bM2mO7u+8EMMbt2ZV2wphc6fhBBCCCGETHlySllE5P+QozOSMeaN4z4iQsiUh7GFEFIIGFtIqTOSxvxQ/bxLAMwA8LPs8mUAthVoTC+lJwzzSKbud42r5oCcryUN2w9o3UvjmzA4eIbWAI316HSHv1j9tktVvtK41pqSCLlTTD1WafAya+bTnlYBgJDVB+fpH2g5R3tqBgCQ1u0iW3Z7dmqvNscaOM8tARm7V+t5mzqV+Awc5U4dRRpP9OzKdXs8u3P+HMev8VktRdlxpM5tpWK+gv7/fL1nr/vG6GuIJo49wlmOPrvVs9Nx/Uj2HeE+1d60LiOvae0vfvkVGZHiiC2EkKlGUcSWg72V+PkTmXKF0utrKNikctXyjXEE0TtTt6vfoLLWvhluPfEtb1VpTN1zyIuaHZrfJMvc7/jueSqmWPVTlYCcde51jl+yXMdXcdAqQ10efE62fCVRr7Kb/iPnO36nv03LN9c9q1Lk7lkLHL+4Jbvtnq0yF7+M5+jPa97y3NfGkLcsm+csR9e+6NmpuL5f+05y/zayJ5uvJPIXqORMzI0xfwUAEfmyMeZV1qr/E5G/5X0UQgixYGwhhBQCxhZS6uSbwjeLiHebU0QWABi+nSQhhOQPYwshpBAwtpCSJN9yiVcCeFBEDmkO5gMIfkR1nIn2GUxfnZkm2b3CnSI5dZrW+H9wj3aHSkdduUPHkfobJN6mdrLccUPlLt2ud7pO04R8HT1rHtUNO5brtNScz213/LpeodMu54be4tlyjvuUtq2IaztvoWcPVS3y7JbfbLW3gN2bs/+0xZ5dvnKTu+9m7eJlV2zxV4bZf6JKR5KVOrWV9n1KYl263flLP2ft2/3bhHqtqbf5dfp6uTut1/5m7YLW+N9/1xWXuh2PB7PVYUyYRROmEJMaWwghU5ZJjS2hAUHN2oysoXuhr1LHuTd59hF4v2fHtrnfoYO1+l1nQmrXbOh2/FKxGs9OWM2Me+a7Y5rxmI6jr0m/h5+48dOO3wVzPuXZ516neUtkxXG+42oulbJkqJ2vaPHsxrs3uNu0afUVc7bmQXVr3M6fyWl6Th2v1BMJ+ZqSty1T6Yhdrcb4uq3a0paTPvIdBFG9Xav7hQdV9uzPOvZdrB1Mpz28X8e6cJrjV9ma2TI0hLzJKzE3xvxRRBYDOJT5Pm+MGcy1DSGEjARjCyGkEDC2kFIlLymLiFQA+CcAHzfGPA1grohcWNCREUKmPIwthJBCwNhCSpV8NeY3AxgCcHp2uRXAVwoyIkLI4QRjCyGkEDC2kJIkX435QmPM20TkMgAwxvSLyIQJfWUwgbKtGQ1P5bzZzrpV/3usZ1vSKsRcCdZLtOSHqNzldvS0O1l1LlSR0rEXrXf8fnH6jZ695Fotw5O4vczxE21ehSGr3GGywqezXqLL8QM6hqrdlibsOPfc442q27ZLJ7pqNkAWz/Xs0CbVwIeX1Tl+bcernapWIVfVJrfuULdVrai6td6zy/7wuOPXe+GpGA6TdrXt8Xb9G3S8+3TL0d0uPJh5QXxNWElJM6mxhRAyZZnU2BLrSqHlz5l239vj9c66hb/8qGfbA/J/t4UDhDfhjh5neaBeyyXb+5CU+yVqd+2e9+N/9+z3rXqf49d5+jGeXbFTn5cdqnNLAQ5ZXcFDSb3PW7tVO5Gi3u3WHhrQk4o+9Kxnm/lufhPuVr/ap7WU8+7Xuhru3tl6wqHpWrKx5kE36Ws/Rt+L/jmaJS39lttxdN+rdP/VrZoHla/Z5vjJEfr8375X6nsU9T27l4pn/sKj+eDle8d8SETKkU2VRGQhAGq1CCEvF8YWQkghYGwhJUm+d8yvAfBHAHNE5DYAZwJ4b6EGRQg5bGBsIYQUAsYWUpKIMfl1URSRRgArkLkj/5gx5kAhB2ZT2TTHHH1hplNTVatbcyYd1QmC+E6d3ule4k6fdB6hUy7Rbj3nus3u/srX7fTsTdfrlEb0abcLpSOVsaaOUj7JTFm7HqusUx1Tvk5bHYt18qJit25Tuc8vTFHC/bo/W8oSWnaU4zc0TUskth2jUht/l1J7fG3L9P0abHbHUDe3Q/ed1N92c/7N9etZrH+DSJ+uS1S5Mp7qDZ2evfdrOqaKW12pzSGeeeC76Dm4g3KHKcJkxpYaaTCnyTkTdThS5Kw0D6DLHGRsmSJMZmyJz5pj5nwsk7e0POzW+Kt4SiWlrZdpeWT4pCy2LKVui5bxi3YlHL/Yi3pa97yo0tqTPuwrC2h95SeqrVKMvtKCIWv3KUudW7HXzRlsqUwyrvurfUHzqvhzrc42ybmaV4Wf1+6Z7W842vET61AdizQ/8st97OW+WZpnmHI3HzlivnZRf2H9TM9e8Btf/UXr6u+bpjLesi53f4OWjOfA8bpR9TYMy8ZfXY++ffnlLflWZREAFwA42RjzewAVIjK8gJgQQvKEsYUQUggYW0ipkq/G/AZknmy+LLvcDeCHBRkRIeRwgrGFEFIIGFtISZKvxvw0Y8xJIvIkABhj2kUkNtJG40W4P4X6dV0AgHTcrRASO6BP4aZqtWuWLY8AgEfv/LJn2x04IwvmOX49y7WCSf3dOlUhaXf+pPZnj3l2r9Wh8tE7P+P4ve7kL3p215HVnl33TIfjl4rpU9sN61SS0zdLtTGdC9w/V8SSolS/4RTPrnhko+tXpecYP+i+fzZ7T7Wmi+bpGEJp9/dbY6U+Ib23WyU+7/v1PY7ft7/yDh1DX7AkZ8+rGjw79is9p47F7qxP3abgfZCSZVJjCyFkyjKpsSXaazDz0YxMItrlSmZTs7WKR9Mz+jzqgePcqm7PXH+lZzt5yxy3gsnQEbq/U96j8pWyATdvqVmveVGqWo/1p0f+1fE7++yve/bu0zWvivS7+0tUam7Q8JzmBaEhlYd0r3BzrCFrm8icpZ5dvt+V55iI+jU+Z1XLW+DqbqpadUzVr1ZJz979rpw5ZecxVmpx4JN9jl/kbqvanSV7TlS4eVDfDF0OJdVvoMnNW+wqe/mS7x3zhIiEoU83N+MlaihCCBk1jC2EkELA2EJKknwT8+8B+A2A6SLyVQAPA/hawUZFCDlcYGwhhBQCxhZSkuQlZTHG3CYiawAcKl9wsTFmfa5tCCFkJBhbCCGFgLGFlCr5asyBTGPNQ9NCAX00C0TfAMyadQBe2j0p+coTPTs84Ct7kwfJF150lkNHqlZroFHfnppt7gyYrSuP9qj2+dwVX3L8TFz3UbtOdeXRH7oa88aPqW2XerT3Xb3d1VhX3rVSx22VSDSzZzp+kR2qu6p9bJdnO1024Zb5SRxQ7fjgyW6Xsc0vTPfs+Xfq69eseKfjV2PVZuqbrtr2aK/7XpZ16bJdcqlyl6vNOqTfF/mnNSBTicmLLYSQqcykxZZQ9wDK//ocACDd2+usMyuO8+xop2rMZz44gHxI7nBLEIZm6XNa5W2aB6XKXFHEYIt+rw9Vq1b7tH/8trv/Bao/j3Xp63vOdDOwJuub+ODR2nvd/k7/+x3uc3e2Vj7crPkWBt3eT9Kk52QOaHfOgx9b5vj1TddzTPxNc5OZr97j+G3fYK37m77e0+J2ZTUhzTt6ZtvdTN38K9KnfpFyfV+SFW7e8tQNnwYAyI+uyjtvybdc4r8BuBVAA4AmADeLyL/m3ooQQnLD2EIIKQSMLaRUyfeO+WUATjTGDACAiFwH4AkAXynUwAghhwWMLYSQQsDYQkqSfBPzbQDiAA7Ns5QB2FKIAQ2HhMMI12TkHakOtwxidKN26jTN1tRHuVsW8PiPazeslnlzPPvgmbMcv7Y3aumc2JNaWal3uju50GtttvAn+z07XePOloX6tATQgVN0yqTqa24n0faz9FipuL1Gp5umrXGnesJ1KnnpsuQvtat3OX7Jne7yIRqeaHeWB2bpmOyOV5G/uWO1+cvNN3j2GVd+NNDP7nTq79wV6depn1U/uSpwH2RKsg2TGFsIIVOWbZjM2BISSDwjCQlXVbrrulSyki6zcpWwKxWxyy2H6zV/SB411/FLVus+bPmKpF1ZxcElmmc8810txXjsVdc7fnbtmrQ1vModbh7U41Zt9Agl1e+1r3B/B0Wma+fPtFU2MrTVzVNs+UqqR6VA83+x0/Hb/6oW3bdV+TB96zTHr75G39u/3/Fpzz7vxH9z/AZm6N+qrE3/TkMNTmLm8OSPPhO4bizkm5gPAlgnIvcjo9U6F8DDIvI9ADDGfHJcR0UIOVxgbCGEFALGFlKS5JuY/yb77xAPjrSBiNwE4EIA+4wxy7KvNQC4A8B8ZH7NvtUY0x60D0LIlIexhRBSCBhbSEkixuTflUhEogCWAdhpjNk3gu+rAPQA+In1Af8mgIPGmOtE5GoA9caYfx7puLXRaeb0psyTvLZcBQDSa58fdpt9l5/hLIeH9DztDlV+dpyr0xjx/YFuiPXo/ir2JgL9jDU11b5E54RqtrlP+PbMVMlK72zdd/le3b661fdUsNXVK9qlT2KHHnoyeOB5Ys48wbMTVe7vt21vsxYGdcrqyP+3yvGzK9fYnVjbj69z/Fb9dHTyFRFZY4xZPqqNSFEzWbGlRhrMaXLOSG7kMGGleQBd5qC/+BcpYSYtb4lNN2fMuCyzEHW/Q/sXNnl2pNf67vZVlgsNam4h/a6U1ab1YtXW1m/QbfxVWSq3aYW1noUqUU1F3Y98OGF1sqwPrhFibzdwVrdnx/+iXc7LOl3tasPjmlgZq5N7+pnhc7mRCMVVYtJ3rla7SfvOaedr1I706jktvmGH49e/dIZnxx/TLurJY49w/P700L+MapyjyVtyVmURkf8UkWOydi2ApwH8BMCTInJZrm2NMX8DcND38kXIPCWN7P8X5zNIQsjUgrGFEFIIGFtIqTNSucRXGmPWZe33AdhojDkWwMkAPjuG4003xuwGgOz/00bwJ4RMTRhbCCGFgLGFlDQjJeZDln0ugN8CgDFmz/Du44eIfFhEVovI6qF0f6EPRwiZWIoitiQQPD1MCClJiiK2MG8hY2Wkhz87RORCADsBnAngAwAgIhGMrYvWXhGZaYzZLSIzAQTqvYwxNwK4EQBqK1rMIW257HdnmSJW6cPki6oVsjXgANB2nC73N6uOvPE5V9M199pHPXvw9ad4tr/EX2hIX7C1TLF7Vzt+dnfNkJUDRPpcvfi0G7SLp73NvtdojGnwSbASVapLbzta/xxz9i1y/Ew0v2d8bb1+9EXVgXW9eo7jN+3B4SWYne9cEbjvbZfqswEVu/N/roFMWYoittRIAz+MhEwtiiK21JbNMIe05akGt+RwzCrDF+5Q3bcJu/dK95yreme75HDD+iHHb/Yvt3l29/KAGoYABqdrd85QUkNf7WNuJ9Hu5apZL+vQXKf2Obdj+fMf0efFtl1qlR28VE270ycA9Fx8qmdXPdemr7/lNMevZqO2HA3t1bzP1Nc4fgNz7E7pms+1LXXLG9av1fNtf4UmY3sucPOb+k26bu/bj/Hs8jZfElhARrpj/hEAHwdwM4ArrF+c5wD4wxiO9zsA78na7wHwv2PYByGk9GFsIYQUAsYWUtLkvJVqjNkI4PxhXr8XwL25thWRnwN4DYAmEWkFcA2A6wD8UkQ+AGA7gLcE74EQMlVhbCGEFALGFlLq5CyXKCLfR6Yw/7BMVIH+5cuXm9WrVw+7zu4q1blIp2kSb/Y/WK30PqOyilkPulNCB5eWeXbLn1TOkVq/yfEbfIPKXCo2a0nTF97uPhdil1y0O3qasOOGL3zoNs++5rZ3evbsB1Wn1jOrzNkmHdGprapWPQ/J8TeN7tdSkUGlJgG3q6i/2+rQeVrxx5bumDOOd/fRpVNCtpTFz4ZrrgxcNxwsl1j6FEtsYblEYsNyiaVPscSWXHnLeSd8wbNTlfq9vvVSV2lTc6TmFubeRs+u3+A+G9M9Rzt61m7TdSbkfpT3nKrHsjtobvxoi+PX9LS+fbaMt2ueK7JY9HptpPrMs/M9+8hbNc9IVrld2CPdVs4lOr50JFjAETmgpRilu9dZl+5WKVD/a472bH+pyLSVc9U9pueemlHv+IV3qFLpxfcu1Nd9jww8e33h8paRpCyrAaxBpq3tSQA2Zf+dACCVYztCCMkFYwshpBAwtpCSZiQpy60AICLvBXCWMSaRXf5PAPcVfHSEkCkJYwshpBAwtpBSZ6Q75odoAVBtLVdlXyOEkJcDYwshpBAwtpCSJL86epmHH54Ukb9kl18N4IsFGdEo6Zupwu2KvdqKFj+sdvz+eo920D3j1m95dqI6+C1INGpZxdRrT3bWGUsbte8VzZ4tvokyOV/LAXXvVN12vMkVLF33vD6rYmuuF0e+49k1L7j7brjp78OOe9/lZ7h+z6vmrHuJjqFmT6PjlzqgYxVLY957zlGOXyil+rPwEi3N2GZp/AEg2qt/m7qNKlTrODLf34PkMKBoYwshpKQp2thiYpp3hPtUc73oNrd8c6pSNeeJWs1v0rHg79CBBtV09ze6ftU79Ht41wVaErFyp+OG/kbNb3rn6Pd9stnVtq9t1d852y7/jGcv3XW9Z7c85OY6ZvVazw4fqRrugYXuc2jlO1VXnq7S9yHc744h1KAa8dhBfS8PHO/mI2Vdeh5mQPcR2vCi45c8er5nN661yi8uyzddfvnkdSRjzM0icg+AQ4Umr56IYv2EkKkNYwshpBAwtpBSZTS3LsMA9gNoB3CkiLyqMEMihBxmMLYQQgoBYwspOfK6Yy4i3wDwNgDrAByaCzEA/lagceVNtEe1I5EBy25zp0/s7lPVy1SakWh2pzseueszw25jzjrJ8du/VN+6pLWLoXq3O1RivU7PhMp0KiUadaesbF532pc8u+IUleRMe2CH4xe0h5Y/uH4DC7WEY+Vd2mHU/3h6yHpfTEL3XtbuHsnudNq1TOUw5Qdcv/4mfY8ev+XTAaMlhzPFHFsIIaVLMccWSei3r/RbpY7b2l2/Xi07GFmywLOTNW5XyzW//6xnn/bObwcet2/68Pdija9AaO8czWPCA7qyqbnb8TuwWyWvy9+vstu5T2qHUNnT5mzzx/Sdnm3nWJU+iUq6XrulhrZoTmNmTXcHe8A6VkrH3fRMn+Nml448+DqV0NQ/7XYzDT+3zbMf6vgfTAb5imYuBrDEGDM4oichhOQPYwshpBAwtpCSJF8py1YA0RG9CCFkdDC2EEIKAWMLKUnyvWPeB+ApEXkAgPfrc6I6aOXCrrZy3nHaTUv2u50/I/PmeLax1uV71Yb/8oSzXHbE6Z49pLM5qNjp/tYZaLaeBA6p3b23yvFrWKN/ip2vsZ6IPnbAs6c/XudsEwnpsZIv6JPFpqvH8Ys9plNJpkw7f93X/zPHz55WsqutxLfsc/ySL+q0Utkpx3p2z1xXFkT5CsmDoo0thJCSpmhjy71Pqlz1/OaPeLYZSjh+oXrrO7+tyzPzTdxi3b4GqJZkJWKpffubXS2LKVepTapW5SEH9ta4+9+jI0lU6D62vlXHPfc+V3ZzQcvHhx1rstUtDRPab3U6r9XjSnuX44eYZnFdi7SSXv2aA47bUIvuI35Qz6/9eDevWvXMl4cd30SS79/3d9l/hBAynjC2EEIKAWMLKUnyLZd4a6EHQgg5/GBsIYQUAsYWUqrkTMxF5JfGmLeKyLPIPM3sYIw5rmAjI4RMWRhbCCGFgLGFlDoj3TF/UkROAfAmAIkRfCedeydQG1S1W0sDdi/Qt7Gsw40D09ZoKaTpX97q2Wv+7HbTHKpVfVa8TfdRdU/Ms9uXljnb1P3kWc9Onm11Jv3zGsdPLF15eIaWTrQ15X5M625diMWcdfcHlDt6dOWdICRPSiq2EEJKhpKKLX/c/+MJO1a0137mTXOOmC9vqX9Cc5rPXvkLz/7cA27OULFH99H8tJYnTK/X598SVW6aGdqn2u9QXPXn6YEBx88krfLLfZYgPuY+GZjas1fHvUafc0vXlDt+f37gc5599jlf9+xVP/0sio2REvNGAN8FcBSAZwA8CuARAH83xhzMtSEhhOSAsYUQUggYW0hJkzMxN8Z8BgBEJAZgOYAzALwfwH+JSIcx5ujCD5EQMtVgbCGEFALGFlLq5FuVpRxADYDa7L9dAJ7NucUUwJZs5MtZr73OWd7xOpWBtD6o8pVQ0i1PFOlVu9wq5dM7LezZNS+6s3L2+M551VcDx2QGtb9Cer+WTrQlLi/x67UGZNsAjv/49Z7d9MAcEPIyOCxjCyGk4ByWsWXlbVeNepsTLv+Os9zzapWlfO6RSz073OeWg+5eYHc6VxmJLZmp3ex2Yb8/qdIYO28JP7bW8bOlLJKy+pRHXImKOf149Xthj9q79jp+x12heUvjv7ilFIuNkR7+vBHAMQC6AaxEZkroO8aY9lzbEUJILhhbCCGFgLGFlDojdf6cC6AMwB4AOwG0Augo9KAIIVMexhZCSCFgbCEljRjzkmpCroOIIPPr84zsv2UADiLzIMU1BR8hgOXLl5vVq1dPxKEKypJrrw9cN9isUzVL/rPTszuXaVeqA8e58hccoRKT8pXaSXT2r3c4brZ8Jd3Xh9Gy7/IznOWmS3X/W9a3eHbtc2HH7+kfXDnqY+WDiKwxxiwvyM7JhFEMsaVGGsxpcs5EHIqUACvNA+gyB2VkT1LMFENsmSp5yxHf+bZnS9q9NMRSssx82JLgztBcoG2FK8Gtn9bt2QOrGj173u/c53Jlh0pRUu062WFLV/xE9mtX0F2vn+msa3xjq2dve1bzlsan3HNafXNhOpaPJm8ZUWNuMpn7WhHpANCZ/XchgFMBTMgHnBAy9WBsIYQUAsYWUsqMpDH/JDK/Ns9Eph7oIwD+DuAmHAYPURBCCgNjCyGkEDC2kFJnpDvm8wH8CsCVxpjdI/gSQki+zAdjCyFk/JkPxhZSwoxUx7wwYpvDlA3XqOZ6/g3fctY1PKXP4e5fUe/ZYa1giERDyt4Eke2Vnh2yZFy9y2Y4fpVWFaJ7X7h1VGMGgHP+4n4McunKCckHxhZCSCFgbBlftn5ayy8u+qZbVrFyh+qzu+ZpOpnU1ATRSldj3r67Rre3mnt2Hl3n+NVa9v1tN45myACAs/7slo3MpSsvNkaqykIIIYQQQgiZAJiYE0IIIYQQUgSMWC6xGBCR/QB6ARRDu6YmTP44DvcxzDPGNE/SsckUgrGFY/DB2ELGBcYWjsFH3rGlJBJzABCR1cVQu7oYxsExEDJ+FMtnuRjGwTEQMn4Uy2e5GMbBMeQPpSyEEEIIIYQUAUzMCSGEEEIIKQJKKTEffb2cwlAM4+AYCBk/iuWzXAzj4BgIGT+K5bNcDOPgGPKkZDTmhBBCCCGETGVK6Y45IYQQQgghUxYm5oQQQgghhBQBJZGYi8j5IrJBRDYiBQgOAAAgAElEQVSLyNUTdMybRGSfiKy1XmsQkftFZFP2//oCj2GOiPxFRNaLyDoR+dREj0NE4iKySkSezo7h2uzrC0RkZXYMd4hIrFBjIKRQMLYwthBSCBhbGFvGStEn5iISBvBDABcAOBrAZSJy9AQc+hYA5/teuxrAA8aYxQAeyC4XkiSAq4wxSwGsAPCx7LlP5DgGAZxtjDkewAkAzheRFQC+AeD67BjaAXyggGMgZNxhbGFsIaQQMLYwtrwcij4xB3AqgM3GmK3GmCEAvwBwUaEPaoz5G4CDvpcvAnBr1r4VwMUFHsNuY8wTWbsbwHoAsyZyHCZDT3Yxmv1nAJwN4FcTMQZCCgRjCxhbCCkAjC1gbBkrpZCYzwKww1puzb42GUw3xuwGMh8+ANMm6sAiMh/AiQBWTvQ4RCQsIk8B2AfgfgBbAHQYY5JZl8n8mxAyVhhbwNhCSAFgbAFjy1iZlMR8lNorGea1w6rGo4hUAbgLwBXGmK6JPr4xJmWMOQHAbGTuBCwdzm1iR0XIS2FsGR2MLYTkB2PL6GBsGTsTnpiPQXvVCmCOtTwbwK7CjTAne0VkJgBk/99X6AOKSBSZD/dtxphfT9Y4AMAY0wHgQWR0Y3UiEsmumsy/CSEAGFtGC2MLIfnB2DI6GFteHhPeYEhETgfwRWPMednlzwGAMebrAf6RxvpQYu6czHtpfD9wwtHjPLt36FnPfuGgO0sS29k77HgajkkEjjUkac+OIO2sE2scIsHvYSjgB5n/57S9HJbhX49Y5woAQ0NPBx7X2bcM9+Md8P/tY7Hj89rfRDEYcH47W1M4eDA9/EmRw5axxJZwTXmibFotgJfeOpkdb/fs7X2Nnh3udO9nhNuGjy2D8ytyDDa/uBtw6Y4KOz4FxaqQ7/VUWs8x3zGM5askV+w0RgL97PHm8rPPIx8S+zqQ7OpjbCEOY4ktDfXi5S1+mLeMzOGctwz/qSksw2mvTvM7iciHAXwYACoqBH+7ZwYAIO37oNW0rPbsx1+c59nvuP1Tjt/8f/n7sIN56117AgdaGRr07IZwj7MuJinPjkrSs8O+D3TcWmcTlXTgcp31XWJ/rUybtRo221pnDuvnJxbwAR/wfcDnz149rN9ksWnHzGFfv+QNByZ4JKREGHVsCZdFcdR33w8ASPu+i7559F2effnqd3p23R8qHb+6nwwfWzZ+8WTfcS07rNd7KBz8BSmhdOC6UMj+kg10QySisSoW0XhkJ7TlMfeLvmegTI+T54+IlLW/tC8hDkoCouFUoN9gIurZZVF3fOVRPY/BpH6NlUXceNtlnYdzHN9yOjv2rVf917D+5LBn1LGlsiKEv94zfdidFTJvqQ73e3ZdqM9Z93LzljJxr9ewdb1OVN4y5Mtb5k7BvGUyEvO8tFfGmBsB3AgAJx1f5q2vadnh+D3x4lzPrg7ph+mGt9/o+H3zX4717M53rvDssPwaQQyZsGf3GTfAx0Q/8Cnr45Uw7kdtCLqPGOwPtfvBt3+hDhj9Mo5bH84tAX9wALC/tsp873DUesu7TfAX/Xbrggm6KABgxqzCzf48v6PFs6O+dcEjJwTAGGJL5eKZ5lAymE6FHb9PPHmZZ8dier22v969i1X3E7WTZ2syLv6E217MkUiHrUTaTp792OtCVgKf605Y2rkTrn79Q+7VZu8hbR0n7Puh4BzL3neOHxT+fbjrdH/2j4WBRCTQL5nS41aVuYmDnfgPWQm8/z3K9Z4RgjHmLaFsblDV8qLjZyfj1SH9nI9H3jKQ1mu5T/LLW9yrxs194mJlF74zLrO2DMpb7EQcAFLWPvLNW3qtffujRzHkLXYy7v+xMZa8ZTIe/iwm7RUhZOrA2EIIKQSMLWTCmIzE/HEAi7MdmGIA3g7gd5MwDkLI1IKxhRBSCBhbyIQx4VIWY0xSRD4O4F4AYQA3GWPWTfQ4CCFTC8YWQkghYGwhE8lkaMxhjLkbwN35+guAqGQ0Txc/fLmzrrHsbM+uiehDD7/fvMzx+9rG33r2v95+hmd3p8odP/vBib606rPSvskFW8dVYT0k6uixAMDSag1YqunqSHBZT1uDNWCJusI5dKlxy/Y/r92RtrVf1r59erFowP79D4m+XNp2Btf0j1rnm/DJ+qqzOtBS6IpFJofRxhYDIJV9UL5rS527LmZcxyzlu1wt+uafnujZzX/Ua9wMuc+RSER3kh7UT7HxadFTQ7r/UDRYO25rzI31sH+sLBno5zygaWnqQz7dd1Clk6T/oU57G8v2P/xpa73tfadzaOhtTbj/IdHK2JAuxNTs7I87fkEVafzHjWTPfzyq4JCpyWhjCwCEsx+oNz70cef15vhZnj1ZeYu9TfQlKnMlIRonWsLdzjr74c+gvMWPncfkylsaZ+3U/Vk68kQR5i32u+zXlFfIS31GgjkOIYQQQgghRQATc0IIIYQQQoqASZGyjJbn+xpwRrZ0WcOFG511P2td5dl9RidD1p7sTij86xf/cdh9f+fv5zrLHzr1Ic+ujWhpoY6U2yxkRqTTs/ck3Slw16/Dsy9eqIXnH9q20PFrtqaVgvCXD7Sxp4HivvnYDmtGp85aF/dNAaWs6adOq6hzhc9vz04taTjeJYjsaanOlPvxbM6WkQtqPEDIaEn3RtC/sgkAsOgrjzrrDv7+SM8eSup07oxPrHf8ut6hZczsaqk1a2Ou39HWVWqV+zNDPnmIVfIvNWDJZkLu1GwoojEuZR14aNC9bmxpiy0xyVW2MKgBUtj3esKSwzg10nOUI7QlKv4x2A2BUqngsdrHteuY58KOGilfn49IVjIkxdmhm5Qgz/c14IwnMv0Pmv7BzVuub33Ms/uMXu8vyVuuKVzesjPR4NlhnwCj2ZLaXnxEcN4yI+zWSR+OseYtdunk5lDI8nP3YectB63TqPb57bTkMLNm784xqtFj5y0HUu4Z12bj4mjyFt4xJ4QQQgghpAhgYk4IIYQQQkgRUBJSliMr2vCXEzLt9U741hXOujfNVvt9G7S71ravnu74zf8XnabueatOPVd90W3nevcfj/Hs5c3bPXtmrNPxGzA6XdGe1Bbdtb6pnVW9OvWT2KxdAatDbkeuOquyS9Rqe9udtjtwuU9O2xIT+4lof4+yavvJaev1sM/Rlq/UhqzKCe7ukLKedranh/zPddvb2b8A/VNWNnbnrtm+9tohyeyFQhYyXoQqkyg/LdMq+cCH3ZjRdKG2w970k5M8O/5u16/uJ+qXfsUJnl37s6ccvwErJiXq9OowMd8VZlcMSQV/2tPdGoNC1TopnKtbqF19JRXQBRTQKiWAW4kl4quOErO2s7txpnynZO/Dlryk0sH3huJW58+U75y6BjR++uU1Niaga2nIt423jsGFjBNLKtrw1xOHz1sutfKWd2/QbuZ55y3XFjZvWdO3wLNz5S0DVt5SYeUnvfb1Lm4wCMpbQuOQtzRYO/FXb7HJN2+xRSnRPPOWFl/e4h9vPvCOOSGEEEIIIUVAXom5iEwXkf8RkXuyy0eLyAcKOzRCyFSHsYUQUggYW0ipku8d81uQ6Xh16DHZjQCuCPQmhJD8uAWMLYSQ8ecWMLaQEiRfjXmTMeaXIvI5wGtPG9wqapwJR49DTUtWUyXfdtbZpcq+e63aoUX56Xpe/YxbprAi/IRn3/bCqZ69rMktr/O5U7UB2JfW/oNnd6fdznNzy9qGPa6/I9eeVJVnN4d7PbtSVK/k/xVl/wHscj1Dvo5Xbp9CJeErDVZt6bPsrln+7V29V/BxBq3d2+Pza666jaq6Kiyt1li0WaTkmNTYYrojSDyYKZcYS7vXQ/rV2tHziJv09f5pweJFW7q88cenuCsjqpku26nqxSF/tdUB60ovsxSPvhJ/zrocl8rggB4rEtW3NhwO7iqaDuj8aZcp9B/W/rP5de62Dtxe59d6pwO6gkZylEu01/g18LZfJKALKGBp3VktcSpREnnLD8Yhb6kOr/HsW7ae5tnHNY8tb5kVax/2uP68ZX9KdeoNlk59LHmLv1NnMeQtdoCLT2Deku8d814RaUQ2bInICgCduTchhJARYWwhhBQCxhZSkuR7x/zTAH4HYKGIPAKgGcCbCzYqQsjhAmMLIaQQMLaQkmTExFxEQgDiAF4NYAkyN/c3GGMSOTccR0ziWSR2Z8oOGrncWVdzu3bQuj99p2efG3pL4P46FupEwX899ipn3ZEfftyzT1q1A0F8MtuJFACqwsG9rcKWLMWeLgr7SgjFZfi3M5pjVsQu0WOXMIyLOxFiT/3YRy3z+Q2a4TsB5trffqs7X1u63PGbE+7x7INWN6wKXzmhppB2SEy/pDgjmaoUQ2wJVScRP3s/ACD9myZ33V+f9OzI7FmeHX5wZ+D+emfpNV67zr1upn9PS59t+qFON7+kXpd9zdvyFV/nTwlb8pCkHstE3WsoZMk77HKJtpzDH2ZCAbKPcMgvAdEtbYlKJOzv6GnFqlzdR619JKxuq4NpXzfTmMaQZCq4nGNZJD/lgl/aQkqbYogtk5W3PJn+qmd/aPW7HT87b6mN6PUV8sn4bH3HROUtFSFXVJKw8pGx5C3+8ob23u28pSPtloCcY3VOHc+8ZTQClxETc2NMWkS+bYw5HcC6UeybEEICYWwhhBQCxhZSyuSrMb9PRC4VyVFhnRBCRg9jCyGkEDC2kJJkNBrzSgBJERlA5q68McbUFGxkPtJZ+YR/xrHtQ9opy54GsqeHcuGfOtr96TM8e6552rNrIu5T0CnrN01XUqd6vnbSrx2/765/rWc3RHoQRNR6itnu8JnKMcPaa00DVfvbZgWwx6pS0BIOnua1p5sGfFNF9uRV1JraqpQhx68hrMeqC6WsbdwpK8pXDmsmPbYcwvhuUwydb1VV+aNOFcM/RdqkEpiq7ToNWvXLZxy/gQu1ypP9kTcRn0TFkn1I0pKKlLvXibG6gkrE6iTqixmhkC1LwbCkfVVU7F3YV6u/o6ctS0kFdPf0Ewqo0PKS44btc3JjRtSKXXbFF38YDJKovOS4ObqlkpJl0mPLROUt+z6uecsHHn+vZ9dEBh0/O29pT1R49g9Out3xs/OWSt8+bPLJW8K+S8uunGJXM0n7ApcdasaStyR8+wvKW+LixqpaS1JTLZOTt+SVmBtjqgs2AkLIYQtjCyGkEDC2kFIlr8RcRF413OvGmL+N73AIIYcTjC2EkELA2EJKlXylLP9k2XEApwJYA+DscR8RIeRwgrGFEFIIGFtISSLGL0jMZyOROQC+aYy5bETncaBszhwz69OZTrrr3v59Z90bZ6kOdNdnVGd11tsfd/z8GqogbO3WxhtUE/rW01c5fjNjHZ69c7A+cH/z4wc8e0ZEexsMGLfE4sLoPs9uCA94doVdqsy3b7sc0LRZuzx7384WBBG1Sg0lAsoMjeTXaZVWWjxHO4vt8R03ahUIqgjp+aZeoiXLT6tV05IpXykia4wxy/PaiJQUEx1bKprnmKMuuRIAEHnTfmdd7es3e3bfJVrecOdZ7j4Wf2KlLpx6rGeaiCtal0f1mZW9n9BY1XmMT49tlztM5Hg+3/KTaPA1FLFKC0aDOn/6trF14ElLOx716Tslh77bxl+NLYiBIY0T9vjCPpFurhKOQcfNNb7BbGnGLZ/+b/Rv3kXB+RSEeYubt+wbUqm9vwOv7TdReUvbzlmOX8p64qQY8xabXDnMWPKWfKuy+GkFsGyM2xJCSBCMLYSQQsDYQkqCfDXm34c+MB8CcAKAp4O3IISQkWFsIYQUAsYWUqrkqzFfbdlJAD83xjxSgPEMSySeRMNRbQDcKSAA2PifOm3zD8t1GuiJr5/k+J17l071XLBOp2n+67bXO34fWNvl2a236dtT/YoBx+9AQh/4PjBU5dmxkDstvX2w0bMrQ1p2yJ4eAoCUNX2SsrvfWdM5/rJDNvZ0TNQ3MR2V4SdGwr7yPwNGp6lzTRdVWLu/ZaOWfbqkylfSTPyTWIeO6zsRq05dVcuLgcclU5JJjS3pKNDbkvk8zrWkKwCw72OW3GSpXhuLbnNjgc3GD2np1Jb73Otu1481ds38s15fncf5pkgt+UpowOro6ZNsGLu+oyVlCYVdv6ByiXaJwFydL235ir+soL/DZxAhO76lgwOZvb/uLu0k3NTYHbiNPSZ/J1Gx1s2u1rj/1DNHOH5NCw5mxskOoFMJ5i058pbrjr/Ls/0dQhNWedLqkJaKnhYJvg7tvCWdQ8pikytviVv5Q8gSd/jzh7HkLe7rY8tbbGnLIbnKeJFvucRbD9kiUg9gzriOghByWMLYQggpBIwtpFTJS2MuIg+KSI2INCAzFXSziHxnhG1uEpF9IrLWeq1BRO4XkU3Z/4OfmiSETHkYWwghhYCxhZQq+UpZao0xXSLyQQA3G2OuEZFnRtjmFgA/APAT67WrATxgjLlORK7OLv/zSAdPDkTQtiEjCfn7zjvcddBpIHu6qBIrHb9tXzndWrrHsz70zrsdv3uOqfPsodu1i1/C13kuHtI+UuVhtXuSMcdvRplOMcVF/VLwT8fYTzvr9JMtX/FPpXRbTxnH7VW+KZuygN9f/ieJw9aGvdaUUMI3u7spoXHpqDJ9ujkF1zHouH7KW7bm5UemJJMaW0IJoHJX5nPbdc9CZ100rVVaFr9hU+A+2t9jxRbrGt91nlvB5MgP6sz6zqtVJoO0r5Od3RnTlq/4u1NafnbllXTK16EuPbJkxS/hSFj7CIWCq6MEyUgSKffaD6qIkvCNdaBf46d9Ti+V0FhdBq2qMf4OprYM58ktcz1bqlzJITt/TkmYt+TIWz665l2e3Z8KzltidkfPHHlLgwwv8RvvvOUl+x9D3rLjxfmevSSaX97iz5cKKbvNtypLRERmAngrgN/ns0G2iP9B38sXATg0vXQrgIvzPD4hZGrC2EIIKQSMLaQkyTcx/xKAewFsNsY8LiJHAAi+hRTMdGPMbgDI/j8tyFFEPiwiq0Vkdaq3dwyHIoSUAJMaW5IDjC2ETFGYt5CSJN+HP+8EcKe1vBXApYUaVPYYNwK4EcgU6i/ksQghk8Nkx5aKZsYWQqYikx1bmLeQsZJvHfNvAvgKgH4AfwRwPIArjDE/G+Xx9orITGPM7uwU074RtwCwrGEfHnvbDQCAtE/HvPy7n/LsFjzq2dduXeP4Xb15vmfPj2k3zs88/mbH78I13jMfaN2meqxE2tVqpawShBFLg9Xn05hXWd2wUtYERcq4kxWVoSHPjkt+Jchs+qy3ZXY4Fuhnl/jxa8J3pVSrVW0NL+ETfx0Va/fsuKMfc8/J1mSFxtzLikxlJju2SH0S0UuGd43e0jDs6y/84jh3H1vUDpdrLKh4otzxs0ukldvVtXLpm63LJuSTcKbKrWs5ofHJr5cOB0R5W2/u157bunJ7f5FIcOfPXF1A+62Onrbu23/cigotKWvr3l9aYlHP1z2uu7/OPv0bxKs0xqaSvvgbGxp2e1K6THZsGY+85XNb5nn2ZOUtzva+vMXWrB81R7t4bm+d6dm5vvkHrLelJc+8xU9Q3jLgG6udt9hP9KV9fmkZPm+ZyBwm3yO9zhjTBeBCZLpnHQngn8ZwvN8BeE/Wfg+A/x3DPgghUwfGFkJIIWBsISVJvon5oR8Yr0emSL//4YiXICI/B/B3AEtEpFVEPgDgOgDnisgmAOdmlwkhhy+MLYSQQsDYQkqSfMsl/p+IPI/MlNDlItIMu6bfMBhjLgtYdc4oxgcAkOixiM5cPey6svacZUk9/mOxlit668+v8Ox0jSsbscttnTt/g2cPpoPfqlllHYF+PSntBJiI6LRSX7rM8auN6jSVXSKxNqTb3NHtlnN7R7WWGUw4ZYLc6eagTlZp3/TQdKtj4H6r3Fmdr5te1JKvVIhOCvnLIlG+QvJgUmNLCAZlWWlF+90tzrr63sRwmyDs66yJI3t0f+u0s168zfXrmavXQ/9st1yfg3W5mTJd8JdBhCXvMDm6abqdP60Si9Z13X6g2tmmrlHPSULB0jpb5pK0xueXnpRF9b0cTAwvawHc+JtLapMvdgnHoUGNzZWWZMbxY9XEqUTJ5y3XL/qlZ7/76fd6dvqgmz+Md97Sl9L9D1l5C3LkLbZ8pTrPvMWW0+abt/i7e+abt4SdvEX3HXScySSvzMkYczWA0wEsN8YkAPQhU0KIEELGDGMLIaQQMLaQUiXfzp8VAD4G4EfZl1oALC/UoAghhweMLYSQQsDYQkqVfLUGNwMYAnCoXV0rMk87E0LIy4GxhRBSCBhbSEmSr8Z8oTHmbSJyGQAYY/pFpCjUeO1LVV/0951aaujCWSc7fvenvXKmWPD5t3j2lttOzOs4VRFXk1hhlTe0Swgtrdwd6Fdt1TubEelw/GJWiZ75s3Uf+3aq7vWupW5fg39s3ebZUeuvUS7BZYdylQOzyxvOCFslg3JosMpEP0L+klCE5MGkxpbySALHNewEAGz4j23OugMf0XbYfX9Y7Nlz3/Cs49d1j2ooa76o6/ZceQZczLAmQr7rxq7lZW9S6dOlW9pKsexYmetnlzh0OmBbsWDJj9z41nGt7sNueR8OBT+T4xzTp8MPOSUNVW+eSzvuP5aNrW23xwff/iKWhv242Ts9u6W80/G7+y+ZG6lDfVGQKUPJ5y1373zCs2devN6zJzJvsUs5z4q0O352aee5Vt7StnOWZ+fKW+wHasY7b8l137lMivs6z/eO+ZCIlCP7NSEiCwEM5t6EEEJGhLGFEFIIGFtISZLvHfNrkCnQP0dEbgNwJoD3FmpQhJDDBsYWQkghYGwhJYmYHB2VACA79TMbmSeaVyAzG/qYMeZAzg3HkeXLl5vVq4cvOzS4+wjPPuNJrXT01xPc5l5Bkouj7viY4/fCFVd59k0bz/Rsf8cru4tnTHTaNwR3+jVmddeyu2Q1hHscvzpL5tJiTb/GLRmJv/ygvzxhEBEML0XpN0POsj29k0bwNHLQ/vzY73PZzK05PEeHiKwxxvAhnhKnGGJLVcMcs+y8TPnU2uddeUP71/V67XxMp2OrTnWHZ8sx7PJ/g3dNd/ymveNFz35++4zAMdmlD8WWufhlI9a6kCUdCfu6c4at6d14TM/J6egZdq/3XN00g/zs/SVSbqyKWWPKJY0JOpYjV/Ed1y7T2DvgTocvata/VTys5/74M24Jt0OyoD1f/R4Gt7UWhdyBjJ1iiC3jnbfYHHnH5c7yZOUtjaF+z55ux5lJylvskov+49j7y1d2O1l5y4h3zI0xRkR+a4w5GcAfXvboCCEEjC2EkMLA2EJKmXw15o+JyCkFHQkh5HCEsYUQUggYW0hJkq/G/CwAHxWRbQB6kZkWMsaY4wo1sHyxpxr+auZ5tn8aw566CFm1CZ5/2w99e7wKwxEWXxcpa+rHPw1kE5Lh18Xg63Jl7aPPkhfZx6kI5Sch8U8BhUV/f9lTPfl25hxrB8/xnAYiU5ZJjS2JCmD/iZl4YN7rTpHufbHRs5ss+UquaiE2ZZfudZY3PjFXF5qtY+Xo2mnjVx0GyT5yVTpJWpIQf9fNIIIqrwBA1HovUjn8bPJ9/3IxMGR1D7VkMrPqXTlSx0C5Z+85aEmLyn3nPpiNmSwsNZUoubzF34UyKG/Z+LYbfHucnLwlZI2vlPIW+730y1qKIW/JNzG/oKCjIIQcrjC2EEIKAWMLKUlyJuYiEgfwUQCLADwL4H+MMclc2xBCyEgwthBCCgFjCyl1RpoTuBWZFrbPIvPr89sFHxEh5HCAsYUQUggYW0hJM5KU5WhjzLEAICL/A2BV4Yc0dqpaXhzZaZwI0melfb91ulOqcZwV1a5ZtaHgPgd2T6qKUHCHKluTZeuxcmFr2Px6NhtbL+rXYEVnbvHsxO6Fw75OyAgURWwprxrEsWdsBgBs+/kiZ92/fvI3nt061ODZtz70Ssfv31/3c8++c79Ww9rS3uT4vfrMtZ795/VLPFt8XTIlQHPurzKWHrKu/3K9IRj2lT60yxjauwjlWRTQ1qL7yxba2Npxv448aDu/31AyMuy6ypir/7d19GHL3t1ZE+hXW62l3dqGqhy/UE92fHnq/UlRUxSxJV+Yt4yMrQmvCLklUVNGzylXThOUtxSDptzPSO+KV8CSU0GEkHGEsYUQUggYW0hJM9Id8+NFpCtrC4Dy7PKhp5trgjclhJBAGFsIIYWAsYWUNDkTc2NMfnVupijvP/KRUW/zXxvcae7qsE6fRq1OW9Uhf6ctnarptVbZXa382CWEYE3n5Ds9lAt7H/4PQXrP4nE9Fjn8KJbY0t9bhmdWZaY17/jsd5111+9+nWc/+fujPfuWD7qlyn7RtsKzT6zZ4dmrNs93/FY+pFXaqlZ0eHZfT5njF63QTnuDXdY6v+QlapU+syQbsUhwGUS79GEsEnwz0faz7VylDm25ir9ko71dLjlMxJLN2Ofk36Yiqu9Rwur8mUz6Oh0mdV3PXku+EnLHV7048/cIx/MrIUmKl2KJLZPFVMxb8l2X6w9v5y3FDrMqQgghhBBCigAm5oQQQgghhBQB+TYYInnyoSUPBa7b3jrTs2O+Egv2L6SWiE5fDxqdsvV3xrKfQG5P9Xl2fbgi7/GOJ/6potCMTZMyDkLypbGmG+88N3PNvvvGK5x1qRO7Pfv5j6t85Y2bznf3Udbr2Q+1uZVdbD747rs9+/tPnOXZFVVupQO7CspQn1YgqK7rc/zKYxobegfdSgU2tqykPKrT0rkkJTaJlPr5ZTK23CTfjp72ePxdRe0KMnZlKP9Y27s1xpWV6ftQEXert/T0xj27bmaXZ/uPe0gO4++uSsjhwGTlLZ1plczUSjkKiV29xcau0AIUR3U53jEnhBBCCCGkCGBiTgghhBBCSBHAxJwQQgghhJAigBrzCWTu7N2evW9ni7Mubumu7HJCdtkhf8kg268qNLy+y7+Psei+S6nMECGjoUha6ysAAAlCSURBVHOoHPe0ZkohznvdNmfdG6c/rbalK//07Pscv+cHVYN5Z8/Jnr1w9n7H76ZNp3t2WbmlwfRpsyNW587p07WsYm3ZgOO3r0fL/9m69HAoWChta7VzacL9GuxDJFOuXrTMKrnYn9CvE39X0ZTVUdPWkcdjbqzyvxfeNr7luKUrT1oa+ETC/Uori6tfyNq3+M6vOp7R+eerkyfkcKGQeUuF6LMx4523+LXjpQTvmBNCCCGEEFIEMDEnhBBCCCGkCBBTAvWhRGQ/gF4AByZ7LACaMPnjONzHMM8Y0zxJxyZTCMYWjsEHYwsZFxhbOAYfeceWkkjMAUBEVhtjlnMcHAMh40mxfJaLYRwcAyHjR7F8lothHBxD/lDKQgghhBBCSBHAxJwQQgghhJAioJQS8xsnewBZimEcHAMh40exfJaLYRwcAyHjR7F8lothHBxDnpSMxpwQQgghhJCpTCndMSeEEEIIIWTKUhKJuYicLyIbRGSziFw9Qce8SUT2icha67UGEblfRDZl/68v8BjmiMhfRGS9iKwTkU9N9DhEJC4iq0Tk6ewYrs2+vkBEVmbHcIeI1cKLkBKBsYWxhZBCwNjC2DJWij4xF5EwgB8CuADA0QAuE5GjJ+DQtwA43/fa1QAeMMYsBvBAdrmQJAFcZYxZCmAFgI9lz30ixzEI4GxjzPEATgBwvoisAPANANdnx9AO4AMFHAMh4w5jC2MLIYWAsYWx5eVQ9Ik5gFMBbDbGbDXGDAH4BYCLCn1QY8zfABz0vXwRgFuz9q0ALi7wGHYbY57I2t0A1gOYNZHjMBl6sovR7D8D4GwAv5qIMRBSIBhbwNhCSAFgbAFjy1gphcR8FoAd1nJr9rXJYLoxZjeQ+fABmDZRBxaR+QBOBLByoschImEReQrAPgD3A9gCoMMYk8y6TObfhJCxwtgCxhZCCgBjCxhbxkopJOYyzGuHVSkZEakCcBeAK4wxXRN9fGNMyhhzAoDZyNwJWDqc28SOipCXDWMLYwshhYCxhbFlzJRCYt4KYI61PBvArkkay14RmQkA2f/3FfqA8v/bu/NQqcowjuPfX2pladq+l2WWVJRpG9liEZKBlWXURUkpiApasZCKsqISo2iVFlrJTK2si4GtWlez1SUNWwhb6I9ooc1ss6c/3ndsmPRq452Zc6+/D1zmzDvnPec93JlnnnPe950jdSG9uSdFxDONagdARPwAzCaNG+spqXN+qZH/E7NqObY4tpjVgmOLY0vV2kNi/g7QJ8+m3Rg4E2huUFuagVF5eRTwXC13JknAg8DSiLitEe2QtK2knnm5K3A8aczYLGB4PdpgViOOLY4tZrXg2OLYUrV2cYMhSScCtwOdgIci4sY67HMyMAjYBvgauBZ4FpgK7AZ8AZweEZUTLdqyDUcCLcBi4O9cfCVpvFZd2iHpANIkiU6kE7mpEXG9pD1JE1q2AhYAIyPi91q0waxWHFscW8xqwbHFsaVa7SIxNzMzMzPr6NrDUBYzMzMzsw7PibmZmZmZWQE4MTczMzMzKwAn5mZmZmZmBeDE3MzMzMysAJyYN4CkYZJCUt+1rDda0k7rsZ9BkmZUW9/MikPSSkkLJS2RNE3SZuuxrVWxQdJJksa2sm5PSRdUsY9xksZU20YzK5act9xa9nyMpHFrqdNqfLH/cmLeGE3AHNJNB1ozGqg6MTezDmVFRPSLiP2BP4Dzyl9U8r9jekQ0R8T4VlbpCfzvxNzMOpzfgVMlbbOuFdYhvlgFJ+Z1JqkbMBA4h7LEXNIVkhZLWiRpvKThwMHApHyVrKukz0ofCEkHS5qdlw+V9IakBflxn/ofmZnVUQuwl6RekpZKmgjMB3aVNFjSPEnz85X1bgCSTpD0oaQ5wKmlDeWeubvz8vaSpuc4tEjSEcB4oHeOQ7fk9S6X9I6k9yVdV7atqyR9JOllwHHIrGP5C7gfuLTyBUlDJb2V85CXJW2fy0dLultSj5zDbJTLN5P0paQuknpLminpPUktaxtN0NE5Ma+/U4CZEfEx8L2k/pKG5PLDIuJAYEJEPAW8C4zIV8lWtLLND4GjI+Ig4Brgphofg5k1iKTOwBDSnfUgJcCP5c//cuBq4PiI6E+KIZdJ2hR4ABgKHAXssIbN3wm8luNQf+ADYCzwaY5Dl0saDPQBDgX6AQMkHS1pAOliw0GkxP+QNj50M2u8e4ARknpUlM8BDs9x6EngivIXI+JHYBFwTC4aCrwQEX+Skv0LI2IAMAaYWMP2F17nRjdgA9REuk0vpDdvE+kE6eGI+BWgitvU9gAeldQHCKBLG7XVzIqjq6SFebkFeJA01O3ziHgzlx8O7AvMlQSwMTAP6Assi4hPACQ9Dpy7mn0cB5wFEBErgR8lbVmxzuD8tyA/70ZK1LsD00txTFLzeh2tmRVORPwk6THgIqD8guEuwBRJO5LizrLVVJ8CnAHMIp3ET8w9ekcA03LMAtikRs1vF5yY15GkrUlffPtLCqATKZF+Oj+uzV/828uxaVn5DcCsiBgmqRcwu42abGbFsSIi+pUX5C+y5eVFwEsR0VSxXj/WLcasCwE3R8R9Ffu4pA33YWbFdTtp6NzDZWV3AbdFRLOkQcC41dRrBm6WtBUwAHgV2Bz4oTK2bcg8lKW+hpO6nHePiF4RsSvprPJ74OzSryzkNy3Az6SrUCWfkd7MAKeVlfcAvsrLo2vTdDNrB94EBkraC1aN49ybNNxtD0m983pNa6j/CnB+rttJ0hb8Nw69QIpXpbHrO0vaDngdGJbnw3QndVWbWQeTe/WnkubKlZTnIaPWUO8X4G3gDmBGRKyMiJ+AZZJOh1WT2A+sWePbASfm9dUETK8oe5rUHd0MvJu7qks/MfYIcG9p8idwHXCHpBZgZdk2JpDOQueSrsKb2QYoIr4hnZxPlvQ+KVHvGxG/kYauPJ8nf36+hk1cDBwraTHwHrBfRHxHGhqzRNItEfEi8AQwL6/3FNA9IuaTuqoXkuJaS80O1Mwa7Vag/NdZxpGGo7QA37ZSbwowMj+WjADOkbSINK/l5LZtavuiCPc8mpmZmZk1mq+Ym5mZmZkVgBNzMzMzM7MCcGJuZmZmZlYATszNzMzMzArAibmZmZmZWQE4MTczMzMzKwAn5mZmZmZmBeDE3MzMzMysAP4ButjAXAt5nCwAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x24a800314a8>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(15,10))\n",
    "grid = gridspec.GridSpec(7, 3)\n",
    "grid.update(wspace=0., hspace=0.2)\n",
    "for i in range(7):\n",
    "    plt.subplot(grid[i*3])\n",
    "    plt.imshow(X_test[0,23,:,:,i])\n",
    "    plt.ylabel(y_labels[i])\n",
    "    plt.xlabel('Actual', fontsize=10)\n",
    "    \n",
    "    plt.subplot(grid[i*3 +1])\n",
    "    plt.imshow(X_hat[0,23,:,:,i])\n",
    "    plt.ylabel(y_labels[i])\n",
    "    plt.xlabel('Predicted', fontsize=10)\n",
    "    \n",
    "    plt.subplot(grid[i*3 + 2])\n",
    "    plt.imshow(X_test_naive[0,23,:,:,i])\n",
    "    plt.ylabel(y_labels[i])\n",
    "    plt.xlabel('Naive', fontsize=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      " 63%|███████████████████████████████████████████████████▉                              | 19/30 [09:38<05:35, 30.47s/it]"
     ]
    }
   ],
   "source": [
    "# Plot some predictions\n",
    "aspect_ratio = float(X_hat.shape[3]) / X_hat.shape[2]\n",
    "plt.figure(figsize = (nt, 7*2*aspect_ratio))\n",
    "gs = gridspec.GridSpec(2*7, nt)\n",
    "gs.update(wspace=0., hspace=0.2)\n",
    "plot_save_dir = os.path.join(RESULTS_SAVE_DIR, 'prediction_plots/')\n",
    "if not os.path.exists(plot_save_dir): os.mkdir(plot_save_dir)\n",
    "plot_idx = np.random.permutation(X_test.shape[0])[:n_plot]\n",
    "for i in tqdm(plot_idx):\n",
    "    for t in range(nt):\n",
    "        for c in range(7):\n",
    "            plt.subplot(gs[t + c*2*nt])\n",
    "            plt.imshow(X_test[i,t,:,:,c], interpolation='none')\n",
    "            plt.tick_params(axis='both', which='both', bottom='off', top='off', left='off', right='off', labelbottom='off', labelleft='off')\n",
    "            if t==0: plt.ylabel('Actual', fontsize=10)\n",
    "\n",
    "            plt.subplot(gs[t + (c*2+1)*nt])\n",
    "            plt.imshow(X_hat[i,t,:,:,c], interpolation='none')\n",
    "            plt.tick_params(axis='both', which='both', bottom='off', top='off', left='off', right='off', labelbottom='off', labelleft='off')\n",
    "            if t==0: plt.ylabel('Predicted', fontsize=10)\n",
    "\n",
    "    plt.savefig(plot_save_dir +  'plot_' + str(i) + '.png')\n",
    "    plt.clf()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [
    {
     "ename": "TypeError",
     "evalue": "unhashable type: 'numpy.ndarray'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-36-cf5f6662ea82>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m()\u001b[0m\n\u001b[0;32m      4\u001b[0m \u001b[1;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m+\u001b[0m\u001b[0mrows\u001b[0m \u001b[1;33m+\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      5\u001b[0m     \u001b[0mfig\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0madd_subplot\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrows\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mcolumns\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 6\u001b[1;33m     \u001b[0mplt\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mimshow\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX_test\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mX_hat\u001b[0m\u001b[1;33m[\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;36m0\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m,\u001b[0m\u001b[0mi\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\pyplot.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, hold, data, **kwargs)\u001b[0m\n\u001b[0;32m   3099\u001b[0m                         \u001b[0mfilternorm\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilternorm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfilterrad\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilterrad\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3100\u001b[0m                         \u001b[0mimlim\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mimlim\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresample\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mresample\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mdata\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mdata\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 3101\u001b[1;33m                         **kwargs)\n\u001b[0m\u001b[0;32m   3102\u001b[0m     \u001b[1;32mfinally\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   3103\u001b[0m         \u001b[0max\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_hold\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mwashold\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\__init__.py\u001b[0m in \u001b[0;36minner\u001b[1;34m(ax, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1715\u001b[0m                     warnings.warn(msg % (label_namer, func.__name__),\n\u001b[0;32m   1716\u001b[0m                                   RuntimeWarning, stacklevel=2)\n\u001b[1;32m-> 1717\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0max\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1718\u001b[0m         \u001b[0mpre_doc\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0minner\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__doc__\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1719\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mpre_doc\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\axes\\_axes.py\u001b[0m in \u001b[0;36mimshow\u001b[1;34m(self, X, cmap, norm, aspect, interpolation, alpha, vmin, vmax, origin, extent, shape, filternorm, filterrad, imlim, resample, url, **kwargs)\u001b[0m\n\u001b[0;32m   5123\u001b[0m         im = mimage.AxesImage(self, cmap, norm, interpolation, origin, extent,\n\u001b[0;32m   5124\u001b[0m                               \u001b[0mfilternorm\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilternorm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mfilterrad\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilterrad\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 5125\u001b[1;33m                               resample=resample, **kwargs)\n\u001b[0m\u001b[0;32m   5126\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   5127\u001b[0m         \u001b[0mim\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mset_data\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mX\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\image.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, ax, cmap, norm, interpolation, origin, extent, filternorm, filterrad, resample, **kwargs)\u001b[0m\n\u001b[0;32m    763\u001b[0m             \u001b[0mfilterrad\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mfilterrad\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    764\u001b[0m             \u001b[0mresample\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mresample\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 765\u001b[1;33m             \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    766\u001b[0m         )\n\u001b[0;32m    767\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\image.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, ax, cmap, norm, interpolation, origin, filternorm, filterrad, resample, **kwargs)\u001b[0m\n\u001b[0;32m    223\u001b[0m         \"\"\"\n\u001b[0;32m    224\u001b[0m         \u001b[0mmartist\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mArtist\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 225\u001b[1;33m         \u001b[0mcm\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mScalarMappable\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnorm\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mcmap\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    226\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_mouseover\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    227\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0morigin\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\cm.py\u001b[0m in \u001b[0;36m__init__\u001b[1;34m(self, norm, cmap)\u001b[0m\n\u001b[0;32m    202\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mnorm\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mnorm\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    203\u001b[0m         \u001b[1;31m#: The Colormap instance of this ScalarMappable.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 204\u001b[1;33m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcmap\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mget_cmap\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mcmap\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    205\u001b[0m         \u001b[1;31m#: The last colorbar associated with this ScalarMappable. May be None.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    206\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mcolorbar\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mc:\\users\\dasputer\\appdata\\local\\programs\\python\\python36\\lib\\site-packages\\matplotlib\\cm.py\u001b[0m in \u001b[0;36mget_cmap\u001b[1;34m(name, lut)\u001b[0m\n\u001b[0;32m    159\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mname\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    160\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 161\u001b[1;33m     \u001b[1;32mif\u001b[0m \u001b[0mname\u001b[0m \u001b[1;32min\u001b[0m \u001b[0mcmap_d\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    162\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mlut\u001b[0m \u001b[1;32mis\u001b[0m \u001b[1;32mNone\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    163\u001b[0m             \u001b[1;32mreturn\u001b[0m \u001b[0mcmap_d\u001b[0m\u001b[1;33m[\u001b[0m\u001b[0mname\u001b[0m\u001b[1;33m]\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mTypeError\u001b[0m: unhashable type: 'numpy.ndarray'"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<matplotlib.figure.Figure at 0x249d9e7ecc0>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig=plt.figure(figsize=(15,10))\n",
    "columns = 3\n",
    "rows = 4\n",
    "for i in range(1,columns+rows +1):\n",
    "    fig.add_subplot(rows,columns,i)\n",
    "    plt.imshow(X_test[0,0,:,:,i-1],X_hat[0,0,:,:,i-1])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_hat[0][0][0][0][2]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}