Datasets
Models
Downloads: 1
1263 lines (1263 with data), 218.0 kB
{
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"machine_shape": "hm",
"gpuType": "V28"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"accelerator": "TPU"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "8XnVMPBXmtRa"
},
"source": [
"# TensorNetworks in Neural Networks.\n",
"\n",
"Here, we have a small toy example of how to use a TN inside of a fully connected neural network.\n",
"\n",
"First off, let's install tensornetwork"
]
},
{
"cell_type": "code",
"metadata": {
"id": "7HGRsYNAFxME"
},
"source": [
"# !pip install tensornetwork\n",
"\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import tensorflow as tf\n",
"# Import tensornetwork\n",
"import tensornetwork as tn\n",
"import random\n",
"import time\n",
"import pandas as pd\n",
"# Set the backend to tesorflow\n",
"# (default is numpy)\n",
"tn.set_default_backend(\"tensorflow\")\n",
"np.random.seed(42)\n",
"random.seed(42)\n",
"tf.random.set_seed(42)\n",
"# Explainability code assistance aided by ChatGPT3.5\n",
"# 2021 Kelly, D. TensorFlow Explainable AI tutorial https://www.youtube.com/watch?v=6xePkn3-LME"
],
"execution_count": 101,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "g1OMCo5XmrYu"
},
"source": [
"# TensorNetwork layer definition\n",
"\n",
"Here, we define the TensorNetwork layer we wish to use to replace the fully connected layer. Here, we simply use a 2 node Matrix Product Operator network to replace the normal dense weight matrix.\n",
"\n",
"We TensorNetwork's NCon API to keep the code short."
]
},
{
"cell_type": "code",
"metadata": {
"id": "wvSMKtPufnLp"
},
"source": [
"class TNLayer(tf.keras.layers.Layer):\n",
"\n",
" def __init__(self):\n",
" super(TNLayer, self).__init__()\n",
" # Create the variables for the layer.\n",
" self.a_var = tf.Variable(tf.random.normal(shape=(32, 32, 2),\n",
" stddev=1.0/32.0),\n",
" name=\"a\", trainable=True)\n",
" self.b_var = tf.Variable(tf.random.normal(shape=(32, 32, 2),\n",
" stddev=1.0/32.0),\n",
" name=\"b\", trainable=True)\n",
" self.bias = tf.Variable(tf.zeros(shape=(32, 32)),\n",
" name=\"bias\", trainable=True)\n",
"\n",
" def call(self, inputs):\n",
" # Define the contraction.\n",
" # We break it out so we can parallelize a batch using\n",
" # tf.vectorized_map (see below).\n",
" def f(input_vec, a_var, b_var, bias_var):\n",
" # Reshape to a matrix instead of a vector.\n",
" input_vec = tf.reshape(input_vec, (32, 32))\n",
"\n",
" # Now we create the network.\n",
" a = tn.Node(a_var)\n",
" b = tn.Node(b_var)\n",
" x_node = tn.Node(input_vec)\n",
" a[1] ^ x_node[0]\n",
" b[1] ^ x_node[1]\n",
" a[2] ^ b[2]\n",
"\n",
" # The TN should now look like this\n",
" # | |\n",
" # a --- b\n",
" # \\ /\n",
" # x\n",
"\n",
" # Now we begin the contraction.\n",
" c = a @ x_node\n",
" result = (c @ b).tensor\n",
"\n",
" # To make the code shorter, we also could've used Ncon.\n",
" # The above few lines of code is the same as this:\n",
" # result = tn.ncon([x, a_var, b_var], [[1, 2], [-1, 1, 3], [-2, 2, 3]])\n",
"\n",
" # Finally, add bias.\n",
" return result + bias_var\n",
"\n",
" # To deal with a batch of items, we can use the tf.vectorized_map\n",
" # function.\n",
" # https://www.tensorflow.org/api_docs/python/tf/vectorized_map\n",
" result = tf.vectorized_map(\n",
" lambda vec: f(vec, self.a_var, self.b_var, self.bias), inputs)\n",
" return tf.nn.relu(tf.reshape(result, (-1, 1024)))"
],
"execution_count": 102,
"outputs": []
},
{
"cell_type": "markdown",
"metadata": {
"id": "V-CVqIhPnhY_"
},
"source": [
"# Smaller model\n",
"These two models are effectively the same, but notice how the TN layer has nearly 10x fewer parameters."
]
},
{
"cell_type": "code",
"metadata": {
"id": "bbKsmK8wIFTp",
"outputId": "5884c86a-ea76-40a4-a270-a3686aee593a",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"Dense = tf.keras.layers.Dense\n",
"tn_model = tf.keras.Sequential(\n",
" [\n",
" tf.keras.Input(shape=(2,)),\n",
" Dense(1024, activation=tf.nn.relu),\n",
" # Start Modified Layers\n",
" TNLayer(),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 103,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_8\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_22 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_21 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_22 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_23 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_23 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 19457 (76.00 KB)\n",
"Trainable params: 19457 (76.00 KB)\n",
"Non-trainable params: 0 (0.00 Byte)\n",
"_________________________________________________________________\n"
]
}
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "GWwoYp0WnsLA"
},
"source": [
"# Training a model\n",
"\n",
"You can train the TN model just as you would a normal neural network model! Here, we give an example of how to do it in Keras."
]
},
{
"cell_type": "code",
"metadata": {
"id": "qDFzOC7sDBJ-"
},
"source": [
"X = np.concatenate([np.random.randn(120, 2) + np.array([3, 3]),\n",
" np.random.randn(120, 2) + np.array([-3, -3]),\n",
" np.random.randn(120, 2) + np.array([-3, 3]),\n",
" np.random.randn(120, 2) + np.array([3, -3])])\n",
"\n",
"Y = np.concatenate([np.ones((240)), -np.ones((240))])"
],
"execution_count": 104,
"outputs": []
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since beginning of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "19TWP-1eKURB",
"outputId": "43b1b7e2-88a5-4029-a18c-356a044a775b"
},
"execution_count": 105,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712551727.1302803\n",
"Mon Apr 8 04:48:47 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "c7b9646a-5445-41b5-d9e6-445cd8750efb",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
}
},
"source": [
"tn_model.compile(optimizer=\"adam\", loss=\"mean_squared_error\")\n",
"tn_model.fit(X, Y, epochs=300, verbose=2)"
],
"execution_count": 106,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 1.0023 - 1s/epoch - 100ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.9975 - 76ms/epoch - 5ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.8507 - 76ms/epoch - 5ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.1117 - 78ms/epoch - 5ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0329 - 77ms/epoch - 5ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0185 - 77ms/epoch - 5ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0118 - 75ms/epoch - 5ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0102 - 73ms/epoch - 5ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0088 - 73ms/epoch - 5ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0079 - 69ms/epoch - 5ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0074 - 70ms/epoch - 5ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0057 - 72ms/epoch - 5ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0054 - 71ms/epoch - 5ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0046 - 69ms/epoch - 5ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0040 - 69ms/epoch - 5ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0032 - 69ms/epoch - 5ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0030 - 70ms/epoch - 5ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0021 - 70ms/epoch - 5ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0017 - 69ms/epoch - 5ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0014 - 69ms/epoch - 5ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 0.0010 - 69ms/epoch - 5ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 7.4994e-04 - 72ms/epoch - 5ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 4.6808e-04 - 72ms/epoch - 5ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 4.4390e-04 - 69ms/epoch - 5ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 2.4576e-04 - 70ms/epoch - 5ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 1.5634e-04 - 68ms/epoch - 5ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 1.1147e-04 - 72ms/epoch - 5ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 7.4414e-05 - 72ms/epoch - 5ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 4.3733e-05 - 74ms/epoch - 5ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 3.2999e-05 - 69ms/epoch - 5ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 2.4605e-05 - 72ms/epoch - 5ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.9113e-05 - 73ms/epoch - 5ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.6686e-05 - 70ms/epoch - 5ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.3679e-05 - 71ms/epoch - 5ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.0668e-05 - 71ms/epoch - 5ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 9.6508e-06 - 72ms/epoch - 5ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 8.0257e-06 - 69ms/epoch - 5ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 7.0060e-06 - 69ms/epoch - 5ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 6.5962e-06 - 70ms/epoch - 5ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 6.1898e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 5.1754e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 4.9432e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 4.7964e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 4.1308e-06 - 69ms/epoch - 5ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 4.2937e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.7828e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 3.2584e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.9771e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.9724e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 2.8885e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 2.3030e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 2.2343e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 2.1989e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 2.0276e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.9212e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.9814e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.8089e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.7033e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.5017e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.3317e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 1.4085e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.3037e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 1.4130e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 1.1663e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 1.0560e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 1.1044e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.0523e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 9.8094e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 8.6530e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 9.8371e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 8.5050e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 7.9595e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 8.8431e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 8.8551e-07 - 56ms/epoch - 4ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 8.9212e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 1.1534e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 9.5566e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 1.0114e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 9.8471e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.0388e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 9.0618e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 6.5194e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 6.2850e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 5.9408e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 6.7113e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 8.3348e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 5.3358e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 4.6226e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 4.7089e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 4.9008e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 4.5298e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 5.6227e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 6.0587e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 5.1576e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 4.4737e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 3.4417e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 3.6697e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 3.7099e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 3.0841e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 3.5584e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 4.2734e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 4.1845e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 4.2607e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 3.5599e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 3.6648e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 3.1276e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 2.5565e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 2.7974e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 2.3440e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.5436e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 2.1995e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 2.5650e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 2.6319e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.4583e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 2.6979e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.6604e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 1.9730e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 1.9665e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 1.8929e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 1.8591e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 3.1807e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 5.0254e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 6.1254e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.3852e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 1.8185e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.9738e-07 - 56ms/epoch - 4ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.8454e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 1.8145e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 1.4415e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 1.8262e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 2.2953e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.1215e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 1.8028e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 1.7266e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 1.9162e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 1.5528e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 2.1223e-07 - 57ms/epoch - 4ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 2.1278e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 4.8598e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.5127e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.1829e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.9039e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.2530e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 5.7791e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 4.2646e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.1884e-06 - 57ms/epoch - 4ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 1.0918e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 6.6377e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 6.4389e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 3.7698e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 6.1407e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 7.4776e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 5.9511e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 7.4537e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 4.3218e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.1160e-07 - 58ms/epoch - 4ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 3.0968e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 3.4397e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 2.1265e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.4072e-06 - 61ms/epoch - 4ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 4.6922e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.2973e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.3339e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 4.5527e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 2.7844e-07 - 65ms/epoch - 4ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.5283e-07 - 60ms/epoch - 4ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 7.5264e-08 - 60ms/epoch - 4ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.1378e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 1.8391e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 4.9894e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.5966e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.3835e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 7.6076e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 2.1893e-06 - 58ms/epoch - 4ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 1.4536e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 2.7191e-07 - 59ms/epoch - 4ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 1.3431e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.4273e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 2.9140e-07 - 64ms/epoch - 4ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 5.3306e-07 - 64ms/epoch - 4ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 8.6440e-07 - 66ms/epoch - 4ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 4.7824e-07 - 64ms/epoch - 4ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 1.6589e-06 - 64ms/epoch - 4ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 9.9811e-07 - 66ms/epoch - 4ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 4.8519e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.1934e-07 - 67ms/epoch - 4ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 2.2653e-07 - 67ms/epoch - 4ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 3.6052e-07 - 66ms/epoch - 4ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.9339e-07 - 64ms/epoch - 4ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 4.8522e-07 - 67ms/epoch - 4ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.8866e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 2.3056e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.3643e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 5.6246e-07 - 63ms/epoch - 4ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 4.7142e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 7.2287e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.0171e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 2.3299e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 2.0576e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 7.4074e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.4979e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 1.0731e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 3.0518e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 7.4313e-06 - 60ms/epoch - 4ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 8.8583e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.0080e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.9635e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 1.7079e-05 - 64ms/epoch - 4ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.9491e-05 - 63ms/epoch - 4ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.0911e-05 - 65ms/epoch - 4ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 3.3790e-06 - 63ms/epoch - 4ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 2.0787e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 4.2652e-07 - 62ms/epoch - 4ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.4451e-07 - 61ms/epoch - 4ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.5545e-06 - 62ms/epoch - 4ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 9.1844e-06 - 59ms/epoch - 4ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 3.2140e-05 - 61ms/epoch - 4ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 3.2546e-05 - 68ms/epoch - 5ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 3.9286e-05 - 66ms/epoch - 4ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 2.6887e-05 - 66ms/epoch - 4ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 2.3730e-05 - 66ms/epoch - 4ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 7.8985e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 8.1140e-06 - 65ms/epoch - 4ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 7.7473e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.9960e-06 - 71ms/epoch - 5ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.2620e-06 - 70ms/epoch - 5ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 4.8832e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 9.9713e-08 - 69ms/epoch - 5ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.2190e-07 - 68ms/epoch - 5ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 2.0059e-06 - 69ms/epoch - 5ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 1.9025e-06 - 74ms/epoch - 5ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.3200e-06 - 75ms/epoch - 5ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 9.8250e-07 - 73ms/epoch - 5ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 2.2560e-06 - 71ms/epoch - 5ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 8.2283e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.6634e-06 - 71ms/epoch - 5ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 8.2100e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 3.3838e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 2.6051e-07 - 72ms/epoch - 5ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 5.6733e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 4.6619e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 8.8079e-07 - 72ms/epoch - 5ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 2.6520e-06 - 72ms/epoch - 5ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 3.6122e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 2.7042e-06 - 67ms/epoch - 4ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.3794e-06 - 72ms/epoch - 5ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.5170e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 1.2719e-07 - 74ms/epoch - 5ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.5478e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 1.8307e-06 - 70ms/epoch - 5ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 2.4844e-05 - 71ms/epoch - 5ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 2.9400e-05 - 69ms/epoch - 5ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.4731e-05 - 72ms/epoch - 5ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 3.1949e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 3.6555e-06 - 71ms/epoch - 5ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.6385e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 3.6987e-07 - 66ms/epoch - 4ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 1.0524e-07 - 73ms/epoch - 5ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 7.2278e-08 - 72ms/epoch - 5ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 3.1167e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 4.4801e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 1.7850e-07 - 68ms/epoch - 5ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 7.8511e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.6156e-05 - 69ms/epoch - 5ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 6.8491e-05 - 70ms/epoch - 5ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 5.6540e-05 - 70ms/epoch - 5ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 4.9481e-05 - 71ms/epoch - 5ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 1.9372e-05 - 69ms/epoch - 5ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 3.5787e-05 - 69ms/epoch - 5ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 6.2425e-05 - 68ms/epoch - 5ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 8.3614e-05 - 69ms/epoch - 5ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 5.8372e-05 - 68ms/epoch - 5ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 4.9462e-05 - 72ms/epoch - 5ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 3.4556e-05 - 70ms/epoch - 5ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 4.0440e-05 - 72ms/epoch - 5ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 2.3191e-05 - 71ms/epoch - 5ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 2.7420e-06 - 68ms/epoch - 5ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 3.2617e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 3.8364e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 3.1620e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.7222e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 7.0001e-08 - 68ms/epoch - 5ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 9.1745e-08 - 71ms/epoch - 5ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 2.5277e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 2.6860e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 1.4157e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 1.3112e-07 - 71ms/epoch - 5ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 2.8328e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 1.9064e-07 - 68ms/epoch - 5ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 1.8961e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 4.2630e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 3.4013e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 1.0841e-06 - 69ms/epoch - 5ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 1.5307e-06 - 72ms/epoch - 5ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 4.1567e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 1.4208e-07 - 69ms/epoch - 5ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 4.5704e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.2157e-07 - 70ms/epoch - 5ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 1.5761e-07 - 67ms/epoch - 4ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 6.7827e-08 - 68ms/epoch - 5ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7ce34015f6d0>"
]
},
"metadata": {},
"execution_count": 106
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "9da6e84e-97ea-40d7-c9a9-9bba81d54a53",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 443
}
},
"source": [
"# Plotting code, feel free to ignore.\n",
"h = 1.0\n",
"x_min, x_max = X[:, 0].min() - 5, X[:, 0].max() + 5\n",
"y_min, y_max = X[:, 1].min() - 5, X[:, 1].max() + 5\n",
"xx, yy = np.meshgrid(np.arange(x_min, x_max, h),\n",
" np.arange(y_min, y_max, h))\n",
"\n",
"# here \"model\" is your model's prediction (classification) function\n",
"Z = tn_model.predict(np.c_[xx.ravel(), yy.ravel()])\n",
"\n",
"# Put the result into a color plot\n",
"Z = Z.reshape(xx.shape)\n",
"plt.contourf(xx, yy, Z)\n",
"plt.axis('off')\n",
"\n",
"# Plot also the training points\n",
"plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)"
],
"execution_count": 107,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7cec8323efb0>"
]
},
"metadata": {},
"execution_count": 107
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAGFCAYAAABg2vAPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACJQklEQVR4nO3dd3wc13no/d+Z2b7oANEIAuy9iKQoUqS6qC5bki1b7o7tOI7jOI5zE79JnNw05+am3Zub5t6bbMtFktVp9cLeKfYKkATR6/aZ8/6xAIi2DVj05/v52CSA2ZkBBO7zzDnPeY7SWmuEEEIIMWMZE30DQgghhJhYkgwIIYQQM5wkA0IIIcQMJ8mAEEIIMcNJMiCEEELMcJIMCCGEEDOcJANCCCHEDCfJgBBCCDHDOdI98J7y3xvL+xBC9Igsm5OV87QvcA/4uLNGDfg4XB0Z8PHcqsYh57ij/NiAjx/O25uVexNCjJ8lcy6lPEZGBoSYZFxHayfkuufqZk3IdYUQE0+SASEmoYlKCIQQM5MkA0IIIcQMJ8mAEJPUWI8OuC+4xvT8QoipQ5IBISaxbCYEuedlg1IhxPAkGRBikhtpQpB/OpzlOxFCTFeSDAghhBAznCQDQkwBsrpACDGWJBkQYoqQhEAIMVYkGRBiCpGEQAgxFiQZEEIIIWY4SQaEmGJkdEAIkW2SDAgxBaWbEAxeXii9BoQQw5FkQIgpKhsjBNKFUAgBkgwIIYQQM54kA0JMYdmuH5BtjIWYmSQZEGKKk4JCIcRoSTIgxDQgCYEQYjQkGRBimpCEQAgxUpIMCDGNuI7WSlIghMiYJANCTHOj2cr4hfqlWbwTIcRkJcmAEEIIMcNJMiCEEELMcJIMCCGEEDOcJANCzDCyP4EQYjBJBoQQQogZTpIBIYQQYoaTZEAIIYSY4SQZEEIIIWY4SQaEmOHcF1xpH/tYx7oxvBMhxESRZECIaUhaEgshMiHJgBBCCDHDSTIghBBCzHCSDAghhBAznCQDQgghxAwnyYAQQggxw0kyIMQMkH86nPax5+pmjeGdCCEmI0kGhBBCiBlOkgEhhBBihpNkQAghhJjhJBkQQiT1Qv3Sib4FIcQYk2RACJER2Z9AiOlHkgEhRMYkIRBiepFkQAgxIpIQCDF9SDIgxAyUe15n5TySEAgxPUgyIIQYFUkIhJj6JBkQQoyaJARCTG2SDAghskISAiGmLkkGhBBZIwmBEFOTJANCCNwXXFk7lyQEQkw9kgwIIbJOEgIhphZJBoQQQwzexlhaEgsxvUkyIIQYEzI6IMTUIcmAEEIIMcNJMiCEGDMyOiDE1CDJgBBCCDHDSTIghBhTMjogxOQnyYAQQggxw0kyIIQYVjaXF8rogBCTmyQDQgggu10IhRBTiyQDQohxIaMDQkxekgwIMUPlntcTfQtCiElCkgEhxLiR0QEhJidJBoQQQogZTpIBIUTasrFhkYwOCDH5SDIghBBCzHCSDAgxQ+SfDmf8msG9BoQQ05MkA0KIcSdTBUJMLpIMCCH6SOMhIWYmSQaEEBnJRhGhEGJykWRACCGEmOEkGRBCJDVcEaGMDggxvUgyIMQMNpqWxKNNCKSIUIjJQ5IBIYQQYoaTZEAIMUAmKwpkukCI6UGSASGEmES0DXY4/qcQ48Ux0TcghJj8ztXNYm5V47Bfe6F+KXeUHxvnO5p+Yh2K5pfdtO9yoSMK5dTkrY9QfEsYZ6FsNy3GliQDQggxwaItivP/lYMVUGArAHRU0b7TRecBJ9Wf7sZdJkMFYuzINIEQYtSkdmB06n/hHZAI9LEVdlhx+afeibkxMWNIMiCEyIqRJASyvBAizQaBk86hiUAvWxGucxC6JG/XYuzIb5cQYojhVhTIDoZjI1yf3ttw+LI5xnciZjJJBoSY4UbTeGgwmS7InJFm5ZaSCi8xhiQZEGIGyT8dnuhbEIN458VQrhQJmanxL4qNzw2JGUmSASFEVsnoQGYMFxTdFAYSJARKU7ApgumT5YVi7EgyIIQQE6z49jD5GyPxDwwNSsf/BHLXRCm9LzSBdydmApmFEkIMy33BRbg6MuBzyZoP9SeNiDKjDCh/V4jCzRHa97iIdSgcOZq8dRE8s6W/gBh7kgwIMU25jtYSWTZnom9DZMBdbssogJgQMk0ghMjqioJMSa8BISaeJANCiIxIvwEhph9JBoQQCWWynfFgsqpAiKlDkgEhRMZkdECI6UWSASFmGGk8JIQYTJIBIQSQeRFhOqMDMlUgxNQgyYAQIqnR1A0IIaYGSQaEECILtA3amui7EGJkpOmQEGLE0u1IOJ11nzJpecVN4KQDtMJVYVG0JUze+ihKHrfEFCG/qkKIlGSJ4fBa33JR9/WcvkQAIFJvUP+Yj/qfedHSSVhMEZIMCCH6jKQT4UxdZhhpNmh43BP/oCcR6P/3jr0uOg86J+DOhMicJANCCDECbTtSjJYoTesbUnwppgapGRBCjNpMrB0IXzQGjggMphXhSybRFkXbThfhyyaGU5OzIkbOqiiGvPuKSURGBoSYgUbSeEjqBgZSDoDU0ypn/imXlpfddB9z0HnYyeVHfZz71xwiLUkSCSHGmSQDQggxAjnLYskPUBodU/HRA60A1TeSEG0zqPumX5YiiklDkgEhxpjpcjD35uWsfM/1LLr7Gty53om+paRGup3xTCskzFsbwczRoIb7eemeQYMEP0tbEW0y6TomcwVicpDfRCHG0LxbV7DxM3fh8nuwYxbKNLju9+7k8M+2c+AHr6YzyjypuC+4CFdHsn7exzrW8XDe3qyfdywZbpjzO93UfsOP1aEGJAXKAG2lmAYwNN1HneSuGH6EIdat0BFw5OqeKQkhxo78igkxRuZcv5gbv/AA2o4HCcNhAmA6Haz5wA1gaw788LWJvMWEcs9rOmtkTjsVd5nN/C900nnISfdxB1jgmWORuyrKmX/MS/n64aYJuo45aP6Nm9CF+Nuz4bEp2BSh+LYwhjvb34EQcTJNIEQWeAv9FM4vxVvo7/vcuo/firY1yhg+qK587/U4/RP37j7S3QtHWkg4HYsIAQwn5K+LUvn+IJUfClJ0cwRHocZZaJF06McGT9XAbKBtp5OL3/YTqjWvHhYyaHnFzYWv5GDLhpNijMjIgBCjULSwnHUfu4XKdfP7PndxzxlOPbef/KripK81nCbV1y/m9LZDY3yX42cmLjEcjlJQsCVC4689CY7QKCfkrbs65RLrUlz5pZd4vcGgBFIrwpfjSUHJnZIRiOyTZECIESpZOpu7/vGDKHPgAFvFNXMpX12T8vXa1rgmcTGhTBWMTuHmCIHTDrqP9r7N9vwsjfhoQeUHApj9/vN37HH2DCQk+JlrRdtbLoq3hmXPA5F1kgwIMUKb//BelGlgDEoGDNPAJnVTesM06G7sYPaGBfhKcgm1dnNxzxns6ORfbzZWhYTTiTJh9ocDtO9y0fqmi0iDgXJAzoooRTeF8cwe+DsSbjDjeUCSmQUrYBA8Z+LI0ziLbZTkaiJLJBkQYgSKF1dQUJN4KV1vgmDbNoYx9DFO25poKMKmz9yFp+BqnUG4M8ieb/yGU88fzP5NixGLtii6TzjRFrgrLbxzrbQCsTKhYFOEgk0RtCbpawxXOktLNLVfzQHAWWJRsjVM3tpoet+EEElIMiDECORVFqZ1nGEYaK1R/aKAbdsopXD53GjPwGI8V46HzZ+/H63h9AtjnxDknw7TviBxEeNIpgqmU92AHYb6x7xXNxxSxLcpLrWo/GAAd3n62xKmSh5yV0VpezNZQamm/xRCtMng8qM+Yh3xokUhRkOSATFlGE6TuTctY/7tq/AW+Omsb6XtfBMF1SV4Cvx01bdx6vkD1B84P+b3EukeeRFX29lGfMU5uPN9Q1YaKKXQWrP+E7dx9qXD2LHJuwfudJ8q0BouftdH4IyDviDc8/AeaTK48BU/cz/XhbMwO80ivPMsvDUxgrUm2IMzh4GJQFz848ZnPOSuieIsmGJNK8SkIsmAGFOG06TmhqUsvHM1vuJcuhs7OPX8Qc6/fgxtpR/o3Pk+7vyHD1A4rxTbsjFMg4K5s6i+fknfk3fJ4grm37aSc6+8zWv/9Hjf+v50FS0sJ39OMbFghMv7zhELDxx+LZxfSuW6+ShD0Xy6nkhXCFdOomrxq5RSxMJRXvzrn9Ld2Im3wMfd//KRpMd78n1UrJ3HxV2nM/oeBnMdrSWybM6ozpFNL9Qv5Y7yYxN9G2kJnDYJnE6wBbGtsMPQ8pqbsneGsnI9pWD2b3Vz8ft+gmcc8UJDTfKiwh4de1wU3y6rDMTISTIgxozT7+aOv38/JUsq+wJ4bmURlevmc+XwBX7zFz8ZEnATufFP3kl+dQlwdT6+d+i998/epj41Ny6j41Ir+7/3SlrnLlpQxubP30/RgrK+z0WDEQ7/7C0OPfoGnjwfN/3ZQ5SvqcHuSWAM0yDY2pXW+QEcbifa0nRebKEwSa1Bf558X9rnH0szdaqgY58rHpCHPKX3sBUde5xZSwYATF+8q2Go1qTriINYUNGxI0UvCgWRZlleIEZHkgExZjZ99h6KFpYDVwN475+zllWx4dN38Na/PT3gNcpQQ57o8+cUU7l+PulShmLpO6/l0E/ewAon30wmv7qEu/75w5iugf8UnF4Xaz9yMy6/m8p188ivnjXg/gHceT5ioQiG04Ey1IC6gGS6mzrSPK4zreMm0nSZKtAaQhdMIs0GplfjWxjD6lakWhRih4yEhYGRZoOOPU5iHQaOXJu8dVFcs4aeUMcg2mqAoXEWapQB3moLb7WFHYOOna7kWyUDhkemCMToSDIgxoSvJJe5Ny5L2H3PMA0W3L6K/d97hdJV1Sy4fRWzls7GneslFolx7uUjHPn5DtovNFG+Zm7STn7DcfndFC+qoOFwbdLj1nzoRkyXY8jywF7L37UxYZCPv8bB2RcPs+CO1UmvEwtHaT5VD0Dzicu01zWTW1mYcKVBoLmTKwfHvvYBUhcRwvTuORA4a3Ll514ijVe7/hkeG1e5nXKpn5k3dHmftqHxKQ+tr7vj+xX0fL35RQ/5m8KUPRBCGWBHoeVFN61vubCD8d8DZ6FF0S0R8q6N0HnASdtbrnifWGu4moEetiJvjawoEKMjyYAYE2Ur56QM3obD5IGv/S4uvxutr77jOlwO5t+2krk3L2fbFx/NKAkYcP4EAb6X0+eievOSpMf1FvQlSwjKr5nL5f3nKFtZjeEYJrhrTf3B89jRq6MUO//rOW7/0vvQto3qlxBo2wYUO//7uYxrHkTmgrUmtV/3DxkBsEMGoXMpht6VpmDj0FGRlpfdtL7es0pEqwHJRPt2F4ZbM+vOMBe/3VOc2O+pP9pqcOWXXppfchFrM+PJRN/Xh0kIVHwUw1M9+XtTiMlNJprE2EhzyNzpc/UcPnCY3XCYGA6Tm7/4EI3HLmacEFhRi9YzDUmPced6UyYMvfeWjNPv5vV/epzO+la01kODuIaqDQt59/c/S9mqagAu7z/Htr94lPa6lgGHdl5q5cW//im120+mvK/JItFeBVNhS+PGpz3xRCDRMLzqq+AbyIg3/SncMrBoz47Ek4HEBX+K1lfcNL/iJHDaMcx14x/H2npGKQZ8vV9S0LNDon9ZjNkfDkjzITFqMjIgxkTj23VJn6iBlF83TANvYQ7+WXk0Hr1I8aLyviLBZGzL5syLhwh3BpMeF+oIYsestM6ZiNaarsttBFu7eer3v8X8ratY/4nbcHicVwscexIZd66X27/0Pp767LfIKctn5SObKegpiox0hTj76tvs+soLWelAWDivlGUPbmD2dQtRTgcN5xs58toxLh6/POzxM3GqINqm4lX7yeh4x8DAWQd2oCdxNDS5q6OUvjM0oJ0wQPCsAzuc6mekaN42mjbUCrTGtyjCrLtkJ0ORHZIMiDHRdaWd2u0nqbpuYcKn73QK7qyYRdGCcl7937/k7n/+ML6SXEDFCw17phZ6z9P7RN52roHdX/tNynPHghHOv3Gcmi1LRpwQKKWo3X4ifr5wlO6Gdpze4Z+UDdMArbn+c/dSuryqb2UCxJsNLb5nLWUr5vDU576dsvAxmbk3LeOGLzwAWvd9X1VLKqleXsX+bYfY/fT+EZ97OrG60khsDHBX2FR+oJPQRRMdA1eZjSNn+CkcO91aykQrFNKmCJx2cv4/ncz5VDfeOTJNIEZHpgnEmHnr356io655wNC5tu0B9QGpKKWwojG6Gzp48jPfZO+3X6a9tolgazctp+qp3X6SrittRIMR2mub2PXVF3jmf3yPaCC9NdcHvv8qdmx0b6Qt/aYjam5clvR8hsNk1rLZ8b8PSpKUUhTUzOJd3/49vEU5I7oXX0kuN/zJO1FKDUhweq91zdZVVC2rHNG5IT46MFqTZStjMzeN78UGR56NcoC3xsK3wEqYCAC4SsexSZSt0DG4/BMvGfyTEmJYMjIgxky4I8jTn/sO87euYtGda/AW59Dd2MH5146y/hO3p1UHYJgGueX5rHrfFi68eZwjj23nyGPbs3aPHRdbePV//4pb/+o9aS8NHCzSbzrC5XcP2cVwsFTX8RT4uf1vH+HXn/1m0kr24Sy+dx0olfBna1s2K29aRt3RS0O+ls5UQSJTcYmhM1/jWxhNMHcfp0zIXZ1+pb67zMZdGSN8aZzeWrUi2mgSPGfimyejA2LkJBkQaTPdDubetJzyNTUopWh4u44zLx4mFkwcBGLhKCee2suJp/YO+Hz56hoqr12QtICvdwRh3m2rUEqx9qM3c/6NY7zxz0+m3awolVnLq7jxCw/0XS/ThCDY2kXDkavLFzvqmuPLIM3hzzN4amM4SimKFpRRsSa+SiETs5bNTvozNUyDsrmjK+ybTrUDs+4JceHLOWhLD5sQlNw1sC5A63hnwq7DTqyQwlNpkX9tBLNff6jy9wY5/285pOoamFiSZYQJjo80GHirLVDI9sZiRCQZEGkpWljO1r97BHe+r2/If96tK1j3sVt46W8e48qhCxmdb/c3XuTeldU4PM4BwWtwQFZKYfYb7p6zaTE3fOGdvPx3Px/x9+IvzWPZAxuYd+tKPAW+vusMJ1WC4PS5KVk6m8a36wA4+ewBVr53c9Lrp5N02DGL2RsXZpwMeIv8KY+xkyxZHM3owFTkqbKZ8zvd1P/CS6S+37SKz6bkzjCF119NdGNditqv+4jUO+gN2J37NI1Peyh9R5DCLfEE1VNhk78xQvsOF5kG9ZElEIrml9xc+YUP0HjnWxTdFCZn2cjrTsTMIzmkSMmd7+OO//V+XLne+Fy0aWCYBkopHB4Xt//tI/hL8zM6Z0ddM898/jtc3nd2QA1BLBgh3BnEtuxhA6ZhGlRvXkLhvNIRfS/Fiyt455c/ydIHNuAt9A9Z0thfOkHbcJhs/btH8BTGg3Dn5Vb2fTfeBnnwEkPbsumoaxm20dCQawOmM7Nc3el3k1dZlPy8tubisaFTBGNlKiwv9NZYzP3DLmr+oJPKD3ZT9YluFn6xc0AioG2o/aq/X8Kgrv6poeEJL+174/sYRNsUVnC8RgXiYm29v1OK4FmTi9/x0/zy8IWsQgxHRgZESovuXBOfCx8miPU+1S+5fx17v/VSRudtr23mN3/5E3wlueSUFRDpChFo7uR9P/ujpK+zYxY1Ny6j9WzyPgKDKUNx618+jOl2pt1fIJ3lj7idLLr7Gg79+A0ADj36Bl1X2lj1vi1Xlw52hzjx9D4O/fgN7vrnD1M4vzTleVtO12f0/S3YuiplvQIKju1I3sNgpMsMp2LdQC+lwDPbxjN7+ALAwCkHkYZEK07ibQobnvDgmx/j/H/kYAUUA4O6HnR8ovOMUP8pjp6/Nz3jxb84hqdy8u58KSYPSQZESnM2L07aRMgwDWpuWJpxMtAr0NRJoKcPv780L+XxWl9tVpSJqk2LepYmpi+dGgLDNKjetLgvGQA4+9IRzr50BH9pHobTQXdDe1//gG1/+Sj3//vHE96Ltm1ioShnXzqS1j3mzylmzYdvombL0pT3q5Qi0J68/8JYcUWieMJRgu6p88Qa61C073bRtiPB7oV9FHZQcfnn3ngiMGTpYDZqLHoSit58z+7tlZzg3Iam7S0X5e/O3kZKYvqSZECk5HA7UwaZwRv9jFSwtZtoMJJwrT7Eg2/HxZaEX09k1pLKUTcZSsSd58VblEOwZeBOht0NQzclCrV284uP/zf3/J+P9u2U2Pvz7V2W+Or//hWxUOoiycL5pdzds9FSul0aw4HUT+/ZrB0oau1k894TLDx/BUNrbKXoWOrjys1FRIonPjGINBp0HnJiBRWuYpvcNRFML7Rtd3HlcU+/bYRTC55wkJ3APwwDPLMt3LMtIg0mwTNm8mvZilDd8P8uY12KaKuB6dE4S4buryBmHkkGRErNJy+TP6c4YRC1Y1bfJjyjZUctTj1/gCX3rx92KF9rjR2zaDhcy+wNC7AiMRrerkura59tJdheLol0N0jKKS/g4e9/ltrtJ9j55ef7RjoS3kvU4pk/+i5L7lvHkvvXkze7CCsa48Lrxzny8+20nL6S1v1t/vz9aU972LZN/ZkGgik6M2ZTVUczH/jNGzgsG6OnNsTQmvxj3eSeDnDmI7MJlU1MwaIdgys/99Kx1xVv72sAFjQ86SF/Y5i2NzwjOOsYRlVbUfZgCHeFxem/z03jWhrlGJjFRJoVjU956Xr76nJKV5lFyV0hcldIweFMJsmASOn4U3tZeOeahF83HCbHn9yTtesd/NHrVF23EH9p/oAgZ1t236jA/f/1ib6n6XBnkCM/287hn72V9LyeQl9aQbN/ApDJngjKUFRtXEjx4gqe+oNvE2rtTnq8HbU4+qtdHP3VrmG3bk6lcH4pxT1bRKeibQ0a9jyzP+3zpxodSLnEUGs+cPh1HJaFMehbUxqMqGb2U42c/nhV2vc0WnYYuk850FFFxwEH3Ud7hv+1gp58Usd0TyIw0ur+saDJWx/FU2URbVFY3enVfsc6FHYEDBdEWhTn/zMHO6QG1BhErhhc+p6f8vcGyF8vux/OVLKaQKTUfOIy+7//KsCAFrq9fz/6+C4u7TmTteuFO4Ps/c7LtJyqx+rXza/tXCPhziD51cUDpi3cuV7WffxWHvj6p1j+7o24c4f2fS9eXMHiu9emvPbg7oi9H6fbNdEwTbyFOax8z/VpHd93nRHsUJg/pyTtY4NdIZ7/5ktcOduY8XUy0X/TojkdzVR1tg5JBHopDb7LYdwN6XWLHA1tQ9Nzbk79XR6Xvufn8o99dL/tStBsSA36c7wNnJdQbk3x7WHKH46P6NhpP8ArYm0GTc/FRzianvHEE4Fh6xk0V37lxU7wn6L7hIPab/o48Rd5nPhiHrXf9NF9Qp4lpxP5rynScvBHr9N6roEV795E6fL4k1zr2Qbe/sWOtAvdUvGV5LL43nUsuW8d7jxvfP68J+iH2rvxFvtx5XgS1i/kVxWz/uO3cc2Hb+K1//2rATv/rX7/liHbBQ+mdfzpuf9owEi6EhqmwaK71rDnG78Zu22IVXrFlgAHfvgau/edH1nCMYragbLu9rSOczdHCZeO7VTBlcc9tG/PdN3/xCm+K4Sn0kY5NN5qC6Mnx7IjcOmHftIftVC07XRReGOYzkPOxLszotARTechJ/nXDhwdaH7JTdOzngHbKQdOOQiccFJyd4jiW8c+mRNjT5IBkbbaN09Q++YJDIcBSmVldz0Aw2my6ffvZsHWVQPm9PvXKLjzfGkFZmUoTKeDm7/4Lp76g2/TeamV1R+6kaqNi9J+fTY4fW4cXhfR7uy/UZZfM5fr/+AecisKUx4b6Q5z+Gdv4QzHiCybk/V7SSbsSFWBH2c7xzZAhxsM2rdPVCOldJYUDtWyzYOZq8nfEMFTYYOrZxOu7S4iV4yMzqUjisA5M0ki0MOASLNBqM7A6jZw5NvYERVPBGDg63tGF5qejS+n9NZIK+SpTpIBkTE7lt11yzd+4QGqNy9O+tSeyRN6fP4dbvjCA+RWFOBwpxeUkp4zwxECKxob0KZZ9TRLWrB1Fd6iHLrq2zj1/AEu7j6d0f4DpSuq2Pp3j0CaScvhn745qh0QIfnoQLK6geNFFYRNB24r8fUtt0H33NFs55tax14nGDoLOwWOhAJTk3dNhI4DLoildw/aUsTaFM3b3LTvdFH9e104CzRtO1wZ71cBYHrT25SpbYeLlhevFk4aXnvAiMAQhqb1TRfemolZriqyR2oGxIQqXlROzQ1LkyYCI2E4TApqStJOBNKpCUi3bsCOWZx96UjfsLzT7+aef/0IN//5Q1Sun0/xwnLmXL+Y2//2EW77q/dgONNf6rju47eBUgm7GGqtsS0bbdsc+smbHP5p8qLKsdBbNxBxONk2b1XS2NWwuQDtGNu3oVjHRL7NaRw5mor3hlj4Fx0YPpvU0XxgA6FYp+LyT+MJU6w9s1EB0Ji5Nv6FFp45sXhgT8LuHnhuO6iSjyjYitCF7C/VFeNPRgbEhJp784oxW/uf0WhCqr0CLDutKQTbsrEtG19JHo/89PNorbHCsb4tiXtXM/T+OXvDAtb91i3s/vpvUp47p7ygr14jmQtvHmf317alXN6YiZHWDjw/fzXuWJTbzx1GK9BKoXqSqqbrC2i6viBr95iII28iO/ApYu1Q+y0fVofCDhhk/GhvK4KnnYQbDEyvJhbNJBlQFN0UQpnxTZfqvpmo3kD3HT/49SmvILnAtCDJgJhQ7ryxGSIeyQ6ESc9lKOp2nmLOxkVDzt1/J8JwVxBvvp/y1dV9CU6ye1GGweL71rH/B68NmFYoXTGHOdcvxuFx0naukTMvHsZTkHoTIm3ZtJyqHzYRcB2tHVXdwEgSAq0UTyy5ljMbS1l2+iL+QJhun4ejCyu5fsH5Ed9LJvLXR2l5KZOeAdleUqgIHHcM+HgkQrUmjiI7vZGOnmmR/E1hCm+I/175F1lUfihA/WPe+BO/ofstXBjh96s0OculP8F0IMmAmFDdV9ozbgSUjtEmAvEhfo3WgNa89e/PcPqFgyy65xrWfezWvuWL/ROBjsut5PUU9fUf6Uh1Lw63k1lLKrm8/xzuXC+3/tXDlK6Ygx2z0IBhGKz/7dvY/Y3UowfKNAg0Z29EYLDhEoJ0tjTuyvGya83CjK9nR6DrbSexdoWZq8ldEcUYJh+xw9B11IkVUDgLbfyLYygT7CgEL5iYeRZWR7qPsL1tfnv/ng2jP0+oziB0ziR5sqLBhPx1UfKvi8S3Ne4nd2UM/9JOuo44iTYbGB6NHaJn+WGG96g0yoSCTbKaYDqQZEBMqFMvHGT1B2/I+HV2zCIajODO9fY1I4J4X//e5GI0CYFGU/vmCVrOXOHUcwf62gxf3ncO9dtG39N+/2vkluWPeESidwri1r9+mJIls4GBCYXpdLDx03fSfKqewnmlCZsnWeEoF944nvA6qUYHPDke5q2uxpPjpqu1m7MHLhCLjP7J71zdLOZWZdbjoG2Hk4anvOiw6iligytOLyV3hii8MYJS8X0qWl5x0bzNg472Hqcwc2wKbwrT+oq7p0FP7yNwZkPsk4em7c10RjfiiUxvT4LhGA7IW3N1+WDnwXRbKPeb3lCgHDD7IwGcRWO0fFaMK0kGxITqbmjn4I/fYM0HEicE/Z++IT4vH+4I8uyffJ+c0nyWP7yJyrVzUYZB2/km2i40MffGZaN6L1coXvlfvxjw/pdTls/9//lxnF7XsAF/pEWQtmXTcraBslXVlC4fPlArQ2FbGisSQ1s2NgxICHqTkD3ffCmtPQ2GXgCuvecaVt+6AqUUttYYhmLLuzdyYudpju88RXNdfD+IbO5bkEj7XidXfuGj7z9ATxGbjkLjU16UCYVbIrS87L669K3fcVaXounp/sEz01+GzIr0xj5xSP/8aa0c6Me/NIZyaXQkyWiDE4pvDxE6Gw8Z3vkx8jdEcfglEZguJBkQE+7A919l8T3X4CnwDx9kez4XDUYItXVzetshjj+1l3B7gM5LrVzefy7+ZK0U2rJx+tzMWlqJrzh3RIWJ2rZpu9A8pM7rlr98GKfPnbVaBIgHccM0uP8/Ps6VQ7VJiykN02DWstk8/6c/ZMOn7qBoflnf10Kt3ez77sucev7giO5j3Z2rWXP7yr7vzewJPg6Xg+U3LGH5DUtorW/jzZ/v5HKa+yaMlLah8Znk7YCbnneTsypC87ZESUmKHf2yZjK1LAbQ5F+b2TbShgv8i6N0HU60aZSCKPiqLUpunZpbVIvUJBkQacuvLmHWstmgNfUHL9BV35aV8/pKcvEW5iQ9xo5ZHHt8F/u++8qwX++d4weIBsI8+8ff5+5//Qg5pfmZ35BSHHti94BPLb5vXd8Og6MxeBqh9++eAj81NyxJ49YUbeca+fVnvknh/FJyywsJdwZpOFKbdofBwVMFLo+TNbetTJnkFJTmc8/vbuXpL79AO8m7C7ovuAhXjyxwBM+bWCmK5OyQQcOTXnTSGYzxCNKTKxFQjviISabCDSlqEQxN204XvgXST2C6kmRApOQtyuHGLzxA+ZqavmCmtaZ2+wne/D9PEeka3X7pvuLkiQAQX1ufxlN+XlUxTq+Trvr2+LNhijn8RF+fs2kRtW+dINTWzbIHN7DhU3dkZYVCotcbpjGg3iGRUHug7+fdeqaB1jMNo7ofgOoVVZhp9Drobea06cENHH9826ivO9hjHet4OG8vVnd6P+Oug66+WoKJl84IQbaLEoeq+FAAR17mP5BYW4r+BbYi2iJtaaYzSQZEUk6fm7v/5cP4Z8X74Kt+xXlV1y3ijn/4AM/80XdH1Zq4Yu38lIHWMA2aTlxO+PWaG5ex9qM3kze7CGBAUWEyvYnN4Kf1yvXzueufP8T2f3+GDZ+6o+/zY0kZ8cLERD8L27I5/us9WdnvoP/ogNvnTnurZsNQlFQVUVyUR3NLR9/n01lRkC5nUQZ9AVK12E19ArIXnJOv389ZGcXMsXtaI2fxd6knISp/JEjuspEVe5o+TSxhzUD8GmbOpMi6xBiRZEAkteiea8gpyx+2OM4wDYoXxjsIjmazorzZRWm9J9fvPzvs56//3L0suvuaIfeW7pP8cMcYpkFeZRHrf/v2MWuKNCyt4/s+DEpmbMum9cwVjjy2PeuX7GjqzHhPhrIOB81Zv5M4d4WNq8IiUm+kEexHHsxLHwjQdcJB4KhzxOe4SqFcNjrC1XOZGleJjbPYxlMRw1Nt0/iUZ+DKxVFy5NnkrIhScH0Ed1niJErb8c2FgmdNUPECQN8Cq28gKn99hOYX3Yl/3lqRv1bqBaYzSQZEUgu3ribZG6Vt2Sy4fdWokoFYKNKzo2DigKttm2hw6JvR6g/dOCQR6DXcU39GFBQtKEtrhGE4g1dBpHdNhR2zaTvfQPHCCgDCHQGOP7WPwz99c2QrBRLoHR2oO36JQEcAb4437aQg2BmCMdpSQCkoezBI7df8YKUK9ukuies5rmfpYcGWMAXXRyncHOXSj6HzQLId/dKh0RFjwMeuWRaxNoPIFSfdb49+f4wBlMY7P8acTwZStumINBrUfcdHtMmkbz/p33hwlVnM/mgAV7FNweYIbTtdWN0M3cPB0LgrLHJWSHOh6UySAZGUp8CXNEAYptHXajcTpsvB7A0L8Bb4CbR0JX3yti2b2u0nh2yQlFtRmHRJIoxuaF8pNardO0bUb0AplKFQyuDH7/5XTLeDcHtg7LZCJl58+dpPtnPHJ25B2zrhvge9x7Y1tNNyqRXGcHmhb65F9ae6qf2Gv+dpOwlTgwXpJAaucpuim8LkrY32BdHydwWJtRkEzzkY+UjD0Da+kfosv732dQxU+JfFqHxf6kTA6lZc+IofK9BzYL9AH2k0qP2qn7mf78SRo6n+dDeXfuAjfMnsV4uh8C+OUfFIQNoOT3OSDIikuhs6cOd5E66hty2LrittGZ1z8b1rWffx23D5r85V2zELjKEb8PQGwcM/fXPIeRbdc03a793DjRCk8+Q+6tGFETBMg6IFZcy+dj7e4lyUgiuHa2lOUjMxWrVHL/LMV7Zx7b1rKZs7a9hjev9b7HhiT1au+UL9Uu4oP5bw694ai8LNYVpeTjLHbmhyVkQJnnVgdTHo6T7+y5F/fYSSrSEMJ8N2LzTcUPpQkPP/7gdrkhbJGZri28MYTo1/WQx3aXp1FfGnfTX8qIcd3zehY6+Lwi0RXMU2NX/QRajOjG8+ZIB/YQzXrInc20GMF0kGRFInnt3Pps/enfDrhmly8tkDaZ9v0T3XsOmz9/R93DvqoEzjalOhmIXWYDgMoqEIr/3j48MGwvyq4owTAW3b8QTENOJPwWkWGU6Em/7sIWwr/kYcL6C8xCt//wu6GzpSvDJ9/QsJL5+6wpP//iw5hX6WbFrI8i1Lcfuurj3v7gjw5s93UnfsUlrnHry8cCRdCAs2RWh5zZ1guiD+9Fp8Sxjz/hCNv/bQedg5ZJi7/S03nXtdFGwJU7I1POwTbsPjXrAm0zLBgZRLU7I187a/HfucKesTOvY5+5YjKgXeORbeOSMvCBZTkyQDIqnT2w6y6K41FC0sHxI4tW1zac9ZLu46lda5DKfJuo/dOuzXep/Ag63dnH7+AKbbSdu5Bs69cpRYePh58mgo0hPYk7+J9yUCWqMMA9X7bUze9/4+/X/mRfPLuOufPsyTn/kG0e4whtOk5oalVG9ZitPnov1CEyef3U/bucwC7mBdrd3seeYA+54/xOwlFXj8Hrrburl86sqAbZwHdyLM5oqCXs5CzewPBbj4Ax/Y+uoTbs+QefnDQTyz4wlT5QeDRNtC1H3TR6TBpP9/YDusaHnRTaTBpPJDA4fXI40GwTOT+a1QkzvC+Xo7pEhVc2EFp8A/BDHmJvO/ADEJ2FGLF/78R1z7O1uZf9uqvvXosXCUE0/vY++3X0p7Prty3by+DX6Go5TCV5RD3a7TNL5dl/J8F14/zvxbV6b3jTD0CT/TCvqJZjhM/LPyWHjnGs6/dpQ7/uED5FcV9608KF9VzbIHNnDgh69x4AevpX3eRPsV2JZN7dsXs/ktjEjO8hjz/riTtu1uAiccaBt882I4Cm3ad7tofM6D6dPkr4uAYkgicJWi67CTwEkH/sXx4BppMmh4OpMdDcebBgWFN45sMyDXLItYe5KEQOm0pxzE9CbJgEgpGojw1r89zd5vvkTRonKwNU0nLhENZLbUyJPvy+pxtdtP0HqugfyqEgzHJJ3rHQMLbl/FgttXkVteAFwdPegtwlzzwRvpuNgyqhUek42rSFN6bwjuje9EePE7Ptq2u/tWB1gdOt7COFV+Z2jadjrxL47Rsc/J5Z+M0ZKIUeupZzGh4gMBPBUjC9j5myIETiVZyaAV7tkyJSBGVSstZppwZ5DLe89yef+5jBMBgO7G9Oa6uxuSt7rtpW3NC3/+Y1rOXOn52B4wjD0dKUPhLcmJL3lMsAJD2zarHtmc0XldR2uzcXvjoukFD4HTPc8xfYVxPUVyds/fE7EV0WaT8GUjnghohi+um2gOKLk7zPw/7yR35ciX9DlyU/170HSfkGdCIcmAGEf1B84TaOpMOK1g2zat5xppGWYjnIK5syhbXUNOz9Nwr1BrN09/7ts894UfcO7VoxNW7JcJrfWIlwralo0VicVXXySgDIOCmll4C/0ZnXsqJAR2BNq2u5IE8BT//ZXGzLVpfdPVc+hk/H3RGE5N0Y1hHKPs+td91HG1t8CwFKHzjrRbQIvpS1JCMWL+0nyWPXAtc29ZgcPjpP1CE8d/vYezLx0ZNthpW7P9P5/l1v/5cE+ToYEd9tCanf/93IDXVG1cyLqP30ZBdUnf564cusCur74wIGm4cugCVw5doKBmFvlzisevY2Caer8/w2Fyef85ShZVxHdAzLBuwTAN2s81ptzYCRjRzyBR/cBkEb5iosOj6EqoFfnrovEphcHNdbKi//4DI+9ZYAcVnUec5K1Jv8mUHYHOQ04iDQaGG3JWRLGTtRju/9ooTK5/MWK8STIgRqRkaSV3/K8PYLocfXPWxYsquOGP30nNDUt5+Uu/QFtD5znrdpzkN3/1E6795NYBAb7tbAM7v/oCDYevPp3W3LiMm/7swXiL3n5mLa/i7n/5CM/+8feGjCK89LePcdc/fQhfcS6ozJYF9p9iyPR1qY6v23mKtrMNnHs1vjpi5SPXs+D2VRjKTPta2ra5fOA8Z146wuwNC5MeG2ztJtDcmfb30N9kTgjS+1ElOkjjrrDJXRmlMeOiwf6/g+l2RBxdR8PGp900POFBW+CZY1G4OYJvYXzKwBhUBtB5xEH9T3zYYeLjvRqanvPgroz1TJ0kZnjsUY9AiKlPkgGRMcNpcutfvWdAIgBXC9mqrlvE8nddx5GfDd9H/9LuMzyx+2sULSjDU+An0NRJ2/mBy+EMh8Gm378LYEjDo97rbPjUHTz3hR8M+FpXfRtP/O7XWXDHaubfugJXjgenz4U735e0s15/djSG6Yq/26YT6NMJ5od+/DotZxpY9b7NrH7/DT1dBtMPFtFghBNP7WXf914BYMPvbMWV6x22T4K2bY49uXtUXQsna0LgKrMwPDZ2aCQznIpZDwRQjnhv/s4DQ3sSJHttwZYwbW+6epLTsR5WVwN2EgycVAROXM0A3BUWhTeGyVsXJXjW5NL3fX0dA/sH//Bls2eQIsE9K03BxihKIsGMJ78CImPVm5fgLUgyH61g2QMbePvnO/oCkjINKtbOxVeUQ7C1m0t7zw5bG9Br9nULceclXlVgmAZlq6rJKS+gq75twNeigTDHHt/Fscd3AeDwOLnn336LwprhO+v13XZPcDacjiGfGymtNXbMonRFNdd9+k5mLavKqKNhd1Mnr3zp57Sea8AKXy0ke/lLP2frl97fN/UA9G2BfHn/OY787K1R3TeklxAM7jUw1gwnFG5JsalOEld+7qP6d7sp3BKhc58r9Qv6uhiGKX1HiNwVUep/4Y33+R9Tg4L3oO81XG9Q/1MfwfNhIk1JGmf0vU7Hawf6Jz9K4y63Kb59dFuQi+lBkgGRsZKllVgxCzPBnLRSCl9xLt6iHAJNncy9eTkbPnXHgIK2UHuAXV99IeHyt5zS/LS2IfbPyhuSDAxmRWJ4kiQWw91/tiilMEyTa3/n9ozOr7Um3BHkmc9/h0DT0OH+hiN1PPmZb7DsweuYd8tyHG4nHRdbOPbkbk49f3DYKZqRmIwjBMW3hwnXm3QdcfYLcOk9rUebDOq+6afms12UvjNIwxPeFK+Nf75wcwSlwLfAImdpjNY3jTRHFbK118Hg08a/3r4jjUTM0OSuiWIFFIHjDkBh+GwKNkUoviU8bItmMfNIMiAypi2d1tubbdnxef8/fXDIkj93npcbv/AAwLAJQbgzmFZxXbgzmPKYvKrijCvrsynTIsFoIMzJ5w5w+KdvEWrrTnhc56VWdv73c0OKLrMtk4RgLLoQDqZMqPxQgO5jDtp2uog2GRheTeiimbqlsFaEL5l0n3BQuCVC+IpB+47UIwS6fx1fRrMvwyUqqRKEDBIIpVOPkCgwvZrK9wWxI2BHFaZXX+3EKQSSDIgRuLz3DCvevTHh17Vt017XQrg9wLW/c/uww+JKKbStufa3b+fcK28Pmd+ufeskViSGwz18w5Tea6TTerd05eR6sk3ll5/4MqG2wETfxgCTbYRAGfHOhDnLr06dNL/soumZNJoIGZrOg04c+TbOQpuUgdfUOIuujrR458dofSOdx+neoJ5JcpRhnYdOY1TEAldJzx4XLjBcUiwohpLcUGTs0r6ztF1oSrjWXRkGh3/2FqUr5uAvyUs4LK4Mhbcoh/I1NUO+Fg2EOfToG8O+TtsalGLvt15Mea/OHA/rP37rlGhGpLWm83LrpEsEek32PgRFN0coviON+W8bOg86Of9vuTQ92ztNkOD3w9DkXRPF7Jdj5CyL4ci340/lCaWeehjMWWRReFPmbYeViyS9BDTKhLy1mTcJEzOLJAMicxp+85c/obups6eBTvypozc5OPSTNzmz7RCeZEWG/SQ67tCjb7L3Oy8TC0fjhXg98+BWNMbFnadw5XoxXYkHt1a+53re+8M/wOX3TIlmREqpvu9xsprMCYFSULI1jCPPJvkTtho47N8XnAe9xtA4C2xm3TswwVAmVH2sG8OrexICPej1mSWehsem5N4g877QRcnWcL/zpkPjWxTFWWAPTQhUPCEpfTCImX7JjJihZJpAjEh3QztP/O7XmHfzcmpuXIbT56btXCMnntlHy6l6gLTXuQ9XINfr8E/e5PiTe5h36wpWPLyR3PJCDNOgYt18qjYuYsOn7uC1f/gll/aeHfC6Ve/bwtqP3jzybzANmawKSFd+VTE5FQV0XW7L6nknyuBtjMdDwZYwTc96UsTkwf/deofb4wHUcGvyr4tQfGsY0z/0RO4Km3n/o4v2XS469juxwwpXmUXeNRHqH/UNc/7E7JCi6RkP7jKbnKUxqj4RoO4bPT0DepcLJtF9zMm8L3TS8qKbjj0udCx+vLvSomRreMBUihCJSDIgRswKxzj1/EFOPX9w2K83Hq2j83IrOWX5Q3oFQHy4P9DUwZXDF5JeJxoMs/DO1fhn5QMDO+u5fC5u/ev38vQffpvWMw3xZY0PXsc1H7kpo+8l08A+ltMOvqLcaZMMTITCLRG6jjgJ1ZqDiutSFeYpUJrc9WFyl8fIWRZLWmTnyNEU3xqm+NarQ/vdJxPtmJhMPBFpfMqDf0kX3jkW87/QRfseJ11HnATPJTunAgu6jjgof1eI0vtCRNsMDLfGWaDRNnS97aB9j4tYu8KRr8m/NoJ/SfLvTcw88usgxo6GHT2V7r1TCX1f6ikY3PHfz6ccVa1cP5+SxZXDLjNUhoFS8SkBgOs/dy/XfvL2IcclvEVbE2juzPgJfywTh2BLV0bHj7fJPFUA8V4Ecz7ZTdEtYQxPup0De2hF5x4Xl77n5+y/5hBpHv4t0gpC6xsu6r7lo/brPpqedxNtU31P5RnTikhDfAMlANOvKbqptwYidfvlzgPxFRGGG9xlNs4CjR2Bum/4uPhdP11vOwjVOug64uDid/zUfdOHLWUEoh9JBsSYurT7DL/5nz+lc9CTbmd9Ky/+zc+o23Ey5TlqbliadGMew2FSc8NSZm9cyKK7rkGp9Lv7KUOx5xu/IdjSNSRhyZZwRzCtWgDbsvtGU8ToGC6YdXeYvGsjGcy/9+gZTYg2GZz/Dz/WoNWrwVqTM/+YS8MTHrqPOwicctL8opsz/5hLtNnI/Hr9WF0D35J1ulsTDPPrdeUJL4EzPYO/vT0Rer63wGlHT48FIeJkmkCMuUt7zvCr3/4KxYsr8BXnEmzpoun4pbRf7/S4IMVafcNhsvT+9diWhWGm1x1Oa82lPWc4+/Lb2DGbm/78obSnC+yYRaCli5zS/JTHvvoPv+TWv34P4EjYREnb8Y2M9nwz9QoJkb5os5Hxar2r4hsGXfhyDjV/0IXhiI8I1H3Thx0atGRQK9Cahl978M61CJ43R7QRkiN/YFT3zO4thkw+veGdN7AuINal6NjjTNyDQCva9zgpuTsk+xIIQEYGxDhqPnGZ2rdOZJQIALRfbEn6hq61prupg5IllWknAhAf6s8piwfzJe9YH99JMZ3ugD1LG9/4lyeSPvHbls2VQxeoP3CeXV95IWlBZeflNl744qM0HKlL+/5FaoZbj3obgcgVg+Zt8b4CHXtc2EGVIMgqUGD4bBx5SZYrDkdp3FUx3GVXf59ClwwuP+olZYMipSneOnBJYvBMGsmIrXrqEYSQkQExBZx6dj+r37cl8QEa3LnehA2KkjFdTvJmF1G+emivgyGX0Rptx//32j89zpVDtRz80etc8+GhxYp2z5P+mRcP8+DXP0VeVXFf7YAds6jbfpLTLx7C4XHRVd9G49GLGd+7SC13VZTO/ck6DKbT7U/R9pab4tvDdB1L8ZZpK4Kn49X9Z/4hN71hfqXBgNJ3XF3CGLpocOHLOeikCwHiv09l7wpiDuqBpNPdt2Fyr2QV40iSATHpdTd2sPvr29jwqTuwbXvA7oO9m/OYzsyfcLRt03zqMgVzk29g1Kv17BUuvHGCk8/u7yvyO/ij17GjFqvevwWn92rQCTR0cPDRN7jud+/E6Lm3vo2QHCZzNi8h2B5gx38+m/F9T2Xn6mYxtyp118hsyVkWw11uEW4Ybi+B/n0BkgdPO6SINBhom5THahscfo2r1CJ8MfXqAsOjcc2y6djjRCnwVFs0PO6NJwIJg7rGWWpT/mAQ34Kh9TSeObE0vi+NZ07iWhwxs0gyIKaEo7/aRXdjB6vfv4WiBeVAfF+CcFeInNL8lBsaDUcZBsef3NMXrFM5+KM3uPDG8SGfP/yztzj25G4qr12Ay++m83IbVw6d5+Y/fwjDaSRYBaFYct863v75DikYHEPKhKrf7ubid32Eah1XG/PYCsOnKdgYoeUlT9rn81ZbBM84EgdppXsCMRRcF+XKL1P/btkhReiCg1CdSftON/4lEYLnU701K0rvCw2bCAC4ijT+pTG6TziGny4wNP4lMZyFUi+QDY91rJvoW0jqi2kcI8mAmDIuvHGcC28cx1Pox3Q6iAbDPPKTzyed509WEHjk59upP3Aeh9tJNBgZ8GQ/mBWJcXnfuYRfj4WiXHj9WN/HDq+LOZuXDBjFGMy2bObduoKDP3o94TFi9By5murPdBM8Z9J93IGOKTyzLXJWRVEGBM874gE+CcNr4yqzKfBGaHnZTcKnbq0o3BJfs5e3PkLbDifhy4P7HcDVUYl+9Qc9Qbv7eDrTXZpoS/IEuPzhIBe+7I8f19e8KF5D4SyyKX849SZfiQTOmrS+5iZwyoHW4J0Xo+iGCP7Fk6/B0WQP1JOFJANiygm1xnfy8xblpCz4G+7rWmuCrd19lfuxcJQjj21nzYduHP54W3P08V1EA+n3jXf53UkTgd7zptuyeTKZTBsWpUsp8M2z8M0b+iRd9Yluzv5zDrE2g+GH1TWFWyIYDjCKNOXvCVL/M298rr/3qbtn98CCLVc7/hlOmPM73Vx53EvnAWe/J/R+icDwd5vOd4TpTf5U78jV1Hy2i/adLtp2urA6Dcxcm4LrIuRvjGCmPyAyQOubLhoe9/bbPhoCJx0EjjspuStE8W2Z76+QigT0sSfJgJiywh2BlE/0w1FK4SvKoXzNXOr3nwPg4I9fx5PvY+k7rx3Q08BwmJx6fj/7vvNyZvfWGcSKxjCdif+JKUMRaOzI6LzTzQv1S7mj/FjqA8eQ4YDqT3dT+1V/v6dt1RfsclbGBgS4/PVRXLNsWl9z0XXMCRo8cywKt4TJWRGjfz5peqH8oSCuYjsekDsy2cUw8Zy/cmr8y1JXJ5re+AZORTdnp8NQ6LJBw+M9WUT/6Yeevzc958E7LzZs0tVLAvvkJMmAmLLsmM3J5/az9B3XZlwzYFs2xYvK+5IBNOz88vMce2I3C7auwleSS7C1m9PbDtF+oSnje7PCMc6+dIT5t63CcCS4NwWnXzyU9DxFC8qoWDcPZRg0HbtI/YHzGd+LSM1ZoJn7h1107HPRvteJHVA4S+JP0f6lQ1v3eqstvB8MAsmH2mPditqv+Ik09h+qT1fi7YmLbwuP+Ml+NNq2u+IL0hOtQjA0rW+4eLp42XjelsgCSQbElHbox29Qdd1CcsoKMkoIlAI7OvTppeNiC/u++0pW7u3AD1+nauMiXDnuYfsfHPzh6wSbh2897Cnwc9OfPUj56pq+XgaGadBe28TLX/rFiBKUqeCxjnU8nLd3Qq5tuKFgU4SCTdnr03vllx4iTUaSVQGJaEruDdHyG098wyJDxwOwGU8Eim7N/lB8OoLnEhQk9rIVrWels+FUJMmAmNLCHUGe+aPvsfajN7Pg9lV9WxrbMQtlGglrCpRhULfr9JjeW3dDO898/rts/P27qFw3v+/zobZuDv74DWq3nyS/uoTuhnZioatDvobT5I5/+AD5VUXxj/slObmVRdz1Tx/iyU9/nWBP7YSYnKLtiq7DSboAJmJofAtjFN8cofD6+KZL0TYD02+TuzI67tsR9x/WX6hr8ZI8WdIpuoWKyUmSATHlhdsDbP/3Z9j99d+QU5pPLBRhzvWL2fCpO4Y93rZs6naeovNiy5jfW+flVrZ98VFyyvLJm1NMLBjFW5zD6vffwHWfvhOIFzCe3naI/d99hXBnkJobllKYoPeBYRq4cjwsece17P9edkYwMjEViwcnSvjicKsIUtE4cjXl745PPxguyFub7gYFo5POXH7HIj+ehkjC7Re0go7F45ytiKyQZEBMG7FghLbz8YY2R3+1C39pPssfuq5vlEBbNobDpPFoHW/8y5Pjem9dV9rputLOknesZ+Pv3TVgUySH28miu6+hYk0NT3/+u8y7ZQW2ZSec9jBMg/m3r5yQZEBkIOMHZI17jkXVxwI4/OO3/j+Tgr6WtXnM2t4Glh6SEGjiyUDL+tT7dYjseaF+acpjvrgi9XkkGRDT1u6vbePU8wdYdNc15FQUEO4IcvblI1zed3YUm9eMnKfAz4bf2QrEpyn6M0yDnIpCVj2yGXeeN2X9g8s//tVjMiqQGe/cGMrUaCudrCDeknj2h8cnERhpRX8sz8G5R8qZ+9N6iOnetgXxfZoMuPBQOeGSzFb3iKvSCexjRZIBMa21nWtk11dfmOjbAGDB1lWQpC+CYRosuucaarefpHhhOYZj+O512rbpqh/froXjmQj0BqqJKiTMFtML+RsjtL3lSmu6oPJD3Tjzxy4RyNaSvu65Po59poaiAx3knA2Chu5qDy1r84jlSkhJZCIDfTrkv5wQ4ySvshB08jd7l9/D+deOsuD2VYkPUorjT+3L8t1NPhO5siBbZt0bItpsxLsK9jXpGbhc0FVmUfH+AJ6K7O8aNFZr+i2/SePmQho3F47J+aeayR7o0yHJgBDjJJJGB0Nta+r3n+fkc/tZeOeaIashbMum8Wgdp7cdHKvbHGIipwem+iiB4YTZvxUgcNJB+24n0VYDM1fjnRPDVWbjLrNxlWQ3CZCmPtk3HYJ9KpIMCDFOzr16lBXv3pTw67Zlc3HXKWLhKG/9v6fpqG1m+bs34S2MtyyOBiOceHof+7//yrA9EpIZq4DevmDg3rmdNQOTl3B1dtbsT+VRAmWAf0kM/5Kx69svCcDozYSAn4zSOsW4ZY97yn9vrO9FzFAzqTDtrk/exuwlFUP2LdC2RmvNk//xLI0Xmvs+rwxFYVk+yjBoa2jHyjAJGEujSQQGb2M80S2JxdQx04P2SLx8+7+kPEaSgWlsJgXZqcLhcnDLB7cwd1U1tmWjtcZ0mIS6w7z8w9epO3Zpom9xWIMDf38jHQ2QhGDqk8A8Ns7VDd9nZMTn++j/l/IYSQYmAQnaM09BWT41K+fgcDlorW/j3MELfW2HsylZEM+GbEwLSFKQmgTdySHbQXq8pJMMSM1AlkhAF5B+8G0nxPlzJ69+Ym46e9hPHtmsDThXN2tAQiCBTyQzVQPyZCfJQBok0E8PY/2UPN0MDviJZKNIcHBCICYHCbxTj/vCyJo+STKABPvJTAL4yKQbyEcjWysFek2lhECCpBjOSAPxZDAjkgEJ9hNHgvnwxiNYj6VsJwK9JMiKVKZywJ3MpmUyIMF/bEmAn/rBPJmxCvRiYkkQFclM+WRAAn92zMQAPx0DugTyxCQYisks9/wE7J7Wz5RLBiT4j9x0D/jTIbhLME9NgvrMNtFBc7qa1MmABP7MTceAP1WD/FQK7CMp3Bur+f3pHOwlkInJalIlAxL80zOdAv5UCvSTPbiPdyV+7/WymRRkOxGQ4CtEeiY0GZDgn9xUD/pTJdBP1iA/VZbZZSspGEkikI1gn+P3snrFfCorStC25nzdFY4cPUswNDl/L2a6/NOpd/8UmRv3ZEASgMSmavCfzEF/MgX6yRjcR9v6t3+3wJEmBYmSgLF+qs8/HWbu6mpu/dANKENhGAZaa2qqyrh+3XKe/8aL1J9pGNN7EGKyGJdkQBKAoaZa4J+sAX+yBPvJEOgnoqf/HeXHhrQPnlvVmHZCMFwikK0kINUTZGF5Abd9+EaUUigj/vutlAIFDpfJXZ+8jZ/+/a8IdoWycj9CTGZjlgxIAjDQVAn+ky3oT4ZgP5GBfjJu2vNw3l4e61jX93HvPWYySpCtJGA0Q8Yrbozfb28i0J9hGOCEJZsWsn/b4RFfIxGnx8mia+dTs2oOTqeDproWjr55gtb6tqxfa7pxHa2d6FuYltJOBmZ6cJ8qwXywyRbcB5sMwb6/mfqEn8rDeXuzdq6RJALZmCceHESqFz+IYRoJj1dKUT13Fm9nOfgU1Mzijv/5Ljx5vvh1DEVJVRHLb1jCnm++yJHHtmf1ekKkY1KtJhgrUzWQD2eyB/fhSMBPbTImAJA4CRg8OjCWxqpgLFkiAPFkwHAkPybjazpNtv79+3DnegeMSBgOE4D1n7iNtgtNXNx5KqvXFSKVSZMMTKeAncpUDOiDTbYAP5zJGPT7m6wJAGR3JGCyajh6kaoNC/oC8WC2ZdP49sWsXrPmhqX4inMTft22bFY+vEmSATHu0k4GZlKwTmU6BPPBpkJwT2SyB32Y3IG/v8mWBGRrVGC4eeZjT+ym+vrFCV+jlOL4U9n9eVSum4cdsxImIIZpULaqGsNhYMfsrF5biGQmzcjAeJiOQby/qRzQE5kKgb6/qRL0B8tGEjDcyoLJrH7/OQ786HXWfOCGAQHajlko02D7fz5DR11zVq+pDANU6vchZRrM3bKUxfeuJbeigHBHkNPbDnHq+YNEA7LOXmTfpE8GpnsA7286BvPhjEuA15qai00sOXsJVyRGW56fQ0vm0J7nz9olpmrg7zXZRgEmwoHvv0rj23Use2ADpSvnoG3Npb1nOPrLnTQeze4UAUDjsYvMu3VFwq9r26btQhO3/tV7qFw7D9uyMUwDX3Ee136yjGUPbuDZP/4+gabOrN+bmNmymgzMpMDda6YE8EQm45O7Oxzloed3UtnQhqUUSmtQig0HT/PmusXsWLsoo/NN9aA/2FRJAsar09ylPWe4tOfMuFzrzG8Os+5jt+JwO+KjBIMowyDQ1EnlunnA1SLH3mJDX3EuN//5u3jmj747LvcrZo60k4HpFuhnehCHyRnIs+H+F/dQ3tgOgKl7lqz1/Lll7wk6crwcXVTVd/x0C/aJTJUkINsm07r0aCDMy3/3GLf99XtRhr46NdEzAnD6N4eo3rxk2EQB4qsOZi2bTdHCclpO1Y/nrYtpbtJPEww2U4P4dA3c2TarqZ2aS4nneTVw2+G3qbqhM62524xojYpptKlgmEY2E2WyJwHD9RiYrP3n3XleHB4nwdZu7Kg1onNc3neOJ37vGyx757XU3LAUw+Wg9cwVjj2xm0BzFwtuX5X09VprylbNkWRAZNW4JgMzIZBL0M6+vid3rfHUR3B2x4jmOgiVuoYE9NKTLWgFKkEPGwW4W6I422JEC51ZuT8VtSnZ2U7x7nacXRbagPbFfho3FxKqmLhVOJM9CZhKKtfNY9UHbqBsRbz5WqQ7zMln93HwR2+MqKCv82ILO7/8PDu//PyAz5csrUz5WqUUeZVFGV9TiGTSTgamcyCXAJ592R56zz3VTfkLzXhaon2fC5a6uHxnCd013r7PKUsnTQZ6GbHs9L9XEZv5P7iEtz4cH3YAlA35x7vJP9HN+feU07kwe0WLw8kk6GsNaFDZ7aUzaY12isDpc3P95++jZsuSgef1u1n24HVUrl/As//je8MmBPnVJax4eBO55QUEW7s49sRuGo7UJb1e65kGtG0nnCbolVNekPH3AuDO97HwjtWULJ2Ntm0u7z3L2ZeOEAtHU79YTGtTbppgMAnkyU2H+fDc493UPDZ0SNTTGGHejy5x9v0VdM+Nt3YNlrkxUizPtpyKSEF2fvVL32jFWx8eknwoHQ+8c355haN/OBftHHn0zcYTfrjBoOUVN50HnOiowlFgU3B9mMLNEYzMdw6eEdz5Pu7514+QW1kI9Gxi1I9hGuTPKWbV+zaz91svXf2Cgpv+9EHm3rR8wPFzb1pO47GLPP///RArEhv2mlYkhm3ZmCmSgfw5xRl/P1UbF3HTnz+I6TABhUZTc8NS1n70Zrb9xaO0nL6S8TnF9DHhycBMCebTIShPCFsz+9n478jgWfjegFv5bBMnPzUHlKJjsZ+oz8QRtIYdHdAKWq/JG1Vw7mNpivZ2JJ2SMCKagre7aF2Tl/A0Yz2cHzhrUvcNP9oG7PhPMdamaHrWQ+dBJ9Wf6saQnmJDbPz0neRUFAxJAvozTIPF96xl33deRtvxX4Trfu+uIYlAr5Illdz2N+/lhT/7UcJzBpo7ySlLfl1vUU5GjYnyq0u45S/ehTKMqzs09vyLcuV62fq/3s8vP/5lot2Ts1ZDjL2sJQPTJahL0J5c/OeDOLsSF2opwNMcxXs5TLDSA6biwrvLmPfjy2DpvkCtew4Olbq4cnN25ludXTEcoeRvxsrQrGqtozRvYrbB1RZc+oEPbRHPhK7eGWgIXzJpet5D6Tsyv7/x3J9gvHkK/VTfsDS+e2EKrhwPnnwfwdZuDEc8OUhEKUX5mhr8s/LobuxAGaoviejVePQSueWFSa9pOh2Urqymfv+5tL6fZQ9uiF9/uB0aTQN3jpcFt6/i2BO70zqfmH7STgamQrCXQD79uDqGH04d7KbYCXLzeo5dCeHP9gyLH3SiYwpHnk3h9REKt7RzjTs7v8sxQ3GaxE/8AGiIdSvsCBMyHN/1tgOrK0lA04q2nS5K7g5hZKeectTGsgVxuorml6XcyKi/aCg+5z7v1hVpbYC09e/fR055IabTpLO+jeNP7ubYk3uwoxaNb9cyP0ljol5OX/q/UNXXL07YAjl+U1C1aZEkAzPYhE8TDDaTA7pUfw/VVeLgIqkL8MycgU9X7nKbikeClL83CBaoMfhNd+Ro3LNjhC+Zg566+9GKzv0uuo46KdwcpuSOMCrJe3K2hS6ZYOi+6YFhbzGiiLYYuMukF34v20rvZ2HbNvX7zxELxgusk21C1F/e7OK+p/Sc0nzWf+J2qjYtYtsXH6X5VHpz9x11LWkdB/HdEpNRSuFwTbpwIMbRuPzXnw4BXgL1xPAtimF4beygYmjVAIDGUaDxVg8/laAUY/pbXnRTmMs/Tp2s6LCi5SU3kSaDyg8Gs97iIJF0E4+xSJYmk4K5s1hy3zqKFpYTC0epffMEp7cdSrgssOnoRaLBCE5v4qdvrTVKKeyoRUHNLNrON9JytiGt++k/XN/799Llc1j5nus5+KPXabvQRN7somFHGWzLpvnEJdovNKV1LYDmk/XxDZASjFrYlk3Tictpn09MP1l/C5gOgb8/SQLGh45BqM7EjoG7zMb0awKnHITqTHwLY3QdGu5NWQOK0vsCE7JUTseg9Q13332kpug65KJte4zC68dnKVfOsijNL3iSHKFxltg4i6bvqMDK91zPuo/f2rcZkbY15atqWPX+LbzwZz+i7dzQaaNYOMrRx3ex6r2bh51nh6urCyrXz6dy/Xxe/tIvqNt5klgogul2Ji0AHI5hGiy5fz2HHn2DN//vr7nzHz/U9/letmVjhaO89e/PZHTuY0/spuKauQm/rgzFiaf3ZXROMb2MOhmYbsEfJAEYT1pD66suml92Ywd63/Q0yhUfvsbQfev3rw53x4Ov6dOUvjNI7ur06gqyreOAk9CFTP8JaRp+5aNjf4zZHwrgyM1Ov4NEPLNtvPOjBM85EkwVKIpvDY/bSMV4q9q4iHUfvxWgb868N7i7c71s/dL7+MXH/nvYboIHvv8quWUFzLt1RdK1/70Jxk1//iA//8h/sfOr29j8uXv7Rg4y4S3048730XTsEs98/jtc8+GbqLpuEcpQ2JbNhTePc+D7r9Jem9luirVvneD4r/ew5P71fa2P4Wob5J1ffj7rOzSKqSXjZGA6Bv9ekgSMv8Zfe2h9ffC6NoWO9ATJ/gFMg7PYovDGCM58G//i2JgPb8c6FKE6ExR4ayxM39Xg3b7T1bO+MZM3/PixoQsmtd/wM/ezXWP+Pcz+UJC6b/kI1Tl6EirAAGxF8dYQeesnV8OZ9gXurBURrnh404Dg1198N8Bcam5YytmXjgz5urY1r/3T49TtPs2Nf/LOpNdRhsJ0mCy8YzVHHtuOYSiu/Z2tONxXqzJ1z/4YqRKE3sSk9UwDL/3NY1dXK7R1j2rp347/eo4rh2tZ9tB1lCwqR9uay/vOceQXO9JelSCmr7TfhiQJENkWvmIMkwj0GuYNUyuizSbOApucZWM7GmAF4MqvvHQedF4N9qYmf0OE0vvjlffRNiPDRKAfWxGpN+k84iRvzdgGY9Ovqf5MN90nHHQedGKHFM4Sm4LrIrhKxnZ6YG5VI+fqZo3pNRIxHAZlK+ckPcaOWVSsnTdsMtCrbHV1woRiIEXJ0tkAnHh6H64cD+s+diva1ihDpU4CemoBIl0Dl3lGukJDPjeYK8eDtyiHcHuAUHsg4XHnXnmbc6+8neL7EDPRNC8bSk6SgInVvtuVstJ9KE3HfueYJgN2BGq/lkO4flCwtxTtO1xEmwyqPhHAkWsTa0tU2JgGpek8MPbJAMTbD+csjZGzdAyTKEsz51ITnnCU9lwfDcV52d8MKhPpXFuphEHecBhs/MxdLLxzTVqX01qje1YhzL5uAes+Fp+eSFRzMOR6psGhn7zZ97GnwI/T5yLY3JWwXXDe7CLW/tYtVG9e3DeNcWnvGfZ99xWapSBQZGDGJQOSAEwesTZ1tR4gbYpY59gFGKtbcflRL+HLBolGJwKnnHQddZB/bZRQ7SjWCWqFFZwek/WF+zoof7mZVYEzfZ9rLMxl25ZVnCP5yEBnjRp258LRsqMWrWcbKKgpSTjfrwxFV0M7+TWzcHpddNW3EWrrBmDTZ+9hwdZVac/7K0Nxae8Z5t+2ki3/4x0pj483G9Lx/SIU7P7qNup2nGLhXWu45kM34iuJ97CwohanXzjI/u+/2ndvEO8qeM//+SgOj2PA91e+Zi53/0s12774KFcOXUjr3oWYMcmAJAGTj+nX8XibYRww3GNTdBdtU1z4ck7qp32lad/tovL9AVrfdBFpNIYZ3ehdYZBkpYGhcZWMbBvckdAaAicctL7lInzJRLk0eaujFGyK4Mgb+c+0eFc7lc8PXeZW3NbJe57ezsXririQXzKaWx+RyLI5HP3VTjZ//v5hv95b4Lf6fVtY/b4t8c/ZNhfeOsGxX+1Ke0Qg/jpNqCOAbdnc8Cfv7KsPSMaOWdTtOk3buQZOPrufQHMnt/3te6nasHDA602nyaJ7rqHy2vk8/YffIdQaTwg2/v5dODzOISMbhmlgK9j8R/fzy4//d8J/X06fm3m3LCevqphoMML5144Ou7JCzAzTOhmQBGByy7smSttbmTfFz1k+NkPdlx/zEmtPY9hfK2KtBoYL5nyqm/qfeuk+5uj3Oo1/WQxnkUXbG0m+P1tRsDGzKQI7DB37XAQvmCgV78OQuzKasghRa7jySw/tO9wDpmaaX4zXbVR9shvvnMwTEyNsU/7i8FXohgaweeD4Lv7junsyOm+2ighPPX+QWcurWHTXNQPm/RNV+ivDYM6mxVSum59WnUBv0I6Fo/zmf/6EO770vrRXERhOk5otSyhbOSd+HQ2zr10Qv49Br1dK4Z+Vx9qP3MRb/+8ZcisLKV9Vk/jchkFueQHlq2uoP3B+yNfn37aSTX9wD6bLgR2zUQrWfOAGLrx5nNf/6QnZxXAGmhbJgAT9qclTY+FfFo0H0nQL8QxNxx4nDU94UaYmZ1mMwhvDeCpHVwgXblIET6bbj1eDGQ8CDr+m6mMBIs0GwXPxKQPv3BiuYo0VgVCtIz6VMOD7i48WFG4J46lKPwAHTptc/K4fO0x8NQDxuovGfJuqT3Qn7SDYsdsZTwRg0AoNhR3RXPy2j/l/1plxS+K8Y12oJNtBGxoWtV6hMNhFqzcns5NnyVv/9jR1O0+x8uFNFC0ox3CaKTcfUu703hqVUmitMZ0mBdWzcOf50r6v3nvw5PtY8Z7rQSVfaaCUYuGda9j9jRfJm516fw2tNbmVRUOSgcp189jyx++Ib2WtFGa/7oRVGxex5U/eyStf+nna34eYHqZUMiBBf3pRCio/GODKL7107HX2G85M9IYYf6INno+vmdcoOvY76djnpPIDgbT6DQTPmbRtdxG+YmK4Nbmro+Sti9D2WiYjFIrwJZPQZQNPRTwAu4ptXMXxv8c6FQ1PeGjb5Yr3SlB6wNO4I19TdHMI78IYocsGrmI75b4FkSaDum/54xsOoeLLA3vEOhS1X/Mz7086MYfpL6Q1tLyapDmSVljdis5DTvLXZfZE6OyyepYpJj8uPxzIOBnI1ujAonvWsuqR68kpK0j7Ncow0hrqh54AbihqtizpWzmQqXT3QVCGwar3bab2rZNp3ddwHRbXfOhGtK0TLres2bKE/OqSjDociqlv0iYDEvhnBsMJFe8NUnJXiO7jDqyQonOfk/Alx9U1/H1r+XveZPs/2fY0Ibr0qI8FczsTzn1r3a+nQb/mRcGzJs0vjmz/3paX3VS+Pzjgc5FWxYV/z8EK9LtfreI3YGrKHgqgYwYtL7uJPeEFQLk0BRsilNwVwnDHA3/bWy66TzlAg39RDKtbxbcgHm4ERSusLujY66Jwc2TIl+0QRBpSFDoamuAZR8bJQMxvpkwEADrc3r6/h6sjuC+Mz65N6z5+Kyvfc/2QnQHT0fvUn86Qv9bgyvOMKBHI1ILbVrH/u68QaO7EW5ST8P5i4SgXd50e8DlPoZ9Zy6qSnt+2bGpuWMrBH72etXsWk9+EJQMS7EV/znxNwXXxQFR0Q4TAKQcd+5zEuhTOIpvQeZNwfaINgRTYmradLopvD6Oj8aV0/efR23c5r/Y06Esm4n9aXWTeL8BWdB1yot93dZ+BWKfi/P/LwQ4O95SnwIIrj/kYXDWpI4rWN10EzpkUbolQ/5h3wH3GCxSv3m8inYcdwyYDaa98HEEca1/qp/LZJpQ1fLC1FZzNL6XFm94GPkPOP4rRgWVblrDy3dcB6S/vG0wplbT7YB+t6bzURtH88qT7GWSDtygHX0ke+7//Kpv/8L4Et6M58vMdQ0YGnJ7U96ZtndGOiGJ6GFUyIAFdjAVlgH9xDP/iq8P+x/88L3nA1tB5ID5lEG2KPwX7FkQpuiWCb1GMlleSD5OPhLYUTc+7KbguXo1f+1V/z4ZKyahBf169h/BFk/qfeXvyhKGjH6nOqyPDX9v0gKvcInIlSZMkW+Gbn3lhpu0xuXJzIRUvDt1BzwY0iicWX5vxeUdryaZFbH7XhhG1BO6ltebKoQt4CnwUVCdfHmk4TC68cYyWU/Vc9+k7R3S9DG+OU88dwOlzs+5jt2CYJrZl9zQ3giM/38GBH7wKQF5VMWWr5gCKphMXiYWjAzojDv1ejIzbHYupL+1kQAK/mFBpjPJGGgY+vQXOOAicdlJyT7AvQUh9gXQDR/z4lhfdtLzoJndtlEhjFvYmHpwI9Em9TNE9O3ExYtHNYep/kqC4TWnMHE3OqpFVkDdtKkA7FGWvtGKGr84ZtOf5eOGG1Zy1Skd03pFyepxsebhnRGAUTY+UUpSumEP7hSYO/fRNVr7n+mHPZ8cs2utauLjrNNrWFC+qYP7tKwccm/50Q/LjtNYEmjrpbuwA4Ogvd3Jm2yHm3rwc/6xcgm0Bzr36NsHmLjz5Pm74k3dSuX7+gFbI3U0dGA5z2JoBbWti4ah0KZyBJm3NgBC9uk8k2mRnsKFP2wBNzybbtS/BazM8vnOfi/R3LxzpPST5uq0o2DjMFEGPvLVRwpfCtL42sGYCBYZHU/XxboyRvhsoRfOGAlrW5pFzNsjR+jLac31cKiuMV4nWpT5FssZDmU4VrLxxKUaqYf00GaZBQc0sCubOGhKoez/uuNTKti/+GG1rPIV+5t++csh5Mk1KkiUFx57YNeDjcGeQ47/eM+BzptvBnf/4wb5VB/3P5S3MQWs9ZOmkbdkopXjr/z1NLCRLC2caSQbEpNfyaqoNgVIPGyiXRkdgdME6mdEmAplch6vX6vm5lNwVSrq8UikovT9EzvIobdtdhC6aGC7IXR0lf0MER87oGzlph0HnIj9Hc5MXqI21svlZHono+VEPTjCUiu8k2HTsIsGWLgBu+5v3pgz8yQL9gGTD1n3LDXu3X7bCMdZ/4nbW/tatXNx1ikM/fQtvoZ+8yiIi3WFq3zpBqK2b+beuJL+6ZNjrGKbRNwVSsrgCR08dQcPbtRz80RuyadEMJcmAmNS0hsCpdPoQJKsnGEGbw4xlIxFIMVWhNN6aGFa30Tcl4ZljUXRzmNyV8fl+bUHgrIkdVDiL7SEJgm++hW9+cMipJ7tMRgesSHa7OqbqSTDv1hXs+uoLgKJ4QdmozjfgOCO+miEaisSL+kwDs6f/gWEaVG1cRNXGRX1JiTIUGz9zF8ce30XJksr4P55E19Lg8Dj5ySP/hrfQTzQYIdwx9X4vRPZIMiAmN01W4riOgLPE7qkdGK+n+JFKfH+lD4bwVNh9jYf6Nwlq2+6i6Xk3VvfVJ1h3pUXZu4Ij6i44VR3bfoKaVcl3KxxNYeFgptOBvzSfynXzU686SFPvvSmlcLicwzYk6l36CFf7FChTsezB64gGwknvRRkKT4EfKxKj60p7Vu5ZTG3Z+c0VYowoA9xVVnw4PPFR6ZyJWIdB+Xu7UWO+amrk2Uv8e6W3l2+coUFpyt4V7GtyZLgHJgItr7q48kvvgEQAIHzZoPYrfkIXZ84/9dqjl+huD6TdNCgb7vhfH+DaT94+JudOtv3x8C2VFU6/G9tKPG1kWzZdV9qydYtiGpg57xBiyiq6MTKqeoG+IyMK5YTCG8IpkouRy98Yxlk80tbIimiTQcX7A+Sti+IosHEU2OSti1LzB119fRgGs4JJiiS1QlvQ+Ew6RZRjY27V+G9+86v/+xThQLygUmvd979e2RoV6D2/J9+b+sBxpPXwHQZ7GabByWf2j98NiUlPpgnEpJe7JkrgbJj27e6BhYSGTqv7XX+Xf+jH9Pe+aLjh+NFNIeSuiFH6QIhz/5pDtDnBNshJ2CFFw+Ne5n1h+NbCw+k86OxpU5yAVgROOol1qFHtTjjRMqkbCHaE+MH//CnLNi9h+fp5uHwuXLleTLcjaysN4OpGRdmaHsgWbWs6G9rwl+YN+X611nTUtXDhrRMTdHdiMppcv8FCDEMpKHswxOyPduNbEMPwaMwcm/wNEYpuD2V8Pqs7SfMd1MAh+gwYHhvv/BjBUw6izSYjSyri+wR07Es9lxHrULS+5aLzoDOtS8U6J0+dRLg68TLIrNFw9I3jPPnpr/Pzj/4XjiwnAhAfYcjmKEO2GKbBkZ+9xYmn96HtQRmzhvw5xdz9zx/GlTNxI0ZicpGRATElKBXfunjw9sV2DFpe8qTZh2DIWYf/tO79v8zOWbw1jOGE7pOOARsTjUTHPgfRJqPvaT5vfaRvZUCsQ3Hx+z5CF/o3OUqvf76243UYk1GyXgPZEN9EKMnXs1hUOJG01liRGGdfPsK6+WXxRQX9vt7bmrlwXinX/+F9skOhACQZEFOc4YBZ9wZp/HX6W8emlFZ74t5kIR68nMU22gYr0LOh0KgoQuedhPoFxtbX3SiHxlFkxVdEpLFXweB7vfAfuTjybQpvDFO4JTJpk4KxcmnvWSrXz8MwE3eKHLwPwWRPEIY0QurZNXHXV15AGQYL71ydsHbAMA2qNy/GX5pPd4OsKJjpZtjbgZhI2iJhoAw3GDQ97+bKLz00v+Qm1pH+G3DRjVFKHwyinP1rAUbJ1BmsYFBEmw2anvZw6m9zaXvTlWJUIN37U/3+BzqmiDaYPeceWYCKtSsaf+3h8o+8WUhaxl/7gpHtMAnxfv2JEgHbsgl3Brm09+zAVQiacV2VkA6tdd8ujNFAeMCOjJ2XW3nl73/ByWf3U7K0EtOZ/HlPKUXZmuoxvV8xNcjIgBhT2oK2nS5a33ARbTRBafxLYxTdEsY310JbUP8LLx27XVfn6jU0Peem5I4wRbeFE/ZN6S/vmgigaXjCA3YWclxLYebZWCmTkkEbD+n+0wtj0c9gtNMh8b93HnKRezhK7urMNyeaqq4cPM/2/3iGjZ+5u6/avrfLX6QryAt//mNazzTgK8klt6KQZQ9tYM6mxZNqZMCOWTQcraNu+0ka3r5I07GLeItyyCkvINodpu381ZUb6d73hk9uJdjUyeV950Z9f7M3LGDpO6+leFEFVjRG7ZsnOPrEbjovDt3ISkwukgyIMaMtuPh9H91H+/2aaUX3cQfdxxxUPBIkeN6kY3fPgvlBT9NNz3sw/ZqCTYmLzUKXDJqe9/RcI7udBl2lFsGOTJ/CBwfefgmB0mPfCLGHe3aM8KVEWz7H76X1TfeMSgYATjy9j8v7zrH4vrV9AatuxynO/OZw33a/gaZOosEIs9cvmFSJAIAyDS7vPcfbv9jZ97lgS1dfO+T+mk5c7mtjnIzL7+b2v3uE577wQxrfTmMjiQQ2/O4dLHtgA7Zl9Y3ALL53LYvuvoYX/+ZnXN57dsTnFmNPkgExZtp2uPoF6X56Nsm5/NNhtusdQNO0zU3+dcPPbwfOmdR93d8z3J1ga+AR0Zi5GtNnZ+F8V0cJDLcmf1OY1lc8Y5sUGBptqxRbPqshuzzOFJ2XW9nzjReTHlNQMwvTNTnfHhfdcw1v/3IHC7auZvE9a8kpzyfSGeL0bw5x/Mk9hNoDAITbA5x56TDzb1uVtOeAMgy0ZbP2t27m+S/8cET3NPfm5Sx7YAPAgKkYw2GibZtb/vLd/PzD/0mkK/PVP2J8zMx3AzEuWt9ItjxO9W54n/QYq9MgVDf0yUbbUP8Tb3x9/Yiq9pP0OVbgWxCj61A2WxUq7LDqSQTG9mlTmYAFqTKOse/EODYyrRuILEvemngwZRosuW9dRq8Z3NRopFKdQylFTmk+9//Hx9n4mbsonFeKy+8hp7yAVe/bwjv++7fJrSzsO37XV16g5VR9yvszTIPyVTX4SnJHdN/LH7ouYcdDZRg4XE4WbF01onOL8SHJgBgTOkbPPgCjD3z2oFmCWIei/qdeoi1JhsHTpgf9XeOpicXX7mf76V2neFrP1mWipH7qV5q8NeOw1n8K2vz5+5h3y4q0j++t6LfC8SkXO2b1fT4TzafqiQZTN1XStk3e7OJ4jwPj6u+TYRq487zc/MV39X0uGojw7J98n7odJ9O6B3deep0UlaGoXD+fpe+8lvm3r6J4cUXS0QeNZtbyid3NUiQ3OcfBxNRnkGLbYXqm1FMFR42r5OoTR+iSQe3X/NjB7AzfexdFCV9wYEfBNcumcHOEcL1B6MLVYyanZMWJPbUKque4wT9jpTFcUHD95EsGxrrXQCpFC8pYcHtmT7C9dQWm28GF7SfQMRtPoZ+SxRUow0gaJPvLKcun6dglKtfNT3XBhLUMhsOkaH4Zs5bNpvHoRQDsqEXt9pNUbVyU9LTa1gSbh9YeDFa5bh7Xf/4+/CV5fUsZUyY+mgGrHsTkI8mAGBPKAP+SGN0nHImH8bXC9FtYgQQdAZXGVWYRPO/AcEUxPHDxu37s0MiX1g1gaLxVFtW/HRjw6TP/nJPB1MM474DYk2Apj0aHkl1XgQYzz8LqMK+u1LAVpl8z+7cCOAsm9s05XB3BfWFyzVXM37oqraK74SilmNOzpTBAd1MHLr8H5XH2fT0Zd66XirXz0rpOMrZlD0gGAM6/dozrPn0nDrcz4Wsu7jrVV2+QSOmKKm7720f6Vvj0jkz07qCYcEMlQ1G//1zSc4uJJcmAGDOFN4fpPuZg2IBpaJyFNmXvDnLxW/74U8OAABwPepF6B5d/5ECZGt+SKLG2LLeTHXS6aFt8d8MMzpDV+xmqN2ArlNvGM8eiYEO0p2YidaOlWfeEMb2awCkH2gbvXIvcFVHUFP+Xn8k+BZnwFuaQ1lrWBPoHQ19RLspQhDuDuHPTHH5Pce3eJ/Hk5wDbGpjoRQNh9nzjRTZ+5q4hQdu2baxwlL3feinl/a396C3xawzT1jnRvduWTaQrxNmXjqQ8v5g4U/wtQUxWOgZtb7i4urzualADcBbYVP12N64iTfVnumje5qHrbUfPCMHQJ1ZtKbrfdpLVJ3Fb0bbLRbTFoGBLBGe+zfn/zEFPqtHzft3lwgqHX5O7JkrwTHpPrs58G98Ci5xlM2sJ4UgFmzt7ekWMXm/QTjcRSO+kQ7skDr2uweV9V5fxVa6bx9IHNjBreRVWNDakEZFhGHS2dBHuTF7p7y3OoWxV6gZF/ZMNrTWxUIRtf/EosfDwu26KyUEKCMWYaHjKQ9eR3iHJgZ30QONfEcNVFH/T9VTazP5IgLn/oxPDaw86tr90pwfSeTOPH2N1GHTsc3LhP3Oo+7YPqztLUxAjlrzrYecBF+f+3Y+zxMaRn2w5hsaRZ+Odl2w7w/EzEdsYj8TpbYdGNEUwXpRSSUcutNZc2nuW9gtNAFzzkZvZ+vfvp3L9fNw5noQdCXPLC7jlL9417Nd6efLSa/k9YIRAx5OTUFt3Wq8VE0dGBkTWWQFF2w5X0p0B27e7KNka6tum1wpB3TdHWxio422ErXRy3KFd+cKXJsM/h9Tff+SyycVv+5l1f5DLP/QzdLQk/nHpOwIzav8BT46HZZsXs3DdPFxeF+2NHZzac4a2Kx0QjdJ65krKIrbWsw2cfG4/C+9Yk3I4fqKkmkownCbX/+G9tF9oYvX7t8Q/l6KI0XCYlK6YQ/HiCppPXB72mEBLV1rTFAPu1VCYLgdL7l/Pvu+8nPbrxPibDO9+YpoJnDbBSjH3GVUEzzj6diHs2OMi1mqQOhgOnG4YSGF4NHb3OBf1jTetCF82MRxQ+cFurjzpHdA22czTlL0jkLC7YPiKQcdeJ7EOA0eeTd66KO6yKbhRQT8FZfnc95k7cftcfdsUe3LclM8v7Tsm0NTJoUff4PhTe/s+5yvJZcHW1eRWFBDpCnHu1aNs//dnyK8uYdbS2ZOuA2EqSinKV1VTumx2T8Of9IO3bdlUrp+fMBkItweo3XGSqusWpr1CAuKJyNybl0syMMlJMiCyTsfSe/PR/WJV+57hq5yHUPFmOTrcLyno2S44b2OYjh29dQpjIdtJxmjOp+k87KTivUFyVnYSOGP2BXfffGvYEQFtw5VfeWjf4ab/9ELLyx48NVGqPhHAHPk+QFmT8fJCBXd8/Bbc3quJAAx9gvYW57Dx9+/GW5TD/u+/yop3b2Ttx2/tKWmJX2/5uzZSt/MUXfVtlC5Lf138ZNvdsHeqI6PRDa1TTpHs/dZLlK+uweFxZpQQOD1p/vsWE2YGDSKK8eKuTG+e2j376tOo1Z3OqACgoebTnZQ9FMI738JdYZG7Osqc3+2i9P5QeucYsVGee8AuiKNPLOL1DT3LOBda5K+L4l84fCIA0LzNTfuO3qV8A+s4QucdnP2XXOwsFOjfUX5s9CdJQ28nwtmLKsiflZcyOPUG61Xv38Kyh65j/W/fjtHTB8BwmH2BsHL9fApqStK+j5PPHUhYHJetzoTjwXCYNJ+4lPSYjrpmnvmj73Ll8IUBn0/2PdqWTcvZhqzcoxg7MjIgss5dZuOdFyN43hx+vb6h8S2I4Sq+mgw4iy1i7ak79BXeGMFdoXFXRIZsYKQ1KJdGR8YiIRhd8Da88Sf24FkTDDBzbCJXRtNBMbPX2WFofsWd5HUKqyNe+Fn+rqnVP75s3ixsy077SVXbmtXv35JwCN0wDYrml2PbdrzLX4on/vm3rUh47ck0WpCMbdkEmzu5uOt0ymPbLzTxwp/+iJzyAnLLC/CV5rHl8/cnPN4wDY7/ek82b1eMARkZmKGsIHQfd9B11EEs5Ta9mSt/bwDTpwc9DQNK48jRlL87OODTBddFUwbG3GsizLovcaBSCgo2hclaH2HVuyRy9E/xJXeEmf2RAAv/qpOFf9nJnE8E4nsIjPheNZ7q9FcKBM44IOX0jaJjtysrowPpClePfh1npk/eylC4c71Jh9Bty067SU58RGH8gn7v92vbI6/z6P8zsy2bWCjKS3/384y6BHbVt3F5/zlOP3+Qwz97K37efvek7fioyOnfHKL2rRMjvlcxPmRkYIbRMWh8xkPbdtfVuX2lyVkZpeyhEA5/dgKpq0gz93NdtLzmpn2XEztoYPhsCq6LUHhjBEfOwOvkrorSvjtK4JRjmKRA41sUo+KRYMp+MMW3Rug86CLWBiN7g9Z458couilC+y5nz/LI0b3RK7dNweaBQc+Rp6n8YICLP/DFhzR6R1AM3berY/LrKnzz0+8dYKc5WqItRbjBxDtncixJTMelE/Wsv/ua7J5Ua64crqW7sZNFd61JcWx2L52IbdkoQxHtDnPs13soXV5F7uwi/MXpby7UmwT0dgzsteO/n6PldD2zNyygdMUc0Jr6Qxfi/QrS+P72fusl2s43suLdmyicFy/a7LrSxtu/3BkfFZgaMyUzmiQDM4jWcPEHvnhXwP4BVyu6jjiJ1JtU/35X33K/0XLkaUrvC1F6XwhtD+32158yYfZHAzQ956Fth6tvqF+5NAXXRyi5M5TWMjnTp6n5bBcNT3roPODs+z4Nj8ZRaBGpTz00X/ZQiM4DTrqOuMjGu5jR868sfNmgY5+LWJfCkWeTvz7KvD/qou1NF11HHWhb4a2JUbglQvNL7qH/nfponLNsvHPTD9ju8vSPVcbUeue+cq6RptpmiioL05oqSGfo3nCYtJ1v5PQLB1MmA8pQ8UCdJHlLp8AwWeW/FbM4+/IRGo/UcfalI8TCUfyl+dz37x9Lu3ixfyLQ/0+U5vrP3cvaj9xETllB30ZLq963hfbaJl78q5/Rebk15fnP/OYwZ35zGFeOJ955sSOY8jVi8pBkYAYJnDLpPpqgqtdWRJoM2ne4KLo5+y340gnkhhNK7w9RckeI0GUTRbwY0Uizfb224zsaKhMq3hek9J0hIg0GygGeSouuYw4ufc+f7Aw4S2ywoXlbb0Y0+uFfq9vg0g+8dB12Xd0jAGh5yUPhDWFm3R+i9J0DX1P2YJAL/5VDrIuBdReGRjmg8n2BjLrmusts3JWxlL0UTL+Nu3zilxlmuqLghW+/zH2/dye5xTlAem19QQ/byc+2bMLtAep2nEJbNpf2naV8dc2wiYa2NbFwFKc38S+pHbPASF57oLVO2l1w99e2cfzJgfPuaz50Iy6/O+26hMT7BhiYToV/Vh7AgBUFuRWF3PVPH+Lx3/0a0e705o8iXVOr5kTESc3ADNK+e2AwGkJD286J3zjGcINvroV3bnqJgI5B84tuTv99Lmf+IY/TX8rj3P/NIXDCgW+ehXeOhTLBWxMjVYe/aLPBlV96Uxw34OppHdt1uCcJs9XV/wGtr7toeWXoej5ngabmD7oo3BxBuXue6ExN3tooc/+gC0+VjRWC1rdc1H3bR+03fTQ97ybaljgwVH4g2PPfP3HXwsKbwj21DJNbb2DrXVHQ3RbgF//ya17/2Xaa6prTOkeoI4htDUx8bMtCWzav/uPj6J6v7f7aNqxIbMixvU/y2//zGVpO1/c9UQ8+BiDUmrwDn1KKQHMX3Q0dAz4f7gjw1r8/MyQRcLidzLtlRda6Jca3Qx4aDgyHibcoh4V3rM7KdcTkJSMDM0is1UixG1+mm/RMPG1B3Xd9BE4OHFKPXDG4/KiPSGOIkjvjTzRtbyarpu89oSJ4LpOCsHTbIyeu4m952UXhDWGMQYM2jlxN6TtCzLovhB0Gw0VfoA5dNKj9hh87oPrOEzjpoPklNxXvDZK3duhSN9csm5rf7xr0uqv3l3dtlKKbJtXGDEOsXDaPdasXMaukAK0152uv8PZTh7h0sp5YJMbx7ac4seM0j/zlQ/jzfUmemjXP/+kPWbh1NYvuuQaX34Nt2Vx48wSHHn2D1jNXl8K1nWvkmT/6Lht+9w4q1szt+3zHxWb2fuslaref5PLec9z21++hZEkldsxCazAcBrFQhFf/8XHWf+xWfEnm9rXWWOEov/rkVyhdMYec0nzCnUEu7z+HHR2aZLjzfZjOccraFMy9eTlHf7VrfK4nJoQkAzOImWf3bYE7PI3pn/gh4ky073YSOOFgaLCNf9z8Gw+5q6K4ym3ad6U76pFuIqAxcjTY9ATX4ef3U53PDhkEz5v4Fw4/r68MMPvtdWMFiQf04KBragVac/knXlyzbDxVQ8/nmW2z8IuddB5y0rHPiRVUuGbZ5G+I4J1rjWbDvpTmVjVyrm7WiF9/9+3XsXxJzdUelEpRXVXK3E/fwRuP7eDom/GKda01+547yI2PXD/sebRtc+qFg7Sfb2LPN19k33dfpuamZcy7ZQUF1SVc+8mtnN52kHOvHu0LxG3nGnnhT3+EvzSfnLJ4oG47d3W/hVBbN0//4XcoW1VN1caFmE4HrWcbOPvyEWKhKMULy1k9pzhpTUNuZSHzblnB2ZeO0EBt0p9FpCuUUXfBwfUCmVBK4fJnqZBITFqSDMwg+eujdB1KEhAVFGyYPDuL2eH41Eb7bhexToWzwKZgY4TctdG+ory2t1K0zDM0bTtd5G+IjMmoR/EtYbzVFrXf8KNj/bdhjr/5Oktsok2pn+B0NN03dWh63pMk+YgnBE0vuqj6yPAFXMoBeWujw44eTCb96waWLqpmxdK5wMDvurfj4OZ3XUfd8Ut0NncBcHzHKby5HtbdfQ2goWe43nCYnH/9GDv+67n4x06T2/76PVSum9/XqyCvqpiKa+ay/KHreP5Pf0R+dQnL3nktpSvnoC2bul2nOfbE7mHv+cqhC1w5dGHI5+t2nWLNB29MWOzXW92/+fP3cWn3GcKdyYvvooFw2q2BI10hLrx1nIV3pFgVkYAds2jr2fhITF+SDMwg/iUxvPNj8cY3g0cHDI0jTw9p5DNRYp2KC1/xE23qfaNTWF2K+lovbTtczPlkN4YbIo0pOhfainC9idWVzUQgHlj8S2LxOX0T5v5hJ62vu+nY70SHFc4Sm4JNEdyVFrVfzkl5Rldp6mr/wFmT+p96ibakSi4U3UecWIFQvNfDNLB29SJs2x7Qbrg/rTVLr1/Erl/v6/vc/m2HObHrDIs3zCffUIQ7g5x96Qit/brhrf/EbZT3DP33BtXePwvmlnL3v36EguoS7JjVNz+/6K41LLp7Da/978c5/3p63RbXfvhmtNYJ7x/iCYFhGszfuoqjv9yZ8pwHfvAqs9fPRys1ZIRAa835149x6NE3aK9txo5atF9oZv0nbhvwvfT/eyKGw+Tk03uTHiOmPkkGZhBlQNVvdXPll1469jsHJATeuRYVjwQws9RnYLQu/8RLtGVQoO+531CdyZUnvFS8JxjvOJismY7S8WWF+aOd/rg63G/m2xTfEqFgY6RvDt9VrCl7IETZAwMrqbUGV4VFpN4Yfnqmrxtj8p97qM6g7ut+dAbfRtPzbsoenPyV3eHqCO4LyadwZpUUJA2khmlQUlU85POB9gD7tx3GdXTosLvT52bxPWsTPlkbpkFBdbwtcf+A2bsB0I3/3wM0nbg0pOhvMH9pHpXXzk9v+Z+tKZzbM5WiwF+SB0oRaOoY0hAob3Zx3yoEuLp8UWuNHbMpWVRB9fVLONa8h3B7gCOPbaf55GWWPbiB8tU1aA2X95/j2BO7WHLvOmpuXBbf+6PnPrUdP/fpbQe5tPdsynsXU5skAzOM4Y4vu5t1b4juUw6wwTPHmlS71kUaDQInk2xsohUd+5zMujdE3ppofLvkRIWRWpG7Kr4rn3t2jPClRH0GUs/t510XpvT+UEab+SgFFY8EqP1yDnZUD1kmaPo0Ze9KvR678TlPPBHIoH1x+27XlEgG0mFbFiR5grVtTSyauAlTZNmcIQlByZIKTNfI3gKVodBaseietez/7itJj82fU5LRXL0VibH4vnWsePdGcisKgfj2wcd+tYsjP9+OtjVlq6q56U8fjN/L4L4BgOk0ySkvYNX7t7Donmt49k++T9flNuoPnKf+wPkh12w4XEvzqXqWPXQdvqL4SFaguZO3f7GDo49L4eBMIMnADOXI0+Svm5xzxvFq/hQsRbjOpPCGCO27XfEnpGGmPpyFNrmr499n6TtD1H7NH58/HnBsTyKQsLhSY7ih7B2htHse9OepsKn5gy6aX3LTuc+JthTKqcm/NkLRLWGcBclHBWLdKkGRZDIKHdVoiymxVDCR3rqBk2cusmxJDWaC0QGl4MKRusxOPspqScM0KF9VPezXPAV+FmxdRV5VEU5v+tmj4TDxFuey5P71A0YCvIV+1v7WLZQsreSVv/8Fqz9wQ3zaYZhRjf5JgWEaeAp83PSnD/H0576d8Lra1hx5bDtv/2IH/rJ80NDd0J5Re2IxtUkyIKY0V4lN1Se6ufg9X7yorrePgq1wldpUfay7r9jQN9dizie7aXjcS/jy1QjpKLQpvi1M8288xDoY+PTes7dC+cOBESUC/e+z4j1Byt8VxA4rDLdOO0jHdyccSeBS6NjUTgZ67T1wgmWLa4YtwLNtm1BXiNN7z2V0zpaT9VhRa8RL9LTWwwbLxfeu5bpP3xkfPcggmPaer/r6xcDA7YeVUqCgevMS5t++iopr5qZ9XsM0KVlcQfHiCppPXE5+D7am63Jb2ucW04ckA2LS8c7vbQ6UOAAqU+Opjg8L++ZZLPhiJ12HnIRqTTDBvySKb8HQpXK+eRY1n+sifNkg1mZg+jWeOfFtf3OWx2h6wU3HHldfdb93rkXJHSF8C7LTq1+ZDFvUZ0ehbbuLtrdcRFsNDE+8wVDRDWEcOamWhCbg0Khpso18Y3M7v37uTe6783pM0+hbKmcYBt2BEM99eRuxSPp7NQCEO4OcefEQC7auTthdEEi8fE9rLu0bOJdetXERmz57T9/H6XTe7DtWKZSpkrYXti2bRfesTf+kvbdqa2YtnZ0yGRAzlyQDYtJxFWv8y2J0H3cMXwugNHnXRQasvTcyWC6nFHgqbagcWCfhyNGUPxTfSyHWqTDcDNlQaSzYYbjwNT/hi2bPQgWFHVC0veWiY7eLOZ/qImdFlK63nSmaRvWnKdgUzigYTXanzl7ia999khVL51FeWohla85duMyJ03XkXBlZH/xdX91GQU0pJUsqQMfbE/cmAYHmTnwlwzcK0raNFbU49ez+AZ9f/YEtGW2nPJxk9QWGaZBXUUCkO4zLn0HxCgzpoChEf5IMiEmp4r1Bar/mjw/n9z4V9/zpnR+jNMlWxqNluEhZ3Z9NTc95ehKBQUHAVtgRzcXv+6j6eIDASSd2JJ0RAo2j0Kbk9nHci3icBEMRdu8/nrXzxYIRnvvC95l/60oW3XMNOaX5BFu7Ob3tIKeeP8Dcm5az6bP3DJifty0bO2bx0t/8jGC/NsPeQj8liyuzdm+JRAMRLrx1mGUPbkg76VCGiu9AKEQCkgyIScn0aao/00XnQSftu11YnQpHoU3Bhgg5K2LTYh4cwI5A2y5X4gCvFbFWk1irQfXvdXHll16C567+szXcGm1odLAnKBiavPVRSu8JYfqGns4KqHjXxlMOtAbffIv8DUO3lB4riboQJltemOmmRZmyoxannj/AqecPDPnayWf303CkliX3r483HYrZXNx9mhPP7CPQ1DngWNOTek4m3R0GE96rZXP25SO8/cudzN6wgLzZRSkTAtuyubjrNJ2XUu88KGYuSQbEpGU4410T89cPP/QfbVVEmg0MN3hmW1NySDzSaPRt15yQoQnWmpQsiVH96W4ijQaRpnhdgbfaAtVznhg4i+wB0yf9Bc6Y1H3bj47St1dR4KSD5m1uKj8cIGdpZnPuM0V7bTM7v/x8yuMCTZ1Eg5GkOxiOhm1ZRAMRjj+1l0hXiGf/x/dY/cEbWHTXNQOu2TtN0ftny+l63vjXJ8fknsT0IcmAmHIiTQZXHvcMWG7nyLcpuTNE/rWTc7lkImmNcGhQjqtPxq5ZNq5ZA+d/U/WJiLYr6r7lR8cYOAqhQcc0F7/nY94fdeEqyc688h3lx3ihfmlWzjVV2FGLk8/sY+kDww/fa1sTC0VQpoHDnV5lp7ZtbFtjOkyCLd28+Nc/JdgSb7kc6Qqx+6vb2Putl/AV5RALRcmvmcWiu9aQW1FIqK2b0y8epvatE307MAqRiCQDYkqJtCjO/5cfOzRwuV2sXVH/Mx9WMEjRjZOjpXI6XKU2jjybWEeS5YNa4V88uqf29h2uoYlAn/h+Bm1vuih95/RoUjRRDvzwdSrWziO/umRAQtBbvPfaPz1B2co5LHvouqTD+9rWaG1z6vmDRLpCNB69SN2Ok8MuVbSjFl1X2gEIHTzPlYNDmwoJkYokA2JKaXrOE08EhlTVxz9ufMZD3roojknSVjkVZUDRLWEankgwtm9ofPNi8dUPo9B11Jm88NBWdL3tnLLJQPsCN/mnrxZMViwoY87y2ZgOk6a6Fs7sPzcu9xENhHn2j7/Hivdcz5L71uHO9aJtzcVdpzn0kzdoOnaJy/vOUryogrLV1cPuV2BbNtrWvPoPv6T2rRPjct9CSDIgpgwrBJ0HUyyvs6Fzv5PCLVNndKBgc4Roi0Hr6+540yT76soJd4VF5QdHtmyuP51Gm4R0jpko6RYRenM93PmJ25hVXRwPqj2rADY9eC2vfenn49JjPxqIsP+7r3Dg+6/i8nuIhaNY/XogWJEY2/7ix8y/bSWL7llLbmURCoiGIoTaurm05ywnn9lHd2PyPQ+EyCZJBsSUYXUZqdfZGxBtHVklYbRN0bbdRdcRJzoW37OhYHME39yxjZJKQek7QuSti9C+y0WkycD0anKviZKzNDsrJ7w1VnyHx0Q/P+NqE6eJks6GRckoQ3H3p7ZSWJYPMGAY3ul2cutfv4enP/edAbsWjiVt64RbEdux+BTAqecPjsu9CJGKJANiyjC9mpQbCtmMaOfFwBlzSIFdtM2g84CL4q0hSu4Y+zX7ntk2ntljM0xfcH2Y9p1JAq2tptRoynDmLJtNcWXhsF8zDIVtK5Y/vJE3/lkq64UYbAouxhIzlenX+BbH+vYLGJaGvDWZBTUrCBe/M0ylfc9TdPM2D11vT+282VNpM+v+nqdUo9/Pr+fvxVtD+OZP4nmCNMxbXZ20y57hMJl7w7JxvCMhpo6p/Q4nZpySO8NcOO0YZudBAE3+pgjOosxGBjr2urDDkHDEQWlaXnOTs3xqr8MvujGCu8Ki9TU3gdMO0OCdF6Pwhsi06DHgdDsT7yPQw3Q5Mt5ASIiZQJIBMaV451jM+UQ3l3/iI9beW2gHGFC4JcKsezIfZg+cccTzgETxQSuCZ020HvWutxPOv9DCvzAwofeQqAthKqmKCNuutFO9siphhz9ta7qutEkiIMQwJBkQU45vgcX8P+0kcNIR78Tn0viXx6bMcsLp5OG8vTzWsW6ibwOAYztOseb2lUmO0Bx7cs+43Y8QU4nUDIgpSRngXxKjcEuE/A2j6yvgmx9LPCoAoDTeeUO3QxaTS1dLFzt6gr1tD6wdsG2bhiN1HP+1JANCDEeSATHj5a2LYLhJXJioFUU3Tr8dACejcPXoVjQcfuUo2779Ms11VzflCXaG2Pf8IV744o+xo1O7SFKIsSLTBGLGM70w+7e6e5YW9itM7GkAVLw1NOWLB2eC3i6E5w7Vcu5QLR6/G8NhEuwMom2NSxIBIRKSZEAI4lv5zvvjzglpOiTGRqhbRnOESJckA0L0cBZoZt0dZtbdEkSEEDOL1AwIIcbEHeXHJvoWhBBpkmRACDHu5lY1JvxasiLCzhpZ0iHEWJBkQAghhJjhJBkQQgghZjhJBoQQQogZTpIBIYQQYoaTZEAIIYSY4SQZEEJMOqNtSyyEyIwkA0KICZFseWEysrxQiOyTZEAIIYSY4SQZEEJMG+0L3BN9C0JMSZIMCCGEEDOcJANCCCHEDCfJgBBizIxmsyJZUSDE+JFkQAghhJjhJBkQQkyYkS4vFEJklyQDQgghxAwnyYAQYsqRxkNCZJckA0IIIcQMJ8mAEEIIMcNJMiCEmLRkeaEQ40OSASHEhJIVBUJMPEkGhBBCiBlOkgEhxJgaTRfCbIosmzPRtyDEpCXJgBBCCDHDSTIghBBCzHCSDAghppX2Be6JvgUhphxJBoQQEy7ZioJEywulC6EQ2SPJgBBCCDHDSTIghBBCzHCSDAghhBAznCQDQgghxAwnyYAQYsyl03hI2hILMXEkGRBCCCFmOEkGhBBCiBlOkgEhxKQnWxkLMbYkGRBCTBpSNyDExJBkQAgxKg/n7Z3oWxBCjJIkA0IIIcQMJ8mAEGLKkv0JhMgOSQaEEOMinV4DQoiJIcmAEGJSkSJCIcafJANCCCHEDCfJgBBCCDHDSTIghJgSpPGQEGNHkgEhhBBihpNkQAghhJjhJBkQQowbWV4oxOQkyYAQYtKR5YVCjC9JBoQQ0077AvdE34IQU4okA0IIIcQMJ8mAEEIIMcNJMiCEEELMcJIMCCHGVbZXFMjOhUKMniQDQgghxAwnyYAQYsqQlsRCjA1JBoQQk5L0GhBi/EgyIIQQQsxwkgwIIYQQM5wkA0KIcSd7FAgxuUgyIIQQQsxwkgwIIYQQM5wkA0KIUXs4b+9E34IQYhQkGRBCCCFmOEkGhBATQooIhZg8JBkQQgghZjhJBoQQk5Z0IRRifEgyIIQQQsxwkgwIISbMSOoGZLMiIbJPkgEhhBBihpNkQAghhJjhJBkQQkx5nTVqom9BiClNkgEhxISSfgNCTDxJBoQQQogZTpIBIYQQYoaTZEAIIYSY4SQZEEJMuGR1A9KFUIixJ8mAEEIIMcMprbWe6JsQQgghxMSRkQEhhBBihpNkQAghhJjhJBkQQgghZjhJBoQQQogZTpIBIYQQYoaTZEAIIYSY4SQZEEIIIWY4SQaEEEKIGU6SASGEEGKG+/8B2ITE9rqoBU4AAAAASUVORK5CYII=\n"
},
"metadata": {}
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since end of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "s_ukr55OORqE",
"outputId": "7cdd2b74-298b-41c0-ec82-1ceb3ee4f8e1"
},
"execution_count": 108,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712551749.232314\n",
"Mon Apr 8 04:49:09 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since beginning of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "o8HTyvcHchzQ",
"outputId": "9c732115-4703-4e92-aa29-351670097e5f"
},
"execution_count": 109,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712551749.238197\n",
"Mon Apr 8 04:49:09 2024\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# Function to compute saliency map\n",
"@tf.function\n",
"def compute_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Function to compute saliency map using Gradient\n",
"@tf.function\n",
"def compute_gradient_saliency(input_image):\n",
" with tf.GradientTape() as tape:\n",
" tape.watch(input_image)\n",
" predictions = tn_model(input_image)\n",
" grads = tape.gradient(predictions, input_image)\n",
" saliency_map = tf.reduce_max(tf.abs(grads), axis=-1)\n",
" return saliency_map\n",
"\n",
"# Compute saliency map for the entire grid\n",
"def compute_saliency_map_grid():\n",
" xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n",
" input_image = np.c_[xx.ravel(), yy.ravel()]\n",
" saliency_map = compute_saliency(tf.constant(input_image, dtype=tf.float32)).numpy()\n",
" saliency_map = saliency_map.reshape(xx.shape)\n",
" return xx, yy, saliency_map\n",
"\n",
"# Compute and plot saliency map for the entire grid\n",
"xx, yy, saliency_map = compute_saliency_map_grid()\n",
"\n",
"# Compute saliency maps for all data points\n",
"def compute_saliency_maps():\n",
" saliency_maps = []\n",
" for data_point in X:\n",
" saliency_map = compute_gradient_saliency(tf.constant(data_point[None, :], dtype=tf.float32)).numpy()\n",
" saliency_maps.append(saliency_map)\n",
" return saliency_maps\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"def find_top_indices(saliency_maps, top_k):\n",
" top_indices = np.argsort(np.max(saliency_maps, axis=1))[-top_k:]\n",
" return top_indices\n",
"\n",
"def plot_most_diagnostic(top_indices, top_k, normalized_saliency_values):\n",
" plt.figure(figsize=(8, 6))\n",
" plt.scatter(X[:, 0], X[:, 1], c=Y, cmap=plt.cm.Paired)\n",
" plt.scatter(X[top_indices, 0], X[top_indices, 1], marker='o', s=200, facecolors='none', edgecolors='r', linewidths=2)\n",
" for i, index in enumerate(top_indices):\n",
" plt.annotate(f'{normalized_saliency_values.iloc[index][\"Saliency\"]:.4f}', (X[index, 0], X[index, 1]), xytext=(X[index, 0]+0.35, X[index, 1]+0.25), arrowprops=dict(facecolor='black', arrowstyle='->'))\n",
" plt.title(f'Saliency Most Diagnostic Data Points (Top {top_k})')\n",
" plt.xlabel('Feature 1')\n",
" plt.ylabel('Feature 2')\n",
" plt.grid(True)\n",
" plt.axis('equal')\n",
" plt.show()\n",
"\n",
"# Compute saliency maps for all data points\n",
"saliency_maps = compute_saliency_maps()\n",
"\n",
"# Find the indices of the data points with the highest saliency values\n",
"top_k = 5 # Number of top diagnostic data points to select\n",
"top_indices = find_top_indices(saliency_maps, top_k)\n",
"\n",
"# Create a DataFrame to store the saliency values\n",
"saliency_df = pd.DataFrame(data=saliency_maps, columns=[\"Saliency\"])\n",
"\n",
"# Save the saliency values to a CSV file\n",
"saliency_df.to_csv(\"saliency_values.csv\", index=False)\n",
"\n",
"print(\"Saliency values saved to saliency_values.csv\")\n",
"\n",
"# Normalizing the saliency values\n",
"normalized_saliency = (saliency_df - saliency_df.min()) / (saliency_df.max() - saliency_df.min())\n",
"\n",
"# Saving the normalized saliency values to a new CSV file\n",
"normalized_saliency.to_csv(\"normalized_saliency_values.csv\", index=False)\n",
"\n",
"# Plot the most diagnostic data points\n",
"plot_most_diagnostic(top_indices, top_k, normalized_saliency)\n",
"\n",
"print(\"Normalized saliency values saved to normalized_saliency_values.csv\")\n",
"print(\"Normalized Saliency Top-k:\")\n",
"print(normalized_saliency.nlargest(top_k, 'Saliency'))\n",
"print(\"Normalized Saliency Max:\", normalized_saliency.max())\n",
"print(\"Normalized Saliency Min:\", normalized_saliency.min())\n",
"print(\"Normalized Saliency Mean:\", normalized_saliency.mean())\n",
"print(\"Normalized Saliency Median:\", normalized_saliency.median())\n",
"print(\"Normalized Saliency Mode:\", normalized_saliency.mode())\n",
"sum_normalized_values = normalized_saliency.sum()\n",
"print(\"Normalized Saliency Sum:\", sum_normalized_values)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"Normalized Saliency Standard Deviation:\", normalized_saliency.std())\n",
"print(\"Normalized Saliency Skewness:\", normalized_saliency.skew())\n",
"print(\"Normalized Saliency Kurtosis:\", normalized_saliency.kurtosis())\n",
"print(\"Normalized Saliency Variance:\", normalized_saliency.var())\n",
"coefficient_variation = (normalized_saliency.std() / normalized_saliency.mean()) * 100\n",
"print(\"Normalized Saliency Coefficient of Variation:\", coefficient_variation)\n",
"print(\"#\")\n",
"print(\"#\")\n",
"print(\"#\")\n",
"cumulative_sum = normalized_saliency.cumsum()\n",
"print(\"Cumulative Sum of Normalized Saliency Values:\", cumulative_sum)\n",
"mean_cumulative_sum = cumulative_sum / len(normalized_saliency)\n",
"print(\"Mean of Cumulative Sum of Normalized Saliency Values:\", mean_cumulative_sum)\n",
"rms = np.sqrt(np.mean(normalized_saliency**2))\n",
"print(\"Normalized Saliency Root Mean Square:\", rms)\n",
"q1 = normalized_saliency.quantile(0.25)\n",
"q2 = normalized_saliency.quantile(0.75)\n",
"iqr = q2 - q1\n",
"print(\"Normalized Saliency 25th Percentile:\", q1)\n",
"print(\"Normalized Saliency 75th Percentile:\", q2)\n",
"print(\"Normalized Saliency Interquartile Range:\", iqr)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1987
},
"id": "95xed6YyDClf",
"outputId": "df47a0a6-d9e1-4e2f-a6a1-db9619cf8c2c"
},
"execution_count": 110,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saliency values saved to saliency_values.csv\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAArEAAAIjCAYAAAAUdENlAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd3xUVdrA8d+dPsmkd5KQhBo6SAcRkKaCvSIW7CtYVlfXsruKFcuq+Np1Vey6uhZULChgoQii9BYgtPTeZjL1vH9MMjAkU9ITON/PB83cOXPvmTuTzDPnnvM8ihBCIEmSJEmSJEldiKqjOyBJkiRJkiRJTSWDWEmSJEmSJKnLkUGsJEmSJEmS1OXIIFaSJEmSJEnqcmQQK0mSJEmSJHU5MoiVJEmSJEmSuhwZxEqSJEmSJEldjgxiJUmSJEmSpC5HBrGSJEmSJElSlyODWElqpkmTJjFp0iTP7f3796MoCosXL+6wPknBmzt3Lunp6R3djXa1YMECFEXp6G4cNxRFYcGCBR3dDS9PPPEEmZmZuFyuju5Ks3z77beYTCaKioo6uitSFyCDWOmEsWXLFi644ALS0tIwGAwkJyczbdo0nnvuuY7uWqdSH+ioVCoOHTrU4P7KykqMRiOKonDTTTe1SR+2b9/OggUL2L9/f1Dt6/tc/y8kJITu3btz5pln8uabb2K1Wtukn52R2WxmwYIFrFy5sk2P05bnfOnSpW0SHM6dO9erz+Hh4QwZMoSnnnqq3d8jjz76KJ9//nmr7rOyspLHH3+cu+66C5VK1eD5+vo3d+7cVu1HY3z1JTMz06vdaaedRq9evVi4cGGb90nq+jQd3QFJag+rV69m8uTJdO/eneuuu47ExEQOHTrE2rVrefbZZ7n55ptbfIy0tDQsFgtarbYVetzx9Ho9H3zwAX//+9+9tn/66adtfuzt27fzwAMPMGnSpCaNlr700kuYTCasVis5OTl89913XH311SxatIivvvqK1NRUT9vXXnuty45W+WM2m3nggQcAvK4UAPzzn//k7rvvbtXjNeWcB2vp0qW88MILbRLI6vV6/vOf/wBQXl7O//73P+644w7Wr1/Phx9+2KR9WSwWNJrmfYw++uijXHDBBZxzzjnNenxj3njjDRwOB7NnzwbghhtuYOrUqZ77s7Ozue+++7j++uuZMGGCZ3vPnj1brQ/+HH3u60VERDRod8MNN3DHHXfwwAMPEBYW1i59k7ooIUkngDPOOEPExcWJsrKyBvcVFBQ0a58TJ04UEydObFnHOqH7779fAOK8884TQ4cObXD/tGnTxPnnny8AMX/+/Dbpw8cffywAsWLFiqDa1/e5qKiowX3vvvuuUKlUYvTo0a3cy86pqKhIAOL+++9v0+O05TmfP3++aIuPpyuvvFKEhoZ6bXM6nWLEiBECEDk5Oa1+TF9CQ0PFlVde2ar7HDx4sLjssst83r9+/XoBiDfffLNVjxuMxs69LwUFBUKtVovXX3+9jXsldXVyOoF0Qti7dy8DBgwgMjKywX3x8fFet998801OPfVU4uPj0ev19O/fn5deeingMXzNid25cycXXHAB0dHRGAwGRowYwZIlS7zaLF68GEVRWLVqFbfffjtxcXGEhoZy7rnnNjo37JtvvmHixImEhYURHh7OyJEjef/99wG4//770Wq1jT7u+uuvJzIyktra2oDP59JLL2Xjxo3s3LnTsy0/P5/ly5dz6aWXNvqYwsJCrrnmGhISEjAYDAwZMoS33nqrQbsPP/yQ4cOHe/o/aNAgnn32Wc+5uPDCCwGYPHmy57Jjcy+Pz5kzh2uvvZbffvuNZcuWebY3Nif23//+N+PGjSMmJgaj0cjw4cP55JNPGuzTYrFwyy23EBsbS1hYGGeddRY5OTkN5kjWX3Lfs2cPc+fOJTIykoiICK666irMZrPXPh0OBw899BA9e/ZEr9eTnp7Ovffe2+Ay9++//86MGTOIjY3FaDSSkZHB1VdfDbjfg3FxcQA88MADnnNX3ydfc2LfffddRo0aRUhICFFRUZxyyil8//33QZ/jY/k657/88gsXXngh3bt3R6/Xk5qaym233YbFYvG0mTt3Li+88AKA12XnesG+RsFSqVSeEev66SvBvo+b+3orikJNTQ1vvfVWg0v6VVVV/PWvfyU9PR29Xk98fDzTpk3jjz/+8Ps8srOz2bx5s9fIa7A+/vhjhg8fjtFoJDY2lssuu4ycnByvNnPnzsVkMrFv3z5mzJhBaGgo3bp148EHH0QIEfSxnE4nlZWVftvEx8czePBgvvjiiyY/F+nEIoNY6YSQlpbGhg0b2Lp1a8C2L730Emlpadx777089dRTpKamMm/ePM8Ha1Ns27aNMWPGsGPHDu6++26eeuopQkNDOeecc/jss88atL/55pvZtGkT999/PzfeeCNffvllg3mnixcvZubMmZSWlnLPPffw2GOPMXToUL799lsALr/8chwOBx999JHX42w2G5988gnnn38+BoMhYN9POeUUUlJSPMExwEcffYTJZGLmzJkN2lssFiZNmsQ777zDnDlzePLJJ4mIiGDu3LmeABVg2bJlzJ49m6ioKB5//HEee+wxJk2axKpVqzzHveWWWwC49957eeedd3jnnXfo169fwD77cvnllwMEDMyeffZZhg0bxoMPPsijjz6KRqPhwgsv5Ouvv/ZqN3fuXJ577jnOOOMMHn/8cYxGY6PnpN5FF11EVVUVCxcu5KKLLmLx4sWeS/71rr32Wu677z5OOukknnnmGSZOnMjChQu55JJLPG0KCwuZPn06+/fv5+677+a5555jzpw5rF27FoC4uDjPF65zzz3Xc+7OO+88n3174IEHuPzyy9FqtTz44IM88MADpKamsnz5cr/nKpDGzvnHH3+M2Wzmxhtv5LnnnmPGjBk899xzXHHFFZ42N9xwA9OmTQPw9P+dd97x3B/sa9QUe/fuBSAmJibo97E/gV7vd955B71ez4QJEzzP74YbbgDgL3/5Cy+99BLnn38+L774InfccQdGo5EdO3b4Pebq1asBOOmkk5r03BcvXsxFF12EWq1m4cKFXHfddXz66aecfPLJlJeXe7V1Op2cdtppJCQk8MQTTzB8+HDuv/9+7r///qCOZTabCQ8PJyIigujoaObPn091dXWjbYcPH+55TpLkU0cPBUtSe/j++++FWq0WarVajB07Vvz9738X3333nbDZbA3ams3mBttmzJghevTo4bXt2OkE2dnZDS7VTZkyRQwaNEjU1tZ6trlcLjFu3DjRu3dvz7Y333xTAGLq1KnC5XJ5tt92221CrVaL8vJyIYQQ5eXlIiwsTIwePVpYLBav/hz9uLFjxza4lPvpp58GdYn+6MvEd9xxh+jVq5fnvpEjR4qrrrpKCCEaTCdYtGiRAMS7777r2Waz2cTYsWOFyWQSlZWVQgghbr31VhEeHi4cDofPPrTmdAIhhCgrKxOAOPfccz3brrzySpGWlubV7tjX3maziYEDB4pTTz3Vs23Dhg0CEH/961+92s6dO7fBZfz6fl199dVebc8991wRExPjub1x40YBiGuvvdar3R133CEAsXz5ciGEEJ999pkAxPr1632cCf/TCer7Uy8rK0uoVCpx7rnnCqfT6dX26PdTY5pzzhv73Vq4cKFQFEUcOHDAs83fdIJgXiNf6i9pFxUViaKiIrFnzx7x6KOPCkVRxODBg4UQwb+PhRDNfr2F8D2dICIiolnTdP75z38KQFRVVflsc+x0ApvNJuLj48XAgQO9/p589dVXAhD33XefZ9uVV14pAHHzzTd7trlcLjFz5kyh0+l8vg/q3X333eKuu+4SH330kfjggw88+xs/fryw2+0N2j/66KMCaPZ0L+nEIEdipRPCtGnTWLNmDWeddRabNm3iiSeeYMaMGSQnJze4tG80Gj0/V1RUUFxczMSJE9m3bx8VFRVBH7O0tJTly5d7RmWKi4spLi6mpKSEGTNmkJWV1eCS3fXXX+916XTChAk4nU4OHDgAuEcxq6qquPvuuxuMph79uCuuuILffvvNM8IE8N5775GamsrEiRODfg6XXnope/bsYf369Z7/+5pKsHTpUhITEz2LSgC0Wi233HIL1dXV/PTTTwBERkZSU1PjdZm5rZlMJsB9qdafo1/7srIyKioqmDBhgtel3PoR73nz5nk91t/iwL/85S9etydMmEBJSYnnsurSpUsBuP32273a/e1vfwPwjDLWT4f56quvsNvtfp9LMD7//HNcLhf33XcfKpX3x0FLU3E1ds6PPr81NTUUFxczbtw4hBD8+eefQe03mNfIn5qaGuLi4oiLi6NXr17ce++9jB071nNlJNj3sT+BXm9/IiMj+e2338jNzQ3q+dQrKSlBo9F4znswfv/9dwoLC5k3b57X35OZM2eSmZnZ6Oj20VeG6jOU2Gw2fvjhB7/HWrhwIY899hgXXXQRl1xyCYsXL+aRRx5h1apVjU4HiYqKAqC4uDjo5yOdeGQQK50wRo4cyaeffkpZWRnr1q3jnnvuoaqqigsuuIDt27d72q1atYqpU6cSGhpKZGQkcXFx3HvvvQBNCmL37NmDEIJ//etfng/N+n/1l98KCwu9HtO9e3ev2/V/yMvKyoAjlz0HDhzo99gXX3wxer2e9957z9Pvr776ijlz5jQpOBk2bBiZmZm8//77vPfeeyQmJnLqqac22vbAgQP07t27QTBUPw2gPhCfN28effr04fTTTyclJYWrr77aExi2lfpLloFWOn/11VeMGTMGg8FAdHS05/L80a/7gQMHUKlUZGRkeD22V69ePvcb6HWt3+ex+0hMTCQyMtJz7iZOnMj555/PAw88QGxsLGeffXaL0lnt3bsXlUpF//79m/V4fxo75wcPHmTu3LlER0djMpmIi4vzfKkK9ncrmNfIH4PBwLJly1i2bBk///wzhw4dYtWqVfTo0QMI/n3sT6DX258nnniCrVu3kpqayqhRo1iwYAH79u0L6rk1Vf1z6du3b4P7MjMzGzxXlUrlOU/1+vTpAxB0Oryj3XbbbahUqkYDYFE3z1bmNZb8kUGsdMLR6XSMHDmSRx99lJdeegm73c7HH38MuD/Up0yZQnFxMU8//TRff/01y5Yt47bbbgNoUkqm+rZ33HGH50Pz2H/HBi1qtbrRfYkmLJwA94fmrFmzPEHsJ598gtVq5bLLLmvSfsA9GvvRRx/x/vvvc/HFFzf4cG+q+Ph4Nm7cyJIlSzjrrLNYsWIFp59+OldeeWWL9utP/Vxof4HmL7/8wllnnYXBYODFF19k6dKlLFu2jEsvvbTJ5/9Ywb6ugT6wFUXhk08+Yc2aNdx0003k5ORw9dVXM3z4cJ9zCzvKsefc6XQybdo0vv76a+666y4+//xzli1b5lkIGczvVmu8Rmq1mqlTpzJ16lQmTJhASkpK855ggGM0Jpg+XnTRRezbt4/nnnuObt268eSTTzJgwAC++eYbv4+LiYnB4XAEvNrQmRiNRmJiYigtLW1wX33AHxsb297dkroQmSdWOqGNGDECgLy8PAC+/PJLrFYrS5Ys8RpNWbFiRZP3XT9iodVqm7ViuDH1+Ry3bt3qNyAD95SCs88+m/Xr1/Pee+8xbNgwBgwY0ORjXnrppdx3333k5eV5LbA5VlpaGps3b8blcnkFuvXZDdLS0jzbdDodZ555JmeeeSYul4t58+bxyiuv8K9//YtevXq1+uhLfb9nzJjhs83//vc/DAYD3333HXq93rP9zTff9GqXlpaGy+UiOzub3r17e7bv2bOn2f2r32dWVpbXAraCggLKy8u9zh3AmDFjGDNmDI888gjvv/8+c+bM4cMPP+Taa69t0rnr2bMnLpeL7du3M3To0Gb3vzHHnvMtW7awe/du3nrrLa+FXI1NK/H1HIJ9jVqiKe/jlvD3OiUlJTFv3jzmzZtHYWEhJ510Eo888ginn366z8fUFw3Izs5m8ODBQfWh/rns2rWrwRWWXbt2NXiuLpeLffv2eUZfAXbv3g3QrOp39dOs6jNqHC07O5vY2NhG75OkenIkVjohrFixotFRkPq5iPWX0+pHUI5uW1FR0awPyfj4eCZNmsQrr7ziCZKP1pyyitOnTycsLIyFCxc2SJN17PM7/fTTiY2N5fHHH+enn35q1igsuAOdRYsWsXDhQkaNGuWz3RlnnEF+fr5XVgSHw8Fzzz2HyWTyXDYuKSnxepxKpfJ86NZfFg8NDQVosDq6Od5//33+85//MHbsWKZMmeKznVqtRlEUnE6nZ9v+/fsbVFWqD8pefPFFr+0tqfx2xhlnALBo0SKv7U8//TSAJ/NBWVlZg9e5PvisP3chISFAcOfunHPOQaVS8eCDDzYYCW3J6HNj57yx3y0hRKMr/n29/sG+Ri0R7Pu4pUJDQxtd/X/stIj4+Hi6desWcMrI2LFjAfc812CNGDGC+Ph4Xn75Za/9f/PNN+zYsaPRjBvPP/+852chBM8//zxardbv71ZtbW2jI8QPPfQQQghOO+20Bvdt2LDB85wkyRc5EiudEG6++WbMZjPnnnsumZmZ2Gw2Vq9ezUcffUR6ejpXXXUV4A4S60cJb7jhBqqrq3nttdeIj49vNBAN5IUXXuDkk09m0KBBXHfddfTo0YOCggLWrFnD4cOH2bRpU5P2Fx4ezjPPPMO1117LyJEjufTSS4mKimLTpk2YzWavXJZarZZLLrmE559/HrVa7bVQpaluvfXWgG2uv/56XnnlFebOncuGDRtIT0/nk08+YdWqVSxatMgzN/Laa6+ltLSUU089lZSUFA4cOMBzzz3H0KFDPaOQQ4cORa1W8/jjj1NRUYFer/fk7vXnk08+wWQyYbPZPNWjVq1axZAhQzxTRnyZOXMmTz/9NKeddhqXXnophYWFvPDCC/Tq1YvNmzd72g0fPpzzzz+fRYsWUVJSwpgxY/jpp588I1LNGUUeMmQIV155Ja+++irl5eVMnDiRdevW8dZbb3HOOecwefJkAN566y1efPFFzj33XHr27ElVVRWvvfYa4eHhnkDYaDTSv39/PvroI/r06UN0dDQDBw5sdB51r169+Mc//sFDDz3EhAkTOO+889Dr9axfv55u3boFVfoz2HOemZlJz549ueOOO8jJySE8PJz//e9/jc4THT58OAC33HILM2bMQK1Wc8kllwT9GrVEsO/jlho+fDg//PADTz/9NN26dSMjI4O+ffuSkpLCBRdcwJAhQzCZTPzwww+sX7+ep556yu/+evTowcCBA/nhhx88eYMD0Wq1PP7441x11VVMnDiR2bNnU1BQwLPPPkt6erpnGlU9g8HAt99+y5VXXsno0aP55ptv+Prrr7n33nv9jpjm5+czbNgwZs+e7Rkx/u6771i6dCmnnXYaZ599tlf7wsJCNm/ezPz584N6HtIJrN3zIUhSB/jmm2/E1VdfLTIzM4XJZBI6nU706tVL3HzzzQ1SuCxZskQMHjxYGAwGkZ6eLh5//HHxxhtvCEBkZ2d72gWTYksIIfbu3SuuuOIKkZiYKLRarUhOThazZs0Sn3zyiadNfYqtY1MnrVixotFUU0uWLBHjxo0TRqNRhIeHi1GjRokPPvigwfNet26dAMT06dODPleBUifVo5GKXQUFBeKqq64SsbGxQqfTiUGDBjU4H5988omYPn26iI+PFzqdTnTv3l3ccMMNIi8vz6vda6+9Jnr06CHUanXAdFv1fa7/ZzAYREpKipg1a5Z44403vFKc1Wssxdbrr78uevfuLfR6vcjMzBRvvvlmg7RUQghRU1Mj5s+fL6Kjo4XJZBLnnHOO2LVrlwDEY4891qBfx57L+tf76PeT3W4XDzzwgMjIyBBarVakpqaKe+65x6vvf/zxh5g9e7bo3r270Ov1Ij4+XsyaNUv8/vvvXvtfvXq1GD58uNDpdF5poBp7LkII8cYbb4hhw4YJvV4voqKixMSJE8WyZct8nu/mnvPt27eLqVOnCpPJJGJjY8V1110nNm3a1OD3xuFwiJtvvlnExcUJRVG8+hzsa9SYYKtGBfM+FsJ3iq1gXu+dO3eKU045RRiNRgGIK6+8UlitVnHnnXeKIUOGiLCwMBEaGiqGDBkiXnzxxYB9FkKIp59+WphMpkZTmQnhu2LXRx995Hn9o6OjxZw5c8Thw4e92tSfu71794rp06eLkJAQkZCQIO6///4G6dmOVVZWJi677DLRq1cvERISIvR6vRgwYIB49NFHG01z+NJLL4mQkBCvdGaS1BhFiBauWJAkqdPatGkTQ4cO5e233/Ykn5faxsaNGxk2bBjvvvsuc+bM6ejuSCegiooKevTowRNPPME111zTqvueO3cun3zySbssIBw2bBiTJk3imWeeafNjSV2bnBMrScex1157DZPJ5Ldik9R0R5dJrbdo0SJUKhWnnHJKB/RIkiAiIoK///3vPPnkk03KpNKZfPvtt2RlZXHPPfd0dFekLkDOiZWk49CXX37J9u3befXVV7nppps8C2Wk1vHEE0+wYcMGJk+ejEaj4ZtvvuGbb77h+uuvJzU1taO7J53A7rrrLu66666O7kaznXbaaZ0uXZzUeckgVpKOQzfffDMFBQWcccYZXjXbpdYxbtw4li1bxkMPPUR1dTXdu3dnwYIF/OMf/+jorkmSJJ0w5JxYSZIkSZIkqcuRc2IlSZIkSZKkLkcGsZIkSZIkSVKXc0LNiXW5XOTm5hIWFtbqZS0lSZIkSZKklhNCUFVVRbdu3bzKPx/rhApic3Nz5cphSZIkSZKkLuDQoUOkpKT4vP+ECmLrywUeOnSI8PDwDu5NcOx2O99//z3Tp09Hq9V2dHc6BXlOGpLnpCF5ThqS56Rx8rw0JM9JQ/KcNNRW56SyspLU1NSAZZ5PqCC2fgpBeHh4lwpiQ0JCCA8Pl780deQ5aUiek4bkOWlInpPGyfPSkDwnDclz0lBbn5NAUz/lwi5JkiRJkiSpy5FBrCRJkiRJktTlyCBWkiRJkiRJ6nJkECtJkiRJkiR1OTKIlSRJkiRJkrocGcRKkiRJkiRJXY4MYiVJkiRJkqQuRwaxkiRJkiRJUpcjg1hJkiRJkiSpy5FBrCRJkiRJktTlyCBWkiRJkiRJ6nJkECtJkiRJkiR1OZqO7oAkSZIkSa3D5XRQW1aISq1BHxmHoigd3SVJajMyiJUkSZKkLs7lsJG15D9kf/8etspSAEzJPelz9g2knHxmB/dOktqGDGIlSZIkqQtzOez89uSNFG1dA0J4tlfn7uOPF/9Odf4BMi+4qQN7KEltQ86JlSRJkqQu7OBPn1G0ZbVXAAt4bu/+9AUqD2d1QM8kqW3JIFaSJEmSurDs798DP3NfFZWaAz9+3I49kqT2IYNYSZIkSerCavL2NxyFPYpwOamSI7HScUgGsZIkSZLUhan1Bv8NFBUao6l9OiNJ7UgGsZIkSZLUhSWPPQNFpfbdQLjoNnpG+3VIktqJDGIlSZIkqQvrcfqVKBotKA0/0hWVmtCkdJJGTe+AnklS25JBrCRJkiR1YaakdMbe/Rq60HAAFLUGRe0emQ1L6c24e99ErdV1ZBclqU3IPLGSJEmS1MXFZI5g2gs/kbfue8r3bUFRa4gfMoHY/qNl1S7puCWDWEmSJEk6Dqi1OlLGzyJl/KyO7ooktQs5nUCSJEmSJEnqcmQQK0mSJEmSJHU5MoiVJEmSJEmSuhwZxEqSJEmSJEldjgxiJUmSJEmSpC5HBrGSJEmSJElSlyODWEmSJEmSJKnLkUGsJEmSJEmS1OXIIFaSJEmSJEnqcmQQK0mSJEmSJHU5MoiVJEmSJEmSuhwZxEqSJEmSJEldjgxiJUmSJEmSpC5HBrGSJEmSJElSlyODWEmSJEmSJKnLkUGsJEmSJEmS1OXIIFaSJEmSJEnqcmQQK0mSJEmSJHU5MoiVJEmSJEmSupwuFcTm5ORw2WWXERMTg9FoZNCgQfz+++8d3S1JkiRJkiSpnWk6ugPBKisrY/z48UyePJlvvvmGuLg4srKyiIqK6uiuSZIkSZIkSe2sywSxjz/+OKmpqbz55puebRkZGR3YI0mSJEmSJKmjdJkgdsmSJcyYMYMLL7yQn376ieTkZObNm8d1113n8zFWqxWr1eq5XVlZCYDdbsdut7d5n1tDfT+7Sn/bgzwnDclz0pA8Jw3Jc9I4eV4akuekIXlOGmqrcxLs/hQhhGjVI7cRg8EAwO23386FF17I+vXrufXWW3n55Ze58sorG33MggULeOCBBxpsf//99wkJCWnT/kqSJEmSJElNZzabufTSS6moqCA8PNxnuy4TxOp0OkaMGMHq1as922655RbWr1/PmjVrGn1MYyOxqampFBcX+z0pnYndbmfZsmVMmzYNrVbb0d3pFOQ5aUiek4bkOWlInpPGyfPSkDwnDclz0lBbnZPKykpiY2MDBrFdZjpBUlIS/fv399rWr18//ve///l8jF6vR6/XN9iu1Wq73BuwK/a5rclz0pA8Jw3Jc9KQPCeNk+elIXlOGpLnpKHWPifB7qvLpNgaP348u3bt8tq2e/du0tLSOqhHkiRJkiRJUkfpMkHsbbfdxtq1a3n00UfZs2cP77//Pq+++irz58/v6K5JkiRJkl9CCLrI7D1J6jK6zHSCkSNH8tlnn3HPPffw4IMPkpGRwaJFi5gzZ05Hd02SJEmSGhBCkLd+Gfu+eYuyrE2gUhE3YAw9Z15F3MCxHd09SeryukwQCzBr1ixmzZrV0d2QJEmSJL+EEGx793H2ffMWqFTgcoHLSdGW1RRu+oWBl99Dj9Ov6OhuSlKX1mWmE0iSJElSV1G0+Vd3AAvuALaOcDkB2PrOQioPZ3VE1yTpuCGDWEmSJElqZfu+fRdFpfZ5v6JSs3/ZB+3YI0k6/sggVpIkSZJaWfm+LZ5R18YIl5OyPZvbsUeSdPyRQawkSZIktTKVJnCeS5VG1w49kaTjlwxiJUmSJKmVJQ4/1e90AhSFxOGT269DknQckkGsJEmSJLWyjBmXg6IASsM7VSo0hlC6T7qg3fslSccTGcRKkiRJUisLS+7ByNv+D5VWVxfM4glqtUYTY+/5D/rwqEYfa60sw1JagMvpaL8OS1IX1KXyxEqSJElSV5F40mSmPbecgyv/R+nuP1FUKuIGjiXl5LPRhpgatM9bv4zdn79CRfY2AHRhUaRPu5TeZ12HWqdv7+5LUqcng1hJkiRJaiP68Gh6n3VdwHZ7ly5m27uPg3LkAqmtqozdn71E8fa1jL37dRnIStIx5HQCSZIkSepA5qIctr33hPuGcHnfKVyU7vpD5pSVpEbIIFaSJEmSOtCBFR+jKI0sAKsnIHvZe+3XIUnqImQQK0mSJEkdqDpnH8Il/LQQmAsPy4VeknQMGcRKkiRJUgdS640oKv8fxyqN1n/eWUk6AckgVpKkTs3pEhwsM7OjoIq9JTVYHb5LeUpSV5Q0arrfErWKSk3SqBn+pxxI0glIZieQJKnTOlhmZv2hMmxOgQIIYL0C/eLDGJwULj/UpeNCwrCJhKX2oTpnb8NgVlFAUeh15jUd0zlJ6sTkSKwkSZ1SboWFVftLsTndcwXrZwwKAdsLqticV9lxnZOkVqRSaxh7z38IT8sEQFFrUNTuMSaNIZTRd7xERN19kiQdIUdiJUnqdIQQbMyt8NtmR2EVmfEm9Bo5T1Dq+gyRcZzy8MeU7FhPwZ8rcdltRKT3o9vYM9DojU3al3C5KNq6hpw1S7FXVxCSkErapPMJS+nVRr2XpI4hg1hJkjqdKquDilr/K7GFgEPlFnrFNqx8JEldkaIoxPYfRWz/Uc3eh91cxW9P/oXSXX+gqNQIlxNFpWbf0sX0nHU1/WffIafhSMcNOZ1AkqROx+Z0BWyjAFZH4HaSdCL544W/U5a1CcAzv7b+/3u/eoP9P8iiCdLxQwaxkiR1OiHawBeJBGDSy4tJklSvKmcvBX+u9JvpIOuLV/3eL0ldifwEkCSpXVVZHewtrqa81o5GpSIlwkhqpBG16sglzhCdmqQwPflVVnylgNeqFVIimjZXUJKOZwUbfwZF1bB07VFqSwuoOryX8O592rFnktQ2ZBArSVK72VlYxZ85FZ50WeCe17o5T82pveK8RlaHJUfy/e5CnC7RaCA7IiXKK/CVpBOdy25DURSEv+JfgMtha58OSVIbk9MJJElqFzkVFv7McWccOPYz1mxzsnJvMa6jPn0jjFqm94knIUzv1TbcoGFCjxjSo0PausuS1KVEpPcLOFVApdURmpjePh2SpDYmR2IlSWoX2wuqfN4ncE8zyKusJfmoKQIRRi2Te8VRY3NQY3OiV6sIN2jk6mpJakT84PEYY7thKc0HV8MpBYpKTeop56INkRk9pOODHImVJKnN2Z0uimv8X8JUgNzK2kbvC9VpiDfpiTBqZQArST4oKjUjbl2EWmdAUamPvRNTcg/6X3J7x3ROktqADGIlSWpzrgBz9I60C7KhJEmNiuo5iImPfkr3yRegNrin3BiiE8i84CYmLPgAbWh4B/dQklqPnE4gSVKb06kVQrRqzHbf8/UEEB2ia9b+XUKwr6SGrKJqKmodqFUKyWHaZvZWkro2U2IaQ65ZwJBrFiBcLhRVw/Gq2rJCclYvpbaiCENkHMnjZ2GIiO2A3kpS88kgVpKkNqcoCn3iTAFLye4sqKK0xkafOBNRQQa0LiH4ZV+J11QEh0twsMyCESiospISLQNaqfUJITr99JZjA1ghBLs+eY6sL15BCPf9wuVi+/v/ps+5N9LnvHmd/jlJUj0ZxEqS1C76xpsorLb6nPcKUG1zUlNqZl+pmZGpkUGVlN1VWN3oPusnJqw5UMo5ESFo1XL2lNRyVYf3sOfrN8hd8y1Om4WQ+FQypl1K+rTZqHX6wDvoYHu+ep3dn73kuS3qquMJAbv+9zwaQyg9Z87toN5JUtPIv+qSJLULlaIwoUcMI1MjiTD4/v5cH3yuP1ROqdn/YjAhBLuLqv22cbgEB8rMTe2uJDVQvH0dP/3jfA7/sgSnzQKAufAw295/gjWPXo3T5vsLWmfgsFrI+vxlv212f/YSTpu1nXokSS0jg1hJktqNSlHoFWvijH6JZMab8HfRUgF2FfpOywVgc7r8zrOt30+p2d7kvkrS0Zx2G78vuhWXw3FMLlYBQlCatZHdn/kPEDta8ba1OCw1ftvYzZWU7FjXTj2SpJaR0wkkqZOqqLWTXWLGYndi0KrIiA4l0qil2urgQJkZm9OFSachLSrEbzDYWRX4KSkL7hHZgmr/I0KqIOfuycJeUkvlrfseW3W57wbCxf4fPqDv+fNQaZq3QLGtOcz+r1rUs1uCaydJHU0GsZLUybiEYMOhcvaU1HgFpzsLqzHp1VRbne7tinse2x855QxJODGTl2vVKqJDtH5HWgWQFG5ov05Jx6WK/dtR1BqE0+Gzjb2mEktJAaEJqe3Ys+CFJqUH1c4kK3pJXYScTiBJQbI5XOwuqua3g6X8fqiM3MpaRBvkNd2WX8meEvclP3HUP4Bqq/PI9rqNLgF/Blj13xklhOkDTidIMAVeKNM/wX/eS5NOLYNYqcVUai0NCyY30k7bOUdhASJ7DCQstTc0knILAJWKiPT+RKT3a9+OSVIzyZFYSQrCoXILa/aX4hTCE3hlFdcQadAwsVccIVq138cHy+50saOw+ZfyWjOodroEhyss5FbU4hKCqBAtPaJDMfh4rrV2J1nFNWSX1mBzuAjVaegVG0qPmFDUjVzP7x1rYpef5yqAvvFhAfuZGmlkaLcINuZWoNAwzJjQIyboaQeS5Ev8sIlkLXnVdwNFISy5J4ao+PbrVBMpisLQ6x9h1UNXIBx2r7m9ikqNSqtjyHUPdmAPJalp5EisJAVQUmNjVXYJzroA8eiR0YpaByv3FLVapanCaivOYMtbNaLS6vtSZ1NUWR18vSOf1ftLOVBm5mC5hU25lXyxLa/Rlf5VVgff7CxgW34lNTYndpegvNbO74fL+TGrELuzYR13k17DuPRoFPAaka3/eWRqZNDFD/olhDGrXwJ9400khelJjTQyKjUKcJeslaSWiu4zjKjeQxqWc60nBL3PvqHT51iN6jmICQ9+SPzQU6C+r4pCwrBJTHjwQyIzBnRo/ySpKeRfd0kKYHtBpc/7BO5ANq+yluQIY4uP1ZIAFsDubHkw7XQJlu8pwmI7MnWhnkvA6v2lmHQaYkLdAaYQgl+zS7A6XI1ebC0129mUW8GIuqDyaN2jQog0askqriGvshaBewpB79jQoIsd1AszaBmWHOm5bbfb2dqkPUiSb4qiMOr2F1iz8FoqD+5EUakRLqfn/5kX3UrK+Fkd3c2gRHTvy+g7XsRWVYa1sgx9RDQ6U2RHd0uSmkwGsZLkhxCCnIpavzPhFNzTDVojiI00tqyylEnX8mkNh8otmG2+01YpwI7CKk7OiAGgxGyj3OJ/YdW+khqGdItotOBAuEHL8JTIFvZaktqePiKGUx75mII/fyL3t+9w1tYQmpRO2uQLMQW5aKoxQggclhpUGg1qXfvN39aFRaELa/jlUpK6ChnESpIfLhF4KYeg5SOo9cINWuJCdRTX2IJYQnJE/QVMX/NVmyKnwtLo3NJ6oq5NfcnN4hr/BQkAnALKLXbiglioJUkdJWvJa7jMlZi6ZZA8dibakIZZP1RqDUkjppA0YkqLj+dy2Mn+/j32ffsOluJcAGL6jaT3WdcTP+TkgI+3m6uxVpagM0XIkVTphCSDWEnyQ61SCNWpqfEzMgkQ4WME1epwsqe4hoNlFuwuFxEGLb1jQ0kKN/icOze6exTf7y7C7mz88vyxFECnab3p7S4hAh736Jg92BmAnXyqoHSCctpq+eOleyF9Inu+fB3FaUM4nWx9eyFDrllA6inntMlxXU4H656+mcJNPx9JNQKU7NpAyePXMeiq+8iYNrvRx9YUHGLnx/9H7m/f1qX8UogfcjKZF95KZA/vOa2Vh7M4/MsSrBXFGKITSJ1wTotGjSWpM5FBrCQF0CfOxJ85vlNYKUCPmFDPbZcQ5FbUsrekhvyqWq+Az2xzkltZS0Z0CKO7RzUayIYZtJyWGc/2giqyS8w4hUCtQHp0KIlhevYU13iKACgKpEUa6R8Xwsr9rfN8I426gFMoNCooqrERb9KTGGYA/Kf40qoVooydN/WQdOL68+V7yf9jJaRPdK/Wr8sD67Jb+fPle9GFRZEwbGKrH/fA8o8p3PhTwztc7kWQWxY/TMLQUwiJS/a6uzovm1/um43DUn1UdgFB0ZZVFG1by9h7/kNsv1G4nA42vfYvDv38udditKzPXyHjtMsZeNndKL5SbUlSFyGDWEkKoHesiZwKC4XV3pfN6y+5j0iN9KTYqrU7WbG32Occ0frAMLvUTHSIjj5xjRcpCNVpGJkaxfCUSBxOgUateNJEdY8KodbuxOZ0YdSq0apV2O2tV1a1Z0wI2/J9L2YDcLjgx6wihqdE0ifORGyIjmKz72kFfePCGk2zJUkdqSpnH7lrvwGNj2kuisKuT19okyA2+7t3wd/EHQUOrviEzItu9dq85c2Hjwlg3YTLBQL+fOkepi5axvYPnuLQL1/U3efdNvvbd9CHx9DnnBta6+lIUoeQX8MkKQC1SmFSzzgGJ4VjPOqyfZxJx6SesfSKdQeiQgh+3ldChZ9FTkfbWVgVMK+rSlHQaVQN8pwatGrCDdpGF0q1VIhOw6juwS322HC4nANlZkotvgPYxDA9AxID53utV2NzsCm3gm93FvDNjgJ+P1RGRW3rBemSVC9v/TL/o5HCRfneLVhK8lv1uEIIqnOz8Tvj3uWiePs6r03mohyKtq5uEJQe2bELS3Eueb//yP7v3/eapnCsPV/+B6etthm9l6TOQ47ESlIQ1CqFAYnh9E8Iw+Z0X97XHBNAlphtlPgZjTxWjc2Jxe4ipBUyCrS2HjGhmHQaft3vTp3liwL8fqjM32clNocz6GIDuZW1/LKvGCGOzsVrJ6u4hlHdo+h51LQNSWopR20NKIG/CDpqa1r92CqNFpfD/9+L0t1/UrRlNXGDxgFQnb8/8I4VhYI/VwTct8NSTemuPzz7lqSuSI7ESlITKIqCXqNqEMAC5FTUBr3IqSuIDwucSUAANqf/hWClFkdQo9Nmm5Nf9hU3yAhR//O6g2VN+pIgSYGYkjLqFkb5ptLoMEYntupxFUUhccQU34UTjrLxP/e5pwoAGkMQX+KEQFGC+2IsR2Klrk4GsZLUSlxCBL9UHwjVqTFqO/evYGtNYw1mOsDekmq/I7oKsLuwqsH2wmorq7JL+HJbHt/syGdLXiUWu/9sEm3FJQQ5FRa25Veys7CKKjkNolPrNnoGakMIvn5xFZWalJPPQmNs/SsAvWZdE0SZaIGlKIeSnb8D7mpb+gBlbRWNluRxZwTVh63vLGTZLVNY/+xfKd6xLvADJKmT6dyfoJLUhUQZdX6DsGNlxod1+hKVyRHGVhldDmbubl6l1e+IrgDyqqxHbgvBxpwKfswq4lC5hWqbk/JaB9vyK/lqe367j9oWVltZsi2Pn/eVsCWvkj9zKvhqRwG/7itptOyu1PE0hhCGXf9IozGsolJjiE4g8+JbG97ZCiJ7DKDXmdcE1dZceAiXw05N/kGfabfcFHqcdgWxA8YQnpYZcKTXXHgYS3Eu+et/YPVDV7Ljo0XBPwFJ6gRkECtJrSQ10oguyIVWGdEh9I7t/PM7+8Q2nj2hnkalBByt1aoV4luryMFRUe6hcgs76kZmj51+4HAJVmWXts4xg1BusbNiTxEWu6tBfw5XWPg1uySIUTepI3Qbcxqj/va81zaVVk/3yRcw4aGPMETEttmxE4ZMCKpd4ZbVfDfvFJbfcQY7//ssGqPJM5dXUWvqFqcppE+fTf9LbkNRFE668XHUemNQUxbqF4plffEKeeuXNfv5SFJ7kwu7JKmVqFUKJ2dEs3Kv98KkeirFvVK/d1wYSWH6Tj8KC+4iDidnxLBqfwnHFiXTqBQm9YyloNrKljzfKbkGJIQHlV4r3qSj1Oy7UpmC9zzdHY1MLTiazelqtz9w2woqfY7CCyC/ykqJ2UZsqKxY1hnF9hsF2UuZ+sx34LCij4xDo295GelAovoMQx8Ri7Wi2GcbRaUmd81Sr20OSzUAkb2GENVrCIaIGJLHzfTKKRvevQ+nPPIJWV+8Ss6qr3A5bChqjf85wCoVe5cuJmnktJY9MUlqJ3IkVpJaUUKYgdP6JpAeHYK6LkgN1akZ2i2CCwYnM7FnHN38VOvqjFIijZw1IIlBSeEkhulJCtczLDmCswYkEWfSMyAhjMx494itcsy/o+8LpFeAUV8Bnry6Tpeg1BzcfNOtAXLetpRLCA6VWfxOhVCAA2WWNu2H1HK68GhCE7q3SwAL7hK2/S653W8bn+m0gPI9m0gaOYXeZ1/foCgCgCkxjWE3PMIZb/zOaa+uIfGkyf5L57lclO7+07OQTJI6OxnESlIrizBqGZMWzUVDk7lkaDJnDUiiX0LXTvZv1KoZmBjO5F5xTOoZR2Z8GPq6nLmKojAsOZKzBiQyuFs4veNMDOkWwVkDkxjcLSLogN2k1zA2PdoTANer/3lot4hmTUvYWVhNbmXbrcJ2uAKX6QWw+UlVdrx74YUXSE9Px2AwMHr0aNat87+IqLy8nPnz55OUlIRer6dPnz4sXXpkNHLBggUoiuL1LzMz02sfN9xwAz179sRoNBIXF8fZZ5/Nzp07vdqsX7+eKVOmEBcXx5w5c5g5cyabNm1qvScehO4Tz2XQVfehrguc6y//q7Q6jLHd8LdaVFGpOfDjfwMeQ6XRojNF1u276/4dkqRjyekEktSGutKIa2NcQuB0CTQqJeBzCdVp6J8Q3qLjpUWFEGHQsruomrzKWoQQxJn09IkzEXdUAKtWKUQbtZQGkbqrPqtBt3BDi/rmi1aloFMr2Jz+Q1mTvvPlA24PH330Ebfffjsvv/wyo0ePZtGiRcyYMYNdu3YRH99wpb3NZmPatGnEx8fzySefkJyczIEDB4iMjPRqN2DAAH744QfPbY3G++Ns+PDhzJkzh+7du1NaWsqCBQuYPn062dnZqNVqqqurOe200zjrrLN49tlnWbFiBStWrGDGjBkcOnQIrVbbJuejMRnTZpM64Szy1v9AbWkB+ogYkkZO48fbZuCvIIJwOanK2Rf0cWL6jSD3t+98N1CpiOk73D3H1tkxGT4kqSlkECtJHcjhdHGw3EKV1YFOrSI10ohJ3/G/liU1NrYXVHK4wj2Cqdeo6B1rIjPe1CZVwo4WadQGVTGsb3wYaw4EXrwlgOKatstUoCgKPWNN7Cyo8hluCNwFJE5ETz/9NNdddx1XXXUVAC+//DJff/01b7zxBnfffXeD9m+88QalpaWsXr3aE0imp6c3aKfRaEhM9J2/9frrr/f8nJ6ezsMPP8yQIUPYv38/PXv2ZOfOnZSWlvLggw+SmJjI3r17+ec//8nw4cM5cOAAvXr1auEzbxqNIZTUCWd7bwsJw1Zd7vtBioI2tPFqeLaqMqrz9qPS6gjv3heVWkPKyWez46NFOGrNIBq5MuBy0fOMq1rwLCSpfcnpBJLUQfaXmvlsax6/HSxjR0EVm3Ir+HJ7PmsPlOI8dhVVO8qpsLBsdyE5FUcuwVsdLrblV/JjVpHPdFF2p4samwNHO6WTSosyBj3ftq0HxPvGmtBpfB9kUFI4obqO/3LS3mw2Gxs2bGDq1KmebSqViqlTp7JmzZpGH7NkyRLGjh3L/PnzSUhIYODAgTz66KM4jxkZzMrKolu3bvTo0YM5c+Zw8OBBn/2oqanhzTffJCMjg9TUVAD69u1LTEwMr7/+OjabDavVyuLFi+nXr1+jQXNHSBk/C/yWxRWkjJvptclaWcofL97Fd/NO4dcFl/LzPy5g2c2nkv3de2iMoYy+82XUeoPXfuunMPQ9/yYSh09uk+ciSW3hxPurKp0wHC4XB8os5FZYcAlBVIiOnjGhnSKYyK2weI0iHh2yZpeaUYDRadHt3i+Hy8Xq/aWNjigK3KmktuVXMjQ50rO93GJnS16FZ9RWAYxaFWpFwaBVkxYVQnp0SKuP4NbPxbU7XewtMftuByS10VQCcM+JXX2gBKuj8S8eg5LCGZjYsmkWXVVxcTFOp5OEhASv7QkJCQ3mp9bbt28fy5cvZ86cOSxdupQ9e/Ywb9487HY7999/PwCjR49m8eLF9O3bl7y8PB544AEmTJjA1q1bCQs7MjL54osv8ve//52amhr69u3LsmXL0Ol0AISFhbFy5UrOOeccHnroIQB69erF999/32BqQiC2qjIO/fwFlYd2o9YbSBwxhbgBY+tSXzVf+rTZZC97H4e5usECL0WlxhiTRPK4WUf6UV3Br/fPxlyU49XeWl7ElrcexlJWQP9LbmfKU9+w/8ePyFv/Ay67jaheg0mfNpvo3kNb1F9Jam8d/2kuSW2gwmJn+Z4iao9aTJNXaWV7fhWjukd1+KVdfympAPaVmhmQGN5uUwvMdifVVgcFVbU4/IwCC2BPcQ2DkiJQqxRKamz8mFXkrlZ2VBtzXb7UKpuTohob2wurmNIrrk2ez5BuERwos/jst8A99aCtbMmroLC68ekKCu4R9wEJnb+wRWfhcrmIj4/n1VdfRa1WM3z4cHJycnjyySc9Qezpp5/uaT948GBGjx5NWloa//3vf7nmmiMFBObMmcO0adPIy8vj3//+NxdddBGrVq3CYDBgsVi45pprGD9+PO+88w6//PILa9euZebMmaxfvx6jMbgMBYd//ZKNr/4Dlyd1lcL+ZR8Qnt6PMXe92qI8s4bIOMb/823WPTUfc9FhFLUGhEC4nISl9GbUHS+gMYR42u/9+k3MRYd9ZhfYs+Q1uk88F1NSBpkX3EzmBTcH7EPBHyuxVxZjiIwlfuhE1Fpds5+PJLU2GcRKxx2HS7B8TxHWY1aD14c4vx0sI0yv8Voo1J5qbI6gFiQdKrfQL6Htgi+AKquDPw6XN2n1vt0lsNidhOrUrD1QiksEXp1vsTn5eV8xp2cmtHowp9eomdQzlpV7i70C2fqjjEyNJCakbT54HS7BnuIan/cL3Oe4oNpKYljbjQZ3VrGxsajVagoKCry2FxQU+JzPmpSUhFarRa0+shCuX79+5OfnY7PZPCOpR4uMjKRPnz7s2bPHa3tERAQRERH07t2bMWPGEBUVxWeffcbs2bN5//332b9/P2vWrMHpdFJYWMj8+fOJj4/niy++4JJLLgn4/Ip3rOOPl+7CO0mw++fK/TtY9eDlnPrk1y0akQ3v3ocpz3xL4aZfKc36E0VRETtwDDGZI71+l4QQ7P/xI7/psRSVmoMrP6X/7L8FPO7h1V8DChteuBPF4a6Upw0JZ8Blf6f7pPOb/XwkqTXJIFY67hwsM3uNwB5LwZ0ov6OC2GBSLSkK2Ns4V2O11cH3uwqbVRJVrVIorrFRafWTOP0oAqiodVBYbSWhDYK5OJOeswYksrfETF5lLS4hiDGoOHTYnfGgrVTV2v2OXIP7/VZcY+taQazZDEuXwrp1sHUr1NSAwQD9+sHIkTBzJhyTLaAxOp2O4cOH8+OPP3LOOecA7pHWH3/8kZtuuqnRx4wfP573338fl8uFqi742717N0lJSY0GsADV1dXs3buXyy+/3GdfhBAIIbBarXVP0YxKpfIKBOtvu4L83cv67BX81ZquydvPwZ8+JW3yBY3eX3k4i4MrP8VSnIvOFEnK+FlEZ45o8EVPUalJGDaRhGETfR7LZbdi97cIDPc5MBcd9tsG4PCqr9j8+gI4/wGv7XZzJRtf/ScoKrpPPDfgfiSprXXZIPaxxx7jnnvu4dZbb2XRokUd3R2pEwk0qijAk76pIy7xhuo0KPhLnOP+XAxr47m7m/MqsDtdQeU4PVq0UYtRq25y7lUFKGijIBbcI7L9E8LoXzd6bbfbOfRnmxzKI9j3T5dZQVtRAQ8/DP/5D5SXN7z/++/d/w8JgcsugwULICnJ7y5vv/12rrzySkaMGMGoUaNYtGgRNTU1nmwFV1xxBcnJySxcuBCAG2+8keeff55bb72Vm2++maysLB599FFuueUWzz7vuOMOzjzzTNLS0sjNzeX+++9HrVYze/ZswD2v9qOPPmL69OnExcVx+PBhHnvsMYxGI2eccQYA06ZN484772T+/Pn85S9/4eDBg1x77bVoNBomTw68uMlpq6Vo6+qA7fZ+/UaDIFYIwbZ3H2ffN2+hqNQI4UJRVBxY/l/iBo9n6PWPULT5V6yVpRhjkkgcMcVTgEEIQVnWRg79/DmWknwMUbGkTDib6D7DUWl1uOy+M3EoioLOFOm3vy6ng23vPeG3zfYP/k3K+FmoNO2XhkySGtMlg9j169fzyiuvMHjw4I7uitQJuYKoUd+Bi//RaVR0jzJy0E+VJ41KITWq7aoG2Z0uv8f3Z0DdIiVNc4o3dOB5bwvhBg0GjcrvyL8AEttwYVmr+eEHuOoqOBx4pA6zGV59FT7+GF58Efxcer/44ospKirivvvuIz8/n6FDh/Ltt996FnsdPHjQM+IKkJqaynfffcdtt93G4MGDSU5O5tZbb+Wuu+7ytDl8+DCzZ8+mpKSEuLg4Tj75ZNauXUtcXBwABoOBX375hUWLFlFWVkZCQgKnnHIKq1ev9uSmzczM5Msvv+SBBx7glFNOwel0MnLkSL799luSAgTmAE6bNfB5AqrzDjT4wrxv6Vvs++Yt4EhFLiHc/y/avJplN58KwuUOcF1ONIZQBlx+N6kTzuaPl+4md81Sz331UwTih06k25jTyVn1lc8qX8Ll9FoI1pjSnRuwlheBxveVKltlKcXb1xE/eHxQ50CS2kqXC2Krq6uZM2cOr732Gg8//HBHd0fqhGJCdF7poRoTZdR26EKbId0iKKiyYnU0PhI6qnsUmhaubPbHYncGHU/WjxorwEkpkaREuoPrpDADKiX4LwQCiA09vhaFqBSFzPgwNuZWNHq/AsSE6ohuozm5reaDD+Dyy48kuNfr3YHp+efD8OEQE+Mepd24EZYsgbffhqoqKCuD2bPdge8dd/jc/U033eRz+sDKlSsbbBs7dixr1671ub8PP/zQ79Pp1q2bV4UvX6ZNm8a0adOw2+0sXbqUM844I+giB9qQsIAjnwAIlzvYVLs/bl0OO1lLXvP3AM8Uhfpg1FFbw6bX/kX+huUU/LnS6776/xdu+oVuo2eg0upw2q1w7JQIRUXcoHFE9z3Jb3er8/f7fz51rJUlQbWTpLbU5YLY+fPnM3PmTKZOnRowiLVarZ75TwCVle4V4Xa7Hbs9uLrrHa2+n12lv+0h0DnpHq5jS47/IK1nVFiHnlOdAqf2iGJLfiWHy2s9fY0yahiYGEGCSduk/jX1faJyOcFPTfZ60UYNJr2WcL2GtOgQjFq15xgK0CfGyM7C6oD7UYAQnZpYo7rdzntb/u5U1NopqLIiBMSEakmL0HGgzNJgmohJp2ZMSnin+f1t9JysXg3XXw/1800nTYIXXoCUFO8HR0XB5Mnuf//6F9x5J3zyCQCuf/0LZ0IC2iAWQ3VGzX2vhPcaRlnWRr9t9BFxOF0Cp8u97/J9W7FaavyOdPqSv3k1qH1/Icr982dG3LKIbe88hrk4F0WlQggBApJGTWPQ3H/icPiex26tLGHHZ68gNPoj/dPoG/1bqotM6DTv6/YiP48baqtzEuz+FCGCuPbaSXz44Yc88sgjrF+/HoPBwKRJkxg6dKjPObELFizggQceaLD9/fffJySk7RZ7SJIknSgqKiq47777GDFihN+FVZIkScEym81ceumlVFRUEB7uO892lxmJPXToELfeeivLli3DYAhuftk999zD7bff7rldWVlJamoq06dP93tSOhO73c6yZcuYNm1au9by7syCPSelZhu7i6rJq7TiEoJIg4ZecSa6RxqPu5ydzXmflJhtrNxT7HPEukd0CCelRAa1rxqbg4NlFiwOJzani5paBxaHC41KIS0qhB7RIei16sA7akWt/bvjdAl+yCqk2tpwlF8BDFoV03rHodO07/Nsigbn5Mkn3Qu5AMaNg6++gqNSW7mcDkp2rKe2NB+dKYrYgeNQH5UhoKSkhOn9+1NbVsaC/Hz6xsXB//1fez+tFgv0XnHarGx9ZyE5a5a6h9pVCrhcGGOTiM4cQc6vXza6X02IiUmPfoou7EgZZVtVGT/efrrPeastNfiaBQ2qeAXDYavlh1um4rLXXb3U6OHse+GLR8Fx1PxfRWHELc+ckPNh5edxQ211TuqvnAfSZYLYDRs2UFhYyEknHZnP43Q6+fnnn3n++eexWq1eeQUB9Ho9en3DSzZarbbLvQG7Yp/bWqBzkhChJSHixKpX35T3SWKElom93bleax0ur7mvveNCGZYciSrIYD9SqyUytO0WorVEa/3uHC6pocoOqBoGqQKwOGF/hc2z8K0z02q1aBXFvSjLYnGXIH3xRXcarTq5675ny5sPYq04MvdRExJGv4tvI2PabMrLy5k5cyb5ajUrQ0PpX1MDb70Fjz7qnnrQhVhK8gEQliq0IQkN7v/zudvI37ACRXjPM60tPEhecQ6Ko/FLn84qOzvee5wRNz/l2aaNjid5xGRy137bJoFsTI/+zXq/20rzEJZKT35lzxc1h9WTJxYgccRUkodPamk3uzT5edxQa5+TYPfVZYLYKVOmsGXLFq9tV111FZmZmdx1110NAlhJkgJLCNMzvW88xdU2zHYnWrVCSoQRQxuMmtqdLvaXmikx21ApColhelIijUEHyh1tf5nv0rb1susqrXUJq1ZBTo7751mzoE8fz135G1bw+6K/cmw6CYe5ii1vPkhVTQ3XPPIKu3fv5u6776Z/QQE895w7IP7yS7jiivZ7Hi1QvH0dOz56htLsHXD+A/xw+2kkDh7HgNl3YOqWAUDZ3i3k//5j4ztwufwWF0C4yF2zlJyR04gbOBadKQKAgVfcS/neLX6razWVolIT2Wsw4al9AjduhMZoCuYgRKRlNmm/jlozub99R03BAbShEXQbNZ2QuORm9VGSjtVlgtiwsDAGDhzotS00NJSYmJgG2yVJ8s/pEuworGJ3UbWnsllMiI4BiWGtEsCWW+zsLKziUJkZl3Av6jLbnbjEkUpae0tqCNGpmdwzlnBD5x/V8JdGq96xVeI6tfXrj/x89tmeH4UQbHvvcZ8PE0Jw6px5lJjdo4/Lli3jzEsvJQMIA/j99y4RxBb8uZJ1T813JwJQ173/hKDwz58o2b6OCQ9+SFhyT3JWf+1JZ9VcG/7vNhS1hpTxs+h/6d/Rh0cz4aH/sm/pYvb/+F9sVaWodUZi+o2gcPOvgAKiae8lbWgYJ93o+3ULRB8eTUy/kZTs2tAws0E94WLft2/jsJrpefqVGKLi/e7z8K9fsumNBThrzShqDcLlYvv7T9J90gUMvupfMs+s1GJdJge3JJ2oKmvtbMytYM3+Uv7MKac8iJK1/jhdgpV7i9iSV+kVdJWYbfy8r4TdRb6zDQghsDtdOP3k1cqpsPDNzgKyS804BLiAapvTk4pLcGR8z2JzsnxPEY5mVA1rb2F6DYHGjE36LnRFaMeOIz8PHer5sSJ7OzX5B/CX1NekVYiJikSv1/PTTz8x5IYbCAfigGW//NJWPW41LoedP1/5J8IlGgSLwuXEabWw9a1HAbAFqIIVLOF0cOjnL/jhr1PZ8tYj2KpKybzoVk57ZRWz3t7EGW9uYMxdrzL2nteJSO/X5P2nT59DaEJqi/rY94Kb6l523+90e00l+5a+xcq7z6E6L9tnu4I/V/LHi3fhrHVfwRBOh/tcC8HBlZ+w5a1HWtRXSYIuNBLbmMbyC0rS8UIIwYbD5WQV13h9pOwsrCYjOoRR3aOadSk+q7iawmrfuS03HC4nOcJA6FEVw5wuwa6iKnYX1WCxu0ekuoUb6J8Q5lW+1+Zw8eu+4PNHCsBid3GgzELP2M49f7lnTCiHyi1+2/SKDeKSbGdRe1Qu5YgIz4+B8n8qisL/ndGDQVfdR/rUSygoKCA7K4vsU07hENCnC0ztKtz0KzY/z1O4nBRtXY25KIeQuGREq1XpEDhrzWR/9x7Z371L73NuIPPCW1FpjiyWixs4lomPfEJ13n6slaVkffEKhRt/DrBfpVUWq8b2G8XIvy7iz5fv9ZviSLic2Gsq+f3/bmfio582euwd//0/fJYmFIIDy/9Ln3NuwBgTuLCEJPnSpYNYSTqebcuvIqu4Bmj4OZBdakavVjEsyOwBR/M30gruz519JTUMSnIHNk6XYMWeIopqvAPfvMpacitrGZceTVqUO2XdvtIamjOmeqjC3OmD2MQwPamRxkYD2fqiBulRXSh1X+hR57ukBHr2BMAYnRjUw40xiSiKQmJiIomKwtj6O2JiWrefLWSrKuPgT59RtmcTikpF3KDx2KrKQFEFvGRfU3CI2rJC35fXARouhQqCu23W569gjEkifcrFDVqYktIxJaWzpawoqP2FJfdqwvEb2UNdOduqnL30OO1yamuqOeCvvctJ5YGdlO/bSlTPQV731RQepvLADh+PrKeQ+9t39Dxjbov6LZ3YZBArSZ2Qw+ViR2GV3za7iqqJCdURadRiDHLwyyUENTb/c/sEUFF7JCH6zsKqBgFsfTuAtQdKSQwzoNeoKKjyXynNF3/TEzoLRVEYlx7NtvxKdhVVY3e6+6xWKfSMCWVIt3DUzSnF21EGDDjy8x9/wKhRAISl9ia8eyaVh3b7DPJ0YdHEDz7Z+/H1OtEahYI/V7J+0V9xOerfvwq5a79FbQgNas7poZ8/4/CvS3w3UFQYouJAUbCWFTVr3uzuz18mbfKFKD4q9GmMQXwxUhQSh09u8rHrWUryWf/MLZTv24JSl33DpdLA+Q3zrB9zYMr3bWkQxDrMgdMjKSoVdnPgQilHq87bT/b375O3fhkuh43IjAFkTJ9D/NBTjru0iVJwZBArSe2soKqWXYXVFFZbQYHEMAN940xel+ULq204AgR2Ali1vxSAaH1wf8AVCFgqVgFPMCaEIKvY/weNS0B2aQ2Z8WEB++zreJHGTl6WtY5KURiUFEH/hHDKLXYEggiDFq26Cy4vqAtaAfj0U/jLXwB3sD5o7j9Y/chV7jjPK9hzXx8eNPcf3oty/ve/Iz+PHNmWvQ5a1eE9rHv6ZoTTyZGvXO7/O63+p4WAgjE2iZzVX/ttpdbpmfDgf1FpNOz+7CUOrvxfEPv2VluST1XOHp9ZBRJPOpXSnRv87iN+6CleUxKawmG1sPrhKzEXuTNVeAJxVTDhgWh0cZYxtlvAxXDC6SA0sXvQ/SzcvIp1/56HcDk9+y3asprCTb+QMeMyBl5xrwxkT0Bd8C+vJHVd2/MrWb6nmNzKWuwugd0pOFxu4YesInYUVpFdUsOOgioKKps2ollqcdT9338dd4vdiUnn/8NJAKmR7pyvdqfAYvc/YqWAZ7FZTEjTS2kKoFcnn0pwLLVKISZUR2yovmsGsACjR3umELBsGfz5p+eumMwRjL33dcJSvC9Rh8SnMOKvz5I89owjG3Ny4P333T+Hh8OZZ7Z1z4Oy79t3cKceaOSLVcBRWEHcwLGIAO2cVgt5675DHx7NoCv/wemvrWXkbU0v9uCy+/697T7pPLShEeArQFMUuo2a0ezsCTmrv6Km4GDzHq8oxA1qWPRAZ4okadR0z6huIw9EYzTRbdT0oA5jq65g/TM343LavfpZ/3P2d++Su2Zpk7svdX1yJFaS2pjF7mRfSQ0Hy8yU112mP/pjtf7njTkVgO+1EMHYnFPBtPDGA8Ls0hp+O1Dmd98KEG7Q0C3cnfTexxXOBjR1I7f9E8ICToM41tBuEUR00hRbpWYbB8rMWB0uTDoNGTEhXgveujSVCubPh/qqhlddBb/9BnUFYmL7jWLSY59TeXAXluI89BHRRPYc7D3a5XLBdde588PW7yO0c3whyfv9x4CBmSEmEWtZIeKo56TWGRl45T1YK0pQFBVC+N/H9g+fIrb/aA6vWkLZ3i0oai2hSRnuDA9BTFlQaXSEJqb5vF9nimTsva+z9rHr3HN5j/0LIQQbX7mXnf99lkFX/YukEVMCHvNoh3/9yh0gN7UCvUpFt9GnERLbrdG7+8/+G8Xb12GvLvd+HRQVIBhy3YOodcFV3zz0y+c4bbW++6io2PvNWyQ3o1KZ1LUdJ3+NJalzKqiq5ad9JU2a89mS2aHFZjtVVgdheu9f7eIaK2sPlAV8fKRRy8SesZ6sBxqVigSTnsJqq89+CSA5wj1yq9Oo6BtnYleAxWMAsaE6+sWHkRLZ+Sp9OV2C1ftLOFxR65UZYkt+JYOSwhmQEHZ8XLqcNw/eeAO2boVNm2D2bPjgA08gqygKEWmZjSe4d7ngllvgm2/ct5OS4P7727Hz/h2ZB+ubMTqBUx76L4fWfsd2Kwy+6j5Sx85AYwglZ/XXQY1OumxWVt59doPtilqLCJA6TlGpSZlwNtqQML/tIjMGMPXZH8hZ/RX7l39Mxb6tDdrUlhWy/umbSBo1HVtlKSqNlvihp5B6yrmeIguNsddUBBXA1k8PqP9/TOYIhl73oM/2IXHJnPLQR+z48Glyf/vOcy4jewwk88JbmlS2tmz3Rvx+vRcuyvdu9fRPOnHIIFaS2ojF7mxyANsazLYjQawQglKLnT8Olwd8nEpxV9XaW1xDr9hQT9GD/olhFOyxNvoYBYgwakkMOzKNYFhyBC4hPJkVjpYRZWRYSiRqlYIm2GHeDrD+UBmHK9xTOo599bbkVWLQqLpWOi1f9Hp4+20YP949mvrZZzBmDLz5plfu2Ab27YNrr4UVK9y3VSp4/fVOVW42MmMAxTvW+c0sYC48TNYXr9Lj7BvY/tMqUk4+E01ducvEEVPRGEJx1DZ8HwdFONGGhJE8bhYHVnzsrsx19MisoiI0KZ3+s/8W1O40hhBSJpzD9g+e8tHC/U7NW/e9Z0vRtrXs/uwlxtz9nwaLr+qZkjKoOrzHd8CuqAhL7UN076GYi3LQR0STcvLZxA0c63MxWr2QuGSG3/wUg666j9rSArShYT5TagmXk5Idv2MpyUMXHk3cwDFH5vkG84VR8fxHOoHIIFaS2si+kppWC2ADLcY6mkHjDj4Pl1v4M6ec6gDZCOq5hLsowZb8SrKKq5nSO45wg5bEMAOju0ex/lCZV8UtAUQYNEzqGes1KqkoCiNSo+gbZyK71IzZ7sSgUZMRHUKEsWXTBpwuQUFVLTanIMygIdqobfUR0Rqbg+xS/yVmt+VX0SMmtMuUzPVr2DD44gt31S6LBTZudG+bNg0uuABOOsmdNquy0n3fkiXu9s76BUAqWLwYTj+9A59EQxnT51C8ba3fNtaKErK/e5d9P34C5y/wuk+t09Nv9t/Y8qbv0UZ/hMuF3VxFeFpfJj++hKwv/0PO6q9x2a3oI2JIm3IxPc+YG3AU9miFm37BXhN45f+RTgjs5mrWPnYtU5/9odFjpU25iNzfvvX3ROg162pSJzQcbQ6WzhThdzQ4f8MKNi9+kNqS/COPCYui/+w76D7pPOIGjiF37Tc+H6+o1ERnjggYVEvHH/mKS1IbyW3i4ix/JmTEcFb/RNQBYqZwvZpwg4aDZWZ+yS4JOoA9ltXh4tfsEkTdZcYeMaGcPSCJId0iSIsKoUdMKBN7xnJaZgJGH2VqwwxaBneLYExaNEOTI1oUwAoh2FlYxWdbc/lpXwlrDpTy/a5Cvt1ZQEkj6b9aIrci8OtmtjtbXDmtI7300kukp6djMBgYPXo06yIiYNUq7/RYy5bBDTfw6ciRjOjRg8ihQwmdO5ehn37KO/UBbPfu8P33VJ97LjfddBMpKSkYjUb69+/Pyy+/7HXM2tpa5s+fT0xMDCaTifPPP5+CggKvNgcPHmTmzJmEhIQQHx/PnXfeicPhoDkSR0whrT7/qhLoo879Ps9Z6x3MZUyb7Xe+akCKQuGmXzB1y2DYDY8wc/GfzHxrEzNe+pXMC25uUgAL7qC7yYQLe00Vh375otG7YweMIcVPgBo7cEybzjUt2Pgz656eT22J93vBVlXGxlf/wYEVn5A8bhY6U6TP11G4nPSaeVWb9VHqvGQQK0ltpKnrJPwx6TWE6jUMTAr3225wt0gE8HsQ0wf8qc8Ve3R+WINWTf+EMMamRzOqexTdwg3tNi90W0EVf+ZUeHKz1quodfBjViFl5tYLZB0uEdRFya6Q27Yxv/76K3feeSf3338/f/zxB0OGDGHGjBkUJifD77/DU09Bjx6e9tHAP4A1wGbgqrp/3116qXsu7ZQp3H777Xz77be8++677Nixg7/+9a/cdNNNLFlyJMfqbbfdxpdffsnHH3/MTz/9RG5uLuedd57nfqfTycyZM7HZbKxevZq33nqLxYsXc9999zXreSqKwuCr7+ekeU8EXcZ1x0eLGmwbeMW9zTo+AEK4y63WsddUsver11l2yxS+unIIy24+lV3/e6FuwVbj7DWVFGz8mfw/VgS9EKoxhZsaLwesKArDbniE5JPPanQlZ99z56NSt81FWyEEW995rP5Wo222v/8kilrDmLtfQxti8ppaUD//td8lt5MwbGKb9FHq3OR0AklqI3EmHaVmW4sLVsaE6AivW73fLz4MBYUt+ZVeQZRB4/7wSQzTk1dZi9XRnLpZDW3Jq+DkjBj0mo5bLFFrd7I1r/FLqAL3NIhNeZVM6hnbKseLMGoDvmYKNFg811V88cUXXHPNNVx1lXvk6uWXX+brr7/mjTfe4O6773ZnK/jrX2HNGli/nklbt0JNjXv+bL9+3DpiBG/dcQe/9ujBjDD3SOLq1au58sormTRpEgDXX389r7zyCuvWreOss86ioqKC119/nffff59TTz0VgDfffJN+/fqxdu1axowZw/fff8/27dv54YcfSEhIYOjQoTz00EPcddddLFiwAJ2u6XlQFUUh5eQziew1mJ//eSEOs//MGbbKEmoKDhGakOrZljD0FIb9ZSGbXl/gXiymqCDYdFSKisiegwGwlBTw878uxFpR7PmGaynJY9enL3Jw5f84+YEPMEYneB7qtFnZ/v6THFjx8ZEUXIqCSqPF5WjqVQDvYPpYh379khwfRR3WPnEdp/zrbcK7N57HtiUq9m+nJi/bbxt7TSWFm34hacQUTn3qWw799Cl5v/+Iy15LZM/BpE+9pPGFh9IJoWv+FZakLqBXrIldhf5X6UcaNEQYtBzwUcpUUWB4auSRbYpCv4QwesWGklsXrIbq1MQa1Xy7393GbG/eFILGFFbb+G5XIdP6xPucNtCaqqwODpWbsTsFYXoN3SONHCy3+A0qBe4SuLV2p2cxWkskhukJ0ap9nkcFdx7d1jhWe7PZbOzdu5dHH33Us02lUjF16lTWrFnDURvdi73Ge68gF0KwfPlydu3ezeOnnOLZPm7cOJYsWcLVV19Nt27dWLlyJbt37+aZZ54BYMOGDdjtdqZOnep5TGZmJt27d2fNmjWMGTOGNWvWMGjQIBISjgRyM2bM4MYbb2Tbtm0MGzasWc+5dPefrFl4TdBFCKwVxV5BLEDqKeeQOGIKh1d9RXVeNod//gJ7kFWp0iZfQN76ZWx4/k5c9kYWSAoXlpI8frr3PE668TFP3tX1z9xM4eZV3ovBhGhGAAuoVET1GtLoXQ6rha2LH/b5UKfdzrb3nmDsPf9p+nEDsJYXB9nOXXpXHx5FrzOvodeZ17R6X6SuSQaxktRGwvQaRnePYu3BMq/kMPU/D0wMZ1Dd9ICMylr+zCn3KvcaG6rjpJRIokMajkBp1SrSoo6Uo7Tbj3ywGVp51NRsc/JHTjnj02Nadb9Hc7oEvx0s5UCZxbPIWAjYcLicxDB9UGksax2uVgksVXXlZVfsKcIlvC9yKoBRq+aklMgWH6cjFBcX43K5vAJFgISEBHbu3OnzcRUVFSQnJ2O1WlGr1bz44otMmzbNc/9zzz3H9ddfT0pKChqNBpVKxWuvvcYpdYFufn4+Op2OyMjIBsfNz8/3tGmsX/X3NYfLYWf9oltw2hrPrtEYQ1R8o9u1IWFkTJsNQGh8KlvfXojfhHiKwvD5T1K2ZxPrn7kl4HFtlaWsffx6EodPIXXiOT4v/zeHoqhIO/XCRu/b983b/jMwuJwUbVmFpSQfY0xiq/UJfJ/rhu0SAjeSTkgyiJWkNpQRE0qEUcuuwiryKq24EMSF6ukbbyIx7Mj8tqRwA4lhCVTWOrA6XITo1Jiaebk6KdyARqU0qwRsYwRwqMxCbXLrjHQ2pj6ArT9efWzgcAlPqqtA6qdUtIY4k57pfRPYll/JobqRYI1KoWdMKP0TwrrkKGxLhIWFsXHjRqqrq/nxxx+5/fbb6dGjh2f6wHPPPcfatWtZsmQJaWlp/Pzzz8yfP59u3bp5jb62t/w/VgQ92lcvb90yes6c67dN+rTZFO9YR/76HxotFBA7YAwD5txJePe+LLulacUH8v9YTlXO3oBlW90U1HoDo//+Cnnrvif7u3cbbTP4qvsbTW1VlbOXXf97Pqh+WUryWj2IDU/LJCylF1U5e31+S9WFRRE/JPicstKJRQaxktTGokN0jA1iFFNRlBanoAJ3sDWkWwQb/CzuamqQK4DKWkezgjeXEORV1lJQ5R4NizPpSI4wetJTVdbaPQFscyhAYrghYN9q7U72ltSQW1mLyyWINenpFRvqs1pYpFHL+IwYnC6Bw+VCq1Z1bEotpxN274bNm6GiArRa6N3bnc/VFFzO2tjYWFQqVYOsAAUFBSQm+g5QVCoVvXq5S9AOHTqUHTt2sHDhQiZNmoTFYuHee+/ls88+Y+ZM9yr2wYMHs3HjRv79738zdepUEhMTsdlslJeXe43GHn3cxMRE1q1b16Bf9fc1R/m+rShqjd/5oMfa9t7jRPYYQEy/kY3e73LYUdQaRt66iEO/LCH7u3epytmDSqun26gZ9DjjCsJTegNQvO03aksLGt2PT0JQU3AgyJWhAqfVQlXOPuwWH6OpisK+794meezpaIze1dR2fvx/QZeb1YW1fg5gRVEYeMW9rH3s2rovrw2f84DL7z6SL1aSjiGDWElqZ0IIXALUqrYLiPrEuYOazbkV2I8KVvUaFSNSItlfZia3orZJi86ak4KxstbOT/uKqbY6PdMEdhWBUavilB6xRIfoOFRuaXapXQV3Dt0hAbI2FFZb+WlvsVfgXmaxs7uomhGpkfT2U7hArVJQd2QVoN274YUX4J13oKyRVewqFcyY4a6+dcYZfl8onU5Hz549WbFiBRdccAEALpeLH3/8kZtuuinoLrlcLqxW95cSu92O3W5Hdcxx1Wo1rrpCA8OHD0er1fLjjz9y/vnnA7Br1y4OHjzI2LFjARg7diyPPPIIhYWFxMe7LzMvW7aM8PBw+vfvH3TfjqbSaJucJkRRqdn77TueIFa4XOStX0b2svcp37sFp9WCWm8kdcLZ9Jx1Dd0nnutzX7V1czmbTAj3ArIgytYC7PjwKd+L1oSLqsN7yf7hA3qfea1ns91cTf7vPwR1fiLS+2NKSg+qL00VN3Aso+96lS2LH/Fa5GWITmTAnDtJHntGmxxXOj7IIFaS2kmJ2caOgioO112eDtWp6R1rok+cqU0C2j5xJnrEhJJXaaHW7p6ikBRuQKUo6DUqcoK8TA/u4Lexubn+2Jwulu8potbu/iA+eppArd193xn9ErE5XUEFsP3iTewpqfFKsxVu0DC6ezRRfvpmc7gaBLBHdYXfD5UTadASZ9I3fHBHslrh4Ydh4cIjhQUa43K5S79+8w1MmuQuI5uR4bP52WefzXPPPceoUaMYNWoUixYtoqamxpOt4IorriA5OZmFCxcCsHDhQkaMGEHPnj2xWq0sXbqUd955h5deegmA8PBwJk6cyJ133onRaCQtLY2ffvqJt99+m6effhqAiIgIrrnmGm6//XaM2HDk72PBC4sZOWwwo0ePBmD69On079+fyy+/nCeeeIL8/Hz++c9/Mn/+fPR6PcLlpGjbWmpLC9FHxHhXdKpjqyrj4Er36nWnzYIxJinokcZ6wuX0FEkoz97G+mduwVKc69XGabWw/8f/cnjVV4y/7x2fq+P1kS3ImBFkAAu4A1h/E8eFiwM/fuQVxNqqy91VxILQb/btQfelOeIHjefUf39N+d4tmItz0Jkiie0/SpaQlQKSQawktYPDFRZ+3edOVF7/MVNjc7Ixt4KcCguTe8W1SSCrUSmkRoY02J4QZmBwUjib8yqDGgXtnxDW5Evp2SU1WOyNf0gKwOEU7CmqDipVlQIMSAxnUFIEBVW12F3u7AVRQVTsyi41+506oQA7C6s6VxBbVgYzZ7rTXNUzGOC002DkSEhIALMZtmyB77+HAwfcbVauhCFD3BW1Jk9udNcnn3wyKSkp3HfffeTn5zN06FC+/fZbzyKqgwcPeo2q1tTUMG/ePA4fPozRaCQzM5N3332Xiy++2NPmww8/5J577mHOnDmUlpaSlpbGI488wl/+8hdPmyceeZCizb9y8aWXYXcKhiWZ+EvfBH665zxG3Po0pqQMvvrqK2688UbGjh1LaGgoV155JQ8++CB565exefHDWMsKPfvTmiIZcNlddD/lHMCdrmn1I1e7swbUBXNVh7LcjYNZGXgUl8NO7tpv2fjqP30vehIuHLU1bHj+b0x+4qtG34ex/UaiCTHhMPvPUtKAWkNkej/Ks7f5LZvr3R//z89Sks/+Hz5k/48fYS7KQRsSHtR5SR57BvGD2n5OasX+7exd+iZ5639AOB0YY5JIn34pPWZcjlrXiX43pU5FBrGS1MbsThdr9pf6DBSLamzsKKxiYKL/S+KtbUBiOHGhenYVVVFUbcPucnmVtq0PbjPjTfSNC27OZT2zzcnWfP8piARwoMzMuPTogPtTFPdlfZWi0C3C2KS+FFb7H3EWQH5V8KvX25zF4g5W6+aHCo2G4ptvx37LLSSmdWv4ZcLphC+/dOd2PXAAqqrcAfDy5TBmTKOHmDdvHrfeemuj961cudLr9sMPP8zDD/tOwQTuOatvvvmmz/tdTgcbF93MlRmCK9K8841WHc7i1wcuY9Jjn5OWlsbSpUu97s/fsJz1zzTsq726nI0v3wNCkDz2dNY8dh0OS5VXUOYZha3bpqhUQY0+umy1/P5/twVshxBU5+yjdNcfxGQOb3C3olKTPuUS9nzZhPRUKhXdTzmXgZfdxcb/3Ocut9pKlVM2v/GAJ3ANlDO3Xt/z57fKsf0p+HMl656+2V0cou41s5TksePDpynYsIKx977eokIP0vFLVuySpDZ2oMz/SCBAVlE1rtYs8XUMp0uQXVrD6v2l/Jpdwo6CKqwOJ/Fheib0iOW8wd24aEgyU3vH0Ss2lNRII33jTczsl8Cw5MgmVeYy2518v7sAmzPw83G4hFdVMF9cgmaXeQ3mtHaq2lv/+IcngK2NjuW7xV/w4+U381OZ4IuteeRXHROUq9VwzjnuUdlZswB41WLh2ZkzobqJI4BtpODPnyjbs6nRS/vC5cReXU72d+81cp8rYEWnbe89waFfv8RWWeo7QFVUmLplkDRqunuua8AytE2zftEtrH/mFoq2rPaUaq6XeeEtaIzBfAl0/45Fpvdn4GV3oTGGMuLmp5j2f8sxJfdsYQ+VI4vbmvh3Jtg0WM3lqK1hw3N3IFzOhu8PISjN2kjWktfatA9S1yWDWElqY2Vme8AyprUOF7ZWqrJ1rMpaO19uz2ftgTIOlpk5VG5hY24Fn2/N49BRRRYURSHOpGdkahQnZ8QwLDnSUymsKbbkVnjmwfqjABEGrXsNSxD7bSzILzPb2JpfyabcCg6UmRstBRtr0vndvwLEhXaS1c8bNsCiRQA4dXpWvPg+Zf0He8K3WoeLlXuKKai2NjwfYWHwyScsysjgBsBRWgoLFrRj533LWfWV3/mNwuXi4E+fNthetncz5sJD+PuaYa8uJ2f11/7nTwoX1bnZnDTvCcb/621G3/EiikbbanMubZWl5K1fxpqF1/DDrdMo2PSLJ5hVabQMvf5hGn+Xu7dpDKGEp/Vl8NX3M/6+d72yCBhjEjlp3uMB+6DS6lEaWdTnfo5NC1w1RhN9zw9+oV9L5KxZ6p6y4Wc+7/5lH+BqQoYJ6cQhpxNIUhtTBTnXNdh2TeFwufgxq8hThvbojwmXgF+zS5jcM5bE8Na5VOdwuthfZg7qI1MAveNC0alVAdurFbxSYdkcLlbtLyG/yuoJDQSgU6sYnx7t9XwyokLZWWzx/RkJTZ4u0WaeecbzYb7lL3+jvE+/Bk0EsDyryFM5rH9iGFFGdxD+0htvcFt2Nneq1dzudMKrr8L997sD3A5krSwJuMDKXlPR8HEVJUHt31KSjwjiXVcfWCYMm8ip/17K/h8+IPe37zGXNTOLQGN9Kc7ht8evJ2XC2Qy74VEUlYpuo2cw6m/Ps+29J6nJ3+9pG5HRn4FX3EtM35P87jMyYwAx/UdRunODz/M48Ip7KNq8mrz1ywDhmTZgjOuGueCQ/04rKnrOnEtkj4FoDKHE9h+FS1Gz65ipHW2hYv/OgGnQbFVl2CpL23xUWOp6ZBArSW2sW7ie3UX+L+vGhurQqVv/wsiBMgu1AUZ4V+wtZnT3KHrEhPptFwyL3Umw6We7RxpJqZvfGqbXUG11NBqGKLiLRmjrzo8Qgp/3FVNcNw3h6MfYnC5+2lfM9D7xmLTu8NaoUzMuPZpV2aVe7evn/A5ICGvyPNs2UVEBH38MgDUikt2XzPXbXACHyi0crrAwsWcsX//3PebNm8c111zD44qC8p//uOfH/ve/cE3HlukMiU+ldNcffgJZBWNMtwZbjdHBVWoyFxzw30BREd69L2rtkRH30PgUBlx6JzF9h/Pbs62/+v7wL18Q3r0vvWa6sz4kDj+VhJMmU7F/uzsgi0n05JMNxshbF7H2iRso37ulrhCCyzPHt+8FN5E+5WLSp1xMTcEhiraswuWwE9ljIEIIVj0wJ8DeBcaYJJLHnO7Z4rI3b/pOU6m0wV0FCbaddGKRQawktbHC6sBzPvsntM1IWU55cEUEfjtYRohO7VVFrDk06uBGk5PC9IxNj/bMtT05I4YfswqxOxuOp0UatQztFuG5XVht9TuPVgjYXlDFqJQjC+VSI0M4PVPL7qJqDle4R2VjQnX0jTO12ih0i/3+O9jcz+vg9DNxGgIH1gL3873tnvv48IUn0Wq1fPHFF7z66afuIBZg1aoOD2K7TzqfQ41MF/BQILWRfKsRGQMITcpwj14GnMt59Jj8MYSLnmdc2eij9BFtV05539LF9Dz9Cs+0BUVRiMwY0Kx96cKimPDAhxRtWUXOmm9wWKoJTUwj7dQLCU3o7mkXmpBKaMIlnttOmxVNSJj/hVxCEDdwbLP61VKJJ01m39LFvhsoKiJ7DERnimyvLkldiAxipeOWw+XC6nChU6s8o3jtze50sSvAKKx7TmbbpJBxBrmIQwG251c1CGKbUpjhULmFrXkNLwk3Jj06hKJqK5FGHXqNikijltMzE9hVVE12qRm700WITkPv2FB6xYaiUak8lbMOlPkvjlA/Qjki2fuLQYRRy8juUYyk9SsPtYo///T8WDJwWJMe+sVid85Wu91OZWUl/a65hgwgA7hx9WoGt2I3myO6zzBSTj6Lw79+SeNBpmDnR89QvHUNvc+5gbgB7qwKiqIwaO4/WPvY9Y0/znsnKGotCJdnxLe+dGv61NmknHxWo4+K7DmYkLhkzEE+l2AzHADUlhVSU3gYU2JakHsPfOz4IROIHzIh6MeodXp6zLiM3Z+/3OgXAUWlJnbAGMJavHiseWL6jSSyxyAq9m9vfKReuOhzzg3t3zGpS5BBrHTcqbY62JpfyYEys+fSdkqEgYGJ4X6T4reFompro4uNjuZO8VRL96iG+VxbKipER0GVNYiPfyiotmJ3usurFlVb2V5QRV6lu6qXSaemT5yJ3nGmRvPF7i6q9lvm9mgKsOaAu/KUokB6VAgnJUcSotMwLDmSYcmRXu3LzDa2HVUkIpi8tgICnvdOp7TU86MlvmGde39eWvYHoeYi9OYSsrOz3f9eeom1VisnFxd3eBCrKArD/vIooYnd2bv0LZ+jgiU71lG87TeG/uVRT/7X+EHj6X3mtWQteTXgcfrP/huWkjzy1n2P024lIr0/PWbMIX7oRJ8ZNhRFod/Ft7Ehz0c+WGDglfcS1XMIKq2O6rz9bAgm/Va9Vsw6Unk4i9KdG0BRiMkcSVhyD899tupycn/7HltVKcaYJJJGTkNjcP9N6XPePKrz9pO79htPYF9fESwstTcnzX+y1frYVIqiMOrOF1m78DoqD+50908ITwrbgVfcQ+LwUzusf1LnJoNY6bhSZXXw/a5C7MdUgcqpqCW3spZTe8W1a1L7ILJM1bVrm4CrV0woOwqCywcJ7gwA+0vNrDlQ6hUsVtuc/JFTQV5lLaf0jPUKZC12J38EGcCCdwAqBOwvNVNmtjGtTzyaY0bMC6usrNhbhBBHHhfMmdJrVGjasKxvm9Ac+XPcK0JLfhMeqjcYycwY6J1r+K233FW/wts3/7AvikpN3/Pm02vWtWx5+xEOLv+EY1/N+hHOTa/9i4Shp6APd+cQjh9yclBBbERGP3qecSUDL7+7SX1LGDYR8paiD4/BVnqkOpfWFEH/2XeQNvkCz7awlF4YYxKxlBYGrKqlC48hJD6lSX1pTG1ZIRteuJOS7eu8tscNHMeweY9zYPlH7P78FYTDUTdS7GTzGw8w4LK7SZ9yESq1huE3P0Xa5As4sOITagoOog+PJmXC2XQbNa1B5bP2ZoiIZeKjn1C46Rdy1y3DWWvGlNyTtMnnY4xp2hc66cQig1jpuPL7obIGASwcmTu49kAps/onNinvaUtEGoL7FatfXd4clbV29hS6L+NvzK2gR2w4MXUpo0x6DSNTI1l/qDzgfgwaFS4h+O2g9wKoo+VVWckqqqZv/JFL9dmlwWUj8EUA5bUO9pTUkHnUfl1CsGp/SdALxeopQO/Y0HZ7jVtN2pFLzqm5+xkz/TS25FdSYwtcNlUAyUfP7c3Lc1f9Ar8laDuCSquj4I+V+Ps6IlxODv38Ob1mXQ1AdN/hGGOSsJTk+3icgjEmkZi+I1rUt8n//oqKXRuwlOajD48hbvB4r8VgACq1hlF3vsyqh67AUeOvoIdCz9OvQKVu2cesw1LDqgcvx1yU0+C+4u2/sfLus7FVHhnFr78k77Ra2Pz6/WgMIaSMn+VOoTdoHHGDxrWoP21FUalJGDaJhGGTOrgnUlci88RKx41qq4P8AJfOq21OCqvbrzpTmEFLgknvM0+pAsSE6Ig0Nj0fqxCCDYfL+XpHAbuL3JdC9xbX8P3uQn7NLvFcTu8Va2JCRuDFK73jTGSXWgIGjcdmWqiyBs6DG4w9xd6Xc/MqawNmVjiWAoQbNF7BcJcx4qgAbPlyMmJCObN/Iqf1jWeAn4V/CpAYpveeKrN8+ZGfhzesJNWRHOYqrOX+U1opioqqw1lHbqtUDJr7z/pbx7YGYOAV9zaaJ7UpVGoN8UNOJm3yBSQOn9wggK0X0b0vU/69lPTpcxoes+520sip9KwLwlvi4M+fUVN4yGehiKMD2MZsf//JoOfwSlJXI4NY6bhRZQ0uGXZlbfsmzR7VPQq9RtXoR69WrWJMWvMWGu0oqPIElMdeaj9UbvG6xJ8SafRb3jU2VEdmfBjllsCZFKptTq8KZNoWBg71zMeMOJZbmhYcqxR3xoGoEB1b8yspMQd+Lp3KwIHQvW6V+TffwL59KIpCVIiOwd0iGFKXoUE56h+4X7vx6Ud9SRECXnzxyO0zzmiP3gdNpdUTsLyFojQoM5o4/FRG/e15jHHeqbiMcd0YeftzJI2c2so99U8fEcPguf9k+ou/0uvMa9GFR6PWGwmJTWbQVfcx4tZFLR6FBTj002ctKilXW1ZIweZfWtwPSeqM5HQC6bgR7BzIYNNAtRaTXsOMzAR2FlSxt6QGh0ugUSlkRIfQLyGMUF3Tfw0rLHY25/m7lAl7S2oYmBSOUetO75MWFUKIVs22ugVb4J5C0CfORN/4MDQqBZWiBLVw6uhT3T3KGDADQzB0miM7dboEpWZbUJ/dE3vEUmy2sj2/iuIaGyV16bd25jsJwZ0hQtv0ge72p1bDDTe4y84KATfdBF9/7V79hjsNW1qUkX0lNVRZHWhVKrpHGYk36b2nTrz3Hqxe7f65f3+YOLEDnoxvap2e+CEnu0u0+sgbK5wOkkZOa7A9cfipJAybRGnWRqxlheij4onuPbTFI7DNJYRg39LF7PnqdfdroKiwFOey5c2HqM7Z2yqjw9bKUlpaGPnADx+ROLT93gf2mkrMRYdR60MITUzrelN7pC5DBrHScSMm1J2uyernErRKgW4dkBc0RKvmpJRIhiVH4BQCtaI0+w+71eHkh6zCoFbo51XWehUxiDPpmWTS43QJXMIdTB/dj+QII9mlvpMNKUBiuMFrYVdMiI7EMH1QWRACqbE50GvUrNxT5DcXbL1QnRqHy8W2/COL147tw7qDZUzqk9jCnrWTefPghRcgN9c9GrtwIdx7r+fuUJ2GQUkRvh+/aZM7+K33yCOeILgz6X329RRu/rXR+xSVmvDufYmtS7PV8H5VwApXrcFhtZCz6ksO//ol1qoyQhO7kzb5QhKGTvQEpnu/esOz4MxdDezI357s799DGxJG5kW3UrZnE/u+fYeirWtRFIgdMJYep11OVC933ghLaQH7l31AzpqlOK1mwlJ6kz5tNkkjphISl0xtWeBFZP4UbVmNy2Fr8wVcteVFbP/gKXJWf+2pwGVK7knm+TfRbcxpbXps6cQkg1jpuKFSFAYlhvO7n5XyvWNN6DWtUy+9ORRFQdPCoCKruAZbkGkPXD6yHqhVCupGLukmRxj8Vs8SgFpRyCquJj0qBK1ahaIonJwRw6/Z7jKwzVVrd/HD7iJSI42ealyBDEgIY1u+/xHpvCor5RZ7s+Ydt7vISHep2Fmz3Lf/8Q8oKIDHHgNjgOIHn33mLmpQUZerd/ZsOOectuxts8VkjmD4/Cf58+V7cTntKIoKFAXhdBCelsnov7/cYaOr4L4Ev+rhK6nJ2+8p31qTt5+CDStIHDmVETc/jXC5yPrCf8aEPUsXowkJY/v7Tx5JbQXkrv2GnNVfM/jq+4jsMZDVj1yF02r2zF21VpVRvG0tyeNm0n3y+ZTu2tCi5+OyW7FVlbdp2dbaimJ++dfF1JYVeo2wV+fu4/f/u41BVaVkTLu0zY4vnZhkECsdV3rFhmJ1uthaf6m97tq4AHrGhDA02c8oVhexr8R3PstjNTVwUykKk3vFsmJPMVVWR6NTC3Iq3aVO/zxcwei0KNLqgtkxadF8vjWvScc7mgDMdidZxdVBjegOTgonMdzAugCZFxTgcIWlawSxADNnuoPWu+vSRP3f/7mnFdx2G1xyCcQcNf/VZoOVK+G55+Crr45sHzPGHQx3YsnjZhI3+GQO//IFlYd2o9YZSBwxhdgBYzr88vP6RbdSk3/QfaPui2B9YJa//kdWPzKX6rz92M3+v0C5bLVsf/9Jr8cf/fPmNx5ApdXhcti988nWBbM5q7/GUWshqvdQyvZsbjgaq6jQhUUGXNyFoqAxmvy3aaHdn77YIIAFPM9r69sL6Tb6dPThnbTYiNQlySBWOq4oisLAxHB6xoSyv9RMjc2BQaMmLTqEMP3x8Xb3N13iaBEGDTHNKO4QqtNwRr8EcipqOVxhIf+YLAH1n7VOIVi9vxS9RkVimAG9RoVOrcLmbNlK6GBSavWMCWFAYjiVtUHUd1fwWojWJdx1lzu/6223uXO97t3rniZw003ulFmJiWA2w44dnlK1HmefDe+8A6a2DVpag84UQY/Tr+jobng47TY2v3IPZVkb/bQSlO76I/id1mft98Fl93/VoeCP5SgaHQlDJ1C0dY2nvUpnIP3UC+k29gx+vX+278PXpa6qL3zQFpw2Kwd/+sznHGdwB+6HVy2h5+mNl/+VpOY4Pj7VJekYRq2afn7SErW2aquDrOJqcipqEUIQG6qjT1yYJ19rawrRqQNmWFCAsenRzR7RUikKqZFGDBoV+wPMkd2WX0limHuebO/YULYXVLV4bmww/QMoCGL6ghDugL7LufFGmDzZPU92xYoj27Oz3f+OlZzsHsGdM6dTzoPtCv586S6KNvzYujtthUImwmGjcMtqxv/rbZy2WhQUIjIGoA1xf1FJGjWdvPU/NDpSi0pFn/NubHEf/LFWluCy1fpto6jUmAsOtWk/pBNPF/zLLkmdS15lLT/vK/aqKlVjs7C/zMKQbhH0b+VguldMKH/kVPht0z3KyJZc96XOOJOeHjEhTZoL7HQJthVUBqz2JYDCahs2hwudRkW/hDDyKmsptQQxQupDMNkRamwOiqqtfuc/19OqFbpHtt0oVJvKzHTnfN2yBRYvhrVr3Yu3amrc+Uj79HHngT33XDjrLLpGGobOq3DTr62S8xgARYWiViMczf9d8OJycWjlpwy6+j4K/vyJLYsfxFFrxpSUQd8LbkatM3D41y9BcefZFS4n+vBoTrrpSSIzBrROH3zQGk0E/M0VAm1IF8zfLHVqMoiVpBaotTv5ZV9xg0vg9Tc35VYQbdSS2IoZEXrGhLKv1EyFxe6jdhEcKLN4budU1rIlr5IJPWJICtAPh8uFEDR5kZbD5UKHCq1axZTeceworCKrqAZr3dSCmBAtIToNZpuDErP/D/Vwg4aKACPN7r5VBhXwjkqNQl2XE8xsc8+5PVBmxuESRBg09I41kRpp7PB5mH4NGgRPPXXktsvlHm3tzH1uRzUFhyjY+BMuu42ItEz3vNpmLAxTVK2z6FNRqVFpdSScNJm8377ze5k9WMLlJHfd95Tt2UTlod2ehWKKSs2eL1+n3yW3MfXZZeRvWI7TaiEspRfxQ09plVy1gWhDw4kbPI7irWt8FlYQLifdxp7e5n2RTiwyiJWkFthbUoO/RAEKsLOoulWDWI1axZRecfyRU87+Y0q+KkrjQZ1TCH7eV8zMfomYjpkbLIRgb0kNuwqrqQyyYMSx1h0sY0RqFCa9Bo1axaCkCAYmhmNzulCrFDR1AYUQgpV7isiv9j0PMJhiFC4BeZXBpfSqD9xLzDZWZBXhcAnP44qqbRRWl9I9ysjYtGiv1GGdWgeu3O9MHLU1bHzlH+T+9n3dCKSCcLkIiU9lxC1PE9ljYJP2J1zOFo/EKioVSaOm0/e8eShqNXnrvie46wuB2c1VOCx1BU7qAuP6/+/48GlC4pLpcdrlLT5Oc/Q9bz7FW9c2PgdYUZE0chrhqX06pG/S8Uv+JZSkFghUwlYE0aY5dBp3NoBzByUxuWcsp/SIOXJAX30RR0rG1tgcVNTasTmcrDlQyvpD5c0OYMGdxur7XYXU2Nz7qLI62FVUTVZxDfmVVk+qL0VRAh4nmI/6poYETpfg573FXgHs0cc6WGYhqxUKNkjtRwjBuqdvJnf9MtwpSIRnFNBSnMOqh6+kOv9Ak/bZ8pFYBXVIOMLpwFpViikpg+E3P4WiVrc8ZZiigHD5HtVVFLI+f6UuX237i+4zjFF/ewFtaLi7O2qNe04uCsnjzuCkeY93SL+k45sciZWkLkyvUZMYrsZud1+i9/fxJYADZWYKq62U1c1ZbZ3xITeb08XGnAoE7rK3R+/foFExLj0ajUqF2d6y7AUKkBplpNrqoDTA1ASA/aVmqh3CK8NCY3YWVtMnzuRzWkFVrZ3yWjsqRSHepEerlmMAHalk53qKt65p9D7hcuGyWdn71RsMufaBoPfZ8pFYgaO6nPwNy8lbv4x+F99G77OvJ/Lpb9n/40fk/7GC6sN7mrlr4T/TgRBUHtqNtbyoTfPB+pMwbCLTX/iZ/A0/UrF/JyqtjpRxszAlpXVIf6Tjn/wrLEktEG/S+71fARICtGlPtQ6XJ4CF1gtg6/d1sNziCWCP3n+tw8XKvcUBCxMEouAu1DAwMZy+ccEtEvn9cDk7CwOPsprtzkYD3Wqrgx+zCvlqRwG/Zpfy874SPtuax6bcCp/FJKS2l7Pqa78jp8Ll5PCvS5o0MhnVZ2gr9OyoS/wfPUPx9nWExCXT/5LbOfWJL+lzbl2mgAZflhRMKb187lMTEg5BhNiu1lpI1kxFm1ex75u32bPkVXb/73lWPXwFWUtew+UIroCJJDWFDGIlqQV6xoSi9jOPUgB949svX2dnntEpBJRZmvZBduzzCdNrmNI7jgiDlrQoIz1i2jbrgNnuZNnuQoqOmcPrdAm2F1Sx/mBZmx7/RGYuziXri1fZ8tajZC15DUtpgdf9tuoKRIBSrE5brd+gTghBadZGDiz/LwD9L/0ban2AymhQd5mcgAUEFJWafd++7bUt88JbOGn+k4Sl9PZsM0Qn0n/OnaSMm+lzXw5zZcDSs1pTRIeNwgLs++Zt1j01z12YoY61rJAdHz3Db0/eKANZqdXJ6QSS1AIGrZoJPWIapNiqv4w+pFsEiWGtt6grkM48LuiuyNW0qQQzMuOpsDhwugThBg2xoTrP5X5FURiVGkVimIHdRdWUmm2oFAVFAXuQZXmPFqbXYNB4f6/fUVCF1eHyeV73lZrpE28iyti2NelPJMLlYvsH/2bv0sXu11pRIVwudny0iN5nX0fmhbeiKAohccnuVFLC98p/XXg0am3jr01Vzl42PPc3Kg/uQmgNcN4CVi24AsXhP98pKCScNIles65h+/tPUJa1yc9zcVKy4/cG21PGzyJ53ExsVeUIlwN9eAwuh43vbpwQ4Nj+uqUiY+psVJqOSbNmLsph67uPuW8cG2wLQdGWNRxY/jEZ0+e0f+ek45YMYiWphZLCDczsl8ie4hpyKiy4hCA2VE+fOFObFDvwZ2BiOFsLa7zmurbmvNfWoAIChbIK7qkaUUad3wBRURTSokJIi3KPyOZX1rJib3Gz+tUvIcxrPqwQgn0lNX7PnQJkl5iJSpFBbGvZ/flL7P36TYC6qQBH3i1Zn7+CNiScXrOupvuk89n79Ru+d6RSkT7l4kbvspTk8+sDc3CY66aZeKYcBP5NUTQaRv/tBffPQSwE87WgS1EUrxKsJTs3eDIP+N+fBhBHLfBSQIHo3kPpfc4NAR/fVg4s/9idHcLP9I3s79+TQazUquR0AklqBSa9hqHJEczsn8iZA5IYmx7d7gEsQGa8iUk9Y0kI06Nyf7YRZ9LRPdLYrKkGWpVC3zgTAxLDGJUaSbi+Zau3NSqFkzOiA7ZTKXBSSmST978x138RiGPVn5O+cSZ6RHtPTXAKEbBcrQAs9pbnAJXcHLU17Pnydb9tsj5/BafNSlhyD3rOurrRNopKTWhCd3qeMbfR+/cuXYzDXN2s/K3C6fAEanGDxnumFvjqR/yQ4EZXnVbflfGO1uf8eaScfCZK3YirSqcnMmMAvc66DpWm475MVR3O8pkj1k1Qnbu/w7InSMcnORIrSceZpHBDg6IGZWYbB49acBUMo1bN5F6xRBiOXJ7MiAnlz8PlZBX7H6FsjIJ7DnFyZAixIdUUm33Pj9OqVU0uFVtldXgtWvPHpFejUVREGN3FDuIaWXynVhQ0KsVvIKvgnlIitY6iLatxWv2/T+3mSkp2/k784PH0n30HxuhEsr54FWuFewReUWtIHjeTAXPu8qR7OtahXz5vXgECRSEspbdnxD7t1AvZs+Q1nHZro1kDhHDR47Qrgtr1sXN+fYkfNJ4DxXkIhx1FpcZlq6Vi/w7W/ftGYgeMYdTfnkdjCA3+ObUStd7oKcDgi0qr69xFRaQuRwaxknQCiArRkRxhILeiNqjgM1yv4bTMBE+lq3oqRWF4ahT9E8PZW1zDliCzDShAiE7NgMQwamwOvwEsuLMZFFRZm1QkoiLIAFalwOl9E9AESJGlKAoZ0SHs8ROwCyAjuouWtO2EHLXBjUY6amvcPwhB0qjpJI6YgrWiFOG0Y+qWgc4U6ffx9ppmZskQgh4zjlwON0TGMepvL/Dbv+e5F5DVzQVVVGqEEAy9/mEiewQu+Vq0ZTVb337UfyOVivCU3uT/uZKDKz52d+eYggfFO9ax8bX7GHHzUz5301aSRkwlZ/XXPu9XVGqSRk1vxx5JJwIZxErSCWJcejRr95dxqCLwiGyfOFODAPZoRq07ID1Ybg5YIlYB0qNDGNotAr1GTVlVoIUzbpVWB4lBtXTz19+jZUSHBAxg6/VLCONAmQW7s/HFXWlRRqJD5HzY1mLq1iOodqGJaez77l32Ll2MpSgHgJC4FHrOnEtUryEBH2+Iiqc24Mhnw5nliSOn0n3S+V6t4gaNY+qi79n/438p2vwLLqeDmMwRpE+9BFNSRlDPZ8d/FxFo9rpKoyOy1xCyPnvJ945cLnLXfoP5ktsJiUsO6titJXHEFEKT0jEXHGo4GltXIrnXzKvatU/S8U8GsZLUSQghsDpcuITAoFW3eglUjUrFyT1iyK+q5ae9xTR2ldx9eVxFehCji4qiMKRbBD/vK/HZJj06hOHJkeiOWvWvCTLYDLZdvTiTLqjL/0O7RQa9z1Cdhul94lhzoIySo0aPVQr0jjUxNDmiSX2U/IvsMZCw1D5U5+xpdH6lolIRkTGQfUvf4tDPn3F0EjZzUQ5bFj9MRfYOhlz/kN/L1mmnXsSu/73gN2VVZK/BlO/ZDAhCE9PocfrlpE+5uNHFXIaoeDIvuInMC25qcJ/DauHA8v9y4MePMBfnoQsNJ2XC2fSYcRmGqHjMRTmU793i/8QAYck9OViXCswvISjcvIr0KRcFbtuKVBot4+59g7VP3EDVoSx3xS7cc4jVeiMjbn6aiPR+7don6fgng1jphFRrd3K4woLNKQjTa+gWbgh6JK8t7C81s72g0jOqadCo6B1nol98WKv3KzHMwJTecfy8twSr0+UJAwTuS/6TesYGXY0qOcLIuPRo1h8sw+4SnrEkBXd+3CHdIhoE49EhOoxaFRY/6bYUoFsTphKAO0jvlxDGljzfl4r7xJm8AupghBm0TO8bT7nFTrnFjloFCSZDk/cjBaYoCsNueJRVD12Oy27zGtFTVGrUeiOpp5zNljcfqtvasIjwwZ/+R7cxpxE/5GSfx+lx2uUcXvUV5oKDjc7h7D7pfIZe/zAupwPhdKLWNb1gicthp3j7Oja/+SDmwkN13RPU2mrZ+9UbHFzxCePvexeXPXBZakWlpiJ7W3AHVhREBxU8MMYkMWnh5xRtWU3Bnytx2W1EZPQnZfyZaIztP09XOv7JIFY6obiEYFNuBbsKqz3BlgB0ahWju0eREhlEovNWtjWvssHc0lqHiy15lRRVW5nYM7bVR2VjQ/WcPTCJg+VmimtsKEBiuIFu4YYmHystKoTkCCM5FRaqrQ50ahUmvQYBVNU6iDB6561UKQqDEiNYd8h3oYDecaHNWjA1ICGMWruTrOIaT3Be/xqnR4e0aOQ00qgl0tgxOThPJJE9BjDhoY/Y9cnz5P/+A8LlQlGp6TZ6Bn0vuIlt7z7hdwGRolKz/4cP/Aax2pAwTr7/Pba+/Qi5a7/1hMJqnQF9VCxlezax/plbSJtyMXGDxjWp/0IIsr9/j92fvYStsrTxNi4n9ppKfv+/vzLuH2+hqFR+V/YLl9N/yVnvDhCR0b9JfQ7E5bCT/8cKCjf9gsthJ6rHIFImnIU2pGHVPEWlIn7IyX7PvyS1FhnESieUjTkV7Co6koux/iPB5nTxS3YJk3vGNmkxUUtVWOx+F0flV1nZV1JDr9jWr/qlVikkhhmIDdVj1LoXouwtrqGkrmhAUriB5IjgglqNyp2v9XCFhT8Pl1NtOxJgRBg0jEyN8soA0DM2FKvTyebcSveXibpIUwA9Y0IYlhwZ1HNwuFzkVtRidbgw6tQkhRkYkRpFnzgTe4oqOXTYHRD3jIuQAWgXEp7Sm5F/fRa7uRpbdTn6sCjPSJ47lZPvFfDC5aTyUFbAY+jDoxh+078ZePk95G9Zw8YSJ05bLRZLJQhBdW42eeuXkTxuJifNezyonLAAuz55jt3+5q0e1c+qQ1lU52WTOGIq+b//6Dcwd6emChDEKirCUnoR1Xuo+xhCULZnE9W52WiMocQPGt/kEdGagkP8/uQNmIsOe87B4V+WsP3DpxhxyzMkDJvYpP1JUmuSQax0wrDYnewu8p9MfFNeRbsGsXtKagIWI/h/9u47Pur6fuD46/u9fdl7ERJC2EOQJQICCuKo2zrqrnVrW7W2aq2rv9Zq1do666h7VOvEgaIsURBFQGYghCSQvS+5fff9/v645MiRWwlJSODzfDx8kHzvc9/73Jnk3vf5vj/v9866tl4PYqssDjZXWfx5nnL7HDpWpwF2N1iJ0WuYX5hGnCHyn4ryJhvflHZdeWpxePhyVx3ThyYxPGX/G+jYjHiGJcdQ2mjD5vZi0MjkJZujeizwvS6bKlsCcmD1GpmpuYnkJZmZkBnPXmBiVgI6nQhgByOdORadOfBnXxNF+ajuBGr6+GT2fPEGTGlvjNC+2tkRUFZ8+wnxuSMZccbVEc9lq69k5wfPRP3YSDLNu39i7IW/o37bOjy21sBAtn31NW3CsdRt/jbiQqzWHMvUXz+KJEk0FW9iw7/vpK2ixH+7Rm+k8LRfMfKs60I2YTjQuoevx9lQBRAwN6/LwbpHb2TuX98lPndk9M9ZEHqRCGKFI8beZnvE8lKNNjdtTg+xUQZSB6vF7o44p1Zn+N3/3VXaaGNNWWCw2flCZuf52Fxelu2q49SxmVidHkoarTjcCkadTEFyjD9VQFFVftjXHPZx15U3oZGg3uqi2e5Gp5HJTTQxIi2225u4dta2sr6ia2MDl1fh29JGZEkiM0b8eTsc5cw8hR37ikNvypIkcmaeEvX5moo30VK6DaaEHrP705cZfuoVEVu67l31QcSuVYFUJI2WmIxcjvvz22x97UGqf1zuf25xQwoZc95vMaVmU7vp67BnihsygmP+8CymlExayov45s+X+cp+deJ1OSh69wnsDVWYUrNwtTZjSsliyOzTMCamBT2vvbEaKdgKsaqCqrL705eYfE2E8mCC0EfEX3nhiOH0KFG1YHV5IzVF7T06TeTgrTc3drm9CuvKQ+eiHkgFbG4vK4rrqGvPne2wo7aNghQz03KTqLL4LulHsqasKeD/QaXFwZZqC8cXpkX1wUFRVbZWt7IlQn3aDRXNnDQiJeL5hMEn7/ifU/LZy7itlqClnGStHre1FVtdRVRlpuq3fue7XB9mjKu1kbaqPRFXHO0NVe0dvKL8G6KqpE+YBUBMRi7Tb30CR0s99rpKdOY4YrLy/VUWhsw+nX3fLO6SF9ux4W36rU9iSvEVpdvxzj9RvZ6QgX75indBkv25uNvfeoTR5/2WEadf1XVwmHQiVfFStW6pCGKFQ0ZsrxWOGDH68G9UHcz92IEpNzF8KSsJ38ap3lLWZMPbg7aPdVZf2oHa6T+AkgYb/91YwXflwTewBHPgo9tcXlaW1PtXr7yKSqPNRYPNhafTBwpFVfm6pCFiAAtgdXlpjLL5gTC4GOKTOfaulzAmpfsOyBr8STCqiur1sPuT//Dlbxey7c2HI6+KhimzFTAsit8bfVxSdJuvaG9JO+k4YrMDa8kaE1JJKpxIbPawgDJhk67+PwpOutTfbrZDXO5IZt/7OjEZuQC42lqo+XFF5I5kquIPdH2B7KOUfhWkhFeE56O4wzcuEYS+JFZihSPG0EQT6/c1h6wjKgHZCcaodsXb3F7cXgWzThN1OapgchNNbKnW0ub0BA2wZQlGpfVePqzF4YlqNbq7nJ6en1HFN68qi4Mmu5sdtW3+1XCtLDE8JYaJ2QmUN9motETXKAHAFcXKsDA4xeeO5ITHvqDmxxXs+ug5mnf/5L+tc/BWvPgFdDEJwVcY2yWPPDpiwKc1xxGbmR9xXkNmn0bxR89FfgJAQv4Yjr7+oajGgq8O6/hLbmfkWdf62vO6nMTnjuzSEczV1hx1IH2goveeJG/+OQGb2MJuaJMk4oYU9uixBKE3iCBWOGJoNTJThiTyXZDL6RKg1UhMyg5fgqna4uCnzhuiJN9K6cTshB6t4GpkieMLU1m5u57m9gAT9pf9mjMshXhj721KiiZ94VCQgB8rmml1BgYTHkVlZ10bjTYX3jBNDIIx6cWFpsOZrNGSOu4Y1j95W9hxuz58loKTLkGjD75hM2XsdGKz8wm55VOSGbbwF1HVio0fMoIhc85g3+qPggeSkkTquGMYtvBCMo6ej6zp/luwPjYxbM6vIT45YsmuUJxNtTSXbAnoeqYqCiH/aqgqw066pNuPIwi9ZdD8lX/ggQeYNm0acXFxpKenc+aZZ1JUVHSopyUMMgUpMcweltJlB3xmnIETR6aHDRjLm2ws310f0LlJUX0bpb4oqsHminD5LgSzXstJozOYX5jKqPRYRqTFckxeEmeOzyI9rvtF1sMZkmjq9VXY3nJgANtBxZfO0OyIPj0g0aQjwSAqEhzu6rZ8i+IKvzrvsbfRsP2HkLdLksSUGx9u/6bTW2L712kTZjLqnOujntOkq/5M/oIL/R2rOnJKYzKGMue+Nzn2zv+QNW1hQACreFxUfb+U3Z+8RPnK93G1dd20GC2dOY7MaQujLgl2II/DFvD9mAt+6/uiczWD9ueUNf1Ecmef1qPHEYTeMGhWYleuXMkNN9zAtGnT8Hg83HnnnZx44ols27aNmBjRCUSIXm6iiSEJRiwODy6vQoxei1kf/g++R1GCruCCL8hyuBU2VTYzM79nm4kkyVezNTOub8t7JZn0pMfoqbUOrDy2aALraK+QShJMHZIYtu2ocHjwOu1RjfM4bWFvj8nIA7Yy8qxrqPr6Q9w2CzEZeeQvuIDsmSd3a8VU1uqYeMWfGHX29dRsXIXXZScup5CUMdOC/kxWrvuCTc/fg7utuVNDAwljSgbpE2eTf8L5JBaMj/rxAcb8/DfUbVqN12Xv5oqsRGxWfsCRYQt/QUJWPsWLn6dhh+/DQEx6LgUnX0r+ggt6HCwLQm8YNEHskiVLAr5/6aWXSE9PZ/369Rx33HFB7+N0OnE697f0s1h8G0Lcbjdu9+DY9NExz8Ey3/7QW6+JWQtmrW8nsTtMC1SAskYbHk/oUlcqUNbYxsSM7rc17Q3RvCZeRWXd3iZqW4OvXEmSL4Who8qAWa/p8erygXm3suRbtY52fKj5dTRECMWs0zB9aBKJBln87gRxuL0mpswCVG3kqxWmzPywz7njtrwTL6Hw1F8G3OZVVLxK918v2RxP1rE/838f7O9H3ZY1fP/kH3yB6wHPw97SRNnqjyn7ejHDTryI0ef9JuoPZoa0IRzzp1fZ8spfadq9ef8NkuRvf3sgSdaQOm4G2vjUgPdIt9tN8vhjmT7+WLwuF6riQWMwIUmSb+NlP1ZzOdQOt9+f3tBXr0m055PU6AvaDSjFxcWMGDGCzZs3M3588E+p9957L/fdd1+X42+88QZmc+/t+BYEQRAEQRB6h81m4xe/+AUtLS3Ex8eHHDcog1hFUTj99NNpbm5m9erVIccFW4nNzc2lvr4+7IsykLjdbpYuXcrChQtF16F2h+I1KaptY0u1JeJq4Smj0zHr+/8CR6TXxOH28sn2mrDzN2plThmT4W8z6/IofLStuttzmZydwPDUrik+dVYXq0rqu6QFSPg2uIWqGtHBrNNgc4dfGe7YoDdveCpmDeJ35wCH498Ty96drP3bVXhdzoAqA5KsQWsyM/OOF4jNGhbmDIfmdbFWl7Hyj+dGPd6clsPcB94/6DQZS/kOdn74nK95gqoiaXXkHHMSI067ClNqln/c4fizcrDEa9JVX70mFouF1NTUiEHsoEkn6OyGG25gy5YtYQNYAIPBgMHQ9VKTTqcbdD+Ag3HOfa0/X5O81Dg211rDjkk26UiIMfXLfEIJ9ZqUt7hQI+SuORRodaukxugBcONtr8EZvRGpMYzKTOjyRquqKusr6lElDQdudVYBL6DRgqJ0vdAp4UtHsHmJOB8V8KiwZq+FRYXJgPjdCeZwek1SCsYx997XKXrvKSq/W4Lq9SBptOTMOJlRZ1/vr58K4LQ0sXfV+7Ts2Yqk1ZEx6Tiypi2A9teiP18Xxd6K5HFGHtjOXlWCu7mWmPQhB/W4KcMnMPOWf+G2teK2WtDHJ6M1hP67dTj9rPQW8Zp01duvSbTnGnRB7I033sjHH3/MqlWrGDLk4H6ZBSFacQYt+clmShtDbxCZkDVwV/c9UW7u6FzGqrY1ujdYrQwdJVl31Vuxu71MzE4goVOlh7o2F21h8mtVfKl1yWYdjTZ3QKmxOIMGm1uJemeXCrQ5PQNu85rQd2KzhzHlxr9z1FX3+wKz2IQuJbUq133Bj0/chuJ1AxKSJLHv6w8xpeUw7bZn+33O3h40CVC9vdOCWvG42fv1h5QufQOX1YIpKZ3hp15B9oyTIrbWFYSBZNAEsaqqctNNN/H++++zYsUKhg0Lf3lIEHrb9NwkUKG0yYaEb4+EovouhU/LTSQ74dCuwgZTZXGwvbY16oC0c4kxJcqg8cCeAhUtDqpbnSwYmUaSybeq2xJleayJWQkYtTLVrU5UVSU11oBRK/PJ9pqo7t9BAppEEHvE0RpMQVcVm0u2sP5fN6Mq+3vOdfx4OxqqWffw9TD/un6da+W3n3T7PstvPxNTUhp5839O/oIL0MV0/4Ozo6We5b8/DXdrs/+Yq6WBH5/8Pbs+eo7Z97yBztx7DVYEoS8NmiD2hhtu4I033uDDDz8kLi6O6mpfrl5CQgIm08ALHoTDj0aWmJmfzPiseMqbbLi9KnEGLUOTTAfVtSsURVVpsrnxqioJRi0Gbfcu7W+rtrCpyhLdzn8gJ8GIqVPDho60gu7yraqqfF/exImjMgBf561oNNpcjMuMJ8m8/7Gtrp6tPokSW0KH4o//g++nvOsVCVXxYm/sfu73war87vNu30d1O7HV7mP72/+kfMW7zLr3dYwJqdHfX1VZdec5AQFsZ617d7H+yds45ranuz03QTgUBk0Q+/TTvl+qefPmBRx/8cUXufzyy/t/QsIRK86gZVxm36UOqKpKUV0b22tacbQvc0rA0CQTR+ckRtUWt8HmYlOVr6RcNAGsUefrZtZZvFFHRqyB2jZntxskqECDzU2L3U2CSUd2gnF/CcwwNldZyE00BawIm3Ua4gxaWp3RB7MqkBlvYHc35y0cXjxOO/Vb1lD1/dLwrWWl/i+L53VH30K5C1XBVlfBpufvZsatT0V9t+oNy3E01YYdU7thBY6mWjSxST2fnyD0k0HTsUtV1aD/iQBWONxsrGxhQ0WLP4AFX1BW3mRn6c5afx3XcHbVtYVuFdmJVpYYkRbLolEZQasqHJOXhClCI4hwLO2Bp0GrYUSQigXB7KwLbAAqSRJjM+KifkwJyIg1BOTkCkcWVVUp/uRFvrh+DuseuSFyLqna/7VO43IKDyp4VhUvNT+uwFZXEfV9Sr94M6px9Tu+7+m0BKFfDZogVhCOBBaHmx21wbu4q4DV5WVHbWvE89RFsXpq0smcMzGbKUMSA9IIOjPrtZw0KoOJWfHE6jVoZcm/yS0auk5pBJNzEtFrwofWKlBp6bpCNSzZzLhMXyAb6gwdxxNNOmYNS45qfsLhadcHz7Dt9Yfw2MNXFPGT+/+tcNiJvzj44FlVad6zNerhXkf4zmUdlB5sOhOEQ2HQpBMIwpFgd4M1bA6rChTXW5mYFR8057PB5mJLTVPYSgAdZPDXhA3HoJUZlxkfkELh9irsbbYHVDM4kF4jkRa7v8SdLEmYdBpcEVbFgqUcSJLExKwE8hLNFDdYaXW40Wlkkkw6Wp0e2lxeDBqJvOQYchKMyJIUsQubcHhyWpooei/6S+yA/xfOZbVga65BY4whJmNon+ZV5x53JtXrl1G9fjmRk35C605L3Pj8MTTu/DHiuJQx07s9D0dLPRXffIy9oRpDfDI5x56KOS2n2+cRhO4QQawgDCBWlzfi25nLq/iqIgR5f125ux5Fiu7yv1tRqWl1kBFnjDz4ADqNzNiMODa3590GMz4zHs0BG7rSYg1YHJ6Qz1ECUmNDbyhLMOm65O4KQmeV3y0Jn//aiSRrUBUvo865kSIVvrp5ETh9q7dxuSMYfe5NZE1b2CfzlGQNU3/7T/Z8/holS17FXl8JgDl9KLLeAIqXtsqSsOeQtXqSR02J+jELTrqE0i9eDzsmJjOPmLScqNt+qqpK8eLn2fH2P1FVFUmWUVWF7W8/xrBFFzP+4j8gdbPetCBES6QTCMIAYtDKEXNZNZKv+H9nHY33IjS9CuDyqiwvrqe2LfqC652Ny4hjTPr+S/wdi1YSMCEznpFpXcv0jEiNDRukq8CoIPcThGg5W+qjDppSxx/DlF//g7Iv3wIC67C27ivm+3/8mrJlb3fr8b1uF1XfL6Xk89eoWPsZHqc95FhZo2X4KZez4J9fcvw/Pichfwy22nLaKndHDGCRJPKO/zn62ISo5xabmUfByZeFPqVGy/Tb/h31+QDKvvov29961PfBQVV8r6Hiq+u8Z8mr7Hj7X906nyB0R7dWYu12O+vXryc5OZmxY8cG3OZwOHj77be59NJLe3WCgnAkyUsyU1wfOo9PAvKTY7pc5my0R7dqciAV+HFfMyeNzog8VlXxKCqyJKGRfcXiJ+UkMDItlrImGw6PF5NOQ16SOWSObaJJx9QhifywrzkgbaLj60nZCaTGdO2yJwjRMialR7ESK7Hg8WWYUzLZ+OyfcFoaug5p/2C4+aW/kD3jpKhqsu79+kO2vPJX3FYLHeU4tMYYxlxwM8NOvCj0bCSJra89iKV8p+9AsOYk7efrWD3OmDSXsRf9PuKcDjTu4j9gSs2i6N0n8dj259cnFkxgyq//QUx69CkAitdD0btPhB2z+9OXKDztyh7VtBWESKIOYnfu3MmJJ55IeXk5kiQxe/Zs3nrrLbKyfL2WW1pauOKKK0QQKwgHIS1GT1acwVfs/4DbJHy1ascE2alvdUZ3+TSYJrubFoc75G5+r6JSVNfKzjpfNy6ArDgDYzPjSY81YNZrgs4plBFpsSSZdeyobaOm1YGKr5rAyLTYHqU2CEJn2TNOYsvLf0XxBN+cJMkaUscfgzklE4/Dxr7VH6GGuf6heFzsXf0RBYsuDvu4FWs+ZcPTt+8/0B4EexxWNr/0f0iyhvwFFwS9b1t1GTXrl4U9vyTJJI6YiDk1m6FzzyZ1/Mwe5exKksTwky+jYNHFWMqL8LqcxGblo4/rfkmtpl2bcLYE+QDQieJxUbNxFUNm/azb5xeESKJOJ/jDH/7A+PHjqa2tpaioiLi4OGbNmkV5eXlfzk8QjiiSJDG7IIWhSfsbeHS8TcUYNJwwIo04Q9fPnnrtwWUG2UNsBPMqKit217Gp0uIPYAGqW518tasubBvecFJjDMwelsI5E3M4d2IOcwpSRQAr9Ap9bAKjz/tN8BtlGUmjZewFtwK+1INQwW5nO975V9hSVqqisPWNv4c9x/a3/hGy1Wz9ljWErrvR8Rhexl5wC1NufJi0Ccce9KYzSdaQkD+W5JGTexTAgi9A781xgtBdUb/zffvttzzwwAOkpqZSWFjI4sWLWbRoEXPmzKGkJELujiAIUdPKMsfmp3Da2EymDklkUk4Cxxem8rMxmSSbg296Suthd60OoRooFNW1UtvW9Y23Y5X4u/JGnJ6erwILQl8o/NkvmXDF3V2Cs4Sho5h196sk5I8BQGuK7gqCx97GmgeuRPEET9tp3LURR0P4rl9um4W6n74JepuqeCPFsL5x3oH1uxablR/lONEmXugbUacT2O12tNr9wyVJ4umnn+bGG29k7ty5vPHGG30yQUE4UsUatIyIcpPTgVUAuiPRqCXB2PVPgaqq7KwLv4KiqFDSYOtWOoEg9IdhCy8kb/65NOz4AbetlZj0XH/w2sEQn0TK2Ok0FG8OXxVEVbFWl1H943Kyp5/Y5WaXpTGqOblag49LKpwUsZ2dpNURnzcqqscJxtFUS+u+YmS9kaTh45G1B/fBFyAmYygpY2fQuOOH4HnIkow5LYeUMdMO+rEEIZiog9jRo0fzww8/MGZM4B+BJ57wJXWffvrpvTszQRC6bWJWPFtrrXi7UaVgck5i0EuTHkUNSCEIRgKaHT3bVCYIfU3W6kgbPzPsmNHn3Mjqv10d8VySrKH6h6+CBrHmtOyo5mNKyQp6PLFgHIkFE2gp3RY0GJRkDbmzT0cfmxjV43TmaKrlp5f+TPUPy/zNFfRxSRSefhXDT7n8oNMSjvrlPXx9zwV47NbAucsaZFnD5Ov+1qf1doUjW9TpBGeddRZvvhm8Zd0TTzzBhRde6C/zIwhC/6i3OllT2sAXRTWAb2X05DGZTB+axPjMeBKDrLB2MOlk5hakkBkfPBc1mkYIANo+foPyeBV2N1j5YW8TGyqaqW11ir81Qq9JGTONo697MOI4VVVCdrKKzxtDXO6IMG1kJYzJGaSOmxHy/FNuegRDQkpg9zBJAkkiLnck4y7+Q8Q5HshpaeTruy+gZv3ygO5grtYmtr3+ENsi5PFGIzZ7GMf93ztkH3PS/tJmkkTGUXOYc/+bpIw6+qAfQxBCiXol9o477uCOO+4IeftTTz3FU091s0uKIAg9oqoqP1VZ2FbT6itPpXgxA1uqLexssHN8YSrDU2IYlxlHRYud4norFocbWZZINRvISzKRFW8Mu0KikSUy4wzUBKmU4J8HkJPQdxuyKlvsfFPaiEfZv398R20bySYdxw1PDVnKSxC6I3PKfPj00wijJOKHjgx+iyQx8fI/8e1ff+mLFTu3k23/HZt4xT1h69fGZOQy94H3Kf3yTfau/ABXaxOm1GzyTjiPofPOQWswhbxvKMWLn8fRVBuy5NjuT14k7/ifH3TOakzGUKbc+DATf3kvTksD+tjEbtWvFYSeEh27BGEQKm+2s63GV+PxwADT7VVYsbue08dloZElchPN5Caae/Q44zLiqW6tC3qbBCQYtWSFWMk9WI02F6tKGvzPr/PzbLK7WbG7nkWj0qNeMRaEyEL/LEmSxNB554S8PWXMNI7940tsefUBWvZs9R+PyxnOuIv+QPpRsyM+uiE+mVFn38Cos2/o3rSDUBWFsmXvhK2ZK8kayle+z9gLbjnoxwPQmWPRmUWzEqH/iCBWEAah7TWtIW9TAYdHYW+znfzkngWvHdLjDByTl8S68iYUdf9bvArEG7XMK0zrs3y3SM+x2e6myuIgJ6H7K1SCEEzahGOp37i8/ROT72OTr7mAwlFX/RljUnrY+6eMnsLcv/yP1ord2BurMSSkEp87sk9+R1RVxWNvQ5JktKaYLrd7XXY89rbw50D1t7sVhMFIBLGCMMh4vApNETp0SUBNq+Ogg1iAYckxZMUZ2dNoo9nuRiNLDEkwRkxHOBiqqrK32R52x7gE7G22iyBW6DVTbvw7FSv+R8nnr2Kr3QdIpI6fyYjTryJ17PSozxOXM5y4nOF9MkdVUShb/j92f/oS1qo9AMQPHU3haVeSc+yp/t9Jjd6IrNOHzOMF3+qyPi65T+YpCP1BBLGCMMhEu6WpY1yD1UVZkw2nVyFWr6EgJYYYffd+9Y267nXlOliKGvl5qvgqKAhCb5G1OgpOvpSCky/F63IgyRpkbfBOdoeCqqpsev5uyle8S+fUB8veIn588jYse3f6UwMkWUPOsT9j39cfhkwpUL1ehsw+rT+mLgh94uDa/AiC0O90Gpn4MFUHwBfgpZj1rNpdzxc7a9lZ10ZZo42t1a18tLWazVWWAb3DXyNLmCNs2pIg4usgCD2l0RsHVAALUPPjivYAFgI+5rX/Lhd/9ByNuzb6D48442o0emPwDWWSTObUE0gaPqHvJiwIfaxHQeyrr77KrFmzyM7OpqysDIDHHnuMDz/8sFcnJwhCcKPTw6+K6jUSNW0OKiwOwPd21/Ef+KoY7G4Y2K0gR0Zo9KACw1O65gIKwuFqz9LXw1Y4kGQNpV++5f8+NjOPWXe/gjljaPsAqX2czNC5ZzHlxkf6dL79qaVsB8WfvMiuxc/TsOOHAf0hXeg93V7GePrpp7n77rv57W9/y1/+8he87W3wEhMTeeyxxzjjjDN6fZKCIAQqSDbTaHVR3GD1ldhqPy7hW8WclpvEN6XhuwhtrW6lICVmwO7uH5kWy74WO/XW4Dl9R+ckdDstQhAGM0tZUdhqA6ripaV0e8CxhPyxHP/wJzQWrcdSXoSsM5Ax6biIm9QGC2dLAz/86xYatq8DSUaSfHnDcbkjmPbbf4qWt4e5bq/EPv744zz33HP88Y9/RKPZ/4lw6tSpbN68uVcnJwhCcJIkMTU3kePamxUYtb5f5ZHpsZwyJgOHR4lwBrC5vbRE2CB2KGlkifmFaYzPjMOg2f+nKtmsY86wFEZFWI0WhMOFx25l92cv47K2RByrNXbd6ChJEimjpzLsxIvIm3/uYRPAet0uvv3L5TQWrfcdUBVUxfe3r62ihG/uvwRnS8MhnKHQ17q9jLFnzx4mT57c5bjBYMBqHdiXJwXhcCJJEjkJJnISTLjdbj4thQmZ8eh0Wn9zgEgX1LwD/JKbVpaYkJXAuMx4HG4FjQwGrWhwIBw5HE21rL7vYmy1eyMPliSyp5/U95MaICq/W0LrvuKgt6mKF6elidKv3uqVurvCwNTtldhhw4axcePGLseXLFnCmDFjemNOgiAcpESjNmIAKwFxhsFxOV6WJMx6jQhghSOC1+WkdvM3VH3/JavvuyiqAFaSZfSxieTOPasfZjgw7Fu9OEyrX0BV2LtK7NU5nHX7HeyWW27hhhtuwOFwoKoq69at48033+SBBx7g+eef74s5CoLQTZnxRsw6DTZ38Pw5CRiaZBJBoSAMIKqqUvzxCxR/+Bxum6Vb9zUkpHLMH547otq9ulqbAlv8BuGOIgVDGLy6HcT+6le/wmQycdddd2Gz2fjFL35BdnY2//znP7ngggv6Yo6CIHSTLEkcm5/M8uK6LjVXJcCs1zA5J/EQzU4QhGC2//cfFH/0XLfvV3j61Yw+9wZkrb4PZjVwxWbmYSnbEXqzmyRhTs/t30kJ/apbQazH4+GNN95g0aJFXHTRRdhsNtra2khPPzySxAXhcJIWa2DRqAy21lgob/J1v9LKEsNTYhiXGXfEr8K2ONy+DmSSRHqcAb1GlM0WDh1bXQXFH/Xsambq2OlHXAALMPT4n1Ox5tPQA1SV/BPO678JCf2uW0GsVqvl2muvZft2XwkPs9mM2XzwbS0FQegbCSYdx+anMGOoildR0WqkAVtSq7+0Oj18V9ZIXafSXbLkK+l1VHbCEf/6CIfGvtUfIckSaje70Ela3RHbsCB17AxyZv2Mim8+ocs2VkkmeeQkhsw581BMTegn3V56mD59Ohs2bOiLuQiC0Ec0soReKx/xAZrN5WXpztoutWcVFXbUtvFdWfjauoLQV+yNNeE3KYWQO/t0dDHxfTCjgU+SJI6+7m+M/vlN6DrlAmsMJgpOuphjbn8eje7IW6E+knQ7J/b666/n1ltvZd++fUyZMoWYmMCOORMnTuy1yQmCIPSm7bWtuDxKyMoNpU12RqW7SDaLNz6hfxkSUv3tY6Oli01kwuV/6qMZDQ6SrGHkWddReNqVWMp3oSpe4oYUojWKq8RHgm4HsR2bt37961/7j0mShKqqSJLk7+AlCIIwkKiqSkmDNWzpMQnY02gTQazQ74bM+hk733sy6vGSrOGY3z+DRm/ow1kNHrJWT2LBuEM9DaGf9ajZgSAIwkDQ4nBT1mjD6VUw6zQMS47BrA++YU1RwRMh31AF7CHKkglCX4rNyid/wYWUfvlmxLGmtBwmX/tXkgqP6oeZCcLA1e0gNi8vry/mIQiCEDVFVVlX3sSeRhuds3x/qrIwISuecRldW9LKkq86Q7hAVgJMuiO7aoNw6Ey4/I/ozHHs/uxlFLfTfzw2ZzhDjv0ZutgEYrPySR07A0kW1TQEodtB7CuvvBL29ksvvbTHkxEEQYjGj/ua2dNoA7q21t1cZcGglclPCLzMKkkSBSkx7KprC5lSoAIFySKXTjg0JFnDmAtupvD0X1G3+Vs8DhtxOcNJHD4B6QjflCkIwXQ7iP3Nb34T8L3b7cZms6HX6zGbzSKIFQShT9ndXorrrWHHbKmyMDQ+tcvxMRlxlDXZQm7uyk8ykyTyYYVDTGeOI3vGokM9DUEY8Lp9PaKpqSngv7a2NoqKipg9ezZvvhk5l0cQBOFgVFocYTdnATg8Ck12d5fjZp2GE0emkxobGKhqJIkx6XHMyEvqxZkKgiAIfanbK7HBjBgxgr/97W9cfPHF7NixozdOKQiCEJQ3ymLwoXJfYw1aFoxIx9LesUuWJTJiDehExy5BEIRBpVeCWPB186qsrOyt0wmCIAQVb4zuz1Z8iCoF+8+jI96o640pCYIgCIdAt4PYjz76KOB7VVWpqqriiSeeYNasWb02MUEQhGAyYg3E6DVYXcFLYUlAVrwRk77XPqMLgiAIA1C3/8qfeeaZAd9LkkRaWhrHH388jzzySG/NSxAEIShJkpiZl8zy4joUNbA6gQQYtDJThiTStW6BIAiCcDjpdhCrKEpfzEMQBCFqabEGFo5KZ0uVhX0tDsBXB3ZYcgzjM+Mw67W43V03dgmCIAiHj27vZLj//vux2Wxdjtvtdu6///5emZQgCEIkSSY9cwpS+fnEbM4Yl8W5E3OYPjQJs0gjEARBOCJ0O4i97777aGtr63LcZrNx33339cqkBEEQoqXVyJj1GjSyKAYvCIJwJOl2EKuqatDOIZs2bSI5OblXJiUIgiAIgiAI4UR93S0pKQlJkpAkiZEjRwYEsl6vl7a2Nq699to+maQgCIIgCIIgdBZ1EPvYY4+hqiq//OUvue+++0hISPDfptfryc/PZ+bMmX0ySUEQBEEQBEHoLOog9rLLLgNg2LBhHHvsseh0oki4IAiCIAiCcGh0exvv3Llz/V87HA5cLlfA7fHx8Qc/K0EQBEEQBEEIo9sbu2w2GzfeeCPp6enExMSQlJQU8J8gCIIgCIIg9LVuB7G33XYby5Yt4+mnn8ZgMPD8889z3333kZ2dzSuvvNIXcxQEQRAEQRCEAN1OJ1i8eDGvvPIK8+bN44orrmDOnDkUFhaSl5fH66+/zkUXXdQX8xQEQRAEQRAEv26vxDY2NlJQUAD48l8bGxsBmD17NqtWrerd2QmCIAiCIAhCEN0OYgsKCtizZw8Ao0eP5u233wZ8K7SJiYm9OjlBEARBEARBCKbbQewVV1zBpk2bALj99tt58sknMRqN3Hzzzdx22229PkFBEARBEARBOFC3c2Jvvvlm/9cLFixgx44drF+/nsLCQiZOnNirkxMEQRAEQRCEYLodxHbmcDjIy8sjLy+vt+YjCIIgCIIgCBF1O53A6/Xy5z//mZycHGJjYykpKQHgT3/6Ey+88EKvT1AQBEEQBEEQDtTtIPYvf/kLL730Eg899BB6vd5/fPz48Tz//PO9OjlBEARBEARBCKbbQewrr7zCs88+y0UXXYRGo/EfP+qoo9ixY0evTk4QBEEQBoMnn3yS/Px8jEYjM2bMYN26dSHHPvfcc8yZM8ff6XLBggVdxkuSFPS/v//97/4xjY2NXHTRRcTHx5OYmMiVV15JW1tb0McsLi4mLi5OVBESDivdDmIrKiooLCzsclxRFNxud69MShAEQRAGi//+97/ccsst3HPPPfz4448cddRRLFq0iNra2qDjV6xYwYUXXsjy5ctZs2YNubm5nHjiiVRUVPjHVFVVBfz3n//8B0mSOOecc/xjLrroIrZu3crSpUv5+OOPWbVqFVdffXWXx3O73Vx44YXMmTOn95+8IBxC3Q5ix44dy9dff93l+P/+9z8mT57cK5MKpzufdgVBEAShrz366KNcddVVXHHFFYwdO5ZnnnkGs9nMf/7zn6DjX3/9da6//nomTZrE6NGjef7551EUha+++so/JjMzM+C/Dz/8kPnz5/ubDW3fvp0lS5bw/PPPM2PGDGbPns3jjz/OW2+9RWVlZcDj3XXXXYwePZrzzjuv714EQTgEul2d4O677+ayyy6joqICRVF47733KCoq4pVXXuHjjz/uizn6dXzafeaZZ5gxYwaPPfYYixYtoqioiPT09D59bEEQBEE4kMvlYv369dxxxx3+Y7Iss2DBAtasWRPVOWw2G263m+Tk5KC319TU8Mknn/Dyyy/7j61Zs4bExESmTp3qP7ZgwQJkWea7777jrLPOAmDZsmW88847bNy4kffee68nT1EQBqxur8SeccYZLF68mC+//JKYmBjuvvtutm/fzuLFi1m4cGFfzNGvu592BUEQBKEv1dfX4/V6ycjICDiekZFBdXV1VOf4wx/+QHZ2NgsWLAh6+8svv0xcXBxnn322/1h1dXWXxRutVktycrL/cRsaGrj88st56aWXiI+P787TEoRBIeqV2JKSEoYNG4YkScyZM4elS5f25by66MmnXafTidPp9H9vsVgAX37QYMnf7ZjnYJlvfxCvSVfiNelKvCZdidckuIN5XTru4/F4Au7v9XpRVTXiOR966CHeeustli5dikajCTr+hRde4MILLwy4Pdz5vV4vbrebK6+8kvPPP5+ZM2fidrvxer1RP0/xs9KVeE266qvXJNrzRR3EjhgxgqqqKv8nv/PPP59//etfXT599pVwn3ZDVUV44IEHuO+++7oc/+KLLzCbzX0yz77S3x8aBgPxmnQlXpOuxGvSlXhNguvJ6+J2u5FlmU8//ZTGxkb/8Q0bNiBJEp9++mnI+37wwQe8/fbb3H///ezbt499+/Z1GbN161Z27tzJddddF3Cu2tpaKisrA455vV4aGhqoqKjg008/ZenSpSxevJhHH33UP0ZRFIxGI9dff33Ild/OxM9KV+I16aq3XxObzRbVuKiDWFVVA77/9NNPeeCBB7o3q352xx13cMstt/i/t1gs/l2gg+XSitvtZunSpSxcuBCdTneopzMgiNekK/GadCVek67Ea9KJxwNLlsDHH+Peto2lt9/OwquuQqfXw4QJMG0aXHQRtG+kCmfKlClYLBZOOeUUwBco3nDDDVx33XX+Ywd6+OGHee+99/j888+ZMWNGyHO/++67HH300dxwww0Bx4cNG8YTTzxBZmYmRx99NOALJFRV5dprryU7O5s1a9b4V18BFi9ezMMPP8zKlSvJyckhKSkp5OOKn5WuxGvSVV+9Jh1XziM5qLaz/Sk1NRWNRkNNTU3A8ZqaGjIzM4Pex2AwYDAYuhzX6XSD7gdwMM65r4nXpCvxmnQlXpOujujXRFXhtdfgzjuhY+XTZAJA19aGzm6HigpfgPvnP8Npp8Hjj0OY9uq33norl112GdOnT2f69Ok89thjWK1WfvWrX6HT6bj00kvJycnxL/w8+OCD3HvvvbzxxhsUFhbS0NAAQGxsLLGxsf7zWiwW3n33XR555JEu/78mTpzISSedxHXXXcczzzyD2+3mt7/9LRdccIG/FfzEiRMD7rNp0yZkWe5WJaEj+mclBPGadNXbr0m054p6Y1dHoeUDj/UXvV7PlClTAkqQdJQkmTlzZr/NQxAEQRikLBY480y49NL9ASyAtn0956ijICsr8D6LF8P48fD66yFPe/755/Pwww9z9913M2nSJDZu3MiSJUv86W/l5eVUVVX5xz/99NO4XC7OPfdcsrKy/P89/PDDAed96623UFWVCy+8MOjjvv7664wePZoTTjiBU045hdmzZ/Pss89G/3oIwiDXrXSCyy+/3L+y6XA4uPbaa4mJiQkY15clPG655RYuu+wypk6dGvBp94orruizxxQEQRAOAxYLLFgA33+//9gpp8CNN8KcOfDVV7BqFeh0vpXY11+Hf/3L93VbG1x8se/fa64Jevobb7yRG2+8MehtK1asCPi+tLQ0qilfffXVQZsXdEhOTuaNN96I6lwAl19+OZdffnnU4wVhoIs6iL3ssssCvr/44ot7fTKRnH/++dTV1XH33XdTXV3NpEmTAj7tCoIgCEIXqgpXXLE/gE1Ohhde8K3KAhy4EzonB37/e1/A+tvfwksvAbDu2muZVFiI/oQT+mvmgiCEEXUQ++KLL/blPKIW7tOuIAiCIHTx3/9Cx1XCpCRYudKXIhBJQgL85z+QlsZjf/87NwPLLrmE+bt2wQFXIQVB6H/dbnYgCIIgCIOGosBdd+3//tlnAwJYVVWpbfPVE/9+bxPbqi3Y3ft39CNJPJ2Xx83AH4B5VVW+wFYQhENOBLGCIAjC4euLL2D3bt/XJ5wA557rv8npUfhyVx2rSnzVAcqb7GyqsvDhlip21bcBvkYD1994I7+9+GIeACSAp5/2pSgIgnBIiSBWEARBOHx9/PH+rzvVWlVVldV76mmwuvYf6/TvD3ub+fu/nuKqq65i2LBhTFqwAGn2bN+A7duhpKTv5y4IQliDpk6sIAiCIHTb+vX7vz7+eP+XDTYXtW2uIHfw2bRmJQ/+xhf0WiwWli1bhjc5mXxgNJC9fj0MH943cxYEISoiiBUEQRAOXx0rpkOG+DZqtatocSCxf/X1QPmjxjFt/klkxRtobGhg2bJlvFpRgYrvjbNs0yayzzuvjycvCEI4IogVBEEQDl8dbVcP6N7oUVQkKXRqa0JyKjc/8hynj8skRu97q3S+9x7l55yDFchq7/IlCMKhI4JYQRAE4fCVlAQNDVBV5QtoNRoAEk06lAh7s3QaCaNW4//eUF3NiI5vkpP7Zr5hqKpKg81FdasTVYXUGD2ZcYZ+7Z4pCAOJCGIFQRCEw9ekSVBcDDYbbN0KEycCkJdo4sd9zXhCRLISUJgSg0buFCCuW7f/68mT+27OQdjcXlaXNNBgc9ExIxWI1WuYU5BKoqn3+tYLwmAhqhMIgiAIh69Zs/Z//eqr/i+1GpmZ+clIwIHrmBKQYNIxLjN+/8G2tv0NE0wmOOqovppxF15FZdmuOhptvo1oKvtzea0uL1/tqsXWubatIBwhRBArCIIgHL4uvnh/Puyzz0JFhf+mIQkmFoxMIzNuf76sQSszLjOOBSPS0Gk6vUU+9hi0tvq+vugiMJv7YfI+5U02Wp2eoJvQVMDtVdlV19Zv8xGEgUIEsYIgCMLhKzUVLr3U97XFAr/6FXg8+2+OMTBrWAoAp4/N5KzxWUzISggMYNevh/vv930ty/DrX/fX7AEoa7KFvV0FShvDjxGEw5EIYgVBEITD29/+BpmZvq+XLIHLLgOHo8swvVbuuknqhx/gpJPA7fZ9//vfw4QJfTzhQE6vEnGMO4oxgnC4EUGsIAiCcHhLTvblw+raNz+98YZvY9bSpaFrbDU1wd13w8yZUF/vO3bssXDPPf0z507iDdouebsHijWIfdrCkUf81AuCIAiHvwUL4N134bzzfKuwO3bAiSfC6NG+ldZ58+Ctt3yluL7/Hj75BOz2/fefNcvXwtZo7PepF6bGUtpkDztmRGpsP81GEAYOEcQKgiAIR4bTTvPlt15+uS9QBV8wW1bmC2KvuSYwcAXQauHOO+GPfwS9vr9nDPjqwQ5PMbO7IXjea3qsnvzk/ttoJggDhUgnEARBEI4cY8fCt9/6Vl2POy70uIQEuOkm2LIF7rvvkAWwAJIkMS03ick5CZh0+9+2dRqJMRlxzBueFljPVhCOEGIlVhAEQTiyaLVw/vm+/xobfauzNhv8/e++4PWoo2DMGN+4AUKSJEanxzEyLdZXbkuFOIM2YvDq9ipUtDhweRVi9Bqy4o3IosOXcJgYOL+hgiAIgtDfkpN9qQSffgpXX71/89cAJUsSCcbIc1RVle21rWypasXbafOaUSszbWgSQxJMfTlNQegXIp1AEARBEA4z22pa2VRpCQhgARweha9LGqiydC0xJgiDjViJFYTDkNPSxJ7PX6V8xbs4LY0YElLJO/5chp14EfrYxEM9PUEQ+pDLo7Cl2hJ2zMbKFrLi+7/SgiD0JhHECsJhxt5Qxep7f4GjqRZV8RVAdzRWU/TuU+xd+QGz730dY1L6IZ6lIAh9ZV+LHSVE+dsOzXY3Foeb+ChSEwRhoBLpBIJwmPnx6TtwNNX5A1g/VcHeUMXG5+4+NBMTBKFfOD1KxOYI4EstEITBTASxgnAYsVaX0bDtO1TFG/R2VfFSu3EVtrqKfp6ZIAj9xazXEGEh1jdOp+nzuQhCXxJBrCAcRlr2bItilErznq19PhdBEA6NnAQT2gilt2L0GtGqVhj0RBArCIcRWRtdfpusEXlwgnC40soS2QnhN21ZXV5anZ5+mpEg9A0RxArCYSR59BQkTfjVFVmnJ2X0lH6akSAIh0KD1RX2dgnY3WDtn8kIQh8R1xIE4TCij0ti6NyzKVv+P1CDbNqQJPIXXIAuJr7/J3cAt62NqnWfY6uvwpCQTPb0RRgSUg71tAQhKk6Pwp5GKw1WF5IEWfFGhiaaB0T7V1VVsbqC58X7xwCtDnf/TEgQ+ogIYgXhMDP+0juxN1ZTu3EVkqxBVbz+fzOnHM/YC2891FNkz9I32fr6QyguB5JGi6p42fLKAxSediWjf/4bJNEWUxjAKlrsfLOnAW/77ikJKGuys7GihfmFaSSaDn26jkbCP79gJEAri4uxwuAmglhBGGCa92xl96cvU7NhBarHTULBOAoWXULW9BOjCu40egMzbnuG+m3fsXfl+ziaajGlZJI79yxSRk875AHi3q8/ZPOL9/u/V70e/7+7Pvg3slbHqLNvOFTTE4Swmmwuvi5pCNj93/G106OwrLiO08ZmotMcugBRkiRyE82UNdlCVilQgSGJotmBMLiJIFYQBpCKtZ/x4xO/AyR/mazGnRto3LGevBPOZ+Iv74kqCJUkibRxx5A27pg+nnH3qIqX7W8/FnbMrg+fo+Cky9CZY/tnUoIQpfImG2vLGsMGhk6PQmmjjRFp0f38ujwKJY1W6q0uJCAzzkhekgntQQbBYzLiKGuyhR1T0+okN9F8UI8Tiqqq1FtdlDRasTq9GHUa8pPNZMUZDvkHaeHwIYJYQRggHE21/Pjk71EVFeiUz9retKDsq/+SOnY6OTNPOTQT7AXNJVtwNFSHHaO4ndRsXMmQY0/tp1n1D0dzHU3FPyFJEkkjJmOITzrUUxK6obTRxpqyxqjGVrTYowpiqywOVpXUB3TXKm+2s6GymeML00g263s6XRJNOmIMGtqcoXNji+utjM2M7/V6sYqqsraskbImOxK+4N6XcmEjPVbP3ILUgw7SBQFEECsIA0bZ8v+1d9kKsc4jyZQseXVQB7Fua/h+7t0dNxi4rRZ+evF+Ktd+5u+iJmm05M45g/GX3onW2DcrYULv8Soq6/c1RT3eo0ZuNWBxuFm5uz7ob7vbq/LVrjpOH5eFQduzYK/N6QkbwILvL82+Zjsjo1w1jtaWKgtlTXb/Y3T+t7bNxbq9TRybLzZxCgdPfBQShAGiefdPwSsKdFAVmku29N+E+oA5PTeqcTEZQ/t4Jv3D63Lwzf9dTuXaJQFtgFWvh/JV7/PdQ9egeEWtzoGu0uLAFW6XVCcSkGyKvIK6saIlbFctj6Kys641ugkG4fJGbikr4Ut/6E0er0JRXVvYMWVNdmwu8XMvHDwRxArCACFptBAhV0wa5LuJY7PySR51dOjnIUkYkzNJGz+wcnl7au/XH2Ip2x68DbCi0LDjB6q//7L/JyZ0i90dfkWzMxUoTI2JOK6q1RFxTElD+JzWcKJJEVCBWEPvphLU21x4lMgBf3Wrs1cfVzgyDe53REE4jKRPnA1hLkNKsob0o+b044z6xoQr7kbWGZDkA948JRlJkpl09f91vW2QKlv+v/AfTGSZshXv9t+EhB7pziX9KUMSiTdGLrEVRZwX1WpqKEadhiEJRsJ9LNbKErmJph4/RjDRPC/fuCgHCkIYIogVhAFiyOzT0MclhVylVBWF4adc0c+z6n0JQ0cx5/63SJs4Gzq9xSaPnMSxd71E+sRZh25yvczRUB32gwmKgr2hqv8mJPRITrwRbYQmBhoJ5hak9Gp+qV5zcLv4J+UkotNIIQPZablJvV4rNsmkCxs4dziYTWuC0EFs7BKEAUJrjGHmHc+z5q9X4mpraT+q+hoVqCpH/eq+w6ZdbHzuSI75/TM4mutwNNaij0/CnJp9qKfV6wyJqThbGgi3Wc+UlNGvcxK6T6uRmZgVz48VLSHHzB6WQnZC9KuaSSYtTfbweaEHlr9yeRVsLi86jUSMPvLbd5xBy4mjMthQ0UxFy/70hQSjlqOyE8jpxnyjZdJpyE00sbfZHvSnXgKSzToRxAq9QgSxgjCAJOSP5YTHvmDf1x9RvWEFisdF0vCJ5B1/HjEZ0W2KGkyMiWkYE9MO9TT6TN68c9n88l9CD1AVcuee1X8TEnpsVHockiSxqbIlIOfTqJWZlpvUrQAWYGJWAitLGkLeLkkwLjMO8OXkbqxooazZ5l/YTzLpmJAVHzEQjTNoOa4gFbvb6w+A4wzaPq3VOmVIIk12N63OwCBdwpeaMVNUJhB6iQhiBWGA0ZnjGLboIoYtuuhQT+WQcDTVUr7yfdqq9qAzxZI9YxHJo6cOygLpuXPPZM/SN7BWl3XZ3CXJMgn5Y8meceIhmp3QXSPTYilIiaHK4sDp8WLWa8mMMyD34GczO8HExKw4fqrqWoFABuYOT8Wg1WB3e/miqBa72xuwstlkd7OqpIEZQ5MoSIm8kcyk02Dq5XqwoRh1Gk4clc6uujaK663Y3V4MWpmClBhGpsX22zyEw5/IiRUEYcDY8/nrLL1pPjve+RcV33xM6Vdv8c2fL+WbP18yKGvHao0xzLr71fYNeZ0CHUkma/qJzLzzP8jawXlZ9cknnyQ/Px+j0ciMGTNYt25dVPd76623kCSJM888s8tt27dv5/TTTychIYGYmBimTZtGeXm5/3aHw8ENN9xASkoKsbGxnHPOOdTU1HQ5z0svvcTEiRMxGo2kp6dzww2918a4YzNUYWos2fHGHgWwHcZlJnDiyHSGJZuJ0WuIN2gYmxHHz8Zlkhnnawn7U2VLlwC2sx/2Nh3UBrC+otfIjMuM54zxWVwweQhnTcjmqOwEEcAKvUqsxAqC0O9ayovYu+oDnM11GBLTyD3uTGw15Wx++f/8Yzrvh2rauZHv//lbjr3zP4dgtgfHEJ/MjNuexlq7j6adG0CSSBk9FVNK5qGeWo/997//5ZZbbuGZZ55hxowZPPbYYyxatIiioiLS09ND3q+0tJTf/e53zJnTtcrG7t27mT17NldeeSX33Xcf8fHxbN26FaPR6B9z880388knn/DOO++QkJDAjTfeyNlnn80333zjH/Poo4/yyCOP8Pe//50ZM2ZgtVopLS3t1effm1Ji9KTEJAe9zeNVKG2yha0n61V9nbBGpIo2zcKRRwSxgiD0G8XrYdPz97B35Xv+DWuSJFHy6UvoYhJ8iYBBdvOripf6LWtoLtlKYsG4QzDzgxeTPoSY9CGHehq94tFHH+Wqq67iiit81TKeeeYZPvnkE/7zn/9w++23B72P1+vloosu4r777uPrr7+mubk54PY//vGPnHLKKTz00EP+Y8OHD/d/3dLSwgsvvMAbb7zB8ccfD8CLL77ImDFjWLt2LccccwxNTU3cddddLF68mHnzj2dvsx2v0UVeah51bU5SY/R9kpaiqCp7m+3sqm+j1eFBp5HJSzJTmBpzUCuPdrc3YskqSfJ15xKEI5FIJxAEod/seOdf7F35PuALTFEVf66o29oSsU5u9fqv+mWeQmgul4v169ezYMEC/zFZllmwYAFr1qwJeb/777+f9PR0rrzyyi63KYrCJ598wsiRI1m0aBHp6enMmDGDDz74wD9m/fr1uN3ugMcdPXo0Q4cO9T/u0qVLURSFrcWl5BWOZMqY4Vx3xSWs3lTEl7vqWLqzDkc3GhdEw+H2srSolm9LG6lrc+HwKLQ6PWyttvDp9hqa7e4en1unieItWo1ynCAchsRPviAI/cJta6NkyauELDcViSThdYkuP4dafX09Xq+XjIzA0mAZGRlUV1cHvc/q1at54YUXeO6554LeXltbS1tbG3/729846aST+OKLLzjrrLM4++yzWblyJQDV1dXo9XoSExNDPm5JSQmKovDg3x7g4lvv4TcP/Zu2lmb+cv0v8LhdNNpcLN9d3yuF9hVVZUNFMx9sqaIxSKCqAm6vwqqSnj+eUachLUYftu6qCgzt5YYFgjBYiHQCQehDXpeD6h+XY2+oxhCXRObUBejMsbjamin76m32rvoAV1sz5rQc8k44jyGzz0CjG5wbfSKp3/Ydiityq81QVK+HkiWv0lK2neEnX0rG5Hm9Njeh77S2tnLJJZfw3HPPkZqaGnSMovg2Jp1xxhncfPPNAEyaNIlvv/2WZ555hrlz50b1WIqi4Ha7uey2+5gw03efmx54gusWHs3W77/lqGPn0Wx3U2VxHHSN1HXlTexpDN8WVgWsLi/VFke3S3B1mJAVz7Li+pC35yWZouoQJgiHIxHECkIf2bvqAza//Bc89jYkWUZVFGTdvQw76RIqvlmMo6kOVN+bt6utmebn7qZ8xfvMvON5tEZzhLMPPgcTwHZQvW4atq2jfssaRpx5DWPO++3BT0zoltTUVDQaTZeqADU1NWRmdt2stnv3bkpLSznttNP8xzqCVq1WS1FREbm5uWi1WsaOHRtw3zFjxrB69WoAMjMzcblcNDc3B6zGdn7cjn+zC0b6b49PSiEuMZmG6krAVyOivMl+UEFsk90VMYDtIAF1VlePg9iMOCOzhyWztqwJj6L6V2VVfAHsjKHBN4UJwpFABLGC0Acq1n7Ghmfu8H+vtr9pK24nuxc/33UDU/vXTbs3se3NR5h4xZ/6db79IX7oqOgGSrI/uA+mI4d21wf/JnXMdNImHNsb0zsyVPoCOX73OygpAUWBlBSYPBmOOw6OPtr3sxmGXq9nypQpfPXVV/4yWYqi8NVXX3HjjTd2GT969Gg2b94ccOyuu+6itbWVf/7zn+Tm5qLX65k2bRpFRUUB43bu3EleXh4AU6ZMQafT8dVXX3HOOecAUFRURHl5OTNnzgRg1ixfy+Kq0t2kZGQB0NbSRGtzI6lZOYAv+PMoB1eSqrTRhkT0iTEHu5UsN9FMVryRvc12Wh0etBqJ3EQzcQbxFi4c2cRvgCD0MlVR2PbmIxEGhXj7UxTKV7zLmPNvRmc+vErmxA0pJHnU0TTt2tSl8D/4Nm4lDh9P2vhjKf3yLVytTWHPJ8kaSj5/TQSx0diwAe6/H5Yuhddfh+eeA7t9/+2vvur7d/JkX4B74YVhg9lbbrmFyy67jKlTpzJ9+nQee+wxrFarv1rBpZdeSk5ODg888ABGo5Hx48cH3L9jJbXz8dtuu43zzz+f4447jvnz57NkyRIWL17MihUrAEhISODKK6/klltuITk5mfj4eG666SZmzpzJMcccA8CoUaOYcfwiXnn4Hn5114OYYmJ56/EHyc4vZOxU38+JBMQd5OV3hzv6IFgF0uMMEce1Oj3sqmuj0uJABdJi9IxMi/W3Z9XKMsOSIzc1EIQjiQhiBaGXNZdswV5X0eP7K24nlvIiUkZP6cVZ9T5VVWnYto6W8h1o9EYyJs2NWPt00jV/ZfU9F+K2WgICWUnWoIuJZ/J1DxKbmceoc25k5R/PwVK2I/TjK16adm3qtedzWPJ44L774IEHwOsFU4RL2hs2wEUX+QLdF16AIOkBAOeffz51dXXcfffdVFdXM2nSJJYsWeLf7FVeXo4sd2/f8FlnncUzzzzDAw88wK9//WtGjRrFu+++y+zZs/1j/vGPfyDLMueccw5Op5NFixbx1FNPBZzn8X+/wO9/dysP/fpyZFlizNHHcPsTr6LV+QJXFRgeRYercEy66J6bBMQbtWTEhg9iK1rsrN7TgKruX921Oj3sabQxZUgiI9MOrw+0gtBbRBArCL3M1dZ80OeQuhkA9Lfmki2sf/xWrDXl7akRgCQxZPZpHHXlvWj0xqD3i83MY+5f36N48fOUr3wPr9OOxmBi6NyzKTztSkwpvkvAkiyj0UdevZK04k9YSG43nH8+vP/+/mNZvteXxYth3DjQaqGsDNauhZdfhu+/993+6acwcyYsXw75+UFPf+ONNwZNHwD8q6ehvPTSS0GP//KXv+SXv/xlyPsZjUaefPJJnnzyyZBjJhdkc+dD/6Le6gp6+8Ss+IO+DD8sOYbttW0Rx5l0Go4rSA1bm9bm8rJ6T0OXerAd367f10ySSUdahEBYEI5E4h1AEHqZOS3noO6v0RtJyB/TS7PpfW1Ve/jm/y7bv1GrIzVCVdm3ejFum4XptzwZ8o3blJLJhMvvYvyld+J12dHoTUGD9ozJ82gq3hwyP1aSNWQePb83ntLh6frr9wewWi3cdZcvVeDLL335r+0rk6SmwpQpcMMN8NFHcM01UF0NpaUoCxci//gjxMUduufRTVpZYn5hKlurWymub8Pl9f18Jhi1jMuMJy+p55smHW4vJY1Wqi1OjFoZhyfEzya+qgIj02Ij1nAtrm8L29BAAorq2g5ZEOvyKiArohatMCCJIFYQellcznASh0+gec9W38aZborNGR5yJXMg2PXRcygup3+zWgBVoWb9cpp3byapcGLY80iyjNYY+rLu0Pnnsuuj5/A6HV0DWUkCSWLYoot68hQOf4sXw/PP+742GHzfL1zoW50N5/TTYepUOP54Piwq4rLiYjZdfz15HTmzg4RWljkqO4HxmfHY3V5kScKkkw+qW1dtq5OVJfV4IrTQSo/VM31oclSrvV5FZVd9+BVdFahp7d/6yKqqUtJgBeCjrdUga0gy6RiTEXdQHwIEobeJj1aC0AcmXP4nZI3Wt9O+mxILJvTBjHqHqnip+OaToBuzOkiyhn3fLD7oxzImpHLM75/1lRvrHHxIMrJGy9RfP0r8kBEH/TiHHa8XfvOb/d8/9ZQvgO3EZW2hct0X7Pv2E9oq9wTePzubT2+7jZ8DJwJDXnsNDqguMFhoZIlYgxazXnNQAazd7Y0YwE7OSeDUMRmcMCI96nSFDfua/CvFA4Wqqqwtb+LHipaA4012N9+WNvJTZUuIewpC/xMrsYLQB5KGT2DW3a+x9fUHadyx3n9c0uhQveFXw1LHTO3r6fWIqihUr1+O4gmea+gfh4qrtblXHjNl9BQW/HMp5Svfp27zt6B4SR49hbz5P8eYlN4rj3HY+fRT2NMemM6fD+0VAwC8bt//u69uORkc+1cAU8bOYPI1f8GclsMXX3zB2TfcwCnjxvH61q1oAJ58Ep55ph+fxMCyu8EaNoCVgBa7m9Hp0aVdqKrK9ppWdjVErjUrARlRVDfozOnxUlTbxu4GK06PglErU5Aaw6i0WAxaTdj77mtxUBqmBu7WmlZyEk2kmA/PpizC4CKCWEHoI0nDJzD77tew1uzF3liFIT6Fui1r2fLy/wW/gyxjiE8ma/rC4LcfQo6Wer578GpaSrdHHCshYU7N7rXH1scmUnjqFRSeekXkwQK8+eb+r2+91b+Kraoqm569C4bNQ/W4A2qXNu74gdX3/gJOvoXTzz2fwsJC/vLCC+hOOAGsVnjrLd+K7gDfcBgtVVXxKCqyJKGRJbztAWqo9rBVlvCNOlSgMsKYzjZXW9ha3RrdXIFR3ahOUG91srw4cNXY7lHYVt3KngYbC0emYdaHfuvfVdcWtgau1D4mJU80WRAOPRHECkIfi8nIJSYjF4DYrGG0lGxh79cfIMma/Zfl2/NDZ/zuGWTtwFrhUFWV7x66Fkv5zujGK15y557Vx7MavJyWJhp2fA+KQuLwCQe9EbCLjgoDRiMsWuQ/3Fj0I9U/Lodh87rcRVW8fLNtD//39FkoqkpRURGff/MNaXPmkLZkCVJLCxQXw8iRXe47mHi8Cjtq29hZ34azfVOWUSvjcLkx48v/HJ4Wz7jMuIAVy1DBbWdOj8KXO2tJNuspTI0J2QrW6vJEHcB22FTZwqxhKZh04VdRW+xuvtxZFzQAVfGlRXxX3sT8wrSQ52i2u8M2cVDbxwjCQCCCWEHoR5IsM+nav5I1fSF7lr6BZe8utAYTOTNPIX/BBQPyEnn91rW07Nka9fjC064kNiu/7yY0SHldDra88gDlK99D9Xraj0pkTJ7LUVf/GWNC6sE/iMvlCzYBJkzwVSVo5//gFOKuVqcHs05G0Rqw2Wzceuut3ArEADOApVu2IA/iINbtVVi2q47GAwKwzhUGPIrKzro29rXYWTgy3R80psUYaLJFDu7qrC7qrS6K6tpC1nfd081uXwD1VhfLius4aVQGGjl4bq+qqqwqqY84x+pWJ61OT8i8XY0sQeiUd8BXAaInGm0udjdYaXN60Gtk8pLNZMcbkQ8iX1k4sokgVhD6mSRJZE45nswpxx/qqUSlev0yJI22U+AVnD4umZFnXsOwky7pp5kNHqqisO6RG6nbsuaASgsqtZu+5pt7L+K4v/wPnfkgS1k5Ol3STkoKuMnZXB92Q95x+Qkcl5/Iaa9vpaWlhT179rDn8cfZ8+KLyIDsiP5y+UC0raaVpihWEFV8tVs3VrQwM993ybwwNYaiush1YTvuD776rnEGLVnxgZVGbK4IEWKIc1ocHn7Y6+tiJ0kSmXEGhiSa/AFgg81FW5TnbrK5QgaxQ5NMFNW2hQ2GcxMjNM04gKqqrN/XzK56qz+Al4DyZjvJZh3zhqdh0B4eqSpC/xoUPzWlpaVceeWVDBs2DJPJxPDhw7nnnntwucJvMBEE4eB5HLbg5bQOkFg4gdbKEhp3/IAaxeXXgcpSvpNNL9zL8j+czoo7zmbH2//E3lB9UOes3fQ1dZu/CVrzVlW8WGv3UvrVfw/qMQBfCkGHpsC2vcbENCQ5/OVofXwSkiSRmJjI5MmTOXvoUG4FbgYwD97SSorqK2UV7U+lCpQ123C1r9LGG3VMH+r7UBDtmqEE7KjtmjZwMMFaSaONPY02ShqsfFPayOKt1bS0B+ZNtt65xD8iNRY5xEqrhG/+3W1/W1TXxq56X8mujv8HHf822dx8W9rQs8kKR7xBEcTu2LEDRVH497//zdatW/nHP/7BM888w5133nmopyYIfcppaaLi208oX/k+LaXbDskcrDXlIRsOdFa7cRXly//HN3++lLUPXo3Hae+H2fWuPV+8zorbz6R8+f9o3bsLS9l2dn70LF/dcpJvFbWH9q56P3wAqaqUL/9fj8/vp9dDYaHv682bA+rCDjnuzAil0WTy5v888OCGDfu/Hjfu4Od3iNjdXtzdLGWlqtDq2n/1YXhKDAtHppGbaEKnkSIGsx2X7g/8QJefZO5WKkGw83bc3+72sqy4DrdXCRl4BlPSYA35QTPWoGX+8FR0Gt/5JPYH7kadhhMK09B3IxBX2isxhNLxOrWIPFuhBwZFOsFJJ53ESSed5P++oKCAoqIinn76aR5++OFDODNB6BuKx8XW1x6i9Kv/BlzGTxg2jqOvf5C4nOH9Mo+Wsh007vghusGqiqr6gqS6zd+y6fm7mXLD3/twdr2rYcd6Nr/kqxwREOwpCorqYt0jN7DgsaUYElK6fW57Y03YABLA0VTX7fMGNX26Ly/W4YDPP4ef/QyA5JGTyZxyAsHWlCVZgyExjYKTL91/sKUFvvrK93ViIgzvn5+5vtDTHE7tAbmaqTEGUof5yl2t3tPA3ubIH9Q6Lp13SDDpyE82hy1jFS0VX07vnkYbQxKiv8Rf1eqkqtVJdnzwpippsQZOHZPBF2WQl2RCo9V1SV+IVovDHbKzWWeVFgcJpuCb4QQhlEERxAbT0tJCcnL4Eh9OpxOnc3+nE4vFAoDb7cYdqXPNANExz8Ey3/5wJLwmG575I1U/fAmSBjrtkm6p2MPX/3cFs+9+DVNqlv94T18TVVVRPG40uuAVEUpXfAB6c8QALJh9675k5Ln7MCZndGs+Tbs2UbtxFV6Xg7jcEWTPWORreNBN3X1Ndi15Lexz9SiwZ8V7DD/l8m7PxZCSDWU7w76OhtTs3vmZvvDC/e1mH38cTjzRX2Zr/C/vpnrZCiRTLGqn+Ctl7AwmXvEnZFPc/jk8/7yv45zJBBdf7Gui4O3+z8Gh0GR3UVxvpcnmQpYkchJMJOqh2RFi/h3/Xzr9/zHrNZg0asj/J4l6mb0Rfi8SjFq8Hk+XfVJHZ8WiVb3sbrAd1Kpsh/IGC8MSDQxN0FPeFDmwloDimmbSTKE/kKnt/6+PyoxF196iONhzicTldge8rqHm4xkE78tHwntPd/XVaxLt+SR1ECavFRcXM2XKFB5++GGuuuqqkOPuvfde7rvvvi7H33jjDcyDOL9LEARBEAThcGWz2fjFL35BS0sL8fHxIccd0iD29ttv58EHHww7Zvv27YwePdr/fUVFBXPnzmXevHk839EbPIRgK7G5ubnU19eHfVEGErfbzdKlS1m4cKH/0/CR7nB/Tba98TBlK/7nXwkJRmMwcuKTq/ytNLvzmrSU7mDt369GcbkCVgYlWcaclsPMO15AH+fbxPLTi/dT8e2nPVqJRZIYe/7N5C+8MOJQVVFY89craCkrCvJYEpIsMfOOF0gsGO8/6nHaqFy7hKrvv8RrtxI7ZDi5x51F0nBf295Qr4nicSPJGqQDCvd/ccNcPI7wl3iTR0/lmNuejvh8gj2/7//xa+q3f98lv1iSNZhSs5h196voTNEXtQ9r6VI491zf13q9rwHCggXR/ZxUVcGpp8Lu3b7vr7oKBknaVrXFwerSxpC3ayQJb/tbXkCZK8WLuXIz9uwJqLKG8RlxjM6IXCmi0uJgTfvjHfhGmpdkYuqQxG61u/UoKttqLJQ02PzNCqIpx2XSyZw6JtM3D1Xl0x212N3hf2czY/XMLghd1q03/85uqGimJMSqs4Rv1fukUekH1Rq4Pxzu7z090VevicViITU1NWIQe0jTCW699VYuv/zysGMKCgr8X1dWVjJ//nyOPfZYnn322YjnNxgMGAxd2/XpdLpB9wM4GOfc1w7X18TdUgsuB1KYzVSKx4kGBY0uMKct0muiKgobn7oV1WYBRemyOcVetYeitx7h6Ot9Hy5zZ55ExYr/Rb0j+0DJw8ZE9f+odvM3tOzybSIK9liSrGHPxy8w/dYnALDW7OXb/7sMe0OV71K5qmIp+YmKFf+j4JTLGXfR7/331el0aCSV0qVvUfL5a9hq9yLJGjKnHE/hab8iqXAiACmFE6j76ZvQAbskkzZyUo9/5o655Z9sfvmv7F31fkCd2PRJxzHp6j9jjE8Ke/9uOeUUuPRS+Pe/wW6H006DO+6A228HQvycqCp88AFcdx3U1PiOjRoFf/kLDJLfs12NzWFr4XqBidm+N0SLw4NWI5Fg1NFitVNZCWOzEilMjw/b0aqzvBQdCWYjRbWt7Guxo6iQZNIxMi2W3ERTt4MyHTBlaCpHDVGwODxIwPYaC2XN4cub2b3gRcbYXtd2RHo8P1VZwt6nID0hqp/l3vg7Ozk3hUaH0qXEmQRoNRJzhqeh1w+sJi/hHK7vPQejt1+TaM91SIPYtLQ00tJCdw7prKKigvnz5zNlyhRefPFF5MOk/aEgHMiYlIEkSYS7RqI1xSLrutdPHaB++zpsNXtD3q4qXirWfMr4S25HH5dE2riZpIyZTkPRD778yGjJMjEZeSSPnhpxqNtqYdNzd4cdoypeqtd/xU//uZ9hJ17E94/dhKOptv1G1T8GoOTTl4jLGU727DMA3ya57x+9kfpt3/mXtHznW0b1+q+Y+pvHyJq2kOEnX0btxlUhZiAhazTkn3Be5OcegkZvZNJV9zPm/N/SsOMHVK+HxOETiUkf0uNzhvX441BfD+++68tl/b//g1dfhX/+E5Yt81Ub0OmgrAzWroWXXgqsRlBQAF98AbG9tDrcx1RVpbbNGXHVssnuZvawwFxQd6KByk0wJiMOna57b4uJJh0z8pKZ0c35hqOVZZLNvqDOFGVA7fQq+4PY1FiK663Y3d4ur4fUPufubAQ7WDqNzIIRaeyqt1Jc34bV5UWnkRmWbGZUeiwxUT5HQTjQoIgEKyoqmDdvHkOHDuXhhx+mrq6O6upqqqsPrnajIAxEQ+eeHaEUkoa843/eo0tvLaXbIcIHQNXrobVyT/tjycz43VNkHDW38wwAMKflYkzO7HJZXpI1aA1mpt70SMQ5Kl4Pa/72K+z1VVHNv2zZ2yz/w+m0Ve4J8xpJFC9+wV9CaM/St9oD2M7FiXyBrKqqrH/iNtxWC2kTjmX0eb/1P4fOz0fSaJjy63/0Skc1Q3wy2dNPJGfmKX0XwIIvQH3rLbj33v2du2rbA/+zzoLcXMjMhBkz4De/CQxgTzsNvv0Whg7tu/n1IqdHYcmOmqg2SXX+cOhVVFqdHuw9aEDQX6IJ8CTA1GkDqF4rs2BkGikxXVc3s+ONzC9MC9n5q69oNTJjMuI4bVwWF0wewjkTszl6SKIIYIWDMih+epYuXUpxcTHFxcUMGRL4R38Q7ksThLDih44k7/jzKFv2dpfbJFmDISGF4adeEXDc6/Y1/tj3zcfEpWWTMmZal+AS8FUhiOJ3pqNagaqq7Fn6BnVbvmmfgO/Svaw3MuLMq8matoCST1+m9Ku3cbU2ojGYyJ1zBsNP/SUxGbkRH6d6/TKad2+OOK5DdLm5KtbqUlwt9QCUffnf0M9ZVVE8Lvau/oiCRRcz8sxrSBk9lT1fvEbjzg1IspbMo+cx7MSLiM0eFvU8BwytFu65B84807cSu2RJ+PHTpsHvfgc//7m/osFAp6gqXxTVRN2tKi1Wj9ursLnKwu4Gqy/3VPFiBsqabHiR2dNow+FRiNFrKEyJYWiSuU+DPqfHS5vTi1aWiDdqAz785SWZ+LGiOeSPsAQMSTR1qd0ao9eycGQ6TTZfK1xJgow4Y8hOXYIwGA2Kn+bLL788Yu6sIBwuVFUla/qJNBStp62yJCAASx0/k6N+dR/GxP1pOKVfvsW2d5+Ek37HT/+5D8njxJSSxcQr7yVj0nEB506fNBde+kvYxzckpBKf59tMufuTF9n+1qOdJweA4nKw6bk/odEbGX3ebxh93m9QPC4kjW7/ZjNbGxVrPsVaXYrWFEv2jJOIyykIeKx93yz2rQx3J1UhSkr7xjhHc23YnF5Jkn0r1O1SRk8hZfSUXp/PIXXUUfDOO7BvH6xf78t7LSnxve4pKXD00TBnjm/cILO32R51AKuRJXITTHy5q44Wu7vLyu33e5uh0yq83e2l3uqiuMHK/OGpaDW9e/Gyvs3JmrLGgPnrNTKTcxIoSPF1xTJoNRyVlcDGypYu95fw1cCdmBV640uSWU+Sue/zTVVVxeVVkCUJXS+/ToIQyqAIYgXhSKEqChuf+xN7V77nu6TdKYA1JqVz1JX3Yk7N9h/b88XrbH7p/1C1gfmx9sZqvvv7dcy8/TnSJhzrPx6TPoTsYxZRue6LkIHj0Lln07p3F4bENIrefTLsfLe/9Qg5M09BkmVk7f43yr1ff8hPL9yL1+VE0vieR9H/Hif7mJOZfO0DaPS++TpbGvokgDUkpWNMii7fHkkKWSf3sJPRXrP3b38bNJu1ItlV1xbVOFmC44alUNJoCxrAhtNgdbGxsoWpufs336mqSnWrk9o2XwWc9FgDmXGGqNN8qiwOVuyu73Lc5VX4rrwJh8fL2AxfcDomIw69RuanqpaAxgFpsXqmDkki3njo/l96FZWiulZ21rVhd/vmlhqjZ2xGHDn9mHcrHJlEECsIA0jJklfYu/I9oOulc2dLA989fD3z/vYBkiThcdjY1nmVtDNVBQm2vPagf3yHSVf/H26rhbrN3yJpNKiKgiTJqIoXrTmOXR89y66PnkXSaAO6hQVjb6imqXgTySMn+4/VbFjJhqfvoCP/tPM5Kr/7HEnWMOVGXyevmPRcmot/6lkJr1AkiYKTLvHntSaPmkLT9rUhg2XV6yHj6Pm99/hCv4qmGxTAUVkJZMQZ+LassdsNBlRgd4OViVkJ6LUyFoebVSUNtDo9/lX+bTWtxBm0HFeQEjGoVFWVr/c0hB2zqdLC8JQYDO25rsNTYxiWYqbB6sKtqJi0MvVWF+v3NeNRVJLMOgpTYvpl1bWDV1FZVVJPdasz4Hi91cWqkgaOzklgVHrkUmWC0FNizV8QBghV8VL8yYthb2/du5OG7d8DUPPjcrzh6pqqKq17d9JaURxwWGuM4Zjbn2fWn15h6NxzyJq2kKQRkwDw2PavakUKYDusffAqtr35MI72HNTt7/yLkJUtVYWKbz+mraoUgKHzzundABbQxyZScPJl/u+Hn3p5yABWkjXE5Y4gfeLsXp2D0H9i9JrIg4Bksx6PouKMMug9kKJCo92Fy6Pw1a462py+34/O2wXbnB6+2lUX8TF21VvxKpFD6d311oDvZUkiLdZArF7Dit31/LCvmZo2Jw02F7vrrSwpqmVLdfjSWr1pd4O1SwDb2Y8VLf7XSRD6gghiBWGAsNbuw9lRNioESdZQv3Ut0H4pXor8K+xs7nrJUpIkUsZM46hf3ce4i35P484f22/p/kZJj93K7k9eYuUdZ9NQ9COW0m3h7yBJVH2/FICUMdPInnkKwavD9oyrtYmmnft32qeNO4aJV97n2+gmySBJ/lXamKx8jvn9s0E3wQmDw9gomhLoZIm0WD0aWTqonzQJX+Dm8ChBf1NUfCvDJQ3WILfutzXKQLPR3rX1pqKqLN9d3yVQ7pjP5ioLe5vDN+3oLTsjpHJIEPG1EISDIdIJBGGgCNPcwE+SUNvHGZMzorqPMSkj7O3lK99vr0vb80ofquLFZWlk43N/imK05F/xlSSJo69/kNisfEo+ewWPvf1N8SA2e0myhn2rPyRhxP4Uh/wTziNj8lzKV/yP1r3FaAxGMqecQMbR85A14s/gYJYeayA9Rk+t1RVyzNTcJCRJ8u/k39ds7/bHNY0kkWzWs6Gi6warA5U22RgTIrhusbujToHQB9kgta/Zji3CRrZtNa3kJkZurW51eXB6FEw6DSZddCvaHVTVV54s7Big2dE1EBeE3iL+egvCAGFOG4I+LhlXa+i2marXQ8oo3875jMnz0Bhj8DpCr3TEZAwlNis/7ONaa8p7sP4aZG6KF2tlSTQDielUrkrWaBl97k2MOP0qmku2+hsb7PnijahTGg6ch9PS1OW4KTmDUWff0O3zCQObJEnMH5HGmtJGypvtAbdpZYmpuUnkJ+8P6MZmxLGvxd7tiw7DU2PQaWRc3sgBqDvMmJZuBHVDk4xsqbbQZHOjkSE73kRNqyNiK9pGmxu3VwlZJaCuzcnGyhbqOwX+WfFGJmcnkGCKfpOYLPnSLELpqJ4gCH1FBLGCMEDIWh3DFl1E0btPBK1rKskaTGnZpE2YBYDX5UBrNIcNYq015az603kc84fnMIRoa6ozxyEh9UogG63MKcd3OabRG/2lrVr37epxrqwkawIqOAiHP1mSmDUshRlepb3Gq5cUk56sBGOXagHJZj3HFaTybWkDbq8aUA5XI/la0x4o3qBlQqavUkCCUYfN1bUTVgcJwm7sirZMl0EjsaK4wf84ElDWZEcrR/e76sv/9aCRpYBV1iqLg5W767uco8rioK7NybzhqdRZneyq8aU8fLClivzUOEanxwXUmJUkidxEE+VNoVe1VejXzmDCkUckggnCADLi9KvIOHqe75vOeZqSjC4mnhm3PuXP3yx69wlfXmwElrIdrHv0hpDpAjkzT47YISzn2FOZcEX41rDdUb9lTdjbs485JaBrVneoipeh887p0X2FwU2rkRmRFsuErASyE00hy11lxxs5c3w2x+QlMSotltHpvta6cwpSCbZwaHF6WFVSj0dRKUyNCRtEqkBhakzI29NjDVGtTjq9asDjdHztiWJDmE6W+HhbNYu3VfPBlio+31HDvhY7iqryXXlTyPl7FJXlxXVsqrRgc3v9x3bXW1myo4aGA1I2xoSpPCABcQYtQxJFECv0HRHECsIAImt1TL/5cabc+DApo6ZgSEglJiufUefcwPyHFhM3pBDwrcKWLXsnqpxYVfHStHMDTcWbgt6ePGoKqeOOCd6OVpKRZA2Fp1/FkFk/Q+6VeqoSe1d/FHaEIT6J0ef9pkdnH3r8z0nIH9Oj+3aXo6mWovee4od/3cKGf/+R6vXLe73agtA3tLLEsOQYJuckMq59lfW78qaQnbHqrC62VFnIjjeSlxQ6MBuaZCIn3hj2cSNtRoszaA9qA5pbUQOC3Ua7m69LGvhxXzN2d/ifT2+Q56/iK6e1ek8DSqcXKMmsZ05Bij8ol9i/RTPeqGV+YSryIOn8JgxOIp1AEAaYjpXPnGNPDTnG3lCF4g5d2qbLOTUaatYvJ7m9lFbAbZLE9FueYP1Tv6dm/TKQZV/dWK8HQ3wSU379KAlDRwEw7MSL2P3pS1G1rg1NxWUJnffbofBnV6I1xlD0vyfC5gl30BpjKTz9SkacfvVBzC16pV+9zeYX7/O/FJIksXfle8TljmDm7c9jTErvl3kI0bG7vRTXt1HWZMftVUgw6hiRFhNwudvu9gZ07DpQcX0bE7LiOSYvGbPOws66Vn/Qp5MlxmTEMSYjLmLDg7EZcbi9Cttr2wKCVRUYmRrDrnprn6T37KrveaUAFbC5vVRbHGR3es1yEkycOT6L0iYbTTY3sgTZCSayutH4QRB6SgSxgjAIybrQKz3BSXjDBL1aUwwzbn2S1ordVP+4HMXlJH7oSDImz0PW7s/vG3P+zViry6le/1XPJk57zmp6buRxksSwhReSN/9cGorW47G1YUzOoGnXRkq/+i/2+ip0MfGkjptB9vRFpE2c1W+dt2o3fc1PL9wTcKwjmG2rKGHtQ9cw9y/vitJdA0ST3cWyXXW4O12id7Y5qWlzkptoYlqOb2U00oYpt6LS5vJQbXGwvbY1IAB1KyolDVbyk83E6Pe/taqqSk2bk+J6K812N1pZYmiiiTEZcYxIi6W00Ybd7UWWJBRVxRom3/ZQk/Ct6mYfkOeq08iMSI09NJMSjmgiiBWEQciUHL5s1oFUryeqS+xxOcOJyxke8nZZqyNpxCSqf1zW49VYVfGSF0XOqqp4qduyFmtVKVpzLBmT56GPTSBp+AQKTrqky3hHUy0N5Tvb53gUSD3LqY3Gzg//HbIMmKp4sZTtoH7r2oCWv8Khoagqq3Y3BASwsD9Y3dtsJ1Ef/YeNujYnP7aX2TrwN8Dq8rKiuJ6Tx2Qgt5etW7+vmV311oAAucnuZnttGyeMSGNcZjzba1rZWNkSMYg+WL1xfpEeIAwkIogVhEFIkmWMSek4IjRH8A2W0JpiyZ6xqFceu2LNJweRTiCRc+wppIydHnZU3ZY1bHjmThyN1SBJoKrIWj3DT7mc0ef9OmDTl6O5js0v/pmqH77y5whrTbHkn3oFaHJ6OM/QPHYrjTvWhx0jabRU/7hcBLEDQGWLw79JKZTihraoArwYvYY9jaEbCaj4NoFVWRzkJJgoabD5L+EfeG63V2F5cR15SSaK6oKP6QsaKXjeazRUCJvvKwj9TVzrEoRBasSZ10QeJPs2Zk254e9o9L3z5tO5NW13aM1xjDz7eiZf97ewuXKNOzew9sGrcTTV+A60B8yKx8Wuj55l6xsP+8e62ppZfc8vqF6/LGCTm8fexq4Pnu3RPCPxukMX1e9McUWfsyz0nTqrM+ImKbvb97OTbNKFHTsyLTagtmowElBpcaCqKttrW0OO6+ju1RHA9odIlRPCkYDMOEO36sgKQl8TK7GCMEjlzf85NT+upHbTqtCDFAUVhfWP38rQ+edSeNqv0Oj0aAymgFxXVVVp2rWRvV9/iLO5HmNyOrnHnUXS8AldThmbMxx7Q1XYXfgag5mEYWPInn4isTnD0RrMJOSPRaM3RHxe29/+p68rWYjV3pLPXmH4KZdjSs6g5NOXsTdUoobp7tVStoPUwq7Po6f0sQkYElJxtnRt59tB9XqJzxvVa48p9I9j85P5uqyZFsf+JhsdK7Sj0mIZlmSOqmOXoqi4vErEjla9LSPWQG2bM+iKrgSkxuqZmJVAk91NbVvwYDzZpKPR7vYH8x3PP9msZ1Z+St9MXBB6SASxgjBIyVod0299gj1fvM7uL/9LR6+i+LzRWMp3+r5pX530OKyUfPYKJUteab80ryN75qmMPONqzOk5rH/iNqrWfYEka1AVL5KsoXTpm+TM+hmTr30goDVr/oLzqd24Muzcpv76UTImz+32c3I019Gw7buI4yrXfMbwUy+nbPk7YQNYgH1ff9SrQawkywxbdBE73nk8RIkzCY3ewJDZp/faYwo9lxFnZEdt+KsHZr0vPcWo07BoVAb7WuyUN9lweVXijVqGp8SQbNajqipmnSZseoKKL1Wg0uLolflL+DpjRZMCYHV5yIozUGt14VFUZF8mDiq++rSzh6Wg1cjMG57G1moLu+rbcLWfOEavYWxGHMNTYrA4POyqbaFiH+QmmhiWGkdWfNfGEcG02N1UtTpQVUiN0ZMaoxdVCoQ+I4JYQRjEZK2O4adcTu6CX/DZZ5+x8IkVrLrtFEANspKp+pPuFI+bim8WU/X9F2RMOo6q75f6RrSvrnb8W/HtJ5iSMxl74a3+s2RMnseQ2aexb/XioHMaMvs00icd16Pn42prjjhGkmWcrY2oihJVswd/WkIvGn7KFdT99A0NResDXmdfrq7K0Tc8hM4cvhao0D+y4gzEGbS0OT0hc05Hpsays71jskaWyEsyk5dk7jJOkiRGpsWysTL8auzeFgd7W3oniFUBvVb2pzyE0+by0uby/e5q2uPGjntZnG6KG9oYnR6HRpaYmJ3AuMx4rC4PsiQRo9f4g80Ek46jshOo2AjThyah00VOIXB6vHxb2kh1qy+NpmMFN8GoZfawlLBdzAShp0ROrCAcBjrefBq2rsXV2hTVxitV8eJ1OahcuyT0eFWl5PPX8Nj35+1JksTkax9g3EV/wJi0v0qCMTmDcRf9gcnXPtDjlRdjYhpI4f8sqYoXU0oWSBKSJvLncH2IdrsHQ6M3cMwdLzD2wt9ham9xK8kaMqYcz+x73yRr2sJef0yhZyRJYm5BCkZd4M9Vx0/o8BQzw1O6BqyhjEqPJTWmf0q5Aeg0EoU9KF/lVQNXb+1uhU2VFr4u2d+wQCNLxBt1xBq0B7Va6lVUlhXXU9O6Pw+846EtDg9f7qqL2GRBEHpCrMQKwmGktbIESaNF9UaZixfhUjyA4nLQsON7MibP8x+TZA3DT72cgpMvwVZfhdtmoX7zWuq2rqVuy7ekjJ7K0HnnYEjoXg6dPjaRrKknUL1+WcicW1mjI2fmKVSt+yKq55lzzCndmkNnqqrSsG0dFWs+xW21YM7IZejcs4nNykej01P4s19S+LNf4nU5kbXaHrfKFfpWnFHHKWMyKW20UdZkw+1ViDfqGJEaQ3qsAY8n+txVWZKI02s4iL4B3TIrP4Vks57i+jYcbuWgKxhUWhyUNtooSOnZBq9g9rXYaba7g96mAi6Pwq76NiZmJfTaYwoCiCBWEA4rGr3JtymqlzWXbA0IYjtIsgZHQxXf/f06PE6bf0W39qdvKHrvKab99p/dzo0dc8HN1G1Zg9dpDxrIjv3F79DHJrDn89d8q7YRnm/SyMldjqmqGnHlyW1rY+3frqKpeKP/cSRZQ/FHzzHyrOsYde5N/nNEs2FNOLT0GpmRabGMTDu4ovy1bU5Km+yRB/aCOL2GrPaSVgtGpLN6TwNN7ZuuDiaY3VXf1qtBbGmYsmPgm+ueBpsIYoVeJ9IJBOEwkjH5uKhWV7urNMQGKkdTLWsfugaP0x6YkqAqKG4n6/5xE21Vpd16rNisYcy5/y1SxkwLOG5MyWTSNX/1Nzpo3rM1YgAL+1MtnC0NbHvrUZZccyyLLxrLZ1fPZNubD+MIUmXAWlPOV7ec5Atg25+P7x9fUL3z/acpX/5Ot56XMPi5vQqrdtf3W0etIYm+zlhtTg+tTg9ThySyYEQqR2UnoDmIy/8WR+9WTXB6Iv8eury9/3dJEMRKrCAcRmIyhpI9YxGV331Bb5ZOdzbW0LD9e1LHzQg4XvrV23hdzpDBpOrxULLkVSZe8ScAvC4HbqsFXUx82Lq1cTnDOfaPL2Kt2Yu1thydKZbEgvEBl+tlrQ6vM9yK2P43eVt9Javv+QXOljp/MO5ua2b3Jy9RvuI9hp96BcakdNLGz8TrcrLyj+fisYWu8Qmw84N/M3TeuUFbyypeD5VrPqP0q7ewVpehi0lgyOzTyDv+fAx9kKMr9I/SJhtupf+awqbE6Fm2q46atv25piadholZ8eQkGNnbbO/Rb7lW7t1qAbEGDY228H9xYvQi1UbofSKIFYTDzKRrH8BWV0lzyeYoRkskj5pMY9GPEUdaa8q6BLE1G1ZEWA1VKV/xLsMWXcyuD56hYs2nqF4PkkZLzsxTGHn29cRm5oW8d0xGLjEZuUFvy5xyPPtWLw5br7bDxn//EUdzXZe5qooXV2sT2996FGjvhJacicceuaGDvb6S1srdxA8ZEXDc63ax7pHrqfvpG38agrOlgR3vPM6ez19n1t2vEpuVH/H8wsCiqio7I5Tq6m2r9zR2OWZ3e/muvImRaTE9CmAlYGiQygsHozAllrIIKRYjerA5TRAiEekEgnCY0RpMzPj9M1FtMkqfNIdR59wU3XmDlIxSouhepbidrLzzbCq+/cS/EUv1eqj49hNW3nkOpcveZvt/H2P7W/+gZuOqiHVfOxScfJnvi2CXVWUZfZwv/85aU0791rVRpR6oioK9vjLqtrqKq+vz3/neU9RtXtNxws4nx9XaxLpHb0Ttcdte4VDZVtOKpZ+bF4RTXG/lqOz4bt9PliVGHWRe8IHSYvXkJZmC3iYByWZdr+bgCkIHsRIrCH3IVldB2Vdv07hrI7JGQ/qk48g97iz0sX2zwWHP569jq9qN1mgmbeIsan9aHSJHViJ13AyO+f2/URUvhqR0nE21Ic+r0RvJOKpr7dekkZNo3bcr4rwUV9eamarixeuw8tPz9/hLZakfPYs5PZfpv3uyywrngRLyRjP1N/9g/eO/Q/G6fdcyJQlUBX1sEtNufZLVm4vZu/qjiPPrCVmnJ+aAVWSvy8meL14PnV6heGmr2E3Dju9JHTO9T+Yl9D6PV2FbTfj0kgMZtDLjMuLQa2TsHi/balpxR9OxIEqKClpZZtGodLZWW6hocYTs1AW+Xw+DRmZOQQqxht5965ckiWPykok3tlJU2+pvoKCRfKu+qTF6SptsJJl0JJv7rzyZcPgTQawgdEPznq1Url2C29ZKbFY+Q2afETLHce/XH7Lx33cC+FcX67aupejdJ5l5x/MkFR7Va/Pat/ojQMv2d/6J7HWD5Gt9qjXG4HFYQZZ9wWz75e2E/DFM/c1jgK/CwJif/5qNz94V8vwjzrgaranrSsqwhb+gfNnBb3DqXCrLXl/Jt3++jPl//xhDfHLY+2VNW8jCx5dRvvI9mnb/hCxrST9qNtkzT0GVtbC5mIatkTuAdZskkTvnTHTmwBWttqo9EVMRJFlDY9GPIogdRGranHiizIUdnR5LVryR9FgDcqerBBmxRpYV1+FV1F7JVpcksLk8JKfFMqcgFUVVqWhxUGmxoyiQZNJi1mupt7pwehVidBpyE00k9VEQKUsS4zPjGZMeR7PdjVdR2NNo8//XIcmkY2ZeMgmm/m1+oKoqdVYXNpcXo07u8v9HGJxEECsIUfA4bKx//FZqNqzwXaaXJFTFy7Y3H2HC5XeRf8L5AeObin9iwzN3dL0srap4nDbW/O0qFjy2tFdWZGs2ruKnF/8M59wHqhqQI+px2NCYYpE1WlTFS0zGUAoWXUz2zFPQ6Pa/mQ2ddw4eu5Vtbz2C4nHvbz8ryRSe/itGnHlt0MdOyBuNPj4Zl6Vr7l5PqYoXV1sLZcveZmSIx+3MkJDCiNOv6nLc7fbVrbQ1VvXa3DqYM4Yy5oJbut4Q9ZuiePMcTKJdQR2SYGRyTmLQ21Ji9Jw8OoOiujbKmmx4vAqxBi1ur4Itim5cXahg0Hba6ChJ5CaayE3cf1m/weqiqK6Neqsv7WVrTSuJJh2TsxPIjA+9sfJgaGSJZLOO1Xsa2Beka1mz3c2Xu2o5aXQGMfr+CUEqW+z8sK8Zq2v/30ajVmZyTiL5yb2bHyz0LxHECkIUfnzqD9RsWgUQECSqXg8/vXAvhvgUsqYt8B8v+exlJElGVYNsOlIUPPY29n79AcM78jq7yVpTTtmyt2kq/omWsh2EDopUvPY2vPhWAFv2bKWlbDtD5pzRZWTByZeSe9yZVKxdgqOhCkNCKtnHnBSxYcHwU6/wbYzqzTxPVWHfNx9HFcQCuFqbcFktGBNTcTTVse+bj3G0NkHyRGS5d1d8EgomcOydLwRtKxuXXONVtgAAU1FJREFUXYA+LsnXNS0EVfF22SAnDGzxxujeKsdnhc9RjTVomTIkkSlDEv3HftjbRHG9tdursyqEzEMFXwD75a5aDlxAbra7Wb67nuMKUshJCH3/g9FgcwUNYME3b7dXZXtNK1Nz+75SR6XFwcqSru2pHR6FNWWNqKrKMJGvO2iJIFYQImjdV0z1D1+GHiBJFL33VEAQW7Pp6/C75lWV2o2rehTEli1/h03P34vUvhoMgDZysf2OsSWfvYI5NYeCky/tMkYXE0/+Ced1az75x59H6Zdv4Wio7vKcJVn2bWLqQYAbqcQVQOOujRT97wnqNn/T/oCS77EkGfQmOHMizpb6Hq17ak2xeOxtvlVpVUGSZPJPvIhxF92GHKLdrazVUXDypex4+18EKzgkyRoSho3t1VQSoe8lm/UkmnS02N0h806TTDqSTN2/VD8iNZZdPWj/NTI1BnOYlcwf9jaF/bX7fm8TWfHGPrmkXtpoC9uQQQX2NNqYMiTxoNrdRqKqKj/uaw47ZkNFC0OTzGh6ueyY0D9EECsIEVT98KX/8npQqoqlbDv2hipMKVm+Q97IZZ+UaFvDdtKwYz2bnrsHUA9q4XPnR8+Sf+IvQgZj3aExGJl118tseOYOGrZ/3+kWiYwpJxCblU/xR89176SSjKTRsO4fN6Ezx5NzzMmkTTg2oCZr3eZvWfvQNQdUAGh/UVQl+ta7XR5bIvuYk5l87V+p2bDSV+fVHEfm1BMwJqZFvPuI06/CsncXlWs+3f9z0x5cm9JymPbbf/XpG7fQN44ZmsSXu7rmtEr4LqFPz+vZqmKCScfknAQ2VLQEBH7hgsBRabFMygmditRid9MYog1sB7tboabV6e8I1sGjKDRa3bg84e8fjsMTuT2uR1FRVN/mr77SaHfTGqGihNOrUN3q6LNVaaFviSBWECLwOGxR5Tp6HJ02LxROpGH796EDX1kmeUTXdqiR7P7kRd/qZhS1UcNxtTSw4Zk7mXT1/wXkxkZLVRTKlv+PkiWv0FaxG5BIGz+TiVfdj6SqSLKG1HHHYE7LQVUUFLeLks9eIeoGDKqCvaEGe301kiyzd+V7JI2YxIzbnkEfm4Di9fDj03/wvQ7djeYl2RchKApSe65wxzk0BhMFiy5h1M9vQtZoyZ5+YpCpefHYrWgMJmRt11QFSdYw5caHGXrcWZQte5u2qlL0sQnkzDqNIbN+htYocvAGG1VVMeo0zB2eQlFtm78SgATkJpqYkBVPvLHnaSuj0+NINOrYXttKTasTFdDIEKoRVoMtfGm7Nld0H+CsncYpqsrmKgs769p8m9gUL2ZgXXkj0/LS0Gujr8hp1mkitsbVaST6evHT4Y7u76Q9ynHCwCOCWEGIIC5neMRVPVln8K/CAhScdImvNmkIEpB3/M+7PZfan1YfdADboeLbj3FbLcz43VNBu06FoioK65/8HZVrPqNzAZ/6bd9Rt+VbJlxxN8OO35+SIMky4y+5nWGLLmbFH06P0GUr4IHa//E93+bdm1n/+K3MvON5ajd9jbO5a7vYSPIXXYyrpR5Jkkkdfww5M0/FbWvFUrYdSasjecTkkEGm09LIro+eo3z5O3jsVn/DhhFnXE1czvCAsZIkkX7UbNKPmt3tOQoDh6Kq7Kxro6i2DVt7oBNn0HJ0TgJZ8UaMOg06Te+UW8+MN5IZb0RVVUoarKzb2xxybL3VRXmTPeSmJEOUAae+fe6qqrKmtJHy5q6/m3ubHbS4alk4Mj3q5zosxUxRXegqHRJQmBLT51ckjLrouoSZohwnDDwiiBWECLJnLGLzS/+Hx24lVJ5j7nFnBgQ/GUfPp+CUyyn59KWAVARffqXKpGsfwJyW0+259FYA6zuZSu3GldT+tJqMSV1rwIayb/VH7QEsdH49Oua2+cX7sdbspfC0X2JMSPXfHpM+BGNyBtaq0p5NV/FSt/kbLOU7aasqbV+R7t6u7vQJx5J59PyAY1qjGVNyRtj7OZpq+fruC3A01fqfZ0fDhqp1Szn2rpdIKpzYvSckDGiqqrKmrJHyAzpRtTo9rK9oYaTTw5ROG5M8XoXdDVaKG6zYXF4MWpmClBhGpMYEVBGIRJIkSjqVpAo6BihpsIYMYlPMesw6jT/wDkYrS2Qn+FIJatucQQNY8P2Gtzg87G6wMjq962bGYJJMegpTYihu6JrrK+ELLqM918FINumIM2jDphQYNDKZcX1TqUHoe6JjlyBEoNEbOfr6B5FkyVdvtRNJ1mBOy2H0z38TeFySGHfR75l+61OkjJmGxmBGa44je+YpHPfn/5I7+/Ruz8NttRA/dFSXORwMSdZQvvx/3bpPyeev+S7Jhxvz6YssvXE+lWuXBBwfMutnEe8byco/nkPJZy93O4AFuqyYRmvLKw8EBLAdVMWL1+1k/RO/69F8hIFrX4ujSwDb2c56K7VtTgBcHoXPdtTwY0ULFocHj6JidXnZXGXhsx01tHWz05fNFf7DqkpgKsCBJEkKmzMLMD4zHm3735KSBmvEzY/F3dx8NiU3kQmZ8egOyBnIijdy4si0qFdJD4YkSRzdqRJEMJOHJIhNXYOYWIkVhChkTjmeY//0Kjvff5q6n74BVDRGM3nzzmHkWdehj+u6qUOSJDKnzCdzyvyuJ+yG+m3rKHrvKRq2RS7aL2m0zLrrP2x5+a+07NkacbyqeLHVV3ZrPpa9O6Nr4er1sv6JWzFn5JI4bBwA+SdcwJ7PX8dttXRdVe5oyBDxvB4cjTXdmrMka0gZM42YjKHduh+As6WBqu+/CB2kqgq22r3Ub/uOtPEzu31+YWDaVdcWNq9TAnbVt5Eea2B5cR1tIQJPu1thTWkjC0elR/3YJp0cdhXVNyZ8EJibaGJcZhw7atrwqqr/uWgkGJ+VwOj0/Y062lzeiNnqkQLrA8mSxPiseEZnxFFvdeJVVBJNuj6rDev2Kjg9CgatHJD2kB1vZG5BiqgTe5gSQawgRCll1NHMvP053LY2PA4rhvgkZG3ftlCsWPsZ6x+/NWLumCRrUIFJV93Pjv8+hqVsR3QPIMsYE1Mjj+t8F60eb1Q7l1VUVaLof08w47anAV9jgll/eoV1j9yAtabc1262vUFDXPZwrDXlKG5nt+YTiSRr0BqNTPzlPT26f2vl7sirrJKMZe9OEcQeRlocwctpdVDx1WKttjgiVgKot7losrmi7pZVkBJDg6054hhVVXF7VWQJtJ0Ct931VjZXWwI2LMUZtQxPiWF4SkyX3FajVo64ESvaPNsDaWWpTy/XWxxuNldZ2Nts989/SIKRiVkJ/q5g2QkmTos3io5dhyERxApCN+nMsV3ajfYFj93Kxn//EVRQQ6x8ShotWoOJtKkLqQAMCWkHlLmKQFHInXNmt+aVNfUEKr79JLr8XFWhZsMKvrn/EiZd81diMnKJG1LI8Y98Rt3mb2nc+SNIMmnjZpA8eipbXvkrpUvf6PaleUmWQQpetSHn2FMYc9a1PcpBBtDooyi9o6po9CKv7nCi1UgQIQvA6vKyYnd0GwwbuhHE5if7Nka1OjxdAksJiDdosbm8fLi1Cnt7t6+0GD1jM+Npsrn4qcrS5ZytDg/ba1oZmmjqEsQOS44J2Zyg4zELUgbeimWz3c3SnbVdyp5VtDioanVywog0Utpfc0mSSI+NXE9bGFxEECsIA9S+bz/B63QQbn1E1uk58enVKEhUfPopNT8u85WNiqJGqiTLJAwbR+bUE7o1r+GnXE7Ft58QvpJloMadG1h974XM/et7GJPSkWQ56O790T//DQ07fsBSHl3KQof8Ey9CkmTM6UMYcuypyDoD9pZGlq1dz8Qr7kan63n5o4T8MRgS03A214UeJElkTJrb48cQBp68RDPbaloj/oRHW+BNkiS8isq+FjttTg96rUxugilobqhWllkwIo21ZU1UWgKDy6x4A26vyubqwEC13upiZZiAWgWcHoUt1a1MHxqY/pSdYCQ1Rk+D1RU0aDZoZUak9v0H9+5aV97UJYAF33NVFJXvyho5eXSGqMt8GBMbuwRhgGqrKEbShM978zpsAcGVxxG8gkIwmVMXMPOOF4LWOg0nIX8MU3/zGHI36suqihdXazO7P30p7DidOZbZ97zG6J//GmOEigGdDVv4C8ZfcjsFiy5GH5eE1mgOen+Pw8a+1YspXvwCe1d/1P56hSdrtIw885rQAySZ3DlnYErJjHq+wsBXmBaLViP1qNtbMF6vwvtbKvm2tJHNVRZ+2NvMB1uq2FjR7Otq105VVapbHf7mB8OSzYzPjGN6biInFKaRYjZQZ+1aJzaa33pfpywr3gN60cqSxLzhqUEL/ieatCwcmd4vG7G6o8XupsHWNeju0FFVodHW86YNwsAnVmIF4RCw1pRTsuQ1Ktd+itfpIG7IcPIX/oIhs36GJPveLDQGc1SF/DWG/W88MRn5qAc2Sz9wvN7EvAc/6NEmp7aqUvau+gB7QxW5c89CcbvYu/K9qO6rKl7Kl79LwcmX4XXaMaVkBr0ErzXGMPLMaxh55jXUbv6WtQ9cGfHcXlfkPNo9S99k25sP43XY/GXPftIbGXP+zUFb8HaWv/AXOJrr2PXBswE1dVXFS+bU43ucbysMXGadhuML01i5ux5HqK4DUTJoZdZXtPi/Vzv9u73WV091Uk4ibq/C1yUN1LQ5u1zn6OiofLAU1bcia9YHBqU6jcycghTanB6qWx143B6K9sEJI9LR6QZeqGCJsuKDxeEmJaZv9y4Ih87A+8kUhAHI3lhD1Xef47JaiEkfQtb0E3vcealhx3rW/u1XKB63P4ezafcWmopvp+r7pb5VTo2WrOkL2fXhv0OfSJZJLpyEIT4Zt9u32jBk1qnsfOcfqN4Qb7qyTMHJl3Y7gFVVlW1vPMzuT/7jD7LBF8QlFIynpaSjEkL4d1m3zcLSG+cBviA9b/45jDr3JnTm4DUjtYZoXmOJhu3rSMgbFXJE+Yp32fzi/QHzBvC6HGx59QFknZ78BReEfgRJYsx5v2Xo3HPYu+p9bPWV6GMTGTLrZyQWjI9ijsJglGzWc8b4LPY12/m2tDHq1IED6WSJcB+zdtS2MTo9jvX7mv1lu7pcIu+FANY/nwN6vXoVlfJmG7sbrNhdXkw6DXkJvZM/and7KW200er0oNNIDE0y+/NUD4Y2yrJYWo2MoqrUtTlxeRVi9FqSTDqRYnCYEEGsIISheD1sfe1B9nzxBuBrp6p6Pfz00p+Z+Mt7ul3v1etysu7RG/G6XYE5n+1fV/+wjJIlr1J46hUkDhtH+lFzqN38TfDSU4rKyLOuCzikj09m4hV/YtPz93RZupFkmdicQgpP+1W35gy+dre7P/lP+1QDN0+17NlK5pT5tJQVYa+viPqcXqeNPV+8Qd3WtRx718s4W+pBVYnNyu9U9SGKd25JCrnxDUDxuNn21j/CnmL7248xdN7ZEatNxGTkMvrnv448J+GwIUu+wGtDRUvEslcHkoDJOQn82GkVNhgVXx3WUA0HeosEpMbocXgU/+Yut1dheXEdDZ0uu7e5vNS12jEDLq9CT1PKd9a18eO+Zn+LXvAF7NnxRmblJwdUVOiu9FgDOo2E2xv6b4RGlnB6vHy4pSpgNT3BqGVqbpLY6HUYEEGsIISx9fW/s+fz1+kIpjo2THkdNjY89Qd0prhu1YGt/G4J7rbmMCNUSj57heEnX4Yky0y56VF++Odvqdv8jW8FVJJQFS+yRsdRv7ovaFvT3OPOpGbj11Sv/yrguCltCNNvfjygsoLicVP9w1fs/fpDnJYGzGlDGDrvHNImHOtfqVA8LnZ99GyYKavUbFjJ9Nue4bsHr4r6tQBfQNy6r5ilNx2P4vJtYNHFxDNs0cWMPPNa4nNHIuuN/ttCnITkkUejqipNuzZSvuJdrLX70CWkwdDZNBStx2VpCDsPd1sLtZtWkznl+G7NXzgyKKpKNB+oClLMOD0KquoLFgtSYsI2JeggAY22rnmuvU0F6qwuPt5WTbJJx6ScBHY3WMPmjf64r5k5hZHz05vtbnbUtlLRYkdRfXVsO3fK6vzqVVkcrC1rYnZBSo+fi0aWGJcRz8bK0B8QMmINfB+kfW+Lw8Oy4jpOKEwjTQSyg5oIYgUhBEdTLaVfvEbINy9JYvvb/yDj6HlRXZryupyURdEdy9FYjdPSgDExDZ05lpl3PE/T7s1UrfsCj8NKbHYBQ2adhj62a0ceVVX54fFbqP7hqy632Wr3sfahqznu/95BZ47DbbWw5m+/onn3Zn+jgZY926hc+xmZ0xYw9aZHkbU6mnZtwt0WYSVJ8eJsqSfn2FOpWPNp9659qmpAkOq2Wtj5/tO07NnG9FufIG/+ub6V8CCrrZKsIT5/DInDxrLx339k76r3/fmuqt4EQ2ez7bWHoprG+iduY+SZ11B42pUBKROCUNHiwOYOnxer00hMy03qUe1Rla6X+Ptao93NsuLI5cH2tTiwubxdcmg7q2ix83WJ74Nix29+uFavKrC3xY7F4Sbe2PPKIaPTY3F7FbbWtCKx/+KTCoxMi6GkIXT7XlWFDRXNnDgq+g2kwsAjqhMIQghV3y8N2DXcharSuncX1urSiOfyOO2s+esvadzxQ1SPLcmBny+Thk9g7IW3MvGKu3078IMEsAD129cFDWB981WwVpdTuvRNADb8+05a9mzz3daertCRKlD9w1fseOdfQHSbpgAUl4PJ1z7A8FOvQNYd5OqGqlKzYQWV675gzAW3kDxqsu945wBBkjAmpTHtN4/9f3t3Hh9VeT1+/HPv7JnJZF9JQkJYwr6DLAooIIhWtGqtGyLF0mLVYqvUVpAKUhewdcXqr2hdKmq/QrXaiqhsYpEdZBUIayAh+55Z7u+PIYGQzJIQMhk479cLTWbunTnzZDI588x5zsO+ZX/lyKqP6j2G2sdUnhdYiYOruoJdS55jy2uzfP/cxSVn/6kyv8c4XBruRhZVWgw6kuxmn10ODDqF9GjreUTonUl//snxqXLvrwHVThdrDuYT2Fz1GQpw9DzLJxRFoVdyBNd3T6JXcgQdY230TLLzo+6JxFpNOP0scs2vcFBSJd0LQpkksUJ44agoRVH8/4o4ykv9HrPnwxcp2LfF/50qCuGpnTGGR/o/1sv9+KaRvWIJ5ScPc2LDl943LNA09n/6BuV5xwlPyYQAGg2Fp3ZG1RvofttvGfvSKrrf8QiRmT2b/BjqqCrZy99Db7Iw9NG/0efeeURl9sRoj8bWLpOut85gxPylmCLjfLfuqp3BDXCG7MjK/6Ngz6bmxy0uOoGuhD+3p2utfu0i0Kve23UNTI0iMdyE3aRvsZZetaqd5/+GzNctHMivwE+u2DgFv0lmoMKMOrolhNM/JZLuiXasRj2VDldAY1nZxDpn0bZIOYEQXljjU/3vSqUoWOKSfR7iqqni0IolgTXv1zQ6/Whqs1fOlh7b7/eYqoKT5O34Fn/zJprLyZpZtzLyTx+R0HcEuVtXNz4eqootMZ3ozp7Z0uPf/oed7y2kIvdIcx7CGW533Sy3qjeSNvJG0kbe2OCwgn1bcJQ33KGoAUUBFL8/B0XVcfjrD4nJ6t+MoMWFVrthQHZBBTUuNzajjsxYG3FW4wVbcW7UKfjvKOxZBNUYu9nA2C7xbDpWTM5ZiW6EWU/v5Ii6/qzDMmL4Yl8uTlfDBv5NpQDRYYZ6C7aaK9ZqpLCihqJKB7rT28gaT29Dm9/MWl5No25b2AvBrNcFNIaWNtb/VjSNJLFCeJE4YDT6sHCcFWU0lvApqo74viMwR8T6vJ3yk4cDaqoP0HniNFKGXduccAHQnA6/sw+qwRjYlrFAdUk+O99bSK97ZrF61q1UF+fXO1dRdeiMZvrf9wyKonB45UdsefXRZsd/LoPV7veYQHYnQ1HpMOZ2Cg9sp9DPjLjmdlF24lCAEYrWVOVw8dUPeRRVnfmZ55dDdmEl6VEWku1malwaYUbPR/jNqU9tTPsoK4WVvuvCAaxG739S7WYDIzNjqXC4qKhxYtSphJv09RLvSIuB8VkJbDhS5HVWtymiw4znncQm2IysOZhfb/GXqkCnWBt92kWgKk3Zu+8Mo04lpZHNFVpKuwgzelXxOdsbZTGcV02uCD4pJxDCC53RRJ+pT3heoc8pK1BUHfowGz3ueMTv7Zxb3+rlKNLH3EbWLQ80L9gmCE/tRHSn3oEdrLk5uvZj9BYbV8z7kIyxt6E73R9X1RtIufxHXDHvQyLSu+GsrmTHm/NaLlBFJSWAFmbhKZ1Q/O06prlJHjKey+f8A4OXeuIz96tgCo/yfcx50jSNirxjlOVke9qtiYCszS6guKr+m5baFCW7sJJvDhWy4WgRqw7ks3RHDkeKvC/sqVXtdFHmp4NAl3gb/rpBWQwqCeH+a8HDDDpirSbs5sZ7lZZVO5uUwKqK59+5NGDfKf9vnnWKJ3n2pqCihsJzEmG3BnvyyvjfoQISw81NroVVgCHto9AF2Ou1OQw6lV5J3t8E17Y/E6FNZmKF8CF58NVc9shr7H7/zxQd2OG5UFFJ7H8l3W77TUCbBtiS2mOOTqCq4KSPozTSRjT8qLyp7CmdKM3e4fOYzPF3E5HejahOvSn8YZvfTgKa00FF7lEi0rvS465H6X7HIzgry9GZw1B1Z15CTmxYEfCMs38Kpoho2o+6ye+RRlsEqcN/xJFVSxudYVZUHeGpnYnq1AegXsyN0jTaDW3+bLg/R9b8i31LF1F2/CAAeouN9NE/ofMNv2z2BhqXgsLKmrqNAAJR7XSz5mABV3RQGt1O9VR5NdtzSjhRWg1uF2HAd0cK6Z0S3WBGVVUURnaI5csfTnlN2KxGPSdLq0kMN/ksa9A0ra63qUGnNDh2W04ApTFn6ZUUQbsIM//ZcxJve5z4PD85gk6xNrILKziQX07F6c0O0iNM7DoKTjdoXhL47MJKOsXaMOtVT2sxL/ehKtTVzSbZzfRItLfKLlpd4sNRFYVtOcXUnNVP1mrUMTA1ioTwhjsGitAiSawQfsT3GkZ8r2FU5B2jpqwIS0wSJnt0wOcrqo5O101l+5tzvV4f1akPkR26n3esmddMYsvLv/V6fVhCGsmDrwag/30L+Oq31+Ly1YP1NJ3pzIu9ouoa/Zi/Mj+nrr3VeVMUhj32FsYAZ0S73/4wRQd2UHJkb4Ok3GANZ8D9z6EoCsWH91Bd7LtnLOB/traZ9i5dxO73/1LvMmdlGT98/P84sfFrrpj3AXrThfuINZSdKAk8gT3blmPFJNvN9ZLFnJIqVu5v2F7qcGElJ8pzubpLfINENj7czNgu8Ww8WsSp8oaz5/nlNXy9/xTtIswMS49pMMuoaRr788vZnVtW134qwqyna3w46dFhKIpChcPV6G170zPRTla8je0nShrdD+VstYlk7Uf/OgV6JEXQJc6GoihkxljJjDnTIaG6poZd+C8TOFxUyaiOcXz5Qx7VZ20oUHs//VMi6RhrpdrpxqAq57XBQXN0irPRIcbKidIqqp1ubEY9cbYLVz8tWpeUEwgRoLC4dkRmdG9SAlsrfextZIy7E+BMD9LTJQrh7TIZ+OBfvJ3aJEmDr6bLTffVv5/TVbJh8akMffRvKKrnfosOfh9AAqtgS87Ampju976N4ZEtk8ACisGILcn/fdYyWO0Mf/xdut32W6yJ7VENRkyna5Uvf/xdwtt1AKDiZGCLzaryc5ocsz9lOdkNEth61x/fz5rHb8MdSI3vJUhDa9bK/ZJqJ0WVZz4Od2sa3x4qaLQllAbUON1sOlrU6G1FhxkZ0zmexEbKBmpv61hxFdty6tfPaprG+sOFfHekqF7/1OIqJ98eLmTz6R29HM7Ap1JVPGUOiqJwuLDSb7IZadYzpH00vZLtDE6LYmLPZLolhHtN5lwBdg44WlxJuEnPdd0SGZASSWK4iTirkc5xNiZ0TaBznA1VUbAYdK2ewNbSqZ7Z+A4xVuL9zJSL0CIzsUK0AkVR6HnXo6QO/xGHvvqQspyDGKx2UoZMIHHAVaj+ajqboMuN00kaOIZDX35AyZG96C02kgeOIfmy8eiMnj++bqeDbX/7YwC3ptHlxukBvegnDRzD1v/3eONb5DZRVIceTT5Hbw6j44TJdJwwGQCHw8Gnn36KKTKu7hiDzf9CMQCDteVnYg9//aHfmeqSQ7vZ+38vy9a2jYgJMzZ7xf7ZW44eL6mq9/25NDwN/isdrkZXrpdVOz0lCD7sO1VOj0R73daux0uqOFDgvT53T14ZKZEWIs2GgBdJufHMKKdFheEM4HfO6Yb06MDLVfQB1quW17hYd6iA4RkxdIqz0SnO5v8kIVqIJLFCtKLIDj2IbEaC1lT21M70nPR7r9fnblvjdytWgMzrfka7oRP8HqdpGsXZu9CbwnBW+m8M70/7K28+79toTHTnfpgi46guyvN6jN5iJa7XsBa/77Kc7IBmqg/85+90uv5edEap1ztbvM3TR7W02tlokrdr47d88vdXObhrG0Wncvn1gtcYOGoc4KmBrFVa5axLFHduWMfbC//I0f17iY2J5vqfP8SI628FPMmqxaDjpZde4plnnuHEiRP07t2bR554GuIy626vprqKdxY+wbrP/4WjpoZeQ0Zwz+/mUVARU1dzuWbbHp5+9CF2bvgGs8XK5dfexK2/molO7/kTrAD7TpUxLD2GtCgLhwoD2wTAcXq2NNJsoMpR7TX5VfC9eKvRc06/cQ0kqT5SVElBeTXRVtnCVbQuKScQ4hJUmZ9DIBsYxHUb5PcYR3kJa/94B+uevKdFElhFb7hgC6tUnZ6utzzo85jON06/IHWperM1oA0XnJXlnq2ART2KojC8QwxGndroM7e6qpL2nbsyeWb92vNz2yjpdQoakHvsMM/cP4luA4Yw/91Pue6663ht7ky2fvN13XFLlixhxowZzJ49m02bNtG7d28m3zKR4oIz9bRvLZjDptVf8MBTi3jstQ8ozDvJc7+5t24hk8vl4uF7forT4eDxxUuZ9sfnWPXxB3zwyrN1t6FBXclDr6QIjAFuQWs3eZLgTnE2n4mmhqclVnMEuh3umuyCgEsQhGgpksQKcQnyLJjy/wfHGO6//nfDiw9RuG9rC0TlYbLHoKoX7qUpbeSN9Lz7D6inZzoVnQ5QUPVGuv7k12Rec/cFud/kweP8doKoJXWxjYswGxjfNYGuCeGEGXToVYWw0x/59xk2ilumP8zAK8fXO6esxllva9F2ERYUYMWHbxPXLpU7ZsyiXUZHJkyYwKArx/PZO69jM+qINBtYuHAhU6dOZfLkyXTr1o1FixZhDQtj5bIlAFSUlvD10iXcMWMW3QcNo0O3Xvz88QXs3bqBfds2AvD5559z9MBeps/9C+ldutNn2Chu/uVvWP7B33Ge1V6t9uN7m0nP1V0SfCayCp4ENvb0Cv9ku9lnqUCnWCtxtuZ1A7i8Q0xAx5XXuNh8rKhZ9yFEc0kSK8QlKKHPiLp+r41TsCakEZHRzeftFB/eQ97WNS22oAugqijP02XgAsoYezvjXllDn2nz6fLj++g9dQ5jX15Fp+vvvWCLPhL6XoE1KcPvcYpOjz2tywWJ4WJgMejonRzB9T2SuLl3O67vkUSS3XvphdOlsfpgPtrpNxBhBh2ZsVb2bdtIj0GX1zu215Ar2Ld9Ez2TInA4HGzcuJHRo0fXXa+qKmPGjObQ95tRgIO7tuNyOugxeHjdMSkZHUlsl8LG79YDsG7dOjpldSMyJu6s+xlBZVkpR/efeZ6nRZ75fbSZ9IzuFI/ey19oRYHB7aPOfOSvKFyWFkX/lMh6pRPhJj2DUj2XN/d5HWE2BFwfuz+/nJpz6o1rXG6KKx1U1Mj2rqLlSU2saFMq809QdvwAOpOFyMye/nt6imbRm8PIuvl+vn/rT41c66mC63bbb/3+4Tu56evA2mqd7sQQ03Ug+bu+8731q+Zm+xvzGPbYm75v8zzpLVbSrph4Qe/jbIqqY/jst/nigTG4qhtf5KOoOtoNuaZZHTAuVU6X22f/WA0oqXKSV15DvM1Ts9k/JZLyonwiYmLrlSZExsRRWVZKgkXh1KlTuFwuEhIS6t1eQkICO3ftwmLQUZSfi95gxBp+ZiFghMVASlISJ06cAODEiROkJCehO2v3qIhoT0JblJ+Hgqcxf4ez2lvV3k56tJUfGtuwQKPBTlSKotA5zkanWCtVTjcKYNKr5/2mrLzGSXKEmcMB1Om6Ncgrr6ZdhIXyGifbjhdzqKiy7gOImDAjPZPsPt90CNEUITcTW11dTZ8+fVAUhS1btgQ7HNFCKvKO8b9nprH8/itZN38Kax6/jeX3jeTgf9+pm0ERLavDuLvofscj6EynZ4BO/7Ez2CLof9+zJA0c7eNszyzs8f/9J6BZ2LQRNzD6z5/Te8rjZ7X+8kLTyN+1nvKThwN6HKHEZI9mxJP/9HQ/ODe5UDztzHrc9bvgBBeiiqucfmsxFTybG9RSFQWzXiUr3kaPJDsdYz0J5ODUyIDuU1UUxmUl1M2eGlSFCLOe/imRjOkc1+BHq1MVruwYh+n01OrZV5sNKld1OnNdraPFlY0nsHg6E6w+kF+vL2vdYz3dzsps0DU7gdU0jYOnuyn8d09eQAnsmXM9ie/ne3I5VFhZr4Imv8LTS/dwof+d1IQIRMhNcz388MMkJyezdWvL1eCJ4KosOMnq2bdSU1JYr2awujif7W/Opbq0gKybfhXECC9OiqLQYfwkdKYw9i59hap8z8yRKTIOt9OBpmle/wgeXfsJm172v+UugKIz0OOuR+t2o0of/RMO/vdtv+eV5x4JaEe0UGNLSmfUs59w8L9vc2TlR9SUFWGOTiT9qp+QPvonngVgImCB5GkaoJyzHCwxMZGi/FP0SLTjcDg4tgUK8k9ht9uxWCzodDp0Oh0nT9bfae/kyZMkJiZi0qsMyMrA6ahhdHsrkZGRDY6pvZ/169cTYzVyffckDhdVsHWnZ2HYiJ6ZjOuehNrIg9iTW+qzM4DTrXGwoJys+HD/A9BEO06UsON4Ec3ZPy46zMCW48U+d/D63+FCkiPM6E/Xvlc5XBzILye/ogZFUUiym2kfZam7XghvQuoZ8tlnn/H555/z7LPP+j9YhIy9H71CTUmh1xm9vR+9QsWp460c1cVP0zR2vDWfbf9vdr0tccuO/cDmRb9jx1vzG50FLz95mM2vPOIpCfBVFnCaMTyy3naqkZk9A4rPEBZYT9dQZI6IpestDzL2pZVc++ZWRj/3Xzpee8+lmcCePAmLFsGUKTB0KPTtC8OGwb33wmuvQb7vVnARZgPGAJron7tBwZAhQ1ixYkW9y7744guGDBkCgNFopH///vWOcbvdrFixou6Y/v37YzAY6h2zZ88eDh8+XHfMkCFD2L59O7m5uehUhYxoK7k712O327nqsv6NJrCappFXVuN36WVeE7bhDVRptZMdJ0qbfJ4CtDudmPrbfMHp1jhS5JndPVJUybLvc9iaU8LR4iqOFFWy/nAh//r+BIWVge9eJi5NITMTe/LkSaZOncrSpUsJCwvs/WF1dTXV1Wd+yUtKPHtSOxwOHA6Ht9PalNo4QyXepnI7azj8zWe4VT2ojT8dFVUle9UyOl33M+DiH5PmaM6YnNr9HQe+eB/0jfd2PPDF+8T2HUls1sBzLv8ATW8OeDGXo6amXlwxPYejmMNxO73/gbLEJGFN6VzvPGd1Jce//Q/Hv/0MR3kJ1oQ0UkfeSGy3wY3OGMvzpKE2NSZHj8KcOfDRR9BYPJs3w9tvw8MPw803w6xZcE59aq3O0WY2HDzBiSPZdZflHT1E9q5thEdEkpWZzvzH/8Dx48dZvHgxAFOmTOHFF1/koYce4o477uDTTz/lww8/ZNmyZXXjc//99zNlyhT69OnDwIEDeeGFFygvL+eOO+7A4XAQFhbG5MmTmTFjBna7HbvdzoMPPshll11G//79cTgcjBo1iq5du3LHHXfw5JNPcvLkSf7whz8wbdo0VFVt9GehaRoE8PuluZwt/rPcl1uC4nad+f0O8PfcatTRL9FGcUWl39cGRYHiiiry9LB2/6lGE96aGhdf7T3JuC7xdZtGBFub+v1pIy7UmAR6e4oWAgWHmqZxzTXXMGzYMP7whz+QnZ1NRkYGmzdvpk+fPl7Pe/zxx5kzZ06Dy999992AE2EhhBBt3/bt23nssccaXD5q1CgeeOAB/vKXv5Cbm8u8efPqnfO3v/2NI0eOEBMTwy233MJVV11V7/x///vfLF26lMLCQjIyMpg6dSqdO3euu76mpobFixezevVqHA4Hffv25ec//zlRUVF1x+Tm5rJo0SJ27NiB2Wxm1KhR3HXXXeh0furDhbhEVVRUcNttt1FcXIzd7v1TuaAmsTNnzuSpp57yecyuXbv4/PPPef/991m5ciU6nS7gJLaxmdjU1FROnTrlc1DaEofDwfLlyxkzZgwGQ8ttTdpWuGqq+Xz6CJ/v3BVVR4dxd9Llx9OBi39MmqM5Y/L1zOupyPNdphEW146Rf1pa77J18+6m8MD3Ad2HoupIGTaBnnfXTy40t5u9H73Cgf+8haa5PR0OXE5Uo5luP3mQtJE/PnOspvHN3LspObzH6/Oky4/vI/OaSfUuk+dJQ21iTBYu9MzA1oqOhrvugmuugV69wGKB8nLYtg0+/tgzG1tcfOb4Z57xlBqcQ9M0TpU7OFBQRlm1E5NeR1pkGO0izOj8tIhqE+NyjhMlVazJLvB6vV5VuCYrAaO3PlzNtPFoEdkFFWhuF2HHt1OR3BPOWYypKnBDjySvNfNf7M2lqMp3r+PxWfF8sTevbtcxbxLDjQzPiG3ag7hA2uLzJNgu1JiUlJQQGxvrN4kNajnBQw89xN133+3zmA4dOvDll1+ybt06TKb6H3sOGDCA22+/nTffbLwVj8lkanAOgMFgCLknYCjGHAiDwUByvxHkrP/cZyKbNnxCg8d/sY5JU9SUFnJ45Ufk7d0MmaM5+uX7pI+ciNEW6fdcxe1EcfquqdPrdQ3GOL77YIp+2AJ+92tXUHQ6Oo67o9GfU49bH6Tj+DvI+fa/VJcWYIlJInnwOAxh9XcWKti7mZIfNp++xcZlf7aYzhMmoeob3o88TxoK2pi8+y7MnHnm+8mTPUntWYuiAM/3V1zh+ffII3DffbDEs8FA5X33oUtIwHjTTQ1uPtloJDmq+XXFbem5khpjoJdDY1tOSb0FXgqgqgojMmOxWlp+m9f02HAOFp31uqDq6iWxCtA+Ogyj0fvmCb1Toll5wHstc0Z0GJFWC25Vh79NV9yKvs38TGq1pedJW9HSYxLobQU1iY2LiyMuLs7vcc8//zxz557ZSvD48eNcffXVLFmyhMGDB1/IEEUr6HzjLzix6Ss0h9ZwoZCikDLsOuwpnYITXBuWt2Md6xdMx1VThaYzQuZodn3wF/b983kG/+YVYrt7/90oPrSbylM5vu9AUUkefDXgmTnN2/4Np3b+D2dlGYqioimazx2oVIORAfc/hz21s9djzBGxZFx9u88wTu1c77cXbU1JAWU5B33eV3O5aqo5snoZh758n8pTOZjs0aSOuIH2V96MIazlV4ZftI4fh+nTz3z/1FOeeld/YmPhH/+Ajh3ZPW8eI4HfTJ7Mb0aNgpjAdpMKVd0T7SSGm9mbV0p+hQNVgZRICx1jbIQZL0wpQoLNRLzNSF5J4221VEWha4Lv531yhIXL2kex4UgRTrfm6SChedLVjOgwBqZ6Si2iLAZOlXuvjVfwdDsQwpuQWNiVlla/zY7N5pmpyczMJCUlJRghiRZkT+nE0N8vZtPLD1Nx8oin6l/TUFQd7a/6CT3uDKyV06XE01f3F57FUWcnkpqGq6aab5+ZxlULPsUSk9To+d+/8zSan84COnMY7a+8hbITh/jfM7+gPOcgyunNJ7TabVEV9cwbj9NfR2b2pN1l15A6IrAZYb8C6IAAXJB+wo6KMtY9OZmiAzvqnpc1pQXs/MezZC//B8Nmv40luvHFRuIcc+ZAUZHn69tua5DAOlxujhZXUuVwYzHoSIk804IJReGHSZO48tlnia2uZlJZGcyfD5dAp5oYq5EhVk+yXlHjJLuwkt25pYQZdbSPCsNiaNlkVlEUrugQy9r9uRRz5tMPDbAYVIalxxBh9p9YZkRbSYmwcLiokrJqJwadSlqkBZvpTNrRJc7GqXLvJRMa0DHW5vV6IUIiiRUXv+hOfbhq4X/J37me0mM/oDNaSOg7AlPExT3T0lzZX/wDzeVofCZU09CcNWQvf4+ut/66wdWV+Sc4tWOd3/voOOEedEYzq35/M9XFnr6WdckrgKKi6g3YkjMAhdhuA0kffSu2ALZWbYrozv38rnY2hNlb/H4Bdrw1n6LsnZ5vznmzUJmfw6aXHr7gO4tdFIqLPbWtAOHh8Pzz9a7enVvKtpwSXG6t7qNz/RGFvu0i6BhrIzs7myuvugp7SgorjhwhrqYG/vY3eOIJTw3tRU7TNLYcL2Z3bhngqUl1a7DlWDE9Eu10Twxv0e2SDTqVYRkxfLrLMxusqDoiwwwk282NtgTzdTuZMd7LO1IjLXSIDuNAQf3ND2qfAwNTIwk3SZoivAvJZ0d6errs4nQRUhSF2O6DfX4MLjxObPwKzUdNquZ2c2Ljl16SWD9lBHgWZKk6HUdWfkRVUa6XZNmN2+kgaeAYutz4yybF3xQx3QZha9eB8pxDjSezikL62J+iM3iv0WuOmtJCjq75l9faX83tIn/XekqO7pNyF38++wwqTicqd95Zrwxgb14Zm4+dWbhV+0xzujW+O1LEyePH+Om1Y6ioqOChhx4iYeNGeOstKCyEL7+ECRNa8YG0vqJKB5uOFnHyrJ6wtWuhNGD7iRIMOoUuF2DTA4CseNsFq/9UFIVBaVHEh5vYm1tGQaUDBUiym8mKt5EQLtvTCt9CMokV4lLndvhvAu7y0ofVaI/2e67mdmO0R3H463/6rHtFc3Ns7ScXNIlVFIVBM15k7R/vpLqksEH5QlzPoRfk/ouyd9afefaicO9mSWL92bDhzNfXXlv3pcutsS2nuJETPGqqq7jqyn5UV1agqipfffUVA/r1IwNIBNQNG1okiS2q8vyuLNuRg1tRibQY6BwXTvsoS4vOcDaFw+Xmm+wCjpdU+T12x4lSOsba/HZhaIsUxbMBREa0tW5yKlhjLkJP2+ggLITAVVPtc3b1bFGdeqOo3mvhFFVHdKc+jV5nS2xPREZ3TxLo7Xy9nqSBY3BUlPmNxVHV+P7uLcmWlMHIpz4m6+ZfYUvKwBQRQ3SnPvT75dMM/u0iVH3LzsICKD7Gp/6B8jLq1+7dZ77u3bvuyxOlVThcPt4kKQqJqemktU8nKiqKZcuWMXz2bNoB4cC6NWvOO7SjxZWs2Ospl3G4NVwa5Fc4WHeogHWHCrx+6udwuXG6Avt9bSpN01h9MJ+cABJYgBqXm7zylt+9q7UpiiIJrGgSmYkVIoic1ZUc/M9bHFz+LlUFJ1F0epIGjqbjdT8jMqO71/Myxt7OsW/+7fV6ze0iY+xtXq/v9tOHWDf/Z+Bld/bO1/8coy2S8JSOlOdke69JVVXCkzt4vZ+WZLJH0XniNDpPnHbB70tzu7Eld0A1mHA7fCcHxdm7Lng8Ie+sft3YzizUqXb6TgKNRhPz3/svwzOiSY0Mo6ysjIPffsvBMWM4AXRppIVik8JyuvjmYL7XJk+HCitJsFWQGeup69Q0jQMFFezOLaXkdB/UaIuBrgnhpEW13AY6p8prOFnatKTU6evNgBAXKZlCECJInFUVfDN3Erve/wtVBScBz8KpnPXLWT3rVnK3rvZ6bnTnvnS56VcA9WZka7/OuuVBojr2bvRcgLgeQxj00IuYIk83ET89+6EazWTd8gCdT388n37VT3wvqnK7SR/zU/8PNkRUFeWx4635fPazQSy/byRul/+tD7OXv8upnetbIboQdlbiyqlTZy42BjaPYj19nM1mo2dsLD8C7gWiz7PF1sGCCvzlfnvySgFPArv+cCHrDxfWJbAABZUO1mYXsO2497KIpjpcVOm1J7I3sgBKXIrkWS9EkOxb+ipFB75v0EJKc7tAUdjw/AzGvrwKvanx1dddbvwlkR16sP/TNzj1w3Y0ICZrAJ3G30F878v93n9iv1HEv3A5edvWUpF7FIMtgsR+o9Bbzqwmju1+GWkjf+ypjW1AIWnQWJIGjG7Kw26zKvNzWD3rp1QXnzpr3/jAPi7e/+kbxHYbdAGjC3E9e8LSpZ6vN26EDp7Z+zibEatRR3mN9zdKEWY9UZazFhZt2lT/ds9Dvo8epbWKq5y43BonSqsarKI/2/cnS2kXYSHGev6lLY4mlCl4eqkaibC07OKrkirPG7gTJVUkRenRh2C9rbj4SRIrRBC4nTVkf/Ge9x6omoazsozj3/6HtBE3eL2dhD5XkNDnChwOB59++imDHnqxSSuJVZ2ehL4jvF6vKAq9f/ZH7Gld2P/vxXWdDUyRcXQYfxcdJ0xGUS+OD3S2/e2P9RPYJji1838XIKKLyNmb0nzwAdx8M+B5fg1MjWLl/lMNPtJXTv9nYGpU/TrJ998/8/Wg83vjoCqKl4Kac2JRPF0UfB2rAPtOlRFj9b9w0p9wk95vTLX3qVM9K/xbSnGlg/8dLiS/rJIwYE12AfqjJXRLCKfb6U0OXBroFFmAJYJPklghgqCqMA9HRYnPYxSdnpLDu30e0xoUVaXDuDvJGHs7lfk5aJpGWGySz4VloaYyP4eTm1fiP51pnKs6sAU4l6wxYyAhAU6ehI8+gj17oEsXwNNOaVTHWLYcK6ag8kz5RnSYkX4pEcRaz6p73bwZ/vtfz9cZGTB8+HmFlWQ3k13ofXZVAeLDTaiKQmGlw+ezQwMKK/yXnwQiI8bK9pwSv8/GlEgLvZLs2APYfCAQpdVOlu/LbVBf63R7tr89VFhBabUTtwZGnUqnWCtZ8eEY9RfHG1kReiSJFSIIVGMAC1I0DdXQ8nujN5eiqoTFtQt2GBdEyZF9NDeBBUBzo7ldF1Vi36KMRvjFL+Dxx8HphMmTYeVKOP2pQUK4mauzzJRUOahyenbsalDjWVXlOa/W9Olwnp8CpEZa2HJcR1V147PvGtD1dP9Vvargb6mVXtcyM5NhBh19ku1sPu79ja7NqGdwWhQGnfcxcGsaOSVVVNS4MOlVkiPO2gWtETtyinG6NK+/CcVn1QLXuNzsPFnK4aJKxnSOw6SX575offL2SYggMEfEEpHe1Wd7Js3tIrHfqFaM6tKlM55fU3Wd0SIJrD+//S107Oj5et06z6YHNfVrUu1mA/E2U+MJ7M03w9atnu979YJf/eq8Q9KpCqM6xmI6ZyaxNhXtnxJJkt3z3EiNtPhdbJUS0XK7h0WG+a6tLatx8sMp7+3tjhRVsHRHDqsO5LPhaBFrswv4aHsOe3JLG20b5nS7OVRU2aS3chpQVu2st1mFEK1JklghgqTTxGlea2IVVUdU575Eeen1KlpWVKc+GKz25p2sqKT6qFsWp4WFwd//DrVtsZYs8dTKbt7s+7xvv4X+/eGTTzzfW63w5pue2d0WEGE2MK5LPABJ4SYSbCa6xNu4tlsinePOdFXoFGtD9bK4ScHz8XoHH1usNtWB/HK/SfP+/MaT2GPFlaw5WNCghZnTrbHpWDF78xr2f65xaj73NfFGA7ILK/y2SxPiQpAkVoggSR40lu53zvTMxqoqKGrdbJ69fRaDZrwoCydaic5gpON1P2v6iYqC3hxG5oTJ/o8VMGQI/POfZxLZLVugXz8YNQr+8hdYtcoz2/r117BwoafmdcgQ2LnTc7zVCh9/DH36tGhY+tMfyQ/LiOHKTnH0bRfZYDbYZtIzKjMWw+mSAYUzM7YmvcqVnRrO6AaitNpJTkkV+eU19WZIy2tcfmdFKxrp6qBpmt+Z0W05JTjP6bxh1CtNbut15j6htLpl6oGFaAqpiRUiiDLHTyJ50FgOffVPyo7vR2+2kjz4auJ6DrtoVv2Hio7XTqG6+BQHPvs7iqpDQ0NRFDSXi8SBo1EUlZz1yz0HKwpobqyJ6Qy4fyHW+JTgBh9KJkyAb76BSZNgxw7PZV9/7fnnS79+nhnYHj0udIRexdlMTOyexKGiSvLKqlEUSLCZSY20NHnL1+JKBxuOFpJbdqakIsygo1eynYxoKxa96rdzQmNJc2Glg9Jq39slO90ax4ur6m3QoFdV0qIsHC5sWklBLZ284RZBIEmsEEFmiUki66b7gh3GJU9RVXrc+TvSr7qVwyv/j8r8E5giokkZ9iMiO3h2T6vIO8bJLatwO2uISO9KTNZAmS1vjn79YMMGePVVeOkl2LvX+7Hdu8N998GUKXULwYJJr1PJjLGSeR6lA8VVDj7fm4vLXT9drHC4+PZQIU6XRnqMlSPFvrteWAwq6w8Xkl9eg1PTiA4zEGMJrMyiqpGP/3sk2jlWXIXL7X1xl7c4WrpPrRCBkCRWCCHOYkvOoNtPH2r0urC4dmRcRDuUBZXJBPff71mgtXmzJ6nduRMqKz31s927w8CBnkVcF9kbhS3Hin0mipuPFTGxRxKxVqOnzMDLcfkVDvLPautVXu3kcGFlQDGEGRsuRLSbDYzuFMf/DhdSWB54v+TuCXbUi+xnJEKDJLFCiItSdUk+ACt/dwPO0kJsSemkj76V5CHjUXXy0tdmKIpnZrZfv2BH0iqqHC6Ol/ieYXVpcKSoipGZsaw/UhhwYhro7KlJp5IU3nhHjqgwI+OyEsgtKWfdURjaPpp4u4VvDxdyorS6rsSh9v/dEsLpGNtyC9qEaAp5JRdCXHRKj+1nzZNTYOyvKc89iuKspqCsiIK9mzj6zScMmvECqr5lVrcL0RSVDv8znIoC5Q4nBp3KsPQY+iQ7+XJfHmU+tudtiv6pkX5reKNOlyUkR5gxGPSMzIwlr7yGQ4UV1DjdWI16MmPCCG+hjRaEaA5JYoUQFxXN7Wb9guk4ykvPvQKA3K2r2bv0r1KHLIIikA4GmgbmszYP0KtKsxLYKIuBwrN2QbMZdfRtF0lKZNP72SqKQrzNRLyt7WzAIoQksUKIi0rejnWUnziEpvfyx1bTOPj523SeeK/MxopWF2bU+611VfBsrlDL6W7ebnJjOsdTVu2kvMaJyaAj2mKQhYjioiI9fIQQF5WCvZv97p7lKCum/MThVopIiPr6JEf4vD4rIRyL4cxz2KzXoW9iC69oiwGdqhBhMZAcYSEmzCgJrLjoSBIrhLioKIH+sfex5a8QF1KczcSIzFgshvrPQVWB7onh9E6qv3ucTlXoEGNt0mYEWQnhLRCpEG2blBMIIS4qsd0uY8+HL4Lq/eXNFBmHNTGtFaOqrzz3KDUl+Zij4rHEJAUtDhE8SXYzP+qexMnSakqrnRh0Cu3sFoxeamZ7JtrJKamirNrpswxBA7LibaQ1o+5ViFAjSawQ4qIS3aUfEeldKT5+yOsf+8wJk4PSZit/90Z2/uNZCvdtqbsspttgut/+WyIzurd6PCK4VEUhyW4mkLcxRr3K2M7x7DhRwv788ro62TCDCigoimchV6c4G4le2mcJcbGRJFYIcVFRFIWBM15k7ZM/o8JzgedyVYfmdpF6xQ1kjp/U6nHl7VjHt3+aiqbVT60Ldn/HmsdvY9hjbxHVsVerxyVCh1Gv0i8lkt7JEVQ5XehVNaBuB0JcrOTZL0SIcFaVU3Twe0qO7EVzt0y/yItVWGwyw//4HgDRnftiT+tC0sAxDPn9Yvr8fB6K2rovfZrbzZbXHkPT3HWtvs6+zu1ysu1vc1o1JhG6dKqC1aiXBFZc8mQmVog2zllZzq73/8zhrz7EVePZ6cccFU/HH00lY+ztsuLYC73JUxN42cOvYjAEtyF7/u4NVOYd836A201x9k5KDu/Fnta59QITQogQJm/jhGjDnNWVrJ07iezl79YlsABVhbnseHMe37/9pyBGJwJVkXskoOPKT0rbLyGECJQksUK0YdlfvEdx9k40t7vR6w989neKs3e1clSiqQxWu/+DAKPNd/9QIYQQZ0gSK0QbduiL9zx7UHqhqDoOffVBK0YkmiOu13D0ZqvPY0yRcUR17ttKEQkhROiTJFaINqzCVx0loLld8hF0CNCbLHT+8XSfx3S95cGgtP0SQohQJa+YQrRheosNR3mx9wNUFaNVPoIOBZnX3I3bUcPe/3sZt9OBolPRXC50RjPdbvsNaSNvDHaIIcfhcpNdWMHJ0moAYq1GMqKtsmpfiEuEJLFCtGEpw39E9vJ3vbfUcrtpN3RC6wYlmkVRFDpP/Dnpo28l57vPqS7OxxydSPLAMegtvksNREP55TV8vT+PGteZcpsjRZVsyynh8owYkuzS8F+Ii50ksUK0YZnXTOLIqo9wVVc2SGQVVYe9fRYJfUfgdDW+8Eu0PUZbBO1H3RzsMEJalcPFVz/k4XA3rBd3uTVWHTjFNVkJhJuD21pNCHFhyWcuQrRhYXHtGPbYm5hjEgFP4srpRv2x3QYz5Hevey5rBdUlhVTkHcPlqGmV+xPCmwP55Y0msLU0DfaeKm/FiIQQwSAzsUK0cRHp3Rj93Ofkbf+GogPbUfQGEnpf0WpN8XO3rmHP/71M4b7NAOjNVtJG3USXH0/HEBbeKjEIcbajxVU+r9eAo0WV9E+JbJV4hBDBIUmsECFAUVXiew8nvvfwVr3fw6uWsmXRo3DWrmDOqnIO/vdt8ravZfjj70oiK1qdy0fbuaYcI4QIbVJOIIRoVE1ZEdtenwVooNWvudXcLsqOH2DfsleDE5y4pMWEGfG12bJy+hghxMVNklghRKOOrv4XbpfT6/Wa2032ivdxOx2tGJUQ0CnWiq95Vg3oHGdrrXCEEEEiSawQolGlxw/4XTTmrCilprSwlSISwiMqzEifZE9/5LNnZGu/7hJnIzHc1OpxCSFal9TECiEa5dkm1X9doc4UduGDEeIcXRPCibAY2H2ylJNlns0OosOMZMXbSI20oCi+Cg6EEBcDSWKFEI1KGjSG/f/+m9frFVVHTLdBGMLkY1sRHMl2M8l2M9rpRVySuApxaZFyAiFEo6I69ia2+2UoamMvEwqaptHlhl+0elxCnEtRFElghbgESRIrhGiUoigM/PXzxHYf4vle1aHoPB/e6ExmBvxqATFdBwYzRCGEEJcwKScQQnhlCAtnyO9ep+jA9+Ss/xxndSXhKR1JGToBvcUa7PCEEEJcwiSJFUL4FdmhO5Edugc7DCGEEKKOlBMIIYQQQoiQI0msEEIIIYQIOZLECiGEEEKIkCNJrBBCCCGECDmSxAohhBBCiJAjSawQQgghhAg5ksQKIYQQQoiQI0msEEIIIYQIOZLECiGEEEKIkCNJrBBCCCGECDmSxAohhBBCiJAjSawQQgghhAg5ksQKIYQQQoiQI0msEEIIIYQIOfpgB9CaNE0DoKSkJMiRBM7hcFBRUUFJSQkGgyHY4bQJMiYNyZg0JGPSkIxJ42RcGpIxaUjGpKELNSa1eVpt3ubNJZXElpaWApCamhrkSIQQQgghhC+lpaVERER4vV7R/KW5FxG3283x48cJDw9HUZRghxOQkpISUlNTOXLkCHa7PdjhtAkyJg3JmDQkY9KQjEnjZFwakjFpSMakoQs1JpqmUVpaSnJyMqrqvfL1kpqJVVWVlJSUYIfRLHa7XX5pziFj0pCMSUMyJg3JmDROxqUhGZOGZEwauhBj4msGtpYs7BJCCCGEECFHklghhBBCCBFyJIlt40wmE7Nnz8ZkMgU7lDZDxqQhGZOGZEwakjFpnIxLQzImDcmYNBTsMbmkFnYJIYQQQoiLg8zECiGEEEKIkCNJrBBCCCGECDmSxAohhBBCiJAjSawQQgghhAg5ksSGkL1793L99dcTGxuL3W5n+PDhfPXVV8EOK+j+/e9/M3jwYCwWC1FRUUycODHYIbUJ1dXV9OnTB0VR2LJlS7DDCars7GymTJlCRkYGFouFzMxMZs+eTU1NTbBDa1UvvfQS6enpmM1mBg8ezPr164MdUtDMnz+fgQMHEh4eTnx8PBMnTmTPnj3BDqtN+dOf/oSiKDz44IPBDiWojh07xh133EFMTAwWi4WePXuyYcOGYIcVNC6Xi8cee6ze6+kTTzxBMPoESBIbQq699lqcTidffvklGzdupHfv3lx77bWcOHEi2KEFzT//+U/uvPNOJk+ezNatW1m7di233XZbsMNqEx5++GGSk5ODHUabsHv3btxuN6+++irff/89zz33HIsWLeLRRx8NdmitZsmSJcyYMYPZs2ezadMmevfuzdVXX01ubm6wQwuKlStXMn36dL799luWL1+Ow+Fg7NixlJeXBzu0NuG7777j1VdfpVevXsEOJagKCwsZNmwYBoOBzz77jJ07d7JgwQKioqKCHVrQPPXUU7zyyiu8+OKL7Nq1i6eeeoqnn36aF154ofWD0URIyMvL0wBt1apVdZeVlJRogLZ8+fIgRhY8DodDa9eunfb6668HO5Q259NPP9WysrK077//XgO0zZs3BzukNufpp5/WMjIygh1Gqxk0aJA2ffr0uu9dLpeWnJyszZ8/P4hRtR25ubkaoK1cuTLYoQRdaWmp1qlTJ2358uXaiBEjtAceeCDYIQXNI488og0fPjzYYbQpEyZM0O655556l914443a7bff3uqxyExsiIiJiaFLly78/e9/p7y8HKfTyauvvkp8fDz9+/cPdnhBsWnTJo4dO4aqqvTt25ekpCTGjx/Pjh07gh1aUJ08eZKpU6fy1ltvERYWFuxw2qzi4mKio6ODHUarqKmpYePGjYwePbruMlVVGT16NOvWrQtiZG1HcXExwCXznPBl+vTpTJgwod7z5VL1r3/9iwEDBnDzzTcTHx9P3759ee2114IdVlANHTqUFStWsHfvXgC2bt3KmjVrGD9+fKvHom/1exTNoigKX3zxBRMnTiQ8PBxVVYmPj+c///nPJfuxxoEDBwB4/PHHWbhwIenp6SxYsICRI0eyd+/eS/KPkaZp3H333UybNo0BAwaQnZ0d7JDapB9++IEXXniBZ599NtihtIpTp07hcrlISEiod3lCQgK7d+8OUlRth9vt5sEHH2TYsGH06NEj2OEE1XvvvcemTZv47rvvgh1Km3DgwAFeeeUVZsyYwaOPPsp3333H/fffj9FoZNKkScEOLyhmzpxJSUkJWVlZ6HQ6XC4X8+bN4/bbb2/1WGQmNshmzpyJoig+/+3evRtN05g+fTrx8fGsXr2a9evXM3HiRK677jpycnKC/TBaVKBj4na7Afj973/Pj3/8Y/r378/ixYtRFIUPPvggyI+iZQU6Ji+88AKlpaX87ne/C3bIrSLQcTnbsWPHGDduHDfffDNTp04NUuSiLZk+fTo7duzgvffeC3YoQXXkyBEeeOAB3nnnHcxmc7DDaRPcbjf9+vXjySefpG/fvtx7771MnTqVRYsWBTu0oHn//fd55513ePfdd9m0aRNvvvkmzz77LG+++WarxyLbzgZZXl4e+fn5Po/p0KEDq1evZuzYsRQWFmK32+uu69SpE1OmTGHmzJkXOtRWE+iYrF27liuvvJLVq1czfPjwuusGDx7M6NGjmTdv3oUOtdUEOia33HILH3/8MYqi1F3ucrnQ6XTcfvvtQXmRuZACHRej0QjA8ePHGTlyJJdddhlvvPEGqnppvI+vqakhLCyMDz/8sF73jkmTJlFUVMSyZcuCF1yQ3XfffSxbtoxVq1aRkZER7HCCaunSpdxwww3odLq6y1wuF4qioKoq1dXV9a67FLRv354xY8bw+uuv1132yiuvMHfuXI4dOxbEyIInNTWVmTNnMn369LrL5s6dy9tvv93qn+xIOUGQxcXFERcX5/e4iooKgAZ/dFVVrZuRvFgEOib9+/fHZDKxZ8+euiTW4XCQnZ1N+/btL3SYrSrQMXn++eeZO3du3ffHjx/n6quvZsmSJQwePPhChhgUgY4LeGZgR40aVTdjf6kksABGo5H+/fuzYsWKuiTW7XazYsUK7rvvvuAGFySapvGrX/2Kjz76iK+//vqST2ABrrrqKrZv317vssmTJ5OVlcUjjzxyySWwAMOGDWvQem3v3r0X3d+YpqioqGjw+qnT6YKSi0gSGyKGDBlCVFQUkyZNYtasWVgsFl577TUOHjzIhAkTgh1eUNjtdqZNm8bs2bNJTU2lffv2PPPMMwDcfPPNQY4uONLS0up9b7PZAMjMzCQlJSUYIbUJx44dY+TIkbRv355nn32WvLy8uusSExODGFnrmTFjBpMmTWLAgAEMGjSIP//5z5SXlzN58uRghxYU06dP591332XZsmWEh4fXtSqMiIjAYrEEObrgCA8Pb1ATbLVaiYmJuWRrhX/9618zdOhQnnzySW655RbWr1/PX//6V/76178GO7Sgue6665g3bx5paWl0796dzZs3s3DhQu65557WD6bV+yGIZvvuu++0sWPHatHR0Vp4eLh22WWXaZ9++mmwwwqqmpoa7aGHHtLi4+O18PBwbfTo0dqOHTuCHVabcfDgQWmxpWna4sWLNaDRf5eSF154QUtLS9OMRqM2aNAg7dtvvw12SEHj7fmwePHiYIfWplzqLbY0TdM+/vhjrUePHprJZNKysrK0v/71r8EOKahKSkq0Bx54QEtLS9PMZrPWoUMH7fe//71WXV3d6rFITawQQgghhAg5l05RmBBCCCGEuGhIEiuEEEIIIUKOJLFCCCGEECLkSBIrhBBCCCFCjiSxQgghhBAi5EgSK4QQQgghQo4ksUIIIYQQIuRIEiuEEEIIIUKOJLFCCCGEECLkSBIrhBDn6e6770ZRlAb/fvjhhxa5/TfeeIPIyMgWua3mWrVqFddddx3JyckoisLSpUuDGo8QQkgSK4QQLWDcuHHk5OTU+5eRkRHssBpwOBzNOq+8vJzevXvz0ksvtXBEQgjRPJLECiFECzCZTCQmJtb7p9PpAFi2bBn9+vXDbDbToUMH5syZg9PprDt34cKF9OzZE6vVSmpqKr/85S8pKysD4Ouvv2by5MkUFxfXzfA+/vjjAI3OiEZGRvLGG28AkJ2djaIoLFmyhBEjRmA2m3nnnXcAeP311+natStms5msrCxefvlln49v/PjxzJ07lxtuuKEFRksIIc6fPtgBCCHExWz16tXcddddPP/881x++eXs37+fe++9F4DZs2cDoKoqzz//PBkZGRw4cIBf/vKXPPzww7z88ssMHTqUP//5z8yaNYs9e/YAYLPZmhTDzJkzWbBgAX379q1LZGfNmsWLL75I37592bx5M1OnTsVqtTJp0qSWHQAhhLhAJIkVQogW8Mknn9RLLsePH88HH3zAnDlzmDlzZl1y2KFDB5544gkefvjhuiT2wQcfrDsvPT2duXPnMm3aNF5++WWMRiMREREoikJiYmKzYnvwwQe58cYb676fPXs2CxYsqLssIyODnTt38uqrr0oSK4QIGZLECiFECxg1ahSvvPJK3fdWqxWArVu3snbtWubNm1d3ncvloqqqioqKCsLCwvjiiy+YP38+u3fvpqSkBKfTWe/68zVgwIC6r8vLy9m/fz9Tpkxh6tSpdZc7nU4iIiLO+76EEKK1SBIrhBAtwGq10rFjxwaXl5WVMWfOnHozobXMZjPZ2dlce+21/OIXv2DevHlER0ezZs0apkyZQk1Njc8kVlEUNE2rd1ljC7dqE+raeABee+01Bg8eXO+42hpeIYQIBZLECiHEBdSvXz/27NnTaIILsHHjRtxuNwsWLEBVPWtt33///XrHGI1GXC5Xg3Pj4uLIycmp+37fvn1UVFT4jCchIYHk5GQOHDjA7bff3tSHI4QQbYYksUIIcQHNmjWLa6+9lrS0NG666SZUVWXr1q3s2LGDuXPn0rFjRxwOBy+88ALXXXcda9euZdGiRfVuIz09nbKyMlasWEHv3r0JCwsjLCyMK6+8khdffJEhQ4bgcrl45JFHMBgMfmOaM2cO999/PxEREYwbN47q6mo2bNhAYWEhM2bMaPScsrKyen1vDx48yJYtW4iOjiYtLe38BkkIIZpBWmwJIcQFdPXVV/PJJ5/w+eefM3DgQC677DKee+452rdvD0Dv3r1ZuHAhTz31FD169OCdd95h/vz59W5j6NChTJs2jZ/85CfExcXx9NNPA7BgwQJSU1O5/PLLue222/jNb34TUA3tz372M15//XUWL15Mz549GTFiBG+88YbPvrYbNmygb9++9O3bF4AZM2bQt29fZs2a1dyhEUKI86Jo5xZUCSGEEEII0cbJTKwQQgghhAg5ksQKIYQQQoiQI0msEEIIIYQIOZLECiGEEEKIkCNJrBBCCCGECDmSxAohhBBCiJAjSawQQgghhAg5ksQKIYQQQoiQI0msEEIIIYQIOZLECiGEEEKIkCNJrBBCCCGECDn/H/LMc1wAdNz0AAAAAElFTkSuQmCC\n"
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Normalized saliency values saved to normalized_saliency_values.csv\n",
"Normalized Saliency Top-k:\n",
" Saliency\n",
"370 1.000000\n",
"37 0.653843\n",
"239 0.460645\n",
"327 0.379969\n",
"377 0.270402\n",
"Normalized Saliency Max: Saliency 1.0\n",
"dtype: float32\n",
"Normalized Saliency Min: Saliency 0.0\n",
"dtype: float32\n",
"Normalized Saliency Mean: Saliency 0.007516\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.00083\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.000047\n",
"1 0.000269\n",
"2 0.000746\n",
"3 0.000754\n",
"4 0.000762\n",
"5 0.000800\n",
"6 0.001076\n",
"7 0.001735\n",
"Normalized Saliency Sum: Saliency 3.60745\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.062508\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 12.158567\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 164.816727\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003907\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 831.722168\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000935\n",
"1 0.003116\n",
"2 0.004207\n",
"3 0.004547\n",
"4 0.005168\n",
".. ...\n",
"475 3.601871\n",
"476 3.606868\n",
"477 3.607134\n",
"478 3.607362\n",
"479 3.607449\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000002\n",
"1 0.000006\n",
"2 0.000009\n",
"3 0.000009\n",
"4 0.000011\n",
".. ...\n",
"475 0.007504\n",
"476 0.007514\n",
"477 0.007515\n",
"478 0.007515\n",
"479 0.007516\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.06289375\n",
"Normalized Saliency 25th Percentile: Saliency 0.000451\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.001293\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.000841\n",
"dtype: float64\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"seconds = time.time()\n",
"print(\"Time in seconds since end of run:\", seconds)\n",
"local_time = time.ctime(seconds)\n",
"print(local_time)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 0
},
"id": "wfZCzuq9KY9b",
"outputId": "8d81df4a-d134-4df9-ffb8-9d63fc8a3281"
},
"execution_count": 111,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712551750.750154\n",
"Mon Apr 8 04:49:10 2024\n"
]
}
]
}
]
}