Datasets
Models
Downloads: 1
1259 lines (1259 with data), 216.7 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": 46,
"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": 47,
"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": "8eb4ddca-d862-4795-f33b-812277a6be23",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 48,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_4\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_15 (Dense) (None, 1024) 3072 \n",
" \n",
" tn_layer_4 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_16 (Dense) (None, 1024) 1049600 \n",
" \n",
" dense_17 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1058817 (4.04 MB)\n",
"Trainable params: 1058817 (4.04 MB)\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": 49,
"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": "b8324ae0-9311-4a7f-92ef-a68f623f4ac2"
},
"execution_count": 50,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712558430.2325056\n",
"Mon Apr 8 06:40:30 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "e2d0b8b7-794f-4ecb-ff36-a7837c3e3e32",
"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": 51,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 1s - loss: 0.5605 - 1s/epoch - 67ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.0929 - 112ms/epoch - 7ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0454 - 105ms/epoch - 7ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0366 - 99ms/epoch - 7ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0290 - 98ms/epoch - 7ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0237 - 111ms/epoch - 7ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0192 - 98ms/epoch - 7ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0134 - 97ms/epoch - 6ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0096 - 96ms/epoch - 6ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0090 - 92ms/epoch - 6ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0074 - 97ms/epoch - 6ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0042 - 89ms/epoch - 6ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0040 - 90ms/epoch - 6ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0030 - 95ms/epoch - 6ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 0.0032 - 89ms/epoch - 6ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 0.0021 - 91ms/epoch - 6ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 0.0023 - 97ms/epoch - 6ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 0.0017 - 94ms/epoch - 6ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 0.0014 - 99ms/epoch - 7ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 0.0023 - 95ms/epoch - 6ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 9.8082e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 0.0012 - 94ms/epoch - 6ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 8.7160e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 5.8578e-04 - 96ms/epoch - 6ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 6.5301e-04 - 96ms/epoch - 6ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 4.1435e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 3.7417e-04 - 98ms/epoch - 7ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 2.3961e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 6.9894e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 3.5827e-04 - 95ms/epoch - 6ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 6.0380e-04 - 92ms/epoch - 6ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 2.5176e-04 - 103ms/epoch - 7ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 1.7059e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 1.5363e-04 - 94ms/epoch - 6ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 1.4641e-04 - 94ms/epoch - 6ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 1.0730e-04 - 102ms/epoch - 7ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 8.9604e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 7.8215e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 6.2449e-05 - 86ms/epoch - 6ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 4.6816e-05 - 88ms/epoch - 6ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 4.9330e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 5.0438e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 4.9871e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 5.1159e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 6.8383e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 6.0236e-05 - 88ms/epoch - 6ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 4.1222e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 2.4281e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.7431e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 3.1956e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 3.7440e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 2.0609e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.6854e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.8500e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.6654e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 2.0672e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 2.5582e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.6297e-05 - 90ms/epoch - 6ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.6208e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.2190e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 1.2277e-05 - 99ms/epoch - 7ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 2.8002e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 2.3270e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.8754e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 5.7573e-05 - 95ms/epoch - 6ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 2.1938e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.9007e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 3.7618e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 4.1834e-05 - 88ms/epoch - 6ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 5.0576e-05 - 88ms/epoch - 6ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 9.5879e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 3.3216e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 1.4463e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 2.3842e-05 - 93ms/epoch - 6ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 3.0649e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 2.3056e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 2.7597e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 3.9737e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 1.0685e-04 - 88ms/epoch - 6ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 1.0389e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 8.1306e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 1.3247e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 1.2315e-04 - 94ms/epoch - 6ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 3.5359e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 0.0014 - 88ms/epoch - 6ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 8.4606e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 4.6244e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 7.0673e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 5.9607e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 0.0032 - 93ms/epoch - 6ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 0.0104 - 89ms/epoch - 6ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 0.0137 - 88ms/epoch - 6ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 0.0100 - 88ms/epoch - 6ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 0.0071 - 92ms/epoch - 6ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 0.0033 - 92ms/epoch - 6ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 0.0013 - 91ms/epoch - 6ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 4.3743e-04 - 89ms/epoch - 6ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 2.1163e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 1.1783e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 9.0922e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 5.0249e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 3.5380e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 3.9010e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 2.2542e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 2.4236e-05 - 92ms/epoch - 6ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 2.3598e-05 - 97ms/epoch - 6ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 1.7642e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 1.4428e-05 - 103ms/epoch - 7ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 1.3528e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 1.1281e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 9.6891e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 8.3808e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 9.0589e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 8.1670e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 6.4787e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 6.7742e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 6.6301e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 6.2910e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 5.5988e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 5.7223e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 6.2402e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 4.4348e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 4.7085e-06 - 99ms/epoch - 7ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 4.2283e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 3.7205e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 3.2526e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 3.5981e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 3.1434e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 4.1208e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 3.8838e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 3.7537e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.9318e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 2.1283e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.0982e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.0560e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 2.3802e-06 - 87ms/epoch - 6ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 1.8953e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 2.1939e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 2.0361e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 2.9090e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 2.4513e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 2.0016e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.7414e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 1.4203e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 1.6707e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.5551e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 1.4089e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 1.7486e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 2.2621e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 2.2782e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 2.2154e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 2.4542e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.7164e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 1.6700e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 1.2366e-06 - 86ms/epoch - 6ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 1.2656e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 1.3145e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.2208e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 9.7976e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.3627e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.3238e-06 - 98ms/epoch - 7ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 1.5121e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 2.2132e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.1847e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 9.6137e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.0411e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 9.9310e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 6.9666e-07 - 97ms/epoch - 6ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 7.6775e-07 - 93ms/epoch - 6ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 7.6159e-07 - 94ms/epoch - 6ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 1.5374e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 1.6370e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 1.1970e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 7.2601e-07 - 89ms/epoch - 6ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 6.7501e-07 - 89ms/epoch - 6ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 6.0267e-07 - 87ms/epoch - 6ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 5.7283e-07 - 96ms/epoch - 6ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 9.8791e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 7.7203e-07 - 90ms/epoch - 6ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 6.5718e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 4.5553e-07 - 93ms/epoch - 6ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 6.8222e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 1.0772e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 1.1539e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 1.3958e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 8.8746e-07 - 96ms/epoch - 6ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.2953e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.5232e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.0473e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.3668e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.8515e-06 - 95ms/epoch - 6ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 1.2621e-06 - 100ms/epoch - 7ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 1.2244e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 8.6652e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 8.5901e-07 - 99ms/epoch - 7ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.0404e-06 - 103ms/epoch - 7ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.1845e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 6.1475e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 4.8967e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 3.6445e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 3.6744e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 3.9718e-07 - 95ms/epoch - 6ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 3.8614e-07 - 90ms/epoch - 6ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 4.2242e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 3.4063e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.2711e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 3.4723e-07 - 89ms/epoch - 6ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 3.9758e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 4.4793e-07 - 90ms/epoch - 6ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 5.0249e-07 - 88ms/epoch - 6ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.1864e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.2285e-06 - 94ms/epoch - 6ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 3.6580e-07 - 96ms/epoch - 6ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 3.8133e-07 - 88ms/epoch - 6ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.6619e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 1.9831e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.3087e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.0119e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 8.8847e-07 - 93ms/epoch - 6ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 8.3492e-07 - 93ms/epoch - 6ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 8.8915e-07 - 89ms/epoch - 6ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 7.5956e-07 - 89ms/epoch - 6ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 8.5361e-07 - 91ms/epoch - 6ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.1352e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.8192e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.8368e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.6701e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 5.9874e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.7594e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 6.4891e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 4.3239e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.8030e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 9.0890e-07 - 100ms/epoch - 7ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.3968e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.6331e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 5.8493e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 8.8628e-07 - 88ms/epoch - 6ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 3.7634e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 7.9048e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 2.8748e-06 - 90ms/epoch - 6ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 1.5127e-06 - 86ms/epoch - 6ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 1.4740e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 6.1169e-07 - 87ms/epoch - 6ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 3.1597e-07 - 87ms/epoch - 6ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 3.0787e-07 - 88ms/epoch - 6ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 3.3929e-07 - 89ms/epoch - 6ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 7.6238e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 6.6100e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 1.9555e-06 - 89ms/epoch - 6ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 1.1312e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 4.9108e-07 - 94ms/epoch - 6ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 7.2224e-07 - 92ms/epoch - 6ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 7.2940e-07 - 87ms/epoch - 6ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 1.2996e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 9.7427e-07 - 90ms/epoch - 6ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.1861e-06 - 87ms/epoch - 6ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 1.8856e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 5.7180e-06 - 96ms/epoch - 6ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 4.1876e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.9843e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 4.2110e-05 - 94ms/epoch - 6ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 5.6474e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 2.2968e-04 - 100ms/epoch - 7ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 1.4500e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 1.1646e-04 - 95ms/epoch - 6ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 6.3207e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 5.1895e-04 - 93ms/epoch - 6ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 5.6093e-04 - 90ms/epoch - 6ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 0.0079 - 90ms/epoch - 6ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 0.0149 - 96ms/epoch - 6ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 0.0110 - 99ms/epoch - 7ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 0.0031 - 90ms/epoch - 6ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 0.0034 - 95ms/epoch - 6ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 0.0066 - 96ms/epoch - 6ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 0.0026 - 98ms/epoch - 7ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 0.0011 - 97ms/epoch - 6ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 3.6390e-04 - 91ms/epoch - 6ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 8.5650e-05 - 88ms/epoch - 6ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 3.6862e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.3928e-05 - 96ms/epoch - 6ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.8628e-05 - 89ms/epoch - 6ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.6360e-05 - 87ms/epoch - 6ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 1.3703e-05 - 98ms/epoch - 7ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 1.0540e-05 - 91ms/epoch - 6ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 8.2065e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 7.9569e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 9.9934e-06 - 93ms/epoch - 6ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 9.1797e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 6.9860e-06 - 97ms/epoch - 6ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 5.2702e-06 - 92ms/epoch - 6ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 4.3922e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 4.0654e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 3.8788e-06 - 86ms/epoch - 6ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 4.7507e-06 - 87ms/epoch - 6ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 5.1633e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 5.1236e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 4.3162e-06 - 88ms/epoch - 6ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 3.9965e-06 - 87ms/epoch - 6ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 3.2705e-06 - 91ms/epoch - 6ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 3.1018e-06 - 90ms/epoch - 6ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x79197c7f00a0>"
]
},
"metadata": {},
"execution_count": 51
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "68bd6327-617b-41d3-9712-32c539ed930e",
"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": 52,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 3ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x79197c376a70>"
]
},
"metadata": {},
"execution_count": 52
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAGFCAYAAABg2vAPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACH4UlEQVR4nO3dd3gc13k2/PvMbN9F750ECfbeqySKpChKspolS+69xXFN7C+xkzfNjhMned/EceIm2ZblompZktUoSlRn750ESRC9Y4HtZc75/hjsAgtsmQV20fb5XZdNEZidGYDAnntOeQ4TQggQQgghJGNJk30DhBBCCJlcFAYIIYSQDEdhgBBCCMlwFAYIIYSQDEdhgBBCCMlwFAYIIYSQDEdhgBBCCMlwFAYIIYSQDKfTeuDu0j9L530QklH8C6s0Hdc/x6jpOEcNi/t5X7U/5udmVXZF/fjO0guarj1R7ss+Ntm3QMi0NL+qNeEx1DNACInq1fYFk30LhJAJQmGAEEIIyXAUBgiZwnKu+DQdl3V9Zm8xQkMEhKQXhQFCMoCx0TDZt0AImcIoDBAyQ8z03gFCSPpQGCBkEhjON2k+VutQASGEjBWFAUJmkLH0DjQ0F6XhTlKH5gsQkn4UBgiZBqh3gBCSThQGCJlhYvUO0CRCQkgsFAYIIYSQDEdhgJBpIhOHCmi+ACETg8IAITMQLTMkhCSDwgAhGYTmDRBCoqEwQMg0kq6hgqm+vJAQkl4UBgiZoWiogBCiFYUBQsiURJMHCZk4FAYImWbGO1SQzLyBV9sXjOtahJDpgcIAIZMkmf0JCCEknSgMEDINae0doHkDhBAtKAwQMk3N5CJENF+AkIlFYYCQaWwmBwJCyMShMEDINJeqQEC1BgjJXBQGCJlEkzWJkCoREkKGozBAyAwQr3dguk0ipPkChEw8CgOEzBA0f4AQMlYUBgiZQSgQEELGgsIAITPMdA4ENERAyOSgMEDIJJuISYTTbd4AIWRiURggJEPRigJCSAiFAULIlEBDBIRMHgoDhMxA03neACFk4lEYIISEURVCQjIThQFCpoBMn0RIQwSETC4KA4QQQkiGozBACCGEZDgKA4RMEakeKqBJhIQQrSgMEJLBqNYAIQSgMEDIlDJZWxoTQjIbhQFCSFyvti+Y7FsghKQZhQFCphjqHSCETDQKA4RkkKlca4AQMnkoDBAyBVHvACFkIlEYIIQQQjIchQFCpijqHSCETBQKA4TMYGMpPESbFRGSeSgMEDKFUe8AIWQiUBggZIqjQEAISTcKA4QQQkiGozBAyDSQzt4B2p+AEEJhgBBCCMlwFAYImSZo7gAhJF0oDBCSYagkMSFkJAoDhEwj1DtACEkHCgOETDMUCAghqUZhgBCS0KvtCyb7FgghaURhgJBpKJnegbGUJCaEZBYKA4RMUzRcQAhJFQoDhJBRaLMiQjILhQFCpjHqHSCEpAKFAUKmOQoEhJDxojBACCGEZDgKA4TMAOPtHaDNigjJbBQGCJkhaLiAEDJWFAYIIYSQDEdhgJAZJJ29A1SFkJCZi8IAITMMDRcQQpJFYYCQDETbGBNChqMwQAghhGQ4CgOEkKioJDEhmYPCACGEEJLhKAwQQgghGY7CACGEEJLhKAwQQgBoK0lMtQYImZkoDBCSAXKu+Cb7FuJ6amDVZN8CIRmNwgAhhBCS4SgMEELIFCI4wH3qn4RMFN1k3wAhZOpqaC7CrMquyb6NjBAcYOh5w4j+wwYIPwPTC2Sv9qPgJh/0eVQxkqQXhQFCCJlkgV6G6/9jg+JmAGcAABFg6D9kgOOkHtVfdMFYQl0FJH1omIAQkhRaUZB67X8wRwSBMM7AfQxtT5gn58ZIxqAwQEiGos2KpgZ/jwT3Zf3oIBDCGXzNOnhb6e2apA/9dBFCkka9A6nja9f2Nuxrk9N8JySTURgghJBJJGmcucVohhdJIwoDhJAwLVUIQ6h3IDXMs4NghgRDNrKAtS44MTdEMhKFAUIImUSSAci/wQcgRiBgArkb/JAtNMeDpA+FAUJIXA3NRTE/R70DqVGw3Yec9X71L5IAmFD/BJC1PIDi272TeHckE9AoFCGETDImAaX3epG3yY/+owYEBxh0NoHsVX6YKqi+AEk/CgOEkHF5tX0BdpZemOzbmBGMpZx6AcikoGECQmYgw/mmyb4FQsg0QmGAkAwRbRvjVBUeorkDhExvFAYIIRGiLS+MN4mQEDL9URgghKQE9Q4QMn1RGCCEEEIyHIUBQgghJMNRGCCEaKJl3gANFRAyPVEYIISMksweBUQlOCCUyb4LQsaGig4RQlIq04oQuepl9L5phPuyDhAMhjIF+Zt9yF4dAKPHLTJN0I8qIRkuVbUGMlHffgOaf24LBwEA8LdLaH/KgvYnzRBUSZhMExQGCCEplwlzB/w9EjqfNal/GQwCw/974JgBjlP6SbgzQpJHYYAQohkVHxpiP5hgXgUT6HuX5l6Q6YHmDBBCyBj4WqTIHoGRBIOvVUagl8F+yABfmwxJL2BbHIRtaQASvfuSKYR6BgjJINH2J4hlvCsKZvpQAdMBQOL5Fld/kIXeN4xwXdDBcUaPtscsaPgPG/y9cYIEIROMwgAhhIyBbWEw/gFMQASZ2nsgGAAW7kkI2CU0P2ylpYhkyqAwQEiayQYdZt24CEvu34i6W1fAmGWe7FsaJZkVBTRvQJW90g/ZJgAW7XsnBjsNYnxfOUOgW4bzAo0VkKmBfhIJSaPZ2xZj/Zd2wWA1gQcVMFnCuj+7BWeePICTv3lLSy/zpDI2GuCr9o/59TO55oBkBKo+50LTQ1YoAywiFDAJEEqCYQBJwHVej6zF0XsYgi4G4Qd0WWJwSIKQ9KEfMULSpGrjPGz91l0QXG0kJJ0MAJD1Oiz/0BaAC5z87duTeYtj1tBchFmVXZN9G5POWMJR+y0HHKf1cF3UAQpgqlKQtTSAq/+anfD10YYJnBd06HnNCG+j+vYsmThyN/hRcLMPkjHVXwEhKgoDhKSAOc8KU54V3j4XPH0uAMCqT22D4AJMiv6EuOQDG3Huj4cQcGmf1EemHkkP5KwKIGdVIPwxIQB9noJAnwQgRg8BB0yVkWnAfkiPjqctEb0M3Cuh900jXJf0qP6CkwIBSQsKA4SMQ/7cUqz65E0oX1Ub/ljL0auof+UEcioL4r5W0suo3jgPV/aeTvNdRsq54kP/nNEtStZ1AUfN6IYr1lAB9Q7ExhiQu9mPrj+ZYhwhwPRA9qqh72vQydDxjBnqfIMR/w6CwdemhoLCWyg8ktSjCYSEjFHhggrs/o+PoXT5rIiPl62YhS3fvCvh6wUXMEzByYSpNtOXGMaSt8kP68Ig1IkhwyaHSAKQgPIPuSEP++cfOKofPCxGT4JgsO83UIljkhYUBggZo01fuw1MliDJkb9GkizFHBoYeZyrawAVa+egbvcKVG2og6SX03W74xKr5gCtLIiNyUDFR90ouccLQwkHmADTC2QtC6Dmz52wLYqcOOjrlGPmgBDFLcHTIMPfLUFM8cmnZHqhYQJCxqBgXhlya2I3hKGAwDmHJI3O3IILBLx+bPjSLphyreGP+xweHH3oNdTvOTXuezScb4J/YVVSr4k1VJDpAr0Mrkt6CAUwliswz1LANHybmAzkbvAjd4MfQiDuaySDltZdoOmnNgCAvlBB4Q4fslcGEryGkMQoDBAyBtnleZqOkyQJQgiwYa0A5xyMMRgsRghT5BO3wWbCpq/fASGAK6+OPxBMBC1zB6brEkPuA9qfMg9tOMSgblNcrKD8w24YS7X32ScKD1lLA7C/F292oMDwroNAt4S2xywIDniQf+PYl38SAlAYINOIpJcx64aFqN2+FOZcKxztfbBf70ZudSFMuVY42+2o33MS7Sevp/1e/ONYAWC/1gVLgQ3GHMuo4QTGGIQQWP3pm3Ft3xnw4NQZIB5vzYHpRgig5REL3Fd1CDfCgw/v/m4JjT+xYtZXndDnpaa/3jxbgbkmCE+TDPCRySEyCKjUv3e9ZELW8gD0uTRuQMaOwgBJK0kvo2bLAsy9ZRksBVlwdQ2gfs8pXH/nAoSivaEz5lhwy/c/hLzZxeAKhyRLyJ1VhOqN88NP3oXzylB78xI0vHkOb//g2fD6fq3y55Yip6oAQY8fbccbEPRFdr/m1RajfFUtmMTQc6UdfqcXBlus2eJDGGMI+gJ4/e+fgKvLAXOuBbf++8fiHm/KsaBs5Wy0HL6S1NegVawVBWM1E1cWuK/IcF+JsQUxZ+A+oPdtI0ru9KbkeowBFZ9woeVRKzxXdepEw/Dcw/jdCgNHDSjYTqsMyNhRGCBpo7casfN7H0Th/PJwA55Vno/yVbXoONOI1/7m8VENbixbv3kncqoLAQyNx4e63kN/hor61GxdiIHWPpz49Zuazp0/pwSbvn4H8ueUhD8W8Phx5sn9OP3YuzBlW3DDX9+D0uU14IMBRpIlePqcms4PADqjHkIRcLT0Ii/OXIPhTDkWzedPpXjzBjKpd2DguEFtkEc9pQ/iDANH9SkLAwAgW9Sqht4mGc6zOgQ9DAMHE4Q2Bvh7aC44GR8KAyRtNnx5N/LnlgIYasBDfxYtrMTaL+7E/v98MeI1TGKjnuhzqgpQvroWWjGJYcGda3D68Xeh+OJvJpNTXYhd//ZRyIbIXwW92YCVH7sRBqsR5atmI6e6KOL+AcCYbUHQ64ek14FJLGJeQDyu7gGNxzk0HTdVJOodmMrzBoQAvI0y/D0SZLOAZW4QiosBCTqvuFeKOTHQ3yNh4KgewQEJuiyO7FUBGIpGn1AEoRYnkgT0eQJMAszVCszVCngQGDhkiL9VMgDJREMEZHwoDJC0sBRmYdbWhTGX2EmyhDnbl+LEr99E8dJqzNm+FEULKmDMMiPoD6LhjbM4+/RB9Dd2o3T5rLiV/KIxWI0oqCtD55mmuMct/8hWyAbdqOWBIYvuXR+zkVdfo8O1189gzs5lca8T9AXQU98OAOi51Ib+5h5klefFXGng7nGg41T65z4QwH1NRsfTZvi7hpZ1SiYOQykfnDAY+7VyNh8VBAQHul4woe8do1pJcPDzPa+bkLPBh5K7vGASwANA7+tG9O03gHvUnwN9noL8m/zIXuOH46Qe9v0GdQG4Em3OwCDOkL2cVhSQ8aEwQNKiZElVwsZb0sm462dfgMFqhBi2aFpn0KH25iWYdeMi7P3OY0mFgIjzx2jgQ/QWA6o3zY97XGhCX7xAULpiFtpONKBkSTUkXZTGXQi0n7oOHhjqpTj0P69g+3cfhOAcbFggEJwDYDj0v68kPechlcY6VDDd5g54mmQ0/dw6qgeAeyV4GxJ0vTOB3PWjvw+9bxjR987gKhHBIsJE/wEDJKNA0S0+tPxycHLisKf+QJ+EjmfM6NlnQNAuq2Ei/PkogYCpvRimatoLmYwPDTSR9NDYZa63GAYPj+xml3QyJJ2MG79zD7outCQdCJSAgr6rnXGPMWaZEwaG0L3Fo7ca8c4PnoWjvQ9CiNGNuAAq187F+x/9MkqWVgMA2k40YO/fPIb+5t6IQx2tfXj9759A04HLCe+LjF/XiyY1CMTqhmcjqgeGSAL6Ao68zZGT9rhfDQOxJ/wx9L1pRM+beriv6KJcV/170D7YSxHx+WGhYHDvAuvCICo+6tb660ZITNQzQNKi61xz3CdqAAk/L8kSzHk2WIuy0XW+BQV1peFJgvFwhePq66fhc3jiHucd8IAHFU3njEUIAWebHZ4+F17481+gdsdSrP70zdCZ9EMTHAeDjDHLjO3ffRAvfPkXsJXkYMkDm5A7OCnS7/Ti2lvncPgnr4IHxv+Ulze7GAvvXouKjfPBJIbO6104+/YFtFxsCx+TaEXBTO8dCNiZOms/HgHYFgfgvqYDdw8GR0mtIlh8pzeinDAAeK7pwH2JWmaGnr3jKUPNACFgqfOjaBftZEhSg8IASQtnRz+aDlxG5bq5MZ++tUy4U4IK8ueU4q1/eQa3/ttHYSnMAsDUiYaDQwuh84SeyO0NnTjys9cSnjvo8eP6uxdRs3n+mAMBYwxNBy6p5/MF4Orsh94cvXSvJEuAENj41dtQvKgyvDIBUIsNzdu9EiWLq/DCV3+ZcOJjPLNuWIgt37oLECL8dVXOL0f1okqc2HsaR148MeZzj9dUmkSoODU8TkuAsYyj/EMOeFtkiCBgKOHQ2aIP4XCtCy1irVDQjMF9RY/rP9Kj6vMumKtomICMDw0TkLTZ/58vYKC5J6LrXHAeMT8gEcYYlEAQrs4BPP+lh3Hsl2+gv6kbnj4Xeuvb0XTgMpwddgQ8fvQ3dePwT1/FS3/xawTc2tZcn3z0LfDg+N5Ie4cNR9RsXRj3fJJORtHCCvW/R4Qkxhhya4pw7y//DOZ825juxVKYhS3fvBOMsYiAE7rWih1LUbmwPPzxnCvxv09Z12fuLHU5S8PXxgFdNgfTAeYaBZY5SswgAACG4gksEsUZRBBoe9xM+xSQcaOeAZI2vgEPXvzqr1C7YynqblkOc4ENrq4BXH/7PFZ/ervmzXyySnOw9MHNaHzvIs4+dQBnnzqQsnscaOnFW//yR2z7u/s1Lw0cyT9sOMJgNYIlmIeQ6DqmXCu2/+MD+NOXH447kz2aebetAhiL+b3lCseSGxai+XxrcieOYrrXHNDnCFjmBmKM3auYDGQt0z5T31jCYSwPwtc6QW+tgiHQJcPTIMMym3oHyNhRGCCayUYdZt2wCKXLa8AYQ+e5Zlx9/QyCntgNQtAXwKUXjuHSC8ciPl66rAbla+bEncAX6kGYffNSMMaw8uM34vq7F/Duvz2vuVhRIkWLKrH1W3eFr5dsIPD0OdF5dmj54kBzj7oMUo5+npFDG9EwxpA/pwRly9VVCskoWlgR93sqyRJKZkUWPRrP3IFYpsu8gaLdXjT+2AahiKiBoHBX5LwAIdTKhM4zeiheBlO5gpw1fsjD6kOVfsCD6/9pQ8ItCGOKs4wwxvH+TgnmagVgAKP+XjIGFAaIJvlzS7Hjnx6AMccS7vKfvW0xVn3yJuz7h6fQcboxqfMdeeh13LakGjqTPqLxGtkgM8YgD+vurtowD1u+dSfe+Kenx/y1WIuzsfCutZi9bQlMuZbwdaJJFBD0FiMKF1Sg61wzAODyyyex5AOb4l5fS+jgQQUV6+cmHQbM+daEx/AxLFmMFQime++AqZKj6nMutP/BDH/7sGEVC0fhLT7kbRz62oJOhqafW+Bv1yHUYDuOC3S9aELx+zzI26wGVFMZR856P/oPGpBsoz62AMHQs8+Ijj9YAAiYaxXk3+CDbeHY552QzEMZkiRkzLFg5z9/EIYsszoWLUuQZAmMMehMBmz/xwdgLc5J6pwDzT146eu/QtvxaxFzCIIeP3wOD7jCozaYkiyhetN85M0uHtPXUjCvDHf++LNYcNdamPOso5Y0Dqel0ZZ0Mnb80wMw5amNsKOtD8cfUcsgj1xiyBWOgebeqIWGRl0bgKxPLqvrrUZkl+fHPy8XaLkweogg0dyBmcxco2DW15yo+YoD5R92ofLTLsz9jiMiCAgONP3UOiwwsKE/BdD5nBn9x9R9DAJ2BsUzUb0CqqA99DPF4Lkmo+VXVvS8EX0iKyHRUM8ASajuluXqWHiURiz0VD//jlU49ot9SZ23v6kHr/3t47AUZsFWkgu/0wt3jwMPPvmNuK/jQQU1Wxei71r8OgIjMYlh29/eB9mo11xfQMvyRxj1qLt1BU7//l0AwOnH3oWzw46lD24eWjro8uLSi8dx+vfvYte/fRR5tcUJz9t7pT2pr2/OjqUJ5yuAARcOjq2GwViGC6YLxgBTBYepIvoEQHe9Dv7OWCtO1DKFnc+ZYKkN4vp/26C4GSIbdTHi+FjnGaPhQxyD/939khnWeUGYyqfOzpdk6qIwQBKq2jQvbhEhSZZQs2VB0mEgxN3tgHuwDr+1ODvh8UIMFStKRuWGusGlidppmUMgyRKqN8wLhwEAuLbvLK7tOwtrcTYkvQ6uzv5w/YC9f/sY7vjhp2Lei+AcQW8A1/ad1XSPOVUFWP7RG1CzeUHC+2WMwd0fvf7CWHcyjDVUMHLegMEfgMkXwBv+ubipuj7p60yG4ABD/xED7Adj7F4YxsA9DG1Pm9UgMGrpYCpC1GCgCOU9HqqVHOPckoB9vwGl70/dRkpk5qIwQBLSGfUJG5mRG/2MlafPhYDHH3OtPqA2vgMtvTE/H0vR/PJxFxmKxZhthjnfBk9v5E6Grs7RmxJ5+1z4w6f+F7v/78fDOyWGvr+hZYlv/csfEfQmniSZV1uMWwc3WtJapdHnHvsY/1h6B/L7HNh07BLmXu+AJAQ4YxhYYEHHjfnwF0x+V7a/S4LjtB6Kh8FQwJG13A/ZDNgPGNDxrGnYNsKJeS7pkJqGPwoJMFUoMFYo8HfK8FyV41+LM3ibo/9eBp0MgT4JsklAXzh6fwWSeSgMkIR6Lrchp6ogZiPKg0p4E57x4gEF9XtOYv4dq6N25QshwIMKOs80oWLtHCj+IDrPNWuq2seVGNvLxaF1gyRbaS7ue/TLaDpwCYd+vCfc0xHzXgIKXvrGI5h/+yrMv2M1sivyoQSCaHznIs4+fQC9Vzo03d+mr9+hediDc472q53wxKnMqKV3IFogiNU7UNTdjwde2A+dwiENzg2RhEDOBReyrrhx9WMV8JZMTgk9HgQ6njZj4JhBLe8rAVCAzudNyFnvg/1d0xjOmsZWlTOU3O2FsUzBle9labiWANNFphh/D0PXC2Y4zw0tpzSUKCjc5UXWYppwmMkoDJCELr5wDHNvWR7z85JOxsXnj6bseqd+9w4q182FtTgnopHjCg/3CtzxP58OP037HB6cffIAzjy5P+55TXkWTY3m8ACQzJ4ITGKoXD8XBfPK8MJXfglvnyvu8Tyg4PwfD+P8Hw9H3bo5kbzaYhQMbhGdiOACEMDRl04kdY1xEQK73j4JnaJAGvGlMQFIAYGKF7pw5VOVE3ZL3Ae46nUQAYaBkzq4zg92/wsGDOZJERSDQWCss/vTQSB7dQCmSgWBXgbFpW3ud3CAgfsByQD4exmu/8gG7mURcwz8HRJaf21F6QfcyFlNux9mKlpNQBLqudSGE4++BQARJXRD/33+2cNoPXo1ZdfzOTw49qs30FvfDmVYNT97Qxd8Dg9yqgsihi2MWWas+tQ23PXzz2PR+9fDmDW67nvBvDLMu3VlwmuPrI4Y+rvWqomSLMOcZ8OS+zdqOj58nTEs98upKtR8rMfpxZ6H96Hj2sSt/a8a6EFxr2NUEAhhArC0+WDsTP9KBsGB7leMqP+nbLT+2oq231vgOmeIUWyIjfhzokWOSzCjQMF2H0rvU3t0uOYHeIagXUL3K2oPR/dLJjUIRJ3PINDxRzN4jH8K1yUdmh624NLfZOPSd7LR9LAFrkv0LDmT0L8m0eTU795BX0MnFr9/A4oXqU9yfdc6ce4PBzVPdEvEUpiFebetwvzbV8GYbVbHzwcbfW+/C+YCKww2U8z5CzmVBVj9qZux4qM34O1/+WPEzn/LPrh51HbBIwmhPj0P7w0YS1VCSZZQt2s5jj70Wvq2IWbaJlsCwMnfvo0jx69rvpdUDRWUuPo1Xc/YE4CvOL1DBR3PmtB/INl1/5OnYJcXpnIOphMwVyuQBqdWcD/Q+lsrtPdaMNgPGZC31QfHaX3s3RnBIPwCjtN65KyJ7B3o2WdE98umiO2U3fU6uC/pUXirFwXbMndZ6kxCYYBo1vTeJTS9dwmSTgIYS8nuegAg6WVs+PNbMWfH0ogx/eFzFIzZFk0NM5MYZL0ON37nXrzwlV/C0dqHZR/Zisr1dZpfnwp6ixE6swEBV+rfKEtXzMLGr+xGVllewmP9Lh/OPLkforYs5feRiE+XaAa+iuvT20D7OiX0H5isrf20LCkcrXevCXKWQM5aP0xlHDAMbsJ1wAB/h5TUuYSfwd0gxwkCgyTA3yPB2yxBcUnQ5XBwP1ODABD5+sHehe6X1eWU5hoqhTzdURggSePB1K5b3vqtu1C9aV7cp/ZkntDV8Xdgy7fuQlZZLnRGbY1S3HMm2UOgBIIRZZrZYLGkOTuWwpxvg7Pdjvo9J9Fy5EpS+w8UL67Ejn96ANAYWs488d6YdkBMRe/Axfwy+GQdjErs6ytGCa5Z49nON7GBY3pAEinYKXAsGCALZK/wY+CkAQhquwehMATtDD17jeg/ZED1nzmhzxWwHzQkvV8FAMhmbZsy2Q8a0Pv60MRJycwjegRGkQT63jPAXBN/u3Ay9VEYIJOqoK4UNVsWpPy8kk5Gbk2h5kZcy5wArXsX8KCCa/vOhrvl9VYjdn7vgyicXx6eBJk3uxg1Wxag+eBlvPG9P2juZVn1qZsBxmJWMQztEMkYcObJAzjzRPxJlenk1+mxd/ZS3FZ/POZzbOemXAhdeqcuBQcmc2qUgM4mUPYBL4rf58XVH2SBjypINFJkAaGgA2h7wozqz7kR7E+uVwAQkLMErHMVmKqC8DbH7yHgrsjPcU+Ce+UM3sbUL9UlE4/CAJlUs25cnLa1/0n1JiTaK0DhmoYQuMLBFQ5LYTYeeOLrEEJA8QXDWxKHVjOE/qxYOwerPnETjvz8tYTntpXmhudrxNP43kUc+dneiOWNhvNN8C+sSvja4UIlisdSiChkT+0yGIMBbG84A8EAwRjYYPDq3piL7o25Yz63VrrsyazAxxDsB5p+YYEywMDdEpJ+tOcMnit6+DolyGaBYCCZMMCQf4MXTFY3XWp+ONZ8AxE+fuTrE16BssCMQGGATCpjdnq6iMeyA2Hcc0kMzYfqUbW+btS5h+9E6HN6YM6xonRZdTjgxLsXJkmYd/sqnPjN2xHDCsWLq1C1cR50Jj3sDV24+voZmHITb0IkFI7e+vaodQ7GEgiA+EMGiYoQCcbw3Pw1uLq+GAuvtMDq9sFlMeH83HJsnHM96XsZi5zVAfTuS6ZmQKqXFDK4L+oi/j4W3iYZunyuradjcFgkZ4MPeVvUnytrnYLyj7jR/pRZfeKXxLCFC2P8epmAbRHVJ5gJKAyQSeXq6E+6EJAW4w0Cahe/gBAAhMD+H76EK6+eQt3uFVj1yW3h5YvDg8BAWx+yByf1De/pSHQvOqMeRfPL0XaiAcYsM7b93X0oXlwFHlQgAEiShNWfuRlHHkrce8BkCe6e2AWP0hEItHDazDi8fG7Sr+N+wHlOj2A/g5wlkLU4ACnKbXAf4Dyvh+Jm0OdxWOcFwWSABwBPoww5W4EyoPURNlTmN/TfqTD+83ibJXgbZMQPKwKQgZxVAeSs86vbGg+TtSQI6wIHnGf1CPRIkEwC3IvB5YdJ3iMTYDKQu4FWE8wEFAbIpKp/9RSWfXhL0q/jQQUBjx/GLHN4HB5Q6/qHwsV4AoGAQNN7l9B7tQP1r5wMlxluO94A9hkp/LQ//BpZJTlj7pEIDUFs+/v7UDi/AkBkoJD1Oqz/4i3oqW9H3uzimMWTFF8Aje9ejHuteIHAZDNh9rJqmGxGOPtcuHayEUG/+uSnNRCkaltj+0E9Ol8wQ/jY4CQ2oENvRuEtXuRt9YMxdZ+K3jcN6NlrggiEjmOQbRx5N/jQ96ZxsEBP6BE4uS72qUPA/p6W3g01yIRqEkQj6YDs5UPLBx2ntJZQHja8wQCmAyo+5oY+P03LZ8mEojBAJpWrsx+nfv8uln8odiAY/vQNqOPyvgEPXv7mo7AV52DRfRtQvnIWmCTBfr0b9sZuzNq6cFzv5QwMb/7zHyLe/2wlObjjR5+C3myI2uDHWw0RD1c4eq91omRpNYoXRW+kmcTAFQHFH4RQODgQEQhCIeTow/s07WkwKhAwYM3uFVi2bTEYY+BCQJIYNr9/PS4duoKLh+rR09w77h4CrfqP6dHxBwvC/wCDk95EAOh6wQwmA3mb/eh9wzi09G3YcYqTofvF4Y1nsj8MyU3SS39w0H5+TSsHhrEuCIIZBIQ/Tm+DHijY7oX3mtpkmGuDyFkbgM5KQWCmoDBAJt3JR9/CvN0rYMq1Rm9kBz8W8PjhtbtwZe9pXHzhGHz9bjha+9B2okF9smYMQuHQW4woWlAOS0HWmCYmCs5hb+wZNc/rpr+9D3qLMWVzEQC1EZdkCXf896fQcbop7mRKSZZQtLACe/7qt1j7+Z3Iry0Jf87b58LxR95A/Z5Tmq89PBCsumUZlm9fEv7a5MHGR2fQYdGW+Vi0ZT762u147+lDwJWOiECgZfOikTsYxiM40PVS/HLA3XuMsC31o2dvrGAS6upPdyM9lUoWA4BAzprkemUkA2CdF4DzTKxNoxgQACzVCgq3jb/Hh0xNFAaIZjnVhShaWAEIgfZTjXC221NyXkthFsx5trjH8KCCC88exvFH3oz6+dAYPwAE3D68/JeP4tb/+BhsxTnJ3xBjuPDckYgPzbt9VXiHwfEYOYwQ+m9TrhU1W+ZruDUGe0MX/vSlh5FXW4ys0jz4HB50nm0aU7VDw/kmYGUtlt+8JGHIyS3Owe4v7MCLP34V/dBWXXAsPNdlKAkmyXGvhM7nzRBx565NRCM9tYIA06k9JsnydSaYiyAJ2A8ZYJlD9QRmKgoDJCFzvg1bv3UXSpfXhBszIQSaDlzCe//3Bfid49sv3VIQPwgAUNfWa3jKz64sgN6sh7O9X302TDCGH+vzVRvq0LT/Erx2FxbevRZrP78zJSsUYr1ekqWI+Q6xePvd4e9339VO9F3tHNf9AEBtngWyPvH3NlTMacPda3Hx2b1xjx3PvAHFpe177DxlCM8lmHxaeghSPSlxtLKPuKHLTv4bErQnqF/AGQK9tJXNTEZhgMSltxhx679/FNYitQ4+GzY5r3JdHXZ+/0N46RuPjKs0cdnK2oQNrSRL6L7UFvPzNVsXYuXHb0R2RT4AREwqjCcUbEY+rZevrsWuf/sIDvzwJaz9/M7wx9OJSerExFjfC65wXPzT0ZTvd2CwmRLu2xAiSQyFlfkoyM9GT+9ASu8jRJ+fRF2ARCV2E58AqWuc46/fty0JQLbxwdLIKfxZGgxEpQ94kLVwbMv8ZItAMOacAfUasm1KpC6SJhQGSFx1u1fAVpITtaGQZAkFc9UKguPZrCi7Il/Te3L7iWtRP77xq7eh7tYVo+5N65N8tGMkWUJ2eT5Wf2Z72ooiRSWEuu/DiDDDFY6+qx04+9SBlF/S0daX9OTHkgEdeob9Xcu8Aa2MZRyGMgX+dklDYz/2xrz4Ljecl3Rwn9eP+RxDGJiBQ/gxdC5ZwFDIoS/gMJUFYarm6HrBFLlycZx02Ry2xQHkbvTDWBI7RAmubi7kuSYDTJ0AaJmjhDuiclb70fO6Mfb3WzDkrKT5AjMZhQES19wdyxDvjZIrHHO2Lx1XGAh6/YNPprEbXME5Ap7Rb0bLPrJ1VBAIifbUnxQG5M8p0dTDEM3IVRDarsnAgxz2650omKtuLuQbcOPiC8dx5on3NK0USFbr0atw9zphzrVoDgUehxdIcb2opwZW4b7sY2AMKLnbg6afWQElUWOvdUnc4HGDSw9zN/uQuzGAvE0BtP4ecJyMt6OfFgLCL0X83VCkIGiX4O/Qw3Vu/PtjRGAC5togqj7rTlimw98loflXFgS6ZYT3k37NBEOJgoqPu2Eo4Mjd5If9kAGKC6P3cJAEjGUKbIupuNBMRmGAxGXKtcQtwyvJUrjUbjJkgw4Va+fAnGuFu9cZ98mbKxxNBy6P2iApqywv7pJEYHxd+4wxYBzDpGOqN8AYmMTAmITfv/8/IBt18PW707cVMtTJl/v/8wVs+7v7IRIMrwguYO/sR29rH5DGJYaWWQqqP+9C00PWwaftOGQBKICWYGAo5ci/wYfslYFwI1p6rwdBuwRPgw5j72kYXcbX357it9dwxUAG68Igyh9MHAQUF0PjT6xQ3IMHDmvo/V0Smn5qxayvO6CzCVR/0YXW31jga5WHzcVgsM4LouwBN5UdnuEoDJC4XJ0DMGabYz4xckWBs8Oe1Dnn3bYSqz51MwxWo7qpjsTAgwogjd6AJ9QInnnivVHnqdu9QvN7d7QeAi1P7uPuXRgDSZaQP6cEFWtqYS7IAmNAx5km9MSZMzFeLYev4NVv/x6rPnGTumIkitC/xcHnjgIYXYRo5FDByEmEI5cXvtq+ADtLL8S8J3ONgrxNPvS+EWeMXRKwLQ7Ac00HxYkRT/fqD0fORj8Kd3gh6RG1eqFkBIrv8eD6D62AMkUnyUkCBdt9kPQC1oVBGIu1zatQn/ZZ9F4Pru6bMHDMgLzNfhgKOGq+4oS3WVY3H5IA69wgDEWTubcDmSgUBkhcl14+gQ1fvjXm5yVZxuWXT2o+X93uFdjw5d3hv4d6HZgsDRUVCioQApB0EgJeP97+12ejNoQ5lQVJBwHBuRpAZAmCC82TDCfDDX99D7iivhGrEyhb8eb3/gBXZ3om7nWcuo6XvvEIrMU5qNu9AvPvWA2jbahwj2vAjfeePoTmC61puX40uRv86H3bGGO4QH16LbjJB/kOL7r+ZILjjH5UN3f/fiMcxwzI3exD4Q5f1CfczmfNgDKVlglGYgaBwh3Jl/0dOK5POD9h4Lg+vByRMcBcpcBcNfYJwWR6ojBA4rqy9xTqdi1H/tzSUQ2n4BytR6+h5XC9pnNJehmrPrkt6udCT+CePheu7DkJ2aiHvaETDW+eR9AXfZw84PUPNuzx38TDQUAIMEkCC30ZU/e9P2z49zy/tgS7fvBRPP+lhxBw+SDpZdRsWYDqzQugtxjQ39iNyy+fgL1BW3GfWFyd/TjxyJs49bt3ULZyNnQLKuGyu9BW36Fpq+dU0ucJVHzEjZbfWAAuhp5wB7vMS+/zwFShBqbyD3sQsHvR/LAF/k4Zw/+BuY+h93Uj/J0yyj8S2b3u75LguTqV3woFssY4Xs+9DInmXCieafCLQNJuKv8GkCmABxS8+u3fYc3ndqD25qXh9ehBXwCXXjyOY7/cp3k8u3zV7PAGP9EwxmDJt6H58BV0nWtOeL7Gdy6idtsSbV8IRj/ha9mSeCqRdDKsRdmYe8tyXH/7PHZ+/0PIqSwIrzwoXVqNhXetxcnfvo2Tv3l73NfjAQUth+rhd8R+Ip2I8sS2RUHM/ksH7AeMcF/SQXDAMjsIXR5H/xEDul4xQbYI5KzyAwyjgsAQBucZPdyXdbDOUxtXf7eEzheT2dFwogmAAXlbx7YZkKFIQbA/TiBgQvOQA5nZKAyQhAJuP/b/54s49vA+5NeVAlyg+1IrAu7klhqZciwpPa7pwCX0NXQip7IQkm6KjvWmwZztSzFn+1JkleYCGOo9CE3CXP7hrRho6R3XCo/hDOebAEDTboepXGIYcQ/5AsW3eYHb1J0IW35lgf2AMbw6QBkQagnjRJeWBOyH9LDOC2LguB5tj6dnC+3xG5zPIgNlH3LDVDa2Bjtngx/u+jgrGQSDsYKGBMi45kqTTONzeNB27BraTjQkHQQAwNWlbazb1amt1K3gAq9++/fovdox+Hc+4d3YE41JDOZCm7rkMcYKDME5lj6wKeXXDoWCdLkv+5im47pfNcF9ZfA5JjwxbnCSHB/871g4Q6BHhq9NUoOAQPTJdZNNBxTe6kPttx3IWjL2JX26rES/DwKuS/RMSCgMkAnUfvI63N2OmMMKnHP0NXSh90rHqM/lzipCybIa2AafhkO8fS68+NVf4pVv/QYNb52ftMl+yRBCjHmpIFc4FH9QXX0RA5Mk5NYUwZxnHestxpTuQJAI9wP2A4Y4DXiCf38mIGdx9L1nGDx0Kv68CEh6gfytPujGWfXPdV43VFsgKgbvdZ3mEtBk5qJISMbMWpyDhXetwaybFkNn0qO/sRsX/3QU1/adjdrYCS5w4EcvY9v/uW9U+VuucEAIHPrfVyJeU7l+LlZ96mbkVheGP9ZxuhGHf/pqRGjoON2IjtONyK0pQk5VwcRVDNQo9PVJOhltJxpQWFem7oCY5LwFSZbQ39CVcGMnAFPue5AKvg4ZwjeOqoSCIWdVQB1SGFlcJyWG7z8w9poF3MPgOKtH9nLtRaa4H3Cc1sPfKUEyArbFAfB4JYaHvzYAzLyfFpIMCgNkTAoXlGPnP38IskEXHrMuqCvDlr+8EzVbFuCN7/4BQhk9ztl88DJe+7vHseazOyIaePu1Thz66avoPDP05FmzdSFu+Ou71RK9wxQtqsSt//4xvPyXvx7Vi7DvH5/Crh98BJaCLIAltyxw+BBDsq9LdHzzoXrYr3Wi4S11dcSSBzZizvalkJis+VqCc7SdvI6r+86iYu3cuMd6+lxw9zg0fw3ThbZvVayDBIxlHFlLAuhKetLg8J9BrRURx1fRsOtFIzqfM0EogKlKQd4mPyxz1SEDacQ0AMdZHdoft4D7oPb3CqD7FROM5cHBoZPYJBMfdw8Emf4oDJCkSXoZ2/7u/oggAAxNZKtcV4dF967D2Sej19FvPXIVzx35GfLnlMCUa4W72wH79cjlcJJOwoY/3wUAowoeha6z9vM78cq3fhPxOWe7Hc994eeYs3MZarcthsFmgt5igDHHMqqgUSw8EIRsUN9ttTT0Whrz079/B71XO7H0wU1Y9sEtg1UGtTcWAY8fl144huO/fhMAsPZzO2DIMketkyA4x4Xnj6StaqHhfJOmyYRpuXaJAsnEwb1jGeFkKLrLDaZTa/M7To6uSRDvtbmbfbC/ZxgMp+nuVmcROwm6LzO4Lw0lAGOZgrytPmSvCsBzTUbro5ZwxcDhjb+vTR7spIhxz0wgd30AjFqCjEc/AiRp1Zvmw5wbZzyaAQvvWotzTx8MN0hMllC2chYs+TZ4+lxoPXYt6tyAkIp1c2HMjr2qQJIllCythq00F852e8TnAm4fLjx7GBeePQwA0Jn02P2fn0BeTVHcryvUOEt63aiPjZUQAjyooHhxNdZ98RYULaxMqqKhq9uBN7/7NPoaOqH4hiaSvfHdp7Hjux8MDz0ACG+B3HaiAWef3D+u+06V8WxlHI2kB/I2J9hUJ46Opy2o/oILeZv9cBw3aHhFqIqhD8Xv8yJrcQDtfzCrdf7TakTjPeJr9bVLaH/CAs91H/zdcQpnhF8n1LkDw8MPEzCWchRsH98W5GRmoDBAkla4oBxKUIEcY0yaMQZLQRbM+Ta4ux2YdeMirP38zogJbd5+Nw7/9NWYy99sxTmatiG2FmWPCgMjKf4gTHGCRbT7TxXGGCRZxprPbU/q/EII+AY8eOnrv4K7e3R3f+fZZjz/pYew8O51mH3TIuiMegy09OLC80dQv+dU1CGamaJguw++dhnOs/phDZy2p/VAt4Tmh62o+bITxXd60PmcOcFr1Y/nbfKDMcAyR4FtQRB970kaexVStdfByNOqn+8/qKHGgySQtTwAxc3gvqgDwCBZOHI3+FFwky9qiWaSeSgMkKQJRWh6e+MKV8f9/+ruUUv+jNlmbP3WXQAQNRD4HB5Nk+t8Dk/CY7IrC9Iys16rZCcJBtw+XH7lJM48sR9euyvmcY7WPhz631dGTbqc6ZgMlH/EDdcFHeyHDAh0S5DMAt4WOXFJYcHga5XhuqRD3mY/fB0S+g8m7iEQw+fxJTX6Ei2oJAoISQQIJhL3kDBANguUP+gB9wM8wCCbxVAlTkJAYYCMQduxq1j8/vUxPy84R39zL3z9bqz53Pao3eKMMQgusOYz29Hw5rlR49tN+y9D8QehM0YvmBK6hpbSu8VLJmd8e6ye+fSP4bW7J/s2pjQmqZUJbYuGhk563jCg+yUNRYQkAccpPXQ5HPo8joQNryygzx/qaTHXBtH3rpbH6VCjnkwYTHKeh9DQK6IAhsLBPS4MgGSgyYJkNMqGJGmtx6/B3tgdc607kySceXI/ihdXwVqYHbNbnEkM5nwbSpfXjPpcwO3D6cfejfo6wQXAGI794vWE96q3mbD6U9umRTEiIQQcbX0UBMYo/0Y/CnZqGP/mgOOUHtf/MwvdL4eGCWL8fEgC2SsCkIdlDNvCIHQ5XH0qjynx0MNI+nwFeTckX3aYGRCnloAAk4Hslambt0FmJgoDJHkCeO1vH4er2zFYQEd96giFg9OPv4ere0/DFG+S4TCxjjv92Hs49qs3EPQF1Il4g+PgSiCIlkP1MGSZIRtid24tuX8jPvDbr8BgNU2LYkSMsfDXOJ3kXBlb3fxUYwwo3OGDLpsj/hM2i+z2DzfOI14jCehzOYpuiwwYTAYqP+mCZBaDgUCMeH1ywVMycRTe5sHsbzlRuMM37LxaCFjqAtDn8tGBgKmBpPhuD2TtU2ZIhqJhAjImrs5+PPeFn2H2jYtQs3Uh9BYj7A1duPTScfTWtwOA5nXu0SbIhZx5/D1cfP4oZm9bjMX3rUdWaR4kWULZqlpUrq/D2s/vxNvffwatx65FvG7pg5ux8uM3jv0L1CCZVQFa5VQWwFaWC2ebPaXnzSS5m33oftmUoE0e+e8W6m5XG1DJKJCzzo+CbT7I1tEnMpZxzP4LJ/oPGzBwQg/uYzCUKMhe4Uf7Y5Yo54+Nexm6XzLBWMJhWxBE5afdaH5osGZAaLlgHK4Lesz+lgO9rxsxcNQAEVSPN5YrKNzhixhKISQWCgNkzBRfEPV7TqF+z6mon+863wxHWx9sJTmjagUAane/u3sAHWca414n4PFh7i3LYC3KARBZWc9gMWDb338AL37tl+i72qkua7x7HVZ87IakvpZkG/Z0DjtY8rMoDIxD3mY/nGf18DbJIybXJZqYxwAmkLXah6xFQdgWBuNOstPZBAq2+VCwbahnxHU51o6J8ahBpOsFE6zznTBXKaj9lhP9R/VwntXD0xDvnAxQAOdZHUrv9aL4di8CdgmSUUCfKyA44DynQ/9RA4L9DLocgZw1fljnx//aSOahHweSPgI4ODjTPTSUEP7U4ITBg/+7J2GvavnqWhTOK4+6zJBJEhhThwQAYONXb8Oaz24fdVzMW+QC7h5H0k/46QwOnl5nUseTSJIeqPqsC/k3+SCZtFYOHCQYHEcNaP21Fdf+wwZ/T/S3SMUD9L1rQPMvLGj6uQXde4wI2Fn4qTxpgsHfqW6gBACyVSD/htAciMTllx0n1RURkhEwlnDocwW4H2h+yIKWR6xwntPB26SD86wOLb+yovlhCzhNIyDDUBggadV65Cpe+z9PwDHiSdfR3ofX/+FJNB+8nPAcNVsWxN2YR9LJqNmyABXr56Ju1wowpr26H5MYjj70Gjy9zlGBJVV8Ax5NcwG4wsO9KWR8JANQdKsP2Wv8SYy/DxrsTQh0S7j+31YoI1aveppkXP3XLHQ+Z4Lrog7uej16Xjfi6r9mIdAjJX+9YRRn5Fuy0Lo1QZQfr47nzHBfHez8DdVEGPza3Fd0gzUWCFFpHiaYrPKjIZO9WxoZu9ajV/HHz/wEBfPKYCnIgqfXie6LrZpfrzcZgARr9SWdjAV3rAZXFEiytupwQgi0Hr2Ka2+cAw9y3PDtezQPF/CgAnevE7binITHvvX9Z7Dt7+8HoItZRElwdSOjow8nXiFBtAv0SEmv1huibhjU+GMbar7ihKRTewSaH7aAe0csGRQMEAKdfzLBPEuB57o8po2QdDmRrbqpIjQZMv7whnl25LyAoJNh4Kg+dg0CwdB/VI/CW720LwEBMI3mDEx2GJnupkKY6rnUhh60Jf26/pbeuG/oQqhd/YXzyzUHAUDt6reVqI35/PethuBc0+tDSxvf/ffnsPP7H47ZwHOFo+tcM9pPXsfhn7yKZR/aEjM8ONrs2P/Dl9B5tlnz/ZPEJKMYmhs4Rv4OCT17jSi61YeBowZwT6zaAeqcA8nCocuWELQjxnHRXipgrFBgLBkKA95WCV1/MiU4h/r1FeyIXNHhuaohjHAGT4OMrCU0wZBMozBAxmeqhiktIaX+5RNY9uDm2AcIwJhljlmgKB7ZoEd2RT5Kl42udTDqMkJAcPV/b//gWXScbsKp372DFR8dPVmRDz7pX339DO7++eeRXVkQnjvAgwqaD1zGlddPQ2cywNluR9f5lqTvnSSWtTQAx4l4FQa1VPtjsO83omC7D84LCd4yOYPnijq7/+r3s7R18zMBSEDx+4aWMHpbJDT+2AYRt51Wf55K7vVAHlEDSWjdt2H6rWQlaUJhgEwqLSHFD+Dgc0ex4e414JxH7D6oPqUDsj75H2XBOXrq25A7K/4GRiF91zrQ+O4lXH75RHiS36nfvQMeULD0g5uhNw81Ou7OAZx67F2s+8ItkPRqb0N4IySdjKpN8+Hpd+Pgj15O+r6JdraFQRhLFfg6o+0lMLwuQPzGk3sZ/J0SBEfCYwUHdFYBQ7ECX0vi1QWSScBQxDFwVA/GAFO1gs5nzWoQiNmoC+iLOUrv9sAyZ/R8GlNVUMPXJWCqij0Xh2QWze+g/XPGvpvFVClKQqavM2+dh9PuwsqdS1FQkQ8A8Ll98Lr9yMqzJtzQKBomSbj4/NFwY53Iqd+9i8Z3L46+tyf348LzR1C+Zg4MViMcbXZ0nL6OG799DyS9FGMVBMP821fh3NMHp/2EwfG8N6Qbk4HKz7jQ8ogF3ibdUGEeziBZBHLX+9G7z6T5fOZqBZ6rutiNNBODDTGQuy6AjmcS/2xxL4O3UQdvs4z+Q0ZY5/vhuZ7orZmh+HZv1CAAAIZ8AeuCIFyXdNGHCyQB6/wg9Hk0X2CiPDWwatKu/R0Nx0xIz8BUfrMYjkLL1NZwqhENpxphzjJB1skI+AL4yD99IO6Ev3gTAk/tO4tGP4cOEgK+APRxhhkUfxBtxxtifj7oDaDxnQvhv+vMBlRtmh/RizESVzhmb1uMU797J+YxZPx0WQLVX3LB0yDDdVEHEWQwVSiwLQ2ASYDnuk5t4OOQzByGEo5csx+9bxgR86lbMORtVtfsZa/2w35QD1/byHoHwFCvBBv63GCj7bqoZbhLINAbPwCX3udB44+t6nHh4kVqT5o+n6P0vsSbfMXiviaj720j3PU6CAGYZweRv8UP67zJn38wmY3udEbDBMNMdmihMKKNx6GOrVqyzQln/kf7vBACHocHh/50DAAQ9Adxat85rNq1LObx5589jIBb+7+PwWqMGwQAdYhDa8lmMj6MAZbZCiyzRz9JV37ahWv/ZkPQLiF6t7pA3mY/JB0g5QuU3u9B+5Nmdaw/9NQ9uHtg7uahin+SHqj6nAsdz5rhOKkf9oQ+LAhEv1stXxFkc/ynel2WQM2Xneg/ZID9kAGKQ4KcxZG7zo+c9X7I2jtEIvS9Z0Dns+Zh20cD7ss6uC/qUbjLi4Kbx/Y+Ro345KIwMIWkK4zM1JDhdfkSPtFHwxiDJduC8rmlaL2slk4+/uopmKxGLN66IKImgCRLuHiwHgcPXoEYnN+gZdKjz+GBEgjGncvAJAZ310BS9z6TPTWwCvdlH5vw60o6oPqLLjT91DrsaZuFGzvbkmBEA5ezOgBDEUff2wY4L+gBAZiqFORt9sG2OIjheVI2A6X3eGAo4GqDPJDMLoaxx/yZXsC6MPHsRNmsbuCUf2NqKgx52yR0PjuYIoYPPwz+d/crJphnByNCFzXy04PmMOCoif5DmXWdxpymulSEjKkYKLjCcfFgPRZtnp/0nAGucBRWFYTDAASw/5nDOPfORdStrYUlxwKPw4PLh6/C3tEf8Vq/hlCg+IK4tu8sam9eCkkX494YcOX103HvM39OCcpWzQaTJHRfaEH7yevav0iimT5XYNbXnBg4bkD/MT24m0FfqD5FWxeMLt1rrlZg/rAHQPyu9qCLoeknVvi7hnfVaxV7e+KCm31jfrIfD/sBg1qqLsYqBCEBp98sQVNB6YTeFxm/cfcMxAoJE4GCyMQZa6BId4g4/uppVC2qQFaeLalAwBiDEqWqYX/XAI68eELTORKFgpO/fQeV6+tgsBmj1i849dt34OmJXnrYlGvFDX99N0qX1YR7KiRZQn9TN9747h/Q39it6R7TIZllqr7q6VPzVjICuRv8yN2QunvueMYEf7cUZ1VALAKFt3nR+5pJ3bBIEmoDLKtBIH/b5IRzT0OMCYmDGAesTRq2kSZTzrQeJpiIIEKBY3zihYhUBAWfy4fn/+tlrLltJeauqYVucGUAVziYFLssMZMYmlK0tj9WKHB19uOlrz+C9X++C+WrasMf99pdOPX7d9F04DJyqgvh6uxH0DvU5SvpZez8/oeQU6mumhgecrLK87HrBx/B81/8OTx9rpTcP0mPQD+D80ycKoCxSAKWuUEU3OhH3kZ106WAXYJs5chaEpjQ7YhHdvHPFU0wI35YEgmqhZKpaVqHgYmQ6sBB4WJIqoKC1+XDO08ewMHnjsCWZ0PAH0TNkkpsvHtt1OO5wtF0vgUDXdq2WNZq+BNzKBg42vqw9zuPwVaSg+yqAgQ9AZgLbFj2wS1Y98VbAABBXwBX9p7GiUfehM/hQc2WBciLUftAkiUYbCbMf98anPj1mym9fy2mavGqqcjXEm0VQSICuiyB0verww+SAcheqXWDgvFLNL4/UGeFqdMfc/sFwYCBeROYVkjKUBiYYOMNF5kSJsYSFAK+IPra7QCAs29dgC3PhqU3Lgz3EgguIMkSOq934Y3fvZuO2w4b2Vvg7OiHs6Mf89+3Guv/bFfEpkg6ox51t65A2fIavPj1RzD7psXgCo857CHJEmq3L5nwMEBBIElJ/6oLGKsUVH7SDZ11Yn/PtU7y612ZjaIDdkARowKBgBoGelcn3q+DTD2aw8BEjf0ZG+OVDiVjCRMzLUBECwrRAsLBZ4/g0qF6zF8/F9kFWfC6fLhy7BpaLreNq1Z9MoaHAlOuFWs/twOAWvBoOEmWYCvLw9IHNsGYbU44/8FgnbjZYxQCxsY8KwgmCwhFy++sWpK44qMTGwSSnekfzNah4YFSzHqiHQiKUNkCdZ8mCWi8pxS+QnoPn46mXM9AOkNHpgaNZALEdA0OIwNCKBz0tdlx4I9HJuOWIvgXVmHBtkVAnLoIkiyhbvcKNB24jIK5pZB00avXCc7hbJ+YqoUUBMZONgM56/2w7zdoGi4o/4gL+pypGwRCXLMsuPClGuSfHIDtmgcQgKvahN6V2QhmTbkmhWiUUf9y4w0amRAmtASH6RAYhoeDqbIsMrsoO2GHhMFqwvW3z2PO9qWxD2IMF184ntJ7G2msIWAyVxdNRUW3eRHokdSqguEiPZHLBQ0lCso+6IapbGJ2DUrFun/FKqNrUx66NuWl4I7IeL3aviDu57+zOPE5MioMjNd4wsRMChKJ3vCnWliI1Wsw0fwef8JhZMEF2k9cx+VXTmDuLctHrYbgCkfX+WZc2XsqffdJvQEpI+mBik+44b6sQ/8RPQJ9EuQsAXNVEIYSDmMJh6Fw+oQAknqJGvKJojkMzKrsSurEDc3adoLLFGMJEtM1QEz1YQmtNRNSHRqunbyOZdtiR/TQKgd3bSne3HMavX4Fy25aBHOWGQAQ8AVwYf9lHHnpBJS55Sm9t7EY+X0c+e8+nWoMpBOTAOv8IKzzJ69uPwWBiTFVGvaxYCK0yXoCN732l+m+FwoQKTJdQ4QWU63XYaREAWLXZ29GxfyyUfsWCC4ghMDz//0yuhp7wh9nEkNeSQ6YJMHe2Q8lMDW2nB1PEBj5YLGz9ELE3yejJPFkoUZ6/KZzAzxR3tj+7wmPmVJhYLwoTIzfTA0SUyVE6PU67N6xDnW1leCcQwhAliV4vD68+OpBNDS2h4+dqOGM8ZarHh4EtPYGJAoEZPqgxnjqy7gwMF4UJlJjpgSKdAaI/LxszK2tgF4no6e3H5evtEDhEzN2nCqpGBYYHgooEKQWNdIkhMLABKMwMX4zJUiETJUeiVRL5fyAVPYSUANIkpEp79kNH///Eh5DqwlSKNlJlolkyg/qcKmYdDaVAsVMX2qXin+vhuaiiN8datCnl0x8n5qJKAxMYakOF0Bm/OKmahb7VAoVU1EqVwuMDAQksUz4XSYTh8JAhpmIN9yZ8iaVrqVx0z1kpOv7kmwgmCk/Z4SMR6reTzSHgXRM7qHuwJkp3YFjujcCtP4+tun+b5uJpnu4JapJ7RmYCrOHKZBMPxPVnUwN08xCjRYhsWX8MMFUCCQjUUCZGmgMO77JDEvUsBOSWhkfBqaiqRhQkkFhJjPMquxKSyCghn56manLZzMNhQGSctM9zAxHwSa+UO9JqkJBKoMANVKEaEdhgJA4ZlKwSbXhQSkVoSCZIJDKht5mNWPZ4lqUlxVCcIHrzR04e/4aPF6a6EkyB4UBQsiYhILSyFCQbCCIFgLS9VQ/cr+HWcuqse0jW8AkBkmSIIRATWUJNq5ahD0PvY72q51puY+ZYrz7WpCpg8IA0SyTdpNLRqbvPLez9MKYewlGBoFUhACtGzzllebi5o9uBWMMTFIrRTLGAAboDDJ2ffZmPPG9P8Lj9I77nmaqidpMi6Sf5jBADQEh0WXq78bwEJRsL8F4egNS1QAt3qreaygIDCdJEqAH5m+YixN7z6TkesPpTXrUralFzdIq6PU6dDf34vx7l9DXbk/5tQjRgnoGCCFjcl/2sTH1imjpDUhVg2843xTzc9Xz7oYkSzE/zxhD9awinItzjrHIrSnCzv9zL0zZFvU6EkNhZT4WbZmPow+/jrNPHUjp9dLJv7Bqsm+BpAiFAUJIRooXBAA1DEi6+MckfU29jB3fexDGLHNEj4SkkwEAqz99M+yN3Wg5VJ/S66ZLtLBFAWF6Su1POiGEjNNE9AoAQOf5FvCgEvPzXOHoOteSknsJqdmyAJaCrJhBhCscS+7bkNJrTjTD+aaI/5HpgXoGCCEzjpZG6MJzR1C9cV7MzzPGcPGF1M4HKV81GzyohHsCRpJkCSVLqyHpJPAgT+m1J0usfwvqQZhaKAwQQmYUrU+j7ScacPJ372D5h7ZENNA8qIDJEg786CUMNPek9N6YJAFs9ITFUcfJEmZtXoB5t61EVlkufAMeXNl7GvV7TiHgnhkz+CkkTC0UBsiMJDjgvqyD45QeipfBUKggZ10AhoKZ8bQ1XaW71HCy3dInH30LXeeasfCutSheUgXBBVqPXcX5Zw6h63xqhwgAoOtCC2ZvWxzz84Jz2Bu7se3v7kf5ytngCockS7AUZGPNZ0uw8O61ePkvH4W725Hye5sqKCRMDgoDZMZR3EDzL63wNuoASQAcgKRD7xtGFN7iQ8H2mfFkNROksrjQWMenW49eRevRqym7j3iuvnYGqz65DTqjTu0lGIFJEtzdDpSvmg1gaJJjaLKhpSALN377Xrz0jUcm5H6nEgoJ6UVhgMw4rb+1wNs0OCbLB7tkBzsEuveYoMvlyFkdmJybI3GNdfLgdJmoFnD78MY/PYWb//4DYJIYGpoY7AG48tppVG+aHzUoAOqqg6KFFcifW4re+vaJvPUpK9G/PYUFbSgMkBnF2yLBXa+Pc4RAz+tGZK8KaBm6TYoQgAgCTAYYrdOZkYzZZuhMenj6XOCB2CsR4mk73oDn/uwhLLxzDWq2LIBk0KHvagcuPHcE7h4n5mxfGvf1QgiULK2iMKARhQVtKAyQaUMIwNciIeiUoMvmMJbxUQ2687x+cGggVkvPEOiWEehlMBSkpoua+4G+d4zo22+AMiABkoBtUQAF23wwVdIchXSbiF6B8lWzsfRDW1CyWG04/C4fLr98HKd+9+6YJvQ5Wnpx6Md7cOjHeyI+XrigPOFrGWPILs9P+pokOgoLKgoDZFpwXtCh808mBLqGlmQZShWU3OmBZc7QE5rQ+LAmggzA+MMA9wNNP7XC2yIPnY4zOM/p4TynR8XH3bAtCI77OqkiBAAxc3ou0h0E9BYjNn79dtRsnh95XasRC+9eh/LVc/DyX/w6aiDIqS7E4vs2IKs0F54+Jy48dwSdZ5vjXq/vaicE5zGHCUJspblJfy0AYMyxYO7OZShcUAHBOdqOXcO1fWcR9NGwWSyZEhYoDJApz3FWh9ZHLaPabn+HhKaHrKj8tAvWuWoKMJUpcXoFVMwgoM9LzRN7z+vGwSAw4ppcDRttv7Ngzt8MQErvJPqEfJ0Set80wnFSDxFg0OVy5G70IW+Tf9LvbazSHQSMORbs/o+PIas8D8DgJkbDSLKEnKoCLH1wE479Yt/QJxhww1/djVk3LIo4ftYNi9B1oQV7/r/fQvFHD4iKPwiucMgJwkBOVUHSX0/l+jrc8O27IetkAAwCAjVbFmDlx2/E3r95DL1XOpI+J9H2czgdAsMMeT4gM5XgQMcfzYNBYESDKxgggM5nzeoTLwDb4iBkGwdYjKd+JpC7NjUNoFAA+wHD6CAwdDFwH+A4GW8OQ/q5r8m4/l82DBxTgwAABO0M3S+b0PgTK/gUWVyRzOTBiRgaWP/FW2Ary1V3NYwxwUSSJczbvTKitPC6P9s1KgiEFM4vx83/8IG413X3OCBE/F4rc74tqVLJOdWFuOlv7oWsU1cxhLZsZozBkGXGjn/+IPRW2o44XUZWZYz2v8lGYYBMae4rsjoOPzIIhAgGf6cMX4s6fMBkoPzDbjAZ6tyBoQMBJmAs4yjclZotaYMDDNyT4FdIAnxt0avNTQShAK2/sajDJxE9JgwQDL5WGd17TBNyL6narngi3jhNeVZUb1mg7l6Y6H5sJphy1E2HJJ0aDmJhjKF0eQ2sRdnq36PsmNh1vjVm+AiR9ToUL6lOeG8hC+9eG/N6kizBaDMnnLhI0ktLYEjnzz4NE5ApLWjXllcDdgZTpfrflloFNV92qt3ip/QQQQY5WyBvox95m32QUvQAxLQ88Asg6GLgfkxKd7zznA6KM873UDDYDxlQeKsX0uR2YGgyUU9Q+bUlCTcyGi7gVcfcZ29brGkDpB3fexC20jzIehmOdjsuPn8EF54/Ch5Q0HWuCbVxChOF6C3af6CqN86LWQJZvSmgckMdLjx3RPM5yeTQ+juQ7NAEhQEypck2bU+PI48zlnKUPeBB6Qc8gAKwNPyk62wCxoogfK1R5gyECAbHCQOc5/XI2+RD4U6f2msxQbytcoLVFYDwMwR6JRhLUrvyoaG5KKXnm8iuVK5o+15wztF+ogFBjx+AWhRIi+yKgvBTuq04B6s/vR2VG+qw9zuPoade29j9QHOvpuMAdbfEeBhj0BmoOZhJkv19oWECMqVZ6oKQzByxZ/4L6HI5zNXRlxEwlp4gEJJ/gy/OnIEhwsfQu8+I1t8PzW+YCFqDRzq/R1NB7qwirP/SLuz+fx/Hzn/5EBbcuQZ6S+wuou7zLQgMNvCxCCHAGAMPKMitUYNP77VOTfczvLueSQxMYiheVIUl929E94UW2Bu7YwYSrnB0nW9Gf2O3pmsBQM/l9rgBhysc3ZfaNJ+PzDwUBsiUIIKAp0GGq15G0MEgOOC6pEPfW0ZY5gYRfc6AAMBQfLtnUpbKiSDQ964R2pcoMjhPG2A/MHH98baFgQSrKwT0hQr0+ZNbDyHR5MHx9AosuX8j7vzxZ1F36woULahA6dIarP38Ttz98BeQOyt670XQF8D5Zw9D8Nj/tqGJheWra3HHjz6FyvV1aDlUj6DXn3ACYDSSLGH+HavBJIb3/t+fwBU+qgHnCofiC2D/D19K6twXnjsSd/iCSQyXXjye9D2TmYPCAJlUQgC9bxpQ/70sNP7Yhuaf23Dlu1m4/HfZaH7Yiu5XjXCeGWw8wxMC1T9li0DZg25kLZucdfwDJ/Xq/gexJjdGJdD5Rwuu/9iKoCPFJRCjMFVwmGsDIyZTDsdQsM2X8mqMU0Xl+jqs+tQ2AAiPmYeexI1ZZuz47oMxu9BPPvoWGt48B0DdQCgWSSeDSRJu+PbdMGZbcOine8EYG1MgMOdZYcyxoPtCK176+q/Qcrg+HEi4wtH43kW8+LVfwd7QldR5m/ZfwsU/HQ2fJyT034d+vCflOzSS6WWGdw6Sqa7rTyb0vTOyu5ZB+AffSIc/1QpAX6Agb6sf+hwO67xg2ru3gwMM3mYZYIC5RoFsGXqD7z9kUJcwahgmGKIe622U0fSQFbO+7Ez711DxEQ+af2GBt3n4xk0AOEPBDi+yp8A+Df1zjGPelyCexfdtCNf9H0ndDTALNVsW4Nq+s6M+L7jA2z94Fs1HrmDrN++Mex0mMcg6GXN3LsPZpw5AkhjWfG4HdMahXqBQOEi0UiBU5rjvaif2/cNT4dUKHrsLAdfYv0cH/+cVdJxpwsJ71qGwrhSCC7Qdb8DZPxxE+4mGMZ+XzAwUBsik8XVIUYJASJQ3TMEQ6JGhz+WwLUxvb4DiVusbOE7phxp7WSBnrR/Fd6gz7wN2KckgMAxn8LfLcJzVI3t5ehtj2SpQ/SUXXJfULZ25l0FfyJG7zg9D4cwtlyzpJJQsiT+jmgcVlK2cHTUMhJQsq44ZKCIxFC6oAABcevE4DDYTVn1yGwQXam9EohCgcPRcaoXfGbn01e/0jvrYSAabCeZ8G3z9bnj73TGPa3jzXLi3g5DhKAyQSdN/xJBwpvtoAgMn9GkNA9wPNP3MBl/7iMZeYeg/aECgW0Llp93QZXEE7QzJDRMMwwQcJ9MfBgC1/LBtQTC9pZEVgarWbph8AfRnWdAgCjGp4w9ars1YzEZe0klY/6VdmHvLck2XE0JADHa7V6ybg1WfVIcnoq3tj3o9WcLpx98L/92Ua4XeYoCnxxmzXHB2RT5WfuImVG+aFy5h3HrsKo4/8iZ6aEIgSQKFATJpgnY2hu0BWFrH2hUXQ9tjZvjaYhQ6Egzuej2c53XIWRMY2ip5LASD4pkZg/V5xwdQ+kYPlrqvhj+2zXYWjy/eiIbc4nGf37+wKulJhDygoO9aJ3JrCmPW+mcSg7OzHzk1RdCbDXC22+G1uwAAG768G3N2LE34RD/8XK3HrqL25iXY/BfvS3i8OhdAqKtLGHDkp3vRfLAec3ctx4qPbIWlUC1MpAQUXHn1FE48+lb43gC1quDu//tx6Ey6iK+vdPks3Prv1dj7ncfQcbpR070TQmGATBrZKtT2NslAIBnTszYvYGdo/LEt8dM+E+g/YkD5B93oe88Af5cUpXdj8B0+/GcUkoChcGzb4I6FEID7kg59+w3wtcpgBoHsZQHkbvBDlz3272nB4X6U7xm9zK3MaceXD7+M/1p3GxpzCsdz62N2/o+HsOnrd0T9XGhp4LIHN2PZg5vVj3GOxv2XcOGPhzX3CKivE/AOuMEVji3fvFPT5EEeVNB8+ArsDZ24/PIJuHscuPkfP4DKtXMjXi/rZdTtXoHyNbV48Wu/grdPDQTr/3wXdCb9qJ4NSZbAGbDpG3fgmU/9b8zfL73FiNk3LUJ2ZQECHj+uv30+6YmJZOagMEAmTfaKAOz7ky8HaFuUnq7utqfMCPZr6PYXDME+CZIBqPq8C+1PmOG6MHxVgYB1YRD6fAX2d+N8fZwhd31yQwTcBwwcN8DTKIMxtQ5D1pJAwkmIQgAdz5jQf9AYMTTT87o6b6Pysy6Yq5IPJpKPo/T16LPQJQgIDtx18TD+e93upM+dCvV7TqFoUSXqdq2IGPcPBYGRmCShasM8lK+q1TRPINRoB30BvPZ/HsfO7z4Y89wjSXoZNZvno2RJlXodAVSsmaPex4jXM8ZgLcrGyo/dgP3/9RKyyvNQurQm9rklCVmluShdVoP2k9dHfb725iXY8JXdkA068KC6FfjyD21B43sX8c4PnqNdDDMQhQEyaUw1CqwLA2pDqnUiniQwcFSPzufMYLKAbWEQeVt9MJWPbyKcr5vBc1nr+n8ByGojoLMKVH7SDX+PBE+DOmRgnhWEoUBA8QPeJp06lBDx9am9BXmbfTBVam+A3VdktDwyuLHQYBvVf8SArhyOyk+74lYQHDiiV4MAMGKFBgP3C7T80oLav3YkXZI4+4ITLBj7KViGQF1fB/I8TriRn9zJU2T/f76I5kP1WHLfBuTPKYWkl+M21pIsgRm1vTWGlhDKehm51UUwZls031foHkw5Fiy+fyPA4q80YIxh7i3LceSh15Fdkfh7KYRAVnn+qDBQvmo2Nv/l+9TtOhiDPGxpZeX6Omz+5p1487tPa/46yMxAYYBMGsbUTYU6njFj4Jh+WHdmrDdE9YnWc10HcAYBhoETegwc16P8Q9rqDXgaZNgPGODrkCEZBbKWBZC9yg/728n0UKgb/HjbJJjK1AbYUMBhKFD/O+hg6HzOBPthA4SfqcsPhz2N63IE8m/0wjw3CG+bBEMBT7hvgb9bQvMvrOqGQ2Dq8sBBwQGGpp9ZMfubDshR9hwSAuh9K1QcKfo8CMXF4DitR86q5J4I9U5lcJli/ONyfO5JCwN1u1di6QMbYSvJ1fwaJkma6wQwxgCJoWbz/PDKgWRp3QeBSRKWPrgJTfsva7qvgHv0UsTlH9kKwUXM5ZY1m+cjp7owqQqHZPqjMEAmlaQHyj7gQeEuL1wXdVC8DI7jevhadUNr+MNr+QffZIc/2XJ1XL71MQvmzHLEHPsWYlhNg3DDLOC5JqPn9bHtXNT7hhHlH/REfMzfx9D4QxsU97D7FUy9AVmg5B43RFBC7xtGBJ8zAwCYQd1WuXCXF5JRbfjt+w1w1esAAVjrglBcalXGqD0ogkFxAgPHDMjbNLqELvcC/s4EEx0lAc9VXdJhIGiVEwYBABgwmpM6b6qs+tQ2LLl/Y9xKgrGEnvq1dPkLARiyTWMKAsmac/NSnHjkTbh7HDDn22LeX9AXQMvhKxEfM+VZUbSwMu75ucJRs2UBTv3unZTdM5n6KAyQKUGfI5C7Tm2I8rf44a7XYeC4HkEngz6fw3tdhq891oZADOAC9kMGFGz3QQTUpXTDx9H7D+uHahqEw4T6p+JE8vUCOIPztB7iQU94BVvQwXD9v2wxtjVmgAJ0PGXByFmTws/Q954B7gYZeZv9aH/KHHGf6gTFofuNxXFGFzUMaF75OIZ2rH+BFeUvd4Mp0RtbDoZruUXoNWchRZtFajb/jtVYcv9GANqX943EGIPgPOZqhDAh4Gi1I7+2FHpzerenNOfbYCnMxolH38Kmr90e43YEzj59cFTPgN6U+N4EF0ntiEhmBgoDZMphEmCdF4R13lC3/8VvZ8dvsAXgOKkOGQS61adgy5wA8m/yw1IXRO+b8bvJx0IoDN17jMhdp87Gb/qpFTzhUkE24s+he/C1yGh/0jyYE0b3fiQ6r/BHv7ZsAgylCvwdcYokcQZLbfITM7lJRseNeSh7ffQOeqGOjOfmrUn6vONVt3sF1v3ZLZqf7KMRQqDjdCNMuRbkVsffgVHSyWh89wJ669ux7ou3jOl6Sd4c6l85Cb3FiFWfvAmSLIMrfLC4EXD26YM4+Zu3AADZlQUoWVoFgKH7UguCvkBEZcTRX4uE/iYqTZxpKAyQ6UFDL6+/M/LpzX1VB/cVPQp3e8IBIfEFtDYc6vG9rxvR+7oRWSsD8HelYG/ikUEgLPEyRWNF7MmI+Tf60P54jMltTEC2CdiWjm0GefeGXAgdQ8mbfZB9Q2MG3ZYsPLZ4E67ljb/OQDL0FiPWf+lWAIlL/8bDGEPx4ir0N3bj9BPvYcn9G6OejwcV9Df3ouXwFQguUFBXhtrtSyKO1T7cEP84IQTc3Q64ugYAAOefOYSre09j1o2LYC3KgsfuRsNb5+DpccKUY8GWb96J8tW1EaWQXd0DkHRy1DkDggsEfQGqUpiBKAyQKc91SaexSuHop20A6H45yqy6RK9N8njHcQPiNtZjOGdSn+cMuetjb7mbvTIAX6sPfW9HzpkAAySTQOWnXJDG+m7AGHrW5qJ3ZTYuHysIVyB8LzBvUioQLrx7reYJeYlIsoTcmiLkzioa1VCH/j7Q2oe93/k9BBcw5VlRu33JqPMkG0rihYILzx2O+LvP4QlvQhQiG3W45V8/HF51MPxc5jwbhBCjlk5yhYMxhv3/9SKCXlpamGkoDJApr/etRBsCJe42YAYB4QfG11jHM94gkMx1MHStwe9L4S5v3OWVjAHFd3hhWxSA/YAB3hYZkgHIWhZAzlo/dLbxF3ISOgnXqkuGPtCc2u+H1iqERYviT5BL2uCXIY2YN8AYA1c4ui+0wNPrBADc/A8fSNjwx2voI8IGF+HlhjyoQNLJUHxBrP70dqz8xDa0HK7H6Sf2w5xnRXZ5PvwuH5r2X4LX7kLttiXIqS6Meh1JlsJDIIXzyqAbnEfQea4Jp373Lm1alKEoDJApTQjAXa+lDkG8+QRjKHOYtFQ0fAmGKpiAuSYIxSWFhyRMVQryb/Qha4k63i8UwH1NBvcw6Av4qIBgqVVgqfWMOvVMovhTW5QqUU2C2dsW4/BPXwXAUDCnJOaxWs4XcZykrmYIeP3qpD5ZgjxY/0CSJVSur0Pl+rpwKGESw/ov7cKFZw+jcH65+ssT61oC0Jn0ePyB/4Q5z4qAxw/fwMz+uSDxURggU5tAStpx4Qf0hXxw7sBEPcWPVez7K77bC1MZDxceGl4kyH7AgO49RiiuoSdYY7mCkns9Y6ouOF1deuk4qjfOi3vMeCYWjiTrdbAW56B8VW3iVQcahe6NMQadQR+1IFFo6SMwVKeAyQwL716HgNsX916YxGDKtULxB+Hs6E/JPZPpLTU/uYSkCZMAY6WidofHPkrLmRAckFD6ARdY2ldNjT29qF8r1HH9EEkATKDkXk+4yJFkjAwCvW8Z0PGMOSIIAICvTULTT6zwtmTOr3rr4Stw9zg0Fw1KhZ3//CGs+ez2tJw73vbH0UsqM+itRnAl9rARVzicHfZU3SKZATLnHYJMW/lb/eOaLxA+0s/A9EDeFl+CcDF2Oet90BeMtTQyQ6BbQtkH3cheFYAul0OXy5G9KoCarzjDdRhGUjxxJkkKBqEAXS9pmUQ59fkXVmk67oUv/wJ+h9rtLYQI/y8kVb0CofObcianqFIsQkSvMBgiyRIuv3Ri4m6ITHk0TECmvKzlAbiv+dB/wBg5kVASmqrfDdf2Wytka+hF0brjxzeEkLU4iOK7vGj4DxsCPTG2QY6Dexk6nzVj9reilxaOxnFKP1imOAbB4L6sR3CAjWt3wunE0+fC4w/+J+bfsRrzblsFg8UAQ5YZslE3aiLgeISX7KXwnKkguICj0w5rcfaor1cIgYHmXjTuvzRJd0emoqn1E0xIFIwBJXd7UfFxFyxzgpBMArKNI2etH/nbvUmfT3HFKb4DFtlFnwTJxGGuDcJTr0OgR8bYQoW6T8DA8cRjGcEBhr79BjhO6TVdKuiYyvMk0kAAF58/iue/+HM8/fH/gS7FQQBQexhS2cuQKpIs4eyT+3HpxeMQfERiFkBOVQFu/bePwmCbGT1GZPyoZ4BMC4ypWxeP3L6YB4HefSaNdQhGnTX6h0Xo/5I7Z8EOHyQ94Lqsi9iYaCwGjusQ6JbCT/PZq/3hlQHBAYaWRy3wNg4vcqStfr7g6jyM6UzrEsOR1E2E4nw+hZMKJ5MQAoo/iGtvnMWq2hJ1UcGwz4dKM+fNLsbGr91OOxQSABQGyDQn6YCi2zzo+pP2rWMT0lSeOBQW1F4EfQGH4IDiHtxQaFwYvNf18F4f6qHoe8cIphPQ5SvqiggNexWMvNfG/86CLocjb6sPeZv90z4UJKv12DWUr54NSY5dKXLkPgRTPSCMKoQ0uGvi4Z+8CiZJmHvLsphzByRZQvWmebAW58DVSSsKMl2GvR2QySQUxGwofZ0SuvcY0fGMCT37jAgOaH8Dzt8aQPHdHjD98LkA4ySLJFYwMAR6JHS/aEL9P2bB/p4hQa+A1vtjw/4HiCBDoFMePPfYGqhgP0PXn0xo+505BaFlejn79MGYQYArHD6HB63HrkWuQhCY0FUJWgghwrswBty+iB0ZHW19ePN7f8Dll0+gcEE5ZH385z3GGEqWV6f1fsn0QD0DJK2EAtgPGdD3rgGBLhlgAtYFQeTf5INllgKhAO1/MGPgiGForF4A3a8YUbjTh/ybfZoq2mav8AMQ6HzOBPAUZFyFQc7mUBKGkhEbD4nhwwvpqGcw3uEQ9b8dpw3IOhNA1rLUFuiZKGMZKug4dR0H/vslrP/SreHZ9qEqf36nB69++/fou9oJS2EWssrysPCetajaMG9K9QzwoILO881oPnAZneda0H2hBeZ8G2yluQi4fLBf7wofq/W+1352BzzdDrQdbxj3/VWsnYMFd65BQV0ZlEAQTe9dwvnnjsDRMnojKzK1UBggaSMUoOVRC1znh/2YCQbXRR1cF3Qoe8ADz3UZA0cGF8yPeJru3mOCbBXI3RC75r63VUL3HtPgNVJbadBQrMAzkOxT+MiGd1ggYCL9hRAHGSuC8LXG2vJZvZe+94zTNgyM1aUXj6PteAPm3b4y3GA1H6zH1dfOhLf7dXc7EPD4UbF6zpQKAgDAZAltxxpw7g+Hwh/z9DrD5ZCH677UFi5jHI/BasT2f3oAr3zrt+g61zzme1v7hZ1YeNdacEUJ98DMu20l6m5dgdf/4Um0Hbs25nOT9KMwQNLGftAwrJEeZnCTnLYnomzXG0Gge68ROeuij2+7G2Q0/9w62N0dY2vgMRGQswRkC0/B+YZ6CSSjQM4GH/reNKU3FEgCgrMEWz6zUbs8ZgpHWx+OPvR63GNya4ogG6bm22Pd7hU498xBzNmxDPN2r4StNAd+hxdXXjuNi88fhbffDQDw9btxdd8Z1N68NG7NASZJEArHyk/ciD3f+u2Y7mnWjYuw8K61ABAxFCPpZAjOcdPfvh9Pf/RH8DuTX/1DJkZmvhuQCdH3brzlcWxww/t4Z2BQHBK8zaOfbAQH2h83q+vrxzRrP06dYwZY5gThPJ3KUoUM3McGg0B6nzaZDEABEiWO9FdiTC+tBYiSxWQJ829fldRrRhY1GqtE52CMwVacgzv++1NY/6VdyJtdDIPVBFtpLpY+uBnv+9/PIKs8L3z84Z+8it769oT3J8kSSpfWwFKYNab7XnTPupgVD5kkQWfQY86OpWM6N5kYFAZIWoggBvcBGH/Dx0eMEgQHGNqfMCPQG6cbXDMx4r8FTDVBde1+qp/eRYKn9VRdJoDET/1MIHt57OGXTLbp67dj9k2LNR8fmtGv+NQhFx5Uwh9PRk99OwIeX+LrcY7sigK1xoE09PMkyRKM2Wbc+J17wx8LuP14+ZuPovngZU33YMzWVkmRSQzlq2ux4M41qN2+FAXzyuL2PgiI1O8mSVJqavaDkelPQoJthzE4pJ6ocRQwFA49cXhbJTT9zAruSU33vbkuAF+jDjwAGIo48jb54WuX4G0cOmZqijc5cXCuAhs8buT3mAlIBiB3I4WBkfLnlGDO9uSeYEPzCmSjDo0HLkEEOUx5VhTOKwOTpLiN5HC2khx0X2hF+araRBeMOZdB0snIry1B0cIKdJ1vAQDwgIKmA5dRub4u7mkFF/D0jJ57MFL5qtnY+PXbYS3MDi9lTBh8BCJWPZCph8IASQsmAdb5Qbgu6WJ34wsG2apAcceoCMgEDCUKPNd1kAwBSCag5REruHfsS+siSALmSgXVn3FHfPjqv9mSGHqY4B0QBwMWMwkIb7zrMkAAcrYCZUAeWqnBGWSrQMUn3NDnTv8357EWIIqldsdSTZPuomGMoWpwS2EAcHUPwGA1gZn04c/HY8wyo2zlbE3XiYcrPCIMAMD1ty9g3Rdvgc6oj/malsP14fkGsRQvrsTN//hAeIVPqGcitINizA2VJIb2Ew1xz00mF4UBkjZ5N/rguqBD1AZTEtDncZS834OWX1jVp4aIBlht9PztOrT9TgcmC1jmBxC0p7ic7IjTBezq7oZJnCGl9zNaqMFmYEYOU5WC3LWBwTkTiQstFe32QTYLuOt1EBwwz1KQtTgARr/5UZnzbNC0ljWG4Y2hJT8LTGLwOTwwZmnsfk9w7dCTePxzAFyJDHoBtw9HH3od67+0a1SjzTmH4gvg2C/2Jby/lR+/Sb1GlLLOse6dKxx+pxfX9p1NeH4yeegtgaSFCAL2dw0YWl431KgBgD6Xo/IzLhjyBaq/5ETPXhOc53SDPQSjn1iFwuA6p0dKn8Q5g/2wAYFeCbmb/dDncFz/kQ1iSvWeD6su52PQWQWylgfguartyVWfw2GZo8C2MLOWEI6Vp8cxWCti/EKNttYgoO2ko6skjr6uhLbjQ8v4ylfNxoK71qJoUSWUQHBUISJJkuDodcLniD/T31xgQ8nSxAWKhocNIQSCXj/2/s1jCPqi77pJpgaaQEjSovMFE5xnQ12SkZX0AAHr4iAM+eqbrqmco+Jjbsz6CwckMx9x7HBahwe0vJmrxygDEgaO69H4Ixuaf2mB4krREMSYxa966DhpQMMPrdAXcuhy4i3HENBlc5hnx9vOML1mVXYlPigFUrmq4Mre02MaIpgojLG4PRdCCLQeu4b+xm4AwIqP3Ygd3/sgylfXwmgzxaxImFWai5v+5t6onwsxZWsr+R3RQyDUcOK1uzS9lkwe6hkgKae4GewHDXF3Buw/YEDhDm94m17FCzQ/PN6JgUItI6xoybijq/L5WqfCr0Pir9/fJqPll1YU3eFB22+tGN1bov69+H3ujNp/wJRjwbzbV6F222IYbCb0N/fi2r4z6G/qQcDjR9/VjoST2PqudeLyKycwd+fyhN3xkyXRUIKkl7Hxa7ehv7Ebyz64Wf1YgkmMkk5G8eIqFMwrQ8+ltqjHuHudmoYpIu5VYpANOsy/YzWO/+oNza8jE28qvPuRGcZ9RQaUBGOfAQbPVV14F8KBowYE+yQkbgwjhxsiMUgmAe6a4El9E00w+NpkSDqg/MMudDxvjiibLGcLlLzPHbO6oK9DwsAxPYIDEnTZHNmrAjCWTO+NCnKqC7HrBx+GwWYON3zGHAtKlgz1Gri7HTj92Lu4+MKx8McshVmYs2MZsspy4Xd60fDWeRz44UvIqS5E0YKKKVeBMBHGGEqXVqN4YcVgwR/tjTdXOMpX18YMA75+N5oOXkblurmaV0gAahCZdeMiCgNTHIUBknIiqO3NRwxrq/qPRp/lPApTi+UI37BQMLhdcPZ6HwYOhuYppEOqQ8Z4zifgOKNH2Qc8sC1xwH1VDjfullolao+A4EDHH03oP2jE8OGF3jdMMNUEUPlpN2TjGG9HA1+1H8bGNFQ6YsC2/3NfRBAARj9BmwtsWP/nt8Kcb8OJR9/C4vevx8pPbRuc0qJ+Pxbdux7Nh+rhbLejeKH2dfFTbXfD0FBHUr0bQiQcIjn2i30oXVYDnUmfVCDQmzT+fpNJk0GdiGSiGMu1jVMbK4aeRhWXll4BAAKo+aIDJfd4Ya5VYCxTkLUsgKovOFF8h1fbOcZsnOeO2AVx/MFCnd8wuIxzroKcVQFY50YPAgDQs9eI/oOhxjhyHof3ug7X/j0LPHHNm5Rx1KTm36qirgzZFfkJG6dQY730g5ux8J51WP2Z7ZAG6wBIOjncEJavrkVuTaHm619+5WTMyXGpqkw4ESSdjJ5LrXGPGWjuwUvfeAQdZxojPh7va+QKR++1zpTcI0kf6hkgKWcs4TDPDsJzXY6+Xl8SsMwJwlAwFAb0BQqC/Ykr9OVt9cNYJmAs84/awEgIgBkEhD8dgWB8jbdkVp/YPddkQAJkG4e/YzwVFJN7HfcBPW8a47yOQRlQJ36W3js59eP75xiRcyX5NFIyuwhc4ZqfVAUXWPbBzTG70CVZQn5tKTjnapW/BE/8tTcvjnntqdRbEA9XODw9DrQcvpLw2P7Gbrz6V7+DrTQXWaW5sBRnY/PX74h5vCRLuPino6m8XZIGFAYylOIBvI3q2nNThQJddmqfXko/4Ebj/9iguBDZ4DEBnU2g9P2eiONz1wXguRK/KzFrhR9Ft8duqBgDcjf40PdWvEYvCRG7DI7vfIU7fcjbPBReggMMV/81CyI41pAhYKrWvlLAfVUHJBy+YRg4YkDx7V5IaRwuSLVkn7yZxBIu9+MKR/vJBk1FgCSdPGG7UQJDQxKcc0hxlhhqOQegfq1BbwD7/unppKoEOtvtcLbbAQA5lQVYcv/GiGWPoe2hr75+Bk37L43pPsnEoTCQYUQQ6HrJBPsBw9DYPhOwLQmg5B4vdNbUvKsZ8gVmfdWJ3reN6D+sB/dIkCwcuev8yNvqh84WeZ2spQH0HwnAXa+L8rQsYKkLouwBT8J6MAXb/HCcMiBoB8bayJprg8i/wY/+w/rB5ZHjCwLMyJG7KbIXQ5ctUP5hN1p+Y1G7NEI9KJII7+oY/7oMllrttQO4xt4SoTD4OmWYqyZvSWKyWi+1Y/WtK1J7UiHQcaYJri4H6nYtT3Bsai8dC1c4mMQQcPlw4U9HUbyoElkV+bAWaN9cKBScQhUDQw7+7yvovdKOirVzULy4ChAC7acb1XoFGr6+Y7/YB/v1Lix+/wbkzS4GADg77Dj3zCG1V2B6jJRkNAoDGUQIoOU3FrUq4PAGVzA4z+rhb5dR/efO8HK/8dJlCxTf7kXx7V4IPrra33BMBio+7kb3KybYDxrCXf3MIJC70Y/CW7yalsnJFoGaLzvR+bwJjpP68NcpmQR0eQr87Ym75kvu8cJxUg/nWQNS8S4mDf6W+dokDBw3IOhk0GVz5KwOYPY3nLC/Z4DzvA6CM5hrgsjb7EfPPuPof6cwAX0Rh3mW9gbbWKr9WCZNr3fujoYudDf1IL8sV1ONAC1d95JOhv16F668eiphGGASUxvqOOFNywTDeDP/laCCa2+cRdfZZlzbdxZBXwDW4hzc/sNPap68ODwIDP8TTGDjV2/Dyo/dAFtJbnijpaUPbkZ/Uzde/7sn4WjrS3j+q6+dwdXXzsBgM6mVFwc8CV9Dpg4KAxnEXS/DdT5GVzxn8HdL6D9oQP6NqS/Bp6Uhl/RA8R1eFO70wtsmg0GdjChpnIAuuNr9zmSg7EEPiu/0wt8pgekAU7kC5wUdWn9tjXcG6As5wIGevaFENP7hBsUlofU3ZjjPGIb2CADQu8+EvC0+FN3hRfGdka8puduDxv+xIehE5LwLSYDpgPIH3UlVzTWWcBjLgwlrKchWDmPp9Ftm+Oov38Adn70ZttLcwUI3iRteQESt5McVDl+/G80H6yEUjtbj11C6rCbqvADBBYK+APTm2D+kPKgAUvy5B0KIuNUFj/xsLy4+HznuvvwjW2GwGjXPS4i9b4AEWc9gLcoGgIhAlVWWh10/+Aie/cLPEHBpm8/hd07OnBMyPrSaIIP0H4lsjEYRgP3Q5G9yLxkByywF5lnagoAIAj2vG3Hle1m4+v1sXPluNhr+nw3uSzpYZiswVylgMmCuCSJRhb9Aj4SOZ8wJjou4uqZjnWcGQxhnQ/8D0PeOAb1vjh6g1+cK1HzFibxNfjDj4BOdLJC9MoBZX3HCVMmheIG+/QY0/9KCpoct6N5jRMAeu2Eo/5Bn8N8/dtXCvBt8YFO3AF8Yk1hETnPZ3Xj+iw/hwA9fQk999HXyI3kHPOBKZPDhigKhcLz1r89CDH7uyM/2QvEHRx0bepI/8KOX0HulPfxEPfIYAPD2xa/AxxiDu8cJV+dAxMd9A27s/+FLo4KAzqjH7JsWp6xaorod8ujmQNLJMOfbMHfnspRch0xd1DOQQYJ9UoLd+JLdpGfyCQVofsQC9+XILnV/h4S2xyzwd3lReIv6RGN/T8PEQsHgaZATHxemtTxy7Fn8vW8YkLfFB2lEp40uS6D4fV4U3e4F9wGSAeGG2tsioekhK7ibhc/jvqxDzz4jyj7gQfbK0UvdDEUcNX/uHPG6ofvLXhNA/g1TamOGSAyYt3YOltywEPnleRBcoOVSG07tO4vWy+1w15bi8ssnUL/nJO791ZdgKciK00MgsOevfou5O5ahbvcKGKwmcIWj8b1LOP3Yu+i7OrQUzt7QhZe+8QjWfmEnypbPCn98oKUHx36xD00HLqPtWANu/vv7UTi/HDyoQAhA0kkIev1461+fxepPboMlzti+EAKKL4A/fvYnKF5cBVtxDnwOD9pONIAHRocMY44Fsn6CUhsDZt24COf/eHhirkcmBYWBDCJn8/AWuNEJyNbp1UXcf0QP9yUdRje26t97XjMha2kAhlKO/sNaez20BgEBySYAjsHGNfr4fqLzca8Ez3UZ1rnRx/WZBMjDJr8rHqgNumfENQUDhEDb42YYijhMlaPPZ6rgmPsdBxyn9Rg4rofiYTAUceSs9cM8SxnPhn3pxYAbP7gJc1fXhjs2mMRQXleKygXlePepgzj/njpjXXCBk799G5u+dnvUUwnOUf/qKfRf78bRh1/H8UfeQM0NCzH7psXIrS7Ems/uwJW9p9Dw1vlwQ2xv6MKrf/U7WItzYCtRG2p7w9DeC167Cy9+7VcoWVqNyvVzIet16LvWiWtvnEXQG0DB3FIsqyqIu/wxqzwPs29ajGv7zqIT8bdl9ju9SVUXHDlfIBmMMRisKZpIRKYsCgMZJGd1AM7TcRpEBuSunTo7i3GfOrTRf8SAoINBn8uRu96PrJWB8KQ8+/4Ea+AkAfshA3LW+tPS61Fwkw/magVND1nVZYLhnhf1zVdfyBHoTvwEJwJa39SB7j2mOOFDDQTdrxtQ+bHoE7iYDsheGYjaezBVzVk5C3Vr5qh/GT6FYrBx3XTvOjRfbEVoVLv+lZMw51mx/KM3RFQYlHQyrr9zAQf/5xX173oZN//9/ShfVRuuVZBdWYCyFbOw6J512PNXv0NOdSEW3rkGxUuqIBSO5sNXcOG5I1Hvs+N0IzpON476ePPheiz/8NaYk/1Cs/s3ff12tB65Cp8j/uS7gNunuTSw3+lF4/6LmLszwaqIGHhQgX1w4yMyc1EYyCDW+UGYa4Nq4ZuRvQOSgC5bjCrkM1mCDobGn1gR6A690TEoTob2JjPsBw2o+qwLkhHwdyWoXMgZfO0yFGcqg4DasFjnB9UxfRmY9TUH+t4xYuCEHsLHoC/kyN3gh7FcQdOPbQnPaChOPNvffU1G+xNmBHoThQsG11k9FLcXsmV6rQyIZdGWBXHX1QshsGBjHU6+cz78sdOPvYcre09jzo6lsJXkwufw4Nq+s+gbVg1v9advRulg13+oUQ39mTurGLf+x8eQW10IHlTC4/N1u5aj7tblePtfnsX1dy5ouv+VH70RQoi4dQEYY5BkCbU7luL8M4cSnvPkb95CxepaCMZG9RAIIXD9nQs4/di76G/qAQ8o6G/swepP3xzxtQz/71gknYzLLx6LewyZ/igMZBAmAZWfcKHjGTMGTugjAoF5loKyB9yQU1RnYLzaHjcj0DuioR+8X2+zjI7nzCi736NWHIxXTIcJdVlhzniHP4a6++UcjoKb/Mhd7w+P4RsKBEru8qLkrsiZ1EIAhjIF/nYp+vBMuBpj/O+7t1lC88+tEEl8Gd17jCi5e2bM7C6oyIvbkEqyhMLKglEfVzcnei/qa/QWI+btXhnzyVqSJeRWq2WJhzeYoQ2Atv5/d6H7UuuoSX8jWYuzUb6mVtvyPy6QN6tI/QsDrIXZAGNwdw+MKgiUXVEQXoUADC1fFEKABzkK68pQvXE+LvQcha/fjbNPHUDP5TYsvHstSpfVQAig7UQDLjx3GPNvW4WarQvVvT8G7zNUNOjK3lNoPXYt4b2T6Y3CQIaRjOqyu6LbvHDV6wAOmKqUKbVrnb9LgvtynGqEgmHguB5Ft3mRvTygbpcca2KkYMhaqu7KZ6wIwtcaq85A4rH97HU+FN/hTWozH8aAsgfcaPqxDTwgRi0TlC0CJfcmXo/d9YpJDQJJlC/uP2KYMWGABzkQ50eCc4FgIAj/wioYzscfbw8pnF8G2TC2t0AmMQjBULd7JU488mbcY3OqCpMaq1f8Qcy7fRUWv389ssryAKjbB1/442GcffoABBcoWVqNG/7qbvVeRtYNACDrZdhKc7H0g5tRt3sFXv7mo3C22dF+8jraT14fdc3OM03oqW/HwnvWwZKv9mS5exw494eDOP8sTRzMBBQGMpQuWyBn1dQcM1Zn8yegMPiaZeRt8aP/iEF9Qooy9KHP48hapn6dxXd60fQzK8BHHjsYBGJOrhSQjEDJ+7yaax4MZyrjqPmKEz37jHAc10MoDEwvkLPGj/ybfNDnxu8VCLpYjEmS8TCIgIBQMC2WCibScKYJc1fNjrMHANB4tjm5k45ztqQkSyhdWh31c6ZcK+bsWIrsynzozdrTo6STYS7Iwvw7Vkf0BJjzrFj5iZtQuKAcb37vD1j2oS3qsEOU78fwUCDJEky5FtzwV/fgxa/+MuZ1BRc4+9QBnPvDQVhLcgABuDr7kypPTKY3CgNkWjMUclR+2oWWX1vUSXWhOgqcwVDMUflJV3iyoWWWgqrPutD5rBm+tqEWUpfHUXCzDz2vmRAcQOTT++BOg6X3uccUBIbfZ9n9HpTe6wH3MUhGobmRVncnHEvDxSCCMyMMnHnzPOaumh11Ah5XOLwuL64ca0jqnL2X26EElDEv0RNCRG0s5922Euu+eIvae5BEYxo6X/XGeQAiCycxptZVqN40H7Xbl6JsxSzN55VkGYXzylAwrww9l+LXYBBcwNlm13xuMnNQGCBTjrk2VBwodgPIZAFTtVqb3zJbwZzvOOA8rYe3SQZkwDo/AMuc0UvlLLMV1HzVCV+bhKBdgmwVMFWp2/7aFgXR/aoRA0cN4dn95lkKCnd6YZmTmlr9TEbUSX08ANgPGGDfb0CgT4JkUgsM5W/xQWdLtCQ0Bp0AmyHbyPe29uG1R97Cto9ugSzLEFA3kZJkCR6HBy/99DUE/dr3agAAn8ODq6+fxpwdy2JWFwTiVDMUAq3HI8fSK9fXYcOXd4f/rqXyZvhYxsBkFre8MFc46nav1H7S0K1ygaIFFQnDAMlcFAbIlGMoELAuDMJ1URd9LgATyF7nj1h7LyWxXI4xwFTOgfLIeRI6m0DpPepeCkEHg2TEqA2V0oH7gMafWeFrCe1+x8DdDPb9BgwcMaDq807YFgfgPKdPUDRqOIHcDb6kGqOp7vqZJvz+H/+AeWvnoKiqAJxzNF9oxbWT16EExzbn5fBP9yK3phiF88sAoZYnDoUAd48DlsLohYIE51ACCupfPhHx8WUf2pzUdsrRxJtfIMkSssty4Xf5YLAmt7XkyAqKhAxHYYBMSWUf8KDpZ1a1Oz/0VDz4p7k2iOI4WxmPl2RAwtn9qdT9imkwCIxoBDgD9wu0PGpB5afccF/Wg/u19BAI6PI4CrdrqyU/nfhcPpx+41zKzhf0+PHKtx5F7bYlqNu9ArbiHHj6XLiy9xTq95zErBsWYcOXd0eMz3OFgwcV7PuHJ+EZVmbYnGdF4bzylN1bLAG3H437z2Dh3Ws1hw4mMXUHQkJioDBApiTZIlD9JSccp/ToP2KA4mDQ5XHkrvXDtjg4I8bBAYD7AfthQ+wGXjAE+2QE+yRU/5kTHc+Y4WkY+rWVjAJCEhCewUZBEsheHUDxbi9ky+jTKW6mVm2s10EIwFKrIGft6C2lMwkPKKjfcxL1e06O+tzll0+g82wT5t+xWi06FORoOXIFl146Dne3I+JY2ZR4TEbrDoMx71XhuPbGWZx75hAq1s5BdkV+wkDAFY6Ww1fgaE288yDJXBQGyJQl6dWqiTmro3f9B/oY/D0SJCNgqlCmZZe4v0sKb9cckyTgaZJROD+I6i+64O+S4O9W5xWYqxWADZ4nCOjzecTwyXDuqzKaf2mFCCBc0td9WYeevUaUf9QN24LkxtwzRX9TDw79eE/C49zdDgQ8/rg7GI4HVxQE3H5cfOEY/E4vXv6LX2PZh7egbteKiGuGhilCf/Zeace7//F8Wu6JzBwUBsi04++W0PGsKWK5nS6Ho/AWL3LWTM3lkrFo6uEQANMNPbkbijgMRZHjv4nqRAT6GZp/YYUIIrIXQgAiKNDyawtmf8MJQ+Hkjiv3zzEi58r0HN7gAQWXXzqOBXdF774XXCDo9YPJEnRGbTM7BefgXEDWyfD0uvD63z8BT68TgFpm+MhP9+LYL/bBkm9D0BtATk0R6nYtR1ZZHrx2F668fgZN+y+Fd2AkJBYKA2Ra8fcyXP8fK7g3crldsJ+h/UkLFI8H+VunRkllLQzFHLpsjuBAnOWDgsE6b3xP7f0HDaODQJi6n4H9PQOK75z+RYqSKTyUaid/+w7KVs5GTnVhRCAITd57+wfPoWRJFRbesy5u977gAkJw1O85Bb/Ti67zLWg+eDnqUkUeUODs6AcAeE9dR8ep0UWFCEmEwgCZVrpfMalBYNSsevXvXS+ZkL0qAN0UKaucCJOA/Jt86HwuRt++JGCZHVRXP4yD87w+/sRDzuA8p58RYQCAunvgurmQDTr01Lej4a1zUHzpHwYJuH14+S9/jcX3b8T821fBmGVWt1o+fAWnH38X3Rda0Xb8GgrqylCyrDrqfgVc4RBc4K3vP4Om/ZfSfs+EABQGyDSieAHHqQTL6zjgOKFH3ubp0zuQu8mPQK+EvneMatEkPrRywlimoPzDicsVJyI0lEnQcsxUZ84y4ZZP34yi6gLwoAIhgPk6CWs/twNvff+ZCamxH3D7ceKRN3Hy0bdgsJoQ9AWgDKuBoPiD2Ps3v0ftzUtQt3slssrzwQAEvH547S60Hr2Gyy8dh6sr/p4HhKQShQEybShOKfE6ewkI9I1tJmHAzmA/YIDzrB4iqO7ZkLvJD8us9LaSjAHF7/Mie5Uf/YcN8HdLkM0CWSsCsC1IzcoJc42i7vAY6/snDRVxmkiOGoas66npxWESw62f34G8khwAkZsL6S0GbPv7+/HiV38VsWthOgkuYm5FzIPqEED9nlMTci+EJEJhgEwbslkg4YZCHGPaedF9VR41wS5gl+A4aUDBDi8Kd6Z/UpupgsNUkZ5u+tyNPvQfijPLnbNp1ZsSTdXCChSU50X9HJMkMC6w6L71ePffaGY9ISNNw8VYJFPJVgHLvGB4v4CoBJC9PLlGTfEALb+KMtN+8Cm6Z68JznPTOzebyjmK7hh8SpWGff8G/7tghxeW2uk9TjB7WXXcKnuSTsasLQsn8I4ImT6m9zscyTiFt/jQeEUXZedBABDI2eCHPj+5noGBYwZwHxCzx4EJ9L5thG3R9F6Hn7/VD2OZgr63jXBf0QECMM8OIm+Lf0w1Bp4aWJWGuxw7vVEfex+BQbJBl/QGQoRkAgoDZFoxVymo+rQLbY9bEOwPTbQDIAF5m/0o2p18N7v7qk7NAbHaB8HguSZDiHHvejvprHMVWOe6J/s20sLe0Y/qJZUxK/wJLuDssFMQICQKCgNk2rHMUVD7Vw64L+vUSnwGAeui4LRZTkjS48LBeizfviTOEQIXnj86YfdDyHRCcwbItMQkwDo/iLzNfuSsHV9dAUttMHavAAAwAfPs0dshk6nF2evEwcHGfuTcAc45Os824+KfKAwQEg31DJCMl73KrxYzirUjoGDI3zo9S+RmmjNvnoez14nl25eiqLoAAOC1u3Dh+aM48+R+8MD0niRJSLpQGCAZTzYDFZ9wDS4tHBYIBgsAFezwTvvJg5mk4XQTGk43Iau1B7JehqfXSfMECEmAwgAhULfynf2XjkkpOpRJfNV+GBvTs6vfqGv1z8yJkoSkA4UBQgbpcwWKbvWh6FYaEiCEZBaaQEgIIYRkOAoDhBBCSIajMEAIIYRkOAoDhJAppX+OcbJvgZCMQ2GAEEIIyXAUBgghhJAMR2GAEEIIyXAUBgghhJAMR2GAEEIIyXAUBgghM5J/YdVk3wIh0waFAUIIISTDURgghBBCMhyFAUIIISTDURgghBBCMhyFAULIpHLUsFEfo5LEhEwsCgOEEEJIhqMwQAghhGQ4CgOEEEJIhqMwQAghhGQ4CgOEkLSZVdk12bdACNGAwgAhZEqiFQWETBwKA4QQQkiGozBACCGEZDgKA4QQQkiGozBACCGEZDgKA4SQKYsmERIyMSgMEEIIIRmOwgAhhBCS4SgMEEIIIRmOwgAhZMbyL6ya7FsgZFqgMEAIIYRkOAoDhBBCSIajMEAIIYRkOAoDhJAJ5av2J3U81RogJP0oDBBCCCEZjsIAIYQQkuEoDBBCCCEZjsIAIYQQkuEoDBBCJp2jhk32LRCS0SgMEEIIIRmOwgAhhBCS4SgMEEKmPKo1QEh6URgghBBCMhyFAUIIISTDURgghBBCMhyFAUIIISTDURgghBBCMhyFAUIIISTDURgghBBCMhyFAUIIISTDURgghBBCMhyFAULItEBVCAlJHwoDhBBCSIajMEAIIYRkOAoDhBBCSIajMEAIIYRkOAoDhBBCSIajMEAIIYRkOAoDhBBCSIajMEAIIYRkOAoDhBBCSIajMEAIIYRkOAoDhJBpg0oSE5IeFAYIIYSQDEdhgBAyJThq2GTfAiEZi8IAIYQQkuEoDBBCCCEZjsIAIYQQkuEoDBBCCCEZjsIAIYQQkuEoDBBCCCEZjsIAIWTC+ar9k30LhJBhKAwQQgghGY7CACGEEJLhKAwQQpL21MCqyb4FQkgKURgghBBCMhyFAULItEI7FxKSehQGCCGEkAzHhBBism+CEEIIIZOHegYIIYSQDEdhgBBCCMlwFAYIIYSQDEdhgBBCCMlwFAYIIYSQDEdhgBBCCMlwFAYIIYSQDEdhgBBCCMlwFAYIIYSQDPf/A0QplhOZMMD1AAAAAElFTkSuQmCC\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": "092abfb3-3b03-4ab4-f64a-0b33a46f1d7e"
},
"execution_count": 53,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712558460.1292584\n",
"Mon Apr 8 06:41:00 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": "9c0da194-6467-48f4-9159-983b77ef30e2"
},
"execution_count": 54,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712558460.135237\n",
"Mon Apr 8 06:41:00 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": 1969
},
"id": "95xed6YyDClf",
"outputId": "085b219e-b938-484f-f40f-f5bda5e73772"
},
"execution_count": 55,
"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": "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\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",
"239 1.000000\n",
"287 0.615745\n",
"377 0.608622\n",
"327 0.562987\n",
"370 0.341552\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 0.018241\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.00535\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.002051\n",
"1 0.002508\n",
"2 0.002916\n",
"3 0.003226\n",
"4 0.003324\n",
"5 0.003546\n",
"6 0.005118\n",
"Normalized Saliency Sum: Saliency 8.755573\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.069072\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 10.033049\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 115.821983\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.004771\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 378.669617\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.003632\n",
"1 0.006919\n",
"2 0.011376\n",
"3 0.021878\n",
"4 0.028059\n",
".. ...\n",
"475 8.712234\n",
"476 8.747760\n",
"477 8.749157\n",
"478 8.751508\n",
"479 8.755573\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000008\n",
"1 0.000014\n",
"2 0.000024\n",
"3 0.000046\n",
"4 0.000058\n",
".. ...\n",
"475 0.018150\n",
"476 0.018225\n",
"477 0.018227\n",
"478 0.018232\n",
"479 0.018241\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.07137063\n",
"Normalized Saliency 25th Percentile: Saliency 0.003244\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.011224\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.00798\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": "569e81b6-ffb4-4f86-e949-8611285a2258"
},
"execution_count": 56,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712558461.4504287\n",
"Mon Apr 8 06:41:01 2024\n"
]
}
]
}
]
}