Datasets
Models
Downloads: 1
1263 lines (1263 with data), 217.4 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": 45,
"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": 46,
"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": "fbdfa416-a175-45e4-878f-d147a4ac8f52",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 47,
"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_12 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_13 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_14 (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: 1069057 (4.08 MB)\n",
"Trainable params: 1069057 (4.08 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": 48,
"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": "fdef67a7-2417-403b-aece-06bf7237527b"
},
"execution_count": 49,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712630635.3426485\n",
"Tue Apr 9 02:43:55 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "ef0e19ee-d816-4dd4-bdda-c8d8b5103214",
"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": 50,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 1.0034 - 2s/epoch - 110ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 1.0000 - 129ms/epoch - 9ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.9992 - 126ms/epoch - 8ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.6231 - 124ms/epoch - 8ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0733 - 129ms/epoch - 9ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0269 - 128ms/epoch - 9ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0135 - 127ms/epoch - 8ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0070 - 119ms/epoch - 8ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0056 - 120ms/epoch - 8ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0043 - 117ms/epoch - 8ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0036 - 119ms/epoch - 8ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0020 - 116ms/epoch - 8ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0013 - 117ms/epoch - 8ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 8.1411e-04 - 118ms/epoch - 8ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 4.7856e-04 - 120ms/epoch - 8ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 1.2988e-04 - 121ms/epoch - 8ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 5.3956e-04 - 122ms/epoch - 8ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 2.3236e-04 - 123ms/epoch - 8ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 4.8753e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 1.8318e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 1.3272e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 1.2556e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 9.9636e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 8.7628e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 8.1315e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 8.6374e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 6.8072e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 6.1926e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 6.7034e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 8.2468e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 7.2891e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 4.9113e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 4.5933e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 4.4020e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 3.5963e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 3.9564e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 3.1414e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 3.2044e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 2.8829e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 2.8295e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 2.6961e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 3.2953e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 4.1020e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 5.4188e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 3.4530e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 3.6809e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 4.0916e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 3.5602e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 2.2521e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 1.5480e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.7136e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 1.6444e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.5770e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.4893e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.2219e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.2704e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.6454e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.7337e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.5804e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.9509e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 1.0376e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 1.8195e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 2.7383e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 3.2482e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 3.3841e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 4.0110e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 1.5350e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 1.1874e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 9.2445e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 8.8728e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 1.3702e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 1.1340e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 6.0499e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 8.8252e-07 - 127ms/epoch - 8ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 6.7213e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 4.4840e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 4.6963e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 6.4668e-07 - 127ms/epoch - 8ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 6.5590e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 7.4891e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 4.8054e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 6.8711e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 4.5125e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 4.0139e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 5.7615e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 7.4042e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 7.8608e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 4.8427e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 3.2390e-07 - 128ms/epoch - 9ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.3261e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.1298e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 4.6878e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 4.7734e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 6.7268e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 5.5759e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.2436e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 1.6079e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 5.4418e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 2.8223e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 4.1114e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 3.0464e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 5.5669e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 1.6555e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 8.5565e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 4.2182e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 4.3084e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 3.4479e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 3.7462e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 3.2935e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 3.9894e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 4.8003e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 3.7502e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 4.9226e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.7178e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 1.9994e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 2.7988e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 2.0335e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 2.1964e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 2.4081e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 4.6015e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 3.7692e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 2.5062e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 3.1708e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 2.2587e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 2.1794e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 1.7958e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 4.5469e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 4.3104e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 5.0714e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 9.6683e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 5.8921e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 2.7142e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 2.4933e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 8.1932e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.2163e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 3.3748e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 6.2020e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 2.5165e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 9.6011e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.7423e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.2631e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 1.8458e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.3639e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 3.5599e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 4.5238e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 1.2821e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 8.4608e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 6.4767e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 5.0605e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.1025e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 3.0972e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 2.9043e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 1.8512e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.6641e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 4.4617e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 3.6704e-05 - 123ms/epoch - 8ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 1.7681e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 1.0064e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 7.1420e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 1.1585e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 1.0567e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 6.0409e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 5.0642e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 3.1916e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 2.4863e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 1.8312e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 1.8544e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 1.5349e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 3.6803e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 3.7763e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 2.9426e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 2.1030e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 5.7077e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 5.2540e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 2.8671e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 1.6766e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 2.8305e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 1.8607e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 3.8363e-07 - 127ms/epoch - 8ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 2.9529e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 6.5541e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 7.1283e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 5.6609e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 4.0284e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 8.7617e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.2772e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 3.8257e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 2.8803e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 9.4837e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 1.0329e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 1.8905e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 2.9178e-07 - 128ms/epoch - 9ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 3.0372e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 2.8427e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 2.2616e-04 - 120ms/epoch - 8ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 1.8199e-04 - 129ms/epoch - 9ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 1.0556e-04 - 122ms/epoch - 8ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 3.6207e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 1.2328e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 6.9532e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 1.9384e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 4.7528e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 3.6307e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 9.1406e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 9.4038e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 3.9667e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 1.8456e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 2.5899e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 2.3281e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 5.1713e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 6.2939e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 3.9063e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.0454e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 2.0618e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 2.6700e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 7.7054e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 2.0603e-05 - 127ms/epoch - 8ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.4820e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 3.7827e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 4.4661e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 5.7942e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 1.9294e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 6.8946e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.1416e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 2.3100e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 1.0411e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 8.3921e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 1.6760e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 3.7050e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 6.4870e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 4.0809e-05 - 120ms/epoch - 8ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 1.0352e-04 - 121ms/epoch - 8ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 5.0266e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 1.0282e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 1.3075e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 1.8748e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 3.7341e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 7.7084e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 1.1921e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 7.2124e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 7.5071e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 8.0956e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 6.6756e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 4.5111e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 1.9188e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 1.8692e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 1.1439e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 3.5966e-06 - 131ms/epoch - 9ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 3.5067e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 9.4277e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 8.5305e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 1.0977e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 1.5406e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 3.4172e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 5.0169e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 1.3477e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 4.2612e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 3.6949e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 1.0604e-05 - 128ms/epoch - 9ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 1.1700e-04 - 130ms/epoch - 9ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 4.3889e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 0.0336 - 124ms/epoch - 8ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 0.0228 - 129ms/epoch - 9ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 0.0144 - 121ms/epoch - 8ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 0.0073 - 119ms/epoch - 8ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 0.0013 - 122ms/epoch - 8ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 0.0018 - 119ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 2.1615e-04 - 119ms/epoch - 8ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 1.5704e-04 - 121ms/epoch - 8ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 8.8615e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 5.6498e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 2.0671e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 6.7822e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 4.1459e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 4.0161e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 3.0053e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 2.2798e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 2.2259e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.7218e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 1.4170e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 1.6735e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 1.9393e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 2.0262e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 1.9199e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 9.8590e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 9.6359e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 8.6744e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 1.2986e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 7.0500e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 5.8410e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 6.4863e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 5.9003e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 7.2857e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 3.6502e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 3.4284e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 2.9003e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 4.1485e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 3.3768e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.8412e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 2.3282e-07 - 120ms/epoch - 8ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x7f3b0073f040>"
]
},
"metadata": {},
"execution_count": 50
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "8429111d-422d-4dfc-f754-baad0d076a98",
"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": 51,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7f3a58619570>"
]
},
"metadata": {},
"execution_count": 51
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAGFCAYAAABg2vAPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACIaklEQVR4nO3dd3xc1Zk//s+5d3pXr5bc5N47xjbY2NhACJAACSmk97JJ9rvJb8t3N1uSrd/sbnaTTTYNEgiBEAIhgDFgA8a4917lIquOpOn93vP742pGGk27I42kkfS8Xy+wNXPn3jOyNOe5pzwP45xzEEIIIWTSEsa6AYQQQggZWxQMEEIIIZMcBQOEEELIJEfBACGEEDLJUTBACCGETHIUDBBCCCGTHAUDhBBCyCRHwQAhhBAyyWnUHnhX1RdGsh2EkAKLzahL+to7zZj0ta8u9V4gUC8nfa2pDSR9Pbe6Y9jt2lR+btjnIISoc7flDJrqW3MeRyMDhBBCyAT1sm+equMoGCBkkrLclHMfRAiZFCgYIIQQQiY5CgYIIaqdba8a9jl2OucUoCWEkEKiYICQScLaHMz7NbFW0wi0hBBSbCgYIIQkmFroI4GQyYh+8wkheSnEVAEhpLhQMEAIGXW0boCQ4kLBACEkq3TrBmh0gJCJhYIBQiax4eQaoICAkImDggFCyJBRQEDIxEDBACEkyWjtKKB1A4QUDwoGCCE5Zcs3QKMDhIx/FAwQQoaNAgJCxjcKBgghhJBJjoIBQkhBDGV0gNYNEFIcKBgghBQMTRcQMj5RMEDIJJKuWFG6XAPpdhRQ0SJCJi4KBgghBUWjA4SMPxQMEEIIIZMcBQOEkLRoqoCQyYOCAUImKM3lm6qPHU6NgnRoqoCQ8YWCAUJIXmh0gJCJh4IBQkhGo1GngHINEDL2KBgghORNzegATRUQMn5QMEDIJJMu1wAhZHKjYIAQAiDzIsJMUwW0doCQiYOCAULIiKGpAkLGBwoGCCFDRqMDhEwMFAwQQnIazq4CGh0gpPhRMEAISRhK8iEaHSBk/KNggBBCCJnkKBgghKiSbaog1+gATRUQUtwoGCBkEqJcA4SQgSgYIIQkybZuYDijA4SQ4kXBACFkzFF9AkLGFgUDhJAUhS5pTAgpbhQMEDJJDXXdwFCnCmgRISHFi4IBQgghZJKjYIAQkhZNFRAyeVAwQAjJ23DSExNCig/9RhMyieVaN0DpiQmZHCgYIIQMCY0OEDJx0G8zIROY5vLNYZ+D1g4QMvFRMEAIGTW0vZCQ4kTBACGT3HDqFGSaKqB1A4SMLxQMEEJyoqkCQiY2CgYIIYSQSY6CAUKIKplGB2iqgJDxj4IBQsiw1g0QQsY/CgYIIaoVYu0A7SggpPhQMEAIGTZKQETI+Ea/wYQQAOqnCmhnASETDwUDhBBCyCRHwQAhJKHQCwlpRwEh4wMFA4RMcIWoT0AImdgoGCCEJFEzOpBu3QAtIiRk/KLfXkIIIWSSo2CAEJKCkhARMrlQMEAIIYRMchQMEELSotEBQiYPCgYIIUOidhEhbS8kpPhRMEAIyYhGBwiZHCgYIISMOipWREhxoWCAkEmAEg8RQrKhYIAQklW2qQIqWkTIxEDBACGkoCgTISHjD/3WEkJyooWEhExsFAwQMkkMd90ABQSETFwUDBBCVEsXENC6AULGPwoGCCEjjhIPEVLcKBggZBIpxBZDmi4gZOKhYIAQQgiZ5CgYIGSSGY0ERLS9kJDxhX5jCSFFYadzzlg3gZBJi4IBQsiw0Y6CAuIcLCIDnI91S8gkohnrBhBCRp/m8k3EZtQN+fXW5iC804wFbBERvRLse7ywHgtAiHDIGgbfYhPct1oQc9BHNRlZ9BNGCCFjTOOKoeZnXRADMljfgIAQ47Ae9cN8OoC2T1QgWqEd20aSCY2mCQiZpKiSYfEof9GVFAjEMRkQwhwVz/eOTcPIpEHBACGEjCFNTwzG5nBKIBDHOKBvi0LXHhndhpFJhYIBQiaxsRwdONteNWbXLia6zqi64zrUHUfIUFAwQAgZksGZCAfvKBica4BSEqfHNaygxxEyFBQMEELIGAo16iDrsnf0XASC0w2j1CIyGVEwQMgkRwsJxxbXCnCvsSBTVgEOwLPCDNlIH9dk5NBPFyGEAoIx5tpghXe5Mo3CBYAz5U8A8C8womezfQxbRyYDyjNACCFjTWDovqcEnpUWWI4HoPFKkMwCfItMiNToxrp1ZBKgYIAQAmD4WQnJ8EUrtejdQqMAZPTRNAEhJIGmCwiZnCgYIIQkoYCAkMmHggFCSAoKCAiZXCgYIIQM2eDEQ4SQ8YmCAUJIWjQ6QMjkQcEAISQjCggImRwoGCCEZJVPQDC4PgEhZHygYIAQkhONEKjAOSBnSipMSHGjpEOEEFUoKVF6huYw7O96YbwSBuNAuEoDz2oLfItNAKNKg2R8oGCAEEKGyHrIh/KX3eAMYH2DArqOGCr+4ILhahjO+0ooICDjAk0TEEJUo+mCfpqeGMpecQPoDwQAIN71W08EYT5NWy/J+EDBACFkxJhaJu5HjPWwP+vznAG2A75Rag0hw0PTBIQQMgT69mjSiMBgjAO69ig0rhisR/zQdUQhawUEZhvgn2sENDR9QIoHBQOEkLzQQkIF1wAc/dMCmdT/V0ffC5SDLWeCiO7yoP2j5YiV0EcwKQ4TdwyPEEJGUGCWMevznAFCTBkhYFwJGuIjCRq3hOonnbQVkRQNCgYIGWGiToOpt83DgodvQdO2JdBbs3ciZHzwLTRCMgvgaYYGeN//MnX1jAPaHgmmC6ERbCEh6tEYFSEjaNqmBVj9pa3QmQ2QYxKYKGDVl7bi1DN7cfyJtzP3FqTocZ2A9kfLUf2EExqvrAQF8XkDAWBSjtcLgOliCIE56YNDISCBRTkkiwiItL6AjCwKBggZIVNumYX137wPvG8oWNCIAABRq8HiD68HOMfxJ3aPZRPJMEUrtGj5SjXMZ4IwXgoBMhCp1cI314iG+FqBbKTUaNB4MQTHbg8MLVHlED2Dd7kZrvVWcD0N5pKRQcEAIQVgLLXA4DAj5PIj2KNsJ1v2qU3gMgcT0t/VLXh4Lc78/gCi/vBoNpUUGNcw+BaZ4FtkGvAgR9QhQuOSMi8wlIFIjS7pIcsRPyr+6EqaehDDHPa9PhivhNH28XJwHQUEpPAoGCBkGEpnVmPZJzeidtn0xGM3D1/Gpe3HYa8vy/paQSuiYe1sXH7txEg3k4w2xuBZZUHpDnfapzn6gojF/QGE4JdQ/rJLmWkYNGDAOKDriML+rg+u220j124yaVEwQMgQlc+tw9Z//giYmHynVrNkGqoXTc35ei5z6KyGEWodGWueVWYYroYTiwTjN/u878el6/0lkA39PzvW4wGAZ96qyDhgO+SH6zYrpTgmBUfBACFDtPZr94CJAoRBwYAgCpCRu5SvIArwd3pQt2omTGVWhHr9uHn4MuRojpVnZHwQGDofLoX1aAC2Az5onTFwkSEwxwD3LZaUKQKtM5bzlGJAhv56BJJFRKxUpKCAFAwFA4QMQdmsWjgaKzI+Hw8QZFmGIKTO8XKZIxqKYM2Xt8HgMCceD3uDOPyTN3Bpx/HCN5oMmcYVg/FSGEziCNdoEZ6iU9cRC8riP+9ys1LiOMtrZB1ThgWy7DDhAGofdwIAIqUauG6zwr/QlPkFhKhEwQAhQ2CrLVF1nCAI4JyDDegEZFkGYww6kx7ckHx3qLMYsPYb7wHnnNYSFAEWkVH+oqu/4FBfdcJIhQad7y9FtFKbx8myBw+BOUbYD2SudzA426G2J4bK3/eixyvBvdaqvh2EpEHBABk3BK2IqRvmYfrmhTA6TPC2ueC61gVHQwUMDhN8HS5cevU42o9fG/G2RPxDTxbjau6EqcwKvd2UstOAMQbOOZZ/ehOad52CHMs93TDWrM1BeKdNwERKnKPqN90wXIv0d8J9d+1aZww1j3Wh9bOViDkK8zEaatQhNEUHfUskZQFhurTH8a9L3vDAt8AEySYWpB1kcqJggIwoQSuicf1czNyyCKZyK/xdHlx69TiuvXMOXFLf0entJtz5Tx9GybRKyJIMQRTgmFqJhrWzE3fe5bNrMX3TQlx96wx2//Pzif39apXOrIZ9ShliwSjajjYjFo4mPV8yvQq1y6aBiQK6L7Uj4gtBZ8m9AJAxhlg4ip1/8zT8XV4YHSZs+38fy3q8wW5GzdJpuHnwcl7vgRSOoTkM49VI2ucYB4Qwh22fDz3bHIW5IGPo+GAZKp/phvFaRFloyJF1UWGc9Zgfrg20y4AMHQUDZMRozXps+e6HUD67NtGBW2tLUbtsOjpOXccbf/mblA43k/XfvA/2hnIA/fPx8aH3+J/xpD6N6+fC09qDY4+/percpTOrsfbr96B0RnXisWgwglO/3YuTT70Dg82EDX/xPlQvboTcF8AIooBgr/rytBq9Flzi8N7sQcnUzGsNBhq4loCMPsupILgAsAwxK+OA5XigcMEAANmoZDXU34zCdD4IFpRhPxLI+TpNLy06JcNDwQAZMWu+ejdKZyodbLwDj/9ZMbceK79wJ/b+x0tJr2ECS7mjt08pQ+3y6VCLCQxz3rsSJ3+zB1I4+wpte0M5tv7rRyHqkn8VtEYdlj56G3RmPWqXToO9MTkQAQC9zYhYKAJBqwETWNK6gGz8XV6Vx3lUHUcKgHPoWyLQ9EqQDQJC0/UQAjJybQoRwzzjwkBNTwyWEwFovBJiFhG+RUbEytKsMZA4NK4YIDDEHMoOgXC9DuF6HRDjsB0NZC2VDAbIetpVQIaHggEyIkzlVkxdPzdj9j1BFDBj80Ic++WbqFzYiBl3LETF3DrorUbEwlFcfesMTj+7D+7rTlQvmZo1k186OrMeZU016Dx1I+txiz+6AaJOk7I9MG7e+1Zn7OQFUQTA0LzzFGZsWZT1OrFQFN2X2gEA3Rda4W7phrW2JONOg0C3Fx0nRn7tAwH018Mof9EFXXd/4CjpGSKV2pyr+2MWITUQ4BylO9yw7/crmQT7zlGy2wvPchO673IAAgOLcdh3e2E76IMYUi4SdYhw32qFd7ERltNBWA/5EzUPMuYfkAH//Am4ZoOMKgoGyIioWtCQs/MWNCLu+8kXoDPrwXn/J65Gr8X0TQsw9bZ5eP0vnlJ9x51y/gwdfJzWpEPD2tlZj4sv6MscEAioXtKItmNXUbVgSmKqYiDOOdpPXIMc7e9sDvxgO+74h0fAZRlsQEDAZRkAw4EfvJr3mgeSP93NCGp+5UwZARDDHMYb6dcLxHEGZcvgIPZ3fLDtV3YFsL45/zjr4QBkPUPvRjuqfu1UFicOeF7jklD+kgv2d7zQuiVw1p+NMN0iQs6A4DS9MopAyDBQkmsyMlT231qT8iHGWPIwu6ARIWhE3PZX70PXuZt5jQoAgBSV0HulM+sxeqsxZ8AQb1s2WrMB7/zLC/C2u8A5T+3EOVC/aibe/8RXUbWwAQDQdvQqXv/Lp+Bu6Uk61Nvai53ffgY39l3I2S4yfKVvuAE5Nf1vHGfpBwY4A6KlGrhXW5IeZ1EZjj3ezHfxAOzv+mF/xwvD1dRdA/HXad3KGoCBzycyGPZdHwACswzofLiUkg+RYaORATIius60ZL2jBpDzeUEUYCyxwFxhQ9fZFpQ11aS98x5MlmRc2XkSYW8w63EhTxByTFJ1zkw45/C1uRDs8eGlL/0M07csxPJP3QGNQdu/wLEvkNFbjbjjO4/gpS//DJYqOxZ88FY4+hZFRnwhNL91Bgd/tKMgGQhLplVi7v2rULd6JgRBQNe5mzj3wkG0Hr4y7HNPFKJHyrhbIIEDgTkGGK5FIAaV4QMuKMPy3Vvt4IbkYNJwLQIhkn1EhwFw7Fa3biTT6zkH/DN06N1oo8JFpCAoGCAjwtfhxo19F1G/akbf3HoqNcP/UkxC6cxqvP2Pv8e2f3sUpnIrAKYsNOybWoifJ35H7rraiUM/fj3nuWPBCK69cw6N6+YMOSBgjOHGvvPK+cJR+Ds90BrTD9kKogBwjlv+5B5Uzq9P7EwAlGRDs+5eiqoFU/DSV3+ec+FjNlM3zMW6b90PcJ54X7XLpqF+1Uyc/M0eHH3szSGfe7hirSZoanOvjh8Nok9F0CUAkSotOt9fCn1rBExSEg7J5gw/01F1UzvCMNNHMACmKxEYf9aFtkfLEamjaQIyPBRSkhGz99//CE9LT9LQOZflpPUBuTDGIEUl+Ds9ePGLP8WRn++C+4YTwV4/ei6148a+i/C1uxANRuC+4cTBH+/AK994HNGAurLAx594G3JseHfiPQOmIxrXz8l6PkEjomJenfL3QVMUjDE4Givwvse+BGOpJd3LczKVW7Hum/eBMZYU4MT/vvCDt6Ju5YwhnXuikSwqAkAZkKwiIDKEp+gRmqrPGAgAQLR89O6vGAdYjKPi+V5lqICQYaCRATJiwp4gXv7qLzB980I0bV0CY5kF/i4Pru0+i+WfukPVOgBBFGCtsmPhI7fi+p7zOP3sPpx+dl/B2uhp6cHb//Q8Nv7NQ0NeqBjx9E9H6EyGlCqGg+W6jsFhxh1//wH88cs/y7qSPZ1Z9ywDGMv4vZUlCXPvX0XJjABINhHBaXoYroYzb90TAf889Sv1oxVahKu10Lery58xXIwDuu4Y9DciCDfoR+WaZGKiYICoJuo1mLphHqqXTAVjQOfpFlzZeQqxYOZ511g4igsvHcGFl44kPV69qBG1K2ZkXcAXH0GYtmkhmMCw9GO349o757DnX/+gOllRLhXz6rH+m/clrpdvQBDs9aHzdP/2RU9Lt7INUkx/nsFTG+kwxlA6oxo1S6ai7ejVvNpTMbc+6/dUEEVUzKvP65wTWc8dNtQ81gVI6RcR9my0JZUZBucwNIdhOheCEJYRqdbCt8QM2dh/TNd7Haj73y61a2hTpNs1kOt4XVesf0dBnottCQEoGCAqlc6sxuZ/+CD0dlNiyH/axgVY9smN2PXt36Lj5PW8znfoJ2/g7gUN0Bi0SZ3X4A6ZMQZR2z8sO+WWWVj3rfvw5t89O+T3Yq60Ye79qzBt4wIYHKbEddLJFSBoTXqUz6lD15kWAMDF7cew4ANrs15fTdAhxyTUrWrKOxgwlubOWphPGuiJLlKrQ/ujFSj7Yy/0nQPyDBgF9N5uhXdl/3SN4JdQ/Ssn9J2xRIfNTwZR+roH3Vvt8K5Sjo1W6+BdboL1cCDvTn0o3TgDYN/jRflLLnAoNQ7ct1gRnJU7VTYhcbRmgOSkt5uw5R8/BJ3VqMxFiwIEUQBjDBqDDnf8/QdhrrLndU5PSzde+dov0Ha0OWkNQSwYQdgbhCzJaTtMQRTQsHY2SqZVDum9lM2qwXt/9FnMuW8ljCXmlC2NA6nptAWNiM3/8EEYSpRO2NvWi6OPv6m8ftAWQ1mS4WnpTptoKPXaSAqC1NCa9bDVlmY/ryzTjoJBwvU6tH6uEjc/U4GOB0vR9uEyXP9GdVIgAM5R87gTur6AIf5TwQCAA2Xb3TCfUHILiO4YhODQAq6hBgSa+FZEAIbrEVT/phv2PUPfsUAmHxoZIDk1bV0MnVmflBwnLn5XP/s9y3HkZzvzOq/7Rjfe+KvfwFRuhaXKgYgvhEC3Fx989k+zvk6OSWjcMBe9zdnzCAzGBIaNf/0QRL1WdX4BNdsfodei6a6lOPnrdwAAJ5/aA1+HGwsHbh30h3Dh5aM4+et3sPXfPoqS6VXZz6sR0HO5I6/3N2PLopzrFcAYLmw/mtd5JwXGEKnRIVKT/mnDlTB0zvQ7POJJCsu2uxFq1KP2p10Qg3JSp84HHZ/pPEOVlI+g7++lb3gQnKFHpJp2GpDcKBggOU1ZOztrUhNBFNC4bk7ewUBcwOlFwKncxZgrc1de41wZns9X/ZpZfVsT1VOzhkAQBTSsmZUIBgCgeecpNO88BXOlDYJWA3+nO5E/4PW/+g3e81+fytgWLsuIhaJo3nVKVRvtU8qw+NHb0HjrnJztZYwh2KO+wFIh6WMRmGNhhKMywto0OfqLkOiVYDkWgPVI9u8ZAyCGOMr/2KsEAnLq88OV6O/7qhkynn0kgTPAesiP7vdQMEByo2CA5KTRa3N2MoML/QxVsNePaDCSca8+oHS+nkGZ+9SomF077CRDmehtRhhLLSkdrb8ztdhQqNeP5z7xA9z17x9H6YwqAP1BR3xb4tv/+HvEQrkXSZZMr8K2f1MKLanN0hjxhlQdVyhVgV7c1XIYi3quQQCHdJzhRN0U7Ji7CKjO/fqRpumOwnwmBCEkI1aqgW++EdwgwHrYj7JXXIkywmoYL0cK0vGnxYBwjRaRGh20zqiSyjjb4RzQt6b/GRL8EjQuCbKBIVaqoQyGhIIBklv3hTbYp5Rl7ETlmITui+0FuZYclXBpx3HMfs/ytEP5nHPIMQmdp66jbtVMSOEoOs+0qMraJ8ty3h96agskWaodePCJr+LGvgs48MNXEyMdGdsSlfDK1x/D7HuWYfa9K2CrK4UUjeH6O+dw+tl9qqcI1n79HtXTHrIko/PUjVEdGaiJOPHZU3+ARpYg9PWoIudYdPMG5ra34uWSZejNc7SmYGLKnbz1RLC/oJAMlL7qgne5Gfa++gL5GMkulXGg+24HItVaNHyvPee1OAA+6BNe0xtD6Q43TBdCiemESIUGvZtsCMymYkeTGQUDJKfzLx3GzK2LMz4vaEScf/FQwa534sndqF85E+Yqe1InJ0uyMipwswfv+eGnE3fTYW8Qp3+7F6ee2Zv1vAaHWVWnOTAAyKcmAhMY6lfPRFlTDV766s8R6s3emchRCWefP4izzx9MW7o5l5LpVShryjDJPYhSAAk49ss387rGsHCO9/e+BY0sQRx0ay1yDkgS1r15Di8+uHLUmsTCMoxXw2BRDvPpIEwXlFGSpIJCMSgVBzGynXs+OADfIiMitTpoXDGIAXULFEWPBBaRwXUCNL0x1P60C0JITlpjoO2KoerpHnTdVwLfYtPIvAFS9Gg3Acmp+0Ibjv3qbQBISqEb//vZAue8D3uDOPLYLvRcaoc0IJuf62onwt4g7A1lSdMWeqsRyz65Cff99POY9/7V0FtT73DKZtVg1l1Lc157cHbE+NdqsyYKoghjqQULHrpF1fGJ6wyhQqF9SpnqY0OuAHb+zTPoPN2S93WGqjbqRG20OyUQiBM5R2WnByXdozBSIXM4dnnQ8L12VD3dg8rnemE+H0qbW4AN+nO0DZ6VkHUMrvVWON9bojygMuUxA6DxyCjZpUxVlbzhTgkE4sdxAGUvu8Ai6YMMw+UQqp50ovG7rWj87k1UPemE8fLoTjeRkUUjA0SVE0/uRm9zJ+Y/uAaVfUlreq904Mxz+9G863RBrmEqt2LWPcsx+55l0NuMyvx5X6cfcvthLLNAZzFkXL9gry/D8k/dgSWP3obd//h8UuW/RR9al1IueDDOlRVZA0cDhpKVUBAFNG1bgsM/fWPkyhAzwFypbjvn8Sd348STu0e9JHJFzKXqOHuvH71lQ0u/rFbZK6689/2Ppd5NVkSqdOAiEJ6iA9cqP7csIqPydz2qRy0YAOuRANxrLDCfTR/8xI9DlMN8JgjfkuRcFfZ3vCjd6Ukqp2y8Eobpchg9m2xwrxujaR5SUBQMENVuvHseN949D0EjAIwVpLoeAAhaEWu+chdmbF6YNKc/cI2C3mZS1TEzgUHUanDbX70PL33l5/C29mLRR9ajfnWT6tcXgtakh8aoQ9SvrkZCPqqXTMUtf3I3rDUlOY+N+MM49cy7ox4IAECEqdsxEMszn0K+tM4obIfHpjiSmi2F6ZS85UXMIsK3xIRItRa871tpPeyHrjOW17mEKIfhRmq55NQDAU1PDLrWCMSAjJhNhBDhKN2pjCyk3b6404PQVH1/9kMyblEwQPImxwqbwW79t+5Dw9rZWe/a87lDV+bfgXXfuh/WGgc0+uFvY8t3hECKxpLSNLO+ZEkztiyEscQCX4cbl149hpuHLudVf6Byfj02/8MHVaecPfXMu8OqgDgcl/R1CDMN9Dzz9SM6EW11uYOa4bAcD4ALSNnuNxoYAC4CvgVGmE8HIaj8p2ASoHVLcLzthfVoAK2fKIdk18B6ZGhBjWRQ8fMiA7YjAZS80z9tIxlY0ojAYFwAbAd96KrPnuyKFD8KBsiYKmuqQeO6uQU/r6AR4WgsV92Jq1kToLZ2gRyT0LzrdOJuXGvWY8t3P4Ty2bWJRZAl0yrRuG4OWvZfxJv/8DvVoyzLPnUHwFjGLIbxCpGMAad+uxennn5X1XlHQlTQ4m3rEmz2HMp4J3t82VRII7DVcyDRN3bplzkAySTAeV8pnNskTPl+B8Qgz74lcODfuZLroOKFXrQ/WgGNW8o7xbFkERCabkCoTgt9azTrCIEwaGGiEMrRVhnQ38hcm4SMHxQMkDE19fZ5I7b3P6/RhFy1AiRZ1RSCLMmQYxJM5VZ84JlvgINDCscSJYnjuxni77du5Qws+8RGHPrf13Oe21LtSKzXyOb6nvM49L+v5dzeOBretC6FYA5jY9tJAAwyYxC4skRu16x5uLp05BMNSJaxWyfNAIheGZW/dkLjlaAJ8nwLUYJxwHg1Aq0zCtnIIHjzKAEOwH2LBRAYejfaUP1Ed9r1BnzA8YNfnwvXjJeVGCQbCgbImNLbRmZv81AqEGY9l8DQsv8ipqyZlXLugZUIw74gjHYzqhc1Jjr8bG1hgoBZdy/DsV+9nTStUDl/CqasnQWNXgvXtS5ceeNUov5B1rZKMnoutxdFIAAAnDG82Lgau6vnY7nzMmzRAHxlWhyZMhVukwlzWX4pl4fCt9gExx71OxYKvaWQATBdCid9PRT6m1FEHSI03twjHfFpEc9yEzxrlEA0NN2AzodKUf5iL8QQB+/LZAg+9DZxBgSoINKEQMEAGVP+DveIZD8bbiCgDPFzKDexHHv/82Vcfu0Emu5eimWf2JjYvjgwEPC09cLWt6hv4EhHrrZoDFpUzKlF29Gr0FuN2Pjth1A5fwrkmATOldGE5Z++A4d+knv0gIlC0QQCA7n0FrxRp+Sq0NSqn/dmURmm8yGIHgmyRYR/tgFcn3qnz8IyTBdDEAIyYg4RwRkGQGRgMQ79zShiVkFVJwr0b7WL/70QCnEeXWsEhhvR7CmIoaxR8C8ywbvUnLKwLzDXiOtNBpjPB6HpkSDrGYQIR8lOT95tjF/LuyJ3kEqKHwUDZExdeu0EFn14fd6vk2MSosEI9FZjYh4e6Euu09f5Dicg4OC4sec8epo7cWn7sUTWvrYjzWCfviNxtz/wGtYq+5BHJOKLJzd++yGUz6kDkBxQiFoNVn9xK7ovtaNkWmXG5ElSOIrre87lff04g92ExvVzobcZ4e/y4Nrus6rSIo8E6xE/Sne4IUS4kiGQA2Uaht6NVuVulzGAc9jf9cHxlhdCjCc6SskswLXGAsdeH8SAnNi7n8+/TDENfnMA9oO5MyLGqyg6782yKFPD4J/fn1zIdCaobjpg0IW4yNDxgVLEHNSNTAT0r0jGlL/DjRO/fgeLswQEA+++AWVePuwJYvv/+SUsVXbMe3ANapdOAxMEuK454brehanr5w3r05yB4a3vPpf0CWipsuM9P/gUtEZd2g4/226IbGRJRs+VDlQtbEDl/Cnp2yMwyBKHFImBSzJkICkgiAchh3+2c2idNwOWfux2zH9wDZggKDkZRAGrv7wNl3Ycx6VXj6PnUmFSTqthORFA+R9d/XfofX9hMY6y1zyAyOBZZYF9jy+x9a3vbQAABL+M0jdSH1cr30V6Ix045HN+yZjfz2GwSQ9ZyyBkSGbEAXAt4FpvheG6MpUVatTDu9QE2TSyiz/J6KFggIy54796G7PuXgqDw5y+k+17LBoMI+QK4PJrJ3D+pSMIuwPwtvai7ehVZXEfY+CSDK1Jj4o5dTCVWYe0MJHLMlzXu1O2/N3+1w9Ca9IXbC0CoHTigijgPf/9KXScvJ51MaUgCqiYW4cd33oCKz9/J0qnVyWeC/X6cfSxN3Fpx/EhtWPxhzdgwQfWJt4bE5Q2aPRazLl3BebcuwKua13Y/4Pt6DhxfUjXUE3mKHnDnbWTdezywDfPCMdbqYWggP6h/pHupIspZTHQl7Y4z5TCXCsgMEMPy7n0GQUZABYFwnV6uNflripKxicKBohq9oZyVMyrB2SO9hPX4Gt3FeS8pnIrjCXZM9DJMQnnXjiEo4+9mfb5+Bw/AEQDYWz/019i2/c+BovKLH1JGMO5PxxMemjWPctQOmP4K98HTyPE/25wmNG4bo6KpjG4rnbhj1/8KUqmV8Fa40DYG0TnqRtDTiykNeux4OFbcgY59ill2PLdD2HH//ckWoMjt11PfyOSc35fDHOUbXeBZdmRORqddLEFAlwDeFbnn81R58yxFkEArMf8CE3Lv3Q4GR8oGCA5GUstWP+t+1C9eGqiM+Oc48beC3j3e39ExDe8HOWmMhXpTBlTMh/mYKsvg9aog6/dpdwd5pjDz/T8lDVNuPHuBYRcfsy9fyVWfv7OguxQyPR6QRSS1jtkEnL7E9/v3isd6L0y/NX4U9Y0qSpBzQQBHDJWff5OPP/v24d93UxElYGG5Uwo7216I0XNCEGhFyWm0/lQKSRr/qNhGo+cM5+ApndskleR0UHBAMlKa9Jj2/97FOYKZXiQDVicV7+6CVv+8UN45RuPDys1cc2yaTk7WkEU4DzflvH5xvVzsfTjt8NWp2RCkyUJgpj7QzEe2Ay+W69dNh1b/+2j2Pf9V7Dy83cmHh9JTBCUpEEZvheyJOP8i0cKnlpYZzHkrNsQJwgCSmdWw1HjgKvNVdB2xMUc6juz4f6LFHKYP9f+ff8cAySLANuhwtZIiC+u7LrfgWDT0LbqSkYBQiTz7zBngGSm9QETGQUDJKumu5bAUmVP21EIotCXQXDOsIoV2epKVX0qtx9rTvv4LV+7G03bkisSCqKo+k4+3TGCRoStthTLP71pxJIipcW5UvdhwA4JQAkEeq904PSz2cs0D4W3zZX34kezwzRiwUCkSotwlUbJwZ8j7hlOZ951lw2mS2GYLoaH3TkzAJJO2aYXPxcXgEiZBrESEZEaLcK1OpS+7kneuzhMMauAwGwjPCvNiFZkSbvNOYxXwtDHFwBO1SM0VZcYifItNsGx25u5kBEHfAupvPFERsEAyWrmlsXI9nErSzJmbF40rGAgFoz23Zlm7nC5LCMaTE17uugjG1ICgbh0d/15YUDpjOqM2/hyGbwLQt01GeSYDNfVTpQ11QAAwp4Azr90BKeefndEtvm1HrqMQI8PRodJdVAQ9I5g+VrG0H2XAzW/coJL2Tt7tVvi2KC/u1eb4VthgW+lFRXP9cB8Opi7kE+Oa4gRnvR1uFyE1iNB3xWD+UJhC1ZxBoQadWj/aHnOqSWtM4rK3/RA1xNTEg0BYLu9iFRo0PGBMsRKNfCsNMN6xA/Rn1rimDMgUq1FYDYlF5rIKBggWRkcpqxpeAVRgLE0/6Qjok6DupUzYCyxINDry3rnLUsybuy7kFIgyVpTgsUfXpf1OsMZ2meMAcPIZDukfAOMgQnKf0+9798g6jUIuwMjWnWQyxx7/+MlbPybh8AHjUikHivDfaMbPS09I9YeAAg36NH2sQpU/6oLLEf8I4tKYR813+1IlQaeW6zwLTQmOlHnexzQuCUYbkSGPNKQLo2vobMwVT3j4hkDGQcCTQZ0PVCSMxAQAhKqH3dC7Ks5MLBYk7Y7hppfdqHl81WQzSLaPl6Bymd7oG+PJqYeGIDgTAO67i8BxGJaLkkKjYIBkpW/0wO9zZjxjlGWJPja3Xmdc9bdy7DsU5ugM+uVojoCgxyTACG1AE+8Ezz1dOrweNNdS1SPE6cbIVBz5z7s0YUhEEQBpTOqUbdyOoxlVjAwdJy6ge4LrSN2zZsHLuG1P/81ln3idlTMTV//QPm3YKrqKBRCuF6XyCWQbZV7YLYBhuthiL7kojrxHw3PChNcG2zgOgauS/055joBznvsqPnfLohjV9MoK5kB7g1WcA1DYJYB0XJ1lTitRwIQA6l3+4ASGIgeGdbjAXhWWxAr1aD1MxXQtUZhaImAC0Bwuh6xsuFX/STFj4IBktWF7Uex5it3ZXxeEEVcfPWY6vM13bUUa77af774qAMThMTfE2l4NQKioQh2/9PzaTtC+5TyvAMBLstKACIK4DJXNQUwmoHAQBv+/H2QJaV3UhZQtuKt7/wO/s70e+uHq+PENbzy9cdhrrKjadtSzL53OfSW/qHhQLcX+3+wHa2HrwAz6kakDYN5l5th3+sDlzMszpMB961W9NzpQOkON8zngimliu2HArCeCMKzyoLe26xp73DLXnFDKNJAAAC4DnBtyH+Pv+VkIOf6BPOpQP92RMYQqdMhUqfL/iIy4VAwQLK6/NoJNG1dgtKZqXPnXJbRevgKbh64pOpcglbEsk9uTPscE5Q78GCvH5d3HIeo08B1tQtX3zqDWDj9OHE0GOnr2LN31olAgPO+oCP+hKpmj6mB3/PSGVXY+q+P4sUv/gRRfxiCVkTjujloWDcHWpMe7utOXHzlKFxXu4Z1TX+HG8cefxMnfr0bNUunwWA3wd/lQceJayM6XZFOzKFB50OlqPxtj7K2su/y8SFz570ORGqUjqvrwVL0eGKoetIJXVdyqV8hwmF/xwutM4rOh0qThtc13VEYrxVvGV4OIDBnaLsEhFCOLYNQv5WTTGwUDJCs5KiE1/78Saz47BZMv2MhRK0ytx8LR3HhpSM48otdqjuI2mXTEwV+0mGMwVRqQcuBS+g605LzfNf3nMP0TQvUvRGk3uGrKUlcTASNCHOFDTO3Lsa1t89iyz99GPb6ssTOg+qFDZh730ocf2I3jj/x9rCvJ0cl1YHeSArMNqLlS1WwHvLDeCUEJgPBRj1idhGWYwGU7PRAMgnwLTIBDCmBQBwDYD4XgvFKWClkBEDTHUPpa/lNc40mDgAMcK9RkYsjjWi5FqI3824JDiCSbRcCmTQoGCA5RQMR7P2Pl3DkZztR2lQNcA7n+VZEA/ndTRns6rYmqT3uxt4L6L3aCXt92eht/SsCM+5YhBl3LIS12gGgf/Qg/j1Y/JH18LT2oHnnqbFqYsHFSjTo3WJHL+xgMY6qp7phP+QHZ8pogejrq0WQI77jAmA56kdwhgHmkwFUPN87Om8gT4nwWgQ631+KaNXQOmzPchOMzZl3MjAA4WoKBsiw1kqTySbsDaLtSDPajl7NOxAAAH+XurlutcdxmeO1P/81evqy8HFZTiwKnKiYwGAstyhbHjMEQFyWsfADa0e5ZaPHscsDw1Wlg0sUMIr/Pc3agoGYDGh7JGg7okogMGDqoZhwDdC7yYbrX6se8hQBAEi27EEyB2C6PILbRMm4QcEAGTXtx68i4PRmnFaQZRm9VzvTVsdzTKtE1aJGWPruhuNCvX68/NVf4NU/+xWuvn12zBb75YNzPuS5d1mSIYVjyu6LDJggwNFYAWNp/jnqix2LyrAd9mdOjpPj9ZxByQJ40Aew4lw2olQJZHDfYoE8zKx/pnOhRG6BdBgAQ0sUQqCw2yDJ+EPTBGTIzFV2zL1vJabePg8agw7u606cf/EwmnedStvZcZlj33+/go1//VBK+ltZkgHOceAHrya9pn51E5Z9ciMcjRWJxzpOXsfBH+1Az+WOpMc6Tl6Ho7EC9inFN20Qf3+CRkTbsasob6pRKiDmuW5BEAW4r3Wp6uiHmiypmGk7YxAi2QOpbLtNGQd8i0woecOTsuugEAamHx5OzgIxyGE+F4R/vvqsfywqw3wmBK0zClknIDDHAJahLHHqa4tweISMKgoGyJCUz6nFlu9+CKJem+h0yppqsO7P3ovG9XPw5t//DlxK/bRt2XcRb/z101jx2c1wNJQnHnc1d+LAj3ag89SNxGON6+diw188oKToHaBiXj22/b+PYfufPp4UEADArr/9Lbb+60eV4kcsv22BA6cY8n1druNbDlyCq7kzsTtiwQfWYsbmhRCYqPpaXJbRduwaruw8hbqVM7MeG+z1I9DtVf0exg0V36qsi+WqNPDPNaL09fwWDQ78CVSbEXE4ow4cQMnrHpRud4NJHOE6HTwrLQhO14GBgWuSz246F0TFC71gYa6M93KgdJdHWQ+QI+iR9AySpbiCZzL6KBggeRO0IjZ+++GkQADovxOtX9WEee9bjdO/TZ9Hv/XQZfzh0GWUzqiCwWFGwOmF61rydjhBI2DNV7YBQErCo/h1Vn7+Trz6Z79Kes7X7sIfPve/mLFlEaZvWgCdxQCtSQe93ZSS0CgTORqDqFMWVanp6NV05id//Q56rnRg4QdvxaIPrVOyDOYRcESDYVx46QiOPv4WAGDl5/zQWY1p7/65LOPci4dGfRvgaIhWaiHpGcRw/u+NAei+yw6IDMFGPSynU3MSZHute5UZtoN+ZYtj3lfPDwOgcffvijBeCcN0uX8hYLhKA88aC3yLTDBcj6Dytz2JjIEDO39dRxRgyNhmzpRcDpRdkFAwQPLWsHY2jI4sKYgZMPe+lTjzu32JDomJAmqWToOp1IJgrw+tR5pT7uoHqlvVBL0t8xCpIAqoWtgAS7UDvnZX0nPRQBjnXjiIcy8cBABoDFrc9Z+fQMmAqYa0ze7rnAWtJuWxoeKcQ45JqFwwBau+eCcq5tbnldHQ7/Tirb9/Fr1XOyGF+0vIvvn3z2Lzdz6UmHoAkCiB3HbsKk4/8+6w2l2suIbBs8qiFNUZwuvLX3Sj7eNaeFZZYD0ZzH099AUCK03o2WpHYI4RZS/1Qtc9snPsg6cYBq+R0HXGUPGCC/qWCLTdys9F2u2U8bwMQGLnReIaDIhUauFaP7Rti2RioWCA5K18Th2kqJTIOTAYYwymciuMpRYEnF5MvW0eVn7+ThhL+gOIkNuPgz9+PeP2N0uVPaVyXzrmSltKMDCYFInBkCWwSNf+QmGMQRBFrPjs5rzOzzlH2BPEK1/7BQLO1OH+ztMtePGLP8HcB1Zh2u3zodFr4bnZjXN/OIxLO46nnaIZLZabMnx1I7dewbXBCl1nFObzoUQHp3Z+XtsTQ/WT3Wj9dAW6t9lRtt2dfY1B35/elRaAMYSm6hGcaYC2169qVKFQtQ5Snu/r1G2HA7nbIAC+BUaIARnGS0rOAcnI4F1ugetWC7h+4q0tIfmjYIDkjctyrvooAJRFc43r52LDnz+QsuVPbzNh/TfvA4C0AUHYE1S1uC7syX13Z6svSwpERlu+iwSjgTAubj+GU8/sRcjlz3ict7UXB37wasqiywlPZOh8uBTGCyFYjwag7Y5BNjDo26NgOW7YGQf07VEYL4fhWWWBtjMK65HcHepQF9ilW0iYK0DIJ4BQe6ysF+C8vxQsKoNFOWSDAIyzpFtkZFEwQPLWdqQZ89+/JuPz8cp2YXcAKz63Oe2wOGMMXOZY8ek7cPXN0ynz2zf2XoAUiUGjT58QJX4NNal3Kxc0qHhXxeP3n/yfrEEAAcAYgrONCM7u34Nv3+NVEg/lwAXAfCaAmE1EzKHJvR1RVJIexYUa9bDvz/3vE++o8+ly8w05VO1akIFYmdJ+rhXAKccQSYPGh0jeWo9cgetaV8a97kwQcOq3e1E5fwrM5baMw+JMYDCWWlC9eGrKc9FAGCef2pP2dVzmAGM48vNdOduqtRiw/FMbx0UyIs45vG29FAgMkXutBT23qZj/lgHz6SDqf9yJ0p0eZT49w6GcKUPssqH/ozIwy4CYTVTK/GZ6HXJPPQwWLRHhviX/ESxZxzK2hQOACPgWqp8mI5MTBQMkfxx446+fht/p7Uugo0yexoODk0/vwZXXT8KQbZHhAIYMQ/gnf7MHR36xC7FwVFmI1zcPLkVjuHngEnRWA0Rd5sGtBQ/fgod//SfQmQ3jIhkRYyzxHskQMAb3bTbErELWO2wGgMWSvwZSAwLOgJhDRM9me/ITAkP7I2WQDQI463/d4D/VkgwM3ZttaPlyFVwbbJANmTv3wTiA4DQdYo7U4IT3JVVy3u2AbKSPepIdTROQIfF3uPGHz/0Y026bj8YNc6E16uC61oULLx9NZBBUu8894Mw8tHvq6Xdx/sXDmLZxPuY/tAbW6hIIooCaZdNRv7oJKz9/J3b/4++VsroDLHzkViz92O1Dfn9q5LMrQC17fRksNQ742lwFPe9k4lllQclOT9ZeefC/Wny4PX5HL+sZvEvNcK2zQDalLpSNVmnR8sVKWI8GYD4VgBDmiFRq4FtgQuXve/OaGhBCHKWvexCt0CLYZED7h8tR/YRTSa6kYhuj6VIYLV+uguMdLyzHAhD6Buwi1Vr0brAmTaUQkgkFA2TIpHAMl3Ycx6Udx9M+33W2Bd62Xliq7Cm5AgBluD/g9KDj5PWs14kGw5i5dTHMFUo994HZBXUmHTZ++2G8/Ce/QO+VDmVb4/2rseTR2/J6L/l27CM57WAqtVIwMAyeVRaYzgWhb40mb6VD7oRBnAGexUYEZhkQnGXMushONotwr7PCva5/asJwJZT37oF4IFL6uhs3Z+oRqdOh5StVsBwPwHQ+BMP1SNYpByYB5vMhdN9Tgp4tdmjcEmQdg2TXADKH8XwQ1uMBiB4Jkk2Ed4kJwZkGWkBIktDYERk5HNjft9I9PpWQeKpvweD+H76ac1y1dvkMlM+qhSCm3qExQQBjypQAANzytXuw4rN3qG+izBHo9uZ9hz+SgUOwx5fX8SQZ1zK0P1oO960WSPr+fyc1/2KMA9bjQVQ/04v6H3ZA0xNLf1xIhu2AD1W/dqLqCSccuzwQ3bGk6Yd8MAC6rhh0HcoJZJMIzy1WuG6z5l7gCMB0StlVw3UCohVaSHYNWFRG9RNOVD/dowQVrVGYzodQ/ZseVD/ZDRalKSnSj4IBMqJaD13GG//3aXhbk0vFett7sfPbz6Bl38Wc52hcPydrYR5BI6Jx3RzUrZ6Jpq1LwJj67H5MYDj8k9cR7PGlBCyFEvYEVK0FkCU5MZpChodrBfRussO7xKR6/j0uPpqg6ZFQ+7NOsFDyz57uZgRTvt+O0u1uGC+FYboShuMdL6b8Vwc0vbG81wwMJPiTr6W6tkCagLNsuxuGa5G+55H0p+FqGKXb80vJTCY2miYgI6718BU8/+kfoWxWLUxlFgR7fHCeb1X9eq1Bl3NIU9CImHPvcsiSlHYEIR3OOVoPXUbzm2cgx2Rs+Mv3qZ4ukGMSAj0+WCrtOY99+x+fx8ZvPwRAkzGJEpeVQkaHf/qGqrYTdbQ9sfxX9PWJFwyq/YUTNz9TCWgYhJCM6iedEMI8JUMg50DZDjdCDToYbkSGVBp5cMnhSI1O1fRGqEGf9Jjgl2A5Hshc3ZED1uMB9G6yDbsyIpkYaGSAjJruC624sfdCXoEAALhburN+oHPO4Xd6UD67TnUgAChD/fGSyLPfuwJcktVlB+zb2rjnX/+Q9Y5flmR0nLyO9mNXcfB/dmRdUOlt7cVrf/EUOk+3qG4/yY3rhWEXEtB2xVDylrLI1XI8ACHE03ayrO9/sklQth7m004GhGu1iFb0JwHQtUdR8fuenAmKOANcG5KrWBquRXJmSGQyYLgRyaOVZCKjkQFS9C5tP4ZFj6zLfAAH9FZjxgRF2Yg6DWz1pahe1JjzWGUbpfLf7n9+Hh0nr+PEr9/Bko9uSDlW7rvTv/LGSdz/08/DVl+WWDsgxyS07LuIy2+cgMagg6/dha6zN/NuO8nNP88Iy6nMWSrVZPBjAGyH/HBtsMF4MZT9WBkwNIfR8pUqTPnPdrBo7jbyvsxE3Xf2jzLp2iKo+YUTTMocUsSfcb7HAa5PDoLTTRukRcsGSB8KBkjR83d5cOgnr2Pl57ZAluWk6oPx4jyZ6iRkw2UZ3Rfb4chRwCiu90oHru85j4vbjyUW+Z14cjfkaAwLH1kHrVGXODbQ6cGJp97Bqi9shdDXtkQhJI2IKWtnI+j2Y/9/bc+73US9wCwDwpUa6JyxlDvlgXkBcgUEQphD64yCyTx38CArCwCj5Vro2qI5j5f1DNFyDSwnAgADwvU6lPWVLs40zM8BRMpFdN/tQHiqIeX5cG3u6QUOIFJL6QiL2U7nnIKc509UHEPBABkXzv7+APydbiz60DqUzqgGAIS9QYR9IVgqbXlND8QxQcD5Fw8lVSnM5sSv38H1PedTHj/1zF6c+8Mh1K6YAZ3FAG9rLzpOXsNtf/E+CBoh7ToBJjDMvmc5zjy7nxYMjiSBof0j5ah6uhuGm1Hwvn8KJgOykcGz3IySd9Tv3gjX6ZQh+EydNAPCdUoH611mRtlLrtxNDHMYWqLQt0ZhOxKAf6Y+5/A9A9C7JX0gACjpkwNNepguhdO2lTMg0GRAzEFdwFgqVGdfCPSTQMaN63vO4/qe8zCUmCHqNIgGwvjAM9/IOs+fbUHg6Wf3of34NWj0WkSDkaQ7+8GkSAxtR69mfD4WiuL6O+cSX2uMOky5dXbSKMZgsiRj2qYFOPHk7ozHjEcjWbFwKGSLiLZPVkB/IwLTxRCYBIRrtPDPNQKCMm9uvJa985UMDJEKLeTlAuzv+jLedTOu5DkAAN8iE6yH/dB1RFM65PiXDANW+veNXJguhXO+Jw5A05t9H6Pz3hLUPtYFTa+USF7E+y4aKxHhvNeR8zqZ6K+FYd/vg/GK0tZQgw7u1RaEZqQPToiimDr/wSgYIONOqFfJ3W8steRc8Jfuec45gr1+HP6ZsnI/Fo7i9LP7sPgj69MfL3Ocff4AooHcH9JxOrM+ayAQP6/BQTnjRwVjCDfoER606h4A2j9Shvr/6oDGI6ft4Dn6OngNQ8yhgfO9DpS/4AIX+jvweCll9yozArOVDjGe76D0FRcsp4P9x8ablKmpat4OkDPFsGwRcfPTlbAe8cN6NACNT0LMIsK71ATvcvOQSxdbD/pQ/oo76f0bL4dhuhRGz0Yb3OtV1IeYJIq58x+MggEyboU9AUSDYWiNqR/w2TDGYOorkNR+7CoA4MSvd8NgM2LOfSuTchoIGhGXXj2Go4+9mV/bvEFI0RjELFMQTGAIdOWuskdGmCig7ZOVqHmsCxqX8m8fz0bIOBCYY4BrQ38H51tsRrRMC9s+H0yXQoCsTA14VluUQGBAQCkbBHTf7UC0VAPbET9Eb/qAI51sc/6yhiEwK/ddODcI8Ky1wrO2MB20tiOKsleU/AQD12DERzdKd3kQatAh3Jjf7+REMZ46/8EoGCDjlhyTcXH7ccx574qM+/czvlaSUdZUkwgGwIED/7MD5148hBmbF8FUZkWw14fLb5yE+5oz77ZJ4Riad53G9E0LktInJ2HA5TdOZT1P6Ywq1CybDiYwOM/dRPvxa3m3heQm2UTc/HwlLCeCsJwMQAjIiJZp4F1qQnBWcgcPKIv8uh4szXleISCh5jEntE5lSD+fXY7ZyhO71luHfGc/HLZDfmVDeoZdCFwAbAd96JokwUAxdv5n26uG9DoKBsi4dvKpd1C/eiYsVY68AgLGADmaOufqaenJexQgk+NP7kb96iZlyiBNQHDiyXcQzJB7wOAwY8NfPIDqRY2JXAaCKMB9w4k3//53cF/PP0Ah2XGdAO8KM7wr8i8jnEnZyy5ou2N5pzrgAHo221DythcswpWFjzIAUQkE3OssOc4wMgw3wlnzF0yG3AXFFgAMtfMfjIIBMq6FPUG88vXHsfRjt2PG5oWJksZyTAIThYxrCpggoOXg5RFtm7/DjVe+9hhWf2UbapdNTzwecvlx4tfv4Mb+i7A3lsPf4UYs1L8hXdCK2PJPH4K9vkz5ekCQY60twdZ//She/MJPqIZBkRM9EsxnQ3lnIuQMCE7Xw7PWCu9KM0znQtC4JUhmAYE5xjEtR8xVFDdSc8x4UywBQKE6/nQoGCDjXtgdwL7vv4xDP3kdlko7YqEIptwyCys/f2fa42VJRsuBS/De7BnxtnnbevH6XzwFS5UdtinliAUjMJZZsOhD67Dqi1sBKAsYL79+EsceexNhbxCN6+agZGpl2vMJogidxYDZ9y7HscffGvH2k6HTt+WfkpgDkKwinPeWKF9rBfgXFs8i00CTIe3uiDjOoGotw3gyloHASHb+g1EwQCaMWDAC17UuAMDZ5w/CXGnHvPetTowScEmGoBHRdbYFe/71D6PaNl+HG74ON2bfuwKrv7Q1qSiSRq9F07YlqFnciJe/9him3T4fsiRnnPYQRAHT71hIwUCR43lWwuRQUhJ3fKgMsqk46wV4l5th3+sD0iREim9b9K4s3DTLWBrtIGA0O/50KBggE9ah/30dl3YcR9O2JbBUlyDsDaB512m0HW0ecvGa4TA4zFj5uc0AlGmKgQRRgKWmBAs/uBZ6mynn+gedeXIs0BrPwg06cBFgmQtuJnAoi+86Hy7eQABQFlp2PFKGqt90AzHen7+AARCAzgdLES0f31kNJ0oQEGvNb0SJggEyobmuduHgj14b62YAAGZsXpiyKn0gQRTQdNdS3Nh7AWVN1Rl3IXBZhq/dNUKtJIUiGwR4lplhO+RXNV3Q+VBpStXCYhSapseNr1bBejQAY3MY4ByhRj28y8yQrMXf/mxGMxAodBCQb+c/GAUDhIwSW12pUuc2C53ZgGu7z2HG5kWZD2IM5186UuDWkZHQu8UObW8MpkvhRN6CwdsFIxUadL6/BNHKzBkwi41sFuFeZ4V73cRIMDReg4DhBgADUTBAyCiJ+FWkmZVltB+7iouvHsPMOxen7IaQJRldZ1tw+bUTI9VMUkBcw9DxSBmMl8OwHPMruwIsIsK1WkQqlJLFsTL6GB5LoxUIFCoIKGQAMBD9FBIySq6+fRbzH1yT8XlZknDzwGXEwlHs/Y+X4LnRjXnvXwNjibIgKxqM4MLLR3Dsl29BjqqYiE4jNqNuSK/LxjvNmPj74LoEgXqqkQvGEJxpQHDmxFplP96NpyBgpAKAgSgYIHkZic5ksuiQgBunW1A3tzalbgGXlcHjo7svJL7Hx4/ewInjLXBUOyCIDK52N6SoBNSP7arjuIFBAKA+EIi1mqCpDQBQPijnVnckntvpnINN5efSvo5MLMWyd79QimX439QytDwUjPMck5h97qr6wpAuQIoDdeLFQaPX4LaPrUfjYiWzIOccokZEyB/G24+9jZYzN8e6iapkCwTUjgbEA4K4gUEBIcWo2Bb9Aeo6/1P/8vWcx9DIwDhFnXu/wR1TsXv+tX0oPXIGM2bWQaMR0d3tweWLLZAkGRhn72U40wLxD8JMowSEFNJY7eMv9BD/UO/8c6FgoEhNls5+vHXkhdLT7UFP9/iuWDiU0YB0Bk8bEDLejNSc/kh1/OlQMFBEJkoAMFk7+Ils8AjAQIVYJDgwICCk2IzGAj5gdDv/wSgYGGPjNQAY6w4/W+dERk8hdwsMnjYgJG60OuORNBodveXm0H8fKRgYZeOp8x+rDp86+uI3klsGJ8IHP5lcRvOOfjgdfjYUDIyCYg8ARrvTL6bOnvbBE0KAsR2iT2ekOv1MKBgYIcUcAIxG5z/SHT514hNXsX0oEzISRruzz4WCgQIp5s4fGPkAYCQ6f+rwJx8KBMh4VGwd+1BQMDAMkzkAKGTnPxqdPi1KGxmFnN+nQIAUykTonNWwNgcLdi4KBoagmIOAYg4ACtXpU8dePDS1gWEHBIODgMnyQU5IJoXs5NWiYEClyRgADKfzH48dP2W/y088QdBwAoKBgcBYBQEWixELFk1HTV0FOOe4fq0dZ041IxSMjEl7yPgzFp13oVEwkEOxBgEjEQCMdedfyI6fOvaRN7e6IykgANRPG+QaDRitD9fGJY24/RMbwAQGQRDAOUdDQxXWrJ6PHf/zOjou0c8RmRwoGEijWAMAoLBBwFgO+w+n46eOvnjE/y3yGSXIFgiM5h2Wo8aBjZ+8DYwxMIEBABhjAANEnYg7v7gZv/2b3yHkDY1amwgZKxQMDFCsQUCxBABD7fyLseOnMrnDN7AErdpRgmzTAqM91Dr/9rkAkAgEBhIEAdACs9fOwvFXTxT82lqDFjNXz0Dj4kZodCK6r3fj7O7zcLW5Cn4tMrI0l8dHpdFcVAcDxdpRjlfjZavfWNz9j+SdPwUBhbOp/JzqmvT5TAuM1ofrlLm1EMTMvyeMMUyZWYnTPyxsexyNFdjyfx+CwaYES0xgKJ9Shrm3zcXhn76B08/uK+j1CFGDRgYKbLxn8xvu3H8xjgLEUSBQnMZq8VW2QABQggFBU9jfL0ErYvN3H4HeakgakRA0IgBg+afvgOu6EzcPXCrodQnJZUIEA2NdNGekFXM2v0Is+qMggIyFzrMtqF85M9ERDyZLMrrOtBT0mo3r58JUZs34vCzJWPDQLRQMkFGnOhiY6B3uaBuL/PyTccU/BQIkk3MvHELDLbMzPs8Yw/k/HinoNWuXToMckzIGIIIooGphAwSNADlG+RbI6JkQIwNjrVgK74xUJr9C7/WnIIAUg/ZjV3H8yd1Y/OH1SR20HJPARAH7/usVeFq6C3pNJjKApS5YTD1OwNR1czDr7mWwVjsQ9gRx+fUTuLTjBKKBcEHbRAiQRzBQLB3eZDZaufpHKtHPaG0J3FR+DuAcxsthmM8EIYRlREs18C41I1ZK8S/pd/xXb6PrTAvm3r8SlQsawGWO1iNXcPa5/eg6W/iFjF1nWzFt44KMz3NZhuu6Exv/5mHULpsGWZIhiAJM5Tas+OwWzH1gFbb/6S8RcHoL3jYyudEn4xgotgI8I53lb1SDAABCUEbVU04YWqLgAgAZAAPse3xw3W6Fa4NtVNpDxofWw1fQevjKqFzryhsnseyTG6HRa8CE1BssJggIOL2oXTYNQP8ix/hiQ1OZFbf95fvwytcfH5X2kslj0gcDxdYxj4SxyOU/2omBBk4LVD7bA/3NKACAxf95ufJHyZtexOwa+BYXrsAOIWpFA2G8+XfPYtPfPgwm8P6pib4RgMuvn0DDrXPSBgqAsuugYm49SmdWo+dS+2g2nUxwqoOBydBpjifFUKynGDIBDl4boGuLwNiceU6VA7Dv9sK3yKhq7jYvnIPFAC4CSJPIhox/epsRGoMWwV4/5Kg0pHO0HW3GH77wE8y9byUa182BoNOg90oHzr1wEIEeH2ZsXpT19ZxzVC1soGCAFNSkHxkYTcXQgQ9FMXT6AADOUdblhTEYwYK6NkSqNACSO13TxRA4AxhPfwoGQNcTg8YlIVZSmB9/FpVh2+eH7ZAPGq8MLgD+2Qa4b7UiUqsryDXI2KpdPh0LP7QOVfOnAAAi/jAuvnIUJ379zpAW9Hlv9uDAD1/FgR++mvR4+ZzanK9ljMFWV5r3NQnJRvWn4XjtyIg6RdPhp7Gp/ByMF0Mo3eGGrjuWeDxcqUHPNgdCU/WJx1gMSo+fIRjoPy7HASqxiIzqXzqhb4smrslkwHwuBPP5EDo+UIZgk6Eg1yoIzpV20siFKlqTHrd8/R40rkvOtKgz6zH3gVWoXTEd27/xy7QBgb2xHPPfvwbWmhIEe30498JBdJ7Onreg90onuCxnnCaIs1Q78n4vAKC3mzBzyyKUz60DlznaDl9B867TiIWjQzofmThoZGCCKeZOXY10WwJN54OofLon5XFdVwzVTzjR/uFyhKYpAUG4Wtu/TiADWcsQc6Tf550vx24v9G3RlJEIxpV+t/K5Hlz/RjW4dmx342idUdjf9cF8KgghxhGzifCsNMOz0gyuo51C6ejtJtz1vY/BWlsCoK+I0QCCKMA+pRwLP7gWR36+q/8JBmz48wcwdcO8pOOnbpiHrnM3seObT0CKxJCOFIlBjskQc/yb2OvL8n4/9WuasOHPH4CoFQEwcHA0rpuDpR+/Ha//5VPouTy+PzvI8FAwMILGe8c80lTlApA5yl52ARg8IdDf4Za94sLNL1QCjCEw24CYWYAYkNNOFXAGeJeZCtM5SxzWw/6sUxIIc5hPB+FbYh7+9YZIfz2M6iecYHL/gkrRI6FkpwfmM0G0PVoOrqeAYLDVX9wKS40jJQgYSBAFzLp7GY4+9ia4rPwgrPritpRAIK58di02/d0H8Nr/92TGcwZ6vLBUZb+uscySV2Iie2M5bv+r94MJQn+Fxr7fKJ3ViM3/+CH8/hM/RNRPOQwmK9XBAHVsZDiGmgTIcDUMjTfzBx4DoHPGoGuLKvPzIkPXg6WoetIJDOj8eN/BkSotem8vzNZCjVeCGMox3SAAuo4xHIKVOCp/2wMmJa+jYADAAV17FCVvetCz1TFGDSxOhhIzGtbNUaoX5qCzGGBwmBHs8UHQCJh199KMxzLGUL24EeYKG/xdHjCBJYKIuK6zN2GtLsl6TVGrQeWCBrQfu6rq/cy9b5Vy/XQVGkUBeosRMzYvxLkXDqk6H5l4aGSA5GW0M/tpPOpWbGs8EiJ9a69CjXq0froS9ne9sJwOgkmAZBXgWWGBZ3XhhsVlrYp5dw6IPhksKo/JVIHpQggaf5ZgigPWowH0brKDq3k/k0Tp9KqchYwGigYjAIBpGxeoKoC0+buPwFJdAlErwtvWi/MvHsa5Fw9BjkroOt2C6VkSE8VpTfqcx8Q1rJ2VMQWy0iigfs0sCgYmMdXBAKV3JWNBMqn7QB58XLRSC+f9pXDex5WkQ2LhOzrZLCJco4WuPXXNQBzjgOV0EKaLIXhWmpVRiRFoSyb6NiXxUrZ1FEKEQ+OKIVqhHbV2FTtZUjf8Lssy2o9dRawvGDCVZy5CNJCtrixxl26pcmD5pzehfk0TXv/Lp9B9Wd2WwXxSJQva7GtkGGPQ6OjecDKjiUJS1ILTDZAMLOPmAA4gZhMRnpJhCx9jI9r5utdYMgYCAwkRDvseHyp+36MsdBglXIOcOysAgI9igDIWHNMqsfpL23DXf3wcW/75w5hz34qsd9bOszcTd/uZcM7BGIMcleBorAAA9FxRN506cLieCQxMEFA5fwoWPHQLnGdvwnXdmTEgkSUZXWdb4L7uVHUtAOi+2J41wJElGc7zrarPRyYeCgZIcZA49DfCMDSHIfqkvtoCIdj3+hCcpk9ZPAgofRwD0H2nvfAJhNSQOGwHfGr6WgBKWy1nQrAe8o9kq5IEmgxZgxUOIFoqIlZSmN0VxWjBw7fgvf/zGTTdtQQVc+pQvbARKz93J+7/+RfgmFqR9jWxcBRnnz+YMp8/EGMMjDHULp+O9/zgU6hf04SbBy4hFoqADyHgE0QBs+9dASYwvPu9FyFLUkoHLksypHAUe7//Sl7nPvfCwazTF0xguPDy0bzbTCYOCgbI2OIctne9aPheO2p/4UTNr5yY8r12NP5TG6qf7EbJWx6Yz4WUQ/v6+/jHrGwS0PlACQLzxqa8tuVUEIab0bSBSiYcQPkrbtT8oguCb2gZ7PIRqdEhOFWX+N4NxgC41lnHJpgaBfVrmrDsk5sAIDFnrtyJM+itRmz+ziMZh9CP/+otXH3rNAClgFAmgkYEEwRs+PMHoLeZcOBHr4ExNqSAwFhiht5ugvNcK1752uO4eeBSIiCRJRnX3z2Pl//kF3A1d+Z13ht7L+D8Hw8nzhMX//uBH+4oeIVGMr7QJBEZU6U73LDvT75TZgAQVT4AB891R0pFeFZbELOJCM40jPj8u+iVoG+NgDOG8BQdZGN//Gw56s+a7TCdeGv1LRHUPOHEzc9Ujvh76HywFFW/7oahNblwE+NA7wbrhK7TMP/BNYm8/4MJogBTmRWN6+eieeeplOe5zLH7n19Ay8HLWP/N+7JehwkMolbEzC2LcPrZfRBEhhWf3QKNvn8dRjw4yLZlEEAizXHvlQ7s+tvf9u1WMCHY6x/W1r/9/70dHaeuY+79q1A+q0ZJOnS0Gad/t1/1rgQycVEwQMaMtiuaEgjEpfu4ZBzQ9UiI2UUEZ43saIAQlFH2sgvmM8FEZ89FwLvUhJ4tDnAtg8Yt5RUIDMQ4oOuMwXwuCP/8ke2MZZOItk9VwHipr6RzqK+k8zIzYmUT9yNA0AioWtCQ9Rg5JqFm6dS0wUBc1aLGjAFFMobyuXUAgAsvHYXObMCyT24Cl7kyGpErCJBkdF9oRcQXSno84gulPDaYzmKAsdSCsDuAkDtzttirb57B1TfP5HgfZDKauJ8EpOhZjgVyrnQfjEMZnh/JYIBFZVT/sgu6zljy3nwJsB4OQNstof3DZZAsghIQDPE6nAHmUyMfDAAAGEOwyTCiqZEFWcZ0ZydM0Qi6TRZc4yNQDCofaq7NWMZOXtAIWP2lbZi5dbGqy3HOwfuG3etWz0xMT6Tb25/2eqKAk795N/G1wWGG1qRDsNuXMV2wrb4USz++EQ1rZyVSGLceuYKjj72F7gu0IJCoR8EAGTMat6RqpftADIDgH7m5diEgoeL3vdB1xDKOThibwzBdDMG3xAz9TdeQr8U4IIQmRjXQWWdu4gPvvgNLpH8Yu9VYgmemr8NVa9WYtEmOSuht7oSjsTxjrn8mMPg6PbA3VkBr0sHX5kLIpYxWrfnKXZixZVHOO/qB52o90ozpdyzArX/63pzHK2sBuLK5hAGHfvQaWvZfxMyti7HkoxtgKleSY0lRCZdfO45jv3w70TZAySp41/c+Do1Bk/T+qhdPxbb/14DX/+IpdJy8rqrthFAwQMaMbBJUFRUabKRy6YseCTW/6Mp5t88ZYDkaQNf7S2A74IPWGUuZLojvdIj/mfY8AhAdzWF6zmG8HIb1kB/69ghkrQD/PCO8K8yQrEPfTTDvxA3c8s6FlMergy586cxL+P78e9GNsQkIzv7+ANZ+4z1pn4tvDVz0wVux6IO3Ko/JMq6/ewHnXjiAmVuXqL4OlzlCngDkmIR1f3afqsWDckxCy8FLcDV34eL2owh0e7Hp7z+A+pUzk14vakU03bUUtStm4OU/+QVCvUpAsPpL26AxaCCIyf92gihAZsDaP70Xv//EDzL+fmlNeky7fT5s9aWIBiO4tvssXFe7VL9nMrFQMEDGjG+hEbYhbLPzzxqZoe7yP/SoGvZnHNC4Y+BaAW0fK0fFCy4YL4YSr+MAArMMiDlE2A5kfn9MBrzL8qtZwCIyLCeD0LdEAAYEp+vhn2vMvQiRKzUebIcDAxY9ytC+44X9gA9tHylHpC7/csvaSAwr911K+5zQd9f73mv78Qt77jvlkXBpx3FUzKtH07YlSfP+8UBgMCYImHLLLNQun65qnUC8046Fo3jj/z6NLd/5YMZzDyZoRTTeOgdVCxogaASAc9StmKG0Y9DrGWMwV9iw9NHbsPc/X4a1tgTVixozn1sQYK12oHpRI9qPX0t5fvodC7Dmq3dD1Gkgx2QwBiz+8Hpcf/c83vnnF6iK4SREwQAZM+F6HfyzDDBdDKleiMcFwHrcj/JX3eCC0ul61lgQqc6/IxtI0xOF6Ur2JDOJNqA/SY9sEtHxSBk0PTEYbihD5KEGPWIlGiAiQ38zAn1rcobC+GiBe7VZqaegkqE5jKpnusHCXDkBA6zHAojZ3Gj/cHnWDIKWYwHYDisLy5LWQXAAEY7qp7px42vV4Jr85vinXumEmKVYjgiOJm877GYf3BpLXuculL3/8RJaDl7CggfXoHRGNQStmLP4ENOr+2iMbyEUtSIcDeXQ29Sv/4i3wWA3Yf5Dtyg7PLK0izGGmVsX49BP34CtrjTn+TnnsNaVpgQDtcun49b/816AK+cUB2ytrF/dhFu/+V689fe/U/0+yMRAeQbI2GEMXe8vhW+REZz1dbJZDudQ7qYNN6IQIhxiiMNyKojan3TBdCao6pL6G2GUP9+D2h93ovqxLlgP+sDCMmz71I9QMAD69ii0AwoQxUo18C02w7fYDK5lKH3VhcbvtcNwMwpwJYiJk2winNvs8C4zQdsRBYvmXjeg6Y6h6iknWIQrcQAfUIHQK6P6l06wcIbzcA773szJkRgHxIAMs8rv4UAmv7LtMhebNHqJlgZrunspVn52Myrm1kPUaVTdtTNBUL34kTElb0HjutlZkxRlI4iCqqJITBCw8INrEVGxxZAxhmgg9bjFH1mf2OGQrh2Nt86BvbFcXcPJhEEjA2RMcS2D875S9G6UYLwUAgvJsJ4KQt8eTQxnx/+Mf3Ql3dnKSpBQ+VwPbkypzjz3zXkip0F8BwMHYLgegWO3B5ln9jNzvOtF1wPJd2iiO4ban3RCDPD+9gLgMiCLgPMuGwSZwb7Hh/LtykJIWcvgXWZC7+02cL0ATU8MtoM+GJuVD/LgND2EgKyUIE7T1zAOiH4ZlhMBeFem3n2zMIfOGcv6XrgAGK6F4VuU386GgEkHpmJ+3CuOTS6DZZ/ahAUP3TKkTjp+168meOBcKQWsdufAcMy4YxGOPf4WAt1eGEstGdsXC0dx88DlpMcMJWZUzK3Pen5ZktG4bi5OXNtdsDaT4kfBACkKkk2Er2/+3HuLBcYrYZhPBiD6ZcQcGuhbwilb/eIYlA9j61E/XOutYDEOLiTXJLAcCyRyGsTvqOPPin6uqkNLuqYMmM8E0XU/T9xBCj4JdT/uTFvWmEHZmljxR0/KmkkhymE74IfhegTu1WZU/MGlDOH2HaTtiilf52iT+WwwbTCgNs7JlKUwm2vTK7D27fPQZMqjD4ar1kq4NOoK+BTS7HuXY8FDtwBQv71vMMYYuCxn3I2QwDm8bS6UzqiG1ji8KatcjKUWmMptOPart7H2a/dkaA7H6Wf3pYwMaA2528ZlPuLvgRQfCgZI8WEMwRkGBGf0LxSc+p2b2dcVcGXPvuVEANoe5Y47OFUP160WhKbrYd/jy7iyf8iJgyTA8aYH3mXKavyaXzohpAkEkl4z6M+BbdC1RVHxgiul42c894YLBoBF0x/F9QLClRolmMr0elkp/ZyviF6LI6umY9Xe1EWEMpQA4w8NqwB33qcelqa7lmLVF7eqvrNPh3OOjpPXYbCbEoWIMhE0Iq6/cw49l9qw6gtbh3S9PBuHS9uPQWvSYdknNkIQRciS3JfcCDj9u/04/sTbAABbfRmqFjYADHCeb0UsFIXGkHl9iaAR4KbUxJMOBQNkXOAq7oy1g4bCDdfCqLkaRs8dNuh6cgyT9/2pttuIH+/Y7YNjtw++hcacQ/FqT5w2YEHubYrZFlF61lpR8Xxv+tcyQDILyq6EITi5pAGSKGDJ/mYYo/3rKLr1Njzdl2fANIrBgNakx+ovbwOQO/VvNowxVM6fAvd1J04+/S4WPHxL2vPJMQnulm7cPKjUEShrqsH0OxYmHat+uiH7cZxzBJxe+Ls8AICzzx3AlddOYurt82AutyHo9uPqW2cR7PbCYDdh3TfvQ+3y6UmpkP1dHghaMe1OCS5zxMJRXH3zdM62komFggFS9AyXQxBU5OZJd7cNACU7PXm/Nt/jrSeDWTvroZwzn+eZDHiXZ96m6FtohK49Cvs+X9KaCTBA1jN0fKgMyHMnQf/FGc4smoIXypaiqbMdpkgY3WYLLoUbxyQD4dwHVqpIHayOIApwNFbAMbUipaOOf+1p7cXrf/EUuMxhKDFj+h0LU86Tb1CSLSg494eDSV+HvUGcf/Fw0mOiXoM7/+UjiV0HA89lLLWAyxwykrdOypIMxhj2/sdLiIVoa+FkQ8EAKXr2vb6sBYHUjPLLOoBFhtdZZzPcQCCf62DAteLfl56NNkSqMw/9gjH03GlHYLYB1kN+6Nqj4FqmJB1aaoJsHn4J45go4mxNXf8DrWOTirhi3pTCnrDvbQxe7c8YgyxJcJ69iWCPDwCw6e8+kLPjz9bRJwUbMk9sN5RjEgSNCCkcw/JP3YGlH9+Imwcv4eTT78JYYoGttgSRQBg33r2AkMuP6RsXwN5QnvY6giiAC8oUSPmsGmj61hF0nr6BE79+h4oWTVIUDJDixjmMzeGc8/pZ75q5Ms0wkgrR7eWaquAMCE3RQfTL0HUrUxLhWi3ct1oRmNM3xC9xGK5HIIRkxEo0KQFCqFE/pLUB44kUKcB0zQDZcxKImLZpPg7+eAcAhrIZuTMt5pPemHOOaCiiLOoTBYh9+Q8EUUD96ibUr27qC0qU9QKrv7QN5144iPLZtX1zaxmuxQGNXounH/53GEvMiAYjCHvy31pKJg4KBkjxK0BHzqJAtEyErlsatbv4ocrYPg503+VAtEoLFpEBxsC1/UdaD/tRsssDMdA/pxKu1sJ5j2NI2QXHqwsvH0HDLbOyHjOchYWDiVoNzFV21C6bnnvXgUrxtjHGoNFp0yYkim99BJAY7mciw9z7VyEaCGdtCxMYDCVmSJEYfB2jvLqTFCVKOkSKG2OI1GqzbntT85HOAGg8MjrvL0nqQEfCcGKXcI1yJz8wSREXlHM671UCAUCpzzDwfdj2elH+kispEAAAXUcUNY93QdemLrviRNB68DIC3V5V9QEKZct3P4QVn9k8IufOVv44fUplBq1ZDznDdk9AWR/ga3cVqolkAqBggBQ99xrLsNYLxAlRDi4qaYCHsqdeDc9yE2IlQ5t/ZwC0PTF0vr8EvkUmRO0ionYRvkUmtH62Ar6l6RcICiEZpRkWSTKubIEseSP3IsqJ5KUv/wwRrzLszTlP/BdXqFGB+PkN9rFJqpQJ5zzrIkpBFHDxlaOj2CJS7GiagBQ9/3wjPNfDsB0KJC0k5AKUzex5qPpdLyRTX7EapI4qDHcKITDbiO677Kj/YSc0PbmLHg0mhDnKX3HjxleqwPXqYnXzmSCQpaoz44DpShiiVxpWdcLxJNjrx9Mf+HfMfs9yzLpnGXQmPXRWI0S9RlXaX7USW/YKeM5C4DKHt9MFc6Ut5f1yzuFp6cH1vamVJsnkVVw/wYSkwxi673Kg4wOlCE3VQTIwxMwCvEtN6F2ff/EbMSBnHGlgAOQhRgOSgSE0VQ/jlQi0QwgE4tcXAkpq4VxErwTrIR9MpwOqIhjRlyVimIg4cP7Fw3jx8z/B7x79b2gKHAgAfXUJxmD7ZC6CKOD0b/fiwstHwOVBETMH7FPKsO3fHoXOMjIVQMn4QyMDZHxgDIHZRgRmD0qME+Mo2eNLpBjO65SZHudDGyFwbbCBaxiMV8KJvfxDZT4ZgLYnBtEnQ7II8C02JZIKCT4JVc90Q9/SvxdcVVs5sq8wn+CU4jxZni/gosKxxDmHFImhedcpLJt+R0rCrnhq5pJplbjl6/dQhUICgIIBMt5pGHq22FD2auHmxNV0B/FgIT7AEC0VAVmGEJSBIVauG3h9Y0sUhgGdvX2/H7IGiNpF6HokVbUKBre17qddiNlEuNdY4FllBkahqE4xaT3SjNrl0yCImadKBtchKPYAISURUl81woP/swNMEDDzzkUZ1w4IooCGtbNhrrLDTzsKJj2aJiCjR8q84V/rjMKxy4Oyl12wv+OF6FU/pO1ZbYXzbjukvtC2EGvIZTF74R426O/aHgmlr3vR8K9tsB30Zx0VUNs+NuA/ABBigK5bSqrgmC/RI6F0hxsVz/WMfPKFInP62X0ZAwFZkhH2BtF6pDl5FwLHqO5KUINznqjCGA2Ekyoyelt78NZ3foeL24+hfE4dRG32+z3GGKoWNYxoe8n4QCMDZGTJHNbDftgO+KHrjoEzINBkgHutBeEGPSBxlP/RBetxZXFg/Ha7ZJcHrtuscK23qhrW9i8wgQMoe8UNoQCf3YIExKwCNN7sY/2DCw9xDFjgiKF32rmuN9TXxP9uOROCf14IgXlDq0cwHnWcuIZ9338Fq7+8LbHaPp7lL+IN4rW/eAq9VzpgKrfCWluCufevwpRbZhXVyIAck9B5pgUt+y6i82wLnGdvwlhqgaXagag/DNe1rsSxapu98rNbEHT60Ha0edjtq1s1E3PeuwJlTdWQohJu7DmPs384BO/NnmGfm4wsCgbIyJE5Kp/pgelCKPEQ44DpYgimCyF0PVACfUsEluOBxHMDb5tL3vRCMonwrsicc1/XHoHjTS9MF0IppYGHK1KugeiN5NUBD+54BwYEvNANzCJUrYG+I33J53hbbAd9kyoYAJSERG1HmzHrnmUom1UDKRJDy/5LuPLGyUS534DTi2gwgroVM4oqEAAAJgpoO9KMM8/tTzwW7PEl0iEP5LzQlkhjnI3OrMcdf/8BvPrNJ9B1pmXIbVv5hTsx976VkCUpMQIz655laLprKXZ++xm0HRl+sEFGDgUDZMRYD/sTnfRA8QV6FS/0Zp375gAcb3vgXWZKO7+tvx5G9RNOMClzaeCh4AAkiwDJJAz7fANHDGQdg2e5CY69/hENCuKLF7OlcGYc0HUVNm3veOFt68Xhn76R9RhHYwVEXXF+PDbdtRRnfr8fMzYvwqy7l8FSbUfEG8Ll10/i/IuHEHIrwXXYHcCVnacw/Y6FWXMOMEEA5zKWfvx27PjmE0Nq09Tb52HufSsBIGkqRtCI4LKM2//6QfzuI/+FiC+U6RRkjNGaATJibPv9GZ9jQF/B+8yvZwA0Phn61jQV1DhHxQu9SiAwhI510CBEyoWDU/WwnCncBxeDkkPAvtc/pPbmg4sA5NzxhjzCmRjHKyYKmH3P8rxeMzip0VDlOgdjDJYqO97z35/C6i9vQ8m0SujMBliqHVj4yK24938+A2ttSeL4gz/agZ5L7TnbJ4gCqhc1wlRuHVK75z2wOmPGQyYI0Oi0mLE5tZojKR4UDJCRIXHoemIFuVNnkeQPGdErofz5Xmh7pWF3rHzQ3zmAUJ0WljPBgt+9M6Ag6xlyXicK6JzZ7/o5A/wLJtcUgVprv/EeTNs4X/Xx8RX9Ulj5nssxKfF4ProvtSMaDOe+nizDVlem5DgYMGImiAL0NiNu+6v3Jx6LBiLY/n9+iZb9F1W1QW9Tl0mRCQy1y6djzntXYPrmhShrqsk6+sDBUTG/wNUkSUEV5zgYGf8EZC07DEApvpLj85IDiJb3V97TtUdR/csuCKHhb98DgMB0PQwtEbAYR7RMA88qC7QdURhao+OzmBEGbHlkSNljDij/LlzH4MmyFmOyKp1ZjRl35HcHG19XIOo1uL73Argkw+Awo3x2DZggZO0kB7JU2eE824ra5dNzXTDjWgZBI6J0ehUq5tah6+xNAIAclXBj30XUr27KeloucwS7vTnbWbt8Om75+j0wl9sSWxlzBj4c4FlqJZCxR8EAGRmMITBTD9OlzOWHGQdiJgFiMH1GQM6ASIUGhhthBKcbIOsZqn7TDSHMC7M2QAAitVp0fKQ86fH6/25XnTBotCsgxgMsSQ9ostxEMgDg/Tsi4oWPmAxIJgEdHyyDZKdf/8Gm37FQ1aK7dBhjmLKmKdFR+50e6MwGMIM28Xw2eqsRNcumqbpONrIko2JufSIYAIBrb5/Fqi/cCY1em/E1Nw9cSqw3yKRyfj02/d3D/VUVhf7qitlyMjCBof3Y1aznJmOLPg3IiHGvtcB0MZy+BgADYg4RXfc6UP3rbmDQ3H98i56+M4bK3/WCi0Bgph4aT2FT6vJBCxNFdyyvHAcjHQjEvyUMSgAQqdHBu8wMyEDl8705X99zhw2yQYCxOQxwIDxFB/8cIyAW87jH2DGWmIeVoXFgZ2gqtYIJDGFvEHqruimZXB19/E48+zmQMn8fDYRx+KdvYPWXtqV02rIsQwpHceTnO3O2b+nHNwJgaWsxZGq7LMmI+EJo3nU65/nJ2KFggIwMicN2wJ8Ysh7YqQFKIND+kXLESjRo+2QlHG97YDofSuw0GIxJgOl8+sBiqJgMWI/6oXHF4FlpgWQTUfuzLrA06xXHysD3KoQBySzCP98IwzV1JYklqwahaXoEZ9H6ADWCPb6CJWOKd9pqAwF1J03Nkph6XQFtx/q38dUun445961Exbx6SNFYSiIiQRDg7fEh7M2+YNZYZkXVwtwJigYGG5xzxEIRvP6XTyEWLqJfLJKCFhCSEVH6mhvmc8qHy+BMehyAf5YBsRLlQylSrUXnw2Vo+UIlYobkYwfK9Phgaj7K48dovDIsJ4Ko+1kXqp5yQvTLY7pWIMcSC1hOB1H7v52IlIqI2YSMx3MoUwShRl3hGzmBXX7txJCmCEYLYyzryAXnHK1HrsB9zQkAWPKx27D5O4+gdtk06C2GjBkJrdUO3P5/35/2uTiDbQijG1wJikKuzDuLSHGgkQFScEJQhu1w5i10DIDtcACu222JMr0sLKP6yW6Iw9jNx6FsqxNUjPKny8qnbx/7ffdqAhFdZwzVT3Wje4sdVb/rTRktiX/dvdUxqeoPGOwmzHrPckzfOB86iwHulm407zoN93UnosEIeq90JKXuTae3uRMXtx/DzDsX5xyOHyu5phIErQa3fP0euK85seiRdcpjOQIcQSOicv4UlM2qQfeFtrTHBHp8qqYpktoqMIg6LWbfuxxHf/Gm6teR0UfBACk4w9UwWI4OWYhxGK6GEeyrQmg9FoDGnbvs7+DphoGUeXUGFijMAsNixTig74iBaxg6HixF2auupLTJklVA91ZHxuyC2q4oLMcDEH0SJIsI32ITohXpF5aNF/aGcmz9l49AZzUmVu/r7SZULegf1g44vTj5mz04/8fDicdM5VbM2LII1poSRHwhXH3rDPZ9/2XYG8pRMbeu6DIQ5sIYQ/XCBlTOretL+KO+85ZjMmpXzMgYDITdAdzYfwH1q5pU75AAlC2PU2+bT8FAkaNggBQci6mbcx0YMFhOZF/F3P8iJZOfEObxLxMZ9zzLjLAeCY5YIFDonQPDOR8HYD4XgvO+EgTmGGC4Gk6UOw5N1acfEZA5yl5xwXY4kDS94HjXh+AULTo+XA6uG4czhwzY+NcPQmc1JHVSgztyY5kFq7+8DcZSC4798i3Mf3ANln5yY39pZwDz3rcaLQcuwdfhQuW8etVNKLbqhvGRgPxGN3jOTv7Iz3ahetFUaAzavAICrWF8B5uTwTj8zSfFLlKt7hd/4HFCQOVcPQfaPlGO7nscCDXqEK7SwD/PiNaPlaNnq2NERwSGe26ePJU67POJgb5oSmAITTfAv8iE0HRDxqkBx1teWA/31YEY8B8AGG5EUf+DjpQET+NBzZJpsNWXZS1NDPQHBwsfuRVz37cKyz99B4S+PACCRkx0oLXLp8PRWJ7tVEkuvno84+K4QmUmHA2CRsw4KhDnaenGK994DB2nric9nu09ypKMnubOgrSRjBwaGSAFF63QItigg+FGJGP+gOA0PWKl/T9+sRIRGk/ujIKeNRZEK3WIVurgXT4oaQ7nkLUMQrTwH77D7bxjBobwVL2yC0AAYmYBuq7MhYRyYcheYjnl+IgM+15v1kRFoldG6WtudN9TkuGo4lQ5vz6v3ABc5lj0yLqMQ+iCKKB0ejVkWVay/OW445++aX7Gu+RiGi3IRpZkBLu9uHnwUs5j3deceO1bT8JS7YC1xgFThQ23fuPejMcLooDzLx7O+DwpDhQMTFIsJMPQEgFkjkiNDpK1sCuonfeVoObnXRADyQmFOFOKADnvdSQd711mhvFq9u1y3gVG9GyxZT6AMXhWmJT8/8No+8C2xsfTh3s+9202eFZbEl+LXglTvt8OLg3t3BxAuFb9TgHD1TCEHOsjGZS1Gz1b7ONquiDXosDBmMBybveTJRntx66qSgIkaMRRq0YJ9E9JyLIMIcsWQzXnAJT3GgtFsevvns3re+lrd8HX7gIA2KeUY8FDtyRte4yXh76y8xRu7D0/pHaS0UPBwGQjcZS+7ob1sD/ROXAG+OcY0H2PA7KpMEFBrESD1s9WwrbPB+sxP8Qgh2QU4F1qgvsWC2Rz8nX884wIHg0oiw8HfR5xAMHpejjvL8mZEMa9zgbz6ZAyyjCEdnMAoUYt3LfYYDnqg/l8eNiBQEwHeFYlj2JIVhEdD5ai6rc9SsrgvvccX/+QaySCAQg16lW3Qe1oCZMAbVcMkbrxsyWx7dhVLHn0tsKelHN0nL4Bv9ODpq1Lchxb2EtnIksymMAQ9Ydx7o+HUDlvCqx1pTCXqS8uFB/Oj2cM7HsU+3+4HT2X21G3cgYqF0wBONB+4hrajjaren9HfrYTrqtdmP/gGpRMqwQA+DpcOPPcAZz/46FRDZbI0FAwMJlwjsrf9sB0MZTU4TKuLEbTdTrR+umKxHa/4ZKsInq32NG7xd6XJD9L9yYwdDxShpKdHiVQ6eu8lLK/ZvRutKnaJicbBbR+pgJlr7phPh1MvE9JzxBziNB15h6a776nBOZTQVj6khwNm0b5fmo7orCcDED0y5CsAryLTWj5QhVsh3wwXQgBspIh0LPSDPseX9ryz0BfvYYyDcIN6jvsSGUeC7jGz6AAAKDrTAu6L7ahZFqlqqkCNUP3gkaE62oXLu84njMYYAJTOuos4ZuaBYbZVv5LMQnNu06j6/QNNO86jVg4CnOVHfd8/5OqFy8ODAQG/gnGcMuf3IOlj94GS5UjUWhp4QdvhfuGEzv/+hl423Jnu7zyxklceeMkdBaDknnRE8z5GlI8KBiYRAzNYZgvpN/Izzig7YnBetgPz9qhlTHNSs2HlYah5047em+3QtceBRgQqdKqH7KWOUSfDAhA1wMl6N5mh7ZL2YIXqdHCdCGEqmd6Ml8fQLRUBGSg5G2lYEshphs0ARkVv+2G5Vw4USMAHHC844N7tRk9d9rRs9WR9JruuzXQt3VC9A2aZhGU71PXA7lHSQaKVmgRrtJA35F9rkAyCfkFDkVi19/+Flv/5aOw1DgSiW6yUYbDedpMfrIkI+wOoGX/RXBJRuuRZlQvbky7LoDLHLFwFFpj5sBMjkmAkH3tAe+rKJUpu+ChH7+O8y8eSnps8UfWQ2fWq16XkLlugABRy2CuUKbgBgZU1poSbP3Xj+KFz/0YUX/uiooAEPEVrvQ3GT3j7B6ADIf1WCD7ojMOWI+o3OI3grhOQLhBj/AUvbpAQOKw7/Ziyr+3o+E/2tHwvXbU/agTxsthhBv1ypC3wBBq0OXM8KftlVD2kkv1iMDAVMvZmM8pH6RM7vuv70W2/X7Y9/hS35JNROtnKuFZZYas60vtKgK+hUbc/EwFIrU6sLAM60Efqp5youpJJxxveiBmqd3Q+WCpEkxkeS/uWyzjom4BE1hSpBZwevHiF36Cff/5MrovZV8RHxfyBFNy+MsxCVyS8fY/PZ+osnfof1+DFImlHBu/k9/3Xy+j53J74o568DEAEOrNnoGPMYZAtw/+Tk/S42FPAHu//3JKIKDRazHt9gUFy5aolENO/V0TNCKMpRbM3LKoINchxYtGBiYRjTv7an0GQJNHkZ6iIHFU/aYbxsvJc/varhgqf9+L3u4YXLcrdzy2/b6cd/qMQ9kFofLyatMjZ1vFb9/jhWeNBVyTfJRkEdGz1YGeLXYIEa4EBX13vLq2CKqfcEII9udbMF4Jw/GOF133lcC/MLUufaxMi9ZPVaD6CSfEYP8PQrx9viUmuNdaUl5XNBgwc8tizH1gJUqmVYHLMlqPNuP0b/eh/dhVxMJRXNx+DJd2HMf7Hv8yTGXWLCMEHDu+9QRmblmEpruWQmc2QJZkXN97ASef2oPeKx2JI11Xu/DKNx7Hys9vQc3iqYnHPTe7ceRnu3Bj3wW0HbmKTX/7MMpn1yoBBQcEjYBYKIK3/+l5LP/kJpiyzO1zziGFo3j+0/+DyvlTYKmyI+wJou3YVcjR1N9JvcMEUTtKaZMZMPX2+Tj7/MHRuR4ZExQMTCIxi5AogZsOByCZx9dgkfV4ICUQAPo735K3vfDPNSJaqYH1mLpRD7WBgPL9ApjMIATTZz1UsyVRDHPor4eVHAHpCAyyof8sLCQrgUAo+ZqMK0szKp7vRbRMg0ia3QaRGh2uf6MG5rNBWE4EIIRkRMs08C41IzxFN6yKfSOKAbf+6b2YfsfCRIIgJgioWTIVdctnYN9/vYILLx0BoNyNH39yN9Z+7Z60p+KyjEuvnYD7mhOHf7oTRx97E40b5mHaxvlwNJRjxWc34/JrJ3D17TOJjtjV3InXvvUkzFX2REftutqVOGfI5cfLf/ILVC1sQP3qJog6DXqvdKD5zdOIhaIoa6rBoillWRP1WGtLMG3jAjTvPIXOUzeyfjsi3lBe2QUHrxfIB2MMOnOGn00yYVAwMIn4FptgOZtlPo8pd4fFgkVkWI8FYDmmpM6N2UV4l5nhW2gC+u6irQdTh9gH4gJgPeKHb6kpKWVvobhvtSNcr0P1E04gyvt3BfQ9Hy0ToevOPdqiNmsjOEfJm56MwQdTDoFjtxedHyhLfw6Rwb/ABP+C4f1b73TOGdbr8zHttvmYsblvqHpAhxZPNLT6S9vQeuQKfG0uAMCl7cdgdJix+NENSRkGBY2Ia7vPYf9/b1e+1orY9LcPo3bZdMiSDEEUYKsvQ82SqZj3vlXY8a0nYW8ox9z7VqJywRRwSUbLwcs494f0d8kdJ6+j4+T1lMdbDlzC4g+vz7jYL766f+3X70HrwcsIe7MvvosGwrix7wLqV+dODRzxhXD93fOYeefirMdlIsckuK535T6QjGsUDEwiwZkGBBt1MFxPTQbEmbL637PCnP7Fo0z0Sah+3Altt7LgjQEQ/TL0N12wHvGj/SPl4HoB2u5Y9i14MqDrikL0Fy4QiH/rgjP18Kw0AyLDzc9VwrbfB8vJAIQIR7RUA88KM8JVWtQ95sx5TjW1AfTXw6h4oRfa3uzBBQNgOh+CEJQhG8fXSE8mc+5bkeis0+GcY9ZdS3Hk57sSj538zR5cfv0EZmxeBEu1A2FPAM27TqN3QDa85Z++A9V9Q//xc8f/dEytxLbvfQyOhvKkpEZNWxejaeti7P7n53Ft9zlV7V/66AZwzrPmBWCMQRAFTN+yEGefO5DznMef2I26FTPAGUsZIeCc49ruszj5m3fhvuGEHJXgvu7E8k/fkfRe1CRrEjQiLr58VMW7JOMZBQOTSd/2vbKXXLCcCiYFBKEGHbruLylYnoHhKn++F9reWMowOADoW6Moe9UN53tLwLUMyHJXzRkg6wTEbMN7XwOH+2M2Ee5bLfAuMycW28VKNOjZ5kDPNsegF3KEqzQZtzRyBoSm6hPlnDPRtUZQ8ysnkEdM49jlQc/djpzHjQcl06uy3gELooDSmTUpj8eLE6WjNekx666lGc8riAIcDUpa4oEdZrwA0Ppv3Q/n+R+mLPobzFxpQ+2KGeq2/8kcJVOVffpggLlc2VIb6PKkJASy1ZUmdiEA/dsXOeeQYzLKZ9WiYe0snHvRi7A7gNPP7kP3xTbMvX8Vqhc3gnOg7Vgzzr1wELPvWY7G9XMB1j+VEE8adPm1E2g9fCVn28n4RsHAJMN1ApwPlKJ3swRDcxhM5gjX6Yqqap3WGYXpSuZtTIwrhY16Ntvgn2+CNVu5ZK4kNIpWaBGu0ULXHk3fKSP33L5nqVEpC5xPdj7G0HV/KWof61KmEQZ05pwpW/mc73HkPE3JLg8wYBeCGtbj/gkTDMgxCdBn/hnlsgwpkr4+QCbls2sh6ob2EcgEBs4Zmu5ahmOPv5n1WPuU8rzm6qVwDLPuWYb5D66BtUZJDR3o8eHc8wdw+tl94DJH1aIGbPjzB5S2DM4bAEDUirBUO7DwkXVoumsptv+fX8LX5kL78WtoP34t5Zqdp24ogcL7VsNUqiwiDXR7cea5/Tj7fO5RCjL+UTAwSUlWEf5FxbM+YCD9jexpiQFl+F/fGoV7tQWW4wEgxtNOfcRKRPj7Svl2b7Wj5pdOpeMfuHcffXPtSB8QcABcx5S7fm3+w+7RKi1ufqYSjne8sJwMgEmArGXwLTHBdasVUo5RCyEgpV0kmQ0DgCgAmatK1lTsrr97HtM3ZtlKxxha9l3M76TD/LYIooDqRQ1pnzM4zJixeSFsU8qy5iBIOadGhLHcgtn3Lk8aCTCWmLH04xtRPrsWb33nOSz6kLL+IN2oBktaUyHAYDdhw58/gJe/+ouM1+Uyx+ln9+HMc/thrrIDHPB3uvNO9UzGLwoGSPHJ40M6VqZB+4fLUPV0D8SgnEjqw2QgUqFBxyNlicWG4QY92h4tR9krrqTkOzG7CNd6Kxy7vSnFkuL1CbreWwI+hEAgcY1SDZzvLYHzHoeyTVDPVHfSotqKjoMwACzKwfXjPxg4+9wBTN+4IO0KelmSEXL70bzrdF7n7LnYDikqDXmLHuc8bWc56+5lWPXFO5XRgzw60/j5Gm6ZDSA5cRJjSl6FhlvnYPodC1GzZKrq8woaEeWzalE2qyZnVUIu88QiTDK5UDBAik6oUZ9z2J6LQLheueMKN+hx/evVMJ8NQt8aARcYgjP0CE3Tp2yVCzfo0frZSug6YhDdMchmEeE6LcAYArMNKHnTC8vxAIS+dQihKTq4brMp5yoEkUE2pllNHuWwHvbDdsgHjUuCrGfwLTTBs8YCySxm3RKaiaxRRjQmgt7mTrz1neew/v+7H6JWVBZxcuXON9jjw+t/+VTGMsKZhL1BXHnjJGZsWZQxuyCQJZsh52g92pz0UP2aJqz56l2Jr1leM0oMTGRZ0wvLkoymu5eqP2m8qTJHxZy6nMEAmbwoGCBFJ1aiQWCWIaWGQhxngHepCbJhwCethsG/0JQ22U4KxhCp1gLVyXPQsllE9z0O9Nxpg+iTIetYSkGlkcAiMqp/6YS+VenMGAAxyGE75If1eABtj5bDP8cA87n03490OJRKkEWbN2AIbuy9gN999L8wY8silM+qhSxJuHnoCq7tPps2MY8aB3/8GhxTK1A+uxbgSnrieBAQ6PbAVJ6+SiaXZUhRCZe2H0t6fNGH1mXd9aBGtvUFgijAVlOCiD8MnTm/AHVwBkVCBqJggBQl530lSgfZEU3cFcf/DDXq0LPFMWLX5loBsZLR25JXsssDfVs0NXGSDCDCUflMDzo+VKosqoykro0YjAOIOkS4bstS7nmcCnuCOPO7/QU7XywYwat/9itM37QATXcthaXSjmCvH5dfO45LO45j6oZ5WPPVu8G5nMhpIEsy5JiEXd/+LYI9/XkujKUWlM+qLVjbMokGIri+9yTm3r9KddDBBKZUICQkAwoGSFGSjQLaPlUB8+l40iEZMYcI71IzAnMME2JRHNCXWOlIIOtuCK1bgsYto/UTFSh72QXj9f4FlrKegQscYl+OGi4oyaV67rClzTEgBGVYjvlhbA4DXJmS8S41jcoISLGSoxIuvXocl149nvLcxe3H0Hn6Bma/ZzkqFzaAx2TcPHQZF14+goDTm3SsqM/9caq2wmDGtkoymt88jTPP7Ufdypmw1ZXmDAhkScbNg5fgbc1deZBMXhQMkKLFNQy+xWb4FqdPhCS6Y9D2SJB1SlXC8RggaLtjiXLNmXAB0LdGEJxpQ/vHK6DpjkLbrawrUFIIA1pnDCzGES3RgBvSdw6Gq2FU/aYbLMoTmZOMV8JwvO1B50NlCDZRytl03De6ceB/duQ8LuD0IhoMQ2ss0PqSQWRJQjQQwfk/HkbEF8L2bzyORR9ej6ZtS5J2LMSnKeJ/9lxux55/e3FE2kQmDgoGyLij6Ymh7BVX0na7mE1E7+1W+JYURwZFtbiaCoE8+bhYmRaxsuT1DrnyRIgeCVVPdYMN3oLJAcSAqme60fL5KsTK6CNhqOSohIuvHMOc+1ZmLnccioCJAjRZciYkv0aGLHOIGhHBHh92/k3/1ETEF8KhH7+GIz/fCVOpBbFQFPbGCjRtWwxrTQlCLj8uv3EKN/ZeSFRgJCQT+s0n44qmN4ban3WmFOkRPRIq/uCCEOLwrCniynuDRMs1iFkFiN7M2wcZB4IzhnfXbj3iTw0E4ucHwGXAdsiHnq2OYV1nsjv+xG7ULJ0Ge0N5UkAQX7y3+19eQNWCKZj7wOqsw/tc5uBcxqVXjyPiD6PrTAta9l9Mu1VRjkrwdbgBAKET19BxIjWpECG5UDBAxpWSXR4I4dROLd6Rlr7uhm+RsWjSKuckMLhvtaJsuzvt00q6Yp2y+2EYTBey70RgXKln0LN1WJcpGlWLGlC/aiZErQbdl9px9e0zkMKx3C8cpmggjO1/+jjmP7QWs9+zDHqrEVxW5uxP/mYPnOda0XakGWVNNaha1Ji2XoEsyeAyx9vffQ439l4Y8TYTAlAwQMYRFpZhPhNMSumbggOWk0F4Vo+f0QHPSjM0vTHY9/vBBWUXQXznRKRai873lw77GkzKvSdRzTHFzlBixqa/fVjZehiTwDkwWyNg5ee24O1//P2o5NiPBiI49vibOP6rt6AzGxALRyFF+gMRKRLD63/5FKZvWoimu5fCWlsKBiAaiiDU60frkSu4+PJR+Luy1zwgpJAoGCDjhuiTswcCAMAAjXtoe85Fdwy2Q36YzofAJI5wrQ6elWaEG0ZmQVgCY+jZ6oBvkQnWowFoemKQjQL8840IzCrMzolQvU6p8Jjh+8cF5ZjxjAkMW77zCOxpigtpTTps/PZDePmrv0iqWjiSuMwzliKWYzIu7VC2LxJSDCgYIOOGbGS5CwpxpfhPvgxXwykL7DTuICyng+jdYIXr9pHfsx+p0aG7ZmQ6ZO9KM2xHAxmfZzLgXTl+RlPSqV/VhJLpVWmfY4IAJnPMe3AN9vzrH0a5ZYQUv4lR7JxMCrJJRHCGXqkXkAkH/AuMeZ1XCMnKlrtBC+zid9Elb3thPJ/+Dm+8iFTr0H2nHQCSvn/xv/dusCI0dYRHQEZYw7rZSnXDDASNiKnr545iiwgZP2hkgIwrvbfbYGzuSqk8CPSl4F1hQsyR34+15XgALMIzjjhwBtj3+RCcnV+QUWw8ayyIVGlh2+eFsTkCgCM8RQ/3GsuEyDGgMerAciTgEXWavAsIETIZUDBAxpVInQ7tHy5HxQs90HjkRFVBCIBnlRk9m+15n9NwLZz1ecYBw/UIwPm4z/UfmqYvXNGlIuO+3g2+hoNlyN3AZQ5fh4sCAULSoGCAjDuhaXrc+Go1jFfC0HbHIOsZArMM42c74SQQa1VRMKrALm0/ioUfWJvlCI5zLx4atfYQMp7QmgEyPgkMwZkGeFZb4FtiHlYgEGrMfqfMGRBq0I37UYGJztfhxqGfvg4gtUKfLMvoPN2C8y8eHoumEVL0aGSATHq+xSaU7PIA0QwZ+jjgHkdZDSezs88dgL/DjQUfWJuoIBhy+XHuxcM49cy7Qy51TMhER8EAmfRkg4COD5ah6qluYMCOgngCoN4N1nG/eLCYWG6ObJ7863vO4/qe89DbTRC1Sk5/WidASHYUDBACIDRVj5YvVsJ22A/TuVFOOjQBnG1Pv79/LIXdmfMqEEKSUTBASB/JrkHvJjt6N+W/I4EQQsYzWkBICCGETHIUDBBC8rbTOWesm0AIKSAKBgghI8rUQh8zhBQ7+i0lhOSFRgUImXgoGCCEqEaBACETE+0mIITklE8QMBapiAkhw0MjA4SQrGg0gJCJj4IBQkhGagKBYkw4RAjJD00TEEJS0GgAIZMLjQwQQpJQIEDI5EPBACEkgQIBQiYnCgYIIQAoECBkMqNggBAy5EBg8OLBwdsKB2cfHFy+2NocHNJ1CSGFRcEAIZMcjQgQQigYIIQMSa5RgaHQXL457HMQQvJHwQAhk9hIjgpQgSJCxg/6bSWE5G0oowKD1wsQQooHBQOETFI0KkAIiaPfWEJIXkZirQAhZGxRMEDIJFSorYTDQdsKCSkeFAwQQlRRGwikmyKg9QKEFDcqVETIJJPvqEC2IICmCAiZGGhkgBCSUb7TArRwkJDxiX5zCZlE8hkVyBUIqB0VoCkCQoofBQOEkBSFXChICCl+FAwQMkmoHRVQEwikGxXIZ4qAdhIQUlwoGCBkEhjpQIAQMr5RMEAIATAygQCtFyBkfKBggBAy7ECAdhEQMr7RbzAhZFgyBQKZRgVovQAhxYeCAUImuEIUJKJ1AoRMbBQMEEKGLN9RAUJIcaJggJBJbqjJhYYSCNAUASHFiYIBQkhR0Fy+OdZNIGTSomCAEJIRjQoQMjlQMEDIJDaUtMO0ToCQiYeCAUJIWrSDgJDJg4IBQohqQx0VoCkCQoobBQOETFLZpgjyGRWg6QFCxj8KBgghqgw15TCNChBS/CgYIIQkoVEBQiYfCgYIITmlGxVQEwjQqAAh4wMFA4RMQpnWC6QbFRiNioSUcIiQsUXBACETWD5Fimh6gJDJi4IBQkhGQ50eAGiKgJDxhIIBQkjBUSBAyPhCwQAhk0y69QKUbZCQyY2CAUJIWqO1g4AWDxIy9igYIIQUDE0PEDI+UTBACCmIoQQCNCpASHGgYIAQokq2KQIaESBkfKNggBCSIp9EQxQIEDL+UTBAyCQ3nJ0EwwkEaIqAkOJBwQAhJKd0UwQ0IkDIxEHBACEkb8MNBGhUgJDiQsEAISTJaBQmIoQUF/qtJ2QSyVStcDTRqAAhxYeCAUJIVoPXC9BaAUImHgoGCJnEqCYBIQSgYIAQMsBIrxegKQJCihMFA4SQjGiKgJDJgYIBQsiooFEBQooXBQOEEELIJEfBACFkxNGoACHFjYIBQsiIokCAkOJHwQAhZMRQIEDI+EDBACFElXx3ElAgQMj4QcEAISStdJUK1aJAgJDxhYIBQkhBUSBAyPhDwQAhBEBhsg9SIEDI+ETBACGkICgQIGT8omCAEDJsFAgQMr5RMEAIGRYKBAgZ/ygYIGSSKkT5YgoECJkYKBgghAwJBQKETBwUDBBC8kaBACETCwUDhJCc8s0+SAgZXygYIIQQQiY5xjnnY90IQgghhIwdGhkghBBCJjkKBgghhJBJjoIBQgghZJKjYIAQQgiZ5CgYIIQQQiY5CgYIIYSQSY6CAUIIIWSSo2CAEEIImeQoGCCEEEImuf8fpYx5W6TvCO4AAAAASUVORK5CYII=\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": "95c2bda5-ad68-45ea-a37d-e14a725b23d7"
},
"execution_count": 52,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712630674.8246243\n",
"Tue Apr 9 02:44:34 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": "da9a62a4-83ee-4160-883f-3bbe2648128e"
},
"execution_count": 53,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712630674.8310766\n",
"Tue Apr 9 02:44:34 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": 1932
},
"id": "95xed6YyDClf",
"outputId": "7a0ebb10-6658-4700-d8e6-0abc8d28d4fc"
},
"execution_count": 54,
"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",
"37 0.295652\n",
"327 0.148724\n",
"377 0.143135\n",
"110 0.120443\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 0.010884\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.003876\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.001982\n",
"1 0.003727\n",
"2 0.004084\n",
"3 0.004421\n",
"4 0.005773\n",
"Normalized Saliency Sum: Saliency 5.224422\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.049641\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 17.13619\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 332.84082\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.002464\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 456.085388\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.004058\n",
"1 0.007209\n",
"2 0.013432\n",
"3 0.015697\n",
"4 0.018671\n",
".. ...\n",
"475 5.205212\n",
"476 5.207337\n",
"477 5.212391\n",
"478 5.214947\n",
"479 5.224422\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000008\n",
"1 0.000015\n",
"2 0.000028\n",
"3 0.000033\n",
"4 0.000039\n",
".. ...\n",
"475 0.010844\n",
"476 0.010849\n",
"477 0.010859\n",
"478 0.010864\n",
"479 0.010884\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.050769985\n",
"Normalized Saliency 25th Percentile: Saliency 0.002269\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.007695\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.005426\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": "1efbdd9b-6992-4342-cb96-4c19cc5e57d7"
},
"execution_count": 55,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712630676.9388988\n",
"Tue Apr 9 02:44:36 2024\n"
]
}
]
}
]
}