Datasets
Models
Downloads: 1
1259 lines (1259 with data), 217.5 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": 79,
"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": 80,
"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": "951e4371-4651-460b-96e7-0b10f6fdfd79",
"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",
" Dense(1024, activation=tf.nn.relu),\n",
" TNLayer(),\n",
" TNLayer(),\n",
" # Finish Modified Layers\n",
" Dense(1, activation=None)])\n",
"tn_model.summary()"
],
"execution_count": 81,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Model: \"sequential_7\"\n",
"_________________________________________________________________\n",
" Layer (type) Output Shape Param # \n",
"=================================================================\n",
" dense_27 (Dense) (None, 1024) 3072 \n",
" \n",
" dense_28 (Dense) (None, 1024) 1049600 \n",
" \n",
" tn_layer_7 (TNLayer) (None, 1024) 5120 \n",
" \n",
" tn_layer_8 (TNLayer) (None, 1024) 5120 \n",
" \n",
" dense_29 (Dense) (None, 1) 1025 \n",
" \n",
"=================================================================\n",
"Total params: 1063937 (4.06 MB)\n",
"Trainable params: 1063937 (4.06 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": 82,
"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": "6af7d3fc-0688-4952-cdc4-255e7cc99e99"
},
"execution_count": 83,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712559721.6102765\n",
"Mon Apr 8 07:02:01 2024\n"
]
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "crc0q1vbIyTj",
"outputId": "124bab85-5fef-42db-8a74-dbe3e01d1ee9",
"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": 84,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/300\n",
"15/15 - 2s - loss: 0.9761 - 2s/epoch - 112ms/step\n",
"Epoch 2/300\n",
"15/15 - 0s - loss: 0.4717 - 130ms/epoch - 9ms/step\n",
"Epoch 3/300\n",
"15/15 - 0s - loss: 0.0845 - 126ms/epoch - 8ms/step\n",
"Epoch 4/300\n",
"15/15 - 0s - loss: 0.0326 - 115ms/epoch - 8ms/step\n",
"Epoch 5/300\n",
"15/15 - 0s - loss: 0.0252 - 120ms/epoch - 8ms/step\n",
"Epoch 6/300\n",
"15/15 - 0s - loss: 0.0215 - 117ms/epoch - 8ms/step\n",
"Epoch 7/300\n",
"15/15 - 0s - loss: 0.0164 - 120ms/epoch - 8ms/step\n",
"Epoch 8/300\n",
"15/15 - 0s - loss: 0.0137 - 116ms/epoch - 8ms/step\n",
"Epoch 9/300\n",
"15/15 - 0s - loss: 0.0107 - 115ms/epoch - 8ms/step\n",
"Epoch 10/300\n",
"15/15 - 0s - loss: 0.0101 - 116ms/epoch - 8ms/step\n",
"Epoch 11/300\n",
"15/15 - 0s - loss: 0.0083 - 115ms/epoch - 8ms/step\n",
"Epoch 12/300\n",
"15/15 - 0s - loss: 0.0037 - 120ms/epoch - 8ms/step\n",
"Epoch 13/300\n",
"15/15 - 0s - loss: 0.0028 - 120ms/epoch - 8ms/step\n",
"Epoch 14/300\n",
"15/15 - 0s - loss: 0.0018 - 120ms/epoch - 8ms/step\n",
"Epoch 15/300\n",
"15/15 - 0s - loss: 8.8048e-04 - 119ms/epoch - 8ms/step\n",
"Epoch 16/300\n",
"15/15 - 0s - loss: 3.6412e-04 - 114ms/epoch - 8ms/step\n",
"Epoch 17/300\n",
"15/15 - 0s - loss: 7.3253e-04 - 118ms/epoch - 8ms/step\n",
"Epoch 18/300\n",
"15/15 - 0s - loss: 2.9720e-04 - 119ms/epoch - 8ms/step\n",
"Epoch 19/300\n",
"15/15 - 0s - loss: 2.3314e-04 - 113ms/epoch - 8ms/step\n",
"Epoch 20/300\n",
"15/15 - 0s - loss: 1.2356e-04 - 123ms/epoch - 8ms/step\n",
"Epoch 21/300\n",
"15/15 - 0s - loss: 6.6671e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 22/300\n",
"15/15 - 0s - loss: 4.4817e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 23/300\n",
"15/15 - 0s - loss: 3.9205e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 24/300\n",
"15/15 - 0s - loss: 3.3151e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 25/300\n",
"15/15 - 0s - loss: 2.6759e-05 - 112ms/epoch - 7ms/step\n",
"Epoch 26/300\n",
"15/15 - 0s - loss: 2.3953e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 27/300\n",
"15/15 - 0s - loss: 2.0857e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 28/300\n",
"15/15 - 0s - loss: 1.6800e-05 - 123ms/epoch - 8ms/step\n",
"Epoch 29/300\n",
"15/15 - 0s - loss: 1.3845e-05 - 123ms/epoch - 8ms/step\n",
"Epoch 30/300\n",
"15/15 - 0s - loss: 1.3638e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 31/300\n",
"15/15 - 0s - loss: 1.1733e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 32/300\n",
"15/15 - 0s - loss: 1.0048e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 33/300\n",
"15/15 - 0s - loss: 8.6393e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 34/300\n",
"15/15 - 0s - loss: 8.4526e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 35/300\n",
"15/15 - 0s - loss: 7.4082e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 36/300\n",
"15/15 - 0s - loss: 6.3283e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 37/300\n",
"15/15 - 0s - loss: 5.7832e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 38/300\n",
"15/15 - 0s - loss: 5.0280e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 39/300\n",
"15/15 - 0s - loss: 5.1115e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 40/300\n",
"15/15 - 0s - loss: 4.2167e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 41/300\n",
"15/15 - 0s - loss: 3.6792e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 42/300\n",
"15/15 - 0s - loss: 3.2607e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 43/300\n",
"15/15 - 0s - loss: 3.5933e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 44/300\n",
"15/15 - 0s - loss: 3.5958e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 45/300\n",
"15/15 - 0s - loss: 3.9817e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 46/300\n",
"15/15 - 0s - loss: 4.2636e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 47/300\n",
"15/15 - 0s - loss: 2.2534e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 48/300\n",
"15/15 - 0s - loss: 1.9528e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 49/300\n",
"15/15 - 0s - loss: 1.7900e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 50/300\n",
"15/15 - 0s - loss: 2.0084e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 51/300\n",
"15/15 - 0s - loss: 1.6954e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 52/300\n",
"15/15 - 0s - loss: 1.7595e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 53/300\n",
"15/15 - 0s - loss: 1.4796e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 54/300\n",
"15/15 - 0s - loss: 1.3043e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 55/300\n",
"15/15 - 0s - loss: 1.4436e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 56/300\n",
"15/15 - 0s - loss: 1.6451e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 57/300\n",
"15/15 - 0s - loss: 1.1902e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 58/300\n",
"15/15 - 0s - loss: 1.1896e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 59/300\n",
"15/15 - 0s - loss: 1.2402e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 60/300\n",
"15/15 - 0s - loss: 1.1322e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 61/300\n",
"15/15 - 0s - loss: 7.3566e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 62/300\n",
"15/15 - 0s - loss: 8.2242e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 63/300\n",
"15/15 - 0s - loss: 7.8549e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 64/300\n",
"15/15 - 0s - loss: 8.1494e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 65/300\n",
"15/15 - 0s - loss: 9.7856e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 66/300\n",
"15/15 - 0s - loss: 3.7390e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 67/300\n",
"15/15 - 0s - loss: 3.3567e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 68/300\n",
"15/15 - 0s - loss: 3.5198e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 69/300\n",
"15/15 - 0s - loss: 1.5647e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 70/300\n",
"15/15 - 0s - loss: 1.5604e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 71/300\n",
"15/15 - 0s - loss: 8.3125e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 72/300\n",
"15/15 - 0s - loss: 1.1766e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 73/300\n",
"15/15 - 0s - loss: 8.2574e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 74/300\n",
"15/15 - 0s - loss: 1.0740e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 75/300\n",
"15/15 - 0s - loss: 5.6160e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 76/300\n",
"15/15 - 0s - loss: 4.5430e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 77/300\n",
"15/15 - 0s - loss: 4.6511e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 78/300\n",
"15/15 - 0s - loss: 4.6150e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 79/300\n",
"15/15 - 0s - loss: 3.6542e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 80/300\n",
"15/15 - 0s - loss: 5.3092e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 81/300\n",
"15/15 - 0s - loss: 5.5465e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 82/300\n",
"15/15 - 0s - loss: 4.1580e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 83/300\n",
"15/15 - 0s - loss: 3.7450e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 84/300\n",
"15/15 - 0s - loss: 6.3822e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 85/300\n",
"15/15 - 0s - loss: 8.4460e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 86/300\n",
"15/15 - 0s - loss: 4.1775e-07 - 130ms/epoch - 9ms/step\n",
"Epoch 87/300\n",
"15/15 - 0s - loss: 9.0002e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 88/300\n",
"15/15 - 0s - loss: 6.5433e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 89/300\n",
"15/15 - 0s - loss: 4.9805e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 90/300\n",
"15/15 - 0s - loss: 1.2008e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 91/300\n",
"15/15 - 0s - loss: 1.9144e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 92/300\n",
"15/15 - 0s - loss: 4.2023e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 93/300\n",
"15/15 - 0s - loss: 5.5406e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 94/300\n",
"15/15 - 0s - loss: 7.7754e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 95/300\n",
"15/15 - 0s - loss: 1.7581e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 96/300\n",
"15/15 - 0s - loss: 1.6568e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 97/300\n",
"15/15 - 0s - loss: 2.7997e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 98/300\n",
"15/15 - 0s - loss: 1.1327e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 99/300\n",
"15/15 - 0s - loss: 9.7699e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 100/300\n",
"15/15 - 0s - loss: 5.4976e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 101/300\n",
"15/15 - 0s - loss: 7.4412e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 102/300\n",
"15/15 - 0s - loss: 2.2672e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 103/300\n",
"15/15 - 0s - loss: 2.8039e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 104/300\n",
"15/15 - 0s - loss: 8.1756e-07 - 128ms/epoch - 9ms/step\n",
"Epoch 105/300\n",
"15/15 - 0s - loss: 1.3926e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 106/300\n",
"15/15 - 0s - loss: 7.0850e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 107/300\n",
"15/15 - 0s - loss: 4.1094e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 108/300\n",
"15/15 - 0s - loss: 8.5644e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 109/300\n",
"15/15 - 0s - loss: 3.6387e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 110/300\n",
"15/15 - 0s - loss: 2.5015e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 111/300\n",
"15/15 - 0s - loss: 5.0919e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 112/300\n",
"15/15 - 0s - loss: 4.4267e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 113/300\n",
"15/15 - 0s - loss: 1.1795e-06 - 130ms/epoch - 9ms/step\n",
"Epoch 114/300\n",
"15/15 - 0s - loss: 2.7169e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 115/300\n",
"15/15 - 0s - loss: 3.6253e-07 - 113ms/epoch - 8ms/step\n",
"Epoch 116/300\n",
"15/15 - 0s - loss: 3.8597e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 117/300\n",
"15/15 - 0s - loss: 3.6218e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 118/300\n",
"15/15 - 0s - loss: 1.9305e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 119/300\n",
"15/15 - 0s - loss: 8.2731e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 120/300\n",
"15/15 - 0s - loss: 8.2769e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 121/300\n",
"15/15 - 0s - loss: 2.2682e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 122/300\n",
"15/15 - 0s - loss: 1.9648e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 123/300\n",
"15/15 - 0s - loss: 6.1284e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 124/300\n",
"15/15 - 0s - loss: 9.4071e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 125/300\n",
"15/15 - 0s - loss: 4.2009e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 126/300\n",
"15/15 - 0s - loss: 7.1143e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 127/300\n",
"15/15 - 0s - loss: 1.6168e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 128/300\n",
"15/15 - 0s - loss: 5.2911e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 129/300\n",
"15/15 - 0s - loss: 2.8587e-05 - 114ms/epoch - 8ms/step\n",
"Epoch 130/300\n",
"15/15 - 0s - loss: 2.7364e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 131/300\n",
"15/15 - 0s - loss: 1.1473e-05 - 114ms/epoch - 8ms/step\n",
"Epoch 132/300\n",
"15/15 - 0s - loss: 3.2765e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 133/300\n",
"15/15 - 0s - loss: 3.3562e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 134/300\n",
"15/15 - 0s - loss: 2.2614e-05 - 113ms/epoch - 8ms/step\n",
"Epoch 135/300\n",
"15/15 - 0s - loss: 2.0109e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 136/300\n",
"15/15 - 0s - loss: 1.4602e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 137/300\n",
"15/15 - 0s - loss: 7.5398e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 138/300\n",
"15/15 - 0s - loss: 1.6535e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 139/300\n",
"15/15 - 0s - loss: 7.7620e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 140/300\n",
"15/15 - 0s - loss: 1.7274e-06 - 129ms/epoch - 9ms/step\n",
"Epoch 141/300\n",
"15/15 - 0s - loss: 1.7617e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 142/300\n",
"15/15 - 0s - loss: 9.4143e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 143/300\n",
"15/15 - 0s - loss: 1.2518e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 144/300\n",
"15/15 - 0s - loss: 2.0548e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 145/300\n",
"15/15 - 0s - loss: 2.1773e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 146/300\n",
"15/15 - 0s - loss: 3.8482e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 147/300\n",
"15/15 - 0s - loss: 2.6590e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 148/300\n",
"15/15 - 0s - loss: 2.3047e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 149/300\n",
"15/15 - 0s - loss: 9.2871e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 150/300\n",
"15/15 - 0s - loss: 1.9176e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 151/300\n",
"15/15 - 0s - loss: 6.2865e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 152/300\n",
"15/15 - 0s - loss: 2.3527e-04 - 127ms/epoch - 8ms/step\n",
"Epoch 153/300\n",
"15/15 - 0s - loss: 4.9768e-05 - 116ms/epoch - 8ms/step\n",
"Epoch 154/300\n",
"15/15 - 0s - loss: 2.3422e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 155/300\n",
"15/15 - 0s - loss: 2.7577e-05 - 123ms/epoch - 8ms/step\n",
"Epoch 156/300\n",
"15/15 - 0s - loss: 2.0633e-05 - 125ms/epoch - 8ms/step\n",
"Epoch 157/300\n",
"15/15 - 0s - loss: 2.0665e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 158/300\n",
"15/15 - 0s - loss: 4.5195e-05 - 118ms/epoch - 8ms/step\n",
"Epoch 159/300\n",
"15/15 - 0s - loss: 2.7804e-04 - 121ms/epoch - 8ms/step\n",
"Epoch 160/300\n",
"15/15 - 0s - loss: 4.5421e-04 - 119ms/epoch - 8ms/step\n",
"Epoch 161/300\n",
"15/15 - 0s - loss: 3.2990e-04 - 117ms/epoch - 8ms/step\n",
"Epoch 162/300\n",
"15/15 - 0s - loss: 4.4646e-04 - 123ms/epoch - 8ms/step\n",
"Epoch 163/300\n",
"15/15 - 0s - loss: 1.3287e-04 - 119ms/epoch - 8ms/step\n",
"Epoch 164/300\n",
"15/15 - 0s - loss: 1.0919e-04 - 118ms/epoch - 8ms/step\n",
"Epoch 165/300\n",
"15/15 - 0s - loss: 6.8276e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 166/300\n",
"15/15 - 0s - loss: 0.0045 - 113ms/epoch - 8ms/step\n",
"Epoch 167/300\n",
"15/15 - 0s - loss: 0.0384 - 120ms/epoch - 8ms/step\n",
"Epoch 168/300\n",
"15/15 - 0s - loss: 0.0179 - 113ms/epoch - 8ms/step\n",
"Epoch 169/300\n",
"15/15 - 0s - loss: 0.0039 - 122ms/epoch - 8ms/step\n",
"Epoch 170/300\n",
"15/15 - 0s - loss: 0.0038 - 123ms/epoch - 8ms/step\n",
"Epoch 171/300\n",
"15/15 - 0s - loss: 0.0040 - 123ms/epoch - 8ms/step\n",
"Epoch 172/300\n",
"15/15 - 0s - loss: 0.0035 - 115ms/epoch - 8ms/step\n",
"Epoch 173/300\n",
"15/15 - 0s - loss: 0.0037 - 117ms/epoch - 8ms/step\n",
"Epoch 174/300\n",
"15/15 - 0s - loss: 5.3851e-04 - 117ms/epoch - 8ms/step\n",
"Epoch 175/300\n",
"15/15 - 0s - loss: 0.0054 - 114ms/epoch - 8ms/step\n",
"Epoch 176/300\n",
"15/15 - 0s - loss: 0.0056 - 123ms/epoch - 8ms/step\n",
"Epoch 177/300\n",
"15/15 - 0s - loss: 0.0408 - 118ms/epoch - 8ms/step\n",
"Epoch 178/300\n",
"15/15 - 0s - loss: 0.0051 - 117ms/epoch - 8ms/step\n",
"Epoch 179/300\n",
"15/15 - 0s - loss: 0.0042 - 118ms/epoch - 8ms/step\n",
"Epoch 180/300\n",
"15/15 - 0s - loss: 0.0011 - 127ms/epoch - 8ms/step\n",
"Epoch 181/300\n",
"15/15 - 0s - loss: 5.4848e-04 - 115ms/epoch - 8ms/step\n",
"Epoch 182/300\n",
"15/15 - 0s - loss: 2.0348e-04 - 116ms/epoch - 8ms/step\n",
"Epoch 183/300\n",
"15/15 - 0s - loss: 1.8680e-04 - 125ms/epoch - 8ms/step\n",
"Epoch 184/300\n",
"15/15 - 0s - loss: 7.7196e-05 - 113ms/epoch - 8ms/step\n",
"Epoch 185/300\n",
"15/15 - 0s - loss: 2.9117e-05 - 111ms/epoch - 7ms/step\n",
"Epoch 186/300\n",
"15/15 - 0s - loss: 1.9826e-05 - 113ms/epoch - 8ms/step\n",
"Epoch 187/300\n",
"15/15 - 0s - loss: 1.5628e-05 - 121ms/epoch - 8ms/step\n",
"Epoch 188/300\n",
"15/15 - 0s - loss: 1.2130e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 189/300\n",
"15/15 - 0s - loss: 1.0245e-05 - 123ms/epoch - 8ms/step\n",
"Epoch 190/300\n",
"15/15 - 0s - loss: 8.7586e-06 - 128ms/epoch - 9ms/step\n",
"Epoch 191/300\n",
"15/15 - 0s - loss: 7.4825e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 192/300\n",
"15/15 - 0s - loss: 7.1844e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 193/300\n",
"15/15 - 0s - loss: 7.1550e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 194/300\n",
"15/15 - 0s - loss: 7.1509e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 195/300\n",
"15/15 - 0s - loss: 1.0024e-05 - 115ms/epoch - 8ms/step\n",
"Epoch 196/300\n",
"15/15 - 0s - loss: 6.9407e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 197/300\n",
"15/15 - 0s - loss: 5.7108e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 198/300\n",
"15/15 - 0s - loss: 4.6228e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 199/300\n",
"15/15 - 0s - loss: 4.3752e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 200/300\n",
"15/15 - 0s - loss: 3.2427e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 201/300\n",
"15/15 - 0s - loss: 3.3642e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 202/300\n",
"15/15 - 0s - loss: 2.9825e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 203/300\n",
"15/15 - 0s - loss: 2.5210e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 204/300\n",
"15/15 - 0s - loss: 2.4107e-06 - 113ms/epoch - 8ms/step\n",
"Epoch 205/300\n",
"15/15 - 0s - loss: 2.4661e-06 - 122ms/epoch - 8ms/step\n",
"Epoch 206/300\n",
"15/15 - 0s - loss: 2.1516e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 207/300\n",
"15/15 - 0s - loss: 2.1311e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 208/300\n",
"15/15 - 0s - loss: 2.1018e-06 - 117ms/epoch - 8ms/step\n",
"Epoch 209/300\n",
"15/15 - 0s - loss: 1.8466e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 210/300\n",
"15/15 - 0s - loss: 1.7886e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 211/300\n",
"15/15 - 0s - loss: 1.5170e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 212/300\n",
"15/15 - 0s - loss: 1.5701e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 213/300\n",
"15/15 - 0s - loss: 1.3390e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 214/300\n",
"15/15 - 0s - loss: 1.3370e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 215/300\n",
"15/15 - 0s - loss: 1.1869e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 216/300\n",
"15/15 - 0s - loss: 1.1066e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 217/300\n",
"15/15 - 0s - loss: 1.1042e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 218/300\n",
"15/15 - 0s - loss: 1.1070e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 219/300\n",
"15/15 - 0s - loss: 9.5987e-07 - 112ms/epoch - 7ms/step\n",
"Epoch 220/300\n",
"15/15 - 0s - loss: 9.6279e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 221/300\n",
"15/15 - 0s - loss: 1.0630e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 222/300\n",
"15/15 - 0s - loss: 8.2732e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 223/300\n",
"15/15 - 0s - loss: 9.3322e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 224/300\n",
"15/15 - 0s - loss: 1.1889e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 225/300\n",
"15/15 - 0s - loss: 1.7213e-06 - 118ms/epoch - 8ms/step\n",
"Epoch 226/300\n",
"15/15 - 0s - loss: 2.3612e-06 - 123ms/epoch - 8ms/step\n",
"Epoch 227/300\n",
"15/15 - 0s - loss: 1.1577e-06 - 121ms/epoch - 8ms/step\n",
"Epoch 228/300\n",
"15/15 - 0s - loss: 8.9531e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 229/300\n",
"15/15 - 0s - loss: 7.0301e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 230/300\n",
"15/15 - 0s - loss: 7.6607e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 231/300\n",
"15/15 - 0s - loss: 7.0172e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 232/300\n",
"15/15 - 0s - loss: 9.7852e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 233/300\n",
"15/15 - 0s - loss: 9.0323e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 234/300\n",
"15/15 - 0s - loss: 8.8879e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 235/300\n",
"15/15 - 0s - loss: 5.1235e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 236/300\n",
"15/15 - 0s - loss: 4.6657e-07 - 113ms/epoch - 8ms/step\n",
"Epoch 237/300\n",
"15/15 - 0s - loss: 6.9554e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 238/300\n",
"15/15 - 0s - loss: 5.7211e-07 - 113ms/epoch - 8ms/step\n",
"Epoch 239/300\n",
"15/15 - 0s - loss: 5.0994e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 240/300\n",
"15/15 - 0s - loss: 5.2670e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 241/300\n",
"15/15 - 0s - loss: 4.0522e-07 - 125ms/epoch - 8ms/step\n",
"Epoch 242/300\n",
"15/15 - 0s - loss: 3.7782e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 243/300\n",
"15/15 - 0s - loss: 4.1283e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 244/300\n",
"15/15 - 0s - loss: 3.5163e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 245/300\n",
"15/15 - 0s - loss: 4.0101e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 246/300\n",
"15/15 - 0s - loss: 4.2432e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 247/300\n",
"15/15 - 0s - loss: 2.9691e-07 - 127ms/epoch - 8ms/step\n",
"Epoch 248/300\n",
"15/15 - 0s - loss: 3.1491e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 249/300\n",
"15/15 - 0s - loss: 3.5015e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 250/300\n",
"15/15 - 0s - loss: 3.0078e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 251/300\n",
"15/15 - 0s - loss: 3.0159e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 252/300\n",
"15/15 - 0s - loss: 3.8187e-07 - 129ms/epoch - 9ms/step\n",
"Epoch 253/300\n",
"15/15 - 0s - loss: 2.6248e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 254/300\n",
"15/15 - 0s - loss: 3.2807e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 255/300\n",
"15/15 - 0s - loss: 3.0686e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 256/300\n",
"15/15 - 0s - loss: 3.7237e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 257/300\n",
"15/15 - 0s - loss: 4.3187e-07 - 126ms/epoch - 8ms/step\n",
"Epoch 258/300\n",
"15/15 - 0s - loss: 5.8032e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 259/300\n",
"15/15 - 0s - loss: 6.1197e-07 - 124ms/epoch - 8ms/step\n",
"Epoch 260/300\n",
"15/15 - 0s - loss: 4.5996e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 261/300\n",
"15/15 - 0s - loss: 3.4202e-07 - 127ms/epoch - 8ms/step\n",
"Epoch 262/300\n",
"15/15 - 0s - loss: 3.6858e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 263/300\n",
"15/15 - 0s - loss: 3.4672e-07 - 119ms/epoch - 8ms/step\n",
"Epoch 264/300\n",
"15/15 - 0s - loss: 3.6171e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 265/300\n",
"15/15 - 0s - loss: 4.6893e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 266/300\n",
"15/15 - 0s - loss: 5.6363e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 267/300\n",
"15/15 - 0s - loss: 1.2746e-06 - 126ms/epoch - 8ms/step\n",
"Epoch 268/300\n",
"15/15 - 0s - loss: 7.3074e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 269/300\n",
"15/15 - 0s - loss: 2.4713e-05 - 119ms/epoch - 8ms/step\n",
"Epoch 270/300\n",
"15/15 - 0s - loss: 4.9441e-06 - 119ms/epoch - 8ms/step\n",
"Epoch 271/300\n",
"15/15 - 0s - loss: 3.1331e-06 - 127ms/epoch - 8ms/step\n",
"Epoch 272/300\n",
"15/15 - 0s - loss: 2.9096e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 273/300\n",
"15/15 - 0s - loss: 9.8735e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 274/300\n",
"15/15 - 0s - loss: 4.6192e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 275/300\n",
"15/15 - 0s - loss: 7.6018e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 276/300\n",
"15/15 - 0s - loss: 1.5521e-06 - 124ms/epoch - 8ms/step\n",
"Epoch 277/300\n",
"15/15 - 0s - loss: 3.0382e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 278/300\n",
"15/15 - 0s - loss: 1.6231e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 279/300\n",
"15/15 - 0s - loss: 1.6201e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 280/300\n",
"15/15 - 0s - loss: 2.5012e-07 - 116ms/epoch - 8ms/step\n",
"Epoch 281/300\n",
"15/15 - 0s - loss: 2.9122e-07 - 120ms/epoch - 8ms/step\n",
"Epoch 282/300\n",
"15/15 - 0s - loss: 8.1879e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 283/300\n",
"15/15 - 0s - loss: 8.5232e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 284/300\n",
"15/15 - 0s - loss: 7.2052e-07 - 123ms/epoch - 8ms/step\n",
"Epoch 285/300\n",
"15/15 - 0s - loss: 4.4955e-07 - 115ms/epoch - 8ms/step\n",
"Epoch 286/300\n",
"15/15 - 0s - loss: 2.4551e-07 - 114ms/epoch - 8ms/step\n",
"Epoch 287/300\n",
"15/15 - 0s - loss: 3.8197e-07 - 121ms/epoch - 8ms/step\n",
"Epoch 288/300\n",
"15/15 - 0s - loss: 3.6193e-07 - 117ms/epoch - 8ms/step\n",
"Epoch 289/300\n",
"15/15 - 0s - loss: 4.8201e-07 - 118ms/epoch - 8ms/step\n",
"Epoch 290/300\n",
"15/15 - 0s - loss: 8.3653e-07 - 122ms/epoch - 8ms/step\n",
"Epoch 291/300\n",
"15/15 - 0s - loss: 2.1745e-06 - 112ms/epoch - 7ms/step\n",
"Epoch 292/300\n",
"15/15 - 0s - loss: 1.0451e-06 - 114ms/epoch - 8ms/step\n",
"Epoch 293/300\n",
"15/15 - 0s - loss: 5.2571e-06 - 115ms/epoch - 8ms/step\n",
"Epoch 294/300\n",
"15/15 - 0s - loss: 5.2543e-06 - 125ms/epoch - 8ms/step\n",
"Epoch 295/300\n",
"15/15 - 0s - loss: 2.1365e-06 - 116ms/epoch - 8ms/step\n",
"Epoch 296/300\n",
"15/15 - 0s - loss: 4.5690e-06 - 120ms/epoch - 8ms/step\n",
"Epoch 297/300\n",
"15/15 - 0s - loss: 1.1204e-05 - 124ms/epoch - 8ms/step\n",
"Epoch 298/300\n",
"15/15 - 0s - loss: 2.2339e-05 - 117ms/epoch - 8ms/step\n",
"Epoch 299/300\n",
"15/15 - 0s - loss: 2.5888e-05 - 122ms/epoch - 8ms/step\n",
"Epoch 300/300\n",
"15/15 - 0s - loss: 8.6946e-05 - 116ms/epoch - 8ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<keras.src.callbacks.History at 0x79197c173cd0>"
]
},
"metadata": {},
"execution_count": 84
}
]
},
{
"cell_type": "code",
"metadata": {
"id": "n-aNP4n3sqG_",
"outputId": "d0066495-096a-47c2-8767-6c68062faf36",
"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": 85,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"16/16 [==============================] - 0s 4ms/step\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": [
"<matplotlib.collections.PathCollection at 0x7919a0215090>"
]
},
"metadata": {},
"execution_count": 85
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAgMAAAGFCAYAAABg2vAPAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAACHi0lEQVR4nO3dd3gc13k2/PvMbN8FFr0XEuy9iZ2URJEURUlWsSVL7i2O7TiuSfwldvLGSew4cZL3TRwnbpJtWS6qliVZokRRoip77wUkQRSiAwtsL3PO98csFlhgyyywi7bP77psEsDszAAC99xzynOYEEKAEEIIIVlLmugbIIQQQsjEojBACCGEZDkKA4QQQkiWozBACCGEZDkKA4QQQkiWozBACCGEZDkKA4QQQkiWozBACCGEZDmd1gN3lv1ZJu+DEJJmgQXVkb/3zTJGfc1Zy6I+9tcEIn+fUdUZ9bXtZReiPn4g91i6bpEQMg7mVd9Iegz1DBBCCCFZjsIAIYQQkuUoDBBCCCFZjsIAIYQQkuUoDBBCCCFZjsIAIYQQkuUoDBBCojQ0F0/0LRBCxhmFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUJIQq+1zZ/oWyCEZBiFAUKygP2Kf6JvgRAyiVEYIISk5Jn+lRN9C4SQNKMwQAghhGQ5CgOEkJRR7wAh0wuFAUIIISTLURgghIwK9Q4QMn1QGCCEEEKyHIUBQsioUe8AIdMDhQFCCCEky1EYIISMCfUOEDL1URgghBBCshyFAULImFHvACFTG4UBQgghJMtRGCCEpAX1DhAydVEYICQL5VwXE30LhJBJhMIAISRtqHeAkKmJwgAhhBCS5SgMEEJgbDSk7VzUO0DI1ENhgBBCCMlyFAYIISM0NBeP6fXUO0DI1EJhgBBCCMlyFAYIIUm91jZ/om+BEJJBFAYIIRlBQwWETB0UBgghhJAsR2GAEJIx1DtAyNRAYYAQQgjJchQGCCEZRb0DhEx+FAYIIYSQLEdhgBBCCMlyFAYIIRlHQwWETG4UBgghhJAsR2GAEEIIyXIUBggh44KGCgiZvCgMEEJiGr5zIe1PQMj0RWGAEEIIyXIUBgghAABjo2Gib4EQMkEoDBBCxg3NGyBkcqIwQAghhGQ5CgOEZKmc62Kib4EQMklQGCCEEEKyHIUBQohm6VheSPMGCJl8KAwQQgghWY7CACEkruGFhwgh0xOFAUIIISTLURgghIw7mjdAyORCYYCQLGG/4p/oWyCETFIUBgghEVpKEtOGRYRMPxQGCCEpo0BAyPRCYYAQMiFo3gAhkweFAUJIQvGWF1LvACHTB4UBQrIY7U9ACAEoDBBCxoB6BwiZHigMEEKiaFlRQAiZXigMEEKSSlSWmHoHCJn6KAwQQgghWY7CACFkzKh3IH0EB7hf/ZOQ8aKb6BsghGSvZ/pX4oHcYxN9G5NCqJ+h+00j+g4bIAIMTC+QuyqAwlv90OfTqg+SWdQzQAhJC+odGL1gD0PDf9ng2K8GAQAQQYa+QwY0/JcN/nZ6qyaZRb9hhJARYq0oSDSJkIxN2+/NUDwM4Cz6C5yB+xlanzJPzI2RrEFhgJAsl87CQ9Q7kLpAtwTPZf3IIDCAM/ibdfDdoLdrkjn020VIFqFtjCcff5u2t2F/q5zhOyHZjMIAISStqHcgNZLGadyMpnuTDKIwQAjRjOYNpJ95ZgjMkGSoRhawzgmNzw2RrERhgBCSdtQ7oJ1kAApu9gOIEwiYQN66AGQLLS8kmUNhgBASE+1RMH4Kt/phXxtQP5AEwIT6J4CcZUGU3OWbwLsj2YBGoQghyLku4KyNM5t9mIbmYsyo6kzbtanwEMAkoOz9PuRvCKDvqAGhfgadTSB3ZQCmSipFSDKPwgAhJCNea5uP7WUXJvo2phRjGadeADIhaJiAEBIXDRUQkh0oDBAyTRnON2Xs3LSqgJDphcIAIYQQkuUoDBCSZeJVIYxXljjeUIGW3gFaYkjI1EBhgBBCCMlyFAYIIaNGcwcImR4oDBBCkqJVBYRMbxQGCCER6dzOeEC2zBsQHBDKRN8FIaNDRYcIIWOS7oqEU427XkbPW0Z4LusAwWAoV1Cw0Y/cVUEwetwiUwT9qhJCNKGhgpF69xvQ/DNbJAgAQKBNQtszFrQ9bYagSsJkiqAwQEgWire8cLSSTSScjkMFgW4JHc+b1A/EkH0dwn/vP2aA85R+Au6MkNRRGCCEkFFwHEzSU8IEet+j3hQyNdCcAUJIlEQ7GBobDfDXBGJ+LdvmDvhbpOgegeEEg/+GjGAPg+OQAf5WGZJewLYoBNuSICR69yWTCP06EkIm3FTcxpjpAEAASLz189Xv56h/CR/qPG2AfreCqs+6YShI/+oNQkaDhgkIIWQUbAtCiQ9gAiLE1N4DwQCwSE9C0CGh+VErLUUkkwaFAUIyTDboMOOWhVj84HrMuWM5jDnmib6lpBLVG0i0qiDRRMLpNokwd0UAsk0ALNbPSqg9AYjzc+QMwS4ZrgvUOUsmB/pNJCSDZm5ZhLVf3AGD1QQeUsBkCWv+7HacefoATv767bhtxXiwX/Gjb5Zx4m5gipOMQPWfutH0iBVKP4sKBUwChJJ4+ACSgPu8HjmLYvcwhNwMIgDockR4SIKQzKFfMUIypHr9XGz+xr0QXG0kJJ0MAJD1Oiz78CaAC5z8zTsTeYsJJZpISFTGUo66bzjhPK2H+6IOUABTtYKcJUFc/dfcpK+PNUzguqBD9+tG+BrVt2fJxJG3LoDC2/yQKLuRDKEwQEgamPOtMOVb4et1w9vrBgCs/PQWCC7ApNgN6uIPrse5PxxC0J3eNf/jIdGqgmwj6QH7yiDsK4ORzwkB6PMVBHslxJ1gyAFTVXQacBzSo/1ZS1QvA/dJ6HnLCPclPWo+76JAQDKCwgAhY1AwuwwrP3UrKlbWRT7XcvQq6l89AXtVYcLXSnoZNevn4sqe0xm+y9EbTe9Ati0xjIUxIG9jAJ1/NMU5QoDpgdyVg4Eq5GJof84Mdb7BsJ+5YPC3qqGg6PapFx7J5EdhgJBRKppfiR3/+hEwOXoebvnyGShbWpv09YILGCZ4MiHNG8ic/A0BeK7o4D4/8DYbbuAl9am/4sMeyEP+8/cf1YfnkMQJX4LBsd+Awm1+2vOApB2FAUJGacNX7wSTJUjDwoAkS+BIXpRekiW4O/tRuXoWLEU58PW60XL0Knhwcq03i9c7QEMFiTEZqPyYB32HDejdZ0CgQwLTAbZFQRTc7IepMvp3xN8hqzkgwaRSxSPB2yBDlyugL+RgNKWDpAmFAUJGoXBuOfJq4y+jGwgInHNI0sjHOMEFgr4A1n1xB0x51sjn/U4vjj7yOup3n0r/TU8Cr7XNx/ayCxN9GykL9jC4L+khFMBYocA8Q9HUEDMZyFsXQN66AIRAwtdIBi1LSwSafmIDAOiLFBRt8yN3RTDJawhJjsIAIaOQW5Gv6ThJkiCEABvSCnDOwRiDwWKEMEWv2TfYTNjwtbshBHDltakbCKbLvAHuB9qeMQ9uOMSgblNcoqDiIx4Yy7RvS5gsPOQsCcKxL9GQTXS1w2CXhNYnLAj1e1FwC/XQkLGhMECmDEkvY8bNC1C3dQnMeVY423rhuN6FvJoimPKscLU5UL/7JNpOXs/4vQTGsALAca0TlkIbjHbLiJUGjDEIIbDqM7fh2t4z4KGx7YFrON+EwILqhMdomTeQjUMFQgAtj1nguapDpBEOP7wHuiQ0/tiKGV9xQZ+fnmIR5pkKzLUheJtkgA//Wccqe6x+3LnLhJxlQejzqLQxGT0KAySjJL2M2k3zMfv2pbAU5sDd2Y/63adw/d0LEIr2hs5ot+D2730Y+TNLwBUOSZaQN6MYNevnRZ68i+aWo+62xWh46xze+f7zkfX9WhXMLoO9uhAhbwCtxxsQ8kd3v+bXlaBiZR2YxNB9pQ0Blw8GW7zZ4oMYYwj5g3jj20/B3emEOc+CO/794wmPN9ktKF8xEy2Hr6T0PZD08VyR4bkSZwtizsD9QM87RpTe40vL9RgDKj/pRsvjVniv6tSJhgKJJxWG9R81oHArrTIgo0dhgGSM3mrE9u9+CEXzKiINeE5FASpW1qH9TCNe/9snRzS48Wz+q3tgrykCMDgeP9D1PvDnQFGf2s0L0H+jFyd+9ZamcxfMKsWGr92Nglmlkc8FvQGceXo/Tj/xHky5Ftz8N/ejbFkteDjASLIEb69L0/kBQGfUQygCzpYe5CeYazCUyW7RfP7xkG29A/3HDWqDPOIpPYwz9B/Vpy0MAIBsUasa+ppkuM7qEPIy9B9MstqDAYFuWl5AxobCAMmYdV/aiYLZZQAGG/CBP4sXVGH1F7Zj/3++HPUaJrERT/T26kJUrKqDVkximH/PTTj95HtQ/Ik3k7HXFGHHv30MsiH6n4LebMCKj98Cg9WIipUzYa8pjrp/ADDmWhDyBSDpdWASi5oXkIi7q1/jcU5Nx6VDJpYYTqV5A0IAvkYZgW4JslnAMjsExc2QbFEI90lxJwYGuiX0H9Uj1C9Bl8ORuzIIQ/HIE4oQ1OJEkoA+X4BJgLlGgblGAQ8B/YcMibdKBiCZaIiAjA2FAZIRlqIczNi8IG71PUmWMGvrEpz41VsoWVKDWVuXoHh+JYw5ZoQCITS8eRZnnz2IvsYulC2bkbCSXywGqxGFc8rRcaYp4XHLProZskE3YnnggIXvXxu3kVdfo8O1N85g1valCa8T8gfRXd8GAOi+1Iq+5m7kVOTHXWng6Xai/VTm5z6kajqWKPZck9H+rBmBTjnyOcnEYSjjSZf6ybkjl/cJDnS+ZELvu0a1kmD4691vmGBf50fpvT4wCeBBoOcNI3r3G8C96u+BPl9Bwa0B5N4UgPOkHo79BnU7OSXBVsmcIXcZrSggY0NhgGRE6eLqpI23pJNx708/D4PVCCEG33F1Bh3qbluMGbcsxJ5vPZFSCIg6f5wGfoDeYkDNhnkJjxuY0JcoEJQtn4HWEw0oXVwDSRejcRcCbaeugwcHeykO/c+r2PqdhyE4BxsSCATnABgO/e+rKc95mEipDBVMpuWF3iYZTT+zjugB4D4JvoYkXe9MIG/tyO+5500jet8NrxIRLCpM9B0wQDIKFN/uR8svwpMThzz1B3sltD9nRvdeA0IOWQ0Tka/HCARM7cUw1Uyu2hRk6qGBJpIZGrvM9RZD+PDobnZJJ0PSybjlW/ej80JLyoFACSrovdqR8BhjjjlpYBi4t0T0ViPe/f7zcLb1QggxshEXQNXq2fjA419C6ZIaAEDriQbs+dsn0NfcE3Wo80Yv3vj2U2g6cDnpfU2URNsbTzWdL5vUIBCvG55FZvBFk9SiP/kboyft8YAaBuJP+GPofcuI7rf08FzRxbiu+nHIEe6liPr6kFAQ3rvAuiCEyo95qPgQGTPqGSAZ0XmuOeETNYCkX5dkCeZ8G6zFueg834LCOWWRSYKJcIXj6hun4Xd6Ex7n6/eChxRN54xHCAFXqwPeXjde+vOfo27bEqz6zG3QmfSDExzDQcaYY8bW7zyMl770c9hK7Vj80AbkhSdFBlw+XHv7HA7/+LW0VCDMn1mCBfetRuWa2WB6HTqud+LsOxfQcrE17muyrTRx0MHUWfuJCLVioOeaDtwTDo6SQM7SIEru8UWVEwYA7zUduD9Zy8zQvWcsZagZIAQscwIo3kE7GZL0oDBAMsLV3oemA5dRtWZ23KdvLRPulJCCglllePtfnsMd//YxWIpyADB1omF4aGHgPANP5I6GDhz56etJzx3yBnD9vYuo3Thv1IGAMYamA5fU8/mDcHf0QW82xDxWkiVACKz/yp0oWVgVWZkAqMWG5u5cgdJF1XjpK79IOvExkRk3L8Cmb9wLCBH5vqrmVaBmYRVO7DmNIy+fiPvadAeCyTyJUHFpeJyWAGM5R8WHnfC1yBAhwFDKobPF7h3hWhdVxFuhoBmD54oe13+oR/Xn3DBX0zABGRsaJiAZs/8/X0J/c3dU17ngPGp+QDKMMSjBENwd/Xjxi4/i2C/eRF9TF7y9bvTUt6HpwGW42h0IegPoa+rC4Z+8hl1/8SsEPdrWXJ98/G3w0NjeSHuGDEfUbl6Q8HySTkbxgkr178NCEmMMebXFeP8v/gzmAtuo7sVSlINNf3UPGGNRAWfgWsu3LUHVgopRnTsZY2PsEDRZyTkafg85oMvlYDrAXKvAMkuJGwQAwFAytiJRKeEMIgS0PmlGCv+kCImJegZIxvj7vXj5K79E3bYlmHP7MpgLbXB39uP6O+ex6jNbNc0DkGQJOWV2LHl4Ixr3XcTZZw7g7DMH0naP/S09ePtf/oAtf/+g5qWBwwWGDEcYrMYRuxgOl+w6pjwrtv7jQ/jjlx5NOJM9lrl3rgQYi/uz5QrH4psXoPn8jbjnGEtFwqlEbxewzA7GGbtXMRnIWap9pr6xlMNYEYL/xji9tQqGYKcMb4MMy0zqHSCjR2GAaCYbdZhx80KULasFYwwd55px9Y0zCHnj942G/EFceukYLr10LOrzZUtrUXHTrIQT+AZ6EGbetgSMMaz4xC24/t4FvPdvL2ouVpRM8cIqbP7GvZHrpRoIvL0udJwdXL7Y39ytLoOUY59n+NBGLIwxFMwqRfkydZVCKooXVCb8mUqyhNIZ2ooeZYPinT40/sgGoYiYgaBoR/S8ACHUyoSuM3ooPgZThQL7TQHIQ+pDlX3Qi+v/aUOyqoHxJVhGGOf4QIcEc40CMND2xmRUKAwQTQpml2HbPz0Eo90S6fKfuWURVn7qVuz9h2fQfroxpfMdeeQN3Lm4BjqTPqrxGt4gM8YgD+nurl43F5u+cQ/e/KdnR/29WEtyseDe1Zi5ZTFMeZbIdWJJFhD0FiOK5lei81wzAODyKyex+IMbEl5fS+jgIQWVa2enHAbMBdakx3ANSxazZTKhqYqj+k/daPu9GYG2IcMqFo6i2/3IXz8YdEMuhqafWRBo02GgwXYeF+h82YSS93mRv1ENqKZyDvvaAPoOGpBqoz66AMHQvdeI9t9bAAiY6xQU3OyHbcHo552Q7EMZkiRltFuw/Z8/BEOOWR2LliVIsgTGGHQmA7b+40OwlthTOmd/czd2fe2XaD1+LWoOQcgbgN/pBVd4zAZTkiXUbJiH/Jklo/peCueW454ffRbz710Nc751xJLGobQ02pJOxrZ/egimfLURdrb24vhjahnk4UsMucLR39wTs9DQiGsDkPWpZXW91YjcioLE5+UCLRfiDxEMZb+SHbXuzbUKZnzVhdovO1HxETeqPuPG7G85o4KA4EDTT6xDAgMb/FMAHS+Y0XdM3ccg6GBQvOPVK6AKOQZ+pxi812S0/NKK7jen1hwOMrGoZ4AkNef2ZepYeIxGbOCpft7dK3Hs53tTOm9fUzde/7snYSnKga00DwGXD55uJx5++usJX8dDCmo3L0DvtcR1BIZjEsOWv3sAslGvub6AluWPMOox547lOP279wAAp594D652B5Y8vHFw6aDbh0svH8fp372HHf/2MeTXlSQ9b8+VtpS+v1nbliSdrwAGXDiYnhoGseYNTNV9ChgDTJUcpsrYEwA99ToEOuKtOFHLFHa8YIKlLoTr/22D4mGIbtTFsOPjnWeUhg5xhP/etcsM69wQTBXjOKmRTFkUBkhS1RvmJiwiJMkSajfNTzkMDPB0OeEJ1+G3luQmPV6IwWJFqahaNye8NFE7LXMIJFlCzbq5kTAAANf2nsW1vWdhLcmFpNfB3dEXqR+w5++ewN0/+HTcexGcI+QL4tres5ru0V5diGUfuxm1G+cnvV/GGDx9iesvRJ07DcMFA8sLDYEgTP4gvMap88Qa6mfoO2KA42Cc3QsjGLiXofVZsxoERiwdTMdky3CgGMh7fKBWcpxzSwKO/QaUfSB9GymR6YvCAElKZ9QnbWSGb/QzWt5eN4LeQNy1+oDa+Pa39MT9ejzF8yrGXGQoHmOuGeYCG7w90TsZujtGbkrk63Xj95/+X+z8v5+I7JQ48PMdWJb49r/8ASFf8kmS+XUluCO80ZLWKo1+T2pP7mMNBGUuB+5+/ShmX2+HJAQ4Y7g0owxshw6BwokPBoFOCc7TeiheBkMhR86yAGQz4DhgQPvzpiHbCCfnvaRDehr+GCTAVKnAWKkg0CHDe1VOfC3O4GuO/e8y5GII9kqQTQL6opH7K5DsQ2GAJNV9uRX26sK4jSgPKZFNeMaKBxXU7z6JeXevitmVL4QADynoONOEytWzoARC6DjXrKlqH1fibC+XgNYNkmxleXjg8S+h6cAlHPrR7khPR9x7CSrY9fXHMO+ulZh39yrkVhZACYbQ+O5FnH32AHqutGu6vw1fu1vzsAfnHG1XO+BNUpkxnar6u/GVQ7ug5wqk8NwQSQjMbWiD+Dlw9eOV8JVOzERFHgLanzWj/5hBLe8rAVCAjhdNsK/1w/GeaRRnzWCryhlK7/PBWK7gyndzNFxLgOmiU0ygm6HzJTNc5waXUxpKFRTt8CFnEU04zGYUBkhSF186htm3L4v7dUkn4+KLR9N2vVO/fRdVa2bDWmKPauS4wiO9Anf/z2ciT9N+pxdnnz6AM0/vT3heU75FU6M5NACksicCkxiq1s5G4dxyvPTlX8DX6054PA8qOP+Hwzj/h8Mxt25OJr+uBIXhLaKTEZwDAji660RK1xgQr3cgYb0BIfDhM+9CpyiQhj1aS0JABIHKlzpx5dNVo7qn0eB+wF2vgwgy9J/UwX0+3P0vGBDOkyIkwkFgtLP7M0Egd1UQpioFwR4Gxa1t7neon4EHAMkABHoYrv/QBu5jUXMMAu0SbvzKirIPemBfRbsfZitaTUCS6r7UihOPvw0AUSV0B/5+/vnDuHH0atqu53d6ceyXb6Knvg3KkGp+joZO+J1e2GsKo4YtjDlmrPz0Ftz7s89h4QfWwpgzsu574dxyzL1jRdJrD6+OOPCx1qqJkizDnG/D4gfXazo+cp1R7FBory7SfKzP4cHuR/ei/VrmSwMPVCKs7u9GlbMXcpw+diYAS6sfxo7Mr1oQHOh61Yj6f8rFjV9Z0fo7C9znDHGKDbFhf4636HEJZhQo3OpH2QNqjw7X/ADPEHJI6HpV7eHo2mVSg0DM+QwC7X8wg8f5T+G+pEPToxZc+ttcXPpWLpoetcB9iZ4lpxP6r0k0OfXbd9Hb0IFFH1iHkoXqk1zvtQ6c+/1BzRPdkrEU5WDunSsx766VMOaa1fHzcKPv63PDXGiFwWaKO3/BXlWIVZ++Dcs/djPe+Zc/RO38t/RDG0dsFzycEELdEG5Ib8BoqhJKsoQ5O5bh6COvZ24bYqZtsiUAnPzNOzj123fhnze2J/BU5w6Uuvs0HWfsDsJfktmhgvbnTeg7kOq6/4lTuMMHUwUH0wmYaxRI4akVPADc+I0V2nstGByHDMjf7IfztD7+7oxgEAEB52k97DdF9w507zWi6xVT1HbKnnodPJf0KLrDh8It2bEEdbqjMEA0a9p3CU37LkHSSQBjadldDwAkvYx1f34HZm1bEjWmP3SOgjHXoqlhZhKDrNfhlm+9Hy99+Rdw3ujF0o9uRtXaOZpfnw56ixE6swFBd/rfKMuWz8D6L+9ETnl+0mMDbj/OPL0/baEklUDg1yWbga/i+sw20P4OCX0HJqqAkpYlhSP17DFBzhGwrw7AVM4BQ3gTrgMGBNqllM4lAgyeBjlBEAiTgEC3BF+zBMUtQWfn4AGmBgEg+vXh3oWuV9TllOZaKoU81VEYICnjofSuW978jXtRs2Fuwqf2VJ7Q1fF3YNM37kVOeR50Rm2NUsJzpthDoARDUWWaWbhY0qxtS2AusMHV5kD97pNoOXIlpf0HShZVYds/PQRoDC1nnto3ph0QtYg3b+BiQTn8sg5GJf71FaME94yxbOebXP8xPSCJNOwUOBoMkAVylwfQf9IAhLTdg1AYQg6G7j1G9B0yoObPXNDnCTgOGlLerwIAZLO2TZkcBw3oeWNw4qRk5lE9AiNIAr37DDDXjt+kVJIZNGeATKjCOWWo3TQ/YRAYDUknI6+2SHMQ0DInQOu8AR5ScG3v2cjTuN5qxM7/+Dhu+eb9qFhVh8LZZahePxdb//Eh3Pb3D0LSa1/quPLTtwGMxa1iKIQAVzgE5zj95D6ceWpwUqXhfFPM16RKa2XCgE6PPTOXJGy7OjbkQegy+zYU6p/ItzkBnU2g/IM+zP7bfkgWjuSteXQBoZCTofUpNTCF+lLrFQAE5BwO62wFpuqQ2rAnwN3R5+ZelrhHgTP4GtO/VJeMP+oZIBNqxi2LMrb2P6XehGR7BShc0xACVzi4wmEpysVDT30NQggo/lBkS+KB1QwDf1aunoWVn7wVR372etJz28ryIvM1EmncdxFHfron6fLG8bC7bimMoSBuazijVu5lDCwcqrrW56FrfV7G70GXO5EV+BhCfUDTzy1Q+hm4R0LKj/acwXtFD3+HBNksEAqmEgYYCm72gcnqpkvNj8abbyAixw9/fdIrUBaYFigMkAllzM1MF/FodiBMeC6JoflQParXzhlx7qE7EfpdXpjtVpQtrYkEnET3wiQJc+9aiRO/fidqWKFkUTWq18+FzqSHo6ETV984A1Ne8k2IhMLRU982KYIAoDb+L8y7CW/XLMB2zylYPX64LSacn12B9bOuj8s92FcF0bM3lZoB6V5SyOC5qIv6eDR8TTJ0BVxbT0d4WMS+zo/8TervlXWOgoqPetD2jFl94pfEkIULo/x+mYBtIdUnmA4oDJAJ5W7vS7kQkBZjDQJqF7+AEACEwP4f7MKV105hzs7lWPmpLZHli0ODQH9rL3LDk/qG9nQkuxedUY/ieRVoPdEAY44ZW/7+AZQsqgYPKRAAJEnCqj+5DUceSd57wGQJnu6JDwLD9yhwmK04PGd2yufhAcB1To9QH4OcI5CzKAgpxlxA7gdc5/VQPAz6fA7r3BCYDPAg4G2UIecqUPq1PsIOlPkd+Hs6jP08vmYJvgYZicOKAGTAvjII+5qAuq3xEDmLQ7DOd8J1Vo9gtwTJJMB9CC8/TPEemQCTgbx1tJpgOqAwQCZU/WunsPQjm1J+HQ8pCHoDMOaYI8WIgHBxnXDjO5ZAICDQtO8Seq62o/7Vk5Eyw63HG8D+RIo87Q+9Rk6pfdQ9EgNDEFu+/QCK5lUCiA4Usl6HtV+4Hd31bcifWRK3eJLiD6LxvYtxr2M434TAguq4XzfZTJi5tAYmmxGuXjeunWxEKDAxT36Og3p0vGSG8LPwJDagXW9G0e0+5G8OgDF1n4qetwzo3mOCCA4cxyDbOPJv9qP3LWO4QM/AI3BqXeyTh4Bjn5beDTXIDNQkiEXSAbnLBpcPOk9pLaE8ZHiDAUwHVH7cA31BhpbPknFFYYBMKHdHH0797j0s+3D8QDD06RtQx+X9/V688lePw1Zix8IH1qFixQwwSYLjehccjV2YsXnBmN7LGRje+uffR73/2UrtuPuHn4bebIjZ4I92EiRXOHqudaB0SQ1KFsZuqJnEwBUBJRCCUDg4EBUIBkLI0Uf3atrTYOQFgJt2LsfSLYvAGAMXApLEsPEDa3Hp0BVcPFSP7ub4+0EkrEQ4Cn3H9Gj/vQWR/wDhSWwiCHS+ZAaTgfyNAfS8aRxc+jbkOMXF0PXy0MYz1XtLbZJe5oOD9vNrWjkwhHV+CMwgIAIJehv0QOFWH3zX1CbDXBeCfXUQOisFgemCwgCZcCcffxtzdy6HKc8au5ENfy7oDcDncOPKntO4+NIx+Ps8cN7oReuJBvXJmjEIhUNvMaJ4fgUshTmjmpgoOIejsXvEPK9b/+4B6C3GtM1FANRGXJIl3P3fn0b76aaEkyklWULxgkrs/uvfYPXntqOgrjTyNV+vG8cfexP1u0+N6j5W3r4Uy7Yujnxvcrjx0Rl0WLhpHhZumofeNgf2PXsIrRr3TRgtwYHOXYnLAXftNsK2JIDuPfHqByTZ0S9tJlPJYgAQsN+U2kZUkgGwzg3CdSbeplEMCAKWGgVFW6be9tREGwoDRDN7TRGKF1QCQqDtVCNcbY60nNdSlANzvi3hMTyk4MLzh3H8sbdifn1gjB8Agh4/XvnLx3HHf3wcthJ76jfEGC68cCTqU3PvWhnZYXAshg8jDPzdlGdF7aZ5Gm6NwdHQiT9+8VHk15UgpywffqcXHWebNBcWGj5UYDDpsey2xUlDTl6JHTs/vw0v/+g14ErHmLc2Hu6Z/pV4IPcYvNdlKEkmyXGfhI4XzRAJRzDGo5GeXEGA6dQek1T5O5LMRZAEHIcMsMyiegLTFYUBkpS5wIbN37gXZctqI42ZEAJNBy5h3/99CQHX2PZLtxQmDgIA1LX1Gp7yc6sKoTfr4WrrU58Nk4zhx/t69bo5aNp/CT6HGwvuW43Vn9uelhUK8V4vyVLUfId4fH2eyM+792oHeq92jOl+AKBmURVkDbUOBoo5rbtvNf7wf18a83XjUdzafsauU4bIXIKJp6WHIN2TEkcq/6gHutzUfyAhR5L6BZwh2ENlaaYzCgMkIb3FiDv+/WOwFqt18NmQyXlVa+Zg+/c+jF1ff2xMpYnLV9QlbWglWULXpda4X6/dvAArPnELcisLACBqUmEiA8Fm+NN6xao67Pi3j+LAD3Zh9ee2Rz6fSUxSJybG+1lwhePiH4+mfb8Do8WoeatmSWIoqipAXqkdfRhbCIxHX5BCXYBkJXaTnwDpa5wTr9+3LQ5CtvFwaeQ0/i6FA1HZQ17kLBjdZE/ZIhCKO2dAvYZsmxSpi2QIhQGS0Jydy2ErtcecHCfJEgpnqxUEx7JZUW5lgab35LYT12J+fv1X7sScO5aPuDetT/KxjpFkCbkVBVj1J1szVhQpJiHUfR+GhRmucPRebcfZZw6k5TJDhwr6u5wp78lgzbMAocyEAWM5h6FcQaBN0tDYj74xL7nXA9clHTzn9aM+xyAGZuAQAQyeSxYwFHHoCzlM5SGYajg6XzJFr1wcI10uh21REHnrAzCWxg9RgqubC3mvyQBTJwBaZimRjij7qgC63zDG/3kLBvsKmi8wnVEYIAnN3rYUid4oucIxa+uSMYWBkC8Q3lEwfoMrOEfQO/LNaOlHN48IAgNiPfWnhAEFs0o19TDEMnwVhLZrMvAQh+N6BwpnlwMA/P0eXHzpOM48tW90KwWSaL54A55+D8w2s+ZQ4HX6gAxtKcAYUHqfF00/tQJKssZe65K48HHhpYd5G/3IWx9E/oYgbvwOcJ5MtKOfFgIiIEV9bChWEHJICLTr4T439v0xojABc10I1Z/1JC3TEeiU0PxLC4JdslpoCABeN8FQqqDyEx4YCjnyNgTgOGSA4sbIPRwkAWO5AtsiKi40nVEYIAmZ8iwJGwhJliKldlMhG3SoXD0L5jwrPD2uhE/eXOFoOnB5xAZJOeX5CZckAmPr2meMjWn3jlHVG2AMTGJgTMLvPvAfkI06+Ps8mdsKGerky3eePIDtn7kVgou4+x4MHOvo6EPPjV4gzRMIh7LMUFDzOTeaHrGGn7YTkAWgAFqCgaGMo+BmP3JXBCONaNn7vQg5JHgbdBh9T8PIMr6BtjS/vUYqBjJYF4RQ8XDyIKC4GRp/bIXiCR84pKEPdEpo+okVM77mhM4mUPMFN2782gL/DXnIXAwG69wQyh/yUNnhaY7CAEnI3dEPY6457hp6rihwtTtSOufcO1dg5advg8E6OFbNQwogjdyAZ6ARPPPUvhHnmbNzueb37lg9BFqe3MfcuzAKkiyhYFYpKm+qg7kwB4wB7Wea0J1gzsRoDB0qaDrfgl0/3oOb7lyB0hnFMY8f+G9x8IWjabn+a23zsb3sQtyvm2sV5G/wo+fNBGPskoBtURDeazooLgx7uld/OezrAyja5oOkR8zqhZIRKLnfi+s/sALKJJ0kJwkUbvVD0gtYF4RgLNE2r0J92mexez24um9C/zED8jcGYCjkqP2yC75mWd18SAKss0MwFE/k3g5kvFAYIAldeuUE1n3pjrhfl2QZl185qfl8c3Yux7ov7Yx8PNDrwGRpsKhQSIEQgKSTEPQF8M6/Ph+zIbRXFaYcBATnagCRJfUpWOMkw4lw89/cD66ob8TqBMobeOu7v4e7oz8j12utb8eLP3gFtnwr5q2bjYUb58NoGVx77u73YN+zh9B84QYAdffCocsLhxceGl6SuKG5GDOqOlO6p7x1AfS8Y4wzXKA+vRbe6od8tw+dfzTBeUY/opu7b78RzmMG5G30o2ibP+YTbsfzZkCZTMsEozGDQNG21Mv+9h/XJ52f0H9cH1mOyBhgrlZgrh79hGAyNVEYIAld2XMKc3YsQ8HsshENp+AcN45eQ8vhek3nkvQyVn5qS8yvDTyBe3vduLL7JGSjHo6GDjS8dR4hf+xx8qAvEG7YE7+JR4KAEGCSBDbwbUze9/6IoT/zgrpS7Pj+x/DiFx9B0O2HpJdRu2k+ajbOh95iQF9jFy6/cgKOhtQa3OFcvW4c3XUSx3efRuW8cpisJrgdbrTWt2vexjld9PkClR/1oOXXFoCLwSfccJd52QNemCrVwFTxES+CDh+aH7Ug0CFj6H9g7mfoecOIQIeMio9Gd68HOiV4r07mt0KBnFGO13MfQ7I5F4p3CvxDIBk3mf8FkEmABxW89s3f4qY/3Ya625ZE1qOH/EFcevk4jv1ir+bx7IqVMyMb/MTCGIOlwIbmw1fQea456fka372Iui2LtX0jGPmEn+oM+okm6WRYi3Mx+/ZluP7OeWz/3odhryqMrDwoW1KDBfeuxsnfvIOTv35nzNfjCkfTuZY03PnY2BaGMPMvnXAcMMJzSQfBAcvMEHT5HH1HDOh81QTZImBfGQAYRgSBQQyuM3p4Lutgnas2roEuCR0vp7Kj4XgTAAPyN49uMyBDsYJQX4JAwITmIQcyvVEYIEkFPQHs/8+XcezRvSiYUwZwga5LNxD0pLbUyGS3pPW4pgOX0NvQAXtVESTdJB3rzYBZW5dg1tYlyCnLAzDYezAwCXPZRzajv6VH0wqPZBsXTRaGAoGSO33AnepOhC2/tMBxwBhZHaD0C7WEcbJ8Jwk4DulhnRtC/3E9Wp/M0JKIMQvPZ5GB8g97YCofXYNtXxeApz7BSgbBYKykIQEyprnSJNv4nV60HruG1hMNKQcBAHB3ahvrdnf0aTpOcIHXvvk79FxtD3/Mx70be7wxicFcZFOXPMZZgSE4x5KHNozznY2frtdM8FwJP8dEJsaFJ8nx8N/j4QzBbhn+VkkNAgKxJ9dNNB1QdIcfdd90Imfx6Jf06XKS/XsQcF+iZ0JCYYCMo7aT1+HpcsYdVuCco7ehEz0xNsLJm1GM0qW1sIWfhgf4et14+Su/wKvf+DUa3j4/YZP9UiGEGPVSQa5wKIGQuvoiDiZJyKsthjnfOtpbnLR4AHAcMCRowJP892cCcg5H7z5D+NDJ+PsiIOkFCjb7oRtj1T/3ed1gbYGYGHzXdZpLQJPpiyIhGTVriR0L7r0JM25dBJ1Jj77GLlz841Fc23s2ZmMnuMCBH76CLf/ngXCRoegKexACh/731ajXVK2djZWfvg15NUWRz7WfbsThn7wWFRraTzei/XQj8mqLYa8uHL+KgRoNfH+STkbriQYUzSlXd0BMcd6CJEvoa+hMurETgEn3M0gHf7sM4R9DVULBYF8ZVIcUhhfXSYuh+w+MvmYB9zI4z+qRu0x7kSkeAJyn9Qh0SJCMgG1REDxRieGhrw0C0++3haSCwgAZlaL5Fdj+zx+GbNBFxqwL55Rj01/eg9pN8/Hmd34PoYwc52w+eBmv//2TuOmz26IaeMe1Dhz6yWvoONMU+Vzt5gW4+W/uU0v0DlG8sAp3/PvH8cpf/mpEL8Lef3wGO77/UVgKcwCW2rLAoUMMqb4u2fHNh+rhuNaBhrfV1RGLH1qPWVuXQGKy5msJztF68jqu7j2LytWzEx7r7XXD0+3U/D1MFdp+VPEOEjCWc+QsDqIz5UmDQ38HtVZEHFtFw86Xjeh4wQShAKZqBfkbArDMVocMpGHTAJxndWh70gLuh9rfK4CuV00wVoTCQyfxSSY+5h4IMvVRGCApk/Qytvz9g1FBABicyFa1Zg4Wvn8Nzj4du47+jSNX8cKRn6JgVilMeVZ4upxwXI9eDifpJKz78x0AMKLg0cB1Vn9uO179xq+jvuZqc+CFz/8Ms7YvRd2WRTDYTNBbDDDaLQkr6w3FgyHIBvXdVktDr6UxP/27d9FztQNLHt6ApR/aFK4yqL2xCHoDuPTSMRz/1VsAgNV/ug2GHHPMOgmCc1x48ciotzSezAylCiQTB/eNZoSTofheD5hOrc3vPDmyJkGi1+Zt9MOxzxAOp5nuVmdROwl6LjN4Lg0mAGO5gvzNfuSuDMJ7TcaNxy2RioFDG39/qxzupIhzz0wgb20QjFqCrEe/AiRlNRvmwZyXYDyaAQvuXY1zzx6MNEhMllC+YgYsBTZ4e924cexazLkBAyrXzIYxN/6qAkmWULqkBrayPLjaHFFfC3r8uPD8YVx4/jAAQGfSY+d/fhL5tbEr60VuO9w4S3rdiM+NlhACPKSgZFEN1nzhdhQvqEqpoqG7y4m3vvMsehs6oPgHJ5K9+Z1nse07H4oMPQCIbIHceqIBZ5/eP6b7nqwkPZC/McmmOgm0P2tBzefdyN8YgPO4IfkLIlUM/Sh5nw85i4Jo+71ZrfOfUcMa72Hfq79NQttTFniv+xHoSlA4I/I6oc4dGBp+mICxjKNwa2Y2nCJTC4UBkrKi+RVQQgrkOGPSjDFYCnNgLrDB0+XEjFsWYvXntkdNaPP1eXD4J6/FXf5mK7Fr2obYWpw7IgwMpwRCMCUIFrHuP10YY5BkGTf96daUzi+EgL/fi11f+yU8XSO7+zvONuPFLz6CBfetwcxbF0Jn1KO/pQcXXjyC+t2nYg7RTBeFW/3wt8lwndUPaeC0Pa0HuyQ0P2pF7ZdcKLnHi44XzEleq34+f0MAjAGWWQps80Po3Sdp7FVI114Hw0+rfr3voIb9ISSBnGVBKB4Gz0UdAAbJwpG3LoDCW/0xSzST7ENhgKRMKELT2xtXuDru/9f3jVjyZ8w1Y/M37gWAmIHA7/Rqmlznd3qTHpNbVTihM+tTnSQY9Phx+dWTOPPUfvgc7rjHOW/04tD/vjpi0uV0x2Sg4qMeuC/o4DhkQLBLgmQW8LXIyUsKCwb/DRnuSzrkbwzA3y6h72DyHgIxdB5fSsPrsYJKsoCQQoBgInkPCQNks0DFw17wAMCDDLJZDFbiJAQUBsgotB67ikUfWBv364Jz9DX3wN/nwU1/ujVmtzhjDIIL3PQnW9Hw1rkR49tN+y9DCYSgM8YumDJwDS2ld0sWT43x8AHPfeZH8Dk8E30bkxqT1MqEtoWDQyfdbxrQtUtDESFJwHlKD52dQ5/PkbThlQX0BYM9Lea6EHrf0/I4PdCopxIGU5zIJzT0iiiAoSi8x4UBkAw0WZCMRNmQpOzG8WtwNHbFXevOJAlnnt6PkkXVsBblxu0WZxKDucCGsmW1I74W9Phx+on3Yr5OcAEwhmM/fyPpveptJqz69JYpUYxICAFna++EBAHD+abkB01yBbcEULhdw/g3B5yn9Lj+nznoemVgmCDO74ckkLs8CHlIxrAtCEFn5+pTeVzJhx6G0xcoyL859bLDzIAEtQQEmAzkrki9SBjJLhQGSOoE8PrfPQl3lzNcQEd96hgIB6ef3Iere07DlGiS4RDxjjv9xD4c++WbCPmD6kS88Di4Egyh5VA9DDlmyIb4nVuLH1yPD/7myzBYTVOiGBFjLPI9ktQxBhRt80OXy5H4CZtFd/tHGudhr5EE9HkcxXdGBwwmA1WfckMyi3AgEMNen1rwlEwcRXd6MfMbLhRt8w85rxYCljlB6PP4yEDA1EBScp8XsvYpMyRL0TABGRV3Rx9e+PxPMfOWhajdvAB6ixGOhk5c2nUcPfVtAKB5nXusCXIDzjy5DxdfPIqZWxZh0QNrkVOWD0mWUL6yDlVr52D157bjne89hxvHrkW9bsnDG7HiE7eM/hvUIJVVAVrZqwphK8+Dq9WR1vNmk7yNfnS9YkrSJg//7zbQ3a42oJJRwL4mgMItfsjWkScylnPM/AsX+g4b0H9CD+5nMJQqyF0eQNsTlhjnj4/7GLp2mWAs5bDND6HqMx40PxKuGTCwXDAB9wU9Zn7DiZ43jOg/aoAIqccbKxQUbfNHDaUQEg+FATJqij+E+t2nUL/7VMyvd55vhrO1F7ZS+4haAYDa3e/p6kf7mcaE1wl6/Zh9+1JYi+0AoivrGSwGbPn2B/HyV3+B3qsd6rLG+9Zg+cdvTul7SbVhz+Swg6Ugh8LAGORvDMB1Vg9fkzxscl2yiXkMYAI5q/zIWRiCbUEo4SQ7nU2gcIsfhVsGu/bdl+PtmJiIGkQ6XzLBOs8Fc7WCum+40HdUD9dZPbwNic7JAAVwndWh7P0+lNzlQ9AhQTIK6PMEBAdc53ToO2pAqI9BZxew3xSAdV7i741kH/p1IJkjgIPhme4DQwmRL4UnDB78391Je1UrVtWhaG5FzGWGTJLAmDokAADrv3Inbvrs1hHHxb1FLuDpdqb8hJ/J4ODtcaV0PIkm6YHqz7pRcKsfkklr5cAwweA8asCNX1lx7T9sCHTHfotUvEDvewY0/9yCpp9Z0LXbiKCDRZ7KUyYYAh3qBkoAIFsFCm4emAORvPyy86S6IkIyAsZSDn2eAA8AzY9Y0PKYFa5zOviadHCd1aHll1Y0P2oBp2kEZAgKAySjbhy5itf/z1NwDnvSdbb14o1/eBrNBy8nPUftpvkJN+aRdDJqN81H5drZmLNjORjTXt2PSQxHH3kd3h7XiMCSLv5+r6a5AFzhkd4UMjaSASi+w4/cmwIpjL+HhXsTgl0Srv+3Fcqw1aveJhlX/zUHHS+Y4L6og6dej+43jLj6rzkIdkupX28IxRX9liy0bk0Q49er/QUzPFfDnb8DNRHC35vnii5cY4EQFQ0TkIy7cfQq/vAnP0bh3HJYCnPg7XGh6+INza/XmwxAkrX6kk7G/LtXgSsKJFlbdTghBG4cvYprb54DD3Hc/M37NQ8X8JACT48LthJ70mPf/t5z2PLtBwHo4hZRElzdyOjoo8lXSBDtgt1Syqv1BqkbBjX+yIbaL7sg6dQegeZHLeC+YUsGBQOEQMcfTTDPUOC9Lo9qIySdPbpVN1UOTIZMPLxhnhk9LyDkYug/qo9fg0Aw9B3Vo+gOH+1LQABQzwAZR92XWtG0/1JKQQAA+lp6Er6hCyHg7upH0bwKzUEAULv6baVqYz7vfavUnRS1VAcML218799fSPjEzxWO9tONaDt5HYd//FrCCZXOVgde+9YT6DjbrPn+02mq7E2QKskoxryNQKBdQvceta5A/1EDuJfFaWQZwADJwqHLTbBcMRYmYKwKwVg6+PvkuyGh9QkzkhYoYgKF26KXJHqvaggjnIXnIxBCPQNkCqh/5QSWPrwx/gECMOaY4xYoSkQ26JFbWYCypSNrHYy4jBAQXP3fO99/Hu2nm3Dqt+9i+cdGTlbk4Sf9q2+cwX0/+xxyqwojcwd4SEHzgcu48sZp6EwGuNoc6DzfkvK9k+RylgThPJGowqCWan8Mjv1GFG71w3UhyVsmZ/BeUWf3X/1ejrZufiYACSh53+ASRl+LhMYf2SASLgRQf59K3++FPKwGktC6b0MWrmR9pn/lRN/CuPuWhmMoDJBJz93ZjyM/24PVn9sOznnU7oMDm/PI+tSfcATn6K5vRd6MxBsYDei91o7G9y7h8isnIpP8Tv32XfCggiUf2gi9ebDR8XT049QT72HN52+HFL63yEZIOhnVG+bB2+fBwR++kvJ9p9t07RUA1AJBxjIF/o5YewkMrQuQuPHkPoZAhwTBkfRYwQGdVcBQosDfknx1gWQSMBRz9B/VgzHAVKOg43mzGgTiNuoC+hKOsvu8sMwaOZ/GVB3S8H0JmKrjz8UZT9nYQE82FAbIlHD+D4fh7uzH0g9tRMGsMgDqvgR+lw+2EnvSDY1iYZKEiy8ejTTWyZz67XtofO/iiM+feXo/Lrx4BBU3zYLBaoSz1YH209dxyzfvh6SX4qyCYJh310qce/bghE4YnM5BAAgXCPoTN1oes8DXpBsszMMZJItA3toAevaaNJ/PXKPAe1UXv5FmItwQA3lrgmh/LvnvFvcx+Bp18DXL6DtkhHVeAN7ryd6aGUru8sUMAgBgKBCwzg/BfUkXe7hAErDOC0Gfn7n5AtTATy0UBsiU0fjeRTS+dxGmfCtkvQ5Brx8PPfm1hOP8iSYEnn32ANpOXofOqEfQG4h6sh9OCYTQerwh7tdDviAa370Q+VhnNqB6w7yoXozhuMIxc8sinPrtu3GPyaSxBoG+WVNjuztdjkDNF93wNshwX9RBhBhMlQpsS4JgEuC9rlMb+AQkM4ehlCPPHEDPm0bEfeoWDPkb1TV7uasCcBzUw986vN4BMNgrMWT+QbjRdl/UMtwlEOxJHIDLHvCi8UdW9bhI8SJ1DoW+gKPsgeSbfMXjuSaj9x0j+i6r/2bc1WZ0r7HDVUelDuN5rW3+hF37W4uSH0NhgEw5vl51Jz9zgS3phL9YXxdCwNvrjszcD/mDOPvMASz76ObYx3OB888fRtCjvW68wWpMGAQGzqu1ZHO6ZaJHwFk7eUs+MwZYZiqwzBz5JF31GTeu/ZsNIYeE2N3qAvkbA5B0gFQgUPagF21Pm9Wx/oGn7vDugXkbByv+SXqg+k/daH/eDOdJ/ZAn9CFBIPbdavmOIJsTP9XrcgRqv+RC3yEDHIcMUJwS5ByOvDUB2NcGIGvsEBn+hF9wpA+Vr3ZBSIAcrheSc9WD3CsetN1SgM5N+dpOPAVMZAM+3igMkCnL3+9J+kQfC2MMlgIbypbNQNuJBgDAqd+9C5Pdgvn33BRV00DSyajffQLHf/lmavfm9EIJhiDr4/8TYxKDp7M/pfOS9JN0QM0X3Gj6iXXI0zZThxQ4g21xCIW3DQZB+6ogDMUcve8Y4LqgBwRgqlaQv9EP26IQhuZJ2QyU3e+FoZCrDXJ/KrsYxh/zZ3oB64LksxNls7qBU8Et2ioMJevaN7X7UfFql3oPQyYfDpRWKHurB+4aEzw1k6+GQTY17EM1NGubE0VhgExZPMRx+dUTmP++m1KeM8AVjsI5ZZEwAAEc+tFuXHjhCGZtWwJLUQ68vW5c2XMafY1dKd+b4g/h2t6zqLttCSRdnHtjwJU3Tic8T8GsUpSvnAkmSei60IK2k9dTvpfhpvs8gdHQ5wnM+KoL/ccN6DumB/cw6IvUp2jr/JGle801Cswf8QJI3NUecjM0/diKQOfQrnqt4m9PXHibX/OTvRZax/cLjvWrC9LjrEIQElB4pG/cw8BUb+i1NtiZRGGATGmnf/ceqtbMhq00L6VAwBjAgyO7jPtbenD8sbfScm8nf/MuqtbOgcFmjFn/4NRv3oW3O3bpYVOeFTf/zX0oW1obqWUgyRL6mrrw5nd+P6qAAoxvEPDXTK16t5IRyFsXQN669N13+3MmBLqkBKsC4hEoutOHntdN6oZFklAbYFkNAgVbUt/qOJZUJ/lZmnxRPQLDMQ5YmzRsIz1KU6HRnwwN+2hQGCBTmr/fi11f/xVWfOIWzNq6JLKlMQ8pYLIUd04BkyQ0H76S0Xtzd/Rh19cew9o/34GKlXWRz/scbpz63XtoOnAZ9poiuDv6EPINdvlKehnbv/dh2KsK1I+HhJycigLs+P5H8eIXfgZveO6EVlOhR+CZ/pV4IPfYRN9GWgT7GFxnElQBjEcSsMwOofCWAPLXq5suBR0SZCtHzuJgWrYjHvVMfw15WySpFqrVZGn4p2rjDgDGRu1DqBQGyJTn7/PgwA924cjPXoetxI6QL4Dq9XOx+nPbYx7PFY7mQ/VwtvRk/N6crb3Y860nYCu1I7e6ECFvEOZCG5Z+aBPWfOF2AOoExit7TuPEY2/B7/SidtN85MepfSDJEgw2E+a97yac+JX2Hox0B4GpspJgIvlbYq0iSEZAlyNQ9gF1+EEyALkrtG5QkNxYl/v1z7HC1BGIu/2CYED/3NTSymRo9Cdbg59KI54uFAbItBHyBuC43glArUtgLbFj4f1rIr0EQuGQdDI6zzfjvX9/cVzvzdXeB1d7H+a9bxXW/tmOqE2RdEY95tyxHOXLavHy1x7DzFsXgSs87rCHJEuo27pYcxiYCj0C01LKD8gCxmoFVZ/yQGdN//r/dKz771mRi+IDDkARIwKBgBoGelbF369jIhv+iW7wJ6KBTwWFATJtHfnpHtTvPok5O5bDVp4Hf78X1948i9bj18awec3omfKsWP2n2wCowxRDSbIEW3k+ljy0AcZcc9L5DwZrGmePkYwwzwiByQJC0ZIK1JLElR9LfxBIZ/GfUK4ODQ+VYcZTbUBIDJQtUPdpkoDG+8vgL4pu9MYzAExUgz9ZG/qc69p/lygMkGnN0dCJwz95baJvAwAwa9sSIEFdBEmWMGfncjQduIzC2WWQdLGr1wnO4WrTVrWQegUmjmwG7GsDcOw3aBouqPioG3p7+oJApioAumdYcOGLtSg42Q/bNS8gAHeNCT0rchHKGWxSxiMEjFfjP9GNfSqN+mhRGCBknORW5AMi8T9qg9WE6++cx6ytS+IfxBguvnQ86fXGMwiks+DQdJpEWHynD8FuSa0qKA0UKYpeLmgoVVD+IQ9M5enZNWg8ygArVhmdG/LRuSG6wFCmA0CmG//xbPTHo4FPBYUBQsZJQEMFQ8EF2k5cx+VXT2D27ctGrIbgCkfn+WZc2XMq8bWmeI/AdAkEkh6o/KQHnss69B3RI9grQc4RMFeHYCjlMJZyGIqmTgiIJZMBIJONf6Yb/olu7O1XUlt+SmFgEpjqb9xEm/qmHiyK0/UPqA190/kWeOrK8Nbu0+gJKFh660KYc9QCLkF/EBf2X8aRXSegzK7I+P1qXTEQq1dAa42B19rmY3vZhZhfG2jcpnooYBJgnReCdV7C/YhHbbqFgEwEgEw1/OPZ4KfauKdKcxigBouQsels7EbT+RZUzisfsW+BCNd4P7EnXJFQAKf3nsOZt84jv9QOJklwdPRBiVEoaTTStTRweBBIFgIamosxo6ozpWukq7FLV6jIpt34puJTfyaf+KdT4z8cEyLJIGbY1i3fy/S9EDLt6Qw63PqRjZixpAZc4RBCQNbJ8Ln9ePM376L5wo1RnXe81/2PpTcAQMxAEK+HgKTXdJndP926+TPZ+L++92+SHkNhYIqioi9TW0F+LmbXVUKvk9Hd04fLV1qg8PSMHaeblsmBoyk9TIFg9CZDoR5gfGbzj8ekvokY3x/PJ38tYSBjcwaosSIkvp7efhw6OjE7FqZz5v9Y9h+INWSQaA7BcJOlQZzOxnPd/njN5J+oiX3j3e2fKs1hgBp3QsYunQ3xREvHRkTxAgFJr4muvjfUeK/Zp8ZfG1pNMIVNp4aFTA2Z2IlwNJMKp4rJ1Ahn2kQX5gEmdjnfVGv8h8uKMECNJiGTe0vhdAeCbGqEM2kyNPADJnrd/nBTvfEfLq1hgBpdkkmTuTEjYzfQgMcLBdTAJzeZGu9UTLaGPpbp1vgPpzkMUEM/+VDjSKajbKk3P91NhQZ+wHRv6LXIimGCsaJGl0wFEzHuPpmf1qmxH7up1KAnQo19clMqDFCjPLVM10lhZNCMqs4JDwTTqdGfLo3veKFGfiTD+aZRvS5tYYAa6vFHjS2ZDAZ+D6dCtTlqbCcXasxTN9rGPhnNYYAa+/ioUZ4+qAKedsPrAaQrFKTzSV9L42+zmrF0UR0qyosguMD15nacPX8NXh+951FjPf4y1dgnM6WGCUaDGurMoYYzuw38909nKBhLEBjNU/+cukrcdft6MAZIkgQhBGqrS7H+poX4/R/fQUtrFzWIZNQmqmEfjUkVBqjhTg01xmQySFcoSDUIpNL4x2rQ88vycPft68EYA5PU1VKMqX/qdDI+cNdmPPXdP8Cb0l2RqWoqNdyZMOYwQA14bNRQZ85U399+uhi+lW+iUJAoEGgJAak+9Wt5ml+0Wb3PgSAwlCRJgB6Yt242Tuw5k9K1tdCb9JhzUx1ql1RDr9ehq7kH5/ddQm+bI+3XSpdsbyynO81hgBr92KjRzzxq/KeveEEgE43/UIbzTaiZex8kWYp7DGMMNTOKcS7NjWBebTG2/5/3w5RrUa8jMRRVFWDhpnk4+ugbOPvMgbRejxAtJtUwwWREjf34o8afpGI0QQBAwiAAqGFA0iU+JlWSXsa27z4MY445qkdC0skAgFWfuQ2Oxi60HKpP63UJSYbCAKjBnwwoAJABY50LkMjQru6O8y2oWj0r0hAPxxWOznMtKZ0/mdpN82EpzIn7da5wLH5gHYUBMu6yJgxQgz+5UOM/PaWy/fBYVg6kY4b/hReOoGb93LhfZ4zh4kvp/T2tWDkTPKTEDSCSLKF0SQ0knQQe4mm9NiGJTOkwQA381EIBgCSjpVdgtEFg+AS4thMNOPnbd7Hsw5uiGmgeUsBkCQd+uAv9zd2julY8TJIAlnyfFyZLmLFxPubeuQI55Xnw93txZc9p1O8+haCHljqS9JuUYYAa+elhIht/wQHPZR2cp/RQfAyGIgX2NUEYCulpaypL95r/k4+/jc5zzVhw72qULK6G4AI3jl3F+ecOofN8eocIAKDzQgtmblkU9+uCczgau7Dl7x9ExYqZ4AqHJEuwFObips+WYsF9q/HKXz4OT5cz7fdGslvGwwA17NPbZHzaVzxA8y+s8DXqAEkAHICkQ8+bRhTd7kfhVnqyGk/pKlM8liCQaFncjaNXcePo1VGfOxVXXz+DlZ/aAp1Rp/YSDMMkCZ4uJypWzgQwOMlxYLKhpTAHt3zz/dj19cfG5X5J9kgpDFDDnr0mY6Mfz43fWOBrCo/J8nCXbLhDoGu3Cbo8Dvuq4MTcHAEQe75AoiGC6VIFMOjx481/ega3ffuDYJIYHJoI9wBcef00ajbMixkUAHXVQfGCShTMLkNPfdt43jqZ5jSHAQoC2WEqNfqx+FokeOr1CY4Q6H7DiNyVQS1DtykRAhAhgMkAS++KtKw21iCQzmI5xlwzdCY9vL1u8KAyqnO0Hm/AC3/2CBbccxNqN82HZNCh92o7LrxwBJ5uF2ZtXZLw9UIIlC6ppjBA0mpSzhkgmTOVG3shAH+LhJBLgi6Xw1jORzTorvP68NBAvJaeIdglI9jDYChMzw52PAD0vmtE734DlH4JkARsC4Mo3OKHqYrmKIzFZAkCFStnYsmHN6F0UTUAIOD24/Irx3Hqt++NakKfs6UHh360G4d+tDvq80XzK5K+ljGG3IqClK9JSCIUBqaBqdzAa+W6oEPHH00Idg4uyTKUKSi9xwvLrMEnNKHxYU2EGICxhwEeAJp+YoWvRR48HWdwndPDdU6Pyk94YJsfGvN10kUIAGLy9VzEGiKYDEMDeosR6792F2o3zov6vMFqxIL71qBi1Sy88he/ihkI7DVFWPTAOuSU5cHb68KFF46g42xzwuv1Xu2A4DzuMMEAW1leyt8LABjtFszevhRF8yshOEfrsWu4tvcsQn4aNst2FAYmmWxo2FPlPKvDjcctI9ruQLuEpkesqPqMG9bZagowlSsJegVUzCCgz0/PE3v3G8ZwEBh2Ta6GjdbfWjDrb/shpW9X3lHxd0joecsI50k9RJBBl8eRt96P/A2Bcb83LfUF0hEExtorYLRbsPM/Po6cinwAg5sYDZBkCfbqQix5eAOO/Xzv4BcYcPNf34cZNy+MOn7GzQvReaEFu/+/30AJxA6ISiAErnDIScKAvbow5e+nau0c3PzN+yDrZAAMAgK1m+ZjxSduwZ6/fQI9V9pTPieZPigMpBE15OknOND+B3M4CAxrcIXa4HY8b8aMr7vAGGBbFIJs41DcbGQDDQBMIG91ehpAoQCOA4bY11EvBu4XcJ7Uw7564p68PNdkND9iheCIBKWQg6HrFROcp/So+ZwbkjEz19aykmB4r8Bk6BEAgLVfuB228rwRIWAoSZYwd+cKHP/lmxBc/T7W/NmOEUFgQNG8Ctz2Dx/Ea3/z27jn9HQ7YStNfF1zgS2lwkT2miLc+rfvB5OkwR0aw/+eDDlmbPvnD+G5T/8IQffk+NmT8Zc1YYAa6qnJc0VWx+HjEQyBDhn+FhmmKgVMBio+4kHzo1b1zTnSSyAABhjLOYp2+NJyb6F+Bu5N0t8uAf5WGcDEhAGhADd+bVGHT6JCCwME4L8ho2u3CSXvS/1n8kDusRE7F04WY+0VMOVbUbNpvrp7YbJr2Uww2S3w9roh6dRwEA9jDGXLamEtzoW7sx9MYpEQMaDz/A3klOUnvKas16FkcQ3aTjRo+n4W3LdavX6sHRplCUabGbO2LsGFF45oOh+ZfsYlDFBDTEYr5NA2uB10MJiq1L9b6hTUfsmldouf0kOEGORcgfz1AeRv9KftKZglWrQwQAAhNwMPYEKGClzndFBcicOU45ABRXf4IGn5fsZoLCWItUrHpMGCutKkGxkNFfSpYW/mlkWaNkDa9t2HYSvLh6yX4Wxz4OKLR3DhxaPgQQWd55pQl6Aw0QC9RfvPsmb93LglkNWbAqrWzaEwkMU0hwFq0MlEkG3aJvkNP85YxlH+kBdlH/QCCsAyEHt1NgFjZQj+GzHmDAwQDM4TBrjO65G/wY+i7X6wBO/J6ea7ISdZXQGIAEOwR4KxdPxXPkzWIQKuaPtZcM7RdqIBIW8AABJuQjRUbmVh5CndVmLHqs9sRdW6OdjzrSfQXa9t7L6/uUfTcYC6W2IijDHoDFnTUUximGRzigmJZpkTgmTmiD/zX0CXx2Guib2MgLHMBIEBBTf7E8wZGCT8DD17jbjxO7M6o3+caA0emfwZjad4vQJ5M4qx9os7sPP/fQLb/+XDmH/PTdBb4ncRdZ1vQTDcwMcjhABjDDyoIK9WnRvRc61D030O7a5nEgOTGEoWVmPxg+vRdaEFjsauuIGEKxyd55vR19il6VoA0H25LWHA4QpH16VWzecj0w+FATIpiBDgbZDhrpcRcjIIDrgv6dD7thGW2SGMmDyovgoAQ8ld3glZKidCQO97RmhfosjgOm2A48A49MeH2RYEk6yuENAXKdAXTN96CIsfXI97fvRZzLljOYrnV6JsSS1Wf2477nv088ibEXuCY8gfxPnnD48Yzx+KMQbGGCpW1eHuH34aVWvnoOVQPUK+AMQoEp8kS5h39yowiWHf//sjuMJHNOBc4VD8Qez/wa6Uzn3hhSMJhy+YxHDp5eMp3zOZPigMkAklBNDzlgH1381B449saP6ZDVe+k4PLf5+L5ket6HrNCNeZcOMpDbzBqn/KFoHyhz3IWTox6/j7T+rV/Q9iBpV4BDr+YMH1H1kRcqa5BGIMpkoOc11wyM9uOIbCLf60V2OcCLF6BarWzsHKT28BgMiY+cCTuDHHjG3feThuF/rJx99Gw1vnAKgbCMUj6WQwScLN37wPxlwLDv1kDxhjowoE5nwrjHYLui7cwK6v/RIth+sjgYQrHI37LuLlr/4SjobOlM7btP8SLv7xaOQ8Awb+fuhHu9O+QyOZWqZJ5yCZqjr/aELvu8O7axlEIPxGOvSpVgD6QgX5mwPQ2zmsc0MZ794O9TP4mmWAAeZaBbJl8A2+75ABYELTMMEg9Vhfo4ymR6yY8SVXxr+Hyo960fxzC3zNQzduAsAZCrf5kDsN9mmINzyw6IF1kbr/w6m7AeagdtN8XNt7dsTXBRd45/vPo/nIFWz+q3sSXp9JDLJOxuztS3H2mQOQJIab/nQbdMbBXqCBcJBoySCASJnj3qsd2PsPzwyuVnC4x7T07+D/vIr2M01YcP8aFM0pg+ACrccbcPb3BzWvSiDTF4UBMmH87VKMIDAgxhumYAh2y9DncdgWZLY3QPGo9Q2cp/SDjb0sYF8dQMnd6sz7oENKMQgMwRkCbTKcZ/XIXZbZxli2CtR80Q33JXVLZ+5j0Bdx5K0JwFA0ccMD6Zo8GC8ISDoJpYurE76WhxSUr5gZMwwMKF1aEzdQRGMoml8JALj08nEYbCas/NQWCC7U3ohkIUDh6L50AwFX9DLPgMs34nPDGWwmmAts8Pd54OvzxD2u4a1zkd4OQoaiMEAmTN8RQ9KZ7iMJ9J/QZzQM8ADQ9FMb/G3DGnuFoe+gAcEuCVWf8UCXwxFyMKQ2TDAEUwsSZToMAGr5Ydv8UGZLIysC1Te6YPIH0ZdjQUdhbtSXM7GsMOEyQi1jH4zFbeQlnYS1X9yB2bcv03QvQgiIcLd75ZpZWPkpdXgi1tr+mNeTJZx+cl/kY1OeFXqLAd5uV9xywbmVBVjxyVtRs2FupITxjWNXcfyxt9BNEwJJCigMkAkTcrBRbA/AMjrWrrgZWp8ww98qIV7vhKdeD9d5Hew3BQe3Sh4NwaB4p8FgPYD84/0oe7MbSzxXI59rseXjyUXr0ZBXkpFrJqsnwIMKeq91IK+2KG6tfyYxuDr6YK8tht5sgKvNAZ/DDQBY96WdmLVtSdIn+qHnunHsKupuW4yNf/G+pMercwGEurqEAUd+sgfNB+sxe8cyLP/oZliK1DClBBVcee0UTjz+duTeALWq4M7/+wnoTLqo769s2Qzc8e812POtJ9B+ulHTvRNCYYBMGNmqVgVMNRBIxsyszQs6GBp/ZEv+tM8E+o4YUPEhD3r3GRDolGL0boTf4SN/xiAJGIpGtw3uaAgBeC7p0LvfAP8NGcwgkLs0iLx1AehyR/8zLTzch4rdI5e5lbsc+NLhV/Bfa+5Eo71oLLc+gtbCQuf/cAgbvnZ3zK8NLA1c+vBGLH14o/o5ztG4/xIu/OGw5h4B9XUCvn4PuMKx6a/u0TR5kIcUNB++AkdDBy6/cgKebidu+8cPomr17KjXy3oZc3YuR8VNdXj5q7+Er1cNBGv/fAd0Jv2Ing1JlsAZsOHrd+O5T/9v3H9feosRM29diNyqQgS9AVx/53zKExPJ9EFhgEyY3OVBOPanXg7QtjAzXd2tz5gR6tPQ7S8YQr0SJANQ/Tk32p4yw31h6KoCAeuCEPQFChzvJfj+OEPe2tSGCLgf6D9ugLdRBmNqHYacxcGkkxCFANqfM6HvoDFqaKb7DXXeRtVn3TBXpx5MJD9H2RuxZ6FLEBAcuPfiYfz3mp0pnzueVCoM1u8+heKFVZizY3nUuP9AEBiOSRKq181Fxco6TfMEBhrtkD+I1//Pk9j+nYfjnns4SS+jduM8lC6uVq8jgMqbZqn3Mez1jDFYi3Ox4uM3Y/9/7UJORT7KltTGP7ckIacsD2VLa9F28vqIr9fdthjrvrwTskEHHlK3Al/24U1o3HcR737/BdrFMAtRGCATxlSrwLogqDakWifiSQL9R/XoeMEMJgvYFoSQv9kPU8XYJsL5uxi8l7Wu/xeArDYCOqtA1ac8CHRL8DaoQwbmGSEYCgWUAOBr0qlDCVHfn9pbkL/RD1OV9gbYc0VGy2NWcD8ii4L7jhjQaeeo+ow7YQXB/iN6NQgAw1ZoMPCAQMsvLKj7G2fKJYlzL7jAQvGfgmUIzOltR77XBQ8KUjt5muz/z5fRfKgeix9Yh4JZZZD0ctLNh5hR21vjwBJCWS8jr6YYxlyL5vsauAeT3YJFD64HWOKVBowxzL59GY488gZyK5P/LIUQyKkoGBEGKlbOxMa/fJ+6XQdjkIcsraxaOwcb/+oevPWdZzV/H2R6oDBAJgxj6qZC7c+Z0X9MP6Q7M94bovpE672uAziDAEP/CT36j+tR8WFt9Qa8DTIcBwzwt8uQjAI5S4PIXRmA451UeigY/Ddk+FolmMrVBthQyGEoVP8ecjJ0vGCC47ABIsDU5YdDnsZ1doGCW3wwzw7B1yrBUMiT7lsQ6JLQ/HOruuEQmLo8MCzUz9D0Uytm/pUTsmnka4UAet4eKI4Uex6E4mZwntbDvjK1J0K9SwkvU0x8nN3vSUsYGM2+A3N2rsCSh9bDVpqn+TVMkjTXCWCMARJD7cZ5kZUDqdK6DwKTJCx5eAOa9l/WdF9Bz8gVGss+uhmCi7jLLWs3zoO9piilCodk6qMwQCaUpAfKP+hF0Q4f3Bd1UHwMzuN6+G/oBtfwR9byh99khz7ZcnVc/sYTFsya4Yw79i3EkJoGkYZZwHtNRvcbo9u5qOdNIyo+5I36XKCXofEHNiieIfcrmHoDskDp/R6IkISeN40IvWAGADCDuq1y0Q4fJKPa8Dv2G+Cu1wECsM4JQXGrVRlj9qAIBsUF9B8zIH/DyBK63AcEOpJMdJQEvFd1KYeBkFVOGgQAoN9oTum8sYwmCKz89BYsfnB9wkqC8Qw89Wvp8hcCMOSaRhUEUjXrtiU48dhb8HQ7YS6wxb2/kD+IlsNXoj5nyreieEFVwvNzhaN203yc+u27abtnMvlRGCCTgt4ukLdGbYgKNgXgqdeh/7geIReDvoDDd12Gvy3ehkAM4AKOQwYUbvVDBNWldEPH0fsO6wdrGkTChPqn4kLq9QI4g+u0HuJhb2QFW8jJcP2/bHG2NWaAArQ/Y8HwWZMiwNC7zwBPg4z8jQG0PWOOuk91guLg/cbjPKOLGQY0r3wcRTvWN9+Kile6wJTYjS0Hw7W8YvSYczCWzSJHEwTm3b0Kix9cD0D78r7hGGMQnMddjRAhBJw3HCioK4PenNmdGc0FNliKcnHi8bex4at3xbkdgbPPHhzRM6A3Jb83wUVKOyKS6YHCAJl0mARY54ZgnTvY7X/xm7mJG2wBOE+qQwbBLvUp2DIriIJbA7DMCaHnrcTd5KMhFIau3UbkrVFn4zf9xAqedKkgG/bn4D34W2S0PW0O54SRvR/JzisCsa8tmwBDmYJAe4IiSZzBUpf6xExuktF+Sz7K3xi5g95AR8YLc29K+bxDjW5oYDnW/Nntmp/sYxFCoP10I0x5FuTVxN7DYICkk9H43gX01LdhzRduH9X1Urw51L96EnqLESs/dSskWQZXeLi4EXD22YM4+eu3AQC5VYUoXVINgKHrUgtC/mBUZcSR34uEviYqTZxtKAyQqUFDL2+gI/rpzXNVB88VPYp2eiMBIfkFtDYc6vE9bxjR84YROSuCCHSmYW/i4UEgIvkyRWNl/MmIBbf40fZknMltTEC2CdiWjG4Gede6PAgdQ8GbfTAFBgNFlyUHTyzagGv5yesMxKs+OJogoLcYsfaLdwBIXvo3EcYYShZVo6+xC6ef2ofFD66PeT4eUtDX3IOWw1cguEDhnHLUbV0cdaz24YbExwkh4Olywt3ZDwA4/9whXN1zGjNuWQhrcQ68Dg8a3j4Hb7cLJrsFm/7qHlSsqosqhezu6oekk2POGRBcIOQPUpXCLERhgEx67ks6jVUKRz5tA0DXKzFm1SV7bYrHO48bkLCxHsU5U/o6Z8hbG3/L3dwVQfhv+NH7TvScCTBAMglUfdoNabTvBoyhe3Ueni5fjZohFQj3BedqqwIYx2iCAAAsuG+15gl5yUiyhLzaYuTNKB7RUA983H+jF3u+9TsILmDKt6Ju6+IR50k1lCQKBRdeOBz1sd/pjWxCNEA26nD7v34ksupg6LnM+TYIIUYsneQKB2MM+//rZYR8tLQw21AYIJNez9vJNgRK3m3ADAIiAIytsU5krEEgletg8Frhn0vRDl/C5ZWMASV3+2BbGITjgAG+FhmSAchZGoR9dQA629gLOSk6GddqSgc/0Tz+QQAAihcmniCXsvC3IQ2bN8AYA1c4ui60wNvjAgDc9g8fTNrwJ2roo8IGF5HlhjykQNLJUPwhrPrMVqz45Ba0HK7H6af2w5xvRW5FAQJuP5r2X4LP4UbdlsWw1xTFvI4kS5EhkKK55dCF5xF0nGvCqd++R5sWZSkKA2RSEwLw1GupQ5BoPsEoyhymLB1BIMlQBRMw14aguKXIkISpWkHBLX7kLFa754UCeK7J4F4GfSEfERAsdQosdd4Rpx5vwzcpSiclkN6iVMlqEszcsgiHf/IaAIbCWaVxj9VyvqjjJHU1Q9AXUCf1yRLkcP0DSZZQtXYOqtbOiYQSJjGs/eIOXHj+MIrmVaj/eOJdSwA6kx5PPvSfMOdbEfQG4O+f+N8LMnEoDJDJTSAt7bgIAPoiHp47MF5P8aMV//5K7vPBVM4jhYeGFglyHDCga7cRinvwCdZYoaD0/d5RVRecqi7tOo6a9XMTHjOWiYXDyXodrCV2VKysS77qQKOBe2OMQWfQxyxINLD0ERisU8BkhgX3rUHQ4094L0xiMOVZoQRCcLX3peWeydSWnt9cQjKESYCxSlG7w+MfpeVMCPVLKPugGyzjq6ZGn17U7xXquP4ASQBMoPT93kiRI8kYHQR63jag/TlzVBAAAH+rhKYfW+FryZ5/6jcOX4Gn26m5aFA6bP/nD+Omz27NyLkTbX8cu6Qyg95qBFfiDxtxhcPV7kjXLZJpIHveIciUVbA5MKb5ApEjAwxMD+Rv8icJF6NnX+uHvnC0pZEZgl0Syj/kQe7KIHR5HLo8jtyVQdR+2RWpwzCc4k0wSVIwCAXo3KVlEuX08dKXfo6AU+32FkJE/jcgXb0CA+c32cdeVCmdhIhdYXCAJEu4vOvE+N0QmfRomIBMejnLgvBc86PvgDF6IqEkNFW/G6r1N1bI1oEXxeqOH9sQQs6iEEru9aHhP2wIdsfZBjkB7mPoeN6Mmd+IXVo4FucpfbhMcRyCwXNZj1A/G9PuhFOJt9eNJx/+T8y7exXm3rkSBosBhhwzZKNuxETAsYgs2UvjOdNBcAFnhwPWktwR368QAv3NPWjcf2mC7o5MRpPrN5iQGBgDSu/zofITblhmhSCZBGQbh311AAVbfSmfT3EnKL4DFt1FnwLJxGGuC8Fbr0OwW8boQoW6T0D/8eRjGaF+ht79BjhP6TVdKuSczPMkMkAAF188ihe/8DM8+4n/gS7NQQBQexjS2cuQLpIs4ezT+3Hp5eMQfFhiFoC9uhB3/NvHYLBlV48RiY96BsiUwJi6dfHw7Yt5COjZa9JYh2DEWWN/Wgz8X2rnLNzmh6QH3Jd1URsTjUb/cR2CXVLkaT53VSCyMiDUz9DyuAW+xqFFjrTVzxdcnYeRjdRNhBJ8PY2TCieSEAJKIIRrb57FyrpSdVHBkK8PlGbOn1mC9V+9i3YoJAAoDJApTtIBxXd60flH7VvHJqWpPPFAWFB7EfSFHIIDiie8odCYMPiu6+Ebsvyu910jmE5AV6CoKyI07FUw/F4b/zsHOjtH/mY/8jcGsi4U3Dh2DRWrZkKS41eKHL4PwWQPCCMKIYV3TTz849fAJAmzb18ad+6AJEuo2TAX1hI73B20oiDbZdnbAZlIQkHchtLfIaFrtxHtz5nQvdeIUL/2N+CCzUGU3OcF0w+dCzBGskhhBQNDsFtC18sm1P9jDhz7DEl6BbTeHxvyP0CEGIIdcvjco2ugQn0MnX80ofW35jSElswYS8GhRM4+ezBuEOAKh9/pxY1j16JXIQiM66oELYQQkV0Ygx5/1I6MztZevPXd3+PyKydQNL8Csj7x8x5jDKXLajJ6v2RqoJ4BklFCARyHDOh9z4BgpwwwAev8EApu9cMyQ4FQgLbfm9F/xDA4Vi+ArleNKNruR8Ftfk0VbXOXBwAIdLxgAngaMq7CIOdyKElDybCNh8TQ4YVM1DMY63CI+nfnaQNyzgSRszS9BXoms/ZT13Hgv3dh7RfviMy2H6jyF3B58do3f4feqx2wFOUgpzwfC+5fjep1cydVzwAPKeg434zmA5fRca4FXRdaYC6wwVaWh6DbD8f1zsixWu979We3wdvlROvxhjHfX+XqWZh/z00onFMOJRhC075LOP/CEThbRm5kRSYXCgMkY4QCtDxugfv8kF8zweC+qIP7gg7lD3nhvS6j/0h4wfywp+mu3SbIVoG8dfFr7vtuSOjabQpfI72VBg0lCrz9qT6FD294hwQCJjJfCDHMWBmC/0a8LZ/Ve+ndZ8yqMAAAl14+jtbjDZh714pIg9V8sB5XXz8T2e7X0+VE0BtA5apZkyoIAACTJbQea8C53x+KfM7b44qUQx6q61JrpIxxIgarEVv/6SG8+o3foPNc86jvbfXnt2PBvavBFSXSAzP3zhWYc8dyvPEPT6P12LVRn5tkHoUBkjGOg4YhjfQQ4U1yWp+KsV1vFIGuPUbY18Qe3/Y0yGj+mTXc3R1na+BREZBzBGQLT8P5BnsJJKOAfZ0fvW+ZMhsKJAHBWZItn9mIXR4zydiY8UpPmjlbe3H0kTcSHpNXWwzZMDnfHufsXI5zzx3ErG1LMXfnCtjK7Ag4fbjy+mlcfPEofH0eAIC/z4Ore8+g7rYlCWsOMEmCUDhWfPIW7P7Gb0Z1TzNuWYgF964GgKihGEknQ3COW//uA3j2Yz9EwJX66h8yPmjOAMmY3vcSNQAsvOF9ojMwKE4JvuaRTzaCA21PmtX19aOatZ+gzjEDLLNCcJ1OZwPGwP0sHAQy+7TJZAAKkCxxZL4S49TEZAnz7lqZ0muGFzUarWTnYIzBVmLH3f/9aaz94g7kzyyBwWqCrSwPSx7eiPf9758gpyI/cvzhH7+Gnvq2pPcnyRLKltTCUpQzqvteeP+auBUPmSRBZ9Bj1rYlozo3GR8UBkhGiBDC+wCMveHjw0YJQv0MbU+ZEexJ0A2umRj2dwFTbUhdu5/up3eR5Gk9XZcJIvlTPxPIXRZ/+CWbbfjaXZh56yLNxw/M6Ff86pALDymRz6eiu74NQa8/+fU4R25loVrjQBr8fZJkCcZcM2751vsjnwt6Anjlrx5H88HLmu7BmKutkiKTGCpW1WH+PTehbusSFM4tT9j7ICDSv5skSavJ2Q9Gpj4JSbYdRnhIPVnjKGAoGnzi8N2Q0PRTK7g3Pd335jlB+Bt14EHAUMyRvyEAf5sEX+PgMZNTosmJ4bkKLHzc8J8xE5AMQN56CgPDFcwqxaytqT3BDswrkI06NB64BBHiMOVbUTS3HEySEjaSQ9lK7ei6cAMVK+uSXTDuXAZJJ6OgrhTFCyrReb4FAMCDCpoOXEbV2jkJTyu4gLd75NyD4SpWzsT6r90Fa1FuZClj0uAjELXqgUw+FAZIRjAJsM4LwX1JF78bXzDIVgWKJ05FQCZgKFXgva6DZAhCMgEtj1nBfaNfWhdFEjBXKaj5E0/Up6/+my2FoYdx3gExHLCYSUD4El2XAQKQcxUo/fLgSg3OIFsFKj/pgT6P3pyHq9u2RNOku1gYY6gObykMAO6ufhisJjCTPvL1RIw5ZpSvmKnpOolwhUeFAQC4/s4FrPnC7dAZ9XFf03K4PjLfIJ6SRVW47R8fiqzwGeiZGNhBMe6GShJD24mGhOcmE4vCAMmY/Fv8cF/QIWaDKQno8zlKP+BFy8+t6lNDVAOsNnqBNh1af6sDkwUs84IIOdJcTnbY6YIOdXfDFM6Q1vsZaaDBZmBGDlO1grzVwfCcieSFlop3+iGbBTz1OggOmGcoyFkUBKN/+TGZ823QtJY1jqGNoaUgB0xi8Du9MOZo7H5Pcu2BJ/HE5wC4Eh30gh4/jj7yBtZ+cceIRptzDsUfxLGf7016fys+cat6jRhlnePdO1c4Ai4fru09m/T8ZOLQWwLJCBECHO8ZMLi8brBRAwB9HkfVn7hhKBCo+aIL3XtMcJ3ThXsIRj6xCoXBfU6PtD6JcwbHYQOCPRLyNgagt3Nc/6ENYlL1ng+pLudn0FkFcpYF4b2q7clVb+ewzFJgW5BdSwhHy9vtDNeKGLuBRltrENB20pFVEkdeV0Lr8cFlfBUrZ2L+vatRvLAKSjA0ohCRJElw9rjgdyae6W8utKF0SfICRUPDhhACIV8Ae/72CYT8sXfdJJMDTSAkGdHxkgmuswNdktGV9AAB66IQDAXqm66pgqPy4x7M+AsnJDMfduxQWocHtLyZq8co/RL6j+vR+EMbmn9hgeJO0xDEqCWueug8aUDDD6zQF3Ho7ImWYwjocjnMMxNtZ0iGu7Ln9KiGCMYLYyxhz4UQAjeOXUNfYxcAYPnHb8G2734IFavqYLSZ4lYkzCnLw61/+/6YXxtgytVW8juqh0Co4cTncGt6LZk41DNA0k7xMDgOGhLuDNh3wICibb7INr2KD2h+dKwTA4VaRljRknFHVuXz35gM/xySf/+BVhktv7Ci+G4vWn9jxcjeEvXjkvd5smr/AZPdgrl3rUTdlkUw2Ezoa+7Btb1n0NfUjaA3gN6r7UknsfVe68DlV09g9vZlSbvjJ0qyoQRJL2P9V+9EX2MXln5oo/q5JJMYJZ2MkkXVKJxbju5LrTGP8fS4NA1TRN2rxCAbdJh39yoc/+Wbml9Hxt9kePcj04znigwoScY+gwzeq7rILoT9Rw0I9UpI3hhGDzdEY5BMAtw9zpP6xptg8LfKkHRAxUfcaH/RHFU2Wc4VKH2fJ251QX+7hP5jeoT6JehyOXJXBmEsnaQbFWhkrynCju9/BAabOdLwGe0WlC6ujhzj6XLi9BPv4eJLxyKfsxTlYNa2pcgpz0PA5UPD2+dx4Ae7YK8pQvH8yklXgTAZxhjKltSgZEFluOCP9sabKxwVq+rihgF/nwdNBy+jas1szSskADWIzLhlIYWBSY7CAEk7EdL25iOGtFV9R2PPch6BqcVyhH9IKAhvF5y71o/+gwPzFDIh3SFjLOcTcJ7Ro/yDXtgWO+G5Kkcad0udErNHQHCg/Q8m9B00YujwQs+bJphqg6j6jAeycZS3M5EYsOX/PBAVBICRT9DmQhvW/vkdMBfYcOLxt7HoA2ux4tNbwlNa1J/HwvevRfOherjaHChZoH1d/GTb3XBgqCOl3g0hkg6RHPv5XpQtrYXOpE8pEOhNGv99kwmTRZ2IZLwYK7SNUxsrB59GFbeWXgEAAqj9ghOl9/tgrlNgLFeQszSI6s+7UHK3T9s5Rm2M547aBXHswUKd3xBexjlbgX1lENbZsYMAAHTvMaLv4EDZweh5HL7rOlz79xzw5DVv0s5+ZWwXLV8+A7mVBUkbp4HGesmHNmLB/Wuw6k+2QgrXAZB0cqQhrFhVh7zaIs3Xv/zqybiT49JVmXA8SDoZ3ZduJDymv7kbu77+GNrPNEZ9PtH3yBWOnmsdablHkjnUM0DSzljKYZ4Zgve6HHu9viRgmRWCoXAwDOgLFYT6klfoy98cgLFcwFgeGLGBkRAAMwiIQCYCwdgab8msPrF7r8mABMg2jkD7WCoopvY67ge63zImeB2D0q9O/Cx7/9SqH1+ysDql2gCCCyz90Ma4XeiSLKGgrgycc7XKX5In/rrbFsUNIpOptyARrnB4u51oOXwl6bF9jV147a9/C1tZHnLK8mApycXGr90d93hJlnDxj0fTebskAygMZCnFC/ga1bXnpkoFutz0Pr2UfdCDxv+xQXEjusFjAjqbQNkHvFHH560JwnslcVdizvIAiu+K31AxBuSt86P37USNXgqidhkc2/mKtvuRv3EwvIT6Ga7+aw5EaLQhQ8BUo32lgOeqDkg6fMPQf8SAkrt8kKbQcEGqT95MYkmX+3GFo+1kg6YiQJJOHrfdKIHBIQnOOaQESwy1nANQv9eQL4i9//RsSlUCXW0OuNocAAB7VSEWP7g+atnjwPbQV984g6b9l0Z1n2T8UBjIMiIEdO4ywXHAMDi2zwRsi4Movd8HnTU972qGAoEZX3Gh5x0j+g7rwb0SJAtH3poA8jcHoLNFXydnSRB9R4Lw1OtiPC0LWOaEUP6QN2k9mMItAThPGRByAKNtZM11IRTcHEDfYX14eeTYggAzcuRtiO7F0OUKVHzEg5ZfW9QujYEeFElEdnVMfF0GS5322gFcY2+JUBj8HTLM1VNnSWLriQYs/9jN6T2pEGg/0wR3pxNzdixLcmx6Lx0PVziYxBB0+3Hhj0dRsrAKOZUFsBZq31xoIDgNVAwccPB/X0XPlTZUrp6FkkXVgBBoO92o1ivQ8P0d+/leOK53YtEH1iF/ZgkAwNXuwLnnDqm9AlNjpCSrURjIIkIALb+2qFUBhza4gsF1Vo9Am4yaP3dFlvuNlS5XoOQuH0ru8kHwkdX+hmIyUPkJD7peNcFx0BDp6mcGgbz1ARTd7tO0TE62CNR+yYWOF01wntRHvk/JJKDLVxBoS941X3q/D86TerjOGpCOdzEp/K/M3yqh/7gBIReDLpfDviqImV93wbHPANd5HQRnMNeGkL8xgO69xpH/nSIE9MUc5hnaG2xjmfZjmTS13rk7zzWj+3Ir8meWaBoq0NJ1L+lkOK534sprp5KGASYxtaFOEN60TDBMNPNfCSm49uZZdJ5txrW9ZxHyB2EtseOuH3xK8+TFoUFg6J9gAuu/cidWfPxm2ErzIhstLXl4I/qauvDG3z8NZ2tv0vNfff0Mrr5+BgabSa282O9N+hoyeVAYyCKeehnu83G64jlDoEtC30EDCm5Jfwk+LQ25pAdK7vahaLsPvlYZDOpkREnjVruCq93vTAbKH/ai5B4fAh0SmA4wVShwXdDhxq+sic4AfREHONC9ZyARjX24QXFLuPFrM1xnDIN7BADo2WtC/iY/iu/2oeSe6NeU3udF4//YEHIhet6FJMB0QMXDnpSq5hpLOYwVoaS1FGQrh7Fs6i0z3PuPz2DH9z8KW1leuNBN8oYXEDEr+XGFw9/nQfPBegiF48bxayhbWhtzXoDgAiF/EHpz/F9SHlIAKfHcAyFEwuqCR366BxdfjB53X/bRzTBYjZrnJcTfN0CCrGewFucCQFSgyinPx47vfxTPf/6nCLq1TfQMuKbWnBOiotUEWaTvSHRjNIIAHIcmfpN7yQhYZigwz9AWBEQI6H7DiCvfzcHV7+Xiyndy0fD/bPBc0sEyU4G5WgGTAXNtCMkq/AW7JbQ/Z05yXNTVNR3rOhMOYZwN/g9A77sG9Lw1coBenydQ+2UX8jcEwIzhJzpZIHdFEDO+7IKpikPxAb37DWj+hQVNj1rQtduIoCN+w1DxYW/4v3/8qoX5N/vBJm8Bvggmsaic5uly4sUvPIIDP9iF7vrY6+SH8/V7wZXo4MMVBULhePtfn4cIf+3IT/dACYRGHDvwJH/gh7vQc6Ut8kQ9/BgA8PUmrsDHGIOn2wV3R3/U5/39Huz/wa4RQUBn1GPmrYvSVi1R3Q55ZHMg6WSYC2yYvX1pWq5DJi/qGcgioV4pyW58qW7SM/GEAjQ/ZoHncnSXeqBdQusTFgQ6fSi6XX2icezTMLFQMHgb5OTHRWgtjxx/Fn/Pmwbkb/JDGtZpo8sRKHmfD8V3+cD9gGRApKH2tUhoesQK7mGR83gu69C914jyD3qRu2LkUjdDMUftn7uGvW7w/nJvCqLg5km1MUM0BszevhQL7luD/JklEJzjxvEGnH3mANpONCDkD+LyKydQv/sk3v/LL8JSmJOgh0Bg91//BrO3LcWcncthsJrAFY7GfZdw+on30Ht1cCmco6ETu77+GFZ/fjvKl82IfL6/pRvHfr4XTQcuo/VYA2779oMomlcBHlIgBCDpJIR8Abz9r89j1ae2wJJgbF8IAcUfxB8++2OULKqGrcQOv9OL1hMN4MGRIcNot0DWj1NqY8CMWxbi/B8Oj8/1yISgMJBF5Fwe2QI3NgHZOrW6iPuO6OG5pMPIxlb9uPt1E3KWBGEo4+g7rLXXQ2sQEJBsAuAIN66xx/eTnY/7JHivy7DOjj2uzyRAHjL5XfFCbdC9w64pGCAEWp80w1DMYaoaeT5TJcfsbznhPK1H/3E9FC+DoZjDvjoA8wxlLBv2ZRYDNn79fajbujhSIIhJEsqX16JyVR0O/PAVXApXFhRc4ORv3sGGr94V81SCc9S/dgp917tw9NE3cPyxN1F78wLMvHUR8mqKcNNnt+HKnlNoePt8pCF2NHTitb/+LawldthK1Yba0dAZOafP4cbLX/0lSpfUoGrtbMh6HXqvdeDam2cR8gVROLsMS6sLE9ZCyKnIx8xbF+Ha3rPoQFPCH0fA5UupuuDw+QKpYIzBYE3TRCIyaVEYyCL2VUG4TidoEBmQt3ry7CzG/erQRt8RA0JOBn0eR97aAHJWBCOT8hz7k6yBkwQchwywrw5kpNej8FY/zDUKmh6xqssEIz0v6puvvogj2JX8CU4Etb6pA127TQnChxoIut4woOrjsSdwMR2QuyIYs/dgspp5y0LM2rZE/WBIgybJ6s927Z/twI1jV+FqdQAA6l89CXO+Fcs+dnNUhUFJJ+P6uxdw8H9eVT/Wy7jt2w+iYmUduMIhyRJyqwpRvnwGFt6/Brv/+rew1xRhwT03oWRxNYTC0Xz4Ci68cCTmfbafbkT76cYRn28+XI9lH9kcd7LfwOz+DV+7CzeOXIXfmXjyXdDj11waOODyoXH/RczenmRVRBw8pMAR3viITF8UBrKIdV4I5rqQWvhmeO+AJKDLFSMK+UyUkJOh8cdWBLsG3ugYFBdDW5MZjoMGVH/WDckIBDqTVC7kDP42GYornUFAbVis80LqmL4MzPiqE73vGtF/Qg/hZ9AXceStC8BYoaDpR7akZzSUJJ/t77kmo+0pM4I9ycIFg/usHorHB9kytVYGxDP/ntWRxjoWIQTm7lyBYz/fG/nc6Sf24cqe05i1bQlspXnwO724tvcseodUw1v1mdtQFu76Hzj3wJ95M0pwx398HHk1RVFFjebsWIY5dyzDO//yPK6/e0HT/a/42C0QQiSsC8AYgyRLqNu2BOefO5T0nCd//TYqV9VBMDaih0AIgevvXsDpJ95DX1M3eFBBX2M3Vn3mtqjvRUuxJkkn4/LLxxIeQ6Y+CgNZhElA1SfdaH/OjP4T+qhAYJ6hoPwhD+Q01RkYq9YnzQj2DGvow/fra5bR/oIZ5Q961YqDiYrpMKEuK7SPdfhjsLtftnMU3hpA3tpAZAzfUChQeq8PpfdGz6QWAjCUKwi0SbGHZyLVGBP/3H3NEpp/ZoVI4dvo2m1E6X3TY2Z3fl1JwidgSZZQMLtsxOfVzYn2xXyN3mLE3J0r4p5XkiXk1ahliYc2mAMbAG3+/+5F16UbIyb9DWctyUXFTXXalv9xgfwZxeoHDLAW5QKMwdPVP6IgUG5lYWQVAjC4fFEIAR7iKJpTjpr183Ch+yj8fR6cfeYAui+3YsF9q1G2tBZCqDUaLrxwGPPuXInazQvUvT/C9zlQNOjKnlO4cexa0nsnUxuFgSwjGdVld8V3+uCu1wEcMFUrk2rXukCnBM/lBNUIBUP/cT2K7/Qhd1lQ3S453sRIwZCzRN2Vz1gZgv9GvDoDycf2c9f4UXK3L6XNfBgDyh/yoOlHNvCgGLFMULYIlL4/+XrszldNahBIoXxx3xHDtAkDPKQAxvi/E4JzKHH2B4inaF45ZMPo3gKZxCAEw5ydK3DisbcSHmuvLkpprF4JhDD3rpVY9IG1yCnPB6BuH3zhD4dx9tkDEFygdEkNbv7r+9R7GV43AICsl2Ery8OSD23EnJ3L8cpfPQ5XqwNtJ6+j7eT1EdfsONOE7vo2LLh/DSwFak+Wp9uJc78/iPPP08TBbEBhIEvpcgXsKyfnmLE6mz8JhcHfLCN/UwB9RwzqE1KMoQ99PkfOUvX7LLnHh6afWgE+/NhwEIg7uVJAMgKl7/NprnkwlKmco/bLLnTvNcJ5XA+hMDC9gP2mAApu9UOfl7hXIORmcSZJJsIgggJCwZRYKphM475LqNuSYCkdY2g+WJ/aScc4W1KSJZQtqYn5NVOeFbO2LUFuVQH0Zu3pUdLJMBfmYN7dq6J6Asz5Vqz45K0oml+Bt777eyz98CZ12CFGrwaLmlMhwZRnwc1/fT9e/sov4l5XcIGzzxzAud8fhLXUDgjA3dGXUnliMrVRGCBTmqGIo+ozbrT8yqJOqhuoo8AZDCUcVZ9yRyYbWmYoqP6sGx3Pm+FvHWxUdPkchbf50f26CaF+RD+9h3caLHvAM6ogMPQ+yx/0ouz9XnA/g2QUmhtpdXfC0TRcDCI0PcLA+ecOoW7Lopgz6LnC4evz4Nresymds+dyG5SgMuolekKImI3l3DtXYM0Xbld7D1JoTAfOV7N+LoDowkmMqXUVajbMQ93WJShfPkPzeSVZRtHcchTOLUf3pcQ1GAQXkUmYJLtQGCCTjrluoDhQ/AaQyQKmGrU2v2WmglnfcsJ1Wg9fkwzIgHVeEJZZI5fKWWYqqP2KC/5WCSGHBNkqYKpWt/21LQyh6zUj+o8aIrP7zTMUFG33wTIrPbX6mYyYk/p4EHAcMMCx34BgrwTJpBYYKtjkh86WbEloHDoBNk22ke+91oG3/vk5bP7/7oWsl9UpnEJ98vX2urDnW0/E3UY4Hr/Ti6tvnMasbUvjVhcEElQzFAI3jkePpVetnYN1X9oZ+VhL5c3IsYyBySxheWGucMzZuUL7SQdulQsUz69MGgZI9qIwQCYdQ6GAdUEI7ou62HMBmEDumkDU2nspheVyjAGmCg5URM+T0NkEyu5X91IIORkkI0ZsqJQJ3A80/tQKf8vA7ncM3MPg2G9A/xEDqj/ngm1REK5z+iRFo4YSyFvnT6kxmuya9l/Csx//IWZtX4qiOeXgCkfLkSu4/u6FmIV5tDj8kz3Iqy1B0bxyQKjliQdCgKfbCUtR7EJBgnMoQQX1r5yI+vzSD29MuOpBi0TzCyRZQm55HgJuPwzW1LaWHF5BkZChKAyQSan8g140/dSqducPPBWH/zTXhVCSYCvjsZIMSDq7P526XjWFg8CwRoAz8IBAy+MWVH3aA89lPXhASw+BgC6fo2irtlryU4m/34tzzx5M2/lC3gBe/cbjqNuyGHN2LoetxA5vrxtX9pxC/e6TmHHzQqz70s6o8XmucPCQgr3/8DS8Q8oMm/OtKJpbkbZ7iyfoCaBx/xksuG+15tDBJKbuQEhIHBQGyKQkWwRqvuiC85QefUcMUJwMunyOvNUB2BaFpsU4OADwAOA4bIjfwAuGUK+MUK+Emj9zof05M7wNg/9sJaOAkASEN9woSAK5q4Io2emDbBl5OsXD1KqN9ToIAVjqFNhXj9xSOpvwoIL63SdRv/vkiK9dfuUEOs42Yd7dq9SiQyG1N+LSruPwdDmjjpVNycdktO4wGPdeFY5rb57FuecOoXL1LORWFiQNBFzhaDl8Bc4byXceJNmLwgCZtCS9WjXRvip213+wlyHQLUEyAqZKZUp2iQc6pch2zXFJAt4mGUXzQqj5ghuBTgmBLnVegblGAVj4PCFAX8Cjhk+G8lyV0fwLK0QQkb2KPJd16N5jRMXHPLDND6X1e5su+pq6cehHu5Me5+lyIugNJNzBcCy4oiDoCeDiS8cQcPnwyl/8Cks/sglzdiyPuubAMMXAnz1X2vDef7yYkXsi0weFATLlBLoktD9vilpup7NzFN3ug/2myblcMh5NPRwCYLrBJ3dDMYehOHr8N1mdiGAfQ/PPrRAhRPdCCECEBFp+ZcHMr7tgKKJx5dHiQQWXdx3H/Htjd98LLhDyBcBkCboENROiX8PBuYCsk+HtceONbz8Fb48LgFpm+MhP9uDYz/fCUmBDyBeEvbYYc3YsQ055PnwON668cQZN+y9FdmAkJB4KA2RKCfQwXP8fK7gverldqI+h7WkLFK8XBZsnR0llLQwlHLpcjlB/guWDgsE6d2xP7X0HDSODQIS6n4FjnwEl90yPIkUT5eRv3kX5ipmw1xRFBYKByXvvfP8FlC6uxoL71yTs3hdcQAiO+t2nEHD50Hm+Bc0HL8dcqsiDClztfQAA36nraD81sqgQIclQGCBTSterJjUIjJhVr37cucuE3JVB6CZJWeVkmAQU3OpHxwtx+vYlAcvMkLr6YQxc5/WJJx5yBtc5/bQJA6VLalC1ZjZkgw7d9W1oePscFH/mh0GCHj9e+ctfYdGD6zHvrpUw5pghuEDL4Ss4/eR76LpwA63Hr6FwTjlKl9bE3K+AKxyCC7z9vefQtP9Sxu+ZEIDCAJlCFB/gPJVkeR0HnCf0yN84dXoH8jYEEOyR0PuuUS2axAdXThjLFVR8JHm54mSEhpV3Wo6Z7Ez5Vtz27Q+iaG45eEiBEMA8nYTVf7oNb3/vuXGpsR/0BHDisbdw8vG3YbCaEPIHoQQGg4gSCGHP3/4OdbctxpydK5BTUQAGIOgLwOdw48bRa7i86zjcnYn3PCAknSgMkClDcUnJ19lLQLB3dDMJgw4GxwEDXGf1ECF1z4a8DQFYZmS2lWQMKHmfD7krA+g7bECgS4JsFshZHoRtfnpWTphrFXWHx3g/P2mwiNNUxSSG7d99GPZqdaOfoaWL9RYDtnz7Qbz8lV9G7VqYSYKLuFsR85A6BFC/+9S43AshyVAYIFOGbBZIuqEQx6h2XvRclUdMsAs6JDhPGlC4zYei7Zlfs2+q5DBVZqabPm+9H32HEsxy52xK9abEUrVmNvJnlsb8GpMkMC6w8IG1eO/faGY9IcNNwcVYJFvJVgHL3FBkv4CYBJC7LLVGTfECLb+MMdM+/BTdvccE17mpnZtNFRzFd4efUqUhP7/w3wu3+WCpm9rjBDUb5yessifpZMzYtGAc74iQqWNqv8ORrFN0ux+NV3Qxdh4EAAH7ugD0Ban1DPQfM4D7gbg9Dkyg5x0jbAundjd6weYAjOUKet8xwnNFBwjAPDOE/E2BaVFjQGc2xN9HIEw26FLeQIiQbEBhgEwp5moF1Z9xo/VJC0J9AxPtAEhA/sYAinem3s3uuapTc0C89kEweK/JEGLMu95OOOtsBdbZnom+jYzoa+qC4HPA5Nj/kQQXcLU7KAgQEgOFATLlWGYpqPtrJzyXdWolPoOAdWFoyiwnJJlR/8oJLPnghgRHCFx48ei43Q8hUwnNGSBTEpMA67wQ8jcGYF89troClrpQ/F4BAGAC5pkjt0Mmk4urvQ9HHnkdwMgd+jjn6DjbjIt/pDBASCzUM0CyXu7KgFrMKN6OgIKhYPP02wFwOjr/3CG42/uw+KENKJpbDgDwOdy48OJRnHl6/6i3OiZkuqMwQLKebAYqP+kOLy0cEgjCBYAKt/mm/OTBbNK47yIa912E0W6BrJfh7XHRPAFCkqAwQAjUrXxn/qVzQooOkczw903PiZKEZAKFAULC9HkCxXf4UXwHDQkQQrILTSAkhBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAULIqDzTv3Kib4EQkiYUBgghhJAsR2GAEEIIyXIUBgghhJAsR2GAEEIIyXIUBgghhJAsR2GAEEIIyXIUBgghhJAsR2GAEEIIyXIUBgghhJAsR2GAEEIIyXIUBgghadfQXDzRt0AISQGFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghBBCshyFAUIIISTLURgghIzZa23zJ/oWCCFjQGGAEDKucq6Lib4FQsgwFAYIIYSQLEdhgBBCCMlyFAYIIYSQLEdhgBCSsmf6V070LRBC0ojCACGEEJLlKAwQQgghWY7CACGEEJLlKAwQQlJC8wUImX4oDBBCMsrYaJjoWyCEJEFhgBCiGfUKEDI9URgghGhCQYCQ6YvCACEkKQoChExvFAYIIQmlGgQamoszdCeEkEyhMEAIIYRkOQoDhJC4tPQKvNY2fxzuhBCSSRQGCCGEkCxHYYAQEhNNGiQke1AYIISMQEGAkOxCYYAQQgjJchQGCCFRqFeAkOxDYYAQEkFBgJDsRGGAEEIIyXIUBgghAKhXgJBsRmGAEDJqVHCIkOmBwgAhJG29ArQvASFTE4UBQrJcJocHjI2GjJ2bEJI+FAYIIeMm57qY6FsghMRAYYCQLEaTBgkhAIUBQgghJOtRGCCETBj7Ff9E3wIhBBQGCMlaNERACBlAYYAQMipUY4CQ6YPCACEkLajGACFTF4UBQgghJMtRGCAkC9F8AULIUBQGCCEZQdUHCZk6KAwQQlJGkwcJmV4oDBBCCCFZjsIAIYQQkuUoDBCSZcY6eTDWEIGWZYW0SREhkxeFAUIIISTLURgghGhGEwcJmZ4oDBBCNKEgQMj0RWGAkCwyXsWGqMYAIVMLE0LQrB5CCCEki1HPACGEEJLlKAwQQgghWY7CACGEEJLlKAwQQgghWY7CACGEEJLlKAwQQgghWY7CACGEEJLlKAwQQgghWY7CACGEEJLl/n8yP0jN4aH6LAAAAABJRU5ErkJggg==\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": "ffb80575-d28b-4c3b-ac15-51576a7e4d76"
},
"execution_count": 86,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712559760.2923527\n",
"Mon Apr 8 07:02:40 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": "81887d9c-3a9d-4f9c-8e8f-08102ed7c6d3"
},
"execution_count": 87,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since beginning of run: 1712559760.2979019\n",
"Mon Apr 8 07:02:40 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": 1914
},
"id": "95xed6YyDClf",
"outputId": "28b8e88a-f494-4448-e714-0bee2af47f50"
},
"execution_count": 88,
"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",
"377 1.000000\n",
"327 0.652552\n",
"239 0.508119\n",
"287 0.416189\n",
"37 0.165825\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 0.012995\n",
"dtype: float32\n",
"Normalized Saliency Median: Saliency 0.007148\n",
"dtype: float32\n",
"Normalized Saliency Mode: Saliency\n",
"0 0.006661\n",
"1 0.008829\n",
"2 0.010742\n",
"3 0.011652\n",
"Normalized Saliency Sum: Saliency 6.237596\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Normalized Saliency Standard Deviation: Saliency 0.062231\n",
"dtype: float32\n",
"Normalized Saliency Skewness: Saliency 12.298806\n",
"dtype: float32\n",
"Normalized Saliency Kurtosis: Saliency 166.612259\n",
"dtype: float32\n",
"Normalized Saliency Variance: Saliency 0.003873\n",
"dtype: float32\n",
"Normalized Saliency Coefficient of Variation: Saliency 478.884521\n",
"dtype: float32\n",
"#\n",
"#\n",
"#\n",
"Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.002117\n",
"1 0.002316\n",
"2 0.004317\n",
"3 0.004862\n",
"4 0.006675\n",
".. ...\n",
"475 6.198670\n",
"476 6.208835\n",
"477 6.218544\n",
"478 6.227903\n",
"479 6.237597\n",
"\n",
"[480 rows x 1 columns]\n",
"Mean of Cumulative Sum of Normalized Saliency Values: Saliency\n",
"0 0.000004\n",
"1 0.000005\n",
"2 0.000009\n",
"3 0.000010\n",
"4 0.000014\n",
".. ...\n",
"475 0.012914\n",
"476 0.012935\n",
"477 0.012955\n",
"478 0.012975\n",
"479 0.012995\n",
"\n",
"[480 rows x 1 columns]\n",
"Normalized Saliency Root Mean Square: 0.063509844\n",
"Normalized Saliency 25th Percentile: Saliency 0.001681\n",
"Name: 0.25, dtype: float64\n",
"Normalized Saliency 75th Percentile: Saliency 0.010944\n",
"Name: 0.75, dtype: float64\n",
"Normalized Saliency Interquartile Range: Saliency 0.009263\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": "a25cd1eb-29cc-486a-f755-a9bb3ae03e28"
},
"execution_count": 89,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Time in seconds since end of run: 1712559761.8174794\n",
"Mon Apr 8 07:02:41 2024\n"
]
}
]
}
]
}