{ "cells": [ { "attachments": {}, "cell_type": "markdown", "id": "6f71ca5c", "metadata": {}, "source": [ "# Tutorial: Reduced Order Model with Graph Neural Networks\n", "\n", "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/mathLab/PINA/blob/master/tutorials/tutorial22/tutorial.ipynb)\n", "\n", "\n", "> ##### ⚠️ ***Before starting:***\n", "> We assume you are already familiar with the concepts covered in the [Data Structure for SciML](https://mathlab.github.io/PINA/tutorial19/tutorial.html) tutorial. If not, we strongly recommend reviewing them before exploring this advanced topic.\n", "\n", "In this tutorial, we will demonstrate a typical use case of **PINA** for Reduced Order Modelling using Graph Convolutional Neural Network. The tutorial is largely inspired by the paper [A graph convolutional autoencoder approach to model order reduction for parametrized PDEs](https://www.sciencedirect.com/science/article/pii/S0021999124000111).\n", "\n", "Let's start by importing the useful modules:" ] }, { "cell_type": "code", "execution_count": 1, "id": "0981f1e9", "metadata": {}, "outputs": [], "source": [ "## routine needed to run the notebook on Google Colab\n", "try:\n", " import google.colab\n", "\n", " IN_COLAB = True\n", "except:\n", " IN_COLAB = False\n", "if IN_COLAB:\n", " !pip install \"pina-mathlab[tutorial]\"\n", " !wget \"https://github.com/mathLab/PINA/raw/refs/heads/master/tutorials/tutorial22/holed_poisson.pt\" -O \"holed_poisson.pt\"\n", "\n", "import torch\n", "from torch import nn\n", "from torch_geometric.nn import GMMConv\n", "from torch_geometric.data import (\n", " Data,\n", " Batch,\n", ") # alternatively, from pina.graph import Graph, LabelBatch\n", "from torch_geometric.utils import to_dense_batch\n", "\n", "import matplotlib.pyplot as plt\n", "import warnings\n", "\n", "warnings.filterwarnings(\"ignore\")\n", "\n", "from pina import Trainer\n", "from pina.model import FeedForward\n", "from pina.optim import TorchOptimizer\n", "from pina.solver import ReducedOrderModelSolver\n", "from pina.problem.zoo import SupervisedProblem" ] }, { "cell_type": "markdown", "id": "c04276af", "metadata": {}, "source": [ "## Data Generation\n", "\n", "In this tutorial, we will focus on solving the parametric **Poisson** equation, a linear PDE. The equation is given by:\n", "\n", "$$\n", "\\begin{cases}\n", "-\\frac{1}{10}\\Delta u = 1, &\\Omega(\\boldsymbol{\\mu}),\\\\\n", "u = 0, &\\partial \\Omega(\\boldsymbol{\\mu}).\n", "\\end{cases}\n", "$$\n", "\n", "In this equation, $\\Omega(\\boldsymbol{\\mu}) = [0, 1]\\times[0,1] \\setminus [\\mu_1, \\mu_2]\\times[\\mu_1+0.3, \\mu_2+0.3]$ represents the spatial domain characterized by a parametrized hole defined via $\\boldsymbol{\\mu} = (\\mu_1, \\mu_2) \\in \\mathbb{P} = [0.1, 0.6]\\times[0.1, 0.6]$. Thus, the geometrical parameters define the left bottom corner of a square obstacle of dimension $0.3$. The problem is coupled with homogenous Dirichlet conditions on both internal and external boundaries. In this setting, $u(\\mathbf{x}, \\boldsymbol{\\mu})\\in \\mathbb{R}$ is the value of the function $u$ at each point in space for a specific parameter $\\boldsymbol{\\mu}$. \n", "\n", "We have already generated data for different parameters. The dataset is obtained via $\\mathbb{P}^1$ FE method, and an equispaced sampling with 11 points in each direction of the parametric space. \n", "\n", "The goal is to build a Reduced Order Model that given a new parameter $\\boldsymbol{\\mu}^*$, is able to get the solution $u$ *for any discretization* $\\mathbf{x}$. To this end, we will train a Graph Convolutional Autoencoder Reduced Order Model (GCA-ROM), as presented in [A graph convolutional autoencoder approach to model order reduction for parametrized PDEs](https://www.sciencedirect.com/science/article/pii/S0021999124000111). We will cover the architecture details later, but for now, let’s start by importing the data.\n", "\n", "**Note:**\n", "The numerical integration is obtained using a finite element method with the [RBniCS library](https://www.rbnicsproject.org/)." ] }, { "cell_type": "code", "execution_count": 2, "id": "9cbfd29d", "metadata": {}, "outputs": [ { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYYAAAGGCAYAAAB/gCblAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjMsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvZiW1igAAAAlwSFlzAAAPYQAAD2EBqD+naQAAh95JREFUeJztvXuwHdV1Jv5dyb4vrsRLRjwswkDsOI4NTCBoBHHZTmmiKnuYoX41ZcZ2gUL8GI/B40GV2MhgFOwYYexQyhjZlLEJk/mFgSRlUylDyZMIq1KOlaICpn6escGDgRFQloDYcCXdq3tBOr8/zt3n7F691tpr7+4+r7u/KpXO7d57d59z+qyvv/XqsVar1UJGRkZGRsYSVvT7BDIyMjIyBguZGDIyMjIyCsjEkJGRkZFRQCaGjIyMjIwCMjFkZGRkZBSQiSEjIyMjo4BMDBkZGRkZBWRiyMjIyMgoIBNDRkZGRkYBmRgyMjIyMgqIJoa///u/x6WXXorTTz8dY2NjuP/++4Nz9uzZg9/8zd/ExMQEfvVXfxV33313wqlmZGRkZPQC0cRw+PBhnHfeedi5c6dp/NNPP433vve9ePe7343HHnsM/+W//Bd8+MMfxne/+93ok83IyMjIaB5jVZrojY2N4dvf/jYuu+wyccynP/1pPPDAA/hf/+t/dbb9h//wH/Dyyy9j165dqYfOyMjIyGgIjccY9u7di40bNxa2bdq0CXv37m360BkZGRkZCXhd0wfYv38/1q5dW9i2du1azM7OYn5+HlNTU6U5CwsLWFhY6Px97Ngx/OIXv8DJJ5+MsbGxpk85IyMjYyjQarVw8OBBnH766Vixor77/MaJIQXbt2/HTTfd1O/TyMjIyBgKPPvss3jjG99Y23qNE8Opp56KAwcOFLYdOHAAq1evZtUCAGzduhVbtmzp/P3KK6/gzDPPBPCHACYaPNuMwQN/jfQGq/p4bIrJfp/AgONIv0+A4GCFufMRYxcAfAmrVtV7rTZODBs2bMCDDz5Y2Pa3f/u32LBhgzhnYmICExMcAUwg/0AGHf005BJW17hWk++vzvPMKGK2wbU5Q269TrjzmhTWlFG3iz2aGA4dOoQnn3yy8/fTTz+Nxx57DCeddBLOPPNMbN26Fc8//zz+/M//HADwsY99DLfffjs+9alP4fd///fx0EMP4S//8i/xwAMP1PcughhEY5VRHXUY0irXRl2GPF+fzcP/jOOMLg/foFu+P+mY/jXErVnHucYjmhj+6Z/+Ce9+97s7fzuXz+bNm3H33Xfj5z//Ofbt29fZ/y/+xb/AAw88gGuvvRZ/+qd/ije+8Y34xje+gU2bNtVw+hzyj2y0UMX4xl4LqcdKveZ67aoaNEXS5F28hlVId/U4Qx36LOl7sxATRxJTyvjmUKmOoVeYnZ3F8ccfD+AGlF1JmQiGH7288485Vsy1FWvk6zbSo/o7aNIoxhJTiEy0c5WOZZ0jjTsC4I/xyiuvYPXq+q6pgcxKsmNUfwyjhibuVOsigrqNv/W91nHtDpoCaAL0PdalMuaZtSW4Y9LvnxIF951yCkNyQ1Hjvxr9Ug5DTgwZg4GmDVSMEa1CBL00/L10kY0S6o4VaJDcRhJRADpZ0PUs7qb+kMMyJ4blcMc1rOiFItCIQFvXcm51KpWU8csBTQRoQ0FlTmn4czSyoIZfUhFubP/IYZkRQyaCwUcdhJBCBinrVTH+fTT0/eaY2u1azBtyB6dzQkFl3zCH5lAj719zlCQ0FdE/clgGxJDJYPBRl6tIWieWDLh1UomoBitcZYlBLPuh51RHbZrZTsZ+mJrxl9xa3LXCuZ8OMmtQFdEfchhiYtC+4EwGw4FBIgQrGUjHSrDe1ikpxn0mYU6/4J/roYaOEbShkpG3uJMoSXAH5NxGNG22P6mpHIaYGDKGEym3vzF39gBPCHWSQeR70IZbjH6skR/mrjETaHd5iMEh6J/jEejfQckWS4M5N5RPEpb4BFC88x9McsjEkNFD1Flwxq1lVQh0bs1kIA3ljJfF6McY+kFq79QLLED+DJ36iFFcqk3mVIUfK9BcSG5sDDm4Mb0nixEkhuxGGkzUGfG0koLF4GukYThnbohkiCQDFjL8VmPfRDzhOOO4ww0cO4SDqK6ONLURRRKWeIMWMxgs5TCCxJAxGohxH1lIIYYQpOMou6hxiSUBzfhbDb7ViGtI5e86M0ePQ3WisZAGVRshlxQgvD+NJPxJnALQyIHu7x0yMWQMIGJUX1VSMBIC3WxxC8WQQMggWYx+FVE2TMFqoE0cqQrJ2V6NOChJuMypYH0dx5DU3RRLDkDZvdQsRowYshtptJFSWDZl3JdICCEysJJAyPCH3nqqYa9DZQwD/JRYqQZNIgpOSdCAdjCA7ZREDDn0lgx8DCkx9LtCJyMenMSOQUywWZvD7TOQgm8YfCPMGRN6WlYi0E43ZPhTDHzdP6P5xPNIwQzk1NbY8ziCcnlBrJoIutKckY8lB26N5jGkxJCRwUFTjJL7iLGOEiEAMin4hqUKEWgEoBm7VCNflwvpUIVzaBpWonCqwn2X1OXk0mjdZ0aznoIEEUsOAE8G/rxmnlyXiSGjh5DaETQByYWUSAqxhFCFCFIIoKqBH8QK6RQcRtxnwZFGiCCAYuDaJwgaiwgqCAs5SNuawwgRQ44vDA9CBDGL+O9TGl+RFKoQgoUIJBJIIYCqxn2QAtC+keXAKRSrMvBdUL4BDxEEUCQJX0Fw6sGtXyCHkALw9/XPnTRCxJAx2qgzRqGQAqcSqhJCiAxiXUoaAdRh3Klxs6CXpHKEOZ7kyrKQhT9XGs+pCN/FFHIvseTAGflc+Zyx7FGna8lXGdagM9lkVQkWQqiLDFKqpetyCw2ie0nKEOI+k9i4B0cQrp6CkmUMQbDk4CBlHvWnfsEhE0PGgML9KBp2EVpIgVMJFkLQyEAy7lYiaFo1DAukojQrWXAKgSMUK0FI7qUSOWjKoP+qIRNDT9A/5u8NqhrvUDdLf5y//yC6v0zuHKiCIGtz7iMHSgqcSqhKCDFqIFY5DHMjPQlcmqhk/C1kEXIhSYqDFte5dFdNPbAxEylLSRrXO2RiqIxRN/oWxH4GGpFQ408D0VKsISVgTUBjCpQUOJUgEYIWZ5Cynbj90hoOGgEMc0O91D5IVrLwx8UQhL/fVxF+LQQlCB9BG0/JQaqEbhaZGKKRiaA6QkacIwd4c/z9vmqQ5qP8t+RCSiEFi1tJq4eIUQOWgjqKQYwVaKAFZ0CZKPw7cocYpTBJ9jm3j2+4XYwhRCC+gqAEAW991aWkZStJfzeHTAxBZCJoBvSCp+AC0z6hcMbfqBqaIAULIVBDFlIOve61NAjgeiBxREHBEQVQJgGg7OKh4yXjH0sQgPH5Ehw5UKLorTspE4OITAi9g0YSlCA448+pBgdjWkqIFDjDT/dZCKGOXkvcOv75SBjUymQHzo3D+fMBm5uM8/P7a3AxAE09uPPRCMLvCut7gVTVQGFxJzWrHjIxNIr+5yP3H7HWSCIJXyE4cvBJwyeHgBsJ4LOQQqTAxRPoPgshxJKBpAZi+y0BwEwrMKAPODTW/j9UsCapCUAuQgNkgnDzZ5jtbiytYPaNP0cibr8fbE5WDaGxzSETAwuNibOxj0Ps52WNLYTcRsI+znD6hjlECppbiSMba/O9EBnEVEiHjP/kor6/lzgyzp/vobFwWqnF7WQtRIO33VcPbpvVvUQv92TV4JCfxzDAyGTQO3CVoJYfRoQy0dQCt6QlnqCRgqWthj/ewVIUB/CG1WD8p2bmgmPqxvyh6eIGep5Hxtv/+++JIwmgrCYAPo0UsBeiUfUQ41465G2XVIPWFXYA6hccMjFkDDjoD8WpBktqqpCJBPDtLrhgc0w8QXMnWTuxhshAUgMMEVgN/3SDBDFHiEA7p/lD0wKhjXdfUpIAwmrCQhAcLOoBKLqXqEsJ4EMEUaqh98jEEIFW6/p+n8Kyx9jYF8iWEEEQK+IbYq6ymVMFMfGE2Apqf33hlEtkIKgByejGGP7xFdXdTIvHuobceuy5Q9Ol8++oi8L7JSQBhNWEQ6jWgLp6LOrBHdMdj6qBaNXg4LtPe49MDCVQt8UA0nkGQYV0G66ymVMFMfEEq0pQK6TDZMARgWSIqxj8aejGfQ5FVRB7rMVj46XzFolCIgnAriZ8cApCCkRz6gEo3vW7fZJq8APRYl0D0G+7k4khY0SwCqp6sPQp0lxI/rYY11FIJWjqgJCBlQg0wxwy8laMYxGLS4Y5dU1HKPR8LURRIgkaxKZqQqo3cOAqrS3qwY0DeJcSUFQNDibV0D9kYsgYMUTWLQC8WgB44y2RguY6ktxGHRWiqwPfIFqJwGKsx1HNbRQ7f5Hc4XPnOIfpIFEkkUQsQVjVgwNVDRxZmFVD/5GJIWMEISgHrTqYUwYA71ZKIQWxbcaSAQuoA0oI1HhyRtZquOtSERx8N1PofBYxXjoXShTRJLF05C6WlARHEC4GwZEDwKsHGndoTDX40rP59NVMDAXkaufRwRRY9aClqHJqwZ/jE4slnqBWT/MuI00dpJJBjOGvqiIcYt1Mc5guHZsSRRJJAN3Pt6AkCEFUJQegumpg4dft9A6ZGDKWN7QWFZoLyYfluQ2c28hACCEyiCGCOoy+NRAdcyxRKXhr1EISlCCci6kqOQBxqoEremPRv4f1ZGLIGH1Q4UCDjDRrRXIraS4ky3MbGLeRhRBCZJDiRmrKfRSjEBxMSqEmkugQRCo5AGWlEKsaHEytMvqDTAwqBigalFENkygbchp0pmoh1oWUSAophFBFORTn9dYyLS59YFLguX1Oi0tjy+6oKiThCKISOQCyUqiiGhwGxORkYshYXohRCwCvDrSUVC3raIkUOJUgEUJIHVjUQ3ucTgDTDVmkOSLXpPNYxESQAIDu+zOTyNLn6giiNnIA0lUDV/RWQP9rGTIxZIwQjKmqWtCZ+5tTDnQtKeU1ghQkQoglA40ELAQwUVFFLHjsqx3PJw3/nC0kEUsi4ysW6yWHGNUQKnobQGRiyBgxGB/vyQWdaWwh1oVUmF8OMmuuI2fErIQQIoMQAViM/5SBROYZMpbWXiByjTvHOUx13gvndkohiWnMNUMOQFg1xKSvDhAyMWSMIIzK4ThmqKQW/NehHkuGeALnOnIGzepKspBBXQSQOtcnDu1cFjok0F7PJwigTBIx8QiNHJQ3ppMDYFMNYLZxgegBQyaGDnINw2ghon8STUHVHsHJFbCxFdJpriObcpAJQTK+FuNf1YXk4CsD7bgSaSxgovCeOJKwupJC5AAImUohxKgGHwNW4SwhE0PGaGMK5YwkDlzQmVMLdIx/HKDgQkp1HXHKob19wRtbtC6+YQ2RgE1FhDOa5sHfcVuUQfsY5fOcx1RtJFEggxRyqEs1DIFCoMjEkLF8MIFumqr0WEyrWtDiCp4LyUIKmnJob0snhBAJWAhgGvOl7CLrXKBIIKH4g/8eNJJw5yPFI1gyEMgBQDneQMGRQ/uk2kjJUAJy8DkjY+DAEQGgV0OHnt3AuJAs8QReOfCEQI3rlMmVZCOAlH0+YghEI4wFTHTel3M5uTGaivAJwkoOmGFqHDBeVA0aLD2PpCC0u54GrNNqJoaMEYExG4kDF4SmhOHUBhDlQoqJJ3AqQSIEqg7KZCETgcXIWwrfFj23kHVtnzg0wvBJIEZFjGOhdF4hcgDAZypRcrCoBkAPQkuYwUBlKWViyBgBcA9sToDmRqLbBBcSF1eIiSdYVIKkECRDqxnrKpXPKeQhnQslDKcmfIJo79NVhE8OvuHvHr9MDlghFMAB4XhD+yTa8EnA4k6imMTABKYzMWSMPkKBZx+cG0mqlhZSU7mUVEs8IUYlaIQgGd+mq585N5J2TJ80qGvIvacYgtDIgT5YyEQOAB+M9kGL1DTVYAlCD0jWUiaGjNGG+6H6gecQaHEbmLnGuIJPBDGkEEsInFGvUgEdClrTYjXLmoBc7eywSFxDMQQRQw7dc+huY2scuDRWyaUEFAkBkFUDECCJ/jJEJoaM5QcXUwgpCW6/H48IpKZyLiQtyExJIUUhcMa2jirolDkx5OFnGXUDyHEEEUMO1M1kylSaaQEYk11KQJkQ3DbOfXQcAnGFKeS22xkZdcNS4+aTBKcm/KCzj4ALiYshWILMMaQgEYJGBOH01fS7VNoeI4Y8uIpnnyAccWgEkUoO5mC0S2Pl2l3QQDTAkwR1J00ikLLqkiryg3oyMvoHiSC42gfPhWSNK2hBZkoKdRCCZpw1ErD2O7Ku56CRB5dhBJTdS+1jlQmiDnIABJeSAxdvsKoGgPcOmVJWV6OXRQ+ZGDKGHBGtL2LABZ3d4RgXEqDHFYruJDnITEkhlhBSW2JY3UkxbieORKRqZ3/tVIKogxzaaxtcSjTe0P2Aym20rQ3zgimrq9CruEMmhozlBd91xNUvUEgBa6G6WYsrSM9KiCEFaxW0v550PA7WamYKrj2G1ZUkZRgBsotJIgh/zdSYg+pS8kHjw1wb7ZhaBsCQsuou2GYJIhNDxpBiCnJRm2DtpYwk5z7SgtEMiVhcSNbsI4kUYlVCbFuMVCJIWUcjD0oQNLjsxxmkALV/HqnkAHitvEkKKwC52R6nCiQXE6CThSkhqdnAdCaGjBGDQArWGrgQQcy0CmoBCKemViWFFEJIaY0xQVp8V8UCSQ3ljk1jBO1xPEGEAtRuXxVyAPgUVkDop+QuN+pOAuSCN6CmlNXVAH6pLZCMTAwZIwRBQcjxUhlSNtIS/NgCUHQhWeIKdZFCqE+SRARWEgg9N5pWFluO4RMGjRG09xdTUNtr2QlizpujkQNFIcZA4g2lfkoA36I71p0UbKYXch01E2NbkTJp586dOOusszA5OYn169fj4YcfVsfv2LEDv/Zrv4apqSmsW7cO1157LY4cGaDGIBlDjtUQfyDa3b+llkHqxIpiLyQgHFdIJYVpzBfmWlJa3T8fE1js/Cu8D8yJ/0LQ5kprcefhny99j9L79D+XcSwUSNRfy/+sJrzPtPv58iRfeu3fDEwypKe1UAkhqGgbSrIQEK0Y7rvvPmzZsgV33HEH1q9fjx07dmDTpk144okncMopp5TG33PPPbjuuutw11134eKLL8ZPf/pT/N7v/R7GxsZw22231fImMjJYaD9K39hbntdAspF8WF1IQBopSHP9bf4aPri7dovBp0+OiwWtMPaP66sMd35ORUh9kqzxB/9vt5amHNrnao83ACgHojl3EhAfeHbKVrxn7l3KarRiuO222/CRj3wEV111Fd761rfijjvuwPT0NO666y52/A9+8ANccskl+MAHPoCzzjoLv/u7v4v3v//9QZWRkVEJ0g2WphIcQWiuJ69Rng+pupkz8LGkYFUJ3e3lO3JJBYxjkf1XFdqamopw76X4foqxlCnmc5E+uxTlIH2XAFENAH+zsApp7ksHq8poEFHEsLi4iEceeQQbN27sLrBiBTZu3Ii9e/eycy6++GI88sgjHSJ46qmn8OCDD+I973lPhdPOyEiA4BJioT3QB103ElUIFheS/9pCCu1xvEEsumDiyaDwniLcQrHuI/+43DG7nwtPEP57dp8H/Sw1tRUCRw6l819BCLNud5KP3nqOSohyJb300ks4evQo1q5dW9i+du1aPP744+ycD3zgA3jppZfw27/922i1WnjttdfwsY99DJ/5zGfE4ywsLGBhoXsRzM7m5zFnWBGZqgqE01WdG4kzBCgbkZALKYUU6Dr+/PZ2vVZCUgEWt1JoPc5txK3vXEj+ozfpODdmAosF9xIgP6dByzpy81MK4Oj78LexdQ1c91TnTnLX1oA9kEdCUvA5Bnv27MHNN9+Mr371q3j00UfxrW99Cw888AA+//nPi3O2b9+O448/vvNv3bp1TZ9mxihDC+xRwnDZSAKRuNqF0t0j7C6k9us4UrCohBRlwI21/JOOY3Ehaefnj+EC1A5cBhanHGJcSm4ORdCd1F6wDM6dNCOMHTBEKYY1a9Zg5cqVOHDgQGH7gQMHcOqpp7JzPvvZz+KKK67Ahz/8YQDA29/+dhw+fBgf/ehHcf3112PFijI3bd26FVu2bOn8PTs7m8khIw2arzcUcO5USctBZ87odl/LLiR/vzWVtb1NVwkxysAaS7CoCi1tlSoELgitjfED1FoLDPn8i8FoK/yU1c42r66hA67YDdDjxL6LMvSMhj4gSjGMj4/jggsuwO7duzvbjh07ht27d2PDhg3snLm5uZLxX7lyJQCg1eJ/cBMTE1i9enXhX0ZGbbC0wqBYCjpzd4uUIPw7Vc4dNFUw5Pb6hpBKiFUG0tjYlFXrfEsQmhvjQOMP2ucVk93FKw3+ey6Buhdj4lj+nAEIOPuITlfdsmULNm/ejAsvvBAXXXQRduzYgcOHD+Oqq64CAFx55ZU444wzsH37dgDApZdeittuuw3/8l/+S6xfvx5PPvkkPvvZz+LSSy/tEERGRiPgFEFIJRge5kODzg50m3bn7xsqa31DextvNLV+TE2oCApLnIHGGPx50hg/dZTGH+JjBy4mEZ7DnX8hJrJ0g1BKW6Xx7gnY4wpsl1W6aG8a6UUTw+WXX44XX3wRN954I/bv34/zzz8fu3bt6gSk9+3bV1AIN9xwA8bGxnDDDTfg+eefxxve8AZceuml+MIXvlDfu8jICMGiEny3U8CNBAiZK8RHrRn5mPqG9jZdJTTtUtKgrUGNPyAHokMEUZUcgHIwWgJLCCjWNHSgVUEPWeAZAMZakj9ngDA7O4vjjz8ewA1o385xv/Cq7iYu86nIzK3W9RWPkVEVY2NfQPv7X4v2d34KupXPqwGc1B44BWANusHkk1HuquqykdagW7/gp6l62Ui0YZ5zH9EUVedGCmUhcS4kiRRCKkHbTvdJY7SxFmgxBh9UWdB52n63z9/mMpdc7MAZehdzcH/PYapDDE4RzGM6OH4O01jEeOeY7vXisfFOY735Q9Pt3kmHxrom4zDahWoH0W7DfWjp70MAXkJ73OGlv+eZ8W7M0tkBB5b+n10a5P5+AcD1eOWVV2p1uedeSRkjBO+GwXcHhVJVI+CTgg9HCsWzkbOQ/NdafUMMKUhEUTh/hhBSycC6hjXILO3394WUgwbfpRTqp1ScxwehXf+kAjh3EoWpgV5/kYkhY3lCelJbYYwupnmCKHc51RrjacFpjhQsKoFLW+XOnX1Pc/H+67lp3UdXpwtJemazQx3xBgf3PYVqGgAsBaHHy+4kDcdBdi8Fn8vQLDIxZIwIPBmt2SlLrMEfo2QjOVC14LuFumPkLBkuOJ0aT+AIhJ5raVsCGcTOd+RhUQh0f4gcmog3VApCA+1ryPrUtj4SgIRMDBmjDb+4zeI2UlSE5EZyCD1RLSau0B6X5jqyuJQA3qCPJzQ9XjSkWrpjpRBEE+TQPgbffrtMEmVCAJSaBizFGiZh63k3hYFzKzVe+ZyRMRRwgWcj/OBzcZmFkluoSlwBKKaiViGF6bn5wr/OnCPdfynw50v/6Dn452gJnHPpuHSbtcahPZcvGqRKT6qEpp/t1Mwc3zLFek2l1D80iEwMGaMLP4YouY8MLbc1NxJQLGjrHppXC/4+La5gMYh0HEcgHBEAMhmMHU7/p35GDEH4sBS51UEO7bH8a/qd0e+UIwQgfH1gApXVaq+RiSFjecLyDAavxXbIjQTY1UJ7XziuQI2eZPwllSCpAo0MqsBCGLHqgfsM/L99hMiBvubUADdOOx7XM0tEJcPf2+4PmRgylh8qPJQH4LORfITUghZX4I7VXiNc8UxVAmBTBQUs1PCPgB7H4l7yESIH7rPhHlAkqYb2Prs7KfT9q7BU3ndPpG/IxJAx+vD9t9qPTXn+Age/oI2CUwuWuIKWVURVAnf3TFWCg6oKFKOeBIUgfFDC0tSDvx2wkQMgPdVOdhlZ3EnLATkrKSPDGHiWfMztJcopqu054aI3iwuJnoe/H9AJgYVEAlWzY3xidcfwYj3ufFpL49y5uswmLnvJz0zitnFj2oftPtOBK1zzH+0JFB8rSudwNQ2d72UFOkrAJSUDYwOXaRSDrBgyli8scQag1DSv2wqjbF1dQZtFLbRf20hB87GbSUFSBoe9f1XBrcMc0+Je6rxWVIHl89HcRN31qGtJLy6oVC0+QEFmCZkYMoYQNQTiDIQQKmwDykbfB3UzSa23u+N1NwU1elIsoeQyktxEEhkcSfhnWVsgiMJ7FGIPocI9acxE4bUtCK25k6LiCwOWghqDTAwZQ4zI6Jz1h6o8xlM+E5kgrGrBvTZl4KQSgqQONCNvgUQUBoKwqgerq60zz6AaqLKj46xZTCIkdaDdmMgNX3uGTAwZIwCGINwPz/JwdtpRNYCYoHN3O68WrHEEjSSACEKgCN3xc/8sqIkgKGJdbkA9qqESIgonBwWZGDJGCIpVl+7QDHdnfpUzNeAu6MylqFpiC/Q47bm60fPVAuAZUyshSOrAavw10uCORedSMATh4N6jpR8T97nFqgYJljEquOusj+moIWRiyBhyMPGGqsE9r3FeTAFTHWqhEik4hNxFFNrdfEoqK13Poh7cMZfgqwdKDjHFbu61X/QmkbUDjf/Uph5iWrxHtoOvG5kYMkYEzO0XJ+FnhNeGJ7YBRTeSNegMFNtvT3h3smyWUSopxLiLJPLQSCC2wC2FIAT1YCUHySUH8CqNIpSd5J4HnVzPQG9aogLUvZMYmRgyRgvcb6fC70lzI7WXni8YfR9cbcOEQR1w+0yk4CPkLqKIiUuEUBdBLCGVHDiy9RGqcA4pBamRYhBUDQTVQe99TpkYMkYTFTI7UtxIQPtuU6ptKI4LqwP/dRQppKiDECGEYgrWIrpYglDscmqmkkOowpk9pjJmfMUipmfmOr21gqDKgbP9qku02d5JmRgyRhtSOwzp0Z+RaaocODcTVRShuEJUTMGhijrQxlsgEYVEPD40gliaS1WDFZzSs8QQKsUZJhfbLsnYG32TW6k3zfQyMWSMHmoM3PluJBpf8N1InFrg3EhUEag9fyRS8OG2he68Y6ueU4rauHXpOUj76XsAguSQohponIGrcI6tglZxHOJqGUQl0Vt3Uu6VlDG68H9k/t2YkThS2h5oQWeHmIfRsKAupCPkbzrOh6YIYovbuPHUsB1GuX/ShLLfrVlz2wj32fq9jrj+Sf5jP6UxSfATIfzPbQoD2VMpK4aM5Y3Coz+7GUmx8QUfoaAzEG4tbY4rcKSQUuCmxSViitss1c8x6qGiaqCvNWituP0xlTOTQhiAgrisGDJGH75C8O9EhSe80f5IkhspBKoWqDGRlENlUvAhkQEHi+Hnxki+cXr3b1EP3HpuHh1vAO24CnRJWuqkCrQJgD4Pmu/Q6l0rK4qKZJiRFUPGkCIQhHN3Xf5vW6thEKDdbdL4Ao09dMfJaoGSRTQp+LDchadWO2sIqYoY9QDo7xF21UAhpZZanvNsjTN0MpNcAJpDpVqG3iATQ8YIwCMJyTdtyUgCCumGVV0FIbUguTuiMm8sRW6SaydEBpYiNumcLKmp3LEoAi4lDVJrDAdaBd2eUyaASpXPUxhIwx9CJoaM0cVx5H+gqBSoL9dLVS3HAOLcSA5aJlJ73XJqqoPZhRQqcoO3X6tliDH+1rFa5pFW2GZUMLGqwY3hqqAtaavJiA2m97nDaiaGjBGBJwmkH5X241QCz9zdZsiNxGUi1epCSilyo6ipBVBnrTpbYwDB92ypbdA+cweJ7Lm01Yml7zqpBbeP6Orn3iITQ8Zow9JVNRB4TsUEyq00pIAzUIEUfFiK3CyKgCIlS8lCEPQYbp52HsIYqhp8SDUNkiKwtMcItUspYQCyjazIxNBBbyoKMxqEVgNkCDzTdgZSoJJTCyFY1AKQSAqWIjc3Rytw0/5JsIzTMqWku31LsB1yIBqwd1/1McF8n1Z30jQi26jUXKtRJzIxZIwm/B9dZCsMzeUgQXMjOZgDzlVIQTLQscVuqZCIwkoOFVxKPqRYQ1V3kgVqzyQtdtD7XnkiRoQY8t1+hgFS4DnQahvgDYTmZ/bdSJo7iVULQDopUFiL3WLaXsS0x6hCDpYsJQ+hbC7J3aMVslWClLIqqdcBwogQQ0YGA+kOTIgvAMXAs1/YRuGIIhR0Ls6JUAtAvPvIh9Yoj0IzqKlkIR0zlRysbirwT3uTXUd2109sRloHISXg7x+Q1NZMDBnLAwZ/Lg08cwgZ//aYolrwEaUW/NeWmAKYsW6fteCtLmh1C7ExB0O8IcadFEIobZWLQwRBm+kNcHwByC0xMpYbEgLPofoF7pnPPrjYAk1PBcCrBYoYUpDusqu0xAiB3vEeAd8SQ2um5+b42zgw+8ePAIsBo+t/F7SFxRTmMW909jslSVtuJOE4AIeqL1MXsmJQMUDRoIzqMN6xhe4wae2Cw9RS4ZTktqAEwbbT1tRCVVKQFIIl9dQKqeqZOy+LcrC4lCLcSSnpxyF1EPUUt0JsK/pUeoasGDKGGImJ4ZEVzw4WN1J3nmwspufm+ZoFzvBXJYVYdWAhCKsfnFMBdHuMcvDH+ustYeww0CLnNo05U2M7971WabHtSCdJQTSRIVYBQ6gY8l18hg9yPdC7MGrE6O9eyUgK3QXSoDMXyNQKoNinsfl3yk2QgqQOYlRDTN1DVeUgHV8Zy2UnSUpBao/RnRffUM895lNEn9tdWDCExJCRQUHIYRXK/ZE4wiAVzzQjqXgEv3BKDj5qD4j3Ywsd+MafS8WsixTqIIQY1EUOWiquFJ9ZAudOAnSyLsxXCMASgO50WR1CZGIoINdDDDVo3EDqR0MK20IVz6HumlJsQSKI8SNLaoHzm2s5/HSshRRiCUGqZ7DULGjnWpdyCKTgatlJ9LUELZmAbncP7VER8/znAXEpjUCMwWrM3TdT4fmtGYMPKtPpD1J5Ylu5EK18V+j/zRkQKUVVNB7+nXEo2JxCCtLxKGIMfmisT7x+zMAacwCK3yMTT2AzlrwYBJedxD20x8F3J6XEGSrFFwYQy0AxTKFoHXKMYuRBjQiXgRRonMepBprL7sNCBn7QuQBrsJmO8cfRsfRuPaQQ6oRW4GZVNhWK83zVILmTHKwZRdOYNyUeRGUoDTBGnBgyCSxbTKF4RzmJ7l2oUL9Qrjco1y9wKsLdbVrVQseNFEpTBbPNJw4rKVBobiFrUDmEFHLgzteSqcXNQzEIzTUxtCQX1NIagwPn1hwgjDAxaKSQCWPZgMYZSHzBoWw4isbAdVPt/i23wOCCm04tlHzgnAvJ3wdlvxtjIYVQjMBq+GOII4YcrKqlYhDaUscQ80zv2ohjQFphOIwwMWRkLIErJBIezOMbDu75zbSorb1N7ssvZiJRA2eJK0AY47ZZ78r98RIhpNo6TslY1YyFCKHsCwShQ9Cez1Acl9gzyYIBIYgRJQaLIqCxBwcazM7qYiTgk4MQX6BuJB/0zlCrXeBcFaVMJKCrFkKN4hAYw8UT/GPQfdJxFrx/9G+pKZ8ETT1o56utJREchXeekjvJR91xBhZDlvMy5MSQ00szIkDqG2h8oftarnaOvVtkA85+zQKFf4cdciH5Y+hrfwy3z60ba/Q5srCk1lrOh46RwH0uCUHoGEIIuYtGIeDsY8iJoQ5kRbDsMNNS4wsOWtDZr10YZ/6nKKkFQFcLFheS1WdPs31i7/4tkIgiRjmA+dtyntw6gXlWQx6qYZEQ9SS3AeyZNAJ1DBR1GPrVAGZrWCdjIOBnJBFo8QWHUO0CBxdbKAWcnVrgjJmmFKzuFO2u3JoCGoLFD+73NeJqDsDsc6+1ugVun4Owz9JxlcJ9x9ZOq7VgBm2X0ySAg707LIesGABk1TBscPGhSFeiZxymZuY68QUuTbV7JLl2IQpawNmHlRQOk/+l/W4tul5s+ik9R0saa0y7Duk4dB1pn6A+uCC0lplkDUBzUDOeUkxMH5XEiBFDFQOfyWE4sRrAVPvrm0E3jjDT3ly6g5yCOU1VVg1xbqQCpICzlHJZByn421PJIASJJKzkwI2R9mlxiECMoo4AtBWWBz8NKkaMGDKWH9IJPZSmChQDj8luJKcWtIAzYCvu0kiBGmbN16+haq8ki3F3x5HmWALwoXiCUeDVFYAOrlU5FdUp5MR28xHIxFCAb2RWC9szBhIujjCJbtXzjPevoyRaBTcSIKepSm4k7WE8QYTSU7V6hpBS8NcIBYCrGH7LPImguLWk8+RgjbUwa0mZSRqsNwPifE01+Go2ycQ0Z5dGiBiy8V7WcMbfCKlpnoPmRuqO591Jof48BWiFbJbsI7dNunvWsoLqhpUcQudkCcZLa0VAI/e2u5AnhORaBmBgW2BQjBAxaFgt/CtjsnAHYQhuzg9Z5cqog8YXqJKYXCypBepfpmmqDr6hCPmkWTeSpBaMgdSCweRIQyOFmLYTGkJxilRyiD0HeqzATT3bvJBB6ME9FpRUSMwzGQbk/naIicGakaKNK+77ML6H/w+fwxvxC9vSzz4LnHsucOedxnPJ6AkcOSiQWmxPdOIJ3d5ItKhtWlANZljcIaG7aOsxpLVS/3FrUKSQAyW6GNWgHX/BnpkU8x1WylAbAgwxMVhgIY/2mEks4lP4Dt6EA9iDL4fJ4dlngXe9C3jySeDWW7NyGEQI8YXxFYsl948D1xupu697N8nNFYPOHGLcJCGyoPNTUkOrIHbNupRDIqSn6/UMzceOKyOJGHbu3ImzzjoLk5OTWL9+PR5++GF1/Msvv4yrr74ap512GiYmJvDmN78ZDz74YNIJ87D0PNKwGkcwjt/BZ/AznIJz8KJHDsw6jhSeego4+2zgoYeAqQHRgBlRcCmqnFrQ3Eg+grEF343kZydJLiROFTRBCnVWQFvjBtrckGqwrqcgJQAtIaqRnvJscRZ9Jo9oYrjvvvuwZcsWbNu2DY8++ijOO+88bNq0CS+88AI7fnFxEf/6X/9rPPPMM/jrv/5rPPHEE7jzzjtxxhlnVD55GSk9lFbjOZyMd+F6hhw8UFLYswdYt66Gc86oHUJ8YRpzJfeP1klVciNxLiS2WR4HLa7g/81tt2b8cOtx86T+R5Z/2jFSM5UkWALsCmFwcQZJKVjjDJJLadh7J0UTw2233YaPfOQjuOqqq/DWt74Vd9xxB6anp3HXXXex4++66y784he/wP33349LLrkEZ511Ft75znfivPPOq3zy9UMih1+2d2dSGF4wd2y+WnCQ1ALtpFp41oKl/YVW+RxKP+UUhlTNzK1DDXKd7vG6yCE2hiKtLxwrpgK6MaOe4lToUxZTFDEsLi7ikUcewcaNG7sLrFiBjRs3Yu/eveycv/mbv8GGDRtw9dVXY+3atXjb296Gm2++GUePHq125iIktTAl/CvP75LDG5bI4WvYgH2ZFIYcfnwhVS34cQXRhaQVtGmVz5Irha7tgyMESxW0PzeUaRSCpW6CHlc6Jzomxp3kr1WhAtrBmpYqVUNHNdIbMEQ10XvppZdw9OhRrF27trB97dq1ePzxx9k5Tz31FB566CF88IMfxIMPPognn3wSH//4x/Hqq69i27Zt7JyFhQUsLHS/5dlZ19Au1Y+vzZsC1yy9TQ43YA/+GOfgRfwAXweeAn6GE/Gup/4fPHfmnyeeS8agoIpaKD3CU3IhaUFozuiFsnLoOJBx2pjQPmn8ccx+rop3AXLjPNrgzt/v5tE5HKQx2lz/vNCOM8xNl23CNOYwh+nCtgksmBrpjWOhNHeY0Xh31WPHjuGUU07B17/+daxcuRIXXHABnn/+eXzpS18SiWH79u246aabjEeQqpW5/ZY15uG6qz6Hk3EFfh8/wBc7e6/AB/EcTjOe23JEL56RsRrt6NyS6vO/PsPX7WIMvipwasEPRGtqobOO9rwFShScWymGFCxBaqvKiIFEInWSA5hxVmNvXVfBOBaxiHF23xTmsSC15/UwjbnSGtMzc5g/VAdh8DewTSGKGNasWYOVK1fiwIEDhe0HDhzAqaeeys457bTT8PrXvx4rV67sbPv1X/917N+/H4uLixgfL38ZW7duxZYtWzp/z87OYl2S26ZKptBqvBFP47+jGDv577gP78If4DmcVGHtfqHfmVN1kMYU2qTgFSn6QWa/uM1PVQU6gWd+1bmSS0BTC9Q/raan+kThQ6tsDqWzWjKOuPPQ1nCw+rXrJAdNNbhtdC4Hog7oelwLbk4pUExgAXNN/H5m0Gw1eiKiiGF8fBwXXHABdu/ejcsuuwxAWxHs3r0b11xzDTvnkksuwT333INjx45hxYp2SOOnP/0pTjvtNJYUAGBiYgITE2GG1iF9iTQP7ODSNtcAvT3vjdiHPfgCzsGL+BlOwRW4Cv8ddy3FHP4E78L1eA4nVzzHqujVE+zq/EFUycNz73dq6fVJ5a6qfo8kkpHkxxdOwMvm2ALAu49KNQsOoYAzl7Lqv9ZIIZSBU4UQtP2SQXZrU2MeQw7SOWjHpM9wSISmFCimMY/FgHIYx2KJZKZm5jB/xHaMQUG0K2nLli3YvHkzLrzwQlx00UXYsWMHDh8+jKuuugoAcOWVV+KMM87A9u3bAQD/6T/9J9x+++345Cc/iU984hP4P//n/+Dmm2/Gf/7P/7nCaXMGMdT0TjJIq7z/2+TwRryAPbge5+AF/Ayn4l34Ap7DxFLMYTvOwX7swfal7W9Ifhcymr6zbzJJOkRWqe+Nfr9TXWWwBsDJAN6AYisM2jgP3X8+KXCxhfZRuu21HTiXUgeaMgilsFrdR/4YkDHcehSpd6dunsVYO1jJgaoGbt3Q+qFjoE3gLW+/RSlQjBuUA+dSKmECwKHAwSxjGkI0MVx++eV48cUXceONN2L//v04//zzsWvXrk5Aet++fR1lAADr1q3Dd7/7XVx77bU499xzccYZZ+CTn/wkPv3pT9f3LoKwGsJVeCMOYA/+AOdgP36G0/AufBnPLc1/DqvxLnwBe3ADzsHPsQc3LO0/pQ/nGosq6iLFmGvHi12PGT+FNiFoHVU9tXDC6pc7asERACUFLubgEKxZoKQgZSZxaiGFFCw5/RQCKcwvzZmy3Hn7a1CS4NRDinKoqAKaxjTmMd9koNm5zfqIpODzNddcI7qO9uzZU9q2YcMG/OM//mPKoQKwGJiQoXUGbHaJFD6Oc/BzjxSKRv85nIl34cvYg0/hHDyPPfgU3oWv4jmsLS+dhBQDXrfhrvM4Nazhpjgj4vogrUFXMcygrRjWeP8EtTCN+dLzFigp0IfxOIgpqrShG3X5cNv8/6uSQgIhAF1S8F+bCMJflyMIy6M8U8CRiXsPNQSgrQpiCnNqQDpmrUHEiD/zmSMFqavqOB7CJ3AOnsfPcIZq7J/DKrwLX8UeXINz8CwewidwLu7HEVPUrk43UaxxbyLdt8JSlo/LkYD7Dfpf6clL661FsJuqrxYmlv7R5y1IpCC5j0oBZy7jSIo/AANFCtz2KILQ1APnIqJzOUNuiUVw4I4XSFl1biWTG2gJ1lRWM45D31xHFCNCDJyBtJMCABzBJG7Fh/ApfBO/gz8LpqS23Up34yF8CLfioziCEyucq4aqF17N8QrrctoP2u986v+AJXHn1vINhws6H4e2UqCxhjUA1izg5FNfwgkrXi6ohRPwcsmF5EN7bKeaosqRgr+fS02tQgqhtNMEUpDGBEkiFIPQXErSuBRw7iogmJnkY9jv9uvAiBCDg2a1wjUO38CV+H/xPhxBSxzj4zmcjXPxfRyJMr41+NerInZJ7kdkeVC59gP3ScBfnxoM/1xnyBhHDs6ldDLETqpOLXCkQNWCGVIcQYs1aAa5KikY/dKiUlhae4r53swqooaagtI8LYU18tg0AA3wmUnTmMOCQTlYaxxUTCJCKUwBmA2OqooRIwYOcUVvsjuIv9M/Elgv5tjJsCxpvYMPIfQb4O76pWNTBUDPh9vv9vnxBheEfsPSnDe0MLXmZZyw+mWcAPfvlzhxKUXVGlfQ1EKp944WgHYIuZAoaiYFTSU4UvBfJxOEpB4k1WApaKNzQjC4k4C0zCSKqBqHAQgsWzCixKAFnKUv0OLi0b78ITP4sTc59CPVjhv68VIjT+doJECP7VRCJwjdJoVpIeA8RdpsJ5MCRwQ+qFvJwepCqpEUQm4jnxS47RpBAApJcAbf4iryx3BxBn+bluLqjweilcsEFitlH8XEKwYNI0AMftGTtA/CmJSc+4oEUMVHX9V9A4T9+CFwPy7pPWnn67uDuPGT6Kac0n1+IHpyaa0pAGsWMDUzhxNWt2MKXbXQVQ0n4OX6SYH724FTBXWRQiD91AKJFKQxySrC6g6S9qeqiYpZUKHsIwdL8dswYYiJQbJGkuXzx2sdWGO2G8BNDRlhyaBaffYxx7P+aOj7kM4xhTgmmW1uu6tgXkXGFuIMLWByESef+hLGVywuGf82MfhZSNOYb54UHDQXkv+6T6SgEcLsa+3/VzPWIVpFcHf83F2+NQMpRBYhNZGA2rOPhgBDSAwpz3rWSIF+4REXQKqrJ8XFk2L4JaOvnXdIlVgMv7QGPU9KAnS7IwRfFQDFZytMLhZUgmt34YhhYingfDL+udQGozZS8GF1Ibmx3L4EUkh1F1E4UvBfxxKEO5+SgrCoBmvaagMEoMESZK6lw+oMetkrT8QQEkMsaiSFuu7+U+786zD+MXf5qetJd//SuFDqqhc7cCTgML302lcJbWL4ZSctdQILOBn/3FEOjcQUUl1I/uuYtFUCjhSsRODDJwVuewpBALCrhtD+OoPTCajUSG9yETg0PK6mESMG7bZa66WkfNl0Vx0KICZzx8Hqook1/jFrALb3rykDH1zRGk1d9VxFUzNz7WK1FcWH5QAoqYQpzJcI4gS8DADppOBDSlXlUlMlF1JFUgilnYYgEYFlPCWJ+YUyObCqIRYhldEwGVCEYglRAecB7awKjAwxSEHlKfI3N1YgBX+zxdDFqADOuGoXt9V4x7qOQgY9dLwQSdDPRPsc2GD0ksvIix9QI+5ASWBqiSRot1QrKbCQMpCoWgDKpEDTWP01weyrmRRiSQDoejS4y2f2NRs5lKAZei3OEIpB9MCd5BBqpDcKBXIjQgxWTAmvlWGSayRk9HxYiCA2s6fqfAvZST9ES3BcUgGAUr/QJYLObqISysa8mHrqCMKakiqhcoM8QCcFLRDtgxyjl4RA/6aXWBQ5xLiTNBXA1T/EYAEYA5bu6fknuVlgbaQ3vqIGkphCz+MOQ04MlkB0RIFbLCFYc/uruIGqzLUadqt7LMUtJpEAUAoiA+jEEKa9WAKNIXCEEOqUGmqKF4wrOFC3kqQWLKQguRGY/dbiNB8WUoixN/OIJwdzEJqDpgJS4g01u52sqazDiCEnBh/OQkl1DVPCdtRLCHWSQIwKsPr1LSRgUUMWEgyoAQCFYDKAjjoAug9sD6mEWFKQ1hVdSEA5C0lSC9QFlJqWGiAFS7ppaY48xYwUcuhAu8O3qoRRwCS6zwWrMqZBDCkxNJRTLKVMOljdI4AthTNEIqkqIMYFFBMHACKIT1YDQFERAGDJwP/b1SRIhNCeY69odmtTl5KpXgHQ3T+cyvDnWNNSQdpiG4LKdZHCLGQ9zpGDBjUITVWBJc7QY6LQlEFtNQ4DkqbqMKTEEAINOhvUQkz6pEMMGaRmBaUogVQ3UCgWormCCusUYwQOfnppZxvx83OBZatKAPT22T4oKUS1u5Ayi+hY381UQ1qqBM1lZLE1Uku2GHKIDkb3OvU0Mh7hXy8LGF92RW4jQAwVviwLKXAqwdIB1EEzrNx4/zh0v1UJpLiCTIVrvDsIKLuEgHKcACgSAVUF/nZHBu39MiH4+9unLHdJ1TKQzKmpkrH3s5A4NxMQTQqSWrAGlCVSiOnN6cZyBGEhhxJiA8ZOUTToauKSEIY9q6gqRoAYfKxmXgtqQSIFq0oIuYpCnUN9hPz+sWqgDncQVQMBFUDBqQKqAuRtusGnsQS3H0BBKbg1Q2mpBVJw4FxIlBRC9QoVahVSSCGkDqo0a9bUQ2GchRwoLMZfQkpm0hLaz9RIz0yKxkwLmB/rzbEqYoiJwb9MfUto+JJTSMFi6C1KIiVTKDZN1poe2llfJgGADxADReMP8HdenCqg28YLFrmoEAD52cztt9Md0/676z5yxwo9bGeMM/hSVhIgkwLd5tAgKVjd0iFScHFOLeuaI4dQMNq5k6KK3SoYe+t87rkMGV0MMTFYoMQWJFLQXEdVCIE7Jnc+3Dz//KRz9BETFzCSgIMUH6A+fH9/SBU4THgEYQku+3M4leC/Vp+pwMUKpLRUSgCcIrDUKlQghSpxAwcp4eUg6iEHE5qIMwxbBtMkBuZxnj5GiBg4NxID7gpOJQXVADNr+dtj00atTzyj52J0CQG8WygUKKbbdYKQyWCKbHMxAi4FtThvbunvskrwX4uP5eSMvcWlBDKGzrUWt9VEClY3kSUDsg5yYIPRTjVUVQSxGDayGAAMOTFY7lMMakHaT0mBUwla/CBECKF4QdLjL+2KQFMDgG7wLUHk9r4iGVBV4G/zA8ZatpE/lhKCOw9OMfh1CsGqZsDmUtJe10wKFBYySE2Fr1M5mFplODgjnkIeNPVV2pYRxJATA8WU8JrZJLmQQqSgPWnMIZRVVLWfkH9sgK0Z6AwzZgsB8URQ3r7gbZddRP42XxnQdWg2kj9echu586Ov2ZiCRApUAVCjL6WWUqVBt1dISQWKakEjhbrqolLIIRqOCDQDXrdxT1hPq3DmWnIP89PbgJEjBgO4u5A6SEGLEcQUztHxNZBBSpzAsr29r0wGHBH42ykZSGvQ4HP7tU4I3D4xphDKNOLUA1OZHFQOAcS6kCgpVCECrVGev7ZEEJQcQvGGnrqTOBdSdiuZMALEQC9ZoZOqphZ8hEghlGmUQggxAWRDa4lUF5GtxsCuCvztVjLw50uE4M7PQggAk47KZR4BYZeSlHrqxmvgCAXVSKEOQqB/awRhJYfO9pTU1RCshNLrOIaC6Zk5zB8arrqIISMGTdj6EC5vi1rwp8eQQqpCMBXN8epAIoNQGmmsMuCCxoCdDPy5UsxBCyr75yORgNtHK5kBpnBNIwVJPYTqEcCMofv7TAqWbCbtjl9TDyG3UlScwUedd/gDRBZYhfDNRB8xZMQgIcHT6V+knHGWSEGLGaQQAncMoFYyqCteECKC9vYyGfjr1UEI7m+JEADIriNATj1NJQUudqC4lGhTvKZJIbYFTxX14Oab3Em9REWC6UlLjCmY3Y9NY0SIAShfigE3EsBf3dbvXiKFPhJCP4LH7W06Gfjb6yAE97fkNgIU1xHQDClwMQdGLWhN8WJJoemeaxpBaOqhMfNJjbvV2NcUvLY893lUMITEkHjZ+Qa5qlqwkoIl3bSztr0baWzwmO7z91eNGfjzqmQlxRCC+1t0GwF215EbC8h3+VZS4GIOPhEMESn4iO6mah1fxbWTShIVUem5z0OEISQGQHYdBVxKklrg7tzrIoWYDCNGIYQIwUoGUhBZMuDtUwwHkS1raeukKgQg4DYCwq4jNx7gCcMynoOiJjRCAAaPFOgxGzGJsUadEgr9u2GS4J77PGqEMaTEEAH6XXFqwR83o2xLJYUGCAEIVx5LbqL2Pr362N/e3hcmhJgYRIpCcH+b3EbuNRBHCiDbtPH+nMCa3MN2UkghYzDAPfeZI4xhxRATg8TOU+V9sXKVcytVJYVAHCHmuQVWQrCQQfvUyoa9vT0ukMyt5a8xwZ6jvC3KbQTwsQR/O4R9gBxXqJEUnFrQCAHQi9esRW5W+BqbWy+mL5KfmeTGRaWspsQCqDqgazSoHqzPfR5GDDExAPb0VehuJE0tAPWRQiCw3AQhxLh32tt5MvDXlQLJ0lpUHcjnrasGtSMqoNchAPWRghZojiAFziWkFa/VTQqWdWqpbo6F1ZiH4gyDlJ46ZBhyYgjA6kbywakFDqmkYHQbWY1ocZtOCBYy8OdKikNbj1MIoXiIhRCAiFgChH2AriK0OoSGSSFUzdwEKfQalZ7oFlITA0ACOcYwUAjcz9CLhQs6A/FqAUgmBavbyEoI7e1yADi15iBmPavLKMaFxMYSAHt2kRRr4PalkAx3TANi21v0mxSqqobkCmjO2HME0qOMpBj4T4CbG7KqZ2AkiAFoW+CIS5cLOgMyUXAupIqkMCyEEJtdVD4/W1DZ36YSAhAfMyCZQCZSgGGfEneQ1EIMKWiqos7MpL7e51LjzymDVMMfUBBjh7HU5m4emMZQN72rGyNCDA7CJc65hGLUgv+ai1VUJAVrHMFamRwiBIkMQmsVt9sIwd8e4zICBEIAZKOfctefoi60Y6J+UqBj+5GuKkGrgtYC1X2pfiagT3CjtT7LmShGjBgA8VIMZTtoakGraq6JFKrEEayVyRZ3kT9XW8uaYeRvr5UQtP1uWyaF2sBlHKUguWdSKgLks6ioCv96riX76JD3vOcBz0EeQWJYAnfl0lsbOkZSC4Be1VwTKdQRWE4lhNiU05jguPZeaycF6/6qgWsUx3BVzZQUqriOuP11wGrgq2YmNdJptSbMTYc/Bfcb0Pol5TqGYQF3NyAZfO5vKStJ7chaDylY4wjtQ/OGPJUQuLWshCC/ByMhAHGxBBjGVCUFTiV4YyykQDEIpODWHZ1cmsEB+6CemRYwP8ZPGDCMNjEA4fiC+zsUWwBkF1JDpFCH2ygmw6i4PUwIUguOkGupMZVgGZMaaOb2w04KWiVzKinUVWOQQg7+HD/OYDkn507qSZzBGLj2s4h6gtx2ewDAqTvulyCpBS4LCSBxiWZIoe6nomlr+Ou0t1vUjM1lBEQQAlDddcSNSY0pcGuiHE8AdFIIEYI/VtpPx7n/qxJEL5TDILuTgHCwmXZWpXULUh1DflDPIINLneDUhKQW/DWkdNeGSaHqw3CkNeg61j5G3ePq7iVKCECNAWbLGpa52rHJ/tADdix1B1VcR9ya/rZUkoglB4tq0Nbsd1ZSXzAFueZlgNLNRoQYVsN0SU8i7EYC9DgDzUICCq0umiaF2LbXMTUNMYVplk6uSYTgb7OShjYmtg5Bq5mA7joC6mmEV9U+VFERkiHvS2uMHmMci8s6RdXHkBMDJQTj/U7IjQTIsQWAb4zntbqIIQWJENqH1UkhtbGdv0Z7ezhmEFN0BxjcRkC8wTcWl5lcR9r6DZNCSC1oSB0bY9T7Sg59SuqZxlyjcYapmTnMHxke0hlyYhDQCQYrY0JuJDpGSnVl1AKgk0IdriPJbWSdX6UwTdrmyAAwZBsBacHjGJWgzRfiBpYWF/SZCoD9Lr9uF5IVls6p9DwGRjk07HKanps3paz2BIeW/j+ijmoco0kMQNfIa3cg3AVHCYPLRCodq6wWgHpIwZJxlNq+IiX1VHMZATW6jfxxdQWY6TGtBXGwPU+hs917rT1gp1ekEFqziqHP6a6JcBeGu8YOSQP7gyEmhoiW26sgG3XuqjY33tPVAiDcWSfGE+pwHVXteErHqnEEoJ5sIssYyzG0McJ+SgghtTAspEDX58iBM/p03CiQwtz0VE5XJRhiYkgAF2gGim0v/G0+AplIAK8WfFDj2h4XRwqxAebU9FOLmqgUR/DHpYzxt1UlFUP2EcBnIPmwGvCYOoUQ6NxUQ70cgsshLGIcc5hmA9BVW2LkdNVhwAzi3UhAWS0wbbRj1UL7MHGkUKUVdgwphAgBqLkmgRvDjUtVCRHnYiUFS7sLLX21TlKg22JJoio5aA31gG4Ng9oraQF9C0D7kAiiMizBKHpt9iGNdUiJoSYBG+tGYuZwD9vhicAnjLKBjyWFWNcRdy4xz0YAGoolVFUJsaRiOBeL+wiwtbvoJSlIY0bB3dMvzGEaC00QhLtIJjFw8QVgaImhRnDZSX6lM8C4mVrgwKkF/3WRMMrG3KEKKdRRlyD1Nersr6NQjRtjWSe0L5R1VJEUQi4kLa6AwD6rK2qA6qB6g8PQM5OGuVCOyz46TtjeQ2RiAOTAtBR0BkyxhVQXUnt8PaRQ10NzgIYDzJZ1QvsqHkeqaHYIPa/ZGmxOJYVhIoRRj1n0r4tqb66CISSGyMvNmrwk1TxIQWeEYwvl13YXko+YILP1OQkW5WDOOALqaWmhrRPaZzmOMk4jBaoSLC0vCvOFuTFrpJqDZe9GGmY1MYG+uZmGkBgMmETRHeRaYbhfiXSxuHkUQooqEKcW2q/Ld/6WDCSHgSAFelr9IAUfWlGaNe4gwEoK1rhCaf3A/mFSCbVgAALPdaPeZz5PoRdP/h49YgjdIjnDPwVZJXAXJ0lRTVUL7eXLd/4OFhdScQ17kJnbpsUTgqRQV+aRpWDNuoakFJRtoaZ4nX3e6xRSiFUadZBCvwrQnK5v9Nj+DZvkDgYGh2wODcezGIBRJIZYaPGFQNA5VS0AugsptvCtSVJQYwlAurFumhR8KOO4imYOTWUgxR5vWEFTVUudVa0unwF1DdGW3Cr6HFi2YEXKpJ07d+Kss87C5OQk1q9fj4cfftg0795778XY2Bguu+yylMMGUOHehCtwc1CCzkC6WvDBVTbHksI05lRXUcxzl819jnxDbslOqkoKoTWgjDMgVKvQ2cfNVfZb5mvjq6JXJBPRi6AL7U7fYUDJYJQRTQz33XcftmzZgm3btuHRRx/Feeedh02bNuGFF15Q5z3zzDP4gz/4A7zjHe9IPlkZNQlWybWkBJ2B6mrB32/NWpKgEYD1ucsAcR1VDOwGx8Q0wePWkMb5CKgFa61CqJV2rx7JOcjoWzZSj1JapQfymGEhwz4jmhhuu+02fOQjH8FVV12Ft771rbjjjjswPT2Nu+66S5xz9OhRfPCDH8RNN92Es88+u9IJNw5JESpuJCBeLViykCSE+h6l1CiY4wnS3XsKKfhoghSU42kuJKlWIaVeYVDQ9DkmqYVU+IZ1QNVEz3sv1YwoYlhcXMQjjzyCjRs3dhdYsQIbN27E3r17xXmf+9zncMopp+BDH/pQ+pn2EtJVrriRgDi1UJxnVwuppMC5k8wP0rEaey07qYr7KGYNOhblsbHtLjTEBpQtGJYU09B5Dsv7qIr5EXynUcHnl156CUePHsXatWsL29euXYvHH3+cnfP9738f3/zmN/HYY4+Zj7OwsICFhe6vdXZW+8kZhKtLVZ2B3EiPwqW4EmhuJCAttlBcr2yOLG2zuXOwFK6ZqpiB9Lt3axZTbEpr6Jy48QwkF5IPy5PYmk8grI5eZCjV6kZKcbloMeAhcOEMCpKCz1YcPHgQV1xxBe68806sWbPGPG/79u04/vjjO//WrVuXdgJau20t4OyD+SVpbiRAVgsOsbGFEKTHbdJzkkhh7HANpMDFCiQ1UZUUuDW4scx7sBayhSqbpTF1YZjuQUNuJDEjyf3+3N8T5G8remjwLdlHo/B40CjFsGbNGqxcuRIHDhwobD9w4ABOPfXU0vif/exneOaZZ3DppZd2th07dqx94Ne9Dk888QTOOeec0rytW7diy5Ytnb9nZ2fjycGaPWYhCKY3kuZGAsKGvi61ENPmAlBaZQOq+6VykNkf52+PLUrjxoXGNpAe2IQLqUlYiCb0rIUYNVA7sQ1KLcIyQRQxjI+P44ILLsDu3bs7KafHjh3D7t27cc0115TGv+Utb8GPfvSjwrYbbrgBBw8exJ/+6Z+Kxn5iYgITExWuBO2RntocVYZyz1LQlQOHOtRCLCloSqEDSwVy6hh/HN1O98es42Acm6IWYlNT68QUehfYDhl9ywN6BqY3Ug8b7kXVLwwRogvctmzZgs2bN+PCCy/ERRddhB07duDw4cO46qqrAABXXnklzjjjDGzfvh2Tk5N429veVph/wgknAEBpe22oKisV9xONL3CwBJ2rqoUU9I0UJEKwxiXAjKPzDYjphcTBkppaOmZ42b6jaWO+uqkS2ioGPtKWz2MaC5gwBZlpNtLiMcatNAQFbtFf2+WXX44XX3wRN954I/bv34/zzz8fu3bt6gSk9+3bhxUrGg1deGjQE2u88CwqwYELQIf6IYWOG5Oq6hBVzUwRIgWLSoghhVQXkrFeIbZB3jAYe4qqd/exj/MchvhIa0DTXAcFSXx+zTXXsK4jANizZ4869+6770455BJ6nFZgCDwDtvhCeY5c5ey/tmQixbqQOqja4kK7ww/FE0KBZm28QygGQRBDCiH0Si1o7iTOANd5XMt2a/2C+tS2OlDqUBCesqiMcY/5bOQhPUOA3CspBEPgGdCVg+RGilULFjUggXUhUVTpR+SPCW2zuIRi4hMKpEK2EClYUlQHEVXv1mPm96So7TjhNfe3NlfA3HT5HVuL06o+B3qQ0SufT2/QlIY1BJ7ptlD1MoVFLXCIaYxXgJa/r7mH6BgOHHnU4BJqKgvJ2svI+o3W7W7qlWum7uNw8YVS87w6wakSg1JxRNDYc56HEKNFDCH4hW6RXiku8ByKL3DGHuDdSEB9aiGYhRQbSAYZ4yOWPCpkFbFQSMHaTtsHJYW61cIgpLZy8YVYUqBqofYgtv/7nBC2c39zMJBRHYTQv6e61Y/lQQyODCgSCCIEzj0UGpeqFhykmgUfrAvJ4papQy1Y19XWCdVbxBzbwzAGkwcNSaRg7WYcC+0hXD1GwSV1hCGePj2dzYLlQQwhGOseLIHn9jZ7mqrpuMbiNX9fMODsI9SZ1B/DrRUiD21dSwA51uWE+tVCDIE04frpR6bPasQbfe48kwPPUnxhxJ7lMIjIxOAwAVM0LTbwTGFxI/VdLdQZW4jZH0JkFlIVhFxIA1PMVQOs6ayNkBNth1EHNHUwOt6eRjHEWUnGn2ZK35WEOwuqHKT4ggZuXIxa6MxpSi2E6h/AbLOSi0UtSFDUgo/U9NR+u5vqPP5QEJolvkB/oxEGv44ahsrPZBhwZMUgQfneY9JEu8vxaaoSaaSoBfN5aamnlvRUa2A6BBtflmF0IQG27qlA/UFh6fJJMczDaIKSMpLqdPUE1lqc5FNVU0GJIiqYPYCV0EOsGHqAmRabqgrwd+w08Gztjmodl6IW1LoFhzqD0KEKZ8vaiT8U63MWAP0u3BpbWI3eZRnVYcKquIcs48znKHVV9aHFFOg6FTDsD9RpClkxVECscpDiCyFoQWazWrDcOaeOCdUtVChQU4+rwKoUlgtiSGGg3U0xDfKM7qWYu/s5TJXSUmkjPUo284eGj3xGmxhqSlGzNM9zoAZfiy9YH94Ti1JswYfWKjtlTGibhBpTTmNhLWirikExvFVJQWuDEXov0c9gsNYvWGF0T4WUwzym6umk2nDSRF0YbWKoEVyqKhCXkdQeX+1W1pKi6mByIzlowWQ6xkdVtaAdr6YfkaV7aioG+u46ErGuJn+8P66xjqoOmpuJIxAjqXDKwXVWtYKuMVdFLfRR9WZiqAFaRhJQVgGhp7pJ6yYj5QKroydSncfkjlNDQVuo0nkYA78+rMbeOo7L6JZIofHGeRI4lRChHAa7gV5vcuRy8DkCXA1Dr6B1VS1sizXoIcS2yIjtcxQ67hBAC0JL3VHpHE15WJ54TsdI69VVs2B1IQEJbiRLYZvkcord1iBKz2Lod95zBDIx9AhSsNmakVRci6m2jnEjVfHjV+2gmtIXqUZJTQ21JbNIa31dBVY3lD9uVphnWasqKcSohc7+XlUbG1VCnc9hsD68JxoDcFM0uq6knvQE7iI1VZVDlSe1lWDpokr/Tm2oVxf6+MPo8WUTjdSYRtWH9YQCzkEXUqxakO7ua4gvaM9hsGAOU9VbbnO/qQEgBIfRJYaGUJvfvyZEF7Vx6FWQq0oX1T6jqmtl0BDjapLIMtQXqTa1oHVUpQRiVA6xxW0LmGBTVQtramRxaCzqeP1GJoYBApeq6scRYjOgWPTTCFt8vJTAGiCtkEmoWzX0O4BdpYjN0l476EKKvUOnaoK+Du0zQjPkCxiPetbzqGFEiGH5fXGVSaKqbA392JtocxyhMmIyYqx3+4N+ldHzm2K2AekZSFJ6ameb5kIC4oLOHLT9KcFolNNLXUZSoxiCRwLm4HOfEGqs1zOX1SBXCPfx3FYh/vfbyxYZDhwZaKiSlsqNbyzgzBW8UWhupIjAs5+imgrqYjKvNaDPZMjE0ENULW4bWByHeAXiz5lEVwFIa1VQOKtfV1+RW2qGEmd8tXW08anKpQopVAo4A9WCzppbSmuD0YOH87jYgwruIT0DjhFxJVVEQ/nNKe22uYyknqgHrZtqVaTeQfrfS2ANqdW2BPpT5gxfTNA1BVPKP218CupQCtKcwv4KxWWl8XU85Y2MrZqR5CMp9pD8++ptEUQmBvf0tlXoy+P/YtGXrKgY4lzmT8katOwk6SlsMSatslpwCKWgamrBGl/gxpJ156anOu6jFMS2yRBhIYk+JYssX2KQnve8zA1bEFU/H8vvqYbvoK7uqimqYVDIISYlFeCDzTEB51KFM6Cnj2q/v1BNgiVN1QA/vmCJM1ge0OMTjrmzKhUEfQ5QL98YwyEMvEKoJT21SfixgZT9lrET6AahpbhETagzeBxLDlWPWzWzKpSWygWcgzUL/jYuBdX/O0UtRKiImIpnmqrq1IFWw+CgEovF3TkgbTOWLzEAbcMyExxlRswzFjJqgEcOU8fFxxmskDKUnLGs41vnDHuILGLJJ7VOIYoUuNRTq6vJohY0A8+pCG9blae2xSqFIAY0G8lheRPDEGHg1UPVzKQ61osEl2GUohqoyajr9qAul1Rq5lEpQG8tZJNIISUTiSMCmnlE01QDaqHuOoVFTFRbcwBJYvnGGBzolzJA/Ur6gqbcaxYpLx1by07y5vhGqu6Wz6u8fyFYMox6Ae743HvgYgkaKZQevgOEg81WV452/Wl1CoGYA81GqquQTVMSlZ7F0GdkxQC0fdgNdU+r44lsGuYwjWnMYW56qtRhtW9o+m7fuP7URDcI7QwbrWeQVAMgKwd6qYTihLHkYP0WY9a11iZYCKEErV7B3+aPleoafMQ+1c2QjUQRE3im0DKTSi23hwyZGBwOYuCD0T4WMd68e6kpA+8HlOs4fkSsgSt2056Z4KC5l3yjW0cySZ0qI5UQAJkURKUQCkBLcQJLawzLMxro+SDejSQFnim0GobGW2r0ANmV5KOBnOHK7XmX4AJboYuuzgKeWhA6H6uLIZSeGOFSWv26sr885PZZjbLLhcMqxLmdmoB2fKtKqEQKnAqIqWvwYVELCW6kGLiuqq7dtqoUpLUtMnCAYg1ZMfQQi5jotMVYwIS5MronCN2dW+/yq6KBNFTfsPn1DZx7yTeS0m/ZqiSAeLeTFTGkY61nYIPLqaTgI6U1hkUhRMQcqBupibt6cU3actv/HQ1oy/lMDDViDlPLI2W14XoC8ViUnCiZGVxKztCFCAKwpaNSoxtLFCE4IomdpymbkNsIKCutaFLQit1CSiEmtqDEHEJupDo7qYpKIaVP0gCQRXYlRWJY/IdiQY8lVTDVHVWlbXIqlDW1Lp9TE2Xjx90xA3EZRlaXkxWxLimtBYaUbdQYKcC4rWpsQVEOFjeSI4iFxBYZkk0wVz0DvFrvo2spK4YILB4bx/gKe8DX6i7qiVvJEsitM9gc45qKOW7IpUUUjG/UJAXBqQcHSUV01lROJVZNxCD1Gc+d+QG3EcAQaywpaHUNIRdSSmxB2B7jRrIEnn1I1dDDnKoKjAwxzKPpjPG5Q9OYnpFTT/34QV2oJfOIM6TOeDqDbBnTBOpqd6G4lHw4Q0cJgnMvOUhups5c8ncMUVBoxBGjQKRfgqiIGNtWGyn4iCWFGIWZ4EaygAae6T4OaqqqH2TiFMGA1FFlV5IBUZJQgKWkHgArZ91FHbqYg+X+lh+aJudTi8a0lEaLYQkVM3FjJiG6xKaO6/4rbGfcSw6cy4VdG3a3U+kYyr8qx9XOnVMJtZJC6rWj1TnU5EZK6bAaUhOqqznmZoe9x+zdY6AyMdQA7mLQ85yrqRtKFKW7IWoQtThCaqwhdHeooSly4KAQBKAThJbq2jRJWNcNkYHkMuLeH0sIdZACmG0WF5I0hx5fcS9Z3EiNB6CBgVECVowuMQzQc1W1WgaJQELGPxmaarBUocYEGTXy0M5DMzTUONHz0YLuAYJgtxtJIkQUVdtkWOfGkgHAkCNHCP73P8FsBzPHIdWFFFKGwuuUbCS/sC0F6u8zlKio7Wf3NW/cRiTGsHwQE3doHQeMcamezievxRHoGB/aWv42CrqWlopqncfNdYZBOgcH8r6kGERnvxKLAMKB68Ja8q5oxMQOOvtCWWtAvcoulRQS1YI1G4mDcxW5+EIl0BoGh1pSUptLjR9dxdAjcBeXXhkp73PKYoGoBO4YjaXNWtxOFNyPl/7w6Vp0HD22ZZ6mHvwxkSpCikF09it33z5i3E4WUIUSUgel7dr7CrmNYkmBKgt/bCopRKoFzo3ExRlCaapSxbPrqhpdwzBAFc4SsmJoGFoqamyaqmuY56sG99rto6hFNXDbpDt8TjnQO3ircqDHdwYipB7AnFtFFeEgZTR19hvVRN2QSEqr5TA9wdBK1iGCr4sUItWCNaZgbV3jqwl1nJSwov3cB6g2drQVwxH0POijtuFV9rm7kZjeSuxFn/ggkgKsgeiYVEVuTGqxlCVewSkINzZkLCOD1YX9RjWRAn9t+s98npPg36OmwLjPrA5SSEWkWuBiCpLS15JGrBBrGAYo7hnC8lAMPhPX6NyV7tJtc/X2GQsYx4SnBDRlwO1bnATGl+5+k1SDGxdSEqFaBDqfUwFcbIKuC2YeyFw6xq3jwMUhuDnc+gQSOfiKoglykBCtDBw0hcDtj3UFam7IHqsFqxspNQCtQoopcG6lASCQ0VYMHObRmI+Pxg+sdx9uXMwFqWUrubulpE6r3A9YiyEAcZWv3N+Wdd0+a+yhLhUxyfxTEIpPVIG/Nv3HQjpf7jMKZXhpmUpuvr/PzQEZV9WFlKAWfEhuJPrb8wvbJPjPcej8zxW3SV6LqAB0b/1MQ6wYZlHp9t99KSHjeWQcmKz+3IN5TJsf2uPGOtVggZSt5JSDWTX44OII1jv8ULwiRjkA5bv9UOzBjXPg4hDcutx4CiUm4aMJchBhuQmQzic26C/N9fc3SQqRasHaPE+6kaNtMurJVqo2vWksP8VAcQTylySkmknZDT6smUnd2EL4wR9UJWjZSoW7pqUfjNhYj0JTDRq0u0a3TbjjY8dKa3Nr0fkUdaoIekzpX92IPdZx5J+PCfAqgR6LrkXnc/t7QQrHdfe1jute45Ja4GMK46WYniWwHAXrjT5ng2pJaU3DECuGmuHuHN2FNw9WkMQ20msvbc8+cmNjFAaXrQRAf9xnE6rBMp7O4dSFPw4Iqwd/DDWSsSpCymbyYU1oaIIcJFhJP1Q0lqoQ6PymSWEJnAvJv3GTXvvgbuIqKwKgoRqG3rTFyIqBQshkmj80LWYblNWDLTNpzhBbkGoarDUONN4QVA3cD5vz71ru7q0GR7tTdfu1u1XuHOh6mq/dB3cnLc0L/asbsceaYP5x6zmkKgQ3l8s+iokZWEDnw+ZC0lxLQDcN1QfXOI+CxhfmDk23U1WHuIYBGDXFMI9m7tKEOIMzyn6WEO2yOo8pTBn1pBub0oabZiv5fzvlUIo3xMYF6DaLcpDG0zmWuEFIQdD9FFJsQJpHDWls89xexhisN7jcOVkzjbj50g0CRzgaKSTEFSwBZ+k150YC+Js6Lr6Q0oBPxAD2UcqKIQQlzhAL/0J0UlVTF7QS2gL/YjUph5SaBWmsZAhjlANneGIVhOVuWltXmq/dffcKnAqIUTc+tDhCSpYSHcepiCqkwLiQqqoFyY1Ua5yhe7Ay6D1jH+MKPkZLMfQAc4emgRmwcQZ6154WW5AVhlTTIP1NzymoHEIKwR8HhJWDVuMAYY77G+AVBJ3nj0vJNgrFJOh86Xj9hlWdSC41H6lZSpqx99etQgqMCylFLfiQ2mhXaarXwWG0r6kBqE2IwZARg4FOjwCYqelwJAA9f2gaU8zDetxdSCHwSwrYfJJw+7SH+6QEoX0kP+THGWnfeFuNfWwaK50DhAnCzXPnxq3rjuuQUthGwbmefPTCHZDimrIQAVAtKK3FKej6nGsokhQsAefOfuG15Ebigs7Wp7kB6MYXDo2FM5JovGGAXEpDRgw9hN/jRwFngDWDzxl6RxR6XyW9ElojgkrxBme8myQHoEwQ8MZJxpwjFjBjLSQhzaXn6aBlO/UDodhaChlw66YSgr/doiYCpLA4WSQFBz8pg3u9UFAOfAsMKehM4wtc4DkZlET6HKTOMQYOnDBhsgyscQbp4guNT5Gx/jlVijdY3QLS2NB4yWetZcZw2yxZR1qcQPqItVgDPS73rwnEHi/0/rVxoe9Cuj64GAWNO9D5mprw9mtxhRgXEnURSbULdfVOYjEgsQQJQ64Y5sE++JCybdW7uUNjwEyrsEmqZ9DiDJwicOpC651EK6GtsYb2+onxBkBWDkC3wyqgZx9R5eDGw9vvoMUg/P3SNs5ASopCqoT2EappsFZHN4nQtW1RBQ6aOuC2ae4guj00ViMOlEmBiyvEupCo0ZeCzrUVvR0CX1BL/y45DaxVcvVhyInBCPoD1r7jgwBWeX8zhW5zh6YxPUPdQXqcwQ8qO0PPkYElCM0hhRwoCuTQPpk4V5FvrLX4gZQGygW1HXxS8seE/P2SC8gSJwgRRl3uI47wUqEpIApNaWh/x7iNpPERgWiJFCQXkoMUcKZqgUIKOlM3kgku8Byb6txnLA9ioKD21l2QCwhmmnAB6Jg4AxdUjglCS6qBO58QOVDVAAg9lVLjCJb4gZvbfcNxKoKuRfdJ6/hrafO49S0evhhDYCWDGM+iVRVIY0NEUodb0aAmQqRAYwn+PvpaUgupQWexsM0FnlOCyQOSvZQUY9i5cyfOOussTE5OYv369Xj44YfFsXfeeSfe8Y534MQTT8SJJ56IjRs3quP7Ak7eAeUvNjHOQPsh+RdbTCV06AlvXHwhFHPgOrG2tB8xUM5Pt8QoJJ81NUDW/HlpLWndUFzDGqvg1uYg1RtU+Wc5r9B75OZx63HzweyX4giWuAOUcbCRgoPWEUBTC/T3F5Ot1Hv0zqUUTQz33XcftmzZgm3btuHRRx/Feeedh02bNuGFF15gx+/Zswfvf//78b3vfQ979+7FunXr8Lu/+7t4/vnnK598ozAEh7gWu1RmasY+VPCmBaH7Rg4WFwEdn0IS1CBajZ4PiwGU7oxDhKEZ5V79iznnmM8hlAjAfTeAjRDoeP9vIJoUNHeS/7wFqhb83xQ1+nK2Uk3Vzu5GNKQqVB5otmfSWKvVaoWHdbF+/Xr81m/9Fm6//XYAwLFjx7Bu3Tp84hOfwHXXXRecf/ToUZx44om4/fbbceWVV5qOOTs7i+OPPx7AfwVwFtpO/1VoB56nAKxFJxAwhfYFN4P2RbZq6e/jlvbNkNeT5H93jdB5QDsAPbnYcSVNz8xhfMUipjHXcdO4186FM46FThzBBZ6nvL+dO8mNCY1v/911ZU14x23PL/4d2uZvdw33nFsJ8NxKQNE94m8/Imync6QxdI2YtaT1Qmtb5qXmldedcRIbyNYUTchFpI2VAst0De6mQhrPqM1YUtDcSX7rC9/g+2rBBZ3puPIYPU2VdSW5GMM/o0sIlBj81y+ifZ0fAvBL94nML/07gDYhHFx6PQ/gBQDX45VXXsHq1UwiTiKiYgyLi4t45JFHsHXr1s62FStWYOPGjdi7d69pjbm5Obz66qs46aSTxDELCwtYWOhagdnZ3nQUbB8c5R8AE4Cm0OsIinUKoUC0NF4rerMEn6WYQ+m9hGIOQPcHrRXDuTkOXNBW8/0fR8ZwWU10PX+8gzUAbYlVcOMoepGRZHFnSWOsROAgGXe6Vgwh+NuJSgDiSKEzhyEFByngTDORtKCzBpUUrPEm9YaihzYQkcTw0ksv4ejRo1i7dm1h+9q1a/H444+b1vj0pz+N008/HRs3bhTHbN++HTfddFPMqdWDQyhXTTOFbjQAzWX6dA21nI5qCUSHyIF7mE8sOfjBaACdgDQgPOSnfWJt+ETgAtOSwY0lCSnQnJotFApAc/M4ErAY5V5COx+NpCxEII2tORDN1igYSYFzJ0kupO64YtxAczU5RGUjxWKAqp6BHhe43XLLLbj33nvx7W9/G5OT8hW7detWvPLKK51/zz77bGDlikEZJ+8o2G1FH6MUZwD4wHRsIJqOKa7BB6Olc1AfB8oUwAHFIjg27gBUiyFAGWcNNNM1LcFa7nxjYgm9QB2xBm0tB+lzC30fUhyBm6OM51xHsaQgFbK1/+ZdSO35xd+ZJVupVoJwbiSKut2RkYhSDGvWrMHKlStx4MCBwvYDBw7g1FNPVed++ctfxi233IK/+7u/w7nnnquOnZiYwMREj7IAjoC/q6L1DABb6EbBpZFS1cAVunGqgaoMrrZBSmNtr1NWCdp5cgVwQMC1BPCN9QDdPeTGcirCH5eSZqo1uZNUhbVQTjpmL2FxVWnnZ1EE2vGkGwR/n2GO5joC4kmBCzZrLiQHrhLahxR0Nj1/gYMl8NxnRCmG8fFxXHDBBdi9e3dn27Fjx7B7925s2LBBnHfrrbfi85//PHbt2oULL7ww/WxVJKgGqR+JpT0uUOqNoj00R8qTbh+urBpolpKmNGKUA5eVpLXO8DOWzOohJdPFrRO6a6VrWRUKdwztvEN34v3850NTEaG01xjVIa3N7ZO+46U5/vXjX1e+SkghBQdKCr5rSEtPDamFYFZSKL4geSYGENEFblu2bMHmzZtx4YUX4qKLLsKOHTtw+PBhXHXVVQCAK6+8EmeccQa2b98OAPjiF7+IG2+8Effccw/OOuss7N+/HwAwMzODmZm62qB6sPDDceADyu5LS4gz+NCKz2IC0ZLS0B7oY1EOnEpwF7wbB3SzlbTYA0Cqpdsn0YUWQwDkiuZQPMKH9ljPUNyA8rW1yR63Vl1IVSOSyA6tZw1Ga1lJdB3hxkGLJQBx6dcWpUCNfXueHHAuu5p4tyvnQhYRSwgD8JS3aGK4/PLL8eKLL+LGG2/E/v37cf7552PXrl2dgPS+ffuwYkVXiHzta1/D4uIi/v2///eFdbZt24Y/+qM/SjjlWQRThELgOqdygWdXhVgyOOUnumlZQamBaEB2Q2mZSiFy8EGJgCMIt89EEEC45QUQV9GsGW86h1vbX18bzx2LQyx51AWrd5U7p5D7yRqI1siA7mcIAbC5jbhtWkoqIJMCTTt1CPVN6r7upqj6SHIjhTAgrTOi6xj6gWIdw0lo1y34dQzu/8RaBnjjJ71tdK5bW6hnALp1DO41UKwjcBlHMbUN7TXC89p/l2sc/HOh50O30e3aPheD6Iwjd0Vj3N00vfBTaxo4xNY5xMr6QfMJ16UEfMRmJHH7A4QA8P2OYlUCYCOF9viua4irWXCvad2COyatXQDAt8EAyq4kv3bB/e9cTlINwxF43o95dOsWBrCOYSTBKYWEtFW/26rmuokJRLuLNMat5C54F5AGEFQPnHvJbXfjgbK68BUEgIKKAIpGgVUTob5IgN70zp9D13br07mhIDOH0DlICBFJnWojhQQAu/spggyANELwt1uUQyopOFgC01IGUocUKDhSCMHNEVEx6zIBy5sYpDgD56tW3El+t1U9vlB0KRVPRXYNxcQcAKiuJYB3Gfnb/O0OWhzCdwl0P9ildSwkYS18c9DcQv5cjig0QykZciuBOKQSSerxfFhdQpZ5FcgAsMcRQtv87Smk0F1vqjNHikF0CaToOhJTVJ1a0EDVgoOUqlpA70kBWM7EEBNnMKatOtXAxxfCgWiHKuRA5wO8egCKSkEjAfc+uH30xyLFIgCFJCyBZuudPhdwDj3JzaHqHbxGZqlIOafUIDRQKxkAPCEA8b29/G2xpOAHm7m4ghZwpte3+KS2mPTTAU9VBZYjMTgCpgTAqQJDewznTuKe0RAbiHYXahXl4M8HECQIKwm4/dI+br/kagLKJBEVuPahtb+Q7ty16mkLpFhGLwLRMeedEoTm5lUgA6Ca28jf5re4iCEFbg6X9i25kDi1IAadnRupKlSh0LyKGFJimEf5Nj4ATd5TpWBNW11yJ3GxBq6oTCs4KxryNLeSPx+wEYRDqivJ7XPvj4X3m5JIghobgFETDpasIL+Hk0NVF49WONdrxLyHGoLQdZOBZXtVleD/rRW8hVxInddciqofdPZRJbtIjTf05oENQ0oMRvj+PIlHaJyBcycBZUXh3ElMrCE1EA3ovZEAqHUObj4QRxDUveTOGwi7kvx9DjHxCOpucogmC4fYeIUE7sfZz2pnDjHvJyEIXYUMgHoJAaiPFOSCN96FVHitBZ0puGykENQxvWukN5rE4Bg89MPh4gwUztBwj/v0Yg2cSykmEO1nIGmFbFoRnENIQdC1uPhDex1dRXCwjPHXLweuZbJor1/GWCgzKcagNxEnaBox708gVY6Eue8ghgzo/hii0AihvS2dFLrH4lNT/fPqbKexBS7obHEjcWmqDqrK6G0QeoiJ4SDa9Qs+uDQjAZwyKKkCZowjE/9QRpeSVATnLmbONUThu5Z8cnDz28cpkkx3Hp+9BJTdSzEqghvjxlniFT4ksuii/ANRyaLXbh9r6+4mYHyvHAkANiIA0slA26e5jdrbyoY9lRSkgjdfsUgupJJakNxIMdXLdcUlasQQEwNQrIKOIAVuKBdnsKStKi4lH5JLqWg47epBqnVw0NYBdPcSgCgVAfCtA2IRUhtRrqjEcwgkHnaREoCWDPdCYH8EJKPPIeQa6mxnvhPN4NP9MWQA8ITQ3i6nolYhBZ8INBdSBzToLNUhWN1HA4ghJwagbeUjKv6o+8jd4YXiDH7aKlUNgksJMyioBo4cAFpL0K1xiGmD4ZMA0L3oqZsJsMUf2vtkFdE+VjkzyUFrtdE+XzkuEVqPTBQQL72luIaD6rKqAmWtGEPvILnhKCxqANCbQ2rj6iYEfzt3x8+RQtjlVCYC6kLqnIeficQFnaWH8gwhQYwAMQBt5aCQg/9lhVxFobRVtz/RpaRVHYdcS6GgNBAmCEsGU3efnSQcghlKDDS3kgO3Xro7yhvrtfUIGdRUFVInqhh9dlzALSSNk8Za3UhVCaG9vl0l+OMoKdDU1M76tPWFgx9b0ILOFP2pVUvCiBADA/9L4LKMLO4kus2pBkoOgClLSVcKumvJUuns4LuY2muVg9QSQbTnx5FEe0xchlIIMWNT0In7RBCI1Sj3Apbztnx+IZeQNpYbbyUDII4Q2mvxsQR/rRRSoOc+B6YfElB0Ifn2RYoRcCrBDzwPMEaXGDRw2Uhc2irQVQ9ONXCV0IYsJS4YHeNashaztU+HVxEOEkG4NTSS4MARRRWE3EpV5ibHRJrjqEoIvY/Q52hVAjFj6bhUddBeq6wQ/O1pGUtFUhBjDFxcgWuW1z3xMhlobqSUvko9wvIjBs5VVCpcA+9ysriUDo0BKLuUgKJbCeBbUkiupVDGkuUun8tiktJcu2sUSSV0HP94gBzErooq5DFq0D6HfqgGTRm091cnBH9d7SFWlkBz6W8vNbUUV3DwXUhULXBkQFNTJRS6qvYPI0gMSnYS2/cIRfeRlJ3kkwMgu5Q684ouJQAd5QCUg9KA7lqioAVtDlNkO1f/4OZLWUwSLGqCqpZRwKCTUC9VAzeeU4saGbT310cI/noxKoH9W0pNdaTgG3jfhWQNOke5kebRbbXdW4wYMSik4N/tA3w2EudOmgGvMmi8wZ/vxRvmgY5q8NNYQ+rB4lpysKqI7nY+BuGjDjVRHGsjCk1ZpAajmwDNsuoXrIRVVQX4qEoE3H4tqEzXj09hjSMFc1yhe0JtxASdg622+4sRIgYlM8lSoyC5k/y51KUUkcIKoJvGCl09WLOWNNA4BFDuutreVySJ9jGrqwl6XG68g4U06nZFVQGX4kh7X/XjXEKoqgJ8xBIBNyZGHdD5tkK3coaUhRQ6CMUVfBcSbadNjf5h8DGEAStscxghYmDgvkyfBGLcST6BcC4lRw7uGFIKK9CJOQAotc5IyVpy4NJbfcSkpLbHVFcT9Ljdtbu3TqGANgV95Gkq/OC/Bf5nrhlWru1Jk0h1bUlEYlEBxfHl7y9GFQAoXVcpCoHOC6kEblsppgDY4wp+0JiSAUcEXKxBKpbsI0aEGKgPSHApUXeSNpVTChI5AHy8wX9ugxdzKBTBAaWsJUB3LQFSczsbQQByfCB0925RE1pLj6ZQd2YUheXOPJZ0mjwXCdJnxH3v2ncYqwgcqpAB3a4RQntbnEoQSYHGFbon04Xbbg06W0ikjxgRYvAhkILlcZ1sEBlFMuBcTKF4A9CtcQBE9WBxLQH2YKhEEO3TC8cHrPURoWNKgfJY+A8j6hViycZ1q+3X8TlY4zsWFaCNBeJUAXdu1TKW4lQCYCQFB9+F5McVQF5zsQMu6MxlMw0IRoAYAlXPgK3vkW/oqWqQyAEoxxv8nv/uQuAIwqgeLM3nQkVkoRhBlbTUXsPvDjuoqMvtVfXzjnfXhVWAg3Q9hYigfRxeGdBziCGD9vZy2w2WJGJJQUpN5YjAVw5S0NkHvZQHIFUVGHpioAEDhiQ4AUGn+WNKQWTISiEUjKYgGUsAVPXgu5YA21PTYgnCGh+gsMQneolBIwzr+TTpcgt9hxQxJCAlQISIgDuORAZ0vRRCKGxjAsxmUpBSU30i4NxJXNDZ5EbqL0MMMTEoqanafi5ttRMTQNvQh8gBCMcbHFzcoYCwevBdSwBKJAHYXEqxKZwWorBUQ6eAc01x8BsN+vAfWDQIoFlhsYa6KmK/I6sK0MZbYhUpqavdfbJ7yN/mb/d/R9EqgWYgaS4k/zW9DJPcSP27loeYGCgCROE+eCltlZKARA5AON7g4LuWpCppQT344EgCgKgmeLWgZzS1x4QVhUVNxMB3ucSojUEjAQ1NB+Jp40S6PQQLGaeSQHtceupqe59u+NXtktsIqE4KR8C7kzgXFPe3yY3U++I2YGiJIRRXICRhcSf5kMgB0IPRPvxUVp8gStDVA1CUvpQkALDZTED1gi+OKAbdIKeeHyXIYUHxQTP1KAQOdZIAd2wrGWj7NEIAGJUAVCMFkNfUhUS30Xncfha9/70NKTFQGALQPiR3kk8AlBz8bSFy8FtncARB1QOA7iNiZPXgB6kdSkSxovx2e1kR3EtIfvyY4C9nHAed/ByqxHNiAtuS4kklAUAngvb+dDIAEggBiCeFkAtJcisF3UjctTfLTGwOQ0gModhCgCSkKmiOHBz89hmWTKUQQVBo7iUHQhQhNcHFJGJQJ5k0aWhTUlgtRrGuzKImUSVryeLeCrkMU0mgPa587pLBD+4LEQLAF6yFVAIQJgXJhURJIdqNJF3TvblhGUJioPB9QtSqk79piqr0fAUurgBmO0cODiEFQY9bAHnAJCWKgJqwEIT1GczDijpqHgYt08lHlbhFisHnUBcJSONqIwNAJwRAVglAmBT81FR/TS2zyV9HhBRfaD7uMALEYIQkNKzkYEljBbpE4gedOYKgYN1LDt5FbVATBTAPKaqqJqQK3163heieD69I6jDs/Siqk86jDmhGv45gdSoJcOOSyAAIEwLAVzJb4gmaO4mLK1grptmTdH9zRNDsNTlkxHAQuhvJR8DlFLqDjyUHoByElvZxvZbMICQBiGqCxiT83kwlMLGJfmMcC9EB1SYQagLY5HHqRGw6Kr+GfkNRFwkA5euUxtei1AFQVuZVVIK/LRRXCDXdM7mROEMxK4ytjiEjBgrf+PuxhYg4A1e5HEsOQJkEoOyTMpi47CXW1eSguJwYFUEfHFScS/4eAKKIUTWyiuFrHqpCMrJOuYTiKk0UAnIG3kKuKQ/ziVnH5DZiblYoEQBGMgBkQuAUApCuEiwuJP9YqloYHAw5MVggxBnqIgdAJgigrBQ0gqgCv+0GAOnR9eb7C+452T4GgDgoJFcWJY0mm93R9NFeqR7JKFd9iE8da6SoAYBxEQE2ZeCguYscuII1jgDoNmr86W+ZO7aDqBb8P/pTv+AwgsSguJDcrrrIAZAJArARAa2ednC2JDlDbUzYzvyItRiFgDl024b7WMR4pwDPAq5jbBOgxqtXx60roN/EE+R6Qhqc2xIBt5ADjaUBOhlIriKAVwedNZnxFtcRJQVrLQRdt4B54XVvMcTE4LuLpGo1hSSk2gMrObg5EkEAYRVBt7uxAB+kjolJcJ1iAfCEwfXirwBGbVgIg1ZypyAlAF7HcZtCnZlidTztrbCeYPQ76yg3G2rA2EFzDzlIbiIHiRA4NeBv57b555BKCgPWXlvCEBNDIrgqZkBuiCcVpFkIghvnjutDq6CuG5QwSi4oh7ARiSWPTnW2FOfwwD6606hEqriKuCaFvUKTz5U2xREChr6zVkBdBtWnhQSAsCIAdDcRYCMDaZ/k8rGSAj0HSjomN9KsMKZZjAAxWALQRDn4xj2WHAA7QdBjSW6mFGipr7VAckX5SItjcIV6FhTu7EPzvBiIZvBiVEwIFjKqQwFwfbOs4zWEDD6QaPR9sDchCKsBIKwIANlNxK1hIQopiG1VChQsKYTgL9ab2MMIEEMF0JgDECYHII4guHFA2c0UUgtViaQJzI/xnrpDSwESl06rLUFSbc2H9lJyOVgNcIyKCaHJO36AN9xs8SLTOsUhNpbUQcjgA7LRB3RDKGXd0etdMraSKuDWsaqGECH4YywxhSFxITmMEDFIFdDuNbXMZDcNEkvkAG+chSAgjKNjq6AXLqgUzHuGwpKd6QgFMJEKkE4spXWYSnJuTIzCqXL8RtayGHcKzdh3DhjYL6ZbQ77ZCbmFHEJN6kJjtHqCECH4Y2JqIsS6BauMaN6lNKTEECheU8czc7m4A0cOQJd7fCKxZihZ3UwUdasFLhuraVAFFcJ8wCClKhVq6ISx84IRlbYPPCwGnsJif1KMvg+LCnAIqQFpnFUZADIZ0LGWdhqcOgmSwqw0sKcYUmLQYIkzJJIDEH7eAhAOQEtuJjeWoh9qgEud5UB/2FIrcx9UeaWAkqyPEKlwY+uvN2sW1G5w55/ivrEiZPQt2XNSjEy63i0kYB1ncRXRcXRsbDsNU4XzYGDIicHSbpuSA9B1LUWSgwMlCYkgQtBUhIa6XFBWUOWjwUooDpRoY1EHyQAy0WjfpUX5xB6/6fl1KM+Q0Q8lRWjXrnZ+qSQAhDOcrCqCHtPiOuLWZE+OqoX+FbkNOTFooNlKQFk9COQAlAvhAL7GgLqZtJYWbIO8AQD9IWnGn7b9qGtdIJ5UKKi7L2VsjOEctGSAEGKLJVOy3mLu9q1zpTWk8ZYMJzo/tVgOiFQJdEeIBA6Scb3BiBCDFHOgAWfOtWQISvsZSw6UJLjiM+3JbVo8QgN1RaXCjzNQWIx/jIqg64bWputr4I4dY9D8729UYH3/darO2Dv9mPnSGpKtlH4fqW4iwJ4WGySFUGVz/9UCMJTEoLmPXPoQHSOpB2PcgTNo1DBWaWchVilXQB3qxGr8OZVkXdtKKpZjV3El1WEkY99LPzPJ6k5mqHIcbX5KnCRVSaSSAZ0fVAn0teRComqhd2QxhMTg4Ky2RBSc+wgoqwcDOfjTNJKo0s7CVyYSOGPfq3hDKEDuI0ZN1GXY/eNWJZtUDJJrqY5rour7CZ1DlTRXbf0YJVEXGajH1lRCahZSsyQxxMRA4Yw6dR5L8QW3z5EDIMYdAN4wUpcLd6GG4hI+JL83LaxrAtq5U2gZQRSW7BnuHKoY9xSD5j7j2LlVyawupBrxpm4qqmZEWc7LGktwsFROAzWRAbeTUwnSdkkt9CbWMELEQMERBKceIuIO8IbBG8JdcBpZ1IWYDCgOoWss8DFEB5cBO6lYs7PqQur3NIiFhQ5N25DYa8/6WVWpn4gpmAPsKbPJZMD9bSWF/mHIiYG6kzhL5hOEpB60lFYfASXhD6tCFjQwnFKEVqeLJsWYx7ibfMQohaZSSaV1644DNYE6VWWdpGclqdD5p9ZPxNZM0GMFz18aYFEJ/r6DypjeYUiJIVS/wBl0v2UGpxL8L80nGX8No1+kju/TEnOwZtSk1Apwbq0YsomtdHaoSyk0cSffK3Xgk2PVY/bCtjRdLOdQpX4iJY02mgy0CSGVAMhvsPcZSkNGDPOQLRJVA3QejT/Q7CQHjiQAG1H4+4TTSIVGFDFB19jcdIl8YshGIpSUbCag+Tv6XhW1SYi9TpqMPXHoRZEcheW6TcmOiv5NxriJQvM1UuhvwdOQEQMHGiyWCMJ3EXEE4eZoJCGNsyLSKc5dg9oSmvuqKrS6B/qj1RSMZhBijAVHRr3IChqkzKMYaJ8t/SzrcHFXaQmfopJC30uyndVqDRwsd/QSIQC6+yg/jyESUlzA309B01PpbW/InSRBIqE6IKTPWhHj9w/BWvUck+GUCsnw1FWophm2QSqGq2KAq67RqwI5DZV/apYFuDHUvljW0QiBW8PifmoGQ0wMHEJpNNYgtRvLwaoq6kJIJkRY+7r4SltHOp0m7rQ5gupFHGCQM5E0SN8B9znW/X31zTNiTb3TIP2+U5QDwEsyzfBbAtv1YgiJgdYhALrbiEKKLbjxIed5qqpw55Vy264F20NkWDcCx+mlAWjam9fEe6nza+oF0fcNdZxUFaNvXSekAmLXTVEi9WMIiYEDFywG9OAwRypUCfQ/n9iO0AUe6kJrRYpcaBIV4za9Rr+PH5Uw0euTrXq8FOVuPaa2dqydkI5pIYX8aM9EaNlJDpzq8GFRAr0mDkuLcQ3GVNtKkD7LJtF3SzsiqONz7FfjtyrnXsX9U/UctGPnrKQEWNwn2oeuGX5LzCA1K6kq/FqMqkj9Ecca+l58TsP2lJ1+Y1jItAmiqXIzF/rcUs83xlXVGyQRw86dO/GlL30J+/fvx3nnnYevfOUruOiii8Txf/VXf4XPfvazeOaZZ/CmN70JX/ziF/Ge97wn+aS7iKwj6CBU8xBap58tcaVS616hak5pE+hvi+IMK/rtmm2CEKtce00RTXVEE8N9992HLVu24I477sD69euxY8cObNq0CU888QROOeWU0vgf/OAHeP/734/t27fj3/ybf4N77rkHl112GR599FG87W1vq+VNlGENyKaqikGDxX3WD/Ty88uqIQ7Dcm3XhaYzB6tg8G5sxlqtlvLk9DLWr1+P3/qt38Ltt98OADh27BjWrVuHT3ziE7juuutK4y+//HIcPnwY3/nOdzrb/tW/+lc4//zzcccdd5iOOTs7i+OPPx7ADai3nWU/jMmgGe9YZAOc0UsMC4H1i3iOAPhjvPLKK1i9uj7bEqUYFhcX8cgjj2Dr1q2dbStWrMDGjRuxd+9eds7evXuxZcuWwrZNmzbh/vvvF4+zsLCAhYVu1c0rr7zi9sScrgFVk7VTjOSwls6OKmLdXanukF641frtqlnu6AeJtW1i5P19EFHE8NJLL+Ho0aNYu3ZtYfvatWvx+OOPs3P279/Pjt+/f794nO3bt+Omm25i9nwp5nQzMjIylgX++Z//ecmrUg8GMitp69atBZXx8ssv41d+5Vewb9++Wt/8MGF2dhbr1q3Ds88+W6tkHDbkzyF/Bg75c2h7U84880ycdNJJta4bRQxr1qzBypUrceDAgcL2AwcO4NRTT2XnnHrqqVHjAWBiYgITE+WGNMcff/yyvQAcVq9evew/AyB/DkD+DBzy59B26de6Xszg8fFxXHDBBdi9e3dn27Fjx7B7925s2LCBnbNhw4bCeAD427/9W3F8RkZGRkZ/Ee1K2rJlCzZv3owLL7wQF110EXbs2IHDhw/jqquuAgBceeWVOOOMM7B9+3YAwCc/+Um8853vxJ/8yZ/gve99L+6991780z/9E77+9a/X+04yMjIyMmpBNDFcfvnlePHFF3HjjTdi//79OP/887Fr165OgHnfvn0FWXPxxRfjnnvuwQ033IDPfOYzeNOb3oT7778/qoZhYmIC27ZtY91LywX5M2gjfw75M3DIn0Nzn0F0HUNGRkZGxmij3ohFRkZGRsbQIxNDRkZGRkYBmRgyMjIyMgrIxJCRkZGRUcDAEMPOnTtx1llnYXJyEuvXr8fDDz+sjv+rv/orvOUtb8Hk5CTe/va348EHH+zRmTaHmM/gzjvvxDve8Q6ceOKJOPHEE7Fx48bgZzYsiL0WHO69916MjY3hsssua/YEe4DYz+Dll1/G1VdfjdNOOw0TExN485vfPPS/idjPYMeOHfi1X/s1TE1NYd26dbj22mtx5Mhw9yb7+7//e1x66aU4/fTTMTY2pvaYc9izZw9+8zd/ExMTE/jVX/1V3H333fEHbg0A7r333tb4+Hjrrrvuav3v//2/Wx/5yEdaJ5xwQuvAgQPs+H/4h39orVy5snXrrbe2fvzjH7duuOGG1utf//rWj370ox6feX2I/Qw+8IEPtHbu3Nn64Q9/2PrJT37S+r3f+73W8ccf33ruued6fOb1IvZzcHj66adbZ5xxRusd73hH69/9u3/Xm5NtCLGfwcLCQuvCCy9svec972l9//vfbz399NOtPXv2tB577LEen3l9iP0M/uIv/qI1MTHR+ou/+IvW008/3frud7/bOu2001rXXnttj8+8Xjz44IOt66+/vvWtb32rBaD17W9/Wx3/1FNPtaanp1tbtmxp/fjHP2595Stfaa1cubK1a9euqOMOBDFcdNFFrauvvrrz99GjR1unn356a/v27ez4973vfa33vve9hW3r169v/cf/+B8bPc8mEfsZULz22mutVatWtf7bf/tvTZ1iT5DyObz22mutiy++uPWNb3yjtXnz5qEnhtjP4Gtf+1rr7LPPbi0uLvbqFBtH7Gdw9dVXt37nd36nsG3Lli2tSy65pNHz7CUsxPCpT32q9Ru/8RuFbZdffnlr06ZNUcfquyvJtfLeuHFjZ5ullbc/Hmi38pbGDzpSPgOKubk5vPrqq7U30+olUj+Hz33uczjllFPwoQ99qBen2ShSPoO/+Zu/wYYNG3D11Vdj7dq1eNvb3oabb74ZR48e7dVp14qUz+Diiy/GI4880nE3PfXUU3jwwQdrelLk8KAu29j37qq9auU9yEj5DCg+/elP4/TTTy9dFMOElM/h+9//Pr75zW/iscce68EZNo+Uz+Cpp57CQw89hA9+8IN48MEH8eSTT+LjH/84Xn31VWzbtq0Xp10rUj6DD3zgA3jppZfw27/922i1WnjttdfwsY99DJ/5zGd6ccoDA8k2zs7OYn5+HlNTtmfI9F0xZFTHLbfcgnvvvRff/va3MTlZ5xPuBhsHDx7EFVdcgTvvvBNr1qzp9+n0DceOHcMpp5yCr3/967jgggtw+eWX4/rrrzc/IXEUsGfPHtx888346le/ikcffRTf+ta38MADD+Dzn/98v09tKNF3xdCrVt6DjJTPwOHLX/4ybrnlFvzd3/0dzj333CZPs3HEfg4/+9nP8Mwzz+DSSy/tbDt27BgA4HWvex2eeOIJnHPOOc2edM1IuRZOO+00vP71r8fKlSs72379138d+/fvx+LiIsbHxxs957qR8hl89rOfxRVXXIEPf/jDAIC3v/3tOHz4MD760Y/i+uuvr70t9aBCso2rV682qwVgABRDbuWd9hkAwK233orPf/7z2LVrFy688MJenGqjiP0c3vKWt+BHP/oRHnvssc6/f/tv/y3e/e5347HHHsO6det6efq1IOVauOSSS/Dkk092SBEAfvrTn+K0004bOlIA0j6Dubm5kvF3RNlaRu3garONcXHxZnDvvfe2JiYmWnfffXfrxz/+ceujH/1o64QTTmjt37+/1Wq1WldccUXruuuu64z/h3/4h9brXve61pe//OXWT37yk9a2bdtGIl015jO45ZZbWuPj462//uu/bv385z/v/Dt48GC/3kItiP0cKEYhKyn2M9i3b19r1apVrWuuuab1xBNPtL7zne+0TjnllNYf//Ef9+stVEbsZ7Bt27bWqlWrWv/jf/yP1lNPPdX6n//zf7bOOeec1vve975+vYVacPDgwdYPf/jD1g9/+MMWgNZtt93W+uEPf9j6v//3/7ZarVbruuuua11xxRWd8S5d9Q//8A9bP/nJT1o7d+4c3nTVVqvV+spXvtI688wzW+Pj462LLrqo9Y//+I+dfe985ztbmzdvLoz/y7/8y9ab3/zm1vj4eOs3fuM3Wg888ECPz7h+xHwGv/Irv9ICUPq3bdu23p94zYi9FnyMAjG0WvGfwQ9+8IPW+vXrWxMTE62zzz679YUvfKH12muv9fis60XMZ/Dqq6+2/uiP/qh1zjnntCYnJ1vr1q1rffzjH2/98pe/7P2J14jvfe977O/cvffNmze33vnOd5bmnH/++a3x8fHW2Wef3fqzP/uz6OPmttsZGRkZGQX0PcaQkZGRkTFYyMSQkZGRkVFAJoaMjIyMjAIyMWRkZGRkFJCJISMjIyOjgEwMGRkZGRkFZGLIyMjIyCggE0NGRkZGRgGZGDIyMjIyCsjEkJGRkZFRQCaGjIyMjIwCMjFkZGRkZBTw/wNZq8gfWDGMMAAAAABJRU5ErkJggg==", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# === load the data ===\n", "# x, y -> spatial discretization\n", "# edge_index, triang -> connectivity matrix, triangulation\n", "# u, params -> solution field, parameters\n", "\n", "data = torch.load(\"holed_poisson.pt\")\n", "x = data[\"x\"]\n", "y = data[\"y\"]\n", "edge_index = data[\"edge_index\"]\n", "u = data[\"u\"]\n", "triang = data[\"triang\"]\n", "params = data[\"mu\"]\n", "\n", "# simple plot\n", "plt.figure(figsize=(4, 4))\n", "plt.tricontourf(x[:, 10], y[:, 10], triang, u[:, 10], 100, cmap=\"jet\")\n", "plt.scatter(params[10, 0], params[10, 1], c=\"r\", marker=\"x\", s=100)\n", "plt.tight_layout()\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "f3619e4f", "metadata": {}, "source": [ "## Graph-Based Reduced Order Modeling\n", "\n", "In this problem, the geometry of the spatial domain is **unstructured**, meaning that classical grid-based methods (e.g., CNNs) are not well suited. Instead, we represent the mesh as a **graph**, where nodes correspond to spatial degrees of freedom and edges represent connectivity. This makes **Graph Neural Networks (GNNs)**, and in particular **Graph Convolutional Networks (GCNs)**, a natural choice to process the data.\n", "\n", "

\n", " \"GCA-ROM\"\n", "

\n", "\n", "To reduce computational complexity while preserving accuracy, we employ a **Reduced Order Modeling (ROM)** strategy (see picture above). The idea is to map high-dimensional simulation data $u(\\mathbf{x}, \\boldsymbol{\\mu})$ to a compact **latent space** using a **graph convolutional encoder**, and then reconstruct it back via a **decoder** (offline phase). The latent representation captures the essential features of the solution manifold. Moreover, we can learn a **parametric map** $\\mathcal{M}$ from the parameter space $\\boldsymbol{\\mu}$ directly into the latent space, enabling predictions for new unseen parameters.\n", "\n", "Formally, the autoencoder consists of an **encoder** $\\mathcal{E}$, a **decoder** $\\mathcal{D}$, and a **parametric mapping** $\\mathcal{M}$:\n", "$$\n", "z = \\mathcal{E}(u(\\mathbf{x}, \\boldsymbol{\\mu})), \n", "\\quad\n", "\\hat{u}(\\mathbf{x}, \\boldsymbol{\\mu}) = \\mathcal{D}(z),\n", "\\quad\n", "\\hat{z} = \\mathcal{M}(\\boldsymbol{\\mu}),\n", "$$\n", "where $z \\in \\mathbb{R}^r$ is the latent representation with $r \\ll N$ (the number of degrees of freedom) and the **hat notation** ($\\hat{u}, \\hat{z}$) indicates *learned or approximated quantities*.\n", "\n", "The training objective balances two terms:\n", "1. **Reconstruction loss**: ensuring the autoencoder can faithfully reconstruct $u$ from $z$.\n", "2. **Latent consistency loss**: enforcing that the parametric map $\\mathcal{M}(\\boldsymbol{\\mu})$ approximates the encoder’s latent space.\n", "\n", "The combined loss function is:\n", "$$\n", "\\mathcal{L}(\\theta) = \\frac{1}{N} \\sum_{i=1}^N \n", "\\big\\| u(\\mathbf{x}, \\boldsymbol{\\mu}_i) - \n", "\\mathcal{D}\\!\\big(\\mathcal{E}(u(\\mathbf{x}, \\boldsymbol{\\mu}_i))\\big) \n", "\\big\\|_2^2\n", "\\;+\\; \\frac{1}{N} \\sum_{i=1}^N\n", "\\big\\| \\mathcal{E}(u(\\mathbf{x}, \\boldsymbol{\\mu}_i)) - \\mathcal{M}(\\boldsymbol{\\mu}_i) \\big\\|_2^2.\n", "$$\n", "This framework leverages the expressive power of GNNs for unstructured geometries and the efficiency of ROMs for handling parametric PDEs.\n", "\n", "We will now build the autoencoder network, which is a `nn.Module` with two methods: `encode` and `decode`.\n" ] }, { "cell_type": "code", "execution_count": 3, "id": "3197831b", "metadata": {}, "outputs": [], "source": [ "class GraphConvolutionalAutoencoder(nn.Module):\n", " def __init__(\n", " self, hidden_channels, bottleneck, input_size, ffn, act=nn.ELU\n", " ):\n", " super().__init__()\n", " self.hidden_channels, self.input_size = hidden_channels, input_size\n", " self.act = act()\n", " self.current_graph = None\n", "\n", " # Encoder GMM layers\n", " self.fc_enc1 = nn.Linear(input_size * hidden_channels[-1], ffn)\n", " self.fc_enc2 = nn.Linear(ffn, bottleneck)\n", " self.encoder_convs = nn.ModuleList(\n", " [\n", " GMMConv(\n", " hidden_channels[i],\n", " hidden_channels[i + 1],\n", " dim=1,\n", " kernel_size=5,\n", " )\n", " for i in range(len(hidden_channels) - 1)\n", " ]\n", " )\n", " # Decoder GMM layers\n", " self.fc_dec1 = nn.Linear(bottleneck, ffn)\n", " self.fc_dec2 = nn.Linear(ffn, input_size * hidden_channels[-1])\n", " self.decoder_convs = nn.ModuleList(\n", " [\n", " GMMConv(\n", " hidden_channels[-i - 1],\n", " hidden_channels[-i - 2],\n", " dim=1,\n", " kernel_size=5,\n", " )\n", " for i in range(len(hidden_channels) - 1)\n", " ]\n", " )\n", "\n", " def encode(self, data):\n", " self.current_graph = data\n", " x = data.x\n", " h = x\n", " for conv in self.encoder_convs:\n", " x = self.act(conv(x, data.edge_index, data.edge_weight) + h)\n", " x = x.reshape(\n", " data.num_graphs, self.input_size * self.hidden_channels[-1]\n", " )\n", " return self.fc_enc2(self.act(self.fc_enc1(x)))\n", "\n", " def decode(self, z, decoding_graph=None):\n", " data = decoding_graph or self.current_graph\n", " x = self.act(self.fc_dec2(self.act(self.fc_dec1(z)))).reshape(\n", " data.num_graphs * self.input_size, self.hidden_channels[-1]\n", " )\n", " h = x\n", " for i, conv in enumerate(self.decoder_convs):\n", " x = conv(x, data.edge_index, data.edge_weight) + h\n", " if i != len(self.decoder_convs) - 1:\n", " x = self.act(x)\n", " return x" ] }, { "cell_type": "markdown", "id": "4d14d91d", "metadata": {}, "source": [ "Great! We now need to build the graph structure (a PyTorch Geometric `Data` object) from the numerical solver outputs.\n", "\n", "The solver provides the solution values $u(\\mathbf{x}, \\boldsymbol{\\mu})$ for each parameter instance $\\boldsymbol{\\mu}$, along with the node coordinates $(x, y)$ of the unstructured mesh. Because the geometry is not defined on a regular grid, we naturally represent the mesh as a graph:\n", "\n", "- **Nodes** correspond to spatial points in the mesh. Each node stores the **solution value** $u$ at that point as a feature. \n", "- **Edges** represent mesh connectivity. For each edge, we compute:\n", " - **Edge attributes**: the relative displacement vector between the two nodes. \n", " - **Edge weights**: the Euclidean distance between the connected nodes. \n", "- **Positions** store the physical $(x, y)$ coordinates of the nodes.\n", "\n", "For each parameter realization $\\boldsymbol{\\mu}_i$, we therefore construct a PyTorch Geometric `Data` object:\n" ] }, { "cell_type": "code", "execution_count": 4, "id": "8f098b6d", "metadata": {}, "outputs": [], "source": [ "# number of nodes and number of graphs (parameter realizations)\n", "num_nodes, num_graphs = u.shape\n", "\n", "graphs = []\n", "for g in range(num_graphs):\n", " # node positions\n", " pos = torch.stack([x[:, g], y[:, g]], dim=1) # shape [num_nodes, 2]\n", " # edge attributes and weights\n", " ei, ej = pos[edge_index[0]], pos[edge_index[1]] # [num_edges, 2]\n", " edge_attr = torch.abs(ej - ei) # relative offsets\n", " edge_weight = edge_attr.norm(p=2, dim=1, keepdim=True) # Euclidean distance\n", " # node features (solution values)\n", " node_features = u[:, g].unsqueeze(-1) # [num_nodes, 1]\n", " # build PyG graph\n", " graphs.append(\n", " Data(\n", " x=node_features,\n", " edge_index=edge_index,\n", " edge_weight=edge_weight,\n", " edge_attr=edge_attr,\n", " pos=pos,\n", " )\n", " )" ] }, { "cell_type": "markdown", "id": "e38ad2d8", "metadata": {}, "source": [ "## Training with PINA\n", "\n", "Everything is now ready! We can use **PINA** to train the model, following the workflow from previous tutorials. First, we need to define the problem. In this case, we will use the [`SupervisedProblem`](https://mathlab.github.io/PINA/_rst/problem/zoo/supervised_problem.html#module-pina.problem.zoo.supervised_problem), which expects: \n", "\n", "- **Input**: the parameter tensor $\\boldsymbol{\\mu}$ describing each scenario. \n", "- **Output**: the corresponding graph structure (PyTorch Geometric `Data` object) that we aim to reconstruct. " ] }, { "cell_type": "code", "execution_count": 5, "id": "bbb3f90f", "metadata": {}, "outputs": [], "source": [ "problem = SupervisedProblem(params, graphs)" ] }, { "cell_type": "markdown", "id": "79875c61", "metadata": {}, "source": [ "Next, we build the **autoencoder network** and the **interpolation network**. \n", "\n", "- The **Graph Convolutional Autoencoder (GCA)** encodes the high-dimensional graph data into a compact latent space and reconstructs the graphs from this latent representation. \n", "- The **interpolation network** (or parametric map) learns to map a new parameter $\\boldsymbol{\\mu}^*$ directly into the latent space, enabling the model to predict solutions for unseen parameter instances without running the full encoder." ] }, { "cell_type": "code", "execution_count": 6, "id": "601b8b11", "metadata": {}, "outputs": [], "source": [ "reduction_network = GraphConvolutionalAutoencoder(\n", " hidden_channels=[1, 1], bottleneck=8, input_size=1352, ffn=200, act=nn.ELU\n", ")\n", "interpolation_network = FeedForward(\n", " input_dimensions=2,\n", " output_dimensions=8,\n", " n_layers=2,\n", " inner_size=200,\n", " func=nn.Tanh,\n", ")" ] }, { "cell_type": "markdown", "id": "45f2d8b9", "metadata": {}, "source": [ "Finally, we will use the [`ReducedOrderModelSolver`](https://mathlab.github.io/PINA/_rst/solver/supervised_solver/reduced_order_model.html#pina.solver.supervised_solver.reduced_order_model.ReducedOrderModelSolver) to perform the training, as discussed earlier. \n", "\n", "This solver requires two components: \n", "- an **interpolation network**, which maps parameters $\\boldsymbol{\\mu}$ to the latent space, and \n", "- a **reduction network**, which in our case is the **autoencoder** that compresses and reconstructs the graph data. " ] }, { "cell_type": "code", "execution_count": 7, "id": "47a02df1", "metadata": {}, "outputs": [], "source": [ "# This loss handles both Data and Torch.Tensors\n", "class CustomMSELoss(nn.MSELoss):\n", " def forward(self, output, target):\n", " if isinstance(output, Data):\n", " output = output.x\n", " if isinstance(target, Data):\n", " target = target.x\n", " return torch.nn.functional.mse_loss(\n", " output, target, reduction=self.reduction\n", " )\n", "\n", "\n", "# Define the solver\n", "solver = ReducedOrderModelSolver(\n", " problem=problem,\n", " reduction_network=reduction_network,\n", " interpolation_network=interpolation_network,\n", " use_lt=False,\n", " loss=CustomMSELoss(),\n", " optimizer=TorchOptimizer(torch.optim.Adam, lr=0.001, weight_decay=1e-05),\n", ")" ] }, { "cell_type": "markdown", "id": "063b118a", "metadata": {}, "source": [ "Training is performed as usual using the **`Trainer`** API. In this tutorial, we will use only **30% of the data** for training, and only $300$ epochs of training to illustrate the workflow." ] }, { "cell_type": "code", "execution_count": null, "id": "7081ca73", "metadata": {}, "outputs": [], "source": [ "trainer = Trainer(\n", " solver=solver,\n", " accelerator=\"cpu\",\n", " max_epochs=300,\n", " train_size=0.3,\n", " val_size=0.7,\n", " test_size=0.0,\n", " shuffle=True,\n", ")\n", "trainer.train()" ] }, { "cell_type": "markdown", "id": "b1d11289", "metadata": {}, "source": [ "Once the model is trained, we can test the reconstruction by following two steps:\n", "\n", "1. **Interpolate**: Use the `interpolation_network` to map a new parameter $\\boldsymbol{\\mu}^*$ to the latent space. \n", "2. **Decode**: Pass the interpolated latent vector through the autoencoder (`reduction_network`) to reconstruct the corresponding graph data." ] }, { "cell_type": "code", "execution_count": 9, "id": "8dd5c0d4", "metadata": {}, "outputs": [], "source": [ "# interpolate\n", "z = interpolation_network(params)\n", "\n", "# decode\n", "batch = Batch.from_data_list(graphs)\n", "out = reduction_network.decode(z, decoding_graph=batch)\n", "out, _ = to_dense_batch(out, batch.batch)\n", "out = out.squeeze(-1).T.detach()" ] }, { "cell_type": "markdown", "id": "91685b70", "metadata": {}, "source": [ "Let's compute the total error, and plot a sample solution:" ] }, { "cell_type": "code", "execution_count": 10, "id": "29d3dbac", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "L2 relative error 10.06%\n" ] }, { "data": { "image/png": "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", "text/plain": [ "
" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "# compute error\n", "l2_error = (torch.norm(out - u, dim=0) / torch.norm(u, dim=0)).mean()\n", "print(f\"L2 relative error {l2_error:.2%}\")\n", "\n", "# plot solution\n", "idx_to_plot = 42\n", "# Determine min and max values for color scaling\n", "vmin = min(out[:, idx_to_plot].min(), u[:, idx_to_plot].min())\n", "vmax = max(out[:, idx_to_plot].max(), u[:, idx_to_plot].max())\n", "plt.figure(figsize=(16, 4))\n", "plt.subplot(1, 3, 1)\n", "plt.tricontourf(\n", " x[:, idx_to_plot],\n", " y[:, idx_to_plot],\n", " triang,\n", " out[:, idx_to_plot],\n", " 100,\n", " cmap=\"jet\",\n", " vmin=vmin,\n", " vmax=vmax,\n", ")\n", "plt.title(\"GCA-ROM\")\n", "plt.colorbar()\n", "plt.subplot(1, 3, 2)\n", "plt.title(\"True\")\n", "plt.tricontourf(\n", " x[:, idx_to_plot],\n", " y[:, idx_to_plot],\n", " triang,\n", " u[:, idx_to_plot],\n", " 100,\n", " cmap=\"jet\",\n", " vmin=vmin,\n", " vmax=vmax,\n", ")\n", "plt.colorbar()\n", "plt.subplot(1, 3, 3)\n", "plt.title(\"Square Error\")\n", "plt.tricontourf(\n", " x[:, idx_to_plot],\n", " y[:, idx_to_plot],\n", " triang,\n", " (u - out).pow(2)[:, idx_to_plot],\n", " 100,\n", " cmap=\"jet\",\n", ")\n", "plt.colorbar()\n", "plt.ticklabel_format()\n", "plt.show()" ] }, { "cell_type": "markdown", "id": "c152bfd1", "metadata": {}, "source": [ "Nice! We can see that the network is correctly learning the solution operator, and the workflow was very straightforward. \n", "\n", "You may notice that the network outputs are not as smooth as the actual solution. Don’t worry — training for longer (e.g., ~5000 epochs) will produce a smoother, more accurate reconstruction.\n", "\n", "## What's Next?\n", "\n", "Congratulations on completing the introductory tutorial on **Graph Convolutional Reduced Order Modeling**! Now that you have a solid foundation, here are a few directions to explore:\n", "\n", "1. **Experiment with Training Duration** — Try different training durations and adjust the network architecture to optimize performance. Explore different integral kernels and observe how the results vary.\n", "\n", "2. **Explore Physical Constraints** — Incorporate physics-informed terms or constraints during training to improve model generalization and ensure physically consistent predictions.\n", "\n", "3. **...and many more!** — The possibilities are vast! Continue experimenting with advanced configurations, solvers, and features in PINA.\n", "\n", "For more resources and tutorials, check out the [PINA Documentation](https://mathlab.github.io/PINA/)." ] } ], "metadata": { "kernelspec": { "display_name": "deep", "language": "python", "name": "python3" }, "language_info": { "codemirror_mode": { "name": "ipython", "version": 3 }, "file_extension": ".py", "mimetype": "text/x-python", "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", "version": "3.12.11" } }, "nbformat": 4, "nbformat_minor": 5 }