|
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805 |
- {
- "cells": [
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "# 多层神经网络\n",
- "\n",
- "本节在前面学习线性回归和逻辑回归模型的基础上,本节学习如何利用PyTorch实现多层神经网络。"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 1. 多层神经网络\n",
- "线性回归的公式是 $y = w x + b$, Logistic 回归的公式是 $y = Sigmoid(w x + b)$,其实它们都可以看成单层神经网络,其中 Sigmoid 被称为激活函数。"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 1.1 神经网络的结构\n",
- "\n",
- "神经网络就是很多个神经元堆在一起形成一层神经网络,那么多个层堆叠在一起就是深层神经网络\n",
- "\n",
- "\n",
- "\n",
- "可以看到,神经网络的结构其实非常简单,主要有输入层,隐藏层,输出层构成,输入层需要根据特征数目来决定,输出层根据解决的问题来决定,那么隐藏层的网路层数以及每层的神经元数就是可以调节的参数,而不同的层数和每层的参数对模型的影响非常大,具体的动态示例可以参考 [demo - classify2d](http://cs.stanford.edu/people/karpathy/convnetjs/demo/classify2d.html) 。神经网络向前传播也非常简单,就是一层一层不断做运算即可。"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 1.2 多层神经网络示例程序\n",
- "\n",
- "首先生成一些训练、测试数据。"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 1,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "import torch\n",
- "import numpy as np\n",
- "from torch import nn\n",
- "from sklearn import datasets\n",
- "\n",
- "import matplotlib.pyplot as plt\n",
- "%matplotlib inline\n",
- "\n",
- "# generate sample data\n",
- "np.random.seed(0)\n",
- "data_x, data_y = datasets.make_moons(200, noise=0.20)\n",
- "\n",
- "# plot data\n",
- "plt.scatter(data_x[:, 0], data_x[:, 1], c=data_y, cmap=plt.cm.Spectral)\n",
- "plt.show()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 2,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 变量\n",
- "x = torch.from_numpy(data_x).float()\n",
- "y = torch.from_numpy(data_y).float().unsqueeze(1)\n",
- "\n",
- "\n",
- "# 定义两层神经网络的参数\n",
- "w1 = nn.Parameter(torch.randn(2, 4) * 0.1) # 隐藏层神经元个数 4\n",
- "b1 = nn.Parameter(torch.zeros(4))\n",
- "\n",
- "w2 = nn.Parameter(torch.randn(4, 1) * 0.1)\n",
- "b2 = nn.Parameter(torch.zeros(1))\n",
- "\n",
- "# 定义模型\n",
- "def SimpNetwork(x):\n",
- " x1 = torch.mm(x, w1) + b1\n",
- " x1 = torch.sigmoid(x1) # 使用 PyTorch 自带的 sigmoid 激活函数\n",
- " x2 = torch.mm(x1, w2) + b2\n",
- " return x2 # BCEWithLogitsLoss 已经带了sigmoid,所以此处不需要\n",
- "\n",
- "optimizer = torch.optim.SGD([w1, b1, w2, b2], 0.1)\n",
- "\n",
- "criterion = nn.BCEWithLogitsLoss()"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 3,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "torch.Size([200, 2]) <class 'torch.Tensor'> <class 'numpy.ndarray'> (200, 2)\n",
- "torch.Size([200, 1]) <class 'torch.Tensor'> <class 'numpy.ndarray'> (200, 1)\n"
- ]
- }
- ],
- "source": [
- "for i in [x, y]:\n",
- " print(i.shape, type(i), type(i.numpy()), i.numpy().shape)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 4,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "epoch: 100, loss: 0.6820940375328064\n",
- "epoch: 200, loss: 0.6518701314926147\n",
- "epoch: 300, loss: 0.5855702757835388\n",
- "epoch: 400, loss: 0.5046236515045166\n",
- "epoch: 500, loss: 0.4404149353504181\n",
- "epoch: 600, loss: 0.397914320230484\n",
- "epoch: 700, loss: 0.37014085054397583\n",
- "epoch: 800, loss: 0.35137924551963806\n",
- "epoch: 900, loss: 0.33840861916542053\n",
- "epoch: 1000, loss: 0.32936176657676697\n"
- ]
- }
- ],
- "source": [
- "# 训练 1000 次\n",
- "for e in range(1000):\n",
- " out = SimpNetwork(x)\n",
- " loss = criterion(out, y)\n",
- " optimizer.zero_grad()\n",
- " loss.backward()\n",
- " optimizer.step()\n",
- " if (e + 1) % 100 == 0:\n",
- " print('epoch: {}, loss: {}'.format(e+1, loss.item()))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 5,
- "metadata": {},
- "outputs": [],
- "source": [
- "def plot_decision_boundary(model, x, y):\n",
- " # Set min and max values and give it some padding\n",
- " x_min, x_max = x[:, 0].min() - 1, x[:, 0].max() + 1\n",
- " y_min, y_max = x[:, 1].min() - 1, x[:, 1].max() + 1\n",
- " h = 0.01\n",
- " # Generate a grid of points with distance h between them\n",
- " xx, yy = np.meshgrid(np.arange(x_min, x_max, h), np.arange(y_min, y_max, h))\n",
- " # Predict the function value for the whole grid .c_按行连接两个矩阵,左右相加。\n",
- " Z = model(np.c_[xx.ravel(), yy.ravel()])\n",
- " Z = Z.reshape(xx.shape)\n",
- " # Plot the contour and training examples\n",
- " plt.contourf(xx, yy, Z, cmap=plt.cm.Spectral)\n",
- " plt.ylabel('x2')\n",
- " plt.xlabel('x1')\n",
- " plt.scatter(x[:, 0], x[:, 1], c=y.reshape(-1), s=40, cmap=plt.cm.Spectral)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 6,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- },
- {
- "data": {
- "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXwAAAEICAYAAABcVE8dAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjQuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/MnkTPAAAACXBIWXMAAAsTAAALEwEAmpwYAAB9nUlEQVR4nO2ddXgU1/eH3zuzFg8JIZDg7u7uUKDQAnWXX92937q7UqXuhZYKpbi7O8GDJCGEENe1ub8/NqRZduNO5n0eHpKxe3aSnLlz7jmfI6SU6Ojo6Ohc+CjVbYCOjo6OTtWgO3wdHR2dOoLu8HV0dHTqCLrD19HR0akj6A5fR0dHp46gO3wdHR2dOoLu8HV0ikEIcVwIMTrv6/8JIb6sgjGHCyFiK3scnbqFoboN0NGpTUgpXy3JcUKIb4FYKeXTlWuRjk7J0Wf4OnUKIYQ+ydGps+gOX+eCIC/s8qQQIkoIkSKE+EYIYTkXGhFCPC6EOA18I4RQhBBPCCGOCiGShBCzhRAhBa51nRDiRN6+p84b53khxI8Fvh8shFgvhEgVQsQIIW4UQtwGXAM8JoTIFEL8k3dshBBijhAiUQhxTAhxX4Hr+Aghvs2zPQroU9n3TKfuoTt8nQuJa4BxQCugLXAunNIQCAGaAbcB9wKXAMOACCAF+BhACNER+BS4Lm9fKNDY22BCiGbAAmAGEAZ0B3ZKKWcCPwFvSin9pZQXCyEU4B9gFxAJjAIeEEKMy7vcc3l2t8r7DDeU92bo6JyP7vB1LiQ+klLGSCmTgVeAq/K2a8BzUkqrlDIHuAN4SkoZK6W0As8D0/PCPdOBeVLK1Xn7nsk73xtXA0ullL9IKe1SyiQp5c5Cju0DhEkpX5RS2qSU0cAXwJV5+y8HXpFSJkspY4APy3EfdHS8osczdS4kYgp8fQLXDB0gUUqZW2BfM+BPIURBR+4EwvPOyb+OlDJLCJFUyHhNgKMltK0ZECGESC2wTQXW5H3tNm6e/To6FYru8HUuJJoU+LopcCrv6/MlYWOAm6WU686/gBAiHuhQ4HtfXGEdb8QAfQvZ523MY1LKNoUcH4/L/n0F7NfRqVD0kI7OhcTdQojGeQuwTwGzCjnuM+CVvBg8QogwIcSUvH2/A5PyFmNNwIsU/nfyEzBaCHG5EMIghAgVQnTP25cAtCxw7GYgI2/x2EcIoQohOgshzi3OzgaeFELUE0I0xrXOoKNToegOX+dC4mdgMRCNK9TyciHHfQDMBRYLITKAjUA/ACnlPuDuvGvF41rQ9VoAJaU8CUwAHgaSgZ1At7zdXwEd87J3/pJSOoFJuBZ2jwFngS+BoLzjX8AVxjmW9xl+KO2H19EpDqE3QNG5EBBCHAdulVIurW5bdHRqKvoMX0dHR6eOoDt8HR0dnTqCHtLR0dHRqSPoM3wdHR2dOkKNzcOvX7++bN68eXWboaOjo1Or2LZt21kpZZi3fTXW4Tdv3pytW7dWtxk6Ojo6tQohRKFV2npIR0dHR6eOoDt8HR0dnTqC7vB1dHR06gi6w9fR0dGpI+gOX6fM5Camcnr1bjJPJlS3KTo6OiWgxmbp6NRcpKax8f6POPTlfFSLCc1qJ2J0T4b/+gwGX0t1m6ejo1MI+gxfp9REzfiTw98sRLPasadl4cy1cWrpdjbcUzOaNGl2Byl7j5EVl1jdpujo1Ch0h69TaqI+mIMz2+q2zZlrI/qX5TittmqyykX0rBX8Ej6NeQPvZU6b65k/7AFyzqRUq006OjUF3eHrlBprSqb3HZrEkVN9Dv/s1oOsveUtbKmZODJzcObaOLMxiiUT/1dtNuno1CR0h69TahoO6wZCeGz3a9oAR3YuybuOVstMf+97v+M874Ej7U5S958gNep4ldujo1PT0B2+Tqnp8+ZtGAN8UIyuNX+hKqg+Jkz1/JnT+jrmD32An8OmcmDmvCq1KyvmDHhRf1WMBrLjk6vUFh2dmoiepaNTaoLaNuGSPV+x9+3ZJG6MIqh9U9IPx5K0/TCazYEz1zXL3vzQJwS2bETE6F7kJqWx/6O/iFu8Ff9m4XR6cDphfdpXqF2RY3qTtPVQ/vjn0Kx2Qnu0rtCxdHRqIzVWD793795SF0+rHWTFJTKn9XU4rXaPfRFjejH0hyf5u8dt2FIyXc5YCFQfE4O/fISWV46sMDusyen81fVWcs+modkcABj8LHR++DJ6PH9jhY2jo1OTEUJsk1L29rZPD+nolJuchBQUs9Hrvuy4s+x541esZ9P/m3lLiTPbyoa7PkCzOyrMDnNIIFN2zKTDPZcQ2K4JDQZ2Ysi3j+vOXkcnDz2ko1Nugjs0Qzo1j+2K0UDEmF7E/LvRq2PXHE7SDsVSr1PzCrPFEhZM37fvpO/bd1bYNXV0LhT0Gb5OuTH4mOn12q2ovub8bcKoYgzypcujV2CpH+T1PGl3YK7nX1Vm6ujUefQZvk6F0PGeSwlsHcmet2aRfSqJyDG96PrEVfhG1KfTg9NJ3nUUR1Zu/vHCaCCsf0d8I+pXo9U6OnUL3eHrVBiNx/el8fi+HtubTR1Cyt5j7HnjVxSzEc3uoF7nFoyY/Ww1WKmjU3fRs3R0qgxrSgbJO4/g0yiU4PZNq9scHZ0LkqKydPQZvk6VYa4XQKMRParbDA+c1rxUUZP3TCMdnQsF3eFfwKQdjiUrJpGQri0LXTity2SeSGDtLW9xetUuENBoZE8Gf/kIfo3Dqts0HZ1KQXf4FUDM/E3se+93cs+k0mRSfzo9NB1LaPU5WGtqJssueYazWw6imAw4c210uOcS+rx5O8KLBk5dxJFjZd6Ae8g9k4rUXCml8cu2M2/gPUw/8mOVzPalpnHir3Ucm7UC1WKi7c0XuXSKdHQqCd3hl5Pdb/7Krpd+yM9ASTsUw5EfFnPJzi8whwRWi01rbnidxI1RLpmDHJeM8cHP/iG4Y3Pa3jS+WmyqaZyYsxp7Zk6+sweQTg17WjYn/15Pi8uGVer4UkqWT3uOU0u3u353hODEH2vo+MA0er10c6WOrVN30fPwy4EtLZOdz3/nlm6oWe3knk0j6qO/qsUma2omcYu35ksLnMORlUvUe79Xi001kfQjp3Bk5nhsd2TnknEkrtLHP7Vk23/OHkBKHFm57HvnNzKOn6708XXqJrrDLwfJO496lRTQcu3ELdxcDRaBPT0LoXj/sVqTM6rYmppLva4tMfj7eGxXfc3U69qy0sc/+c96t4nCOYSicGrJtkofX6duojv8cmBpEOxdC0YIfCOrZ+HPr3EYpmA/j+3CoBI53mumVp2k6cUD8I0IzZd4BlBMRvybhhM5vk+lj28K8kcYVM8dqsAY4Pkg0tGpCHSHXw6COzQjuEMzjz9cg4+JTg9MqxabhKIw6POHUH3N+TN9xWzEFORXaSJiWXGJ7Ht/Drtf/4WkXUeJ+XcjBz77h6QdhytlPIDs08nseP5blkz6H9ue+Ybs+KRSna8YDUxaP4PWN4zFGOSHKdifNjeNZ8KaD8hNTPPaDzf7dDJr/+9tfmk4jd9aXsOet2ahOZxlsr/19WNQjJ4OXwBNLh5Qpmvq6BSHXnhVTnISkll26bMk7zqKYjQgpaTf+3fT9qaLqtWupJ1H2Pfe76QfiaPR8O50vO9SfMJDKnyco78sY90tbwPgtDvAqaGYDAhVdaU6jujBqD9ecJtJl5fUAyeZN+AenLk2NKsdxWxENRuZuG5GuYTY0g7FsPKql0mLOgFC4N+iEcN/foqQbq2wpWXyZ6ebyTmTisxz8qqvmSYT+zNiVtkqho/8uIT1t7+X7/iFEIya+zINh3Qt82fQ0Smq8Ep3+BVExrF4rEnpBHdugcFiqm5zqgRrcjqzGl/h0XCkIKqPmR4v3kiXhy+vsHEXjnmE+OU73btbCUHDoV25aMW7ZbqmI9fGb82vIjcxze26piA/Ljv+M4e/Wci2p7/2aN6uWkxM2TmToLZNyjSuLT2L+BU7Uc1GGo3ojmquG787OpWHrodfBQS0aET93u3qjLMHiF2w2XscugDOHCuHZv5boeOeXrXbs5WhlJxes5uyTmBO/r0OR47V47qa3Un0LytIWLvXw9mDSxU0aceRMo0JYAr0o9mUQTQe31d39jqVju7wdSodzebZCas8GHy8O0bVYiq2sExqGlmxidgzst22Z8UkouV62unIziXzZAJB7ZqgmLyEpaTEv1l4yY3X0alGdIevU2YaX9Q3P55dGIrZSPMrhlfouK1vGo963puUajHR+oZxRZ53/M+1zGp8OXPa3cDPDaay8qqXsOfl4of1be/VoRv8fWjQvyPtbp/ksQ4hjAYCWkQQ1q9DOT+Rjk7VoDv8WoLTZseR7Zm3XZ2YQwIZ9NUjqBZToS0OfRrUo9uTV1fouL1f+z8aDuuK6mPGGOiL6mOmweDO9H3r9kLPSdy0n9XXvkrO6RScOVY0q50Tf61j5VUvAxA+pAv1e7dD9fmviYtqMRHYJpLGE/vh3zSccYvfdM30zUYUk4HIMT0Zv/QtXa5Cp9agL9rWcKwpGay//V1Ozl2PdGqEdG/NoC8eJrR76+o2LZ+suETW3vQW8St2eLQ6tDQK4cqYWYUWg5WH1P0nSN1/kuD2TQju2LzIY5dNe46Tf63ziNGrFhPTDn+PX2QYTquNPW/OYu+7v2FPywIh8GtcnwGfPkiTCf3yz8lNTEW1mDAG+Fb4Z9LRKS/6om0tRUrJojGPcnLuejSbA+nUSNp2iAXDHix13nll4hcZRubJBK99bR3p2aQfrhypguAOzWg+dUixzh4g4+gpz4VeXCGnrBhXzr1qNpF+OPY/WQopyYpJZMXlL5C4aT+a08mRH5aw8upXWHHFixyfs7rMi8Q6OtVBhSRHCyG+BiYBZ6SUnb3sF8AHwAQgG7hRSrm9Isa+kDm7+QBpB2M8dHGcNjsHv/iXHs9eX+ZrS00jbvFWknceJaBlI5pOGViuLBGDr8X7OE7NrddtRWJNyWDPm79yfM4ajP4+dLjnEtrcOM7r20T4kC6k7j+BtLuvOWhWO8EdXM1YcpPSOP77ao80U2eOjZ2v/OjKBFq5K18SIWHNHmL+3ciQrx+rlM+no1PRVNQM/1ugKBnGi4A2ef9uAz6toHEvaNKPnkIonvFhzWonde+xMl/Xlp7F3N53sOLyF9n+zNes+7+3+a3ltWSeSCjzNdvfORmDn7vTF4pCcKdm+DdpUObrFoY9K4d/+tzJvvfnkHEkjuSdR9h030esu917Hn6Xx67E6OcDBR4GBl8LnR65DFOQq5F6VkxioZk4yTuPuDl7cAnSHZu1kuTdRyv2w+noVBIV4vCllKuB5CIOmQJ8L11sBIKFEI0qYuwLmZCuLdEcnmES1ddMWP+OZb7ujme/JXX/SRyZOS5J4Iwccs+ksOamN8p8zba3XETzaUNRfUwY/H0wBPjg27g+I357vszXLIqjPywl+3QKmvW/VEpHdi7RPy3zqjbp36QBF2/5lBZXDMMSXo/gzs0Z8OkD9HzhpvxjAltFoNk9s46EqmAM8vMqdiY1zVUEVgI0h5Njv61izc1vsvXJL0mvAlVOHZ2CVJUefiQQU+D72Lxt8QUPEkLchusNgKZN9Z6n9Tq3oOHwbpxeuRNnjivMIFQFo78PbW4uu3TD0V+WuTlKcIVeEtbuxZ6V45oJlxKhKAz59nG6PnUNiRv34xsRSqMR3StlsRbg1LLtOL1kLSlGA4mb9hPQvKHHvsBWEQz/6elCr2kM8KXTA9OI+uAPt4wo1cdMkwn9yThyyuO+KUYD5pCAYu11Wm0sGPkwKbujcWTlIowqUR/+wdAfnqT51CHFnq+jUxHUqEVbKeVMKWVvKWXvsDC9zRzAqD9eoNNDl2FpEIwx0Jfm04dx8ZZPMQf7l/2ilbjQGNSmMa2vG0PEqJ6V5uwB/JuHI7yIj0kp8Y0ILfN1e758M33evh3/Fg0xBvgSMaYXE9d+QKf7p3r9PEJAs0sHF3vdQ18vJGVXdP5bgrQ7ceZYWXHZC2x/4Tvvqqs6OhVMVc3w44CCYiON87bpFINqNtHrpZsrtAtSi8tHcOjL+e4VsIqgQf+OZZrdVwft75jMwU/n4igQghGqgk/DEMIHdynzdYUQtL9jMu3vmOyxb+Sc51l11cuuzBzpyvAZ9ddLJUrPPPbrcu91FFKy57VfSN0dzcg5L5TZbh2dklBVDn8ucI8Q4legH5AmpYwv5hydSqLnyzcTv2IHWTGJODJzMPj7oFpMhPRozZz2N6CajbS7/WJXdalatFZOdRHYKoKRf7zImpvewJ6ejXRq1OvWihGzny22ECorNhFHjpXA1pGlKppqPL4vVybMIXHjfoRBJaxf+xLfn/MXtAui2ezELtxM2sEYgtqVTYRNR6ckVEjhlRDiF2A4UB9IAJ4DjABSys/y0jI/wpXJkw3cJKUssqpKL7yqXDSHk5h5G0jeeRS/pg3Y++5sMqNP56ckqr4WGl/Uh5GVtOhaEdjSMklYuwdbRi7hgzoVmw2UeSKB5Zc9T+re4whFwVTPn6E/PEmj4d0r3dYTf69j9bWvel34Bdf6waAvHqbF5cMr3RadCxtdHrmOYkvLJOdMKv7NwlFN3qUPAKJ/Xc6629716PGq+pqZtOEjQrq0REqJM9dWIoGyqiBqxp9sfXwmitmI1DTMwQGMXfQGwe29L/ZrTie/t76O7JhEt8blBj8Ll+77Gv+mlSuAJqVk80OfsP+jv7wWqBn8LIxf/g5hfdpXqh06Fz56pW0dw5FrY9V1r/JLw+nM7XUHvzSYyv5P/i70+NOrdnlt6K3ZHex54xd2vvYTvzSYyo+Bk5gVeRmHvllQmeYXy5kN+9j65Bc4c23Y07JwZOSQFZvI4rGPuTnzgpxesRNbcobHfs3u5NCX8yvdZiEE/d67m4tWvuehO6QYDQS1a0L93u0q3Q6duo3u8KsAKSVHf1zCXz1uY1aTK1hzy5tknvyvyMlps5NzJgXNWbZ2eeez/o53OfHHGjSrHUdmDvb0bLY+9jkn5673erxf03AULzr+0u7k2OxV7Hjqa6xJ6UinRs7pFDbeO4OjvyyvEFvLwv5P5+anqeYjJba0TM5siPJ6TvapJKT0fBhoNjtJO4+w581fiZrxZ6VLVoQP6syEVe8T3Lk5ilFFMRloPLEf4xa/WSPenHQubPSQThWw7amviPrwj/z4rVAVTMH+TNk5kwOf/UPU+3NcEgQ+Znq+dBMd7ppS5rFs6Vn8Gj4Np9VT271+3/ZcvPFjj+3Z8UnMaXt9ofFlbwS0imD64R/KbGd5WDzhCeIWbvHYbgz0Y9jPT7kJnZ0j7WAMf/e4zUM2QRjUfEcrDK75z5DvnqDF9GFex3ba7Bz9YQlHf1yCajHT7vZJNJ0yqEzO2pqaiWo2YvCpHOkJnbpJUSGdqsrSqbNYUzLY997vbo7mXHXryiteJHnnURx5nZScuTa2PPY5pmB/Wl09qtBrOnJtHPz8H47+sATFaKDdbZNodf0YFFXFmpTu6kLlxeFnx3o25gbwbRTK2AWvs+qaV8mKOwuFhEUKkhVzpthjKotmlw4hYfUejzRHzWanwcBOXs8JateEZtOGcPLPdfnnCaOKdGj/CaDl3bI1N7xB5Jhe+ZIL+dd3Olk07nGSthzMv0bC2j20vmEsAz66v9Sfo7BairPbDrH37VmkHzlFw6Fd6fzwZfhG1C/19XV0zkcP6VQyKXuPedWK12x2zmzcn+/sz+HMtrLzxe8LvZ7mdLJo9CNse+orkrYfJnHTfjbeN4NV17wKgF+TBl4bhgtFoUER+enhg7tw2fGfiRjVo0SfK7BNJADZp86y48XvWX3j6xz+ZqGrTWAl0+q6MQS1b/KfYJsQqL5mer12a5EFaUO+fZw+79xBva4tCWgdSb0uLb0eJwwqsV7eIGLmbSRp20G3B40jK5fDXy8k7XBs+T5UHif/Wc/8YQ9wbPYqkrYdYv/Hf/Fnl1u9ykXo6JQW3eFXMn6NwzzK8QFXiWYh4bTsU2cLvV7s/E0k745266/qyMolZt4GknYeQTGo9H7rdjeFSqEoGPzM9HzhxiJtFUJ4FUE7H9XXTO/XbyNh/T7mtLuB3a/9zNHvl7Dxvhn81fVWrCkZRZ5fXgwWExPWfkjf9+4iclwfWl41knGL3qTT/dOKPE9RVdrffjGX7PyC6Ye+J6xPYYuk0uvPJm7RFhyZXsJeiuD0yl1l+CTnjapprL/jPdfPNm98zebAnp7Fjme/Kff1dXR0h1/JBLRoRNiAjijnpUWqPibMIYFez6nXuUWh14tf6T2jRjo1EtbsAaDdLRMY+dtzNBjYCb+mDWh+uUuOoSRFPU0nD6TpJYNcTl8Rrm5WJgO+kfVRLSbqdWnJiNnP0XhCP1Zf58orP/dAc2TlkhVzht2v/VzsOOXFYDHR7v8mMnbB6wz78X+ED/JQ5S6SjOhTnFm/z6tjlw4nkeP7emz3aRDsVU1TUdUS6ekUR2bMGWypmZ72ODVOLdXVxHXKjx7DrwJG/fECa258g9iFW1BUBUOALwM+eQBnTi7rbnvXbbau+prp82bhrfp8G4WgWkwei4+KyYBPeL387xtf1I/GF3kuXhaHUBSGfv8kZ7ccJG7hZoxBfrS8cgQ+4SFux2WeTCAn3lMgVbM5OPbbqiI/Q3XjyLXx76D7yDmT6rFPtZgY/NWjXkNDrW8Yx563ZgPuujfCoNJ4Yv8y23N260HW3/k+SdsOFXqMOdT75EBHpzToDr8KMAX5M+rPl7CmZGBLy8K/aYN8IS5TkD87nvuWjGOnqdelBb1evZXwQhYeAVpdO4adL3jG+BWjgSaTB1aIvUIIwvq2J6xv4UVAqsVUaLcng0/ZG6lUBSf/XIs9K9djdq+YjPR69RZaXjnS63kBLRox/JenWX39a64NUmIM8GX0P69g8JLWWhIyok+xYOTDXt/azmHws9Dpoctw5NpI2nYIg5+FkG6t9DROnVKjO/wSkhWXSPQvy7EmpRM5tjcNh3cv9R+cuV4A5nrur/5NJvanSSlmh6rFxPBZz7L2lrdcaZRSYmlQj1F/vlBmp1MWfBrUo36vtiRu2u9WOWrwNXsVHqtu0g7FsPmhT4hfsQsh8Lq4rNns2NKyi7xO08kDuerMHyRu3I9qMVG/d9syq4LmJCSz9tZ3Cm1ObwjwQdqddLjnElQfE7+GTwUhkJqGT3gIY+a9qmvv6JQKPQ+/BMT8u5EVV7yIdGpoVjsGPwuNRvZg5B8vVJm4WNrBGFZf/xrJO13dler3bU/XJ68moHk4QR2aIYTAkWvj5F9ryTyRQFjf9mV6KJWGzJgzLBj2ILlJaaBJpCZpPKEvw395BsVQc0TXsuOT+LPTzdjSsoqUhjb4+zDsx//RtILelIri6E9LWfd/7+C02UHztMkQ4EOPZ2+gzc3jyT6VxD9978JZ8CElBL4RoVx2/OcaK3CnUz3oefjlwGm1seqaVzyyYuKX7+D47FW0vMr7639FYs/M4d/B92FNzsh3WIkbolj3f29zWfRPgGsGO3/IAzhzrThyXJo3Id1aMW7xm5VW2OPfpAHTj/xA/PIdZMUmUr9Pe+p1al4pY5WHqBl/umb0RU1uBJjrB9J4YunXPUpL9ulkl7M/bx2mIM4cG0d/WcappdtQjAZ3KWsAKbGnZ3N65S4iRvWsZIt1LhR0h18MZ9bv87rdkZXLkR8WV4nDPzZ7pcs5FHBYUtOwp2fzT7+7Sd13HKm5pxI6MnNI2n6IPW/+So/nbqg024SiEDG6V6VdvyI4u+WA99TYgkjITUglZXc0oT3aVKo9J/9aB156FecjBFJKkrcfdn2rKl4F10CSezatcozUuSDR0zKLQagqFDIxLC5s4cixcuy3VRycOY/0o6fKbENGdLxX2QNHVi4pe6JdzsDL7NWZY+PId4vLPO6FQr0uLRFeitHOx5lrY9erlZ9SqjmcXsM44Kr+FQYFCjh4787eJfwWPrh06ag6dRvd4RdDg4GdvOZeG/wsRfaVTdx8gFkRl7H21rfY9NAn/NXlFjY98HGhmS1FUb93Wwz+hXSiKuZyhalH1iU63nspqpdqZw+kJHXfsUq3p+nFA7xuV33NNBzSFemlkTqKcKvlMPhZ6Hj/NPwi9VagOiVHd/jFoBhURv35IsYAHwz+PihmI6qPmRZXjqDplEFez9GcTpZe/BS2POleZ7YVZ66NQ1/NJ3b+plLb0GTSAPybNnCTaBBq8T861WKi1TWjSz3ehUZAi0aMX/Y2oT3bIBQFYTJ4vX9CVQjt2bbS7fFvFk7Pl25C9TG5dI8UBdXHTMd7LiGofVOvthl8LbT9vwmEDehI5Lg+DPv5KXq9ekul26pzYaFn6ZQQe0Y2J/5cizU5g4jRPYushk1Yu4clE/+HPcMzxa/plEGM+vPFUo9vS8tkxwvfE/3LcoQiCO7YjDPr93nKBOdh8PchsHUEE1Z/gLGwt4M6iNNmRzGobH7kMw7OnOe2GG/ws3Dx5k8I7tCsSmxJjTpO9OyVSIdG82lDCO3RhpS9x/in/91udiEEvpGhXHZMz8jRKR6941UVc2rZdpZPew57uqfDjxjbm3EL3yj3GLa0TH5vc71bUw9hMuAXEUrLa0YT1rc9jSf0QygKh75awL73fsOWkknEmF70fOmmSu/wVFU4cqxsffILjnyzEEeOjYbDutJ/xn2Fdr46h9Q09r33O3vf/Q1rcgZhfdvT9927qN+r8mf4xRH963LW3f4uQgikU8OnYQhj/n2VoLYXTs69NTmdfR/MIWbeRiwNgun8wHQix/WpbrMuCHSHX8U4cqz8Ej7No3rS4GdhwCcP0Pq6MRUyTsbx02y6bwZxi7aimAy0vHoUfd++A2OAb/4xmx/+lIOfz/tPElhVMAX5c8ner/BtGFLYpWsNi8Y9xumVu9Ds/8kdGIP8mLr/21r9+c5V1Rr9fajXteUFVVVrTcng7x63kZOQkp89ZfC10OOFG+j88OXVbF3tR29xWMUYfMwM+eYxVB9zvlSxwd9CgwGdKjSNM6B5Q0bPfYUbrIu4LuNfBn3+kJuzzz2bxoFP57pVckqnhj0rh6gP5lSYHdVFzPyNnFqyzc3Zg+uBe/CzudVkVcVgsJgIH9T5gpRQOPDJ3+SeSXVLlXVk57L92W+xpWdVo2XlIzUlhx2bYzh2JKlMyRlVgZ6HX0k0nzaU0J5tOPLdInLPptF4Qn8aj+9T5jL8spCyJxrFbPQo8NGsdk6vKr+cb3Wz4e4PvW6XNgdntx1Cczpdi7QXmMOs7cT8u9Fr0ZliMpC84wgNh3WrBqvKjpSSX7/ZxtIFBzEaVTRNUj/Mj0dfGE29EN/iL1CF6A6/Eglo0Ygez99Y5vM1pxN7WhbGIL8yLdb5NWmAZnN4bBeKQmCbxmW2qyaQFZtIzmlPtc5zJO04wnemcSgmA62vH0vfd+/E6Fd1i9eZJxLY8/YsEjfuJ7hjMzo/cjkhhTRcqWv4RtT32g9CszuwNAiuHqPKwaa1x1mx6DAOu4bD7lpPi49LZ8brq3j2zcJTt6sD3eHXQKSU7H1rFrte+xlnjg2Dr5nuz11Px/umlmq2Gtg6krB+7TmzPsqtNF+xGOn80GWVYXqFI6UkYe0ezqzdi0/DEJpPH4oxwBfN4SzybSnnlKsZuWa1c/SHxWREn2L8krerxObU/SeYN+AeHDlWpN1J8o4jnJizmlFzXyFiZMk6ipWH7PgkjvywmOzYszQa0YMmFw+oUdpGnR6YRuzCzW6ZSMKgEty+aZVlSJWGzHQrWzacIDvLRqdujWjeKtRt/6J/DmC1uk+sNE1y8lgKSYlZhIb5VaW5RaI7/Aog/Ugc2576itMrd2KuH0TnR66gzY3jyhxKiPrwD3a+9EN+da3NZmf7U19j8LPQ7taJpbrWqD9fZO3NbxHz7yaEKjDXC2DgzIcJ6daqTLZVJZrdwZKLn+LMur04c136QJsf+oRxy94mtEcbfCNDyTjipYJZEW6VrM5cO2c2RJG6/0SVOJQtj32OPSMnfwYrNQ1HtpUNd77HtIOFt6+sCE6v3s2SiU8inRrOXBuHv11EcIemXLTyvRrTLD18cBf6vXcXmx/+DKEINLuTep2aMervl6vbNA/27Yrng1dXIpE4HRp/zdpN34HNuPW+gfl/3zlZ3lOjFVWQk1OMpEcVo2fplJPMkwn81e3/cGTk5KdHGnwtdLx/Kr1eKVthzC/h08hNTPXY7ts4jCtO/lqma9rSs7BnZOMbUb/WxLSjPvqTrU984Z6TDvg3b8j0oz+StO0QC0c9guZw4syxYvD3QQhczvY8jIG+DPnuCZoVUixXkfwYdLHXGgxhULkm6S+3hfWKRGoas5pc4dGYRvUx0eP5G+ny6BWVMm5ZceRYSdkdjTk0kMDWkdVtjgd2u5N7b/iNnGx3p222GLjjwcH07OdKk539/XYW/bM/P5xzDv8AMzO+nY5SgiLJikTP0qlE9rz5K47sXDcJA0d2Lvve+x1bmme7uuKQmubV2QNFxqyLwxToh19kWK1x9gCHv17o4ewBchNTSTsYQ/3e7bjs2E/0fv1WOj18GUO/f4LICf1c8eHz0GwOgjtWTbjAFOz9FV4xqKiV2LMgdf9Jr7UfzhwbR39aWmnjlhWDj5mwfh1qpLMHOBR1xqt0iTXXwZrlR/O/n3BpJ4KCfTCZXGEzRRGYzCq33DOgyp19ceghnXKSsGavV+0TxWwkdf9JGvTvWKrrCUXBv0UjMo/Fe+wLalu7F1pLTVFvn3n7zCGBdLx3KgDH56zm5Nz1XjtZRYztTVAVLVR3enA625/+GkfB1pUWEy2vGZWfplsZKEa10HRA1VQCLSEdTwqZHxW8z/4BZl75YBKrlhxh7854QsP8GDOxHY2b1fN+cjVSsx4/tZDANpFeZ5TOXBtZMWc49PUCknYeKdU1+7x9B6qve7xV9THT5+07ymVrTcWRnUv0rBUcnDmPjOj/YvKtbxzncR/A1d816LxKWiklmx/+FM2L1ISpnj8jZj1T8YYXQsf7prpst5gwBvmhWkxEjutD/w/vrdRxA9s0xq9xmMfvo8HPQtv/K93ajw606dDA65zDbDEweIT7GpiPr4nxUzryyHOjuOmu/jXS2YMewy8xUkpi5m0g+pflKEZXql+jkT04u/UgC0Y85BZ6UMxGV1ZE3uKhlJKGQ7oy6q8XUc0le6WPXbiZ7U9/TfqROILaNaHXq7dekI0uEtbvY8mEJ5BSumSANUmHey6h9xu3odkdLB7/BGe3HsSRlYPBx4IwKIxb8hZhfdz77TqtNr73m+BVdlgxG7khZ2FVfaR8cs+mkXbgJP7NG7occQXiyM5FqIrH71Nq1HHmj3gILdfuKkhTBE0m9mfYz0/pOjxlYPf2OGa8sQopwWF3YjKpdO/bhDseHIxSVE+DakSXVignUkpWXfsqMXPX52fOGPwstLt9En3fvpOTc9ez4a73sSZnIKXEXC+A3LNpSMd/oR7Vx0SXx6+kx7Nla0YipSRp+2EyTyQQ2rMNAc0blvr8U4u3cvj7xaBptLp2jEtrpxpj+prdwS+NpmNLznDbbvCzMPKPF4gc0xspJfHLd5Cwdi++jUJoccVwTEH+HteSUvJz6CXYUj3XTfybN8zvDFbbSdl3nLW3vEXS9sMIIYgc34dBXzyMT4P/ZpROq42YfzeRE59E+OAutSIjqyaTlprDprXHycmy06l7I1q1rdmJD7rDLyen1+xmyYQnPZqQqD4mpmyfSVC7JkgpXYuqiuC3pld5lPtD2bNscs+msWjcY6QfikWoCprNQYsrhjPoy0dKPGtbf+d7HP1xqdsDq/llwxjy9WOltqeiOLV8B8unPut1obH55cMY8euzpbrertd/ZvfLP7lJSRh8LfT/6F7a3Di+3PZWBVJKrMnpGHzMGHwtbvtyk9KY0/o6bOnZ+esUwqAS2DqCS/d+XaVV3Do1Fz1Lp5zEzt/k5kTOISXELdoCgBAC30ahRS6OFdXDtChWX/caKXuP4cjKxZ6ejTPXxrHfVnHgk79LdH7yrqMc+X6J2wPLkZXLsdkrSdxyoEw2VQSatYierrmlz1/u+vhVdH7sCgz+PqgWE6YgP3q+enOtcfanV+9mTrsbmBV5OT+FTGH55S+4ZXod/nYRTpvDvdWlw0lW3FniV9Z+qQydyueCdvgp+45zfM5qUqOOl+s6xkA/FKOnI1dUxSOn2lwvgKAOntK8wqjS7JLS54Db0jKJX7HDIxPImW1l/0d/legacYu2oDk83zicuXbiFm4ptU0VRfjQrkiHZ0cug5+lTCJzQgh6PHs91yT9xWXHfuKqxD/pdN+0ijC10kk7HMuSCU+ScSQOzeZAszmImbuBJZOe+u+YAydx5nimqUqnRkYZWmjGLd7KsmnPsWjcYxz+ZqHXt1Kd0qM5NU7FppGa7PnmWt1ckGmZjuxclk55hjMb9qEYVDSHk/BBnRn110tlqjZsdfUodr38g9d9TS8d7LFtyDePsWDEQ2g2B85cGwY/C+bQQHq+fHMZPosVUcjikLcCI28YA3xRjAac5z00VJPBaxFQ3JKt7HjuW9KPnKJelxb0fOlmwgd2KrXtxdrl58Ogrx5h7c1vIR1ONLsDg5+FhsO60Xz60DJfVzEa8AmvPGnk3LNppB+Oxb9FowqTYI76YA5Om/tbjWazk7TjMCn7jlOvU3PC+rTn2K8rPEKLQohSx+m3/u9L9s/4M/9aZ9bv4/C3Cxm/7J0aJcNQ29i68STffLwRu92J06nRul0Ydz8yhMDgmtGEqEJm+EKI8UKIg0KII0KIJ7zsv1EIkSiE2Jn379aKGLcwNj/6uascP9vqCoFkWzm9Zg9bn/iiTNfzbxbOkG8eR/U1YwzwxRjoizHAl1F/vog52HMBMbRHG6Yd+p7uz11P6xvH0fedO7l039duC2slxadhCBZvzktVaDLZe2/U8ynUeQpoccVwt03H/1jDskufJXHjfqxn0zi9YieLxjxaInXNMxv2sXTy0/zR8UbW3PIm6Ufiij2n5RUjuGT3l3R54ira3z2Fkb8/z+i5L9fIjBLN6WT9Xe8zu+mVLJ7wJL+3vIaVV7/s4ajLQtrBGLdF/nMoBpXMEwkAtLxmFKZgf1dbxDxUi4nQ3m2p36ddicfKjDlD1Hu/e4T4krYf5uTf68rxKeoWqcnZZKT/dw9PHkvm83fXkplhxZrrwGHXOLz/DG+/uLwarXSn3Iu2QggVOASMAWKBLcBVUsqoAsfcCPSWUt5T0uuWZ9H2e/8JXis0jQE+XJs2r0zXBFebw/gVOxEGlUYje2CoxKrJgqy48iWOz17ptk0YVKYd/I6AFo1KdI3YBZtYccVL+W8L0qkx7KenaDp5YP4xUkp+a3E1WSfPeJxfv3c7Lt78SaHXPzl3PSuvetm1TiElQlUw+JqZtOEjgjs2L5GNNZ3db/zCzpd+cPvdUn1MtLv9Yvq9e1e5rr3j+W/Z/cavbhrx4HLoUw9+h3+TBgBkn05m6+MzOTl3ParJSOsbx9Hj+RtK9eZ65IclbLj7A48GPQCtrx/LkG8fL9dnudA5diSJz99bS+KZTJDQrFUIdz40hL9n7WbtymjkeanBJrPKs29cRJPmVZObX9SibUWEdPoCR6SU0XmD/QpMAaKKPKuSkFIWujjqKKT/a0kxBvi6OciqICs2kRgvsy7FZODU0m2YggPIjjtLWL/2hPXvWGi6WOOL+nFVwhzil+8AKV0PrPOyQJxWO9mxZ72en7wnulAbpZRsuPsDt/iydGrYM3PZ+uSXjK6BolhlIeqDPzwmEs4cGwdnzqPv23eUK0umw92XsP/jv7E5nK56BED1NdPi8uH5zh7At2EIQ7/zeIkuFaZgP6+/J8KgYg4LcqUAJ7oakdRv4PkGW5fJSM/l9WeWkFtAFO3Y4SRe+d8iGjQM8HD2AKqqkJqSU2UOvygqwuFHAjEFvo8F+nk5bpoQYiiut4EHpZQx5x8ghLgNuA2gadOie5IWhhCC8CFdSFi9x73EXggaDutapmtWJwnr9qKYjDjPm/k5s61svO8jVJMBp9WBYlRpMKATo+e9UmimkMHHTJOJ/QsdSzUbMQT4YE/z7Drk2yjUyxkurEnp5J5N89whJQlr9xZ6Xm3DW44/uLKvNIcT1VR2h28JC2by1s9Ydd2rnFm/z1VApiiE9mqDlLJC874jx/VBMXn+6StGAwHjBvHEPXP/c/hhftz16FCa1gBnVRNYuyIap9M90UDTJDnZNkLDfDGaVOw299Ccw+6kWcua0W6zqrJ0/gGaSym7AkuA77wdJKWcKaXsLaXsHRZW9srEgR/fjzHQF8XscnyKxYQx0Jf+M+4r8zWrC0tYMF4VnHBpvdszctBsdhxZuSSs20vUB3+UeSwhBJ0fudxDzsDga6bb09cUep5LpdK7Q7KEBZXZnppGWP8OXrcHd2hWIVo1ybuOkrT9cH61sDMzh22Pf0nUjLL/TL2hmoyMW/wmPg1D8tekDL4W+nx8Px9+E8XpuHTsNid2m5P4uHRef3qx24y2LnPmdIaHQwfQnJImzevh52/CYPjPrZrMKmMmtScwyOJxTnVQEQ4/DmhS4PvGedvykVImSSnPvQt/CfSqgHELJbhjc6bu/5Yuj15B40n96frYFUzd/y3B7cv21lBWsk8nc+Dzf9j/yd9kxSaW+nwpJUk7D2PP8qwB8IYzx8qhrxcUe1zy7qNsfvQzNtz9AaeWbXcTgur25NV0emA6Bj8Lqo8ZY6AvPV64kTY3Fd65x5AnDKb6uK9pGPwsdHnsyhLZXhvo997drodbngKiUBQMvhYGfHx/hVx/21NfeYSMHNm57HzxBzc11oogtEcbLo/5lTHzX2PEb89x1Zk5JDZp5TF7BXA4NLasP1mh49dW2rZvgNniJTAioEPnhrz07kRGTWhHg4b+tGgdys13D+Dy62uOJEpFhHS2AG2EEC1wOforgasLHiCEaCSlPCf/OBnYXwHjFolvwxB6vnhTZQ9TKIe/X8SGO9536elI2PLIZ/R64//olKfsWBL2vDWLXS/+4KEPo/iYwKF5zZv2lulRkH0fzmHbk1+h2exIp8aR7xfTdMoghv7wJEIIhKLQ6+Wb6f7MtViT0rGEBZdI4bH/jPtwZOVy4s+1qGYjmt1Jp4em0+am2lH0VBJCurViyvbP2fPmr5zdcpDgTs3p+sRV1OvcokKun3nstNft9vRsHNlWjP4Vk9qXmJBB0tlsGjcNJnxQ5/ztKUnZ2Kyev1M2q4OUGphTXh30HtiUv2fvJjEhE0deDYnRpNK2QwNatHaFPa++uTdX3+x1zbTaKbfDl1I6hBD3AIsAFfhaSrlPCPEisFVKORe4TwgxGXAAycCN5R23JmDPzOH476vIPpVEgwEdaTi8O0IIsuOT2HDH+x6Lx9se/4LG4/oQ1LZJIVf8D83pZPdrP3ut8A1q2xhntpX0w+5pj4rFRKtrRhV6zezTyWx74ks3uxxZuZz8ex3xy7YTMbpX/tjpR05h8DWXWM7XYDEx/OenyU1MJSvuLIGtIiqt0Ud1Etg6kkEzH66Uawe0jiBlt+fiuCnYD4Nf+UMCOdk2ZryxikP7EzEYFBx2jdET23HFDT0RQtC6XRgmswFrrrvTN5kNtGpbv9zj11ZsNie52Tb8Ay0YjSrPvHER//y+h01rj2MwKAwb04bxk72H+2oaFVJ4JaWcD8w/b9uzBb5+EniyIsaqbBLW7WXb/74kNeqEqwn5izfSeHxfj+OSdx11FVfZHfnt9+r3bsfYha9z4s+13ptwOJwc/3013f5XeDz8HPb0bK9VleCaCY5f9g4LRz2MZv+v21Ng6wg6F9HV6NTirW453OdwZOVyfM5qIkb3Im7JVlZf9xqOLFdTl8A2jRk55wUCW0UUazO41hxc6w46paX3a7eyfPoLbj93g6+Zni/cVCGLtl9+tIGD+87gcGj5cejlCw4R0TiIoaNb06FLQ5q2qMfxo8n5+40mlWYtQujYtXRifRcCdruTn77YwtoV0Ugkfn4mrrm1D/0GN+fKG3tx5Y2VGpmuFC7IStuycnrVLhZPeDL/D86alM7y6c8z5NvHaTF9WP5xUkpWXP6CW9aGIyuXxM0HiJrxp0uy1lt9g5QlLl83Bflh8PPBZsvw2BfUrgn1e7XlsuifOPrzMjJPJBA+qDNNJhXdrFoxG703dFBcOfMZx0+z/NLn3N4qUvYeY+GIh5h+7KcaWQx1IdH4on4M//Vptjw2k4wjcfhG1Kf789fTtoj1k5KSk2Nn5+bY/DDEOaxWBwv+jmLo6NYoiuCxF8aw+J/9rM3r6DRkVCvGTOpQo9UhK4tvP9nI5nUnsOdVqKel5vLljPUEBfvQvnN4NVtXNnSHX4DNj3zmMat2ZlvZ8vBnNJ82NP+XPvNYPFle8tWdOVaOfLuI0fNeZevjMz32KyYjzbxIMXhDKAo9XriBbU984d45ycdMr1ddhcrmkEA63nNpiT9fkwn9vOrFq2Yjra4by6Gv5ntq7mgSW1oW8ct3EDmmZsYlLySaXjyQphdXfK1HTra9UKedmfHf75fJpDJpWmcmTevs9di6QlamlU1r/3P257BZnfz9227adx5TTZaVjwtaPK20pO477nV79qmzOK120o/Ese/9ORz5YUmh7fekhIDmDenx4o2oPiaEQXU1qvA10/H+qYR0LbnmScd7LqXfjHvxaxaOYjRQr0sLRv3xQpkboRgDfBk55wUMfhaMAT4Y/C2oFiM9X7qJ0O6tyTqRgGbzshCsaR6NsXVqLokJmSxfeIh1K6LJznKt1wTX88EvwLMyXFGgc7eSVWvXJVJTclAN3h+QiadL36u6pqDP8Avg0yjEa6aEwd+HPW/+yp7Xf3GlMArhVdpX9THT5qZxAHR55AqaTOzPsdkrkQ6NZtOGENq9daltanvTRRXySn+OyLG9ufLUb8T8uxFnro3IcX3yi6oiRvfixJ9rPcS5pFOjQSWIp+mUDmuuHYdD4udfuKTHH7/sYv4fe/MyrgTffraR+54YTpceEVx3Wx8+e3ctDruGlGAwKJgtBqZe3b3qPkQtIayBP9JLJqxQBK3a1d4FbL0BSgEOf7uQjffMcIthq75m2tw0nsNfL/S6iKr6ml2Lpn4+hPZozdhFb1aZxk5F48i18U/vO8iIjs/P5KkJjVLqOhnpuXzxwXr27ooHCY0iA7n1voH5aYDnOHIgkTeeW4LN6h6GMJlUmrYMIfqQKwwZGGQhIMhC524NGTelI/VCLrxsqopg3py9/D1793/3U4DZbOD5tycQ0bjmFhRWtpbOBUPrG8ZhS81kxwvfo1ntCINCpwen48y1eUgbwH9aJwEtGtFgQEcajepZqxe3DBYTkzZ8xL7353Bs1goMvhba3zWZ1tePrW7T6ixSSl5/ZgnxsWk4na7JWezJVF5/ZjGvfzzFzVmvWX7UaxWozebk6MHE/ChkelouBqPCZdf3RFX1qG5hTJzaiZD6vvzz+17SU3No3S6My67rUaOdfXHoDr8AQgg6PTCdDvdcSu7ZNMwhAagmI5sf+9xrzF4IQfigzrS9ZUI1WFs5GAN86f7MdXR/5rrqNqVKSdxygB3Pfkvy7qMEtmlMj+eup9GIHtVtFkcOJpKYkJnv7M/hdGisXHyYS6/slr/N4XAWtrTktl3TJJkZVvZsP0X3Po0rw+wLAiEEA4e1ZOCwltVtSoWhP969oBhUfBuG5OujtLhsmIdsALhi200mFS5GVtFknzpL/MqdZMWVXqahtmHPyMZRSB1CRZOwbi8LRjxE3KIt5MQnk7B6N0sufooTf62tkvGL4szpTG8lHdjtGvGx7oJ1/QY391727wWHQyMh3jPlV+fCRnf4JSCsT3s63DUF1ceMUBUUowHVx0S/D+6u1M5K59DsDlZd+yq/t7qWZZc+y5w217PyqpeKbLyRFZtI8p7oWte2LmXvMf7pexc/hV7CT8GTWTzhCbJPV26G0OZHPvOUPc62svnBT6juNa5mLUPQnJ42mMwqrds3cNvWpUcEPfs2xmQqvl5CVRWaNA+uKDN1agkXXEgneddREjftxzcilMjxfSusXVufN2+n1bWjOfn3ehSTIT92XxXseP47Tvy5FqfVnr+WcHLuBrY//Q193rzN7dichGSWT3+BpG2HEEYVRVUZ8OkDtLxiRJXYWh5yk9KYP/SB/II2CZxaup0Fwx5g6v5vy6U3XxQpu4563Z4Vk4jTaq/WRfjGTYPp1K0Re3aewmF3pY0IBXx9TfToHcms77aza1ssgUEWxk/uyO0PDub3H3cw/68orw8KAINRoVFkIB261L3qWXCti8TFpGHNtdOsRQgGY90pKLxgHL7mcLLiihddTbkFKKqKMcCHCavfJ6BlyWQBiiOka6tS5dFXFAc+netZEJZj5eDn/3g4/CUT/0fy7miXiFpestHaW94isFUE9XuXvA1eZSOlJOrDP9j79mysSenU792O0N5tPRbHpcNJzulkTi3bXmmFX5bwemTltREsiMHPgupFN76qGTOpPXt3xud/LxBcdGkHXv7fIjLTrTgcGnGkcfTQWaZc3pUtG04W6ux9/YwMGtGK6dd0r9UJBmUlIT6d915eQfLZLISiIATcfM8A+g5sVt2mVQnV/9tcQRz4bC5xi7bkO0YnYM/KYfnlLzJl62fVa1w5sXtpRXdue8HmGCl7j5F2wLM3qjPXxr4P5jDsh/9Vuq0lZevjMznwydz8FNiEtXs4szHKq9qn5tAKVZKsCLr972o2P/ipRzpuxwemlemtIivTyqGoM/j4mmjbIQylHJkwOdk2PnhtpVvFp6ZJZn27A0URblIJNquTv2btppCe96iq4N0vpuLjWzvThsuL5tR4/ZklpCRl5y1iu+7pF++vo3GTYCKaFJ19Y7M52bjmGHt3xhNa34/hY9sQ3iig8g2vQC4Yh3/ws388+9hqkrSoE2TFJuLXuOwNVaqbsL7tXV2QzqN+n3Zus7Sc08kIb6+nmvTap7YqSFi7h+3PfUvagZMEd2pOzxduJLhTc/Z/9JeHmqh0aghVyW/xdw6hCEK6Vd6bVdtbJ5J7Np3dr/0MUiI1Sfs7J9P92dJnKi2et5/Z3+/AYFCQUmI2G3j0+dFlbm+3fVOs1+2aJtG8yGQYDAr1w/yIOZHqsS8gyILFp/yNWmorB6POkJ1l88hkcjg0li86xLW39gFcBW4rlxxh+6YYAoMsjJ7QjqYtQ3jx0QUkJWZhtTpQVcHS+Qe49/FhNGsZwv49p7H4GOncrVGNDhFdMA7fW548AIoofF8tof+Me5k/7EGcuTakw4kwqKhmIwM+cu/gFdqzjUcTbHA1wo4c16eqzM0nbvFWlk19Nv9BnBOfzML1++j3/t0oJoNn72EpQSgIo4rMm9GqFhOhvdtRv2/7SrNTCEG3J6+m80PTyY5Pxie8Xqmagp/j6KFEfvthR363KIDcHAdvPb+U97+aVqaZfna2rdDwjDecDo2LL+vClzPWY7M585ulmcwqV9/cu06Gcc6Rnua9kZCmSVKTXHr/uTl2Xnh0AWfPZLrun4CdW2Pp0LkhiQmZ+W9aTqfE6XQy441VaJp09dJ2uG52y7ah3Hb/IBpF1rx8/QsmS6fl1SNRzZ6zF58G9QhoWbu1QkJ7tGHKjpm0vXUC9fu2p83NFzFlx0yPmLw5JJDOj17upp2umIyYQwNpf+fkqjabTQ985DX7Zd/7c7w/hIUgYlQPWl83BlO9ACzh9ej4wDTGzn+tShyVajYR0LxhmZw9wPKFh7wWPlmtDg5Gle0Nq3P3Rl4VTo0mFVX13GHxMdB3UDOeenUcXXtEEFTPhzbtw7j/yeH0G9y8TDZcKLTp0ACnw1MvwWQ20LV3JAArlxz5z9kDSFeobPf2OA8hNXDtc9i1fGcPEH0oiecfmU9qDWwac8HM8Ls8cgUn/lhL5onTODJzUS0mhKow9Mf/XRCzmsBWEQz85IFij+vx/I2EdGvNvvd+x5qURpNJA+jy2JWY61VtrFFKSdpBjz71AKRFnaDNLRcR/ctytweC6mOix4s3EdanPT2ev5GUPdEEtIwoswOuarIyPMMFLgQ5ZewJ2ygyiOFj2rB66RGsed2ozBYDnbo1JGr3aZw57mm3ubkOdm2Lo3vvxjz8bOHNcOoiIaG+jJrQjhULD+ffS6NJpUG4P/2HuLqWbd908j9nXxBBYa2lvWKzOVm64BDTr+lefsMrkAvG4RsDfJm87TNOzFnD6dW78G/ekNY3jMO3Yc3oFl9VCCFoPnUIzacOqXY7zCGBWJPSve4PaB1Jh7sv4cAnf+PIsRLYOpL+M+4ltGcb1tz0BsdmrUQxG9FsDsL6d2D0Xy/V+A5avQc0Zd/ueA8tG6dTo13HBoWcVTzX3Nqbrr0iWLPsKA67xsDhLQgIshC123Mh22Z1smrJEbr31itovXHljb1o06EBy+YfJCfbTr9BzRh5Udv82oWAQO+dxVRVAZX81Nji0JySY4c9JdSrmwvG4QOoJiMtrxpJy6tGVrcpOkCnhy5j+1Nfed13YMafXBE7m96v3Ypmd7iaxuDq43vst1Uu/aK8GP+Z9ftYf+f7DPuxdFlGiVsOEP3LcqQmaXnFcBoMqFzFz/5DmrN80SFijqdgszoRwjWDnH5Nd/z8y/6WIoSga89IuvaMzN+2b1c8wms3G7z2pdVxIYSgd/+m9O7f1Ov+MZPas3t7nNtDWwgIDfOjfadw1q885gqlCTAYVKy5Dq+hHlUVNG1R8yabulqmTrk4vWoXWx7/nJS9x/GLDKP7c9fT6mpXKMGencuPAZO86hCpPmauz5rvsX12syvJivGUjlBMRq5Nm5v/YCiObc9+zb53f8eZY8sbz0S72yfR7527SvPxSo3D7mTjmuNsWX8SvwATI8e1pXX7is8Qs1kd3HPDbx79Z81mA9ff0ZfBI6q+XuRCYfE/+5n9gyvTStMkwSE+PPrcKMLCA0hMyODwgUSCgn1o2yGM915ZQdSeBOR5GVMWHwOvfjiZ0DC/Kre/KLVM3eHrlJnTa3azePwTbkVhqq+Zvm/fQfs7XIvEf3S8ibQDJz3ObTSyB+OXvu2x/cd6k7GnZXlsFwaVqxP/wBTkX6xdaYdi+LvHbfnOPt82HzOT1s+o1BTPqmTL+hPMfH9dXsaIhtlioHW7+jz87Cg3FUynU2PL+hNsWnsCHx8Dw8a0oV2ncLIybaxdcZSTx1Jo1jKEwSNa4utXN3P0zycn28bRQ2fx8zfTvFVIoeuAmlNj07oT/PHLThJPZyIltGpbnxvu6EezltUzw9flkXUqhW1Pfum1JeT2Z76h3W2TEIrCgI/vY8nFT7nCM5p0df/yMdP3nTu9XjNiTC9O/rEWqbnHSgNbR5bI2QPE/LMB6SWVUbPZOTl3/QXj8PsMbEbzViGsWR5NRlou3Xs3pkvPCJQClVeaU+OdF5dx5OBZ19uAgC0bTjJ8bBvWr4zGZnNiszrZvO44c2fv5rm3JhAWXrL7fCHj42uic/fiK/QVVWHA0BYMGNoCmVfDUZ5Cu8qm5lqmU+NJKaQlpD0zB2uKS4mx0YgeTFo3w6U91LIR5vpBIGD19a9x4k9PNco+r/8fxmA/V8N1XDN7g6+FgZ8/WGK7zmVonY9QFdRa2pymMMLCA5h6VTduuKMf3XpHujl7gO1bYv9z9pCfZrh43gGyMm35sWqb1Ulmpo0fZm6u6o9wwSCEqNHOHnSHr1MO/JuFe92umoxus/GQbq3ocPclZJ9OJjchBUdGDil7jrHqulc5/O1Ct3MDWkYwdd/XdH74chqO6E672yYyecfnNBzStcR2NZs2FG85dEJRaHH5cI/tdruTRf/s55kH5/HsQ/NYOv+Am2RBbWb7phiPOD8A0nNpRWqSvTtPVY1h5eBEdDLffbaJj95YxfpV0Ti8LJrqeEcP6eiUmZ4v3sTKq192y6U3+Fro9PBlHiqlW5/4wmsR1tbHv6D19WPdNGt8wkPo9fLNZbbLt2EIg79+jLU3vYkwqC65BKfGgE/u93hIaZrk7ReWEX34bP5sd9Z329m5JY6Hnx1Z62s4fP1MKApoJXx+GSpIXbakJCVmsXT+QWJOpNCyTSijLmpHULBPocevXnKYH77YgsOhoWmS3TtOsXT+QZ58eSzGGixpUFPQHX4RpB2MISvuLCFdW2KpX/PKpKubppMHMmjmQ2x5dCa5iakY/Cx0efQKuj5xlcexKXuivV7DlpaJLT0bc3DFxo1bXjGCyDG9iPl3E0hJ4wn9vP4Mo3bHc+xIklsans3q5FDUGQ4fSKRth7Lnz9cEho1uzcrFh9HOKyYyGBQkuFWeGgwK/Yc2rzLbjh9N4tWnFuNwaDgdGgf2nGbJvIM8//ZFGAwqZ89kEtk0GP8AV0prTo6dH77Y4lYYZc11EHM8hQ2rjjF0dOsqs720JCdlc3j/GQKDLLTr2KDaQj91wuHHLdnK9me+Jv3wKYLaN6HXyzcX2b7OmpzO0inPkLT9MIrJgGa10+HeS+n9+v/V+hlfRdPq6tG0vGoUjuxcDD7mQtUl/Zo0INVLzF8xGTH6Fz6jKw/mkEBaXzeGXdviePHF1SScSiekvi9Tr+7GgKGutnWH9p/xGvKwO5wc3n+m1jv8Js3rce2tffjxyy35gm4Gg8Jdjwxl9vfbiY9LdymuIohsGsRVN1eOBLU3vvlko9u9t9s1HA4bLz2+kNxcBwaDgsOuMeqitlx5Uy+OHEhENShw3sPLZnWyae3xGunwpZT8+u02ls0/6LId11vXEy+NIbxRYJXbc8E7/Jh5G1hxxUv52SSJG6JYMukpRv3xQqGCYquue42zmw+g2R355x345G/qdW5B6+vGVJnttQUhBEa/op12j+dvYPUNr3uGfx6cVqYmNUk7j5AadYLgDk0J7dGm0ON2b4/jozdW5c8Kz5zO5OuPN2K3Ohk6pg3B9XwxmVWP6lijUS0ytFCbGD62DX0HNePAvgTMZgPtOoVjMCg8//YEDh9IJD42jcgmwbRqV7/KJjQOu5MT0Ske26WEjHTX78g5XaLliw7RMDKQyKbBhXYgq6nppNs2xbBi4WHsdg17XpWuNdfBey+v4LWPJlf5BPKCX7Td/PCnXpuHbH7kU6/H5yalEb98h0drQEdWLvve+63S7LzQaT5tKP0+uAdz/UAUkxGDvw8dH5pGj+duAODstkMsHPMIP4VM4c8ut3Bs9kqv17Fn5bBgxEPMH3wf6+98j/lD7mf+sAcK7Rnw2w87PLRRbFYnv/20Eykl/QY3Q/HyVqIqgt4DvFdj1kZ8/Uz07NuETt0aYcibaQohaNuhAcPGtKF1+7AqdT6KIryKv3nDZnWy8O/9tG4Xho8XeWeTWWXk+LYVbWKFsGz+wXzdnnNICUlnszh1Xk/iquCCdvhSStIPx3ndl3bAu7CXPT3ba0ofgDVJb/pcHtrdMoGrTs/hylOzuSbpL3q9eDNCUTi7/RALhj1A/LId2FIzSd13nDU3v8n+j//yuMaWx2aSuDEKR7YVR0YOjmwriZsPFPoAPx3nXcsnM92KzerAz9/MYy+MJqS+L2azAZNZJSzcnydeHlunteMrG0VV6D+kOQZjyVxQVqYVRRE8/OwoAoMsWHwMWHwMGI0Kk6Z1rrHtGnOyvYvmKYpCbk7VS2Bc0CEdIQSWsCByEz2fpD7h3htS+DcLxxjg65FRIgwqkRf1rRQ76xJCUTCHuMcutz/9NQ4vGTzbn/6adrdNQjH+92t69PvFHtLKmtXO0R+WMuizhzzGC23gR3ysp9P38TViMruu26ptfd79YqrrOAGNIgP1tZoq4Lrb+nI2MYvow2dRVVe8HiGx2zwb4Jxz6E2a1+P9r6dxYG8CWZk22nVqUKNDb30HNSP2ZKqHbLYQ0KxF2ZrilIcLeoYP0PXJazD4uivgGXwtdHv6Wq/HC0Vh0OcPofr+twCpmI2Y6wXQ/Rnv5+iUj6Tth71ud9od5CS4x3kLa2bjtNq8xnenX9MjXwnxHCazypTLu7g5dSEEEU2CiGgcpDv7KsLiY+TJl8fy3FsT+L/7BvLKh5O49/HhmMwq534Eqqrg42Ng+rX/JVmoqkKnbo3oO6hZjXb2AKMuakt4w4D8yYWiCEwmlZvvGVAtnbEu6Bk+QMf7p+LIzmXPG7+i2R0oZiPdnrqGdrdfXOg5TScPZOLaD9n33u9kRJ+i0cgedLznUixhwUWOlRF9it1vzuLs5gMEd2pGl8euJKRLywr+RO44cm1sf+orDn29AGe2lYYjutP/w3sIatukUsetSPybNyT3TKrnDgnmUPe3gUYjunNq6Xb3qiEhaDTCe1Pu3gOaYrP1Z/b3O0hNzsbP38yUy7swZlLlddDSKR2NmwbTuGkwAOGNAnn6tfHM/3MfCfEZtOkQxkVTOhJSv+pFyCoCs8XIc29PYOOaY+zeGkdwqC8jx7Utsn9uVqYNkOVSWC2MOiOeptkdWFMyMIcElikrpDiS90Qzf/B9OHLy2hAqCqrFyOh5r9JoePcKH+8ciyc+yekVO/9rFygEpiA/pu7/Bp/wmifP6o3YBZtYftkL7s1QfM20u3Ui/d6/2+3YtMOxzOt/t0s+OceGajGhWkxM2vARQe2Kfsg57E5Ug3JBzeBtNifZWTYCA801vqz/QiEtNYd5v+9l59Y4/ANMjJvcgX6Dm5f79yoxIYPP31tH9JEkAJo0C+b2BwcT0bh0NUC6WmYVsHDso8Qv3e6xPah9U6ZGfVMpY6buP8Hc3nd6ZCEpFhNdn7iSHs/eUCnjVgZHfljMlkc/x5aWhaIqtLvjYnq/fpvXh3Pu2TQOffEvZ7cfJrRna9rdOrHYt6+CHD+axLIFh0hPzaFH3yYMHNYi/5W7tuBwaPzy9VZWLT0CuGSRr7qxJ4NHVVwuujXXzp+/7mbdimg0TdJ7QFMuu7YH/oG1owNZZZCZYeWp+/4hI8OaX7RmNhsYM6kdl13XM/+45KRskhIzaRQZlF84VhR2u5NHbvuTtLTc/6SWBfj5mXjni6les5MKQ1fLrALOrN/ndXv64VgcOdZKadOXGnUCxajiPC8jUcu1cXbLwQofrzJpfd1YWl0zGmtSOsYgP1RT4b/glvpBdH3y6jKNc6403+7QkJokas9plvx7gGffvAhzLXL6P325hbUrjuYvBtptTr6buZmAIB+69Y4s5uzikVLyxrNLOXksJb/Bx5rlR4naHc+rMybXWRmDZQsOkpVpdatQtlodLJp7gPFTOmI2G/js3bXs3n4Kg9G1ED1iXBuuurm3h7BdQXZuiSU31+6uqy9dD/ZNa48zfEzhtSaloULeAYUQ44UQB4UQR4QQT3jZbxZCzMrbv0kI0bwixq1JmAqRBlBMBhRT5TiSoHZN0ByewlGK2UhI94r5BalKhKJgCQsu0tmXFYfdyfefb+Krjzdisznz/7BsVidn4jNYtdj7wnFNxJprZ82yox7FYjark79n766QMQ5GnXFllxQQJnM6NNJSc9m63rO/QV1h7874/AKqghiMCieik/nhiy35Dc9zsu3Y7U5WLjnMsvkHirxuYkKmRyYPuIq0Ek9XXDp4uR2+EEIFPgYuAjoCVwkhOp532C1AipSyNfAe8EZ5x61pdLp/Gqqv+yxe9THR5qaLUNTKmQ3V69yCBv075ksJ549rNtLhzsIXpWsaUkqys2wVonqYlWkjIT4Dp9P9j/KbTzayaskRr+fYbE42rD7Gbz9s583nljL7++0kn/VswlLdJMRn8NsPO/hyxvpCK07PJlaM3Sejkz3uIbgc0LGjSRUyRm0krIEf3kL1TqdGQKCZDauiPR4INquThXP3F3nd5q1CvGbtWCwGWrSuXy6bC1IRU8++wBEpZTSAEOJXYAoQVeCYKcDzeV//DnwkhBCypi4glIHOD19G5vHTHP5moav5ttVOk4sH0PedOyp13FF/v8Tmhz/l6PdLcNrshA/sRP+P78c3ouJ+SSqTPTtO8d1nm0g+m4WiCAaPbMXVt/TxSKUsDmuunS8/2sD2TTGoqoLBoHD1Tb0YPKo1melWNq09XqTk8fGjyZw8loLDoXFwXwLLFhzkqdfG07R56XOld2+PY8m8A2RmWOnVvymjJrQrVQzWG9s2nuSzd9fidGo4vTR3AUBAy9ah5RrnHGHh/vlaNgUxmw00jKh6DZjKICM9l9nf72DrhhMIIRg4vCXTrule5M9q3OSObNlw0u3tSlUFkU2DCQsPQNO8/2xcmTeF06FLQxo3DebkseT8B4bBoBAS5kf3PhXXkL4iHH4kULBsNRboV9gxUkqHECINCAXc2roLIW4DbgNo2rR2lbW7ujvdT48XbiTtYAwBLRpWidM1+vkw6LOHGPjpgyBloeJlNZFjR5L48PWV+X88Tqdk7YposjJt3P3o0FJd6/P317F7WxwOu4bDrmEFvpu5mXr1/fAPMGMwql5fxcFVBKNpMv+P1eHQcDg0fpi5madeHVcqO+bO3s0/c/bmf6aYE6msXX6UF96ZgNlSNqdvtzv54sP1HhIR7h8CzCYDU6/pXqYxzqdrr0j8/M3YrM78+yKEK3QxoAoVNSsLu93Ji48tICkxO/9NZsWiQxyKOsML70woNOOmWcsQbrt/EN9+ugm73YnTqdGmXRh3PToUH18jIfX9SEzIdDtHCGjXsWgRPiEEj780hrmz97B2xVGkhP5DmnPJFV3zpTAqghq1SiWlnAnMBFeWTjWbUyYs9YOqRUpZCIHXd80azLw5ez3ilnabkx2bY0hNySG4XsmKatLTctmV5+wLYrM6mffHXu57fFihs3uhCK9N1gEO7z/jUpIs4X3NTLcy97e9bnFvu81J0tksVi09ytgy5v4fO5JUmImYzComk4GWbUKZfm2PMr2ReENVFZ5+fTxffriOA3sTAGjeKpRb7xuIj2/NFCorDds2niQtNdctbOWwayScSmf/ntN07Nqo0HP7DGxGz35NSIjPwNfP5PZ7euOd/fjgtZXYbU6kBEUVmEwGrrihV7E2mc0GLruuB5ddV7iSb3mpCIcfBxRMgG6ct83bMbFCCAMQBNTdQKAO4NK58ebIDEaV5LNZbn9IVquDzHQrQfV8PGY86ak5XsMPAElnsvDxNTFmYjuWzj/o9ipuMCo8/uIY3nlxObk5nhW8JpOhVLnVRw+dxWBU3Bw+uB48O7fGltnhG41qoTH7dh3DeeS5UWW6bnGEhPry2AtjsFodaJosd1iqJnH8SLJXWWyHQ+Pk8ZQiHT64Hoje8uM7d4/g6dfG8+8f+zh9Ko1WbcOYcGmnGtMnuCIc/hagjRCiBS7HfiVwfs7cXOAGYAMwHVh+IcXvdcpGq3b1ORWb5hH3dDi0fK1wh0Pj56+2sHrZUVdIwaAw7ZoejJ7QLv/4Bg0DvD44FEXkv0pffn1P6oX6suCvKDIzrLRqW5+rbupNs5YhDBvTmuULDrk5aqNRYcio0jU79w80e43hCkGJ31a80axlCH7+Jg8HZbYYGDGu8rOxalO6aklp2DgQs9ngoWRpMCo0aBhQrms3axnCXY8MKdc1KotyB4eklA7gHmARsB+YLaXcJ4R4UQgxOe+wr4BQIcQR4CHAI3VTp+4xcWpnTGYVCkyiTWaVURe1xc/fFTb45ZttrFnmyje3WZ1kZ9mZ9d02tqw/UeAcA1Ov7ua6Vh5CuBzi5Mu75H0vGDupA+99OY0vZl3NEy+NpVlLVyXy9Gt70KlbQ4wmFR9fI0aTSocuDbnihv8KaUpCyzahBNfzcYWJCmA0qYyZWPzsPivTRlxMKrbznJCiCB58eiT+gWYsPkbMZhWjUWXoqNb07FfxEhpJiVns3BJL7MnUCr92TaH/4OYYC2j2gOs++/mb6dar/HUMNRW90lanWok9mcqs77ZzKOoM/gFmLrqkI6MuaosQApvNyV3XzvKan9ykeTAvv++eerpt40nmzdlLanIO7TuHc+lV3Uo1Wzt9Kp1TsWlERAbRMLJsmSiJCZm8+/Jyzp7JRFUVNE1y3f/1YUgRFbB2u5NvP9nIxrXHXV2pNLh4emcmTe/sFlJy2J3s2XGKjAwr7TuFl3smej6aU+Orjzeyac0xDEYVp1OjWcsQHnp6ZI1tMFIaHHYnO7bEcuZ0Bk1bhFC/gR/ffLyRwwcSQUCnro245d4B1AvxrW5Ty4UuraBTK0lNyeGR2/70iIkD+AeY+fiHy6vBquKRUhIXk0ZOto1mLUKKlW2Y+f5aNq494Va9aTKr3HBHPwaPKF1YqTws/DuKOT/vdF/nMCh079OYex8fVuh5yUnZHD2YSECQhbYdGhRZUVpdJCVm8dITC8nJtmGzOTEZVRo0CuB/r4xFVRWEIkpUPaw5NZbOP8iyhYew5TroNaApUy7vQkCgpdhzqwpdWkGnVhIYaMZsMXh1+C0qKN+8MhBC5Ks/FoWUkh9mbmbdymMe+2xWJ/Pm7K1Sh7/k3wMe1bsOh8bOLbFYrQ6PWL63fq3+/mYef2lMud8+Dh84w4pFh8nKsNFnUFP6D25eLjnhL2esJy0lJ3+NJdfp4FRsGnN+3sW1t3pvdVoQKSVHD57l+5mbiDuZlp/1tWLhIbZviuHVDy+uFQ1zak/Stk6dQ1EVrrqxp1tsHuGK2Vdm6lpVsWH1MdYsP1ro/vTU3Cq0Bq+ZSuewWz0futs2/tevNTfHQW6Og6SzWbz/6opy2bHg7yjefG4p61dGs3NrLN9/tpnXn1lSZOFcUdisDg7uS/BMDrBrbFjl+bA9H7vdyZvPLeX1Z5dwIjrFzQ6HQyMjPZd1K6PLZFtVozt8nRrN4FGtufvRobRsE0pgsIXuvSJ55vVx+QuutZnF/3jOqAvSql3VVkt37hGBt7q90DA//AI8Y/hL/j3gtV9rYkIm8XFl69eamW5lzo87sFmd+ZlXVquDk8dS2LzueJmuKSm01KLQdNeCLPgriiMHEr2uJYHrbezgvoQy2VbV6CEdnRpP996N6d7bVV6enJRNfGwaiQkZhIVX7KJlVVNYv1NwZfZcfl3psoTKy+XX9WTvjnisuXbsdg1FFRgNru5M3uoRiurXWtRnA1csfMm/B1g6/yC5OQ66945k6jXdXbUMBs+qaKvVwZb1Jxk4rPQNhcxmA63bh+UV0v23XVUFfQc1K/b81UuPFFnlbDCUP5WzqtAdvk6twOnU+HLGerasO4HBqOJwaHTq2pC7Hx1a67Tsz9GrfxMWzd3vEaowGBSef3tCidYBKpLQMD9e+2gyyxcc5FDUGRo1CWLMxPaFauf0GdiUU7FpXvu1Nm1R9BvYlzM2sGXDifw3nLUro9m5LY4b7+iHtzm3EJRIV74wbr13IC89sQCb1Yk114HFx0BwPd8ShQYL08c5h6oqjBjXtsy2VSW18y9Fp84xb85etq4/id2u5c/+9u06zc9fb+XGO/tXs3VlY+LUTmxae5z01FxsNieKIjAYFe5+ZGilOPtTsWn89OUWDuxNwGwxMGxMa6Ze3d0tOyUwyMIlV3Yr0fXGTGzP+pXHSErMxGrNs9+gcMs9A9i/5zS/fruN03Hp1Av1ZerV3fJn54kJmWxed8JtMV5zSnKy7ZyKTcNkUj3WE4wmtVxFZuGNAnjn80vZvO5kXlpmPXr0bVIinZr+Q5qz6J/9Xiu5w8L9ue3+QYSG1Y4WjHpapk6t4N4bfiM9zXMR02hUmTnrqhqZClgScnLsrFl6hL0746nfwI/RE9oX2e+0rKQmZ/PEPXPJzbHnhzWMJpXO3RrxwFMjynxdm9XB+tXH2LU1jpD6vowc35aUpGw+eHWlWxjEZFa5+ubejBjXlq0bT/Llh+u9hn269orgsut68tbzS7FZHQgEDqfGlTf0ZHQJitcqg5xsGy89vpCziVlYcx2YTCqKKrj70aF06RFR41pm6mmZOrWewjJIHA4nmlNDUWpnByYfHyNjL+7A2Is7VOo4S/OkIwrO7+w2J3t3xZMQn54vZVFaTGYDw8e0cevI9Pl76zxi3jarkzk/7WT42DbUD/ND8yLxrKqChhGBNG1ejw++msbBqDPk5Nhp1zE8v/K6OvDxNfHie5PYsTmGw/vPUD/cn4HDWpYrxFRd6A5fp1bQtmMD9u6K5/wAb+NmweXKzy4re3ee4tdvtxMfm0ZQPR8uubIrQyuwn2xFc+zIWa8hCYNBIe5kWpkdvjdOx6V73Z6dZSM310HDiECEl0iKqiqMnuCaxSuqQocuDSvMpvJiMCj0GdiMPgOLX+StyehpmTq1gmtu6YOPxZhf4KMoArPZwI13VH38fv+e03zw6kpijrtyspMSs/hh5mYWzyu6q1F10rR5iNd4tdOhlVlGojDqh3uPZ5stRsxmAz/M3Ow1p37A8BaEN6od2S61Fd3h69QKIpoE8cqHFzNmQjvatA9j+Ng2vPjeRFq3D6tyW2b/sMNryOLPX3ajeWkLWBMYPaEdBqP7n7vRqNCmQ5hXmd/yMO3q7h4dy0xmlYsv64ymSTauPe71bWPX1vNV1XUqGj2ko1NrCA3z46qbva5FVSnxsd6LimxWB9lZdvwDKy62K6Uk+Ww2qioILoeoV2iYH/97ZRzff74pP9d90IiWXH1Lxd/PXv2bcvM9A5j93XZSkrPx8zcz+bLOjL24Azarw2v8HiC3mNz98hIfl8b2TbGoBkGfAc1qTWZNRaI7fJ1aTWaGlZ+/3sqWdSeQUtK9bxOuvbVPsfrzJ6KT+eWbbRw9lIi/v0ulc8yk9iXKuGjQMIAT0cke241GFR+/itNTOX40iU/fWUvS2SyQksimwdz1yNAyhz2atQzhmTcuQnNqCEVUanbJgKEtGDC0BQ67E9Wg5I9lthhpGBnIqRj3h6YQFNt0pDz89esu5v2xD80pEQr8/uNOrv2/Pm6LzXUBPaSjU2vRnBovP7GQjWuOY7M5sds1tm04yQuPzi+yMjI+Lo1X/reI/XtOY7M6SU7K5rcfdzDru+0lGnfa1d3d9X0Ao0mhcbNgnn3oX959aTn795wu12fLzLDy+jNLOH0qHXveZzsRncwrTy7E4UVMrjQoqlJlqYQGo+ox1k139cdsNuSn0hoMCj6+Rq64sXIqi08eT+HfP/Zht7l60DrsGnabkx9nbiE1JadSxqyp6A5fp9ayZ0c8KUnZbrLCmibJzrSxbcPJQs/757c9HtWhNquTpfMPkp1lK3bcbr0j+b8CxTY+vkYUIYg+kkTsiVR2bYvj3ZeXs3rpkTJ+Mli/Ktrtc4FLD8ZqdbCzlse623ZowIvvTWT42Da07xTOuMkdeHXG5EIresvL5rXHcTg8H5JCgR2bYyplzJqKHtLRqbXExaZ6lU7OzXUQeyIFaOH1vOgjSV7L5Q0GhTOnM2jeqnjp5b4Dm9F3YLP8FowrFx/GWSA2bbM6+fnrrQwc1qJMaaNnz2R5fUtxODSSk7JwOjWyMm34+ZtQVQUpJetXHWPR3P1kZVrp3rsxky/vQlBw2VsrViYNIwK54Y5+ZTrXZnUw+/vtrM7rhNauUwOuu60vkU2CCz2nhtaXVjm6w9eplWhODX9/c15nJnfFRiFg07oT+AeYGXlRW8wW97h6ROMg4uPSPXL6HXZnqRfyDAaFvTvj3Zz9OaSUnD6VTuNm9Tz2xZ5IIfpIEqH1/ejQpaFHpXCb9mGsXHzYo4+tIgQJ8Rncfd1s7HYnRoPKxGmdycq0smzBofz2iCsWHWbL+hO8+uHkCl1Ergl8+PpKDuxNyJfY2L83gZceX8jrH032urDdd1AzFs3d7/EAlRr06FvxLSJrMrrD16l1rFsZzc9fbc1XdUTg5rzPSfTO+WUXa1dG89xbE9zSBC+e3oU9O065SRObTCp9BjYrU+eioHo+JMRneGx3OjT8z7ue06nx8Vtr2LM9DiEEQoGAQAv/e2UsIfX/e9j06NuEBg39OR2Xnu/YTCaV0DBfl3pjnu0Ou8bfs3fjdGhuby1Op0Z2lo1lCw8y5fKupf5MNZVTMWkc3HfGXU1TujTrly44xPRrunuc07RFCBOmduLfP/blp81KCS3ahHLkQCI9+jZGVetGdLtufEqdC4ao3fF8++lGMjOs+X/0hS0/2m1OEhMy2bTmuNv2Fq1Duf/J4YQ3CkBRBCazyvBxbbj57rIVcU24pKPHIq7BoNCuc7hHttCSeQfYsyMOm82J1ZrXNCQxi0/fWeNx/lOvjWf8lI6ENfAnvFEAl1zZlZwch4eGvt3m9Bqists19u2KL9Nnqqmcikvz6pwddo0T0UmFnnfpld148d2JDBjmCvMJAYeizjDzg3W8+r9FXkODFyL6DF+nVvHP73s9HJ6UrgU4k8ngEQKx5jrYtTWWIaPcWwV27h7Bm59egtXqwGhQUMoxw+vRtwlTr+rGH7/sQlUVHA6NNu3DuOvhIR7HLl90yMN+TZNEH04iIz3X7Q3Dx8fI9Gt7MP3a/yR8f/9xZ4ntEoogLNy/9B+oBhMRGYTTS3GbwajQrGXhay9SSg7uTWDdimi3eL4118HJ4ymsXnqEURe1qwyTaxS6w9epVSQmZHrdblAVrytziiIIDi28YOn8Pq1l5aJLOjFyfFviYtIICvYpdC2gsK5JQohC9xWkUWQgcTGehV/n1gAKzvSNBoVxlSzKVlFoTo1d2+LYvzeB4Ho+DBrRkqBgH2w2lzjeuX6xgcEWzBaDRzzeaFQZdVHhmvSL/9nPbz/s8Lp4a7M62bDqmO7wdXRqGm3ah5GUmOURwhCKwNfPjM2W7fZHbTAojKyi5hRmi5GWbQpvS5iZbi00/71eqA/1ingwnePKm3ox4/VVnhk8QiI1V6jCaFIxmw3cfPeAYhuR1ARsNidvPLuYmOOpWHMdGI0qf/66i2YtQog+nIRE0rhpMLfcM4CvP95IdpZ7Ra5QBPc+Pox6hVQiO50af83a7dFFqyDnh+QuVPQYvk6tYsoVXTGZVQr6TZNZZepV3Xji5TGENwrEbFax+Bjx8TXyfw8MqhR9+bLwzkvLSEnK9thuMqvc/sDgEhVDde0ZyYNPj6BV2/pumT2a0/WCoxoUho9ty4ffTKdnv9qRgbJ84SFORqfkh+Psdic2q5PDBxJxOjU0p+TksRRe+d8i4mPTPEI6qiKIKqLQLSvDWuTbk9lsqDUdq8qLPsMvBdlZNjSnvODS3GoTDSMCee6tCfzx804ORp0huJ4PF0/vkt+b9PWPJxMXk4Y1106zFiHVIp3sjZjjKcSeTPW6uNqrX9NSicB17NqIh54O4f6bf/e4nsOusWNTDNeUQCPn6OGzfP7uWs6czkBVFfoObsYt9wwsUReoimT9yqNFVkafw2F3onmZpDscmodUQ0F8/c2oquJ9hi9g0IgW9B7QtDQm11p0h18CkpOymfn+Wg7tT0QADSMDue3+QTRrWfNfly9EIhoHcc9jw7zuE0JUeS/YkuASQFMAT8eWllr68n6nphWanuQogWJn7MlUXnpsQX74y+HQWL/yGCeOJvPqjMmltqc8lDQl0puzP0dI/cLDYQaDwoRLOzHvD/cFf9WgcMMd/Rg2uub2Maho9JBOMWhOjVf/t4iD+87gdGg4HBqxJ1J57enFZKR7ttzT0fFG05b1Ck39a9I8uNTXCwr2Ibyhp4iawaDQb3DxTTq++XiD1wXMuJg0Du4rnw5QaRkxrm2JFs+VIrxVWIOis5EmX96FS67slt85q34DP+56eHCdcvagO/xi2bf7NBnpuZ6vzg6NtcuOVpNVOjUBKSU5OXavYZrzqRfiS48+jb3u274xlrL0lr79wcH4+Brzi8rMFgNh4f5Mvqz4QquYE6mF7pv7295S21IeBo9oSbfekZhMKgajgsXHgKoKt9CSogiMZhWj0dNlmS0qkcW81QkhmHhpJz7+4XK++v0a3pk5ld4Danf3qrKgh3SK4eyZTO9FLTYnp71UV+rUDdatjGbWd9vJTM/FZDZw0SUduXh6lyKbqZvMBo+qYID09FyiD5+lVdvSNXMxmlT6Dm7OkQNn8A8wM2RkKwYMLZl2j8XiWbNwjsQz3lNfKwtFVbj70aGciE7mUNQZAoMtdOkRwcK/o1i55Ah2m4PuvRszaXpnXn5iEXaHLf8eKqoguJ4vnbqVTFpZCIHBULOajlclusMvhsLi9GaLgTbV0G1Jp/rZvimGbz/ZmL/QmJNtZ96cvUhNcsmV3Qo9Ly0lx8PZg2v2mpFuLZUNO7fE8vFbq3HkSSqYzCqpyTn06t+0RA5/7OQO/Pb9Dq/7GlWSamVxNGsZkv/3FnsylcBgH669tQ/d+zTOf4t5+vVxfPHhek5EJyOATt0bccs9A4t80Or8h+7wi6Flm/q0aR/Gof2J+aldBoNCYJAlPzNEp27xxy87vbY4XPBXFBdf1qXQRcjufRpzKOqMx7l2u5NWbQvP3z8fp1Pjiw/Xu13HZnWSdDaLhXOjmHpV92KvMWlqZxb8uY/MDHc5aINRMLYai7U0TfLljPWuhjaAqgpUVeGJl8bQtEUIkU2Cef6tCeTm2PNkMWqGCzsVm8aG1cew25z07t+UVu3qV1nPgdKgx/BLwINPj2TS1E6E1PclMMjCsDGtef6tCTXml02najl7JsvrdodDIyer8DZ9Q0e1IjTMD2MBITez2cDk6V1KJdp2KibNaxMUh11jy/rC+wCcz4vvTqJR40CMRgWzRcVoUpl+TY8Sh0cqg41rjrF1/UlXQxubk9wcB1mZNt5/ZYXbOofFx1hj/v6Wzj/Isw/9y7w5e1nwVxRvPLeEbz/dVKZ1mcqmZtyxGo7RqHLJld2KfF3XqTtENgnmyMFEj+0WHyO+eVkg3jBbjDz39gSWLzzE1g0n8fc3MXpie7r1iizV+BYfI85CFoozM6xomixRiCM0zI/XZkwm5ngKGelWWrQOxdevcPtLSmpKDnNn72bXtjj8/EyMm9yRgcNblGjGu3LxYaxWz7WFzEwbJ4+l1LhU6LTUHH79Zqtbjv85qYZBw1vStmODarTOE93h6+iUksuu78E7LyxzC6mYzCrTr+1erKP18TEy8dJOTLy0U5nHDwv3J6JxECeOJXusCWRlWln4dxQTSnh9IUSZ5BeklNjtGkaje7vEzHQrzz44j8wMK06n5CxZfPvZJmJOpHDljb2Kva7D4T3ZXgi8iqZVN7u2xaEoCuBum9XmYNPa4zXO4ZcrpCOECBFCLBFCHM7737PTg+s4pxBiZ96/ueUZU0enumnfKZyHnx1Fy7b1MZsNNIwI5NZ7B1Zpef69jw31ugDsdEgW/bO/0saVUjL/r33cfd1sbrviFx64ZQ7rV0Xn71+24CDZWfbzun85WPrvAdLTiq9bGTishVddG9Wg1LjZPeQVjXl5xgvwmkJa3ZR3hv8EsExK+boQ4om87x/3clyOlLJ7OcfS0akxtO8cznNvXlRt4wfV80EI7637sjOL78tbVv79cx9/z9qdX7GampzD5++tY9vGk9z50BD27Y73WmBmMKqciE6mS4+IIq8/bEwbNq09wYnoZKy5DgxGBUUR3PXwkBrZpKR778Z8q2302G40qgwY1rIaLCqa8jr8KcDwvK+/A1bi3eHr6NRp4mJSWTR3P6dPpdOuUzhjJrQjsBz9Zk1mAw0jA4mPTffY16ZD5aQLa5pknpd+BABbN8Qw441VherwOJ1aidRAjUaVJ18aw+7tp9i78xRB9XwYPLJVoUqY1Y2fv4k7Hx7Mp++sRSjCVbMjYcqVXWvkG4koz0qyECJVShmc97UAUs59f95xDmAn4ABel1L+Vcj1bgNuA2jatGmvEydOlNk2HZ2awt6dp/jgtZU47K6ceYNRwWIx8uK7E0vdQ7cg+/ec5t2Xl2O3a8i8hVqjSeWZ18fTpLnX6Gq5yMm2cfd1s7327wVXnN1g8BQpU1VBs5YhPPfWhAq3qaaQmWFl++YYHHaNbr0iy/VzLS9CiG1SSq/qecU6fCHEUqChl11PAd8VdPBCiBQppcdvmhAiUkoZJ4RoCSwHRkkpi9Ql6N27t9y6dWuRtuno1HSklDx8258kJbqncgoBA4e35Lb7B5Xr+jHHU/j3j33ExaTSsk0oEy7tTHgjT42dikDTJPfe8BuZGaUrEmvfuQH3PDasTP2CdUpPUQ6/2JCOlHJ0ERdOEEI0klLGCyEaAWcKuUZc3v/RQoiVQA9AF6LRueBJS8kh3YsappSwYfUxrrmlN37+ZZfbbtK8Hnc8NLjIYzLTrSScziCsgV+5wkiKIph+bXe+/3xTkcqVBbFYDIyZ2EF39jWE8sbw5wI3AK/n/f/3+QfkZe5kSymtQoj6wCDgzXKOq6NTKzD7GL0urAJoTsmXMzZw/5PDK2Vszanxw5dbWL30CEajit3upN+g5tx8z4Aya96PGNcWh8PJT19udftchS0gIwSGGpitUlcp70/idWCMEOIwMDrve4QQvYUQX+Yd0wHYKoTYBazAFcOPKue4Ojq1Ah8fI117Fl5YtXtbnNdCo4rg3z/3sXb5URx2jZxsOw67xub1J/j9R+8aOiVlzMQOvPDORFq0Ds0TI1Po3K1Rvt5NQYRwNWzRqRmUa9G2MtFj+HUbzamxae0J1q2MxmBUGDa6Nd37NK6R+iTFkZVp457rZ3tVXVUNCh9+Mx3/gIrvonbvDb95zX03Wwx8/suVFXIv7XYnqiJQVIU/ftnF/D/2IRSBktdT/qGnR9K+c3i5x9EpOeWK4evoVDVSSt5/dSUH9ibkz36jdp1m0IiW3HBHv2q2rvT4+ZvoP6Q5G1Yf8wh7NAj3rxRnD66WnN6wWh1omkRVy+/wjQWUOade1Y1ho1uzZ+cpLBYD3Xs3xuJjLPcYOhWHHlzTqXHs2xXPgX0JbqEOq9XBmuVHi+xdWpO57Loe+Aea84XTVIOC2WLglnsHVNqYLQtR4GzcNLjSiphCw/wYPqYN/Ye00J19DUSf4evUOHZvP+W9OYeEfbvjiWgSVPVGlZOQ+n68/tEUVi4+zOH9Z2gUGcioCe0JCy+6NV95uPrm3rz21GLsdieaJhGKwGhUuP62vpU2ZnWQlWlj1ZLD7N+bQMNGAYye2I7wRtWj6V/T0R2+To3DP8CEwajg8FLA41eEGmVNxz/AzKRpnatsvBatQ3nh3QnMm7OX40eTadw0mEnTOldIUdap2DTOnsmkSfN61VoFm5qSw3MP/UtWlg27zck+VbByyWEeenokHbp4Kx+q2+gOX6fGMWh4K/7x1ldVQM++TareoFpMo8gg/u++8hV3FSQ7y8b7r67g2OEkVIOCw+5k0IhW3HBHv2rpOvXnL7vISM/Nr/51OiVOp5MvZ6zn7c8vrZWL/JWJHsPXqXGEhvlx5yNDsPgY8PExYvEx4B9g5pHnRulx4Wrmq483cPTQWWw2JznZdux2jfWroln674FqsWfn1livUg9pqbmkJHsWvNV19Bm+To2kZ98mzPjucg7vP4NqUGjTPqxGqiXWJay5dnZujvXQrLdZnSz+90C1tEa0WLy7MKlJzDWkI1ZNQv8L0qmxmEwqnbo1on2n8AvC2SclZrF/z2nSvEgt1AasXlQyz1FUa8fKZPTE9l718wF+/2lHiTT46xL6I1BHp4KRUpKTbcdoUjEaVWxWB5+8s4a9O+IxGBXsdidDRrTi+tv7olTyg8xmc1bYW1JAoJl6ob4kJmS6bRcCOveonmraURe140R0MhtWReN0yvw6B4dDY9XiI+zcEsurMybjo4cCAd3h6+hUKAf2JvD1Jxs4m5CJUAR9BzZDUQR7d7oag5xrDrJuVTRhjQLK1eqwOLZviuHz99ciEEgkBoPKA08Np037srXdE0Jw8939ee+VlTjyUj1dUs8GLru2RwVbX1Kb/vvifNUAp1MjM8PK2uVHGTOxfdUbVwPRpRV0dCqIU7FpPP/wfLeCMYNRwenQvAqL1Qv15f2vplWKLUmJWTx+99/Ybe5hGIuPkQ+/mYbZUvYZ76nYNFczl7h02nZqUO5mLuVhy/oTfPHB+iL1iHoPaMq9jw+rQquqF11aQUenClj4d5RHe7/zawkKUpj0QUWwbuVRpBftHikl2zfFMmBYizJfO6JxEDfd1b885lUYq5YeKdLZGwwKDSMqpz9AbaT2r4Tp6NQQTsWmeRVI85oKLqBdp7KFVkpCZobNI5sGXJLMWZX4oKlqnF4+Y0FUVanS5vI1Hd3h6+hUEG3aN/CqM6+oCkaTkl+YpBoUfCxGrrrR61t3hdC1ZwRmbymLAjp1u3AqUAePaFVo+mVYA38eeW4U9RtUnnxFbUMP6ejoVBBjL27PysWHcDr/i9mbzCr9h7Rg/JQOLPgziriYVFq1C2P85A6V6og6dnWlsxZUHDWbDQwa0ZJGkbVPi6gw+g9tzqa1x11ie7kODEYFIeCmuwYwcFgLvdL2PPRFWx2dCiQhPp1Z3+0ganc8vr5GxlzcgXGT2ld6+qU3LqSeAkUhpSRq92n27jxFQKCFAcNaVKu+T3VTribm1YXu8HV0dHRKT1EOX4/h6+jUAaSUnIpJI+Z4iteFZZ26gR7D19G5wDl5PIUPX1tJWmoOQgh8fIzc/ehQ2nasvCwhnZqJPsPX0bmAsVodvP70YhITMrFZnVhzHaSm5PD2i8t0nZk6iO7wdXQuYLZvivGaq65pkg2rjlWDRTrVie7wdXQuYNJSc7wWYNltTlJTsqvBIp3qRHf4OjoXMO06hqOonmmYZouB9p0unAIsnZKhO3wdnQuYFq1D6dIjAnMBzXiTWaVpi3p0qSZJY53qQ8/S0dG5wLnn0aGsXnaElUuOoDk1Bo1oxcjxbaulGEynetEdvo7OBY6iKgwf25bhY3URsbqO/ojX0dHRqSPoDl9HR0enjqCHdHR0dKqMpMQs1iw/SmpyNp26NaJnvyYXRIP62oLu8HV0dKqEvTtP8cFrK9E0icOusX7VMSKaBPG/l8diKkTTXqdi0R+tOjo6lY7m1Pj03bXYrM78to/WXAdxJ1JZvvBQNVtXd9Advo6OTqUTcyIVx3kN1QFsNifrdYmHKkN3+Do6OpWOwahQWO8Nk0n1ul2n4tEdvo6OTqUT0TiIoHq+cJ7Kg9ls0JuMVyG6w9fR0al0hBA88NRwAgLMWHwMmMwqJpNK74FNGTCsRXWbV2co19K4EOIy4HmgA9BXSum1J6EQYjzwAaACX0opXy/PuDo6OrWPyCbBvP/VNHZvP0Vaag7tOoYT0eTCaaheGyhvLtReYCrweWEHCCFU4GNgDBALbBFCzJVSRpVzbB0dnVqGwajSs1+T6jajzlIuhy+l3A+u17Ui6AsckVJG5x37KzAF0B2+jo6OThVSFTH8SCCmwPexeds8EELcJoTYKoTYmpiYWAWm6ejo6NQdip3hCyGWAt46JTwlpfy7Io2RUs4EZgL07t3bew6Xjo6Ojk6ZKNbhSylHl3OMOKBg0K5x3jYdHR0dnSqkKkI6W4A2QogWQggTcCUwtwrG1dHR0dEpgCis+q1EJwtxKTADCANSgZ1SynFCiAhc6ZcT8o6bALyPKy3zaynlKyW4diJwIu/b+sDZMhtatdQWW3U7KxbdzoqlttgJNc/WZlLKMG87yuXwqwohxFYpZe/qtqMk1BZbdTsrFt3OiqW22Am1y1a90lZHR0enjqA7fB0dHZ06Qm1x+DOr24BSUFts1e2sWHQ7K5baYifUIltrRQxfR0dHR6f81JYZvo6Ojo5OOdEdvo6Ojk4doUY6fCHEZUKIfUIITQhRaLqTEOK4EGKPEGKnEMKrNHNlUwpbxwshDgohjgghnqhKG/PGDxFCLBFCHM77v14hxznz7udOIUSVFcgVd3+EEGYhxKy8/ZuEEM2ryrbz7CjOzhuFEIkF7uGt1WDj10KIM0KIvYXsF0KID/M+w24hRM+qtjHPjuLsHC6ESCtwL5+tahvz7GgihFghhIjK+1u/38sxNeKeFouUssb9w6Wv3w5YCfQu4rjjQP2abiuugrOjQEvABOwCOlaxnW8CT+R9/QTwRiHHZVbDPSz2/gB3AZ/lfX0lMKuG2nkj8FFV23aeDUOBnsDeQvZPABbg6j/VH9hUQ+0cDsyrznuZZ0cjoGfe1wHAIS8/9xpxT4v7VyNn+FLK/VLKg9VtR0kooa35EtFSShtwTiK6KpkCfJf39XfAJVU8flGU5P4UtP93YJQoRpe7EqgJP8dikVKuBpKLOGQK8L10sREIFkI0qhrr/qMEdtYIpJTxUsrteV9nAPvxVPytEfe0OGqkwy8FElgshNgmhLituo0pghJLRFci4VLK+LyvTwPhhRxnyZOo3iiEuKRqTCvR/ck/RkrpANKA0CqxzosNeRT2c5yW91r/uxCiJnb7qAm/jyVlgBBilxBigRCiU3UbkxdK7AFsOm9Xrbin5e14VWYqSHZ5sJQyTgjRAFgihDiQN2uoUKpSIro8FGVnwW+klFIIUVg+brO8e9oSWC6E2COlPFrRtl7A/AP8IqW0CiFux/VWMrKabaqtbMf1+5iZp8f1F9CmuowRQvgDc4AHpJTp1WVHeag2hy/LL7uMlDIu7/8zQog/cb1yV7jDrwBbq0Qiuig7hRAJQohGUsr4vFfNM4Vc49w9jRZCrMQ1m6lsh1+S+3PumFghhAEIApIq2a7zKdZOKWVBm77EtXZS06gVkuUFnaqUcr4Q4hMhRH0pZZULlQkhjLic/U9Syj+8HFIr7mmtDekIIfyEEAHnvgbG4uqxWxOpCRLRc4Eb8r6+AfB4MxFC1BNCmPO+rg8MompaUZbk/hS0fzqwXOatllUhxdp5Xtx2Mq54b01jLnB9XmZJfyCtQLivxiCEaHhunUYI0ReXv6rqhzx5NnwF7JdSvlvIYbXinlb7qrG3f8CluGJgViABWJS3PQKYn/d1S1xZEruAfbjCKzXSVvnfKv4hXLPlKrcVV7x7GXAYWAqE5G3vjUvKGmAgsCfvnu4BbqlC+zzuD/AiMDnvawvwG3AE2Ay0rKafd3F2vpb3+7gLWAG0rwYbfwHiAXve7+YtwB3AHXn7BfBx3mfYQxGZcNVs5z0F7uVGYGA12TkY13rhbmBn3r8JNfGeFvdPl1bQ0dHRqSPU2pCOjo6Ojk7p0B2+jo6OTh1Bd/g6Ojo6dQTd4evo6OjUEXSHr6Ojo1NH0B2+jo6OTh1Bd/g6Ojo6dYT/ByliQP+uQ4LpAAAAAElFTkSuQmCC\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "y_res = torch.sigmoid(SimpNetwork(x))\n",
- "#y_pred = np.argmax(y_res, axis=1)\n",
- "y_pred = (y_res > 0.5)*1\n",
- "\n",
- "# plot data\n",
- "plt.scatter(x[:, 0], x[:, 1], c=y, cmap=plt.cm.Spectral)\n",
- "plt.title(\"ground truth\")\n",
- "plt.show()\n",
- "\n",
- "plt.scatter(x[:, 0], x[:, 1], c=y_pred, cmap=plt.cm.Spectral)\n",
- "plt.title(\"predicted\")\n",
- "plt.show()"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 2. Sequential 和 Module"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "\n",
- "对于前面的线性回归模型、 Logistic回归模型和神经网络,在构建的时候定义了需要的参数。这对于比较小的模型是可行的,但是对于大的模型,比如100 层的神经网络,这个时候再去手动定义参数就显得非常麻烦,所以 PyTorch 提供了两个模块来帮助我们构建模型,一个是Sequential,一个是 Module。\n",
- "\n",
- "Sequential 允许我们构建序列化的模块,而 Module 是一种更加灵活的模型定义方式,下面分别用 `Sequential` 和 `Module` 来定义上面的神经网络。"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 2.1 Sequential"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 7,
- "metadata": {},
- "outputs": [],
- "source": [
- "# Sequential\n",
- "seq_net = nn.Sequential(\n",
- " nn.Linear(2, 4), # PyTorch 中的线性层,wx + b\n",
- " nn.Tanh(),\n",
- " nn.Linear(4, 1)\n",
- ")"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 8,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Linear(in_features=2, out_features=4, bias=True)"
- ]
- },
- "execution_count": 8,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "# 序列模块可以通过索引访问每一层\n",
- "seq_net[0] # 第一层"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 9,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Parameter containing:\n",
- "tensor([[-0.6814, -0.4472],\n",
- " [ 0.5195, -0.1132],\n",
- " [-0.6897, -0.1030],\n",
- " [ 0.6170, -0.4806]], requires_grad=True)\n"
- ]
- }
- ],
- "source": [
- "# 打印出第一层的权重\n",
- "\n",
- "w0 = seq_net[0].weight\n",
- "print(w0)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 10,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "epoch: 1000, loss: 0.2772306501865387\n",
- "epoch: 2000, loss: 0.16978605091571808\n",
- "epoch: 3000, loss: 0.11684117466211319\n",
- "epoch: 4000, loss: 0.09669271111488342\n",
- "epoch: 5000, loss: 0.08626393228769302\n",
- "epoch: 6000, loss: 0.08026610314846039\n",
- "epoch: 7000, loss: 0.07644043117761612\n",
- "epoch: 8000, loss: 0.07377094030380249\n",
- "epoch: 9000, loss: 0.07179124653339386\n",
- "epoch: 10000, loss: 0.07025747001171112\n"
- ]
- }
- ],
- "source": [
- "# generate sample data\n",
- "\n",
- "# np.random.seed(0)\n",
- "# data_x, data_y = datasets.make_moons(200, noise=0.20)\n",
- "\n",
- "# 变量\n",
- "\n",
- "# x = torch.from_numpy(data_x).float()\n",
- "# y = torch.from_numpy(data_y).float().unsqueeze(1)\n",
- "\n",
- "# 通过 parameters 可以取得模型的参数\n",
- "param = seq_net.parameters()\n",
- "\n",
- "# 定义优化器\n",
- "optim = torch.optim.SGD(param, 0.1)\n",
- "\n",
- "# 我们训练 10000 次\n",
- "for e in range(10000):\n",
- " out = seq_net(x)\n",
- " loss = criterion(out, y)\n",
- " optim.zero_grad()\n",
- " loss.backward()\n",
- " optim.step()\n",
- " if (e + 1) % 1000 == 0:\n",
- " print('epoch: {}, loss: {}'.format(e+1, loss.item()))"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "可以看到,训练 10000 次 loss 比之前的更低,这是因为 PyTorch 自带的模块比我们写的更加稳定,同时也有一些初始化的问题在里面,关于参数初始化,我们会在后面的课程中讲到"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 11,
- "metadata": {},
- "outputs": [],
- "source": [
- "def plot_seq(x):\n",
- " out = torch.sigmoid(seq_net(torch.from_numpy(x).float())).data.numpy()\n",
- " out = (out > 0.5) * 1\n",
- " return out"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 12,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Text(0.5, 1.0, 'sequential')"
- ]
- },
- "execution_count": 12,
- "metadata": {},
- "output_type": "execute_result"
- },
- {
- "data": {
- "image/png": "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\n",
- "text/plain": [
- "<Figure size 432x288 with 1 Axes>"
- ]
- },
- "metadata": {
- "needs_background": "light"
- },
- "output_type": "display_data"
- }
- ],
- "source": [
- "plot_decision_boundary(lambda x: plot_seq(x), x.numpy(), y.numpy())\n",
- "plt.title('sequential')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 2.2 保存模型参数\n",
- "\n",
- "保存模型在 PyTorch 中有两种方式,一种是将模型结构和参数都保存在一起,一种是只将参数保存下来。"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 13,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 将参数和模型保存在一起\n",
- "torch.save(seq_net, 'save_seq_net.pth')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "上面就是保存模型的方式,`torch.save`里面有两个参数,第一个是要保存的模型,第二个参数是保存的路径,读取模型的方式也非常简单"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 14,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 读取保存的模型\n",
- "seq_net1 = torch.load('save_seq_net.pth')"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 15,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Sequential(\n",
- " (0): Linear(in_features=2, out_features=4, bias=True)\n",
- " (1): Tanh()\n",
- " (2): Linear(in_features=4, out_features=1, bias=True)\n",
- ")"
- ]
- },
- "execution_count": 15,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "seq_net1"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 16,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Parameter containing:\n",
- "tensor([[-3.5468, -3.0485],\n",
- " [ 3.5039, -1.2536],\n",
- " [-3.3143, 0.9123],\n",
- " [ 0.4555, 0.3162]], requires_grad=True)\n"
- ]
- }
- ],
- "source": [
- "print(seq_net1[0].weight)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "我们可以看到我们重新读入了模型,并且将其命名为 seq_net1,并且打印了第一层的参数\n",
- "\n",
- "下面我们看看第二种保存模型的方式,只保存参数而不保存模型结构"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 17,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 保存模型参数\n",
- "torch.save(seq_net.state_dict(), 'save_seq_net_params.pth')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "通过上面的方式,我们保存了模型的参数,如果要重新读入模型的参数,首先我们需要重新定义一次模型,接着重新读入参数"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 18,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "<All keys matched successfully>"
- ]
- },
- "execution_count": 18,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "seq_net2 = nn.Sequential(\n",
- " nn.Linear(2, 4),\n",
- " nn.Tanh(),\n",
- " nn.Linear(4, 1)\n",
- ")\n",
- "\n",
- "seq_net2.load_state_dict(torch.load('save_seq_net_params.pth'))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 19,
- "metadata": {},
- "outputs": [
- {
- "data": {
- "text/plain": [
- "Sequential(\n",
- " (0): Linear(in_features=2, out_features=4, bias=True)\n",
- " (1): Tanh()\n",
- " (2): Linear(in_features=4, out_features=1, bias=True)\n",
- ")"
- ]
- },
- "execution_count": 19,
- "metadata": {},
- "output_type": "execute_result"
- }
- ],
- "source": [
- "seq_net2"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 20,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Parameter containing:\n",
- "tensor([[-3.5468, -3.0485],\n",
- " [ 3.5039, -1.2536],\n",
- " [-3.3143, 0.9123],\n",
- " [ 0.4555, 0.3162]], requires_grad=True)\n"
- ]
- }
- ],
- "source": [
- "print(seq_net2[0].weight)"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "通过这种方式我们也重新读入了相同的模型,打印第一层的参数对比,发现和前面的办法是一样"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "有这两种保存和读取模型的方法,我们推荐使用**第二种**,因为第二种可移植性更强"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "### 2.3 Module\n",
- "\n",
- "下面再用 Module 定义这个模型,下面是使用 Module 的模板\n",
- "\n",
- "```\n",
- "class 网络名字(nn.Module):\n",
- " def __init__(self, 一些定义的参数):\n",
- " super(网络名字, self).__init__()\n",
- " self.layer1 = nn.Linear(num_input, num_hidden)\n",
- " self.layer2 = nn.Sequential(...)\n",
- " ...\n",
- " \n",
- " 定义需要用的网络层\n",
- " \n",
- " def forward(self, x): # 定义前向传播\n",
- " x1 = self.layer1(x)\n",
- " x2 = self.layer2(x)\n",
- " x = x1 + x2\n",
- " ...\n",
- " return x\n",
- "```\n",
- "\n",
- "注意的是,Module 里面也可以使用 Sequential,同时 Module 非常灵活,具体体现在 forward 中,如何复杂的操作都能直观的在 forward 里面执行\n",
- "\n",
- "下面我们照着模板实现一下上面的神经网络"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 21,
- "metadata": {},
- "outputs": [],
- "source": [
- "class SimpNet(nn.Module):\n",
- " def __init__(self, num_input, num_hidden, num_output):\n",
- " super(SimpNet, self).__init__()\n",
- " self.layer1 = nn.Linear(num_input, num_hidden)\n",
- " \n",
- " self.layer2 = nn.Tanh()\n",
- " \n",
- " self.layer3 = nn.Linear(num_hidden, num_output)\n",
- " \n",
- " def forward(self, x):\n",
- " x = self.layer1(x)\n",
- " x = self.layer2(x)\n",
- " x = self.layer3(x)\n",
- " return x"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 22,
- "metadata": {},
- "outputs": [],
- "source": [
- "mo_net = SimpNet(2, 4, 1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 23,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Linear(in_features=2, out_features=4, bias=True)\n"
- ]
- }
- ],
- "source": [
- "# 访问模型中的某层可以直接通过名字\n",
- "\n",
- "# 第一层\n",
- "l1 = mo_net.layer1\n",
- "print(l1)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 24,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "Parameter containing:\n",
- "tensor([[ 0.6708, -0.0416],\n",
- " [-0.4098, -0.1417],\n",
- " [-0.2024, -0.7049],\n",
- " [-0.0413, -0.0382]], requires_grad=True)\n"
- ]
- }
- ],
- "source": [
- "# 打印出第一层的权重\n",
- "print(l1.weight)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 25,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 定义优化器\n",
- "optim = torch.optim.SGD(mo_net.parameters(), 1.)"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 26,
- "metadata": {},
- "outputs": [
- {
- "name": "stdout",
- "output_type": "stream",
- "text": [
- "epoch: 1000, loss: 0.07538169622421265\n",
- "epoch: 2000, loss: 0.06741848587989807\n",
- "epoch: 3000, loss: 0.06558582931756973\n",
- "epoch: 4000, loss: 0.0639200359582901\n",
- "epoch: 5000, loss: 0.0623852014541626\n",
- "epoch: 6000, loss: 0.061241135001182556\n",
- "epoch: 7000, loss: 0.06033353880047798\n",
- "epoch: 8000, loss: 0.05957018956542015\n",
- "epoch: 9000, loss: 0.05890002101659775\n",
- "epoch: 10000, loss: 0.05829467251896858\n"
- ]
- }
- ],
- "source": [
- "# 我们训练 10000 次\n",
- "for e in range(10000):\n",
- " out = mo_net(x)\n",
- " loss = criterion(out, y)\n",
- " optim.zero_grad()\n",
- " loss.backward()\n",
- " optim.step()\n",
- " if (e + 1) % 1000 == 0:\n",
- " print('epoch: {}, loss: {}'.format(e+1, loss.item()))"
- ]
- },
- {
- "cell_type": "code",
- "execution_count": 27,
- "metadata": {},
- "outputs": [],
- "source": [
- "# 保存模型\n",
- "torch.save(mo_net.state_dict(), 'module_net.pth')"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "可以看到我们得到了相同的结果,而且使用 Sequential 和 Module 来定义模型更加方便\n",
- "\n",
- "在这一节中我们还是使用梯度下降法来优化参数,在神经网络中,这种优化方法有一个特别的名字,反向传播算法,下一次课我们会讲一讲什么是反向传播算法"
- ]
- },
- {
- "cell_type": "markdown",
- "metadata": {},
- "source": [
- "## 练习题\n",
- "\n",
- "* 改变网络的隐藏层神经元数目,或者试试定义一个 5 层甚至更深的模型,增加训练次数,改变学习率,看看结果会怎么样"
- ]
- }
- ],
- "metadata": {
- "kernelspec": {
- "display_name": "Python 3 (ipykernel)",
- "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": "3.8.12"
- }
- },
- "nbformat": 4,
- "nbformat_minor": 2
- }
|