{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# 多层神经网络,Sequential 和 Module\n", "通过前面的章节,我们了解到了机器学习领域中最常见的两个模型,线性回归模型和 Logistic 回归模型,他们分别是处理机器学习中最常见的两类问题-回归问题和分类问题。\n", "\n", "下面我们会讲第一个深度学习的模型,多层神经网络。" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 多层神经网络\n", "在前面的线性回归中,我们的公式是 $y = w x + b$,而在 Logistic 回归中,我们的公式是 $y = Sigmoid(w x + b)$,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,之后我们会详细介绍激活函数以及为什么必须使用激活函数,下面我们从理解神经网络入手。" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "### 理解神经网络\n", "神经网络的灵感来自于人脑的神经元系统,下面我们放一张人脑的神经元和神经网络的对比图(来自 cs231n)\n", "\n", "![](https://ws4.sinaimg.cn/large/006tNc79ly1fmgiz5mqs3j30or0773zg.jpg)\n", "\n", "左边是一张神经元的图片,神经元通过突触接受输入,然后通过**神经激活**的方式传输给后面的神经元。这对比于右边的神经网络,首先接受数据输入,然后通过计算得到结果,接着经过**激活函数**,再传给第二层的神经元。\n", "\n", "所以前面讲的 logistic 回归模型和线性回归模型都可以看做是一个单层神经网络,而 logistic 回归中使用了激活函数 sigmoid。\n", "\n", "神经网络使用的激活函数都是非线性的,每个激活函数都输入一个值,然后做一种特定的数学运算得到一个结果,下面举几个例子\n", "\n", "sigmoid 激活函数\n", "\n", "$$\\sigma(x) = \\frac{1}{1 + e^{-x}}$$\n", "\n", "![](https://ws1.sinaimg.cn/large/006tNc79ly1fmgj7yto7gj308w05oa9w.jpg)\n", "\n", "tanh 激活函数\n", "\n", "$$tanh(x) = 2 \\sigma(2x) - 1$$\n", "\n", "![](https://ws3.sinaimg.cn/large/006tNc79ly1fmgj8yjdnlj308w05mt8j.jpg)\n", "\n", "ReLU 激活函数\n", "\n", "$$ReLU(x) = max(0, x)$$\n", "\n", "![](https://ws1.sinaimg.cn/large/006tNc79ly1fmgj94ky2oj308n05uq2r.jpg)\n", "\n", "我们下面重点讲一讲 ReLU 激活函数,因为现在神经网络中 90% 的情况都是使用这个激活函数。一般一个一层的神经网络的公式就是 $y = max(0, w x + b)$,一个两层的神经网络就是 $y = w_2\\ max(0, w_1 x + b_1) + b_2$,非常简单,但是却很有效,使用这个激活函数能够加快梯度下降法的收敛速度,同时对比与其他的激活函数,这个激活函数计算更加简单,所以现在变得非常流行,之后你会发现我们激活在所有的神经网络中都会使用它。" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 神经网络的结构\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,我们可以通过下面的图展示一个两层的神经网络和三层的神经网络\n", "\n", "![](https://ws2.sinaimg.cn/large/006tNc79ly1fmgjiafmmjj30nu07075w.jpg)\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,我们看看这个网站的 [demo](http://cs.stanford.edu/people/karpathy/convnetjs/demo/classify2d.html)\n", "\n", "神经网络向前传播也非常简单,就是一层一层不断做运算就可以了,可以看看下面这个例子\n", "\n", "![](https://ws2.sinaimg.cn/large/006tNc79ly1fmgj4q1j78g309u0cc4qq.gif)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## 为什么要使用激活函数\n", "激活函数在神经网络中非常重要,使用激活函数也是非常必要的,前面我们从人脑神经元的角度理解了激活函数,因为神经元需要通过激活才能往后传播,所以神经网络中需要激活函数,下面我们从数学的角度理解一下激活函数的必要性。\n", "\n", "比如一个两层的神经网络,使用 A 表示激活函数,那么\n", "\n", "$$\n", "y = w_2 A(w_1 x)\n", "$$\n", "\n", "如果我们不使用激活函数,那么神经网络的结果就是\n", "\n", "$$\n", "y = w_2 (w_1 x) = (w_2 w_1) x = \\bar{w} x\n", "$$\n", "\n", "可以看到,我们将两层神经网络的参数合在一起,用 $\\bar{w}$ 来表示,两层的神经网络其实就变成了一层神经网络,只不过参数变成了新的 $\\bar{w}$,所以如果不使用激活函数,那么不管多少层的神经网络,$y = w_n \\cdots w_2 w_1 x = \\bar{w} x$,就都变成了单层神经网络,所以在每一层我们都必须使用激活函数。\n", "\n", "最后我们看看激活函数对神经网络的影响\n", "\n", "![](https://ws1.sinaimg.cn/large/006tNc79ly1fmgkeqjr34g306r065diu.gif)\n", "\n", "可以看到使用了激活函数之后,神经网络可以通过改变权重实现任意形状,越是复杂的神经网络能拟合的形状越复杂,这就是著名的神经网络万有逼近定理。\n", "\n", "下面我们通过例子来感受一下神经网络的强大之处" ] }, { "cell_type": "code", "execution_count": 1, "metadata": { "collapsed": true }, "outputs": [], "source": [ "import torch\n", "import numpy as np\n", "from torch import nn\n", "from torch.autograd import Variable\n", "import torch.nn.functional as F\n", "\n", "import matplotlib.pyplot as plt\n", "%matplotlib inline" ] }, { "cell_type": "code", "execution_count": 2, "metadata": { "collapsed": true }, "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\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": "markdown", "metadata": {}, "source": [ "这次我们仍然处理一个二分类问题,但是比前面的 logistic 回归更加复杂" ] }, { "cell_type": "code", "execution_count": 3, "metadata": {}, "outputs": [], "source": [ "np.random.seed(1)\n", "m = 400 # 样本数量\n", "N = int(m/2) # 每一类的点的个数\n", "D = 2 # 维度\n", "x = np.zeros((m, D))\n", "y = np.zeros((m, 1), dtype='uint8') # label 向量,0 表示红色,1 表示蓝色\n", "a = 4\n", "\n", "for j in range(2):\n", " ix = range(N*j,N*(j+1))\n", " t = np.linspace(j*3.12,(j+1)*3.12,N) + np.random.randn(N)*0.2 # theta\n", " r = a*np.sin(4*t) + np.random.randn(N)*0.2 # radius\n", " x[ix] = np.c_[r*np.sin(t), r*np.cos(t)]\n", " y[ix] = j" ] }, { "cell_type": "code", "execution_count": 4, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 4, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXYAAAD8CAYAAABjAo9vAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nfopUyhxCuwAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plt.scatter(x[:, 0], x[:, 1], c=y.reshape(-1), s=40, cmap=plt.cm.Spectral)" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "我们可以先尝试用 logistic 回归来解决这个问题" ] }, { "cell_type": "code", "execution_count": 5, "metadata": {}, "outputs": [], "source": [ "x = torch.from_numpy(x).float()\n", "y = torch.from_numpy(y).float()" ] }, { "cell_type": "code", "execution_count": 6, "metadata": {}, "outputs": [], "source": [ "w = nn.Parameter(torch.randn(2, 1))\n", "b = nn.Parameter(torch.zeros(1))\n", "\n", "optimizer = torch.optim.SGD([w, b], 1e-1)\n", "\n", "def logistic_regression(x):\n", " return torch.mm(x, w) + b\n", "\n", "criterion = nn.BCEWithLogitsLoss()" ] }, { "cell_type": "code", "execution_count": 7, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "epoch: 20, loss: 0.7033562064170837\n", "epoch: 40, loss: 0.6739853024482727\n", "epoch: 60, loss: 0.6731640696525574\n", "epoch: 80, loss: 0.6731465458869934\n", "epoch: 100, loss: 0.6731461882591248\n" ] } ], "source": [ "for e in range(100):\n", " out = logistic_regression(Variable(x))\n", " loss = criterion(out, Variable(y))\n", " optimizer.zero_grad()\n", " loss.backward()\n", " optimizer.step()\n", " if (e + 1) % 20 == 0:\n", " print('epoch: {}, loss: {}'.format(e+1, loss.data[0]))" ] }, { "cell_type": "code", "execution_count": 8, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def plot_logistic(x):\n", " x = Variable(torch.from_numpy(x).float())\n", " out = F.sigmoid(logistic_regression(x))\n", " out = (out > 0.5) * 1\n", " return out.data.numpy()" ] }, { "cell_type": "code", "execution_count": 9, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5,1,'logistic regression')" ] }, "execution_count": 9, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEWCAYAAABmE+CbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDIuMS4wLCBo\ndHRwOi8vbWF0cGxvdGxpYi5vcmcvpW3flQAAIABJREFUeJzsvXdwJNl54Pn70pRDOXjb3k/b8Y4c\nxxHJoZMorUSt3O5eKKjVXWzshnSnW/H2Nu4udk97OsVJ2jsp9ni3Wl1otZQjKXpyOOTMkBzb43q6\np70B0PCmUIXyVZn57o8soAFUFRroBlBAd/4iOhpI8/JlIvN9731WlFJ4eHh4eHhoje6Ah4eHh8fm\nwBMIHh4eHh6AJxA8PDw8PCp4AsHDw8PDA/AEgoeHh4dHBU8geHh4eHgAnkDw2GBEpF9Enl2Ddv6D\niPyPt3DedhHJiIh+u33Y7IjIh0XkQqP74bF1EC8OwWMjEZF+4NeVUi/cidfz8NjKeCsED49bQESM\nzdyeh8et4AkEj4YhIn4R+SMRGan8+yMR8S/Y/zsiMlrZ9+siokRkb2Xfn4vIv6n83CYi3xSRpIgk\nROTHIqKJyF8A24FvVNREvyMiOyvtGJVzW0TkP1WuMSMif1+nr/9YRF4RkT8UkQTwP1W2/1cicq5y\n7vdEZMeCcz4qIhdEJCUifyoiL4vIr99Ke+LyhyIyUWnvfRE5Utn3CRE5KyJpERkWkf+2sv0pERla\n0J9DIvJS5Tl9ICKfWbDvz0XkT0TkW5V23hCRPbf7N/bYWngCwaOR/A/AI8AJ4DjwEPCvAETk48Bv\nAc8Ce4Enl2nnt4EhoB3oBL4AKKXUrwKDwKeVUmGl1O/XOPcvgBBwGOgA/nCZ6zwMXK0c929F5Gcq\n1/rZyrV/DHyp0v824O+A3wVagQvAY7faHvBR4AlgPxAHPgdMV/b9R+A3lFIR4Ajww6UdFxET+Abw\nfOV6/wz4SxE5sOCwfwj8z0AzcBn4t8s8C487EE8geDSSXwb+F6XUhFJqEncw+tXKvl8A/pNS6gOl\nVK6yrx5loBvYoZQqK6V+rFZgHBORbuA54J8qpWYq5768zCkjSqn/UyllKaXywG8Av6eUOqeUsoD/\nFThRmdV/AvhAKfWVyr5/D4zdRntlIAIcxLX9nVNKjS64/3tEJFq5j3dq9P0RIAz8O6VUSSn1Q+Cb\nuEJgjq8opd6sXPsvcQW1x12EJxA8GkkPMLDg94HKtrl91xfsW/jzUv533Bnt8yJyVUT+5Qqvvw1I\nKKVmVnj80j7sAP64ooJJAglAgF6W9L8ioIaWnL/i9ioD+P8F/AkwLiJfFJFo5byfwxVAAxW11KM1\n+t4DXFdKOQu2DVT6OsdCgZXDFSAedxGeQPBoJCO4g+Ac2yvbAEaBvgX7ttVrRCmVVkr9tlJqN/Bp\n4LdE5CNzu5e5/nWgRUTiK+zv0rau46pq4gv+BZVSry7tv4jIkvtZbXsopf69Uup+XPXWfuC/q2w/\nqZT6aVxV0N8Df1Oj7yPANhFZ+M1vB4ZXeO8edwGeQPBoJF8C/pWItFd07v8a+M+VfX8D/JOKITRU\n2VcTEfmUiOytDLqzgF35BzAO7K51XkXl8h3gT0WkWURMEXliFf3/D8DvisjhSj9iIvLzlX3fAo6K\nyM9UDNj/DdB1q+2JyIMi8nDFFpAFCoAtIj4R+WURiSmlygvufylvVM77ncp9PoUrPP9qFffrcYfj\nCQSPRvJvgLeA94HTwDuVbSilvoOrd38RVx30WuWcYo129gEvAJnKcX+qlHqpsu/3cIVOcs77Zgm/\niquDPw9MAP9ipZ1XSn0V+N+AvxKRWeAMrk0CpdQU8PPA7+Maf++p3Gut/t+0PSAK/D/ADK6qZxr4\ngwX30F85558Cv1Kj7RLwmUp7U8CfAr+mlDq/0vv1uPPxAtM8tgQicgh3gPRXjJ5bioqqZgj4ZaXU\ni43uj4dHLbwVgsemRUQ+W1GJNOPOnL+xlYSBiHxMROLixlZ8AddA/HqDu+XhURdPIHhsZn4DmASu\n4OrFf7Ox3Vk1j+L2fQpXX/8zFfdSD49Niacy8vDw8PAAvBWCh4eHh0eFLZVQK274VJcZanQ3PDw8\nPLYUFwqpKaVU+82O21ICocsM8Wd7P9Tobnh4eHhsKR4/862Bmx/lqYw8PDw8PCp4AsHDw8PDA/AE\ngoeHh4dHBU8geHh4eHgAnkDw8PDw8KjgCQQPDw8PD8ATCB4eHh4eFTyB4OHh4eEBeALBw8PDw6OC\nJxA8PDw8PABPIHh4eHh4VPAEgoeHh4cH4AkEDw8PD48KnkDw8PDw8AA8geDh4eHhUcETCB4eHh4e\nwBYrkOPh4bH2KKXIph1mEha2pWiKaDS3mhiGNLprHhuMJxA8PO5ypsbLzCRslHJ/L5ZsUjM2O/YE\nME1PKNxNNFxlJCK6iLwrIt9sdF88PO42yiVnkTAAQIFtw/REuWH98mgMDRcIwD8HzjW6Ex4edyPZ\njFN3XyZtb2BPPDYDDVUZiUgf8Eng3wK/1ci+eNweSinKZYWuC7q+vmqGKV+cN1qOMRZsw+eUOZy6\nzPHkeXTUzU/2WIQsMyUUT1t019FoG8IfAb8DROodICKfBz4P0GkGN6hbHqthZrrM1IQ1r3YIR3S6\neky0dRAM074YX+t9BksMEMHSTN5pvodJfwsfG39lza+3lVBK4TigaSAiKKXI5x2sssIf0PD7q0f/\ncERnjNqqoWhcX+8ue2wyGiYQRORTwIRS6m0RearecUqpLwJfBDgYjHtTwE1GasZictxapIPOpG2G\nBhXbd/kXHZtJ28xMW1iWIhTSaGk3MM3Fg1Sx6JCZdVUVkaiOb8kg9mbLUSzRF01fbc3geqiLhC9G\nSym1xne4+VFKkUxYTE9a2LY764/FdDIZG9tyH5VSEGrS6NnmQ9NuPDvlQL2FVS0B4nFn08gVwuPA\nZ0TkE0AAiIrIf1ZK/UoD++SxSqYmFwsDcAefQt6hWHTmB5WpyTKJBceWijazKZsdu/3zg/7kWGmR\ngXN60qK51aC905xvezzQVlfPMRZouysFwsy0tWiFphxIztzQ/89tz2YchgaLOLZrNG4Ka+j6DYGx\nlKmJMrmsgz8gxOLGuqz4PDYXDZsCKKV+VynVp5TaCfwi8ENPGGw9rHLt6aUIlIruPstSi4TBHI4D\nE2OuuiKXtau8XfL+ENdUC4nSDYHgt0s1r2eLzuXwNsrSaC3oxqKUYrrGs61HPqsoFhRWWZGasUlM\n2XXPLZchlbSZGLO4fKFAIecZme907q6vx2PNMQywrOrtSoHP584o81kHhJqqiVzW9XJJztwYmCzd\n4Oz9T5Js70Ych1O6zq7ZQR4ffZOjqYu80XocS1vy6oow5m/ju90f4tMjL63Z/W12bLv27H6tUQoG\n+kvsPRBYd6cBj8axKZSESqmXlFKfanQ/PFZPa7tR0xvFHxD8Aff1Wokni23dGNXO3fdhZtq7cXQD\n2/ThaDrXwtv4gf8owbfPsCM1WHMUVJrOuL+VhC92W/e0ldA38gtWkJjyYhPuZDaFQPDYusSaDVco\naHPeLa5uum/HDYNyqEmj1pxSBCIxjbGR0vxKoeQPMNPRi9IXrwAcw2B0+36KlsaOV36EqDr+87ZD\nf64JtRHT5k2AaEKsWd8wF9FsxlMb3cl4KiOP20JEaG03aW41KJcUuiFVOXA0TejZ5mN40NX/K+Wu\nGkwDigVFIX9jcC8GmhDHgVoejwKW6cMo5QmW8uQC4apDlAjORIpU0CbefHe83h2dJo4N6Vl73kAc\nDAmhJo3pyfo2glvBcYTZlEU4oi/yVvK4M7g7vhiPdUfTBH+g9gBRLDrMJi1MvytAdM21O5TLClVa\nPFoFs7MorfbCVRwbs1RAKdg38D5n9j6EvXAl4dgEc2nCM1MksnLXCATRhO4+H+2WolR0ME3B9LnP\ncHoyv6bXKpcUY8NlNK3Mtp3+ebWgx52B99f0WFcmx0r0Xy4ym3IoFaCYV+SyilJRUUvrY1hluvsv\nolmLddWaVWbnxVNoSiEC20Yvs+3S+2iWhV4uodkW0Zkpjr/2PMJim8TdgmEIoSZ9XhjA8vYb4xbl\nparkOhoeLN01qrm7hbtjCuXREDJpm8T06nXOez84iWGVGN5zD7amo1sWOy68R981N+WVCGRmHXbO\nvk/flbPkIjF8xQKBfHa+DU0H21Z3vUdMNKaRTNS2t9g2hKNCZvbWBnXLUhSLikCdlaHH1sMTCB7r\nxq16pAiKXRfeY+eFU/iiJk6+hGMBAj6/EIvrTE1YOA4YtkU0OV3Vhm3B1UsFduxyA98cWzE1WWY2\n5erUIxGdtg4T4w5P79zcYpJMFGvuE4GWFpNSsTwfMzJHsEnIZ5cXFCLg2N4K4U7CEwge60a9oLWV\nIiisdInuPpNAUEcAwxQyafumaeyUAmXD6HCJ7bv8DPYXXTVV5cRU0iaTttm1N4B+BxeCMX2CbrgC\nshb+oMbOPX6yGYd81gaBmWn7psIA3MDCVNJiZKiEiCuoW9oMz9i8hfFsCB7rRiB0+8nRlILZpI1p\nyvxsPtSk1c2/s5RCQZGcsSguEAZzOA7MJOqMlHcIIkJHl1nllioCbZ3u4C0ihCM68RaDmenVeSXN\nJh1syxX+iSmL69eKnl1hC+MJBI91o17QGtwISBPNncWGI/VfxaXji6YJXb3Vg1ztk2Fi1KopQJS6\nO/zqozGDvh0+giENTYdAwHUDbm4xFx03NlK+LRdVpaBYcstxemxNPJWRx7rh92ts3+VnfKREoeCO\nND4fdPaYWGXX7dTv12iKaGQzDtlMqWpAEoForHqlEY0ZBAIayYRFseSQz9X2WroZm93orJSikFfk\nsjbFgkOx6HpZxVsMYnEdWWFEWqhJZ/uu+is2x1HzwYG31V/HFbLhqJc6eyviCQSPNcVxXNXBbNLV\n80ejGn07/cyFFtQbwJrCGqEmjVzWmRcKIhAICpEaAgHA59fo6PYBkE3bDF+vFijLIQLNrZv3E3Ac\nxdBAiVzOYbJnJ9ePH6bkDxKfHmfnpVO0zWbo3e5bsVBYljXU8tzJNpk7nc37NXhsOZSjGLy22Hg7\nk7BJpx127vYvmz5ZROjd7iM96xZ4VwpicZ1obGWz4KaIzo7dfmamLTftdkDDLisyy5SIbGkzaApv\n3pns1HiZfN7h6sH7GN59CMdwVTzjgRBTXdu475Vv05LLEWq6/XvQdDewsFion712JcJWxCuss5Xx\nBILHmpFO24uEAbiDiFVWpJIWza1m/ZNxhUI0ZhCN3dpr6Q9odPX65n9PzVhkF6w4FtLcqtPSajAx\nWiKVdAVQU1ijvdOsKsrTKFJJm6IvyNCeexbndtI0bDG5fM+D9F364ZoIBICuHh/X+4s4S2RoJKqR\nnq0vWBfK685uE59vczw/j9XjCQSPNSMzW3vwVQoyaYfm1o3tTySmMzVpVbm/6rqrKlrqippJO+Sy\nRXbu9VdVcmsEjgOp1k40x8FeOuaLuPuurJ16JlBxQZ2ZtijkFaZfaGk1KBYcMhmnpo3G5xPira7z\nQDiiV+Wx8thaeALBY83Ql3mbGmG81TRhx24/k2Nl0mkbFIQj7iqgWFCUSrVdURNTFp3dvtqNbgAK\nGAl2cOVEFzkzhKqjMtNsu6bB/XYwfTfsMje2CTJarjIziLieZNG4N4zcKXh/SY81I9ZszOv/F+J6\nxTRGr2wYbuK37iXbkzOlul5Ja+Ftc6so4Pudj3E91IUlRmVLtUDQbIvdU5c3RL2laULfDj/Dg0U3\n4K/S0eYWva7B32Nr4gkEjzUjENBo6zCYmlgc7NXcahAMaqSSFumU7RaBjxs0hbW18ZC5BQxDA2rH\nIDQysOpqU58rDLQ5e4vMdQrNtnE0Dc2xiWVn+FDh3Ib1KxjS2LXXz2zKuaEeusPTftyNeALBY01p\naTOJxAwys+5g2xTRMAxhsL9IsXBDRZNNl4jEdLp6zIYIhaaIBmO199mWKxQa0a/z0d0LhMEClCKa\nGKd5aozozCSdmXHMvYEN6ZNSiqnxMjOJG/UW0rM2Pdt8mz6Ow2N1NN5y5nHHYZpCc6tBc6uBz+eu\nDBYKA6gMKil7UXGcjcSxqRvprFT93D/rjVPvkxQhmMuw4/JpmqfHMDdwdj4zZTGTcFWBjuM+n1zW\nmS945HHn4AkEj3UnnazvfZSebUzqiJsFT2kNUo3vywxgONXSSLMt2kf6gY0NqFNKMTVl1fz7FfIO\npaKXpuJOwhMIHuvPJtQqmKYQCFa//iIQjjauPOTe9AAhK7+oZrRmlWmZGqE1MTrv2bPeAXXFosP0\nZJn+y4W6xncRN/2Ix52DZ0PwWHdicZ1CvnqV4OYpatwr2LPNx9CAG4uAAAqCQY2u7uUD6NYLBfyg\n8xGyRgA1V+pMOcSsLB8Zew29x0eoSVvX1BCOoxi5XlqUQqRuf5Ubh+Bx5+AJBI91JxrXmU3Z5PM3\ngptEINas15ylbxSG4cYpFAuKcknh80tDawQP+DsZCnVhLzQqi0ba18RU93b2Zq6vex8mx8srEgbg\nRnabXlTyHYUnEDzWHRGhb4ePTNohnbLRNFdIBEONH0xEhEBQCAQb14dCwWFsuMR7B3trehhZmsml\n8I51FwhKKZKJldt0unobs5LyWD88geCxIYgIkahOZAukRXZsRTJpkcs4GIYQbzHWbSVjlRXnJ/yM\n7ryH2Xi7q4ep4f4ka5mOtA6rrQ3hVUa78/AEgkdDKZccpqcsCjkHwxRa2ow1S9Z2K1iWYuBKAdu+\nkd1zNmXT3mVUFZRZC942d/L+Ew/giLiuTTV0NYZT5kC6f82vvZTE9MoFgs8nDQsq9Fg/PIHg0TCK\nBYfBazeyaxaLily2RHuncdPMqOvF1HgZa4HX52yslWRbFyNWiYecMULa2gUoZPQg7297AGdhEqiF\neaZFMJwyfbkxdmaH1+y69bBKK1uFiEB7l6cuuhPxBIJHw5gYLVelWlYKJsctYnFj2foJ68VcXIQj\nwgcPPE2ivRslGoLiEvCxiVfYnqsT4rxK+pv6au8QQS+X6J25zmFriG35sQ3x3PUHpK4bqaZVvIr8\nQnunuanrSHjcOp5A8GgISilyufpBTbmsTTjagNezMvIO7zzEdEfPfApXVfn33c7H+bVrf0+gTh6k\n1WCLVjdc2iwVeTZxcsMikpWj6goD0yfs2uv3VER3AY138/C4a1kudcTUpNWQJHNzRu+hPffUzOet\nROctffeaXGt7bqSmsVhsiz2ZwQ1NT5Gcsdx4jBp0djcm35THxuMJBI+GICLLFmIvFhSp5MantWjr\nMDFMoeTz1z1mONx1y+0rpVCOO/A2l9McnL2K4ZTn9+uORZNT4IHcxVu+xq0wm6xOWz5HLtuY9CIe\nG4+nMvJoGJ1dJpnZ+gNRMlEm3ryxr6hhuOoRn12iaNQwnIogzupXLuWSw9homVylxnMwpNHZY/L4\n9Ltsy4/xQXQvRd3HrswQh9JX8S8QEhuBl4DCAzyB4NFAdEMQDVSdCajToImppgkH0v2877unWq/l\nOHRPD8IqCqrZtmLgahF7wf3kcw6DV4vs2htgR26UHbnRten8LRKN60yNVyexE4FII2w5Hg3BUxl5\nNJTlNNO+BqaRuC99AV+5uDguwHHwF/Mcd4ZW1dZs0qrypgJwFMwkNnYlUI94s4HfL4vkn4grKBqZ\nXsRjY2nYX1pEtonIiyJyTkQ+EJF/3qi+eDSO5QabeHPjXBv9TpmfH/4e2xL9aJaFZpXpGb/GT/c/\nTzSwupTP+Vx17WYAlLtvM6BpwvZdfjp7TJrCGpGoTu92H50NSvTn0RgauRa0gN9WSr0jIhHgbRH5\nvlLqbAP7VJMrTdt4q+UwaaOJqJXlgcRpdm9AoNDdQFuHSS5brBowDcMtxuI4qmEpEsJOgU8k34Tk\nmzc2rkJVNIfpk/lsqkvZyGyhVlkxPVkmk3bcMqbNOi0tBlJ5vqIJsbhBLO6piO5WGrZCUEqNKqXe\nqfycBs4BvY3qTz3ORPfyUsdDJH0xbM1gxhfjxY5HOBdZG9fDu51AUKNvhw+/f/HAaNkwPlLm8oXC\nqnPsbDbiLXpN1dhGFrqxLEX/1QLJGRvLcrO7Tk9YXB8sNbSG9EajAPsmw15ZdMpydwbebYqpgIjs\nBO4F3qix7/PA5wE6zY1NSWmj8WbLUSxt8WOyNIM3Wo9xIH0N7Rb9M0YC7bzVcoQZM0q0nOH+mQ/Y\nnl+bCNitRqhJZ+denfSsxcj1ik5duTp2gOHBErv3BzDWsQ7AeqAcxeyszWzSwjCgvMBcIOJmC92o\ndNsz0+VFRm1wzSOFnEM2YxOObIqh4LbI6gGuhLdT1Ex68xN0FybnBfHct3w2tgdLDKJWlkem3mVX\nbmT+/KQZ4eX2BxgPtAHQWZjmicmT+J0S78YP0d/Uh6FsDs1e4XDqMjp3XrW4hr8FIhIGvgz8C6XU\n7NL9SqkvAl8EOBiMb+hUZtZsqhs9ZYtOxggRtbKrbvdqUy8vdjwyL2gKRoDv+x/nsal3OJS+Vve8\npBnmvfghxgOtRMtZjiQvYioLU9m0lJKbsTDZqlgu9XI6ZW/YbHo5SkWHdMVVNhzVCdQZ0B1HMXit\nQLFQvU/EVRWFIxs3C82knZoqK6VgdKjM7v06egNShawVV5r6eLHjYRSCIxrvNR8iZOX5yPjrdBWn\neaHzEa6HurEr39ysGeaHnY/y7Pir7MiNktd8fLX3WUqaAZXiRGOBVr7a+yyGcihqJk6lrurJlqMM\nhrr55OjLW/6bW0pDvzARMXGFwV8qpb7SyL7UIuCU6hY9d0TwO6svMq6AV9rur7nqeL31BOFyjrdb\njpDwxWiyc9w3c459mQHOh3fyo44HUQiIkDSjDIa60ZSNAD6nzHOjP6K9lFzUbk4PoIAmu8bItMmw\nrNryXimwrMbPxqYmyiQW1BdOTFlE43rNSN6ZRJliwf17j23bS/+BExQDIQL5DDvPv0v3yDVSSWtd\nMqjWwh3saz9fx4HEVJn2zlswkGwCcpqfH3Q+eqPKHOCgkzGa+FrPM5hOmbLuq5rcuSv94+zIjfJe\n/CAlzVx8jGiUNQMLFrVtaQbjgVZGAh30FibW+/Y2lIYJBHG/oP8InFNK/R+N6sdyBO0iXYVJRoPt\nOAt0ippj05cfu6XgoawepFijCAqAJTrf6Xli/uVL6jFe7HiIV1uPU9ADVPkEAo64f8K86Hyl76P0\n5Mc5nrpI0MrzUsfDpMwIANFyhqcn3qC9NLPqPm8UoSaNUrF6lSAaBEP6vK67EWkUCnlnkTAAV1DN\nJm3CEb1qtp+spJK+vucI/QeO41SC3ApNUS4efwzbMAlMXqa5ZWP639xikM/Vn8DMphzaOzemL7dC\nygjzXvyguzq2MhxPXqC7MAUwvzKoQtzJU1mqhcEcycr3cT66p/YxUlspbInBUKjTEwhryOPArwKn\nReS9yrYvKKW+3cA+VfGR8df4Vs9TpMxwxVFEiJdmeXrizZueWwtTWag6L6dTI9mZEo2CsQLbSeW8\nkVAX44E2HMQVLJXtM/4Y3+h9ms8NfnvTrhZa2kxmk/Yin30RME23eMvI9RJKuV47HV3mhqpcUsnq\noC1whUJqxqrqi+OArekMLBAG8/sMk2uH7mdv4sp6dnkR4ahGICgU8rVXCY1SfZRFJ6cHCdl5zDoR\nipO+Zr7e+zS26CjRmPHFGAp2cWj2CmErx1Cwo35iLFh2X8AuMms0UdbqDIV1ChYBjAbayOqBTfs9\n3QoNEwhKqZ/QuPdwxQSdEj839DwT/lZSZoR4eZb2YuKWO+53yvTmJhgKdaAWejIs8+KtFlszarZn\no/FBbC8PJc5giU5/Uw85PUh7MUG8NMuFyC5mfFHaizPsywxsePoE03RrHE+Ol8lmKq6RMZ1c1llk\nXyiX3ELwvdt9G5aGebmo6VpBZ6ZfSBuRmgVvABxNw+yIAhszmIgIPX0+rl4q1tgHkdjGetXYCK+3\nnuBcdDcaCgfh0OwVHp0+VeWo8eP2+xeXFhXBFoMzsf1oypnX+a8W3bE4mrxAUfdhKJtyrXbqfZMi\nTPhb+bttH+MfXH+eJjt/S33YbDTeSrcFEKCzOE1ncXpN2nt68g2+1vMMOSOIjVZzZXDb1GjP0XSm\nfM1M+pr5Vs+TOKJh4+b6d0RDUw62ZnDVsXir5Qg/M/wC8XJmbft1E3x+jd7tNxLLTU2UKNbIwqkU\njI2U2LN/YzzPwlGddNpGLRn8RdzZ91I6Ok3SI4V5Q2QVmkZLYIMFrk+jrcNgevLGakfEXXG1tm3s\nUPBa2wkuRHZja8Z8IvEzsf2MBDr49OhLBCr2ORuNKX9z7UZEFqlyV4VS7Mlc50TqgrvyuJUmNJ2i\nEt5uvocnpt6+tX5sMryY9AYQtIt87vp3+OjYKzySOIXhrF0VruXQHJvmUorvdH+You6nXPGcsDUD\nJdq8B4alGRQ1kxc7Ht6QftVDKUViqv7U3CqzYT704YhGIFCd2sH0Sc1ArlCTTk+8THxqFFni76k5\nFjuzw/jXoKbCamltN9m2y08srhOOaHR2m+zY7V/TYkQOQl7z1/X3L4vB+cjuKscKREj443y576fm\n4wCktnXgtjGUzROTJ5HKzw9Nn67+DlfwbinRuBDZxd/1fZS34ocpaFvTMD+Ht0JYByzRGQm0I0B3\nYRKjhm5UgL78OH35cUYD7fQ39S7yZFgRC6d5tfYt2a7h0F5McC629+ZtizszK2i++dnaRmNZN/8m\niwVFILj+mkcRoW+Hn+SMNZ8qOhrTaW4x6kZSt7T7eLh4kVdKEXK+JjQcHNHoKE7z5OTJde9zPYJB\njWDv+gxcH0T28EbrMSwxUEC8nOL+mXPsyg4xNw/PGEE0VG1xKEJeD3AxspPDs1fQUGzPjjDQ1HPz\n70MpN1Oi6MuuuDXH5oHEGRauC47OXqLJzvFO82EyRoh4aRYlwpSvuf4qr4Kj6Uz7m0n4YpyJ7+Pn\nrn8Pn7IYDPVgi0ZfbozwFlEpeQJhjbnS1MdLHQ8hlZFMifDUxJvsydZPiPZw4n2Gg52UKzP1miwZ\nGQ1l05WfoKyZ84E0cx+B4ZSJl9IUdJ/rnYRrPHtm4nWKmm9FM5/5y9aYn+U1H1fC28npATqL02zL\njdUN0CtVvKB8avWrIH2TBYtJ81luAAAgAElEQVRqmtDSatKygnrPKSPMt7ufIGcEEKVQInTnJ3lo\n+n1ay1XhNncEZyO7eaX9vkXvcNLfzA86HyFWzvDZ4RfwO2WarDzOMvN+WzMYDHVzeNY1un946i2m\n/c9SqKxq69nbgnaB50Z/xKwZ5kxsHwlf/EbEsbhrDb9T4v7EGY7MXq46f3d2eFFKmoLm45s9TzHt\ni8+3sRxKNIqajy9t/yQaqlL8yL3useR5Hpo5s+z5mwFPIKwhM2aEFzsenle9zPFSx8O0DKVoLqdr\nnhcrZ/i5oed5p/keroV6KS31mVaKgF3k6fHXGQ11YIvOruwQXYUpBNdTYyDUw+XIdhw09mUG2J25\njoZi1gyjKtcQ3MF8pXrXWDlD0FlshBwKdvC9rg+7KQBEx1AWsXKazwy/uGjQT5hRXup4iOmK/ret\nmOCpiZM0r2Iw1DQhEtNJp2qrVjTNrQO80eRzNokpi1JJEQxqtLQZ+PwLfeCFb/Q8RdYILjJ4jgQ7\nGQu2b1mBkNUDfBDby4S/lVg5zZHUpfl3WgGvtx6vPaERjVmziddaj/PU5Fv4lMWBdD/nortrHi/K\nIWTdMLaH7CKfG/wO15p6mfS3kDMCXGvqW/SdGY7Fh6bepr2UpL2UrJqAKdyVu1GJ21kJAafEE5Mn\n+XrPM1XftNtoDcEkgkLDXrL9dPwAXcVptjc4zfnN8ATCGvJBdK9rIF6CLRo/brufbfkxevIT+JwS\n5yN7yBghevPj7MsMELWyPDV5kic5yTvxe3i3+RCaclUMbcUZPjr+KiG7wPbCeFX7prLZm73O3uz1\nqn2xJUbhoFPiWPI8p+MHbuhwlQMIgkKJhqZsNOXw5MRitYYlGs93fmiR7tcSkxkzxsmWozw+/S4A\nOd3P13o/sijqc8Lfyt9s+ziCImQVeGT6vZr9XUpXt0m55FS5S4pAzzbfhsckpGYsxkfL84usUtFm\nNmWzbaefYMi91yF/OwUxq7xfLM3gVPzg/Mx3K5HwxfhazzNYouNoOiOqg4uRXfzU+Ktsz41ii+bO\n3uugROdKeAdPTb4FwGNT71DQfVxt2lY1qOrK4Z4lz0jHWfSOD4QGeaf5MLNmmHgpxQOJD5aNCRCo\n69a6HEXNj66c1Vl7aryTlmZwOrbPEwh3E2mzqeaMR4nGWLCdsWD7/KxCAYjG1fA2Xmm/j/sSH3Ai\neQEdh/uTZzmWusiML0rQLhCxcmvazwdnztBSSnEqfpCcEaSjMM3+9DUGQz3M+GK0FxMcTV2sSssx\nHOys6SjsaDoXIzvnBcLZyJ5KAfkFz6LykSiErBniB52PkpkOciK1fKlITRd27A6Qy9kkExZWGYIh\nId5sYPo21ifCcRTjY+VFGrdcU4RiMIyaTnIg5G4bmTVRXbUFVb6iwttqvNz+wKJIXiUalmj8sONh\nfq3/a+hL3a9q4CwYKHUUPzX+Gu/FpjnZcgxRDiKg0Hho+tRNAyg3qqhQezGBvUaJ7gp6/bKsmwVP\nIKwh3flJhoOdNZeX84Ji6TghgoPO2y1HGAp18+mRF9FQmMqio5hYl34K1FxRLEz0VQtLjLq1Fu0F\ng/9EoLX2EntRJ4STrcc4mrrESpz+QiGdUKixRoVCwZnPYl3y+Tnz4DNkYq2IY+PoOiOZQR4fO4lv\nYgr21zE0F5M1t29myqIz6W+p7cpccT7oKCboKEwxEWir4+Tg0JurXt2eSF3kQGaAwVA3ANtzowTt\n6liJRhFwShxLXuB0fP+ilbHuWNyTuszp+IEVuYxrjs22Tb46AM/tdE05lL6Kz7FY5Ky+QgOuEo1p\nf3z+w9iM9BQmaqrEUA59+Rsfe3NpFm0Fy3MHjVkzvJZdXFe0uZUdcObBZ0g3t+EYBrbPj9INrkS2\n81bLEcKZJLHpMTR7sSFdsyweGH+vuuFNgI3GpL+ZoUAHJ5uP8GL7g1wM78BagefbnAPFR8dfQVd2\n9TuvHHyOxWPTte89aBc5kO7nQLp/UwmDOR6cOc2HJt8mXprFZ5foyY3zqZGXeCxxynVddRbcs3JA\nKbQFkYyiHHxOmaOpS425gVXgrRDWEL9T5rPD3+fV1nsZbOpBMTehXpmeu6yZ9Df1si03xrWmXkaC\nHTRZeQ6kr20Kt7WgXeTe5Fneix+any2JsjEdm0emT80fd3j2Mmdje3FWcNu1XFot0bnatI0pf4x4\nOcOezOCGR03Xwh8QdA1mg1EysVbUEndEWzM437qfx9VJjpx8kWsH72Vk5wEc3aApnWTf2Tfpa5tZ\n+yDE2+RcZDevtZ24ESQJIMLV8DbebjnMZ4deoKswxVigrUolajgWbRX1TpNd5JcGv8XbzfdwJbwN\nW3R8dold2WFOJM9vinf4VhDgQKafA5n+qn2H0tdoKyZ5r/kgCV+M1mKSI6lLDDZ1u4F3orEzO8yD\niTObUtgtRbZScYyDwbj6s70fanQ3VkzCF+PLvc/i3Ex9ModyODR7hdFgJxkjiKWZaI6NhuIj46+x\n8yYqnY1iINTN+7ED5IwgPflxTiTPV9k5hoId/LDjUcqa7qqalg6CFc+pfzTwtUWb00aIv6+kIbY0\nE8MpoynFp0depK3UeHVLIe9wKt3C6QeewjardcKiHH7mzb8mOeFWgZubEGiiaO80aF6By+pGcj3Y\nyfNdH6oOEqugOTb70/2cSJ7nq33PYouOpRnz7+Vzoz+ipzC5wb3eeBSQMUIohIiV3fw5d5bw+Jlv\nva2UeuBmx3krhHWkpZSiuTTrul6uYFbo5l33MWs0zQfDOJpbhuMHnY/wa/1fuyVPibVmJQa9vvwE\nvzrwNaZ9cS6Gt3M6ftDdIQLK9dH+xOjLVee91P4ged0/PxO1Kn7nX+t5hs9d/86qZpm2pSgUHDRd\nKlHGt/8ZB4Ia9wTzvK/X/nSCdoG2VsHUDBKTFpYFhglt7Sax5s33ub3bfE9dYQDu+3clvI0np97i\nHw5+i/ORXUz4W4mX025yuS06618Nk/5mftDxCBnD9RoI2QWeqdRZuNPYfG/oHUZXYYrpwApyHCuF\n7lhcDW+vKTxEwVCwi125rVPLWYC2UpK2hOsXfrLlCBmjic78JA8nThNaEuNQEoOxYHu1p5YIlmbw\nd9s+xs9f/w5jgQ7yeoDO4hTtxWpvFKUUU+NlZhL2nPzBMIS+Hb5F8QK3SoQi+zIDXA5vX2w8V4qW\n/Awl3U9zi2xYrYPbYSU2nLm/h98pc/wmXmFbEUs0zkX3cCGyCwdhf3qAw7OXMJVNTg/wjZ6nF7nU\nprUw3+p5kl+4/t019wBsNJ5AWGe6ilNccHYtztZYh6KxvEuivQID32als5jgU6M/WvaYmgbrOUQo\ni8F/2f4p9Ep2TAE6C1M8N/rjReUMU0mLmYSbXmJOI1ouKwb7i+zZH1iTlcITk28hmSwXug676cwr\n/4ZDnfxt30f5+aHnG5byYzW0FJNk9WD9Faxy2J7dHKrK9cBB+GrPsyT8sXk36TfNCBcjO/jZ4e9z\nNrK7ZlS1g8aZ6F4eTby/0V1eVzyBsM7sygxzsvkoGUNbPifKTQYpR7RFnjx3IgGnRLScIemL1dw/\nr0ZbsG000MZX+p4lrwcwlMU9qSuEL79f07nLtuB6f4mObrNu6cuVomyH0NVB6Djo6oTmtusGOU3n\nb7Z9nEemT7EvM7Am+mbbViSmysym3LuPxjRa2szbLnv5wMwHDIW6aqeQUwqfU+aRxKnqfXcI78f2\nk/DHF31/StNJ+qJcDu8g4Y/XdKF2NN097w5j6045twg6Dp8dfoG9mQF0p5KtbWkQz3KGfaUwHIsH\nE6e3xIzzdnly8i2k4rpXRY1tjmaQ8MXJG0HSZoQ3Wo/zg5/6FU49/CzpaLWqLp9zGLxaJJO+PVtM\nLusw3dGLqmVLECFvBPlx+wP8pO2+27oOVOozXy0yM21jlRVWWTEzbTN4tYjj3J5TSEcxwdPjr1c/\nc+XQXkjwi4PfuePUIgs5VSeOwM1iuoPWYtL9bpegOTatWzCm5GZ4K4QNIOCUeHryJE9PnsRB+Enb\nfVyM7EJXNmXRKxXUql9KwynTlxvnaOriXeHJAa7N5eOjP+K73U+sPPHx0pzUIsx09PJOayf3/uQ7\nRGcXB/gpBWPDJfYcuHX1kQgYVhlxHFSdLHyWZnAhspvjyQtVUd+rYTZlUy6rqvKd5bIinbJv21i9\nL3ud3oEJ3o0fYjjYScApcSR1iV3ZoS3nTXMzbDQsTcfnlBGgWC96WCkc0TmUvsKp5oNVqSs0HI5s\ngbiC1eIJhA1GQ/HE1Ns8mDjNjC+G7lh8o/eZKvuA4Vg8PvUuB9PXGtTTxrE9P84z46/zcsdDbsZI\n5dpPFFK3/GgVIijd4J0nP0XPtQvsOfcW+oK6BLYNuaxNIKih66tfKIeaNNr7+7l24N5l46wFh5Fg\nB9Hb+Dtm0nbdBVM6ffsCAdwEco/XCRzbipRFZ6Cph6Lmozs/ScTK8ZO2e7kS3oESIWjleWz6XUzH\ncpNJ1mBndpiQXeQzwz/kB52PkDbCgCJs5Xh64o070sPKEwgNIuiUCFZm/c9MvM4POx5BcI1cGoqd\n2SEO3IXCYI692ets7x9lKNSFg9CXH+ft5sOcjy4orHKzsqOVldfYjn1ko3HuffV7i3YPDbjBboYJ\n23b4V+WBpGlCxMqx9/3XuXzsEde+Ucs7DDBvM6jOWGAnKARCTPbuwtINWiZHiKr1SW+ylRkJtPPd\n7g+DupE/yXQsSpWCUABZs4kfdjzCzswQVyPbqzzbdGVzLHkBcD3lPnf9u2R0tzpfk52/41ZOc3gC\nYROwOztMz8A3uNrUh6UZ9ObHaS2lVnz+tVAvb7YeZdYM02TluXfm7PzK4nqoi5FABwGnyL704Jaq\n/epTFrsXpDF+bPpdWktJ3o8fIK/5abJzJM3oTfMmObpBOt7GbKyVaKrad9wqw7XLRXbv8684YZ5S\ninJZ0XP9Mi2TI1w4/hjJ9u6q6GVg1RkulVIUiwptriJbs8Fsyma0dw8Xjz/qRsBrOtf3HmEyN85z\nk6/WrUdxt1EWne92f7gq86pdo2iOrRkk/VH6cmOMBDtwREOUQlc2nx55qSrH1p24IliKJxA2CQGn\nxD3pq6s+72J4Bz9uf2B+1pw2w7zadh9po4nhUCcJXwxLM9Edm7eaj/DMxOuLioBsJQQ4mL42L+wU\nbhbOS+Edbo2HZdVJQiZeWyDM0X+lyK59fgxjdSqkQCHH0ZM/5P2Hn2W2uR1Hc/PuI8JHx15ZVTDh\nbMpifKTsDkUKDFPo3eYj1BPh4vFHcRYYsR3DZCzcxbni7i2ZUns9eD+2H6tWdtI670bKjPIPhr7P\nlC/OeKCVoF1gR3Z0kRvzVuALn/yvlz/gzLdW1I4nELYwc0VJlkaaWprBe82HEOXMp82wKzPXH3Q8\nQu/A1zdFbqDbRYCnJt/iRPIC5yK7OBvbWztNBqCJQ7O2/AzPceDqxSJdvSbR2PKfhogQieqkZ93B\nXnMcjr/2PLPN7cy2d9HbYrM7O7Sq55zL2owOLT6+XHLjJ/IP7q85plmawdnoHk8g4EYUv9NyeFWl\naEOW+060lZKbIjXKHIEXfxaA3/qDrg29ricQtjAF3e+WxKyBQlB10nD3h3o4kBmo2jfti/NGy1HG\ngu347DKHU5c4nrqw6dUR8XKaRxPv81DiDK+1HuNcdO/imA/lYCqbo8EpqgsnLsb1QCpjGEKoafl0\n253dJoWCg2UplAOaQHNqkmPNswTSq1tlOI5ieLC2W7FjQ7ak1w3cWy71xN3EGy3HcOp50teoP244\nFvclz25Az+DEc67rauj3/3ue+pcrUD39wTp3qA7em7SFMR1r5V43FRTCeKCtSiBM+2L8fe8z8zPs\nsmbyTsthpgLN/NT4a2vZ7XVDx+Hx6fcwlc3p2AF0ZeOIELSLPDf6I3SBSEwjnVpeHaAUTE1YbN+1\nvEDQDWHXXj+ZtEMhb2P6NKJRHe0WgsVmUzbOMt1qnR5G7zlSlY5ac2x2ZramCnCOomZyMbyTyUAz\n8VKag+lrhOzCzU9cwkSgtU4tBoWmbGLlLLNm03wlwuPJ8+xP999W3088Z/G7P/NrnPr6CoPUViIM\nGognELYwhrKJlDPM+qLVO+eS+NSo+Zo0I1WHv9lyzNW9Ljje0gwGQj3MmFHyup9z0d0UNR87s8Ps\nywxsikR7SxHg4cRpjiUvMOlvIeCUaC8m5r1Cunt9FIsFSjcZb0rFlemQ51RHTWGN9KzN+GgZ3YB4\ns3FTryXbUiRnylhlRS63/Cqsy0qyMztEf1PvfBoUzbEJOCVOJM+vqK+bkZQZ5qu9N7Ko6o7Fe82H\n+MTIy6tOHhewizXLeAqKx6fe4570FVJmmLweoKWYXFQDfCGPnf5tgJXN5AG+vqpubmo8gbDFOZE8\nz4/bH6jWm1bqJNdCaqiAxgJtVTWAqbTweusxRoKd7uxUNEaD7ZyOH+CzQ9+v+1E1mqBTYnt+rGq7\niLBrT5CpiRLTk/UFmukTSkWH1IybsTQU1ohEdTSt+pnatmLgahFrQfBYMmHT2WMSi9f+xCbGisxM\nr1ToQDiq88zEG1wK7+SD2B5Kmsmu7DBHkxcIbrEIdgch6YtiOmVebH+Ionaj/rStGdjAC52P8suD\n31yVe+fR5EXebD22WIWmFH67xOcev8in9X+2soY2+Sx+PfEEwhZnf3qA9+KHSBuhGy6PFZ25g2DL\n4j+x4ZTZX8N+4HdKdQJ0FEPBrkU6eUszSRvCqfgBHpz5YC1vZ8No6/ARjdkMXC1VqWpEIBjS6L/i\n1jQoBkJYykd0Ks2uXdX5g6YmypTL88UPAHdxNj5SJhzRq44fHS4wm1y5Xaa7z5wXRPsz/eyvUahl\nq3ClqY8ftz+AIxoOWqX2dvWwX9R9zPhitNzE/fqv/+9fAnBVNkrRMpalabaSRVdcm9nVXZ0rFwZ3\nOZ5A2OLM5Up6vfU4V8LbcNDYlh/j0al3eb31OEOhrnkVg+FYtJRS7E0PVrVzJHWJky1HqwyUquZ6\nwp3JXY7s2LICAcDn19m518/I9RLFggJxV0St7TpTEzYFX5CzDzxJOt6GVKTG5MC7PEr/onZSSbtm\nrWkFZDP2Io+lQsFesTAQgVizTiS6uT7TWaOJU/EDjAfaiJUzHEuep3MF9b/HAm281PFw1Qy+FiXd\n5I8//DnKgZvc+0J1jQiJ7jCp1iD+goWjC4WQuekq1G1mNteb5nFLBJwST02e5KnJk4u2f3T8Va42\nbeN8dBcOGvsyA+xLD9T0sT6SusSkv5lrTX1IJYuQphz2p69xNrq3KpcLUHMQXEhJDCxNJ2gXN21k\np2lq7NgdoFxysB3w+4R02kaJzXuPf5x8KAKaBpUF0pmd99E5VV4Uy7E0V+GNHdXjXXL65naXaFxD\nEyEaNwiGNlf+ySlfnK/3PoMlulsH3BdjMNTNhyffqrnynOPRPzvGL/zRMYLZ8uJ3oc5grQTK/uWN\n+vWwfTo5362de7fjCYQ7GAH2ZK+zJ3v9psdqKD4y8QYp8wNGA+0E7CLbcmPkjABno/uqjtcdi/11\nUmvkdD/f6fowU/5mQPA5JZ6YfIs9C6KONxumT2PeHKkg2dJFKRByhcECHMPk7ebD8wLhZsZnX9jk\nUng7GSNEa2kGseoPmuDWbe7urZNwbRPwo/YHFhtuRcMSjR90P8Kf7/2E63tbiy9DT2lmRRMDBSQ6\nmryZfQPwBILHImLlDLFyZv73iJXj/pkzvN18GEc0lGgYTtlVFdSonuUg/PW25yhpvvkPuqT7eaHz\nMcyRl9leWL6mw6zRxFCoC8Ox2ZEbbkgAXSiskzcidRdAbpIzl3JZIVrtVUImEuev9z6HIxqWuNHL\nwdhxjr78bcxybUNwV2/tuJKN4NE/OwbA01+uU7fcUWy/mKjrquAvWBRD9QtBlfw6RrlWuZlq8pHG\nPYe7GU8geNyUe5Pn6cuPcy5ScTvNDbM7M1RT9XQhsnORMFjIj9vv55evf7vmNRTwWusJzkb3Mme5\n+BH38/TEG/Mri5IY5I0ATVYOo66e5vYxDKHHyFAvuXG8nAYgn7NJTJdrCgMFnHn4I27gYOVZlEXD\nDkS4dPwR7nmrunpc347bK9yjcEti2mjEy+lFAYU3TW0A8OWb7F9uJFfqpjExs20hgtkUstD4vqRZ\nBeTDJuoWMtB63D6eQPBYEe3FGdqLb9/0uIFQb+0dImTNprrn9Tf1ci66ez7FxhwvdjxM2/UE77Qc\n4UrTdgTXnfZY8jwPzHwwP5go4Gx0D6fiByjoAdoLCR5KvL8iY2ct9gWSvFdOk9RiixLWGY7FAzOn\nmUmUmRyz6tY2ysZasPyBKsHoaDpTXTsIRXVyadcYHWrS6Or1YZq1B9RpM0rKjNCTn8CnLAZDXZT+\nyXPoGnzpPSHXZNI0W6J5ModUCuYoXZjuDpMPr+FMW4R82CSYKVfJBkcXSoHl9falgMFkb4TWsSya\n7SDKtRWoBVKh7NeZ7r55nWeP9cETCB5rStCpH/GlLTOrPx3bX6futPB814dJmeGKsHAHnffjBzEc\nm3tTblDWK233cSGya96DZSTUyTcDT/PJ0ZfpKkwtavFaqJdT8QPkjCDd+QnumzlH0hfhVGw/eS1A\nX36cE6kLfGbsZV5qf5DroW6UCJpy2DV5GfPqIBMV43A62sJE7y7yTRGsSinNlskRwqkEylHzxuiF\nOKLx/cd/gYCVxxBFQJX52K7LHIv086kF7pF60aJ7IIVW67F9N+t6RAFti55WBVvRNpxmbEfs5p46\nqyDRGaarkESzFZoCp3LByd7IinT+hbCP4T0muuWgNMHRBH/ewijblH06pUDtXFQeG8Oyb4qIRIF2\npdSVJduPKaVuu7q0iHwc+GPcz+b/VUr9u9tt06Ox3Jv4gPOR3dU7lGJPptrddY56OZls0ZjxRasC\n7+YS+B1PniOnBzkfqV5dWJrBq60n+NnhF+a3nWw+zPvxg/OCI2OEuBze4VbIqmQSTZkRLkR28slL\n3yV06RrqWBcK19X2asseRo50cO9Pvs3gvqMM7T6Ms6RiWrK9x/2hXi4KEcqmn7JxQ530Z+Md/Gn6\nSehT81HmPf2uemW54VGjWu0yfxkF0USe6Z7qyPRbxTY1hnc305Qu4StYWKZGNubHWY2KRwTbvPHM\niiGTIvVtDx4bR12BICK/APwRMCEiJvCPlVJzfo1/DtxWsVgR0YE/AX4KGAJOisjXlVIbk23KY12I\n2nnuT5zh7ZYj7obK4Baxsnx46p26523LjZI0I4uT0uEWKhGoyuEDbu77cxdtZtoj0GdDjVoErqeT\nS173cyp+aJHgUKKhUIu8Y5SuU3aEH8dPMLOkbrJtmuTCUS4ffYiJnt04xjJzKk1zM9PNBwwuSSWy\n4GdNQSBXJpAtUwj7aEoVbyoM5ptZZrtZtBHH4eDb73LwnXfRHJtrhw5y6vHHsM1bHIQ1IRvzk41t\nXm8oj1tjuRXCF4D7lVKjIvIQ8Bci8gWl1FdY2Xt6Mx4CLiulrgKIyF8BPw14AmGL80DyLHuy1zkd\n209e97M3Pciu3PCyWVOPJs9zLryLEjLv6qk7Fs3FFDP+2onDdNtCt8qYxWLddg3rhpfSaKAdTTnY\nS/U4tVQUmkaivRethtpH6QYTvburhFcVIqCEyMwk6XjbTVUhmoJQukQh7MNXuP2UIAooBXQ+9f/9\nBc2TU/Mf7ZE332L/qdP87W9+HtvnefN43GA5gaArpUYBlFJvisjTwDdFpI+bhiStiF5goYP8EPDw\n0oNE5PPA5wE6zeAaXNZjI2gup3liqtoIXSw4JKYtigUb3dCIxXUiUZ3UYIb7L3+da/tPMN21Dc22\n6R68yOPWJV7d+RiDoe5FldE0q8y2S2cQIJYYR7fK2MbiqFTNtugevMCXf++zvP2TbgKZEu0j6do6\n+RpoyqnrOVOvZOZSRCm6By6SC8ewzeUHX4VrZAUoBg0iyfqCbiUoIDo9skgYgDub8xWLPPzCD3n1\nEx+f3948PsFDP3iRjuFhHF3nyuFDvP3Uk5T93krgbmE5gZAWkT1z9oPKSuEp4O+Bw2tw7VpfU5Wg\nUUp9EfgiwMFgfHMn5vdAVdxupMZgmUnbS3L+O+QyDuNaGccBPzkOnnoVTt04IhHSeCb0Bj9qv5+r\nTdsxA1DOO/RdOcv2y6fdawHHX/8+7z36URzdqAziQnxqlJ7LZ/neV49COxSazEoM9pLXqEZWWLEt\n2oeuMLG9OiivrmtRDUQ56LZF59AVRnYcqAp0W9SsMK+GyUX9qLEsLFUbLe3rXF+Umm9bAY4Gk31R\nnvny92rbF4AdFy/OC4TodILn/stfYZbdFZVmWew5c5a20TG++Y9+9abCTxyHnWfPsf/900RnkuSb\nQpy//z4uHznsGYm3EMsJhN8ENBG5Z06vr5RKVwzBv7gG1x4Cti34vQ8YWYN2PRpAqWAzNFiiMp6g\nG9DT55svMqOUYnS4TgGYZWbs6ZLGv/7EbwAgtoNuKT7+pb+kdWJy0XFN6SSPfv9vmWnvoeQPEklO\nEU4nKZsms80VlZMIk30ROq7Pur9W3B4DuQyWP+jO0HUDzSoTzMzSNn4NX7nE0O57XINzvZTiN6F1\n7DrNE8MkW7vIRW70ZaFgUQLpeJBS0JzfP7w7Tnd/Ct2eO04RzMxSCjbh6DqabdE8OULH9ctcuO8R\nSr4Iti6kmwOuYBFBXAtJHaPzjesfe+11dGuxmsqwbaIzSXr6BxjZtbPu/YWTSZ77yy8RzObcdoFQ\nNstDz79AV/8AP/n0J1f1vDwaR12BoJQ6BSAiZ0TkL4DfBwKV/x8A/uI2r30S2Cciu4BhXCHzS7fZ\npkcDsMoO164sHuxtC64PlDjw8if5wjcP0jI2zscu/zU+u3bkcb1BqxS4oa5Quoalw9kHH+CR51+Y\nn83OoSlF68SNHENlw+C9xx9dZPgthkyG9rpeMrrlUAwa4Ph5/Lvfx9FDFPxBoslJrt6zh+/88i/y\nzFe+Tmg2Saa54tz5//ELa/EAACAASURBVLf35tFxXfed5+e+92qvAgo7QCzcV5GiFlKiZFGyJVuS\nZdmSZTu2YztOnE7smfTp9JnO6el0zvwxc+afnPTpTGa6Z9G0+2QSW+14jbxIliVZokUtJCWu4ipu\n2IgdKNS+vPfu/PEKRRSrCgQJoAog78cHMlH16tWtV3j3d+9v+f7mawykRApoGLtIpKWJtM/H3W/9\nikhLB0M9m0h7/XhTCcBmaE0Pkx0NTsrlLGyXzuDGRrSchWHaZD06d791mnvfOoxuWWhSknO5mGhr\npXdrZ0m2E8C5nTtoHiqVAZfAldWrC7+3Dl5BK7PzMXI5moeG5zQIj/70n/ElkiXfn8uyWHf6DMM9\n3ZzfeeccF0uxXJhPgvL9wF8D7wAh4PvAxxb6xlJKUwjxL4FXcMJ2/1VKuXKlM28hshmnLaTHqxVJ\nN8+0AXxK+1dFx9//yqts5njJhCAl/O4rR+DrW7B1rahCtRzXGgXTMDh9z90lx13ctpX6iQm2HXwf\nISWalEUFagCJuhBHHvoYF7eXejelrhEPe2c94ub1L30eXzyOJ50m2tCAreusO3qOj3Y87BiBG3V7\nCMc1dfiRB0B7kGf/3+/iskxahvtpGb4aOrN0nVN7vl1iDGZju3Sy+TTNI4/spX/jBjac+BAjl6N3\n80YG1q9HVnBFnd+xgx3vHSQUmS66Rpau897jnywclwgFCU2XSk2bLhfJYOWCwvqJiaJzl1wGYM+r\nrzPd1ERHXx8dl3tJBoOcufduxjorFDEqasZ8DEIOSAE+nB3CJSkXRzdASvkSUF7LQLHkSCmJTVtc\n9AZhKMNESwuBRJxQZBpb19DNHMNdnQyv7mFw3VqmtNay5+no66vop24cGwUg0txMxustWdXPYBk6\nOcOFbtsIKRFS0rdxAyfv213mxIIjD+/l1O5dtAxeoeXKEKsuXcKdydC7cSMnHtxzU4HQVDBIKhgE\nKWm/FMHyNM7PEFRwI2m2jW5LpLSpi5ROtlPN7fStv4PWvhjTTZJ4g3de+fzjqzoYX9Uxr8+EEPzz\nH/8Rd+1/m03HTqDZFoNr13Lw0U+QDl6tCD55326aRkZw5YrdRlIILm/eXPH07nQae464CDjxhcf/\n6UcgwDAtbKDno/PE6+twZ7LEwmGOP7hnzl2IojrMxyAcAl4EduMURv4/QogvSim/uKQjUyyIcm0A\nvYkkd+3fz+pzHwGCeF0d4YlJfOYUAJ29jhKnAMjPC6t6++jo7WPnO+9xefMm3n7qyZLJLxUMUDcV\nKWsUcjOZNUKw75nP8vgPfohhmsU7AV1npKuL17/4HB29fXiTScZWdRBraChzxqtkfD4GNqxnYMN6\njjxcQZDtRpGS1t4o7ow1P2NgW2U7zYEzEVq6E+C2dB1jlo/+8sY76du4A1s30KSgfiJF3WQKT3oY\ny6UzsG4t5iJl90hd58gjD3PkkYcrHjOwYT3H9+xh57vvFtJpbV3n9S88i+mpnB011dKKNlcQCKd4\nTlhW4TvXAM2yqJ+cKsQbPvGzFzn42Cf4SLmWasp8DMIfSynfz/97GHhGCPGNJRyTogyV3DUVuaYN\noCuT4el/+Ee8iSR6/gb2pFIl6YjXIvI/mmmy+txHXFmzhkt3bC065vDDe/n0939Q8loJnLz/6gp/\nfFUHP/nOn7Bz/7usOXsWbypFzu3m3F07OfLQg0hNq+kq0chatPRP48rJii6QAvkYgTsboWlkgpHO\ntUjDVfR83cQwiHYAzt25g03HjmNYFhmPj95NO5GzfP6aBCybpqGok2kFpPw+Dj32KJe3blncD1qB\nDx+4n3N33Unr4BVybjejXZ0VXVEzmG4XRx56kLv2v43LLN/roWJQe9a/DdNk1xv7uHDHtrmL/RRL\nynWv/CxjMPuxhQaUFXkePPFv+PN3hoB8G8AlQM/luPeNN/HMMgZw49WFrlyOLUeOlBiEsc5OTtx/\nHzsOHCx6fHDtak7turfosYzfz8HHH+Pg44/d4LsvLUbGouNyZH7VwVKSCLmZaguy9xdv033hAlMt\nq8jos3R4hCDS2oknmSPjd/HBxx+mbmqK9v4Bxjp6ENJGXlvxpmlMtPcg8gbBn0zx8C9+xaajx3jt\nS1+oykSZze+6boRT9+0mUV/Pjv1v0zjhiAnebKJpeHyCyfa2ksedauvDbDlyFFcmy9Dq1Rzd++B1\nd5GKG0OZ4iXgurrys/l3KWBpDAFAz5mzPPTyK+imWTaL5EapVBV85JG9nNx9L3cc+gDdNDm3cwfR\n5uayxy5HwmOJ6xuD/PUbb/eTaPAD0DY4SCLUQM5dqmyK0AiPJRlZXY9tGLz+pS8QHh8nPBrF1oyy\n73WtAKAA2vsH+Mr//p85uXsXJx64f1muoHs3b6J38ybqJyZ45MVfEopMIYVGzu1morWVVb29RYuR\ncmi2XTH288iLv2DVpcu48m63NWfP0nXxIr/85jeINSzd/XO7sfz+spYx89KUh+vryi8B7lSK+3/z\nGqs/Oo9m25guF2d23snWo8eKfNcLwdR1+jaWKdTKk/X7OfLI3kV5r0VHSsLj43iTKSbbWsl6vUVP\n+5LmnMbAKfYSXFnXgO266kbJejzE65qoVLzvzhS7USLNzUQbGuk8P1WSdSXyBWzXIgCXabL94EHa\n+/t55atfXrbFXtNNTfz8W98kEI2imybRhgbc6TSf+d4L+OIJXLlcXsC82PjaQhBtaCg7uTeMjNJ5\n6XLR37EmJUYux86332H/008t+ee6XbjtDYL3jecA+B/+Q3uNR3LzeJJJPv/8d3Fns4WbzJXLsf39\n6/cvKMfseWrmfJamkfV6Ob1rQZqGNSEwPc1jP/4Zweg0UtPQTItTu+51AtH5idXWhKNbVAYJZN0a\nw2vqSyqNT917D+tOflRU5DUbSy+duG1dY6I9QNPw1V2JbubwJmOsPnus9CR5DMumaWSUtv4BRnq6\nKx63HEjU1RX+nfX5ePGPvsmas+fouNxLxuuh5/wFPMkUumVhGQamy8Ubn/9c2XO19w+UrQ7XpKSj\nt7KCruLGueUMwg25awD+wxIOpkrsePdAkTGY4Xor3krPW7rO6889S/3kJJuPnXDy3Tdt5MP7d5Px\n+xdn0NVCSp74wQ8JRGNFLrOthw8TC9cXCqZiYQ/1EyknuDv75UDapzPaXV+2X/DA+nXsemOfo6Wk\nG0UGQwLTjd6S1wAk671kfS4C02k8qSw73zlAW/8F9Ou49fRcjtbBwWVvEK7FNgwu3rGNi3dsA+CD\nT3ycVZd7qR+fIB6up3/9uqIg+2wyXo+T2mqVBq2z88zE0nM52vsHkMBId9fNK73e4qwogzAYbrm+\n26YG7polpUKOe8PoGK2Dg6R9PtaeOVNxci838VuaxnB3F62Dg+imVdDUB4g2hNn/mU8zvmoVw2vX\ncPbelbcjmE17Xz+eVKokfuLKmew4cLBgEKJNPjwpE28y50ha5I+bbAuQaCg/qQNsP3gIgWTd6Q84\nc/e17jJJIJYl0VBelNF060y3BIAA79Z9nN2vS7ovOC6jisbaMMj4rjmflLRcGSIUiRBpaioblF1u\nSE1jcN1aBtetve6xfRs3sufV10sezxkGp+8tLVwUtk1b/wDeRALNtmm+MsSmY8cLfwO2prH/00/Q\nt2UzummSc5dv+Xo7sqIMwu3Eug9PcvdbbxOMxch4PFi6jjudJlkXIuv2EJ6YABz3gys7dyN6Gyf3\nGxxfbdbr4XfPfBZvIsH2AwdpHh4h2tDAyft2M9a5amk/WJUJxGIVK6R9icTVX4RgrLsOd8rEk8ph\n6xrJoBtZxuUzm9Vnz6HbNoNrt5YK5OF0A3NlTHKeuW+1eLieN77wLNg2e37zGhs+PIlmFzekz3j9\nZF0uLm+6GsfxxuN85h9fwB+PA04h2VRrC7/58pduGZVS0+Pmt889w6M/fRHJTOBd0L9xA+fu2ll0\nbNPQMI/95Ke4Mln0WTuK2ddRt20e/tXL2C+/AkAyGOTQY5+gf+OGpf8wyxxlEJYhm44cZdeb+wpV\no55ZmT11keniVX/+j76SC0gCfZs20n3hIiAZWLeOQ499gqzXS9br5Z2nPr10H2QZMNnaWlGdNNJU\nmgWV9RlkffO7LXrOnsOTcuo9EnWV0x/daeu6BqGApvHek49z4JOPct9rv2XDhydJ1DdydufHSAXq\nsHWN1sE00QaINvp4+h++hz+euPrdS0nT8AgP/fIl9j3zWbouXsKbcAr9ptrKV5qvBIZXr+aHf/Yd\nus9fwJ3JMNzdzXRzU9Exei7Hp37446L7ZS5msp5C0SgP/+JXvP6FZxmepe90O6IMwjJD2Db3vPV2\niYRA0TFlHrs2EDzz+5vPfo7+TZUzg251plpbGOtcRevAIMasFaNpGBxeYEbU3W+9Xdh5uTIpMv7S\nVpWGaWIaN9BeMo80DA48+Tgn99xP01AWKQTO/0C3JOHxFOHxJFlPiEA8UfRaAXRfuMjX/+PfAc6u\nUGoaw6t7eOPzz5QVwVsJmG43l7Ztrfh8z7nz162anuHae8gwTe753X5e+sbtbRBu/C9VsaR4E8kS\nGeL5YBkGZ3feyWRLC/FggMubNvLDP/vObW0MADTL5sAnn+Loxx5jvLUTSwimG8K8+cxnGV7ds6Bz\nzxaD6/noQzTzGtedbePKpAlEJ2/6PYTtxta0vCmY9TiOS+rD+x/DNEoDpGLWjy4lhmXR3tfPne+8\ne9NjWe74E3G0MoHn+VI/cfPf062C2iEsM7Jezw01YJlBIDm1exexRlW5OYM3kaNlwOl9EAuv4vgD\nq8h5dEZ66pFlMoZulGTwqkLoqt6zpAIhrqzdgrAtpNDwpBJs/WAfx/buYbLj5gK9roxVkvk0GwmM\nrVpDR99H1z2XYZpsPnqco3sXSfdpmTHe3o6t69ctgKtEag5V19sFZRCWGZbLxaWtW1h7+kyRi2M2\nM/PDzJSWcxn0btqkjMFsbEnLYLRoMhXSmWDrx5NEWhd+8x958AE2HTvjyE0gae+/QM/5E8Trm3Bl\n0gSjk5guF9EFfC85j44tqGgUbE0n666cBXUtrmz5JkW3AiPdXUy1NNM4PIJxjVG49vJJit0jOcPg\n+J6SDr63Hcog1AAjm6NxdISsx0M0HEaTEnNWs/MDn3oMbzJJR18/tqbhyuWQUmIaBkIIUsEA0w1h\nWoaGyXi9nL73Xs7evXOOd7z98CXKZ15pEoLTmYUbBClJ1Hdx5t5WR+1USsbbe2gZ6mXLkf0InPTe\naEMD4+03X/SYqPdQP55CygqCewKCkbGyxYTlGJuvbPZKRAhe/b0vcffv3mLDiRO4ciZSCGxd58rq\nHibb2sj4vEy0t3H/q69TPzmFrWlots2JPfcVaiSAQnDeH48x2dpGor6u8vveQgi5CPo21SLUsVHe\n+82/q/UwFsTWQx9wz1v7sTWBkTMRUjqpgi3NvPfEpxjvuHrDhqYi1E9MEGsIo5kW4fEJYg31zjEq\nb3pOAtMZGofjZVfWtoD+zU2lT9wAockUDaOlXcI002TrB2/SMD7ESHcXbz391IKL+Vxpk5bBGEbO\nWfXOvKctIOs1iNfDutOncafS+ONxes5fKJErkTjSI6/8/leY6HAMVP34BHfv309b/yAZr5dTu+5x\n0jhvk7+tuolJPKkUUy0tRRLfgWiUT/7wJwRiMaQQaJZF36aN7H/qyYrFc8udfX/9mQ+klLuud5wy\nCFWk+6Pz7P3lrypmEOVcLn7xh9+4LRUc2/oH2HjsOK5slt5NG7m8ZfONibhJ6RSU5WMDes5i1cVI\n2crjZNDFeNfCVnxd5ybQy7mqpUTPxbmyvpV0YHGruj2JLPUTKTxJE6kL4vUeppv9RfEQzbJ4+Be/\npPPiJZCgWxZSCEa6Onn/0Y8z2ebEMsJj4zz1vRfQc7mC6yRnGFzeupl3Pv1k0edZffYcWw8fwZ1K\nM7B+Lad27yIdWPn+dk8ySff5CwhbMrh+LclQCKTkmf/699RNThUVM5qGwcnd93J070PouRw9584T\njEaZbG3hyto1ZWXCw2NjbDx+Am8yxcC6dfRu3lgzYcL5GgTlMqoiO947MGc6qW6a3HHwEO898XgV\nR1V77nnzd2w5cgQ9Z6IBHb19bHv/MC9/7SvXlRjQTJvG4Tj+uOMiynl0JtsCZPwuYmEvoUi6YBQk\njsFYqLtIN+287lH5lXQgGscfbaZpaApbF0RnNb1fCJmAm9FA5WY14DS1efPZZwhNTtE0MkIqGGSk\nq7Pkve/Z97siYwCOgN7a02c5sWdPQWRuphZiptNd3dQUG06c5Jd/+A1nAl2hbDx2nPte+60zkUvJ\nfa//lhN77mdg/boSmRNwAvJbDh/l8tYtPPHCP6HZFkbOxDQMUqEgL//+V4p2gpsPH2HXm79Dy/e+\n7j5/gR0HDvLS1746Z8OhWqPSTqtIIBqb83lNSlqulDZEv5Wpn5hg6+EjuPLGABxhvvrJSbYcPjrn\na7WcyaoLU/jjuUKKpTtj0dofxZU2ibT6megIkvEa5Fwa8XoPQ2vqMd0L3Pbbcs7+0PFwC6GpFIZp\n485YNA/FaByOL+w9b5BYYwOXt25hpLurrCFqGxgse/NLIWgdGAAgNDnFxhMfFrU91W0bdya9otNX\n6ycmuO/1NzAsC1cuh8s0MSyL7QcP0nG5F1nBcLszGT7x03/Gk07jzubQpMSdyxGMTLPnN68VjvPG\nE+x6Yx/GLMl5Vy5HaGqK7df0DFluqB3CEqLncqz/8CTd5y+Q8XmJ14XwJRIVg342jpbQrUT9+ASb\njh7DH49zZc1qLt6xrWjV3/3ReUSZNEHDNFl/8lRRx7XZ6DmLzgtOymeJqJ+E+okU450hknUeknWL\nK+FguTQn86fck1I6QmyzXQhCIxRJE23yL9wYLRI5txt3mYwjKURBGnxVby/lZL1121nxvvfEUo9y\nadhw/MOy9QpGzqRtYLBI8mI28bo6fInSuJFu23Sfv4BmmtiGQff5C2WNimFZrD95iqOL1e51CVAG\nYQnwx2J0XLrM3fvfwZ1J48qZzCcz2jaM8k3lVyjrT3zInldfL2ybOy9dZsd7B/nVH3xtwYHWpmGn\nOrdSa0Z3enF6QJRDs/OCgyW5jBLNtsv6iTXLJhhJEGldHtkqZ+7eyc53D5QGn4VgcO0awPGbS6EB\npROkNasYzhtPsO7UKfzxBKNdnfRvWH/d1pu1xJtMlm0WJQAjl+XCtq2sO32m6NqYhsHZu3dy57sH\nyp5T4HzHtgGiUkYYVJRJXy4s329tJSIlu1/7LZ9//rs88Mqr+OPxQsxAy//MyErM/NhCkHW5yLrd\nvPPk44yvlLRAKfHGE7jT6bJPu9Jp9rz6esm22R+Pc8/v9heO69u4oezkYRoG57dvK3l8Bm8iN2d6\npelaupW4P5Yt3w9HiIruBkf5NLpkY7pRTt63mytrVmMaBqZhkHW7yHrcvP7F5woGrX/jhrITmGkY\nnLtzBwCrLl3mC8//F+5+623ueP8D9v7yJZ757t9X7Ky3HBhct5ZcmdiUaRgMrF/Hxa1bSu7Rk7t3\nceaeuytO6NMNDYXYwOD6tWWLSy1d5/KWzYv4SRYftUNYRNafPMXG48crFpTNIHAyivY9/RTJujoM\n02SivW3ZaMwIy0JIWTEjor23lwd/7Rg8pGSscxUf7N2LL5UgFQgy3tHOqsu92GWqgXXbZvXZc7z7\npBM4jzY1cWrXPWx9/7DT5hPn2kw3NnL27rvKvr83PndxlcSRs14qNNOuvAK07YrXzhZLt2u5UaSu\n88Zzz9IwOkrr4BXSPh8D69cVufOyXi/7n3qSh176tZM9ZVmYLhcT7W2c2n0vmmnyyIu/KFpJG6ZJ\n3dQUT/3jC/z8W99cljuFvk0b2fHuAeqmpgr3qqVpzjVYt46n//H7hVad4Kzq7zj0Ppe3bOb9jz/M\nrjf2FZ63cWRjjux9iHve/B3dH53Hm0yS9XgQmQzCcuTlc4ZBOuDn+APLu/hNGYQFUj8xwdb3D1M/\nMUF4fByXOT8tFVcuR/eFi5y7ayedFy7SefEivZs3M9XasqTj1SyL1WfP0XPuI3JuF+d37GC0uwtw\nXF0PvPwKnb19ICWmy+Dkrns5/rEHCzd2w+gYj/7kn4tumLb+AZ564b+Rc7kQOJIOp+8p1amfQVyz\nvD7y8F4G1q1j44kTuNOZQn/ecgYyPBynLpKZs/9DrM5NOrB0DVAqdVYDpzYgPDlCtLHV0SCyHanm\nrgunaB28wHtPPMbg+nVLNrYbZaq1lanWyiqovVs2M9rZydozZ/Ck0gyt7ma4pweEoPPCxbKvEUD9\n5CQ73jvAqV27aO/rQ0ib4Z4eR5JbStr7+mkcHSNeX8fA+nVVXQzZus7LX/sq2w8cYMPJUwhbcnnz\nJo4/uIfNR46VjWlplsXWDw7z7pOPEw+H2f7eQYLT00y2tTLW0c4jv/hlIS4x87dpahrTzU2kAwH6\nN6zn/I7tRQWoyxFlEBZA54WLfPzFXxR85DfiHbSFoPnKEOtPnUYzTRCCOw59wOl77ubwxx9ekvHq\nuRxP/LcfEp6YKPS2XXP2HGfuvptjH3uAz/zD94uC3q6cyc53D9A2eIXffPlLIAQ73jtQEnSbOd6d\nz0YJRSJs++AwmlV6Y1maRm+ZvsxjXZ2MdXXOOX53KlfRGMxc+4xHY6ojOOd5FkpltxCYXjfNwx+x\n5uxRxjpWM9KzEVtoDK7bSv+GO1h1sZfh7i6sZT4xzCYVCnJqd2kKu2GaCFk+OiaA7e8dZPuBQ871\nyu8wBteupnF0HG8igW7b2JpGzu3m5a9/lWhj4xJ/kquYHjdHH97L0YeLFW/rJifK7vA1KambdMTv\nrqxdw5W1awDwxeM89/x3ywaiDdumbirCK7//lZIe3suV5befWyEI2+ahl14u8pHfSJa51DTqIhHn\n9eSbhpsmWw4foWVwcEnGvPHYcRrGxwtphBrOpL/18BHuOPQ+nlSqbBvO1v4B2vv6AWeHUC4gNxtN\nSnyJBKd23YNpGNj5CTRnGKT9fg4/fHOy0+HR5JzPT3QEGFkTXvJK26zPQJZ5Cwmk/S5e/70v4I9F\nGOtci+lyYbtcWC43UjcY71hNx+XRJR1fRWxJcCpFa980Lf1RfLHsTQkpzjDc013W6M9gmCauXA53\nNos7l3OycS5cIhCLYeSb/+i2jSed5snv/2BBY1kMhGXRPDxadmFn6nrZ5lFrzpybc9y2rtM8tHJS\nydUO4SZpGB2bt9TutX8utqYRDdfTUEZuVzdNNpw4yVhnhdWylIQi07gyaTovXcYXTzDS003fhvXX\nLavf+OHJkqwScLbD606eqqgSqUlJ54WLDK/uIdrYQN3k5HVXElIIxlet4uXNm9ly5Cj+eJzBtWs4\nv2P7/Dt5SUlgOkN4PIluXsfoCkjUV2cVlgq4MF06rqxVNB4prsYuok1tTiaOKL5StmGg2dWXhhC2\npK13Glf2qnqqN5kjGfIw0RG4KSOa8fk4uXsXOw4cnPdiqFJWmDeVor23j+E1C+9HoJkm3Rcu4o/F\nmGhrY7RMYV45Nh4/4XTYu+ZxiXPPXtqyBU8qVdTC1JXNztmDQUhJZoXsDkAZhJtGatqcxUnXUjxx\niIqTogaEx8d54OVXSIaCnN+xnUR9PQBd5y/wwCuv4k6lCpO3ADZ8eJKddXW8/PWvzj3ZVhivkJLg\nVGTOrmum2/HJn9hzP6su9zpurjnQLIuJ9jaSoRDvfPrmEtbrJlJlG9+XHd91Wl0uKkIw2h0kPJYi\nkM84ynqdCumZzmgjnV1zvL76yQPBSLrIGIAj9OePZYg1eMj6bi7mcuSRvTQPDdHeP1C0c7SFuO5O\n8lq6Ll5csEEIj43zxA9+iGZZ6JaFrWlEmpv4zZe/dF3//cbjJ8oumMAxCJ/53guAZLKllf2feZJo\nUxNDq3vYfuAgWq5UTFHiGM2JFdDjegblMrpJplqayZaZfG2c9LKcy8DS9bKTrG5ZGNlc2dQ3CTSO\njLLpxIfsOHCIZ7/79/ScPUfT0DCP/PyX+BOJwnb7qq8/R93UFHe99facYz6/fRtmmewXAehlxln4\nTLrOpa1Op6rxVR3sf+pJMl4vOZer8BlnYxoGl7dsXpC0gbDlvIzBzPjT82x7uSCkZOuhD/i9/+P/\n5Gt/+3c8+rPv40kN0LepgeE14aJJ9dxd25wCtTJk5ttOcxEJRDNlr6WQ+TTaBfDal77Ah/fvJut2\nOxle4XrO3bmd3A3q9ixYCkNKHvvxT/GkUrizTk9lVy5Hw+gYu97Yd92Xz7XS92Yy6JaFbtk0DQ/z\n1Pd/gCudZmxVB0Oru4vuq5l01YzXy2tffG5FiQWqHcLNIgT7nnmaT/3wJwhpY5gWOcPAMgxe+tpX\nCY+Pc+++t6iLREpfilMAEwvXEx4bL1jlmft1Jqg1E6h66KWXGerpmXNVrts260+d5viDe2geHiE9\nszKZ9cd47q6drDt1hvrJSUdSe9Z4rmXmOVsIDj+8l2jT1YBf75bN9G3aSP3EBJbhIjQ1xa439xGe\nmCTj9XD63ns4sQBteVfapGE0Me8dmA2kQ0vfUH7n2+9yx8FDhQwrfyLB7t++iSub49R9xUHXaHMD\nvsQU3oRZVLVsC4i0Lq7o3XyoXCpF2XjIDZ1b1zny8F6O7H3IUe/VNIxslu6Ll9DicfR5fI+2EPRu\n3rSgcTQPDePOpEvbY+YrhN97/JNzTs6Xtm6hbvLd66aNazhuqQ0fnuT0rnt589ln2HT0OJuPHsWT\nSjHd0MjF7du4eMe2ZZNKPl+UQVgAY52d/PRP/piNx49TPznJeEcHF7bfQXtfPw//6mV00yx7G9o4\nvX4bRseLHq+YSik0moeGr7udM7JZvvh/PY+t6wgpSQUCvPal5wrqqZbLxctf/yprzpxl9dlzhKam\nysYxALJuNyfv28XlrVsLQmdFY9I0Ii1OimysIczP1629zujmhyeRo3UgipDzC9LbgOnWSYaWNmtH\nz+XYfvBQiUvBrtqPzQAAG7pJREFUZZrsfPddTt97d0kMZ6QnTN14irpIGs2SZL06U62O8F61SYQ9\nuEfMUvVXAcnFMqazCvNMt5tf/sHX2fXGPlafPYtuFUt3z+ycJU7m2fEH95CoW1gVt1MkWf6vRjev\nSs1X4sw9d7Pp2An8sVjBJVvJ9eUyTZqGR5zPommcvecuzt5Tvm5mJaEMwgJJBwOcePCBwu/Ctnnw\n17+p6IsEJ7A41LOajt7+efvskqGQU3Jf4XmJEwvQbRtmdhiRCI//4Ef89Nv/olBHYOs6F+9wVi89\n5z7ioV+9XCReBmBpgkvbthZ9rmrRNFK+h8G1OBWkTiA50uJb8m15eHwcKrgUhG3jjydKm6gIQbTF\nT7Sl+juCa4nXe/BHM3hSjlGQ5IPgjT5y3qWZBtKBAPuffor9Tz9F4/AIO995l8bRUWL19Uy0tlI/\nNUXG5+PcXXdWTqK4AcZXdaDZ5Vf3k22t1y2S23bofXzxOMK289dHkPZ68aZSJfedaehEmpsXPObl\nhjIIi0z95CR6BWMggUQoyDuffoL6icl5ZylplsXhRx7i0Z++WOQ2mlllWbqOsO2SlYwGuDNp2vv6\nGSoTrOvfsJ5kKEgwMl1YEUkcnZoPK4jKLSWaZWNkr6/6JIGsR2d4bXWEAF3pNI/8/FcVs7CELcn4\nlnkmiRCMdtfhTeTwx7JIIUjUe8hWI/YCTLa38cZzzy7pe2S9Xk7cfx/bDx4qSMbYOAuwA489Oudr\nw2Nj7DhwqMhdJKR0XKu6XlhkzWBrOud3bF/0z1BrlEFYZEzDqKh3Ymsav/jmN8jmhd2kppX8ocHV\niX52WfzQmjXs+9zTPPDKq06qW15GIBEKMbB+HVs/+ACtTJW0kDgSE2WQmsZLX/squ97Yx9ozZ9Es\ni+Gebg49+olCZlM1mWs7P9vFIDUYX1U9Lf4d7x1wVo5lnjM1jd7Nm5d9BSoAQpAOukkHV8BYb5Lj\nH3uQ6aYmdrx3EH88znh7G0cf+hiT18n0WXv6TNkFmss0mWhpxpdM5ftRS9L+APs+9/SiN0BaDtTE\nIAgh/gb4LJAFLgB/JKUsjb6uQOLhMPH6OuominP1bSEY72gvGIOh1atJBgMEp6fRZ0khmLrO5c2b\nqItEHAmIXfcw2uWkMA5sWM+P1q8jFIlgulykglcrctv7+2m9MlQyHiElE22Vb4asz8c7Tz3JO089\nWfGYaiE1QSrgwneNcN2MeyPj1sgE3MQafFiu6iXIrTt9pmygUQLRxkbefeKTN3fimYXDCspCWQn0\nbtlM7w2KyOmmVbHAzDYMfvTff5vwxAS20Ig2Ntyy31mtdgivAn8ppTSFEH8N/CXwP9ZoLIvOvmc+\ny5Mv/BNaPu0t53KRc7nY/5mnrh4kBL/+6lfY+6uXaBsYxNY0LMPgwGOf4PK2rZVPLkTZFpuHH3mY\nT/7oJ9dI9uoMd3cRaVkhvk4pCxkvs29NCQyvriPnrX4w1qH8zW8ZBmfvueu6Xd2uJTw2zn2v/5a2\n/gGkpnF582YOPfbxooKnamNkLQLTGTRbkg64SAVct+ykV47+jRvYdOx4ST2BaRhc3LYVhLglYwbX\nUhODIKX8zaxf3wO+WItxLBWR5mZ+/O0/Ye2ZM9RNTBJpbeHy5k0lE0c6GODVL38JTzKJK5slUVd3\n0+qQI91d/Pa5Z9n92zcIj09gulycu3MHhx+5OZmIWuBN5kp2B+AYBMOUlJb+VIeL27aw9f3DpbsE\nKelfv/6GzhWYinDHgQ+5vOl+Lm55gJahPro/Os6nh17gxW/9YU2auAciaRpHEoXMrmAkTdZjMNJT\nB2UUa29FRro6GVy3ls6LlwpJFqZhEG0I81Fe6vt2YDnEEL4F/FOlJ4UQfwr8KYCnbmmVQBcT0+Pm\no513zuvYjN+/4IYxAENrVvPzb/3hinVFBKYzZWsPtPxzqRr5vk/suZ/ujy4QiMUcUUAhsHWdw3sf\nIhW6ASE9KWnvjzK4ditSd269odUbGe/o4a79v6Ln/IUF5+LfKJpp0ziSKKlgdmdM6iZTRJtvPT95\nWYRg3+eeZs2Zs2w8dgLdMrm0ZQvn79x+wzvAlcySGQQhxGtAe5mn/kpK+WL+mL8CTOD7lc4jpXwe\neB4g1LFxebcbWi6sMEMww5y1BzUUPst5PPziD7/ButNn6LxwkbTfx0d33nndQOW1+OI5bN1TMAYA\nUtPJudyMdq6nefBK1Q1CpSplTUJwOnP7GAQAIbi8dQuXt26p9UhqxpIZBCnlnJE2IcQ3gaeBx6Rc\n5n3lFFUhUefBF8+W1CHYgkXvi3yj2IbB+R3bF5Rq6E1ksfXSW07qBuPt3ViuxEKGeFPM1dJxubd7\nVCw+NdEyEkI8iRNE/pyUcm5NY8VtQyroIu13MVsM1BaQ8bmWvBK5Gti6RqWuGa5chkt3VG4ZulSk\ngu6yoocS0CxJ82AM1xL2p1YsL2oVQ/hPgAd4VTjujfeklN+p0VgUywUhGOsK4Y9lCUw7PXkT9R7H\nGFTRDeaLZamfSKHnLLJeg+lm/6IUcCXqPdRNpkriJJppMtLdUpMsI8vQKkpSzwjf+WJZxrqCpIO1\n3aUplp5aZRltqMX7KlYAQpCs89TMRRSaSBEeTxbcVnoihzc5zWhXHZkFtuU03Y5EduOI4xqacclM\ntQSItC1tl7dKuNMmUgNRoUB8RlW3+UqcgY3VNcyK6qPkrxWKPMKWRcYAnMlQkxQm8YWSCHsZ6QqR\n9eiYhkYi5CEerl39ga2Jin0yZqPZTq2C4tZmOaSdKhQ1x53K0ThcWXLblbUQtkQuMC/fF8/SPBgr\nZFQZsSz+eJbRrhC2oSGFwHRXrxYh59Edt1HOvq66rCttYtagl4OieqhvV3Hb403kaBmIzq2yKhbe\nNwApaRqKl+xAhIS2/ljh/KZLZ6wzWJ3JVwhGu0K090URlixqvHQtN1s0qVg5qG9YcdvTcE1h1rXY\nQGIRAtszu4xyzLimNOkc194brXjsYmN6DAbWNzDRHpjzuKxvZTV7Udw4aoegqCneeJaGsSSujIVl\naEQbvcQavNULXtoSVwXf+IyonunWmWqbe7KcD3Opuc7G2TVI/NEMiXCVZLU1QTLsJZHIEoiVigum\nAi5sQxmEWx1lEBQ1wxfL0nwlVlidG6ZNeCyJnrOql3UzxxwtgcnWAImwZ1EMlOnSsFwaInt9f/3M\nTqHaTHaE0OwY3kSuoDee8RuMd1ZPblxRO5RBUNSMhtFSV40mIRTJEG3yYxtV8GhKsHSBbsmSVbHl\n0hbNGABOncWqEG19UYSUhc5lUGqXbAHZGgRwpSYY665Dz1q4chamS69qkFtRW5RBUNQGKTFy5ZPf\npRC4MyZpY+mrk+umUmh2+Rb04x3BRXdd5bwGg+vDBKYzuLIWtq6VFKvNtAetZXW25daxlCG47VAG\nQbGk6Dmb8GgCf9wRUUsG3UTaAli6QArKpnkKKbGqsTsAgpFM2YCyFODOWmT9i690KXWNeOPV2oOM\n30XjcBx9VuqnJqHj8jRjXSG1QldUDZVlpFgyhGXTfjlCIJYtZNAEYlnaL0cQtiQe9hTpFoGzOjbd\nOrkquUvmFHerUpZPOuAi0uwDcbUyeCaG0NYXranSq+L2Qu0QFEtGMN+Ba/acL3BE04LTGaZaAhg5\n2wlg5rEMjdGu6gUwk0E3oUimrMsoFaiey6Z+Il2yU3GulXN9qtkHWdiSYCTt6EkJiNd5iIe9t02z\nnNsZZRAUS4Y3kSvrjtGk0x0t1uhjrKsOI2PhzphYhkbGZ1RVL2e62Y8/lkWzZWGstoB4vQfTUz1X\njWFWEBOCirGWJcGWtPVO48pahevhSicJRdJkvQbCskkH3CTr3CoN9RZEGQTFkmG6NCSlGTQSMGfF\nCEyPXtXJdza2oTG0LkxoMo0/nsXSBbEGb9W7s2U9Ot5UeZnprFcHKdFNia2LBctnzEUgmikyBuD4\nlV1ZG1c2iwD8CZPG0SSpgIuJVUFsXXmebxWUQVAsGfEGL8EybTGlcJ5bLti6xnSLn+mW2nUHi7T4\nae0vls+whaM15EqbtA7EEHn3WyLkZrI9uCSGwR8rbVAElLj9AHyJHK19UYbX1CsV1FsEZRAUS0bO\nYzDZHqBxOHF1FpEw0R6oWtB4Ltr6+rnz3feom5piqrmZ4w8+wPiqjpqMJeN3MdYZonEk4biI8mmn\naZ9B42ixAqs/lkU3Y4z21C36OKQmyu7qyiEAd8bCkzQXLA2uWB7U/q5U3NLk3DqpgBt3xiTn1plq\n9VddMTMwPY03mSLS3FRomL721Gke/PVvMEzHTeOPxujo6+fNZz7L4Pp1VR3fDOmgmytBN8KSSA0Q\nglUXpsoW73lSOYyMteiutkTIXbHPciWahmJcWdeggs63AMogKJaMhqE4oXznM4ETHPX2TjPcU0/O\no1NYii6Ru8Efi/Hxf/45DWPj2JqGkJJjD+7h1K57uf+11wvGABw/uWaa7PnNa/zkO39SUxeI1K++\nd8WAsgBX1lx0g2AZN/a5BaCbkkAsS6JedVRb6SiDoFgSgpNJQtOZUt+zDS2DMSerx5LYmiDa6CXa\n5FvcSVhKHv/BDwlFptFm5fHvfPtdkE46Zzm8qST+eJxkaHlo91iGVj4DSToy2Yv+fi69YsFgJVeS\nBvhjGWUQbgFUeoBi8ZGShrFUxV69Rs4uaAfptqR+IkV4NLmo79/WN4A3nkBqGil/EEtzJk+XabLx\n2PGKBWnCluRcy8cfPt3kLVu8l/Po5LyLv56zXDoZn4trTZCdf99yV02S77ymWPGoHYJi0TGy9pxt\nGa+dOhxBuzTTzT7kQlIYpaRuIkXdZBrd8vHep74MmkDYzvTWeek0604fwZ9MMt3YSMPYWNHuwRaC\nke4uct7lkwEVD3vRLedzFdRHfUurPjrWGaRlMIYnZRbeMxlyY+mCuqlMyfEyP07FykcZBMWiY+ti\nXlkqRQhw5WyyCzAI4bEkoal8xa8QSMP585b53cHg2q0goX5qkN997mmefOEHGLkcRi6HaRhkfD72\nP/Xpm37/JUEIppv9RBt9GHkxPMu1tBt7qWuM9tRjZC30nI3p0bE1QddHk2W/V6kLMkug+aSoPsog\nKBYd29BI+114k7l5GwYhi4vVipASfyzrrPxNm7TfYLrZXyT6Jix51RhUHJeLwXVbuehbQ6whzE++\n/S/oPn+BuqkIkeZGBtavX7ZtIqUmilxERiZL65UrmC6DsVWrlmTcpvuq9LUnmXNiPGVcbZolF6Xf\ntKL2KIOgWBLGVwVp649iZKw5+/SC45/OenTCY0k0W5IMuR3p53yQuWjlDwSiWfyxLMOr6wuTpJGz\nCu6NubANg5GensK/e7dsXtDnrAVbPjjMvfvewtY0QGIZLt74/DOMda4qPlDOmqjnEbAXlu3UOFiS\njM8okhGxtfLGoPBWyhbcEiiDoFgSbENjaE097lSO9r5Y2WNmgpSWIZwCp7RjPHzxLKFJnZGeejRb\nUjeVLsp6EfkXN4wmC8VZlqFd1xiAEydYyVIL7b293LPvraKUWbI5Pvmjn/Dj7/xJIf7hn07TMJpE\ntyRSQKLew2RroHytgJSEJtM0jF0N7Evh9KUQtgTNqU+wdQ3tmownCaSCLlWpfIuwcu8MxfJHCLK+\nuX3L001O0FSTV3cRmnQqYEORNN5kruzqUwDe1FWVVNvQSAdKs2NmYwOxsHdFuza2HziEyyzVPBK2\nzdrTZwHwRzM0DScw8plcmoTAdIaWK45hFpZNMJKmfiyJL5qhpT9Kw1iysJObeY1mS6c+w4bAdLaQ\nTTST9WQLR69qor1K7U4VS47aISiWFiFIhFxlG7fPTCzlct41SV4iu7K+kH3NqnS8I0jX+amyOwWJ\nIxIXaa2dXtFiEIiW3225TBN/3HkuPJYsW93sTeTwRTM0D8dBOte9UBtY5pyzH9MALJuJtgAaoOcs\nsl7DEQFUu4NbBrVDUCw5k+1Bch69kMtuA7YGI2vquV4+UjrgolyDS1tAos6NfzqDL5ZxfOW6hjlH\nBk76Fpi8xjpXlRhCgJzLxUR7G1C5ullIaL4SR7Mp7Mg05qdbBHnJjIxFPOxluiVAKrSI/aYVywK1\nQ1AsOVJ34gneZA532sJ0aSSDbtAEyTpKegpDvidBnTOBj3WFaB2IXl3VCie1NRTJEIpczYufavGR\nDHkwJlMlK2QpqLqk9VJwYs99rDlzFi03q6mQppEMBRlYvx5wro1ulW6TFjp12wJMHQKRNP5YFqkJ\n4mEPab+KIdwqqB2CojoIQTrgJl7vQQqBO2OClOQ8hvMYVz09tnBE8eINTt/hjN/FwPpGJtsCRFr8\nRJp8aKYs8nkLoGEshWU4QePZ1b0zDeuzS1DZW21iDQ38+ve/zEhnpxOQ13Uub9nMy1/7qpN6KqUT\nAK7w+gVN2xKCsRyNIwn8iRz+WJaWgRgNI4mFnFWxjFj5d4hiZSAlDSMJQtMZJ0gsncygifYAgWgG\nibM6kTj/SYTcheCvnrMcnf58t676sUTZlYwAwmMprqyrJxjJEIhlsTVBLOwlWbfydwczTLa18euv\nfeVqGmh+de5O5Zy+CVIWZeDOxwjMJXk9c56sR8M9q3mOwNmxBaczxMPeJZHSUFQX9Q0qqkJwKl1o\nljPjHhI5Oz+BXZ2MZlb74YkUibAXbyJL07CzAhUS6ibTc6aXarYEIYg2+4k2r+wA8nWZ5aYRlk1b\nfxTtmq3B9TJxZ3ZmcxmDGePiydjlg8/S6dEwrQzCikd9g4qqUD9Zvok8svJk5I9laRhNFL1uJjNm\nrkmsXND1Vscfy5ad/Rd6JcQ1/6+4tVExBEVVqCQ3PRfudPkew7OarxUhcWIFt2OjFt20y6bvQnGK\n77WHzE45nUddX/nzC24pl9ztjDIIiqqQnaNLWjlTIfLFVJUmOUvLV9Ny9Sfr0ZloDyzCaFceWZ9R\ntoBPAsmgi2iDF1NUrjeY+ZGzXnc9ZgxNrMG7LFqiKhZOTb9FIcRfAH8DtEgpx2s5FsXSEmkt30Q+\n7XNhmBZGzkaTxYHQStJEEkjWe5lq9eNN5DByNjmPXqS9c7uR9rvIeXRcmatBX4ljNCPNfppGEujz\nmOUF+aysoNNKs9KKUeKkBccbvNetRlesHGpmEIQQ3cCngL5ajUFRPTJ+F6NddTSMJnBnLKQmiIU9\nRJr9IBwfeP1YEleuOHA5YxRmHrNx5Jan8x3W0rdAbcGiIAQjPfWERxMEoxmEDWm/wVRrAHfWwp02\nb0h51rCmCUbTJAMh0IunCVtApNlHrOkWD9rfhtRyh/C3wL8FXqzhGBRVJBNwMbw27KRLXrOST9Z5\nCOf1dMphGgJbE6SCbqKNPuxKUtm3MVITTLUHmbpGW6h+orRQby5ybo1Hf/ozdNNitHMtg2u3kgqE\nsHUDpMVkZ1i1y7xFqYlBEEJ8DhiUUh4T19niCyH+FPhTAE9dSxVGp1hyKnzntq5BGdkFKWC62a+6\nct0kUoiyWVnl6hRsAa7sFAC6bdHRf56O/vOF5xOhID/+7769lMNV1JAlMwhCiNeA9jJP/RXw74HH\n53MeKeXzwPMAoY6NN5sIoVgBRBu9NA3Fy65mEyHlGrpZ4mEP/lhpgN6R83DhS5hOL2m3zlSbn64L\nVyr2nHZls1UYsaJWLJlBkFJ+stzjQogdwFpgZnfQBRwWQtwnpRxeqvEolj/JkBt32kvdVNpZvQrn\nP6NdoYX1Wr7NyfgM4mEPwchVo1DokdAWuNoJLb9zG+nuLvShno0NDHV3V3HkimpTdZeRlPIE0Drz\nuxDiMrBLZRkpEIJIa4Boo8/pg6AJUn7XbVlXsKgIwVRbkES9F3/UEQNMhtzF2UGz3HixhjAXt21l\n7ekzhd4LthCYLheHH9lb1aErqotKHlYsO2xDI1mngpaLTdZrzFvg790nH2dsVQfb3j+MJ51muKeb\nYx97gGhj4xKPUlFLam4QpJRraj0GhUJxDUJwfuednN95Z61HoqgiyjGrUCgUCkAZBIVCoVDkUQZB\noVAoFIAyCAqFQqHIowyCQqFQKABlEBQKhUKRRxkEhUKhUADKICgUCoUijzIICoVCoQCUQVAoFApF\nHmUQFAqFQgEog6BQKBSKPMogKBQKhQJQBkGhUCgUeZRBUCgUCgWgDIJCoVAo8iiDoFAoFAoAhJSy\n1mOYN0KIMaC31uOoQDNwu/eFVtfAQV0HdQ1geV2D1VLKlusdtKIMwnJGCPG+lHJXrcdRS9Q1cFDX\nQV0DWJnXQLmMFAqFQgEog6BQKBSKPMogLB7P13oAywB1DRzUdVDXAFbgNVAxBIVCoVAAaoegUCgU\nijzKICgUCoUCUAZhSRBC/IUQQgohmms9lmojhPgbIcQZIcRxIcTPhBDhWo+pWgghnhRCnBVCnBdC\n/Ltaj6faCCG6hRBvCCFOCyFOCiH+vNZjqhVCCF0IcUQI8ctaj+VGUAZhkRFCdAOfAvpqPZYa8Sqw\nXUp5J3AO+Msaj6cqCCF04D8Dnwa2AV8VQmyr7aiqjgn8GynlVmAP8Ge34TWY4c+B07UexI2iDMLi\n87fAvwVuy2i9lPI3Ukoz/+t7QFctx1NF7gPOSykvSimzwA+AZ2o8pqoipRySUh7O/zuGMyF21nZU\n1UcI0QV8BvgvtR7LjaIMwiIihPgcMCilPFbrsSwTvgW8XOtBVIlOoH/W7wPchpPhDEKINcDdwIHa\njqQm/G84i0K71gO5UYxaD2ClIYR4DWgv89RfAf8eeLy6I6o+c10DKeWL+WP+CseF8P1qjq2GiDKP\n3Za7RCFEEPgJ8K+llNFaj6eaCCGeBkallB8IIT5e6/HcKMog3CBSyk+We1wIsQNYCxwTQoDjKjks\nhLhPSjlcxSEuOZWuwQxCiG8CTwOPydun0GUA6J71exdwpUZjqRlCCBeOMfi+lPKntR5PDfgY8Dkh\nxFOAF6gTQnxPSvn1Go9rXqjCtCVCCHEZ2CWlXC5qh1VBCPEk8B+BR6SUY7UeT7UQQhg4QfTHgEHg\nEPD7UsqTNR1YFRHOSuj/AyallP+61uOpNfkdwl9IKZ+u9Vjmi4ohKBab/wSEgFeFEEeFEP93rQdU\nDfKB9H8JvIITTP3h7WQM8nwM+AbwaP67P5pfKStWCGqHoFAoFApA7RAUCoVCkUcZBIVCoVAAyiAo\nFAqFIo8yCAqFQqEAlEFQKBQKRR5lEBSKRUII8WshRGSlKVwqFDMog6BQLB5/g5OHr1CsSJRBUChu\nECHE7ny/B68QIpDX/t8upXwdiNV6fArFzaK0jBSKG0RKeUgI8XPgfwV8wPeklB/WeFgKxYJRBkGh\nuDn+Fxy9ojTwr2o8FoViUVAuI4Xi5mgEgji6Td4aj0WhWBSUQVAobo7ngf8Jp9/DX9d4LArFoqBc\nRgrFDSKE+APAlFK+kO+l/I4Q4lHgfwa2AEEhxADwx1LKV2o5VoXiRlBqpwqFQqEAlMtIoVAoFHmU\nQVAoFAoFoAyCQqFQKPIog6BQKBQKQBkEhUKhUORRBkGhUCgUgDIICoVCocjz/wP12NqcwI1LDAAA\nAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot_decision_boundary(lambda x: plot_logistic(x), x.numpy(), y.numpy())\n", "plt.title('logistic regression')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "可以看到,logistic 回归并不能很好的区分开这个复杂的数据集,如果你还记得前面的内容,你就知道 logistic 回归是一个线性分类器,这个时候就该我们的神经网络登场了!" ] }, { "cell_type": "code", "execution_count": 10, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# 定义两层神经网络的参数\n", "w1 = nn.Parameter(torch.randn(2, 4) * 0.01) # 隐藏层神经元个数 2\n", "b1 = nn.Parameter(torch.zeros(4))\n", "\n", "w2 = nn.Parameter(torch.randn(4, 1) * 0.01)\n", "b2 = nn.Parameter(torch.zeros(1))\n", "\n", "# 定义模型\n", "def two_network(x):\n", " x1 = torch.mm(x, w1) + b1\n", " x1 = F.tanh(x1) # 使用 PyTorch 自带的 tanh 激活函数\n", " x2 = torch.mm(x1, w2) + b2\n", " return x2\n", "\n", "optimizer = torch.optim.SGD([w1, w2, b1, b2], 1.)\n", "\n", "criterion = nn.BCEWithLogitsLoss()" ] }, { "cell_type": "code", "execution_count": 11, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "epoch: 1000, loss: 0.29002276062965393\n", "epoch: 2000, loss: 0.276983380317688\n", "epoch: 3000, loss: 0.26818233728408813\n", "epoch: 4000, loss: 0.2620616555213928\n", "epoch: 5000, loss: 0.2571246325969696\n", "epoch: 6000, loss: 0.23155273497104645\n", "epoch: 7000, loss: 0.2241673469543457\n", "epoch: 8000, loss: 0.220903217792511\n", "epoch: 9000, loss: 0.21872615814208984\n", "epoch: 10000, loss: 0.2170446664094925\n" ] } ], "source": [ "# 我们训练 10000 次\n", "for e in range(10000):\n", " out = two_network(Variable(x))\n", " loss = criterion(out, Variable(y))\n", " optimizer.zero_grad()\n", " loss.backward()\n", " optimizer.step()\n", " if (e + 1) % 1000 == 0:\n", " print('epoch: {}, loss: {}'.format(e+1, loss.data[0]))" ] }, { "cell_type": "code", "execution_count": 12, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def plot_network(x):\n", " x = Variable(torch.from_numpy(x).float())\n", " x1 = torch.mm(x, w1) + b1\n", " x1 = F.tanh(x1)\n", " x2 = torch.mm(x1, w2) + b2\n", " out = F.sigmoid(x2)\n", " out = (out > 0.5) * 1\n", " return out.data.numpy()" ] }, { "cell_type": "code", "execution_count": 13, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Text(0.5,1,'2 layer network')" ] }, "execution_count": 13, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEWCAYAAABmE+CbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nQmCC\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "plot_decision_boundary(lambda x: plot_network(x), x.numpy(), y.numpy())\n", "plt.title('2 layer network')" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "可以看到神经网络能够非常好地分类这个复杂的数据,和前面的 logistic 回归相比,神经网络因为有了激活函数的存在,成了一个非线性分类器,所以神经网络分类的边界更加复杂。" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Sequential 和 Module" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "我们讲了数据处理,模型构建,loss 函数设计等等内容,但是目前为止我们还没有准备好构建一个完整的机器学习系统,一个完整的机器学习系统需要我们不断地读写模型。在现实应用中,一般我们会将模型在本地进行训练,然后保存模型,接着我们会将模型部署到不同的地方进行应用,所以在这节课我们会教大家如何保存 PyTorch 的模型。\n", "\n", "首先我们会讲一下 PyTorch 中的模块,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,我们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,我们下面分别用 Sequential 和 Module 来定义上面的神经网络。" ] }, { "cell_type": "code", "execution_count": 14, "metadata": { "collapsed": true }, "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": 15, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Linear(in_features=2, out_features=4)" ] }, "execution_count": 15, "metadata": {}, "output_type": "execute_result" } ], "source": [ "# 序列模块可以通过索引访问每一层\n", "\n", "seq_net[0] # 第一层" ] }, { "cell_type": "code", "execution_count": 16, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Parameter containing:\n", "-0.4964 0.3581\n", "-0.0705 0.4262\n", " 0.0601 0.1988\n", " 0.6683 -0.4470\n", "[torch.FloatTensor of size 4x2]\n", "\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": 17, "metadata": {}, "outputs": [], "source": [ "# 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, 1.)" ] }, { "cell_type": "code", "execution_count": 18, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "epoch: 1000, loss: 0.2839296758174896\n", "epoch: 2000, loss: 0.2716798782348633\n", "epoch: 3000, loss: 0.2647360861301422\n", "epoch: 4000, loss: 0.26001378893852234\n", "epoch: 5000, loss: 0.2566395103931427\n", "epoch: 6000, loss: 0.2541380524635315\n", "epoch: 7000, loss: 0.25222381949424744\n", "epoch: 8000, loss: 0.2507193386554718\n", "epoch: 9000, loss: 0.24951006472110748\n", "epoch: 10000, loss: 0.2485194206237793\n" ] } ], "source": [ "# 我们训练 10000 次\n", "for e in range(10000):\n", " out = seq_net(Variable(x))\n", " loss = criterion(out, Variable(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.data[0]))" ] }, { "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": 19, "metadata": { "collapsed": true }, "outputs": [], "source": [ "def plot_seq(x):\n", " out = F.sigmoid(seq_net(Variable(torch.from_numpy(x).float()))).data.numpy()\n", " out = (out > 0.5) * 1\n", " return out" ] }, { "cell_type": "code", "execution_count": 20, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 20, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEWCAYAAABmE+CbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\nkgAAAABJRU5ErkJggg==\n", "text/plain": [ "" ] }, "metadata": {}, "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": [ "最后我们讲一讲如何保存模型,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,下面我们一一介绍。" ] }, { "cell_type": "code", "execution_count": 21, "metadata": { "collapsed": true }, "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": 22, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# 读取保存的模型\n", "seq_net1 = torch.load('save_seq_net.pth')" ] }, { "cell_type": "code", "execution_count": 23, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Sequential(\n", " (0): Linear(in_features=2, out_features=4)\n", " (1): Tanh()\n", " (2): Linear(in_features=4, out_features=1)\n", ")" ] }, "execution_count": 23, "metadata": {}, "output_type": "execute_result" } ], "source": [ "seq_net1" ] }, { "cell_type": "code", "execution_count": 28, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Parameter containing:\n", " -0.5532 -1.9916\n", " 0.0446 7.9446\n", " 10.3188 -12.9290\n", " 10.0688 11.7754\n", "[torch.FloatTensor of size 4x2]\n", "\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": 24, "metadata": { "collapsed": true }, "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": 26, "metadata": {}, "outputs": [], "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": 27, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "Sequential(\n", " (0): Linear(in_features=2, out_features=4)\n", " (1): Tanh()\n", " (2): Linear(in_features=4, out_features=1)\n", ")" ] }, "execution_count": 27, "metadata": {}, "output_type": "execute_result" } ], "source": [ "seq_net2" ] }, { "cell_type": "code", "execution_count": 29, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Parameter containing:\n", " -0.5532 -1.9916\n", " 0.0446 7.9446\n", " 10.3188 -12.9290\n", " 10.0688 11.7754\n", "[torch.FloatTensor of size 4x2]\n", "\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": [ "\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "下面我们再用 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": 30, "metadata": { "collapsed": true }, "outputs": [], "source": [ "class module_net(nn.Module):\n", " def __init__(self, num_input, num_hidden, num_output):\n", " super(module_net, 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": 31, "metadata": {}, "outputs": [], "source": [ "mo_net = module_net(2, 4, 1)" ] }, { "cell_type": "code", "execution_count": 32, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Linear(in_features=2, out_features=4)\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": 33, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Parameter containing:\n", " 0.1492 0.4150\n", " 0.3403 -0.4084\n", "-0.3114 -0.0584\n", " 0.5668 0.2063\n", "[torch.FloatTensor of size 4x2]\n", "\n" ] } ], "source": [ "# 打印出第一层的权重\n", "print(l1.weight)" ] }, { "cell_type": "code", "execution_count": 34, "metadata": { "collapsed": true }, "outputs": [], "source": [ "# 定义优化器\n", "optim = torch.optim.SGD(mo_net.parameters(), 1.)" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "epoch: 1000, loss: 0.2618132531642914\n", "epoch: 2000, loss: 0.2421271800994873\n", "epoch: 3000, loss: 0.23346386849880219\n", "epoch: 4000, loss: 0.22809192538261414\n", "epoch: 5000, loss: 0.224302738904953\n", "epoch: 6000, loss: 0.2214415818452835\n", "epoch: 7000, loss: 0.21918588876724243\n", "epoch: 8000, loss: 0.21736061573028564\n", "epoch: 9000, loss: 0.21585838496685028\n", "epoch: 10000, loss: 0.21460506319999695\n" ] } ], "source": [ "# 我们训练 10000 次\n", "for e in range(10000):\n", " out = mo_net(Variable(x))\n", " loss = criterion(out, Variable(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.data[0]))" ] }, { "cell_type": "code", "execution_count": 36, "metadata": { "collapsed": true }, "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": [ "**小练习: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**" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "下面举个例子" ] }, { "cell_type": "code", "execution_count": 103, "metadata": { "collapsed": true }, "outputs": [], "source": [ "net = nn.Sequential(\n", " nn.Linear(2, 10),\n", " nn.Tanh(),\n", " nn.Linear(10, 10),\n", " nn.Tanh(),\n", " nn.Linear(10, 10),\n", " nn.Tanh(),\n", " nn.Linear(10, 1)\n", ")\n", "\n", "optim = torch.optim.SGD(net.parameters(), 0.1)" ] }, { "cell_type": "code", "execution_count": 104, "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "epoch: 1000, loss: 0.3165791928768158\n", "epoch: 2000, loss: 0.25367119908332825\n", "epoch: 3000, loss: 0.22129501402378082\n", "epoch: 4000, loss: 0.20364265143871307\n", "epoch: 5000, loss: 0.19186729192733765\n", "epoch: 6000, loss: 0.18199527263641357\n", "epoch: 7000, loss: 0.173702672123909\n", "epoch: 8000, loss: 0.16727975010871887\n", "epoch: 9000, loss: 0.16238373517990112\n", "epoch: 10000, loss: 0.15855807065963745\n", "epoch: 11000, loss: 0.15542374551296234\n", "epoch: 12000, loss: 0.1527201235294342\n", "epoch: 13000, loss: 0.15030623972415924\n", "epoch: 14000, loss: 0.14812862873077393\n", "epoch: 15000, loss: 0.1461697667837143\n", "epoch: 16000, loss: 0.14440736174583435\n", "epoch: 17000, loss: 0.14280635118484497\n", "epoch: 18000, loss: 0.1413293182849884\n", "epoch: 19000, loss: 0.13908402621746063\n", "epoch: 20000, loss: 0.13768813014030457\n" ] } ], "source": [ "# 我们训练 20000 次\n", "for e in range(20000):\n", " out = net(Variable(x))\n", " loss = criterion(out, Variable(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.data[0]))" ] }, { "cell_type": "code", "execution_count": 105, "metadata": {}, "outputs": [ { "data": { "text/plain": [ "" ] }, "execution_count": 105, "metadata": {}, "output_type": "execute_result" }, { "data": { "image/png": "iVBORw0KGgoAAAANSUhEUgAAAYQAAAEWCAYAAABmE+CbAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\noVAoGvz/dG9A+o7Owg0AAAAASUVORK5CYII=\n", "text/plain": [ "" ] }, "metadata": {}, "output_type": "display_data" } ], "source": [ "def plot_net(x):\n", " out = F.sigmoid(net(Variable(torch.from_numpy(x).float()))).data.numpy()\n", " out = (out > 0.5) * 1\n", " return out\n", "\n", "plot_decision_boundary(lambda x: plot_net(x), x.numpy(), y.numpy())\n", "plt.title('sequential')" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.5.2" } }, "nbformat": 4, "nbformat_minor": 2 }