{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# DCGAN for MNIST (PyTorch)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"arXiv: https://arxiv.org/abs/1511.06434\n",
"\n",
"\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Deep Convolution GANに以下の改善を行う。\n",
"- すべてのプーリングレイヤを strided convolutions(discriminator)と fractional-stirided convolutions(generator)に変更する。\n",
"- generator と discriminator に batchnormを使う。\n",
"- 全結合隠れ層を取り除く。\n",
"- ReLU 活性関数を generatorで使う。ただし、output層は tanhを使う。\n",
"- LeakyReLU活性関数をdiscriminatorのすべての層で使う。\n",
"\n",
"もとい!\n",
"\n",
"公式チュートリアルにサンプルコードが公開されているので、それを参考に実装する。\n",
"- [examples/dcgan at master · pytorch/examples](https://github.com/pytorch/examples/tree/master/dcgan)"
]
},
{
"cell_type": "code",
"execution_count": 45,
"metadata": {},
"outputs": [],
"source": [
"% matplotlib inline\n",
"import torch\n",
"import torch.optim as optim\n",
"import torch.nn as nn\n",
"import torch.nn.functional as F\n",
"from torch.autograd import Variable\n",
"\n",
"if torch.cuda.is_available():\n",
" import torch.cuda as t\n",
"else:\n",
" import torch as t\n",
"\n",
"from torchvision import datasets, models, transforms, utils\n",
"import torchvision.utils as vutils\n",
"\n",
"import numpy as np\n",
"from numpy.random import normal\n",
"import matplotlib.pyplot as plt\n",
"import os"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## mnist datasetの準備"
]
},
{
"cell_type": "code",
"execution_count": 207,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"bs = 100\n",
"sz = 32"
]
},
{
"cell_type": "code",
"execution_count": 208,
"metadata": {},
"outputs": [],
"source": [
"dataloader = torch.utils.data.DataLoader(\n",
" datasets.MNIST('data/mnist', train=True, download=True,\n",
" transform=transforms.Compose([\n",
" transforms.Scale(sz),\n",
" transforms.ToTensor(),\n",
" transforms.Normalize(mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5))\n",
" ])),\n",
" batch_size=bs\n",
")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Model"
]
},
{
"cell_type": "code",
"execution_count": 246,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"nz = 100\n",
"ngf = 32\n",
"ndf = 32\n",
"nc = 1"
]
},
{
"cell_type": "code",
"execution_count": 263,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"'''Discriminater'''\n",
"class netD(nn.Module):\n",
" def __init__(self):\n",
" super(netD, self).__init__()\n",
" self.main = nn.Sequential(\n",
" nn.Conv2d(nc, ndf, 4, 2, 1, bias=False),\n",
" nn.LeakyReLU(0.2, inplace=True),\n",
" nn.Conv2d(ndf, ndf * 2, 4, 2, 1, bias=False),\n",
" nn.BatchNorm2d(ndf * 2),\n",
" nn.LeakyReLU(0.2, inplace=True),\n",
" nn.Conv2d(ndf * 2, ndf * 4, 4, 2, 1, bias=False),\n",
" nn.BatchNorm2d(ndf * 4),\n",
" nn.LeakyReLU(0.2, inplace=True),\n",
" nn.Conv2d(ndf * 4, 1, 4, 1, 0, bias=False),\n",
" nn.Sigmoid()\n",
" )\n",
"\n",
" def forward(self, x):\n",
" #x = x.view(100, -1)\n",
" x = self.main(x)\n",
" return x\n",
"\n",
"'''Generator'''\n",
"class netG(nn.Module):\n",
" def __init__(self):\n",
" super(netG, self).__init__()\n",
" self.main = nn.Sequential(\n",
" nn.ConvTranspose2d(nz, ngf * 4, 4, 1, 0, bias=False),\n",
" nn.BatchNorm2d(ngf * 4),\n",
" nn.ReLU(True),\n",
" nn.ConvTranspose2d(ngf * 4, ngf * 2, 4, 2, 1, bias=False),\n",
" nn.BatchNorm2d(ngf * 2),\n",
" nn.ReLU(True),\n",
" nn.ConvTranspose2d(ngf * 2, ngf, 4, 2, 1, bias=False),\n",
" nn.BatchNorm2d(ngf),\n",
" nn.ReLU(True),\n",
" nn.ConvTranspose2d( ngf,nc, 4, 2, 1, bias=False),\n",
" nn.Tanh()\n",
" )\n",
"\n",
" def forward(self, x):\n",
" # x = x.view(bs,100)\n",
" x = self.main(x)\n",
" x = x.view(-1, 1, sz, sz)\n",
" return x"
]
},
{
"cell_type": "code",
"execution_count": 264,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"criteion = nn.BCELoss()\n",
"net_D = netD()\n",
"net_G = netG()\n",
"\n",
"if torch.cuda.is_available():\n",
" D = net_D.cuda()\n",
" G = net_G.cuda()\n",
" criteion = criteion.cuda() "
]
},
{
"cell_type": "code",
"execution_count": 265,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"netD (\n",
" (main): Sequential (\n",
" (0): Conv2d(1, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
" (1): LeakyReLU (0.2, inplace)\n",
" (2): Conv2d(32, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
" (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)\n",
" (4): LeakyReLU (0.2, inplace)\n",
" (5): Conv2d(64, 128, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
" (6): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)\n",
" (7): LeakyReLU (0.2, inplace)\n",
" (8): Conv2d(128, 1, kernel_size=(4, 4), stride=(1, 1), bias=False)\n",
" (9): Sigmoid ()\n",
" )\n",
")\n"
]
}
],
"source": [
"print(net_D)"
]
},
{
"cell_type": "code",
"execution_count": 266,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"netG (\n",
" (main): Sequential (\n",
" (0): ConvTranspose2d(100, 128, kernel_size=(4, 4), stride=(1, 1), bias=False)\n",
" (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True)\n",
" (2): ReLU (inplace)\n",
" (3): ConvTranspose2d(128, 64, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
" (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True)\n",
" (5): ReLU (inplace)\n",
" (6): ConvTranspose2d(64, 32, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
" (7): BatchNorm2d(32, eps=1e-05, momentum=0.1, affine=True)\n",
" (8): ReLU (inplace)\n",
" (9): ConvTranspose2d(32, 1, kernel_size=(4, 4), stride=(2, 2), padding=(1, 1), bias=False)\n",
" (10): Tanh ()\n",
" )\n",
")\n"
]
}
],
"source": [
"print(net_G)"
]
},
{
"cell_type": "code",
"execution_count": 267,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"optimizerD = optim.Adam(net_D.parameters(), lr = 0.00005)\n",
"optimizerG = optim.Adam(net_G.parameters(), lr = 0.00005)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Train"
]
},
{
"cell_type": "code",
"execution_count": 268,
"metadata": {},
"outputs": [],
"source": [
"input = t.FloatTensor(bs, 1, sz, sz)\n",
"noise = t.FloatTensor(normal(0, 1,(bs, 100, 1, 1)))\n",
"fixed_noise = t.FloatTensor(bs, 100, 1, 1).normal_(0, 1)\n",
"label = t.FloatTensor(bs)\n",
"\n",
"real_label = 1\n",
"fake_label = 0\n",
"\n",
"input = Variable(input)\n",
"label = Variable(label)\n",
"noise = Variable(noise)\n",
"fixed_noise = Variable(fixed_noise)"
]
},
{
"cell_type": "code",
"execution_count": 269,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"niter = 4000"
]
},
{
"cell_type": "code",
"execution_count": 270,
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[0/4000][0/600] Loss_D: 1.4583 Loss_G: 0.6733 D(x): 0.4899 D(G(z)): 0.5208 / 0.5122\n",
"[0/4000][100/600] Loss_D: 0.8505 Loss_G: 1.0397 D(x): 0.7121 D(G(z)): 0.3881 / 0.3562\n",
"[0/4000][200/600] Loss_D: 0.7463 Loss_G: 1.4093 D(x): 0.6796 D(G(z)): 0.2835 / 0.2488\n",
"[0/4000][300/600] Loss_D: 0.4877 Loss_G: 1.7799 D(x): 0.7802 D(G(z)): 0.2050 / 0.1744\n",
"[0/4000][400/600] Loss_D: 0.2743 Loss_G: 2.1677 D(x): 0.8965 D(G(z)): 0.1476 / 0.1226\n",
"[0/4000][500/600] Loss_D: 0.2653 Loss_G: 2.4174 D(x): 0.8809 D(G(z)): 0.1229 / 0.0918\n",
"[1/4000][0/600] Loss_D: 0.3351 Loss_G: 2.3313 D(x): 0.8596 D(G(z)): 0.1513 / 0.1084\n",
"[1/4000][100/600] Loss_D: 0.1897 Loss_G: 2.5091 D(x): 0.9367 D(G(z)): 0.1142 / 0.0856\n",
"[1/4000][200/600] Loss_D: 0.1651 Loss_G: 3.0968 D(x): 0.9173 D(G(z)): 0.0717 / 0.0505\n",
"[1/4000][300/600] Loss_D: 0.1211 Loss_G: 3.2050 D(x): 0.9333 D(G(z)): 0.0482 / 0.0489\n",
"[1/4000][400/600] Loss_D: 0.0623 Loss_G: 3.7729 D(x): 0.9775 D(G(z)): 0.0377 / 0.0286\n",
"[1/4000][500/600] Loss_D: 0.0437 Loss_G: 4.2053 D(x): 0.9774 D(G(z)): 0.0203 / 0.0169\n",
"[2/4000][0/600] Loss_D: 0.0459 Loss_G: 5.1992 D(x): 0.9650 D(G(z)): 0.0093 / 0.0063\n",
"[2/4000][100/600] Loss_D: 0.0269 Loss_G: 4.5801 D(x): 0.9886 D(G(z)): 0.0151 / 0.0134\n",
"[2/4000][200/600] Loss_D: 0.0290 Loss_G: 4.7458 D(x): 0.9847 D(G(z)): 0.0132 / 0.0110\n",
"[2/4000][300/600] Loss_D: 0.0333 Loss_G: 4.4435 D(x): 0.9858 D(G(z)): 0.0186 / 0.0139\n",
"[2/4000][400/600] Loss_D: 0.0148 Loss_G: 5.9011 D(x): 0.9900 D(G(z)): 0.0047 / 0.0037\n",
"[2/4000][500/600] Loss_D: 0.0576 Loss_G: 4.2954 D(x): 0.9596 D(G(z)): 0.0144 / 0.0174\n",
"[3/4000][0/600] Loss_D: 0.0207 Loss_G: 4.9039 D(x): 0.9907 D(G(z)): 0.0111 / 0.0091\n",
"[3/4000][100/600] Loss_D: 0.0168 Loss_G: 5.0898 D(x): 0.9933 D(G(z)): 0.0100 / 0.0080\n",
"[3/4000][200/600] Loss_D: 0.0184 Loss_G: 5.3518 D(x): 0.9884 D(G(z)): 0.0063 / 0.0059\n",
"[3/4000][300/600] Loss_D: 0.0375 Loss_G: 4.2995 D(x): 0.9820 D(G(z)): 0.0171 / 0.0172\n",
"[3/4000][400/600] Loss_D: 0.0247 Loss_G: 4.5011 D(x): 0.9957 D(G(z)): 0.0200 / 0.0136\n",
"[3/4000][500/600] Loss_D: 0.0480 Loss_G: 4.9786 D(x): 0.9663 D(G(z)): 0.0113 / 0.0095\n",
"[4/4000][0/600] Loss_D: 0.0281 Loss_G: 4.7039 D(x): 0.9857 D(G(z)): 0.0129 / 0.0124\n",
"[4/4000][100/600] Loss_D: 0.0160 Loss_G: 5.3887 D(x): 0.9950 D(G(z)): 0.0109 / 0.0056\n",
"[4/4000][200/600] Loss_D: 0.0120 Loss_G: 5.2138 D(x): 0.9962 D(G(z)): 0.0081 / 0.0074\n",
"[4/4000][300/600] Loss_D: 0.0267 Loss_G: 5.4105 D(x): 0.9807 D(G(z)): 0.0061 / 0.0061\n",
"[4/4000][400/600] Loss_D: 0.0314 Loss_G: 4.5322 D(x): 0.9854 D(G(z)): 0.0159 / 0.0145\n",
"[4/4000][500/600] Loss_D: 0.0316 Loss_G: 4.9962 D(x): 0.9869 D(G(z)): 0.0178 / 0.0099\n",
"[5/4000][0/600] Loss_D: 0.0157 Loss_G: 5.4832 D(x): 0.9948 D(G(z)): 0.0103 / 0.0051\n",
"[5/4000][100/600] Loss_D: 0.0111 Loss_G: 5.5713 D(x): 0.9966 D(G(z)): 0.0076 / 0.0053\n",
"[5/4000][200/600] Loss_D: 0.0496 Loss_G: 7.2147 D(x): 0.9660 D(G(z)): 0.0011 / 0.0010\n",
"[5/4000][300/600] Loss_D: 0.0163 Loss_G: 6.0031 D(x): 0.9882 D(G(z)): 0.0039 / 0.0035\n",
"[5/4000][400/600] Loss_D: 0.0257 Loss_G: 5.1657 D(x): 0.9892 D(G(z)): 0.0143 / 0.0076\n",
"[5/4000][500/600] Loss_D: 0.0170 Loss_G: 4.9780 D(x): 0.9918 D(G(z)): 0.0084 / 0.0106\n",
"[6/4000][0/600] Loss_D: 0.0147 Loss_G: 5.3444 D(x): 0.9931 D(G(z)): 0.0075 / 0.0069\n",
"[6/4000][100/600] Loss_D: 0.0085 Loss_G: 6.4237 D(x): 0.9955 D(G(z)): 0.0035 / 0.0024\n",
"[6/4000][200/600] Loss_D: 0.0083 Loss_G: 5.8357 D(x): 0.9984 D(G(z)): 0.0066 / 0.0043\n",
"[6/4000][300/600] Loss_D: 0.0302 Loss_G: 6.3633 D(x): 0.9740 D(G(z)): 0.0013 / 0.0023\n",
"[6/4000][400/600] Loss_D: 0.0168 Loss_G: 5.3458 D(x): 0.9918 D(G(z)): 0.0072 / 0.0062\n",
"[6/4000][500/600] Loss_D: 0.0123 Loss_G: 5.5281 D(x): 0.9934 D(G(z)): 0.0056 / 0.0050\n",
"[7/4000][0/600] Loss_D: 0.0195 Loss_G: 4.1918 D(x): 0.9977 D(G(z)): 0.0169 / 0.0198\n",
"[7/4000][100/600] Loss_D: 0.0139 Loss_G: 6.9196 D(x): 0.9890 D(G(z)): 0.0021 / 0.0014\n",
"[7/4000][200/600] Loss_D: 0.0076 Loss_G: 5.8415 D(x): 0.9980 D(G(z)): 0.0055 / 0.0045\n",
"[7/4000][300/600] Loss_D: 0.0112 Loss_G: 6.0420 D(x): 0.9913 D(G(z)): 0.0023 / 0.0028\n",
"[7/4000][400/600] Loss_D: 0.0084 Loss_G: 6.7065 D(x): 0.9955 D(G(z)): 0.0038 / 0.0017\n",
"[7/4000][500/600] Loss_D: 0.0160 Loss_G: 5.0663 D(x): 0.9928 D(G(z)): 0.0083 / 0.0091\n",
"[8/4000][0/600] Loss_D: 0.0234 Loss_G: 6.2596 D(x): 0.9807 D(G(z)): 0.0025 / 0.0034\n",
"[8/4000][100/600] Loss_D: 0.0208 Loss_G: 4.9983 D(x): 0.9884 D(G(z)): 0.0083 / 0.0095\n",
"[8/4000][200/600] Loss_D: 0.0070 Loss_G: 5.8495 D(x): 0.9993 D(G(z)): 0.0063 / 0.0039\n",
"[8/4000][300/600] Loss_D: 0.0451 Loss_G: 4.0558 D(x): 0.9906 D(G(z)): 0.0341 / 0.0239\n",
"[8/4000][400/600] Loss_D: 0.0500 Loss_G: 4.2978 D(x): 0.9896 D(G(z)): 0.0376 / 0.0190\n",
"[8/4000][500/600] Loss_D: 0.0104 Loss_G: 5.6674 D(x): 0.9966 D(G(z)): 0.0068 / 0.0059\n",
"[9/4000][0/600] Loss_D: 0.0132 Loss_G: 6.7846 D(x): 0.9893 D(G(z)): 0.0018 / 0.0016\n",
"[9/4000][100/600] Loss_D: 0.0064 Loss_G: 6.7528 D(x): 0.9965 D(G(z)): 0.0028 / 0.0017\n",
"[9/4000][200/600] Loss_D: 0.0035 Loss_G: 7.1330 D(x): 0.9991 D(G(z)): 0.0025 / 0.0010\n",
"[9/4000][300/600] Loss_D: 0.0281 Loss_G: 6.4849 D(x): 0.9753 D(G(z)): 0.0010 / 0.0019\n",
"[9/4000][400/600] Loss_D: 0.0322 Loss_G: 4.5061 D(x): 0.9872 D(G(z)): 0.0185 / 0.0144\n",
"[9/4000][500/600] Loss_D: 0.0330 Loss_G: 6.4354 D(x): 0.9729 D(G(z)): 0.0028 / 0.0021\n",
"[10/4000][0/600] Loss_D: 0.0234 Loss_G: 3.9369 D(x): 0.9966 D(G(z)): 0.0197 / 0.0225\n",
"[10/4000][100/600] Loss_D: 0.0333 Loss_G: 5.5747 D(x): 0.9722 D(G(z)): 0.0029 / 0.0045\n",
"[10/4000][200/600] Loss_D: 0.0190 Loss_G: 4.6906 D(x): 0.9993 D(G(z)): 0.0180 / 0.0122\n",
"[10/4000][300/600] Loss_D: 0.0319 Loss_G: 4.9564 D(x): 0.9848 D(G(z)): 0.0125 / 0.0098\n",
"[10/4000][400/600] Loss_D: 0.0400 Loss_G: 3.7710 D(x): 0.9901 D(G(z)): 0.0270 / 0.0260\n",
"[10/4000][500/600] Loss_D: 0.0292 Loss_G: 5.3283 D(x): 0.9807 D(G(z)): 0.0060 / 0.0058\n",
"[11/4000][0/600] Loss_D: 0.0398 Loss_G: 3.8591 D(x): 0.9935 D(G(z)): 0.0321 / 0.0282\n",
"[11/4000][100/600] Loss_D: 0.0221 Loss_G: 5.4589 D(x): 0.9849 D(G(z)): 0.0058 / 0.0049\n",
"[11/4000][200/600] Loss_D: 0.0180 Loss_G: 5.8926 D(x): 0.9878 D(G(z)): 0.0040 / 0.0040\n",
"[11/4000][300/600] Loss_D: 0.0141 Loss_G: 5.6494 D(x): 0.9903 D(G(z)): 0.0040 / 0.0045\n",
"[11/4000][400/600] Loss_D: 0.0296 Loss_G: 4.7325 D(x): 0.9823 D(G(z)): 0.0107 / 0.0121\n",
"[11/4000][500/600] Loss_D: 0.0167 Loss_G: 4.8233 D(x): 0.9937 D(G(z)): 0.0100 / 0.0098\n",
"[12/4000][0/600] Loss_D: 0.0188 Loss_G: 4.0977 D(x): 0.9964 D(G(z)): 0.0149 / 0.0213\n",
"[12/4000][100/600] Loss_D: 0.0353 Loss_G: 5.8658 D(x): 0.9712 D(G(z)): 0.0025 / 0.0041\n",
"[12/4000][200/600] Loss_D: 0.0133 Loss_G: 4.8877 D(x): 0.9991 D(G(z)): 0.0123 / 0.0091\n",
"[12/4000][300/600] Loss_D: 0.0351 Loss_G: 3.5154 D(x): 0.9908 D(G(z)): 0.0250 / 0.0394\n",
"[12/4000][400/600] Loss_D: 0.0246 Loss_G: 4.4346 D(x): 0.9955 D(G(z)): 0.0197 / 0.0145\n",
"[12/4000][500/600] Loss_D: 0.0230 Loss_G: 6.3850 D(x): 0.9887 D(G(z)): 0.0100 / 0.0023\n",
"[13/4000][0/600] Loss_D: 0.0183 Loss_G: 6.4122 D(x): 0.9862 D(G(z)): 0.0033 / 0.0021\n",
"[13/4000][100/600] Loss_D: 0.0346 Loss_G: 7.1310 D(x): 0.9696 D(G(z)): 0.0010 / 0.0010\n",
"[13/4000][200/600] Loss_D: 0.0207 Loss_G: 5.4381 D(x): 0.9912 D(G(z)): 0.0104 / 0.0054\n",
"[13/4000][300/600] Loss_D: 0.0244 Loss_G: 6.1792 D(x): 0.9798 D(G(z)): 0.0034 / 0.0033\n",
"[13/4000][400/600] Loss_D: 0.0052 Loss_G: 6.2734 D(x): 0.9986 D(G(z)): 0.0037 / 0.0024\n",
"[13/4000][500/600] Loss_D: 0.0405 Loss_G: 5.2515 D(x): 0.9736 D(G(z)): 0.0038 / 0.0070\n",
"[14/4000][0/600] Loss_D: 0.0437 Loss_G: 3.6655 D(x): 0.9936 D(G(z)): 0.0351 / 0.0417\n",
"[14/4000][100/600] Loss_D: 0.0170 Loss_G: 7.8187 D(x): 0.9856 D(G(z)): 0.0008 / 0.0006\n",
"[14/4000][200/600] Loss_D: 0.0207 Loss_G: 5.9847 D(x): 0.9874 D(G(z)): 0.0065 / 0.0033\n",
"[14/4000][300/600] Loss_D: 0.0251 Loss_G: 5.0931 D(x): 0.9844 D(G(z)): 0.0079 / 0.0103\n",
"[14/4000][400/600] Loss_D: 0.0294 Loss_G: 4.3311 D(x): 0.9894 D(G(z)): 0.0170 / 0.0167\n",
"[14/4000][500/600] Loss_D: 0.0527 Loss_G: 4.3634 D(x): 0.9655 D(G(z)): 0.0107 / 0.0159\n",
"[15/4000][0/600] Loss_D: 0.0182 Loss_G: 4.5039 D(x): 0.9928 D(G(z)): 0.0103 / 0.0130\n",
"[15/4000][100/600] Loss_D: 0.0152 Loss_G: 5.0779 D(x): 0.9979 D(G(z)): 0.0129 / 0.0091\n",
"[15/4000][200/600] Loss_D: 0.0089 Loss_G: 5.9251 D(x): 0.9948 D(G(z)): 0.0035 / 0.0037\n",
"[15/4000][300/600] Loss_D: 0.0150 Loss_G: 5.8004 D(x): 0.9885 D(G(z)): 0.0030 / 0.0036\n",
"[15/4000][400/600] Loss_D: 0.0481 Loss_G: 4.1151 D(x): 0.9982 D(G(z)): 0.0444 / 0.0214\n",
"[15/4000][500/600] Loss_D: 0.0374 Loss_G: 3.8988 D(x): 0.9921 D(G(z)): 0.0286 / 0.0263\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[16/4000][0/600] Loss_D: 0.0167 Loss_G: 5.8045 D(x): 0.9914 D(G(z)): 0.0077 / 0.0036\n",
"[16/4000][100/600] Loss_D: 0.0135 Loss_G: 6.2537 D(x): 0.9913 D(G(z)): 0.0038 / 0.0024\n",
"[16/4000][200/600] Loss_D: 0.0278 Loss_G: 4.4945 D(x): 0.9992 D(G(z)): 0.0266 / 0.0124\n",
"[16/4000][300/600] Loss_D: 0.0314 Loss_G: 3.8853 D(x): 0.9917 D(G(z)): 0.0191 / 0.0263\n",
"[16/4000][400/600] Loss_D: 0.0183 Loss_G: 5.9444 D(x): 0.9889 D(G(z)): 0.0063 / 0.0031\n",
"[16/4000][500/600] Loss_D: 0.0129 Loss_G: 5.4947 D(x): 0.9972 D(G(z)): 0.0100 / 0.0055\n",
"[17/4000][0/600] Loss_D: 0.0167 Loss_G: 4.2397 D(x): 0.9957 D(G(z)): 0.0122 / 0.0176\n",
"[17/4000][100/600] Loss_D: 0.0134 Loss_G: 6.7091 D(x): 0.9904 D(G(z)): 0.0027 / 0.0014\n",
"[17/4000][200/600] Loss_D: 0.0096 Loss_G: 5.5225 D(x): 0.9992 D(G(z)): 0.0087 / 0.0054\n",
"[17/4000][300/600] Loss_D: 0.0135 Loss_G: 5.8190 D(x): 0.9934 D(G(z)): 0.0058 / 0.0040\n",
"[17/4000][400/600] Loss_D: 0.0163 Loss_G: 5.0729 D(x): 0.9993 D(G(z)): 0.0155 / 0.0072\n",
"[17/4000][500/600] Loss_D: 0.0065 Loss_G: 6.5167 D(x): 0.9958 D(G(z)): 0.0022 / 0.0022\n",
"[18/4000][0/600] Loss_D: 0.0049 Loss_G: 6.0791 D(x): 0.9988 D(G(z)): 0.0037 / 0.0033\n",
"[18/4000][100/600] Loss_D: 0.0232 Loss_G: 6.8614 D(x): 0.9819 D(G(z)): 0.0015 / 0.0013\n",
"[18/4000][200/600] Loss_D: 0.0053 Loss_G: 5.5069 D(x): 0.9986 D(G(z)): 0.0039 / 0.0046\n",
"[18/4000][300/600] Loss_D: 0.0309 Loss_G: 5.2258 D(x): 0.9783 D(G(z)): 0.0059 / 0.0080\n",
"[18/4000][400/600] Loss_D: 0.0350 Loss_G: 4.5266 D(x): 0.9811 D(G(z)): 0.0115 / 0.0131\n",
"[18/4000][500/600] Loss_D: 0.0499 Loss_G: 5.1939 D(x): 0.9721 D(G(z)): 0.0051 / 0.0078\n",
"[19/4000][0/600] Loss_D: 0.0232 Loss_G: 4.9324 D(x): 0.9994 D(G(z)): 0.0222 / 0.0095\n",
"[19/4000][100/600] Loss_D: 0.0053 Loss_G: 6.9558 D(x): 0.9976 D(G(z)): 0.0029 / 0.0016\n",
"[19/4000][200/600] Loss_D: 0.0279 Loss_G: 5.9954 D(x): 0.9770 D(G(z)): 0.0012 / 0.0031\n",
"[19/4000][300/600] Loss_D: 0.0277 Loss_G: 4.4582 D(x): 0.9816 D(G(z)): 0.0065 / 0.0145\n",
"[19/4000][400/600] Loss_D: 0.0134 Loss_G: 5.1444 D(x): 0.9975 D(G(z)): 0.0109 / 0.0070\n",
"[19/4000][500/600] Loss_D: 0.0214 Loss_G: 5.0411 D(x): 0.9913 D(G(z)): 0.0120 / 0.0105\n",
"[20/4000][0/600] Loss_D: 0.0121 Loss_G: 5.5655 D(x): 0.9936 D(G(z)): 0.0055 / 0.0057\n",
"[20/4000][100/600] Loss_D: 0.0115 Loss_G: 6.3353 D(x): 0.9918 D(G(z)): 0.0031 / 0.0022\n",
"[20/4000][200/600] Loss_D: 0.0087 Loss_G: 6.3995 D(x): 0.9949 D(G(z)): 0.0034 / 0.0019\n",
"[20/4000][300/600] Loss_D: 0.0085 Loss_G: 5.0294 D(x): 0.9974 D(G(z)): 0.0058 / 0.0097\n",
"[20/4000][400/600] Loss_D: 0.0109 Loss_G: 6.2946 D(x): 0.9919 D(G(z)): 0.0025 / 0.0023\n",
"[20/4000][500/600] Loss_D: 0.0184 Loss_G: 5.2594 D(x): 0.9905 D(G(z)): 0.0077 / 0.0068\n",
"[21/4000][0/600] Loss_D: 0.0140 Loss_G: 5.2731 D(x): 0.9943 D(G(z)): 0.0081 / 0.0065\n",
"[21/4000][100/600] Loss_D: 0.0081 Loss_G: 5.5001 D(x): 0.9975 D(G(z)): 0.0055 / 0.0048\n",
"[21/4000][200/600] Loss_D: 0.0173 Loss_G: 5.7054 D(x): 0.9944 D(G(z)): 0.0111 / 0.0038\n",
"[21/4000][300/600] Loss_D: 0.0139 Loss_G: 4.9281 D(x): 0.9915 D(G(z)): 0.0049 / 0.0083\n",
"[21/4000][400/600] Loss_D: 0.0674 Loss_G: 4.4146 D(x): 0.9956 D(G(z)): 0.0568 / 0.0174\n",
"[21/4000][500/600] Loss_D: 0.0137 Loss_G: 5.1917 D(x): 0.9937 D(G(z)): 0.0067 / 0.0081\n",
"[22/4000][0/600] Loss_D: 0.0129 Loss_G: 5.2115 D(x): 0.9945 D(G(z)): 0.0070 / 0.0064\n",
"[22/4000][100/600] Loss_D: 0.0186 Loss_G: 5.6644 D(x): 0.9902 D(G(z)): 0.0064 / 0.0045\n",
"[22/4000][200/600] Loss_D: 0.0098 Loss_G: 5.7732 D(x): 0.9992 D(G(z)): 0.0089 / 0.0075\n",
"[22/4000][300/600] Loss_D: 0.0519 Loss_G: 5.3750 D(x): 0.9608 D(G(z)): 0.0016 / 0.0065\n",
"[22/4000][400/600] Loss_D: 0.0364 Loss_G: 3.2274 D(x): 0.9995 D(G(z)): 0.0350 / 0.0514\n",
"[22/4000][500/600] Loss_D: 0.0151 Loss_G: 5.7490 D(x): 0.9937 D(G(z)): 0.0085 / 0.0038\n",
"[23/4000][0/600] Loss_D: 0.0297 Loss_G: 5.4422 D(x): 0.9793 D(G(z)): 0.0059 / 0.0054\n",
"[23/4000][100/600] Loss_D: 0.0224 Loss_G: 5.7041 D(x): 0.9836 D(G(z)): 0.0037 / 0.0040\n",
"[23/4000][200/600] Loss_D: 0.0058 Loss_G: 7.5284 D(x): 0.9953 D(G(z)): 0.0010 / 0.0007\n",
"[23/4000][300/600] Loss_D: 0.0215 Loss_G: 4.1006 D(x): 0.9965 D(G(z)): 0.0177 / 0.0218\n",
"[23/4000][400/600] Loss_D: 0.0155 Loss_G: 5.9333 D(x): 0.9971 D(G(z)): 0.0123 / 0.0050\n",
"[23/4000][500/600] Loss_D: 0.0201 Loss_G: 3.9720 D(x): 0.9945 D(G(z)): 0.0143 / 0.0240\n",
"[24/4000][0/600] Loss_D: 0.0170 Loss_G: 5.2324 D(x): 0.9912 D(G(z)): 0.0074 / 0.0064\n",
"[24/4000][100/600] Loss_D: 0.0267 Loss_G: 8.6456 D(x): 0.9799 D(G(z)): 0.0003 / 0.0003\n",
"[24/4000][200/600] Loss_D: 0.0109 Loss_G: 5.6551 D(x): 0.9989 D(G(z)): 0.0097 / 0.0051\n",
"[24/4000][300/600] Loss_D: 0.0309 Loss_G: 3.8027 D(x): 0.9934 D(G(z)): 0.0237 / 0.0324\n",
"[24/4000][400/600] Loss_D: 0.0356 Loss_G: 4.2823 D(x): 0.9860 D(G(z)): 0.0186 / 0.0174\n",
"[24/4000][500/600] Loss_D: 0.0325 Loss_G: 5.3249 D(x): 0.9799 D(G(z)): 0.0054 / 0.0056\n",
"[25/4000][0/600] Loss_D: 0.0327 Loss_G: 3.3077 D(x): 0.9964 D(G(z)): 0.0282 / 0.0449\n",
"[25/4000][100/600] Loss_D: 0.0053 Loss_G: 7.0892 D(x): 0.9968 D(G(z)): 0.0020 / 0.0011\n",
"[25/4000][200/600] Loss_D: 0.0214 Loss_G: 6.0966 D(x): 0.9883 D(G(z)): 0.0083 / 0.0030\n",
"[25/4000][300/600] Loss_D: 0.0413 Loss_G: 5.5926 D(x): 0.9742 D(G(z)): 0.0077 / 0.0053\n",
"[25/4000][400/600] Loss_D: 0.0234 Loss_G: 4.7018 D(x): 0.9954 D(G(z)): 0.0183 / 0.0117\n",
"[25/4000][500/600] Loss_D: 0.0521 Loss_G: 5.0089 D(x): 0.9693 D(G(z)): 0.0157 / 0.0099\n",
"[26/4000][0/600] Loss_D: 0.0190 Loss_G: 5.3465 D(x): 0.9863 D(G(z)): 0.0044 / 0.0059\n",
"[26/4000][100/600] Loss_D: 0.0425 Loss_G: 7.0930 D(x): 0.9665 D(G(z)): 0.0017 / 0.0012\n",
"[26/4000][200/600] Loss_D: 0.0194 Loss_G: 5.5221 D(x): 0.9931 D(G(z)): 0.0118 / 0.0048\n",
"[26/4000][300/600] Loss_D: 0.0133 Loss_G: 5.3891 D(x): 0.9940 D(G(z)): 0.0068 / 0.0065\n",
"[26/4000][400/600] Loss_D: 0.0240 Loss_G: 4.9055 D(x): 0.9934 D(G(z)): 0.0158 / 0.0114\n",
"[26/4000][500/600] Loss_D: 0.0371 Loss_G: 4.3043 D(x): 0.9917 D(G(z)): 0.0263 / 0.0225\n",
"[27/4000][0/600] Loss_D: 0.0348 Loss_G: 3.8016 D(x): 0.9926 D(G(z)): 0.0263 / 0.0313\n",
"[27/4000][100/600] Loss_D: 0.0379 Loss_G: 5.4233 D(x): 0.9725 D(G(z)): 0.0048 / 0.0064\n",
"[27/4000][200/600] Loss_D: 0.0123 Loss_G: 6.8725 D(x): 0.9914 D(G(z)): 0.0034 / 0.0012\n",
"[27/4000][300/600] Loss_D: 0.0133 Loss_G: 4.9791 D(x): 0.9994 D(G(z)): 0.0126 / 0.0093\n",
"[27/4000][400/600] Loss_D: 0.0156 Loss_G: 5.9467 D(x): 0.9913 D(G(z)): 0.0065 / 0.0034\n",
"[27/4000][500/600] Loss_D: 0.0393 Loss_G: 6.3075 D(x): 0.9771 D(G(z)): 0.0022 / 0.0023\n",
"[28/4000][0/600] Loss_D: 0.0497 Loss_G: 4.9014 D(x): 0.9813 D(G(z)): 0.0260 / 0.0098\n",
"[28/4000][100/600] Loss_D: 0.0478 Loss_G: 4.9777 D(x): 0.9834 D(G(z)): 0.0146 / 0.0091\n",
"[28/4000][200/600] Loss_D: 0.0239 Loss_G: 5.1270 D(x): 0.9917 D(G(z)): 0.0150 / 0.0086\n",
"[28/4000][300/600] Loss_D: 0.0304 Loss_G: 4.5994 D(x): 0.9796 D(G(z)): 0.0071 / 0.0172\n",
"[28/4000][400/600] Loss_D: 0.0268 Loss_G: 4.6256 D(x): 0.9975 D(G(z)): 0.0238 / 0.0132\n",
"[28/4000][500/600] Loss_D: 0.0107 Loss_G: 5.9704 D(x): 0.9928 D(G(z)): 0.0032 / 0.0039\n",
"[29/4000][0/600] Loss_D: 0.1413 Loss_G: 9.8566 D(x): 0.9076 D(G(z)): 0.0001 / 0.0001\n",
"[29/4000][100/600] Loss_D: 0.0153 Loss_G: 5.4854 D(x): 0.9944 D(G(z)): 0.0093 / 0.0069\n",
"[29/4000][200/600] Loss_D: 0.0221 Loss_G: 4.2034 D(x): 0.9963 D(G(z)): 0.0181 / 0.0192\n",
"[29/4000][300/600] Loss_D: 0.0285 Loss_G: 4.5905 D(x): 0.9897 D(G(z)): 0.0174 / 0.0134\n",
"[29/4000][400/600] Loss_D: 0.0177 Loss_G: 6.4779 D(x): 0.9873 D(G(z)): 0.0045 / 0.0023\n",
"[29/4000][500/600] Loss_D: 0.0540 Loss_G: 4.7669 D(x): 0.9737 D(G(z)): 0.0119 / 0.0121\n",
"[30/4000][0/600] Loss_D: 0.0684 Loss_G: 3.5928 D(x): 0.9983 D(G(z)): 0.0617 / 0.0427\n",
"[30/4000][100/600] Loss_D: 0.0346 Loss_G: 5.8301 D(x): 0.9790 D(G(z)): 0.0069 / 0.0040\n",
"[30/4000][200/600] Loss_D: 0.0103 Loss_G: 6.6071 D(x): 0.9924 D(G(z)): 0.0025 / 0.0016\n",
"[30/4000][300/600] Loss_D: 0.3093 Loss_G: 3.8214 D(x): 0.9918 D(G(z)): 0.2230 / 0.0400\n",
"[30/4000][400/600] Loss_D: 0.0598 Loss_G: 5.1490 D(x): 0.9685 D(G(z)): 0.0165 / 0.0079\n",
"[30/4000][500/600] Loss_D: 0.2032 Loss_G: 5.5491 D(x): 0.8794 D(G(z)): 0.0023 / 0.0073\n",
"[31/4000][0/600] Loss_D: 0.3519 Loss_G: 8.7604 D(x): 0.8185 D(G(z)): 0.0002 / 0.0002\n",
"[31/4000][100/600] Loss_D: 0.0297 Loss_G: 5.8127 D(x): 0.9834 D(G(z)): 0.0107 / 0.0035\n",
"[31/4000][200/600] Loss_D: 0.0363 Loss_G: 5.0433 D(x): 0.9825 D(G(z)): 0.0168 / 0.0087\n",
"[31/4000][300/600] Loss_D: 0.1372 Loss_G: 4.8375 D(x): 0.9099 D(G(z)): 0.0056 / 0.0143\n",
"[31/4000][400/600] Loss_D: 0.0482 Loss_G: 5.4184 D(x): 0.9742 D(G(z)): 0.0129 / 0.0065\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[31/4000][500/600] Loss_D: 0.0124 Loss_G: 5.5754 D(x): 0.9950 D(G(z)): 0.0071 / 0.0060\n",
"[32/4000][0/600] Loss_D: 0.0533 Loss_G: 3.6932 D(x): 0.9795 D(G(z)): 0.0271 / 0.0456\n",
"[32/4000][100/600] Loss_D: 0.0232 Loss_G: 4.5650 D(x): 0.9920 D(G(z)): 0.0133 / 0.0135\n",
"[32/4000][200/600] Loss_D: 0.0148 Loss_G: 5.3049 D(x): 0.9989 D(G(z)): 0.0134 / 0.0074\n",
"[32/4000][300/600] Loss_D: 0.0732 Loss_G: 4.7389 D(x): 0.9740 D(G(z)): 0.0164 / 0.0116\n",
"[32/4000][400/600] Loss_D: 0.0513 Loss_G: 6.6460 D(x): 0.9592 D(G(z)): 0.0031 / 0.0017\n",
"[32/4000][500/600] Loss_D: 0.1010 Loss_G: 4.3334 D(x): 0.9533 D(G(z)): 0.0141 / 0.0149\n",
"[33/4000][0/600] Loss_D: 0.0777 Loss_G: 3.4117 D(x): 0.9807 D(G(z)): 0.0384 / 0.0466\n",
"[33/4000][100/600] Loss_D: 0.0746 Loss_G: 5.9954 D(x): 0.9436 D(G(z)): 0.0060 / 0.0042\n",
"[33/4000][200/600] Loss_D: 0.0322 Loss_G: 4.9772 D(x): 0.9902 D(G(z)): 0.0193 / 0.0087\n",
"[33/4000][300/600] Loss_D: 0.0297 Loss_G: 4.8024 D(x): 0.9937 D(G(z)): 0.0228 / 0.0112\n",
"[33/4000][400/600] Loss_D: 0.0661 Loss_G: 3.5844 D(x): 0.9857 D(G(z)): 0.0478 / 0.0423\n",
"[33/4000][500/600] Loss_D: 0.0497 Loss_G: 5.0600 D(x): 0.9705 D(G(z)): 0.0132 / 0.0088\n",
"[34/4000][0/600] Loss_D: 0.1098 Loss_G: 3.1484 D(x): 0.9857 D(G(z)): 0.0857 / 0.0605\n",
"[34/4000][100/600] Loss_D: 0.0290 Loss_G: 5.1954 D(x): 0.9867 D(G(z)): 0.0138 / 0.0090\n",
"[34/4000][200/600] Loss_D: 0.0363 Loss_G: 7.2023 D(x): 0.9741 D(G(z)): 0.0031 / 0.0011\n",
"[34/4000][300/600] Loss_D: 0.0575 Loss_G: 4.7596 D(x): 0.9635 D(G(z)): 0.0119 / 0.0120\n",
"[34/4000][400/600] Loss_D: 0.0911 Loss_G: 6.5178 D(x): 0.9323 D(G(z)): 0.0031 / 0.0027\n",
"[34/4000][500/600] Loss_D: 0.0475 Loss_G: 6.3898 D(x): 0.9625 D(G(z)): 0.0030 / 0.0026\n",
"[35/4000][0/600] Loss_D: 0.0608 Loss_G: 3.9193 D(x): 0.9819 D(G(z)): 0.0388 / 0.0292\n",
"[35/4000][100/600] Loss_D: 0.1373 Loss_G: 4.7893 D(x): 0.9433 D(G(z)): 0.0122 / 0.0127\n",
"[35/4000][200/600] Loss_D: 0.0549 Loss_G: 5.3084 D(x): 0.9784 D(G(z)): 0.0069 / 0.0063\n",
"[35/4000][300/600] Loss_D: 0.0636 Loss_G: 6.5685 D(x): 0.9549 D(G(z)): 0.0043 / 0.0025\n",
"[35/4000][400/600] Loss_D: 0.0965 Loss_G: 4.6090 D(x): 0.9521 D(G(z)): 0.0233 / 0.0171\n",
"[35/4000][500/600] Loss_D: 0.0243 Loss_G: 6.3961 D(x): 0.9830 D(G(z)): 0.0063 / 0.0030\n",
"[36/4000][0/600] Loss_D: 0.0328 Loss_G: 6.4059 D(x): 0.9785 D(G(z)): 0.0084 / 0.0026\n",
"[36/4000][100/600] Loss_D: 0.0289 Loss_G: 4.8943 D(x): 0.9927 D(G(z)): 0.0204 / 0.0135\n",
"[36/4000][200/600] Loss_D: 0.0235 Loss_G: 4.9015 D(x): 0.9964 D(G(z)): 0.0194 / 0.0115\n",
"[36/4000][300/600] Loss_D: 0.0784 Loss_G: 6.5640 D(x): 0.9577 D(G(z)): 0.0023 / 0.0019\n",
"[36/4000][400/600] Loss_D: 0.0524 Loss_G: 4.0011 D(x): 0.9941 D(G(z)): 0.0441 / 0.0288\n",
"[36/4000][500/600] Loss_D: 0.0226 Loss_G: 5.9078 D(x): 0.9849 D(G(z)): 0.0063 / 0.0049\n",
"[37/4000][0/600] Loss_D: 0.0552 Loss_G: 5.4299 D(x): 0.9700 D(G(z)): 0.0157 / 0.0071\n",
"[37/4000][100/600] Loss_D: 0.0287 Loss_G: 5.7458 D(x): 0.9853 D(G(z)): 0.0109 / 0.0080\n",
"[37/4000][200/600] Loss_D: 0.0791 Loss_G: 7.1558 D(x): 0.9424 D(G(z)): 0.0015 / 0.0014\n",
"[37/4000][300/600] Loss_D: 0.0782 Loss_G: 4.6399 D(x): 0.9706 D(G(z)): 0.0115 / 0.0157\n",
"[37/4000][400/600] Loss_D: 0.0399 Loss_G: 4.3240 D(x): 0.9837 D(G(z)): 0.0216 / 0.0178\n",
"[37/4000][500/600] Loss_D: 0.0774 Loss_G: 5.2213 D(x): 0.9571 D(G(z)): 0.0070 / 0.0081\n",
"[38/4000][0/600] Loss_D: 0.0451 Loss_G: 4.7974 D(x): 0.9768 D(G(z)): 0.0114 / 0.0112\n",
"[38/4000][100/600] Loss_D: 0.0216 Loss_G: 4.4794 D(x): 0.9973 D(G(z)): 0.0186 / 0.0162\n",
"[38/4000][200/600] Loss_D: 0.0219 Loss_G: 6.7290 D(x): 0.9871 D(G(z)): 0.0075 / 0.0024\n",
"[38/4000][300/600] Loss_D: 0.0500 Loss_G: 5.6503 D(x): 0.9631 D(G(z)): 0.0097 / 0.0081\n",
"[38/4000][400/600] Loss_D: 0.1088 Loss_G: 5.5792 D(x): 0.9450 D(G(z)): 0.0081 / 0.0064\n",
"[38/4000][500/600] Loss_D: 0.0508 Loss_G: 5.1057 D(x): 0.9586 D(G(z)): 0.0039 / 0.0083\n",
"[39/4000][0/600] Loss_D: 0.0660 Loss_G: 5.1460 D(x): 0.9667 D(G(z)): 0.0178 / 0.0090\n",
"[39/4000][100/600] Loss_D: 0.0277 Loss_G: 5.0814 D(x): 0.9888 D(G(z)): 0.0157 / 0.0088\n",
"[39/4000][200/600] Loss_D: 0.1090 Loss_G: 3.2656 D(x): 0.9964 D(G(z)): 0.0961 / 0.0513\n",
"[39/4000][300/600] Loss_D: 0.3058 Loss_G: 2.0767 D(x): 0.9887 D(G(z)): 0.2236 / 0.1700\n",
"[39/4000][400/600] Loss_D: 0.0496 Loss_G: 6.5793 D(x): 0.9718 D(G(z)): 0.0064 / 0.0021\n",
"[39/4000][500/600] Loss_D: 0.0717 Loss_G: 4.4750 D(x): 0.9591 D(G(z)): 0.0113 / 0.0160\n",
"[40/4000][0/600] Loss_D: 0.0239 Loss_G: 7.6247 D(x): 0.9811 D(G(z)): 0.0030 / 0.0009\n",
"[40/4000][100/600] Loss_D: 0.0335 Loss_G: 5.3945 D(x): 0.9854 D(G(z)): 0.0147 / 0.0066\n",
"[40/4000][200/600] Loss_D: 0.0498 Loss_G: 5.5435 D(x): 0.9831 D(G(z)): 0.0270 / 0.0065\n",
"[40/4000][300/600] Loss_D: 0.0274 Loss_G: 7.4191 D(x): 0.9791 D(G(z)): 0.0024 / 0.0008\n",
"[40/4000][400/600] Loss_D: 0.0488 Loss_G: 5.7045 D(x): 0.9718 D(G(z)): 0.0160 / 0.0060\n",
"[40/4000][500/600] Loss_D: 0.0651 Loss_G: 4.4725 D(x): 0.9640 D(G(z)): 0.0155 / 0.0170\n",
"[41/4000][0/600] Loss_D: 0.0761 Loss_G: 4.1495 D(x): 0.9744 D(G(z)): 0.0387 / 0.0226\n",
"[41/4000][100/600] Loss_D: 0.0398 Loss_G: 4.8696 D(x): 0.9769 D(G(z)): 0.0138 / 0.0111\n",
"[41/4000][200/600] Loss_D: 0.0382 Loss_G: 5.5100 D(x): 0.9933 D(G(z)): 0.0296 / 0.0088\n",
"[41/4000][300/600] Loss_D: 0.1428 Loss_G: 4.3012 D(x): 0.9476 D(G(z)): 0.0240 / 0.0221\n",
"[41/4000][400/600] Loss_D: 0.1584 Loss_G: 6.3666 D(x): 0.9022 D(G(z)): 0.0035 / 0.0028\n",
"[41/4000][500/600] Loss_D: 0.0245 Loss_G: 5.0860 D(x): 0.9975 D(G(z)): 0.0213 / 0.0114\n",
"[42/4000][0/600] Loss_D: 0.1870 Loss_G: 9.1120 D(x): 0.8883 D(G(z)): 0.0002 / 0.0002\n",
"[42/4000][100/600] Loss_D: 0.0975 Loss_G: 7.5505 D(x): 0.9356 D(G(z)): 0.0015 / 0.0007\n",
"[42/4000][200/600] Loss_D: 0.0616 Loss_G: 3.8727 D(x): 0.9839 D(G(z)): 0.0426 / 0.0297\n",
"[42/4000][300/600] Loss_D: 0.0490 Loss_G: 5.3011 D(x): 0.9665 D(G(z)): 0.0088 / 0.0067\n",
"[42/4000][400/600] Loss_D: 0.0937 Loss_G: 4.2388 D(x): 0.9613 D(G(z)): 0.0356 / 0.0199\n",
"[42/4000][500/600] Loss_D: 0.0725 Loss_G: 3.8486 D(x): 0.9664 D(G(z)): 0.0301 / 0.0300\n",
"[43/4000][0/600] Loss_D: 0.0413 Loss_G: 5.7884 D(x): 0.9781 D(G(z)): 0.0152 / 0.0060\n",
"[43/4000][100/600] Loss_D: 0.0900 Loss_G: 4.5424 D(x): 0.9640 D(G(z)): 0.0292 / 0.0170\n",
"[43/4000][200/600] Loss_D: 0.0427 Loss_G: 4.7969 D(x): 0.9866 D(G(z)): 0.0269 / 0.0121\n",
"[43/4000][300/600] Loss_D: 0.0813 Loss_G: 4.5771 D(x): 0.9551 D(G(z)): 0.0090 / 0.0129\n",
"[43/4000][400/600] Loss_D: 0.1272 Loss_G: 3.3563 D(x): 0.9903 D(G(z)): 0.1026 / 0.0472\n",
"[43/4000][500/600] Loss_D: 0.0087 Loss_G: 6.4952 D(x): 0.9943 D(G(z)): 0.0029 / 0.0021\n",
"[44/4000][0/600] Loss_D: 0.0997 Loss_G: 4.6448 D(x): 0.9417 D(G(z)): 0.0139 / 0.0115\n",
"[44/4000][100/600] Loss_D: 0.0420 Loss_G: 5.1208 D(x): 0.9750 D(G(z)): 0.0129 / 0.0096\n",
"[44/4000][200/600] Loss_D: 0.0694 Loss_G: 4.0479 D(x): 0.9982 D(G(z)): 0.0616 / 0.0267\n",
"[44/4000][300/600] Loss_D: 0.1015 Loss_G: 4.2735 D(x): 0.9419 D(G(z)): 0.0228 / 0.0205\n",
"[44/4000][400/600] Loss_D: 0.1619 Loss_G: 5.6287 D(x): 0.9178 D(G(z)): 0.0083 / 0.0074\n",
"[44/4000][500/600] Loss_D: 0.0398 Loss_G: 5.0423 D(x): 0.9762 D(G(z)): 0.0112 / 0.0123\n",
"[45/4000][0/600] Loss_D: 0.0255 Loss_G: 5.1073 D(x): 0.9970 D(G(z)): 0.0220 / 0.0094\n",
"[45/4000][100/600] Loss_D: 0.0307 Loss_G: 5.1965 D(x): 0.9869 D(G(z)): 0.0144 / 0.0080\n",
"[45/4000][200/600] Loss_D: 0.2302 Loss_G: 5.8453 D(x): 0.8751 D(G(z)): 0.0047 / 0.0098\n",
"[45/4000][300/600] Loss_D: 0.0363 Loss_G: 4.4610 D(x): 0.9917 D(G(z)): 0.0263 / 0.0165\n",
"[45/4000][400/600] Loss_D: 0.1060 Loss_G: 4.9406 D(x): 0.9546 D(G(z)): 0.0119 / 0.0101\n",
"[45/4000][500/600] Loss_D: 0.0294 Loss_G: 6.1611 D(x): 0.9791 D(G(z)): 0.0032 / 0.0027\n",
"[46/4000][0/600] Loss_D: 0.0635 Loss_G: 3.4131 D(x): 0.9957 D(G(z)): 0.0559 / 0.0450\n",
"[46/4000][100/600] Loss_D: 0.0460 Loss_G: 4.1045 D(x): 0.9985 D(G(z)): 0.0416 / 0.0272\n",
"[46/4000][200/600] Loss_D: 0.0356 Loss_G: 7.9512 D(x): 0.9760 D(G(z)): 0.0017 / 0.0005\n",
"[46/4000][300/600] Loss_D: 0.0639 Loss_G: 6.0574 D(x): 0.9529 D(G(z)): 0.0036 / 0.0039\n",
"[46/4000][400/600] Loss_D: 0.0247 Loss_G: 4.8915 D(x): 0.9879 D(G(z)): 0.0084 / 0.0093\n",
"[46/4000][500/600] Loss_D: 0.0755 Loss_G: 4.9247 D(x): 0.9437 D(G(z)): 0.0080 / 0.0098\n",
"[47/4000][0/600] Loss_D: 0.0389 Loss_G: 4.1013 D(x): 0.9958 D(G(z)): 0.0330 / 0.0274\n",
"[47/4000][100/600] Loss_D: 0.0172 Loss_G: 5.7586 D(x): 0.9951 D(G(z)): 0.0120 / 0.0054\n",
"[47/4000][200/600] Loss_D: 0.0543 Loss_G: 5.4202 D(x): 0.9776 D(G(z)): 0.0096 / 0.0075\n",
"[47/4000][300/600] Loss_D: 0.0811 Loss_G: 3.7703 D(x): 0.9883 D(G(z)): 0.0592 / 0.0364\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[47/4000][400/600] Loss_D: 0.0364 Loss_G: 5.5982 D(x): 0.9765 D(G(z)): 0.0102 / 0.0081\n",
"[47/4000][500/600] Loss_D: 0.1097 Loss_G: 6.7903 D(x): 0.9357 D(G(z)): 0.0017 / 0.0024\n",
"[48/4000][0/600] Loss_D: 0.1174 Loss_G: 6.3698 D(x): 0.9160 D(G(z)): 0.0040 / 0.0031\n",
"[48/4000][100/600] Loss_D: 0.0345 Loss_G: 4.7988 D(x): 0.9875 D(G(z)): 0.0197 / 0.0133\n",
"[48/4000][200/600] Loss_D: 0.0250 Loss_G: 4.8016 D(x): 0.9975 D(G(z)): 0.0221 / 0.0104\n",
"[48/4000][300/600] Loss_D: 0.0442 Loss_G: 4.4848 D(x): 0.9795 D(G(z)): 0.0159 / 0.0144\n",
"[48/4000][400/600] Loss_D: 0.0999 Loss_G: 6.0857 D(x): 0.9431 D(G(z)): 0.0061 / 0.0034\n",
"[48/4000][500/600] Loss_D: 0.0493 Loss_G: 4.6668 D(x): 0.9740 D(G(z)): 0.0151 / 0.0122\n",
"[49/4000][0/600] Loss_D: 0.0881 Loss_G: 4.1870 D(x): 0.9700 D(G(z)): 0.0379 / 0.0221\n",
"[49/4000][100/600] Loss_D: 0.0571 Loss_G: 4.5915 D(x): 0.9712 D(G(z)): 0.0188 / 0.0151\n",
"[49/4000][200/600] Loss_D: 0.0109 Loss_G: 5.8679 D(x): 0.9965 D(G(z)): 0.0073 / 0.0037\n",
"[49/4000][300/600] Loss_D: 0.0635 Loss_G: 6.3964 D(x): 0.9638 D(G(z)): 0.0031 / 0.0021\n",
"[49/4000][400/600] Loss_D: 0.1893 Loss_G: 5.8633 D(x): 0.8908 D(G(z)): 0.0060 / 0.0042\n",
"[49/4000][500/600] Loss_D: 0.0577 Loss_G: 7.4644 D(x): 0.9583 D(G(z)): 0.0011 / 0.0007\n",
"[50/4000][0/600] Loss_D: 0.0335 Loss_G: 4.3722 D(x): 0.9915 D(G(z)): 0.0241 / 0.0180\n",
"[50/4000][100/600] Loss_D: 0.0592 Loss_G: 4.1266 D(x): 0.9773 D(G(z)): 0.0312 / 0.0222\n",
"[50/4000][200/600] Loss_D: 0.1450 Loss_G: 7.5133 D(x): 0.9113 D(G(z)): 0.0014 / 0.0008\n",
"[50/4000][300/600] Loss_D: 0.0441 Loss_G: 4.9267 D(x): 0.9785 D(G(z)): 0.0152 / 0.0115\n",
"[50/4000][400/600] Loss_D: 0.0584 Loss_G: 4.2687 D(x): 0.9829 D(G(z)): 0.0267 / 0.0203\n",
"[50/4000][500/600] Loss_D: 0.0845 Loss_G: 4.9608 D(x): 0.9476 D(G(z)): 0.0098 / 0.0108\n",
"[51/4000][0/600] Loss_D: 0.0582 Loss_G: 2.9596 D(x): 0.9929 D(G(z)): 0.0483 / 0.0708\n",
"[51/4000][100/600] Loss_D: 0.1034 Loss_G: 4.3409 D(x): 0.9644 D(G(z)): 0.0429 / 0.0181\n",
"[51/4000][200/600] Loss_D: 0.2785 Loss_G: 7.2224 D(x): 0.8321 D(G(z)): 0.0017 / 0.0014\n",
"[51/4000][300/600] Loss_D: 0.0381 Loss_G: 4.7525 D(x): 0.9896 D(G(z)): 0.0261 / 0.0145\n",
"[51/4000][400/600] Loss_D: 0.0567 Loss_G: 4.4424 D(x): 0.9665 D(G(z)): 0.0185 / 0.0168\n",
"[51/4000][500/600] Loss_D: 0.0674 Loss_G: 4.8393 D(x): 0.9523 D(G(z)): 0.0072 / 0.0107\n",
"[52/4000][0/600] Loss_D: 0.0141 Loss_G: 6.3135 D(x): 0.9960 D(G(z)): 0.0099 / 0.0026\n",
"[52/4000][100/600] Loss_D: 0.0742 Loss_G: 4.4437 D(x): 0.9800 D(G(z)): 0.0397 / 0.0174\n",
"[52/4000][200/600] Loss_D: 0.0881 Loss_G: 4.4894 D(x): 0.9504 D(G(z)): 0.0180 / 0.0170\n",
"[52/4000][300/600] Loss_D: 0.0200 Loss_G: 6.8474 D(x): 0.9878 D(G(z)): 0.0064 / 0.0021\n",
"[52/4000][400/600] Loss_D: 0.0425 Loss_G: 4.6783 D(x): 0.9819 D(G(z)): 0.0228 / 0.0146\n",
"[52/4000][500/600] Loss_D: 0.1120 Loss_G: 2.8360 D(x): 0.9757 D(G(z)): 0.0777 / 0.1023\n",
"[53/4000][0/600] Loss_D: 0.0345 Loss_G: 5.1028 D(x): 0.9822 D(G(z)): 0.0138 / 0.0088\n",
"[53/4000][100/600] Loss_D: 0.0258 Loss_G: 5.5293 D(x): 0.9866 D(G(z)): 0.0103 / 0.0056\n",
"[53/4000][200/600] Loss_D: 0.1263 Loss_G: 4.0230 D(x): 0.9882 D(G(z)): 0.0955 / 0.0294\n",
"[53/4000][300/600] Loss_D: 0.0949 Loss_G: 4.4906 D(x): 0.9475 D(G(z)): 0.0127 / 0.0235\n",
"[53/4000][400/600] Loss_D: 0.1504 Loss_G: 3.1553 D(x): 0.9706 D(G(z)): 0.1070 / 0.0617\n",
"[53/4000][500/600] Loss_D: 0.0296 Loss_G: 5.3400 D(x): 0.9836 D(G(z)): 0.0115 / 0.0074\n",
"[54/4000][0/600] Loss_D: 0.0838 Loss_G: 3.8117 D(x): 0.9957 D(G(z)): 0.0721 / 0.0401\n",
"[54/4000][100/600] Loss_D: 0.0636 Loss_G: 3.8068 D(x): 0.9889 D(G(z)): 0.0481 / 0.0431\n",
"[54/4000][200/600] Loss_D: 0.0255 Loss_G: 6.2156 D(x): 0.9834 D(G(z)): 0.0059 / 0.0044\n",
"[54/4000][300/600] Loss_D: 0.0746 Loss_G: 5.7871 D(x): 0.9532 D(G(z)): 0.0041 / 0.0057\n",
"[54/4000][400/600] Loss_D: 0.0368 Loss_G: 5.2535 D(x): 0.9763 D(G(z)): 0.0101 / 0.0076\n",
"[54/4000][500/600] Loss_D: 0.0607 Loss_G: 4.5068 D(x): 0.9661 D(G(z)): 0.0156 / 0.0156\n",
"[55/4000][0/600] Loss_D: 0.0446 Loss_G: 6.7231 D(x): 0.9725 D(G(z)): 0.0043 / 0.0016\n",
"[55/4000][100/600] Loss_D: 0.0600 Loss_G: 5.4967 D(x): 0.9704 D(G(z)): 0.0083 / 0.0085\n",
"[55/4000][200/600] Loss_D: 0.0294 Loss_G: 5.3717 D(x): 0.9853 D(G(z)): 0.0120 / 0.0081\n",
"[55/4000][300/600] Loss_D: 0.0809 Loss_G: 4.5917 D(x): 0.9542 D(G(z)): 0.0080 / 0.0152\n",
"[55/4000][400/600] Loss_D: 0.0210 Loss_G: 5.6150 D(x): 0.9951 D(G(z)): 0.0156 / 0.0078\n",
"[55/4000][500/600] Loss_D: 0.1076 Loss_G: 5.7107 D(x): 0.9394 D(G(z)): 0.0047 / 0.0060\n",
"[56/4000][0/600] Loss_D: 0.1032 Loss_G: 5.3333 D(x): 0.9414 D(G(z)): 0.0058 / 0.0067\n",
"[56/4000][100/600] Loss_D: 0.0621 Loss_G: 5.4814 D(x): 0.9623 D(G(z)): 0.0090 / 0.0058\n",
"[56/4000][200/600] Loss_D: 0.0931 Loss_G: 5.5189 D(x): 0.9487 D(G(z)): 0.0161 / 0.0065\n",
"[56/4000][300/600] Loss_D: 0.0343 Loss_G: 5.8384 D(x): 0.9741 D(G(z)): 0.0039 / 0.0038\n",
"[56/4000][400/600] Loss_D: 0.0225 Loss_G: 5.0236 D(x): 0.9952 D(G(z)): 0.0168 / 0.0091\n",
"[56/4000][500/600] Loss_D: 0.0629 Loss_G: 6.1544 D(x): 0.9567 D(G(z)): 0.0034 / 0.0036\n",
"[57/4000][0/600] Loss_D: 0.0302 Loss_G: 4.3713 D(x): 0.9916 D(G(z)): 0.0213 / 0.0160\n",
"[57/4000][100/600] Loss_D: 0.0286 Loss_G: 5.3148 D(x): 0.9859 D(G(z)): 0.0110 / 0.0065\n",
"[57/4000][200/600] Loss_D: 0.0268 Loss_G: 4.6221 D(x): 0.9993 D(G(z)): 0.0255 / 0.0134\n",
"[57/4000][300/600] Loss_D: 0.0194 Loss_G: 5.1755 D(x): 0.9947 D(G(z)): 0.0137 / 0.0111\n",
"[57/4000][400/600] Loss_D: 0.0646 Loss_G: 4.5038 D(x): 0.9588 D(G(z)): 0.0168 / 0.0149\n",
"[57/4000][500/600] Loss_D: 0.0182 Loss_G: 5.1807 D(x): 0.9925 D(G(z)): 0.0104 / 0.0095\n",
"[58/4000][0/600] Loss_D: 0.1326 Loss_G: 9.9539 D(x): 0.9300 D(G(z)): 0.0003 / 0.0001\n",
"[58/4000][100/600] Loss_D: 0.0193 Loss_G: 5.4067 D(x): 0.9921 D(G(z)): 0.0093 / 0.0093\n",
"[58/4000][200/600] Loss_D: 0.1221 Loss_G: 6.3810 D(x): 0.9437 D(G(z)): 0.0042 / 0.0025\n",
"[58/4000][300/600] Loss_D: 0.0134 Loss_G: 5.5555 D(x): 0.9934 D(G(z)): 0.0066 / 0.0053\n",
"[58/4000][400/600] Loss_D: 0.0210 Loss_G: 5.7650 D(x): 0.9918 D(G(z)): 0.0121 / 0.0054\n",
"[58/4000][500/600] Loss_D: 0.0313 Loss_G: 4.6934 D(x): 0.9820 D(G(z)): 0.0107 / 0.0123\n",
"[59/4000][0/600] Loss_D: 0.0179 Loss_G: 5.2895 D(x): 0.9910 D(G(z)): 0.0074 / 0.0075\n",
"[59/4000][100/600] Loss_D: 0.0145 Loss_G: 5.9681 D(x): 0.9890 D(G(z)): 0.0029 / 0.0036\n",
"[59/4000][200/600] Loss_D: 0.0228 Loss_G: 5.6461 D(x): 0.9895 D(G(z)): 0.0111 / 0.0071\n",
"[59/4000][300/600] Loss_D: 0.0652 Loss_G: 7.0754 D(x): 0.9525 D(G(z)): 0.0015 / 0.0028\n",
"[59/4000][400/600] Loss_D: 0.0318 Loss_G: 6.6199 D(x): 0.9762 D(G(z)): 0.0030 / 0.0020\n",
"[59/4000][500/600] Loss_D: 0.0624 Loss_G: 3.6466 D(x): 0.9779 D(G(z)): 0.0320 / 0.0389\n",
"[60/4000][0/600] Loss_D: 0.0140 Loss_G: 6.4851 D(x): 0.9916 D(G(z)): 0.0045 / 0.0022\n",
"[60/4000][100/600] Loss_D: 0.0195 Loss_G: 5.4892 D(x): 0.9961 D(G(z)): 0.0149 / 0.0091\n",
"[60/4000][200/600] Loss_D: 0.0239 Loss_G: 10.7857 D(x): 0.9815 D(G(z)): 0.0002 / 0.0000\n",
"[60/4000][300/600] Loss_D: 0.0452 Loss_G: 6.0586 D(x): 0.9696 D(G(z)): 0.0052 / 0.0043\n",
"[60/4000][400/600] Loss_D: 0.0202 Loss_G: 7.8870 D(x): 0.9854 D(G(z)): 0.0016 / 0.0007\n",
"[60/4000][500/600] Loss_D: 0.0597 Loss_G: 4.0527 D(x): 0.9919 D(G(z)): 0.0488 / 0.0280\n",
"[61/4000][0/600] Loss_D: 0.0085 Loss_G: 6.8405 D(x): 0.9959 D(G(z)): 0.0043 / 0.0021\n",
"[61/4000][100/600] Loss_D: 0.0469 Loss_G: 5.3645 D(x): 0.9897 D(G(z)): 0.0315 / 0.0091\n",
"[61/4000][200/600] Loss_D: 0.0311 Loss_G: 4.5898 D(x): 0.9909 D(G(z)): 0.0210 / 0.0148\n",
"[61/4000][300/600] Loss_D: 0.0797 Loss_G: 5.6997 D(x): 0.9635 D(G(z)): 0.0082 / 0.0064\n",
"[61/4000][400/600] Loss_D: 0.0512 Loss_G: 4.3276 D(x): 0.9876 D(G(z)): 0.0366 / 0.0191\n",
"[61/4000][500/600] Loss_D: 0.0178 Loss_G: 5.1315 D(x): 0.9904 D(G(z)): 0.0076 / 0.0101\n",
"[62/4000][0/600] Loss_D: 0.0317 Loss_G: 4.8872 D(x): 0.9823 D(G(z)): 0.0101 / 0.0121\n",
"[62/4000][100/600] Loss_D: 0.0480 Loss_G: 4.0487 D(x): 0.9891 D(G(z)): 0.0355 / 0.0206\n",
"[62/4000][200/600] Loss_D: 0.3436 Loss_G: 6.9486 D(x): 0.8521 D(G(z)): 0.0011 / 0.0014\n",
"[62/4000][300/600] Loss_D: 0.0714 Loss_G: 5.1042 D(x): 0.9634 D(G(z)): 0.0080 / 0.0085\n",
"[62/4000][400/600] Loss_D: 0.0188 Loss_G: 6.1888 D(x): 0.9868 D(G(z)): 0.0045 / 0.0029\n",
"[62/4000][500/600] Loss_D: 0.0507 Loss_G: 6.5782 D(x): 0.9637 D(G(z)): 0.0023 / 0.0026\n",
"[63/4000][0/600] Loss_D: 0.0337 Loss_G: 6.1050 D(x): 0.9771 D(G(z)): 0.0055 / 0.0028\n",
"[63/4000][100/600] Loss_D: 0.0172 Loss_G: 6.4681 D(x): 0.9884 D(G(z)): 0.0049 / 0.0023\n",
"[63/4000][200/600] Loss_D: 0.1033 Loss_G: 3.9099 D(x): 0.9958 D(G(z)): 0.0911 / 0.0283\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[63/4000][300/600] Loss_D: 0.0443 Loss_G: 4.4225 D(x): 0.9757 D(G(z)): 0.0177 / 0.0230\n",
"[63/4000][400/600] Loss_D: 0.0669 Loss_G: 6.5660 D(x): 0.9518 D(G(z)): 0.0023 / 0.0020\n",
"[63/4000][500/600] Loss_D: 0.0165 Loss_G: 6.8555 D(x): 0.9863 D(G(z)): 0.0018 / 0.0018\n",
"[64/4000][0/600] Loss_D: 0.0581 Loss_G: 4.6683 D(x): 0.9705 D(G(z)): 0.0233 / 0.0126\n",
"[64/4000][100/600] Loss_D: 0.0131 Loss_G: 5.4762 D(x): 0.9974 D(G(z)): 0.0104 / 0.0058\n",
"[64/4000][200/600] Loss_D: 0.0259 Loss_G: 6.0072 D(x): 0.9839 D(G(z)): 0.0065 / 0.0038\n",
"[64/4000][300/600] Loss_D: 0.0644 Loss_G: 3.4501 D(x): 0.9873 D(G(z)): 0.0463 / 0.0522\n",
"[64/4000][400/600] Loss_D: 0.0352 Loss_G: 6.9611 D(x): 0.9728 D(G(z)): 0.0040 / 0.0021\n",
"[64/4000][500/600] Loss_D: 0.0190 Loss_G: 6.5146 D(x): 0.9851 D(G(z)): 0.0016 / 0.0025\n",
"[65/4000][0/600] Loss_D: 0.0354 Loss_G: 3.6836 D(x): 0.9959 D(G(z)): 0.0304 / 0.0339\n",
"[65/4000][100/600] Loss_D: 0.0475 Loss_G: 5.4622 D(x): 0.9833 D(G(z)): 0.0086 / 0.0077\n",
"[65/4000][200/600] Loss_D: 0.0581 Loss_G: 5.4979 D(x): 0.9685 D(G(z)): 0.0147 / 0.0075\n",
"[65/4000][300/600] Loss_D: 0.0175 Loss_G: 4.8711 D(x): 0.9965 D(G(z)): 0.0137 / 0.0113\n",
"[65/4000][400/600] Loss_D: 0.0099 Loss_G: 6.2953 D(x): 0.9937 D(G(z)): 0.0034 / 0.0023\n",
"[65/4000][500/600] Loss_D: 0.0551 Loss_G: 5.0453 D(x): 0.9641 D(G(z)): 0.0071 / 0.0093\n",
"[66/4000][0/600] Loss_D: 0.0156 Loss_G: 7.1667 D(x): 0.9891 D(G(z)): 0.0036 / 0.0013\n",
"[66/4000][100/600] Loss_D: 0.0593 Loss_G: 5.5071 D(x): 0.9803 D(G(z)): 0.0131 / 0.0078\n",
"[66/4000][200/600] Loss_D: 0.0399 Loss_G: 6.0377 D(x): 0.9765 D(G(z)): 0.0082 / 0.0036\n",
"[66/4000][300/600] Loss_D: 0.0469 Loss_G: 3.8034 D(x): 0.9908 D(G(z)): 0.0351 / 0.0317\n",
"[66/4000][400/600] Loss_D: 0.0399 Loss_G: 7.7873 D(x): 0.9667 D(G(z)): 0.0013 / 0.0007\n",
"[66/4000][500/600] Loss_D: 0.0643 Loss_G: 3.9461 D(x): 0.9882 D(G(z)): 0.0447 / 0.0346\n",
"[67/4000][0/600] Loss_D: 0.0321 Loss_G: 5.1282 D(x): 0.9862 D(G(z)): 0.0137 / 0.0081\n",
"[67/4000][100/600] Loss_D: 0.0109 Loss_G: 5.6704 D(x): 0.9979 D(G(z)): 0.0087 / 0.0062\n",
"[67/4000][200/600] Loss_D: 0.0050 Loss_G: 7.6709 D(x): 0.9984 D(G(z)): 0.0032 / 0.0009\n",
"[67/4000][300/600] Loss_D: 0.0086 Loss_G: 6.4505 D(x): 0.9958 D(G(z)): 0.0042 / 0.0036\n",
"[67/4000][400/600] Loss_D: 0.1256 Loss_G: 5.6361 D(x): 0.9393 D(G(z)): 0.0050 / 0.0081\n",
"[67/4000][500/600] Loss_D: 0.0708 Loss_G: 6.0308 D(x): 0.9525 D(G(z)): 0.0041 / 0.0040\n",
"[68/4000][0/600] Loss_D: 0.0794 Loss_G: 5.7070 D(x): 0.9566 D(G(z)): 0.0118 / 0.0049\n",
"[68/4000][100/600] Loss_D: 0.0686 Loss_G: 3.5454 D(x): 0.9956 D(G(z)): 0.0602 / 0.0404\n",
"[68/4000][200/600] Loss_D: 0.0587 Loss_G: 6.7163 D(x): 0.9667 D(G(z)): 0.0117 / 0.0035\n",
"[68/4000][300/600] Loss_D: 0.0174 Loss_G: 5.7377 D(x): 0.9900 D(G(z)): 0.0067 / 0.0052\n",
"[68/4000][400/600] Loss_D: 0.0579 Loss_G: 5.2230 D(x): 0.9709 D(G(z)): 0.0129 / 0.0091\n",
"[68/4000][500/600] Loss_D: 0.0490 Loss_G: 7.2261 D(x): 0.9607 D(G(z)): 0.0014 / 0.0011\n",
"[69/4000][0/600] Loss_D: 0.0570 Loss_G: 4.0280 D(x): 0.9958 D(G(z)): 0.0495 / 0.0309\n",
"[69/4000][100/600] Loss_D: 0.0172 Loss_G: 5.4828 D(x): 0.9925 D(G(z)): 0.0091 / 0.0070\n",
"[69/4000][200/600] Loss_D: 0.0639 Loss_G: 4.0276 D(x): 0.9983 D(G(z)): 0.0585 / 0.0259\n",
"[69/4000][300/600] Loss_D: 0.0229 Loss_G: 5.0567 D(x): 0.9913 D(G(z)): 0.0130 / 0.0105\n",
"[69/4000][400/600] Loss_D: 0.0099 Loss_G: 6.3637 D(x): 0.9955 D(G(z)): 0.0052 / 0.0030\n",
"[69/4000][500/600] Loss_D: 0.0146 Loss_G: 5.8237 D(x): 0.9933 D(G(z)): 0.0076 / 0.0047\n",
"[70/4000][0/600] Loss_D: 0.0272 Loss_G: 4.3618 D(x): 0.9980 D(G(z)): 0.0247 / 0.0178\n",
"[70/4000][100/600] Loss_D: 0.0463 Loss_G: 4.5076 D(x): 0.9861 D(G(z)): 0.0246 / 0.0209\n",
"[70/4000][200/600] Loss_D: 0.0113 Loss_G: 6.5568 D(x): 0.9967 D(G(z)): 0.0079 / 0.0019\n",
"[70/4000][300/600] Loss_D: 0.0203 Loss_G: 4.6552 D(x): 0.9957 D(G(z)): 0.0156 / 0.0160\n",
"[70/4000][400/600] Loss_D: 0.0264 Loss_G: 5.5285 D(x): 0.9917 D(G(z)): 0.0164 / 0.0106\n",
"[70/4000][500/600] Loss_D: 0.0114 Loss_G: 6.0149 D(x): 0.9934 D(G(z)): 0.0045 / 0.0033\n",
"[71/4000][0/600] Loss_D: 0.0237 Loss_G: 7.5374 D(x): 0.9839 D(G(z)): 0.0046 / 0.0012\n",
"[71/4000][100/600] Loss_D: 0.0173 Loss_G: 6.0861 D(x): 0.9929 D(G(z)): 0.0088 / 0.0049\n",
"[71/4000][200/600] Loss_D: 0.0302 Loss_G: 5.1810 D(x): 0.9999 D(G(z)): 0.0290 / 0.0112\n",
"[71/4000][300/600] Loss_D: 0.0448 Loss_G: 5.1768 D(x): 0.9803 D(G(z)): 0.0100 / 0.0077\n",
"[71/4000][400/600] Loss_D: 0.0532 Loss_G: 7.1913 D(x): 0.9648 D(G(z)): 0.0056 / 0.0029\n",
"[71/4000][500/600] Loss_D: 0.0248 Loss_G: 6.4169 D(x): 0.9826 D(G(z)): 0.0042 / 0.0027\n",
"[72/4000][0/600] Loss_D: 0.0307 Loss_G: 7.3533 D(x): 0.9838 D(G(z)): 0.0037 / 0.0014\n",
"[72/4000][100/600] Loss_D: 0.0182 Loss_G: 6.0139 D(x): 0.9898 D(G(z)): 0.0062 / 0.0061\n",
"[72/4000][200/600] Loss_D: 0.0340 Loss_G: 5.3329 D(x): 0.9881 D(G(z)): 0.0099 / 0.0066\n",
"[72/4000][300/600] Loss_D: 0.0540 Loss_G: 3.3482 D(x): 0.9926 D(G(z)): 0.0433 / 0.0529\n",
"[72/4000][400/600] Loss_D: 0.0424 Loss_G: 7.6102 D(x): 0.9693 D(G(z)): 0.0030 / 0.0007\n",
"[72/4000][500/600] Loss_D: 0.0061 Loss_G: 7.7341 D(x): 0.9954 D(G(z)): 0.0014 / 0.0008\n",
"[73/4000][0/600] Loss_D: 0.1310 Loss_G: 3.3794 D(x): 0.9984 D(G(z)): 0.1130 / 0.0636\n",
"[73/4000][100/600] Loss_D: 0.0571 Loss_G: 7.5951 D(x): 0.9608 D(G(z)): 0.0014 / 0.0019\n",
"[73/4000][200/600] Loss_D: 0.0096 Loss_G: 6.2057 D(x): 0.9995 D(G(z)): 0.0086 / 0.0056\n",
"[73/4000][300/600] Loss_D: 0.0857 Loss_G: 5.9737 D(x): 0.9606 D(G(z)): 0.0040 / 0.0042\n",
"[73/4000][400/600] Loss_D: 0.0766 Loss_G: 4.4313 D(x): 0.9825 D(G(z)): 0.0433 / 0.0212\n",
"[73/4000][500/600] Loss_D: 0.0691 Loss_G: 5.2992 D(x): 0.9577 D(G(z)): 0.0046 / 0.0081\n",
"[74/4000][0/600] Loss_D: 0.3534 Loss_G: 3.9915 D(x): 0.9999 D(G(z)): 0.2791 / 0.0261\n",
"[74/4000][100/600] Loss_D: 0.0233 Loss_G: 6.7626 D(x): 0.9840 D(G(z)): 0.0014 / 0.0018\n",
"[74/4000][200/600] Loss_D: 0.0310 Loss_G: 4.5151 D(x): 0.9994 D(G(z)): 0.0296 / 0.0156\n",
"[74/4000][300/600] Loss_D: 0.0373 Loss_G: 3.8110 D(x): 0.9937 D(G(z)): 0.0287 / 0.0318\n",
"[74/4000][400/600] Loss_D: 0.0286 Loss_G: 5.1935 D(x): 0.9849 D(G(z)): 0.0108 / 0.0084\n",
"[74/4000][500/600] Loss_D: 0.0169 Loss_G: 6.6794 D(x): 0.9877 D(G(z)): 0.0019 / 0.0018\n",
"[75/4000][0/600] Loss_D: 0.0774 Loss_G: 9.6187 D(x): 0.9547 D(G(z)): 0.0005 / 0.0002\n",
"[75/4000][100/600] Loss_D: 0.0494 Loss_G: 4.1838 D(x): 0.9987 D(G(z)): 0.0463 / 0.0200\n",
"[75/4000][200/600] Loss_D: 0.0951 Loss_G: 4.9381 D(x): 0.9675 D(G(z)): 0.0401 / 0.0111\n",
"[75/4000][300/600] Loss_D: 0.0366 Loss_G: 4.3679 D(x): 0.9834 D(G(z)): 0.0168 / 0.0221\n",
"[75/4000][400/600] Loss_D: 0.0186 Loss_G: 4.9118 D(x): 0.9993 D(G(z)): 0.0174 / 0.0143\n",
"[75/4000][500/600] Loss_D: 0.0088 Loss_G: 6.3192 D(x): 0.9948 D(G(z)): 0.0034 / 0.0027\n",
"[76/4000][0/600] Loss_D: 0.0798 Loss_G: 3.8517 D(x): 0.9998 D(G(z)): 0.0733 / 0.0342\n",
"[76/4000][100/600] Loss_D: 0.0111 Loss_G: 5.8538 D(x): 0.9952 D(G(z)): 0.0060 / 0.0047\n",
"[76/4000][200/600] Loss_D: 0.0315 Loss_G: 5.1758 D(x): 0.9886 D(G(z)): 0.0138 / 0.0105\n",
"[76/4000][300/600] Loss_D: 0.0395 Loss_G: 5.9776 D(x): 0.9781 D(G(z)): 0.0070 / 0.0055\n",
"[76/4000][400/600] Loss_D: 0.0591 Loss_G: 4.7402 D(x): 0.9663 D(G(z)): 0.0162 / 0.0108\n",
"[76/4000][500/600] Loss_D: 0.0149 Loss_G: 5.4019 D(x): 0.9914 D(G(z)): 0.0059 / 0.0063\n",
"[77/4000][0/600] Loss_D: 0.0202 Loss_G: 6.4982 D(x): 0.9848 D(G(z)): 0.0019 / 0.0020\n",
"[77/4000][100/600] Loss_D: 0.0141 Loss_G: 7.3993 D(x): 0.9909 D(G(z)): 0.0041 / 0.0014\n",
"[77/4000][200/600] Loss_D: 0.0329 Loss_G: 7.4390 D(x): 0.9770 D(G(z)): 0.0040 / 0.0009\n",
"[77/4000][300/600] Loss_D: 0.0255 Loss_G: 6.2294 D(x): 0.9889 D(G(z)): 0.0096 / 0.0068\n",
"[77/4000][400/600] Loss_D: 0.0163 Loss_G: 6.3106 D(x): 0.9950 D(G(z)): 0.0105 / 0.0028\n",
"[77/4000][500/600] Loss_D: 0.0219 Loss_G: 6.7109 D(x): 0.9864 D(G(z)): 0.0041 / 0.0025\n",
"[78/4000][0/600] Loss_D: 0.0837 Loss_G: 3.2544 D(x): 0.9927 D(G(z)): 0.0685 / 0.0643\n",
"[78/4000][100/600] Loss_D: 0.0325 Loss_G: 6.0012 D(x): 0.9791 D(G(z)): 0.0033 / 0.0036\n",
"[78/4000][200/600] Loss_D: 0.0186 Loss_G: 7.6826 D(x): 0.9883 D(G(z)): 0.0048 / 0.0008\n",
"[78/4000][300/600] Loss_D: 0.0691 Loss_G: 4.4508 D(x): 0.9754 D(G(z)): 0.0168 / 0.0160\n",
"[78/4000][400/600] Loss_D: 0.0160 Loss_G: 6.3330 D(x): 0.9909 D(G(z)): 0.0063 / 0.0028\n",
"[78/4000][500/600] Loss_D: 0.0507 Loss_G: 6.3826 D(x): 0.9824 D(G(z)): 0.0062 / 0.0032\n",
"[79/4000][0/600] Loss_D: 0.0186 Loss_G: 6.0574 D(x): 0.9896 D(G(z)): 0.0072 / 0.0037\n",
"[79/4000][100/600] Loss_D: 0.0260 Loss_G: 4.2779 D(x): 0.9945 D(G(z)): 0.0195 / 0.0201\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[79/4000][200/600] Loss_D: 0.0080 Loss_G: 6.1510 D(x): 0.9980 D(G(z)): 0.0059 / 0.0032\n",
"[79/4000][300/600] Loss_D: 0.0138 Loss_G: 7.5473 D(x): 0.9891 D(G(z)): 0.0011 / 0.0011\n",
"[79/4000][400/600] Loss_D: 0.0524 Loss_G: 4.7939 D(x): 0.9791 D(G(z)): 0.0230 / 0.0139\n",
"[79/4000][500/600] Loss_D: 0.1064 Loss_G: 7.5499 D(x): 0.9388 D(G(z)): 0.0007 / 0.0008\n",
"[80/4000][0/600] Loss_D: 0.0465 Loss_G: 2.8720 D(x): 0.9991 D(G(z)): 0.0435 / 0.0917\n",
"[80/4000][100/600] Loss_D: 0.0125 Loss_G: 5.8585 D(x): 0.9975 D(G(z)): 0.0098 / 0.0040\n",
"[80/4000][200/600] Loss_D: 0.0233 Loss_G: 5.1494 D(x): 0.9998 D(G(z)): 0.0225 / 0.0103\n",
"[80/4000][300/600] Loss_D: 0.1094 Loss_G: 5.9639 D(x): 0.9437 D(G(z)): 0.0045 / 0.0040\n",
"[80/4000][400/600] Loss_D: 0.0871 Loss_G: 3.9321 D(x): 0.9928 D(G(z)): 0.0739 / 0.0309\n",
"[80/4000][500/600] Loss_D: 0.0112 Loss_G: 9.3177 D(x): 0.9898 D(G(z)): 0.0003 / 0.0002\n",
"[81/4000][0/600] Loss_D: 0.0140 Loss_G: 6.6058 D(x): 0.9924 D(G(z)): 0.0055 / 0.0023\n",
"[81/4000][100/600] Loss_D: 0.0258 Loss_G: 5.1318 D(x): 0.9966 D(G(z)): 0.0213 / 0.0116\n",
"[81/4000][200/600] Loss_D: 0.0311 Loss_G: 5.1572 D(x): 0.9983 D(G(z)): 0.0284 / 0.0121\n",
"[81/4000][300/600] Loss_D: 0.0318 Loss_G: 6.4956 D(x): 0.9822 D(G(z)): 0.0031 / 0.0032\n",
"[81/4000][400/600] Loss_D: 0.0088 Loss_G: 5.6437 D(x): 0.9987 D(G(z)): 0.0075 / 0.0051\n",
"[81/4000][500/600] Loss_D: 0.0231 Loss_G: 5.6180 D(x): 0.9849 D(G(z)): 0.0035 / 0.0056\n",
"[82/4000][0/600] Loss_D: 0.2068 Loss_G: 11.7429 D(x): 0.9023 D(G(z)): 0.0001 / 0.0000\n",
"[82/4000][100/600] Loss_D: 0.0908 Loss_G: 3.9470 D(x): 0.9994 D(G(z)): 0.0779 / 0.0668\n",
"[82/4000][200/600] Loss_D: 0.0130 Loss_G: 5.8660 D(x): 0.9967 D(G(z)): 0.0096 / 0.0035\n",
"[82/4000][300/600] Loss_D: 0.0390 Loss_G: 4.4446 D(x): 0.9890 D(G(z)): 0.0212 / 0.0194\n",
"[82/4000][400/600] Loss_D: 0.0239 Loss_G: 5.2717 D(x): 0.9946 D(G(z)): 0.0178 / 0.0070\n",
"[82/4000][500/600] Loss_D: 0.0142 Loss_G: 6.3259 D(x): 0.9908 D(G(z)): 0.0037 / 0.0023\n",
"[83/4000][0/600] Loss_D: 0.0147 Loss_G: 5.1139 D(x): 0.9968 D(G(z)): 0.0111 / 0.0115\n",
"[83/4000][100/600] Loss_D: 0.0090 Loss_G: 6.0662 D(x): 0.9974 D(G(z)): 0.0062 / 0.0042\n",
"[83/4000][200/600] Loss_D: 0.0070 Loss_G: 6.3383 D(x): 0.9960 D(G(z)): 0.0028 / 0.0030\n",
"[83/4000][300/600] Loss_D: 0.0113 Loss_G: 6.3072 D(x): 0.9940 D(G(z)): 0.0045 / 0.0031\n",
"[83/4000][400/600] Loss_D: 0.0332 Loss_G: 6.3654 D(x): 0.9784 D(G(z)): 0.0051 / 0.0029\n",
"[83/4000][500/600] Loss_D: 0.0104 Loss_G: 6.0089 D(x): 0.9923 D(G(z)): 0.0024 / 0.0034\n",
"[84/4000][0/600] Loss_D: 0.0240 Loss_G: 7.4294 D(x): 0.9820 D(G(z)): 0.0032 / 0.0009\n",
"[84/4000][100/600] Loss_D: 0.0155 Loss_G: 5.7492 D(x): 0.9914 D(G(z)): 0.0066 / 0.0055\n",
"[84/4000][200/600] Loss_D: 0.0273 Loss_G: 5.8773 D(x): 0.9968 D(G(z)): 0.0232 / 0.0038\n",
"[84/4000][300/600] Loss_D: 0.1935 Loss_G: 5.7464 D(x): 0.9163 D(G(z)): 0.0012 / 0.0047\n",
"[84/4000][400/600] Loss_D: 0.0118 Loss_G: 5.7657 D(x): 0.9949 D(G(z)): 0.0064 / 0.0042\n",
"[84/4000][500/600] Loss_D: 0.0625 Loss_G: 5.7797 D(x): 0.9672 D(G(z)): 0.0032 / 0.0046\n",
"[85/4000][0/600] Loss_D: 0.0785 Loss_G: 3.8528 D(x): 0.9930 D(G(z)): 0.0666 / 0.0321\n",
"[85/4000][100/600] Loss_D: 0.0110 Loss_G: 5.8654 D(x): 0.9963 D(G(z)): 0.0070 / 0.0049\n",
"[85/4000][200/600] Loss_D: 0.0177 Loss_G: 5.7423 D(x): 0.9985 D(G(z)): 0.0158 / 0.0071\n",
"[85/4000][300/600] Loss_D: 0.0252 Loss_G: 5.2248 D(x): 0.9931 D(G(z)): 0.0175 / 0.0104\n",
"[85/4000][400/600] Loss_D: 0.0768 Loss_G: 5.2523 D(x): 0.9635 D(G(z)): 0.0075 / 0.0087\n",
"[85/4000][500/600] Loss_D: 0.0573 Loss_G: 4.5027 D(x): 0.9813 D(G(z)): 0.0262 / 0.0194\n",
"[86/4000][0/600] Loss_D: 0.0574 Loss_G: 4.4162 D(x): 0.9963 D(G(z)): 0.0501 / 0.0194\n",
"[86/4000][100/600] Loss_D: 0.0685 Loss_G: 6.2291 D(x): 0.9626 D(G(z)): 0.0034 / 0.0059\n",
"[86/4000][200/600] Loss_D: 0.0217 Loss_G: 8.7058 D(x): 0.9854 D(G(z)): 0.0003 / 0.0002\n",
"[86/4000][300/600] Loss_D: 0.0695 Loss_G: 4.7411 D(x): 0.9597 D(G(z)): 0.0095 / 0.0132\n",
"[86/4000][400/600] Loss_D: 0.0609 Loss_G: 5.4478 D(x): 0.9643 D(G(z)): 0.0074 / 0.0076\n",
"[86/4000][500/600] Loss_D: 0.0345 Loss_G: 5.5291 D(x): 0.9784 D(G(z)): 0.0094 / 0.0080\n",
"[87/4000][0/600] Loss_D: 0.0233 Loss_G: 4.8125 D(x): 0.9936 D(G(z)): 0.0163 / 0.0153\n",
"[87/4000][100/600] Loss_D: 0.0090 Loss_G: 5.6359 D(x): 0.9959 D(G(z)): 0.0048 / 0.0048\n",
"[87/4000][200/600] Loss_D: 0.0254 Loss_G: 6.0518 D(x): 0.9878 D(G(z)): 0.0049 / 0.0043\n",
"[87/4000][300/600] Loss_D: 0.0657 Loss_G: 5.4723 D(x): 0.9649 D(G(z)): 0.0058 / 0.0067\n",
"[87/4000][400/600] Loss_D: 0.0157 Loss_G: 6.3700 D(x): 0.9907 D(G(z)): 0.0059 / 0.0022\n",
"[87/4000][500/600] Loss_D: 0.0162 Loss_G: 5.0480 D(x): 0.9949 D(G(z)): 0.0107 / 0.0093\n",
"[88/4000][0/600] Loss_D: 0.0940 Loss_G: 8.1145 D(x): 0.9358 D(G(z)): 0.0017 / 0.0005\n",
"[88/4000][100/600] Loss_D: 0.2523 Loss_G: 11.0974 D(x): 0.8961 D(G(z)): 0.0001 / 0.0000\n",
"[88/4000][200/600] Loss_D: 0.0364 Loss_G: 5.5070 D(x): 0.9948 D(G(z)): 0.0295 / 0.0076\n",
"[88/4000][300/600] Loss_D: 0.0222 Loss_G: 7.8858 D(x): 0.9825 D(G(z)): 0.0009 / 0.0007\n",
"[88/4000][400/600] Loss_D: 0.0594 Loss_G: 5.4400 D(x): 0.9708 D(G(z)): 0.0151 / 0.0079\n",
"[88/4000][500/600] Loss_D: 0.0639 Loss_G: 3.9783 D(x): 0.9809 D(G(z)): 0.0359 / 0.0354\n",
"[89/4000][0/600] Loss_D: 0.0712 Loss_G: 4.2183 D(x): 0.9984 D(G(z)): 0.0644 / 0.0229\n",
"[89/4000][100/600] Loss_D: 0.0510 Loss_G: 5.8407 D(x): 0.9648 D(G(z)): 0.0040 / 0.0055\n",
"[89/4000][200/600] Loss_D: 0.0144 Loss_G: 4.9478 D(x): 0.9988 D(G(z)): 0.0130 / 0.0113\n",
"[89/4000][300/600] Loss_D: 0.0951 Loss_G: 6.0169 D(x): 0.9478 D(G(z)): 0.0042 / 0.0041\n",
"[89/4000][400/600] Loss_D: 0.0500 Loss_G: 5.2406 D(x): 0.9784 D(G(z)): 0.0127 / 0.0086\n",
"[89/4000][500/600] Loss_D: 0.0906 Loss_G: 5.0283 D(x): 0.9686 D(G(z)): 0.0115 / 0.0113\n",
"[90/4000][0/600] Loss_D: 0.0364 Loss_G: 7.2007 D(x): 0.9837 D(G(z)): 0.0053 / 0.0017\n",
"[90/4000][100/600] Loss_D: 0.0218 Loss_G: 5.0574 D(x): 0.9960 D(G(z)): 0.0167 / 0.0164\n",
"[90/4000][200/600] Loss_D: 0.0721 Loss_G: 7.4805 D(x): 0.9646 D(G(z)): 0.0027 / 0.0009\n",
"[90/4000][300/600] Loss_D: 0.0114 Loss_G: 6.3896 D(x): 0.9956 D(G(z)): 0.0068 / 0.0029\n",
"[90/4000][400/600] Loss_D: 0.0985 Loss_G: 7.1734 D(x): 0.9397 D(G(z)): 0.0037 / 0.0020\n",
"[90/4000][500/600] Loss_D: 0.0284 Loss_G: 4.8324 D(x): 0.9906 D(G(z)): 0.0164 / 0.0157\n",
"[91/4000][0/600] Loss_D: 0.0147 Loss_G: 6.0541 D(x): 0.9942 D(G(z)): 0.0087 / 0.0038\n",
"[91/4000][100/600] Loss_D: 0.0271 Loss_G: 5.6182 D(x): 0.9902 D(G(z)): 0.0111 / 0.0083\n",
"[91/4000][200/600] Loss_D: 0.0172 Loss_G: 5.0920 D(x): 0.9954 D(G(z)): 0.0123 / 0.0106\n",
"[91/4000][300/600] Loss_D: 0.0331 Loss_G: 4.8196 D(x): 0.9927 D(G(z)): 0.0230 / 0.0153\n",
"[91/4000][400/600] Loss_D: 0.0237 Loss_G: 7.1809 D(x): 0.9875 D(G(z)): 0.0037 / 0.0015\n",
"[91/4000][500/600] Loss_D: 0.0392 Loss_G: 5.3551 D(x): 0.9702 D(G(z)): 0.0046 / 0.0070\n",
"[92/4000][0/600] Loss_D: 0.0116 Loss_G: 5.5869 D(x): 0.9954 D(G(z)): 0.0068 / 0.0054\n",
"[92/4000][100/600] Loss_D: 0.0136 Loss_G: 5.5625 D(x): 0.9950 D(G(z)): 0.0078 / 0.0053\n",
"[92/4000][200/600] Loss_D: 0.0123 Loss_G: 6.0353 D(x): 0.9938 D(G(z)): 0.0036 / 0.0033\n",
"[92/4000][300/600] Loss_D: 0.0144 Loss_G: 4.4787 D(x): 0.9992 D(G(z)): 0.0134 / 0.0171\n",
"[92/4000][400/600] Loss_D: 0.0168 Loss_G: 5.2140 D(x): 0.9971 D(G(z)): 0.0136 / 0.0077\n",
"[92/4000][500/600] Loss_D: 0.0664 Loss_G: 5.1415 D(x): 0.9706 D(G(z)): 0.0093 / 0.0089\n",
"[93/4000][0/600] Loss_D: 0.0300 Loss_G: 6.3588 D(x): 0.9818 D(G(z)): 0.0060 / 0.0030\n",
"[93/4000][100/600] Loss_D: 0.0157 Loss_G: 5.5486 D(x): 0.9939 D(G(z)): 0.0091 / 0.0089\n",
"[93/4000][200/600] Loss_D: 0.0262 Loss_G: 5.0458 D(x): 0.9995 D(G(z)): 0.0250 / 0.0112\n",
"[93/4000][300/600] Loss_D: 0.1272 Loss_G: 6.3623 D(x): 0.9274 D(G(z)): 0.0007 / 0.0033\n",
"[93/4000][400/600] Loss_D: 0.0594 Loss_G: 4.3573 D(x): 0.9722 D(G(z)): 0.0212 / 0.0248\n",
"[93/4000][500/600] Loss_D: 0.0270 Loss_G: 6.1542 D(x): 0.9835 D(G(z)): 0.0053 / 0.0038\n",
"[94/4000][0/600] Loss_D: 0.0185 Loss_G: 4.1406 D(x): 0.9990 D(G(z)): 0.0171 / 0.0263\n",
"[94/4000][100/600] Loss_D: 0.0434 Loss_G: 4.4047 D(x): 0.9874 D(G(z)): 0.0282 / 0.0187\n",
"[94/4000][200/600] Loss_D: 0.0119 Loss_G: 6.2143 D(x): 0.9948 D(G(z)): 0.0065 / 0.0031\n",
"[94/4000][300/600] Loss_D: 0.0290 Loss_G: 5.9852 D(x): 0.9805 D(G(z)): 0.0045 / 0.0042\n",
"[94/4000][400/600] Loss_D: 0.0185 Loss_G: 6.0606 D(x): 0.9905 D(G(z)): 0.0083 / 0.0039\n",
"[94/4000][500/600] Loss_D: 0.0268 Loss_G: 4.4209 D(x): 0.9937 D(G(z)): 0.0196 / 0.0197\n",
"[95/4000][0/600] Loss_D: 0.0067 Loss_G: 7.1059 D(x): 0.9982 D(G(z)): 0.0048 / 0.0018\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[95/4000][100/600] Loss_D: 0.0342 Loss_G: 4.8496 D(x): 0.9990 D(G(z)): 0.0319 / 0.0146\n",
"[95/4000][200/600] Loss_D: 0.0306 Loss_G: 5.9187 D(x): 0.9890 D(G(z)): 0.0143 / 0.0043\n",
"[95/4000][300/600] Loss_D: 0.0116 Loss_G: 5.5698 D(x): 0.9991 D(G(z)): 0.0105 / 0.0097\n",
"[95/4000][400/600] Loss_D: 0.0103 Loss_G: 6.2059 D(x): 0.9961 D(G(z)): 0.0062 / 0.0036\n",
"[95/4000][500/600] Loss_D: 0.0045 Loss_G: 6.0662 D(x): 0.9984 D(G(z)): 0.0028 / 0.0033\n",
"[96/4000][0/600] Loss_D: 0.0059 Loss_G: 5.9425 D(x): 0.9984 D(G(z)): 0.0042 / 0.0038\n",
"[96/4000][100/600] Loss_D: 0.0466 Loss_G: 5.9024 D(x): 0.9725 D(G(z)): 0.0065 / 0.0058\n",
"[96/4000][200/600] Loss_D: 0.0318 Loss_G: 7.9483 D(x): 0.9833 D(G(z)): 0.0022 / 0.0006\n",
"[96/4000][300/600] Loss_D: 0.0112 Loss_G: 10.0428 D(x): 0.9898 D(G(z)): 0.0002 / 0.0001\n",
"[96/4000][400/600] Loss_D: 0.0401 Loss_G: 6.0794 D(x): 0.9806 D(G(z)): 0.0136 / 0.0034\n",
"[96/4000][500/600] Loss_D: 0.0129 Loss_G: 6.0008 D(x): 0.9947 D(G(z)): 0.0063 / 0.0040\n",
"[97/4000][0/600] Loss_D: 0.0068 Loss_G: 5.9932 D(x): 0.9994 D(G(z)): 0.0061 / 0.0051\n",
"[97/4000][100/600] Loss_D: 0.0117 Loss_G: 5.1045 D(x): 0.9994 D(G(z)): 0.0109 / 0.0092\n",
"[97/4000][200/600] Loss_D: 0.0143 Loss_G: 5.7177 D(x): 0.9995 D(G(z)): 0.0133 / 0.0061\n",
"[97/4000][300/600] Loss_D: 0.0965 Loss_G: 5.5103 D(x): 0.9570 D(G(z)): 0.0033 / 0.0061\n",
"[97/4000][400/600] Loss_D: 0.0885 Loss_G: 3.3838 D(x): 0.9811 D(G(z)): 0.0602 / 0.0395\n",
"[97/4000][500/600] Loss_D: 0.1144 Loss_G: 3.8144 D(x): 0.9663 D(G(z)): 0.0266 / 0.0295\n",
"[98/4000][0/600] Loss_D: 0.0107 Loss_G: 5.2687 D(x): 0.9979 D(G(z)): 0.0085 / 0.0070\n",
"[98/4000][100/600] Loss_D: 0.0098 Loss_G: 9.2806 D(x): 0.9914 D(G(z)): 0.0006 / 0.0002\n",
"[98/4000][200/600] Loss_D: 0.0138 Loss_G: 9.3767 D(x): 0.9881 D(G(z)): 0.0013 / 0.0002\n",
"[98/4000][300/600] Loss_D: 0.0146 Loss_G: 5.8655 D(x): 0.9944 D(G(z)): 0.0087 / 0.0084\n",
"[98/4000][400/600] Loss_D: 0.0174 Loss_G: 4.7542 D(x): 0.9986 D(G(z)): 0.0157 / 0.0159\n",
"[98/4000][500/600] Loss_D: 0.0220 Loss_G: 5.7759 D(x): 0.9856 D(G(z)): 0.0058 / 0.0043\n",
"[99/4000][0/600] Loss_D: 0.0484 Loss_G: 8.9349 D(x): 0.9676 D(G(z)): 0.0002 / 0.0002\n",
"[99/4000][100/600] Loss_D: 0.0556 Loss_G: 4.8826 D(x): 0.9830 D(G(z)): 0.0288 / 0.0107\n",
"[99/4000][200/600] Loss_D: 0.0179 Loss_G: 5.6804 D(x): 0.9972 D(G(z)): 0.0147 / 0.0044\n",
"[99/4000][300/600] Loss_D: 0.0238 Loss_G: 4.7208 D(x): 0.9969 D(G(z)): 0.0200 / 0.0119\n",
"[99/4000][400/600] Loss_D: 0.0479 Loss_G: 4.2749 D(x): 0.9873 D(G(z)): 0.0304 / 0.0264\n",
"[99/4000][500/600] Loss_D: 0.0094 Loss_G: 5.9392 D(x): 0.9982 D(G(z)): 0.0075 / 0.0056\n",
"[100/4000][0/600] Loss_D: 0.0258 Loss_G: 6.3243 D(x): 0.9864 D(G(z)): 0.0075 / 0.0032\n",
"[100/4000][100/600] Loss_D: 0.0249 Loss_G: 5.3388 D(x): 0.9882 D(G(z)): 0.0096 / 0.0079\n",
"[100/4000][200/600] Loss_D: 0.0518 Loss_G: 4.3115 D(x): 0.9999 D(G(z)): 0.0486 / 0.0212\n",
"[100/4000][300/600] Loss_D: 0.0293 Loss_G: 6.2319 D(x): 0.9779 D(G(z)): 0.0042 / 0.0026\n",
"[100/4000][400/600] Loss_D: 0.0484 Loss_G: 5.2291 D(x): 0.9790 D(G(z)): 0.0145 / 0.0087\n",
"[100/4000][500/600] Loss_D: 0.0424 Loss_G: 4.4553 D(x): 0.9846 D(G(z)): 0.0159 / 0.0148\n",
"[101/4000][0/600] Loss_D: 0.0172 Loss_G: 6.2510 D(x): 0.9899 D(G(z)): 0.0063 / 0.0030\n",
"[101/4000][100/600] Loss_D: 0.0114 Loss_G: 6.0162 D(x): 0.9942 D(G(z)): 0.0055 / 0.0033\n",
"[101/4000][200/600] Loss_D: 0.0335 Loss_G: 8.9405 D(x): 0.9726 D(G(z)): 0.0010 / 0.0002\n",
"[101/4000][300/600] Loss_D: 0.0225 Loss_G: 5.6299 D(x): 0.9884 D(G(z)): 0.0097 / 0.0050\n",
"[101/4000][400/600] Loss_D: 0.0166 Loss_G: 6.4816 D(x): 0.9885 D(G(z)): 0.0043 / 0.0029\n",
"[101/4000][500/600] Loss_D: 0.0269 Loss_G: 4.2495 D(x): 0.9972 D(G(z)): 0.0235 / 0.0196\n",
"[102/4000][0/600] Loss_D: 0.0093 Loss_G: 5.6286 D(x): 0.9965 D(G(z)): 0.0056 / 0.0052\n",
"[102/4000][100/600] Loss_D: 0.0274 Loss_G: 5.7548 D(x): 0.9956 D(G(z)): 0.0202 / 0.0099\n",
"[102/4000][200/600] Loss_D: 0.0138 Loss_G: 6.2278 D(x): 0.9934 D(G(z)): 0.0065 / 0.0028\n",
"[102/4000][300/600] Loss_D: 0.0110 Loss_G: 6.0323 D(x): 0.9966 D(G(z)): 0.0075 / 0.0034\n",
"[102/4000][400/600] Loss_D: 0.0922 Loss_G: 4.9933 D(x): 0.9766 D(G(z)): 0.0181 / 0.0107\n",
"[102/4000][500/600] Loss_D: 0.0203 Loss_G: 8.2900 D(x): 0.9846 D(G(z)): 0.0006 / 0.0005\n",
"[103/4000][0/600] Loss_D: 0.0070 Loss_G: 6.3482 D(x): 0.9965 D(G(z)): 0.0034 / 0.0028\n",
"[103/4000][100/600] Loss_D: 0.0279 Loss_G: 5.2230 D(x): 0.9986 D(G(z)): 0.0257 / 0.0131\n",
"[103/4000][200/600] Loss_D: 0.0411 Loss_G: 4.8738 D(x): 0.9981 D(G(z)): 0.0369 / 0.0145\n",
"[103/4000][300/600] Loss_D: 0.0203 Loss_G: 4.2419 D(x): 0.9989 D(G(z)): 0.0187 / 0.0241\n",
"[103/4000][400/600] Loss_D: 0.0982 Loss_G: 6.5540 D(x): 0.9408 D(G(z)): 0.0033 / 0.0027\n",
"[103/4000][500/600] Loss_D: 0.0249 Loss_G: 5.8928 D(x): 0.9861 D(G(z)): 0.0052 / 0.0039\n",
"[104/4000][0/600] Loss_D: 0.1213 Loss_G: 2.5168 D(x): 0.9996 D(G(z)): 0.1049 / 0.1417\n",
"[104/4000][100/600] Loss_D: 0.0107 Loss_G: 7.3029 D(x): 0.9925 D(G(z)): 0.0027 / 0.0026\n",
"[104/4000][200/600] Loss_D: 0.0081 Loss_G: 5.6789 D(x): 0.9993 D(G(z)): 0.0074 / 0.0056\n",
"[104/4000][300/600] Loss_D: 0.0650 Loss_G: 5.0095 D(x): 0.9649 D(G(z)): 0.0074 / 0.0082\n",
"[104/4000][400/600] Loss_D: 0.0436 Loss_G: 4.7850 D(x): 0.9826 D(G(z)): 0.0210 / 0.0141\n",
"[104/4000][500/600] Loss_D: 0.0152 Loss_G: 5.0897 D(x): 0.9979 D(G(z)): 0.0128 / 0.0102\n",
"[105/4000][0/600] Loss_D: 0.0434 Loss_G: 4.0893 D(x): 0.9983 D(G(z)): 0.0402 / 0.0238\n",
"[105/4000][100/600] Loss_D: 0.0107 Loss_G: 6.4639 D(x): 0.9944 D(G(z)): 0.0047 / 0.0043\n",
"[105/4000][200/600] Loss_D: 0.0242 Loss_G: 5.2817 D(x): 0.9938 D(G(z)): 0.0174 / 0.0098\n",
"[105/4000][300/600] Loss_D: 0.0172 Loss_G: 5.8718 D(x): 0.9909 D(G(z)): 0.0051 / 0.0048\n",
"[105/4000][400/600] Loss_D: 0.0379 Loss_G: 4.5974 D(x): 0.9933 D(G(z)): 0.0299 / 0.0150\n",
"[105/4000][500/600] Loss_D: 0.0279 Loss_G: 4.8662 D(x): 0.9886 D(G(z)): 0.0147 / 0.0107\n",
"[106/4000][0/600] Loss_D: 0.1050 Loss_G: 9.4208 D(x): 0.9368 D(G(z)): 0.0002 / 0.0002\n",
"[106/4000][100/600] Loss_D: 0.0381 Loss_G: 5.2959 D(x): 0.9826 D(G(z)): 0.0074 / 0.0076\n",
"[106/4000][200/600] Loss_D: 0.0334 Loss_G: 4.6999 D(x): 0.9856 D(G(z)): 0.0151 / 0.0155\n",
"[106/4000][300/600] Loss_D: 0.0128 Loss_G: 6.2805 D(x): 0.9908 D(G(z)): 0.0031 / 0.0029\n",
"[106/4000][400/600] Loss_D: 0.0192 Loss_G: 4.9422 D(x): 0.9984 D(G(z)): 0.0172 / 0.0139\n",
"[106/4000][500/600] Loss_D: 0.0160 Loss_G: 5.1852 D(x): 0.9925 D(G(z)): 0.0078 / 0.0081\n",
"[107/4000][0/600] Loss_D: 0.1360 Loss_G: 10.6186 D(x): 0.9300 D(G(z)): 0.0001 / 0.0001\n",
"[107/4000][100/600] Loss_D: 0.0200 Loss_G: 5.9243 D(x): 0.9920 D(G(z)): 0.0110 / 0.0052\n",
"[107/4000][200/600] Loss_D: 0.0129 Loss_G: 7.1352 D(x): 0.9903 D(G(z)): 0.0015 / 0.0014\n",
"[107/4000][300/600] Loss_D: 0.0634 Loss_G: 5.8193 D(x): 0.9571 D(G(z)): 0.0031 / 0.0048\n",
"[107/4000][400/600] Loss_D: 0.0139 Loss_G: 5.2395 D(x): 0.9926 D(G(z)): 0.0062 / 0.0086\n",
"[107/4000][500/600] Loss_D: 0.0492 Loss_G: 6.8845 D(x): 0.9648 D(G(z)): 0.0010 / 0.0014\n",
"[108/4000][0/600] Loss_D: 0.3708 Loss_G: 12.0550 D(x): 0.8057 D(G(z)): 0.0000 / 0.0000\n",
"[108/4000][100/600] Loss_D: 0.0548 Loss_G: 4.4697 D(x): 0.9912 D(G(z)): 0.0373 / 0.0226\n",
"[108/4000][200/600] Loss_D: 0.0254 Loss_G: 4.4543 D(x): 0.9970 D(G(z)): 0.0218 / 0.0198\n",
"[108/4000][300/600] Loss_D: 0.0816 Loss_G: 3.8452 D(x): 0.9638 D(G(z)): 0.0254 / 0.0316\n",
"[108/4000][400/600] Loss_D: 0.0264 Loss_G: 5.7544 D(x): 0.9867 D(G(z)): 0.0090 / 0.0057\n",
"[108/4000][500/600] Loss_D: 0.0186 Loss_G: 4.5680 D(x): 0.9945 D(G(z)): 0.0116 / 0.0180\n",
"[109/4000][0/600] Loss_D: 0.0572 Loss_G: 4.6743 D(x): 0.9989 D(G(z)): 0.0533 / 0.0142\n",
"[109/4000][100/600] Loss_D: 0.0258 Loss_G: 5.6626 D(x): 0.9838 D(G(z)): 0.0037 / 0.0045\n",
"[109/4000][200/600] Loss_D: 0.0025 Loss_G: 7.1250 D(x): 1.0000 D(G(z)): 0.0024 / 0.0022\n",
"[109/4000][300/600] Loss_D: 0.0041 Loss_G: 8.1162 D(x): 0.9974 D(G(z)): 0.0015 / 0.0006\n",
"[109/4000][400/600] Loss_D: 0.0393 Loss_G: 6.9964 D(x): 0.9730 D(G(z)): 0.0022 / 0.0013\n",
"[109/4000][500/600] Loss_D: 0.0142 Loss_G: 6.3517 D(x): 0.9905 D(G(z)): 0.0034 / 0.0028\n",
"[110/4000][0/600] Loss_D: 0.0137 Loss_G: 5.5542 D(x): 0.9954 D(G(z)): 0.0086 / 0.0067\n",
"[110/4000][100/600] Loss_D: 0.0198 Loss_G: 5.9869 D(x): 0.9917 D(G(z)): 0.0069 / 0.0071\n",
"[110/4000][200/600] Loss_D: 0.0602 Loss_G: 4.4377 D(x): 0.9999 D(G(z)): 0.0556 / 0.0232\n",
"[110/4000][300/600] Loss_D: 0.0048 Loss_G: 7.4880 D(x): 0.9971 D(G(z)): 0.0019 / 0.0009\n",
"[110/4000][400/600] Loss_D: 0.0302 Loss_G: 4.5230 D(x): 0.9969 D(G(z)): 0.0262 / 0.0171\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[110/4000][500/600] Loss_D: 0.0082 Loss_G: 7.1025 D(x): 0.9947 D(G(z)): 0.0022 / 0.0015\n",
"[111/4000][0/600] Loss_D: 0.0069 Loss_G: 9.0722 D(x): 0.9942 D(G(z)): 0.0004 / 0.0002\n",
"[111/4000][100/600] Loss_D: 0.0064 Loss_G: 6.3419 D(x): 0.9995 D(G(z)): 0.0058 / 0.0033\n",
"[111/4000][200/600] Loss_D: 0.0168 Loss_G: 5.9142 D(x): 0.9999 D(G(z)): 0.0163 / 0.0054\n",
"[111/4000][300/600] Loss_D: 0.0095 Loss_G: 6.2018 D(x): 0.9972 D(G(z)): 0.0067 / 0.0031\n",
"[111/4000][400/600] Loss_D: 0.0448 Loss_G: 6.3646 D(x): 0.9674 D(G(z)): 0.0044 / 0.0028\n",
"[111/4000][500/600] Loss_D: 0.0558 Loss_G: 7.4167 D(x): 0.9743 D(G(z)): 0.0059 / 0.0041\n",
"[112/4000][0/600] Loss_D: 0.1838 Loss_G: 13.9284 D(x): 0.9066 D(G(z)): 0.0000 / 0.0000\n",
"[112/4000][100/600] Loss_D: 0.0308 Loss_G: 4.4620 D(x): 0.9907 D(G(z)): 0.0188 / 0.0210\n",
"[112/4000][200/600] Loss_D: 0.0435 Loss_G: 5.9615 D(x): 0.9724 D(G(z)): 0.0075 / 0.0039\n",
"[112/4000][300/600] Loss_D: 0.0082 Loss_G: 6.9072 D(x): 0.9939 D(G(z)): 0.0018 / 0.0018\n",
"[112/4000][400/600] Loss_D: 0.0857 Loss_G: 4.9127 D(x): 0.9574 D(G(z)): 0.0101 / 0.0133\n",
"[112/4000][500/600] Loss_D: 0.0208 Loss_G: 5.8020 D(x): 0.9864 D(G(z)): 0.0050 / 0.0042\n",
"[113/4000][0/600] Loss_D: 0.0396 Loss_G: 7.9266 D(x): 0.9812 D(G(z)): 0.0015 / 0.0007\n",
"[113/4000][100/600] Loss_D: 0.0145 Loss_G: 5.3031 D(x): 0.9989 D(G(z)): 0.0132 / 0.0065\n",
"[113/4000][200/600] Loss_D: 0.0290 Loss_G: 6.0687 D(x): 0.9852 D(G(z)): 0.0021 / 0.0032\n",
"[113/4000][300/600] Loss_D: 0.0210 Loss_G: 5.5922 D(x): 0.9906 D(G(z)): 0.0085 / 0.0070\n",
"[113/4000][400/600] Loss_D: 0.0341 Loss_G: 4.8368 D(x): 0.9881 D(G(z)): 0.0202 / 0.0142\n",
"[113/4000][500/600] Loss_D: 0.0077 Loss_G: 5.5637 D(x): 0.9989 D(G(z)): 0.0065 / 0.0055\n",
"[114/4000][0/600] Loss_D: 0.0138 Loss_G: 6.6886 D(x): 0.9961 D(G(z)): 0.0086 / 0.0044\n",
"[114/4000][100/600] Loss_D: 0.0536 Loss_G: 5.9556 D(x): 0.9859 D(G(z)): 0.0168 / 0.0052\n",
"[114/4000][200/600] Loss_D: 0.0112 Loss_G: 6.0862 D(x): 0.9972 D(G(z)): 0.0082 / 0.0041\n",
"[114/4000][300/600] Loss_D: 0.0097 Loss_G: 5.2874 D(x): 0.9993 D(G(z)): 0.0089 / 0.0074\n",
"[114/4000][400/600] Loss_D: 0.0244 Loss_G: 5.1328 D(x): 0.9978 D(G(z)): 0.0215 / 0.0098\n",
"[114/4000][500/600] Loss_D: 0.0153 Loss_G: 6.4439 D(x): 0.9900 D(G(z)): 0.0041 / 0.0029\n",
"[115/4000][0/600] Loss_D: 0.0166 Loss_G: 5.1101 D(x): 0.9962 D(G(z)): 0.0126 / 0.0074\n",
"[115/4000][100/600] Loss_D: 0.0319 Loss_G: 4.7173 D(x): 0.9987 D(G(z)): 0.0296 / 0.0164\n",
"[115/4000][200/600] Loss_D: 0.0036 Loss_G: 7.5097 D(x): 0.9998 D(G(z)): 0.0033 / 0.0009\n",
"[115/4000][300/600] Loss_D: 0.0121 Loss_G: 6.1149 D(x): 0.9939 D(G(z)): 0.0054 / 0.0037\n",
"[115/4000][400/600] Loss_D: 0.0391 Loss_G: 4.8112 D(x): 0.9994 D(G(z)): 0.0369 / 0.0152\n",
"[115/4000][500/600] Loss_D: 0.0090 Loss_G: 5.7154 D(x): 0.9985 D(G(z)): 0.0075 / 0.0052\n",
"[116/4000][0/600] Loss_D: 0.0276 Loss_G: 5.8334 D(x): 0.9860 D(G(z)): 0.0081 / 0.0064\n",
"[116/4000][100/600] Loss_D: 0.0048 Loss_G: 7.3192 D(x): 0.9974 D(G(z)): 0.0021 / 0.0011\n",
"[116/4000][200/600] Loss_D: 0.0106 Loss_G: 5.4561 D(x): 0.9988 D(G(z)): 0.0093 / 0.0082\n",
"[116/4000][300/600] Loss_D: 0.0141 Loss_G: 5.9709 D(x): 0.9999 D(G(z)): 0.0138 / 0.0076\n",
"[116/4000][400/600] Loss_D: 0.0155 Loss_G: 5.9228 D(x): 0.9943 D(G(z)): 0.0083 / 0.0040\n",
"[116/4000][500/600] Loss_D: 0.0471 Loss_G: 6.2754 D(x): 0.9822 D(G(z)): 0.0029 / 0.0027\n",
"[117/4000][0/600] Loss_D: 0.0057 Loss_G: 6.9664 D(x): 0.9970 D(G(z)): 0.0026 / 0.0015\n",
"[117/4000][100/600] Loss_D: 0.0042 Loss_G: 6.7744 D(x): 0.9988 D(G(z)): 0.0030 / 0.0028\n",
"[117/4000][200/600] Loss_D: 0.0058 Loss_G: 6.9366 D(x): 0.9976 D(G(z)): 0.0033 / 0.0016\n",
"[117/4000][300/600] Loss_D: 0.0072 Loss_G: 7.2163 D(x): 0.9963 D(G(z)): 0.0030 / 0.0011\n",
"[117/4000][400/600] Loss_D: 0.0194 Loss_G: 5.4542 D(x): 0.9982 D(G(z)): 0.0173 / 0.0066\n",
"[117/4000][500/600] Loss_D: 0.0129 Loss_G: 6.6851 D(x): 0.9906 D(G(z)): 0.0025 / 0.0022\n",
"[118/4000][0/600] Loss_D: 0.0121 Loss_G: 9.3434 D(x): 0.9918 D(G(z)): 0.0003 / 0.0001\n",
"[118/4000][100/600] Loss_D: 0.0146 Loss_G: 4.9553 D(x): 0.9948 D(G(z)): 0.0087 / 0.0104\n",
"[118/4000][200/600] Loss_D: 0.0052 Loss_G: 6.8403 D(x): 0.9996 D(G(z)): 0.0047 / 0.0016\n",
"[118/4000][300/600] Loss_D: 0.0241 Loss_G: 4.7693 D(x): 0.9965 D(G(z)): 0.0201 / 0.0152\n",
"[118/4000][400/600] Loss_D: 0.0607 Loss_G: 4.8911 D(x): 0.9587 D(G(z)): 0.0104 / 0.0115\n",
"[118/4000][500/600] Loss_D: 0.0109 Loss_G: 7.0426 D(x): 0.9913 D(G(z)): 0.0017 / 0.0014\n",
"[119/4000][0/600] Loss_D: 0.0153 Loss_G: 6.1536 D(x): 0.9989 D(G(z)): 0.0137 / 0.0046\n",
"[119/4000][100/600] Loss_D: 0.0243 Loss_G: 7.8840 D(x): 0.9818 D(G(z)): 0.0006 / 0.0007\n",
"[119/4000][200/600] Loss_D: 0.0051 Loss_G: 6.0567 D(x): 0.9991 D(G(z)): 0.0042 / 0.0040\n",
"[119/4000][300/600] Loss_D: 0.0186 Loss_G: 10.6132 D(x): 0.9839 D(G(z)): 0.0001 / 0.0001\n",
"[119/4000][400/600] Loss_D: 0.1897 Loss_G: 7.2248 D(x): 0.9085 D(G(z)): 0.0005 / 0.0015\n",
"[119/4000][500/600] Loss_D: 0.0275 Loss_G: 6.1164 D(x): 0.9827 D(G(z)): 0.0053 / 0.0041\n",
"[120/4000][0/600] Loss_D: 0.0152 Loss_G: 5.9098 D(x): 0.9966 D(G(z)): 0.0116 / 0.0043\n",
"[120/4000][100/600] Loss_D: 0.0110 Loss_G: 6.1689 D(x): 0.9959 D(G(z)): 0.0062 / 0.0055\n",
"[120/4000][200/600] Loss_D: 0.0425 Loss_G: 4.2534 D(x): 0.9930 D(G(z)): 0.0305 / 0.0247\n",
"[120/4000][300/600] Loss_D: 0.0254 Loss_G: 4.4932 D(x): 0.9998 D(G(z)): 0.0245 / 0.0172\n",
"[120/4000][400/600] Loss_D: 0.0268 Loss_G: 4.5935 D(x): 0.9993 D(G(z)): 0.0256 / 0.0134\n",
"[120/4000][500/600] Loss_D: 0.1093 Loss_G: 6.7108 D(x): 0.9433 D(G(z)): 0.0007 / 0.0022\n",
"[121/4000][0/600] Loss_D: 0.0129 Loss_G: 4.8092 D(x): 0.9975 D(G(z)): 0.0102 / 0.0119\n",
"[121/4000][100/600] Loss_D: 0.0073 Loss_G: 6.0256 D(x): 0.9988 D(G(z)): 0.0060 / 0.0048\n",
"[121/4000][200/600] Loss_D: 0.0089 Loss_G: 7.0662 D(x): 0.9946 D(G(z)): 0.0032 / 0.0022\n",
"[121/4000][300/600] Loss_D: 0.0179 Loss_G: 4.9280 D(x): 0.9998 D(G(z)): 0.0174 / 0.0116\n",
"[121/4000][400/600] Loss_D: 0.0292 Loss_G: 5.0155 D(x): 0.9951 D(G(z)): 0.0236 / 0.0099\n",
"[121/4000][500/600] Loss_D: 0.1024 Loss_G: 2.8155 D(x): 0.9901 D(G(z)): 0.0841 / 0.0940\n",
"[122/4000][0/600] Loss_D: 0.0060 Loss_G: 7.6053 D(x): 0.9958 D(G(z)): 0.0011 / 0.0008\n",
"[122/4000][100/600] Loss_D: 0.0266 Loss_G: 5.8198 D(x): 0.9908 D(G(z)): 0.0129 / 0.0057\n",
"[122/4000][200/600] Loss_D: 0.0762 Loss_G: 5.1310 D(x): 0.9449 D(G(z)): 0.0046 / 0.0092\n",
"[122/4000][300/600] Loss_D: 0.0347 Loss_G: 8.2439 D(x): 0.9735 D(G(z)): 0.0006 / 0.0007\n",
"[122/4000][400/600] Loss_D: 0.0223 Loss_G: 6.3804 D(x): 0.9890 D(G(z)): 0.0044 / 0.0027\n",
"[122/4000][500/600] Loss_D: 0.0033 Loss_G: 7.9465 D(x): 0.9976 D(G(z)): 0.0008 / 0.0007\n",
"[123/4000][0/600] Loss_D: 0.0082 Loss_G: 5.3540 D(x): 0.9999 D(G(z)): 0.0080 / 0.0075\n",
"[123/4000][100/600] Loss_D: 0.0282 Loss_G: 4.6891 D(x): 0.9961 D(G(z)): 0.0233 / 0.0126\n",
"[123/4000][200/600] Loss_D: 0.2100 Loss_G: 10.0530 D(x): 0.9045 D(G(z)): 0.0005 / 0.0001\n",
"[123/4000][300/600] Loss_D: 0.0269 Loss_G: 5.0629 D(x): 0.9922 D(G(z)): 0.0183 / 0.0102\n",
"[123/4000][400/600] Loss_D: 0.0717 Loss_G: 4.8123 D(x): 0.9730 D(G(z)): 0.0280 / 0.0164\n",
"[123/4000][500/600] Loss_D: 0.0197 Loss_G: 6.7354 D(x): 0.9873 D(G(z)): 0.0031 / 0.0029\n",
"[124/4000][0/600] Loss_D: 0.0676 Loss_G: 4.2953 D(x): 0.9928 D(G(z)): 0.0549 / 0.0315\n",
"[124/4000][100/600] Loss_D: 0.0288 Loss_G: 5.5708 D(x): 0.9936 D(G(z)): 0.0208 / 0.0092\n",
"[124/4000][200/600] Loss_D: 0.0285 Loss_G: 5.7548 D(x): 0.9905 D(G(z)): 0.0148 / 0.0058\n",
"[124/4000][300/600] Loss_D: 0.0519 Loss_G: 5.7487 D(x): 0.9669 D(G(z)): 0.0043 / 0.0049\n",
"[124/4000][400/600] Loss_D: 0.0326 Loss_G: 7.3913 D(x): 0.9768 D(G(z)): 0.0013 / 0.0009\n",
"[124/4000][500/600] Loss_D: 0.0167 Loss_G: 5.6859 D(x): 0.9908 D(G(z)): 0.0068 / 0.0058\n",
"[125/4000][0/600] Loss_D: 0.2443 Loss_G: 1.9519 D(x): 0.9998 D(G(z)): 0.1975 / 0.2178\n",
"[125/4000][100/600] Loss_D: 0.0109 Loss_G: 6.9882 D(x): 0.9946 D(G(z)): 0.0051 / 0.0028\n",
"[125/4000][200/600] Loss_D: 0.0342 Loss_G: 5.3307 D(x): 0.9867 D(G(z)): 0.0137 / 0.0088\n",
"[125/4000][300/600] Loss_D: 0.0787 Loss_G: 3.0084 D(x): 0.9971 D(G(z)): 0.0684 / 0.0827\n",
"[125/4000][400/600] Loss_D: 0.1018 Loss_G: 4.7236 D(x): 0.9588 D(G(z)): 0.0135 / 0.0167\n",
"[125/4000][500/600] Loss_D: 0.0271 Loss_G: 5.4433 D(x): 0.9834 D(G(z)): 0.0082 / 0.0091\n",
"[126/4000][0/600] Loss_D: 0.2156 Loss_G: 3.0119 D(x): 0.9996 D(G(z)): 0.1757 / 0.0786\n",
"[126/4000][100/600] Loss_D: 0.0248 Loss_G: 6.3426 D(x): 0.9842 D(G(z)): 0.0035 / 0.0040\n",
"[126/4000][200/600] Loss_D: 0.0403 Loss_G: 4.7559 D(x): 0.9987 D(G(z)): 0.0370 / 0.0155\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[126/4000][300/600] Loss_D: 0.0183 Loss_G: 5.8866 D(x): 0.9873 D(G(z)): 0.0036 / 0.0044\n",
"[126/4000][400/600] Loss_D: 0.1243 Loss_G: 5.9009 D(x): 0.9466 D(G(z)): 0.0130 / 0.0127\n",
"[126/4000][500/600] Loss_D: 0.0101 Loss_G: 6.2085 D(x): 0.9949 D(G(z)): 0.0047 / 0.0032\n",
"[127/4000][0/600] Loss_D: 0.0073 Loss_G: 7.6415 D(x): 0.9955 D(G(z)): 0.0024 / 0.0008\n",
"[127/4000][100/600] Loss_D: 0.0107 Loss_G: 7.7017 D(x): 0.9916 D(G(z)): 0.0016 / 0.0019\n",
"[127/4000][200/600] Loss_D: 0.0204 Loss_G: 6.2806 D(x): 0.9996 D(G(z)): 0.0193 / 0.0045\n",
"[127/4000][300/600] Loss_D: 0.0145 Loss_G: 5.6637 D(x): 0.9998 D(G(z)): 0.0141 / 0.0057\n",
"[127/4000][400/600] Loss_D: 0.0201 Loss_G: 5.0533 D(x): 0.9951 D(G(z)): 0.0148 / 0.0087\n",
"[127/4000][500/600] Loss_D: 0.0227 Loss_G: 4.3197 D(x): 0.9897 D(G(z)): 0.0116 / 0.0173\n",
"[128/4000][0/600] Loss_D: 0.0278 Loss_G: 10.5306 D(x): 0.9783 D(G(z)): 0.0005 / 0.0002\n",
"[128/4000][100/600] Loss_D: 0.0265 Loss_G: 5.8184 D(x): 0.9854 D(G(z)): 0.0079 / 0.0043\n",
"[128/4000][200/600] Loss_D: 0.0716 Loss_G: 4.5634 D(x): 0.9690 D(G(z)): 0.0188 / 0.0175\n",
"[128/4000][300/600] Loss_D: 0.0489 Loss_G: 5.6330 D(x): 0.9751 D(G(z)): 0.0039 / 0.0049\n",
"[128/4000][400/600] Loss_D: 0.0276 Loss_G: 6.9744 D(x): 0.9781 D(G(z)): 0.0016 / 0.0014\n",
"[128/4000][500/600] Loss_D: 0.0200 Loss_G: 5.3758 D(x): 0.9861 D(G(z)): 0.0047 / 0.0062\n",
"[129/4000][0/600] Loss_D: 0.0085 Loss_G: 6.0365 D(x): 0.9976 D(G(z)): 0.0060 / 0.0031\n",
"[129/4000][100/600] Loss_D: 0.0309 Loss_G: 6.5152 D(x): 0.9874 D(G(z)): 0.0066 / 0.0045\n",
"[129/4000][200/600] Loss_D: 0.0058 Loss_G: 6.4276 D(x): 0.9971 D(G(z)): 0.0028 / 0.0023\n",
"[129/4000][300/600] Loss_D: 0.0067 Loss_G: 6.4020 D(x): 0.9976 D(G(z)): 0.0042 / 0.0028\n",
"[129/4000][400/600] Loss_D: 0.0436 Loss_G: 4.6206 D(x): 0.9981 D(G(z)): 0.0393 / 0.0220\n",
"[129/4000][500/600] Loss_D: 0.0076 Loss_G: 6.1370 D(x): 0.9973 D(G(z)): 0.0048 / 0.0040\n",
"[130/4000][0/600] Loss_D: 0.1522 Loss_G: 13.8136 D(x): 0.9085 D(G(z)): 0.0000 / 0.0000\n",
"[130/4000][100/600] Loss_D: 0.0569 Loss_G: 4.8681 D(x): 0.9778 D(G(z)): 0.0164 / 0.0137\n",
"[130/4000][200/600] Loss_D: 0.0117 Loss_G: 6.2998 D(x): 0.9951 D(G(z)): 0.0062 / 0.0035\n",
"[130/4000][300/600] Loss_D: 0.0368 Loss_G: 4.7624 D(x): 0.9874 D(G(z)): 0.0204 / 0.0170\n",
"[130/4000][400/600] Loss_D: 0.0431 Loss_G: 4.6366 D(x): 0.9963 D(G(z)): 0.0366 / 0.0242\n",
"[130/4000][500/600] Loss_D: 0.0107 Loss_G: 7.0177 D(x): 0.9920 D(G(z)): 0.0021 / 0.0018\n",
"[131/4000][0/600] Loss_D: 0.0272 Loss_G: 5.0225 D(x): 0.9953 D(G(z)): 0.0218 / 0.0109\n",
"[131/4000][100/600] Loss_D: 0.0114 Loss_G: 7.6320 D(x): 0.9914 D(G(z)): 0.0018 / 0.0008\n",
"[131/4000][200/600] Loss_D: 0.0178 Loss_G: 5.1538 D(x): 0.9980 D(G(z)): 0.0155 / 0.0102\n",
"[131/4000][300/600] Loss_D: 0.0199 Loss_G: 5.0208 D(x): 0.9890 D(G(z)): 0.0077 / 0.0099\n",
"[131/4000][400/600] Loss_D: 0.0354 Loss_G: 5.1592 D(x): 0.9887 D(G(z)): 0.0154 / 0.0098\n",
"[131/4000][500/600] Loss_D: 0.0106 Loss_G: 5.9569 D(x): 0.9951 D(G(z)): 0.0055 / 0.0043\n",
"[132/4000][0/600] Loss_D: 0.0216 Loss_G: 4.7990 D(x): 0.9943 D(G(z)): 0.0150 / 0.0159\n",
"[132/4000][100/600] Loss_D: 0.0139 Loss_G: 5.7656 D(x): 0.9972 D(G(z)): 0.0109 / 0.0062\n",
"[132/4000][200/600] Loss_D: 0.0097 Loss_G: 5.8126 D(x): 0.9992 D(G(z)): 0.0087 / 0.0049\n",
"[132/4000][300/600] Loss_D: 0.0185 Loss_G: 5.0804 D(x): 0.9953 D(G(z)): 0.0132 / 0.0108\n",
"[132/4000][400/600] Loss_D: 0.0217 Loss_G: 6.8273 D(x): 0.9865 D(G(z)): 0.0048 / 0.0017\n",
"[132/4000][500/600] Loss_D: 0.0459 Loss_G: 5.4517 D(x): 0.9737 D(G(z)): 0.0076 / 0.0086\n",
"[133/4000][0/600] Loss_D: 0.1615 Loss_G: 4.1042 D(x): 0.9963 D(G(z)): 0.1211 / 0.0321\n",
"[133/4000][100/600] Loss_D: 0.0076 Loss_G: 7.7352 D(x): 0.9935 D(G(z)): 0.0010 / 0.0009\n",
"[133/4000][200/600] Loss_D: 0.0175 Loss_G: 5.4649 D(x): 0.9996 D(G(z)): 0.0168 / 0.0070\n",
"[133/4000][300/600] Loss_D: 0.1093 Loss_G: 5.7628 D(x): 0.9526 D(G(z)): 0.0041 / 0.0040\n",
"[133/4000][400/600] Loss_D: 0.0482 Loss_G: 5.1433 D(x): 0.9756 D(G(z)): 0.0166 / 0.0098\n",
"[133/4000][500/600] Loss_D: 0.0116 Loss_G: 5.5569 D(x): 0.9971 D(G(z)): 0.0086 / 0.0053\n",
"[134/4000][0/600] Loss_D: 0.0218 Loss_G: 8.3353 D(x): 0.9819 D(G(z)): 0.0013 / 0.0003\n",
"[134/4000][100/600] Loss_D: 0.0218 Loss_G: 4.5398 D(x): 0.9989 D(G(z)): 0.0200 / 0.0201\n",
"[134/4000][200/600] Loss_D: 0.0444 Loss_G: 4.5679 D(x): 0.9839 D(G(z)): 0.0249 / 0.0192\n",
"[134/4000][300/600] Loss_D: 0.0286 Loss_G: 6.7198 D(x): 0.9771 D(G(z)): 0.0029 / 0.0018\n",
"[134/4000][400/600] Loss_D: 0.0323 Loss_G: 5.4792 D(x): 0.9817 D(G(z)): 0.0072 / 0.0074\n",
"[134/4000][500/600] Loss_D: 0.0249 Loss_G: 5.4787 D(x): 0.9889 D(G(z)): 0.0089 / 0.0088\n",
"[135/4000][0/600] Loss_D: 0.0361 Loss_G: 5.5764 D(x): 0.9857 D(G(z)): 0.0105 / 0.0062\n",
"[135/4000][100/600] Loss_D: 0.0172 Loss_G: 6.2909 D(x): 0.9886 D(G(z)): 0.0027 / 0.0029\n",
"[135/4000][200/600] Loss_D: 0.0176 Loss_G: 6.8411 D(x): 0.9875 D(G(z)): 0.0025 / 0.0021\n",
"[135/4000][300/600] Loss_D: 0.0394 Loss_G: 4.0456 D(x): 0.9917 D(G(z)): 0.0291 / 0.0254\n",
"[135/4000][400/600] Loss_D: 0.0397 Loss_G: 4.3076 D(x): 0.9961 D(G(z)): 0.0337 / 0.0229\n",
"[135/4000][500/600] Loss_D: 0.0049 Loss_G: 5.8307 D(x): 0.9976 D(G(z)): 0.0025 / 0.0047\n",
"[136/4000][0/600] Loss_D: 0.0099 Loss_G: 4.9919 D(x): 0.9992 D(G(z)): 0.0090 / 0.0110\n",
"[136/4000][100/600] Loss_D: 0.0045 Loss_G: 6.1199 D(x): 0.9998 D(G(z)): 0.0043 / 0.0042\n",
"[136/4000][200/600] Loss_D: 0.0472 Loss_G: 6.3436 D(x): 0.9774 D(G(z)): 0.0044 / 0.0028\n",
"[136/4000][300/600] Loss_D: 0.1121 Loss_G: 5.6234 D(x): 0.9561 D(G(z)): 0.0031 / 0.0053\n",
"[136/4000][400/600] Loss_D: 0.0264 Loss_G: 10.1014 D(x): 0.9763 D(G(z)): 0.0003 / 0.0001\n",
"[136/4000][500/600] Loss_D: 0.0153 Loss_G: 6.6431 D(x): 0.9906 D(G(z)): 0.0042 / 0.0041\n",
"[137/4000][0/600] Loss_D: 0.0240 Loss_G: 5.1459 D(x): 0.9973 D(G(z)): 0.0206 / 0.0127\n",
"[137/4000][100/600] Loss_D: 0.0101 Loss_G: 8.0981 D(x): 0.9911 D(G(z)): 0.0005 / 0.0006\n",
"[137/4000][200/600] Loss_D: 0.0438 Loss_G: 6.4494 D(x): 0.9762 D(G(z)): 0.0023 / 0.0035\n",
"[137/4000][300/600] Loss_D: 0.0072 Loss_G: 6.0331 D(x): 0.9993 D(G(z)): 0.0064 / 0.0055\n",
"[137/4000][400/600] Loss_D: 0.0906 Loss_G: 7.9187 D(x): 0.9376 D(G(z)): 0.0008 / 0.0010\n",
"[137/4000][500/600] Loss_D: 0.0158 Loss_G: 5.6069 D(x): 0.9931 D(G(z)): 0.0085 / 0.0075\n",
"[138/4000][0/600] Loss_D: 0.0119 Loss_G: 6.0146 D(x): 0.9988 D(G(z)): 0.0104 / 0.0049\n",
"[138/4000][100/600] Loss_D: 0.0118 Loss_G: 6.3519 D(x): 0.9943 D(G(z)): 0.0050 / 0.0044\n",
"[138/4000][200/600] Loss_D: 0.0247 Loss_G: 5.8790 D(x): 0.9999 D(G(z)): 0.0237 / 0.0052\n",
"[138/4000][300/600] Loss_D: 0.0095 Loss_G: 5.1359 D(x): 0.9993 D(G(z)): 0.0086 / 0.0125\n",
"[138/4000][400/600] Loss_D: 0.0094 Loss_G: 7.6251 D(x): 0.9949 D(G(z)): 0.0039 / 0.0008\n",
"[138/4000][500/600] Loss_D: 0.0205 Loss_G: 6.9626 D(x): 0.9894 D(G(z)): 0.0023 / 0.0019\n",
"[139/4000][0/600] Loss_D: 0.0342 Loss_G: 4.7339 D(x): 0.9986 D(G(z)): 0.0315 / 0.0137\n",
"[139/4000][100/600] Loss_D: 0.0149 Loss_G: 5.5693 D(x): 0.9922 D(G(z)): 0.0057 / 0.0051\n",
"[139/4000][200/600] Loss_D: 0.0106 Loss_G: 5.5929 D(x): 0.9955 D(G(z)): 0.0058 / 0.0060\n",
"[139/4000][300/600] Loss_D: 0.0061 Loss_G: 6.5960 D(x): 0.9975 D(G(z)): 0.0035 / 0.0025\n",
"[139/4000][400/600] Loss_D: 0.0090 Loss_G: 6.5512 D(x): 0.9996 D(G(z)): 0.0085 / 0.0029\n",
"[139/4000][500/600] Loss_D: 0.0343 Loss_G: 4.4598 D(x): 0.9936 D(G(z)): 0.0219 / 0.0387\n",
"[140/4000][0/600] Loss_D: 0.0039 Loss_G: 7.3004 D(x): 0.9983 D(G(z)): 0.0021 / 0.0015\n",
"[140/4000][100/600] Loss_D: 0.0058 Loss_G: 7.1100 D(x): 0.9962 D(G(z)): 0.0019 / 0.0014\n",
"[140/4000][200/600] Loss_D: 0.0289 Loss_G: 6.0716 D(x): 0.9949 D(G(z)): 0.0218 / 0.0061\n",
"[140/4000][300/600] Loss_D: 0.0389 Loss_G: 5.7929 D(x): 0.9775 D(G(z)): 0.0032 / 0.0050\n",
"[140/4000][400/600] Loss_D: 0.0644 Loss_G: 7.0227 D(x): 0.9678 D(G(z)): 0.0016 / 0.0016\n",
"[140/4000][500/600] Loss_D: 0.0227 Loss_G: 6.9640 D(x): 0.9875 D(G(z)): 0.0071 / 0.0056\n",
"[141/4000][0/600] Loss_D: 0.0338 Loss_G: 11.8575 D(x): 0.9802 D(G(z)): 0.0001 / 0.0000\n",
"[141/4000][100/600] Loss_D: 0.0104 Loss_G: 6.8389 D(x): 0.9939 D(G(z)): 0.0031 / 0.0019\n",
"[141/4000][200/600] Loss_D: 0.0205 Loss_G: 8.0190 D(x): 0.9897 D(G(z)): 0.0043 / 0.0006\n",
"[141/4000][300/600] Loss_D: 0.0123 Loss_G: 5.6908 D(x): 0.9974 D(G(z)): 0.0093 / 0.0061\n",
"[141/4000][400/600] Loss_D: 0.0153 Loss_G: 5.8628 D(x): 0.9926 D(G(z)): 0.0048 / 0.0048\n",
"[141/4000][500/600] Loss_D: 0.0340 Loss_G: 5.0269 D(x): 0.9819 D(G(z)): 0.0066 / 0.0119\n",
"[142/4000][0/600] Loss_D: 0.0085 Loss_G: 11.5673 D(x): 0.9919 D(G(z)): 0.0001 / 0.0000\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[142/4000][100/600] Loss_D: 0.0397 Loss_G: 4.0267 D(x): 0.9965 D(G(z)): 0.0348 / 0.0233\n",
"[142/4000][200/600] Loss_D: 0.0613 Loss_G: 4.5401 D(x): 0.9721 D(G(z)): 0.0122 / 0.0183\n",
"[142/4000][300/600] Loss_D: 0.0188 Loss_G: 5.1746 D(x): 0.9938 D(G(z)): 0.0107 / 0.0092\n",
"[142/4000][400/600] Loss_D: 0.0054 Loss_G: 6.4890 D(x): 0.9983 D(G(z)): 0.0037 / 0.0024\n",
"[142/4000][500/600] Loss_D: 0.0383 Loss_G: 4.9180 D(x): 0.9786 D(G(z)): 0.0063 / 0.0107\n",
"[143/4000][0/600] Loss_D: 0.0094 Loss_G: 7.5428 D(x): 0.9946 D(G(z)): 0.0037 / 0.0013\n",
"[143/4000][100/600] Loss_D: 0.0194 Loss_G: 6.0826 D(x): 0.9985 D(G(z)): 0.0170 / 0.0093\n",
"[143/4000][200/600] Loss_D: 0.0140 Loss_G: 5.6264 D(x): 0.9951 D(G(z)): 0.0087 / 0.0063\n",
"[143/4000][300/600] Loss_D: 0.0182 Loss_G: 4.9479 D(x): 0.9919 D(G(z)): 0.0094 / 0.0119\n",
"[143/4000][400/600] Loss_D: 0.0174 Loss_G: 5.9416 D(x): 0.9885 D(G(z)): 0.0026 / 0.0042\n",
"[143/4000][500/600] Loss_D: 0.0114 Loss_G: 5.5360 D(x): 0.9985 D(G(z)): 0.0096 / 0.0089\n",
"[144/4000][0/600] Loss_D: 0.0277 Loss_G: 5.0499 D(x): 0.9999 D(G(z)): 0.0265 / 0.0114\n",
"[144/4000][100/600] Loss_D: 0.0329 Loss_G: 5.7226 D(x): 0.9986 D(G(z)): 0.0299 / 0.0121\n",
"[144/4000][200/600] Loss_D: 0.0186 Loss_G: 7.1935 D(x): 0.9995 D(G(z)): 0.0175 / 0.0016\n",
"[144/4000][300/600] Loss_D: 0.0353 Loss_G: 4.6866 D(x): 0.9898 D(G(z)): 0.0221 / 0.0234\n",
"[144/4000][400/600] Loss_D: 0.0032 Loss_G: 7.2333 D(x): 0.9991 D(G(z)): 0.0023 / 0.0014\n",
"[144/4000][500/600] Loss_D: 0.0113 Loss_G: 6.2084 D(x): 0.9937 D(G(z)): 0.0046 / 0.0041\n",
"[145/4000][0/600] Loss_D: 0.0518 Loss_G: 3.1433 D(x): 0.9986 D(G(z)): 0.0478 / 0.0642\n",
"[145/4000][100/600] Loss_D: 0.0155 Loss_G: 5.4756 D(x): 0.9979 D(G(z)): 0.0130 / 0.0102\n",
"[145/4000][200/600] Loss_D: 0.0228 Loss_G: 4.9227 D(x): 0.9972 D(G(z)): 0.0187 / 0.0145\n",
"[145/4000][300/600] Loss_D: 0.0101 Loss_G: 6.3743 D(x): 0.9955 D(G(z)): 0.0053 / 0.0036\n",
"[145/4000][400/600] Loss_D: 0.0591 Loss_G: 5.8058 D(x): 0.9613 D(G(z)): 0.0042 / 0.0053\n",
"[145/4000][500/600] Loss_D: 0.0131 Loss_G: 5.8895 D(x): 0.9971 D(G(z)): 0.0099 / 0.0075\n",
"[146/4000][0/600] Loss_D: 0.0182 Loss_G: 5.0087 D(x): 0.9974 D(G(z)): 0.0149 / 0.0106\n",
"[146/4000][100/600] Loss_D: 0.0134 Loss_G: 5.9686 D(x): 0.9947 D(G(z)): 0.0073 / 0.0047\n",
"[146/4000][200/600] Loss_D: 0.0063 Loss_G: 6.4191 D(x): 0.9996 D(G(z)): 0.0058 / 0.0034\n",
"[146/4000][300/600] Loss_D: 0.0105 Loss_G: 6.0354 D(x): 0.9953 D(G(z)): 0.0054 / 0.0035\n",
"[146/4000][400/600] Loss_D: 0.0185 Loss_G: 4.5779 D(x): 0.9986 D(G(z)): 0.0168 / 0.0160\n",
"[146/4000][500/600] Loss_D: 0.0272 Loss_G: 6.0718 D(x): 0.9867 D(G(z)): 0.0035 / 0.0030\n",
"[147/4000][0/600] Loss_D: 0.0458 Loss_G: 4.8736 D(x): 0.9996 D(G(z)): 0.0417 / 0.0191\n",
"[147/4000][100/600] Loss_D: 0.0242 Loss_G: 5.4968 D(x): 0.9888 D(G(z)): 0.0117 / 0.0062\n",
"[147/4000][200/600] Loss_D: 0.0155 Loss_G: 5.9355 D(x): 0.9991 D(G(z)): 0.0141 / 0.0048\n",
"[147/4000][300/600] Loss_D: 0.0061 Loss_G: 8.1483 D(x): 0.9952 D(G(z)): 0.0011 / 0.0004\n",
"[147/4000][400/600] Loss_D: 0.0708 Loss_G: 5.4206 D(x): 0.9673 D(G(z)): 0.0063 / 0.0087\n",
"[147/4000][500/600] Loss_D: 0.0366 Loss_G: 7.7552 D(x): 0.9709 D(G(z)): 0.0011 / 0.0007\n",
"[148/4000][0/600] Loss_D: 0.0630 Loss_G: 9.4768 D(x): 0.9647 D(G(z)): 0.0007 / 0.0002\n",
"[148/4000][100/600] Loss_D: 0.0128 Loss_G: 6.1042 D(x): 0.9933 D(G(z)): 0.0056 / 0.0045\n",
"[148/4000][200/600] Loss_D: 0.0161 Loss_G: 5.4232 D(x): 0.9988 D(G(z)): 0.0146 / 0.0068\n",
"[148/4000][300/600] Loss_D: 0.0498 Loss_G: 8.2150 D(x): 0.9664 D(G(z)): 0.0007 / 0.0004\n",
"[148/4000][400/600] Loss_D: 0.0532 Loss_G: 4.6833 D(x): 0.9802 D(G(z)): 0.0287 / 0.0154\n",
"[148/4000][500/600] Loss_D: 0.0182 Loss_G: 6.6466 D(x): 0.9866 D(G(z)): 0.0030 / 0.0027\n",
"[149/4000][0/600] Loss_D: 0.0532 Loss_G: 4.7696 D(x): 0.9985 D(G(z)): 0.0473 / 0.0201\n",
"[149/4000][100/600] Loss_D: 0.0212 Loss_G: 5.2430 D(x): 0.9906 D(G(z)): 0.0100 / 0.0087\n",
"[149/4000][200/600] Loss_D: 0.0066 Loss_G: 5.5655 D(x): 0.9991 D(G(z)): 0.0056 / 0.0060\n",
"[149/4000][300/600] Loss_D: 0.0216 Loss_G: 7.6108 D(x): 0.9854 D(G(z)): 0.0014 / 0.0009\n",
"[149/4000][400/600] Loss_D: 0.0242 Loss_G: 5.5491 D(x): 0.9880 D(G(z)): 0.0097 / 0.0078\n",
"[149/4000][500/600] Loss_D: 0.0256 Loss_G: 6.2210 D(x): 0.9800 D(G(z)): 0.0032 / 0.0030\n",
"[150/4000][0/600] Loss_D: 0.0137 Loss_G: 6.3040 D(x): 0.9944 D(G(z)): 0.0075 / 0.0038\n",
"[150/4000][100/600] Loss_D: 0.0314 Loss_G: 6.2354 D(x): 0.9836 D(G(z)): 0.0076 / 0.0030\n",
"[150/4000][200/600] Loss_D: 0.0262 Loss_G: 4.8704 D(x): 0.9918 D(G(z)): 0.0136 / 0.0165\n",
"[150/4000][300/600] Loss_D: 0.0158 Loss_G: 7.1361 D(x): 0.9881 D(G(z)): 0.0017 / 0.0013\n",
"[150/4000][400/600] Loss_D: 0.0853 Loss_G: 4.9445 D(x): 0.9729 D(G(z)): 0.0158 / 0.0114\n",
"[150/4000][500/600] Loss_D: 0.0126 Loss_G: 10.5356 D(x): 0.9894 D(G(z)): 0.0002 / 0.0001\n",
"[151/4000][0/600] Loss_D: 0.0209 Loss_G: 5.7399 D(x): 0.9923 D(G(z)): 0.0126 / 0.0061\n",
"[151/4000][100/600] Loss_D: 0.0142 Loss_G: 5.5533 D(x): 0.9977 D(G(z)): 0.0115 / 0.0067\n",
"[151/4000][200/600] Loss_D: 0.0893 Loss_G: 6.4738 D(x): 0.9669 D(G(z)): 0.0105 / 0.0052\n",
"[151/4000][300/600] Loss_D: 0.0559 Loss_G: 10.2411 D(x): 0.9613 D(G(z)): 0.0001 / 0.0001\n",
"[151/4000][400/600] Loss_D: 0.0873 Loss_G: 7.9763 D(x): 0.9408 D(G(z)): 0.0007 / 0.0009\n",
"[151/4000][500/600] Loss_D: 0.0328 Loss_G: 6.8931 D(x): 0.9846 D(G(z)): 0.0021 / 0.0024\n",
"[152/4000][0/600] Loss_D: 0.1628 Loss_G: 9.0938 D(x): 0.9093 D(G(z)): 0.0003 / 0.0002\n",
"[152/4000][100/600] Loss_D: 0.0161 Loss_G: 5.1731 D(x): 0.9980 D(G(z)): 0.0139 / 0.0093\n",
"[152/4000][200/600] Loss_D: 0.0202 Loss_G: 6.2212 D(x): 0.9943 D(G(z)): 0.0136 / 0.0043\n",
"[152/4000][300/600] Loss_D: 0.0298 Loss_G: 5.6929 D(x): 0.9783 D(G(z)): 0.0035 / 0.0052\n",
"[152/4000][400/600] Loss_D: 0.0234 Loss_G: 5.2934 D(x): 0.9902 D(G(z)): 0.0099 / 0.0077\n",
"[152/4000][500/600] Loss_D: 0.0245 Loss_G: 5.7863 D(x): 0.9863 D(G(z)): 0.0045 / 0.0045\n",
"[153/4000][0/600] Loss_D: 0.0325 Loss_G: 4.5546 D(x): 0.9951 D(G(z)): 0.0267 / 0.0163\n",
"[153/4000][100/600] Loss_D: 0.0233 Loss_G: 4.8952 D(x): 0.9987 D(G(z)): 0.0212 / 0.0141\n",
"[153/4000][200/600] Loss_D: 0.0234 Loss_G: 5.8707 D(x): 0.9946 D(G(z)): 0.0171 / 0.0043\n",
"[153/4000][300/600] Loss_D: 0.0151 Loss_G: 6.8283 D(x): 0.9889 D(G(z)): 0.0029 / 0.0033\n",
"[153/4000][400/600] Loss_D: 0.0897 Loss_G: 6.0048 D(x): 0.9552 D(G(z)): 0.0037 / 0.0041\n",
"[153/4000][500/600] Loss_D: 0.0311 Loss_G: 6.3451 D(x): 0.9777 D(G(z)): 0.0040 / 0.0041\n",
"[154/4000][0/600] Loss_D: 0.0185 Loss_G: 4.8008 D(x): 0.9982 D(G(z)): 0.0160 / 0.0158\n",
"[154/4000][100/600] Loss_D: 0.0734 Loss_G: 4.0105 D(x): 0.9997 D(G(z)): 0.0682 / 0.0262\n",
"[154/4000][200/600] Loss_D: 0.0089 Loss_G: 5.5465 D(x): 0.9970 D(G(z)): 0.0058 / 0.0060\n",
"[154/4000][300/600] Loss_D: 0.0378 Loss_G: 5.3256 D(x): 0.9805 D(G(z)): 0.0099 / 0.0124\n",
"[154/4000][400/600] Loss_D: 0.0451 Loss_G: 5.7099 D(x): 0.9956 D(G(z)): 0.0373 / 0.0062\n",
"[154/4000][500/600] Loss_D: 0.0355 Loss_G: 3.7947 D(x): 0.9842 D(G(z)): 0.0169 / 0.0436\n",
"[155/4000][0/600] Loss_D: 0.0268 Loss_G: 4.7697 D(x): 0.9918 D(G(z)): 0.0173 / 0.0151\n",
"[155/4000][100/600] Loss_D: 0.0250 Loss_G: 4.5350 D(x): 0.9977 D(G(z)): 0.0220 / 0.0175\n",
"[155/4000][200/600] Loss_D: 0.0218 Loss_G: 6.9550 D(x): 0.9844 D(G(z)): 0.0038 / 0.0018\n",
"[155/4000][300/600] Loss_D: 0.0108 Loss_G: 8.3249 D(x): 0.9916 D(G(z)): 0.0017 / 0.0005\n",
"[155/4000][400/600] Loss_D: 0.0172 Loss_G: 5.5049 D(x): 0.9972 D(G(z)): 0.0139 / 0.0070\n",
"[155/4000][500/600] Loss_D: 0.0179 Loss_G: 4.9783 D(x): 0.9979 D(G(z)): 0.0154 / 0.0115\n",
"[156/4000][0/600] Loss_D: 0.0227 Loss_G: 6.7181 D(x): 0.9916 D(G(z)): 0.0125 / 0.0027\n",
"[156/4000][100/600] Loss_D: 0.0106 Loss_G: 6.8559 D(x): 0.9976 D(G(z)): 0.0080 / 0.0021\n",
"[156/4000][200/600] Loss_D: 0.0687 Loss_G: 4.9591 D(x): 0.9842 D(G(z)): 0.0209 / 0.0107\n",
"[156/4000][300/600] Loss_D: 0.0263 Loss_G: 5.9491 D(x): 0.9990 D(G(z)): 0.0237 / 0.0135\n",
"[156/4000][400/600] Loss_D: 0.0239 Loss_G: 5.0502 D(x): 0.9921 D(G(z)): 0.0145 / 0.0099\n",
"[156/4000][500/600] Loss_D: 0.0384 Loss_G: 4.7397 D(x): 0.9770 D(G(z)): 0.0126 / 0.0134\n",
"[157/4000][0/600] Loss_D: 0.0169 Loss_G: 9.4412 D(x): 0.9873 D(G(z)): 0.0010 / 0.0002\n",
"[157/4000][100/600] Loss_D: 0.0242 Loss_G: 6.4129 D(x): 0.9835 D(G(z)): 0.0044 / 0.0025\n",
"[157/4000][200/600] Loss_D: 0.0402 Loss_G: 6.1309 D(x): 0.9797 D(G(z)): 0.0118 / 0.0041\n",
"[157/4000][300/600] Loss_D: 0.0234 Loss_G: 6.0488 D(x): 0.9917 D(G(z)): 0.0137 / 0.0046\n",
"[157/4000][400/600] Loss_D: 0.0124 Loss_G: 5.4757 D(x): 0.9976 D(G(z)): 0.0098 / 0.0082\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[157/4000][500/600] Loss_D: 0.0152 Loss_G: 5.6168 D(x): 0.9900 D(G(z)): 0.0045 / 0.0051\n",
"[158/4000][0/600] Loss_D: 0.0325 Loss_G: 4.9181 D(x): 0.9924 D(G(z)): 0.0219 / 0.0139\n",
"[158/4000][100/600] Loss_D: 0.0195 Loss_G: 5.9961 D(x): 0.9920 D(G(z)): 0.0110 / 0.0045\n",
"[158/4000][200/600] Loss_D: 0.0143 Loss_G: 5.7493 D(x): 0.9955 D(G(z)): 0.0096 / 0.0049\n",
"[158/4000][300/600] Loss_D: 0.0139 Loss_G: 7.4042 D(x): 0.9888 D(G(z)): 0.0020 / 0.0011\n",
"[158/4000][400/600] Loss_D: 0.0503 Loss_G: 5.6597 D(x): 0.9666 D(G(z)): 0.0070 / 0.0070\n",
"[158/4000][500/600] Loss_D: 0.0554 Loss_G: 6.2117 D(x): 0.9617 D(G(z)): 0.0036 / 0.0035\n",
"[159/4000][0/600] Loss_D: 0.0023 Loss_G: 7.1288 D(x): 0.9991 D(G(z)): 0.0014 / 0.0020\n",
"[159/4000][100/600] Loss_D: 0.0198 Loss_G: 5.1193 D(x): 0.9990 D(G(z)): 0.0183 / 0.0114\n",
"[159/4000][200/600] Loss_D: 0.0460 Loss_G: 4.0124 D(x): 0.9994 D(G(z)): 0.0434 / 0.0279\n",
"[159/4000][300/600] Loss_D: 0.0124 Loss_G: 4.6961 D(x): 0.9990 D(G(z)): 0.0113 / 0.0116\n",
"[159/4000][400/600] Loss_D: 0.0451 Loss_G: 5.1139 D(x): 0.9871 D(G(z)): 0.0224 / 0.0103\n",
"[159/4000][500/600] Loss_D: 0.0228 Loss_G: 5.1533 D(x): 0.9878 D(G(z)): 0.0079 / 0.0095\n",
"[160/4000][0/600] Loss_D: 0.0167 Loss_G: 5.1639 D(x): 0.9980 D(G(z)): 0.0144 / 0.0119\n",
"[160/4000][100/600] Loss_D: 0.0159 Loss_G: 6.4604 D(x): 0.9945 D(G(z)): 0.0099 / 0.0035\n",
"[160/4000][200/600] Loss_D: 0.0117 Loss_G: 6.3299 D(x): 0.9938 D(G(z)): 0.0048 / 0.0047\n",
"[160/4000][300/600] Loss_D: 0.0164 Loss_G: 5.2374 D(x): 0.9921 D(G(z)): 0.0072 / 0.0083\n",
"[160/4000][400/600] Loss_D: 0.0170 Loss_G: 5.0914 D(x): 0.9990 D(G(z)): 0.0157 / 0.0112\n",
"[160/4000][500/600] Loss_D: 0.0195 Loss_G: 5.9594 D(x): 0.9838 D(G(z)): 0.0009 / 0.0043\n",
"[161/4000][0/600] Loss_D: 0.0161 Loss_G: 10.0137 D(x): 0.9850 D(G(z)): 0.0002 / 0.0001\n",
"[161/4000][100/600] Loss_D: 0.0465 Loss_G: 7.9421 D(x): 0.9746 D(G(z)): 0.0013 / 0.0006\n",
"[161/4000][200/600] Loss_D: 0.0078 Loss_G: 6.4884 D(x): 0.9979 D(G(z)): 0.0056 / 0.0025\n",
"[161/4000][300/600] Loss_D: 0.0244 Loss_G: 5.1404 D(x): 0.9887 D(G(z)): 0.0122 / 0.0082\n",
"[161/4000][400/600] Loss_D: 0.0460 Loss_G: 5.7427 D(x): 0.9718 D(G(z)): 0.0053 / 0.0053\n",
"[161/4000][500/600] Loss_D: 0.0381 Loss_G: 4.3642 D(x): 0.9738 D(G(z)): 0.0065 / 0.0229\n",
"[162/4000][0/600] Loss_D: 0.0384 Loss_G: 5.2230 D(x): 0.9985 D(G(z)): 0.0352 / 0.0094\n",
"[162/4000][100/600] Loss_D: 0.0621 Loss_G: 4.9320 D(x): 0.9841 D(G(z)): 0.0248 / 0.0110\n",
"[162/4000][200/600] Loss_D: 0.0298 Loss_G: 4.4433 D(x): 0.9934 D(G(z)): 0.0223 / 0.0190\n",
"[162/4000][300/600] Loss_D: 0.0184 Loss_G: 7.3162 D(x): 0.9849 D(G(z)): 0.0017 / 0.0011\n",
"[162/4000][400/600] Loss_D: 0.0131 Loss_G: 5.4399 D(x): 0.9963 D(G(z)): 0.0092 / 0.0063\n",
"[162/4000][500/600] Loss_D: 0.0195 Loss_G: 4.4039 D(x): 0.9937 D(G(z)): 0.0125 / 0.0196\n",
"[163/4000][0/600] Loss_D: 0.0514 Loss_G: 4.1065 D(x): 0.9998 D(G(z)): 0.0485 / 0.0292\n",
"[163/4000][100/600] Loss_D: 0.0177 Loss_G: 4.6555 D(x): 0.9971 D(G(z)): 0.0142 / 0.0172\n",
"[163/4000][200/600] Loss_D: 0.0463 Loss_G: 5.9644 D(x): 0.9726 D(G(z)): 0.0091 / 0.0052\n",
"[163/4000][300/600] Loss_D: 0.0196 Loss_G: 5.5772 D(x): 0.9899 D(G(z)): 0.0081 / 0.0076\n",
"[163/4000][400/600] Loss_D: 0.0153 Loss_G: 4.7270 D(x): 0.9994 D(G(z)): 0.0144 / 0.0175\n",
"[163/4000][500/600] Loss_D: 0.0422 Loss_G: 3.7469 D(x): 0.9952 D(G(z)): 0.0348 / 0.0379\n",
"[164/4000][0/600] Loss_D: 0.0056 Loss_G: 6.3223 D(x): 0.9984 D(G(z)): 0.0039 / 0.0031\n",
"[164/4000][100/600] Loss_D: 0.1118 Loss_G: 6.2430 D(x): 0.9742 D(G(z)): 0.0036 / 0.0033\n",
"[164/4000][200/600] Loss_D: 0.0690 Loss_G: 4.4425 D(x): 0.9540 D(G(z)): 0.0115 / 0.0170\n",
"[164/4000][300/600] Loss_D: 0.0487 Loss_G: 3.4780 D(x): 0.9774 D(G(z)): 0.0204 / 0.0613\n",
"[164/4000][400/600] Loss_D: 0.0190 Loss_G: 5.4307 D(x): 0.9956 D(G(z)): 0.0142 / 0.0066\n",
"[164/4000][500/600] Loss_D: 0.0288 Loss_G: 5.5192 D(x): 0.9837 D(G(z)): 0.0046 / 0.0054\n"
]
},
{
"ename": "KeyboardInterrupt",
"evalue": "",
"output_type": "error",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 1\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mepoch\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mrange\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mniter\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 2\u001b[0;31m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdata\u001b[0m \u001b[0;32min\u001b[0m \u001b[0menumerate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataloader\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m0\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 3\u001b[0m \u001b[0;31m############################\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 4\u001b[0m \u001b[0;31m# (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 5\u001b[0m \u001b[0;31m###########################\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py\u001b[0m in \u001b[0;36m__next__\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 188\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 189\u001b[0m \u001b[0mindices\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_next_indices\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 190\u001b[0;31m \u001b[0mbatch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcollate_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mindices\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 191\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpin_memory\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 192\u001b[0m \u001b[0mbatch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpin_memory_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/torch/utils/data/dataloader.py\u001b[0m in \u001b[0;36m\u001b[0;34m(.0)\u001b[0m\n\u001b[1;32m 188\u001b[0m \u001b[0;32mraise\u001b[0m \u001b[0mStopIteration\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 189\u001b[0m \u001b[0mindices\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_next_indices\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 190\u001b[0;31m \u001b[0mbatch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcollate_fn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mi\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mi\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mindices\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 191\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpin_memory\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 192\u001b[0m \u001b[0mbatch\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpin_memory_batch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbatch\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/torchvision-0.1.8-py3.6.egg/torchvision/datasets/mnist.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, index)\u001b[0m\n\u001b[1;32m 53\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 54\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransform\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 55\u001b[0;31m \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 56\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 57\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtarget_transform\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/torchvision-0.1.8-py3.6.egg/torchvision/transforms.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, img)\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__call__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mimg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[0;32mfor\u001b[0m \u001b[0mt\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransforms\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 29\u001b[0;31m \u001b[0mimg\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mimg\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 30\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mimg\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 31\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/torchvision-0.1.8-py3.6.egg/torchvision/transforms.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, img)\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[0moh\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 139\u001b[0m \u001b[0mow\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mint\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m*\u001b[0m \u001b[0mw\u001b[0m \u001b[0;34m/\u001b[0m \u001b[0mh\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 140\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mimg\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mow\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0moh\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0minterpolation\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 141\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 142\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m~/anaconda3/lib/python3.6/site-packages/PIL/Image.py\u001b[0m in \u001b[0;36mresize\u001b[0;34m(self, size, resample)\u001b[0m\n\u001b[1;32m 1710\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconvert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'RGBa'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresample\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconvert\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'RGBA'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1711\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1712\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_new\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mim\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mresize\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0msize\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mresample\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 1713\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 1714\u001b[0m def rotate(self, angle, resample=NEAREST, expand=0, center=None,\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"for epoch in range(niter):\n",
" for i, data in enumerate(dataloader, 0):\n",
" ############################\n",
" # (1) Update D network: maximize log(D(x)) + log(1 - D(G(z)))\n",
" ###########################\n",
" # train with real (data)\n",
" net_D.zero_grad()\n",
" real, _ = data\n",
" input.data.resize_(real.size()).copy_(real)\n",
" label.data.resize_(bs).fill_(real_label)\n",
" output = net_D(input)\n",
" errD_real = criteion(output, label)\n",
" errD_real.backward()\n",
" D_x = output.data.mean()\n",
"\n",
" #train with fake (generated)\n",
" noise.data.resize_(bs, 100, 1, 1)\n",
" noise.data.normal_(0, 1)\n",
" fake = net_G(noise)\n",
" label.data.fill_(fake_label)\n",
" output = net_D(fake.detach())\n",
" errD_fake = criteion(output, label)\n",
" errD_fake.backward()\n",
" D_G_z1 = output.data.mean()\n",
"\n",
" errD = errD_real + errD_fake\n",
" optimizerD.step()\n",
"\n",
" ############################\n",
" # (2) Update G network: maximize log(D(G(z)))\n",
" ###########################\n",
" net_G.zero_grad()\n",
" label.data.fill_(real_label)\n",
" output = net_D(fake)\n",
" errG = criteion(output, label)\n",
" errG.backward()\n",
" D_G_z2 = output.data.mean()\n",
" optimizerG.step()\n",
" if i % 100 == 0:\n",
" print('[%d/%d][%d/%d] Loss_D: %.4f Loss_G: %.4f D(x): %.4f D(G(z)): %.4f / %.4f'\n",
" % (epoch, niter, i, len(dataloader),\n",
" errD.data[0], errG.data[0], D_x, D_G_z1, D_G_z2))\n",
" if epoch % 10 == 0:\n",
" fake = net_G(fixed_noise)\n",
" vutils.save_image(fake.data, '%s/fake_samples_epoch_%03d.png'\n",
" % ('results', epoch),normalize=True)"
]
},
{
"cell_type": "code",
"execution_count": 271,
"metadata": {},
"outputs": [],
"source": [
"fake = net_G(fixed_noise)\n",
"vutils.save_image(fake.data[:64], '%s/fake_samples3.png' % 'results' ,normalize=True)"
]
},
{
"cell_type": "code",
"execution_count": 273,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
""
]
},
"execution_count": 273,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAQUAAAD8CAYAAAB+fLH0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzsfXd4VFX6/+eW6TNJZjKpJCShBQIBkVACEkGKSlMRFd21\nIWvd32LvLvaCBV0rAtbFCirKCkgLLQFpgUCAhDSSQMokk0zv7+8PuPebQMrMZAKo+TzPfRgmc897\nzrnnvue8nSEidKMb3eiGAPZ8d6Ab3ejGhYVuptCNbnSjBbqZQje60Y0W6GYK3ehGN1qgmyl0oxvd\naIFuptCNbnSjBbqMKTAMcwXDMEcZhjnGMMzjXUWnG93oRmjBdIWfAsMwHIBCAJMAVALYBeBGIioI\nObFudKMbIUVXnRRGADhGRCVE5ALwDYCruohWN7rRjRCC76J2ewCoaPb/SgAj2/oxwzDdbpXd6EbX\nw0BEUR39qKuYQodgGOZOAHeeL/rd6MZfEOX+/KirxIcqAInN/p9w+jsRRPQxEWUQUcaZNzMMA4Zh\nwLIsZDIZlEolOI7roq52oxsXHvR6PXj+/OzZXcUUdgHoyzBMCsMwUgCzAfzc0U0Mw4DnefA8L35W\nq9VQqVToDtwKHgzDnO8udCNAeDwe+Hy+80K7S1gREXkYhvkngLUAOACfENEhP+6D1+sFwzAgIhAR\nzGaz+P9AIJw2ztfEXkjoZqh/PJhMpvO2drvEJBlwJ9pRNApihM/nAxGB4zjxs7ADCqcKr9crTqTA\nFLxebyj6B47jwLIs3G43gD/vi8bzPFiWhdfrDcncdeP/wHEciOh8blR7WhPXz8R5UzT6C2ES+/Tp\ng1mzZuHQoUMoKiqCx+PB+PHjER8fD4lEgoSEBFx66aWQSCRwOBz46KOPsGzZMpw4ccIvOhzHQSKR\nIDw8HCqVCsOGDcPIkSMxZcoU6HQ6yGQy7Nu3D1arFV6vFzfffDPMZnMXjz54CAzTH+Yll8uRmZkJ\ntVqN6667Dj/++CPWrFkDu90eMM1zxSzPBa3O0AgLC4NMJoPD4YDb7RbXVyjWzNSpUzF06FBERUXh\n4MGDWLJkSUjn4oJnCgJ8Ph/uueceFBYWwuFwwOl04o033kB+fj6ICE6nEzt37sRDDz2EHj16YPTo\n0Xj33Xf9bj8mJgazZs3CPffcg7CwMBARtFotpFKpuHNmZGSA4zgwDIMbbrgBS5cuvWAXZiD3qFQq\nzJ49G8nJyaiurkZ+fj4cDkfIaQbCqEIB4UXU6XTw+Xyoqanxm7Zw0vR3TFKpFAzDQCaTISYmBnfd\ndRcUCgWqq6vRu3dvFBcXY+/evTh06BDKysqCngOO4/Dhhx9Cp9OBiFBRUYENGzagpKQkqPZawx+C\nKRAR6uvrUVRUhK+++grbt2+H2WyG0WgU9RButxv79+/H9u3b8dtvv2H//v3weDx+01AqlUhNTUVU\nVBQkEgk4jgPP8yAiGAwGvPzyyygrK0NcXBwyMzPxyCOPYNu2bTh69GinF3lzpWp4eDgmT54MjuNg\nNBrR0NCAnTt3wmQyddnLFBYWhosvvhh6vR5ff/01ysvLQ0ZLKpUiOjoaaWlpuPbaa1FWVoa8vDwU\nFRXhxIkTsNlsQbUr9K/5i8uyLHQ6Hfr27Ytp06ZhxowZAACXywWDwYCnn34ae/fu9UssEnRa7UEi\nkUCpVCI8PBz//ve/ERMTg4svvhgRERFwOp2QSCSQy+VgGAY2mw1NTU04ePAgbr75ZhgMBr/GybIs\nJBIJ3G63KDabzWZotVooFAr07NkTQ4cORWlpaejWhzD483kBoPYuhmGoR48elJKSQjKZjDiOI4lE\nQjKZjHiep9M6CQJAWq2WDhw4QJ988gnJZLJ2221+8TxPiYmJdPfdd9OSJUuooaGBmpqa6Oeff6bB\ngwcTy7LEsixJJBKKioqi4uJiWrVqFUVGRvpN48yLZVnS6/U0cuRIevLJJ+nbb7+lgwcPkt1uJ5fL\nRVarlcrKyui9996j9PT0FuMM1RUVFUUvvfQSlZeX08mTJ+nSSy8ljuM61SbDMKRSqSghIYFef/11\nys7OppqaGnI6neR2u8lsNtOhQ4fo3XffpaioqE7RkkgkpNPpSKvV0ltvvUUbN26kgoICMplM5PF4\nyOFwkMlkotraWtq/fz8NGjQoJPPGcRwlJibSBx98QDU1NWQ2m8lms5Hdbie73U5NTU1kNpvJZDKR\n1WoV6d9///2k1+sDWiN33nkn3XLLLRQZGUkymYwee+wxKi8vJ5vNRkajkRYsWEAKhcKf9nb79T6e\nb4bQHlNQqVSk1+spMjKSdDodSaXSdl+M1NRUeuONN8hqtdIDDzxAcrk84IetVCrpscceo7KyMlq6\ndCkNHDiQWJZt8ZuIiAjKy8ujqqoq+vjjj4N+iaKioug///kPGQwGMplMVFBQQG+99RbNmjWL7r77\nblq8eDEVFxeT0Wik3bt3k1KpDOjF7GhRK5VK+uqrr6ihoYGOHz9O999/P0kkkk6/MJGRkfTRRx9R\nQUEBWSwWOnz4MP3nP/+hhx56iF599VVav3491dXVUWNjIx04cCCgcZ156XQ6eu2112jHjh1kMpmo\ntLSUPvnkE3r00Udp7ty5NHfuXNq0aRPV1taS1WqlVatWdbiO/GEI9957L5WXl1NjYyMtX76c5syZ\nQyNHjqThw4dTRkYG8TwvPgepVCpuKBzHBUx7/vz5VFRURMeOHaMlS5bQsGHDSK/X05gxY+irr76i\n77//3t816BdTuGDFB47joFAowLIsGIaByWRqVxxgGAb3338/MjMzwbIscnJy4HK5AqLJ8zzGjBmD\nCRMmIDc3F0uXLsWxY8fO0hY3Njairq4OUVFRGDFiBLRard/HQaGvHMdh4sSJmDlzJliWRUVFBbKz\ns7FixQrk5uaCiKDRaHD99ddj/vz50Gq10Gg0AR2325OJZTIZJk+ejCuuuAJqtRpVVVX4/fffAxK5\nWgPP8xg7diymT58OnU6HqqoqbN26FStXrsS+ffvQ1NSE+Ph4PPDAA5gwYQLi4+PRs2dPHDlyJGBa\nHMdh6NChmDx5MpKTk5GXl4ft27fjxx9/RGFhIZqamsCyLHJzc/H555/joosuwtixYxEZGYnq6uqg\nxscwDNLS0vDggw9CrVbj448/xuuvvw6JRIL6+nr4fD5IpVJxHolIXIfBWh169eoliiMSiQTp6elo\nampCXFwchgwZgrKyspD6olyQ+RQ4joNKpcKoUaOQkZEBk8kEu90uylStISIiAlOmTEFKSgokEgkU\nCgVkMllAk+X1epGcnIz09HRs2LAB5eXlognyTFRXV0OpVCImJgaJif/nvOkPPYEj33777YiOjkZt\nbS2+//57LFy4EDt37hTHabPZUF5eDqlUCrVaDblc7vdYgFPyaFvfy2QyaDQahIeHw+v1YsOGDZ2S\nS5sr5u6++25ERUWBZVn88MMPeO+997B161Y0NDTA6/Wivr4ex44dg8PhgEKhQHR0dFD0AOC6665D\namoq5HI5/vvf/+L999/Hnj170NjYKOqbSktLsW/fPjAMA4lEgri4uKDGCJxipuPHj0dkZCR8Ph/K\ny8shk8lgMBjgdrvhdrthtVqDbr81jB07FjqdDhs2bMATTzyBDRs2YMiQIbj99tshl8vxzTffhFTf\ndEExBUF7K5hzHn74YURFRfllGouPjxfvs1qtOHToEKRSKaRSaUDuolOnToVer4fBYEBDQ0Ob3L2w\nsBAsyyI8PByDBw8Wvw9Euz1gwACwLItt27bhm2++QVVVVYudmud53HDDDdDpdAgLC0N6erpfbbMs\nK56w2vr7fffdh2eeeQYAsGvXLixevDig086ZaK74Gzx4sOjTsWzZMpSUlLQ4tcnlckyfPh19+/aF\nVCrFqFGjgqLHMAzGjRsHqVQKr9eLLVu2oKam5ixFol6vR8+ePQFAtB4F+xLFxsZiyJAh4HkeHo8H\n4eHhokJaGH+ooVKpUFJSgtdffx0nT55EQ0MDxo0bh6ysLHAchxUrVoTWp+R86xOa6xQYhiGWZUkq\nldKAAQNo7969NHz48HZlO7VaTVOnTqW9e/eS0+mkPXv2kE6nE9tTKpV+KXbCwsLo5ptvppqaGtq8\nefNZeoTmF8MwNHjwYFq7di253W7auXPnWXJie3IjwzA0ceJE2r17N7300kvE8/xZ9HiepwULFlBx\ncTHZbDZavHhxpxWAwhUfH08rVqyghoYGcrvdNGfOnICUsu1dN9xwA5WXl9OqVato9OjRZ/VZJpPR\ne++9R6WlpWS322nnzp2kUqkCpsMwDP3zn/+kmpoaWr58OWVlZbU655mZmZSdnS0q/Pbu3dvus+3o\nUqvV9PTTT5PX6yWv10t2u50sFgtZrVaqrq6mr776ijIyMkIyl8L1008/kcFgoIaGBlEXYzAYaO3a\ntTRv3rx2348zvvvj6RSETgm7c0FBAdxut8jZJRIJZDKZyBXHjx+PSZMmYfLkyYiLi4PNZsOmTZuQ\nmpqKw4cPQ6VSISIiAiaTqUPaEyZMwEsvvYSIiAhs2rSpQ/lPJpNBLpfD7XZDoVBAKpXC6XS2GEtb\n4HkeAwYMgMViwZo1a+D1elv8nud5zJs3D2PHjoVSqUR1dTXeeeedkOwGPM8jNjYWP//8M9RqNS69\n9FL0798fcrm8Rf+DxeDBg+FyubBx40bk5+efNY/3338/RowYAaVSCZ/Ph7fffjuo4zYRYd68eQgL\nC0NNTQ0OHz581pxHRERgwoQJ6NWrF2QyGerr6/HUU091yqNQJpNBpVIB+D9TsqBDiIiIwPTp0xEd\nHY2JEycGTeNMrF+/HqNGjYJOpxO9ez0eD+RyOQ4daj16oC3R0R9cUEwBOHW8U6vVGDRoEEaNGoWH\nHnoIDz30EKxWK9LT0zFixAiwLAur1YqFCxeKciJwyl+8b9++eP/99xEZGQmHw4F169bhm2++QUVF\nRbt0iQixsbHgOA5KpbLD3548eRK5ubno168fysrKRAbR1oJrfmT1+XwoKCiAUqls1c+B4zhMmjQJ\nffr0gUQiwebNmwNyTmFZtvkprAV8Pp/o5bllyxZkZmaisrIyaIbT3O0cAA4dOoStW7di06ZN8Hg8\nZ/UhMzMTycnJkEqlMJvN2Lx5s9+0zjz2R0dHi2tBKpWe9fvw8HCMHz9edEYzGo3Ys2dPUOMU4HQ6\n0djYCJvNJooNLMti7969YBgGSUlJSEhICKnH5ZEjR1BTUwOdTgeGYeByueByuVBSUoK9e/e2ek/z\nzTVQXHBMwefzwWazITc3FzqdDlOmTEFcXBzWr1+PkSNHQq/XQyKRQKPRiI4hzRdlfHx8C6WcoB/o\nCA6HAz6fDxzHIT09vcOHarVakZOTA5lMhm+//Va0CrR1X/PviEjUxLe2S/bp0wdxcXHgOA5msxlv\nvPFGQC7HPp+vTdnW5/PBYDDAZrMhLy8PjY2NyMnJCdqJ6MyFt2XLFhiNRpSXl7dqyVCr1QAAs9mM\n7du3o66uzm9azeeQYRgUFRUhJSUFjY2NrXpgxsbGQq/Xg2EYuN1uFBUVobGx0W96rcHtdqOpqQlu\ntxtVVVWwWCyoq6vDgw8+iMmTJ2PmzJnQaDTgOK7TlhwB27dvx8aNG9GvXz/RcuVwOGA0GmGxWFq9\np1MM6XzrE1rzU+A4jvr3709ut1uU3axWKx0/fpyqq6uprq6O3G43uVwuqqyspJycHLrrrrtIqVSS\nTCYjlmVJLpdTTEwMRURE+GUH53mennvuOXK5XGQ2m+lvf/sbhYWFtaorYBiGkpKSaP78+XT99ddT\njx49SCKRiA5OHdECTjmlpKWl0eDBg1vQYBiGDh8+TDabjerq6mjFihVBy8Bt3adSqahPnz6UnZ1N\n9913X6dk7NZo6vV60mq1oq1eGFdSUhIZjUaqrKykzz//nFJTUztFSyaT0b///W/6+9//Tmq1WqQD\nnPI32bt3LzU2NpLJZKLDhw/TkCFDOj0+juNowYIFdPz4cZo7dy7FxcWRXC6npKQkevHFF6mgoICO\nHz8elI9MWxfDMNSzZ09at24dWa1WcjgclJubS7fddlugPh5/PJ0CcErmDQ8Ph1wuh9frFWWjxsZG\neDweqNVqsCwLs9kMr9eLX375BS6XCwUFBS12O2Hn9/l8fh2NvV4vli9fjgceeAAcx2HatGk4ePAg\nDh48KIZzC5GSUqkUDzzwAGbNmgWDwYBjx47hqaeewvHjx/32jfD5fCgtLRUj54RoUJZlkZiYCJ/P\nh7q6Ovz2228BHwMF82BrpwWO4xAXF4dZs2ahb9++2Lx5c0ij9nw+H+rr61uErQuWkMsvvxw+nw8l\nJSX48ccfUV7uVyKgNuF0OvHll1+KgUfNT2k8zyMuLg4SiQQulwubN2/GwYMHOz0+hmGg0Wiwd+9e\nbNu2DU1NTZBIJJg9ezYmTJiAsLAwrF+/vk1TdjBQqVQYN24cBg0aBJ7nsX37djz//PPIy8sLiR7o\nTFxwTMHj8cBsNqOxsRHHjh1DbGwsbDYbVq1aBZfLhaioKBQXF6OhoQF6vR7vvfceLBZLq8fwQJyX\niAilpaXYvn07hg8fjjFjxuCmm27Ca6+9BovFAp7noVKpoNVq0bNnT0yePBlarRYxMTEYOHAgioqK\nsHDhQjQ0NPhN0263t3hxGYZBYmKiGE23evVq/PDDD36313wsbR0fWZYVYx18Ph/KysoCbj9Q+gzD\nID4+HvPmzUNTUxM+//xzbNy4MaigqzNx/Phx8DzfQoQU5lGtVoNhGDQ2NuL7778PiaLW6/XixIkT\n0Gq1MBqNcLvdSE1NxTPPPAOGYVBXV4ctW7aE1EQ4YsQIPP3009Dr9aLptbS0FE6nUwzWCynOt+jQ\nmvgAdOym21UXwzCUmZlJ5eXlZDKZyGQyUVNTkyiuCL7tdXV1dOLECaqtrSWDwUA5OTm0YMEC6t27\nd8B9V6lUNGTIEBo3bhy9+eab1NTURB999BElJiaGfB7+9a9/0f79+6miooK+++67Lp/PHj160PDh\nw2nhwoVUXV1Nc+bMIa1WG9JxMQxDCoWCRo8eTb169aLBgwfTvn37yGKxUE5ODmVlZbUQZTpLa8qU\nKXTkyBHavHkz5eXlUXV1Nb388st00003UUZGRlAm1vaupUuXktPpJJ/PRy6XizZt2kQLFy6kcePG\nBRp788cUH843iAh79uzBypUrMXnyZCgUCnEXkkgkovZ3+fLlyMvLg0wmQ2FhIeLj43Hw4EExdj4Q\nJZPL5QLP85g8eTKysrJQUFCAZcuWoaGhIWQabAEjR45EfHw87HY7Pvroo5C23RqUSiWmTZsm5rpY\nvXo1rFZrSMdFRHA4HJBKpZg5cyYyMjLQt29fNDQ0YNu2bdi3b1/IdlOGYXDw4EGsW7cO8fHxKC4u\nxq5du7Bp0ya4XC74fL6QH+mNRiPq6+sRHR0NhmEwcuRI9OvXDx6PB8ePH0d9fX1I6V2wTCHUL0Mg\ncLlceOmll5Cbm4uYmBhYrVY4HA4olUpotVo0NTVh69atKCkpEV1bBdfhsLCwgG3EXq9X9F/v06cP\n7rzzTuzYsSOkcqkAtVotyv27d+8OeftnoqGhAQqFAr169YLP50NtbW2XZHQiIuTl5WHAgAG49NJL\nwfM8rrvuOuzfvx9Op7PN9RSo6dDn86GiogLvvfceNBoN6urqRCtAe2JbR+A4rs15+fLLL3Ho0CGM\nGDECF198Mfr37w+WZZGeno74+PizzNXtmaT9wQXLFM436urqsHz5chCR6DAlOFKxLHtWYk2fzweH\nwyHuFoGAZVk4HA7k5+eDZVkcPHiww5NGsHbw3NxcyGQyfPnll22as0IJIT4AgBi/0h46Y9+3WCxY\nt24dHnnkEUilUuzZs6fDILpgaBERjh49GlQf20J7TKGgoABFRUX47rvvMGzYMMyaNQtGoxEej6dV\nE2tnFccXfI7GvxoEn/r2EIoMRuc6sa1cLgcRdYm2/Ex0J+1tE37laLygAqK6Gucy1XmwtPzRRZx5\nNGxeE8NfusF6vAneo4HQAiCm0AsEwbrqdsab73zjQkjH/5diCufyVHQuaTU/dnY13eZ6jq6m9Ud9\nsTuDC+Hk/pdiCt3oRjc6RjdTaAZBiXiuaAmVsC4UhKJMmeD52ZXjOtPhqxuhxV+eKTRnBG25Bncl\n7QvhuCig01rr0xGrgdb99HfOm7uCN//8Z0Qg6zDU6/Yvb5JsrrRrL7qwK+h2hR9CZ9BZpkBELXIT\n+gMh/DiQtOsCMxU+/xkRyGYhxM+Eyv/jT8EUhB2KZVnRUUXIlR8oLqSdu7MIhekyUPjLWIVnNnDg\nQHi9Xhw7dszv8O0zxyMwifN18jqfJlCO49CrVy8wDIPKykrYbLZOz8EfmilERkZCoVAgJSUFEyZM\nQFZWFhITE8GyLJYsWSJmKyIiv4OjWJbFNddcgwEDBuDDDz9s4ULKMAykUilSUlJw7NixkMXLS6XS\nFv3jeR46nQ56vR56vR65ubkBMzghM5Q/Waf8QXsv3JkvRUeLUqlUIjk5GbfccgseeughNDY2YsSI\nESgtLQ24XyzL4m9/+xseeOABTJs2DVVVVS3+znEcNBoNWJYNKFjtTCQmJiIxMREmkwk8zyMhIQGz\nZs1CWloa9Ho9Fi9eDCKCUqnEwYMH8d133wVNyx9oNBr07dsXt912G+666y5UVlZi9OjRQefFaIHz\nHQzVVkBURxfP8/Twww/Tr7/+StXV1WS328VYc7vdTpWVlfT111/T9ddfTxdffLHf7XIcR/Pnz6ey\nsjIaN27cWbkO4uPj6fPPP6cePXqELMCmX79+LXIayOVyysjIoC+//JKKi4tp7NixAednjI2NFXNV\nBnJxHEccxxHP8ySRSGjIkCE0fPhw0mg0IQsqUqvVNGHCBPr666/J4XDQkSNHgq43wfM8zZ8/n0wm\nE11zzTVn5YbQaDR0991306233hp0f3mep7Vr15LRaCSDwUD79u2juro6cjgc5Ha7yeFwUGVlJdXX\n15PRaKSysrJWA75CFQTGMAwlJibSM888Q/n5+WSz2ei7777zp/0/b0CUTCbDRRddhMcee0zMciMo\nnITdKjY2FjNmzEBmZiZqa2sxZsyYFlWp24KgvBKyMJ35t5SUFKSnp0Oj0fjd3/Z2WYlEgjvuuAOf\nffYZCgsLRXdqp9MJrVaL+Ph4XHHFFcjNzfWbHgAYDIY2FX6ChQA4VTJOqVSid+/eGDRoEEaOHAmH\nw4GwsDAMHToUERERMBgMWLNmDdasWYMNGzZ06pjMMAzCwsKQlpYGrVaL77//Hm+++WbQ+hXheRER\nqqqqWvSN4zgkJSVh4sSJcLvd+Pzzz4OiIYTMy2QyEJ1K26fRaMAwDOrr65GTk4OlS5ciIiJCnMNe\nvXqhpKSkxXMPlWjDMAxGjBiBSZMmISoqCkuXLsWzzz4bsvb/cExBIpEgNTUVH3zwgVhkU1DaCRdw\nKqipqakJDQ0N2Lt3L3w+n/iytwe5XI7+/fuLiTibRzzK5XKMGzcO0dHRCAsL87vP7T0slmVx9dVX\nY/To0fjss8+wbNkyOJ1ONDU1QaVSiXUIA1WoeTyeNhVPUqkUcXFxePHFFzFhwgTwPI+IiAgwDAOz\n2SxaEJxOJ2QyGZRKJcaMGYPPPvsMKpWqU5WT1Wo1Ro8ejb///e9ITEzEvffe22byUX+g0Wgwbtw4\nsCwrJncR5lupVGLcuHFIS0sLuDBQc5jNZjz66KO4+eabER8fj5SUFKhUKuTm5uKpp55Cfn4+PB4P\nOI7Dr7/+ittuuw3PPfcc5s2bF/IIRgBISEjAtGnT0Lt3b/A8j6VLl3ZKNDoTnWIKDMOUATAD8ALw\nEFEGwzA6AN8CSAZQBuB6IjJ2rpuncPHFF+Nvf/sbbrnlFoSHhyM/Px8bNmzApk2bcPLkSTQ2NuLk\nyZNwOByIjIyE3W4XE5l0pJlVKpUYOHCguOvU1taCZdmzYhFUKhUkEgmamppCMSQ4HA7s2bMHvXv3\nxvTp01FcXIycnBzwPI/CwkL069cP27Zt81t/0fylaI0Z6fV6PP7447j11lvhdrvx5JNPorq6Glar\nFdHR0Vi5cuVZuzbDMGIBldaS2fir0FSr1dizZw+ioqJgNBqRl5eHn3/+OaiTB8uyWLBgAeLi4tCz\nZ0+UlZWdpT9xu92IjIxEVFQUqqqqglZE+nw+bN68GQcOHMCjjz6KmJgYrF69GgsWLMC+ffvE/nu9\nXsjlcng8HlxyySV45ZVXcO+99/r17Pzpm3DKWr16tZjhadmyZcjLywt4TO0hFCeF8UTUPDPq4wA2\nENGrDMM8fvr/j3WWCM/zmDFjBm6//Xao1WoYDAYsWrQI27dvx5EjR0SFovCAGhsb/U7FxjAMYmJi\n0LNnT4wcORJ9+vRBWVmZWOVIOG5ffvnlmDx5MpRKZUCJVDtCeXk5hg4dKiYWjYiIwLXXXouLLrqo\nRayBP+hoYQ0bNgw33ngjJBIJXnnlFXzzzTfgeV7MgtTaMZ7oVPZqIXNza+goA1DPnj0xdepUxMXF\nobGxEb///jt++eWXoFLNSSQS9OjRA1lZWejTpw84jsPOnTuh0WhaJOnNysrCVVddBbVa3emqTVKp\nFJdddhkyMjKg1Wrx8ccf4/Dhw2f132QyYeXKlXjwwQeRmZmJhIQEv6t4d6TMHTZsGCZMmICePXui\npKQEP/zwQ8gZAtA14sNVAMad/vw5gGyEgClERkbihhtuELMBl5WVYfny5TAajWfVTQBaX9ytgeM4\naLVajBo1Cmq1WqxpqNPpUF1dLbYtk8mQlpaG1NRUSKVSMU16KKDT6SCVSmG321FcXAyPx4O8vDzc\nd999kMlk2L9/f0jkRZZlRbHLarVCo9HA5XLB4XB02H5zH4TmEF5SqVTaZvIUnucxaNAg3HjjjQCA\noqIifPvtt9i0aVNA/WcYBnK5HIMHD8akSZMQHx8Pk8mE48ePg+O4s0SE1NRU9O3bFxzHYcOGDZ2a\nQ+HUkZqaCqfTiaKiojbTyVVVVUGj0UCpVCI1NRXHjx8HEbWb50DYeNpatzKZDEOGDMFtt90Gr9eL\nVatWYcdRd+kqAAAgAElEQVSOHV0innSWKRCA9QzDeAEsIqKPAcQQ0cnTf68GENPajQzD3AngTn+I\nMAyDWbNmISUlRTzaL1myJKD04K1BoVAgNjYWUqkU/fv3x86dO7Fp0yawLIubbroJpaWlkEql8Pl8\niI2NRXJysrhbBrPDAa3v5AqFAmazGfv27YPL5YLb7RbrVPA8H9K8B4J51mazQaFQtKgBGczxWi6X\ni3Uy2tqNR40ahauuugr9+vVDXV0d1qxZgy1btgRsLo2MjMSwYcOgUqmQkpICg8GA2bNn4/jx4xg+\nfDjMZrP4fDiOQ0pKCoBTCV63b98eEK3WMH78eMTExKCyshIGg6HdGh88z0OpVGLQoEFYt24dgLZ9\nOARTN3M6FX1rf7/55ptx8803IyEhATk5Ofjmm2/E2pwhRydNiT1O/xsNYD+ALACNZ/zG2FmTpEwm\no/nz55PNZqOGhgbKzs6mKVOmUFxcHCUnJ5NWqw24xLfwW5ZlKTIykpYsWUIPPfQQ9ejRg+bOnUtV\nVVVkNBrJ4XCQy+Uii8VCBoOBSktLad++fdS7d+82TXqBmp7uuOMOKi0tJYvFQna7nRwOBzkcDqqp\nqaH333+fpFJpm7Q0Gk1AY87LyyOPx0Ner5dsNhvZbDYymUxUVFREt912W8Dp3pnTKe/buo/jOLFk\nelNTE915550UHh7e5hwJ7bX2N5ZlSSaTUWZmJi1fvpwMBgPdeOONNHv2bPrtt9/IaDSK82cymWj7\n9u309ddf04cffkh33HFHq7TkcnmHY2ZZlv7xj39QdXU1rVu3jnr16tXufMhkMvrf//5HLpeLdu/e\n3emSfFqtlhYsWED79+8nm81Go0ePbnNNnLm+z7j8Mkl2ynGciKpO/1sL4EcAIwDUMAwTBwCn/63t\nDA0A4k7OcZyYVZllWVxxxRUYMGAAevToAZ1OF5DPvbAj+nw+NDY24r777sPHH3+MmJgYTJ48GU1N\nTWKxFpvNhuXLl+OHH36Ax+NBcnIyrrzySiiVSrFPp8fbaqWijrBmzRp8++23Yul0nufF4rXTp0+H\nTCZr9T6ZTBawVt3tdounArlcLiY/iYmJwfPPP49hw4YF1N4ZzP0sSKVSFBYWiiKQkAY/WIWfy+XC\noUOHsHDhQvz000+47bbb8NJLL2HgwIEAIBZJ+e233/Dcc8/BarVizJgxuPHGG6FSqaBUKqHT6aBU\nKiGXy6FSqdrtiyAezZ8/H1qtFhs2bMDJkyfb/D1wSkwTRAGZTCaeWIJFSkoKsrOzsWfPHni9XigU\nig5jPjojKgUtPjAMowLAEpH59OfJAJ4H8DOAWwG8evrflUH37jQ0Go3oY2C1WuF0OqFUKvHDDz+I\ncl1UVBSSk5NRWVnZbk6+1uD1euH1euF0OnHgwAE8++yz6NevHyIiIqBQKGC32/H777+jd+/euOyy\nyyCXyzF37lxEREQgNzcX1dXVOHLkCCQSSVCRhrW1tfjqq68QExODK6+8EhqNBj6fD3K5HHq9HnK5\nvFUzoODT4C+ICNu2bYNcLkfPnj2hUqlgtVqxePFi7Nq1C3//+9/x0ksvYcqUKX5bOwRG3BZjUCqV\nkEqlIjOqrKxsl5H5o9uw2+3Iz8/HM888gxkzZuDaa6+F0+mE0WhEdXU1CgoKxNR2ffr0QUJCAuLi\n4rB48WKYzWYYjUZ8+eWX8Hq9sNvt7ZrziE5li4qJiQHLsqL+pC1Fs2Ae37RpEwYNGoSioiJRNOiI\n+bT3d4HZ+Xw+NDU1dY3YcBqd0SnEAPjxtIzEA/iKiNYwDLMLwHcMw9wBoBzA9Z3tpJD7kGVZRERE\nICEhAenp6Vi3bh18Ph/CwsJw5ZVXIioqCr/++iuOHj0atHXA4/GgoKAAR48ehUQigUqlEhmPTqeD\nw+GA1+tFz549cdlll2HlypWi/C/4SQTKpd1uNwoLC7F69WoMGTIE0dHR0Gq1AE7pFGJiYmAwGM5q\nN5gdd/z48WBZFq+99hrCwsKwceNGbN68GRKJBEajERMmTAioveZydWsL2+12IyIiAjqdDhaLBeXl\n5e0uaH/0Gm63Gx6PByaTCUuXLsXy5cvFQq8KhQL19fXwer3IzMwUs3EDwPDhw/HJJ5+IJeuFvJr+\nzKFQEGjgwIGIj49v1yTt9XqxdetWEBF+/fXXThe9KSsrQ2xsrGhNq6ioCJmLfavojE4hVBc6kKnC\nw8Ppiy++II/HQ263m8rKyujZZ5+lF154gVatWkWlpaVUV1dHn3/+OWVlZQVaSsvvSy6X0yWXXEIb\nNmygmpoaevjhh0Pm+gucqv8wa9YsOnbsmFgez2w206+//krJycmdbp9hGLJYLLRv3z669tprKSkp\niaRSKUVHR9OiRYvo6NGjdOWVVwbscswwjOgWfeb3U6dOpbfeeotKS0tp2bJlfrcXivnkOI50Oh3N\nnTuXdu7cSddff32rffSnraeeeorcbjdZrVbaunUrDRky5Cy5XtCHcBxHt99+O11++eXUo0cPCgsL\n67CkoHBfa/0ZPHgwPfroo1RZWUkFBQV+9bcNWn8eN2dq5n/g9XrhcrkwcuRIDB8+HADE7MpLlizB\nvn37QupD0BwOhwO///478vLykJaWhpKSkpBzbJZl8d5772Hr1q1ITEzEnDlzAnKpbg8Mw6CqqgqF\nhYXYs2ePaMpLTEyExWKByWRCdnZ2QEfT5lYVhmGgVqsRHh4Ou92O1NRUvPHGG9DpdHA6ndi2bZtf\nbYbC/AqcWitGoxE7d+7E5MmTsWvXrrPELX9prVq1Co8//jgkEgnS0tLw4IMP4t///jeOHz/eIrGM\nUPbw6aefhslkQnV1NdavX48PPvig3arkQl/O7A/Hcbj77rtxxRVXQC6X+136rjOu6H8IpmC1WvHf\n//4XN954o2gOlEqloquxw+HAkSNHsHPnzk65s/oDn8+H4uJiKJVKxMS0am0NCszpGoWZmZlYvHgx\nSkpKYLFY0NTUhKFDh4pVtDuLgoIClJeXo6KiAkSESZMm4YsvvoDdbkdubi6cTmdAC0pYxILOZ+jQ\nobj99tsRFhaG/v37Iz4+Hk6nE/v27RNNc+cSRIS6ujqxSE+wKC4uRnZ2NrKysiCTyXDFFVegpKQE\nq1evhlQqRVVVFaRSKfR6PYYPH46YmBgkJSUhPT0dI0aMwNdff92uCb0thqBSqZCZmQmNRoP6+nr8\n+uuvQY/BX/whmILX68Xu3btx4MABqFQqFBUVwWw2w+FwwG63Izs7G++///45S1py6NAhWK3WkPqb\nNy/uIbjkDh48GBkZGfB6vSGpuyj4KKSmpiIlJQXHjx/HihUrQETYvXs3Fi1a1KmkJUQErVaLqVOn\nIjw8HAqFAlVVVVi6dCkWLVrUab+SYGG1WlFXV9cpxmqxWDB79mx89NFHyMrKgl6vx5w5c3D11Vej\nb9++sNlssFgssNlsUKvVoieqcHq688478f7777eqG2oLSqUSM2fOhE6ng81mw+LFi/Hhhx8GPQZ/\n8YdgCsApt+VJkyYhMjISDMPAYrHgrrvugkKhgEajgcfjCdmxsy0ISrBjx45h3759qKysBM/zrXpU\nBgqe52E2m6FQKFBUVCSaOwFg165d0Ov1ISkGa7FYoNVq8euvv0KlUuH2229HTk4OLBaLWPSmM8jO\nzsYnn3yCuXPnwm63Y/bs2di5c2en+90ZOBwObNmyBQ0NDZ2qnmS1WnHLLbdAo9Hg6aefxoABA6BW\nq1FXV4ewsDBER0fD5/PBbrfjkUceARGhoqICOp0OR44cQVhYGBobG/3evGQyGWbMmAG3243XXnsN\nS5cuPSeJXP4wTAE4taCdTqdYz9Hj8cBms3WJq2drEHQbNpsNe/fuhVarhVQqhcfjCcrq0BxutxsH\nDhzAvHnzsGbNGgAQTVklJSXgOE6sIhRsRiUiwrvvvgutVouEhATYbDb8+OOPIV1obrcbn376qVgR\n+fDhwyFrO1j4fD7s3LlT9B8QvmteqdpfEBFMJhMWLlwo6kqEsOr09HQkJyfD6XTik08+gdPpFBmA\nSqUKKLIWOBWdeeDAAcjlcuzZs+ecZXb6y1eICsa1l2VZpKamwmazoaKiwu+H5W8k3NVXXw2O49C/\nf3+MHTsWixcvRnZ2dotgnwsVDMMgPDwcGo0GTU1NsFgsIV3MwUY6chwHmUwGu90ekhNlc9dw4TPL\nspBKpeA47izXdCHRbCCMiOd59OvXD8nJycjOzg5FViW/KkT9pZlCZ3P6BXJ/oLSExSbkc7gQnpO/\nEMSQUIhVzXG+cjCeLwjWDJZlg/YCPQN+MYU/lPgQanR2kgO5v/lv/Vncgtx7IVdJamscoaoXeWYu\niz8jQ2hvLQjekecaf86k+Rc4/iyLu6vH0aVeexcILsS10M0UutGNbrTABcsUmtvLO2M7D4Qez/OQ\ny+WdcnK5EMHzPPR6fUjKwnUEQaH2Z4OQ7SnQTFjB4lys+bZwwT09YVEJkyIo3LqKlnAJIdlyuTzo\nBCoXKohOZU06ZyatczQf53LeBcevczWH55Ox/qWtD83RPE28v8qd5owLuLBLp3fGaacbpyBkdToX\nc9hFlpZu60MgEHz32+LQzcWKsLAwaDQa2O12SKVS0XPtXDOFM2tdtIcLmWF1FUL9YnVlDoMzcV6Z\n9/kOm/YndJplWbr66qvpySefpIiIiLNCdsPCwmjEiBFBVRlqLf0XwzCk1Wpp2rRptHLlSjIYDOTz\n+cjn85HT6aSqqiqyWq3kdrvJ7XaTxWKhESNGhCzkt7Xxy+VyUqvVYvowpVJJOp2u06HbarWaZsyY\nQS+99BItWrSIkpKSOp0+DDgVtjxw4MCz5iQqKop69+5Nl1xyCfXv379L5ku4CgoKqKqqih588MGQ\njKm9a8aMGfTGG2/Ql19+SS+++GJAafLauvr27UvvvPPOWX2XSCSk0+lo7NixlJGREUibfoVOn3eG\n4A9T4DiOXnjhBTp27BiNHDmyxULjOI5GjBhBGzZsoNTU1JA95ClTptBPP/1EDodDZAgOh4NycnLo\n3nvvpR07doh/c7lcpNVqO2QK/jANhmFIIpGQVColmUxGGo2GLr30Urr//vvpkUceoblz59KHH35I\nzz77LM2ePZsGDBjQInY+UMb0/PPPU2NjIzkcDrLZbPTTTz/R448/7leuxvZoqVQqeu+990gul7f4\nfe/evWnhwoVUWFhIa9asCTgnpL8XwzBUUVFB1dXV9Pbbb5NKpeoSOsIaNJvN5HK5yOFw0MmTJ2nR\nokUBl/o785o5cyZVVlZSampqi7mWSCR05ZVX0u+//05r1qwJpM0/Xj6Fto57EokEMTExkEgkCA8P\nb/E3IX14v379oNPpQtaXkpISLFq0CE6nE5mZmTh+/DiWLl2KtWvXoq6uDj/99BPefvttTJ8+HSdP\nnhSLzrR37OvoSMjzPBQKBW644QZkZGQgPj4ew4YNg1qthsPhgFQqhUqlAnAqyMdsNqOgoABXXXWV\n6ALbEQ2pVCqKSkSnwopdLhfkcjmkUilGjx4NtVqNJUuWoL6+PuhjbM+ePTF+/HhkZmZiy5YtIj2v\n14u4uDgkJCSE9Hk1B8MwSE5OhtvthtfrhcFgCLni7kwdjcfjgVQqhUQiEUsGJCQkiOndg2k/OTkZ\nCoUCw4YNQ1FRkdiOUA4vOTkZ8fHxIR0XcIFZH9qaPJVKhdTUVHAchwEDBrQIgVUqlbjkkkugVqtD\nlnMAAI4ePYq1a9fitttuw/Tp0/Hss8/i559/FuMPtFotHA4H6urqsHHjxk7LrxzHIS4uDq+88gre\neecd3HTTTZg4cSIiIyNFv32hlJvD4YDb7YbRaMTq1asDGrdOp8Pw4cMxduxYhIWF4bfffkNOTg6s\nVqvYZmJiIq666iooFIp222prvAzDICkpCXq9HgsWLMA111wjJrT1eDyIi4sTE9SGEhzHQSKRQK1W\n46abbkJMTAyUSiWSkpJCujYAYMCAARg+fDgiIiKgUqlQWFgopue3Wq3Q6/W4++67z9rEAhlLTEwM\neJ7H9OnTERMTIyq0ZTIZhg8fLjLyUOOCOimcifDwcAwePFisgxAXF4fk5GSEh4eLyVkZhoHH44HH\n40F1dXXANNqKOBR2Abvdjv3794tRinq9HuPGjcMrr7wCi8WCvXv34rnnnutUtqfevXvj6quvxoMP\nPgiNRoNXXnkFZWVlOHLkCHw+HwwGA06cOAGPx9OiAK5EImm3ZmRrsFqtuOiii/DEE08gLCwMmzZt\nwi+//II5c+ZArVZj//79sNvtOHz4cNBjIiJs3LgRH330Ea677jqMHj0au3btQlVVlXjqsdvtKCws\nDKkCVHhmDocDOTk5YFkWtbW1yM7ODpnrtYBRo0aJGZ5tNhtWrFiB66+/HjzPY8qUKXj++edbLWXn\nDxiGgc/nwxdffIERI0YgLCwMiYmJqK+vh9vtFk+UHo8HhYWFIR0XcAEzBYZh0KNHD/Tq1QvDhg1D\nWloa6urqoNVqxRdZLpfjrrvuwrhx46BQKIIumtJRyTPgFOfW6XRQq9WYOHEipFIpSkpK8Omnn3aY\n8rs9MAyDmTNn4l//+hdUKhU+++wzfPDBB2IiVSFZp8C0mheiCWah+3w+9OnTB263GyzLIjo6GpGR\nkWLiU7lcjtra2qCPvc0hFFvlOA5Ep6II582bhwEDBoDjuKCYeHsQ+iuVShEeHg6WZVFUVISdO3eG\nPIYgJSUFLperRfSjUGT28ssvh8ViQW5ublA+L4LfjE6nw9atWzFu3DjRZC4Uhhk2bBgkEkmn1l5b\nuCCZAsdxiIyMxNChQ6FQKHDw4EGwLIvevXujrKxMzMCrUCjQo0cPJCQkgOO4gCdIiEKUyWQd1hrk\neR69evXCtGnTMHHiRDidTvz4448BFX9tDUqlEjNmzEBERAQ8Hg+OHz8Ou90Os9ksyv6hhFDaPiws\nDPn5+ZgzZw6sViuSk5Mxc+ZMVFRUYMmSJWhsbOwUHY/Hg759+wIAjEajmBKtsrISERER4Hkev//+\ne1BttyWqCTus2+3GxRdfDI/HgxMnToj5N0KJqVOnIiwsDCUlJXjxxRexa9cuxMbG4vLLL0dSUhI+\n/fRTMcu3vxC8JQVns7q6OgwfPhwOh0MU74gI0dHRonflrl27Qjou4AJkCiqVCtHR0WAYBhEREdi9\nezfy8vLAcRyeeOIJ7Nq1S8y/L3ggCoshkBdIKNzirwejXq9HUlISRo0aBSLCt99+i++++67F6SSY\n5CcJCQlikVSHwyEyB+EoHKyuoq2+ZGVlQavVoqCgAPfeey+KioqgUqnw8MMPY+7cuXjyySfx+eef\n+12QtS06ws7Z2NjYQkwoKSlp8TnYcbX1N7VaDa1Wi9mzZ6O8vByFhYVB53Ro73nq9XocOXIEDz/8\nMPbs2QOVSoV//vOfmDt3LiwWC956662AKpMrlcoWyliv14tjx47B5/PBaDSK+hKv1wuNRiOevior\nKwMeV4c43+bI5iZJlmXFVNc6nY4mTZpE/fr1I5VKRddeey1VV1eTyWQSS7k5HA6yWq1UW1tL+fn5\nlJCQ0KoppqPU2u3Z+jmOI5lMRhs3bqS8vDw6cuQI/e9//yOdTtcqnY7KeZ15qVQqqq6uJq/XK/pB\n2O12slgsVF1dTV988UVQNnZhLlsbz5dffkknTpyg2tpaqqqqosbGRjIYDJSdnd2u70AgPhEsy9Kt\nt95KjY2NZLPZyG63k9PpJKfTSdXV1bRo0SIaO3Zsm/cGM2aZTEapqan0wgsvkMvlory8PMrKygr4\nmXQ0hwBo2bJlVFVVRbW1tVRXV0cmk4kaGhpo69at9Oqrr7bbZlvrkOM44jhO/M3AgQMpLy9PnDuX\nyyWue4PBQLt376ZXXnmlTTqt0Or6snGhRnNOaTKZsH79ehw7dgwSiQQXX3wxqqqqUF1dDZPJBJvN\nhry8POTn54va7uHDh4spzJqjvSAWorZzFgjynVD6S61Ww2Aw4Ntvv4XRaGz194HuSFKptIUGmeM4\n0bQVERGBq6++Gj179gyoTQDtuuPu3LlTrLYdGxsLpVIpKq7a2r2DSRKzdu1arFu3DkajUTz1+Hw+\nhIeH45prrsH117deJ0gwmwYKjUYDnudF60xYWBi0Wm3QQUztzeGhQ4cgk8mg0+mg0+kgl8vFMn7t\nVdNuq73mJwShEK1er8f//vc/FBQUoKGhATabDSaTCQaDATKZDP3798dVV13VagCfRCIJWid0wYkP\nAgTlGhGhqakJb775Jn755RdotVqxbuT+/fuRlpaG119/HWq1GjfeeCOMRiPy8/PFTMs8z7cZ9Sgo\niYS6f80nkTldazEiIgJJSUmIjY0Vy3Xt27fvrAlXKBRBZRpyOp0wGAwiM/D5fDCZTMjPz4dMJkOf\nPn2Qnp6OY8eOdVrxJ+DgwYMwGo2IjIwEANEakJeX167sHciL6vV6UVNTg2effRazZs3C1KlTkZCQ\nAI/Hg9jYWISHhyMtLU1U0p15b2u0OmJMwktz8OBBWCwWFBYWwmg0dklehkOHDsFms4mKb6fTCavV\nir179yI3N7fN+/x9hkSnSvzt2bMHX331FXr27AmtVgutVouMjAzMmjVLTCkfGxuLmpoacf0J8/Sn\nYwrNB0REaGhowO+//y4qBgWO6vP5UF9fj4iICGRkZGDChAnYtWuXODltLTChXWE30Gg0sFqt4m+Z\n04VFExIScM0114h1B7dv347S0tKz2hJqUQiJZf19IILG2ul04tixY2hsbMSnn36Kbdu24fLLL8d1\n110nap1DwRS8Xi9yc3Pxyy+/4F//+pc4nyaTCSdOnGjzvmBoExGOHj2KFStWwOfzYcCAARgxYgSA\nUxaf+Ph4MW9ic7SVfq6jPjgcDtTU1GDHjh1iHZCDBw92SfaitWvXYtWqVZg7d67I0I1GI06ePOm3\nPqYjeL1eWCwWHD58GCUlJeKa5HkeM2bMgEwmA8/zGDx4MNauXSvOD1EnMzadb31Cc51CMJdcLqfx\n48fTrl27yGg00ssvvxyQ7MswDKlUKpo/fz49//zzNGfOHNLr9ZSUlER33HEHrVixgpqamuinn36i\n3r17k0KhaLetQF1bOY4jo9FIR48epWuvvZb0ej3J5XKKi4ujJ554gvbu3UszZ84MKq6jvX5qNBp6\n++23yePxkMvlopycHLr00ku7JH6D4zgKDw+nYcOG0RdffEFHjhwhq9VKdrud7r///oBoMu2Uved5\nnqRSKaWlpdGBAweoX79+IZ231tbefffdRwaDgVwuF23bto3Gjh3baffmjq7IyEh6/PHHqbq6mhwO\nBy1cuNBfd/E/T+xDR5dEIqE333yT6uvr6a677gpogXEcR2q1mvLz88lkMpHBYKD58+fTunXrRMWm\nwWCg8ePHt1AChfKFqa2tpS+++IJSUlJIJpNR37596Z577qENGzZQaWkpRUZGhowuwzAkl8tp4MCB\ntGfPHnK73VRaWkpXXHFFiziFUF4Mw5BCoaDo6GhSKpWUmppK69atI6PRSA8++GBA7bRXk1GpVFKv\nXr3ohRdeoPr6epJKpV0WpCaTySgpKYnWrl1LNpuNTpw4QVOnTiWZTNZlNM8c68qVK8lisdDLL7/s\n731/vNiHYCGIF3K5HH369AnoPkEsEI7REokEN910k6iHqKiowOrVq5GTk9MlobOCUsntdsNkMsHj\n8eCDDz7AyJEjwTAMampq0NTUFDJ/BSE9/RtvvIFBgwYBODXGoqIiv46cwYoxgjOWYH83GAyQSqUY\nO3Ys3nrrLb/a6EhOZhgGKSkpGD58uGi+C5Ue5kwMGTIETz/9NLKyssCyLCwWC4qLi89ZolVhHlmW\nRf/+/UPa9p+CKXAch6amJrjd7qA0zT6fDx9++CEeffRRqFQqnDx5Ejt27MBPP/2EI0eOiI4jXQFB\n/hs0aBAmT56MyspKsVRcWVkZli9fHnJX4MGDB2PMmDHgeR5OpxM1NTWiwrWjMvHBQLCxC0FbycnJ\nuOiii8R4j1AhPT0d06ZNg0ajQWNjY5fmkJgwYQImTZokWkrMZrOo1D4XCWdlMhmAUwmBQu2Y9Ydn\nCkJMwqFDh8SFEB4eHpDjCBHhgw8+wPvvvw+pVAqWZeFwOM5JYhKO47Bo0SKkpaXhnnvuQVNTE6ZO\nnYr6+nox138o+yGRSJCeng6z2SwqqsaOHYt33nkHTzzxBPbv39/qfZ1xomJZFmq1GikpKfjwww+R\nkJAgRnvW19dDqVR2ukgLy7JYtGgRIiIi8MMPP2DcuHFddkoATjmdNTU1ISoqCizLIjY2Fs899xye\nfPJJFBcXt8oYQqUsVqvViIuLQ0NDA9xuN5qamqBSqWC320OyVjpkCgzDfAJgGoBaIhp0+jsdgG8B\nJAMoA3A9ERlP/+0JAHcA8AL4FxGtDbRTgUye1+uF0+lEeXk5ysrKoFAooNVqYbVaRcuCP20JO6TD\n4TinRUe8Xi8WL16MxMRE6PV6lJeXi6XWgk39JbyIre36Xq8XK1asQFlZGYYMGYIrr7wSjY2NICKM\nHDkSBw4cOIumXC5vl1F2VLvA4/GgqqoKBoNB9E6NjY2FRCJBaWkpJBKJmP8wWFMaEaG+vh7FxcV4\n9913O32ya28OAeDjjz/G1q1bMWjQIKSkpCA1NRVSqRRZWVmor68/q5qXRCIJWVEXm82G2tpaFBUV\nwWAwICwsDOHh4fD5fGKgYGdodJijkWGYLAAWAF80YwoLADQQ0asMwzwOQEtEjzEMkwbgawAjAMQD\nWA+gHxG1K4w3z9EYjKswcMofYdq0abBardiyZUvIo+L+SBBMV20dKwXdidfrxb333ouKigoYjUYw\nDIN169adNfftpX0L5HkxDAOtVoukpCRce+210Ol0+OGHH7Bp06ZO62sYhsGsWbOwa9cuVFRUhKS9\n9uZQqNxERIiMjMQll1wCu90OmUyG3Nzcs+JwOpqnYJzD9Ho9srKyEB0djU8//dSfyuR+5Wj01zqQ\nDDq1jY4AACAASURBVOBgs/8fBRB3+nMcgKOnPz8B4Ilmv1sLIDMQ60Nnteydvf9caI67+motxZw/\nvw9m7BzHBXVfZ2i21Z5gbQhFm8G0E8rxBPoM/Pxtl7o5xxCRwAqrAcSc/twDQPPQsMrT350FhmHu\nZBhmN8Mwu5t/31mZqLP3h0psOJ+1IwI9Pp7BoANCcy+6QJS8gdLsSMlJROLRPBTPMJh2QkE7GGVu\nqK1inVY0EpHAHQO972MAHwMXRor3UONcZv69ECBYUbqy/b8CLoRxBntSqGEYJg4ATv9be/r7KgCJ\nzX6XcPq7bnSjG38QBMsUfgZw6+nPtwJY2ez72QzDyBiGSQHQF0BwmTSaIVj7+IXS/l8BzedQiC7t\nyvb/ijhX4/bHJPk1gHEA9AzDVAKYD+BVAN8xDHMHgHIA1wMAER1iGOY7AAUAPADu68jy0BGEnIRd\n4RAiLF4hcEr4/EcvnCIEUAnjUKvVACCaaUNNqzlUKhU4joPZbA7pUZiIWpQTFDxBhWf3V8C5Ei26\ny8Zd4Ai23FtzE5eg9PTn5Wm+yweTX1BwJguFPb49OkLb59KnxF9ciH06je6ycZ1BsP4SoaSvUCgQ\nFRUFAKisrBRPM/70qflvhPs6AsdxiI6OhlKpFHNems1mv/ssOCoJ/e+quTuzXYHW+X4ZmdMJVyUS\nieihGeqTrnBa6srT0R+GKQh1As5MhgKE/gWOiIiATCZDfX19l7qrtgWJRILo6GikpqZi8uTJ0Ol0\nqKiowKpVq9DU1BRUbsP2+suyrJgB6h//+AfS09MRGxuLr7/+GosXLw7YqkBE6N+/P1iWxaFDh7r8\nRY2Li0OfPn2wY8eOVp2NzgWzEOI7VCoVIiMjodFo4HA40LdvXxQUFKCwsLDVhDL+gOd5yGQyqNVq\nREVFoa6uDiaTSfS49MNpKTD448zQ1Rf8cLwYOHAgLV++nKKiolp8L5FIaPLkybR582aKi4sLidPK\ns88+S3V1dTR79uyznKF0Oh2988471KNHj5A7oTAMQzExMVRcXEwWi4U8Hg/5fD7yeDzk8XjIbrdT\nRUUFTZgwgXQ6HSkUiqBj9yUSCclkMuI4juRyOYWHh1NqaqpI1+PxBF3WTSqV0uOPP04Gg4FGjhxJ\nPM+3Wq8zFI4+EomEXn31VWpqamr1eUmlUrrkkkto4sSJIX9eQvtRUVG0Zs0aqqurI7vdLuYQdblc\nZLPZqL6+nu677z667LLLOlyjDMOQXq+ntWvXUnZ2Nr3zzjtUWVlJTqeTPB4Pud1uqquro8bGRjKb\nzXTy5MlA5vGPFzrdFkdnGAYZGRkYOnQorrjiCixbtkzkuEIJrbS0NKSmpvqd5r0tWkLuQq/XK2bM\nFcCyLHr16oUxY8YgOjoaVVWhs7YyDIPIyEj8v//3/5CYmNhCqSbsMDzPIzo6GvPmzcOSJUtgMBhQ\nXFyMmpqagOkJJyBhITAMA7PZjB07dqB///7geR7PPfdcUMdyr9eL/Px8eL1ecTc78/5QOokJmZqE\n7McCGIZBeHg4LrnkEkRGRmL9+vUhoSlAqVQiMzMTt95661m1GYR+yGQySKVSPPnkk2hoaMAvv/yC\n+fPnt3n64nkePM+LsRTh4eGIjIwUn8/Ro0f/P3vfHR5Vtb39njO9ZSa9FwghhBBKAEOCIMI1EKQp\nAqKIckFFr12veq149T7Wn6JYUVAUFVFAuHSlg9SEACGEkF4ndTIp02fW9wec8yUhZWYySPDyPs95\nIDNnzj57n33WXmvttd6Fzz77DGq1GomJiRgyZAiio6ORn5/vsTHtVUKhs06xLIvQ0FAEBgbiqaee\nwpkzZ3Dq1CkQEcRiMRITE/lU0p625eXlhaSkJFitVr78PPcCyWQypKamIigoCF5eXq51rgswl6jJ\nU1JSsHjxYgiFQr4IDFcP0eFw8A68Y8eOoaysDJWVlairq3NLPW7thGRZFnK5HBMmTICfnx/q6uqw\ndetWnDp1yulrtz5PqVRi4cKFEIlEV9x88PLywpgxY/hqUK3vQy6XY+TIkRg/frzH25VIJEhISMAn\nn3yC6Ohovl2uYheXe2O1WsEwDIqKinDy5El88803XZoQVqsVNTU1WLJkCYYOHYoRI0bAarXixIkT\nePnll3H06FFYLBYIhUJ4e3vjkUcewRtvvIFHH30UNTU1HulbrxIKHYFzqnz66ad48sknIZFIkJiY\niPz8fLS0tEAqlUIkEqGlpQUXLlxwux2NRoO//e1vUCgUYFkWNTU1qKqqauOgczgcPPuxuy9jR5gw\nYQIeeughvv3MzEysW7cO2dnZKCkpgU6n47cT09LScOHCBWRlZcFms3WZpAR0vyIPHDgQ//znP3HL\nLbfwDMxLlixBcXGx0/Yvt+vg6+uLbdu2ISoqCmKxmC/c0x1YloVare6QIbszCAQCfPfdd5DL5YiK\nikJOTs5lTlG73Y7IyEgMGDCgQ15NdyGRSPDhhx9i9uzZUKlU0Ov1WL58OQ4dOoSqqiq0tLSgoKCA\nL/Hm6+uL6uqL8X3OZL5ymax9+vSBQCDA5s2b8fbbb7fJYOX4G4uKijBv3jy8+eabePDBBz3igOz1\nQqH1AFZXV/PU1QKBABqNBs899xxuueUWKBQKt8NsGYZBUFAQ/P39kZqaCl9fX2RlZfFqG3Bx4k6d\nOhWTJk2CTCbzGDmnUCjErFmzMHHiRJ5A9ZdffsGqVatQWVnJe7C5F3T37t3o378/v1XZETiVvzuE\nhITgvffe46spVVVVYenSpS4JBODi2Pj4+GDevHmIjY3lqc7Xrl3b5QvACVWxWIzIyEinhALnFI2P\nj8eNN94IjUYDIsKGDRsgl8vbVLYaMmQIpk2bBrVazb+UPYVQKMSECRMwd+5cyOVy1NfXY+3atVi9\nejXy8vJ4Il5uLlosFtTX17v0sjIMg5tvvhljx46Fv78/nnnmGZw/f/6ysWxubsa2bdvw2muvYdy4\ncQgKCkJFRUWPF6peKxTar8Icz4HdbudXTl9fX/j4+CAgIAAsy/K07q6AZVl4e3tj6NChEIvFyMzM\nhNVqRVNTE88zAFysRZCQkIDw8HAIhUKUlZV5REtQqVSYPHkyb/7k5eXhk08+QWNjI399bnXhVtQz\nZ87wefMdgVu5ufz9jiAUChEfH8/Tvmm1WuzevZsvaussmEtU+DfeeCMWLFgAqVQKm82G1atXY8eO\nHZ1uxXFCi2EY+Pv7Q6PRdOudZxgGCoUCU6ZMwb333guNRgODwYD09HS0tLRcxgodERGBYcOGQSgU\nYtOmTU73qSv4+vpi4sSJkMvlICKUlJTgxIkTOH/+PP/it++Dq8xIRITg4GDExMSgqakJ+fn5nVIB\naLVaqFQqyOVyREdHd8nI7Sx6nVDggmfaT3hOKDQ2NsJisfC06DU1NS5n3HHgCq5wKuiZM2ewf/9+\nsCyLGTNmoLCwkK/F4Ofnx5cD74o23tW+zp07F0FBQXA4HKioqMCrr77aJWuUXC7vliuCK0zC+SQ6\nGpdhw4bhpptuglQqhVarxb59+/DFF1+4XGlaoVBg6NChCA8PR1BQEBiGwXvvvYeXXnoJQNfmC3OJ\nyESr1aKiooLXAplLdRTaw8fHBzfffDNuuOEG/oWZNGkSzp8/j7CwMBgMBl6DEolEiI6OhsViQVVV\nFTIyMlzqV2eYM2cOZs+eDYfDgaqqKnzxxRf45ZdfupwP7iweo0aNgp+fH/R6PV9MpyNwNHqctnXg\nwAGX22qPXicUWnvDW0OlUvGFWTZs2ADg/3vl9Xo9srKyEBAQAK1We9kACoXCDlcsq9WKurq6Ni+P\nRCLB2LFj8dprr0GtVvO1Kk0mEwwGAy5cuACdToe+fft26PEVCoVOE4aGhITgb3/7GywWCzIzM/Hi\niy/i6NGjADoWjizLYvDgwZBKpThx4gTMZnOHK6vRaITRaOxyh0UoFCIwMBBEhFWrVuGTTz7p1FHV\nVfi3wWBAVlYWpk+fzle6qqio4F9OiUQCjUYDsVgMvV7P2/0ymQy+vr5oaWnhiWntdjv8/f0RFRWF\n9PT0y1ZYznvPsixuvfVW+Pn5Ydq0acjPz8fs2bMxduxYyGQyMAzDO2RXr16NsrIyBAcH4+zZs5f1\nSyaTOU29JxaLERwczHNb1tbWorS0FCqVCgqFAna7nS8Y5K4WyWmukyZNwv79+7F48eJOFwGWZaHR\naFBbW4vQ0FDMmDEDq1evdqvd1uh1QoFD+0EVCAT46aefMHToUMTExEClUvFbXgqFAiNHjkS/fv1Q\nW1t7WTGRzoQCAF6ofPTRRxAIBOjbty9mzJgBnU4Hi8UClUoFh8OBb775Bna7HWlpaYiNjcXNN9+M\nyspKvhy5xWLh7V1nV9u4uDi+SpLRaERlZSXsdnubUnJWqxUOhwMsyyIyMhKzZ8/Gvffe26lA6GoM\ngYsvgkQiQW5uLjIyMnDbbbfh9OnT3eYqdPadw+FAc3Mzdu7ciSlTpiAmJobnmqyvr0d0dDT0ej1M\nJhOOHTsGmUyGYcOGYejQofDz88OmTZsQGxuLqKgoZGdnIzY2FjqdrsNqykQEs9mMHTt2QKlU4sUX\nX8Tdd98NtVoNsVjM+zIMBgN+//13/Pzzz0hJScGkSZOQlJSEw4cP84Fh9fX1sFgsUCqVTm9ji0Qi\nfrtYKBRCJpOBiBASEgIigsFggFAoRENDg9th3iKRCNOmTYOvry/S09O79YXIZDJem9VoNFAoFG2K\nHruDXisU2qOhoQFLliyBt7c3EhISMGDAAAwfPhwJCQmIjo7mHYG1tbUoKiriX0xnQkJbb//l5ubi\nzTffRFBQEGQyGaRSKRoaGlBaWoo+ffpg5syZUCqVePDBBxEVFYWsrCxUVFTg8OHDkEgkYFmWZy3u\nCgzDYPDgwfzKVlVVxe+kcGXcuJWsf//+GD58OCZMmACdToeqqqpu1XJOS2h/Hrf3TURobm6G2WzG\n+fPnuzRJupvcHMU5N0ZyuRzz5s2Dn58fJBIJSktLkZubi7i4OEydOhURERF8lN4dd9wBHx8fiMVi\nNDU1oaWlBbt27eqSFdlgMGD79u2orq7G7bffjpSUFBARXzLwyJEjyM7ORlhYGEaNGoWYmBgwDIOd\nO3ciMDCQJ3nNyspCTU1Nh9plR5BIJDz3oslkgtlshkKhwIkTJ6DX68GyLHx9fREbG4v8/HwYDAaX\nBQO33cjFy6hUqk5fcofDgfr6elRWVsLLyws1NTWQSCT/O0IBuCgYuAKbJ06cQFlZGWJiYviBnzZt\nGvLy8pCXl8f/hqh78o/WD85ms+HcuXPIzc2FQCCAVCqFxWLhVwnOnxAeHo7Ro0dj+/btyM7OhsPh\ngMlkcnoSMAzDS3iWZTFu3DgAwA8//IBTp05Br9fD29sbw4cPx6JFizBs2DCIxWJ8/fXX3bbR+vuO\nTAij0QgvLy/4+vpi165dKCoq6lLr6C4py2q1IiMjA2vXrsWgQYOgUCgwbNgweHl5wWKxwMfHB336\n9IFUKkVwcDCI/j9DtUqlgsVigc1mg81mQ2NjI44dO9ZlH61WK7RaLbZu3YrDhw9j4MCBUCgUvHO2\nuLgYLMti/PjxvKbncDgwYMAAlJaWIicnBzk5OSgvL+d3eJyB2WyGxWKByWSCn58ffHx8EBcXh/T0\ndDQ0NPDErRMmTMCPP/6IjIwMNDY2OnVtDkTE72zFx8cjIiKiS03GaDSiqKgIYrEYX375ZY8FAn8T\nV/uAG+HALMuSn58fzZgxgzZu3Eh6vZ7MZjP99NNPV6xsl0gkov79+9Nnn31GeXl5tGjRIpdK1HEH\ny7Lk4+NDH3zwAZWXl7cJX01PTyedTkeNjY3U0NBAVVVVlJWVRefPn6ddu3ZRcnKy02MkFAovuz+u\nzN7zzz9PmZmZTleF6i7cmblUbUskElF8fDwtWLCAPv30UyopKaHi4mLS6XSk1WppxYoVtGTJErr5\n5pspLi6ORCIRCQQCEovFFBERQeHh4RQeHu427yNXPp67H5lMRlFRUfTAAw9QaGjoZZySroRxS6VS\nWrp0KdXW1pLVaqXc3Fx6+OGHady4cbRixQrKyckhrVZL5eXlNHbsWFIqlW7NM5lMRlarlVpaWmjT\npk3k5eXVaZi4WCymI0eO0NKlSykqKqq753nthTk7C06y19XVYdOmTThy5Ag2bNiAoUOH8o7DKwGr\n1Yr8/HwcO3YMY8aMwalTp9zKfuNW79ra2jZajEwmw4ABAyCVSvnVVCQS4cCBA9izZw82b97s1JZT\n6/Rn5hJ3Ile05J577sGjjz4KjUaDuro6p1mvnfFfcFrU2bNnkZ2djdWrV2PNmjXo168fv7IuX74c\nANDY2AidTsc/K7vdztvP7trj7bUZrvpXZWUldu7cCa1We9nccGX7ldM6OR+V0WhESkoK7rvvPoSH\nh/NjfPToUWRkZLgdy2IymdDS0gKxWIzBgwcjJiYGmZmZ/L1z6elyuRx9+vRBfHw8goKCEBQUhLVr\n1+K///0vbxK7g2tSKHDgJkFzczNqamogFArRv3//K9qmw+FAeXk5P8ndvYZer8enn34Km82G119/\nnd+ea/0yOxwOVFdX45FHHkFNTY3TdSC4ceGISLy9vTFq1CgMHjwYc+fO5bfv/vjjD4/EWnR2D1ar\nFQcPHsQff/zBx010VZfA49l+l2CxWFyKluzqOr/88gsmTZqEvn37wmazQSwWo0+fPtBoNDCZTDhz\n5gxWrVrVIzWeiLBt2zaMHz8eMpkMd999NwoKCtDU1MSXN/T398egQYMwdepUSCQSvjr6kCFDsHv3\nbpdS3tvjmhQK7bfrVCoVL6Wv1CRvDW7XgWM0chXcS6HT6bBs2TJEREQgPj6e916PGjUKZrMZ27Zt\nw6efforq6mq3GZO4oKfFixdj+PDhUCgUqKiowKpVq/Dll1+6dU1XwNnzf0Yptc7Aq8WXtot7cp2z\nZ89ixYoVWLx4MQoLC/mSgnq9Hnv27MHSpUtx8uTJHt/zQw89hGXLliElJQXz5s1DREQE9u7dizvv\nvBMOhwNSqRQajQZ+fn68z4dzdI4ZMwZ79uxxXzBdbX+COz4FXLIFFQoFDRs2jB566CHas2cP1dXV\n0c8//0xqtdrj/oTW7fr4+NCvv/5KU6dOJYlE4pFaFRKJhKRSKYnFYt4WDgwMJD8/vy5/50zbAoGA\nxo8fTydPnqRTp07R3LlzPV49u7cfYrHYY2XphUIhRUdHU1xcHIWHh5O/vz8FBgZSZGQkBQcHe2xs\npVIpjR49mvLz86mqqooqKyupubmZT8/W6/VUVlZGjzzyCN1+++0UERFB/fr1o7CwMFKr1R351q5d\nn4IziUYOhwNGoxF5eXkQCAQYOnQowsLCAFxMbmpubm4veDwCbpfh6NGjUKlUkMlkfEk1d9vhVG3O\nZCCiNgFI3f3WmXvOyMjA//3f/8HHxwfp6el/ikblKq4kRyan6rfXJt0ZB64MXusycK3v2VNjazKZ\ncPjwYSxZsgQJCQlwOBwICwvjIxzLyspQUVGB9evXw2w281qQWCyGUqmEQCBwq/Rgr+NodJVFiaPA\nio6Oxr333ouCggL88MMPHktY6qzNPn36wG638zRpvRlczoBUKuWzLf8Xy+q5y3x0tSGRSPj0eoVC\nAa1Wy/uguAWkNbjcF850awWnOBp7nVDoyYNzdaXpaerz1eYEdAUcRwPnfLxW7rs1rtX77kVwSii4\nW/fhiqE9c44raK/GOXN+T9AbJ2hnY9aae6En9y0U/nkWZ/u+9Mbx/iui1wmF1rg+CVzHlR6zP3MX\n4frzvzro1ULhOq7jOv58XBNCoXVQz9Vq/6+IP9MUuI5rB71+trMs61KJ8yuB9n6OngqoqyngWoMr\nEiMWi+Hl5QW5XH61b+k6egF6vVBwOBxXtASZM+Aox/z8/CCTyfgybO6iN9jKXJ+eeuopbN++HUuW\nLMHw4cOv9m15HK1zP67DOVwT+uPVeIk4diKhUAilUsmTw/76668wGo0up8S62jbgXO1HdyASidC/\nf3/ceuuteOaZZyAWi8GyLFpaWngK8b8CBAIBgoKCkJiYCH9/f6fSzq/jGhEKXaF9ApGnEBgYiKSk\nJIwcORKxsbG44YYbUFlZCbFYjIaGBqxbt84pMpWO7rejidn68379+kGpVOLcuXNutdEVWJZFcHAw\nHn74YUyePBne3t6wWq0ICwvDjTfeiH79+rlM3tobwTAMkpOTkZaWhnHjxsHX1xdFRUV8abkrlSfD\nBRX19oC2LnG18x6czX1gGIb69OnTJq6cy91ftWoVFRQU0A033OB23DnLsiSTyWjRokW0b98+qqys\nJJPJRHa7nRwOB9ntdr4UmMVioTVr1pBcLvdYbD7LsiQUCkkqldKWLVvom2++obvvvtvjeRwRERH0\n/fffU2NjY5tydGazmcxmMxUUFNBNN93kkZJuXfVVIpGQRCLx+LUZhqGAgAB64okn2jw/h8NBRqOR\ncnJy6MUXX6Tk5GQSCoVOzxfu+XB8DHK5nO6++246ffo05ebm0vr16+nUqVNUVlZGGRkZbo+fM78T\niUQUHBxM//jHP+ipp566rA9M5yX5nMp9cOaFXQmgGkBWq8+WACgHkHnpmNzqu38ByANwHsBETwkF\nlmXpX//6F8XHx/OJHgKBgBISEmjr1q1kNBrp5ZdfdptgRSAQkK+vL61atYrKysrIYDCQ1Wolq9VK\nzc3N9M9//pNSUlLo9ttvpw8++ICKiopo0qRJHiF0YRiGlEolRUdH0xNPPEE6nY7OnDlD//nPfygw\nMNCjL83nn39OlZWV1NLSQi0tLfTYY49RXFwcjRw5kl555RVqbm6mjRs3UmRkpMcEA5fgFRMTQ999\n9x1t2bKFNm/eTJ9++imFhoZ6rB3mUh3G999/n8rKyshqtZLFYiGbzUZ2u53MZjM1NzeTVqulnTt3\nkr+/P/n4+HQrnLiXTK1Wk7+/P6lUKnr//feppKSEamtrqbq6mrKysmjv3r20d+9eysjIoEGDBnmM\n7IdhGNJoNDRixAj697//TSUlJVRVVUVVVVVUXFxMd911V5u2/gyhMBZAIi4XCs90cO5AAKcASAD0\nAZAPQOApoZCZmUl//PEHPfTQQySVSnntYf/+/WQ2m+n55593iwmJO0QiEaWkpNDq1aupqamJWlpa\n6NChQ3TXXXe1YfORy+WUk5NDW7du9UihWW9vbxo/fjy9/fbblJ+fTzabjUwmE+Xn59OcOXM8JhDE\nYjFlZGRQXV0dXbhwgfbs2UMikagNS1FFRQXl5+fTc88957YmxDECiUQimjx5Mr3++uu0bt06qqys\nJKvVSiaTiRoaGqi8vJx27txJvr6+Humfj48PzZo1i2pra8lms1FTUxNVV1fTqVOn6OTJk1RZWUk6\nnY4qKyvp4MGDpFarSSaTOS2URCIR+fj40JgxY0ir1VJ2djYtX76cHnvsMbrzzjtp+PDhNG7cOPro\no49o7dq11KdPH7f7wrIsKZVKUqlUtGzZMtq+fTudOXOG9Ho9z8pUV1dH5eXllJ+fTyNGjHDmup7J\nkiSi/QzDRHV33iVMB7CGiMwAChmGyQNwA4DDTv6+U3DZXgqFAuPHj8fhw4dx6tQpNDY28sSbPbUT\nrVYrzp49C6vVCpvNhubmZqxYsQKbN2/mr8sx2pSWliI+Ph7Tpk3DF1980a0N3lVOR1BQEAYMGAC1\nWo2qqiqEhobCbrdDKBTypKOesH+HDx/OF10xGAyXFWthLtU8HDhwIObNm4eDBw/i0KFDLrcjkUhw\n6623AgBWrFjB18IEAL1ej5aWFn73Y9CgQYiMjERdXV2P+zd79mzcddddfJ3P9PR0lJaWYs2aNSgq\nKsKjjz7KV10KDw/nORedHVuHw4GoqChMnjwZUqkUmZmZWLp0KfLz82Gz2XjKdblcjrfffhvTp0/H\nRx995JZ/RiaT4dFHH4WPjw8WLlzIk/k2NTVBr9ejuLiYL0kXFBSEO++8ExkZGZ7xBTmp3kfhck2h\nGMBpXDQvvC99/jGAea3OWwHgDk9oCgDomWeeoezsbFq/fj2NHj2aIiIi6N1336WsrCyqr6+nMWPG\n9EgVFQgENHHiRDp8+DBlZmbSzJkzO+XZ+/XXX6moqIiys7MpKSmpRysct7JyNuumTZuopKSE9u/f\nT08//bRH1OugoCDaunUr1dfX07Fjx2j27NkdqrevvvoqHT9+nEpKSuj48eMkFotdXuGSk5Pp4MGD\nVFNTQwcPHqR///vfNHjwYF7zEAgE1L9/f1q/fj2ZzWbKyMjokaotFApp4sSJZDQayWazUV1dHX31\n1VeX8RVyHBxr1qyhpqamy3xU3c2NwYMH07fffktZWVn0j3/8g8LCwjp8NhqNhhobG6m5uZnGjx/v\nlp9rzpw5dO7cOdLr9XT48GF6++23KSkpqY1WJRaLaeXKlbxpNG3aNF7z47gq213XKU3B3TiFzwD0\nBTAUQCWA/3P1AgzDPMAwzAmGYU44+xt/f3/I5XLY7XZkZ2dDp9PhxIkT8PX1hUgk4itRuwsiQmRk\nJCIjI3H48OEuqc9zcnIgkUjg6+vbZn/fnehLIuK1E7vdjpCQEIhEIvTp0wdDhgzpsZbA8U1ERERA\np9Nh27ZtOHToUIce8vT0dNTW1kIgECA0NJRv25k+cefMmTMHw4YNg1KpxMqVK7Fs2TJkZWXxOylc\nynl2djZYluVz/90Bc6nc/E033cQHueXm5uKnn366jN6N6CL7EsfK7UqVZofDgREjRmD8+PEQCAQ4\nePAgqqurO3w2HL8iV5rPlfnABcfdcccdiIqKgkgkwpdffomlS5fixIkTbTQqq9WKrKwsABfnXUpK\nikeib926AhFVEZGdiBwAvsRFEwG46HwMb3Vq2KXPOrrGciIaQU6kcnLw8vKCwWDAqVOn+IpN586d\n41U3V0uetQfLspgyZQr8/PyQnp6OwsLCTunhjx07BuBi2fX4+Hj+8+5ILTqbIK1/w6m/XJ96Z9W6\nHAAAIABJREFUGgHp5eWF6dOn85Ren3/+eae04fn5+TAajXzufkeVqjoD0UVKsIkTJ/L09YcOHYJO\np7tMrQ0ICEBycjIYhulRJCXLsnjggQfwwAMPwG63o7CwEE899RR27dp12blcIJNKpWpzz86AuVTi\nz8/PD3a7HSUlJZ3Gc0ilUr6cW2vB6iyICCNGjIBIJILNZsNvv/2Gqqqqy4S4UChEZGQkf38mk4kv\nhOQOuQoHt4QCwzDBrf68DUDWpf9vAnAnwzAShmH6AIgBcMytO+sADQ0NYFkWM2fOxG233YYpU6bg\n22+/hZ+fH5qamnr08jAMg5CQEMTFxcFsNuPAgQNdxggYjUaUlpaC6GIxUGfbduZB+fn5QS6Xo7a2\nFhs2bOixphAbG4uxY8fCbrfjq6++QlVVVae2p0AgwKlTp/h6FK6GmPfr1w/e3t5obGzE+vXrUVhY\neFlmpUgkwvTp0xEVFcWT07pbMdzX1xcjRoyAXC5HdXU1Pv/8c5w+ffqy/nHPx263w2Kx8Fqes/kf\nffv2RUxMDBobG/Htt9+2qW7dGgKBAJGRkXwIeetCwc6CZVl4eXlBr9dj9erVqKio6LA/w4YNQ1xc\nHC8E1q5d65n4CCfs/R9x0USwAigDsBDAdwDO4KJPYROA4Fbnv4iLuw7nAaR5aksSAAUGBtL7779P\nVVVVZDab+X12i8VC5eXlpNFoOvydM1701NRUOnPmDBmNRnriiSe6teN9fX1p0aJFpNVqKT8/n1Qq\nVY9sfm53g2EYMplMZLFYKD09nW677bYeXVcoFNLy5cvJZDLRmjVruu2XSqWiqKgo2r59O2VnZ7sc\nS7B9+3aqqamhRYsWdTju/fr1o2XLllFJSQmZTCbas2eP27EYEomEDh06RHq9npqbm2nhwoUkFov5\nPrIsSyKRiK8toVQq6eGHH6aGhgaqq6tzeneFZVkqKysjo9FIjz/+OHl5eXV6blhYGH3yySdkMBjI\naDTSPffc4/I8GDBgABmNRnr33XfJ29u7w3OioqJo8+bN1NzcTHV1dfTkk086c32P7T7M7eDjFV2c\n/x8A/+nuuu6goaEBv/zyC/r164fRo0dDqVTydqKPjw8vXdtLZmc8sgKBADExMRAKhZ3aiq3R3NyM\n/fv34/Tp0ygqKoLNZutSzRYIBE5J8daRmT01h4CLK2NKSgoYhsGaNWu67RdXOHX58uWorKzslrat\nffWo2NhYSKVSSKXSDv0EgwYNQmpqKry9vUFEOHPmjNuswzKZDH5+frBYLJDL5UhPT2+jNnMsUzKZ\nDF5eXpgzZw7mzZsHrVaLr7/+2unxdTgcCAgI4FdwtVrdaZi7wWDgfRkOhwO1tbUu7R4REQICAiAS\nieDv7w+lUtkhPX3rEgP19fXYvn27U9d3BtdUmDNXnfn333/HoEGDIBKJIJVKAVy0rwYMGICysrLL\nHoAzfIRCoZCf3EOHDsWaNWu6FCZ2ux1arRaPPfYYqquruyVudaUYrNFohFAoxK5du3Dq1Klu770r\ncHUfbDYbzGZzlxOUe4GICL///rtTL2trgQAAp06dQlJSUqdtxMbGQqVSgYj4mpDuqrwxMTEQiUS8\nmTd+/Hg0NDSgurqa9zMFBwdj9OjRGDhwIBYuXAipVIodO3bgm2++cUmt50yO5ORk/P777ygtLe3w\nPLvdjtOnT0MoFMJkMiEnJ6fbdlo/E4Zh0NLSArvdDm9v7w7NUi6ng4j4Yjed3Y87uKaEAhHBZDJh\n7969SEpKwm233dZm//++++7DwYMH3coXqKiogE6nQ2BgIObMmYOvvvoKeXl5nb7MXOXhysrKNoVE\nO3vpnJ2ALMtCIpHAaDRi3759KC/v0E/rNBiGgcFgQEBAAF5++WWcOnWKf2latykQCKBSqTBkyBCY\nTCacP3/eqeu37hfDMPjss88QHR2N5ubmyzQFhmEwfvx4iMViEBFsNhsyMjLc7tfIkSPh4+PDV226\n5557IJFI0NDQgKCgIIwaNYpPDec0SYvFgoaGBpeKpbAsi/LyckRHRyM2NhaBgYEdPmeWZaFSqRAR\nEcEzfFdVVXV7/fZjWFpaCrvd3mlGbmhoKEaPHo3g4GC+gK8ntMo2N3S1D7hgc7EsS3FxcbRv3z7a\ns2cPLVy4kJ5//nnKysoirVZLd955p1v2KcuyNHbsWGpqaiKj0Ujl5eX022+/0dixY0kkEpFYLOZj\nCaRSKb3xxhuUkZFB69ato88++4zCwsK6rC3QRegpAeBt3oiICDIajbR8+XIKDg7uUYQm169XX32V\nDAYDmc1mamhooIqKCjp9+jQdO3aMdDodX7uysbGR9Ho9NTU1UUFBAa1YsYKEQmG3996+H4sWLaJ7\n772XjxbkfqtWq0mn01FTUxPl5eW5/ayAi3v0H330ERUXF/N1RC0WC99PLl+Fi/6rrKykd955hxIS\nEtyK1IyMjCS9Xk8Gg4FOnz5N/v7+bb4PCQmhKVOm0ObNm6muro7sdjvt3r3b5TgP7jh06BBlZWXR\n1KlT28RwsCxL33//PdXU1FBzczMVFxdTeHi4s9f1TJhzbxMKYrGY7rnnHqqoqKBnnnmGAgICaNKk\nSXT48GEyGo30zjvvuD3RlEolrVu3jurq6shoNFJDQwOtXbuW5s6dS7GxsRQfH08DBgygsWPH8iGn\nXILU66+/Tv7+/m4n+bAsS0FBQfT000+TTqejtLQ0jxUv8fb2pvfee4/Ky8vJaDSSxWKhpqYmfpJz\nOR4Wi4Xq6+t5wdjQ0EA33ngjSaVSlwJwvL29KTAwkE8e4oJphgwZQg0NDVRTU0OrVq0iHx8ft/vE\nJQUlJSXRBx98QMePHyer1coLB7vdTna7nYxGI+Xl5dG3335LIpGos6Cebg+1Wk379++nmpoaKi4u\nppiYGP5aUqmU5s6dS5s3b6ba2loymUxkMplo48aNbheZnTlzJn366ac0efLkNkJBLpdTbm4uGQwG\namlpoT/++MOVZ/PXFAoKhYK+++47qq6uphtuuIHCwsLo1Vdf5Sf80qVLe/QCSaVSevfdd/mXo6Ki\nggoLC8lgMFBjYyOVlJRQdnY2NTQ0kMlkIqvVSna7nQoLC+nFF1+k8PBwtyLYlEolpaWl0bZt2+js\n2bP8S+UJoQBc1FSio6Ppueeeox07dtCGDRto/fr1ZDAYyGKxkNFopIqKClq2bBmtXLmScnNzSafT\nUX5+Pn388cfUv39/p/vFZRHK5XJSKpUkFotJLpfTZ599Rnq9nrKzsyktLc3tVbT9IRQKSaPR0PLl\ny2nVqlW0bt06Ki8vJ61WS0uXLqWBAweSTCbrcTtRUVH022+/UUVFBf3xxx80ZswY8vX1pTvuuIOy\nsrKopqaGDAYDmUwmOnz4MA0aNKhNbokrwkgikdCCBQvopZdeoqFDh5JUKiWRSER33XUXNTc3k8Fg\noNLSUnrjjTdc6YNTQqHX1X3oDr6+vrjvvvvw0EMPITg4mI8gJCJUVFRg+fLleO+993q8XxsSEoLJ\nkydj+PDh8PPzQ2xsLPz9/SGVSmGz2bB+/Xrs3bsXDMNAq9UiKioKOTk5aGxsRF5eHl9I1RkwDINx\n48bhrbfegp+fH2JiYq44nwHnwBIIBFCr1ejbty8qKyv5oCaRSASZTIZ58+aB6GIR3w0bNri0786y\nLJKTkzF8+HCMGDEC06ZNw7lz57B27Vp89dVXfGEaT6F9NB/LspDL5XA4HGhpaenwvl0ltPHx8cH9\n99+Pl156CcDFXSgvLy9+16iqqgpbt27Fk08+eZnfhmEYl+Yly7IICgrCF198AYlEApFIhBtuuIGP\nZPz73/+O/Pz8Dq/ZiW/LqboPV11L6EhT6EqiikQi8vPzo9GjR1NVVRU1NDSQXq+nhoYG2rZtG913\n3338CuSKLdz+YFmWVCoVhYaGUkBAAAUGBlJ8fDzNnj2bnnzySRozZgxJpVJ+NWdZluRyOYWFhbls\nQggEAkpNTaVffvmF9u3b5zHtwJWjdZxE68+5Vbh///5umUYajYbuv/9+KiwspMbGRho4cKDL5oir\nfXBlPgkEApfvRSqV0rfffkvp6elUUFBAlZWV9PHHH9Ojjz5KQ4YM6TS2gIuXcLVPo0aN4lO1W1pa\naNq0aaRWq7vsV09yH3qdpsCF1TqTdfjss8+ioaEBcrkcycnJ2L9/P3bs2NHlroGb9wcAICJ+18Fu\nt18moTnWHVdDTLlQaX9/f/j5+eGbb77x2L17Au6schxEIhEiIyOxfv16aDQaREdH86G4HcFTGaFX\nGj4+PtBoNLj77rsRGhqK5557DhaLhc9f6Wj+tY/pcBZisRj+/v5YtWoV+vTpgwEDBnQ7hhzanXNt\nagquOoJa8xx4iqzjzz64HQ2pVEpBQUFO9/tq37ezB8uyNGrUKHrmmWf+Uv3i+nYlGKQ6OgICAig5\nObkn17g2NYV2n18Tq8bVhlAo/FMrN/1ZuFYLwvZiXJu1JFvjukBwDn9FgQA4F55+HZ5HrxYK13Ed\n1/Hno9cKhdbOkp7yCfyVwTlmW//d2f+v5XHs7N4FAsFftqzf1UKvGk3Oe88dDMPwBVmuo2O092Zz\nOyTci8IwDBQKBU/ccq2iI1OSmx9/JTOTI4JRKpVXTYj3qret9QTnnIwcWcV1OA8uZZgbS7PZ7DaJ\nSW8GETmVAXutweFwwGg0uhQkxm3je0JA9iqh0Bpc51oLifbf/S+gfYyAK9RoHGw2G4RCIe/NdyYO\n5DquDlxdCFmWRVxcHORyOS5cuICmpqYeR/P2KvOhMzAMg9jYWJ6e/GqDM3OudBsCgQAikQheXl4I\nDw9HeHg4brrpJv4cV82qxMRE+Pn5QSgUduhvEIlEl313raCje+b65Q6ZrqsQi8VQq9WQSCT8GPak\nTWcEP8uy8PX1xXvvvYdPPvkEEydObMM/2aPGr/aBboIuVCoVrVmzhgoLC2ncuHEdhqX2NLlGIpGQ\nr68v3XLLLZSYmEjBwcF0zz33UGZmJjU2NlJmZibt2LGDysrKSK/X06xZs1wOqXXm4FK4X3jhBTp2\n7BjV1NRQfX09n3nX3NxMu3fvpqeffppuueUWCgkJceq6Xl5e9OOPP5JOp6O3336bYmJiSKPRtAn+\nUqlUFB0dTXPmzKEnn3yS5s+f75GgG4ZhSCKRkLe3N/Xr14/mzJlDP//8M61evfqy8WJZtsPn2924\nBgQEXHbOmDFj+Ge2e/fuKxJazR3vvvsuFRcX0/79+2nGjBlXrB1uLBQKBQ0dOpS+//57slqtpNPp\nnKkm5hk6tj8TrcOJW6vJLMtCq9UCQIdJNJ5YBWw2GwQCAaZOnQqGYRAWFoZRo0bxtGEikQje3t6o\nqKiAXC7HW2+9hby8PJ7klENPTBuxWIy+ffti+fLlPIGGSCT6/5Fml1bzlJQUDBo0CDqdDps3b8Y/\n//nPbs0BjrVqwoQJ0Gq1KC8vb5O05XA40NTUhObmZlRUVOC2225DTEyMW/1o/RzlcjkmT56MmTNn\nYuDAgfD39+cZqoVCIcaOHYsDBw7w9+/u+PXt2xdyuZwnKOHg7e0Nf39/qFQqCASCK2Y2qdVqyGQy\nKJVKnibtSoG5RGs/cOBAaDQapKen46uvvkJ1dbVHrt+rhELrCcEJBYZh4O/vj9TUVOTk5CAvL6/N\nb7iS8T1V5+12O+rq6rBs2TIMGzYMy5Ytg1KpRENDAw4cOIAPPvgARqMRNpsNISEh+PDDD/Hqq6/i\n4YcfRkVFRY/aBi7mCPTr1w+ff/45+vXrx09eq9XK14QALgovg8GAxsZGnDp1CitXruw08q+1YFWp\nVJgyZQp27tyJ9evXt6Enb++vsVgsMBqNGDNmjNtRhUKhEFKpFOvWrYNCoeAdnQaDASdOnOCrLb3x\nxht48MEHkZ2dzbffEboTFhKJBF9//TV27NiBZcuWwWAwtGE9ar0j42koFApMmjSJn4ed8Td6Cmq1\nGsOHD8f8+fMRFxeHDz/8ED/88IPHfG29Sihw4CYzZzOlpKTAz88PGzZsQEtLS5tzHQ4HHA4HNBoN\nX2LcXdjtdhQXF2PcuHH8ltCZM2fw+uuv4/Tp07ydX11djaysLCQkJGD8+PH4/vvve/RApFIphg4d\nisWLF2PkyJEALpLUFhUVISsrC1qtFs3NzSgpKeFXdK1Wi+rqatTX10MikXQa1cgwDFQqFWbOnIn4\n+Hj89ttvqKura+Opbu3M5XgaFy1ahGHDhkEqlbpMbycQCDBixAjcdNNNSE5OhlarxfHjx7FixQoc\nP34czc3NvH/kH//4B+bPn48XX3yxR97z8vJyaDQaTJw4EZmZmdi7dy9qa2uRnZ2NQYMGXRGfAuev\n4DQgs9mMEydOYP/+/R5vi4NYLMbrr7+O5ORk+Pn5weFwYP369X99OjaBQEB+fn504sQJnmqrqamJ\nEhMTL2Oy4Vh9/Pz8emzPC4VCmjx5Mh05coSOHj1KL7zwQqc2+8qVK6m2tpZqamqob9++PWrz1Vdf\npfr6ejKbzVRUVEQzZ86kgQMHkkQi6TC115n0W5ZlycvLi/72t7/xlPjNzc00adKkLinVfX19KSUl\nhbRaLVksFpJIJC6Nq1Qqpfnz59ORI0eourqaNm7cSLfffnuHhVyDgoJ4pqTFixe3YWpy9VmyLEtZ\nWVm0fft2uvXWW8nLy4ueeOIJ2rVrF1VWVtLx48d7TG3X/hCLxRQbG0svv/wyWa1W2rJlC4WEhLjl\n3+LmcVff9+/fn5566ilqbGyk4uJi+vrrr131X1zRsnFXDNzKNn36dMTHx0Mul8NqteKnn35CSUlJ\nh/vSUqkU/v7+PVafHA4HEhIS0LdvX2zZsgW//fZbp3aaRCKBXC6HTCZrY3u76ukODAzEzJkzoVAo\nAAAFBQXYu3cvLly4wGs+7dX37rQhjlxk4MCBePDBB+Hr6wuLxYKlS5fi8OHDnbI0CwQCxMbGYsGC\nBbxdrFarne4Pt9U5duxYDBgwACzL4ocffsDu3bs73Hdvbm7mx2vUqFFtfEiuQiAQQKlUwmaz4dix\nY2hubsbJkycRHh4OmUyGnJwct8ygzvre2hyZNm0arFYr9uzZg5aWFrdiQridps4gFouRmJiIWbNm\nweFwICsrCxs3brwiWkmvMx+8vb1x8803Izo6mi89tmDBAqxbt+6y/XXuwRBRp6zHzvIzcOdOmjQJ\nGo0GBQUFyM3N7VIt51iQudJdgOtJPLNnz0ZMTAyICFVVVVi1alWPKzCr1WrEx8fD19cXgwYNAgDM\nnz8fGzZs6PJ3LMvirrvuwi233ILGxkZs3rwZYrEYCoUCJpOp28nOmXyjR4+GXC5HVVUV9uzZA71e\n3+H5AQEB/EvX2qHqjgnIMAwsFgsyMjLQ1NQEIkJJSQlYloVYLO6yKlZn1+sKLMsiNTUV8+fPx6BB\ng3Ds2DH8/vvvLgUdtW6LE2idBWPNmDEDs2bNQr9+/VBaWop169bhwIEDnVaq6gl6nabQ1NSE4uJi\nqFQq3oYvLCy8uFVyKeTZy8sLkZGRSEtLQ3x8PGQyGaxWa4cPUiQSISAgoNt2GYZBdHQ0IiMjYTAY\ncPTo0S4dRnK5HBaLhV+VO7qeM23W1dVBIBDAZrOhpKQEhYWFbcK73dljb2lpgV6vR0hICHx9fcEw\nTIe1FVtDIBDA29sbaWlpEIvFeOutt/DAAw9Aq9VCIpHwtOXd9WfChAl82bjvvvsOtbW1Hb4kUqkU\nycnJ/IuamZnZI02P6GLptFtvvRUTJkxAdHQ0Vq9ejdDQUL7+aFf33dH1Wpm3HX7fp08fjBo1CmKx\nGLt27UJBQYFbWgIRoampqUvfjVAoRFBQEBQKBfLy8nD48GE0NjZekd2UXqcpWK1WZGRkwGw2Y/Hi\nxWAYBnv37uW58ICLHuzy8nJMnToVRqMRAQEBCAsL41cJuVyOQYMGwWg0ol+/fjCZTNi0aVOX7T76\n6KN49dVXoVQq8fzzz+PChQudnisQCJCbm4sbb7wREokECQkJl53jzAQXCoVISEjgBd6AAQMwc+ZM\nvPDCCygoKMDZs2eRnp6OzMxMlzgfLRYLcnJyEBUVhfLycsjlcjzyyCNYuXIlhEIhvL29IRaLodFo\nUFNTAx8fH0ybNg2jRo2CXC7H8ePHERcXh5dffhm7d+9GYGAgGhoaUFhY2GmbzKX6CmvXroVYLMaK\nFSuwdOnSTndFRo4ciWeffRZWqxV1dXVYuXKlU33rDFarFd988w0effRRrFu3js+J4PgZw8PDO/wd\nt0K3r1DdHTgnbG1tLQIDAxEXFwepVOpSPYnW6Eo78vLywr59+xAdHY2EhASsXLkSxcXFVyx0vdcJ\nBeDiC9XQ0ICqqiooFArY7fY2BUTq6uqQmZmJl156CRKJhH8geXl5ICIMHz4cVqsVJpMJLS0t2LJl\nS7dCwWg08vZzd8lDDocDubm5MBqNkMvlqKurc2vrTigU8mXuLBYLTCYTRCIRnn76aWi1WhAR4uLi\nMHLkSKSnpzutmnIvqJeXFz/ZU1JSYLVakZCQgMDAQLS0tMBisWDs2LF8IRiWZWGz2ZCYmAiFQgGJ\nRIIFCxagtLQUmzdvxq5duzrtI9cHrmKXr68vAgMDO/TJcJoQy7KwWq3Izs72yDbepk2bMGzYMIwf\nPx4qlQoOhwMikQi+vr7w9/fv8Dc2m63D6tHdUadVVFQgPT0dERERiImJQU5ODqxWq9vaTuvYjvaQ\nSqUQCoWwWCwgIpSWll7RXJZeKxTKy8uxcOFCDBw4EGPHjkWfPn2gVqtht9t5beCWW26BVCrlhUXr\nUlrV1dUQiUSoqKjAyZMnu22ztLSUzxFITEzsMseAU/fsdjtve7szGaxWK5qbm8EwDB+o5O3tDb1e\nj+bmZgQEBCAtLQ0ajQZmsxlZWVlObQ8SXayktXXrViQnJ2Pw4MH8v2q1mm/b4XDwpcm4F4Db4uUc\nZtznOTk5TvWJCwILDw+Hn59fh+dwuRwlJSUICQnB7t27PUIUk5+fjz179iAxMRFCoZA360QiEUJC\nQjp8pp1pYN09z5qaGpw4cQIikQi33347Dh486LaW0LrNju7RaDRCpVJBo9HAZDLxtUuvFHqlUAAu\nrsY7d+7Ezp07sXLlSiQmJiIpKQlpaWkIDw8HEeHAgQMoLS1Feno6+vTpA19fXxARDh48CIVCgeLi\nYl5IdIeqqirU1NQgJCQEiYmJUKlUna5eDMMgIiICCoUC5eXlOH/+vFtCgWVZ3gnHaRo6nQ7h4eEI\nCgrCpEmTMHnyZIhEIuh0OuTm5jodM2C322E0GnH27Fk4HA4olUp+h4Pzg3AT0Gg0oqysDE1NTdi1\naxd0Oh1ycnIQEBDACwlnouVEIhGvTvv7+0OhUHQ4yaVSKaKjo/lS8Onp6R4JvLFarThw4ABGjBiB\nMWPG8CSx3K6SK/R+3Ava2W84p2piYiIA4OTJkz16UbtqTyaTIT4+HuPGjYPVau2wiHJ79IjK8GrH\nKHQUp9DVwcXpc+XMuM+4km3t97ed3e9mGIbi4uL4qklffvklJSQk8HvHDMOQUCgkmUxGkZGRVFVV\nRVarlaqqquill14imUzmMumsQCCgBx98kC9tdujQIXrvvffowoULVFZWRnV1dVRbW0tJSUmkVCpd\nJrTlSrGHhoZSWloajRs3jjZu3EhZWVlUXFxM5eXlVF9fT9u3b6elS5fSkCFDLruOXC4niUTidN7A\noEGDqKWlhUwmE2VlZZFGo2nz/fjx4+nXX3+lyspKamhooPz8fFIoFC7v63d0sCxL/fv3p23btlFh\nYSHdddddtGDBAtq4cSMdOXLE6TwR7lrcPOvo+/DwcLrvvvvozJkzVFVV1aNyAq3nFzevufa9vb3p\njz/+oIqKCiorK6OXXnqpJ2N07eU+OIOOtqw4e7ajrEFXVobKykocPnwYiYmJuPHGG5GVlYWCggKY\nTCYIBAJ4eXkhNjYW06ZN4wuA+Pj44LHHHsPKlStRU1Pj0mrhcDiwd+9eOBwO2O12NDc3w2q1Iiws\nDAKBACaTCdnZ2Th58mSHdm93/QEuqvPl5eUoLy+HUCiEVquFUqmERCKBt7c3pk+fjnfeeQeVlZWX\nRYsCcDmasbKyEuXl5QgODoZGo4FEIuFXLZFIhDvvvBNJSUnQaDRwOBxYvny5y06+ziASiTBmzBgM\nGTIEWVlZ2L59OyIjI5GSkoKEhIQu4wDaozv/kI+PD2644QYIBAKnVu7uwJnAHDQaDcLDwzFu3DhE\nR0eDYRicO3cOW7Zs6VE7Tt9MN6t4OIA9ALIBnAXw+KXPfQD8BuDCpX+9W/3mXwDyAJwHMNGTmkJX\nB7da9+QagYGB9Ouvv1JdXR1VVlbS119/TXPnzqWNGzfSnj17KCsri9cSbDYbmUwmqqmpofnz51P/\n/v1djmZTKpV0/vx5Onv2LH355Zf09ttvU2NjI1VXV9PPP/9MY8eO9SjtOafNcFqEp0q3tT4GDx5M\np0+fpurqavrxxx8pMjKSpFIpjR49mioqKviyZ3V1dW7XWuzo8PHxod27d5Ner6e1a9dSQEAAzZs3\nj9LT06murs5p+nxnxvBf//oX7d+/n3bv3k0vv/yyx8cwNTWVvv32WyorK6P8/Hz68ccfadiwYT2d\nCx7TFGwAniaiDIZhVADSGYb5DcB9AHYR0VsMwzwP4HkAzzEMMxDAnQDiAYQA+J1hmP5E1DPmBycg\nFAp7zMRTU1ODb775BklJSfDy8sIdd9yBqVOnQqlU8oPGsiwsFgtaWlqQk5ODffv2Qa/XQ6FQ8F5i\nZ2E0GvHpp58iMDAQFy5cgFKpxPLly5GZmYnS0lLk5+d7xN7m0Dob8UplDGZnZ+OLL77AI488gtTU\nVAQGBmLdunWYNWsWNBoN76A9evToZdqJuwVTgIu2t1QqhUgkQmhoKJ566imkpaUhNDQUQqEQMpnM\nI/2TSCSYPn06AgMDkZ2djY8++sgj120NLy8vjBo1Cmq1Glu2bMGbb76Jc+fOeXQudAaZvbwBAAAg\nAElEQVSX6z4wDLMRwMeXjnFEVMkwTDCAvUQUyzDMvwCAiN68dP4OAEuI6HAX1/RIT7lgJ465RiQS\n8Wq4qy9AeHg45s2bh5EjR0KpVKKpqQl6vR52ux25ubnYtWsXsrOz23ivuVBbo9HokmAQCoUQiUR8\nVJ7NZnOaaerPqI3grtNKKpXirbfeQmJiIsLDw6FWq/H5559j+/btOHnyJAwGQ4dVtgQCQYdmYnf3\nIpFI4OPjg6ioKKSmpuKJJ54Ay7Kw2+3QarWYOnUqCgoK+N93tQ3YFVQqFdLT05Geno4FCxZ4zPxp\nDYVCgdmzZyM1NRVffPEFDhw40GNGJThZ98ElocAwTBSA/QAGASghIs2lzxkAOiLSMAzzMYAjRLT6\n0ncrAGwjol/aXesBAA9c+nO40zfhItyd0AKBAGKxmE9pbmhoQGVlJe8hNpvNl/kPuNDnK7kKX2vw\n8vKCRqPB448/jri4OMyePZsfu46eS2sPfGffd/U8ud9rNBrMmTMHfn5+GDx4MM6ePYulS5d6JCxY\nKpVi4cKF+PXXX1FRUXFFVm+NRsPv/nBZsh6AZ8vGAVACSAdw+6W/G9p9r7v078cA5rX6fAWAO/4M\nn8L1o/ceQqGwx/4DVz38rb34nvbLSKXSK1rizsvLi8+S9WA7ntt9YBhGBGAdgO+JaP2lj6sYhglu\nZT5wG9nluOic5BB26bPr+B+GzWbr8WrHrchcDkZ32pi7vonu4HA4eJOhR/EAXaC5ufmqaZvdJkRd\nMg1WADhHRO+3+moTgHsv/f9eABtbfX4nwzAShmH6AIgBcMxzt3wd/+vgAqp6A66U4+9q9s8ZTWE0\ngHsAnGEYJvPSZy8AeAvAWoZhFgIoBjAbAIjoLMMwa3FxC9MG4B9/xs7DdVzHdXgGvbrq9KXveLqx\nv2oh1Z7AXQ86cL2qc2fozCTgdkWu4TFzytF4TUQ0XqnJ23rbTywWQ6lUwuFwQK/XXzMPvidCnesj\nl7XIbd/2BK7GGfREqF0pdHYvzpL1XOvo9UKBiNxis3H22hy4zEBX7FVnYwl6KxiG4UOdw8PDUVRU\nhO+++84jgsZZCIVC2O32a2L8/lc01V4vFIA/54XjzBNn+AFZloVarYZarYZUKkV1dTUf2PRnoifR\nfwKBABqNBsuXL8eoUaNgNBrR1NSEzZs3o76+/grc7eVgWRYhISEwm82ora39n3npPIkrsfvR6+jY\nXAXHkygWi3tcpqs7e1EoFEKhUEChUGDBggV499138fnnn2PmzJkeC6HtDFxQjkAg4D/jCE3cAccb\nMXHiRPj4+MDPzw8hISG4+eabr3iVb64fSqUSs2bNwowZMzqktOspuD5JJJI243YlwPGFCgSCP620\nIRcsxwXZKZVKfh66kvx1GZwNXrqSB9wMxpg7dy7l5+eTXq8nvV5Pf//738nPz8+jQSRcqrZUKqXQ\n0FAaOHAgjR07lgwGA1mtVjKbzXTPPfd0G2DiSuCNTCYjtVpNwcHBNHz4cHrllVdo165ddOjQIVq3\nbh1t3LiR/vOf/9CUKVMoPDzc5eAWsVhMixYtorKyMrJYLGQ0GslisZDFYqG6ujp66623SCaTXZGg\nHKFQSLNnz6YtW7ZQXl4enT59miIiIq5IW7t37yatVksHDhyglJQUj86J9n+vXr2asrOzqbS0lLZs\n2eIUDb+7czE5OZkef/xx+vnnn+nQoUNUVVVF1dXVdOHCBTp37hw9++yzlJaWRn379m1/r04FL111\ngeCKUGif25+cnEzHjx+nhoYGslqtdOjQIRoxYsQVeRhcFFtwcDDFxcXRjh076MyZM7Rv3z6PvUAC\ngYC8vLxoyZIltHPnTjp9+jQ1NjbyNSSNRiNZrVayWCzU2NhIRUVFtHr1ahKJRE63IZfLKS0tjXbu\n3El1dXX0ww8/0G233UYzZ86klStXkslkouzsbJoyZQpJJBKPj6WXlxdt376dqqqqSK/XU0pKyhWJ\nDBQKhbR161bSarV05MgRj9Z3lMlkpNFo+GhDlmXpzTffpPz8fDKbzaTT6UgqlXq0P1wtlNGjR1Np\naSnpdDqyWCx8pi73f7vdTg0NDVRUVERr1qxpz1Xx1+NTiIyMRHJyMqxWK/773/8iKysLy5cvxzPP\nPIOwsDCYzWbExcXh5MmTHrXviYinS1MqlUhNTYVQKMSZM2fw/vvveyQhRiAQICgoCM8//zzuv/9+\n3r/BJfRw9R/MZjMcDgesVitqa2uxadMmiEQipzn7Ro8ejXvvvRdKpRIWiwWvvPIKSkpKIBAIsH//\nfkycOBFqtRqLFy/GhQsXcP78+R73rTXmz5+PgQMH8qXksrKyPGYTc7yPQqEQI0eOxPDhwyEWiyGV\nSj2q0guFQrz99tsoLi7GV199hfr6eqxduxapqakIDQ0Fy7KQSCROzQtnfAICgQBhYWF45513MHny\nZIjFYgDg5wHHZG632yEUCtHS0oLS0lKsWrXKLT/NNSUUiAiDBg1CWloaZs6cifvvvx8HDx5EY2Mj\nHn74Yb5suzPoLvGmPXx9fTFixAhMnjwZycnJaGxsxLZt2zySzioUChEfH49FixbhvvvuA3CRGPTs\n2bOora2FwWCATqdDYWEhn0wkEonQ2NiICxcuOF3ajWEYpKam4oYbbuDTzLnCvVzx1YMHDyI1NRVJ\nSUl48cUXce+993bZP1ccXTKZDM8++yw0Gg0aGhqwa9euDold3G1LLBZDIpFAKpVi0qRJUKvVsNls\nqKiowOnTp51upzuYzWaEh4dj5MiRkMlk+PDDD1FQUICff/4ZUVFRYBjG6ZfRmbEbMmQIHnzwQUyd\nOhVisRiVlZXIzc3FhQsX0NjYCJ1Oh4KCAjgcDoSGhqK4uBharRYlJSVu+dmuKaFQWVnJszsnJibi\nlVde4Wv3WSwWfPvtt8jJyXFqoDlh0Ho17gxBQUFYuXIlhg0bBqvVioqKCsyZM8cjGXIsy+KVV17B\nokWLoFKpsGfPHjz++ON8dhynJbRux12Pc0xMDCZMmMATgM6aNQsGgwEOhwMWiwXNzc144YUXkJGR\ngRkzZiApKQnBwcGorKzstD0i6jbWQCgUYtSoUZgwYQICAwNRUlKCZ599FkePHnVJo+uuz2azma/I\nnJubC5Zlcfr0abz22mse3VHh0uKrq6thMBggl8sRGxsLi8WC/Px8jzmdBQIBkpKSsHHjRqhUKhQW\nFuLdd9/F8ePHkZeXB6vVCpFI1IaD1BMxPdeUUOjbty9uvvlmqFQq7Nq1C2+99RZYlkVSUhIWLlyI\nwsJCbN++3enrcZ5biUTSaRUjgUCA4OBgjBw5EizLoqqqCkeOHEF1dbVH1F6FQoEJEybAy8sLdrsd\nWVlZqK6u7rRkHODc6tIeUqkUgwcPhkwmg8FgwJkzZ3hS19bQ6XQ4f/48zyDszIrH7SZ0lA7NXKKb\nDwwMxJ133gm73Y4dO3bg+PHjqKmpcbkfXQkghmFgtVqh0+lw0003wW63Iy8vD01NTZ5KPQZwcd5E\nRkaisrISa9asQVlZGWw2GxYtWoTw8HCcO3fOIxTsPj4+SE1NhUqlAhHh7NmzyMvLw/nz53lC2vbP\nxxPBVb1SKHS2Eo4bNw5qtRoFBQV47bXXUFFRAYVCgdTUVIwZMwaLFy/Gli1bnBoYlmXx/9r78uCo\nqrT95/SeXtJJE0hCCAnZgLAkhLAo1LBZQwKiKCAfyk8QRtRSxrFU1PmskhlnZERUtAYQxwVRRET5\nFAeFQpBIwhIlQEJCNrIQ0lk6SWfpJZ1e3t8fyb2ThHTSne6Q4PRTdSud7nvvec+59773vMt5H41G\nw3MgOFMKXI0/mUyG6upqpKWlYdeuXV6rux8bG4u4uDgIBAK0tLSgoqKC1/zesrWFQiHGjBmDF154\nATabDbt27cJHH33UY5+5WcmIESOgUCj6lIELw3FKoTsYY1i2bBnWr1+PiIgIXLx4ER9++CFqa2vd\nHkNOIfRWYXnkyJFISEjAokWLUFlZibNnz/arLVeQnp4OrVYLh8OB5uZmBAUFwd/fH3V1dW7X1OwJ\nS5YswcqVKwG0K+t///vfyMrK8sq5e8OQzFNwZgdxJc5VKhVGjhwJpVKJjRs3YtWqVRAIBMjPz3e5\nHBsRoampCeXl5aipqXG6n8PhQGhoKEQiEQwGA3766SeUlZX1p1s9orq6mo9tSyQSjB8/HmFhYZg5\ncybGjRuHgIAAj51kUqkUjz76KEaMGIH09HTs3r3bKZ0bYwz5+flobm7mi5X0Zpdyzq7eGKyCgoIw\nZswYiMViHDp0CEVFRf2mV+stl8ThcEAkEuHOO++EWq1GRUUF0tLS0NjY6PUEH5vNhnnz5mHcuHFQ\nq9XYtm0bZsyYgdbWVpw6dcrpca7a+KyDUlCpVAJoL9tnNBp5AuaAgAC+9JzXMdjhSHdCkkKhkJ5+\n+mmqqamhtrY2stvtZLVayWw2U0ZGhtMipP0t5sqVdJ8zZw5VVVXRokWLvB6mi4qKopaWFrLb7WS3\n26m1tZVsNhuZzWYymUyk0+koOjq63+cXCAR0xx13kNFopPz8fFKpVE5DgFypfI1GQ/v27aPq6moa\nNmyYRyHDyMhISk1Npa+++orMZjNt27aNgoKCBiQMGRwcTJMmTaLXXnuNjEYjZWdn05QpUwakOO2G\nDRuotLSUDxNzOSsFBQX00EMP9XiMO4VyBQIBPfHEE3T16lWyWq3U2tpKFy9epOvXr1NZWRnl5ubS\n559/TnPmzHFH7tuTir4vZGVloaamhte4VqsVbW1tuH79utO3j7O3BBeB6El7c4uEuDCXwWBAbm6u\n16duJpMJra2tsFgsfHipvLwcx44dw5kzZ2A0GrF48eJ+ZxkyxvDwww9DKBTi/PnzaG1t7dODr1ar\nIRQKcfToUTQ0NPS6f18EuAaDATU1NcjPz4fdbkdNTY3TUmx9oa+29Ho9KisrkZGRAbPZjOLiYrc4\nON1BWloaMjMz+fFsa2vj15I4i6hwsypXodVq+XvDYrFAJpOhqKgI69evx7PPPgudToeHHnqID1F6\nC7eVUrDb7cjMzMSxY8d4J5xQKERbW5vT6TDgXCl0m63cBIfDAYlEglGjRuHIkSOoqanx+g1mNpv5\n1Xf19fW4fv06tmzZgueeew7Hjh2DXq9HREREv1OaxWIxlixZAsYYb6r0BIFAAJVKhcTERKSmpkKr\n1eIvf/lLn/3t6/empiaUlpbyRW7T09P77fTrqy2r1Yrm5mZcuHABJSUlSE9Px/Xr1wdkTUVpaSlO\nnToFs9kMq9XKj2tvKdXuLPzi2ML0ej2EQiEsFguMRiPOnDmDzMxM6HQ6jBgxAsnJyQgKCvIoxb87\nbiulALSHg3bt2oWsrCwA7U40g8GACxcu9PucPQ2oQCCAQqHAuHHjsHz5cnzwwQcuJ6O4g9bWVn62\nUllZiS+//BJpaWm8F91gMPA0dv0B56sQCoVITU1FbGwsVCoVxGIxFAoFQkNDMXXqVCxYsAAPPfQQ\n1q9fj7Vr10Iul7uUQ+BKnodEIsHvf/97EBEuX77c50PqbAy5dnobY84PYjab8csvvwzYClur1YoT\nJ04gOzsbBoMBIpEIVqsVJpMJU6f2XIfY3XtDp9PxTlzOn3X48GGMGDEC06dPR2RkJEaPHo0JEyZ4\nVSkMyeiDMzDGeF690aNHw+Fw4MKFC3jxxRddIpF1dk6hUAipVAq1Wg1/f3/U1tZi7dq1WL9+PQID\nA6HX65Gbm+vS+dy9ATkz5dKlS3jppZeQl5eHFStWYPbs2UhISEBgYCCSk5Nd4nJ0Jk9FRQVUKhVi\nYmKQkZEBo9EIIoJGo4FYLOYddw6Hg5d/9OjRCA8Pxz333ONSLoGziMDkyZOxevVqpKSkAHCNcao3\nc6+3tjiG6QULFiAuLg6//PLLgCgE4D9ZhmPHjoWfnx8ef/xxlJaWYuzYsRAIBD1mmbori9VqRVBQ\nEOrq6vDJJ5/g+PHjiI2NxVNPPYWRI0dCIpHgp59+wunTp71a5+G2UwqJiYnYunUrQkJCYLPZ8Ouv\nv6KioqLftj5RO12XSqXC8uXLcdddd8FkMiEpKYkPV2ZkZAzYzcUxO9tsNjQ1NcFqteLll1+GRqOB\n3W7HjRs3oNPp+p223dbWhkceeQRLly7F/fffj5iYGAQGBvKmF/CfhBeiduo8q9UKf39/TJkyBdHR\n0bh27Vqf7Tsbn4iICCQmJvJs4Z6Aa6M3c1Cj0eDOO++EQqHgY/kDgcDAQDz++OMICQlBTU0Njhw5\nAplMhuDgYCxatAi7d+/2uI2qqioUFRUhKSkJBoMBdrsdDzzwAKZOnQqLxYLCwkIcPHjQ67wTt51S\nWLBgAaKjoyEQCGAymWAwGKBQKCCTyTxihzKZTAgJCcEdd9wBsVgMkUiE2tpafPjhh3jvvfe82Iuu\ncDgcMBgM0Gg0SE1NRWVlJfz9/WGxWFBQUIC9e/d6dGPb7XZkZ2cjOzsbb7/9NiZNmoSFCxfC398f\ngYGBWLp0KcRiMerr63Hq1Cm8/fbbsNlsvCJ55513sHfvXhw9etTt0J5EIsGyZcsQFBSEkpIS7N+/\nv9/9cAWhoaFISUnB6NGjYTQaB7S+RVRUFObOnctzScrlckyYMAH33nsvEhISvKKMLBYLMjIyMGHC\nBMTExEAmk2HSpEkwGAz49ddfsXPnTqSlpXmhN11xWykFgUCA2NhYfhoplUoxZ84cAMD+/fuRk5Pj\n0fmvXr0KoD1H32Kx4Pvvv8c///lPp5T03gBjDCUlJVCr1Zg3bx78/PyQn5+PI0eOICcnBwUFBV57\n27W0tODMmTM4f/48n9796quvIjo6GoGBgbh06RIKCwvBGMNf//pXlJaWYtmyZVi8eDEcDge+/vpr\nt5x2arWaXx+Ql5eHjz/+2Cv96AmMMWzYsAELFy6EQqHAk08+OWCzOwAYOXIkxGIxBAIBhg8fjjfe\neAPjx4+Hv78/nz7vqVJyOBxIS0vjF+DFxsbixo0bePfdd1FQUIDCwkK31o64jMHOUeiep8AtRUUP\ncVaRSETJycn0xBNP0AcffEDNzc3U0NBA169fp4MHD/Z4nFAodGltO7dsOSUlhfbt20dbtmyhsLAw\nr8e3e9oUCgWNHDmSYmJiKDAwkAQCgcu09gNJSMKNi0wm4+Vy59jg4GAqLCykTz75ZECWYXfeBAIB\nZWVl0ZkzZyg+Pt7j8/V2H3J9mz9/Pv3xj3+kw4cP83kljY2NlJmZSXK53Gt9CwgIoKCgIPLz8yOx\nWOwJ7f3tu3Ta2aIOm82Gy5cvIy8vD3v27AERoa6urlcqsM7Os97ALUuurKzE9u3bUVBQMDBauAcY\njcZ+tzWQb0MA/IKs/sT7LRYLtm7dim+++cZj4l9XcPjwYaSlpeHatWteOV9vHv3a2lrU1dXh559/\nxnfffYc//elP8PPzQ1xcHDIyMryaVu0Nqjt3MORKvLtb3debxVNFIhECAgLQ0tJyS27i3zq46XVb\nW9uAKy/GGBQKBZ9M5OnU3VUWqs7tc9utrtXpBrxPMDtQ6I334VZiKJYb/61goOjVeoI3KQFupdy3\nAL8d3odbhd/QxR9yuJVj680w5H/jPXHbZTT64IMPA4v/GqXAlcMe6vBUxs4+Fmefb0c4W7SmUqkg\nlUoHQSLvwNl1CQgI8PpCJ1cx9J8SL4Gobw5ATnEM5gPk6XS1+/Gd+3Q7K4aexoVb13GrqNwGYvyc\nXW+ZTDZoFHU+n0IHOjsZXXkwO888XA17ugIigkQiweTJk5GQkACz2YwDBw545NHmkml+azyIdrsd\ner3+lvXrVvoXdDqdTykMJFzxILt7wQMCAhAREQF/f3/k5uaivr7eExEB/Idh+5FHHsH69evh5+fH\nryy8evWq2zdJ5z5xiqGv9QO3G35rio7DoIY1BzubsXtGo6cbl+3VORvN28QcjDHasGEDHT16lM6c\nOUMpKSleySwUCAQUERFBN27coKamJmpsbKSGhgb6xz/+QaNGjfKoDaFQSDNmzKCQkJABYS/qb38H\n8vxCoZDEYjHJ5XKvEfYEBATQxIkTSSQS9XhfiESiAe+XQCAgkUhECoWiO9lLX5t3MhoZY+EA9gII\n7jjx+0T0DmNsM4BHAXAlef9MRN93HPMSgPUA7AD+SETH+mrHG5BKpQgNDYVSqUR5eTlMJhPPs9d9\nJVl/489isRgajQbvvPMORCIRmpubodPpvPLmFYlEiIyMxPDhw3nzhIiwatUq2Gw2bN++HQ0NDf16\nO8rlcjz//PMoKyvDa6+91mPJc6FQOCBvKI6D09/fH1qtFn5+foiOjoZIJPKoDkZfuO+++5CYmAi5\nXI4LFy7giy++8Kh/jDGkpKTgmWeeweLFi1FXV8f/xvk34uPjIZVKcfbsWW90oUekpKRg1qxZCAgI\nwMWLF7Fnzx7vFpJx4S0eCiCp47MKQCGAeACbATzXw/7xAC4DkAIYA+AaAKE3ZwoikYjUajVt3ryZ\nvvnmGzp9+jTV1dWR2WymlpYWMplMZLfbeXo1rVZLGo3G4xkDY4zi4+Pp9ddfp5ycHHrvvfcoKirK\nY80vEokoNjaWdu3aRTqdjnJzc+n999+n9957jzIyMshsNtP169fpo48+oilTppBIJOJnRL3NHjr/\nFhAQQJ988gldv36dJk+efNN+UqmUwsPDPXrLMcZILBbTxIkTaerUqRQSEkLfffcd6XQ60uv1VF1d\nTVlZWXTq1CnKzMyk0tJSmjx5sldmLlx9SU5+oVBIFRUVZDabyWazkcFgoFdeecWjtqRSKX366afU\n0tJyE3+oSCSiJUuW0LVr16ioqMjj/nS/P7i2BAIBabVavl9Go5G2bdvmau1H78wUiKgKQFXH5xbG\n2FUAYb0cci+AL4jIAqCUMVYMYDoAr6hOjl7t5Zdfxtq1a3l6Na6kGef04+rh2Ww2vh6Bq1RePYEL\nf82bNw8pKSkoLS3F/v37UV5e7nGfxo0bh9WrV2PcuHEQiUR4//338eWXX/JUdXv27EFwcDDuuOMO\n6HQ6ZGdnuz0zGTZsGKZNm4bc3FyUlpZ2+U0sFkOtVvO1ATytTVFSUgKNRoM77rgDs2bNQkNDA37+\n+WdkZGRAp9NBq9UiNDQUq1evxssvv4xnnnkGlZWV/Wqzc9v33HMPJBIJjh8/DqPRiJ9//hkpKSl8\nbYWEhAQMGzas3wVrFAoFoqKiIBAIMGHChC7VqeRyOebPnw+1Wu31+gYcE/jZs2dhsVhw7NgxLF68\nGCqVChaLBTExMQgPD0dpaemt531gjEUCmALgPIBZADYyxh4G8CuAZ4lIj3aFca7TYTfQgxJhjG0A\nsMEtYUUixMfH4w9/+ANWr14Nxhh0Oh2uXLnC38x6vR5FRUVgjKG5uRkymQyNjY1wOByQy+VduA7c\nMSHCwsLw9NNPY/HixZDL5Th9+jSys7O9Mt1OSUnBkiVLeNKP48ePw2w28wVj33rrLbz66qsIDg7G\n6tWrsXnz5i6sQM7A9Y0rPKJWq5Genn7TsVztQG5K3F1puAOi9iKm8fHxWLlyJSQSCa5evYq33noL\nBQUFsNvtEAqF0Gq1UKlUeOmll3DXXXdh7969HptgkydPxsqVK/HYY4/xtQaqqqowf/58yOVyjyjp\nhUIhGGOoqqpCUlISFAoFFAoFzGYzT8oiFoshl8v5NR/ecoImJydj9erVqK6uxs6dO/ll9ampqQgI\nCMCwYcOgUqm853R1wxmoBHABwP0d/wcDEKI91+HvAD7q+P6fAFZ3Ou5DAMs9NR8YY/TCCy9QZWUl\nGQwGOnz4MMXFxVFcXFyXJaWunKv7efuagkdGRtKpU6eovr6esrOz6bnnnuvR0dSfbdSoUZSenk4G\ng4FMJhNt376dFArFTVPTkJAQ2rRpE+Xl5dGKFSv6nC4KBAJSq9X04IMPUkNDA7W2tlJjYyM/Xp33\nFYlEFBYWRjt37vS4HLpEIqGlS5fSiRMnqKysjN54442eKNEJaDdpmpubyWAwuFuqvMdt586dVFhY\nSHq9noqLi+lvf/sbxcbG0oIFC+jixYt08uRJt/vHmURTp06ldevW0cmTJ+no0aN06NAhioqK4s2R\njRs3UnFxMZlMJvrxxx+9uqT9zTffpIKCAtLr9VRQUEDPP/88hYeH07Rp0yg9PZ3Onj3r6lJt75V4\nZ4yJAXwNYB8RHQIAIqohIjsROQD8C+0mAgBUAgjvdPioju88gkwmw6JFi6BWq+FwOHD58mVotVqU\nlZXx5dHdfdNw9Rl7K58uEokwduxYJCcng4iQlpaG77//3iuOHYlEgqioKISHh4MxBqPRiB9++IGv\nociBiNDa2oq6ujoIBAJUVFTAbrc7TaZhjEGpVGL58uV49tlnoVQqYbVa8dVXX0Gn090ku1AoxNSp\nUxEYGOjxkl+73Y6YmBiMHz8edrsdR48eRWVlZY/XxmAwQCqVQiQSYcaMGV3k7w/uuusuBAYGIj8/\nH4899hj27NmD2NhYPPzww1CpVDhw4IBbb1Nu5aVGo4HFYsGVK1eQnp6OkJAQNDU1obW1FQ6HA4wx\nREREYOTIkRCJRF4v37do0SIEBgbi8uXLWLNmDQ4ePIj4+Hg8/vjjCAoKwmeffeZVR6Mr0QeG9rf9\nVSJ6q9P3oR3+BgC4D8CVjs+HAXzOGHsLwEgAsQAyPRU0KioK48ePh0AgQHNzMyoqKvgioP25AFxO\ngFQqhd1ud/owzJs3DytXroRYLMbVq1fx7bffejS97tx+UFAQXn31Vfj7+6OkpAQ7duzA6dOne9yX\nMQaNRsNTyAPO+x0SEoK7774bCQkJCAsLAxFh/fr1+Prrr286TiKRQKlUorm5GXv37vW4XwAwf/58\naDQalJSUICsry+kydJlMxkdZoqKi+O97u569mXxqtRqlpaV4+umnceHCBcjlcmzcuBH3338/mpub\n8emnn7r88HCmACffjRs30NLSgry8PEyfPh1arRZKpRJSqRRE7bUhOb9WcXGxS7udfeUAAA60SURB\nVG10Rm/mRmBgIEpKSrBx40bk5ubykaQHHngAjY2N2LNnj1f5SFzxKcwC8P8A5DDGLnV892cAqxhj\niWiflpQBeAwAiCiXMfYlgDwANgBPEpHHhnddXR1v10kkEsTGxiI8PBxjxoxBbW0tqqqq0NTU5PKb\ngIh4WvfeIJVKMXr0aAgEAly6dAlXrlzxSq0FsViMNWvWIDo6Go2NjXjzzTdx8uTJHp1UXE0CvV4P\nxhjGjh2L/Px8/k3VHU1NTaioqMDs2bP5cu7Xrl0DEUEmk4GIoFAooFKp8Oijj8JsNvN96wkCgQAy\nmcylcumRkZGIjo6G0WjEwYMHnRYIEQgECA8Ph91uh1gsdtk305tSMBqNkMlkCAwM5Pu2bt06CIVC\nFBUVueUAtNlssFgsEAqFvP+gqakJQqEQ4eHhEIvFmDRpEqqrqzFu3DhMmzaNpxYMDQ11W/beZkdG\noxFSqRRKpRIKhQIbN27EmjVrIBQKUVxc7JJ/yS30J9nI2xtcsKvCw8OpubmZp1fjQjJcGSy9Xk8T\nJ070mh3HGCOlUkkhISH05JNPUlVVFc2dO9criVACgYAmTJhARqORamtrKTExkcRicY8ycAk4Go2G\nvv32WzIajTR37tw+fRoCgYASEhLo3LlzfOiqtraWTCYTmc1m0uv1dPnyZYqMjKTg4GCaMmUKLV26\nlDQaDU+XFxYWxpdii4iI6NNOFovF1NTURFarlT744APSaDRO91UoFLRu3ToymUxktVppy5YtHo/r\n888/T9XV1WS1WvmQtMlkopMnT9LChQudjlNvYcrOPiepVEqbNm2ir7/+mvLz86m2tpYaGhqovLyc\n0tLSqKamhpqbm6mkpISkUmmXknpc2Lc/voY///nPpNPpburXiRMnaMGCBe706/Ytx9YT2tra0Nra\nypNjWK1WaLVaXLlyBf7+/oiNjcWcOXOQl5fn8myhcyizuwbn/A1EBIPBAIvFAq1W65UyW1KpFEuX\nLuU1fXl5udMZCxcunD9/PpKSktDS0oJz5871OcMhImi1WnzxxReIjY0FEUEsFsNms8Fms0Gr1eL0\n6dN46qmnIBAIeI/6gw8+yBfIlclk2Lx5M5qbm3H9+vU++2W1WqFQKPixU6lUPSZJAe2l2qqrq/kw\nslar7Xvg+kBWVhZ0Oh2GDRsGxhja2tpgNpuRk5OD8+fP93gMF752hs73hcViwc6dO/H5558jMjIS\noaGhkEgkaG5uhkKhwLZt26BWqxEQEIB58+bh4sWLaGlp6XLf9sfUvXDhAvR6PQIDA2/q1y+//NKv\nfvWG20YptLa28nZXfX099Ho93nzzTWRkZOD+++/HAw88AKVSCbFY7BbztLOLxDn3uGlbcXExamtr\nvRKCjImJwapVqwAAZWVlvM+gsyyMMajVaiQnJ3cJWf7www8uTYOJ2utXfvbZZ9DpdFi2bBmfRWi1\nWqHT6WAymbBw4UIEBARAJBKhra2NN5VqampQVlYGs9mMsrIyVFVV9dkm0D7tFolECA8PR0hIiNM8\nDofDgaysLP4mP3fuXI/7uYP09HQcOXIEcXFxYIxBLBajsbER1dXVTqnq3H1IDQYDDAYDqqqquqxk\nHDduHBoaGnhOjVmzZiE9PZ2vbWmz2fp975w6dQrHjh3Dhg3tEXyuXzqdzmltT08cnbeVUuAenvLy\nchw6dAhpaWk8aWlDQwOSkpL48uyugBu4zguFOkMsFiM8PBwpKSk4cOCA10q9jxw5EkqlEiKRCElJ\nSUhMTER+fj6ampqgVqsRHx+PSZMmITY2FmFhYZg8eTJPfuPM7nfWv/r6euzbtw+HDx9GcnIy4uLi\nMHfuXIwePRoKhQKvv/46zGYz6urqEBMTg2nTpgFoL4IqFApx4sQJnlOzr7wOoVCI+vp6BAcHY+zY\nsUhMTERmZmaPx3AsSiKRCHq9HiUlJe4PZDe0tbVhx44dmDlzJpKSkiCXy2E2m3H16lWvL3u22+18\njgLQTtyyY8cObNq0CTKZDPX19bzPx9NIhMViwZYtWxAXF4cZM2ZAqVTCbDYjNzd3YJbDD7Y/wVWf\ngkwmo8bGRkpPT6eZM2dSQEAArVixgnbv3k1XrlwhrVbr9mIfbuGUUCjsspBKIBDQtGnT6PDhw1Ra\nWkrl5eVeXeRyzz33UGZmJplMJjKZTGQwGEin05FOp6O2tjZyOBxkt9t5evPW1lYyGo2Ul5dHTz31\nlFdk6J6fwRgjuVxOERERHpVjnz59OhkMBmptbaXy8nKKi4vr0o5UKqURI0ZQamoqHTp0iGw2G5WV\nldHYsWM9ju3L5XJauHAhlZaWksViodLSUlq+fDmpVKoBX6TE9W337t1UX19P9913n1fPm5SURLm5\nudTa2ko5OTk0c+ZM8vPzc3fMfls+BavVCsZYF3o1jj6Os0nr6urcmqJ1Nx84Utng4GC89NJLSE5O\nhlgsRn5+vleX6F68eBFr167FokWLsHz5ckyYMAFKpRJEdJPmt1gs+PHHH3HhwgXY7Xa0tbX1yFPo\nLrq/vThzSaVSQafTOTmqb5SVlaGoqAjR0dFQKpWYMGECysrKYLPZIBQKERoaitmzZ+PBBx9EQkIC\niAiBgYFYtmwZtm7d6hYzc3ckJydj+/btGDVqFIjaOTQLCwtvWWVuIuJZoiMjI7123okTJ2LHjh28\nbygnJwc3btzgnwlPZyLdcdsoBYfDAbPZjBEjRuDuu+9GWVkZgoKCYLFYUFxcjE8//dTjB1cgEGD6\n9OlYs2YNfve738FgMODy5ct45ZVXvNSLdlRUVAAA8vLysGvXLkRERODOO+9EcHAwwsLCsGrVKgiF\nQhQWFuLjjz/Gvn370NraiqCgICxYsAAzZ85EeXk5dDqdV8NRDocDarUaEonEJSLYnqDT6bBixQrs\n378fkZGReOuttzB27FgcPXoUS5YswZw5cxAWFobhw4dDLpejra0NxcXFaGhoQFBQEFpbW9HS0tIv\n+zs1NRXR0dEQCoWw2Wyora2FQCCASCTiHZoDCc4UMplM/U6n7gnz5s1DYmIi7w+qq6uDXC6HRCKB\n1Wr1er9uG6XAGENFRQWUSiVSU1MhlUpRVFSEI0eOIDs72yv0akQEf39/zJo1i4/tb9u2DZcuXer7\n4H7CaDQiLy8P+fn5XajcQkJCIBQKUVJSwsf6Kysr8e2332LWrFmYMmUK6urqcP78ea9ms3F5/P0F\nEaGsrAwff/wxHnvsMcTExGDTpk1Yt24dNBoNZDIZAPAPzfnz57F161ZkZmZCLBZDIpH0m3JtzJgx\n/ExLIBAgMjISCxYsQHV1dZdlzgMBLuJiNBohkUjg5+fntXNzSXtA+7hNnjwZ9957L7788kuXHcDu\n4LbifVCr1QgMDIRcLodOp+OrHfUWRXAXYrEYs2fPxvr163H06FEcOHDAq2w/3gK3fr+trc27NOQi\nER+JAP6TcONuG1yS2ZYtW5CQkACZTAa5XI5z585BIBCgqKgIOTk5OHHiRBclJBAIeGdxT8qpt8y/\n5ORkTJ06FdOmTUNcXBxiYmJQV1eH48eP41//+hfy8/O77M8pJmcKyJ2pORftmDp1Kv7yl7+grKwM\nf//736HX610iu+2trRkzZmDSpEmIjo5GbGwspk+fjsbGRqSlpeHdd99FUVFRl/17IbLxkcH0B0Kh\nkM+Ks1gsqKur87rNNpTBRXi8pWhUKhXPlqxUKnH8+HF+RmSz2W4yf7i0Ymde+94KwUgkEt5UiIiI\nwOLFi9Hc3AzGGNLS0lBYWHhTW71d2/7Y635+foiJiUFERASOHz/usj+jN2UnFov5fg8fPhxLlizh\nV2UeO3bsprT7zvVGu8GnFPqDzjfCQDhxfPAM7r69Obh7HT299u4unXa3vV4e/N7gY4jqDzoPsk8h\nDD24c008uX6eXntPiuwOxP7u4L+G98EHH3xwDT6l4IMPPnTBUDEf6gAYO/4ORQRh6MoG+OTzBENZ\nNsC78kW4stOQcDQCAGPsV1ecIIOBoSwb4JPPEwxl2YDBkc9nPvjggw9d4FMKPvjgQxcMJaXw/mAL\n0AuGsmyATz5PMJRlAwZBviHjU/DBBx+GBobSTMEHH3wYAhh0pcAYS2GMFTDGihljLw62PADAGCtj\njOUwxi4xxn7t+E7DGDvOGCvq+Bt4C+X5iDFWyxi70uk7p/Iwxl7qGM8CxtjCQZBtM2OssmP8LjHG\nFg2GbB3thTPGfmKM5THGchljT3d8P+jj14tsgzt+g1xxSYh2AtooABK0E9PGD4FKUGUAgrp9txXA\nix2fXwTw+i2U53cAkgBc6Use9IPgdwBk2wwvkQ97QT5nBMmDPn69yDao4zfYM4XpAIqJqISI2gB8\ngXaC2qGIewF80vH5EwBLb1XDRPQzgO5lkZ3JwxP8ElEpAI7g91bK5gy3VDYAIKIqIsrq+NwCgCNI\nHvTx60U2Z7glsg22UggDUNHp/x7JaAcBBOBHxtgF1k6ECwDB9B9GrGq0c2kOJpzJM1TGdCNjLLvD\nvOCm5oMqG+tKkDykxq+bbMAgjt9gK4WhitlElAggFcCTjLHfdf6R2udyQyZsM9TkAbAL7SZhIoAq\nAG8OrjgAY0yJdj7UPxFRl7Lcgz1+Pcg2qOM32EphQMhoPQURVXb8rQXwf2ifotUwxkKBdh5NALWD\nJyHQizyDPqZ0i8mH+wLrgSAZQ2T8epJtsMdvsJXCLwBiGWNjGGMSAP+DdoLaQQNjTMEYU3GfAfwe\n7eS5hwGs6dhtDYBvB0dCHs7kOQzgfxhjUsbYGHiJ4NcdcA9bB7qTD99S2RjrmSAZQ2D8nMk26OM3\nkJ5fFz2wi9Dudb0G4H+HgDxRaPfwXgaQy8kEYBiAEwCKAPwIQHMLZdqP9mmkFe125Pre5AHwvx3j\nWQAgdRBk+xRADoDsjhs5dDBk62hvNtpNg2wAlzq2RUNh/HqRbVDHz5fR6IMPPnTBYJsPPvjgwxCD\nTyn44IMPXeBTCj744EMX+JSCDz740AU+peCDDz50gU8p+OCDD13gUwo++OBDF/iUgg8++NAF/x89\nla3FAt/jSQAAAABJRU5ErkJggg==\n",
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"from PIL import Image\n",
"im = Image.open(\"results/fake_samples3.png\", \"r\")\n",
"plt.imshow(np.array(im))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": []
}
],
"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": "3.6.2"
},
"toc": {
"colors": {
"hover_highlight": "#DAA520",
"navigate_num": "#000000",
"navigate_text": "#333333",
"running_highlight": "#FF0000",
"selected_highlight": "#FFD700",
"sidebar_border": "#EEEEEE",
"wrapper_background": "#FFFFFF"
},
"moveMenuLeft": true,
"nav_menu": {
"height": "83px",
"width": "254px"
},
"navigate_menu": true,
"number_sections": false,
"sideBar": true,
"threshold": 4,
"toc_cell": false,
"toc_section_display": "block",
"toc_window_display": false,
"widenNotebook": false
}
},
"nbformat": 4,
"nbformat_minor": 2
}