You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
face_generation_gan/dlnd_face_generation.ipynb

648 lines
230 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Face Generation\n",
"In this project, you'll use generative adversarial networks to generate new images of faces.\n",
"### Get the Data\n",
"You'll be using two datasets in this project:\n",
"- MNIST\n",
"- CelebA\n",
"\n",
"Since the celebA dataset is complex and you're doing GANs in a project for the first time, we want you to test your neural network on MNIST before CelebA. Running the GANs on MNIST will allow you to see how well your model trains sooner.\n",
"\n",
"If you're using [FloydHub](https://www.floydhub.com/), set `data_dir` to \"/input\" and use the [FloydHub data ID](http://docs.floydhub.com/home/using_datasets/) \"R5KrjnANiKVhLWAkpXhNBe\"."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Downloading mnist: 9.92MB [00:19, 505KB/s] \n",
"Extracting mnist: 100%|██████████| 60.0K/60.0K [00:06<00:00, 9.26KFile/s]\n",
"Downloading celeba: 1.44GB [15:22, 1.56MB/s] \n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Extracting celeba...\n"
]
}
],
"source": [
"data_dir = './data'\n",
"\n",
"# FloydHub - Use with data ID \"R5KrjnANiKVhLWAkpXhNBe\"\n",
"#data_dir = '/input'\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL\n",
"\"\"\"\n",
"import helper\n",
"\n",
"helper.download_extract('mnist', data_dir)\n",
"helper.download_extract('celeba', data_dir)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Explore the Data\n",
"### MNIST\n",
"As you're aware, the [MNIST](http://yann.lecun.com/exdb/mnist/) dataset contains images of handwritten digits. You can view the first number of examples by changing `show_n_images`. "
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.image.AxesImage at 0x7f8f25eb23c8>"
]
},
"execution_count": 2,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAQQAAAD/CAYAAAAXKqhkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz\nAAALEgAACxIB0t1+/AAAIABJREFUeJzsvVlwXFd2LbhuzokckQOQQCIxJeYZIMWZ4iBKpFRyzbbL\n9bqsdvePPzriOV5Hx3v9vjqioz9eR9jl9k+H7XoOl+0IV9lll0olyRooiRRHkCBBEBMxz1NmAsh5\nzrz9Ae3Dk5cJEgAToujGjkAAyOHec8+wz95rr72PIIoiDuRADuRAAED2ohtwIAdyIN8cOVAIB3Ig\nB8LkQCEcyIEcCJMDhXAgB3IgTA4UwoEcyIEwOVAIB3IgB8Jk3xSCIAiXBEF4JAjCuCAI/3m/7nMg\nB3IghRNhP3gIgiDIAIwDeA3AMoC7AH4kiuKjgt/sQA7kQAom+2UhHAEwIYrinCiKKQC/APCdfbrX\ngRzIgRRI9kshOAEscP8vfvXagRzIgXyDRbFP1xXyvJbjmwiCcMCZPpADeUEiimK+NbpvCmERQCX3\nfwW2sIQ9iyAIkMvlyGazyGaz7DX6EUUR2WwWMpkMgiAgk8lAJpNBLpcjnU6Dx0oEQYBSqUQqlWKv\nC4IAmUyGbDaL/c7vEAQBCoWCtRHAE8+lVCqhUCggk8kQj8eRyWQgl8tz2st/55sk1P5sNot0Op13\nnAp9P+qPfONP98xms9DpdFAqlQgEAjnjQOPOt5O/7ovI+aE5qVQqIYoikskkVCoV5HI5EokEMplM\n3u/J5XJoNBqk02kkEond3XOfQEU5gDFsgYorAO4A+ANRFEe5z+z6xjKZDKIossGRyWRQKBRIp9Ns\nkqnVasjlcsTjcYiimHeRk3KhDuUXWSH7gyYU/z8/8eg3vUfKQdrWTCazrUKUyWTIZDIvZMKS0CKU\ntkEmk0Emk0GtVkMURUSjUTahY7FYQRUD3YvmR75Ngx+PVCqVs/hlMhlUKhVSqRTS6TSArYWlUCiQ\nSqX2VYnxIpfLIZfLAYApKhpnUm7867ThkRKm58tkMuxz+eRrtRBEUcwIgvC/APgEWzjFf+eVwXNc\n94nFwgv9T5+hicFre/460h1hPxcVDR5/b/65pMJ/Zrv3pc//IoUmLbWblC1NbuCx4tgv4ZUj3xZR\nFKFQKJhVSNZWRUUFKioqYDAYoNFooFAosLCwgMXFRWxsbDDF8CJFOvbSDWG77+x1Pu+LhbCjGxcA\nQ+DNfOCxBSHVirQYyTzkNSevKPbT/CZrhu5P9yYLJ58FA+QqNVpQvKXxTUlfl8vlUKlU7Pn4Z6T3\nlUol0un0E89bCCHTmqxF3mUBAKVSCb1ej2g0ylyHt99+G7/3e7+HpqYmmM1mJBIJfPzxx/joo49w\n69YteL1eJJPJgrZzL6JUKgEgx/0CkHeuA2DWTiaTQSqVynvNrxtDKLjwZr7UAuBNLFo4RUVFALY6\nkUw+mojS3ZlM9UKLUqmESqVik1TquvALXNomGmhRFHN2WX73BcDciBetGLLZLMNkBEFAUVERmpqa\ncOjQIZSXlyMUCuHevXuYm5vD2toaEolEwRQw9SP1syiKSKfTbGGk02lkMhlEo1FUV1ejqakJx44d\nQ3d3N1paWmAymaBSqVBUVIRXXnkFCoUCarUafX19GBsbe8LyLLTw84CE3+W3cxlpk+NdZnKdnuYu\nPE1eOoXAdxBv9gNbnahWq2EymeByuZBMJuH1ehEIBBCPx/NqWPqdb2E+r9CEBMBM1XzXz3dvfjDz\nuTWkKHg35EUKLUJBEKDT6VBdXY0zZ87ge9/7HhoaGjA/P49EIoFIJIL19fWC7ry830xCACNtIoIg\nQK1Wo62tDW+99RYuXryI0tJSyOVyJJNJ9hm32w2j0cjmWzQaxfr6OmKxWMHau90z8BsTvyHwzyK1\nCngsjK5DuNO/a4UA5IJ/vHLgfT2n04nOzk689tprWFpawtWrVzE1NcXAIlpE2WyWdRoP3BRyt6WJ\nxpv3vK9N9yatzj8nv8jp+XjXh0Cx/bJudiO8glUqlXA6nfj93/99vPrqq2hvb2dKkRZfNBrdFiHf\ni2x3LbJastksrFYrmpubceHCBZw/fx5ms5m1W6lUQiaTIZ1OQ6FQwOFw4NKlS6ioqEB9fT1+8Ytf\nYHh4uGDtBfDEePNuFv+69DP0XX7+SiMizzOHXxqFwKOrAHIWNY8St7a24rXXXsPJkydx//593Llz\nhw048CTyL71HIXdaXrtT+0khkYnLL3Ye11Cr1WxCC4IArVYLs9mMsrIy6PV6eL1e+Hw+rK+vv3Dr\ngNosCAJTyIcPH0ZDQwP0ej2WlpYwNjaG0dFR+Hy+gioD/v68+8RvGKIowmg0oqWlBXV1dSgrK8tZ\nPFKTXaFQoLi4GC0tLVCpVPjyyy8xPj6+rT++F5GCwlIMSaVSQa/Xw2w2w2AwoKioCCqVChUVFbBa\nrcwFikQiUKlUSCQS8Pl8mJqawvLy8p5xmpdOIQC5ISYSAo26urpw/vx5VFRUYHx8nHWMNPzHL/79\nAhU1Gg10Oh0EQUAymUQ4HGbgG92TzGz+/gqFAhqNhk1mlUqF0tJSNDU1oaurC3a7HSMjI+jr68Pq\n6mpB27wXIYWsVqvR2NiIY8eOob6+HiaTCYlEAqOjo7h16xZu376NSCSyL22gDSGZTOaAihSH1+l0\nqKysRHFxMQN3yWqkfqa+VigUyGazTCnYbDYWoSiUSBcrKSSFQgGVSsXcXrfbjYqKCthsNuj1epw4\ncQLNzc1Ip9Pw+XxYW1uDXq/H5uYmhoaG8OGHHyIajcLv9++pvS+NQiChxZNMJlmnqlQqGI1GOBwO\nNujz8/MYGRnB+Pg4AoEA22lp16VJQNoYwK5JHM+S119/He+88w6mp6fR19eHTz75BNFolPmj5Kqo\n1WoAYCYr+a5kUfT09ODUqVM4d+4cSkpKEI/HEY1GMT4+XtD2Po+YTCbU1NTgwoULuHTpEkpKShAO\nhzE/P4+PPvoI165dQzweB/DY5C2kZLNZpgzob554tL6+jjt37qC2thaVlZXQ6XTY2NjAzMwMPv30\nUywtLcFoNOJ3fud3cOLECTYnMpkM4vF4weeGFA/Q6XSw2+1oaGhAQ0MD6urq4HK5UFpaCp1OxxSV\nTCbD4uIiAxP1ej0ymQyMRiNOnTqF4uJi1NTU4De/+Q0WFxd3jdW8dAqBRIq06/V6OJ1O2O12aLVa\nbG5uYnV1FR6PJ8fP4sGa3cp2oKMUpFSr1XA4HDh27Bi+/e1vY2pqCgDwxRdfsGgH78LQ93iCTyqV\ngslkQmVlJc6dO4fz58/jyJEj2NzcxOjoKFZXVxEMBvdlcW337PmINLQzl5WV4fjx4zh06BDq6uoA\nALOzs7h9+zbu3r2LycnJHDLQdsIzN/O1QWrV8SArAYMEqlGoN5vNIhgMYmRkBNeuXUMymURxcTF8\nPh/Gx8fx0UcfwePxwOVy4ciRI5DL5Tk4D4/i71byhcX5jUylUsFiscDlcqG5uRltbW1wu90s8iEI\nQs6Ov7y8jM3NTUbAI9fT5XLh9OnTMBgMUKlU6Ovr2xN4+1IphKcRiLRaLcrLy2EwGACA+ee84tiO\n4LMT7S8FA3mhgSGMw2Qy4ezZs2hra4NcLofb7UZ1dTWSySRzERQKBXueeDzOXuNxEbfbjTfffBPf\n/va30draCpVKhQcPHuC3v/0tPvjgA3g8HmbKFlop8KxJWmTEiuMnuEKhgMFgQH19Pd566y3U1tYy\nhTY+Po5PPvkEs7OzzCp6Fk5DFpI0LCnFCPi+krabFgl/v1gshsXFRfzyl7/EBx98ALPZjGg0Cp/P\nh0gkAovFAqPRCK1WmxPeI3eIQnk76TepQuK5EDQnaVd3Op145ZVXcPz4cZw8eRIlJSVIp9Ms5Dk7\nOwuv14uNjQ2Ew2GmEGj+kIV58eJFHDp0CDabDW63G2VlZZienkYgENjFqL9kCgHIZbvxMedsNsvY\nZsRDIFO8EMIrAmmYkLc6aMfU6/XQaDTsc3K5HEVFRYhGo8x3pfekVovdbsebb76JY8eOoaurC2Vl\nZQiHw9jc3ERfXx96e3uxvr6ORCLxBJZSCOHpvDxxShoR0ev1sNvtOHfuHE6fPo3GxkaYzWb4/X58\n/vnnuHz5MoaGhhCNRpniou9vxwLMF/nhrQA+Ni99bukY0b1ogVPUJxaLwe/3M65/NpuF3W7H6dOn\nUVZWxhQ3YRC7sRDyRQb4aBGFxi0WC7q6unDy5El0dHSgqqoKRqMRDx8+xMDAAHp7e7GysoJQKIRg\nMMg2Lb/fj0gkwvIbMpkMlEolHjx4gJ/97Gc4deoUtFotdDoddDrdLkZ9S14qhUALiw/Z8GFHSlyR\nyWTQaDSM4VXI+wO5oKY0wYjnBtB72WwWWq0WtbW1KCoqQiQSeWLiKpVKZgbW1dXhxz/+Mbq6umC1\nWhEIBDA3N4eBgQHcuXMH4+PjLFej0Ig9r+z4OD5NbAK9NBoNqqur0dHRgW9/+9vo6emByWRCNpvF\n0tISPvroI9y8eRMLCwtMSVPfPY3zIY2pb9fPpDCk7gdvvdB7vBtBfRaNRgFsjZfFYkFDQwNOnz4N\nh8PBsAifz4exsbFd77Ik0vHJZDLMRejs7MT58+dx4cIFmEwmJJNJTExM4NNPP8UXX3yBR48eIRqN\nslCtTCaDVqvN6wIoFApEIhEMDQ2hsrISZWVlTwDpO5WXSiEAeGK3oL9VKhVsNhu0Wu0T7+9HG7br\nbJp4m5ubCAaDDCh0u9340Y9+hLW1NablydxTq9Ww2Wyorq6G2WxmZp/RaEQ2m2WWwc9+9jNMT08j\nHo+zBVZohUB9Roo3Hz+jqKgIDQ0N+Na3voUf/OAHKC4uhlarRTabxcLCAgYGBjA6OgqPxwNRFNkC\nA5BjGT1N6DN8+IwWNq9cyI2hNpNJzuNG0pg/LwqFAsePH8cbb7zB3DJ6xt7eXvz0pz/F/Px8zn2e\n1W7p3ODxjuLiYrS3t+MnP/kJenp6YLfbcfXqVdy8eRO9vb1YXl6G3+9nm18ikWBzmWjXPAlMpVLB\n7Xbj3Llz+PGPfwyTyYTZ2VksLi7C5/M9s71SeekUAm9e8+CM2WyGy+WCwWBAOp1GMBhku0ChRJpN\nl29SZ7NZRKNRzM7OYm5uDl6vFxaLBSUlJTh9+jTC4TCi0SgzAckXNBgMKCsrg8FggFarZbtqOp3G\ngwcPcP36dYyOjiISibDJwi/WQolarYZCochZxMDjBapUKmGz2XDs2DEcOXIEbreb9ffKygquXr2K\nK1euYG5uDvF4HHK5nIW/lErlMxl0UiYprwyk2aC8SU4YA32OXidLgoS/Znl5OVpaWnDmzBl0dHRA\nr9czEG98fBwDAwMYHh7eUzapVOlRGxwOB1paWhjH4dGjR+jt7cXNmzcxNDSEeDzOwqb8fQljIqWk\n1+ths9ngdDpx5swZnDx5Eo2NjfB4PPB4PFhfX99TiPelUwhSM4xIO1arFTU1NTAajUgmk/D5fAiF\nQgW7L0043uzM95lMJoNQKITJyUmMjIxgYmICDQ0NsNlsaGlpyfHB6TqhUAiZTAZqtRoqlYopgmw2\ni1gshuvXr+PGjRvM1aD78CZ1oawhwl42NjaYz0+LVBAE6PV6VFZW4syZM2hqamLA3vr6OgYGBvDe\ne+/h8uXLAB6j6NRXPE9gO+HdFOmCkvL2peAmpf/yvv9246RSqdDS0oLvf//7OHToEKqqqlheTDgc\nxvXr1zE8PJzDU9hOtlNg9BoJZVg2NTWhuLgYi4uL+OSTT9Db24upqakcV1LaboVCAa1Wi0Qiwa7T\n2tqKnp4efOc734Hb7UY8Hsfq6iqmp6f//8FDyNfJgiBAo9HAbDbD4XBAr9cjEAjA5/MhGAwW9N5P\ncxP492jHvHLlCpaWlnD27Fn09PTA7XajpKSEWTF+vx8ejwerq6sIBAJIJpNwOBxwOp0oLy+H3+/H\n6OgoxsbG4PV6c9J3t+uP55VwOMyiHjxPXqlUwmAw4MKFC3jrrbfQ1taG4uJiptzC4TCmpqbg9/vZ\n4qUICrVvJwlNpCRJ8ZESoKIfVCyGRC6Xw+VywWQyMQJYNBrFxsZGDoZDIggCrFYrTp8+jVdffRWH\nDx9m31coFBgZGcHdu3cZ5Z0vTLOde/Y0hUCvK5VK6HQ61NTUoK6uDtlsFo8ePcKnn36Kubk5Nld5\nvIWnM6fTaUQiEdhsNjQ2NuK73/0umpubUVZWhrKyMkSjUczPz+P27du4ceMG/H7/v/9cBjLDpPFo\nuVwOtVrNYrCpVKrgFoI03JgvJs5/NpFIYHZ2FktLS4jH41haWkJNTQ1KSkpgNBoZzuDxeFgCViwW\nw4ULF+B0OiGTyTA7O4t/+7d/w+zsLCP18IDcfmAkFAGhBc2b42q1Gi0tLThx4gQcDgfUajWSySQG\nBgZw69Yt9PX1wev15kSB+KpQvFWz3WTl3QGp+8C7abRIFQoFurq6UF9fz/z8SCSC5eVl+Hw++P1+\nBINBiKIInU7HiDtvvPEG2tvbUV1dzdikoVAIDx8+xOeff44HDx5gZWUlpx07xWvyYUxKpRLFxcWo\nrKyEw+HAysoKRkZGMDIyglgsxjgavFBfqdVqWK1WVFdXo6qqCu3t7Xj99ddRUVEBtVqNeDyOiYkJ\nfPHFF/jyyy8xMjLCXMvdykulEPL5ZGQiEipOMehCWwgE5JDk4yRIQ2X0nf7+fgwODrLFwWeuEV+C\nnuH48eOoqakBADx48AB/+7d/C2Br54hGozlhtP1SCsQjIFEoFAzrMJvNKCkpYQzAUCiEv/u7v8MH\nH3wAr9fLnpE3s/mIAF/nYbu2SzECYGuHDIfDOaFdcrPOnz+PS5cu5WwICwsLmJiYwKNHjzA2NoZs\nNova2lp0dXWhtbUVLpcLOp2OtdXv92NxcRG3b9/Gl19+CZ/Px3CenQCgzxK1Wo2SkhJWkOXq1asY\nHh5GMBhkAK4UXyFXyGq14uTJk3jnnXfgdDphs9lgsVhYH6ytreHLL7/En/7pn7Jw6l7B5pdeIfAg\nH03CZDKJ1dVVbG5u7ks7pCXD+AlBCoHnGBAphx8kaVispKQEbW1tqKqqYrtzOp1GKBRinyUyzn4q\nA54nwIdE6+rq8MYbb6Cjo4OZtaFQCIuLi1haWoLP52PRD96So/8phyOZTObUstzu/vSMvDIRRREl\nJSWwWCyQy+WMkq7X66HT6aDVaqHRaFibLRYL3G43Ojs7kUwmYTQaUVFRgdLSUtbHABCLxTAyMoJ/\n/ud/xp07dxAKhRiwx0cuthNpG4HcEHU2m2WRJCLOBQIBpuAAsHBuKpWCQqGA0+lEY2MjmpqaYLFY\nUF9fj/b2dqb0AGBzcxM+nw+ff/45bty4gVAoxCjbarX6iUzgnchLpRCkHc4vKHqNdjePx7Pn+PGz\n2iDdEfKFAHlqcr4EK96akMlkcDgcOHfuHFwuV85n+Yw8XiFIEfdCCbWHV0J2ux1dXV343d/9Xbhc\nLgBbuSTz8/O4c+cOVldXWXxc2h4+RLgTViUfTaA+okw/mUyG9vZ2FtlYXFzE2toatFptzhyQy+Uw\nm80sQaihoYEVJdVqtVCpVDkRipWVFdy/fx/vvvsuCxWTO7KTNucDEsmSIWuR+AfENTEYDCgtLUVl\nZSWSySRjfJJr097ejmPHjuHYsWNQq9UwGo0oLS1llkQ8HsfKygoGBwfxxRdfoL+/nz07sKVgAPz7\nVQi0y0hBIp7Uw+e1b25u7ktmHb9QeX8WAJs4NNmIhsvXF6TP8gsolUpBrVajpqYGOp2OVdelicWn\nb9Mz0w5Q6BJflGdB7VSpVDhz5gwuXbqE2tpaqFQqRKNRbG5u4uOPP8Zf//VfY21tLUdR80qBj8qQ\nZfA0DIHMZqr7oFQq4Xa74XA4YDAY8NZbb+Hw4cMIBoMYHBzE8PAwLBYLY6fyrhzhIRqNhlXQ4i0z\nYMs6uHXrFq5fv45AIMDchGdR3rcTqVLg54hWq4VMJoPRaMRbb72F6upqdHd3Y2JiAqIoora2loGE\nLpcLNpsNRqMRgUAgB2yln4mJCbz77ru4f/8+VldX2ZwTBOGpVZmfJi+NQiB52uDQRKOJsB9JP9KB\nBp4MEdF7fLo279qQ8Ci6Xq9HfX09rFYr0uk01tfXGWJP3+MpvU+LevAiNd95RbYdQEn/q1QqGAwG\nVFZWwuVyQa/XAwA2Njbw5Zdf4ubNm5idnd2WWyBVElJOwHb9S31Gm0BLSwt6enpQUVGBrq4uVFdX\nIxaLwWg0orKyEjU1NQzgpKrOdB/CNMjMlj4/MQBJwdLr9F3pmG3Xx3zbgdxsRnL/wuEwfD4fAoEA\nSkpKoFarYbfb0dbWhkwmA6vVipKSEuZaUHKYWq1GeXk5rFYrlEolNjY28MUXX+Dy5cu4d+8eVldX\nGedD2o+7lZdGIfAmHpA7CHyYinai3SSk7LYdUtku3ksLmOLjfMgQANsBAcBoNDJ2YjAYxPT0NFZX\nV3NAU57uLLWU8gm/4Hnlw0986bkE9IxEty4tLYXVamXKQBRFrK+v48MPP0R/f/8z+1jaXzuZqFJ/\nvK6uDmfPnkVHR0eO5WIymdDa2gpgy+IKBoPsmXimJX9faZ4E4SNut5u5ZDzAt5NNhbca6X+yZslk\nj8fjWFtbw+TkJEpLS9Hc3Mzcmvb2dqYwiLuRSqXQ39+Pf/iHf2CRndbWVmQyGSwuLuJv/uZv0NfX\nx3Ay6i+ai1Kca6fy0igEqUjBG+BxHT3e1/4miJRIRQuazPPKykpUV1ezyR6PxzEzM4O1tTVmPtN3\naPLxBU2fNuj84uIVAS16nhpM9yfztqOjAxcuXMDx48dRUVGBTCaDGzdu4PLlyxgfH2fkl0L2M01k\nmtjpdBqjo6NoaGhAa2sr2235Q2vIpSLrgBYG4Q9UaJdcNinZymq1wmKxAHhsQfAYwLOISfnYkATK\nkmIIBAJ4+PAhVldXcePGDbS3t8PlcsFisbAox/z8PILBIGKxGERRhNVqxfnz59HQ0IDq6mpEIhEM\nDAzgypUrmJmZQTweh1arzaFr8236dx92zCfSXY0GYb9Q+N0KLWSSfLz6xsZGNDY2Qi6Xsxj60NAQ\nFhcX2XPQ5OXTa+n6T3tOvh+2M+v56xNCXVpaympT1tXVQaVSwev1ore3F5999hlWVlYYzXY/hK5L\nadQPHjxAV1cXy1fh+xF4XJeBlAERisgCkroJ/P9Go5ERm3hQk97f6U7Lh4Npc6KfVCoFr9cLj8eD\n6elpLCwsoKysjJVDo7AnKVmr1YqLFy/i2LFjcDq3jkUdHx/H1atX8dlnn2FtbQ2pVIq5QgBylNhe\nz5TYs0IQBKECwN8BcADIAPhrURT/QhCEYgC/BFAFYBbA74miWHi4XyL8DiidLC9KpDsMv+ho4igU\nCnR2dqKzsxMKhQLLy8sYHh5Gb28vZmZmAOQuav6aUs6DVLbDBvj28UfdkTVCmZmdnZ3o7u6GTCaD\n1+vFyMgI7t27h8HBwZxFVUiRKphUKoXp6Wn09vbC5XLh+PHjaG5uZm4B/2xKpZIxGSkqIYpb6cbS\nHZz6Ty6Xs1RhQXh8hB5hUM/KvSDJ55JJXUa6Xjwex9TUFKanpwGAWbTEELVarWhra8Mrr7yCzs5O\nqNVqRjz67LPP0NfXx+5B7E/eytuJVbOdPI+FkAbwn0RRfCAIgh7APUEQPgHwRwAui6L4fwuC8J8B\n/O8A/stz3IfJdg+4U4DtRYiUowA8XpgUaqqurkZFRQUEQWB+5urqKsLhMPs8/z3eVdiNaSj1p8mH\n5jkcDocD7e3tePvtt9HT0wO5XA6Px4N79+7h3XffxaNHj3J2n/06F4J3+xKJBKanp/GrX/2KLZrq\nrxiG5E6RciSuQzAYxOzsLCYmJiCTyWCz2diBLGRh0CKMRCKIRqMQRZHVQuD7fCchPB7jks5FPveC\nFiyVAKRdnb5z4sQJnDp1CocOHUJLSwsUCgX6+/tx/fp1XL58GdPT08hkMswVomxIkp0qsG37fa9f\nFEVxFcDqV3+HBUEYxdahrt8BcOarj/0cwBUUSCFsJ/zO+01WDFJEX6PRwGq1MtNREAT4/X6srKyw\n3AapyUqLj1cIu72/9DX6WyaTwe124/Tp0zh37hyqqqqQyWQwPT2N27dv49NPP8XGxgaAx+g9KYRC\ninQsRVGEx+PB0tISdDodiygQW89oNLJU4VQqhXA4jLm5OVZMRhAENDc3w2g0skNY+JOdYrEYo4bz\nVbDp3juxOHncQNq3+SIbvNLJZDKspuLZs2fx/e9/H7W1tUin05iZmcGVK1eYZRCLxZgi5zcHasPz\njkVBMARBEKoBdAG4DaBUFMU1YEtpCIJgL8Q9nnLvHILPN0khSCMj/A4PbBUmraqqgslkYtEG6SKl\nHZAmHA+cCoKwY1+RX2R0fx6MoqrVR48excWLF+FwOKBUKpFIJHD37l3cunULGxsb7JBWKbJeKOHp\n53wfAFvuA9UKnJmZgc1mQ1FREY4dOwaFQoEHDx7A4/GwmgwrKysIh8NsQb/xxhs5C5GqW1MxHb6v\n+UX2rKxBqeVH85G3BngKNu+u0LM6nU5W4LW8vBwymQx9fX34l3/5F/T392N6ehqxWIx9NxQKseeg\n2ou81bFXeW6F8JW78CsA//ErS+FrQ/KkABCBN3yG3YuUfCE3fqcgJp1Wq33C1KTJxLMSn8c85ycr\nD7rS4tbr9aiqqkJ9fT2r7ASAUY1TqRSr3COtOVjIvpZiHgSgEhkrEAhgfHwcmUwGer0eSqUSMzMz\nEAQBk5OT8Pv9WF9fx/z8PNLpNFQqFbLZLEskc7lcT4Bu+U7AIsuA6iDu5Bl5C1AaeaC/SeHxStjl\ncuHo0aO4dOkSY2Hev38fX3zxBa5cuQKPx5OjAHhrhGes7iXMKJXnUgiCICiwpQz+XhTF33z18pog\nCKWiKK4JguAA4HmuFj79/jmgmiAIiMfjCIfDbEBetGKQTnASYqw5nU42aXm/mS/cKopPHtu2W8VA\n36E8BB43kMvlMBqNjClnNBoBPM58NJlMMJvNAB5zJyjCUGgLgfer6f9UKgWlUomioiLE43GEQiEM\nDg6yz15LLQyRAAAgAElEQVS7di3vTq7T6aDX6xGLxRCLxTA3N4eGhgYAj5mitEClICm1gcbmWXwW\nKWi5HYmMZxJqtVq4XC5cvHiR1aVMJpOYmprCRx99hM8++4ydLZnPwqP/aRz51/c675/XQvgbACOi\nKP4/3GvvAfgfAfw3AO8A+E2e7xVUKIkjm80iFArB5/M9NYHm6xYpmEdCRS/4yejxeDAzM4NwOMwm\noXTHkaLku1EOPClHel0C8GKxGOPcE1GGJrIUdNsPIcSeJ/ak02lWY5AwBFJGtBnwB+tSpSa/349M\nJsPi/5QcVVJSwhY7FVPR6/WIx+NMWUh5GtsJvxDJveHHjv8+8SNEUURnZyd+9KMfob29HVVVVQCA\nu3fv4rPPPsPnn3+OhYUF6HS6nBoQ9Kw8GMy3Q7qR7FaeJ+x4EsB/ADAoCEI/ABHAf8WWIvgnQRD+\nJwDzAH53r/fYqZBCEEURoVAIm5ube47Dfl3Cm++8eDweVracD2Xxi5d2+J2CqDxrja7DJ1+JosiY\ndFTvMZlMwu/3szRiOt+CinZIv18o4c1gnmRGFgCfMMSbyfn6gaev+/1+DA0Nobi4GOFwmNVzINLQ\nwMBA3vT2nSgEKQCaD8Clz9EZInSOwmuvvQabzYZIJIIbN27g448/xtWrV/Ho0SMkEgkW4ch3LbpH\nvkS37TahZ8nzRBluAJBv8/aFvV53D+1gkzSb3apnSBlr3wSRThYS2n2kE25tbQ2zs7NIp9NQq9XQ\naDSsdHsmk2HgF4WbdmIdUByc+kl6UEwmk2GAIYU74/E47t27h8uXL+POnTuYm5vLMcl5hVRIhUDY\nCRVp0Wg0rJ/4szZ48I4WL5/oJc08jcfjWFhYwK9//Wt8+OGHOcqVKhsHAgH2Om+hPCuzlA9LSnNV\neOVNeRM1NTX48Y9/jDNnzqCiogKpVAoPHz7En/3Zn+HRo0dYXV1lfc1bQrwlyY87AdKU0MS3f7fU\n/ZeGqch3Lr8jZDIZVp3o17/+NSKRCDt6/JsifDov/xotRh4f4HPY0+n0EyXD8uUdPEsIgOJ9fqkL\nQib5+++/j4mJCaTTaayurmJ2dhZra2ssLMfLfrgNPNOPlCUfTuPdBP7zT2sLH90hzgGfdyAdH6ll\nsFOchHZrGtd81s7hw4cZXuB0OhEOhzE5OYn+/n7Mz88zpqI0SiF9Tt4lkG5+NI++VpfhRQhvKtLf\nlAI8MzODd999FxqNBqFQKO8EflEiNWdpoqRSKXYQB7k5fKVovqYeyV5AvO12CSmIlk6ncfPmTdy8\neXPH1y60UpDy8aXP+7TIzXYifU7p//n6Zzf9LAWLSfmSkKtQVFSEzs5OXLhwAU1NTUgkEpiZmcGN\nGzdw9+5ddvSaNGyZj4rPX/9528/LS6MQ8vlzZLKm02msra0hHA6zcBlVKXrRQu0mIRMX2KqaMzk5\niXv37mF5eZkRag7k5RLp4pMSkkRRRFFREWw2G8rKymC32yGXy1k04fLly3j06BHL1qQS7OQCUU5G\nIU+f3k5eGoUgdRmAXC4+ndBLRJRCpz0XWkRRhM/nY6W+9Xo9gsEgOxj2QF4e4YlkUlyHfpM1ePfu\nXSSTSajVaszOzmJgYAATExOsCAof/XkR2brCiwrN7ZbAxJNE+Ew2hULBwkbSz+/EnPw6hPdR8yU8\nUZ09nnxyIC+P8Af3PmshU6o2Xz2KuCFkTX4dgLgoinnDUy+NQiDklC+GQlYDr6H55I5vyuLKpxD4\niUMo8ddhEh5I4YX3+Ukp8DwRUhg05jQPpOQlfgPjQ8X7kTy2nUJ4oXnCPJ97J0IdSbF7QqLzMcJ2\n24FS5VIo4a8nvT6PgeTbFYgYJKVn0/Pvtv922t58tQb4MOVu+ona+E1JSZfOE/71vY4/v2ifNe/y\nKQGpVcErBQoZb/cs+cb/eebDCx0lYp1JC1LkGxhCg4ndJz3hhj/bYC/alGiqUqLQ84iUEkscAnoe\nui//wz83ZfJRnJteI3Zjvv57XuF3NBKlUsmsGN5Ve1ZfkTmsUqkKfhL3TkSq3Pgdm/qa5zLwpdek\n13nWIiPiFF8PgVyAeDyOWCzGeAI0l/nQp1wuzymmS9eQFtjl27LdhvE8G9sLBRWfFi/dblETQYdw\nBI1GkxOb5wkrdJ18LC/pe2RtFBKM5NmFwFa8mApw8CcxbccrSKVS7JRojUbDXCaelPSssxJ3KzzP\ng/gRfBiN7+ftxohoxNLIEG9p7IefzG8mxKbkmY7A9rs5///X4WpK78dzGEhorPnxlea0kJspPQDn\nWcfPbScv1ELYjiuebwHzJhYpETKpSKtLfTB+F5BeS/pevrBmIYQWF01SADlmHk+yksazs9ksy9yk\nnZbayROzCtlmnt0m9YulJu7TFAKvSMh641OM98M143d7eo23vki2UwbbPdd+gNN0PenmxN+HQo/8\nHOHxCuAx6Ywv8c/Pud3KSwEq8mYcmVC85uSVgHRAnzZp+XjxfgoVs+DPPOAnoVqthiiKOYPPl92i\nZ+Iz8yhWTRZTIceRFj6vhHmiDCnlp91XmparVCqh0WiQSCSeqPLzvMLXFeABXL79JOQuUF8/rQ+o\n/fsl+SJO+e6n0WgAgLFvpW0jF4+3lLe7Fsl2oOI3locg5Y/Tbyl1l96Tfu5ZYUdeQz+r855XpG0i\nLISn6ZLw6LL0OQi5BpCDmeyHSFFvKdrNR0z43ZVeo1wEvs4gVWguNE9EOs58H0oVG9/f/A76dW+M\nPJ7BW70GgwHFxcWw2+2wWCwwm82w2+0QRRFer5cd3zY7O8sOdOX7X/pcu5UXqhBoR5cKdRbwGFyh\nB5ZW0qE0V+lA76QUez6zbT+ExzWkxCpaPNQOqt4DPAbwaDFRiTD62S/hrRHeVeCLchB+Q8xQAs8I\nAI1EIiw5KRKJMMCN3IZCKrN8NGHeXeEtGz4BiffZpYp5v4UHXPl+drlcaGxsREdHBxoaGlBbW4ua\nmhpks1lMTk5iZmYGDx8+xIcffojFxUXE4/EncBpSgHshN71wUBHIvyD5B+JRVR4Qkh6mwWtGfsHw\nPrsUUNoP/1AqtEj4MwzS6TQr/+31epFOp6HT6dDd3Y2enh60tbVBr9cjk8lgZWUF4+PjuH//Pqan\np+Hz+Rie8CzTdy9CERfqX145WCwW2Gw2lJSUoLq6Gm63Gy6XC9lsFrOzs6yEWX9/P0ulFkWRKQI+\nVb1QIsWCqOoyb9XwfjfJM0zqgrUvn1C/GgwG1NfXo6KiAhaLBR0dHWhsbITZbM45wFYUt456czgc\nKC8vRyqVwvXr19mZjqRgeHxtL5bCN8JlyKcQ+B1EpVKhqKgIBoMBOp2OIe6xWAzBYBCBQACxWOyJ\n9Nyn3Ut6v/0U3swmK8BisaChoQENDQ1YXFxEOp2GxWJBV1cXDh06hO7ubhiNRqRSKayurmJ0dBRW\nqxXXr1/H0NBQTiGP/RRB2DrsxGQyobi4mO1aDoeDHTBDCmFmZgY+nw9zc3MwmUwYHBzE9PQ0syx4\nYlmh28i7BEqlEk6nE7FYDB6PB6IosiKmBoMB2ezWuYj7cfbnbtpcVFSEsrIynDx5Eh0dHbDb7ait\nrYXVamVH+S0uLrJIkiAIMJvNsFgsOHXqFCKRCBYXFxEIBJgSJCtyr27wN8JC2C79lN4zm81wOp2o\nqamB2+1GZWUljEYjlpaWMDQ0hOHhYczPz+cca8VfX5obz/vlX4eZyC9chUIBi8WC48eP4/XXX8e5\nc+fg9XohCFtHwpMZSUCSWq2Gy+ViBVlVKhXi8TiGhob2JcWb+o6AP7lcDovFgtbWVhw/fhynTp1C\nW1tbDv9BFLfCX9XV1Whubsbx48fR09ODd999F//4j/+IjY2Nfa1gxSP0grBFBT9y5Ai8Xi9Lda6o\nqMCxY8fQ1dWFbDaLP//zP8fMzMzXjh0Aj11aq9WK+vp6vPrqqzh8+DArre71enHjxg0MDw+z4qrU\nf+3t7Th06BAOHTqEeDyO2dlZDA4Owu/3s/MppUcG7ka+ERYCL7z/Q+cWdHd348iRIzh8+DBMJhM7\nWKOlpQVdXV1YWlrCzMwMxsbG4PP54Pf7EY1G4ff7WVqx1EXIp0ELnf9AoBqZ9RRdUCqVaGpqQmNj\nI8rKyqBUKhEOh+H3+3H37l1MTU3BYDDA4XDA5XLBbrfDarWivLwcZ8+eZaf1jI+PY3Nzs6BKje8n\ns9mMsrIy1v/Hjx9HZWUlNBoNlpeXMTMzg+npaWxsbCAYDCIajcLtdqOhoQH19fV4/fXXoVQq8cEH\nH2B8fDxnp9sPl4FAObfbjYsXL2JychLz8/PweDys4GpFRQW0Wi2sVitWVlaeiPPT9aTuK983zyvk\n1shkMuj1ehiNRnZQzODgIG7duoXbt28zi4sHkIPBIJLJJOrr61FdXY3XXnsNa2trWF9fZ8pPelrV\nbuQboRCkoBANgEajgc1mw5EjR/D666/j8OHDDFBTq9Us3BKPx7G4uIjBwUHMz89jdXUVoVAIY2Nj\nGBwcRCwWyykykc1mn/An9yPaQH4dXz49m81CpVKhqqoKZWVlrK7f6uoqxsbG8Nvf/hZ3796FXq9n\nO25TUxO6u7tRXl6Ozs5OaDQapgz4E6ILKWSZHD58GCdOnEB3dzeam5sRDAbx6NEjDA4Oor+/H/39\n/VhbW8PGxgYikQhaW1vx6quvwuFwoKmpCcXFxRgZGcHMzAwSicS+9DNPRNPr9SgvL8ehQ4fYhrK2\ntsYiO2azmZndtCPzmwBPbNpPIWJdUVER1Go1ACAajeL+/ft4//33MTIygo2NDWZd0pogotrJkyfh\ndrtx6tQpXLlyBWNjY4jFYjmJUnsBbr8RUQapNqYfqj33yiuvoKWlhRUAJZOIDtzQaDSorKyE2WxG\nIpFghUA//PBDbGxsYH19HcFgkPmMXweQCDxmVdIz0ll8RUVFMBqNUCqViEQiGBoawueff46PP/6Y\n1XWIRqMIBAKYnp7G0tISFAoFuru7odVqYbFYUFlZiZGRkX0JPapUKjgcDhw7dgw//OEPUVdXB5PJ\nhFAohPfeew+ffvopFhYWmCIgFy+ZTGJsbIydTXj27Fl2ovV+RBdIKBxLHBU+okMWgFKphMlkYqi+\nwWCAXq9n7/NnZeabl/shRMMXBAHRaBQrKysYHBzEgwcPEA6Hc05ypkgJVY/++OOP8fbbb+Po0aOo\nqqqCzWbD2toaw2v2Gnr8RlgIfFiOfxAqRGm32+HxePDo0SMsLy8jEAhAoVCgo6MDJ06cgEKhQFFR\nESO+UO3BkydPIhwO4/bt2xgdHWWHjAC5J0WTeVXoSSC9pihunehbXV2NkpIShgVcvXoV169fx/T0\nNDOpE4kEKylvMBgY8CgIW7RgOsHoae3l3a/diMlkwokTJ3D69Gm0tbVBoVBgcXERd+/exSeffILb\nt28jGAwiHo8jlUqxKEo2m0U4HMbs7Cw+/fRT+P1+NDY2YmlpKadU+H4sNFrUVqsVFRUVrCoxSSQS\nwezsLEKhEKxWKxwOB0wmEzwez7Y8hZ3Kdi7F015XKpWoqanBqVOnYLfb4fV6WXFVv9+f83k+ypPJ\nZBAOhxlmptVq4XA42DX4MX9pXQbgMdDC+/i1tbV47bXXIIoi7t27h/fff5+digwAf/iHf4j29nam\nAICtmgLpdBpWqxWdnZ1wOp1QKBQIh8PweDw5p9vQwPDEkEI/k3S3cTqdaG1tRVlZGYLBIHp7e/HF\nF1+wcwb4gqjUTp/Ph/X19ZyQ6U6Siygmzy/CZ/nDCoUCJSUluHjxIo4fPw6r1YrZ2Vncvn0bP//5\nzzE5OQmv15vzHal5HQqFcO3aNYyMjMBut8Pn8+WcXrQfQnkd5eXlaG5uZq4Yid/vR39/Py5evIjm\n5mY4nU5mUfIKgecoADvDDaQJSUCupStdnAqFAkajEW1tbXjzzTchiiKuX7+ODz74AJOTkzl4E1k/\nZIXRa5FIhG1wVqsVdrs9hyOyV8D5hUcZaMcDwJBUlUoFm80GnU6HUCiEhw8f4v79++jr62PVgWUy\nGfr7+/Gzn/0sZ8Lb7XbU1NTg6NGj0Ol0MBgM+O53vwuTyYRgMIjl5WWEQiE2SFTDjmLkhX4+ignT\nZGtsbGQLbXNzE8FgkFk11AdScg25HUS22iliT/fklcB2uxhJRUUFOjo60NLSAoPBgKWlJXz00Ue4\ncuUK5ufnmQ9Lk1apVOYwEHlqOT0bFbDhMz/3gzuhUCjgcrnQ0NAAvV4PADnjSy4LuZvUn/kwjd20\nL59FsR14LZfLYbPZ8Oqrr6KtrY3t+MvLyxgfH0cgEHhiE+F5BryyoLVDjEaZTMbGgj+fYTfyQhWC\ntLOkWMLa2hru3LmDO3fuYHR0FEtLS0xLUk06irvSoDQ0NCCRSDBij1arRVNTE+LxOIaHh3Hz5k12\nGg6Rmsg/43fmQgl/fYVCgZqaGraDBQIBLC4uspOH6f4ymYydGcCfycDvRGSuP03470l3qu18TJfL\nhfb2djgcDhQVFSEcDiMUCiGVSqGkpATFxcWIx+PY2Nhg145GozmhVdqpkskkEonEc6Xj7kR41l9Z\nWRmqqqogCALC4TACgQCrYswraHK5qJ+o3fnm47PmQz4lK/0uWQu0gI8cOYK6ujpkMhmMj49jaGgI\nq6uriMfjOexVfjPh70f/KxQK6HQ6FBUV5YzxXtP4C3G2owxAH4BFURS/LWwd/PoLAMUA7gP4iSiK\neXNdiXbMm22kHT0eD27evImRkREWUpH6eh6PB16vN2dA0uk07HY7QqEQSkpKWBJQaWkpvve972F1\ndRXDw8M5g0ZmGWEQhaYFE2nEYDCgvLwc5eXliEQiWFpawujoKILBIPUl+00+sNTvpoEOBALsuPin\nCSkanqlJ18mHm1RWVqK1tZWdCVFWVobOzk6o1Wp2mtTm5ibu37/PqgTTrktjSUxHQRDYMWwA9oU3\nAYCdLqVUKlFSUoLS0lJsbm5ibW0Na2trbIHQuKrVaphMJka7Bp507/a6KUjzKHiFoFQqoVarUVxc\njJaWFrhcLqRSKVy7dg1ffvnlE8lLpOikvIJ8LghfM4Pci71IISyE/whgBIDxq///G4A/FUXxnwVB\n+H8B/M8A/jLfF6XHUPHAYjqdRigUYuam1L+TmsP0mxb8o0eP2NmJqVQKsVgMXq8XyWSSAYl0TiHh\nCrzpXiihxWi329HZ2Yny8nLEYjEMDQ1hYGAAMzMzSCaTOYeKZrNZVi+B+gV4TH2Ox+OYmprC6urq\njtsA5NY6kGIJBMw2NDSgvb0der2ejUdraytKS0sRDAbZoa8nT55k7sDi4iJWVlawtraG+fl5dupy\nvkSmvQKdTxOyAKjATTabhdfrRSgUYkV4E4kE1tfXsbm5iXg8juLiYphMppyNQcpDeZ6IQz43hJ6d\nCtsIgoBIJIKxsTFMT0+ztvO8GX6jpPfVajWcTieKi4shilunlUWjUQYyPysT9WnyvIe9VgB4C8D/\nBeA/ffXyeQB/8NXfPwfwf2AbhfC07CzawciEos9Lk2743HdBEJgZvrS0hEAgAKfTyczHyclJ5qOR\nT0s7MZ1yXEjhzcTy8nJ2Uk84HMbAwACGh4extrYGjUbDdjDqC/J9FQoF9Ho9dDpdjrJYWFjAxsbG\ntglifBtItpsggiBAq9XCZrPB5XLB5XIxfkckEoFWq4XJZGIglk6nQ1VVFYqKiqBQKLCxsQGv14vl\n5WU8ePAA/f39ePjwIbMWeKtkP4TmhU6nY5T2mZkZeL1ehg3ROY+BQADJZBIWiwUmk4nxRPjFz/fL\ns/p3L22NRqOYm5tjbR0bG8Pa2hqzqvhx4jdBaitxRGw2GzKZDHw+HzY3N3PyNV5UlOGnAP43ACYA\nEATBCmBTFEXqwUUA5dt9mTqbT/5JpVKQy+UsPktVY/iyVCTSHY+AIyozRqYqnVY8MjKC1dVVZhEQ\nX2E/fVy5XA6DwYC6ujpcvHgRTqcTXq8XIyMjLFoiNf9oVyU3xu12w+12MzozmeYA2MGn+Swb6hPp\nPaSugkqlgslkQkVFBTQaDcta9Pl8mJ6exsTEBEZHRzE0NMTOuygqKkJlZSUaGxvR09OD+vp6dHV1\noa2tDbW1tVhaWkIoFGLtopg78UQKKSqVCsXFxXC73TAYDNjc3GShZj75i6+0RUAc7aq8tcn3H++m\n7kS2Ux6iKDIweHp6Gj/96U+ZyzIxMcFwIcJCaEz5TZPSyFUqFSorK2GxWNhhL1NTUwiHw88N2j7P\nYa/fArAmiuIDQRDO0stf/fDyzJbxFYBocOg1vsqydOGq1WrodDqYzWbo9XpoNBrodDrU1taivr4e\nZrMZyWQSs7OzGBoawtLSEus0GmQ+O0ytVhe8jBoAmM1mlJeXo6KiAplMBouLi5iYmIDX633CJOXz\nOeg1l8uFyspKKBQKrK6uYmpqCpFI5AnkPp9IfVngyZoLhAHwypVA2A8++ABzc3NYWFjA8vIyI/Io\nFApMT0+z7MtTp07h3LlzaGhoQCwWQ2NjI8LhMHw+3xP5I4UWslooSzASiWBiYgIrKyssRAtszTOy\nZlwuFwwGAzQaTQ6LVdp3zytSfkM6nWYkOd6V410rfnz472cyGWi1WtjtdtTX18PhcADYOpQoEonk\nHB+3V1fneSyEkwC+LQjCWwC0AAwA/hyASRAE2VdWQgWA5e0uoFQqWRKNdOeXnrxEIS7+syaTCS6X\nC/X19SgrK4PRaITdbkd1dTU6OzthMBgQiURw79499Pb2wufz5QCYfOyZ8vtjsVjBFAINqM1mg91u\nh1qtxvz8PMbHxzEzMwO/3898XD7KwBdCEUURTqcTFRUVkMlkmJmZYUy2ZwFHNIl4ocnCK5JUKsVy\nP+jAm42NDdy+fRt///d/zzjyBNDSNf1+P8tniEQiOHToEKxWK6qqqtDZ2QmPxwOfz8co5vuB0VD7\ntVotmpubUVxcjFgshpWVFfj9foYtENDm8XgwPz+P6upqljlLyjWfwnoeJSbFamg8eOCSqOwUAuWF\nXAC+bUajEVVVVaivr0dJSQk74IW/J8+h+NoUgiiK/xVbx79DEIQzAP5XURT/B0EQfomtI+B/CeAd\nAL/Z7hrUGfQ3FbOQ1rfXaDQQBCGnxJhMJoPb7calS5fQ0dEBp9PJkHHKI+fNp3g8zhJFVCoVY9hR\n9iCdq1jICUuuDyWiJBIJDA4O4ubNm+xQFn5n5qm95PoUFxezvAdRFDE3N4fR0VGGrexm0KXxeF6i\n0Sjm5+fx7rvvYmxsDF6vl+WBUBsJvCNfliasz+fD/Pw8FhYWGC7T3t6OiYkJDAwMMNeNjrgvNOdD\nrVbDbrejubkZJpMJCwsLLBRKmAu1K5lMshoNBCrnC+0BOy+aIs3WBXILvvJWH/3mz23g08PpWsDW\nhqnValmBGQCora1Fd3c39Ho9Njc3MTExgc3NTeaOSBXObmU/eAj/BcAvBEH4PwH0A/jvz/qCFEnN\nB+4AT2IGTqcTp0+fRkNDA6xWa04BT55j4HQ6UVdXh6qqKrZz8B1G9ys0qEgx59bWVtTV1SGb3ap6\n8+DBA2YBkTskjZYAW346FcQwm81IpVIsy5CiELs1DWmS830JbJnTgUAAd+/eZUeLBYPBHLRa2la6\nXiQSgc/nw/LyMqxWKwwGA5xOJ+x2O1MG0mIrhRIK55lMJlRWVkKn0z1RW5CUD20EZPHQIpTu4tK+\n2quFIL2W9D3eHQCeDAXzlqxarYbRaERXVxdeeeUV6HQ6LC0tseQywpSe1y0riEIQRfEqgKtf/T0D\n4OhOvkeMNtKUPI2YD73QzsJr2HQ6zeK5er2e+WCkFEjTKpVKHDt2DMXFxdBoNHjvvffQ29sLAKys\nF8WwCx0n1+l0cDqd6OrqQlNTE1vQExMTrI1ERAKQU+4rk8mwjEebzQaVSoVQKASv14u1tTUGzD0N\nBZeG+Kjf+PdJCZMFsLq6Co/Hw97nszUB5CgTfgeNx+NYXV1FQ0MDbDYb1Go1tFottFptDnGpkIg9\nCbl7ZrOZ7bK0+9Mz0xwjhcATf6hvaH7tJDLDS77P7GRh8hEEfg6QAqOydNnsVqWqlpYWvPrqqzh1\n6hREUcT8/Dxu3bqFhYUFtsHsBgDNJy+UqUiDwpvO9P/TNCpxwfksOp5pyFffJe1aVlaGY8eOYWRk\nBGNjY4hEInnBnJ1OWKm5TguLR4Zra2vxxhtvMO7B7Ows1tfXGXUWeLxz8ouXQo1utxtHjx6F1WpF\nOBzG+Pg4VlZWGIBE399uAuTzLaVsRXpNuuC3Q9j51/jnj8VimJ+fRyAQQE1NDVNkPD7C37eQ4CIR\nd8gakclksNlscDgcDEgURRF6vZ4Vdslms6irq8N3v/tdvP/++xgfH3+ikM5Od9vnxRhoThP4bLVa\ncw7DyWazKC0tRVdXF5qbm5HNZrGysoKhoSHcvXsXwWCQcWue5Yo9q+9fqEKQEpN28jDA1mBptVok\nk0ksLCywTEeaEKQEqEMJjGlpacGhQ4ewuLiI0dFRFhajRcVn7W13f+kuwmMaNHjUvoaGBpw9exbF\nxcXwer3MvKPvS01Vur5MJoPdbkdTUxOOHj0Ko9EIn8+Hhw8fYmVlJSdst5vJuF0IjQ8NSrMStwvF\nSSWZTMLj8bDiqqWlpTCZTE/ct9D1Bvi2EvZiMBjQ0dGB4uJiJJNJeL1eZLNZFBcXo66uDna7HQqF\nArW1tXjzzTcZLZ7ARWrzfgpZMWq1miUnlZaWoqWlBdXV1U+cN2Kz2dDS0gKr1Yp4PI65uTmMj49j\nfHyc8Vik7gb1z27kG5PtuFOhXXRjYwO9vb055qLD4UBJSQmsVisLRRKhRyaTwWQy4Yc//CHcbjd+\n+tOf4uHDh9jc3GQTiZJH8ikEAqXIpJPuJgAYiFVUVAS3243W1lY0NjYimUxiYmICH3/8Mebm5hjI\nmc8KAsCUCcX1E4kEZmdncfPmTaysrLAdTuoS5GszWUBSKwzILTirUqmg1+sRjUYZPsG3iZQeP+l4\nNyYKLpkAACAASURBVI/aQW0iV5B4AbzipM8WwkoQBAE6nQ4qlQrRaBQWiwWNjY344z/+YwbGEZBK\noeWioiLYbDb2fLW1tZiamsLS0hJzb6T4UiFFJpNBo9FAr9ejpKQE77zzDg4fPpwTQucVbyKRgFKp\nhNlshlKpxPr6OqsERe+TRUEW3nYWzrP6/KVSCDy4lUgkMD09zcgcRUVFKC4uZpRUKpNVVlaGtrY2\nVFRUwGQywel0IhgMsjMTybekhfM0Yol0Ekt3ePquyWTC0aNH0dbWBqPRiMnJSUxNTWFoaAg+ny9n\n9yWrgv7W6XSorq7GkSNH0NzcDIPBwJKJxsbGmPnL98fT+isfsCUFcalfGhoaMDQ0hPHx8RysgBfe\nzaCx4EExYuKtr69jfX2dZabyWEShXQayAgYGBtDW1oby8nLU1NQgnU7nKATaRamt0WgU0WgUkUiE\nRZikEQF65kK2l8a6o6MDly5dwtmzZ1FbWwu1Wo14PI54PI5MJgOdTgej0ZjDlaGNiHJijEYj+zyP\n9exVob2UCoF+ezwepiVJ+B2opKQETU1NeOedd6DX65kJy3+W16z8zpjv3nwUgvex+UVBlsjJkyfR\n0tICQdjK2pyZmWHhMOn9CUzU6XSorKxEV1cXTp48idraWoiiiFgshvX1dczNzT0Rd35Wf0nzCOg3\nPbdarUZlZSVeeeUVXLx4Eb/85S+xsLDAckh4hij56XwaMdGtZTIZ29lCoRAjMgUCAcYa5SdsoUQU\nRYTDYczMzODKlStQKpUoKipi4WxKLwbA3EjaCEKhEBYXF1n1J57xKcVR6F6FErlcjiNHjuBP/uRP\ncohRq6urWF1dhUwmQ3l5OQwGQ86ZnjRXOjo6MDk5iVu3bsHj8SAQCOTMX4qwUXLUTvv9pVII0glN\n3AUafL6Ip0wmYxmFhNSSf0vl28nU2u449u2EJ/ZId1EyB0tLS2E2m5HJZLC0tISVlRVGM6Z7UfsJ\nBGtoaMDrr7+OkydPwuVyQafTIZFI4P3338dvf/vbnIQhfrI+65wD+jxvBfFp5FSqrqOjA3fu3IHV\nasXa2lpOCS++vYS30PPr9Xo0NDTg7bffRkNDA2QyGTY3NxnXgjgfhPsU+qBXURSxvLzMahGWl5dD\nqVQy39zv97MEIL1ej9raWnznO99BKpVCOBxGJBLJmTu8ki+kEiAhUFyn0zHi1NraGoaHh9Hb24vN\nzU1861vfQlFREWsHbQr8Jnb8+HGYzWb09fWxMgGkMHjFJwjCjisxv3QKIZ8JS2AgD7bJ5XKYzWa4\nXC5YrVZotVoAYMqAnwR73bmkE4ZvH8/Om5mZwfz8PAuL8qceUXXlmpoatLa24vTp02hqakI0GsXa\n2hpLA6ey62Ru0v132m9SkIwmGj07KYauri54vV4MDw9jcXERXq83h0NA+AkpCQIQ3W43mpubYbFY\n4PF4MD4+juXlLZIqD1ruh4jiVjXiUCiEpaUlaLVaKBQK2O12OBwOxqkIBoOw2Wx45ZVXcP78efY5\nvj/2G0wk4QvgRCIRzM/P48aNG9jc3GSFYIlWHQ6HMTc3h3v37gEAjEYjKisrYbfbcfr0aVgsFtjt\ndtjtdmYlqNVqLC8vY3Jykllz/+4UAkk2m82pRsuHGIHHNOe2tjZ873vfY4dgKJVKLC8vw+fzsYNO\n9kJG4sN0JLxvHY/H4ff7EQwGIZfLGRocDoehUqlgNBrhcDhQXV2Nuro6nDp1Ci0tLSgrK2MWDPnE\nvb29GBsbY0VUKL6eD9zcTvLhCPR3KpXKqR3w6quvoqenB5999hk+//xz3Lhxg2UIUkl5SoGmaEp1\ndTVDxmUyGcLhMK5fv46RkZGc/trP4+eALUuGcAGFQoFAIIDZ2VnmX1ORW3oGs9nMKnPxRwKSPAu0\n3auQEqAiN8vLyxgaGsKtW7fwgx/8AG+99RZzvyKRCKampvDJJ5/gL//yLxGLxVBaWoo333wTZ86c\nwZEjR9Dd3Y3u7m785Cc/QTgcZiDkP/3TP+Ev/uIvdtW2l0ohkInLpy/zh4mKosgOyiwpKWGFQh0O\nBzKZDILBIK5fv46PP/6YId9AfuqpVPLF8el1HlQkv5wsBI1Ggx/96Ec4evQoI1ip1WpYLBZ2lFtl\nZSVsNhs0Gg1WVlYwNjaGa9euYXR0FDMzM1haWkIikWCgGFk2SqUSOp0uh2iTT8gUpvZKIwbr6+t4\n9OgRrly5wupQHjt2DKWlpeju7sbo6CjjP2xsbCAcDkMQBDgcDrjdbpw9exY9PT2sGOvQ0BAWFhYQ\nCoVYdIbaTTUL8p2H8DwijQ4R6YwsKno/FArB5/MhHA7DYrHkHDiT75rAzubHboRAcQIzDQYDurq6\noNVq0draiuLiYiiVSiwsLGBoaAi3b9/G7du3sbm5yVyuK1eusMLD3d3dqK6uRnFxMfR6PeLxOK5d\nu4aHDx8y5bfTMO9LpxB4AhAlMwGPF6zT6YTT6YTD4UBXVxcqKyuRyWTg8XgY8HTlyhVW2ZY/9/FZ\nPqM0ji81L2kHV6lUTElptVq8+eabAJDjP1OuBR2AGo/HsbS0hIGBAdy+fRuXL1/GwsJCjmvDg3kU\nKqRcjKe1mX8uPrpAroDf78fExAQr69bT04OOjg5UVFSgp6cH/f397EAWr9eLQCAAQRBQU1ODzs5O\nHDlyBHa7HdFoFKOjo7h16xZWV1eZEuMP7iVuSCFToGkcqI9ow6AFzD8zRUCCwSDS6TTjr0jrUfAA\n9nYKY68iilvFeFZWVjA8PIzKyko0NDSgubkZqVQKoVAIgUAAAwMDuHbtGm7fvo2pqSk2d6jADtVh\n9Pl8aG9vR3l5OQRBYHjK4OAgm3M7dS9fKoUAPNb8xDS7ePEiqqurYbfbWW05qrKsUqkwOTmJYDCI\n8fFx3LhxA3fv3sXKysoTyU2iKD6RzceLNI7PF6LghcDOhYUFVFdXs0Eiy4AWtTRisbS0hPfffx/X\nr1/H4OAgO68ykUjkHOzKnwZF5d620/5SHgIpB2nIkA668fv9GBsbQ39/P/7gD/4AXV1dqKiowIkT\nJ9DT08OiCuQyUKiXwM+1tTV8/vnneO+999gBMgBYoRQ6aqzQWY/E+qQQtPTkIjqaXqPRsEpcfr+f\nbSpUTi2ZTDKFIq2jUEghl/fatWvY2NjAH/3RH+HkyZMoKSnB4uIiqzBOhVOCwSArTsNH0ajkvcfj\nwUcffQSTyYRkMolQKIT19fWcLM6dykunEEgoLHP8+HHU1NTAarUyHzaVSsHj8WBwcBD3799n1ZbH\nxsbY8V3AY9+WJ3E8rfO2I3nwO0gqlWILg4A6g8GAoqIiKJVKVt0mnU7D5/Mx5uL8/Dxu3ryJ0dFR\nLC8vs0Hn+QBkHdA9CRB9WnullgF/PSnuQZMpGo1Cq9VidnYWTU1NsNlsrKAIAXGUg+/z+TA2NsbO\nGLx27RoWFhZywnd0v2dxPfYq/PWoj/iqw6TMyWqLRCIYHx9HVVUV6urq2LMFAoEcq4L6cD8km92q\nG5pIJGA2mzE6OgqTyYSVlRVMTk6ir68PXq/3ifIAfK0DshxDoRA8Hk9OxGyvffzSKQTyCQVhq85A\nY2MjLBYLy2RLJpMMWLp37x7+6q/+isVvpWBgJpNhuy6ZcTsVXoHwYchkMslKuBFwVVZWBovFAoPB\nwHCBVCqFkZER9PX1IR6PIxqNIhwOs1RsEjJ/+d2KsIpnIeI8D0Gam8ArBP5ZEokEFhYW8K//+q/o\n6+tDY2Mj2tvb0dDQwCyxoqIiRKNRLC8vY2pqCo8ePcL9+/dx48YNZvlIFxT5zbzVUijhrS3+VC/e\n2iOlJ5PJEI/HMTg4iIaGBjQ1NcFut8Nms2F+fp4pDT4KsF9KgQDdX/3qV09wRnjcgxe+RgJZmhR2\nj0ajOQSsfO1+FlHppVIIvMlLR8Ink0ncvXuXFdSkKj5LS0sYHx9nSUz5GGi8G7DbQZfuStLri6KI\nBw8eYHNzExqNhmVUUsgzm80iGAyycubbafZ8zD7CHnYjUpeHrs0/O/8MiUQCS0tLzN0yGAysdDnh\nD2QlBINBZvXw99uu3wod2pPei3bPfG3IZreK7ywsLLADZ7q7u7G4uIjh4eGcEClvbeRbnM8rT1M2\n271HCosfK14hbscw5d9/mryUCoEGZ25uDpcvX8bExAT8fj+USiXm5uYwNzeH1dXV/4+9N42N68ry\nPH+PIhkRDJLBIBnc950URVkLJVmyJTmltNIuq11V2WmgpjDo7Cp0o7p7ajCD+tA1n2aA+TLdQGPQ\nMw3Mgi5kZgFVlZXOysmqlNNLZtqyZGsXRXHf953BWBgMBpcgYz5Q5+rGU5CiuFiS7QMIkoLB9+67\n795zz/mf/zlnWwVPzJp5J7LZ5Esob7cS6/o7ObWe5Tpra2sEAgECgYDiE+yV7NeJq8tW71Qwk3v3\n7pGVlaUUn1hNZutG8KK9rgWp32O7n8fa0Ppnu51b46t4OTFvbBjPfGNzwobFYlF1EHVCELDn1Y++\nla+PiNsprdgXFxcJhUIsLi5GZWOKgpBiqMIF+TpIJBKJaaa9VArBMIyo+nNCNtHjxDqwuNcm3rfy\n9RLxt80VlgTn0K2Fr4JY9VXKZgrhpXIZhJiUmJioNLhesdmMon8r38pWomMoOvYjikGAxf3Iv3hR\n5aWyEABFItFLYJkLfEgBy52Ahd/KN0MkAUia1QpYJ5aBvm7EVf06uaCbWQh7S8H6CkTIMYIb6Oad\nOea9XTT7q0poMd9HP4W2+zvy2V4XK/06iD4f5tRl888hOlpjBhJ1N/Rph0qs96GX9dtqnC+avFQK\nQTS3WVPLphLcQPcDn3Y9PTV4P0U2v34fycWIde9YC1r/3Hytb7qYN6XE63UswLxBpYiprhTEqhSK\n9XbEjDnoKcrmd7iddfk85aVzGXQSkDk2r7Py9D86u0/fUGam316DkDqJRABRuY9O4Inl2sSKfW+W\nR/FNd4tiEa50y+tphV7l+3qinKwxeLIwT6z7i4gi0Wt1xsoned7v7GsBKpo1vL4AdNYdPG6PtR1t\n/FW9IP0eOptMV16iAAQP0fnr8CSZ6EU2P5+XmBWsftLr82emc8NjYFqUgp4LstX9RMzvycxr0MOa\nL6LstvuzA/ivQD2wDvwJ0MNG16ZiYAh4LxKJ+Hc3zMdFTnXNq/9Mb5Kql/3SGV36S9AZimLa7QcT\nzcz+k/HqnX7FzZGMu/X1dZUxKdmQ+sI0W0bfdDErR/1dS1JZQkKCihjIHOvJbZJ0pVN/DeNxZa7t\nzLO+/kShmH9fLIi9Tv/eK9mVy2AYxo+BzyORyI8Mw4gH7Gy0d5uLRCL/0TCMfw84I5HIX8b43We6\nsW7my0Sauzzpppm8VNlEEq40l0uLRCKqfPt+xJktFgtnz55VxT/1ccmzBINBRkdHaWlpUW3epU29\nlMTSlYf+fN9GUmKDifrJr+MtMo+rq6uq9Z/eKk0OFh1X2I5CMK8v3TrQ35E56ep5yZ67DIZhpACv\nRyKRHz66QRjwG4bxLnDu0dd+Alxlo73brkTfDI/ur1683uxEfiYLQl6IYRhRnaHkmvspUjvv3Llz\nvPXWW1RUVCgmpZwi0g24o6MDh8PB7du3WV1djdlIRkSUo46Sf5NFN9MFt9GtBb2GhGz4WErEfE1z\nMtzTxqA3ZtUL0Oig9YvOkdmNy1AGuA3D+BFwGLgH/A9AdiQSmQaIRCJThmG4dj/MDTFztnX3Qcwz\n+Z6U37ZYLCr/Xpp8QnRPRHlZT8sEe1ZJSUlRrdwlnViqHGVmZipXJSMjg8bGRiorKyksLOTDDz/k\n/v37hEKhKJNWl295Fo9Ff2di8ktqMDyulyBVlcVq0Csy61aYuRO0XuBlM5FkL1FKNpuNcDis6lno\nNTZfZMbjbhRCPHAU+HeRSOSeYRj/OxuWwL6uUB18k5M/PT1d1eJ3uVwkJycDqI7OHR0dDA0NMTs7\nq35H19T7ZTGsrq7i9/tpa2vD4/EwNjZGXFwcKSkpFBcXq3LhRUVFqtDqa6+9pvokjo+PqxNGNz9l\nzN8qgw0xWwNyImdmZpKfn69qOsj3QqGQqjbU09OjsAJzVWxgW6C03FsIcXoUTLc+9C7PL+r7241C\nGANGI5HIvUf//wc2FMK0YRjZkUhk2jCMHGBm0yvsQHRzUKrwlJWVceLECS5cuEB9fT2FhYXEx8er\nKrw//elP+d3vfoff71faWT9V9svslvoGH330EYZh0NXVpRpwlJWVqTz8s2fPcvz4cdLS0qivr2d9\nfZ1bt27h8/nwer3qWc1l1L+VDZFNq1uL0rrvzJkzvPXWW9TW1qqmwHNzc1y7do2f//zn9Pf3KyUi\nxWv165r7dW5nLAJe6hEvvXaB4ENfK4XwaMOPGoZRFYlEeoALQPujPz8E/gPwL4B/3IuBCjIvLych\nIYHS0lIaGho4deoUDQ0NlJWVYbVa8fl8hEIhrFarOnnLyspUo1WpVqS3U9MLtu6l27C2tqbSh6Wq\n79LSEpOTk7jdbuLi4picnGRqaorU1FRVfDU/P5/+/n5mZmbUeMwYisiLuLC+StHfV1lZGYcOHeLE\niRPU1NRQVlZGeno6i4uLjI2NqT6gx44dY2Jigs7OToaHh1WlqFjdsZ8WIjRbKDrILb8vPBRR5i9i\nhAF2z0P474G/MQwjARgA/iVwAPiZYRh/AowAP9jlPaIkEolgsVgoLCzk1Vdf5cKFC1RXV5OcnMz0\n9DQLCwuEw2GSk5PJz88nPT2d2tpa1tbWyM3NJRwO4/P5uH//PhMTE6rhK2zeyHSnIkDT/Pw8gDpt\nVlZW8Pl8anFILYeqqiqOHz9OamoqZWVldHV10d3dvedVf79uEolEsNlspKWlcezYMc6fP09jYyMO\nh4NwOExvby9jY2OMjIzgdDopLS2lsbGRqqoqDh48iN/vJxAIqCKr8p7k2mZ3zSy6QjB/BmC328nL\ny6O2tpauri7VK+FFVOS7UgiRSOQh0BjjRxd3c91YopfAcjgcnD59msuXL/Pmm28SCoV48OABP/vZ\nzwgEAjidTi5evEhWVhaGYXDs2DGOHDmiQJ6BgQF+/OMfc+vWLfr6+hR91VyXf7cifunS0hKGsZFX\nv7S0xPLysnqWuLg4AoEA3d3dXLlyhczMTI4dO0Z9fT1tbW3KMgJiNmH9VlA40iuvvMLFixc5e/Ys\nSUlJ9Pf3c/fuXW7fvk1nZydjY2Pk5uby6quvUlRUhNPppL6+XtXaXFlZURWhBMiVStFbWQpmToy5\nTFxBQQFvvfUWf/7nf85//s//mR/96EdRB9GLJC8VUxGgsLCQY8eOcenSJUpLS5mYmODOnTs8fPiQ\nyclJTpw4wcmTJykqKsJut+P3+1V5L+m4m5OTw8WLFwkEAnR1dUUBd3u50cQagMfEJDMHQhDvYDBI\nR0eHciOkXJmOeseS7YzZnAAmPIaysjKqqqqYmprC6/Wqlnex3BJpfiNdhVJTU0lMTFTWi9PppKys\nLIpyLUVYP/30U/r7+1XrPKlXsVdzbRgG+fn5/P7v/z75+fkMDQ3R1dVFW1sb7e3tzMzMMDc3h9/v\np66ujuLiYiwWi+ovoT+nHqrWafJbWWcSztb7XOrRDHFFnE4nFy5cYHFxkU8++YTx8XFV6VlnL+pu\nrIQyLRYLaWlpZGRkEBcXR39/f1SfUD3ULlbNTub3pVIIcXFxlJeXc+bMGU6dOkUoFOLOnTv8+te/\nZmJiApfLxfHjxzl79iwzMzNMTU3hdrsZHR0lEomQm5tLZWUlGRkZVFVVkZOTE7Uw91opCJAkm0Yq\n6MqzwGOTVFwHademb2IzgKhzK7Yj+vVgY3Onpqbyyiuv8NZbb9HX18fk5CSBQOCJhS/3kjLm2dnZ\n5OTk4HK51GlqGAa5ubmqWYv40T6fj6GhITweD3Nzc8zOzkYt8r2YZ8MwVG/K48ePMzo6yq1bt7h2\n7Zo6+SVl3mq1UllZqZqiBINBZmZmCIVCUQCgfm091X4z0SnzOidCfibtA+fn5zl06BBxcXGMjIyw\nvLyM2+1+gnSmvzMh46WlpdHQ0EBJSQkAPp9PZf3q39fDpTtZyy+NQpAFWVNTw7Fjx0hJSeHBgwf8\n9Kc/pauri8LCQt5++21KS0uZnp7m/fff58GDBwwPDxMMBsnPz+fs2bPk5uaqstfDw8Mx6cx7KWbK\nNGxsyKSkJMLhMKFQiNXVVWw2G1VVVTidTsWZkJNBp7maQ5DbGa+OkicmJuJwOKitreXMmTN873vf\nIxQKEQqFVF8Dnfuvn1yGsdGJSpqbiPWSkJCAzWaLqgYcHx9PWloapaWlHDp0iJGRERXl2UtQLT4+\nnrq6OsrKylR/go8++giPx6Na0YfDYWw2G3l5eRw/fpzGxkYsFguDg4N8/vnnTE5Oqo2lWwOi0IXJ\nullVbr3Woq4IdG6M1+ulubmZmpoaysvLef311zEMg4cPH+L1eqOUkoQmI5GNKt6GYVBSUsIf/dEf\nUVhYiNfrZWBggNXVVTwezxO8CXmOHc3njn7rOYgAcMvLy4oAIu28PR4PiYmJdHZ2sri4yOrqKp98\n8gk9PT2qY650V05JScHv9zMwMMDs7KzSwLsxs54mZmq0bCQ9C1N8YJfLxfLyMrOzswqMjGUJbGes\nOkNOX+iiXOXkzMrKUqEwcykxcwqwXE84HtJSb2VlhaWlJWw2m2qPphN7dtKafDuyvr6O1+uls7OT\n9fV17t27pxS9fs/09HROnz5NTU0NCQkJClsYGhpSLeb0XBGdJv8s49XnTxTK4uIiAwMDXLlyhaSk\nJI4cOcK5c+dwuVzU1NTQ29vLzMwMS0tLBAIBBYwLrhUfH09WVhYHDx4kJyeHsbEx1Tk6Fnt3N+v4\npVII0u5saGiI+vr6KMBteHiY999/H4fDQSQSobe3VxXNlIjDhQsXWFpaor29ncHBQbxer1owsHk3\npt2I8Si5Bog6hUKhEIBiteXm5tLY2EhWVhahUIjx8XHcbvcTVsuzuDf6CaVbCcKqm56epq+vj9zc\nXBwOB/Hx8aoJqSSTSS9Gc8bg4uIiXq+Xubk5hSWsr68r7AY2TlS/3x/VD9K8iHcra2trdHd3q1wQ\n6cgEj0Hd+Ph4CgsLuXDhAsXFxczNzfFP//RPXL9+HZ/Ph91ux2q1qr4e4vvrm3orMYeAdXcuHA6z\nsrKiujAdOXKEs2fPcurUKerr65mZmeH+/fsMDAzg8/kYGRlhfHwcv9+vmsEmJCQoNy01NVX1nNBd\nBj21/xuhEETEQgCorKzke9/7Hr/4xS/o6+tjbm4On8+nTmAx24qKiigqKiIuLo4bN25w5coVmpqa\nlKkoAJJ0Bt5LhaCDTRBNooENJVRZWcmxY8eoq6sjMTGR0dFRent7mZqaUua1eTNtZ1PpGIZ8d3V1\nFZ/PR0dHB4FAgPb2drKzsxVIuLCwoOZXsgFFIej+cSgUwufz4fF4WF1dxel0UllZyaVLlxQrcG5u\njs7OTlpbWxkYGFCW3X5IOBxmYWFBdaWWitzJycmcOnVKhSKDwSAtLS08ePCAyclJlXkoz6Wf7rr5\nLz/fbJ5j+fC6yLzLWlhdXWVhYYGFhQWqqqqoqqoCNlyLQCBAJBJR/S5sNhuFhYWqGZH0w5Bn1a02\n3Sp7GhgaS14qhWAYhmpbFQgEyMjI4PTp0+rFjo+Pq3bYhmHgdDrJy8vjzJkzVFRUMDo6yt27d7lx\n44bqZqz793sdGxZtLcQU8bsFpBNf++DBgxw9epT8/HzGxsbo7u6mr6+P2dnZJ0CuZ8EO5Hv66SGW\n1vLyMoFAgOHhYdLS0khKSlLhNtkgoghEGej3X1lZUQt6eXmZoqIiUlJSVFKWYRi43W46OzsZHR1V\njEt5jr0U2YjiwiQkJOByucjLy6OkpIQLFy7wyiuvkJqaSnNzM1evXmVgYIBAIKBAWx3sjWWKP22e\n9XHoonMUZM7m5+dJSEhgdnaW1tZWZSWmpaWpdWu1WhVvxmq1KhdBNrne09McCdGV09dWIQji63a7\n6e/vZ3x8nIqKCg4ePKjyAX75y18yPDysTvnS0lLefvttLly4gM1m4/r16yo8KX6aiJjReyliskui\nlc1mU5wHMfsSEhI4cuQIR48exW63Mzw8zO3bt+nv71cdqkXMCLJ89rR5MxdYkbFJKzEJX5nBPjMG\noYfi5AQVl8ZisZCXl4fdblexe7EQBAvRn2MvRdxGUWTJycmUlpbyxhtvcPHiRfLz84mPj2dycpJP\nP/2UK1eu4PV6o0KMIoKbPCvWEQvUi1Xmbm5ujrGxMYqKihgZGeEf//EfVZfmkkfNgaVdXnFxMWVl\nZYRCIdWYVjp+6+8lFp9hp4l6L41CEG03NzdHS0sLf/u3f8t3vvMdzp49S2lpKWtra8zPz3Pv3j0G\nBwexWq2cOHGCs2fPYrPZ6Ovr44MPPqCrq0s1cdFDYMAT9RZ2KwKEykvTe0yurq6Sk5NDbW0tNTU1\npKWl4fF4aGlp4c6dO8zPzytQTBScbtLqYOjT5k3vbxhrjIKSx1pYZsWjhzBlLOIuvP766xQVFSmE\n3O1209XVRSAQ2PR6eyECvCUlJZGUlERFRQU/+MEPOH78OKWlpdhsNrX5jx07hs/no6uri/HxcTwe\nzxMWlDkkup31YLag9PelS1tbG9evX+f3f//3WVpaYnZ2VrkJi4uLjI6OKg5KWloaTqeT9fV1qqur\nFc9COCGbldnTFfazykujEGBjEQUCAQYGBvB6vUQiEbKzs6moqKC0tJTz58+TlJREXl4eNpuNxsZG\nqqur6ejooKmpiZs3byo/DqIbdcj/93KhymaUBSc8BFk0hYWFnD9/nsLCQsLhMENDQ7S1tdHV1aXS\nZsWS2AxN3o7EWhj6iaYTs/Sfx/oslpWSkpJCQUEBhw4dwuFwABuJXdPT0yrsu58ic5yQkEBSUhLp\n6elUVFTgdDqZn5/H7/djsVhwOBw0NjaSnJxMbm4uTU1NtLW1qRNYxw52ug7Mbp1+HcMw6OnpOdS7\nHwAAIABJREFU4YsvvqC6upqxsTG8Xi+rq6sqsjQzM6PcS7nO2toaZ86c4cyZM7hcLoXt6A1/zWtj\npyH0l0Yh6H7R2toaXq+Xq1evMjMzw+XLlzlx4gSNjY3U19crEojdbicUCnHz5k1u3LjB/Pz8E26C\neWPstTkrlGVAbYwDBw7gcDg4ePAgFy5cID4+ns7OTr744gv6+vpUppw8q3lRxfp8s3tLdMC8sfXf\n14Eo/TtmX1S3NHQXwlwaf3l5meHhYYXpbKcJ7G4lHA4TCAQIhUKEw2H+6q/+irS0NBUxqKmp4Z13\n3iEnJ4fs7Gzq6uooLS0lMTGRlpYWZmZmlOKWQ0LGKpGaraINMqfiJpjxBJlLn89HU1MTCwsLeL1e\npqenFbVdByVjFeFdX19X4LckacnY9He6Gyv3pVEIZo27tramGrpKAtF3vvMdCgsLqaioUB1+7927\nx/379+nv71ckD90qkEmWa+71gtVNdtH8wjk4duwYhYWFdHZ2cvv2bT799FPGxsbUGAWIkhNcdxPM\nkYet7q//rS8w81yY51rmR/99eBziEnA0Pz9foeAAgUCAhw8fMjAwEDX+vQ45mmV9fV2x/+7cuaPC\nvYZhMDw8zOLiIlVVVZSXl1NUVMRrr72mTtkHDx4wNzcXNV/SyEWv0xlLzNWQ9GfUQ5BC55aIyOrq\nqkqqimV9yf8TEhKUxSDXMtcWNVsjW0U8tpKXRiHA48Upi2t1dZXZ2Vl++9vf4vF4SEpKUgVIUlJS\n8Pl83Lx5k56eHlUcJSEhQfnler1F2J/uvoBizCUkJJCamkppaSmXLl3i6NGjJCYm0tXVxbVr17hx\n40bUKSPEFHicS2COPevsQLPEApz0RSUYhX7iP23Dyuknyik+Pp7a2lrq6uqUJeTz+bh79y69vb1R\nC1zGv19JPfJcYqGIS7i+vq54CkePHuXs2bN8//vfp7q6mqKiIhWu9vl8UWtAqlvNz89vOWadv7KZ\nctYtvpWVFcVM1De1fnDo+IDUftQVy/LysirmEst1lOd+1rl+aRSCXq9ATFXYeGm5ubnU1NRw8uRJ\n8vPzgY1Ovfn5+bzzzjuKMjs0NKS0vrx4MXm3q0nNCS9msE3Xyvo1k5KSyM3N5ciRI5w8eZJz586x\ntrbGJ598wieffEJzc3NMCqoOUu0FR8JsZemLWActRVGIgpLv6yZtJBLBarVSUVFBRUWFQuf9fj8d\nHR1MTU0pDCRWtey9FLPVoxODxNLyer00NTXh8XjweDxcvHiR06dPc/r0aebm5ujq6lLKVRSt2c2M\nJU/7ufmZI5HHtTBjzYeuyCORiKKW6yIH22bX34l1AC+RQhDRtaQASCdPnuTEiRNkZWUxNzfHwMAA\n4XCYzMxMDh8+zNjYmFqMQrwRV0GUw7MgybE+181okcTERKxWKykpKeTn51NXV8fp06c5cuQIeXl5\nNDU18emnn9LS0sL09HSUS7AZgKiDSNs50bcS86Ixm5wQfWrpz7m+vq6SnYqLi8nKylIJWpOTk0xM\nTODz+ZTZDvtXz0EPq4qYyUXy/mdmZlRb94KCAl599VWqqqqora3FYrGoEKwAc9sZ807m/2m/o//c\nXClcDkdzSFOXna6Ll0YhyAkpL39tbY3k5GSqq6t57733OHz4MAsLC3z22We0tLRgtVp54403VM0E\np9OJYRjcvn0bt9tNJBJRpth2XrycmrH8yc2yEu12O/n5+VRVVXH48GG1+NLT05menqalpYWrV6+q\nnAqr1arcBP2EENNeLCTJg9jLEKlZYi0omQOZf5fLxcGDB8nPz1fZg6OjowwODqpionpJcv06e2kp\nSEKWYTzu1CxRA9090q2VqakppqenWVxcJD09XeVzSMj0Rax5qCvlWBwHfV53OvaXRiHoWlFe8qFD\nh/jBD36gQEQJLTY3N2O321UZ9IqKCurq6lTyyPT0tPLhJJNQB+228sfNp6ge+YAN18DpdJKfn8/h\nw4c5fvw4OTk5ZGVlqVO0tbWVq1evcv36dTwej8IzZCyiBHTEWMcJ9AIc+6UQ5Jkhdv3JSCSC0+lU\nGZqJiYlEIhEmJibo7u5WyLkZ9NqpKbuVyNwL8CaiE8N0l2ttbU25CDdu3KChoQG73U5DQwOtra1M\nTEyod7AVRvM8RNbadjkozyovjUKQDSuxZqfTyYkTJ7h48SLBYFCF7Zqbm+np6cFmsynl8Qd/8AdU\nVFRw5swZenp6GBgYUKizTK5o3a0m0bwoRFvruIbUWjh58iSnT5/m5MmTJCcnK8785OQks7OzDAwM\nEAwGycrKIi0tjYWFBVVWDaJbvcm9Jd6uj3U/FqqZHq2f8DoNOzs7m5qaGhwOh3o3U1NT9PT0KPq4\n/P5+iozJ7GrpoKu8Z3El5GAYHh5W5KXy8nKVXKTTtl+kykaSLPU0cPZrbyHICWq32xUl+dy5c6Sm\npvLhhx/y8ccfc/fuXebn5zEMg1AoRGdnp4o+rK+vc/ToUU6fPo3P5+NnP/tZVK3Dp/mMscJmuqYW\nk7SyspLz58/z9ttvk5WVxfLysiq3brVaKSgoIC0tjfLycgYHBxkcHGRlZYWuri4++ugj5ubmVOUi\nnaCiWwmxTu69En3jy310E1U6SWVmZlJZWcnhw4dJSUlRY5menmZwcJDFxUXlYugKcz82l4CeUjRX\n518I+KkzLGFjY7lcLg4fPkx2dnZUeFTSw9fW1tS7eFFEclAkhwS2run4tQ47AuTm5tLQ0MCJEyfI\ny8vD5/Px8OFDmpubmZ6ejtqsgUCAcDhMe3s7ZWVlHD16lKqqKmZmZvjggw/UNXXiyWYTGMvc1Xn9\nck+3201vby937txR2YNOp5OkpCTi4+PJzc0lPT0dq9VKVVUVpaWlrKysqBDY2NiYSt7y+/0qDTYY\nDDI/P/8EKehZoyRPE53Cq/9fBzCtVivl5eVUVVVRVFREYmIiHo+HiYkJhoaGmJubi8rwlOvsJw9B\nxme321U6s1hdOhAqoefMzEzKysooLy8nOTmZpaUlpqenWV5ejmqj9yIpA9gIYevrAjZXCN8Il6Gw\nsJBDhw5RVlaGYRj09vbS09Oj/D4zKSQcDjM6Osro6CgrKysK7bfZbOq6AiRtVhFHxMwZF7BPgKrl\n5WXFkX/w4AGwcWqlpKSQnJys6NQHDx7EbrdTVFREWVkZkUiE6upqLl26xMjICIODg4yMjNDb20tv\nby8ej0dRWnXMQ8a0l5vMHNXQSTfy/Ha7ndraWlWOLhgMMjk5qZiW0g1JVwB6hGKvRVyG+Ph4cnJy\nFHVdsizNTEO73U5VVRXV1dXk5eWxtLSE1+tVbqTUQdSzCWUOnrcsLS3h9/uZn5+Pah4MT65P+AZY\nCEtLS8zPzyvc4P3332doaEidAOYTLlYIT5dIJBJVzXgz0WPzssjNJ4iAkouLi0xNTSkga2FhQYFb\nY2NjXL9+nYyMDFJSUlRDkYKCAhwOB9nZ2Rw6dIjy8nKOHj2Kx+NRxUimpqaYnZ1VfwYGBujr69vT\nE1dXpqLw9Oe02+1kZWVRXl6Oy7XRpU+U7gcffMDAwEDUtXQXQY847LWV4HA4KCoq4p133uH48eMs\nLS3x8ccfMzg4GBUZkupDb775JvX19SwsLNDU1MSNGzeYnp5WJ69wEfYTq9mJSBQq1ubX5RvBQxBg\nTRaV2+2mvb1dgXGRyONmnisrK8THx5OSkkJ6ejopKSkYhqE2ls5LlxNmuxmEIrLg9VNVlIDf71fj\nlXutrKwwMzOjqhcLSaq/v5+CggJSUlKorq6mtLQUh8OhUmCtVivr6+ssLCwoa2FiYoK7d++yurrK\n1NTUniUQxVKeOlmpuLiYI0eOUFdXR3Z2Nuvr64r70draqrIH5ffEtZH3t19isVjIycnh8OHDnDt3\njvn5eUZGRsjKysLv97O2tobVaiU1NZXa2loaGxvJy8tTZKUHDx6oBj/CwNTzEV6UEKROwNI/i/W9\nnciuFIJhGP8j8KfAOtDKRqOWPOCngBNoAv7byEZn6F2JbD5Jc01NTcXpdOJ0OnG73WrTSVpoOBxW\nzVarqqooLCwkLi6OwcFBHj58+MQGkqQRnRpsvv/Tklv0Ba+fjHoPBqGdzs7OqhJln3/+uRpDSkoK\nOTk5NDQ0UFNTQ2VlJRUVFaqEVnl5Oaurq8zPz6v4/29+85uok3k3oi84/Zlk3o8fP87v/d7vcfTo\nUVwuF2tra/T29tLV1aU2njmWb45Q7IeFIApdiGBxcXGKAzIyMsL6+jq5ubkUFRXxyiuvUF5ejsVi\nYXR0lNbWVlWPU8afnJysqhq9SCKHiIC8W4XJd3T9nQ7MMIw84M+BmkgksmIYxt8DfwS8DfynSCTy\nvmEY/xcbCuP/2el9TPdUnHTJdf+zP/szxsbG8Pl8hMNhVfJrdXUVh8OhfMrc3FyCwSBNTU1cu3aN\n+fn5KE4+sO2iGOYFvZm21kE/IKp+4/r6urqfvFgpIru4uKh6RmRkZJCVlaX6Esr9DMNgfHycnp4e\nPB7P7ifX9Hw6XXl9fR2bzYbT6aSuro6jR4/idDoVEPfFF19w7969J7I0dXzGDFLu9XilkGlbWxul\npaVkZ2dz5MgRkpKSmJiYYH19naysLJxOJxkZGdhsNh48eMAHH3ygrAOLxaLeifBUZPwvitsgERCJ\nXOml/eFJUPiZr7/L8R0A7IZhrAM2YAJ4gw3FAPAT4H9hDxSCLNLJyUmam5tpamri2LFjvPHGG8qv\nWl5ejioIarfbVVkvr9dLV1cXt2/fpqmpiWAwqBQCEOVn7nR8sV6MbPZYFGTR7nqVYokx+3w+ent7\nAbDZbFFYh5TckrDYXos+bllYDoeD+vp6Dh48SGlpKevr60xNTamCLpIHoP+ezgPYT5PbMAyWlpYY\nGxvj7t27OBwOGhoayMnJ4eTJkywsLBAXF6fcNPnu9evX+dWvfsXs7CwrKyuqkIrMq5789SIoA8Mw\nlAWUkpKiulWbcSwzJ+NZZDfNXicMw/hPbPRvXAQ+YcNF8EUiERnhGBsuxK5FThtpxfaTn/yE3t5e\nzp8/T0NDA7m5uU/k/svpPDg4yN27d7l58yYPHz5UteyFe/CsE2f+/lbMRh2T0Psr6NcwZ1mar2+O\nfugn2H6IuEc6D6GyspJ/82/+DYcPH1ZuT2dnJ1euXFEFVGVs+jjNodz94k7InNy8eVORjUpLSykp\nKSEzM5PU1FSlWKempvj4449VlWYh+eh5DDoeJHPyPEUOxNTUVFZXV8nIyCApKQm/3x/1PVHCX3mB\nFMMw0oB3gWLAD7wPvBXjq3s2k6K9FxYWVMNMaYCRnp4eBWbpL7Wvr4+enh66u7vxer1RloCeM7Af\nsp3N8LR7x/q9r4KyLJaCIPiHDh0iLS1NRVHa2tpUbshOn20vRFeybrdbsRD7+/vJysoiPT1d8UDW\n1zc6SrW1tTE7O6uqJZkB4q9q7NuVtbWNmp+GYZCSkkJubi5Op5Pp6eknlPBuZDcuw0VgIBKJeAAM\nw/j/gNNAmmEYcY+shAI23Ihdi/jYIsFgkPb2djo6OjbldusJQfJzM+1Xn8CdFpX4OopwBqQASnFx\nMWlpaRw4cACv10t3dzdtbW10dnY+9/nS7y8n/eLiIhMTG0tPBzJlDYjLFasGRiwCGjxfHoIUxF1e\nXsZisSiCm7mXiLlPw1fJQxgBThmGYQWWgQvAXSCDjRbwfw/8C+Afd3GPKNF9cfm/mUFoRl8FJNLp\nvrFYh2KSvYhZbl+1SLhW3KrLly/zzjvvYLVaVYOXzz77jLa2thdirgS8Na8NnTNittSE5qzLZmDn\nfpCpnlWEkVtQUEBOTo7KJl1bWyMxMRHDMKLyG4Rt+bQmM2bZDYZwxzCMnwMPgNVHf/+/wK+BnxqG\n8b8++uyvdnoPs+gugfytU3j170B00RL9+9/K9iQubqPhSX5+Prm5ucTFxaky8bdv32Z4ePh5DzFK\nniWkuVUlqRdxjXi9Xu7du6dqUHR2dkaVfBPZLRvUeF4PbxjGM91Yipmsra09USwiISFBbXy9mITU\nO9C16aN7R1U9+laeFEG0MzMz+eEPf8hbb73F8ePH+dGPfsTf/M3f0NraqshXL7qYQ52xDobNKmEB\nUZGo5yWSym2z2YiPj1c9TM0YmHAUnlb0JxKJxNQaL41C0GPj5o2sa0Xd5DfnGphZeFtZDLoJ+k1y\nI/RTMjExkeTkZCorKykuLiYnJ4f29nY6OzsVGWw7CUvm0zdWeHYvrbfNkn100UvEyc/1lPO9yAt4\nFpFsWamNIWOJVYxHxmJ+Pj2MvlWi3qPff7kVgojehHO/XABZHLJYX8Sst/0SvSJVrI7Neqq42dLa\nSrnGqmytczP2ylrbSvno49EzGs3j+CosR7NrI3U+pHiqEKJilbDfTOHFKsm+mXxtFMKj340KLcLe\n4gPm0+SbYh0AqkSaLMRY/qg+1+YaAzuVr+IUNm98cyky4V/oBVf2axy6BaCPSy/HFysiFgs41a8r\n8rQuZJsphJcquUnEHCfXQUP5XNf25knUxWyCmYGpbxreIItOn1PzYhVTWxasmSqrfxdi97vQT7Pn\nCfbq1o2+BmKd0Ht5T/1eEO0Sy3j0d6HPkfn39Gvqn+0EXHypFEIsnoCZYquHoPSFq0+O+bsQnbko\n95GNINp2v/o2vEiyGetSd6NkzgXoMm942VD6YtV9YTHZ9Xe03/Uh9WeRMUB0Bq15fGYAey/FnOgV\nFxenAHC93L15vcdyt/bU5XpZXAZZfLo/ry/OzQAk86kfK/Zs/plZs25mXXxdRTdp9bk1n/q68oyl\nqEVizbsOEJstvP0WGbdUa5ZNqFubuoWQkJAAbN3KbTdjEeUpilPWWUJCAhaLRUXO9KYs+lrVrTR5\nX09zwV56l8Fs0seaGH0RmpXEZmap+TOd4fW8zdnnKbHMzlhKczOmZyzlGQub2a/cBv0eZtnuu9U3\n1l6LrnD1mpDw+PATtwqi3TA98hVrX+xmzb5UCkHq9JlPMJks4SNAdCKR+Tq66MrFMAx1Db3b0DdN\ndPcJYiP3+uKUdyBMz1hglp5qbhiGOvmeVrbuWcR8WGylbITFp4fn9GcTsFFAxr08FGSdyXX1JrtS\nlyM5OZmVlRUCgUDUmMyhd92qkOfW63w+89heFpdB+70nimZCNHYgk2R+NjPAaAZ25DrmKIaO8n5T\nRJ8TocaKu2ZGu80Ygz7/seYcnuQB7NVYddlsbethR/MhI5vLnCOw1fWeVTIzM7lw4QLl5eXY7XZ+\n/vOf09bWpsYiJe2BKHxFV3h6QlcsK/lp8/rSuwwiujLQwUEgKu/ebPrDY39NZ57pvyOmmPxbbxYK\n3wwMIZbvqWMH+vyaTX4BGmNhO2blG8sf16MbOxn309wUXTkJHqU/o36yxsJI9kqcTidvvfUWZ8+e\nxel00t3dzcDAgCraYxiGqu0hikvGoleh0gvw6GPcDllsM3mpFIJuypm79MLjugEHDhxQvRgEMILH\nZcCk36BUJ5KFYQbSRDvvlx/5IopuKsuCks2rm7hJSUmEw2GVkis/j3Wi6gtTFLI56UyP5jyr4t3K\nEohltcRKbooVbZBeGkIT3iux2WxUVFSQm5vL2toaJ0+eZGpqiqtXr5KYmIjFYlFt42Wc0ok6FAqp\nz8S9WFpa2jPX9qVSCDpgJQvTYrGQlZWlqt3IxOXn55OYmBhlFiYmJpKamqrali8uLjI/P69KfyUk\nJBAKhVTDUrfbjc/n+0aBivqpH8slkD6I2dnZhEIhZmZmVIWhhYUFlpaWojaPnMiJiYmq41ZGRgY5\nOTmEQiGmpqaYmppSXZZ3OtfmKFN8fDyJiYnK3ZEy+aKIdCWvk5NKSkooKyujsLAQu93O6uqqKi8v\nTWJ3K3FxcaoE2urqKtXV1Zw6dUoVvTEX+5X5TExMZGRkhImJiSjimP4s5v8/q7zwCkHMItH2ehFV\nq9WKw+GgsrKSzMxMEhMTsdvtuFwuamtrSUtLU92dJQc+LS0Nu90OoBp56FrY6/UyMjLC3bt3aWpq\nwufz7evzxTJp9f/H+r5uLuqLWZTfbmLn5l4EoggSExOx2WzU1tZSV1dHeXk58/PzDA4OEgqF8Hq9\nTExM4PF4CAaDUYDkgQMHSElJITs7m8LCQqqrqzlz5oyqeHz9+nV6e3uZn5/f0YaLhU+kpqaSmpqq\nNvXi4qIqAisYgVgFcrAkJiZy6tQpLl++zPnz50lOTlbNW6SYyl4oBB2TiouLo7i4mFOnTpGSksLC\nwgJra2skJSVhtVpJSEggEAgQCoUIh8Pcu3ePcDgcpZzMCkGPtj2rvDAKQbS6bnbabDbVq6C4uJiK\nigpKSkpIT08nGAyq6riZmZmq4IW8WECZX9JWTEqxi1gsFqU05BSRngONjY383d/9HV1dXVEm506f\nDZ48xSQbU669urqqFoGYi1KxWfIKbDYbdrud9PR0SkpKqKioICMjA4C5uTk+/fRTHj58qKyjnZCp\nhCQjGEtubi6HDh3i3LlzVFZWUlBQELXRpEvWzMyMaiBisVhUrkAkEiE5OZmcnBzS0tKUlRAKhcjL\ny6Ojo4P29vYncAuz727GGHTUXe4VF7fRX/PChQscP36csrIy7ty5w71797h3755S/maXyOVyceTI\nEb7zne9w4sQJrFYrhmGQlJTEysrKnpes03NDcnJylKUrIUeILvAjf958803Vkay3t5f79+9z48YN\nxsbG1LzpbtKzynNVCFuFR8SsSk9Pp7CwkLq6OtW+LTk5mUAgoJSIZIjBBi7g9/uZmJhgbW2NhIQE\nhS3YbDYVRtIXnCSWOBwOZS6urKyQnZ2962eMhbCLOJ1OSkpKyM7OVoorJSUFq9WqTPCFhQX1nBaL\nhdTUVNLS0khPT6e4uJjS0lISExOZn59nYGCA1NRUNX87XcAJCQm4XC4cDofqFXH8+HHeeOMNsrOz\nSUlJeeJ3lpeXWVhYIBQKsbq6qsg2YvqK8hWL5sCBAwSDQUKhkLL49EW8mRKNNY+64sjOzqahoYHv\nfve7nDp1iuLiYlJSUpSJ7vP58Pv9zM3NqYrFdrud+vp6vve973H8+HEKCgoIh8NMTEzQ0dHB1NTU\nE9WNdys64G2327FYLKqLtn4wyvqUudSTz3p7e3G5XAwODjI+Ph7FS9CzfJ9FnqtCkM0M0X0PJE4r\nmzQ1NVW1Q5uYmFANNeRUbWlpYX5+nrS0NHVSDQ4OEgwGWV9fVxpX7xyk17ZfXV0lPz+f06dP8957\n75GVlcXY2Bizs7O7rsS8GVEkEomQn5/Pd7/7XS5dukRhYSGBQIDU1FTVl3BhYYHFxUVWVlY4cOAA\nycnJOBwOkpOTo9rP9fT0MDo6GlU0Y7sl5WOJ1WqloqKCxsZGjh49SmVlJXl5eTidTuWL67kIcjJn\nZmayurrKysoKy8vLyoWT7wmYJ+7e3Nwcg4OD+P3+mCw881ya0fNYC76hoYHLly/zxhtvkJeXR1xc\nHK+88goFBQWcOXMGt9vN8PCw6tS0trZGeXk5r732Gt///vdxOBxqfdy7d4//8l/+C/39/XvKR9HX\nRTgcVkCrYFuAqnmwsLCAw+HAYrFEcRDC4TAlJSWkpaXxy1/+Us2NvPekpCRWV1dV8dvtynNVCPok\n6yEe+ZnP52NtbQ2/38/s7CyTk5NYLBaWlpbo7+9X5qrb7VYLUCbB7/crcpIAS4Il6P5tXFwcqamp\n5Obm8uqrr2Kz2ejp6eGLL76gs7NzV88nz2JGuuPi4khOTiYtLY2UlBTS0tJwuVw4nU51Eoj743K5\nVN0Bm82GYWyUynK73fT399PZ2UlXVxdDQ0NMTU2pHpc7JdPk5eVx6NAh3n33XWpqasjOziY7Oxu7\n3R51QokS0MlgejRH/ujFOqTJSCQSUd2tpqamnkD8n8YrMFsShmGQmppKXl4eZ86c4fTp06Snp7O+\nvlGJ2Wq1kpWVhcViIS8vj7KyMqqrq5Uf7nA4yM/Px+FwEIlE8Hq9TE5O0tLSQmdnp+rmtFfidrv5\nxS9+wfj4OJWVlWpNT09PK8u3qKiIzMxM0tLSohShzI1YYBaLJSrkKtiSHl17FnlhFAJEm4ThcJhA\nIEAgEGBqaoq5uTlCoRBlZWVYrVbcbjdjY2N4vV51Assi1UVPXtIBOfEP09PTKSsro7Gxkfr6etW/\n4bPPPqOnp2fXzyj3E+0uXaeKi4upqakhNzdXVQSOi4tjenoat9tNMBjkwIEDys2BDUxEoiBjY2M0\nNzdz584dhoeH8Xq9SnEIwWYnkpKSQlFREa+++irFxcXKdTOMjd4HKysryp2RMQHKWotFrBGXTcJp\n0sp8aGiIzs5O5ufngSeJY7qIhWEG0OReogxOnDhBdXU1FouFUCjEwsKCat7jcDhISEggPj6egwcP\nRrEnRZaXl/F6vdy+fZvm5mZmZmaimIR7IR6PhytXrjA9Pa3wikAgwODgIF6vl4SEBE6ePMmxY8fI\nzc2NcgVEEcr+GBsbU13IdIUhkbNnlRcGVNzqVFtfX8fhcHD8+HHOnz9PaWkpAwMD/OY3v+HKlSsq\n3BUXF0c4HI4qNKkX+ND9sLS0NE6cOMGFCxc4fPiwcke+/PJLbt26RWdn5647IunNUsWPrqys5OjR\no5w/f56amhoKCgpUrX2v18vvfvc7bty4gcfjURaO/C2+9vLyMsFgEJ/Pp74nkQUBJQWtflYZGRmh\ntbWV2dlZCgoKSE5Ojio+297eTnt7O3NzcwSDQaUExKqRUJ9YBktLS6oRzdraGp2dnQwNDannCgaD\neDyemCSgzdaCiCiEtLQ06uvree+996isrFRKZW1tjWAwyODgIPHx8RQVFSl/PBgMKrdUxibuayAQ\n4MMPP6SpqQnY+9JpS0tL9PX1MTMzw/Xr19VzidskPRdycnKoqqpSh4WMRQrd3r59m9/97ncMDQ2p\ntbFbuv1zBxUhuq6+iB5ai0Q2uhYNDw8zMjJCdnY29fX1qpdfc3MzfX19TE9PR5m0Otl0jq0lAAAg\nAElEQVREQkuVlZVUVVVRWlqKy+UiOTmZ8fFx3G43ra2tdHR00N/fr07c3YgeXnK5XBw9elRp/rq6\nOpxOJ3FxcQwNDdHf3097ezu3bt2io6ODYDDIyspKVHanLFxBnOXaZsWzG+59UlISaWlpqnVcKBTC\nZrPh8Xhob2/n2rVrNDc34/f7WVxcZHl5Oepd6fRaGacexRFsRn/fOiM0Ft5izpwUiY+Px+FwcP78\neb773e9SX1+P3W5nbW2NmZkZ+vr6aGlpYXBwkOXlZdWwxWq1Kh/84MGDOJ1ObDYbBw4cwO12Mzg4\nSH9/P263e0dz+DQRLEXCmXrEQdZ0aWkp+fn56tml6/m9e/doa2vD6/XS09Oj/m2uGL7TjlPPVSHo\nplisZBjxQ8Wvu379ujI5//k//+e8+uqrVFVV8fOf/5y1tTVmZ2ejuN6ywCRU53A4ePPNN3n77bep\nrq6mq6uLjz/+mIcPH9Ld3c3Q0NCmbgw8O5dd5/0XFRXxh3/4h7z22mtUVVUBEAqFcLvdNDU18bvf\n/Y4PP/wQr9f7RHs2WSj6SSyKQBrGyufCQ9ipQsjNzaW6upqcnBwSEhKYn58nISGBmZkZPvvsM65d\nu0Z7e7sKi4pCkJ6DUgJM5k73f3Vasz4+wRVilQvTFY3MpVwrKSmJ7Oxs3n33XS5evEhaWhqRSIT5\n+XmGh4e5du0aH374IX19fczNzREOh9VaSEpK4sKFCxw4cIDq6mqys7OxWq2Mj4/T3t6+JwfCZiLz\nBdGHoShQi8XCmTNnlFuztrbG/Pw8fX19/PjHP+Yf/uEfonAUm832RA5OrMI125EXAkPQLQFZPGaS\njZhN7e3teDwehoeHuXTpEhcvXuQP/uAPFMLd39+Px+PBarVisVhwOBz83u/9HkeOHCE7O5v09HTW\n1tb42c9+xp07d7h//z7Ly8sEAoEohp7OctxN1V0xAQsLCyktLSUlJUW5LYmJiaSlpZGRkYHT6VSm\ntc4DEHdBB9H0cK1YT7oClM93ImLmr6yskJCQoKyYlJQUGhoalIJYX19nYmKCgYEBdTKZLRP9fZoJ\nM/o49eiSedz674v1kJiYSHZ2NqWlpRw8eJDCwkJsNhvhcFiZzoODgwpwXV5eVutLgFDBjwRMBJRy\nvn37NisrK1FcjL10G2Tzi2Wnpzmvrq6ytLTEwMAAubm55OTkYBgGfr+fBw8eMDs7q1ifKysrKgol\nc6XP6UuHIegb0AwkmR9GfLzp6Wnm5ubwer0kJydTXl5OYWEhJ0+eZHBwkISEBMbHxykuLsblcpGV\nlcWbb75JWVkZkUiE2dlZZRm0tLQwOjpKUlJSTFN1L0Sey+/309rayvT0NJmZmRQUFJCVlYXD4VAt\n66uqqlhdXWVqauqJTa+bgnrYSvcZ5aTdaWILbLA3Z2dn8fl85OfnY7fbCYfD2O12ysvLiUQilJSU\nsL6+zvj4OAMDA8qcnZubY3p6Gr/fHwXgyvg2G5Pki2xW9Vh/fsMwsNlsFBYWcuTIEV599VXy8/MV\nmWtoaIiOjg5u3rxJR0cHbrdbAZ/itiQmJnLw4EHq6urIzs4mKSmJYDDIyMgI3d3d9Pb27mvvTIhO\nBNPnxjA2Olk3NzcrhSAub0pKCna7HavVGqVc9bnSi+Dui0IwDOOvgHeA6Ugk0vDoMycbnZmKgSHg\nvUgk4n/0s/+DjR6PQeCHkUik+Wn3iKV9dWqumD5iShuGwezsLDdu3ODAgQO899575Obm8vbbb2Oz\n2ZicnOStt95SYbNQKMTAwABffvklfX199PX10draitfrBVBNPkUkvq//f6cSiUTweDx88cUXPHjw\nAKvVSmFhIf/sn/0zxYqrqqoiEokQCAQIBoNMT09H1dwX0X11c90BOfUEnNqsHsTTZHZ2loGBASYm\nJigqKsJut2MYhmoQUlxcjMViUfkLoVCI+fl5Ojo6+Pjjj7l58yZ+v1+dxNJt2XzKxooGieVhzt7T\n5cCBA9jtdoqLizl27Bjf+c53FAM1Eonwm9/8hvfff5++vj4FCusZrMKifPfdd3nttdfIzMxUIe6u\nri4VuRIMZz9F3pXOzo2PjycYDHL16lUKCws5ffo0a2trZGdnc/nyZTo6Orh37x5+v19ZVmLBhsNh\nRWySkPyzynYshB8B/yfw19pnfwn8NhKJ/EfDMP498D8Bf2kYxltAeSQSqTQM4yTwfwOnNrvwVvRK\n80knC0RMv1AoxPDwMBaLhcbGRlwuF+Xl5YrUU1JSQiAQ4PPPP6ezs5Oenh76+/uZm5vD4/GwsLAQ\n5aea/S3RygkJCTE353ZFxi1x4UAgwNLSEr/61a+YmJigv7+f1157DZfLxbFjx2hubqa9vX3TF6rj\nB3IS6ApTP113Ql8Nh8PMzc3x5ZdfkpycTGpqqqKAp6amYrFYlCVis9lITk5WoFxycrLyZ0dGRpRS\nktNffx7d15VnEuwjVhakjE38bwnfpqamYhgGMzMzdHZ2cu/ePbq6uvD7/VGmtGBShw8f5vz58xw6\ndIiMjAw1Dq/Xy927dxkYGFAhX3n3ZvB7L0QsA3l2Gd/6+jrBYJD+/n6Fa6Wnp2Oz2bBarTQ2NjI+\nPs7Vq1dxu91PKE9Zqzsd61MVQiQS+cIwjGLTx+8C5x79+yfAZ2woiXd5pDgikchtwzAchmFkRyKR\n6VjX1gFA/bNHv79p1EFPthEyEoDL5SIzM5NgMMjk5CRNTU18/vnnNDU1MTo6qhJE5AWYx2G+v7yk\nrZKFzCQZ/d/iH+ox4XA4jMfj4e7du0xNTTE+Pk5eXh5Hjhyhurqa8vJysrOzGRkZYWVl5YlNLQpA\nkHsRCeOJPEuCix4dWF9fx+/3c/PmTUWaEmISEEUuklPdZrNhs9nIzMzE7/fj9XqZnZ1VSU5CUDLH\n03U8RBSCzL0+v/K78jMz/rCysqLC0BIyNWMZcXFx2O12GhsbuXTpEsXFxSqF2+v1MjAwQFNTE2Nj\nY8qK0BO89ktkHuQ5RbFPT0/T3t7Ol19+yfHjxykqKsJisdDQ0EAwGGRsbIzV1VV8Pl8UiLzborA7\nxRCyZJNHIpEpwzCyHn2eD4xq3xt/9NmmCsHcCEQvfKmf4KKxBSmuqanh7bffVoBicnIysNEDr62t\njZ/85Ce0tLQwNTWliDBm2quIbDKzEjKbc2aRcen1FHQTPj09nfT0dMbHxxVoqT+Tx+OhtbWV3t5e\nSh7lNNTW1nL48GHcbrfiVuhhR/n30wBEs19pfmYdkbZarYrNKW5AW1sbPp+PlpYWXn/9dUpLS0lI\nSKCmpobCwkIFtopiEqCsrKyMo0ePcvPmTdxudxSAZrVaVShVxmguYWYGTc3PKq6Kx+NhdHSUvr4+\nlpeXuXv3Lr/4xS9wu91YLBalHMW9stls5OXlUVFRQXl5uYpera2t8fnnn3PlyhU6OztZWlpS+S8y\nX3vNQ5BnFYUqa0zWvCigO3fuMD09zZ/92Z8pKnZeXh6NjY0MDg4SDoe5c+dOzOvrtT2eRfYaVIyl\nSje1WXXuddRFHi3ScDisiC9S56Curo66ujqqq6s5dOgQTqeToaEhwuEw2dnZalF3dHTQ1dW1bT8w\n1qYyg1mxKKQ6ey4SeUyDPXXqFPHx8czOzjI/P08gEHgCNFtaWsLr9dLZ2UlxcbHKCKytraWpqUlR\na4X6az71dPQ9lugsSVn85p9bLBbOnTtHYWEhy8vLNDc309PTw+LiIiMjI8zPzzM/P4/L5SI+Pp6q\nqirKy8vJysqitLSU0tJSdUJZrVaSkpKU2yDhUp0TYnYfzGPfDFzWWYXBYJDu7m4ikQjDw8Osra3R\n19fHyMiIoobrp24kEiErK4s33niD+vp6MjIyVELY+Pg49+7do7W1VTEmzTH9/RIdN9Hfpzy3z+dj\neXmZW7du4XK5yM3NVfUWJclsM/dwpyD5ThXCtLgChmHkADOPPh8DCrXvFQATm11ER6D1DSbJGSsr\nK1E8fpfLxeXLl7l8+TJpaWn4fD5aW1v54osvWF9f58SJE5SXlytwba8TUsR90C0K8ecBlT792muv\n8Rd/8RfMzMzwy1/+ktbWVuBxaW89nLq6ukpPTw9FRUWUlJSQnJxMUVERaWlpeDwe9V0zySSWmxJr\nfvUkJF1k8SUlJfHuu+9y+vRp/H4/P/nJT1Qas0R1JiY2XuGBAwfIzs5WyUBxcXGUlJSoZxFS0MLC\ngspdkCxOATrFAtwsEqJvCn3cOuFscXGRjo4Ouru7FXApUSj5vigjUQiFhYW8++67HDx4UFmTbreb\nBw8e0NLSopQJPFmxe78wBHGB9ec0SzgcpqmpicLCQi5duqQOUamXoLu/+jX2DUOQ8RN9+v8T8EPg\nPzz6+x+1z/8d8PeGYZwCfJvhB/Ak68xms6mqNrKoYGPySkpK+MM//ENqa2txu9189tlnPHz4kPb2\ndtxuN/n5+WRkZOByuUhNTeX48eOEQiG6u7u3+Yhbi7wIUQz6aacvoJqaGk6cOAHA8PAwLS0tqkuy\nxMPF9ZEYt1RyyszMZGxsTBFpZA7kXuZsv2cZs06GAaIWv6TeJicnc+nSJWw2G1euXFGVeSTJSiyD\nkpISTp48SXFxcdQpvL6+zsjICJ2dnVGl6WKZ/1tZNXpYFR67biL6BhAXRLIF9UrKYrnotSOkDBnA\n6Ogod+/eZXR0VOUD6NiLbpXstbUgh6GMRawSPQNX5mtkZIShoSGCwSAOh4OcnBzOnTtHf38/H330\nURQuJslmO40ybSfs+LfAeSDDMIwR4H8G/jfgfcMw/gQYAX4AEIlEfm0YxtuGYfSxEXb8l1tdW/yo\nR/eJshIE5U9JSaGmpobGxkbq6upUPP/GjRu0tbUxMDCgTujJyUlWVlbIysqipqZGIbV7JTq6r49X\nN/esVqsiySQmJpKbm4vf78dqtap0bHhc91HqGrhcLux2O8vLy3g8nig3Qe6jc/23s0D1yIzMsYgA\niGtra0r55ObmcvToUQW2CXAlRKDa2locDgdZWVlUV1crkldcXBzBYJDZ2Vna2tqiMgRlc+pj2Grs\nOshmXg/y+7rCEFdIB4XlZ3FxcVgsFmpqaqivr8flcqk8j/HxcR4+fEhzczOzs7NR0QR9DPq49lr0\nZ7JYLNjtdiorK7Hb7dy5c0e5MIFAQFWTEqtLQFy5jnnedgqEbifK8N9s8qOLm3z/v9vuzUWjyUud\nn59XJ6GYs3l5efzxH/8xdXV1uN1uPvroI65fv65KWsHjPoGBQABA+fHp6enbHcq2RSZfrAS9tt2B\nAweYmpqiv7+f2tpaDh06RFZWFrdu3aK1tZWhoSE8Hg/hcBiXy6XScMvKyigoKFDPLVmOSUlJio5s\nXqTPskBlocdCoMPhMG1tbZSXl1NSUqIsrcOHDysa8srKChaLhYyMDGXyyzgEkZ+bm+PatWvcunWL\nrq4uRewRxS5/npZ8I5aGTlnW8znMLoTMfSQSYXFxMYqnkZiYSHp6OufOnePVV19VMfqlpSWuXbvG\n1atXaWtrU9EQPQQqync3IbytZH19o/6nAJiCj/2rf/WvKCws5N/+239LZ2enencJCQlYrVZljUl0\nRY8wiALervKNJc+VqWiecHOCS3l5Od/97nc5cuQIq6urfP7557S0tCjijm5SzszMcPfuXU6cOKF8\ncb3gxF6IjhuI4oLo5pwjIyPcv3+fgoICamtrKSgo4I033uCVV17B7/erwi52ux2n04nT6SQpKYnk\n5GQFljU3N6ucBrmuKATdjdLncTvjNn8mhUj7+/tpbm6msrKS3NxcVbVJzG/5roTixFSXOfD5fPT3\n93Pr1i2Gh4dVfoM+X+Z5eproJ79+kpp/Zv5cd2HE4jl27JjCOhYWFhgcHOTatWu0trYSDAbV78la\nlOeKBcTuhQhIDqhqX6Wlpfzpn/4pJ0+eJBAIqKhPXFwcDQ0NHDlyRFnCKysrqn6lGdTW989XCSru\niegvVn+R8iB5eXmcOHGCjIwM2tvbuXnzJqOjo8oX1ydifn6e3t5eJicn1Umx13nsci/5O9aYZ2Zm\naG9vJzMzk1AoxMGDB3G5XCoCIjUfJVV7eXlZ1TgYGhriwYMHdHR0qDClOdRoNgefdgpspgxk7IZh\nMDIyQnNzM0VFRZw4cYLKykpFkdb9Uv164v8uLi4yNDSkitJOTU2puhT6vfWFu5XoJDF93LHMYDMA\nqbtzFouF4uJiTp8+TU1NjXof4+PjtLW18eDBA0ZGRtRJLZaIXFOf951YZVuJrnAEwykpKeHtt98m\nLS2N1tZW4uPjVe3M119/ncbGxiiewtjYmArrmse7U2UAL4BCgI0cfthI8ZTTSGr3S3poe3s7Y2Nj\nrKysKPBRJkBISuK/wwYfQYp47PV4ZUPIOAUMEs78zMwMV65c4bPPPsPhcHDkyBHy8/NVWmteXh6J\niYnMzc0xOjrKwsICY2NjKhknEAgok9disSj2mX4qPg2c08esR3J0PEJOzJWVFZqamhTVNysri+Tk\nZNVsVGccJiYmEolECAaDPHz4kBs3btDS0qLKuAl2oI9Nz9aUMW1WwEMUuTlcrLtMujsh7oGMTa7r\ndDqpqanhzJkzpKenEw6HWVlZ4eHDh3z++ed4vd4ofof+fs1zJX08zFmoO5X19Y3itwImO51OXC6X\nAk/FJZXq1O+88w4NDQ1q7peWlhgfH8fr9UYpXb324k4zXp97TUUzghzLpFxYWFDmtiDKepx4fX2d\nlJQUamtryc/PJxKJ0N3dzejoKPshurugRxskeiDNNDwejyIlSdGLzMxMVblnYWGBubk5FhcXmZub\nY2JiQpmw+vUl5Ki/YPmObIhYL18WdaxYtb5pDxw4gM/no729nQ8//JDFxUUOHjxIbm4uDodDVX9e\nXl5mZmaG6elpxsfH6e3tpauri+HhYQWESt0JHfcwm/hbyWYKTP+5jN/swonStNlslJSUqLoXEn1Y\nWFhgaGiI3t5e5dZs5haY19deiz72wsJCiouLleWYkZHBu+++S2JiIg0NDdTW1uJ0OgEYGhri4cOH\nXL16VVX0ijUnYk08b2LSM4lsIL3IhjyEvBCZJHh8qunpsrIpXC4Xr7/+OsXFxYpgMzg4uOdj1s1o\niX0nJiaqeLj4hEL1lZTswcFBkpKSnqghoJ+GevltWSyS2iyib3wzKBtrrGbKsPk6OpgWCAS4cuUK\nLS0tXL58mUOHDpGfn682k8fj4fbt29y/f5/h4WF1YsrmF5zBHKp7Fj/cHF4016PcDIPQlZ0cDtKv\nY21to3KS2+1mfHycyclJFR0RJWKeGx2A3eskJ3n3wrrMy8ujpKREFWnJzc3lX//rf63IePAYMGxp\naeGDDz7go48+Ynp6Ospq1QFuwSBeKoUgiKgsVj2sFw6HmZ2dpb29ncbGRhU10KnC0niloaGB06dP\n8+abbzI9PU1TUxNDQ0N77jLA41NLD6fJeKWIa0JCgtrIOtCjlzqD6EaeEB0F0F+03FcwEbPS3Ipa\nbW6qqlsV8n8xs+W5pqam+O1vf8utW7eUchLF7ff7o7osmVFuURJmJqJuOTyt8IjZApPr6BELeW6d\no3HgwAFcLhf19fWcO3dOZZEuLy8zNjbGtWvXVGk8Cevqc6UrTZ3tuNesRfO86QQlWStS2k3+Pzo6\nyu3bt/nkk0/48ssv8Xq9Kj9DWrnpHIqXsh5CrPixbiLOzc3R2dlJTk4OcXFxHD16VCkNWexWq5VD\nhw5RVlbG4uIiDx484OrVq0xOTu6Zz2cW/UTWN5eUC5NT3/xCdJp2LP9/K20ey9x+GgquK6OtRBa8\nLP5AIEB3d7cKeeq+v7lZrpl0pJv7scDMZ5HtRiTk2nFxcVRUVHD69GkOHz6sagkEAgGGhoa4du0a\nAwMDMUuT7+WG347oQPHU1BTDw8NMT0+Tnp6u6h3ICT85Ocn9+/f51a9+xf3791Ueg0400+WlBhV1\nLZmYmKjKSAGqAnIkEqG+vp7vf//7FBQUqLZtUpRjbW2jVp8Uxuzp6dnz0tki5mua/bTNTsDdhrB2\n4g/Givmbr2PGb+RvXZnqi0t/P2aJ5ZLo99lub8St5irWM+kuUUNDA2+++aaq5bC+vo7X66W7u5tr\n164pss9m4xbZj7UT656rq6vcvXuXxMREKioqeOWVV8jPz1fdnyORCPfv3+fXv/41H3zwQVTxXHO5\nvL0Y83MvsqqfmOYTZ2lpCbfbjWFslJAaHBwkIyND5cDPz88r00l+PjMzQygUesLk/Faev+zXKWxu\nxVdWVobNZmNhYYHJyUk+/PBDrl69SjAYfCHWg/AQJBoQDAbp6Ojgr//6r/n1r3+tQFAhUkk9j1iV\ntPd6Tl/YMuzilwcCAZVk8/DhQ1UDQUJfCwsLqgSaVD4S0OarNgO/lecjYl7LJpI+ElKZ+PPPP+f+\n/fu7rhWwV6KDimJxSTVqPZlNws5SceqrWM/P3WUws6wEYBHrQZB8McMFuBNwMRKJPGGim0Gbb+Xr\nLXohmcnJSfr6+sjPz2d6epru7m7Gx8eZn5+PAmWfp5h5GGLNCt9Dxqf3E9HB9P2UF0Ih6EpB/0x/\ngTJ5UkZLp/PGQoH3I0PtW3kxRcei7t69C2yUk5eqQ+Pj4yqi9TTuxlcpujUM0dwHPbqzH4zbzcR4\nXpNiGEbk0d9P+PviY5lDfDpybc78e94v91t5cSQ+Pp6UlBTFn9BFeBJmfsdXKeIyiAWsV28CVJam\nWMf7IZFIJGbI57krhEf/Bp4k3YjoloOEHHWXQLcyNrMMdMVjDmftNVd9K9nqXmaFJ9+LFb4zW1Vb\niVCqN1tcW/WdkDHJPc2RIX2cm/2+yH7Nr3n8OoZk7ioteMNeF8+R62/nu+ZQuzk8bM51iHV9PUwf\n61A08yrMsplCeCFAxe2GfcwWQazJlcWhsxnN1zIrh69annUBbeezZ7nGVpvUPKewfZ/b/Hvybz2c\nuZ+ib47NyE/7aRWYuRdmXo2OmZmVulkJCNFILImtrqt/tltr+YWwEHb4+yqfXNKEperSgQMHVLxZ\n6MRmi0DvTvxV4g3mLM2nvcBYhC14tnCqfoLKqS73NZ9AwgTUFaZOqNrMOtEVstxPrh8rF2O/ZCvL\nSn6+1xaCiNnC0zNuZZMLcK67BGLRSHKW3u1bulgLoLhZNqi5EtfT5IV2GbYjoi31DWyxWKJq9ump\nunoqa6wFqecLxMIl9lPMp/D/396ZBsd1XXf+dxsNoIHeiW7sG7FxExdxjyiJsrXL44xSjmyXa2qc\n5MtU5cOkUqlJ4uRDPuRDMqmayuwzNVW2x2UnHo8dzcS2LJtUJKokkZIoUiRBAMS+A43G1ujGTgBv\nPgDn8vZjNxYSDUoenCoUut/r9+5+7jn/s1yTMchEMhHldBKBvGejxWb3NBRQTZ6zS0up1Cv7RJdy\nzcmXinnZmYZQpnZqU40x62/WMRPlS5+ZKsB6fWEyXTNrt116FPO7nSGb7zaxB/md6eeQij7TKsNm\nSHYf6aB0fvxizjE5swyWPeDGzmEzkW03lXieSuUx62HPJWAn89mN1Id070m3UOW6nSEJszSv2cte\nj5na67udC9IUl4XM+u6U2mK20e4Ratf5xfXYPK3KdH2Xa2ZOTLP+9viHVPEqD9LWz42EAPfcmx0O\nh1YTZKE7HA6d99/UH0U9MFNP2UUqmfCpwrEfhiQkeiuis+mDId/NncNkhlL3dO9LZWJLdU2SoZgB\nMmZ8g2RKMs+pMCUbuxi+nj4rZW2nn4j4/ouTj/29OzXH7ZuWXZ2Ce1KAPWLXrKt9w5C5YIY0p2LG\nJn2uQcXNkLlLyWSVRSxmyVS7uylFpNsV5d52588zxe3N4AX2Z8zv6+ntm53wpohpZyj2iWgyJTNq\nU66ZprJ0wKcpPguZzGS7yJQWU/VPqr7bLNl35vXIrirY1QgTQ7BHocpJ0HamJvgC3Os7YaqpVDah\nB53HnxuGIPiA/Yh4yU1/9+7dpKPMTLLrUan0vQcJHtqIVlZWNmVHti8oe/CRfUcWMj0217PKyG/t\nkkEqVUqiScVUaXqPim+InK0o8fwiOQj4aJZp14EzgR2ksiiYY5yKMUn/bJbWY2LpmLUp3YlKIAtY\nQEUZXzkST/R+meeSOQtWY3vkeECHw5FW2n2Q9unnPy8qg32Axb5sujALiWohXNlcBALm2KUJ83DP\n7XQRNZF30x3bnDx2sMlUESA5a5L93aZIma58+TOZh13fhXtiZl5enj6DYc+ePYTDYQoLCwmHw+Tl\n5WnnnkQiwejoKH19fQwMDDA8PKxz/ZmepHbsIJOA4kYYRSqJYaM1sJFEY75PFqsJapsMSSxjsqDv\n3r2Ly+WipKSEgwcPUlJSQm5uLp2dnbS1tdHR0aHnjoyVWRfzszmOksDn1xZUdLlchEIhKisrCQaD\nxONxfYAFJFshUqkFdo4tLqG5ubn4/X68Xi/5+fkMDg4SjUZTVWHbSCbIVsVRedZ8bqPFlU5Fspvn\nJL9feXk51dXVHDhwgKKiIoLBIIWFhRQVFVFcXKyDy2A17f3ExAR9fX309vbS29tLY2MjbW1tjIyM\nMDMzo8+A3AgofVhKB96m++1GOvhm75llixprAnpZWVn4fD7y8vJ04lSv10swGGR+fp54PI7b7aa6\nuprTp09TWVlJXl4enZ2dNDY2UlpayuzsrJaCpqamiMViSZGb9rFMN+aboQ0lBKXUt4F/BoxYlnVk\n7drfAF8GFoBO4Hcty4qv3fsW8HvAEvAHlmVdSPPeLc2MiooKzp07x6uvvsqxY8fo7e3lRz/6Ed/5\nznc08CWn8gjgKGRZlhaDRWpYWlrC7XYTDoc5dOgQlZWV+P1+3nrrLe0Pn2kyAaXNLG64dxgusO4O\nkK6sdGapYDBITU0N3/jGN3j55ZcpLCzUu5hIXBJFKO+TOkuKstHRUa5evcqVK1f44IMP6OvrIxaL\naUYsiXN3MgQ5lUQg0pJ57UHwBSFzPHJycsjKytL5DDwej871Kadpl5WVcfLkSbGzEIQAACAASURB\nVKanp+nq6iI/P5+KigqOHDmCx+PRrtXRaJT+/n56e3v1adrt7e20tbXR1dWVlIxXpJLNSmAPIyF8\nF/hPrB3zvkYXgD+1LGtFKfXXwLeAbymlDgJfBQ6weq7jW0qpemsbtgWv10t9fT2VlZWUlJTgcDgo\nLy8nEAhoDjo7O6t1XvtCMbECkSIkzfv58+epra3VnDkTDEEWZE5ODm63m0AgQCgUoqCgAI/HQ25u\nLkopysrKCAQCJBIJBgcH6e7upqenR08IUxTfzMCb2IP5rElZWVn4/X5qamqoqqqiuLgYl8tFNBql\nt7dXO8YopRgdHSUWi6GUIi8vD7/fT319PcXFxZSUlHDy5El98pNSKuk4uodZdBuR6ODFxcWUlZVR\nVVVFYWEhwWAQy7KYnp5mdHSU0dFRhoeHaW9v1wf7PGydUql3SilKSko4cOAAzz77LPv27cPtduNy\nufRGtLS0RFVVlcZk8vPztUVMGL/b7aaoqEgffDMxMcHQ0BDNzc3cunWLpqYmpqam9CYoz2YshZpl\nWe8rpaps194yvn4IfGXt828C/8uyrCWgRynVDpwGPlqvjM0AIXl5eZSUlODz+fTgS+r1+fl5FhcX\nmZubS8rNL5NfJqLd1FZZWcn58+d55plnKCkpYXp6Gp/Pt1GXrEvmbiS4hNQ1Ly9P6+TFxcWUl5dT\nUVFBMBjE7XaTlZVFQ0MDRUVFTExM0NrayvXr13nnnXdobGzUAJ5p3tpqncxrcl1E2aKiIp0IdnR0\nlObmZj799FOmp6eZm5vj7t279PX1EY1GcTgceDwewuEwZ86c4bHHHtOJSRoaGkgkEkxPT+s082be\nRlNS2Wrf2ueHiOQFBQWUlJSwb98+Dh48yGOPPUZ1dTXFxcUsLS0xPj5OZ2cnkUiE9vZ2lFJ0dXUx\nPj6e9F7Ttv8gZFoNKisree6553j++eepr6/H5XJpRi5h/KbFQPpI5k5+fr4+d1O8G1dWVkgkEvpo\nusXFRZqbm/XZlMJIHmUa9t8Dfrj2uQy4YtwbXLu2Ltm9tuyDIVxPXDPj8TiRSIRIJKJTqNkBMulU\nE0gT6UHE34aGBp566inC4TDDw8NcunSJjo6OtPVMZdu1T1IZkIWFBfLy8igoKNBHqFdXV7N//34q\nKyv1cW1utzsps7To53v27OHYsWOUlpbqNPQTExN6p8jNzd2Uz4RlWdoXIp33o2kNGBoa0uc0XLt2\njVu3biV5NUqiWAHPlFJcv36d0tJSGhoaaGhoYN++ffzGb/wGi4uLdHV10d7ezsTEhNaxNyPd2LNF\n28X85eVlLZI/+eSTnDlzRqcfC4VCuFyupCQ5cqxbRUUFR48epaKigp///Oe88cYbSRaY3NxcnE5n\n0jmcG2E9ZqJXc/PZv38/X//61/F4PEm4lSzuu3fvMj8/r9UMWfCmZcfeV7Ih7N27l3g8TjweZ2Rk\nhNHRUeBeWjVzU9wKPRRDUEr9OXDXsixhCKm2rLQ1kkE2O0EmTU5OThLXdLvd1NXVUVBQwMrKCmNj\nY8RisSRmYEoEorcK0Aj39EWPx8PZs2c5ceIEoVCIeDzOrVu3+MUvfpE2dXsqE52QpLw2F1xeXh41\nNTWcOHGC48ePU1tbSygUorS0VJ85aa+fOYBiXrIsi8LCQvx+f9LElB1gs7utHWA1JYSlpSVisRht\nbW1MTk7idDrp6emhp6eHwcFBXVfJeSkOTDJuk5OTjI2NMTw8TG9vL1NTUxw/fpzi4mJ9orX5+40k\nm3QT2QTLBJmvr6/n+eef59SpU1RUVLCysqJPk4pGo4yNjekzEJeXlzlw4ACFhYWEQiECgcB90oHg\nKkqp+1LrpyPzedPSIWeM2pPYSsiz6ZAk70kkEvqsSdkw5H2yFnJycsjJyaGwsJCKioqkIwsfVv15\nYIaglPom8ArwRePyAFBhfC8HhtK9Iz8/H7fbTTweT4pPF91JvA6zs7MJh8McOXKEQCDA2NgYExMT\nTE9PJ6G6whxEnDbRbbi3s/h8Pl5++WVOnjyJw+Ggu7ubjz/+mH/6p39aN3V7uoksnnLShqysLEKh\nEMePH+fVV1/l5MmTWnQ1HXtMqUhMVqa0JLq3BLnYd2phehvp5qnumUj43bt3tVVgbm6OhYUFDToK\nyZjMz88nBdtIn8zOztLd3c3ExATZ2dnMzMxodUnMbHbHoXR9nEqCkLGDVbzA7/dz6NAhnn32WZ57\n7jkqKyuZm5ujs7OTO3fucPv2bZqbm3XCXafTyZ49e3jmmWc4duxYkhXAjCUw0+vLiWCpErumI8EA\npI+FeQrjmZ2dZWFhAZfLpRm7mTR1YGCAkZERlpeXKSgooKysTEsYc3NzeDweXC4Xy8urB9IEg0GN\nP5n4UKYdkxTG7q+Uegn4Y+Bpy7JMb6CfAn+nlPpbVlWFOuDjdC8V8R/uHecmKHQikSA7O5tQKMT5\n8+d56aWXcLlc+mSkeDyuxWdZUCJKO51OFhYWNIOQQZEIR7fbTXl5OUVFRTgcDj799FOuXr2adDyc\nney7shz5vrCwwOzsrC6nrq6Ow4cPa726oaFB4xJK3fMyk0lvRiCmSvEljGZ2dvY+1Wgz8RepmJhl\nWUkTX+ohAKCMjflOGatUdnBRS9xuN+fOnePFF18kGAzS1dWld1dzAZp2+nR9LXU3RXFZOG63m2PH\njvHss8/y4osvkpWVxfXr17l58yY3b96kvb2dyclJJicnicfjOh5genqa5uZmXC4XdXV1+oAdab+o\nDILyyxzayJIjc1dOy5Y+n5qaIhqNagxgenqa9vZ2jV0kEgnm5ub0eMqZGOPj4ywtLREKhXSWcTmw\n5eTJkxw8eFCrQHJyeDAYZHJyUvfbg0oKGzIEpdTfA88ABUqpPuAvgD8DcoCLa43/0LKs37csq1kp\n9b+BZuAu8PvrWRjsAR1mwEZ2djZlZWXs27ePl156idOnT5Odnc3o6ChtbW20trYyOjqaVow3nTTW\n2qHVk+zsbAoKCvSO19vbS19f34YDby9DJqz5XG1tLV/4whd48sknKS0t1RiBfRHZ4wvM99j1+1gs\nxuTk5KZiBdYj8xlTzxQpw2yH6WIr38Xr0lQ3ZDK7XC5KS0s5deoUp0+fZnFxkeHhYYaHh/WkF0/H\njaQZ8912/wWlFB6Ph4MHD2pHno8++oiPPvqIDz/8kLa2NoaGhpLcmWV+zM3N0dvbi9/vp7i4+L7Q\nd8uyqKmpobCwkP7+fsbHx4nH40mq6Eb9K3VfXl6mu7ubCxcu6AOGpqenaWlpob29nfHxcaampnRi\nYFFVpqamNGP2+XyEQiH27NmjD26xLAuv10tVVRUej4fS0lJqa2uTzgR9GNqMleEbKS5/d53f/xXw\nV5spXCagACGyQ7pcLoqLi3niiSd45ZVXOHnyJOXl5TidTtra2nj77be5dOkS/f39SYCZ6e4pupbL\n5dK7qzCglZUV3cHxeJxEIqFF8I2Cj2B18GSS23fohoYGzp07R3X16pH0diBS6rC4uKhFarH3z8zM\nJLmmCpOMRCIMDQ0l1U0WYjp3bduY3IeBiC5vSk52O7bUTyQKmbyQrC8vLS3h9XrZt28fx44do7a2\nlpaWFm7cuMHt27c1oi4MeKMDdMz6ithtovder5e6ujoCgQDRaJSLFy/y1ltv6UNY0jF2wZ76+vrY\nt2+fVlXNNj399NM88cQTXLp0iU8++YSmpqb7JBQ7zc/Pa+YpAPHMzAzXrl1jYGBAq0yWZRGNRpma\nmko6xtBstzlX5HxQM+OVnAgtJutAIMCBAwdob2+ns7NzU/N3PXrk5zIASYulsrKS/fv38+STT3Lw\n4EFqa2sJBoPMzc0xPDzM1atXuXr1KkNDQzpPvak/yUSXXU+OuRKmIWh4dnY27e3tvP/++/T09DA3\nN7dh6LO5uGUHlR3B9DHIz89PSuElv3M4Vo9Nm5qaYnBwkMHBQUZGRvD7/VRWVnL48GEdWShtWlxc\nZGJiglgsdp81YzO6rX3xS7+YO6gsILtTy/Lysj7lSBisTDiHw4HX66WgoECrSWfPnmVpaYmf/OQn\n3Lx5k2vXruly5F2CsaxXb2m7uYObmJAwhdnZWQYHB2lpaaGvr08zLLvHqujYcgbCwMAA165dY3h4\nWJcpFqHa2lqqqqo0TrNZXTyVhJVIJDQGJkxeVF0BCKU/UmEn8k557/LyMj09PbS0tHD69GkCgQBO\np5O9e/dSV1eHz+cjFos9VB7GR8oQ7J2glNIqwgsvvEAoFAJWB2toaIjLly/z8ccf09LSQjweT7Jt\n23dAEzEWWl5epra2VjvPNDc3c/nyZQYGBjY86cluxrGLsqb/uJlOWySChYUF5ubmGBsbY2hoiPb2\ndm7fvk1bWxt79+7l6aef5vHHH9e7NaAPKJ2cnNSnQktZG+1aJpmMRJ4zAT7TCmP+TupummplF/R4\nPJSUlFBdXc2pU6c4dOgQdXV1vP766/zsZz/jzp07WqeVd5tqymZEcHO3NDEWQANrJsBsovemeiW4\njTDYsbExGhsbNbNzOBzs2bOHI0eOUF1djdvtJhaLaXXBBGBTkQnkmWqVnCsiWIXpHyB9YbrTC9mZ\ngqn+jo6O0t3dreerw+HQzlj5+fkkEonPr4QggyUipcvl4umnn+a1117TQIxw0N7eXr7//e/T1tbG\nxMSEdvqx57c3AZpU9Pjjj/Piiy8SDoc1uDU3N5fyvD+TzIUjoKJE+8l9OXCjra2NkpISfZRYd3c3\nra2t3Llzh6amJjo7O5mcnGR6epqlpSUCgcB9/hfLy8sMDg5y9erVpIVl6qgm40vXvyaTNM1f9ral\nGhdhqC6XS+uz5eXl1NTUaNVAVLlYLMZ7773HlStXaGpqIhaLaVBOQMf8/HwWFhZYWFjYslXEbLP8\nLygoIDc3l/Lycjo6OhgfH0/CDESqEC8+y7K0hDQ2NqY3i9zcXOrq6vja177G3r17mZycpLe3l/Hx\ncc0MgbSqjki6JhMyXcPNfk+lzphqnKkSmv0gZt/5+XmmpqZ025aWlrQZ0mz7g9IjZQiyg5oJOnw+\nnz7cVUJql5eXCQQCnDt3jsLCQoaGhpidndVIsvzOfsCqiWyLV11dXR2lpaU6Wk/MbcJtt2KuMQcP\nVidEe3s77733nt51FhcX9SLp7+/XJ/TIohAHI3mfDOjS0hKDg4Ncu3ZNuwqbZZlqQDpw0WQI5vtT\n1d2cgNJfLpcLl8tFdXU1VVVVVFdXU1ZWpl2DFxcX6evrIxKJ0NXVRVNTEy0tLRqTMcV2adNGapnU\nxVRtTEa/srJ6wvTg4CDV1dVUV1fz7LPPkpubS2NjI5FIhFgspmMwxJQo7Zb/YmURc2pZWRnHjx8H\nIBKJaGYt5W51kZkAozmupjRsjqWdGZhSlDm/TNdoYUTiuCZ9bo7rVuv9yA9qWVpaIi8vD4C5uTmm\np6eZnp7WphxhGrW1tfzRH/2RNi11dXXR09PDwMAAi4uLOhTX7oRkWZZ2Yjl8+DDl5eXaph+LxRga\nGtKg0GbdVgVks3uyCUOYmZlhfHwcn8/H4uIily5doru7O2lym2SqTiZDGB4e5ubNm8Tj8SQxWOpg\nWk42I9LaGYepasl9cZktKSmhsLCQ4uJiTp8+zdGjRzlw4AB+v1972b377ru8/vrr3L59W8dbiNed\nvWwJgNoMKaWSnKDsmbRnZ2dpbm6mvr6eI0eO8OUvf5mqqiouXLjAJ598Qmtra1KSXdMZypQURMoM\nh8OaybW2ttLb26vNh0qpDeMCUt0z+zqVb4CdWZjXU5mgRR0xrTVCo6OjRCIRnVsUHjw/6CMHFc1A\nDKUUV69e5cc//jGHDx+muLgYv9+flCJr37592p1XXDdFt2pqamJiYoLx8XHtgpuTk8PevXsJBAIA\nOnxXENuSkhJmZma0N9tGzEAGwowpMAd1fn6eSCTC+++/r/GAkZERPSlNoEsmplgdTNBPJIfJyUkt\nTZhmQ5OBpKuz6egljMiMNrSj2gD79u3j5MmTPP/885SWlpKfn08wGCQQCODz+bRXptPp1IBiLBYD\noLy8nJmZGRKJBE6nk9nZWebn53U/LC4uJiUM2QjANR23TMYVj8d5++23NRAogGwgEODw4cPcunWL\nK1euMDIywtzcHD6fT7u+CwgtKlBxcTH19fWcOHGCrKwsbt68yaVLl3SbzE1ivX4WDEl+Z/pZ2LEZ\nO3M355U5v+RZ00/F4/Hg9Xq1WrywsEAkEiEajd6HPTwIfSbyIZgurU1NTRpNraysJBwO4/V6cbvd\nuN1u8vLyyM/PJxQKac8+p9PJ5OQkNTU1TExM6IgwYQhVVVW4XC5isRiFhYXA6iIpLi7myJEjjI2N\nMTY2tqVOTCeyC2OZmJhI0vPs4JQ5AUQ0F3FQFs3KyorOKQDJWXU3CyrKZF2PzHaXl5dz+vRpvvCF\nLxAKhXTcguyoop45nU78fj9VVVU4HA4OHjxIdnZ2kkPQyMgIkUiE0dHRJA9Qu4SUiqQvpH7Sf0op\nFhcX6e3t5eOPP6agoIDf+q3for6+Hr/fTzgcpqKigsLCQoaHh5mdndXMICcnRzMEr9dLKBSiqKiI\n0tJSysrKyMrKIhqN0tPTk4Q7bIbsvzMX53rObukoOzsbl8ulgVy/369B3KNHj+L1evXGUFBQQE1N\nDUePHtVBZaOjozr6dyv0SBmCDLqpI3Z2dtLf38/777+Pz+cjEAjg9XopKyvjwIEDhMNhioqKdJhu\nOBwmKytLBwPZFxwkp7cWK4BE5b3wwgt8+umn2g9ivZ0Akgcx1YK0mwJTvUtUAml7UVER4XCYhYUF\n7SlngqMmKCXt2KzZEUgyXW1EoVCIiooKXC4Xc3NzxGIxAoEA+fn5GqC7e/cuXq+XvLw8ysvLOXXq\nFH6/X5+RMT09zfj4OG1tbVy/fp2f/exnTExMpOyfVCQ4QapFJjtlVlYWd+7cYWJiQuezyMrK0ov7\n7NmzSZYU4D7GKO+S3AWmg5yUtxWzYzog294Gc3OwYzqWterC7vF4KCsro7KykpycHPbv38+LL75I\nVVWVDt4SSe2pp56ioqKCqqoqxsfH6evr4+LFiwwMDGw5+9dnQkIwB17s1RLOHI/Hyc3NJRKJ0NnZ\nidvtxuPxEAwG8fv9+Hw+LSU4HKshuT6fD5/Pp/Uup9NJeXk5J06cIDc3l6mpKa5fv65dliORiE5w\nuVWOulG7Uun3JliWm5tLQUEBoVBIB6nMzs4yMzPDxMSE1gtFIjH/PwyaLGTfrbu6urh48SIdHR1a\nZZFsP0op4vE4CwsLeDwe5ubmmJqa0nWXekkkaXl5OSUlJUQiERYWFohGo0nA13p1Stc2u3oWjUb5\n7ne/ywcffIDf76eiooKKigrKysoIh8P4/f6khLDiABaNRolEIgwPDzM2NkZ5eTlf+tKXWFhY0L4D\nwkgfFKBLR/Z5Id6g4odTW1vLvn37aGhooKamBofDQTAYpKqqKkmFlndZlsWePXs4d+4c8/PzjI+P\nU1tby4ULF/jlL3+5pbo9coZgR1blu5j0RO8cGxvTPumir5n56UTECgaDeoGJSdHv93PmzBkOHz5M\nXl6e1kHfeecdbty4oTl2Jttnp5WVFe3/L+6pkjB2ZmaGoaEhRkdHteedudOZprftqp9M+q6uLqam\npvB4PCwsLDA9Pa3HZWVlRec2ECB4eXkZl8ulpSuHw0FZWRmvvfYa58+fp6GhgcbGRkZHR4nH45q5\npav7RuqEHbGfmZnhzTff5NKlS4RCIRoaGjhw4AD79+/XUqQ4Ji0sLDA/P8/k5CSdnZ20t7fT0dFB\nNBrlzJkzfPGLX9Rqnhne/aAA3Wb6He6ZFHNycjhy5Ajnzp3jxIkT1NfXU1FRocdbmJMZ0wJoybKh\noUF/r6+vZ2xs7PPHECA5tZXp8CMdkcpRQyaWHe2PRqPk5ubi8Xg0h29oaODQoUNa5B0YGOCdd97h\n1q1bOkBKKaXR8+1MsmqSXfpwuVzaDdXn8yVZDQYGBohGo2mDgB7WZz0dTU5OkkgktNpiMh9TbTF3\nzunp6aT7TqdTm8Gys7N5/PHH6evr44MPPkjyVEyHzm9EdgRfcIWRkRESiQStra1aevR6vdqdWObN\n7Owsw8PDJBIJ7claX1/PysqKxiAkwGi7GUEqWl5eJhgMcvToUV555RWeeuopioqKdJQj3MuzIRHA\n9kRAUkeZY/n5+dpStxX6TDCEVGRyZfug2HcJc3JJ9KEEiDidTp2haHl5mUgkQkdHB0NDQyQSCT1R\nhPNup8qQasBMzu71eiktLSUcDuPxeLSkcvfuXfr7+4lGo0l2ZdMmvd2TVN4nmYCBpPMGpR5iVjQt\nQ+aOb1mWdj4SplFUVERhYaEer/VUggettxkjEo/HiUajOmzcNOGJri/zQyRD8S4tLi6mrq6OO3fu\nEI/HNxVe/iBkNzvu2bOHJ554gmPHjlFZWalNiyIVm6qS6fotaqeox2LBEMe3rdIj91S0L3S5bl9M\ndjFTJlaqyWVZlnYhzc3NZf/+/TQ0NLC0tERfXx9tbW3a98A0Gz6MD3i69tl3Q7kG6BgG0cGlTYKi\nm+ZKkyGYO7QsyO2utzAnMQubE1AmndRNQD55TsA5+S4o/1YdvzZLqYBewQskeEikA5PMBDUyByTW\nRUDUzfghPAiZG15WVhbhcJizZ8+yd+9encbO7F+Zn5JfQtRp09o0PT1NTk6OzgsxMjKy5Xo9coYA\n9w9oKnQ3nXhpvy4TViatOLmIaW9qaorh4WGts83Pz+uB325VIRUjM+3pIiG43W7tZ7Gysprxp7e3\nV9uWTb1aVCr5224w1MxXIOK19KMsHlHTBJkXC43f76ewsJBDhw7pCNWlpSXef/99rly5ohnMduEf\nQumkJpMJmNKVuMkvLy8nxcPk5uZqU6QAfakcybaDRDoRAPbxxx+nvLxcZ0gS3w3TAidjI8CoRJTK\nHPb7/dpJKRqN0tzcvOV6PXKVwd7ZmxXPTDu+Ka7afyOAo4i64+Pj2rvRLspvxutvK2RnCHaPNUmg\nKc4+0hbRh6emplK2y2xfJiarLA5Rx8yyZPeVvs3KyiIYDFJSUkJtbS01NTUcOHCAgwcPkpWVRWtr\nK5cvX9a5GTNR31T1l//2MTZJxkckl5mZGfLy8giHw0kejpnAEIQJuVwujh8/zunTpwmFQhoAlfJN\nk6nDsZosZ2xsjKamJi5fvszly5eZm5vTOT6EGSwsLGhvza3QI49lgGQubOpKqcjcHU0EWCavKV2Y\nMeoiuo+MjOhUXyJymRF92w0qmpNR6ipglUwIM+WW3JdsOqn6bD0m+LAk5lCfz4dlrab8MrMemRNU\n6LHHHuOpp57i/PnzVFVVEQ6Hyc7O5ubNm/zqV7/iypUrdHR0JPVFphB7U0KUe/ZYgeXlZWZnZ/V3\nCZLr7++npqaGYDCoHcrM8PXtlmpE/3/iiSc4d+4cXq83STUUnxkzyXA8HqelpYXvfe97Ot+C3Ulu\nIw/W9eiRSwiQOktOKq5uLgJ5xg46miK5eDRK/EJjYyOdnZ068aadIW23H4LURXZGYUpShoQR23EA\n0Qnh/uzDZltTqSSp6mD23UaUnZ1NMBjk0KFDOBwOJicn6e7u1i7ilZWVVFRUUFpaqpH8I0eOUF9f\nr/t5cnKSlpYWLl26xFtvvcXY2BjZ2dkbRjluldLhR/bFYN9lAR0jIcy4p6eHH/zgB3zlK18hFApR\nW1urfRU26xW6WZLNR5KdiL+EHTSWOSMu0YlEgtu3b/Puu+/S1NSk/TvsY/wwkuNngiHA/UxByN7Y\nVCCkSab0EAgE2Lt3L2VlZTidTrq6uhgeHta2dXu56+X5exAShmCaRc17LpdLJ7kwGZy5o9lj++3t\n32x9N8sYHI7VxCcHDx4kEAgwPT1Nfn6+Dlw6evQoR48epb6+nnA4TCAQoLS0FKfTycTEBJFIhJ6e\nHt59910++OADrl+/jsfjwel0au/D7VIbNosrSfvNP1EVZHwGBwd54403OHToEE8//TQNDQ309/cT\niUT089tJEmUZDod1jIgZsyG7vlgb5ubmGBoa4pNPPuHy5csMDg7qhDCpNk0z7H0r9MiDm+y73mYp\nFfOA5N21pKSEc+fOEQwGk0AZUSVEzciUTV/qZy5GWRBOpxOfz0dRUZE+pEUQbbuInq5/TCvJdjEy\nwVYqKys5deoUJSUltLa2EovFyM3NpaqqitLSUlwuF7m5uRr86uzs5MKFCzQ3N9PR0cHAwACxWIzs\n7Oyk5DPi8bjdzDcV2fvdHjpsmqwtyyIWizE+Ps78/DwNDQ3a9Xq758fKymoKvtzcXMrKynSMhWwG\nUm8Z27m5OQYGBrh8+TLvvfcejY2NWNZqAJwwWZO52U3xW6HPjISwVTJ3VPt1Ia/Xq/PWy+IxUVsT\npZdO3W7d1hwY+ZyTk0NRUZEWvU0HkpGREXp6epJi8dPt7pup61bbY2I4ctKUHO0m7YlEIhrjEPfh\njo4Obty4ofM9SGCN6MLpVLxMUippJJW6KeNuZlo2vRW32yoCq8wqkUjQ29tLS0uLdkeWE7edTieN\njY1cuXJFpw+8c+cOzc3NmjmbUasi8TwstvSZABUflDZqtGTpERMSJMfni8uocNV0fg0PUz9T3JfP\nLpeLmpoaamtrtcOUgHk9PT1JiUklshBICXZup1VESGIYhoaGcDqdDA8P61Oj5ufnSSQSeuGPjo7S\n2tqqg5fWo+3UwzdL6frGdP8VlU0iVcVxaSuJd7dCgg1I5uXa2lq9yCUVncvl4uLFi/zlX/6lBjfN\n4Cl79qbt6tvPrYSwGRIOLG7BfX19+ugsyagjtBmA7kHJzNsPq2BiIBDA7XZjWZbO2JSXl8fg4CAd\nHR0kEomUDEAkHBF/M7HbTk5O8uabb3LlyhUt8ovH3OLios4PKV6Nm0188lkku/oyODioD3cxXeS3\nk8SSJBLre++9x40bN3A4HBpgXF5eprOzU2f33gmJCn7NGcLIyAhXr14ls+ALjgAABiBJREFUGo2i\nlKK/v5+RkZEkET5Vdp/t6nzRVU3xVBbzzMwMN27c4Ktf/SpKKWKxGM3Nzdy4cYOOjg69yOwYgQmM\nZYIZKKWYn5+ntbVVOyHBPWTcDKUWLCZTsR+ZJsmGLNYPp9PJyMgI7e3t2nHJHlW4XSSYlmxUoiKK\nq7WZgi5TgXep6NeaIXR3dzM4OKhNe5IZSSa5qd+KA5Ok7doOMhPBmvrezMwMd+7c0ZPA4/HQ0tLC\nt7/9ba5du0ZnZ6f2PpPnzV0qk849pqdiKm9ROwq+E45G201SbzMxzfLy6tFoExMTdHZ2UlJSoiM5\nhQlmkvGZALGZAwMeXrXeCqmdEkXuK1ipjBcsnWzqiEb59+UY2G59UZBfKcP0RxAvxd/+7d8GVhN7\n3rhxQx/kIYFZ4l5t+iXIghVGtp0TxnQSk4Vjz9Mn94QypWplmnJycu6TEHw+H8FgkFAoxNjYGD09\nPSl9Gx6G7NiF+WfeEwnNnqZvO8iyrJSc/NeaIcgOK51pAnyS/n0n2m+evCNMwr7bpGJIZryF/N7M\nSQgPbm/eiEQdkJBbU2oSRmv26a8TOZ1OvF6vBhe3m0xvSsn3ASQxfbfbrWNJ1gOVH5T+v2QIu7RL\nu5SaPnMMYZd2aZc+e7Rz8OUu7dIufeZplyHs0i7tkqZdhrBLu7RLmh4JQ1BKvaSUuqOUalNK/ckO\nlFeulHpbKdWslGpUSv3rtetBpdQFpVSrUupXSil/huvhUEpdV0r9dO17tVLqw7Xyf6iUyphfiFLK\nr5T6sVKqRSnVpJQ6s5PtV0r9oVLqtlLqllLq75RSOZlsv1Lq20qpEaXULeNa2vYqpf6jUqpdKXVD\nKXUsQ+X/zVr/31BK/YNSymfc+9Za+S1KqRcetvwHJrsdNNN/rDKhDqAKyAZuAPszXGYxcGztswdo\nBfYD/xb447XrfwL8dYbr8YfAD4Cfrn3/EfDa2uf/BvyrDJb9P4HfXfvsBPw71X6gFOgCcox2fzOT\n7QeeBI4Bt4xrKdsLvAy8sfb5DPBhhsp/DnCsff5r4K/WPh8EPl0bl+q19aEyORfT1nvHC4SzwJvG\n9z8F/mSH6/B/1wbnDlC0dq0YuJPBMsuBi8AzBkMYNSbIWeCXGSrbC3SmuL4j7V9jCL1AcG3S/xR4\nHohmsv2sbjrmgrS3t2Xt838Hvmb8rkV+t53l2+69Cnx/7XPSGgDeBM5kai6u9/coVIYyoN/4PrB2\nbUdIKVXNKuf+kNVBHwGwLCsChDNY9N8C/waw1upRAExaliXuZwOsLpxMUA0wppT67prK8j+UUvns\nUPstyxoC/h3QBwwCU8B1ILZD7RcqtLW3cO26fU4Okvk5+XvALx5h+SnpUTCEVA4RO+IMoZTyAD8B\n/sCyrOkdLPdLwIhlWTe4137F/X2Rqfo4gePAf7Es6zgww+qutFPtDwD/nNUdsxRwsyqm2+lROcXs\n6JxUSv05cNeyrB8+ivLXo0fBEAaASuN7OTCU6ULXAKufsCqm/ePa5RGlVNHa/WJWRdhM0DngN5VS\nXcAPgS8C/x7wK6VkDDLZDwNAv2VZn6x9/wdWGcROtf85oMuyrAnLspaB/wM8AQR2qP1C6do7AFQY\nv8tYXZRS3wReAb5hXN6x8jeiR8EQrgJ1SqkqpVQO8HVWdcpM03eAZsuy/oNx7afA76x9/ibwj/aH\ntoMsy/ozy7IqLcuqYbW9b1uW9S+Ad4DXdqD8EaBfKdWwdulZoIkdaj+rqsJZpZRLrUZFSfmZbr9d\nCjPb+ztGeT8F/iWAUuosq6rM1k852aB8pdRLwB8Dv2lZ1oKtXl9fs7zsBeqAj7eh/K3TowAugJdY\nRfrbgT/dgfLOAcusWjQ+ZVV/fQnYA7y1VpeLQGAH6nKee6DiXuAjoI1VxD07g+UeZZUZ3wBeZ9XK\nsGPtB/6CVbDuFvA9Vi1MGWs/8Pes7rILrDKk32UV1EzZXuA/s4ru3wSOZ6j8dlbB1etrf//V+P23\n1spvAV7I9DxM97cby7BLu7RLmnY9FXdpl3ZJ0y5D2KVd2iVNuwxhl3ZplzTtMoRd2qVd0rTLEHZp\nl3ZJ0y5D2KVd2iVNuwxhl3ZplzT9PwQ2U3APvkvhAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f8f2d056c88>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_n_images = 25\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL\n",
"\"\"\"\n",
"%matplotlib inline\n",
"import os\n",
"from glob import glob\n",
"from matplotlib import pyplot\n",
"\n",
"mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'mnist/*.jpg'))[:show_n_images], 28, 28, 'L')\n",
"pyplot.imshow(helper.images_square_grid(mnist_images, 'L'), cmap='gray')"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### CelebA\n",
"The [CelebFaces Attributes Dataset (CelebA)](http://mmlab.ie.cuhk.edu.hk/projects/CelebA.html) dataset contains over 200,000 celebrity images with annotations. Since you're going to be generating faces, you won't need the annotations. You can view the first number of examples by changing `show_n_images`."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<matplotlib.image.AxesImage at 0x7f8f21fb7240>"
]
},
"execution_count": 3,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAQQAAAD/CAYAAAAXKqhkAAAABHNCSVQICAgIfAhkiAAAAAlwSFlz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\n29r/BIV7eMiBdTsYAAAAAElFTkSuQmCC\n",
"text/plain": [
"<matplotlib.figure.Figure at 0x7f8f78253080>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_n_images = 25\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL\n",
"\"\"\"\n",
"mnist_images = helper.get_batch(glob(os.path.join(data_dir, 'img_align_celeba/*.jpg'))[:show_n_images], 28, 28, 'RGB')\n",
"pyplot.imshow(helper.images_square_grid(mnist_images, 'RGB'))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Preprocess the Data\n",
"Since the project's main focus is on building the GANs, we'll preprocess the data for you. The values of the MNIST and CelebA dataset will be in the range of -0.5 to 0.5 of 28x28 dimensional images. The CelebA images will be cropped to remove parts of the image that don't include a face, then resized down to 28x28.\n",
"\n",
"The MNIST images are black and white images with a single [color channel](https://en.wikipedia.org/wiki/Channel_(digital_image%29) while the CelebA images have [3 color channels (RGB color channel)](https://en.wikipedia.org/wiki/Channel_(digital_image%29#RGB_Images).\n",
"## Build the Neural Network\n",
"You'll build the components necessary to build a GANs by implementing the following functions below:\n",
"- `model_inputs`\n",
"- `discriminator`\n",
"- `generator`\n",
"- `model_loss`\n",
"- `model_opt`\n",
"- `train`\n",
"\n",
"### Check the Version of TensorFlow and Access to GPU\n",
"This will check to make sure you have the correct version of TensorFlow and access to a GPU"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"TensorFlow Version: 1.3.0\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel_launcher.py:14: UserWarning: No GPU found. Please use a GPU to train your neural network.\n",
" \n"
]
}
],
"source": [
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL\n",
"\"\"\"\n",
"from distutils.version import LooseVersion\n",
"import warnings\n",
"import tensorflow as tf\n",
"\n",
"# Check TensorFlow Version\n",
"assert LooseVersion(tf.__version__) >= LooseVersion('1.0'), 'Please use TensorFlow version 1.0 or newer. You are using {}'.format(tf.__version__)\n",
"print('TensorFlow Version: {}'.format(tf.__version__))\n",
"\n",
"# Check for a GPU\n",
"if not tf.test.gpu_device_name():\n",
" warnings.warn('No GPU found. Please use a GPU to train your neural network.')\n",
"else:\n",
" print('Default GPU Device: {}'.format(tf.test.gpu_device_name()))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Input\n",
"Implement the `model_inputs` function to create TF Placeholders for the Neural Network. It should create the following placeholders:\n",
"- Real input images placeholder with rank 4 using `image_width`, `image_height`, and `image_channels`.\n",
"- Z input placeholder with rank 2 using `z_dim`.\n",
"- Learning rate placeholder with rank 0.\n",
"\n",
"Return the placeholders in the following the tuple (tensor of real input images, tensor of z data)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ERROR:tensorflow:==================================\n",
"Object was never used (type <class 'tensorflow.python.framework.ops.Operation'>):\n",
"<tf.Operation 'assert_rank_2/Assert/Assert' type=Assert>\n",
"If you want to mark it as used call its \"mark_used()\" method.\n",
"It was originally created here:\n",
"['File \"/home/spike/.pyenv/versions/3.5.1/lib/python3.5/runpy.py\", line 170, in _run_module_as_main\\n \"__main__\", mod_spec)', 'File \"/home/spike/.pyenv/versions/3.5.1/lib/python3.5/runpy.py\", line 85, in _run_code\\n exec(code, run_globals)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel_launcher.py\", line 16, in <module>\\n app.launch_new_instance()', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/traitlets/config/application.py\", line 658, in launch_instance\\n app.start()', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel/kernelapp.py\", line 477, in start\\n ioloop.IOLoop.instance().start()', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/zmq/eventloop/ioloop.py\", line 177, in start\\n super(ZMQIOLoop, self).start()', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tornado/ioloop.py\", line 888, in start\\n handler_func(fd_obj, events)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tornado/stack_context.py\", line 277, in null_wrapper\\n return fn(*args, **kwargs)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py\", line 440, in _handle_events\\n self._handle_recv()', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py\", line 472, in _handle_recv\\n self._run_callback(callback, msg)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/zmq/eventloop/zmqstream.py\", line 414, in _run_callback\\n callback(*args, **kwargs)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tornado/stack_context.py\", line 277, in null_wrapper\\n return fn(*args, **kwargs)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel/kernelbase.py\", line 283, in dispatcher\\n return self.dispatch_shell(stream, msg)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel/kernelbase.py\", line 235, in dispatch_shell\\n handler(stream, idents, msg)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel/kernelbase.py\", line 399, in execute_request\\n user_expressions, allow_stdin)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel/ipkernel.py\", line 196, in do_execute\\n res = shell.run_cell(code, store_history=store_history, silent=silent)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/ipykernel/zmqshell.py\", line 533, in run_cell\\n return super(ZMQInteractiveShell, self).run_cell(*args, **kwargs)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/IPython/core/interactiveshell.py\", line 2683, in run_cell\\n interactivity=interactivity, compiler=compiler, result=result)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/IPython/core/interactiveshell.py\", line 2793, in run_ast_nodes\\n if self.run_code(code, result):', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/IPython/core/interactiveshell.py\", line 2847, in run_code\\n exec(code_obj, self.user_global_ns, self.user_ns)', 'File \"<ipython-input-6-f20bd8a9e3c0>\", line 23, in <module>\\n tests.test_model_inputs(model_inputs)', 'File \"/home/spike/ml/udacity/nd101/project5/problem_unittests.py\", line 12, in func_wrapper\\n result = func(*args)', 'File \"/home/spike/ml/udacity/nd101/project5/problem_unittests.py\", line 68, in test_model_inputs\\n _check_input(learn_rate, [], \\'Learning Rate\\')', 'File \"/home/spike/ml/udacity/nd101/project5/problem_unittests.py\", line 34, in _check_input\\n _assert_tensor_shape(tensor, shape, \\'Real Input\\')', 'File \"/home/spike/ml/udacity/nd101/project5/problem_unittests.py\", line 20, in _assert_tensor_shape\\n assert tf.assert_rank(tensor, len(shape), message=\\'{} has wrong rank\\'.format(display_name))', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tensorflow/python/ops/check_ops.py\", line 617, in assert_rank\\n dynamic_condition, data, summarize)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tensorflow/python/ops/check_ops.py\", line 571, in _assert_rank_condition\\n return control_flow_ops.Assert(condition, data, summarize=summarize)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py\", line 175, in wrapped\\n return _add_should_use_warning(fn(*args, **kwargs))', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py\", line 144, in _add_should_use_warning\\n wrapped = TFShouldUseWarningWrapper(x)', 'File \"/home/spike/.pyenv/versions/3.5.1/envs/ml/lib/python3.5/site-packages/tensorflow/python/util/tf_should_use.py\", line 101, in __init__\\n stack = [s.strip() for s in traceback.format_stack()]']\n",
"==================================\n",
"Tests Passed\n"
]
}
],
"source": [
"import problem_unittests as tests\n",
"\n",
"def model_inputs(image_width, image_height, image_channels, z_dim):\n",
" \"\"\"\n",
" Create the model inputs\n",
" :param image_width: The input image width\n",
" :param image_height: The input image height\n",
" :param image_channels: The number of image channels\n",
" :param z_dim: The dimension of Z\n",
" :return: Tuple of (tensor of real input images, tensor of z data, learning rate)\n",
" \"\"\"\n",
" \n",
" inputs_real = tf.placeholder(tf.float32, (None, image_width, image_height, image_channels), name='inputs_real')\n",
" inputs_z = tf.placeholder(tf.float32, (None, z_dim))\n",
" learn_r = tf.placeholder(tf.float32)\n",
"\n",
" return inputs_real, inputs_z, learn_r\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"tests.test_model_inputs(model_inputs)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Hyperparameters"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"alpha = 0.2 # for leaky relu"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Discriminator\n",
"Implement `discriminator` to create a discriminator neural network that discriminates on `images`. This function should be able to reuse the variables in the neural network. Use [`tf.variable_scope`](https://www.tensorflow.org/api_docs/python/tf/variable_scope) with a scope name of \"discriminator\" to allow the variables to be reused. The function should return a tuple of (tensor output of the discriminator, tensor logits of the discriminator)."
]
},
{
"cell_type": "code",
"execution_count": 65,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Tests Passed\n"
]
}
],
"source": [
"def discriminator(images, reuse=False):\n",
" \"\"\"\n",
" Create the discriminator network\n",
" :param images: Tensor of input image(s)\n",
" :param reuse: Boolean if the weights should be reused\n",
" :return: Tuple of (tensor output of the discriminator, tensor logits of the discriminator)\n",
" \"\"\"\n",
" with tf.variable_scope('discriminator', reuse=reuse):\n",
" \n",
" # Input layer is 28x28x3\n",
" x1 = tf.layers.conv2d(images, 32, 5, strides=1, padding='valid')\n",
" relu1 = tf.maximum(alpha * x1, x1)\n",
" #print(relu1)\n",
" # 24x24x32\n",
" \n",
" x2 = tf.layers.conv2d(relu1, 64, 7, strides=1, padding='valid')\n",
" bn2 = tf.layers.batch_normalization(x2, training=True)\n",
" relu2 = tf.maximum(alpha * bn2, bn2)\n",
" #print(relu2)\n",
" # 18x18x64\n",
" \n",
" x3 = tf.layers.conv2d(relu2, 128, 7, strides=1, padding='valid')\n",
" bn3 = tf.layers.batch_normalization(x3, training=True)\n",
" relu3 = tf.maximum(alpha * bn3, bn3)\n",
" #print(relu3)\n",
" # 12x12x128\n",
" \n",
" x4 = tf.layers.conv2d(relu3, 256, 5, strides=2, padding='valid')\n",
" bn4 = tf.layers.batch_normalization(x4, training=True)\n",
" relu4 = tf.maximum(alpha * bn4, bn4)\n",
" #print(relu4)\n",
" # 4x4x256\n",
"\n",
" # Flatten it\n",
" flat = tf.reshape(relu4, (-1, 4*4*256))\n",
" logits = tf.layers.dense(flat, 1)\n",
" out = tf.sigmoid(logits)\n",
" \n",
" \n",
"\n",
" return out, logits\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"tests.test_discriminator(discriminator, tf)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Generator\n",
"Implement `generator` to generate an image using `z`. This function should be able to reuse the variables in the neural network. Use [`tf.variable_scope`](https://www.tensorflow.org/api_docs/python/tf/variable_scope) with a scope name of \"generator\" to allow the variables to be reused. The function should return the generated 28 x 28 x `out_channel_dim` images."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def generator(z, out_channel_dim, is_train=True):\n",
" \"\"\"\n",
" Create the generator network\n",
" :param z: Input z\n",
" :param out_channel_dim: The number of channels in the output image\n",
" :param is_train: Boolean if generator is being used for training\n",
" :return: The tensor output of the generator\n",
" \"\"\"\n",
" # TODO: Implement Function\n",
" \n",
" return None\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"tests.test_generator(generator, tf)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Loss\n",
"Implement `model_loss` to build the GANs for training and calculate the loss. The function should return a tuple of (discriminator loss, generator loss). Use the following functions you implemented:\n",
"- `discriminator(images, reuse=False)`\n",
"- `generator(z, out_channel_dim, is_train=True)`"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def model_loss(input_real, input_z, out_channel_dim):\n",
" \"\"\"\n",
" Get the loss for the discriminator and generator\n",
" :param input_real: Images from the real dataset\n",
" :param input_z: Z input\n",
" :param out_channel_dim: The number of channels in the output image\n",
" :return: A tuple of (discriminator loss, generator loss)\n",
" \"\"\"\n",
" # TODO: Implement Function\n",
" \n",
" return None, None\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"tests.test_model_loss(model_loss)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Optimization\n",
"Implement `model_opt` to create the optimization operations for the GANs. Use [`tf.trainable_variables`](https://www.tensorflow.org/api_docs/python/tf/trainable_variables) to get all the trainable variables. Filter the variables with names that are in the discriminator and generator scope names. The function should return a tuple of (discriminator training operation, generator training operation)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"def model_opt(d_loss, g_loss, learning_rate, beta1):\n",
" \"\"\"\n",
" Get optimization operations\n",
" :param d_loss: Discriminator loss Tensor\n",
" :param g_loss: Generator loss Tensor\n",
" :param learning_rate: Learning Rate Placeholder\n",
" :param beta1: The exponential decay rate for the 1st moment in the optimizer\n",
" :return: A tuple of (discriminator training operation, generator training operation)\n",
" \"\"\"\n",
" # TODO: Implement Function\n",
" \n",
" return None, None\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"tests.test_model_opt(model_opt, tf)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Neural Network Training\n",
"### Show Output\n",
"Use this function to show the current output of the generator during training. It will help you determine how well the GANs is training."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL\n",
"\"\"\"\n",
"import numpy as np\n",
"\n",
"def show_generator_output(sess, n_images, input_z, out_channel_dim, image_mode):\n",
" \"\"\"\n",
" Show example output for the generator\n",
" :param sess: TensorFlow session\n",
" :param n_images: Number of Images to display\n",
" :param input_z: Input Z Tensor\n",
" :param out_channel_dim: The number of channels in the output image\n",
" :param image_mode: The mode to use for images (\"RGB\" or \"L\")\n",
" \"\"\"\n",
" cmap = None if image_mode == 'RGB' else 'gray'\n",
" z_dim = input_z.get_shape().as_list()[-1]\n",
" example_z = np.random.uniform(-1, 1, size=[n_images, z_dim])\n",
"\n",
" samples = sess.run(\n",
" generator(input_z, out_channel_dim, False),\n",
" feed_dict={input_z: example_z})\n",
"\n",
" images_grid = helper.images_square_grid(samples, image_mode)\n",
" pyplot.imshow(images_grid, cmap=cmap)\n",
" pyplot.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Train\n",
"Implement `train` to build and train the GANs. Use the following functions you implemented:\n",
"- `model_inputs(image_width, image_height, image_channels, z_dim)`\n",
"- `model_loss(input_real, input_z, out_channel_dim)`\n",
"- `model_opt(d_loss, g_loss, learning_rate, beta1)`\n",
"\n",
"Use the `show_generator_output` to show `generator` output while you train. Running `show_generator_output` for every batch will drastically increase training time and increase the size of the notebook. It's recommended to print the `generator` output every 100 batches."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"collapsed": true
},
"outputs": [],
"source": [
"def train(epoch_count, batch_size, z_dim, learning_rate, beta1, get_batches, data_shape, data_image_mode):\n",
" \"\"\"\n",
" Train the GAN\n",
" :param epoch_count: Number of epochs\n",
" :param batch_size: Batch Size\n",
" :param z_dim: Z dimension\n",
" :param learning_rate: Learning Rate\n",
" :param beta1: The exponential decay rate for the 1st moment in the optimizer\n",
" :param get_batches: Function to get batches\n",
" :param data_shape: Shape of the data\n",
" :param data_image_mode: The image mode to use for images (\"RGB\" or \"L\")\n",
" \"\"\"\n",
" # TODO: Build Model\n",
" \n",
" \n",
" with tf.Session() as sess:\n",
" sess.run(tf.global_variables_initializer())\n",
" for epoch_i in range(epoch_count):\n",
" for batch_images in get_batches(batch_size):\n",
" # TODO: Train Model\n",
" \n",
" "
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### MNIST\n",
"Test your GANs architecture on MNIST. After 2 epochs, the GANs should be able to generate images that look like handwritten digits. Make sure the loss of the generator is lower than the loss of the discriminator or close to 0."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"batch_size = None\n",
"z_dim = None\n",
"learning_rate = None\n",
"beta1 = None\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"epochs = 2\n",
"\n",
"mnist_dataset = helper.Dataset('mnist', glob(os.path.join(data_dir, 'mnist/*.jpg')))\n",
"with tf.Graph().as_default():\n",
" train(epochs, batch_size, z_dim, learning_rate, beta1, mnist_dataset.get_batches,\n",
" mnist_dataset.shape, mnist_dataset.image_mode)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### CelebA\n",
"Run your GANs on CelebA. It will take around 20 minutes on the average GPU to run one epoch. You can run the whole epoch or stop when it starts to generate realistic faces."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"batch_size = None\n",
"z_dim = None\n",
"learning_rate = None\n",
"beta1 = None\n",
"\n",
"\n",
"\"\"\"\n",
"DON'T MODIFY ANYTHING IN THIS CELL THAT IS BELOW THIS LINE\n",
"\"\"\"\n",
"epochs = 1\n",
"\n",
"celeba_dataset = helper.Dataset('celeba', glob(os.path.join(data_dir, 'img_align_celeba/*.jpg')))\n",
"with tf.Graph().as_default():\n",
" train(epochs, batch_size, z_dim, learning_rate, beta1, celeba_dataset.get_batches,\n",
" celeba_dataset.shape, celeba_dataset.image_mode)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Submitting This Project\n",
"When submitting this project, make sure to run all the cells before saving the notebook. Save the notebook file as \"dlnd_face_generation.ipynb\" and save it as a HTML file under \"File\" -> \"Download as\". Include the \"helper.py\" and \"problem_unittests.py\" files in your submission."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.5.1"
}
},
"nbformat": 4,
"nbformat_minor": 1
}