notebooks/Fully-QGAN_Gaussian.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "99a6fd09-39c6-4b73-bc6a-2c3c39330494",
   "metadata": {},
   "source": [
    "### Fully Quantum GAN\n",
    "\n",
    "This notebook shows how to build and train a fully quantum GAN. The fully quantum refers to the fact, that no classical discriminator is used. Instead a SWAP test is employed to compare the GAN circuit output with true training data.\n",
    "\n",
    "The output of the SWAP test is used as objective for the training."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "23567f97-58cc-4085-bf1c-ea50ac7f53a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import pennylane as qml\n",
    "from pennylane import numpy as np\n",
    "import time\n",
    "from pennylane.optimize import AdamOptimizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "7e19958e-228b-4d4e-bd2d-e0d1cd9248d8",
   "metadata": {},
   "outputs": [],
   "source": [
    "dev = qml.device('lightning.qubit', wires=9)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "f7518b81-98e1-4fd4-9fb8-fd3bb4d09d1c",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.rcParams.update({\n",
    "    \"text.usetex\": True,\n",
    "    \"font.family\": \"Helvetica\"\n",
    "})"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "ebb6f303-b556-4d8c-85a2-5ae089873a62",
   "metadata": {},
   "source": [
    "## Data generation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "d31ee30d-a8d1-43e7-8a27-12027ac5ae61",
   "metadata": {},
   "source": [
    "As toy dataset we draw $N=120$ integers between $0$ and $16$ from a gaussian peak."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "8a684c67-54b4-4233-b93b-f63b0ca70570",
   "metadata": {},
   "outputs": [],
   "source": [
    "N = 120"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "8dc12198-1f99-44ca-a1ec-3e757ce002d4",
   "metadata": {},
   "outputs": [],
   "source": [
    "data = np.random.normal(loc=7,scale=1.5, size=N).astype(int)\n",
    "values, counts = np.unique(data, return_counts=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "48bdbbe0-76f1-421f-8162-afb446f0b960",
   "metadata": {},
   "source": [
    "Pad values which were drawn $0$ times for plotting."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "f35ea780-7f4e-46fe-b680-96d53ec88ded",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=np.arange(0,16)\n",
    "zerovals = [i for i in x if i not in values]\n",
    "zeros = np.zeros(len(zerovals))\n",
    "values = np.append(values, zerovals)\n",
    "counts = np.append(counts, zeros)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2a74f9fd-a275-4b18-8c24-478e4af78f8b",
   "metadata": {},
   "source": [
    "Lets look at our distribution"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "22c64642-1ce3-4a75-a521-3bd81e12d1a1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2700x1500 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(9,5))\n",
    "plt.plot(values,counts/N, 'b.', markersize=12)\n",
    "plt.ylabel('$P_i$', fontsize=18)\n",
    "plt.xlabel('$i$', fontsize=18)\n",
    "plt.xlim(0,16)\n",
    "plt.gcf().set_dpi(300)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "867cbc1f-9d87-4922-905a-9fea63216a2d",
   "metadata": {},
   "source": [
    "To embed the data into a quantum basis, we convert the number into binary and build respective quantum states by applying $X$ gates to nonzero bits."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "3920532f-1691-4b30-b91b-a1562aa5f34c",
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "def num_circuit(num, wires):\n",
    "    bin_str = format(num, '#06b')[2:]\n",
    "    for i, c in enumerate(bin_str):\n",
    "        if c == '1':\n",
    "            qml.PauliX(wires=i+wires[0])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "4af12f0f-e001-48d9-8e60-d6d175e4c0c0",
   "metadata": {},
   "source": [
    "Lets look at an example circuit by plotting it:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "58a54fa4-b8ba-40cf-b684-5553ddda18cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "devs = qml.device('lightning.qubit', wires=4, shots=10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "6933688b-4914-4dae-a6ab-27b95180d07e",
   "metadata": {},
   "outputs": [],
   "source": [
    "@qml.qnode(devs)\n",
    "def circuit(num):\n",
    "    num_circuit(num, [0,1,2,3])\n",
    "    return qml.sample()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "351f7bcf-4c10-402c-bf32-8a1e1b6cac92",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_1038374/2324509256.py:2: UserWarning: Matplotlib is currently using module://matplotlib_inline.backend_inline, which is a non-GUI backend, so cannot show the figure.\n",
      "  fig.show()\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 288x216 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = qml.draw_mpl(circuit)(3)\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bea33615-8b4a-4d20-9fa7-e378a09010cd",
   "metadata": {},
   "source": [
    "## Model"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "df7dc517-850f-479e-9733-d4b43d8af598",
   "metadata": {},
   "source": [
    "### Generator"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "61a78130-698a-4688-b20f-9dae6fe74c8a",
   "metadata": {},
   "source": [
    "We build the generator as a [Strongly Entangling Layer](https://docs.pennylane.ai/en/stable/code/api/pennylane.StronglyEntanglingLayers.html)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "8b3e8e7d-0cba-4bee-ab17-cbe679096e42",
   "metadata": {},
   "outputs": [],
   "source": [
    "def generator(params, qbits):\n",
    "    qml.StronglyEntanglingLayers(weights=params, wires=[qbits[0],qbits[1],qbits[2],qbits[3]])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "f90d6cc8-327c-4f2d-92ec-f768c21db1f1",
   "metadata": {},
   "source": [
    "Lets again look at an example generator circuit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "539c88b4-6903-49c1-a28c-096f43757eca",
   "metadata": {},
   "outputs": [],
   "source": [
    "@qml.qnode(dev)\n",
    "def circuit2(params, wires):\n",
    "    generator(params, wires)\n",
    "    return qml.expval(qml.PauliZ(0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "c45626ea-0a86-469e-89ed-03b1ac166ff7",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_1038374/1974881317.py:2: UserWarning: Matplotlib is currently using module://matplotlib_inline.backend_inline, which is a non-GUI backend, so cannot show the figure.\n",
      "  fig.show()\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 936x360 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = qml.draw_mpl(circuit2)(np.zeros(shape=(2,4,3)), [0,1,2,3])\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bf134c12-475c-48bc-9009-4ef652427c54",
   "metadata": {
    "tags": []
   },
   "source": [
    "### Gan circuit"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "51d0efcd-b5c1-4d8f-9b0d-956b278d9aad",
   "metadata": {},
   "source": [
    "The GAN is build from the real data in qubits $1-4$, the generator circuit in qubits $5-8$ and a SWAP test between the two states to measure the similarity.\n",
    "The result of the SWAP test is read out from qubit $0$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "356aa568-1970-4743-b119-cead5680829b",
   "metadata": {},
   "outputs": [],
   "source": [
    "@qml.qnode(dev)\n",
    "def training_circ(data, paramsg):\n",
    "    # top 4 qbits real data\n",
    "    num_circuit(data, [1,2,3,4])\n",
    "    \n",
    "    # bottom 4 qubits generator ansatz\n",
    "    generator(paramsg, [5,6,7,8])\n",
    "    \n",
    "    # swap test\n",
    "    qml.Hadamard(wires=0)\n",
    "    qml.CSWAP(wires=[0,1,5])\n",
    "    qml.CSWAP(wires=[0,2,6])\n",
    "    qml.CSWAP(wires=[0,3,7])\n",
    "    qml.CSWAP(wires=[0,4,8])\n",
    "    qml.Hadamard(wires=0)\n",
    "    \n",
    "    return qml.expval(qml.PauliZ(0))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5edfc7c2-0061-4e9d-9c08-9b17b3527747",
   "metadata": {},
   "source": [
    "Lets draw an example of the training circuit:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "be51e548-5863-41c8-a435-4914475c4efe",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/tmp/ipykernel_1038374/2202411966.py:2: UserWarning: Matplotlib is currently using module://matplotlib_inline.backend_inline, which is a non-GUI backend, so cannot show the figure.\n",
      "  fig.show()\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAACMYAAALeCAYAAABLQo/HAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAC2J0lEQVR4nOzdfXRV9Zkv8CdAeJlWCfEFpdarBFpEWzXolGqnQIHWl2m1LZFSsC/3KqHtOIYZxWXb6XTWHcdilYuO0zFYF1apSkOtI1odjIj40l4VxCUMKEmmtYgFEYIvg+Ht3D+8OUOsxEDOyT5nn89nLdba55Cc/ZwfJ999svaXfcoymUwmAAAAAAAAAAAgZXolPQAAAAAAAAAAAOSDYgwAAAAAAAAAAKmkGAMAAAAAAAAAQCopxgAAAAAAAAAAkEqKMQAAAAAAAAAApJJiDAAAAAAAAAAAqaQYAwAAAAAAAABAKinGAAAAAAAAAACQSooxAAAAAAAAAACkkmIMAAAAAAAAAACppBgDAAAAAAAAAEAqKcYAAAAAAAAAAJBKijEAAAAAAAAAAKSSYgwAAAAAAAAAAKmkGAMAAAAAAAAAQCopxgAAAAAAAAAAkEqKMQAAAAAAAAAApJJiDAAAAAAAAAAAqaQYAwAAAAAAAABAKinGAAAAAAAAAACQSooxAAAAAAAAAACkkmIMAAAAAAAAAACppBgDAAAAAAAAAEAqKcYAAAAAAAAAAJBKijEAAAAAAAAAAKSSYgwAAAAAAAAAAKmkGAMAAAAAAAAAQCopxgAAAAAAAAAAkEqKMQAAAAAAAAAApJJiDAAAAAAAAAAAqaQYAwAAAAAAAABAKinGAAAAAAAAAACQSooxAAAAAAAAAACkkmIMAAAAAAAAAACppBgDAAAAAAAAAEAqKcYAAAAAAAAAAJBKijEAAAAAAAAAAKSSYgwAAAAAAAAAAKmkGAMAAAAAAAAAQCopxgAAAAAAAAAAkEqKMQAAAAAAAAAApJJiDAAAAAAAAAAAqaQYAwAAAAAAAABAKinGAAAAAAAAAACQSooxAAAAAAAAAACkkmIMAAAAAAAAAACppBgDAAAAAAAAAEAqKcYAAAAAAAAAAJBKijEAAAAAAAAAAKRSn6QHoLBkMplYs2ZNvPDCC7F+/fpobm6O1tbWaGtri0wmk/f9l5eXx4ABA+LYY4+N4cOHx/Dhw+PUU0+ND37wg3nfNwAAAAAAAABd5/xy56xPYVCMISIinn322bjjjjuioaEhfv/73yc9Tgf9+/ePc845Jy644II4//zzo1+/fkmPBAAAAAAAAFCynF/unPUpLGWZnqghUbA2btwYl19+edxxxx1Jj9Ilw4YNi3/+53+Os846K+lRAAAAAAAAAEqK88udsz6FSTGmhP3yl7+Mb37zm/HGG290uH/gwIFxxhlnZC+lNHjw4Ojbt2/06tUrr/NkMpnYvXt3vP7669HS0hLr16+P5557LtauXfsnXztlypS49dZbo2/fvnmdCQAAAAAAAADnl9+P9SlcijElqqGhIaZMmRJ79uzJ3vfFL34xLrroopgwYUJBveDXrl0bCxcujLlz58b27duz93/hC1+IhoaGgpoVAAAAAAAAIG2cX+6c9SlsijElqLGxMc4666zsD2VVVVXU19fH+PHjE56sc5s3b47LLrssbr/99ux9U6ZMKZrLUAEAAAAAAAAUG+eXO1eI6/Pggw/Gxz72sfjQhz60368ppfPvijElpq2tLU466aRoamqKiIgRI0bE0qVL4+ijj054sq7JZDJx5ZVXxuzZs7P3PfDAA6n/zDMAAAAAAACAnub8cucKbX0ymUxcffXV8b3vfS8+8IEPxA9+8IOYOXNmlJeX7/frS+H8u2JMibnqqqvi+9//fkS881lm//Ef/xFDhgxJeKoDk8lk4mtf+1osWLAgIiKGDRsWq1evjn79+iU8GQAAAAAAAEB6OL/cuUJan507d0ZtbW3ceuut2ft69eoVra2tccghh+z3+0rh/HuvpAeg5+zatSvmzJmTvX3VVVcVXWhFRJSVlcV1110XAwcOjIiIpqamuOeee5IdCgAAAAAAACBFnF/uXCGtz7Zt2+Kss87qUIqJiDjppJM6LcVElMb5d8WYErJ06dLYunVrREQcc8wxMWPGjIQnOnhHHnlk1NXVZW83NDQkNwwAAAAAAABAyji/3LlCWZ+WlpY444wz4pFHHvmTv/vkJz/ZpcdI+/l3xZgSsu+Lt6amJnr37p3gNN03efLk7Pavf/3rePPNNxOcBgAAAAAAACA9nF/uXCGsz5NPPhmf+MQnYt26ddn7BgwYkN0ePXp0lx8rzeffFWNKyBNPPJHd/tKXvpTgJLlxwgknxIgRIyIiYseOHfHss88mPBEAAAAAAABAOji/3Lmk12fhwoXxmc98JrZs2RIREf369Ys777wz/uzP/iz7NV29YkxEus+/K8aUiD179kRLS0v29sknn5zgNLmz7/NoampKcBIAAAAAAACAdHB+uXNJrk8mk4l/+qd/iq985SvR1tYWERGHH354LF26NKqrq+O1116LiIjKysr4yEc+ckCPndbz74oxJeKll16KnTt3RkTE4MGD45BDDkl4otwYPnx4dnv9+vUJTgIAAAAAAACQDs4vdy7J9bn00kvje9/7Xof7tmzZEqeeemr85je/yd43evToKCsrO6DHTuv59z5JD0DPeOmll7Lbxx9/fIKT5FZVVVV2e9/nCAAAAAAAAMDBcX65c0muz6xZs2Lz5s2xcOHCDvf/2Z/9WVRWVmZvH8jHKLVL6/l3V4wpETt27MhuH3rooQlOklv7Nu/2fY4AAAAAAAAAHBznlzvXU+uzd+/e+MMf/hDr1q2LNWvWRHNzc1RWVsZdd90VDz/88J98/datW7PbB1OMSev5d1eMKRG7du3KbpeXlyc4SW7t+1zaL1UFAAAAAAAAwMFzfrlz+Vqf3bt3x7//+7/HfffdF88991w8//zz8eabb3b4ml69esXw4cM7XN3l3crKyuLP//zPD3j/aT3/rhhTgg70c8QKWZqeCwAAAAAAAEChSdM52Xw8l1w85oYNG+LGG2+M2267LV555ZVOv3bv3r3xwgsvxAsvvNDh/jPPPDOeeOKJiIg46aSTOlz9pavS9G+9L8UYAAAAAAAAAIAetmvXrrjhhhvi7//+7+Ott956z6857LDD4vDDD49evXrFf/3Xf8VLL70UmUzmT77uiSeeiE9+8pPx6quvHtTHKKWZYgwAAAAAAAAAQA9au3ZtTJ48OZ5//vkO9w8ePDguvPDCGD9+fJx88slx1FFHdbiSy+uvvx4DBw58z8f8zW9+E/37948hQ4ZEJpNJ7RVgDpRiDAAAAAAAAJSoN998M37+85/HggUL4pVXXomdO3dGRUVFjBs3Lr71rW/FiBEjkh4xUdanc9anc9aH/Xn00UfjvPPOi+3bt2fvO/HEE+Oqq66Kc845J8rLy/f7veeee26H2zfddFM8/fTTccstt0RExNtvvx0//OEP47XXXou5c+dGr1698vMkiogVAAAAAAAAgBKzc+fOmDVrVgwZMiRmzJgRjz/+eDQ3N8cf/vCHeP755+OGG26IE044IcaPHx9r1qxJetweZ306Z306Z33ozNKlS+Pss8/OlmIGDBgQ11xzTTz77LNx3nnndVqKaW5ujscff7zDfbW1tfHTn/40nnzyyfj4xz+evf+f//mfY/r06e/5sUulRjEGAAAAAAAASshbb70V55xzTvz4xz+ON954o9OvXbp0aZx55pnx2GOP9dB0ybM+nbM+nbM+dObll1+Ompqa2LFjR0REHH300fHEE0/E5Zdf3mkhpt2wYcM63N68eXN2+5Of/GT89re/jQsuuCB73y233BL/8i//kqPpi1dRFGNqampi0KBBUVVVFYsWLUp6HN5DVVVVzJs370/unzdvXgwaNCiBiQAAAAAAAHi3PXv2xJQpU+Lhhx/u8vds3749Pv/5z5fElS2sT+esT+esT9eV4vnlPXv2xLRp02Lr1q0RETFkyJBYvnx5nHrqqV36/p/+9Kcdbk+bNi2OOOKIDvcNGDAg7rjjjvja176Wve+yyy6L5557rpvTF7eCL8bU1NRES0tLPPzwwzF79uyoqamJlStXJj0WAAAAAAAAFJ1FixbF4sWLD/j7tm/fHpdeemkeJios1qdz1qdz1ofO3HjjjbFs2bKIiOjVq1fceeedf3IFmP3ZvXt3XHzxxR3uu+22297za3v37h3z5s2LU045JSIi2traYtq0abF3796Dnr3YFXQxprW1NRYtWhQ333xzVFdXx6RJk2L69Olx9dVXJz0aAAAAAAAAFJ2f/OQnB/29Dz/8cKxbty6H0xQe69M569M568P+7Ny5M3784x9nb3//+9+PT3/6013+/nHjxnW4fd9990VZWdl+v75fv35x1113xZ/92Z9FRMTq1avjvvvuO8Cp06OgizHPPPNMRERUV1dn75s4caIrxgAAAAAAAMABWr16dSxfvrxbj3HTTTflaJrCY306Z306Z33ozMKFC+Pll1+OiIjBgwfHd7/73S5/b3Nzczz++OMd7jv33HPf9/s++tGPxl/91V9lb1977bVd3mfaFHQxprW1NYYOHdrhvoqKimhpaUloIjpTW1sbZWVlHf7U1tYmPRYAAAAAAAAR2Y/w6I5HHnmk+4MUKOvTOevTOetz4Erp/PK+padLLrkk+vXr1+XvfffHLW3evLnL3/vXf/3X0adPn4iIeOyxx2LNmjVd/t406ZP0AMWqrq4uVq1alfQYXbZly5a872PWrFl/ElSLFi3qsY++evLJJ2Ps2LE9si8AAAAAAIBi8/vf/77bj/HCCy+k9nyM9emc9elc2tbH+eXOHcj6vP322/H0009nb1900UVd/t6f/vSnHW5PmzYtjjjiiC5//4c+9KH4y7/8y7jnnnsiIuKJJ56IE088scvfnxYFXYypqKiIrVu3drjvva4iQ2Goqqp6zyv8AAAAAAAAkLyysrJuP0avXgX9gRTdYn06Z306Z30OXKmcX3722Wdj165dERExfPjwGDx4cJe+b/fu3XHxxRd3uO+222474P2feeaZ2WLMb3/725g+ffoBP0axK+hizGmnnRatra3R0tKS/YF46KGHorq6OuHJIubOnZv0CAdk8eLF8YUvfCHpMfLqjDPOiMWLFyc9BgAAAAAAQEG6/fbb42tf+1q3HuO0007LyUfGFCLr0znr07m0rY/zy507kPVZuXJldnv06NFd3se4ceM63L7vvvsOqoD1iU98Iru9YsWKA/7+NCjoyllFRUVMmjQpamtro7W1NRobG2PevHmp/VwxAAAAAAAAyJfzzjsvPvCBD3TrMaZNm5ajaQqP9emc9emc9WF/Wltbs9sf+tCHuvQ9zc3N8fjjj3e479xzzz2o/R9zzDHZ7e3btx/UYxS7gi7GREQ0NDRERUVFHH/88VFbWxsNDQ0xYcKEpMcCAAAAAACAonLooYfGhRde2K3v/+pXv5rDiQqL9emc9emc9WF/vv3tb8fatWtjxYoV8e1vf7tL3zNs2LAOtzdv3nzQ+x8yZEg89dRT8fzzzxfMFYl6WsEXYyLeKcds27YtmpubY9KkSUmPw3tobm5+z88imz59emzbti2BiQAAAAAAAHi3Sy65JMrLyw/qe2tra+ODH/xgjicqLNanc9anc9an60rp/PKgQYNixIgRUV1dHR/+8Iff9+t/+tOfdrg9bdq0OOKIIw56//369YvTTz89TjrppDjuuOMO+nGKWVEUYwAAAAAAAIDuGzlyZMyfP/+Av2/ChAnxj//4j3mYqLBYn85Zn85ZH7pr9+7dcfHFF3e477bbbktomvRQjAEAAAAAAIASMnXq1Lj99tu7fGWLL3zhC3HPPfdE37598zxZYbA+nbM+nbM+dMe4ceM63L7vvvuirKwsoWnSQzEGAAAAAAAASsy0adNi1apV8a1vfWu/H98yZsyYWLhwYdx9993xgQ98oIcnTJb16Zz16Zz14WA0NzfH448/3uG+c889N6Fp0kUxBgAAAAAAAErQyJEj4yc/+Um8/PLLcfvtt8fQoUPjuOOOixtvvDFWr14dy5YtiwsuuCB69+6d9KiJsD6dsz6dsz4cqGHDhnW4vXnz5oQmSZ8+SQ8AAAAAAAAAJOfQQw+NadOmxU9/+tOIiPjOd76T8ESFxfp0zvp0zvrQFTfffHOH21OnTo0jjjgioWnSxxVjAAAAAAAAAAASsHv37pg+fXqH+26//faEpkknxRgAAAAAAAAAgASMGzeuw+3FixdHWVlZQtOkk2JMidj3B2fv3r0JTpJb+z4X4QAAAAAAAADQfc4vdy5X67Np06Z4/PHHO9z3l3/5lwf9eN2V1vPvijElol+/ftnttra2BCfJrX2fS//+/ROcBAAAAAAAACAdnF/uXK7W53//7//d4fbmzZsP+rFyIa3n3/skPQA9o6KiIru9adOm5AbJsX2fy8CBAxOcBAAAAAAAACAdnF/uXK7Wp70Y86//+q9x6623xhFHHHHQj5ULaT3/7ooxJaKqqiq73dzcnJrLXa1fvz67PWzYsAQnAQAAAAAAAEgH55c7l6v1GTRoUNx4442xevXqmDZt2kHPkytpPf+uGFMiKisro7KyMiIiduzYERs3bkx4otxoamrKbg8fPjzBSQAAAAAAAADSwfnlzuV6fU444YQoKyvr1mPkQlrPvyvGlJARI0Zktx999NEEJ8mNtra2ePLJJ7O3P/rRjyY4DQAAAAAAAEB6OL/cOetTPBRjSsi5556b3W5oaEhwktxobGyM7du3R0TEcccdFyNHjkx4IgAAAAAAAIB0cH65c9aneCjGlJCamprs9gMPPBAbNmxIcJruu+WWW7LbNTU1BXFpKQAAAAAAAIA0cH65c9aneCjGlJDhw4fHaaedFhERO3fujMsuuyzhiQ5eY2Nj/OpXv8renjJlSoLTAAAAAAAAAKSL88udsz7FQzGmxFx77bXZ7YULF8aCBQsSnObgvPLKK1FbW5u9PXXq1Dj11FMTnAgAAAAAAAAgfZxf7pz1KQ6KMSVmzJgx8dWvfjV7++tf/3pR/XBu3LgxPvOZz0RLS0tERBxyyCHx4x//OOGpAAAAAAAAANLH+eXOWZ/ioBhTgubOnRsnnnhiRETs3bs3Lrzwwpg8eXJBf+bZ7t2748Ybb4yRI0fGunXrIiKid+/eMX/+/Dj66KMTng4AAAAAAAAgnZxf7pz1KXyKMSXoiCOOiKVLl2Z/OCMifvGLX0RVVVWcd955sWDBgtiwYUPs3bs3wSkjXn/99Xjsscdi5syZcfzxx8cll1wS27dvj4h3fijvuuuu+PKXv5zojAAAAAAAAABp5vxy56xP4SvLZDKZpIcgGVu2bIm6urr4+c9//p5/P2DAgKiqqoojjzwy+vfvH7165bdHlclkYufOnfHGG29ES0tLbN68+T2/btiwYXHTTTfF+PHj8zoPAAAAAABAKRk7dmxERCxbtizROQqV9emc9elcGtbH+eXOWZ/CpRhDPProo3H55ZfH008/nfQonTrssMNi5syZcdlll0W/fv2SHgcAAAAAACBV0nDiPp+sT+esT+fStD7OL3fO+hSePkkPQPLGjBkTTz31VDQ1NUVDQ0Pcf//9sW7dunjttdcSnatv375RVVUVZ555ZlxwwQUxduzYKC8vT3QmAAAAAAAAgFLm/HLnrE/hccUY9mvbtm3R1NQU27dvj7fffjt64qXSt2/fGDBgQBx77LHx4Q9/OHr37p33fQIAAAAAAJCuK1rkg/XpnPXpXCmsj/PLnbM+yXHFGPZr0KBBcfrppyc9BgAAAAAAAAAFzvnlzlmf5PRKegAAAAAAAAAAAMgHxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAABSpKGhITZs2NBj+8tkMlFfXx87duzosX0CQFcpxgAAAAAAAEBKbN26NaZPnx7jxo3rkXJMJpOJmTNnxowZM+K2227L+/4A4EApxgAAAAAAAEBKVFZWxgMPPBCbNm3KezmmvRRz/fXXR11dXUyfPj1v+wKAg6UYAwAAAAAAACkyevToWLJkSV7LMe8uxcyZMyfKyspyvh8A6C7FGAAAAAAAAEiZfJZjlGIAKCaKMQAAAAAAAJBC+SjHKMUAUGwUYwAAAAAAACClclmOUYoBoBgpxgAAAAAAAECK5aIcoxQDQLFSjAEAAAAAAICU6045RikGgGKmGAMAAAAAAAAl4GDKMUoxABS7oijGtLa2Rk1NTdJjAAAAAAAAQFE7kHKMUgwAaVDwxZjW1ta4+OKLo6WlJelRAAAAAAAAoOh1pRyjFANAWhR0MeaKK66IQYMGxaJFi5IeBQAAAAAAAFKjs3KMUgwAaVLQxZjZs2dHJpOJ2bNnJz0KAAAAAAAApMq7yzFtbW1KMQCkTp+kB+iKioqKpEcAAAAAAACA1Gkvx3z2s5+NDRs2REVFRSxfvlwpBoDUKIpiTCGqq6uLVatWJT0GAAAAAAAAdFtVVVWsWrUq/vjHP8ZRRx0VK1eujHHjxiU9VkFpPzc4duzYROcoVNanc9aH7jrllFNi7ty5SY9RlAr6o5QAAAAAAACA/MpkMvHqq69mb7e2tsbOnTsTnAgAcscVYw6SJhYAAAAAAADFLpPJxMyZM2P58uXRt2/f6NOnT/Tu3Tu2bNkSjzzySBxzzDFJj1gw2q/0sWzZskTnKFTWp3PWB5LjijEAAAAAAABQgtpLMddff33U1dVF//79o7y8PJYsWRKbNm2KcePGxYYNG5IeEwC6RTEGAAAAAAAASsy7SzFz5syJsrKyiIgYPXq0cgwAqVEUxZjp06fHihUrkh4DAAAAAAAAil5npZh2yjEApEVRFGMAAAAAAACA7utKKaadcgwAaaAYAwAAAAAAACXgQEox7ZRjACh2ijEAAAAAAACQcgdTimmnHANAMVOMAQAAAAAAgBTrTimmnXIMAMVKMQYAAAAAAABSKhelmHbKMQAUI8UYAAAAAAAASKFclmLaKccAUGwUYwAAAAAAACBl8lGKaaccA0AxUYwBAAAAAACAFMlnKaadcgwAxUIxBgAAAAAAAFKiJ0ox7ZRjACgGijEAAAAAAACQEtu2bYv7778/76WYdu3lmC1btsRvfvObvO4LAA5Gn6QHAAAAAAAAAHKjsrIynnrqqaioqMh7Kabd6NGjo7m5OSorK3tkfwBwIBRjAAAAAAAAIEUGDRrU4/tUigGgUPkoJQAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVOqT9AAUlkwmE2vWrIkXXngh1q9fH83NzdHa2hptbW2RyWTyvv/y8vIYMGBAHHvssTF8+PAYPnx4nHrqqfHBD34w7/sGAAAAAAAAANJFMYaIiHj22WfjjjvuiIaGhvj973+f9Dgd9O/fP84555y44IIL4vzzz49+/folPRIAAAAAAAAAUAR8lFKJ27hxY0ydOjWqq6vj2muvLbhSTETE22+/HXfffXd85StfiZNOOikefPDBpEcCAAAAAAAAAIqAK8aUsF/+8pfxzW9+M954440O9w8cODDOOOOM7EcZDR48OPr27Ru9euW3R5XJZGL37t3x+uuvR0tLS6xfvz6ee+65WLt2bfZrmpqa4uyzz44pU6bErbfeGn379s3rTAAAAAAAAABA8VKMKVENDQ0xZcqU2LNnT/a+L37xi3HRRRfFhAkTCqpwsnbt2li4cGHMnTs3tm/fHhERd955Z7z11lvR0NBQULMCAAAAAAAAAIXDRymVoMbGxg6lmKqqqmhsbIy77747zjnnnIIrmpxwwgnxwx/+MF588cW48MILs/ffe++98Y1vfCO5wQAAAAAAAACAgqYYU2La2triW9/6VrYUM2LEiHjsscdi/PjxCU/2/o488sj42c9+FldccUX2vjvvvDMefPDBBKcCAAAAAAAAAAqVYkyJufbaa6OpqSkiIgYOHBgPP/xwHH300QlP1XVlZWVx9dVXx7Rp07L3XXLJJdHW1pbgVAAAAAAAAABAIVKMKSG7du2KOXPmZG9fddVVMWTIkAQnOjhlZWVx3XXXxcCBAyMioqmpKe65555khwIAAAAAAAAACo5iTAlZunRpbN26NSIijjnmmJgxY0bCEx28I488Murq6rK3GxoakhsGAAAAAAAAAChIijElZN/ySE1NTfTu3TvBabpv8uTJ2e1f//rX8eabbyY4DQAAAAAAAABQaBRjSsgTTzyR3f7Sl76U4CS5ccIJJ8SIESMiImLHjh3x7LPPJjwRAAAAAAAAAFBIFGNKxJ49e6KlpSV7++STT05wmtzZ93k0NTUlOAkAAAAAAAAAUGgUY0rESy+9FDt37oyIiMGDB8chhxyS8ES5MXz48Oz2+vXrE5wEAAAAAACAYtDQ0BAbNmzosf1lMpmor6+PHTt29Ng+AfhvijEl4qWXXspuH3/88QlOkltVVVXZ7X2fIwAAAAAAALzb1q1bY/r06TFu3LgeKcdkMpmYOXNmzJgxI2677ba87w+AP6UYUyL2baAeeuihCU6SW/te+UbLFgAAAAAAgM5UVlbGAw88EJs2bcp7Oaa9FHP99ddHXV1dTJ8+PW/7AmD/FGNKxK5du7Lb5eXlCU6SW/s+l/aPigIAAAAAAID9GT16dCxZsiSv5Zh3l2LmzJkTZWVlOd8PAO9PMaYEpemgm6bnAgAAAAAAQM/IZzlGKQagsCjGAAAAAAAAACUnH+UYpRiAwqMYAwAAAAAAAJSkXJZjlGIACpNiDAAAAAAAAFCyclGOUYoBKFyKMQAAAAAAAEBJ6045RikGoLApxgAAAAAAAAAl72DKMUoxAIWv4Isxra2tUVNTE4MGDYpBgwZFbW1t0iOxHy0tLVFWVhbz5s3rcH9ra2uUlZXFNddck9BkAAAAAAAA8P4OpByjFANQHAq+GDNq1KhobW2NFStWxMMPPxyNjY1RU1OT9Fi8h6FDh8bs2bOjtrY2Wltbs/fX1NTEhAkTYtasWckNBwAAAAAAAF3QlXKMUgxA8SjoYszKlSujpaUlGhoaYujQoVFdXR319fWxaNGipEdjP2bNmhXV1dXZ8tK8efPimWeeiYaGhoQnAwAAAAAAgK7prByjFANQXAq6GFNRURH19fVRUVGRvW/fK5FQmBoaGqKxsTGuueaaqK2tjZtvvrnDvyEAAAAAAAAUuneXY9ra2pRiAIpQn6QH6MzQoUNj+vTp2dstLS1xxRVXdLiPwjN06NCor6+P2tramDRpUkyaNCnpkQAAAAAAAOCAtZdjPvvZz8aGDRuioqIili9frhQDUEQKuhizr2uuuSZbiqmvr096nKirq4tVq1YlPUaXbdmypUf3t2LFioh4p8zUU5588skYO3Zsj+0PAAAAAAAgTd58882ICOdb3kNVVVWsWrUq/vjHP8ZRRx0VK1eujHHjxiU9VkFpP3fq9fPerA/ddcopp8TcuXOTHqMoFfRHKUW889FJo0aNioULF8aKFSsKohRD5xobG2PevHmxYsWK7FV+AAAAAAAAoBhlMpl49dVXs7dbW1tj586dCU4EwIEo+CvGjBo1KiZMmFBwhZhia2ItXrw4vvCFL+R9P62trVFTUxOzZs2K6urqaGhoiIkTJ8bkyZOjuro6r/s+44wzYvHixXndBwAAAAAAQFpVVFRERMSyZcsSnaOQZDKZmDlzZixfvjz69u0bffr0id69e8eWLVvikUceiWOOOSbpEQtG+5VQvH7em/WB5BT0FWMaGxujpaUlamtro6WlpcMfCtPFF18clZWVMXv27IiImDBhQkyfPj1qamoSngwAAAAAAAC6rr0Uc/3110ddXV30798/ysvLY8mSJbFp06YYN25cbNiwIekxAXgfBV2MWblyZUS8c9WYqqqqDn8oPIsWLYpFixZFQ0NDh/vr6+tj69atUVtbm9BkAAAAAAAA0HXvLsXMmTMnysrKIiJi9OjRyjEARaSgizGzZs2KTCbznn8oPJMmTYpMJvOeH5m0bdu2gvs4LAAAAAAAAHi3zkox7ZRjAIpHQRdjAAAAAAAAAHpKV0ox7ZRjAIqDYgwAAAAAAABQ8g6kFNNOOQag8CnGAAAAAAAAACXtYEox7ZRjAAqbYgwAAAAAAABQsrpTimmnHANQuBRjAAAAAAAAgJKUi1JMO+UYgMKkGAMAAAAAAACUnFyWYtopxwAUHsUYAAAAAAAAoKTkoxTTTjkGoLAoxpSIfQ/ke/fuTXCS3Nr3ueTqzQoAAAAAAADplc9STDvlGIDCoRhTIvr165fdbmtrS3CS3Nr3ufTv3z/BSQAAAAAAACh0PVGKaaccA1AYFGNKREVFRXZ706ZNyQ2SY/s+l4EDByY4CQAAAAAAAIVu27Ztcf/99+e9FNOuvRyzZcuW+M1vfpPXfQHw3vokPQA9o6qqKrvd3Nwce/fujV69ir8XtX79+uz2sGHDEpwEAAAAAACAQldZWRlPPfVUVFRU5L0U02706NHR3NwclZWVPbI/ADoq/mYEXVJZWZk92O7YsSM2btyY8ES50dTUlN0ePnx4gpMAAAAAAABQDAYNGtRjpZh2SjEAyVGMKSEjRozIbj/66KMJTpIbbW1t8eSTT2Zvf/SjH01wGgAAAAAAAACg0CjGlJBzzz03u93Q0JDgJLnR2NgY27dvj4iI4447LkaOHJnwRAAAAAAAAABAIVGMKSE1NTXZ7QceeCA2bNiQ4DTdd8stt2S3a2pqevySdwAAAAAAAABAYVOMKSHDhw+P0047LSIidu7cGZdddlnCEx28xsbG+NWvfpW9PWXKlASnAQAAAAAAAAAKkWJMibn22muz2wsXLowFCxYkOM3BeeWVV6K2tjZ7e+rUqXHqqacmOBEAAAAAAAAAUIgUY0rMmDFj4qtf/Wr29te//vWiKsds3LgxPvOZz0RLS0tERBxyyCHx4x//OOGpAAAAAAAAAIBCpBhTgubOnRsnnnhiRETs3bs3Lrzwwpg8eXJs2LAh4cn2b/fu3XHjjTfGyJEjY926dRER0bt375g/f34cffTRCU8HAAAAAAAAABQixZgSdMQRR8TSpUuz5ZiIiF/84hdRVVUV5513XixYsCA2bNgQe/fuTXDKiNdffz0ee+yxmDlzZhx//PFxySWXxPbt2yPinVLMXXfdFV/+8pcTnREAAAAAAAAAKFx9kh6AZBx55JGxbNmyqKuri5///OcREbFz586499574957742IiAEDBkRVVVUceeSR0b9//+jVK789qkwmEzt37ow33ngjWlpaYvPmze/5dcOGDYubbropxo8fn9d5AAAAAAAAAIDiphhTwg4//PBYsGBBXHzxxXH55ZfH008/3eHvd+zYEatXr05ouj912GGHxcyZM+Oyyy6Lfv36JT0OAAAAAAAAAFDgFGOIMWPGxFNPPRVNTU3R0NAQ999/f6xbty5ee+21ROfq27dvVFVVxZlnnhkXXHBBjB07NsrLyxOdCQAAAAAAAAAoHooxZA0bNiyuvPLKuPLKKyMiYtu2bdHU1BTbt2+Pt99+OzKZTN5n6Nu3bwwYMCCOPfbY+PCHPxy9e/fO+z4BAAAAAAAAgHRSjGG/Bg0aFKeffnrSYwAAAAAAAAAAHJReSQ8AAAAAAAAAAAD5oBgDAAAAAAAAAEAqKcYAAAAAAAAAAJBKijEAAAAAAAAAAKSSYgwAAAAAAAAAAKmkGAMAAAAAAAAAQCopxgAAAAAAAAAAkEqKMQAAAAAAAAAApJJiDAAAAAAAAAAAqaQYAwAAAAAAAABAKinGAAAAAAAAAACQSooxAAAAAAAAAACkkmIMAAAAAAAAAACppBgDAAAAAAAAAEAqKcYAAAAAAAAAAJBKijEAAAAAAAAAAKSSYgwAAAAAAAAAAKmkGAMAAAAAAAAAQCopxgAAAAAAAAAAkEqKMQAAAAAAAAAApJJiDAAAAAAAAAAAqaQYAwAAAAAAAABAKinGAAAAAAAAAACQSooxAAAAAAAAAACkkmIMAAAAAAAAAACppBgDAAAAAAAAAEAqKcYAAAAAAAAAEBERDQ0NsWHDhh7bXyaTifr6+tixY0eP7RMoLYoxAAAAAAAAAMTWrVtj+vTpMW7cuB4px2QymZg5c2bMmDEjbrvttrzvDyhNijEAAAAAAAAARGVlZTzwwAOxadOmvJdj2ksx119/fdTV1cX06dPzti+gtCnGAAAAAAAAABAREaNHj44lS5bktRzz7lLMnDlzoqysLOf7AYhQjAEAAAAAAABgH/ksxyjFAD1NMQYAAAAAAACADvJRjlGKAZKgGAMAAAAAAADAn8hlOUYpBkiKYgwAAAAAAAAA7ykX5RilGCBJijEAAAAAAAAA7Fd3yjFKMUDSFGMAAAAAAAAA6NTBlGOUYoBCUPDFmJUrV8aoUaOirKwsBg0aFFdccUXSIwEAAAAAAACUnAMpxyjFAIWi4Isx48ePjwkTJkRzc3PcfPPNcc0118S8efOSHgsAAAAAAACg5HSlHKMUAxSSgi7GNDY2RkTE7NmzY+jQoTFp0qSYNGlSPPTQQwlPBgAAAAAAAFCaOivHKMUAhaagizETJkyI//zP/+xwX0tLS5x++ukJTQQAAAAAAADAu8sxbW1tSjFAQSroYkxEREVFRUREjBo1KgYNGhSVlZUxa9asZIcCAAAAAAAAKHH7lmNWrVoVL774olIMUHDKMplMJukhumLlypXR2NgY9fX1ccUVV8T06dMTnaeuri5WrVqV6AwAAAAAAACQK48//nhERHzqU59KeJLCZH32b/v27dlzp0cddVR85CMfUYp5l/b1OeWUUxKdg+J1yimnxNy5c5Meoyj1SXqAzrS2tkbEO1eNqa6ujurq6hg6dGhBFGMAAAAAAAAASl0mk4lXX301e7u1tTV27twZ/fr1S3AqgP9W0MWYefPmxcKFC2PFihUd7t+6dWtCE/03TSwAAAAAAADSpKKiIiIili1blugchcr6/KlMJhMzZ86M5cuXR9++faNPnz7Ru3fv2LJlSzzyyCNxzDHHJD1iwRg7dmxEeP1AEnolPUBnJk2aFCtXrox58+ZFa2trrFy50tViAAAAAAAAABLWXoq5/vrro66uLvr37x/l5eWxZMmS2LRpU4wbNy42bNiQ9JgAhV2MGTp0aDz00ENRX18fgwYNipqampg0aVLMnj076dEAAAAAAAAAStK7SzFz5syJsrKyiIgYPXq0cgxQUMoymUwm6SEAAAAAAACAZLV/VFBra2uicxQq6/OO/ZVi3r0+v/3tb+Ozn/1sDB482McqhY9SgiQV9BVjAAAAAAAAACgMnV0p5t1cOQYoFIoxAAAAAAAAAHTqQEox7ZRjgEKgGAMAAAAAAADAfh1MKaadcgyQNMUYAAAAAAAAAN5Td0ox7ZRjgCQpxgAAAAAAAADwJ3JRimmnHAMkRTEGAAAAAAAAgA5yWYpppxwDJEExBgAAAAAAAICsfJRi2inHAD1NMQYAAAAAAACAiMhvKaadcgzQkxRjAAAAAAAAAOiRUkw75RigpyjGAAAAAAAAABDbtm2L+++/P++lmHbt5ZgtW7bEb37zm7zuCyhdfZIeAAAAAAAAAIDkVVZWxlNPPRUVFRV5L8W0Gz16dDQ3N0dlZWWP7A8oPYoxAAAAAAAAAERExKBBg3p8n0oxQD75KCUAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFTqk/QAFJZMJhNr1qyJF154IdavXx/Nzc3R2toabW1tkclk8r7/8vLyGDBgQBx77LExfPjwGD58eJx66qnxwQ9+MO/7BgAAAAAAAADSRTGGiIh49tln44477oiGhob4/e9/n/Q4HfTv3z/OOeecuOCCC+L888+Pfv36JT0SAAAAAAAAAFAEfJRSidu4cWNMnTo1qqur49prry24UkxExNtvvx133313fOUrX4mTTjopHnzwwaRHAgAAAAAAAACKgCvGlLBf/vKX8c1vfjPeeOONDvcPHDgwzjjjjOxHGQ0ePDj69u0bvXrlt0eVyWRi9+7d8frrr0dLS0usX78+nnvuuVi7dm32a5qamuLss8+OKVOmxK233hp9+/bN60wAAAAAAAAAQPFSjClRDQ0NMWXKlNizZ0/2vi9+8Ytx0UUXxYQJEwqqcLJ27dpYuHBhzJ07N7Zv3x4REXfeeWe89dZb0dDQUFCzAgAAAAAAAACFw0cplaDGxsYOpZiqqqpobGyMu+++O84555yCK5qccMIJ8cMf/jBefPHFuPDCC7P333vvvfGNb3wjucEAAAAAAAAAgIKmGFNi2tra4lvf+la2FDNixIh47LHHYvz48QlP9v6OPPLI+NnPfhZXXHFF9r4777wzHnzwwQSnAgAAAAAAAAAKlWJMibn22mujqakpIiIGDhwYDz/8cBx99NEJT9V1ZWVlcfXVV8e0adOy911yySXR1taW4FQAAAAAAAAAQCFSjCkhu3btijlz5mRvX3XVVTFkyJAEJzo4ZWVlcd1118XAgQMjIqKpqSnuueeeZIcCAAAAAAAAAAqOYkwJWbp0aWzdujUiIo455piYMWNGwhMdvCOPPDLq6uqytxsaGpIbBgAAAAAAAAAoSIoxJWTf8khNTU307t07wWm6b/LkydntX//61/Hmm28mOA0AAAAAAAAAUGgUY0rIE088kd3+0pe+lOAkuXHCCSfEiBEjIiJix44d8eyzzyY8EQAAAAAAAABQSBRjSsSePXuipaUle/vkk09OcJrc2fd5NDU1JTgJAAAAAAAAAFBoFGNKxEsvvRQ7d+6MiIjBgwfHIYcckvBEuTF8+PDs9vr16xOcBAAAAAAAAEi7hoaG2LBhQ4/tL5PJRH19fezYsaPH9glpoxhTIl566aXs9vHHH5/gJLlVVVWV3d73OQIAAAAAAADk0tatW2P69Okxbty4HinHZDKZmDlzZsyYMSNuu+22vO8P0koxpkTs2yA89NBDE5wkt/a98o2WJAAAAAAAAJAvlZWV8cADD8SmTZvyXo5pL8Vcf/31UVdXF9OnT8/bviDtFGNKxK5du7Lb5eXlCU6SW/s+l/aPigIAAAAAAADIh9GjR8eSJUvyWo55dylmzpw5UVZWlvP9QKlQjClBaQrNND0XAAAAAAAAoPDlsxyjFAO5pxgDAAAAAAAAAAcgH+UYpRjID8UYAAAAAAAAADhAuSzHKMVA/ijGAAAAAAAAAMBByEU5RikG8ksxBgAAAAAAAAAOUnfKMUoxkH+KMQAAAAAAAADQDQdTjlGKgZ5RVMWYlpaWWLRoUdJjsB8tLS1RVlYW8+bN63B/a2trlJWVxTXXXJPQZAAAAAAAAAD5dSDlGKUY6DlFVYyZOHFi1NfXJz0G+zF06NCYPXt21NbWRmtra/b+mpqamDBhQsyaNSu54QAAAAAAAADyrCvlGKUY6FlFU4ypra2NlpaWpMfgfcyaNSuqq6ujpqYmIiLmzZsXzzzzTDQ0NCQ8GQAAAAAAAED+dVaOUYqBnlcUxZjGxsZobGx0xZEi0dDQEI2NjXHNNddEbW1t3HzzzVFRUZH0WAAAAAAAAAA94t3lmLa2NqUYSEifpAd4P62trVFTUxMPP/xwNDY2Jj0OXTB06NCor6+P2tramDRpUkyaNCnpkQAAAAAAAAB6VHs55rOf/Wxs2LAhKioqYvny5Uox0MMKvhhTU1MTV155ZVRXVxdUMaauri5WrVqV9BhdtmXLlh7d34oVKyIievTjr5588skYO3Zsj+0PAAAAAAAgTd58882ICOdb9sP6dM767F9VVVWsWrUq/vjHP8ZRRx0VK1eujHHjxiU9FkXmlFNOiblz5yY9RlEq6I9Suuaaa2Lr1q0xffr0aG1tjddeey22bt0ara2tSY9GJxobG2PevHmxYsWKaGlpiSuuuCLpkQAAAAAAAAB6XCaTiVdffTV7u7W1NXbu3JngRFB6CvqKMc3NzbFy5coYNGhQh/sHDRoUzc3NMXTo0IQmi6JrYi1evDi+8IUv5H0/7R99NWvWrKiuro6GhoaYOHFiTJ48Oaqrq/O67zPOOCMWL16c130AAAAAAACkVUVFRURELFu2LNE5CpX16Zz1+VOZTCZmzpwZy5cvj759+0afPn2id+/esWXLlnjkkUfimGOOSXpEKAkFfcWY+vr6yGQy2T+zZ8+OCRMmRCaTSbQUw/5dfPHFUVlZGbNnz46IiAkTJsT06dOjpqYm4ckAAAAAAAAAekZ7Keb666+Purq66N+/f5SXl8eSJUti06ZNMW7cuNiwYUPSY0JJKOhiDMVl0aJFsWjRomhoaOhwf319fWzdujVqa2sTmgwAAAAAAACgZ7y7FDNnzpwoKyuLiIjRo0crx0APK6pizKxZs+Khhx5Kegz2Y9KkSZHJZN7zI5O2bdsW9fX1CUwFAAAAAAAA0DM6K8W0U46BnlVUxRgAAAAAAAAAKERdKcW0U46BnqMYAwAAAAAAAADdcCClmHbKMdAzFGMAAAAAAAAA4CAdTCmmnXIM5J9iDAAAAAAAAAAchO6UYtopx0B+KcYAAAAAAAAAwAHKRSmmnXIM5I9iDAAAAAAAAAAcgFyWYtopx0B+KMYAAAAAAAAAQBfloxTTTjkGck8xpkTsG8R79+5NcJLc2ve55OpgAwAAAAAAAPBe8lmKaaccA7mlGFMi+vXrl91ua2tLcJLc2ve59O/fP8FJAAAAAAAAgDTriVJMO+UYyB3FmBJRUVGR3d60aVNyg+TYvs9l4MCBCU4CAAAAAAAApNm2bdvi/vvvz3sppl17OWbLli3xm9/8Jq/7gjTrk/QA9IyqqqrsdnNzc+zduzd69Sr+XtT69euz28OGDUtwEgAAAAAAACDNKisr46mnnoqKioq8l2LajR49Opqbm6OysrJH9gdpVPzNCLqksrIyG5Y7duyIjRs3JjxRbjQ1NWW3hw8fnuAkAAAAAAAAQNoNGjSox0ox7ZRioHsUY0rIiBEjstuPPvpogpPkRltbWzz55JPZ2x/96EcTnAYAAAAAAAAAKDSKMSXk3HPPzW43NDQkOEluNDY2xvbt2yMi4rjjjouRI0cmPBEAAAAAAAAAUEgUY0pITU1NdvuBBx6IDRs2JDhN991yyy3Z7Zqamh6/ZBkAAAAAAAAAUNgUY0rI8OHD47TTTouIiJ07d8Zll12W8EQHr7GxMX71q19lb0+ZMiXBaQAAAAAAAACAQqQYU2Kuvfba7PbChQtjwYIFCU5zcF555ZWora3N3p46dWqceuqpCU4EAAAAAAAAABQixZgSM2bMmPjqV7+avf31r3+9qMoxGzdujM985jPR0tISERGHHHJI/PjHP054KgAAAAAAAACgECnGlKC5c+fGiSeeGBERe/fujQsvvDAmT54cGzZsSHiy/du9e3fceOONMXLkyFi3bl1ERPTu3Tvmz58fRx99dMLTAQAAAAAAAACFqCyTyWSSHoKet3nz5vjMZz4Ta9asyd7Xt2/fOOuss6KmpibGjh0bQ4YMiV69kutOvf766/Hcc8/F3XffHYsWLepQ3Ondu3fcddddMWnSpMTmAwAAAAAASJOKioqIiGhtbU10jkJlfTpnfTpnfSA5ijElbMuWLVFXVxc///nP3/PvBwwYEFVVVXHkkUdG//79816SyWQysXPnznjjjTeipaUlNm/e/J5fN2zYsLjpppti/PjxeZ0HAAAAAACglDhx3znr0znr0znrA8lRjCEeffTRuPzyy+Ppp59OepROHXbYYTFz5sy47LLLol+/fkmPAwAAAAAAkCpO3HfO+nTO+nTO+kBy+iQ9AMkbM2ZMPPXUU9HU1BQNDQ1x//33x7p16+K1115LdK6+fftGVVVVnHnmmXHBBRfE2LFjo7y8PNGZAAAAAAAAAIDi4Yox7Ne2bduiqakptm/fHm+//Xb0xEulb9++MWDAgDj22GPjwx/+cPTu3Tvv+wQAAAAAAMAVLd6P9emc9emc9YHkuGIM+zVo0KA4/fTTkx4DAAAAAAAAAOCg9Ep6AAAAAAAAAAAAyAfFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCVFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASKU+SQ9AYclkMrFmzZp44YUXYv369dHc3Bytra3R1tYWmUwm7/svLy+PAQMGxLHHHhvDhw+P4cOHx6mnnhof/OAH875vgEImn4GkyB8gKfIHgGLk+AUAAIVHMYaIiHj22WfjjjvuiIaGhvj973+f9Dgd9O/fP84555y44IIL4vzzz49+/folPRJAj5HPQFLkD5AU+QNAMXL8AgCAwlWW6YmaOgVr48aNcfnll8cdd9yR9ChdMmzYsPjnf/7nOOuss5IeBSCv5DOQFPkDJEX+AFCMHL+AtKmoqIiIiNbW1kTnKFTWp3PWp3PWB5KjGFPCfvnLX8Y3v/nNeOONNzrcP3DgwDjjjDOyl9ocPHhw9O3bN3r16pXXeTKZTOzevTtef/31aGlpifXr18dzzz0Xa9eu/ZOvnTJlStx6663Rt2/fvM4EkAT5DCRF/gBJkT8AFCPHLyCNnLjvnPXpnPXpnPWB5PgopRLV0NAQU6ZMiT179mTv++IXvxgXXXRRTJgwoaB+IVq7dm0sXLgw5s6dG9u3b4+IiDvvvDPeeuutaGhoKKhZAbpLPgNJkT9AUuQPAMXI8QsAAIqHK8aUoMbGxjjrrLOyv7RVVVVFfX19jB8/PuHJOrd58+a47LLL4vbbb8/eN2XKlKK5TCnA+5HPQFLkD5AU+QNAMXL8AtLMFS06Z306Z306Z30gOYoxJaatrS1OOumkaGpqioiIESNGxNKlS+Poo49OeLKuyWQyceWVV8bs2bOz9z3wwAM+ExdK2K5du2LNmjWxYsWK2LBhQyxevDgymUycc845UVFRESeffHJUV1dHZWVl0qN2Sj5D8ZE/hUH+UIrkT2GQPwAHxvGrMDh+UYrSkj89xYn7zlmfzlmfzlkfSI5iTIm56qqr4vvf/35EvPNZt//xH/8RQ4YMSXiqA5PJZOJrX/taLFiwICIihg0bFqtXr45+/folPBnQU5qamuLmm2+OZcuWxXPPPRdtbW3ZvysrK4uysrLIZDKx7yHu+OOPjz//8z+PadOmxdlnnx29e/dOYvT9ks9QHORPYZI/lAL5U5jkD0DnHL8Kk+MXpSCN+dNTnLjvnPXpnPXpnPWB5CjGlJBdu3bFUUcdFVu3bo2IiBtvvDG+853vJDzVwdm8eXN85CMfyX4m7l133RWTJ09OeCogn/bs2RO//vWv41/+5V/i3//936NPnz5x5plnxmmnnRajRo2KUaNGRVVVVfayxY888khs3bo1Vq5cGStWrIgVK1bEY489Fps2bYrjjjsuZsyYEf/zf/7POOKIIxJ+ZvIZCp38KQ7yhzSSP8VB/gB05PhVHBy/SKM0509PcuK+c9anc9anc9YHEpShZDz44IOZiMhEROaYY47J7N69O+mRuuXv//7vs8/ny1/+ctLjAHn0zDPPZD72sY9lIiIzZMiQzD/8wz9kXn755ff82jFjxmTGjBnznn+3c+fOTENDQ2bcuHGZiMj0798/c9111yWeh/IZCpf8KS7yhzSRP8VF/gC8w/GruDh+kSZpz5+eNHDgwMzAgQOTHqNgWZ/OWZ/OWR9ITq+eKN9QGBoaGrLbNTU1RX8ZwH3/B8Ovf/3rePPNNxOcBsiHtra2+P73vx+f+MQn4rXXXou77rorfve738UPfvCDg7pMcXl5eUyaNCmWLl0aa9asiYkTJ8bf/u3fxqc//el48cUX8/AMukY+Q+GRP8VJ/pAG8qc4yR+g1Dl+FSfHL9KgVPIHAOgexZgS8sQTT2S3v/SlLyU4SW6ccMIJMWLEiIiI2LFjRzz77LMJTwTkUlNTU5x22mlx1VVXxYUXXhirV6+OyZMnR3l5eU4ef+TIkfFv//Zvcfvtt8fatWvj5JNPjptvvjknj32g5DMUFvlTvOQPxU7+FC/5A5Qyx6/i5fhFsSul/AEAukcxpkTs2bMnWlpasrdPPvnkBKfJnX2fR1NTU4KTALn0/PPPx6c+9al45ZVX4r777ov58+fHoEGDcr6fsrKymDZtWqxZsybGjBkT06dPj3/6p3+KTCaT833tj3yGwiJ/ip/8oVjJn+Inf4BS5PhV/By/KFallD8AQPcpxpSIl156KXbu3BkREYMHD45DDjkk4YlyY/jw4dnt9evXJzgJkCtr166NcePGRe/evWP58uVx7rnn5n2fRx99dCxevDimTp0a3/ve9+JHP/pR3vfZTj5D4ZA/8geSIn/kD0Axcvxy/IKklFr+HKyGhobYsGFDj+0vk8lEfX197Nixo8f2CQBd1SfpAegZL730Unb7+OOPT3CS3Kqqqspu7/scgeL08ssvx8SJE6NPnz7x6KOPxrBhw3ps3+Xl5XHbbbdFRMR3v/vdOPzww+Piiy/O+37lMxQG+SN/ICnyR/4AFCPHL8cvSEop5s/B2Lp1a0yfPj0OP/zweOSRR+KYY47J6/4ymUzMnDkzrr/++oiIqK2tzev+AOBAuWJMidi3oXvooYcmOElu7fs/M7SQobhlMpm46KKLYtu2bbFkyZIe/aW2Xa9evWL+/Pnxuc99Lv76r/86XnzxxbzvUz5D8uSP/IGkyB/5A1CMHL8cvyAppZo/B6OysjIeeOCB2LRpU4wbNy6vV47ZtxRTV1cX06dPz9u+AOBgKcaUiF27dmW3y8vLE5wkt/Z9Lu2XMgWK06233hoPPvhg/OhHP4qPf/zjic1RXl4e8+fPjwEDBsQ3v/nN2LNnT173J58hefJH/kBS5I/8AShGjl+OX5CUUs2fgzV69OhYsmRJXssx7y7FzJkzJ8rKynK+HwDoLsWYEpSmNyVpei5QyjZs2BB1dXUxZsyY+M53vpP0OHH00UfHDTfcEE8++WT28p89IU2ZlqbnQrrJn3ek6Wc2Tc+FdJM/70jTz2yangvA/jh+vSNNmZ+m50K6yZ+Dk89yjFIMAMVEMQaAxF1xxRWxe/fuuOWWW6JXr8I4NE2dOjU+//nPx/e+97149dVXkx4HyBP5AyRF/gBQjBy/gKTIn4OXj3KMUgwAxaYw3j0AULL++Mc/RkNDQ9TW1kZVVVXS42SVlZXFj370o3j77bdj/vz5SY8D5IH8AZIifwAoRo5fQFLkT/flshyjFANAMVKMgR7y5ptvRn19ffzFX/xFDBs2LI499tj4+Mc/HpdeemmsW7cu6fEgMbfcckvs2rUrZsyYkfQof2LkyJExduzY+Nd//deC/axguk8+ly75A4Utzfksf6CwpTl/oDscv0iafC5d8ic3clGOUYoBoFgpxkCe7dy5M2bNmhVDhgyJGTNmxOOPPx7Nzc3xhz/8IZ5//vm44YYb4oQTTojx48fHmjVrkh4XetTu3bujvr4+Jk6cGB/5yEeSHuc9ffvb347f/e538eCDDyY9Cjkmn0ub/IHClfZ8lj9QuNKeP9Adjl8kST6XNvmTW90pxyjFAFDMFGMgj956660455xz4sc//nG88cYbnX7t0qVL48wzz4zHHnush6aD5D322GPxhz/8IWpra5MeZb/OP//8GDx4cNx+++1Jj0IOyWfkDxSmUshn+QOFqRTyB7rD8YukyGfkT+4dTDlGKQaAYlfwxZgrrrgiysrKOvwp5DdAaTdx4sQ/+fcYNGhQ1NTURGtra5cfp6qqKhobG/M3aAHYs2dPTJkyJR5++OEuf8/27dvj85//vP/ZQMl46qmnIiJi3LhxCU+yf+Xl5fGpT30qnn766aRH6ZR87jr5TIT8ySX5Q66USj7Ln9yRP+RKqeQPdIfjV+44fnWdfCZC/uTLgZRjlGIASIOCL8asXLkyZs2aFStWrMj+mT17dtJjlbTp06dHc3Nz9k9DQ0M0NjbGxRdfnPRoBWXRokWxePHiA/6+7du3x6WXXpqHiaDwrFixIo4//viorKxMepROjRo1KlpaWmLbtm1Jj9Ip+dw18pkI+ZNr8odcKJV8lj+5JX/IhVLJH+gOx6/ccvzqGvlMhPzJp66UY5RiAEiLgi/GtLS0xMSJE6O6ujr7p6KiIumxSlpFRUUMHTo0+2fChAkxe/bsDv9Dof3fraysLKqqquKaa67J/l37G8SJEyd2uD9tfvKTnxz09z788MOxbt26HE4DhemZZ56JUaNGJT3G+2qfceXKlQlP0jn53DXymQj5k2vyh1wolXyWP7klf8iFUskf6A7Hr9xy/Ooa+UyE/Mm3zsoxSjEApElRFGNmz54dgwYNikGDBsUVV1yR9Ejsx76N7YkTJ0ZFRUU0NzdHfX19XH311TFv3ryIeKfhPXTo0HjooYdi1qxZSY2bV6tXr47ly5d36zFuuummHE0Dhen111+P//zP/4zq6uqkR3lf7TOuWrUq2UEOknz+b/KZCPnTk+QPXVUq+Sx/eo78oatKJX+gOxy/eo7j13+Tz0TIn57y7nLM3r17lWIASJ0+SQ/QmZaWloh45w1FfX19tLS0RE1NTUSEj1NKUGtra/bzbrdu3ZotL7WXlhobG2Pr1q3R0NAQERFDhw6NK6+8MmbPnh3Tp09PauwetWzZsm4/xiOPPNL9QaCAbd++PSIijjjiiIQneX+HHXZYRPz3zIVKPr8/+UyE/MkH+UN3lUo+y5/ckz90V6nkD3SH41fuOX69P/lMhPzpSe3lmM9+9rPx5ptvRp8+fZRiAEiVgi7GDB06NDKZTIfbN998c1x88cWJF2Pq6uqKqvm7ZcuWnD3WvHnzsv87oV11dXX2l7KVK1fGaaed1uHvJ0yYkPer/Tz55JMxduzYvO6jq37/+993+zFeeOGFgnk+kA//9V//FRER1113XSxYsCBnj9uezbn++SkrK4v/83/+T7f/t9K7yeeeJZ+JkD/t5A+FpFTyWf68Q/5QSEolf6A7HL/e4fjVs+QzEfInCVVVVbFq1arYtWtXHHXUUbFy5coYN25c0mMVlDfffDMicv/6SQvr0znrQ3edcsopMXfu3KTHKEoF/1FK7zZ06NBsm55kzJo1KzKZTPbPihUrorW1NWpra5MerWDkoj3dq1fR/XjCAWn/Odm3AFnIimFO+fz+5DMR8icf5A/dVSr5LH9yT/7QXaWSP9Adjl+55/j1/uQzEfKnp2UymXj11Vezt1tbW2Pnzp0JTgQAuVPQV4xZtGhR1NfXx0MPPZS9r6WlJSoqKpIb6v8rtibW4sWL4wtf+EJeHru6ujomTZoUK1euzN6++uqrO3zNM888E0OHDs3L/tudccYZsXjx4rzuo6tuv/32+NrXvtatxzjttNNycslQKFSvvPJKDBkyJC699NL41re+lbPHbW9a5/LnZ8+ePdGnT5+4/PLL4wc/+EHOHjdCPvc0+UyE/GknfygkpZLP8ucd8odCUir5A93h+PUOx6+eJZ+JkD89KZPJxMyZM2P58uVRV1cXF1xwQXzuc5+LLVu2xCOPPBLHHHNM0iMWjPZzlPLlvVmfzlkfSE5BV6arq6ujsbExamtro6WlJRobG+OKK66IK6+8MunReJfDDjsstm7dGhHvXNazsrIyampqOvy7vftSny0tLUmM2iPOO++8+MAHPtCtx5g2bVqOpoHCdPjhh0e/fv2iubk56VHeV1NTU0REUf4CKJ87ks9EyJ+eIn84EKWSz/KnZ8gfDkSp5A90h+NXz3D86kg+EyF/ekp7Keb666+Purq6mDNnTnzyk5+MJUuWxKZNm2LcuHGxYcOGpMcEgG4p6GLM0KFDY8WKFdHS0hJVVVVRW1sbtbW1MWvWrKRH412qq6tj5cqV2f/V8NBDD0Vra2v23+3KK6/MfkZuRGT/La+55pqkRs6rQw89NC688MJuff9Xv/rVHE4Ehae8vDxOPvnkWLFiRdKjvK/2GUeNGpXwJAdOPnckn4mQPz1F/nAgSiWf5U/PkD8ciFLJH+gOx6+e4fjVkXwmQv70hPcqxbR/hNXo0aOVYwBIjYL+KKWId34h2PejlEjW/v4tJkyY0OHzM4cOHdrpv9usWbNSX3C65JJL4pZbboldu3Yd8PfW1tbGBz/4wTxMBYVl1KhR8fOf/zz27t1b0J/7vGLFiujXr1+MHDky6VH2Sz53nXwmQv7kkvwhV0oln+VP7sgfcqVU8ge6w/Erdxy/uk4+EyF/8qmzUky79nLMZz/72Rg3bpyPVQKgaBXuuwgociNHjoz58+cf8PdNmDAh/vEf/zEPE0HhGTVqVLz++uuxfv36pEfp1IoVK+KUU06J8vLypEchB+QzEfIHClGp5LP8gcJTKvkD3eH4RRLkMxHyJ1+6Uopp58oxAKSBYgzk0dSpU+P222/v8pvhL3zhC3HPPfdE37598zwZFIYxY8ZERMSiRYsSnmT/Nm7cGI8//niMHTs26VHIIfmM/IHCVAr5LH+gMJVC/kB3OH6RFPmM/Mm9AynFtFOOAaDYKcZAnk2bNi1WrVoV3/rWt/Z7+c4xY8bEwoUL4+67744PfOADPTwhJGfYsGExYcKEqK+vj927dyc9znu6+eabY+/evXHxxRcnPQo5Jp9Lm/yBwpX2fJY/ULjSnj/QHY5fJEk+lzb5k1sHU4pppxwDQDFTjIEeMHLkyPjJT34SL7/8ctx+++0xdOjQOO644+LGG2+M1atXx7Jly+KCCy6I3r17Jz0q9Lhvf/vb8Yc//CHuv//+pEf5E7t27Yp58+bFWWedFVVVVUmPQx7I59Imf6BwpT2f5Q8UrrTnD3SH4xdJks+lTf7kRndKMe2UYwAoVoox0IMOPfTQmDZtWnz4wx+O//E//kd85zvfiRNPPDHpsSBRn//85+NDH/pQ3HDDDZHJZJIep4Nf/vKXsXHjxvj2t7+d9CjkmXwuTfIHCl9a81n+QOFLa/5Adzh+UQjkc2mSP92Xi1JMO+UYAIqRYgwAierTp09cfvnlsXTp0rjjjjuSHidr27Zt8Td/8zfxsY99LM4+++ykxwHyQP4ASZE/ABQjxy8gKfKne3JZimmnHANAsVGMASBxf/VXfxVnnHFGXHLJJfHKK68kPU5ERMycOTM2b94ct956q8vwQorJHyAp8geAYuT4BSRF/hycfJRi2inHAFBMFGNKxL5vdPbu3ZvgJLm173PJ1Zs5oOf17t075s+fHzt27IgZM2YkfknU+++/P372s5/Fd7/73aiurs7rvuQzJEv+vEP+QM+TP++QPwDFxfHrHY5f0PNKOX8OVj5LMe2UYwAoFooxJaJfv37Z7ba2tgQnya19n0v//v0TnAToro985CNx1VVXxb333htXXXVVYnP8x3/8R3z961+Pj33sY/H9738/7/uTz5A8+SN/ICnyR/4AFCPHL8cvSEqp5s/B6IlSTDvlGACKQZ+kB6BnVFRUZLc3bdqU3CA5tu9zGThwYIKTALlQV1cXq1atir/7u7+LQw45JC699NIe3f/69etj4sSJUV5eHr/61a+ib9++ed+nfIbCIH/kDyRF/sgfgGLk+OX4BUkpxfw5GNu2bYv7778/76WYdu3lmLPPPjt+85vfRE1NTV73BwAHSjGmRFRVVWW3m5ubY+/evdGrV/FfMGj9+vXZ7WHDhiU4CZALvXr1iltuuSXefPPNqKurizfeeCO+973v9cilfJ977rn43Oc+F3v27ImlS5d2yM18ks9QGOSP/IGkyB/5A1CMHL8cvyAppZg/B6OysjKeeuqpqKio6LGPSRs9enQ0NzdHZWVlj+wPAA5E8b9zp0sqKyuzb0Z27NgRGzduTHii3GhqaspuDx8+PMFJgFwpLy+PX/ziF3HhhRfG3/3d38X5558fr7zySt72t3fv3rjhhhvik5/8ZJSXl8djjz0WH/vYx/K2v3eTz1A45I/8gaTIH/kDUIwcvxy/ICmllj8Ha9CgQT1WimmnFANAoVKMKSEjRozIbj/66KMJTpIbbW1t8eSTT2Zvf/SjH01wGiCX+vTpE7feemtcd911sWTJkjjxxBNjwYIFkclkcrqf5ubmGDduXFx66aUxbty4+O1vf9shK3uKfIbCIX+Km/yhmMmf4iZ/gFLl+FXcHL8oZqWWPwBA9yjGlJBzzz03u93Q0JDgJLnR2NgY27dvj4iI4447LkaOHJnwREAu9erVK/7mb/4mVq1aFSeccEJceOGFMX78+Ljnnnti9+7d3XrsF154IWbOnBkf//jH47nnnov58+fHfffdFx/60IdyNP2Bkc9QWORP8ZI/FDv5U7zkD1DKHL+Kl+MXxa6U8gcA6B7FmBJSU1OT3X7ggQdiw4YNCU7Tfbfcckt2u6ampscvCQj0jI9+9KOxfPnyuP7662P9+vXxxS9+MY4//vj4x3/8x3jhhRdi7969XXqc1157LRYtWhQTJ06MESNGxL/8y7/E+eefH6tXr45vfOMbiWaIfIbCJH+Kj/whLeRP8ZE/AI5fxcjxi7QohfwBALqnLJPr68pR0E4//fR45plnIiJi8uTJcddddyU80cFpbGyMiRMnZm+vXLkyTj311AQnOjBjx46NiIhly5YlOgcUm927d8d9990XP/nJT+Khhx6KiIhDDjkkqqurY9SoUTFs2LC4/vrro6ysLP7mb/4mXn311Vi5cmWsWLEifve730VExIc//OGYMWNG/K//9b9i8ODBCT6bjuRzYZDP7I/8KXzFnj90rpTzWf4UPvmTbqWcP9Adjl+Fr9iPX/KZ/Ulz/lAYKioqIiKitbU10TkKlfXpnPWB5CjGlJhHH300+0tDRMTtt98e06ZNS26gg/DKK6/Epz71qWhpaYmIiKlTp8aCBQsSnurA+MUNuq+5uTkeffTRWLFiRaxYsSJWrVoVbW1tf/J1Q4cOjdNOOy1GjRoVp59+enz605+O3r17JzBx5+RzYZDPdIX8KTxpyB86J5/fIX8Kj/xJP/kD3ef4VXjScPySz3RF2vKHwqDY0Dnr0znrA8lRjClBU6dOjTvuuCMi3vkMzp/97GdF88vbxo0bY/z48bFu3bqIeKfp/cILL8TRRx+d8GQHxi9ukHu7du2K1157Lc4777yIiPjlL38Zhx56aBx66KEJT9Z18jl58pmDIX+SlZb8oXPy+b3Jn2TJn9IgfyD3HL+SlZbjl3zmYKQhf0ieYkPnrE/nrA8kp1fSA9Dz5s6dGyeeeGJEROzduzcuvPDCmDx5ckF/Ju7u3bvjxhtvjJEjR2Z/aevdu3fMnz+/6H5pA/KjvLw8jjrqqBgwYEAMGDAgjjnmmKL7pVY+Q3GSP8mQPyB/kiJ/ALrH8SsZjl+QjvwBAA6OYkwJOuKII2Lp0qXZX94iIn7xi19EVVVVnHfeebFgwYLYsGFD7N27N8EpI15//fV47LHHYubMmXH88cfHJZdcEtu3b4+Id35pu+uuu+LLX/5yojMC5JJ8BpIif4CkyB8AipHjFwAAFJc+SQ9AMo488shYtmxZ1NXVxc9//vOIiNi5c2fce++9ce+990ZExIABA6KqqiqOPPLI6N+/f/Tqld8eVSaTiZ07d8Ybb7wRLS0tsXnz5vf8umHDhsVNN90U48ePz+s8AEmQz0BS5A+QFPkDQDFy/AIAgOKhGFPCDj/88FiwYEFcfPHFcfnll8fTTz/d4e937NgRq1evTmi6P3XYYYfFzJkz47LLLot+/folPQ5A3shnICnyB0iK/AGgGDl+AQBAcVCMIcaMGRNPPfVUNDU1RUNDQ9x///2xbt26eO211xKdq2/fvlFVVRVnnnlmXHDBBTF27NgoLy9PdCaAniSfgaTIHyAp8geAYuT4BQAAha0sk8lkkh6CwrRt27ZoamqK7du3x9tvvx098VLp27dvDBgwII499tj48Ic/HL179877PpMwduzYiIhYtmxZonNAGpXCz5d8zp9SeP2QP6Xw+pE/JKUUfr66oxTWR/6QlFL4+YKklMLPl+NX/pTC64f88fqhOyoqKiIiorW1NdE5CpX16Zz1geS4Ygz7NWjQoDj99NOTHgOAd5HPQFLkD5AU+QNAMXL8AgCAwtAr6QEAAAAAAAAAACAfFGMAAAAAAAAAAEglxRgAAAAAAAAAAFJJMQYAAAAAAAAAgFRSjAEAAAAAAAAAIJUUYwAAAAAAAAAASCXFGAAAAAAAAAAAUkkxBgAAAAAAAACAVFKMAQAAAAAAAAAglRRjAAAAAAAAAABIJcUYAAAAAAAAAABSSTEGAAAAAAAAAIBUUowBAAAAAAAAACCV+iQ9AIUlk8nEmjVr4oUXXoj169dHc3NztLa2RltbW2Qymbzvv7y8PAYMGBDHHntsDB8+PIYPHx6nnnpqfPCDH8z7vgEKmXwGKEzyGUiK/AEoTPIZAAAKj2IMERHx7LPPxh133BENDQ3x+9//PulxOujfv3+cc845ccEFF8T5558f/fr1S3okgB4jnwEKk3wGkiJ/AAqTfAYAgMLlo5RK3MaNG2Pq1KlRXV0d1157bcH90hYR8fbbb8fdd98dX/nKV+Kkk06KBx98MOmRAPJOPgMUJvkMJEX+ABQm+QwAAIXPFWNK2C9/+cv45je/GW+88UaH+wcOHBhnnHFG9lKbgwcPjr59+0avXvntUWUymdi9e3e8/vrr0dLSEuvXr4/nnnsu1q5dm/2apqamOPvss2PKlClx6623Rt++ffM6E0AS5DNAYZLPQFLkD0Bhks8AAFAcFGNKVENDQ0yZMiX27NmTve+LX/xiXHTRRTFhwoSC+oVo7dq1sXDhwpg7d25s3749IiLuvPPOeOutt6KhoaGgZgXoLvkMUJjkM5AU+QNQmOQzAAAUDx+lVIIaGxs7/NJWVVUVjY2Ncffdd8c555xTcL8InXDCCfHDH/4wXnzxxbjwwguz9997773xjW98I7nBAHJMPgMUJvkMJEX+ABQm+QwAAMXFFWNKTFtbW3zrW9/K/tI2YsSIWLp0aRx99NEJT/b+jjzyyPjZz34WQ4YMidmzZ0fEO/+z4Wtf+1qcddZZCU/XuV27dsWaNWtixYoVsWHDhlixYkVERPzd3/1dVFRUxMknnxzV1dVRWVmZ8KRAUuQzkDbvfv+zePHiyGQycc455xTV+x/5DMVH/iSvmPPH7+/A+5HPQNqk5f0zAHRGMabEXHvttdHU1BQR73zW7cMPP1wUv7S1Kysri6uvvjpefvnlWLBgQUREXHLJJbF69ero169fwtN11NTUFDfffHMsW7YsnnvuuWhra8v+XVlZWUREXHXVVZHJZLL3H3/88fHnf/7nMW3atDj77LOjd+/ePT43kAz5DKTB+73/KSsri2effbao3v/IZygO8qfwFFP++P0dOBDyGUiDNL5/BoDO+CilErJr166YM2dO9vZVV10VQ4YMSXCig1NWVhbXXXddDBw4MCLeeQN3zz33JDvU/7dnz55YvHhxnHXWWTF8+PCYM2dODBgwIP7qr/4q7rjjjnjhhRdi9+7d8elPfzo+/elPx549e2LLli2xZMmSuPrqq2PUqFGxbNmy+PznPx/Dhg2L2bNnx6uvvpr00wLyTD4DxexA3v/8xV/8RVG9/5HPUNjkT+Er5Pzx+ztwMOQzUMzS/P4ZAN5XhpLx4IMPZiIiExGZY445JrN79+6kR+qWv//7v88+ny9/+ctJj5N55plnMh/72McyEZEZMmRI5h/+4R8yL7/88nt+7ZgxYzJjxox5z7/buXNnpqGhITNu3LhMRGT69++fue6664r+3wt6Smc/X4VKPheOYnz9UDhK8fWT9vc/8rlwlOLP14EoxfWRP8Wl0PIn7a8fKBbFePySz4WjGF8/FI5SfP14/5M7AwcOzAwcODDpMQqW9emc9YHkuGJMCWloaMhu19TUFP1l7iZPnpzd/vWvfx1vvvlmInO0tbXF97///fjEJz4Rr732Wtx1113xu9/9Ln7wgx8c1P8YKS8vj0mTJsXSpUtjzZo1MXHixPjbv/3b+PSnPx0vvvhiHp4BkDT5DBSbUnn/I5+h8Mif4lQo+VMqrx8gf+QzUGy8/wGAdyjGlJAnnngiu/2lL30pwUly44QTTogRI0ZERMSOHTvi2Wef7fEZmpqa4rTTTourrroqLrzwwli9enVMnjw5ysvLc/L4I0eOjH/7t3+L22+/PdauXRsnn3xy3HzzzTl5bKBwyGegmJTS+x/5DIVF/hSvQsifUnr9APkjn4Fi4v0PAPw3xZgSsWfPnmhpacnePvnkkxOcJnf2fR5NTU09uu/nn38+PvWpT8Urr7wS9913X8yfPz8GDRqU8/2UlZXFtGnTYs2aNTFmzJiYPn16/NM//VNkMpmc7wvoefIZKCal9P5HPkNhkT/Fz+/vQLGTz0Ax8f4HADpSjCkRL730UuzcuTMiIgYPHhyHHHJIwhPlxvDhw7Pb69ev77H9rl27NsaNGxe9e/eO5cuXx7nnnpv3fR599NGxePHimDp1anzve9+LH/3oR3nfJ5B/8hkoFqX2/kc+Q+GQP/KnO0rt9QPkj3wGioX3P13T0NAQGzZs6LH9ZTKZqK+vjx07dvTYPgH4b32SHoCe8dJLL2W3jz/++AQnya2qqqrs9r7PMZ9efvnlmDhxYvTp0yceffTRGDZsWI/sN+Kdz++87bbbIiLiu9/9bhx++OFx8cUX99j+gdyTz0AxKMX3P/IZCoP8kT/dUYqvHyB/5DNQDLz/6ZqtW7fG9OnT4/DDD49HHnkkjjnmmLzuL5PJxMyZM+P666+PiIja2tq87g+AP+WKMSVi3wbqoYcemuAkubXv/8zoiZZtJpOJiy66KLZt2xZLlizp0TeV7Xr16hXz58+Pz33uc/HXf/3X8eKLL/b4DEDuyGeg0JXq+x/5DMmTP/KnO0r19QPkj3wGCp33P11XWVkZDzzwQGzatCnGjRuX1yvH7FuKqauri+nTp+dtXwDsn2JMidi1a1d2u7y8PMFJcmvf59J+KdN8uvXWW+PBBx+MH/3oR/Hxj3887/vbn/Ly8pg/f34MGDAgvvnNb8aePXsSmwXoHvkMFLpSff8jnyF58kf+dEepvn6A/JHPQKHz/ufAjB49OpYsWZLXcsy7SzFz5syJsrKynO8HgPenGFOC0nTQ7cnnsmHDhqirq4sxY8bEd77znR7b7/4cffTRccMNN8STTz6ZvfweUNzkM1BovP95R5oyLU3PhXSTP+9I08+s39/9/g5pIp+BQuP9z8HJZzlGKQagsCjGQBddccUVsXv37rjllluiV6/C+NGZOnVqfP7zn4/vfe978eqrryY9DgCQMt7/AEmRP3SH1w8AUGq8/zl4+SjHKMUAFJ7CODpCgfvjH/8YDQ0NUVtbG1VVVUmPk1VWVhY/+tGP4u2334758+cnPQ4AkCLe/wBJkT90h9cPAFBqvP/pvlyWY5RiAAqTYgx0wS233BK7du2KGTNmJD3Knxg5cmSMHTs2/vVf/7VgP6uzK958882or6+Pv/iLv4hhw4bFscceGx//+Mfj0ksvjXXr1iU9HkDJks+ly/sfKGz75vP//b//N37729+mJp/lD93h9ZN/3h8CFCb5XLq8/8mNXJRjlGIACpdiDLyP3bt3R319fUycODE+8pGPJD3Oe/r2t78dv/vd7+LBBx9MepQDtnPnzpg1a1YMGTIkZsyYEY8//ng0NzfHH/7wh3j++efjhhtuiBNOOCHGjx8fa9asSXpcgJIhn0ub9z9QuN4rn99+++1oa2tLRT7LH7rD6ye/vD8EKEzyubR5/5Nb3SnHKMUAFDbFGHgfjz32WPzhD3+I2trapEfZr/PPPz8GDx4ct99+e9KjHJC33norzjnnnPjxj38cb7zxRqdfu3Tp0jjzzDPjscce66HpAEqXfMb7HyhMpZDP8ofu8PrJn1LIH4BiJJ/x/if3DqYcoxQDUPiKohhzzTXXRFVVVQwaNKigD+6lYOLEiVFWVtbhz6BBg6KmpiZaW1u7/DhVVVXR2NiYv0Fz6KmnnoqIiHHjxiU8yf6Vl5fHpz71qXj66aeTHqXL9uzZE1OmTImHH364y9+zffv2+PznP+9/NsB7KMV8Jj/kMxHe/+SSfCZXSiWf5U/ulGL+eP3kR6nkD/SUUsxn8kM+E+H9T74cSDlGKQagOBR8Meaaa66J+vr6aGhoiIaGhvjFL34R11xzTdJjlbTp06dHc3Nz9k9DQ0M0NjbGxRdfnPRoebFixYo4/vjjo7KyMulROjVq1KhoaWmJbdu2JT1KlyxatCgWL158wN+3ffv2uPTSS/MwERS/Ustn8kM+E+H9T67JZ3KhVPJZ/uRWqeWP109+lEr+QE8qtXwmP+QzEd7/5FNXyjFKMQDFo+CLMVdffXXU19dHdXV1TJgwIW6++eZ47bXXkh6rpFVUVMTQoUOzfyZMmBCzZ8/u8D8UWlpasv/7oaqqqkOZqf0N0MSJE4ui5PTMM8/EqFGjkh7jfbXPuHLlyoQn6Zqf/OQnB/29Dz/8cKxbty6H00A6lFo+kx/ymQjvf3JNPpMLpZLP8ie3Si1/vH7yo1TyB3pSqeUz+SGfifD+J986K8coxQAUl4IuxqxcuTJaW1tjwoQJ2fsmTZoUs2fPTnAq9mffRvLEiROjoqIimpubo76+Pq6++uqYN29eRLzTYB46dGg89NBDMWvWrKTG7ZLXX389/vM//zOqq6uTHuV9tc+4atWqZAfpgtWrV8fy5cu79Rg33XRTjqaB9EtjPpMf8pkI7396knymq0oln+VPz0lj/nj95Eep5A8UijTmM/khn4nw/qenvLscs3fvXqUYgCJU0MWYlpaWqKioiCuuuCL7easTJ048oM9aJfdaW1uzf1paWqKxsTFmz54dV1xxRURENDY2xtatW6OhoSH7Px6uvPLKoiw0bd++PSIijjjiiIQneX+HHXZYRPz3zIVs2bJl3X6MRx55pPuDQMqUUj6TH/KZCO9/8kE+012lks/yJ/dKKX+8fvKjVPIHelop5TP5IZ+J8P6nJ+1bjnnzzTdjx44dSjEARaZP0gN0ZuvWrdlfENo/d7CmpiZqamrioYceSnS2urq6omq2btmyJWePNW/evOz/TmhXXV0d06dPj4h3rvRz2mmndfj7CRMmZH+xy5cnn3wyxo4dm9PH/K//+q+IiLjuuutiwYIFOXvc9tdOructK/t/7d17cFT1/f/xVy4bYBQIAUUQ/Uo2KMQimkCraCH5kqjocFEJVAEv3wrBCyVQgSJq2xmpYoUK01IDXyZYkKpBa0GqA5GrtVZJDCMomEu9IFS5JYCFkMv+/uC3++Uakuw5+zlnz/Mxw8yGy553wslzz868sxuj3/3ud2H/tIDdvvzyy7DvY+fOnZZ//RAd7Pr+sgt9dha3nT9Wo8/hiZbzh+ufE+izs0TL91dLeaXP9OcE+tMynD/28Ep/YIbbHt/ps7O47fyxGn0OT7ScP1z/RJ7f71dpaalqa2t1ySWXqKSkRJmZmabHcpQjR45Icv/3l134+iBc1157rV544QXTY7iSo18xJjk5WZKUn5+vxMREJSYmnvFeq4i8adOmKRAIhH4VFxerqqpKubm5pkezXHDLNxAIGJ6kadwypxXb07Gxjs4XYISX+gx70GdIXP/YgT4jXF7pM/2xnpf6w/ljD6/0B4g0L/UZ9qDPkLj+ibRAIKC9e/eGPq6qqtLx48cNTgQAaA5Hv2JMcDHmZAcOHDAwyZnctom1atUqDR061Jb7TktL04gRI1RSUhL6+Jlnnjnl72zZsuWs/59W6t+/v1atWmXpfe7Zs0ddu3bVpEmT9NBDD1l2v8FNUCte8jKovr5e8fHxmjp1qp566inL7tcOS5cu1b333hvWffTt29fSrx+ihx3fX3aiz87itvPHavQ5PNFy/nD9cwJ9dpZo+f5qKa/0mf6cQH9ahvPHHl7pD8xw2+M7fXYWt50/VqPP4YmW84frn8gJBAKaPHmyNm3apLy8PI0cOVK33HKL9u3bp/Xr16tbt26mR3SMxMRESe7//rILXx/AHEevBAffPzUnJ0eVlZUqKSlRbm5u6CUl4RwdO3YMLS1lZWUpKSkp9P9WVFSk6dOnn/FSn5WVlSZGbZZOnTqpVatWqqioMD3KeZWXl0uSKy7Ahg0bpgsuuCCs+xgzZoxF0wDRLVr7DHvQZ0hc/0QKfUZzeKXP9CcyorU/nD/28Ep/ACeI1j7DHvQZEtc/kRJcipk3b57y8vI0d+5c3XDDDVqzZo2+/fZbZWZmateuXabHBACch6MXYyRp7dq1kqT09HQNGjRII0aMUH5+vuGpcLq0tDSVlJSEfqph7dq1qqqqkt/vV25urmbMmHHKQlNubq5yc3P13HPPmRq5SXw+n/r06aPi4mLTo5xXcMb09HTDk5xfu3btNHbs2LD+/T333GPhRED0itY+wx70GRLXP5FCn9EcXukz/YmMaO0P5489vNIfwAmitc+wB32GxPVPJJxtKSb4FlbXX389yzEA4CKOfiuloMLCQtMj4P8LLiqdLisr65T3h0xOTj7n35VOvI/utGnTLJ/PDunp6Xr55ZfV0NDg6PddLS4uVqtWrZSammp6lCaZOHGiFi9erNra2mb/29zcXF144YU2TAW4lxf7DHvQZ0hc/1iJPsMqXukz/bGOF/vD+WMPr/QHiBQv9hn2oM+QuP6xU2NLMUHB5Zibb75ZmZmZvK0SADiYcx8lAYdIT0/XoUOHVFZWZnqURhUXF+vaa6+Vz+czPUqTpKamqqCgoNn/LisrS08//bQNEwEAJPqME7j+AZzHK32mPwgH5489vNIfAHAb+gyJ6x+7NGUpJohXjgEAd2AxBjiPgQMHSpJWrFhheJJz2717t9577z1lZGSYHqVZRo8eraVLlzb5Ynjo0KF68803lZCQYPNkAOBt9Blc/wDO5IU+0x+Eg/PHPl7oDwC4EX0G1z/Wa85STBDLMQDgfCzGAOeRkpKirKws5efnq66uzvQ4Z7Vo0SI1NDRo3LhxpkdptjFjxqi0tFQPPfTQOV++c+DAgXr11Vf1xhtv6IILLojwhADgTfTZ27j+AZwr2vtMfxAOzh97RXt/AMCt6LO3cf1jrZYsxQSxHAMAzsZiDNAEDz/8sL7++mutXr3a9ChnqK2t1cKFC3XrrbfK7/ebHqdFUlNTtWDBAn3zzTdaunSpkpOTdcUVV+j3v/+9tm3bpg0bNmjkyJGKi4szPSoAeAp99jaufwDnOr3Pzz33nJ5++umo6TP9QTg4f+zF9SEAOBN99jauf6wRzlJMEMsxAOBcLMYATTBkyBBdeumlmj9/vgKBgOlxTvH6669r9+7devjhh02PErZ27dppzJgxuuyyy/Rf//VfeuSRR3T11VebHgsAPI8+exPXP4DzBfs8depUzZw5M2r6TH8QDs6fyOD6EACciT57E9c/4bNiKSaI5RgAcCYWY4AmiI+P19SpU7Vu3TotX77c9DghBw8e1JQpU9S7d28NHjzY9DgAACCKcP0DwBT6g3Bw/gAAAK/h+ic8Vi7FBLEcAwDOw2IM0ESPPvqo+vfvr4kTJ2rPnj2mx5EkTZ48Wd99952WLFnCy2ACAADLcf0DwBT6g3Bw/gAAAK/h+qdl7FiKCWI5BgCchcUYjzj5gbyhocHgJNY6+XOx6mLlXOLi4lRQUKCjR49qwoQJxl+ScPXq1XrppZf0+OOPKy0tzegsAFqOPgNwMi9f/9BnwCz6cwL9aRkvnz8A7EOfATgZ1z/NZ+dSTBDLMQDgHCzGeESrVq1Ct2tqagxOYq2TP5fWrVvbfrwrr7xSs2bN0sqVKzVr1izbj3cun376qe677z717t1bTzzxhLE5AISPPgNwOq9e/9BnwDz6Q3/C4dXzB4B96DMAp+P6p+kisRQTxHIMADhDvOkBEBmJiYmh299++625QSx28ufSvn37iBwzLy9PpaWlevLJJ9W2bVtNmjQpIscNKisrU3Z2tnw+n/7yl78oISEhoscHYC36DMANvHj9Q58BZ6A/9CccXjx/ANiHPgNwA65/mubgwYNavXq17UsxQcHlmMGDB+sf//iHcnJybD0eAOBMLMZ4hN/vD92uqKhQQ0ODYmPd/4JBZWVlodspKSkROWZsbKwWL16sI0eOKC8vT4cPH9bMmTMj8lKjW7du1S233KL6+nqtW7fulP9XAO5EnwG4gRevf+gz4Az0h/6Ew4vnDwD70GcAbsD1T9MkJSXpww8/VGJiYsTeRu76669XRUWFkpKSInI8AMCp3H/ljiZJSkoKPdgePXpUu3fvNjyRNcrLy0O3e/ToEbHj+nw+vfbaaxo7dqyefPJJDR8+XHv27LHteA0NDZo/f75uuOEG+Xw+bd68Wb1797bteAAihz4DcAuvXf/QZ8A56A/9CYfXzh8A9qHPANyC65+m6dChQ8SWYoJYigEAc1iM8ZCePXuGbm/cuNHgJNaoqanR+++/H/r4qquuiujx4+PjtWTJEs2ZM0dr1qzR1VdfrWXLlikQCFh6nIqKCmVmZmrSpEnKzMzUBx98cMr/JQD3o88A3MJr1z/0GXAO+uNupvvjtfMHgH3oMwC34PoHAIBTsRjjIbfffnvodmFhocFJrFFUVKTq6mpJ0hVXXKHU1NSIzxAbG6spU6aotLRUvXr10tixYzVo0CC9+eabqqurC+u+d+7cqcmTJ+uaa67R1q1bVVBQoLfeekuXXnqpRdMDcAr6DMBNvHT9Q58BZ6E/7uWE/njp/AFgH/oMwE24/gEA4P+wGOMhOTk5odtvv/22du3aZXCa8C1evDh0OycnJ+IveXeyq666Sps2bdK8efNUVlamO+64Q927d9fTTz+tnTt3qqGhoUn3s3//fq1YsULZ2dnq2bOn/vCHP2j48OHatm2b7r//fqOfIwD70GcAbuSF6x/6DDgT/XEfJ/XHC+cPAPvQZwBuxPUPAABSTMDq102Do/Xr109btmyRJI0aNUqvvPKK4YlapqioSNnZ2aGPS0pKdN111xmc6P/U1dXprbfe0oIFC7R27VpJUtu2bZWWlqb09HSlpKRo3rx5iomJ0ZQpU7R3716VlJSouLhYX3zxhSTpsssu04QJE/TTn/5UnTt3NvjZmJGRkSFJ2rBhg9E54E5uPX/oszO49fyJFL4+jfPy1year3/oszN4+fsLjaM/zufk/kTz+RMp9BnhcOv5Q5+dwa3nT6Tw9Wmcl78+XP/AbomJiZKkqqoqo3M4FV8fwBwWYzxm48aNoYs+SVq6dKnGjBljbqAW2LNnj2666SZVVlZKkkaPHq1ly5YZnursKioqtHHjRhUXF6u4uFilpaWqqak54+8lJyerb9++Sk9PV79+/TRgwADFxcUZmNgZvPzEBOFz6/lDn53BredPpPD1aRxfnxOi7fqHPjsD319oCvrjPG7qT7SdP5FCnxEOt54/9NkZ3Hr+RApfn8bx9TmB6x/YgcWPxvH1AcyJNz0AImvgwIG65557tHz5cknSfffdJ0muefK2e/duDRo0KPSkrW3btvrtb39reKpz8/v98vv9+p//+R9JUm1trfbv36+jR4+qvr5erVu3Vrt27dSuXTvDkwIwjT4DiBbnuv4ZNmyYJOn111931fUPfQbcg/44i9v6w/N3AE1FnwFEi2i7fgYAoDGxpgdA5L3wwgu6+uqrJUkNDQ0aO3asRo0a5ej3xK2rq9Pvf/97paamaseOHZKkuLg4FRQUqEuXLoanazqfz6dLLrlE3bt3V0pKirp168ZFJYAQ+gwgGgWvf9q0aaM2bdq48vqHPgPuRH/MiJb+8PwdQGPoM4BoFA3XzwAAnAuLMR500UUXad26daEnb5L02muvye/3a9iwYVq2bJl27dqlhoYGg1NKhw4d0ubNmzV58mR1795dEydOVHV1taQTT9peeeUV3XXXXUZnBAAr0WcAcCb6DMAU+gMAzkSfAQAAAHfhrZQ86uKLL9aGDRuUl5enl19+WZJ0/PhxrVy5UitXrpQktWnTRn6/XxdffLFat26t2Fh796gCgYCOHz+uw4cPq7KyUt99991Z/15KSopefPFFDRo0yNZ5AMAE+gwAzkSfAZhCfwDAmegzAAAA4B4sxnhYp06dtGzZMo0bN05Tp07VRx99dMqfHz16VNu2bTM03Zk6duyoyZMn67HHHlOrVq1MjwMAtqHPAOBM9BmAKfQHAJyJPgMAAADuwGIMNHDgQH344YcqLy9XYWGhVq9erR07dmj//v1G50pISJDf79eNN96okSNHKiMjQz6fz+hMABBJ9BkAnIk+AzCF/gCAM9FnAAAAwNlYjEFISkqKZsyYoRkzZkiSDh48qPLyclVXV+vYsWMKBAK2z5CQkKA2bdro8ssv12WXXaa4uDjbjwkATkefAcCZ6DMAU+gPADgTfQYAAACcicUYnFOHDh3Ur18/02MAAE5DnwHAmegzAFPoDwA4E30GAAAAnCHW9AAAAAAAAAAAAAAAAACAHViMAQAAAAAAAAAAAAAAQFRiMQYAAAAAAAAAAAAAAABRicUYAAAAAAAAAAAAAAAARCUWYwAAAAAAAAAAAAAAABCVWIwBAAAAAAAAAAAAAABAVGIxBgAAAAAAAAAAAAAAAFGJxRgAAAAAAAAAAAAAAABEJRZjAAAAAAAAAAAAAAAAEJVYjAEAAAAAAAAAAAAAAEBUYjEGAAAAAAAAAAAAAAAAUYnFGAAAAAAAAAAAAAAAAEQlFmMAAAAAAAAAAAAAAAAQleJNDwBnCQQC2r59u3bu3KmysjJVVFSoqqpKNTU1CgQCth/f5/OpTZs2uvzyy9WjRw/16NFD1113nS688ELbjw0ATkafAcCZ6DMAOBN9BmAK/QEAAACch8UYSJI+/vhjLV++XIWFhfryyy9Nj3OK1q1b67bbbtPIkSM1fPhwtWrVyvRIABAx9BkAnIk+A4Az0WcAptAfAAAAwLl4KyWP2717t0aPHq20tDQ9//zzjnvSJknHjh3TG2+8oZ/85Cf6wQ9+oHfeecf0SABgO/oMAM5EnwHAmegzAFPoDwAAAOB8vGKMh73++ut64IEHdPjw4VN+v3379urfv3/opTY7d+6shIQExcbau0cVCARUV1enQ4cOqbKyUmVlZdq6das+++yz0N8pLy/X4MGDdffdd2vJkiVKSEiwdSYAMIE+A4Az0WcAcCb6DMAU+gMAAAC4A4sxHlVYWKi7775b9fX1od+744479OCDDyorK8tRT4g+++wzvfrqq3rhhRdUXV0tSfrzn/+s77//XoWFhY6aFQDCRZ8BwJnoMwA4E30GYAr9AQAAANyDt1LyoKKiolOetPn9fhUVFemNN97Qbbfd5rgnQr169dKvfvUrff755xo7dmzo91euXKn777/f3GAAYDH6DADORJ8BwJnoMwBT6A8AAADgLrxijMfU1NTooYceCj1p69mzp9atW6cuXboYnuz8Lr74Yr300kvq2rWrZs+eLenETzbce++9uvXWWw1Ph3DU1tZq+/btKi4u1q5du1RcXCxJevLJJ5WYmKg+ffooLS1NSUlJhicF7EOfzaA/AM6HPgOINqdf/6xatUqBQEC33Xabq65/6LMZXD8D9McU+gMAAIBwsBjjMc8//7zKy8slnXiv23fffdcVT9qCYmJi9Mwzz+ibb77RsmXLJEkTJ07Utm3b1KpVK8PToTnKy8u1aNEibdiwQVu3blVNTU3oz2JiYiRJs2bNUiAQCP1+9+7d9cMf/lBjxozR4MGDFRcXF/G5AbvQ58ihPwCagz4DiAbnu/6JiYnRxx9/7KrrH/ocOVw/A6eiP5FDfwAAAGAV3krJQ2prazV37tzQx7NmzVLXrl0NTtQyMTExmjNnjtq3by/pxBOkN9980+xQaJL6+nqtWrVKt956q3r06KG5c+eqTZs2evTRR7V8+XLt3LlTdXV1GjBggAYMGKD6+nrt27dPa9as0TPPPKP09HRt2LBBQ4YMUUpKimbPnq29e/ea/rSAsNFn+9EfAC1BnwG4WXOuf3784x+76vqHPtuP62fg7OiP/egPAAAA7MBijIesW7dOBw4ckCR169ZNEyZMMDxRy1188cXKy8sLfVxYWGhuGDRJcXGxrrvuOg0dOlSffPKJfv3rX+vLL7/Uhg0b9Pzzz+vuu+/WlVdeecpPccTExKhjx47Kzs7WL37xCxUWFurrr79WYWGhunfvrl/84he6/PLLNXfu3NDL1wJuRJ/tRX8AtBR9BuBW0X79Q5/tFe3nDxAO+mMv+gMAAAC7sBjjISc/ucnJyXH9y0iOGjUqdPtvf/ubjhw5YnAanEtNTY2eeOIJ/ehHP9L+/fv1yiuv6IsvvtBTTz3Vop+o8fl8GjFihNatW6ft27crOztbP//5zzVgwAB9/vnnNnwGgP3osz3oD4Bw0WcAbuOV6x/6bA+vnD9AOOiPPegPAAAA7MZijIf8/e9/D92+8847DU5ijV69eqlnz56SpKNHj+rjjz82PBFOV15err59+2rWrFkaO3astm3bplGjRsnn81ly/6mpqfrrX/+qpUuX6rPPPlOfPn20aNEiS+4biCT6bD36A8AK9BmAm3jp+oc+W89L5w8QDvpjPfoDAACASGAxxiPq6+tVWVkZ+rhPnz4Gp7HOyZ9HeXm5wUlwuk8++UQ33XST9uzZo7feeksFBQXq0KGD5ceJiYnRmDFjtH37dg0cOFDjx4/Xb37zGwUCAcuPBdiBPluP/gCwAn0G4CZeuv6hz9bz0vkDhIP+WI/+AAAAIFJYjPGIr776SsePH5ckde7cWW3btjU8kTV69OgRul1WVmZwEpzss88+U2ZmpuLi4rRp0ybdfvvtth+zS5cuWrVqlUaPHq2ZM2fq2Weftf2YgBXos7XoDwCr0GcAbuG16x/6bC2vnT9AOOiPtegPADhbYWGhdu3aFbHjBQIB5efn6+jRoxE7JgBviTc9ACLjq6++Ct3u3r27wUms5ff7Q7dP/hxhzjfffKPs7GzFx8dr48aNSklJidixfT6f/vSnP0mSHn/8cXXq1Enjxo2L2PGBlqDP1qE/AKxEnwG4gRevf+izdbx4/gDhoD/WoT8A4GwHDhzQ+PHj1alTJ61fv17dunWz9XiBQECTJ0/WvHnzJEm5ubm2Hg+AN/GKMR5x8oZlu3btDE5irZN/MoMtUvMCgYAefPBBHTx4UGvWrInok9qg2NhYFRQU6JZbbtHPfvYzff755xGfAWgO+mwN+gPAavQZgNN59fqHPlvDq+cPEA76Yw36AwDOl5SUpLffflvffvutMjMzbX3lmJOXYvLy8jR+/HjbjgXA21iM8Yja2trQbZ/PZ3ASa538uQRfyhTmLFmyRO+8846effZZXXPNNcbm8Pl8KigoUJs2bfTAAw+ovr7e2CzA+dBna9AfAFajzwCczqvXP/TZGl49f4Bw0B9r0B8AcIfrr79ea9assXU55vSlmLlz5yomJsby4wCAxGKMJ0XTg0o0fS5ut2vXLuXl5WngwIF65JFHTI+jLl26aP78+Xr//fdDL78HOF00NS2Snwv9AWA3+gzAabj+OSGamsb1M9fPcBf60zL0BwDcxc7lGJZiAEQaizEALDF9+nTV1dVp8eLFio11RlpGjx6tIUOGaObMmdq7d6/pcQDYhP4AAACv4foH4eD8AWAK/QEA97FjOYalGAAmOOPqE4Cr/fvf/1ZhYaFyc3Pl9/tNjxMSExOjZ599VseOHVNBQYHpcQDYgP4AAACv4foH4eD8AWAK/QEA97JyOYalGACmsBgDIGyLFy9WbW2tJkyYYHqUM6SmpiojI0N//OMfXf1ewUeOHFF+fr5+/OMfKyUlRZdffrmuueYaTZo0STt27DA9HmAM/YFpJ/f5n//8pz744AP6DAAOEM195voH4eD8sR/P34Gzoz8wLZqvD4FIsGI5hqUYACaxGAMgLHV1dcrPz1d2drauvPJK0+Oc1cMPP6wvvvhC77zzjulRmu348eOaNm2aunbtqgkTJui9995TRUWFvv76a33yySeaP3++evXqpUGDBmn79u2mxwUiiv7ApLP1+dixY6qpqaHPAGBQtPeZ6x+Eg/PHXjx/B86N/sCkaL8+BCIpnOUYlmIAmMZiDICwbN68WV9//bVyc3NNj3JOw4cPV+fOnbV06VLTozTL999/r9tuu02//e1vdfjw4Ub/7rp163TjjTdq8+bNEZoOMI/+wBT6DADO5IU+c/2DcHD+2McL/QHCQX9gCn0GrNeS5RiWYgA4gaMXY1asWKGYmJiz/qqsrDQ9nidlZ2ef8X/RoUMH5eTkqKqqqsn34/f7VVRUZN+giJgPP/xQkpSZmWl4knPz+Xy66aab9NFHH5kepcnq6+t199136913323yv6murtaQIUP4yQaP8mKf6Q9MoM9oLi/2GTDBK33m+sc6Xuwz5489vNIfWIf+OJMb+4PG0WfAPs1ZjmEpBoBTOHoxJisrS8XFxaf8mj17tpKTk5WcnGx6PM8aP368KioqQr8KCwtVVFSkcePGmR4NBhQXF6t79+5KSkoyPUqj0tPTVVlZqYMHD5oepUlWrFihVatWNfvfVVdXa9KkSTZMBDfwWp/pD0ygz2gJr/UZMMErfeb6x1pe6zPnjz280h9Yi/44k9v6g8bRZ8BeTVmOYSkGgJM4ejEmMTFRaWlpp/zKz89XYWGh6dE8LTExMbSclJycrKysLM2ePfuUn1CorKwM/fSD3+/Xc889F/qz4BOM7OzsU34f7rRlyxalp6ebHuO8gjOWlJQYnqRpFixY0OJ/++6772rHjh0WTgO38Fqf6Q9MoM9oCa/1GTDBK33m+sdaXusz5489vNIfWIv+OJPb+oPG0WfAfo0tx7AUA8BpHL0Yc7rp06crKytLaWlppkfBWZy88Z+dna3ExERVVFQoPz9fzzzzjBYuXCjpxE8IJCcna+3atZo2bZqpcWGBQ4cO6V//+pcrvieDM5aWlpodpAm2bdumTZs2hXUfL774okXTIBpEY5/pD0ygz7BaNPYZMMErfeb6J3Kisc+cP/bwSn8QOfTHLDf1B42jz0DknL4c09DQwFIMAEeKNz1AU1VVVWnhwoX617/+ZXoUz6uqqgq93+2BAwdUWVmp2bNna/r06ZKkoqIiHThwIPTKPsnJyZoxY4Zmz56t8ePHmxobNqiurpYkXXTRRYYnOb+OHTtK+r+ZnWzDhg1h38f69evDHwSu46U+0x+YQJ/RUl7qM2CCV/rM9Y/1vNRnzh97eKU/sB79cSY39QeNo89AZAWXY26++WYdOXJE8fHxLMUAcBzXLMZMnz5d48ePV2JioulRJEl5eXmu2hzft2+fZfe1cOHC0E8nBKWlpYWelJWUlKhv376n/HlWVlboiZ1d3n//fWVkZNh6DJzqP//5jyRpzpw5WrZsmWX3G/zesvr/MyYmRr/73e/C/mkBu3355Zdh38fOnTs9+/1g1/ljF/rcMvTHDLd9f1mNPofHbecPfXYWt50/iCyv9JnrnxPoc8tw/tjDK/2xi9se3+lPy9AfM9z2/WU1+hwer58/aDm/36/S0lLV1tbqkksuUUlJiTIzM02P5ShHjhyRxPcXWu7aa6/VCy+8YHoMV3LNWyktXLhQubm5pseApGnTpikQCIR+FRcXq6qqiv8fDwpu+QYCAcOTNI1b5rRiezo21jV5h4W81Gf6AxPoM1rKS30GTPBKn7n+sZ6X+sz5Yw+v9AfWoz/O5ZY50Tj6DEReIBDQ3r17Qx9XVVXp+PHjBicCgFO54hVjFi5cqLS0NCUnJ5seJcRtm1irVq3S0KFDbbnvtLQ0jRgxQiUlJaGPn3nmmVP+zpYtW2z//+vfv79WrVpl6zFwqj179qhr166aNGmSHnroIcvuN7gpa8VLXgbV19crPj5eU6dO1VNPPWXZ/dph6dKluvfee8O6j759+1r69XMTO84fO9HnlqE/Zrjt+8tq9Dk8bjt/6LOzuO38QWR5pc9c/5xAn1uG88ceXumPXdz2+E5/Wob+mOG27y+r0efweP38QfMFAgFNnjxZmzZtUl5enkaOHKlbbrlF+/bt0/r169WtWzfTIzpG8J1R+P4CIs8VK6+FhYXKysoyPQYa0bFjRx04cEDSiZf1TEpKUk5OjiorK1VUVKTp06ef8VKflZWVJkaFhTp16qRWrVqpoqLC9CjnVV5eLkmuuAAbNmyYLrjggrDuY8yYMRZNA7eL1j7TH5hAn2GlaO0zYIJX+sz1T2REa585f+zhlf4gMuiPeW7qDxpHn4HICS7FzJs3T3l5eZo7d65uuOEGrVmzRt9++60yMzO1a9cu02MCgDsWY4qKitSvXz/TY6ARaWlpKikpCf1Uw9q1a1VVVSW/36/c3FzNmDEj9B65kpSbm6vc3Fw999xzpkaGBXw+n/r06aPi4mLTo5xXcMb09HTDk5xfu3btNHbs2LD+/T333GPhRHCzaO0z/YEJ9BlWitY+AyZ4pc9c/0RGtPaZ88ceXukPIoP+mOem/qBx9BmIjLMtxQTfyuz6669nOQaAo7jirZR4X0/nWLt27Vl/Pysr65T/p+Tk5HP+XenE++hOmzbN8vkQeenp6Xr55ZfV0NDg6PddLS4uVqtWrZSammp6lCaZOHGiFi9erNra2mb/29zcXF144YU2TAUn82Kf6Q9MoM9oLi/2GTDBK33m+sc6Xuwz5489vNIfWIf+0B9EBn0G7NXYUkxQcDnm5ptvVmZmJm+rBMAo516FAnCF9PR0HTp0SGVlZaZHaVRxcbGuvfZa+Xw+06M0SWpqqgoKCpr977KysvT000/bMBHgPPQHJtBnAHAmr/SZ6x+Eg/PHHl7pDxAO+gMT6DNgn6YsxQTxyjEAnILFGABhGThwoCRpxYoVhic5t927d+u9995TRkaG6VGaZfTo0Vq6dGmTn4wPHTpUb775phISEmyeDHAG+gNT6DMAOJMX+sz1D8LB+WMfL/QHCAf9gSn0GbBec5ZigliOAeAELMYACEtKSoqysrKUn5+vuro60+Oc1aJFi9TQ0KBx48aZHqXZxowZo9LSUj300EPnfPnOgQMH6tVXX9Ubb7yhCy64IMITAubQH5hEnwHAmaK9z1z/IBycP/aK9v4A4aA/MIk+A9ZpyVJMEMsxAEyLNz0AAPd7+OGHdeedd2r16tUaNmyY6XFOUVtbq4ULF+rWW2+V3+83PU6LpKamasGCBXr22We1cuVK/fKXv1RDQ4Mee+wxZWRk6OqrrzY9ImAM/YFJp/d5z549On78uBITE+kzABgU7X3m+gfh4PyxF8/fgXOjPzAp2q8PgUgIZykmKLgcc/PNNyszM1Pr169Xt27dbJoYAE7FYgyAsA0ZMkSXXnqp5s+fr6FDhzb7YshOr7/+unbv3q38/HzTo4StXbt2GjNmjP73f/9XkvTII48Ynggwj/7ACYJ9BgA4S7T2mesfhIPzJzJ4/g6cif7ACaL1+hCwmxVLMUEsxwAwhbdSAhC2+Ph4TZ06VevWrdPy5ctNjxNy8OBBTZkyRb1799bgwYNNjwPABvQHAAB4Ddc/CAfnDwBT6A8AuJOVSzFBvK0SABNYjAFgiUcffVT9+/fXxIkTtWfPHtPjSJImT56s7777TkuWLFFcXJzpcQDYhP4AAACv4foH4eD8AWAK/QEAd7FjKSaI5RgAkcZijEec/EDV0NBgcBJrnfy5OOnlN70oLi5OBQUFOnr0qCZMmKBAIGB0ntWrV+ull17S448/rrS0NKOzAI2hz+GjPwDsQJ8BOJmXr3/oc/i8fP4A4aA/4aM/AOAedi7FBLEcAyCSWIzxiFatWoVu19TUGJzEWid/Lq1btzY4CSTpyiuv1KxZs7Ry5UrNmjXL2Byffvqp7rvvPvXu3VtPPPGEsTmApqDP1qA/AKxGnwE4nVevf+izNbx6/gDhoD/WoD8A4HyRWIoJYjkGQKTEmx4AkZGYmBi6/e2335obxGInfy7t27c3OAmC8vLyVFpaqieffFJt27bVpEmTInr8srIyZWdny+fz6S9/+YsSEhIienygueizdegPACvRZwBu4MXrH/psHS+eP0A46I916A8AONvBgwe1evVq25digoLLMYMHD9Y//vEP5eTk2Ho8AN7EYoxH+P3+0O2Kigo1NDQoNtb9LxhUVlYWup2SkmJwEgTFxsZq8eLFOnLkiPLy8nT48GHNnDkzIi/Vv3XrVt1yyy2qr6/XunXrTjnvAaeiz9ahPwCsRJ8BuIEXr3/os3W8eP4A4aA/1qE/AOBsSUlJ+vDDD5WYmBixt2G+/vrrVVFRoaSkpIgcD4D3uP/KHU2SlJQUejA5evSodu/ebXgia5SXl4du9+jRw+AkOJnP59Nrr72msWPH6sknn9Tw4cO1Z88e247X0NCg+fPn64YbbpDP59PmzZvVu3dv244HWIk+W4v+ALAKfQbgFl67/qHP1vLa+QOEg/5Yi/4AgLN16NAhYksxQSzFALATizEe0rNnz9DtjRs3GpzEGjU1NXr//fdDH1911VUGp8Hp4uPjtWTJEs2ZM0dr1qzR1VdfrWXLlikQCFh6nIqKCmVmZmrSpEnKzMzUBx98cMq5DrgBfbYW/QFgFfoMwC28dv1Dn63ltfMHCAf9sRb9AQAAQKSwGOMht99+e+h2YWGhwUmsUVRUpOrqaknSFVdcodTUVMMT4XSxsbGaMmWKSktL1atXL40dO1aDBg3Sm2++qbq6urDue+fOnZo8ebKuueYabd26VQUFBXrrrbd06aWXWjQ9EDn02Xr0B4AV6DMAN/HS9Q99tp6Xzh8gHPTHevQHAAAAkcBijIfk5OSEbr/99tvatWuXwWnCt3jx4tDtnJyciL+kG5ruqquu0qZNmzRv3jyVlZXpjjvuUPfu3fX0009r586damhoaNL97N+/XytWrFB2drZ69uypP/zhDxo+fLi2bdum+++/n3MArkWf7UN/AISDPgNwIy9c/9Bn+3jh/AHCQX/sQ38AAABgp5iA1a9LCEfr16+ftmzZIkkaNWqUXnnlFcMTtUxRUZGys7NDH5eUlOi6664zOBGaqq6uTm+99ZYWLFigtWvXSpLatm2rtLQ0paenKyUlRfPmzVNMTIymTJmivXv3qqSkRMXFxfriiy8kSZdddpkmTJign/70p+rcubPBz8aMjIwMSdKGDRuMzuFUbv360Gf70Z/wufX7C87g1vOHPjuDW88fwLRovv6hz/aL5vMnUnj8apxbvz70x370J3xu/f6CM3D+APZJTEyUJFVVVRmdA/AiFmM8ZuPGjaGLGklaunSpxowZY26gFtizZ49uuukmVVZWSpJGjx6tZcuWGZ4KLVFRUaGNGzequLhYxcXFKi0tVU1NzRl/Lzk5WX379lV6err69eunAQMGKC4uzsDEzsATk8a59etDnyOL/rSMW7+/4AxuPX/oszO49fwBnCTarn/oc2RF2/kTKTx+Nc6tXx/6E1n0p2Xc+v0FZ+D8AezDYgxgDosxHjR69GgtX75c0on3cH3ppZdc8+Rt9+7dGjRokHbs2CHpxE8K7Ny5U126dDE8GaxQW1ur/fv36+jRo6qvr1fr1q3Vrl07tWvXzvRojsITk8a5+etDn82hP03j5u8vmOfm84c+m+fm8wdwquD1z7BhwyRJr7/+uuuuf+izOVw/Nw2PX41z89eH/phDf5rGzd9fMI/zB7APizGAObGmB0DkvfDCC7r66qslSQ0NDRo7dqxGjRrl6PfEraur0+9//3ulpqaGnrTFxcWpoKDANU/acH4+n0+XXHKJunfvrpSUFHXr1o0ntfAU+mwO/QHQGPoMIBoFr3/atGmjNm3auPL6hz6bw/UzvI7+mEN/AAAA0BIsxnjQRRddpHXr1oWevEnSa6+9Jr/fr2HDhmnZsmXatWuXGhoaDE4pHTp0SJs3b9bkyZPVvXt3TZw4UdXV1ZJOPGl75ZVXdNdddxmdEQCsRJ8BwJnoMwA4E30GYAr9AQAAANwl3vQAMOPiiy/Whg0blJeXp5dfflmSdPz4ca1cuVIrV66UJLVp00Z+v18XX3yxWrdurdhYe/eoAoGAjh8/rsOHD6uyslLffffdWf9eSkqKXnzxRQ0aNMjWeQDABPoMAM5EnwHAmegzAFPoDwAAAOAeLMZ4WKdOnbRs2TKNGzdOU6dO1UcffXTKnx89elTbtm0zNN2ZOnbsqMmTJ+uxxx5Tq1atTI8DALahzwDgTPQZAJyJPgMwhf4AAAAA7sBiDDRw4EB9+OGHKi8vV2FhoVavXq0dO3Zo//79RudKSEiQ3+/XjTfeqJEjRyojI0M+n8/oTAAQSfQZAJyJPgOAM9FnAKbQHwAAAMDZYgKBQMD0EHCmgwcPqry8XNXV1Tp27JgicaokJCSoTZs2uvzyy3XZZZcpLi7O9mMCbpORkSFJ2rBhg9E5nMoLXx/6DFO88P0F+3jh/KHP9vHC+QOY4oXvL/oMU7zw/RUOL3x96A9M8cL3F+zD+QPYJzExUZJUVVVldA7Ai3jFGJxThw4d1K9fP9NjAABOQ58BwJnoMwA4E30GYAr9AQAAAJwh1vQAAAAAAAAAAAAAAAAAgB1YjAEAAAAAAAAAAAAAAEBUYjEGAAAAAAAAAAAAAAAAUYnFGAAAAAAAAAAAAAAAAEQlFmMAAAAAAAAAAAAAAAAQlViMAQAAAAAAAAAAAAAAQFRiMQYAAAAAAAAAAAAAAABRicUYAAAAAAAAAAAAAAAARCUWYwAAAAAAAAAAAAAAABCVWIwBAAAAAAAAAAAAAABAVGIxBgAAAAAAAAAAAAAAAFGJxRgAAAAAAAAAAAAAAABEJRZjAAAAAAAAAAAAAAAAEJXiTQ8AZwkEAtq+fbt27typsrIyVVRUqKqqSjU1NQoEArYf3+fzqU2bNrr88svVo0cP9ejRQ9ddd50uvPBC248NAE5GnwHAmegzADgTfQZgCv0BAAAAnIfFGEiSPv74Yy1fvlyFhYX68ssvTY9zitatW+u2227TyJEjNXz4cLVq1cr0SAAQMfQZAJyJPgOAM9FnAKbQHwAAAMC5eCslj9u9e7dGjx6ttLQ0Pf/884570iZJx44d0xtvvKGf/OQn+sEPfqB33nnH9EgAYDv6DADORJ8BwJnoMwBT6A8AAADgfLxijIe9/vrreuCBB3T48OFTfr99+/bq379/6KU2O3furISEBMXG2rtHFQgEVFdXp0OHDqmyslJlZWXaunWrPvvss9DfKS8v1+DBg3X33XdryZIlSkhIsHUmADCBPgOAM9FnAHAm+gzAFPoDAAAAuAOLMR5VWFiou+++W/X19aHfu+OOO/Tggw8qKyvLUU+IPvvsM7366qt64YUXVF1dLUn685//rO+//16FhYWOmhUAwkWfAcCZ6DMAOBN9BmAK/QEAAADcg7dS8qCioqJTnrT5/X4VFRXpjTfe0G233ea4J0K9evXSr371K33++ecaO3Zs6PdXrlyp+++/39xgAGAx+gwAzkSfAcCZ6DMAU+gPAAAA4C68YozH1NTU6KGHHgo9aevZs6fWrVunLl26GJ7s/C6++GK99NJL6tq1q2bPni3pxE823Hvvvbr11lsNTwfYp7a2Vtu3b1dxcbF27dql4uJiSdKTTz6pxMRE9enTR2lpaUpKSjI8KcJBn+FE9Aegz6bQHwDnQ5/hRDx+eQP9gRPRHwAAgMbFBAKBgOkhEDmzZs3SE088IenEe91++umn6tq1q+GpmicQCOjee+/VsmXLJEkpKSnatm2bWrVqZXgywDrl5eVatGiRNmzYoK1bt6qmpib0ZzExMaHbJye8e/fu+uEPf6gxY8Zo8ODBiouLi+jMTpGRkSFJ2rBhg9E5mos+wynoD+xCn81xS5/pD2AGfTbHLX1G43j8ajn6Yw79iQ70B3Zxa58BN0hMTJQkVVVVGZ0D8CLeSslDamtrNXfu3NDHs2bNct2TNunERf2cOXPUvn17SSeeALz55ptmhwIsUF9fr1WrVunWW29Vjx49NHfuXLVp00aPPvqoli9frp07d6qurk4DBgzQgAEDVF9fr3379mnNmjV65plnlJ6erg0bNmjIkCFKSUnR7NmztXfvXtOfFpqAPsM0+gOcHX22H/0B0BL0Gabx+OVd9Aem0R8AAIAWCsAz3nnnnYCkgKRAt27dAnV1daZHCssvf/nL0Odz1113mR4HCMuWLVsCvXv3DkgKdO3aNfDrX/868M0335z17w4cODAwcODAs/7Z8ePHA4WFhYHMzMyApEDr1q0Dc+bMcf33e3M09vVxKvoMk+gPIoU+m+e0PtMfwBnos3lO6zMax+OXdeiPefTHXegPIsWNfQbcon379oH27dubHgPwJF4xxkMKCwtDt3Nyclz/MomjRo0K3f7b3/6mI0eOGJwGaJmamho98cQT+tGPfqT9+/frlVde0RdffKGnnnqqRT9x5PP5NGLECK1bt07bt29Xdna2fv7zn2vAgAH6/PPPbfgMYAX6DBPoD3B+9Nke9AdAuOgzTODxCxL9gRn0BwAAIHwsxnjI3//+99DtO++80+Ak1ujVq5d69uwpSTp69Kg+/vhjwxMBzVNeXq6+fftq1qxZGjt2rLZt26ZRo0bJ5/NZcv+pqan661//qqVLl+qzzz5Tnz59tGjRIkvuG9aiz4g0+gM0DX22Hv0BYAX6jEjj8QtB9AeRRn8AAACswWKMR9TX16uysjL0cZ8+fQxOY52TP4/y8nKDkwDN88knn+imm27Snj179NZbb6mgoEAdOnSw/DgxMTEaM2aMtm/froEDB2r8+PH6zW9+o0AgYPmx0DL0GZFGf4Cmoc/Woz8ArECfEWk8fiGI/iDS6A8AAIB1WIzxiK+++krHjx+XJHXu3Flt27Y1PJE1evToEbpdVlZmcBKg6T777DNlZmYqLi5OmzZt0u233277Mbt06aJVq1Zp9OjRmjlzpp599lnbj4mmoc+IJPoDNB19thb9AWAV+oxI4vELJ6M/iCT6AwDOVlhYqF27dkXseIFAQPn5+Tp69GjEjglEm3jTAyAyvvrqq9Dt7t27G5zEWn6/P3T75M8RcKpvvvlG2dnZio+P18aNG5WSkhKxY/t8Pv3pT3+SJD3++OPq1KmTxo0bF7Hj4+zoMyKF/gDNQ5+tQ38AWIk+I1J4/MLp6A8ihf4AgLMdOHBA48ePV6dOnbR+/Xp169bN1uMFAgFNnjxZ8+bNkyTl5ubaejwgWvGKMR5x8gZhu3btDE5irZN/MoMtSThdIBDQgw8+qIMHD2rNmjURfVIbFBsbq4KCAt1yyy362c9+ps8//zziM+BU9BmRQH+A5qPP1qA/AKxGnxEJPH7hbOgPIoH+AIDzJSUl6e2339a3336rzMxMW1855uSlmLy8PI0fP962YwHRjsUYj6itrQ3d9vl8Biex1smfS/ClTAGnWrJkid555x09++yzuuaaa4zN4fP5VFBQoDZt2uiBBx5QfX29sVlAnxEZ9AdoPvpsDfoDwGr0GZHA4xfOhv4gEugPALjD9ddfrzVr1ti6HHP6UszcuXMVExNj+XEAr2AxxoOiKZrR9Lkguu3atUt5eXkaOHCgHnnkEdPjqEuXLpo/f77ef//90Mvvwbxoalo0fS5uR3+A8EVT0yL5udAfAHajz7ADj19oimj6no2mz8Xt6A8AuIudyzEsxQDWYzEGACJg+vTpqqur0+LFixUb64z0jh49WkOGDNHMmTO1d+9e0+MAsAn9AWAK/QEAuBGPXwBMoT8A4D52LMewFAPYwxlXVwAQxf7973+rsLBQubm58vv9pscJiYmJ0bPPPqtjx46poKDA9DgAbEB/AJhCfwAAbsTjFwBT6A8AuJeVyzEsxQD2YTEGAGy2ePFi1dbWasKECaZHOUNqaqoyMjL0xz/+0dXvFXzkyBHl5+frxz/+sf75z3/qgw8+0DXXXKNJkyZpx44dpscDjKE/MI0+exf9AZyNPgNnx+OX/egPcHb0B6bRZyA8VizHsBQD2IvFGACwUV1dnfLz85Wdna0rr7zS9Dhn9fDDD+uLL77QO++8Y3qUZjt+/LimTZumrl27asKECXrvvfd07Ngx1dTU6JNPPtH8+fPVq1cvDRo0SNu3bzc9LhBR9Acm0Wdvoz+Ac9Fn4Nx4/LIX/QHOjf7AJPoMWCec5RiWYgD7sRgDADbavHmzvv76a+Xm5poe5ZyGDx+uzp07a+nSpaZHaZbvv/9et912m37729/q8OHDjf7ddevW6cYbb9TmzZsjNB1gHv2BKfQZ9AdwJvoMNI7HL/vQH6Bx9Aem0GfAei1ZjmEpBogMxy/GVFZWKjs7WzExMerQoYOmT59ueiRPC/5fnPyrQ4cOysnJUVVVVZPvx+/3q6ioyL5BAYf48MMPJUmZmZmGJzk3n8+nm266SR999JHpUZqsvr5ed999t959990m/5vq6moNGTIkan+ygT7jdPQHJtDnM3mxz/QHcB76fCYv9hmN4/HLHvTnTPQHp6M/MIE+A/ZpznIMSzFA5Dh+MSY7O1uJiYkqLi7WokWLtHDhQi1cuND0WJ42fvx4VVRUhH4VFhaqqKhI48aNMz0a4DjFxcXq3r27kpKSTI/SqPT0dFVWVurgwYOmR2mSFStWaNWqVc3+d9XV1Zo0aZINEzkDfcbJ6A9MoM9n57U+0x/Aeejz2Xmtz2gcj1/2oD9nR39wMvoDE+gzYK+mLMewFANElqMXY6qqqlRZWakZM2YoLS1NI0aM0MiRI7V27VrTo3laYmKikpOTQ7+ysrI0e/bsU35C4eRX+vH7/XruuedCfxa8gM7Ozj7l94FotGXLFqWnp5se47yCM5aUlBiepGkWLFjQ4n/77rvvaseOHRZO4xz0GSejPzCBPp+d1/pMfwDnoc9n57U+o3E8ftmD/pwd/cHJ6A9MoM+A/RpbjmEpBog8Ry/GBJ8g5Ofnq6qqSiUlJXrttdeUnZ1tejScxckb7cFX+qmoqFB+fr6eeeaZ0Cv9FBcXKzk5WWvXrtW0adNMjQvY7tChQ/rXv/6ltLQ006OcV3DG0tJSs4M0wbZt27Rp06aw7uPFF1+0aBp3oM/eQ39gAn1uvmjsM/0BnIc+N1809hmN4/HLHvSn+eiP99AfmECfgcg5fTmmoaGBpRjAkHjTA5zP2rVr5ff7Qxf9WVlZGj9+vOGpvK2qqir0frcHDhxQZWWlZs+erenTp0uSioqKdODAARUWFkqSkpOTNWPGDM2ePZv/O3hKdXW1JOmiiy4yPMn5dezYUdL/zexkGzZsCPs+1q9fH/4gDkSfEUR/YAJ9Pjcv9Zn+AM5Dn8/NS31G43j8sgf9OTf6gyD6AxPoMxBZweWYm2++WUeOHFF8fDxLMYABjl6MqaqqUnp6euiC/8CBA8rJydH06dM1e/Zso7Pl5eW5ajN63759lt3XwoULQ4tKQWlpaaEnZSUlJerbt+8pf56VlRV6YmeX999/XxkZGbYeA2iO//znP5KkOXPmaNmyZZbdb7A9Vp/vMTEx+t3vfhf2TwvY7csvvwz7Pnbu3OmYXtBn2IH+wAT6fG5e6jP9AZyHPp+bl/qMxvH4ZQ/6c270B0H0ByZEW58Bt/D7/SotLVVtba0uueQSlZSUKDMz0/RYcJlrr71WL7zwgukxXMnRb6VUVFSkpKQkTZs2LfS2SrNnzz7jSQMia9q0aQoEAqFfxcXFqqqqUm5urunRAEcJbvkGAgHDkzSNW+a0Yns6NtbRD38tRp8RRH9gAn0+Ny/1mf4AzkOfz81LfUbjePyyB/05N/qDIPoDE+gzEHmBQEB79+4NfVxVVaXjx48bnAjwHke/YsyBAwfO+vvBl5k0yW2bWKtWrdLQoUNtue+0tDSNGDFCJSUloY+feeaZU/7Oli1blJycbMvxg/r3769Vq1bZegygOfbs2aOuXbtq0qRJeuihhyy73+AmvhUveRlUX1+v+Ph4TZ06VU899ZRl92uHpUuX6t577w3rPvr27Wvp1y8c9Bl2oD8wgT43XTT3mf4AzkOfmy6a+4zG8fhlD/rTdPTHu+gPTIi2PgNOFwgENHnyZG3atEl5eXkaOXKkbrnlFu3bt0/r169Xt27dTI8IeIKjVzpHjhypAwcOaPr06aqsrFRJSYlyc3N5H1UH6tixY2iRKSsrS0lJScrJyVFlZaWKioo0ffr0M17qs7Ky0sSoQMR06tRJrVq1UkVFhelRzqu8vFySXHEBNmzYMF1wwQVh3ceYMWMsmsb56LM30R+YQJ+bJ1r7TH8A56HPzROtfUbjePyyB/1pHvrjTfQHJtBnIHKCSzHz5s1TXl6e5s6dqxtuuEFr1qzRt99+q8zMTO3atcv0mIAnOHoxJjExUe+++65KSkrk9/s1aNAgjRgxQvn5+aZHw2nS0tJUUlIS+qmGtWvXqqqqSn6/X7m5uZoxY8YpC025ubnKzc3Vc889Z2pkwHY+n099+vRRcXGx6VHOKzhjenq64UnOr127dho7dmxY//6ee+6xcCJno8/eRH9gAn1unmjtM/0BnIc+N0+09hmN4/HLHvSneeiPN9EfmECfgcg421JM8K3Mrr/+epZjgAhz9FspSSeeEKxdu9b0GPj/zvV/kZWVdcr7iyYnJzf6/zZt2jRNmzbN8vkAp0lPT9fLL7+shoYGR7/vanFxsVq1aqXU1FTTozTJxIkTtXjxYtXW1jb73+bm5urCCy+0YSqz6DNOR39gAn0+kxf7TH8A56HPZ/Jin9E4Hr/sQX/ORH9wOvoDE+gzYK/GlmKCgssxN998szIzM3lbJcBmzr3KAoAokJ6erkOHDqmsrMz0KI0qLi7WtddeK5/PZ3qUJklNTVVBQUGz/11WVpaefvppGyYCnIf+wAT6DIn+AE5En4Hz4/HLHvQHOD/6AxPoM2CfpizFBPHKMUDksBgDADYaOHCgJGnFihWGJzm33bt367333lNGRobpUZpl9OjRWrp0aZOfjA8dOlRvvvmmEhISbJ4McAb6A1PoM+gP4Ez0GWgcj1/2oT9A4+gPTKHPgPWasxQTxHIMEBksxgCAjVJSUpSVlaX8/HzV1dWZHuesFi1apIaGBo0bN870KM02ZswYlZaW6qGHHjrny3cOHDhQr776qt544w1dcMEFEZ4QMIf+wCT67G30B3Au+gycG49f9qI/wLnRH5hEnwHrtGQpJojlGMB+8aYHAIBo9/DDD+vOO+/U6tWrNWzYMNPjnKK2tlYLFy7UrbfeKr/fb3qcFklNTdWCBQv07LPPauXKldqzZ4+OHz+uxMREZWRk6OqrrzY9ImAM/YFJ9Nnb6A/gXPQZODcev+xFf4Bzoz8wiT4D4QtnKSYouBxz8803KzMzU+vXr1e3bt1smhjwHhZjAMBmQ4YM0aWXXqr58+dr6NChzb4YstPrr7+u3bt3Kz8/3/QoYWvXrp3GjBljegzAUegPnIA+exP9AZyPPgNn4vErMugPcCb6Ayegz0DLWLEUE8RyDGAf3koJAGwWHx+vqVOnat26dVq+fLnpcUIOHjyoKVOmqHfv3ho8eLDpcQDYgP4AMIX+AADciMcvAKbQHwBwJyuXYoJ4WyXAHizGAEAEPProo+rfv78mTpyoPXv2mB5HkjR58mR99913WrJkieLi4kyPA8Am9AeAKfQHAOBGPH4BMIX+AIC72LEUE8RyDGA9FmM84uQQNzQ0GJzEWid/Lk56eUngdHFxcSooKNDRo0c1YcIEBQIBo/OsXr1aL730kh5//HGlpaUZncXr6DPsRn+AlqHP4aM/AOxAn2E3Hr9wLvQHdqM/AOAedi7FBLEcA1iLxRiPaNWqVeh2TU2NwUmsdfLn0rp1a4OTAOd35ZVXatasWVq5cqVmzZplbI5PP/1U9913n3r37q0nnnjC2Bw4gT4jEugP0Hz02Rr0B4DV6DMigccvnA39QSTQHwBwvkgsxQSxHANYJ970AIiMxMTE0O1vv/3W3CAWO/lzad++vcFJgKbJy8tTaWmpnnzySbVt21aTJk2K6PHLysqUnZ0tn8+nv/zlL0pISIjo8XEm+oxIoT9A89Bn69AfAFaiz4gUHr9wOvqDSKE/AOBsBw8e1OrVq21figkKLscMHjxY//jHP5STk2Pr8YBoxWKMR/j9/tDtiooKNTQ0KDbW/S8YVFZWFrqdkpJicBKgaWJjY7V48WIdOXJEeXl5Onz4sGbOnBmRl6rdunWrbrnlFtXX12vdunWndAHm0GdECv0Bmoc+W4f+ALASfUak8PiF09EfRAr9AQBnS0pK0ocffqjExMSIvQ3h9ddfr4qKCiUlJUXkeEA0cv+VO5okKSkpFMujR49q9+7dhieyRnl5eeh2jx49DE4CNJ3P59Nrr72msWPH6sknn9Tw4cO1Z88e247X0NCg+fPn64YbbpDP59PmzZvVu3dv246H5qHPiCT6AzQdfbYW/QFgFfqMSOLxCyejP4gk+gMAztahQ4eILcUEsRQDhIfFGA/p2bNn6PbGjRsNTmKNmpoavf/++6GPr7rqKoPTAM0THx+vJUuWaM6cOVqzZo2uvvpqLVu2TIFAwNLjVFRUKDMzU5MmTVJmZqY++OCDU1oAZ6DPiCT6AzQdfbYW/QFgFfqMSOLxCyejP4gk+gMAAGAdFmM85Pbbbw/dLiwsNDiJNYqKilRdXS1JuuKKK5Sammp4IqB5YmNjNWXKFJWWlqpXr14aO3asBg0apDfffFN1dXVh3ffOnTs1efJkXXPNNdq6dasKCgr01ltv6dJLL7VoeliJPiPS6A/QNPTZevQHgBXoMyKNxy8E0R9EGv0BAACwBosxHpKTkxO6/fbbb2vXrl0Gpwnf4sWLQ7dzcnIi/pJlgFWuuuoqbdq0SfPmzVNZWZnuuOMOde/eXU8//bR27typhoaGJt3P/v37tWLFCmVnZ6tnz576wx/+oOHDh2vbtm26//77+R5xMPoMU+gP0Dj6bB/6AyAc9Bmm8PgF+gNT6A8AAEB4YgJWv+4eHK1fv37asmWLJGnUqFF65ZVXDE/UMkVFRcrOzg59XFJSouuuu87gRIA16urq9NZbb2nBggVau3atJKlt27ZKS0tTenq6UlJSNG/ePMXExGjKlCnau3evSkpKVFxcrC+++EKSdNlll2nChAn66U9/qs6dOxv8bNAc9Bmm0R/g7Oiz/egPgJagzzCNxy/voj8wjf4AAAA0H4sxHrNx40ZlZGSEPl66dKnGjBljbqAW2LNnj2666SZVVlZKkkaPHq1ly5YZngqwXkVFhTZu3Kji4mIVFxertLRUNTU1Z/y95ORk9e3bV+np6erXr58GDBiguLg4AxMjHPQZTkJ/gP9DnyOL/gBoKvoMJ+Hxy1voD5yE/gAAADQNizEeNHr0aC1fvlzSifcofemll1zz5G337t0aNGiQduzYIenEJvzOnTvVpUsXw5MB9qutrdX+/ft19OhR1dfXq3Xr1mrXrp3atWtnejRYhD7DqegPvI4+m0N/ADSGPsOpePyKfvQHTkV/AAAAzo7FGA/au3evMjMztX379tDvjRw5UnPmzFG3bt0MTnZudXV1evHFF/XEE0+ourpakhQXF6dXX31Vd911l+HpAMAa9BkAnIk+A4Az0WcAptAfAAAAwF1YjPGo7777Tv/93/99ypO3hIQE3XrrrcrJyVFGRoa6du2q2NhYYzMeOnRIW7du1RtvvKEVK1Zo165doT+Li4vTK6+8ohEjRhibDwDsQJ8BwJnoMwA4E30GYAr9AQAAANyDxRgP27dvn/Ly8vTyyy+f9c/btGkjv9+viy++WK1bt7b9SVwgENDx48d1+PBhVVZW6rvvvjvr30tJSdGLL76oQYMG2ToPAJhCnwHAmegzADgTfQZgCv0BAAAA3IHFGGjjxo2aOnWqPvroI9OjNKpjx46aPHmyHnvsMbVq1cr0OABgO/oMAM5EnwHAmegzAFPoDwAAAOBsLMYgpLy8XIWFhVq9erV27Nih/fv3G50nISFBfr9fN954o0aOHKmMjAz5fD6jMwGACfQZAJyJPgOAM9FnAKbQHwAAAMCZWIzBOR08eFDl5eWqrq7WsWPHFIlTJSEhQW3atNHll1+uyy67THFxcbYfEwDchj4DgDPRZwBwJvoMwBT6AwAAADgDizEAAAAAAAAAAAAAAACISrGmBwAAAAAAAAAAAAAAAADswGIMAAAAAAAAAAAAAAAAohKLMQAAAAAAAAAAAAAAAIhKLMYAAAAAAAAAAAAAAAAgKrEYAwAAAAAAAAAAAAAAgKjEYgwAAAAAAAAAAAAAAACiEosxAAAAAAAAAAAAAAAAiEosxgAAAAAAAAAAAAAAACAqsRgDAAAAAAAAAAAAAACAqMRiDAAAAAAAAAAAAAAAAKISizEAAAAAAAAAAAAAAACISizGAAAAAAAAAAAAAAAAICqxGAMAAAAAAAAAAAAAAICoxGIMAAAAAAAAAAAAAAAAohKLMQAAAAAAAAAAAAAAAIhKLMYAAAAAAAAAAAAAAAAgKrEYAwAAAAAAAAAAAAAAgKjEYgwAAAAAAAAAAAAAAACiEosxAAAAAAAAAAAAAAAAiEosxgAAAAAAAAAAAAAAACAqsRgDAAAAAAAAAAAAAACAqMRiDAAAAAAAAAAAAAAAAKISizEAAAAAAAAAAAAAAACISizGAAAAAAAAAAAAAAAAICqxGAMAAAAAAAAAAAAAAICoxGIMAAAAAAAAAAAAAAAAohKLMQAAAAAAAAAAAAAAAIhKLMYAAAAAAAAAAAAAAAAgKrEYAwAAAAAAAAAAAAAAgKjEYgwAAAAAAAAAAAAAAACiEosxAAAAAAAAAAAAAAAAiEosxgAAAAAAAAAAAAAAACAqsRgDAAAAAAAAAAAAAACAqMRiDAAAAAAAAAAAAAAAAKISizEAAAAAAAAAAAAAAACISizGAAAAAAAAAAAAAAAAICqxGAMAAAAAAAAAAAAAAICoxGIMAAAAAAAAAAAAAAAAohKLMQAAAAAAAAAAAAAAAIhKLMYAAAAAAAAAAAAAAAAgKrEYAwAAAAAAAAAAAAAAgKjEYgwAAAAAAAAAAAAAAACiEosxAAAAAAAAAAAAAAAAiEosxgAAAAAAAAAAAAAAACAqsRgDAAAAAAAAAAAAAACAqMRiDAAAAAAAAAAAAAAAAKISizEAAAAAAAAAAAAAAACISizGAAAAAAAAAAAAAAAAICqxGAMAAAAAAAAAAAAAAICo9P8A2E4RPb1WJwsAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 2232x720 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "fig, ax = qml.draw_mpl(training_circ)(5, np.random.random(size=(5,4,3)))\n",
    "fig.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "60acc0f0-7c80-43cc-8322-9967abd6651d",
   "metadata": {},
   "source": [
    "## Training "
   ]
  },
  {
   "cell_type": "markdown",
   "id": "23eea058-4ece-4fc6-a74b-04a18dfea2fe",
   "metadata": {},
   "source": [
    "Training parameters:\n",
    "1. Epochs\n",
    "2. Batch size\n",
    "3. Learning rate\n",
    "4. Layers in the Strongly Entangling generator circuit"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "499f8e11-f5e3-44f6-898e-bbbeee4dea5f",
   "metadata": {},
   "outputs": [],
   "source": [
    "epochs = 40\n",
    "batch_size=16\n",
    "learning_rate=0.01\n",
    "layers = 18"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0b7aa64b-a616-49f6-b112-ef76d5183a51",
   "metadata": {},
   "source": [
    "To train the circuit we first define the loss function.\n",
    "\n",
    "It is given by\n",
    "$$\\mathcal{L}=-\\log\\big[\\big|\\big<\\sigma|G(\\Theta_g)\\big>\\big|^2\\big]$$\n",
    "where the fidelity is exatly the output of the swap test.\n",
    "\n",
    "We also add a small regularization $\\epsilon$ in the $\\log$"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "233c9b8d-468e-4d3b-b863-b8a646f045a2",
   "metadata": {},
   "outputs": [],
   "source": [
    "def cost_batch(paramsg, batch, reg=0.000001):\n",
    "    loss = 0.0\n",
    "    for i in batch:\n",
    "        f = training_circ(i, paramsg) + reg\n",
    "        loss += - np.log(f)\n",
    "    return loss / len(batch)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "64ec7f0c-5e97-4f12-8a99-b3c769077d32",
   "metadata": {},
   "source": [
    "We initialize the parameters of the generator and the optimizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "dc5b21c6-9ec8-44f1-a673-3b3c7e8c431d",
   "metadata": {},
   "outputs": [],
   "source": [
    "paramsg = np.random.uniform(0,np.pi, size=(layers,4,3), requires_grad=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "b54a745c-75cd-4dd7-b0df-89b5ec9ef424",
   "metadata": {},
   "outputs": [],
   "source": [
    "optg = AdamOptimizer(learning_rate, beta1=0.9, beta2=0.999)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a3456b9a-4aa3-4086-9374-a31da1347d35",
   "metadata": {},
   "source": [
    "To train we iterate over the data in batches"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "f424a83a-2115-4dbe-8996-8863ea08381a",
   "metadata": {},
   "outputs": [],
   "source": [
    "def iterate_minibatches(data, batch_size):\n",
    "    for start_idx in range(0, data.shape[0] - batch_size + 1, batch_size):\n",
    "        idxs = slice(start_idx, start_idx + batch_size)\n",
    "        yield data[idxs]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "13f174dd-f966-4fc4-8b5f-34e73254ca91",
   "metadata": {},
   "source": [
    "In the training loop we save the loss.\n",
    "\n",
    "Note that we define a the loss function with a lambda function for every batch of data to have only a single argument when passing it to the optimizer."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "id": "2289552e-d72b-4553-90b1-c4121f19ac7c",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch: 0 | Loss: 1.93 | \n",
      "____\n",
      "Epoch: 1 | Loss: 1.84 | \n",
      "____\n",
      "Epoch: 2 | Loss: 1.84 | \n",
      "____\n",
      "Epoch: 3 | Loss: 1.81 | \n",
      "____\n",
      "Epoch: 4 | Loss: 1.81 | \n",
      "____\n",
      "Epoch: 5 | Loss: 1.81 | \n",
      "____\n",
      "Epoch: 6 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 7 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 8 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 9 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 10 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 11 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 12 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 13 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 14 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 15 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 16 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 17 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 18 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 19 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 20 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 21 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 22 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 23 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 24 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 25 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 26 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 27 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 28 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 29 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 30 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 31 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 32 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 33 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 34 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 35 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 36 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 37 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 38 | Loss: 1.8 | \n",
      "____\n",
      "Epoch: 39 | Loss: 1.8 | \n",
      "____\n",
      "Time for 40 epochs: 40914.13648891449\n"
     ]
    }
   ],
   "source": [
    "losshist = []\n",
    "\n",
    "start = time.time()\n",
    "\n",
    "for it in range(epochs):\n",
    "    start_b = time.time()\n",
    "    for j,Xbatch in enumerate(iterate_minibatches(data, batch_size=batch_size)):  \n",
    "        cost_fn = lambda p: cost_batch(p, Xbatch)\n",
    "        paramsg = optg.step(cost_fn, paramsg)\n",
    "        print(j, end=\"\\r\")\n",
    "\n",
    "    loss = cost_batch(paramsg, data)\n",
    "    \n",
    "    losshist += [loss]\n",
    "    \n",
    "    print(f\"Epoch: {it} | Loss: {loss:.3} | \")\n",
    "    print(\"____\")\n",
    "    \n",
    "end = time.time()\n",
    "\n",
    "print(f\"Time for {epochs} epochs: {end - start}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "79d5d823-ed38-43f8-b5ec-8dd7f691b478",
   "metadata": {},
   "source": [
    "## Evaluation"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2d908f86-db92-45f7-a0d5-ee45a0a2240c",
   "metadata": {},
   "source": [
    "Lets check the training results:\n",
    "\n",
    "The loss evolution during training:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "id": "cf196299-4086-40a7-a382-f081e0b05cc9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAZsAAAEFCAYAAAA19ErLAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAAcXUlEQVR4nO3df3Ac533f8c8XOBBHEUccSMpOa4uijrTSce2MeQITj5Sf9jHNZMpOHMP0TNt0IjcC68ZNZxxXqv5w0mknUcS4TdImnQCZjDMZp6lMpuOUaeqUqJs4aTMuCdDOqKksiZAluRlZlqkDSVH8BXz7xz0LLA53wOF4e7vAvl8zGNzu3u3z3EqDD58fu4+5uwAASNJA2hUAAGx/hA0AIHGEDQAgcYQNACBxhA0AIHGEDQAgcYW0K5BV+/bt8wMHDqRdDQDYMmZnZ19z97tbHSNs2jhw4IDOnz+fdjUAYMswsxfbHaMbDQCQOMIGAJA4wgYAkDjCBgCQOMIGAJA4wgYAkDjCBgCQOMKmx973r/9YP/P7T6ddDQDIFMKmx9yl+rVbaVcDADKFsOmxkeGCrlwnbAAgjrDpsVKxoKs3bqddDQDIFMKmxxotG8IGAOIImx4bKRI2ANCMsOmx3cUhxmwAoAlh02Mjw40xG3dPuyoAkBmETY+VigUtuXTt5mLaVQGAzCBsemyk2FiPjhlpALCCsOmxUnFIkhi3AYCY3C0LbWZlSbWwOePu9V6evzTcuKTMSAOAFXls2Tzu7qclzUia7PXJS0XCBgCaJRI2ZjZhZmfXOf6omdXM7NGwXTazavjck70sN+yrmVkULJXY4YPdltUOYzYAsFYiYRNaDi2FgKm7+0zYrko6Lmk8+lwsGO6oXDObCPujsmqS5mNvudhNOethzAYA1kqjG22vpEux7Zq7T7v7dNiuaHUgKLR6qrHtyTD2spEjsXPNS6pKmgohVJM03fwBMztmZtMLCwudfp9VRhizAYA10gibKUlHQlis6sYys4qkS1FLJOLuc5IqIXQm1fnAfrlpe6+7z7v76fCz5hzufsbdJ0dHRzv+QnGEDQCs1fewCX/sH5O0R41urHgrZsLdT7T53GlJJ6JzdFhcPZTTN4MDpl07BhmzAYCYvodNNBEgBMaR2DjNhLufjN7T4nMTarSKohZQJ85ppXVTkdR20kIvlYpDukrLBgCWJTUbrSZpPBqgD/vOSstdYlF4PBF7/5NmNmtms2pqjYTwqbv7XBjbqbUas2kuNwRZJewvN3fPJWWkWNCVG0wQAIBIIjd1hj/qY037jsZen27x/rbTkKOAim2vGdhfp9yT4WVfgkZq3GvDmA0ArMjjTZ2JYwE1AFiNsEnA7uIQEwQAIIawSUCjZcOYDQBECJsElIoFZqMBQAxhk4CRYkFv3FzU4hKrdQKARNgkIno+GuM2ANBA2CRgZU0bxm0AQCJsElFimQEAWIWwScAIC6gBwCqETQKiJz8zIw0AGgibBEQTBC4zZgMAkgibRDBmAwCrETYJKDFmAwCrEDYJ2Dk0qMEBY8wGAALCJgFmxvPRACCGsEnIyHBBVxizAQBJhE1iWEANAFYQNgnhyc8AsIKwSUipOKQrNxizAQCJsEnMyDAtGwCIFNKuQL+ZWVlSLWzOuHs9iXIYswGAFXls2Tzu7qclzUiaTKqQkSKz0QAg0rewMbMJMzu7zvFHzaxmZo/2soywr2ZmUbBUYocPdlvWRnYXh3Tz9pJu3F5MqggA2DL6FjahNdFSCJi6u8+E7WovyjCzibA/Om9N0nzsLRe7KacTPPkZAFZkpRttr6RLse1a/KCZVeMBZGaTYexlI0e0Ei7zkqqSpkII1SRNN3/AzI6Z2fTCwsLmvkETno8GACuyEjZTko6EAFnTteXuc5IqIXQm1fnAfrlpe6+7z7v76fCz5hzufsbdJ0dHRzf7HVZZbtkwbgMA2QibEACPSdqjRtfWfIv3nJZ0Inp/h6euh3P2XbSmDS0bAMhI2IQWy0QIkSOtxndC19dUeF1pPt7GOa20biqS2k5Q6LWVbjRu7ASAfs5Gq0kajwbtw76z0nI3WRQoT7T4bFWNCQRz7j4tqdZqzKa5jBBalbC/HE0U6AcWUAOAFX27qTP8oR9r2nc09rrtbLUojGLbawb21ynjZHjZt6CRVsZs6EYDgIx0o21HI7RsAGAZYZOQ4cKgdhQGdJkxGwAgbJJU4mGcACCJsEkUD+MEgAbCJkEjxQJjNgAgwiZRpeEh7rMBABE2iRqhGw0AJBE2iWLMBgAaCJsElYYZswEAibBJVKk4pKs3bsvd064KAKSKsEnQSLGgxSXXm7dYrRNAvhE2CWIBNQBoIGwSxMM4AaCBsEnQ7uUF1LjXBkC+ETYJ4snPANBA2CSIMRsAaCBsEhSN2fDkZwB5R9gkqBTGbFjTBkDeETYJWm7ZMGYDIOcImwQNDph27RhkzAZA7hXSrkC/mVlZUi1szrh7PcnyRoqs1gkAeWzZPO7upyXNSJpMurBScUhXbjBmAyDfEgkbM5sws7MbHK+Z2eR6+3pRbovzVmKHD3ZbVqdGhllmAAASCZvQcmjJzGqS5t19RtK8mVVb7etFuWY2EfbPxMuOveViN+VsBmvaAEA63WjnJZ0KgVJx97k2+5aFQKrGtifD2MtGjmglXOYlVSVNhRCqSZq+42+zgVKRNW0AoO8TBNy9bmZTkk6pMW7Scl/TZ+ZCd5gkjavzgf1y0/Zed5/X6tbNKmZ2TNKxQ4cOdXD6jZWGh5ggACD3+t6yCV1ZM+5+UFI9GlNp3tf8udBFdiK8bhsWTeqS9mymfu5+xt0nR0dHN/OxtkaKBR7ECSD30uhGq8a6yZ5QIwxa7VslBNBUeF1pPt7GOa20biqS2k5aSMrIcEFv3FzU4hKrdQLIr6Rmo9UkjcdbKLFZYtNhzKUm6bi7T7fZFz9fVVLd3efCsVqrMZvmckNrqBL2l6OJAv1U4snPAJDMmE34oz7WtO9o+F1X08B8q31Nx+eatlu+t025J8PLvgeNtDpsRncOpVEFAEhdHm/q7KsSC6gBAGGTNJYZAADCJnEsoAYAhE3ilsOGCQIAcoywSRhjNgBA2CSOMRsAIGwSd9eOQQ0YYzYA8o2wSZiZaWSYh3ECyDfCpg9KxSFdZswGQI4RNn1QYmloADnXUdiY2YHw+31m9gkz251orbYZFlADkHcbho2ZPSVpwszuU+P5ZSbpN5Ku2HbCmA2AvOukZVNx909J+qCkKXf/RTUe148OlYpD3GcDINc6eerzC2b2CTUWLnvAzD6opicrY30jLA0NIOc6adk8okbX2XF3vyzpiKSjidZqmykVC7rMmA2AHNswbNx9QdIpd79gZu+T9JqkbyVes22kNFzQzdtLunF7Me2qAEAqmCDQB9Hz0Zj+DCCvmCDQB8vPR2PcBkBOMUGgD1jTBkDeMUGgD0YIGwA5t2HLJkwQ+MXY9j9PtEbb0G7WtAGQc51MELjPzM6b2XNmdsnMzpnZe/pQt0SYWdnMJsJPuR9lMmYDIO866Ub7rKRH3P0d7r5HjbGbrTwb7XF3Py1pRtJkPwqMutEIGwB51UnYmLtfiDbcfU6NMZz2H2i0Gs5ucLxmZpOxfdWoxdFJxTstt0VZ8Zl0B7stazOYIAAg7zoJm/Nm9pSZ/Wj4eUrS+fU+EFoOLZlZTdK8u89ImjezajgUtTj2mFlXU6uby42CK5S1XHbsLRe7KWezhguD2jE4QNgAyK1OniDwj9ToSvtBNWahnQ37unVe0qkQMhV3nwutjnNmVnH3aXePB0LU6qnGtic7HG85opVwmZdUlTQVQqimxk2qq5jZMTObXlhY6OrLtdNYZoAJAgDyqe1sNDP7Z5I8titqBYyZ2SfCjZ6b5u51M5uSdEqNcRNppTvrUjj2mLvXY5+ZC91hkjQuaSZ+fB3lpu29IcjmW7w3KuuMpDPj4+OPdHD+jvEwTgB5tl7LZl7SC7Gf+djPC90WGLqyZtz9oKR6bIzmYgiQWbUYuA9dZCfC67Zh0aQuaU+3de0lFlADkGdtWzbu/nsJlVl195Ph9ROSjks6p5VQKKsREquEUJqSNB662zoJnHNaad1UJLWdtJC0kWGWhgaQXx0tC71ZofUyHp9ZFpslNh3GXGpqPJVgOrRaymGf3H266XxVSXV3nwvHaq3GbJrLDeethP3laKJAGkrFIV1mzAZATnXybLRNC3/Ux5r2HQ2/62oxMB9r7awJhDDdOr695vPrlNv2vP1UYmloADmWSMsGazFmAyDPCJs+iWajufvGbwaAbYaw6ZNScUiLS643b7FaJ4D8IWz6ZPlhnHSlAcghwqZPouejXSZsAOQQYdMnJZ78DCDHCJs+KbGAGoAcI2z6hDEbAHlG2PQJa9oAyDPCpk9Kw6EbjTEbADlE2PTJyHLLhjEbAPlD2PTJ4IDprh2DjNkAyCXCpo94PhqAvCJs+miEJz8DyCnCpo9GWNMGQE4RNn20u0jLBkA+ETZ9NDLMmA2AfCJs+qhULDAbDUAuETZ9NDI8xH02AHKJsOmjUrGgN24uanGJ1ToB5Ath00fR89HeuElXGoB8KaRdgX4zs7KkWticcfd6v8qOP4xzd1hyAADyII8tm8fd/bSkGUmT/Sx4JDyMk0kCAPImkbAxswkzO7vB8ZqZrfljb2ZP9rLcFmVVYocPdltWN0o8jBNATiUSNqHl0JKZ1STNu/uMpHkzqzYdq7T77GbLNbOJsH8mXnbsLRe7Lasby09+5sZOADmTRjfaeUmnQshU3H1OksysotVBsMzMqk2hNBnGXjZyJHbOeUlVSVMhhGqSpluUdczMphcWFjbxlTqzmwXUAORU38MmDMhPSTol6YHYoYq7twybEEiVEDqT6nxgv9y0vdfd5939dPhZcw53P+Puk6Ojox2cfnOiSQG/+oXn9Ot/clFfe+2NnpcBAFnU97AJXVkz7n5QUj0aU4m6utoJXWQnwuuWodRCXdKeO6lvL91dGtbPHnunikOD+oX/+oy+/1N/rB/65S/qV2ae01dfuSJ37r8BsD2lMfW56u4nw+snJB1XY+ympkZLpGJm1ah7LRK6vqYkjZtZ21ZQk3Naad1UJLWdtNAPZqaHH7pPDz90n77++jV9/ulX9PmnX9Ev//dn9Uszz6qyb5d+5PDb9LEfOKSBAUuzqgDQU0nNRqupEQoTsX3RH/rpMOZSk3Tc3afdfS60bPZobdeXwnhNPbxvWlKt1ZhNc7mhNVSJgmyj1lM/vX3sLv3E91R0+qMP6kuPv1//6kfepX2lYf2bs8/qT579ZtrVA4CeMrpuWhsfH/fz58/3tcxrN2/rXT/7R/rJHzikn/7Bb+9r2QBwp8xs1t3HWx3L402dmXXXjoL+xrft1oWX6mlXBQB6irDJmOq9ZX355ToP6wSwrRA2GXP4njFdvXFbz796Ne2qAEDPEDYZU713TJI099LrKdcEAHqHsMmYA3vv0thdQ5p7kbABsH0QNhljZjq8f0wXXq6nXRUA6BnCJoOq+8t6/tWrWrjG06EBbA+ETQZV9zfGbS68TFcagO2BsMmg77inrAET99sA2DYImwwaGS7o/reWmJEGYNsgbDKqeu+YvvxyXUvc3AlgGyBsMurwPWVduX5bF7/JzZ0Atj7CJqO4uRPAdkLYZFRl3y6N7hzS3Iv1tKsCAHeMsMmoxs2dZaY/A9gWCJsMq+4f03OvXtXl69zcCWBrI2wy7PD+stylL3O/DYAtjrDJsPfcU5ZxcyeAbYCwybBScUj3v4WbOwFsfYRNxh3eX9aFl17n5k4AWxphk3HV/WO6fP225l97I+2qAEDXchc2ZlY2s4nwU067Phup3luWxM2dALa23IWNpMfd/bSkGUmTaVdmI5V9I9pdLOgCYQNgC0skbEKr4ewGx2tmNhm2y2ZWDfuf7GW5zWVJqsQOH+y2rH4ZGDC9Z/8YM9IAbGmJhE1oObRkZjVJ8+4+I2nezKqSjksajz4XC4Y7KtfMJsL+mXjZsbdc7KacfqvuL+ur37iiK9zcCWCLSqMb7bykUyFkKu4+5+7T7j4djle0OhAUWj3V2PZkh+MtR2LnmpdUlTQVQqgmabr5A2Z2zMymFxYWNvu9EnN4/5jcpa+8nJ06AcBm9D1s3L0uaUrSKUkPxI+ZWUXSpaglEvvMnKRKCJ1JSTPhPBspN23vdfd5dz8dftacw93PuPvk6Ohop18pce+5pyxJjNsA2LL6HjahK2vG3Q9KqkddXcGEu59o9bnQRXYivJ5v9Z4W6pL23EF1M2F055AOvWWEGWkAtqw0utGqoaUiSU8ohIGZTbj7yfC62vyhEEpT4XWl+Xgb57TSuqlIajtpIeuq+8u68HJd7tzcCWDrSWo2Wk3SeLzVEpslNh3GXGqSjrv7dHj9pJnNmtmsmlojIXzq0fiOpFqrMZvmckNrqBL2l5u757aS6v4x1a/d0gvc3AlgCyokcdLwR32sad/R8LuupoH58P6205BjLaFoe83A/jrlngwvt2zQSI1JApI091JdlbtHUq4NAGxOHm/q3JLe8ZYRlYYLjNsA2JIImy2icXNnmZs7AWxJhM0WMn7vHj3zymX92XOvpV0VANgUwmYL+ch3H9C3v7Wkj35mVs+8cjnt6gBAxwibLaRUHNKnHz6iu4YH9fCnz+mVhetpVwkAOkLYbDF/bXSnPv3j36kr12/r4d86x/PSAGwJhM0W9M6/vlu/9veqevYbV/ST/+GCbi0upV0lAFgXYbNFfd/9d+vnP/AuffHZb+qTn3uaJwsAyLREbupEf3z4yH59/fU39e++8LzePrZTH3vfO9KuEgC0RNhscR8/er++/vqb+tR/e1ZvG9upDxx+e9pVAoA1CJstzsz05Ae/Q68sXNejp/9Cb91d1IMH96VdLQBYhTGbbWBHYUC//mMP6MDeXfrIb53Tma/8VdpVAoBVCJttYnTnkH538r1699tG9U9+94I+9Udf1dISkwYAZANhs43sGxnW7/zEe/Xh8Xv0q//jeZ34zKyu3riddrUAgLDZbnYUBvQLH3y3/sWxd+oLz7yqH/33/1Mvfeta2tUCkHOEzTZkZvrxh+7Tb3/kO/WNyzf0d37tz/S/LvLwTgDpIWy2sYcO7dN//thDuntkWD/2m/9bv/3nX+PmTwCpIGy2uXv37tJ/+scP6vvvv1s/8/v/Rz996iu6zPPUAPQZYZMDpeKQpv/BuH7q/e/Q5y78P/3QL32RNXEA9BVhkxODA6aPH71fv/fRB1XcMai//5tf0ic/97TeYLYagD4gbHLm8P4x/eFPfY/+4Xffp8986UX98L/9U5372qW0qwVgmyNscqg4NKhP/u136j8+8l4tuev41J/r5/7LX+r6rcW0qwZgm8rds9HMrCypFjZn3L2eXm3S9V2Vvfr8P/1e/fwf/l/9xp++oC8886oePLhPA9aYPm0mDZjJJA0MmAbMVCoWtHvnkHYXCxrdOaTdO4cav4uN3zsK/PsFwFq5CxtJj7v7YyF0JiWdTLk+qdo1XNDPfeDd+lt/89v0L//gL/UHf/FXWnLJ3eUuuaSl8HpxyXVzg4XadhcL2jcyrL0jO5Z/7901rH0jO7RruKDbi67bS67FpSXdWnQtLrluLS1pcdEb5aoxNTuaoR2fqD00YBoeGtCOwQENDw2G3wMaLgxqaNDkatR7aalR5+h7LHm03ShvcSl6vbLfXRowSWYaiIdsCF0zkySFtyhsytQ47qHu7lq+bu7h28S+RPP3u1N3eprmevgdn7H7spENA2b6u9+1v+fn7VvYmNmEpBPufnSd43VJFXef7lUZLc5biX3kYDflbEffe//dmvn49234vuu3FnX5+i1dfvOWFt68rctv3tLl67e08OYt1a/d0reu3tBrb9zUt67e0POvXtWXXrip16/d5A8LsEXsGBzY2mHj7qfN7ESrY2ZWkzTv7nNmVjOzqrvP3WkZIWjk7jNmNhmVE/vIxc2WkXfFoUEVhwb1llKx48/cXlzSpWs3de3GogqDpqHBAQ0OmAoDpsLggAoDpsEB02DUeohaDdELNVoJt5dcN28v6cbtpfB7MfZ6ablFMhDrAhwYWN0VOGiNsqLX8eNRK06u5daQS8sPNI23XqTVrRcL9V1u+YQWT/R94t8lehXbtS739d9r6vBE7T7f9PE7O9tmC+9nYUhTVrrRzkuaNbMPqdECmYkfNLOqJEUBZGaTkj7bwXjLEUlPhdfzkqqSpqIQkrSmBWVmxyQdO3ToUJdfBc0KgwONcCp1fw4z01AIql3DvasbgP7IRNi4e93MpiSdkjTT4vicmU2Efx2Oq/OB/XLT9l53n9fq1k1zWWcknRkfH3+kw+oDADaQialDoXtrxt0PSqrHWh7L3P20pBPhdduwaFKXtKdX9QQAdCcTYSMpPkbzhFoERAigqfC60ny8jXNaad1UJJ29s2oCALrRt7AJrZfxeKvFzKI//tOxAfzjzbPRwphN3d3nwrFamLq8bhmhNVQJ+8vNY0EAgP4wHjnf2vj4uJ8/fz7tagDAlmFms+4+3upYVrrRAADbGGEDAEgc3WhtmNk3Jb3Y5cf3ScrqgjHUrTvUrTvUrTtbtW73uvvdrQ4QNgkws/Pt+i3TRt26Q926Q926sx3rRjcaACBxhA0AIHGETTK6emp1n1C37lC37lC37my7ujFmAwBIHC0bAEDiCBsAQOIImx4KyyDUwno7mWJmr5vZWTN7NO26RML1OttiX+rXsE3dUr+GZlY2s2qo35Ox/alft3Xqlvp1C/WohZ9MXbd16paJ6xa50+tG2PRIfFXQsF1Lt0ZrfMjdj7r7ybQrEgkPSl2WpWvYXLcgC9fwuKTxqH7hAbZZuW5r6hb2p37dwsN8q+EaVc2skpXr1qpu4VDq1y0Srk0lvO7quhE2vXNEK4uyRauCZkl5E0szpIVruAF3n449Fb2ixnXKxHVrUzcpG9dtzt1PhqfFz4c1sbJy3VrVTcrAdZOWl3SJryHW1XUjbHqn3LS9N41KrGOPpEthRdSsKjdtcw3bCH8ALoV/XZabDqd63ZrqJmXouqmx0u/F8LrcdCzt/9/idZOyc90qTQtWlpuOd3TdCJveqSvDq4KGf3XW1WYl1Iyoi2vYqQl3PxFe15Wt6xavW6auWwjAg6EedWXoujXVLRPXzcxqLdYBq6uL60bY9E5mVwUN/fpZ65JqhWvYATObiPrxQ50yc92a65aV62ZmT8bGkOpq/LHMxHVrVbesXDc1Wla1EHaVO/n/jbDpkYyvCvpZadXAXqvB777L8sqqLVaWzcQ1DPV60sxmzWxW0p6sXLdWdVNGrpsaS8rPx67RdFauW6u6KSPXLYwnzajx37Icq8umrxtPEAAAJI6WDQAgcYQNACBxhA0AIHGEDQAgcYQNsA01P2cLSBthAwBIHGEDpMjMpszsYrg3pRr2TYYb/WbDsVrT+2fDT6XN/nLYXQlPDZ5N+859oJB2BYC8CgGwx90PhuA4K+mgGjfP1dz9gbB/VtJY7P0PhGA6JemBcPd5PeyflPR4OFc1du5TkjJxMy/yibAB0nNEjdbHqbBdibVKnpIkd583s/kQGEdj++di7z0q6Ymwf1pavpt/JnaO6L1AKggbIF2PNT/uw8w6/eyeVq9jwVK/k4oBvcSYDZCes5JOSI3H8ofniUU+HPaXtfKI99nY/qpW1hQ5K+lDYf+EJGahIXNo2QApcfcZMzsaQqasEBjBfPN+d582swdiofRIbP+p2P73q7E2CpAZPIgTyBhrrDk/n5WncwO9QDcaACBxtGwAAImjZQMASBxhAwBIHGEDAEgcYQMASBxhAwBIHGEDAEjc/wdi5k9voja+PAAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.plot(losshist)\n",
    "plt.xlabel(\"epoch\")\n",
    "plt.ylabel(\"loss\")\n",
    "plt.yscale('log')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e8fd4851-9028-42fc-9b08-95032ab106f6",
   "metadata": {},
   "source": [
    "Lets also check the distribution we get when sampling from the generator:\n",
    "\n",
    "To do so we write a new qunode containing only the generator and sample from it."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "id": "282f682c-27f2-4013-9b86-8c3c1e6f703f",
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_dev = qml.device('lightning.qubit', wires=4, shots = N)\n",
    "@qml.qnode(sample_dev)\n",
    "def sample_test():\n",
    "    generator(paramsg, [0,1,2,3])\n",
    "    return qml.sample()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "945f0e34-5bf6-4e56-97d4-026590abe112",
   "metadata": {},
   "source": [
    "To compare it with our generated data we convert convert a sample measurement from binary to integer and plot it "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "id": "03cafea7-6653-4d8b-be71-cc7c2a1b7e42",
   "metadata": {},
   "outputs": [],
   "source": [
    "testresult = [int(''.join(str(i) for i in a), 2) for a in sample_test()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "id": "6760a2b6-d7f6-4d7a-a787-e5e5ba443c6b",
   "metadata": {},
   "outputs": [],
   "source": [
    "valuestest, countstest = np.unique(testresult, return_counts=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "id": "fa5276b1-6d69-4079-ba5e-c238bfb61b5c",
   "metadata": {},
   "outputs": [],
   "source": [
    "x=np.arange(0,16)\n",
    "zerovals = [i for i in x if i not in valuestest]\n",
    "zeros = np.zeros(len(zerovals))\n",
    "valuestest = np.append(valuestest, zerovals)\n",
    "countstest = np.append(countstest, zeros)\n",
    "\n",
    "x=np.arange(0,16)\n",
    "zerovals = [i for i in x if i not in values]\n",
    "zeros = np.zeros(len(zerovals))\n",
    "values = np.append(values, zerovals)\n",
    "counts = np.append(counts, zeros)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "de18e5b2-b26f-4d83-b19e-cc42045abaad",
   "metadata": {},
   "source": [
    "We see a good agreement with the original distribution."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "id": "4935258c-e5c0-4e40-bd39-22e273fb7cb1",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 2700x1500 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(9,5))\n",
    "plt.plot(values,counts/N, 'b.', markersize=12, label=\"True\")\n",
    "plt.plot(valuestest,countstest/N, 'r.', markersize=12, label=\"QGAN\")\n",
    "plt.ylabel('$P_i$', fontsize=18)\n",
    "plt.xlabel('$i$', fontsize=18)\n",
    "plt.legend()\n",
    "plt.xlim(0,16)\n",
    "plt.gcf().set_dpi(300)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tfq",
   "language": "python",
   "name": "tfq"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}