diff --git a/docs/tutorials/10_effective_dimension.ipynb b/docs/tutorials/10_effective_dimension.ipynb index 8026668cf..e3e7de821 100644 --- a/docs/tutorials/10_effective_dimension.ipynb +++ b/docs/tutorials/10_effective_dimension.ipynb @@ -50,9 +50,9 @@ } }, "source": [ - "## 3. Basic Example (CircuitQNN)\n", + "## 3. Basic Example (SamplerQNN)\n", "\n", - "This example shows how to set up a QNN model problem and run the global effective dimension algorithm. Both Qiskit `CircuitQNN` (shown in this example) and `OpflowQNN` (shown in a later example) can be used with the `EffectiveDimension` class.\n", + "This example shows how to set up a QNN model problem and run the global effective dimension algorithm. Both Qiskit `SamplerQNN` (shown in this example) and `EstimatorQNN` (shown in a later example) can be used with the `EffectiveDimension` class.\n", "\n", "We start off from the required imports and a fixed seed for the random number generator for reproducibility purposes." ] @@ -68,21 +68,19 @@ "outputs": [], "source": [ "# Necessary imports\n", - "from qiskit.circuit.library import ZFeatureMap, ZZFeatureMap, RealAmplitudes\n", "import matplotlib.pyplot as plt\n", "import numpy as np\n", - "\n", - "from qiskit_machine_learning.neural_networks import CircuitQNN, TwoLayerQNN\n", - "from qiskit.utils import QuantumInstance, algorithm_globals\n", + "from IPython.display import clear_output\n", "from qiskit import QuantumCircuit\n", - "from qiskit_aer import Aer\n", - "\n", - "from qiskit_machine_learning.neural_networks import EffectiveDimension, LocalEffectiveDimension\n", - "\n", - "from qiskit_machine_learning.algorithms.classifiers import NeuralNetworkClassifier, VQC\n", "from qiskit.algorithms.optimizers import COBYLA\n", + "from qiskit.circuit.library import ZFeatureMap, RealAmplitudes\n", + "from qiskit.utils import algorithm_globals\n", + "from sklearn.datasets import make_classification\n", + "from sklearn.preprocessing import MinMaxScaler\n", "\n", - "from IPython.display import clear_output\n", + "from qiskit_machine_learning.algorithms.classifiers import NeuralNetworkClassifier\n", + "from qiskit_machine_learning.neural_networks import EffectiveDimension, LocalEffectiveDimension\n", + "from qiskit_machine_learning.neural_networks import SamplerQNN, EstimatorQNN\n", "\n", "# set random seed\n", "algorithm_globals.random_seed = 42" @@ -101,7 +99,7 @@ "source": [ "### 3.1 Define QNN\n", "\n", - "The first step to create a `CircuitQNN` is to define a parametrized feature map and ansatz. In this toy example, we will use 3 qubits, and we will define the circuit used in the `TwoLayerQNN` class." + "The first step to create a `SamplerQNN` is to define a parametrized feature map and ansatz. In this toy example, we will use 3 qubits, and we will define the circuit used in the `SamplerQNN` class." ] }, { @@ -118,7 +116,7 @@ "outputs": [ { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAWAAAACoCAYAAADerTQhAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/NK7nSAAAACXBIWXMAAAsTAAALEwEAmpwYAAAgNklEQVR4nO3de1yO9x/H8Vd3pYN0EiJzSDSiRub0y8ommjnNxJxGGiZsjptTDkMzctjM2Ry2Wc42hzBGYc4z0WwSkSiHVYhC993vj7jn7o5uiutmn+fj0ePRfX2v63t9r+t79b4v3+t2f01ycnJyEEII8dyplG6AEEL8V0kACyGEQiSAhRBCIRLAQgihEAlgIYRQiASwEEIoRAJYCCEUIgEshBAKkQAWQgiFSAALIYRCJICFEEIhEsBCCKEQCWAhhFCIBLAQQihEAlgIIRQiASyEEAqRABZCCIVIAAshhEIkgIUQQiESwEIIoRAJYCGEUIgEsBBCKEQCWAghFCIBLIQQCpEAFkIIhUgACyGEQsyUbsDL4tROuHlF6VaIvEqUBvc3C1eH9K0oyNNeZxLAReTmFUhPUroV4lmQvhXPigxBCCGEQiSAhRBCIRLAQgihEAlgIYRQiASwEEIoRAJYCCEUIgEshBAKkQAWQgiFSAALIYRCjDqANRoN4eHhVK1aFUtLS7y8vIiOjsbd3Z3evXsr3TyDqDVqFmwaRvtxpWg9ugTjl73H9VvXlG6WKALSt6KwjDqAg4ODmTBhAn369GHLli106NCBTp06cfbsWby9vZVunkFW7JrMvj9/ZtaAg0SMyv3/rF9GdFO4VaIoSN+KwjLa74KIiIhg6dKlREVF4evrC0CTJk04evQo69ato06dOgq30DCRBxbQ1X8MZUu6AtDrnSl0/9KNy2nnKeNQUeHWicKQvhWFZbR3wGFhYQQEBGjD9wE3NzfMzc3x9PQE4Ny5c/j6+lKtWjVq1arFnj17lGhuvjIy07mSnkhVl3/v1ss5VcHa0pYzl2IUbJkoLOlbURSMMoCTkpKIjY0lMDBQrywxMREPDw8sLCwA6NOnDx07diQuLo758+fz/vvvc/fu3QL3YWJiUqQ/0dFRevu4fecmAMWt7HSW21jaczvrxlOcGfGkoqOjpG/FM5f3OjOU0QYwgLOzs87yzMxMoqOjtcMP165dY+/evQQHBwPQqFEjypUrx65du55vgx/B2qIEALcyr+ssz8hKx9rSVokmiSIifSuKglEGsJOTEwBxcXE6y6dMmUJycrL2AVxiYiJlypTR3g0DVK5cmfPnzxe4j5ycnCL98fX109uHjZU9pe0rEH/xqHZZ8j9nuZ11A9eynk9zasQT8vX1k74Vz1ze68xQRvkQztXVFU9PT8LCwnB0dMTFxYU1a9YQGRkJ8MJ8AgKgRYPerIz6Ei+3Jthal2Rh5GfUrdYcZ8dKSjdNFJL0rSgso7wDVqlUrF69Gg8PD/r27UtQUBBOTk7069cPU1NT7QO4ChUqcPnyZe7cuaPdNiEhgYoVjecJ9PtNhtOgeiv6f/U6nSa6oNGoGd75B6WbJYqA9K0oLJOcJ7lfVli3bt2IiYnh+PHj2mXNmjWjbdu2hISEsG/fPtq3b8+5c+coVqzYc23bkRUybY0xsi8Pdd8vXB3St6IgT3udGeUQxKMcOXKEBg0a6CybN28ePXr0YObMmRQrVoyIiIjnHr5CCPE0XpgAzsjIIC4ujpCQEJ3lrq6u7N69W6FWCSHE03thAtjGxga1Wq10M4QQosgY5UM4IYT4L5AAFkIIhUgACyGEQiSAhRBCIRLAQgihEAlgIYRQiASwEEIoRAJYCCEUIgEshBAKkQAWQgiFSAALIYRCJICFEEIhEsBCCKEQCWAhhFCIBLAQQihEAlgIIRQiASyEEAqRABZCCIVIAAshhEIkgIUQQiESwEIIoRAJYCGEUIgEsBBCKEQCWAghFCIBLIQQCpEAFkIIhUgACyGEQiSAhRBCIRLAQgihEAlgIV5i2w4vpftkN6WbwZC5fizfMVH7utUoG06e21+k+7ianoT/MBNSUs8Vab3PkpnSDfivO3F2DyO/fVtvuVqTzb3sO0zvu5ul20L56/x+TE3NteV+r73PkMBFhdp3Suo5un1RmR9HXaCUfflC1VWQbYeXEr4qiNdffZuw4EidsuCpNUi88hfhH+3Cq4rfM22HMRoy10/bvyqVKc4Olen81ih8vQKf2T5/PbqcyRFd+cB/HN2ajX1m+3mUjZMytL/HnIni0wVN2fZl9nNvh9IkgBVWy7WxzsUIcPdeFkPm+mJvUxqPSv8DoEvTULo0Ha1EEwuUrb6H2UNvDo9S0rYcf58/wJW0REo7VAAgNmEvak02KpXps26mUXvQv2p1Nj/v+4YvfuyMm0ttXJyezd3r5gPzKWHtyJbD39K56WhM/+PnXylGPQSh0WgIDw+natWqWFpa4uXlRXR0NO7u7vTu3Vvp5j0z4at6cudeJiO7RKBSPb6LElJiGb6wOe3HlaLzpAp8GzmCbPU9bfnUlUF0nvgKrUeXIHhqDXb+8aO2rM8MLwB6TnGn1Sgbftg+AQD/YSbEJuzVrhdzJormn/37Xj1krh9zfh7I2KVtaTPaljXR0wCIPLiQXuE1aRNqx0czanPk1C86bbUwt8LvtffZenixdlnkwYW0qN9LZ72r6UmMWBhA+3GlaBNqx6A5jYlL+l1b/t0v4xg2/y3mbhhEu7El6TSxPCt2Tn78SX1BmJqa8Xb9Xqg12Zy5dAyA32J/ImSmN21D7ek5tTq/Hl2uXb+gc5Wf85f/4kTCHj7tuIzUG8kc/nuLTnnXsEos3zGRofOa0GqUDb2m1eLspePs/COC7pPdaBNqx7TVH6JW596xpqSew3+YCZEHF9Hjy2q0CbVjzJI2pGVceWQbHlxj165fYuSit9Fo1LQaZUOrUTb8cmSZts6r6UnabfIOp6TeSCF0SWvahNrR48tqHD61VW8/j7sm4y/+wcDZPrQJtaPdGEc++aYRN2+nPfbcFTWjDuDg4GAmTJhAnz592LJlCx06dKBTp06cPXsWb29vpZtnkF3HVjBoTmPajLbVCbFH+X775/wR/ysTem7EysLmseumZVxhyFxffGq2I2L0Rb7uv5/fT28nYucX2nVqVvZh3qBjrP88na7+Y5i6sgfnL58EYP6gGAAWf3qKjZMy6OofavBxbTu8mLY+H/PThOu09fmYyIMLWbnrS4Z3Xs768WkEBUxi/HftuHgtXme7FvV7sfXwYjQaDRmZ6ez782f863bXWScnR0OrRiH8MPI8q8ak4OZSh/HL2um8sZw4uxsHmzKsDE1mfI+fWbt7us6by7P2pP1qqHvZd9m0by4A5Z2q8XvcdqatDqZv65msG5/Kpx2X8c1P/Tl+djdg2LnKK/LgAlzLetKgRkvqvdqCzQfm663zy+/LGPDuHNZ/nkaVsl6MW/YuMWd2MW9wDAsHn+DAnxuIilmps82O379jet/d/DjqAioTFZN/7Frg8TrZlSPswy2oVKZsnJTBxkkZNMtzPTzKFxFdMDUx5ceRiUzvu5tfjizNc5yPvyZnre+Hd7VmrBufyqqxl+nTajpmZsUM2ndRMdoAjoiIYOnSpWzYsIGhQ4fSpEkTRo0aRcOGDcnOzqZOnTpKN9EgNlYOtGoYQt/WMwtcNzpmNSt3TWZ8958o41BRp+zHXyfRNtRe+3Py/AF2HPmOKmW9aNmwD+ZmxXCyc6FTkxHs+P077XZv1wvGtnhJTFWmNHntfSqX9STmTFShj6uxZ3tqu72JiYkJlsWsWb/nK7o2HUOVcl6oVCrqV2/Ba1WaEHVshc52bi61sbcpzeFTW9hx9AfqVPPHwaa0zjqlHSrQyKM1lsWssTC3Iqj5RK6kJ3Lx2mntOo62ZenY5DPMzYpRrbw3LRr0ZtvhpYU+LkM9Sb8a4kH/thxpxZJtoxkcuAjXcp6s3/sV7/p8Qi3XxqhUKl6tUI+36nRl+/0+NuRcPezuvSy2//4dzV8PAiCgXjCHTm3RudMEeKd+byqWqY6ZqTlNancmOfUsQQGTsCpWnNIOFfCs4kdc0hGdbbr6j8XR1pnilrb0ajmVo6e3c+36pSI5P3ldu36RY/E76d0ynOJWdjjaOtPNX3csu6Br0sy0GFfSE7mafgEzU3NqVGyAVbHiz6S9j2K0Y8BhYWEEBATg6+urs9zNzQ1zc3M8PT0BGDNmDCtWrCA+Pp5Vq1bRvn17JZr7SK+7NwcoMPROXThC+MoeDGq/kBqVGuqVd35rlN4Y8I7fv+fPc7/RNtReuyyHHDQaNZA7hPPd9nFEx6wk9WYKJpiQdfcW1zOuFu6ggDIOlXRep6QmMOunfsz++WPtMrUmGyc7/Yd7Ler1IvLgQlJSE+j1zlS98uu3rjFvw2BizkZxKzMdE5Pc+4T0jKtULPNg/xUxMTHRac/eE+sKfVyGMrRfDfWgf2/eTmPa6mBi4nfxdr1gUlITiInfxdrd07XranLU1KzcGDDsXD0s+vhqsu5k8Fad3LvT+q+2wL54KbYcWsQHzcZp13MsUVb7u2Uxa1QqU+xtSmmXWZhbc/vOTZ26nR+6Jh78fu16Ek525Z7qnDzO1eu5bxgP36g4O1bWWaega3JoxyUs3zGBQXN8MFOZ81adrnTzH4up6fOLRaMM4KSkJGJjYxk0aJBeWWJiIh4eHlhYWAAQEBBAjx496Nmz5xPt4+E/3qJQmCf4165fZOzSNrz3xmDeqtPF4O3KOFSkdtWmTArenG/5rmMRbDm0iMm9fqFi6RqoVCpCvqpLDjkAqEzy/weQlYUNmXdvaV//c0P/LibvtqUdKvJBs/EGPbl/s3ZnFm4ehm1xJ7yr+euVfxs5gtSbycwacJCStmW5nXWTNqG2cL/dAJfTzpOTk6Ptx8tp5/IN++joKF7v1KTANj3O8/x0RglrBwYHLqL75Crsi/2Z0g4VaVa3Bx38huW7viHn6mGRBxegzlHTK7ymdllGVjpbD31Ll6ahhXoYl5J2jnJOVbS/A/n2SV4m+VyH1hYlAMh6xHXoZOsC5F4HD/Z5Oc/Hzwq6Jss6VmZoh9znEQnJJxi+sBnOjpUJqPdkWQL611lOTv7nPy+jHIJISsp9d3N2dtZZnpmZSXR0tM7wQ6NGjXB1dX2u7StKWXdvM2ZpG2pUakT35p8/0bb+3h8Ql3SErYcWc/deFhqNhuR/znL479yHEbezbmCqMsO+eClycjRsPbSYs5ditNvb2ZRCZaLS++dqVRdvth9Zxr3su6SknmPNQ3dfj/LeG4P4fvs44i8eIycnhzv3MolN2Evilb/11rW2LMHUj3YxseemfN8Ib9+5gYW5NSWsHMi8k8GiyM/01km9kcyqqKlkq+8Rf/EPIg8uNHjs0NjZWjvyXuPBLN46knY+A1m7ZwYnzu5BrVFzL/sucUm/c+pC7j//DTlXD5y/fJLYhL2M676eeYOOaX++GXCI1JspHPo78pHbGmL5jgmk3bzMrawbLNr8GXWqNjXo7texhDMajZrk1IR/z0HxkpRxqMjWw4tRa9QkJJ9gy8GF2vJS9uXxquLHws2fcivrBmk3L/PDDt2/n4KuyV+OLNMOkRS3ssdUZfbcP41jlHfATk5OAMTFxdGiRQvt8ilTppCcnFwkD+AMfYcy1JEVkGcYzSB7TqzldNLvJF4+SevRJfTKB76n/4DkAUdbZ8I/2sWiyOEs3jKSO9mZODtU4p0GfQDwr9udP87spPuXbliYW9O0Tjdq3f+nK+R+KqF78wmELe/E3ewsAv2G0eWtUfR/9xumrepJu7GOVCxTg2Z1ezB3w8DHHkeL+r0wMy1G+KogUlITMDM1x82lDn1ahue7frXyj+7D7s0+Z+rKHrw3tiT2JcrQvdnnbD64QGedWpUbk3ozmQ6fO1PMzJJ3fT7hzdqd9ery9fUjZ27h+vpp+7Yw3m38Cev2zOCfG5cY3H4hCzYPI+nqKUxMVFQq46F9szbkXD2w6cB8qrrUoWGNVjrLHW2decMzkM0H5uuVPYm36nRl0JzGpGVcxrPyG3z2/vcGbVe+VDVaNezLgK/rka2+R7+2s/D37sawjsuYtT6EDftmU6NiQwLqBes8aBvR+UdmrOlF50mv4GBThg5+n3IiYY+2vKBr8lj8Tr6NHM7trBvYWDvwZu0uNK3T7amO/WmvM5Ocok6iIqDRaKhduzbJycmEh4fj4uLCmjVriIyMJDExkQMHDlC/fn2dbfz8/Ojfv79iY8AF/ZH+lz9sXtS++2UcsQl7mdJnR4Hr2peHuu8Xbn+P61vp1+f7H3qM1dNeZ0Y5BKFSqVi9ejUeHh707duXoKAgnJyc6NevH6amptoHcC8CtUbN3XtZ3Mu+C+Q+hb57L6vI78DF8yX9KoqCUQ5BAFSrVo1du3bpLOvWrRs1atTAyspKoVY9uR2/f0/4qiDt63dG5rb9+xEJODtWUqhVorCkX0VRMMohiEepXr06DRo0YMmSJdploaGhLFmyhKtXr2JjY4OVlRXR0dFUqVLlubZNiXFCUbBnPQQhBLxkQxD5ycjIIC4uTu8/YEyYMIGkpCTu3LnDP//8Q1JS0nMPXyGEeBpGOwSRl42NDWq1WulmCCFEkXlh7oCFEOJlIwEshBAKkQAWQgiFSAALIYRCJICFEEIhEsBCCKEQCWAhhFCIBLAQQihEAlgIIRQiASyEEAqRAH5JTFnRgwFf1+dW5nXU6mwmR3Rj4Gwf7XTtsQl76TnlVSIPLnqqOuMv/kGvabXoGlZJW17YOvef3MiAWQ34eFZDVt+f2v7itXj6TH+NJVtHF1CTcfs2cgSD57zBt5EjgNwp1YOmuBNzJhqAVVFTGTjbhy9+7EK2+h6ZdzIYMKvBY2cS3n18DQNn+zBuWTuy7t4mJfUcgePLsG7PVwB8vS6E9uNK6fTHtNUf6kzlnlfS1TgGz/Vl8Jw3SLoaB0DQFHemrsz9prfvfxnPx7Ma8vGshhw9/au2HV3DKnE0Lv/vY9ZoNExb/SGD5jRm/d6vgdzvcO4z3YsLV06RkBLLJ980YtCcxkxdGUROTo5B/b5+79cMmtOYaauC0Wg0xJyJosukikQd+3d25tNJR/EfZoJanfv9zKMXt2TgbJ9H1hmb8BsDZ/vw2YJmpGVcAaBNqJ223x5cr0Pm+mln3f7pt2/oMN5Zb8bvpyEB/BIZ3nk5xa3s2HdyA6+UfpWZ/fYSe24vqTdSqFnZh45Nhj91neVKuvH1gAM6c3wVts4qZb2Y2e83vuq/j/0nN3Ar8zouTm6EtJn5xHUak4SUWG5l3WB6yG5u3P6Hcyl/AhDoOwyvKr6kZVzh2JldzOy3l8plPfkt9iesLGwY1WXFI+tUa9RsPrCAaX2jecOzPdsO534joHdVf9o1/gSALk1D9SY5HRK4CIcSznr1PbDsl7GM7BzB8E4/sGzbGADsipdiWMfc+pvW/YCvB+wn7MMt/LB9PABveLanWd0ej6zz0N+RvFLKnRkhezgat50bt1MB6NNyGq+UdueVUu581X8fM0JyZ6+ISzpSYL/fuJ1KTPwuZoTsoWzJKhw+tSW3fd7d8Huto3a9DfvnUNXl3y/smthz0yPrBIjYGcYXvbbxQbNxrI7KPXeVnWsR3OIL7TrDOy9nWt8o7Ywrbf/Xn7ruAY+t11ASwC+gAyc3sWDTMDQaDSMWBnAlLVGn/O/zB/CumjvZpVeVJvx94VCh67S2LPHEU3YXVGdphwqYqkwxMTHBVGWW7+SML6LYhL3UrdYMgDpV/XWmyQGIu3AEL1e/++VN+ev8/gLrvHjtNJWcPTBVmVKnqj+xeeoEKGlbNp8tHy/jdhpOduUo7VCB9Fv6s2WXvT/TsLmZBRg4kW3sub143z/+Wq5vcCpR9/ozMzXX/m5uZkEpu1cKrPNU4iE870+M6l1N/5wCnEv5k1J25bGy0J/aKz937mVibloMq2LF8ajUiNMXj+qtY2JiwpQVHxC6uBWX084bVO+TeGG+DU38q0GNlkTHrGLG2t40qNGK0g4VdMozstKxtrQFoLilHbcy0wtd57No5wOH/t5CuZJVsLY07A/H2N28ncqm/fNYu2cGGZnp+Hp1oKTtv5NT3srTPxlZ6QbV+VvseuIv/gGAmWmxImlr/MWjDJnrB0Di5ZOPXO+7X8bR8v5cgwW5eTuVmWv7UMzMkrSbKXT1H6O3zr4/N7Bky0hcnKpiW7xkwXVmprJp/1x+i13P3ewsXMvqz4qzbs9Mglt8QcyZKAPbmcbJ8/u1x3/z/p36w/q0moattSOxCXuZv3EIYz5YY1Ddhno5bjn+g95p0IfdMat4u/6HemXFLe24nXUDyJ0ZubiVfaHrfBbtBEj+5yyroqbwUesZRbZPpZWwdqR788+Z1jeKoICJlLB21CnP2z82lvYG1elTsx3T+kYxsecmbPPU+bSqlvdmWt8opvWNwr1CvXzX2XtiPTdu/5PvpKePauug9xYwrW8Urf/XnxJW+m1t5NGahUNjcbIvz4GTjx8mAChh5UirRiFM6xvF4MBFeuc06epprC1tsSvuZFAbc9vpQI1KjbTHn98NwoPzXLOyD6k3Uwyu21ASwC8gjUbD8h0T6Oo/lpX3H7I9rHrFhvwRn/vAJObMLtxfeV1vnWvXLz5RnYZ40jpvZ91k6soeDAn89omHN4xZzco+nDi7G8idtPPhmagBqr3yOsfP5j6MO3p6B9UrNtCrI++5dHGqysVrp7UPn2rmqdMQN26ncudeps4yW+uSpGdcJT3jar5BefbScTbsm82Ad2fnW6danU3azcs6y2pW8uF4Qu7x/3V+v16w382+o/3d2sIWC3P9KcbyHr97hXr8df4AkP85TUg5QdyFw4xYGEBC8nFmrvtIr860jCtkq+9pX1uYW5GTo+HOvUwSUmKpULq63ja37r9RXrhyChsDb2SehATwC+in377mfzXfJdB3CAkpJ7QPeR5oWKMV51JiGTjbh+oVG+qNDarV2Uxd2eOJ6rySfoFP5zflXEosn85vSkrquULX+fO+b0hJTSB8VU+GzPUjOTXhyU+GEarsXBMzU3OGzPXDzNScSs4eOuUONqWp5foGA2f7cObSMRp5tNWr48sVH6DRaLSvTVWm+NftzpB5vmw7vITmrwfpbbP810msjp7K2t3T+X7753rla3dP53SS7jhnl6ahTPg+kAnfB9L5rVF62yzYPIy0jMuMWNicMUva6JWnpJ3T++RCvVdbcObSMQbP9eXVCvX17taP/L0195MXc31Jy7isHS9+2Bc/dtF5bWvtSPWKDRg815czl47xuvvbOuWNa7Vjeshuvui1lcplPRnYbp5enfM3DCb9/icdHgj0Hcbwhc2Yv3EIgX7D9LaZ/GMXBs72YfqaDwlu8XQ3Jo/zQs0JZ8yUnjds/sah/JV4gEk9N1Pcyk6vPDZhL3M2DKSD7zDKOblx9lIMAfV6Gl2dF6/FMzmiK294BhLoO6SAoy6YscwJt/v4GlbsmkyfltPwquKrV555J4MRiwJwf+V1+rScxpwNn9C/7azH1nk1PYmRiwJ4u34v7Sch8pq2+kOSrp5iRsgevvlpACGtv0Klevx915C5fjg7VtZ+EiK/Y1m+YyID3p1N2s0UbKwdqO325mPrXLdnJruOreDTjst4pbS7XvnD/d6sbnd+2juL7s3HP7bOk+cP8NXaj+j05gidT0I8bPTilhQzt2JMt9V8vS6Ej9vNeWydAD2nvMr/ar6r80mIh/302zds3j+PicGbKeNQEXj660wCuIgoHcAif8YSwOLl9tJPyimEEC8bCWAhhFCIBLAQQihEAlgIIRQiASyEEAqRABZCCIVIAAshhEIkgIUQQiESwEIIoRAJYCGEUIgEsBBCKEQCWAghFCIBLIQQCjHqANZoNISHh1O1alUsLS3x8vIiOjoad3d3evfurXTzhBCiUIx6Trjg4GDWrVtHaGgo3t7e7Nu3j06dOnH16lUGDx6sdPMKtHDzZxz8axNX0y9gaWFD/Vff4cN3viyy6WSEcqRvRVEw2jvgiIgIli5dyoYNGxg6dChNmjRh1KhRNGzYkOzsbOrUqVNwJQpTqUwZ3ukH1o7/h/mDYrh2PUlv1gjxYpK+FUXBaAM4LCyMgIAAfH11Zw9wc3PD3NwcT09P0tLSaNmyJdWqVcPLy4tmzZoRHx+vUIv1Bb8dhptLbcxMzbG3KcW7Pp9w3MAZW4Vxk74VRcEoAzgpKYnY2FgCAwP1yhITE/Hw8MDCwgITExMGDhxIXFwcMTExtGzZkqAg/bmyjMUf8b/iWs5L6WaIZ0D6VjwNow1gAGdnZ53lmZmZREdHa4cf7O3tadq0qba8UaNGJCQYNrGjiYlJkf5ER0c9dn97jq9l04F5hLT+6gnOhCis6Ogo6VvxzOW9zgxllAHs5OQEQFxcnM7yKVOmkJycjLe3d77bzZw5k7Zt2z7r5j2x6JjVzFjTi897bKBqeeMfuxaGk74VhWGUn4JwdXXF09OTsLAwHB0dcXFxYc2aNURGRgLkG8Djx48nPj6enTt3GrSPop6L9FETN249vIQFG4fwedBGalb+X5HuUxTM19ePnLmF62vpW1GQp73OjPIOWKVSsXr1ajw8POjbty9BQUE4OTnRr18/TE1N8fT01Fl/4sSJbNq0ia1bt2Jtba1Qq/Wt3/s1CzYN5Yte2+QP9CUjfSuKwgs1LX23bt2IiYnh+PHj2mXjx48nMjKSbdu2YW9vr1jb8rtL8h9mgqnKDHMzC53lGydlPMeW/bc9q2nppW/Fw572OjPKIYhHOXLkCA0aNNC+/vPPPxk3bhxVqlTBz89Pu/zYsWPPv3H52D71hXlvE09I+lYUhRcmgDMyMoiLiyMkJES7zMPDo8jHcoUQ4nl5YQLYxsYGtVqtdDOEEKLIGOVDOCGE+C+QABZCCIVIAAshhEIkgIUQQiESwEIIoRAJYCGEUIgEsBBCKOSF+RywsStRWukWiPwURb9I34qCPO018kJ9F4QQQrxMZAhCCCEUIgEshBAKkQAWQgiFSAALIYRCJICFEEIhEsBCCKEQCWAhhFCIBLAQQihEAlgIIRQiASyEEAqRABZCCIVIAAshhEIkgIUQQiESwEIIoRAJYCGEUIgEsBBCKEQCWAghFCIBLIQQCvk/Cw/Oo7ASzogAAAAASUVORK5CYII=\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -146,7 +144,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "The parametrized circuit can then be sent together with an optional interpret map (parity in this case) to the `CircuitQNN` constructor." + "The parametrized circuit can then be sent together with an optional interpret map (parity in this case) to the `SamplerQNN` constructor." ] }, { @@ -177,18 +175,14 @@ }, "outputs": [], "source": [ - "# declare quantum instance\n", - "qi_sv = QuantumInstance(Aer.get_backend(\"aer_simulator_statevector\"))\n", - "\n", "# construct QNN\n", - "qnn = CircuitQNN(\n", - " qc,\n", + "qnn = SamplerQNN(\n", + " circuit=qc,\n", " input_params=feature_map.parameters,\n", " weight_params=ansatz.parameters,\n", " interpret=parity,\n", " output_shape=output_shape,\n", " sparse=False,\n", - " quantum_instance=qi_sv,\n", ")" ] }, @@ -388,7 +382,7 @@ "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -427,7 +421,7 @@ "source": [ "### 4.1 Define Dataset and QNN\n", "\n", - "We start by creating a 3D binary classification dataset:" + "We start by creating a 3D binary classification dataset using `make_classification` function from scikit-learn." ] }, { @@ -442,17 +436,24 @@ "source": [ "num_inputs = 3\n", "num_samples = 50\n", - "X = algorithm_globals.random.normal(0, 0.5, size=(num_samples, num_inputs))\n", "\n", - "y01 = 1 * (np.sum(X, axis=1) >= 0) # in { 0, 1}\n", - "y = 2 * y01 - 1 # in {-1, +1}" + "X, y = make_classification(\n", + " n_samples=num_samples,\n", + " n_features=num_inputs,\n", + " n_informative=3,\n", + " n_redundant=0,\n", + " n_clusters_per_class=1,\n", + " class_sep=2.0,\n", + ")\n", + "X = MinMaxScaler().fit_transform(X)\n", + "y = 2 * y - 1 # labels in {-1, 1}" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ - "The next step is to create a QNN, an instance of `TwoLayerQNN` in our case. Since we pass only the number of inputs, the network will continue with the default values for feature map and ansatz." + "The next step is to create a QNN, an instance of `EstimatorQNN` in our case in the same fashion we created an instance of `SamplerQNN`." ] }, { @@ -465,7 +466,9 @@ }, "outputs": [], "source": [ - "opflow_qnn = TwoLayerQNN(num_inputs, quantum_instance=qi_sv)" + "estimator_qnn = EstimatorQNN(\n", + " circuit=qc, input_params=feature_map.parameters, weight_params=ansatz.parameters\n", + ")" ] }, { @@ -509,11 +512,11 @@ "outputs": [], "source": [ "# construct classifier\n", - "initial_point = algorithm_globals.random.random(opflow_qnn.num_weights)\n", + "initial_point = algorithm_globals.random.random(estimator_qnn.num_weights)\n", "\n", - "opflow_classifier = NeuralNetworkClassifier(\n", - " neural_network=opflow_qnn,\n", - " optimizer=COBYLA(maxiter=150),\n", + "estimator_classifier = NeuralNetworkClassifier(\n", + " neural_network=estimator_qnn,\n", + " optimizer=COBYLA(maxiter=80),\n", " initial_point=initial_point,\n", " callback=callback_graph,\n", ")" @@ -530,7 +533,7 @@ "outputs": [ { "data": { - "image/png": "iVBORw0KGgoAAAANSUhEUgAAAtAAAAGDCAYAAAACpSdYAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/NK7nSAAAACXBIWXMAAAsTAAALEwEAmpwYAABY3ElEQVR4nO3deXxcZ3X/8c+ZRTPaZS2W4y1OHNshDllN9pCQsiQ0EAhrgLKT0hJKW2gLtD+g9MevLVvZyr6ENSmELW0IIQVCdpI4+27HsS2vkqxdI2m25/fHvSONlpFm5JmRR/q+Xy+9NHPvnTvPXE3iM2fOcx5zziEiIiIiIvkJLPQAREREREQqiQJoEREREZECKIAWERERESmAAmgRERERkQIogBYRERERKYACaBERERGRAiiAFpGczOxjZvaDWfY/ZmYXluB5S3XeV5pZh5kNmdmpxT7/LM/7RjP7TbmeLx9mdrWZ/d+FHkchzOxGM3vLYnmeOcYwZGbHLuQYRCQ3BdAiS5iZvdXMHjGzmJkdMLOvmFlTvo93zm12zt1ymGOYFsgV47w5fBq4yjlX55x7oATnx8zWmZkzs1Bmm3Puh865F5fi+ZYS59wlzrnvHs45/Pf87fk+Tz7HHy4zu8XM3jllDHXOuR2lfF4RmT8F0CJLlJm9H/h34O+ARuAs4GjgZjOrWsixldDRwGMLPQhZOrI/SInI4qEAWmQJMrMG4J+B9zrnfu2cSzjndgKvBdYBb8o6PGpm/2Vmg2Z2v5mdnHWenWb2Qv92wMw+aGbPmNkhM/uxmTVnHXuemd1pZn1+GcVbzexK4I3A3/tfWf939nnNbKWZjUw5z6lm1m1mYf/+283sCTPrNbObzOzoGV5vxMyGgCDwkJk94293ZnZc1nHj2XAzu9DM9pjZ+82s08z2m9nbso6tNrPPmNkuM+s3s9vNrBq41T+kz39NZ0/NYprZOWZ2r/+4e83snKx9t5jZv5jZHf41/42Zteb4Oz5hZpdm3Q+ZWZeZnebf/4n/zUK/md1qZptznGdaljX72vjX79NmttvMDprZV/3XOtO51pvZ7/z3QLeZ/TD7Ww0zO83MHvBf20/891bmmi8zs//xX0Ovf3v1lGvzzuwx++PqNbNnzeySKa9ph/88z5pXRvMc4KvA2f7fpi/Ha7jFzN6Z6/jZrkfW++YfzOwA8J3ZXpeZfQI4H/iS/xxfmuH6N5rZ9/zH7zKzfzKzQD7XQURKQwG0yNJ0DhAFfpa90Tk3BPwKeFHW5suAnwDNwI+AX5gfvE7xXuAVwAXASqAX+E8A84LaG4EvAm3AKcCDzrmvAz8EPul/Zf2yKePZB9wFvCpr8xuA65xzCTO7DPgwcLl/3tuAa6YOzDk35pyr8++e7Jxbn+vCTLECLzu/CngH8J9mtszf92ngdLxr2Qz8PZAGnu/vb/Jf013ZJzTvw8ANwBeAFuCzwA1m1jLlNb4NWA5UAR/IMb5rgCuy7r8E6HbO3e/fvxHY4J/nfrxrPR//BmzE+7sdh3c9PpLjWAP+Fe898BxgDfAxAPO+2fg5cDXeNbsGeGXWYwPAd/C+KVgLjABfmmVcZwJPAa3AJ4FvmacW7/pe4pyrx/sbPeicewJ4N3CX/7dpmu1Fz3L8XNdjhf/6jgaunO11Oef+Ee99myktumqGoXwR7314LN5/X2/Ge3/Meh1me20icngUQIssTa14gVZyhn37/f0ZW51z1znnEnjBXhSv3GOqdwP/6Jzb45wbwwuaXm3eV9hvAP7XOXeNn+0+5Jx7MM+x/gg/SPSDgtf72zLP+a/OuSf81/L/gFNshiz0PCWAj/tj/hUwBGzys39vB97nnNvrnEs55+70X/dc/hTY5pz7vnMu6Zy7BngSyP7w8B3n3NPOuRHgx3iB2kx+BLzczGr8+28g6wOEc+7bzrnBrL/HyWbWmO+Lh/FrfiXwN865HufcIN51fv1MxzvntjvnbvY/tHThvWcu8HefBYSAL/jX9GfAPVmPPeSc+6lzLuY/zyeyHjuTXc65bzjnUsB3gaOAdn9fGjjRzKqdc/udc0Up3cnzeqSBj/rXYGQeryv7+YL+uT/k/y13Ap8B/izrsNmug4iUgAJokaWpG2i1meszj/L3Z3Rkbjjn0sAevOziVEcDPzevRKMPeAJI4f1DvgZ4Zp5j/SneV+hH4WV303gZu8xzfj7rOXvwMqCr5vlcUx2a8iEjBtThfcCIMr/XtBLYNWXbLiaP+cAMzzmNc2473nV+mR9Evxz/w4WZBc3s38wrqRkAdvoPm7EcZBZtQA2wNes6/9rfPo2ZtZvZtWa213/eH2Q950pgr3POZT2kI+uxNWb2Nb9MYQCvHKbJDyJnMn6dnHMx/2adc24YeB3eB6z9ZnaDmR1f4OvOJZ/r0eWcGz2M15WtFQgz+T2T8/2SfR0KeE0iUiAF0CJL013AGF7pwzgzqwMuAX6btXlN1v4AsBrYN8M5O/C+Mm/K+ok65/b6+3KVTbgc272dzvUCv8ELiN4AXJsVgHUAfz7lOaudc3fOds4sMbxgKGNFno/rBkaZ+TXN+nrwrt3UDPlaYG+ezz1VpozjMuBxP6gG71pdBrwQ7+v/df72mb7aHybrOphZ9nXoxis52Jx1jRuzSmKm+n941+C5zrkGvHr6zHPuB1ZNKS9Yk3X7/cAm4Ez/sZlymILLEZxzNznnXoT3gfBJ4BuZXYWeasr9fK7H1MfM9bpmG1M33jch2e+Zw3m/iEgRKIAWWYKcc/14kwi/aGYXm1nYzNbhlQvsAb6fdfjpZna5n63+a7zA++4ZTvtV4BOZ8gkza/NrlMGrvX2hmb3WvIluLWZ2ir/vIF5t52x+hFf3+Womyjcyz/kh8yfH+ZOtXjP3FRj3IPAGP1t7MXl+re5n4r8NfNa8iY5B8yYLRoAuvCx5rtf0K2Cjmb3BvxavA04A/qeAcWe7Fngx8BdMvjb1eH+rQ3jB8f+b5RwPAZvN7BQzi+LXLMP4a/0G8B9mthzAzFaZ2UtynKser9Sl38xW4XV5ybgL71uJq/zXfhlwxpTHjuBNwGwGPjrbC8/Fz4Jf5tdCj/njSfu7DwKrLf9OM5OOn8f1gLlfV87/BvyyjB/j/bdV7//39bd4mX0RWSAKoEWWKOfcJ/Em4H0aGAD+iJfR/ZMptby/xMv+9uLVXV7u10NP9XngeuA3ZjaIF2Sf6T/XbuCleJm4HrzANdPN41vACf7X4b/IMdzr8SbDHXDOPZT1Gn6O14rvWv+r8UfxMuj5eh9e7XEfXjeQXM8/kw8AjwD34r2mfwcC/lfonwDu8F/TpHpx59wh4FK8a3EIb/Lhpc657LKZvDnn9uMFpucA/5W163t4X/XvBR5n5g89mXM8DXwc+F9gGzC17/E/ANuBu/3r/L94GdWZ/DNwGtCPN1lyfKKqcy6O963HO/Cu+ZvwPjhk3m+fA6rxsq5345VGzEcAL8jch/e3uQDvAwbA7/BaGR4ws3yu+UzHF3I9YO7X9Xm8+QK9ZvaFGR7/XrxvCXbg/W1+hPcBTkQWiE0uRRMRyZ+Z7Qbe5Jy7dc6DRWZgZn8Evuqc+85Cj0VEJF/KQIvIvJhZG97EqZ0LPBSpIGZ2gZmt8Es43gKcxPwzzSIiC0IrJIlIwczsecDNwBf98gyRfG3Cq+mtxStJeLVfhiIiUjFUwiEiIiIiUgCVcIiIiIiIFEABtIiIiIhIASquBrq1tdWtW7duoYchIiIiIovc1q1bu51z01ZerbgAet26ddx3330LPQwRERERWeTMbNdM21XCISIiIiJSAAXQIiIiIiIFUAAtIiIiIlIABdAiIiIiIgVQAC0iIiIiUgAF0CIiIiIiBVAALSIiIiJSAAXQIiIiIiIFUAAtIiIiIlIABdAiIiIiIgVQAC0iIiIiUgAF0BUqnXZs7xxc6GGIiIiILDkKoCvU75/q5EX/cSt7+0YWeigiIiIiS4oC6ArVOTiGc3BwYHShhyIiIiKypCiArlDDY0kABkYSCzwSERERkaVFAXSFisVTAAyOJhd4JCIiIiJLiwLoCjUc9zPQo8pAi4iIiJSTAugKFRvzMtADI8pAi4iIiJSTAugKpQy0iIiIyMJQAF2hJjLQCqBFREREykkBdIXKZKA1iVBERESkvBRAV6hMFw6VcIiIiIiUlwLoCqU+0CIiIiILQwF0hZrIQKuEQ0RERKScFEBXqFhcGWgRERGRhaAAukINj6kGWkRERGQhKICuQKm0YySRoioYYDSRJp5ML/SQRERERJYMBdAVaCThZZ/bGyMADCoLLSIiIlI2CqArUMzvwLGiIQpoIqGIiIhIOSmArkDDfgeOFY3VgCYSioiIiJSTAugKlOkBfVRjJgOtAFpERESkXBRAV6BMD+jxEo4RlXCIiIiIlIsC6Ao0HJ+cgdYkQhEREZHyUQBdgWJjmRpolXCIiIiIlJsC6AqUyUC31kUIBkwlHCIiIiJlpAC6AmXa2NVFQtRHQ8pAi4iIiJSRAugKlGljVxMJ0hANq42diIiISBkpgK5AsXiSUMCoCgZoqA4xqIVURERERMqmZAG0mX3bzDrN7NEc+99oZg+b2SNmdqeZnVyqsSw2w2MpaqqCmJmXgVYJh4iIiEjZlDIDfTVw8Sz7nwUucM49F/gX4OslHMuiEosnqY2EALwaaE0iFBERESmbUKlO7Jy71czWzbL/zqy7dwOrSzWWxWY47mWgAWWgRURERMrsSKmBfgdw40IPolLExiYy0A3VmkQoIiIiUk4ly0Dny8xegBdAnzfLMVcCVwKsXbu2TCM7ck3NQA/HUyRTaULBI+XzkIiIiMjitaARl5mdBHwTuMw5dyjXcc65rzvntjjntrS1tZVvgEeoWDxJbVUmA+39HhpTHbSIiIhIOSxYAG1ma4GfAX/mnHt6ocZRiWJjKWoyJRzRMIAmEoqIiIiUSclKOMzsGuBCoNXM9gAfBcIAzrmvAh8BWoAvmxlA0jm3pVTjWUyG40lq/RKO+qj3J9REQhEREZHyKGUXjivm2P9O4J2lev7FLDaWoqZqYhIhMG0i4Ug8xf/55aP83Us20d4QLfsYRURERBYrzTqrMM45LwMdmZhECNMz0A929HHd1j3c9UzO0nIRERERmQcF0BVmLJkm7cjKQPslHFNqoDt6Y952lXaIiIiIFJUC6Aoz7HfbGM9AV8+cgd7T4wXQg6OaXCgiIiJSTAqgK0wsngImMtB1VSHMYGB0agZ6BFAGWkRERKTYFEBXmOG4n4H2u3AEAkZdJDRtEmGHn4FWezsRERGR4lIAXWGGx/wMdGSigUpDNDwt05ypgR5UBlpERESkqBRAV5jYlAw0eHXQ2Znm0USKgwNjgGqgRURERIpNAXSFGc9AV2VnoEOTMs17/PpnUA20iIiISLEpgK4w4xnoyJQMdFamOVO+sbw+ogy0iIiISJEpgK4ww/HpGej66ORJhJkWdiesbFANtIiIiEiRKYCuMLGxGTLQUyYRdvSOUBUKsL6tTl04RERERIpMAXQeeofj/Ofvt/PkgYGFHgrD8RRmEA1NLuEYGkuSTjvAa2G3elk1jdVhRhIpEqn0Qg1XREREZNFRAJ2HlHN86qanuHP7oYUeCrGxJDXhIIGAjW9riIZwDgb97HRHb4w1y2qoj3plHkOqgxYREREpGgXQeWiti9BSW8VTBwYXeigMx1OTekDDxHLemXrnjp4R1jRXUx+deZlvEREREZm/0NyHCMCmFfU8dXDhA+hYPDmpBzR4NdDgrTrYH03QP5JgbXMNDX4GWp04RERERIpHGeg8bWyv5+mDg+N1xgtleCw1qQMHMB4oD4wmxpfw9ko4lIEWERERKTYF0HnatKKeWDzF3r6RuQ8uoVg8OakDB0yUcAyMJNjj94Be0zxRA61OHCIiIiLFowA6T5tW1AMseB30cHymDHQm05yko8cL8Ncsq6FxSm20iIiIiBw+BdB52tjuB9BFqoP+2h+e4WPXP1bw42JjM2WgM5nmBB29MeqjIRprwuMZaNVAi4iIiBSPAug81UVCrF5WXbQM9I2PHuCn9+/BucJqqmMzZKDrIhOBckeP18Iue7tqoEVERESKRwF0ATb5EwmLYU9vjMHRJPv7Rwt63PAMXThCwQC1VUFvEmGv18Iue7sy0CIiIiLFowC6ABtX1PNM19Bhr+wXiyfpHooDhZeExMam94EGbyJh/0hiUgYaoD4aZmBEGWgRERGRYlEAXYDjV9STSDme7R4+rPPs6Z3o5FFISUg8mSaeSk/LQIM3kfCZriHGkmnWNGcH0CFloEVERESKSAF0ATITCZ88zDroTK9mKCyAHomnAKbVQIM3kfDJ/d651mYF0A3VYQbHlIEWERERKRYF0AU4tq2WYMB4+jAD6N1+AH3iqoaCAujhuJdJntqFA7wM9EjCC7AzNdDgZaDVB1pERESkeBRAFyASCnJsa+1ht7Lr6BmhOhzknPWtbO8aIplnTXXMD6BnzkCHx2+vnlIDrT7QIiIiIsWjALpAG1fUH3Yru47eGGuaq9nUXk88mWbnodjcD8JbxhtmzkBnej631UeIhif2N6gGWkRERKSoFEAX6Pj2enb3xMazwfOR6ZRR6OqGw7NloP3VCNcsq560vT4aZmA0UXC/aRERERGZmQLoAm30g95tB4fm9XjnHHt6R1jTXMNxy+sIWP6t7GKZDHSOSYTApA4cme2JlGMseXit90RERETEowC6QJvaC8saT9UXSzA0lmT1smqi4SDrWmt56sBAXo8dz0DnmEQITOoBDV4GGrQaoYiIiEixKIAu0NrmGqLhwLwnEnb0evXOmUzxpvb8a6pj8dky0H4A3Ty5hKPBr41WJw4RERGR4lAAXaBAwNhYQNA7VUePt4hKplfzphX17OqJjfd4ns3wWO4MdHtDBIDjltdN2p7JTKsTh4iIiEhxKICeh03t9fPOQGd6QGdnoJ2DbZ1zny+Tga4JTw+gT1u7jOuvOpfTj26etD3TnUOdOERERESKQwH0PGxaUU/X4Bg9w/GCH9vRG2NZTZi6SGj8XJBfTfVwPEkkFCAUnP5nMzNOWt00bbtqoEVERESKSwH0PGw8jImEHT2xSZ0yjm6pJRIK5HWu2FiK2sj0+ufZZLpzKAMtIiIiUhwKoOfheD9rfNNjBwrur7ynd2RSp4xgwNjQXpdXSchwPElN1fTyjdnUqwZaREREpKgUQM/D8oYorzl9NVffuZN//MWjeS/FnU479vaOsHpKp4xN7Q0zZqBHE5MnFsbGUjN24JhNbVWQgKkLh4iIiEixKICep0+++iT+4sL1/OiPu3n3D7bm1UXj4OAo8VR6Wq/mTSvq6Bwco9evqU6nHVf96H4u+NTvGUtOnHc4npyxA8dszIz6aFgZaBEREZEiUQA9T2bGP1x8PP9y2WZ+92QnV3zj7jknFWZa2E1dLXDTigZgYkXCf/v1k/zPw/s5ODDG1l2948fF4oVnoMHrxKEaaBEREZHiUAB9mP7s7HV89U2n89i+fr70u+2zHtuRaWG3bHIJx/FZnTi+f9dOvn7rDl67ZTWhgHH7tu7x44bHCq+BBq8OWl04RERERIqj8HSmTPPizSs4cVUjj+/vn/W4jt4YZrBqSgC9vD5CY3WYa+7ZzdMHB3nhc5bzr5efxM7uGLdt6+bvL/aOi8UL78IB3mqEA8pAi4iIiBSFMtBFsnF5PdsODs16zO6eGO31USKhyVlkM2PTinqePDDIiasa+cIVpxIMGOdvaOXRff3jpSGxeXThAD8DPaIMtIiIiEgxKIAuko0r6jk0HKd7aCznMXt6RsaX8J7q3PWtHNNayzffsoUav875vA2tOAd3bPfKOIbn0QcavAy0aqBFREREikMBdJFsbK8D4OlZ+jl39MamtbDLeN8LN/Dbv72A5fXR8W0nrW6iIRritm1dpNKOkURqXhnohmp14RAREREpFgXQRZJZnTBXGcdYMsWBgdFpLeyyBQI26X4wYJy3oZXbt3UTi3sZ5Hl34RhLkk4XtuiLiIiIiEynALpIMhMBc60ouK9vFOemt7Cby3nHtbGvf5RH9noTFAvtAw3QEA3jnNdHWkREREQOjwLoIjEzNrbXsS1HAJ2rhd1czt/QCsBNjx4A5p+BBlQHLSIiIlIECqCLaGN7PU8dGMS56aUSHb1+AF1gBnpNcw3rWmq46bGDAPPuwgGoF7SIiIhIESiALqKN7fUMjCbpHJzeiaOjZ4Rw0GhviM7wyNmdv6GNAwOjAPPrwlGtDLSIiIhIsSiALqINs3Ti6OiNsaqpmuCUiYL5yJRxwOFloNWJQ0REROTwKYAuok3tE0tyT/Xk/gHWtdbO67xnrW8ZD7znk4HO1EAPjCgDLSIiInK4FEAXUUtdhJbaqmmt7J7tHuaZrmEu2Ng2r/M2RMOcuqYJmF8GukEZaBEREZGiUQBdZBva66a1srv5ca+DxotOaJ/3eS/Y2EbAJsoxCjGegVYNtIiIiMhhK7weQGa1qb2e67buwTmHmVd28ZvHDnLCUQ2snmURlbm86/nHcuaxLTRWFx5AR8NBqoIBdeEQERERKYK8MtBmdrSZvdC/XW1m9aUdVuXa0F7PcDzF3r4RALoGx9i6u5cXb55/9hm8IPiMY5rn/fiG6pC6cIiIiIgUwZwBtJm9C7gO+Jq/aTXwizwe920z6zSzR3PsP97M7jKzMTP7QAFjPqJtWjF5Se/fPnEQ5+DFJ6xYyGFRHw0rgBYREREpgnwy0O8BzgUGAJxz24DleTzuauDiWfb3AH8FfDqPc1WMjcu9ADrTyu7mxw+yelk1zzlqYZP29dEQAyMq4RARERE5XPkE0GPOuXjmjpmFgOlL7U3hnLsVL0jOtb/TOXcvsKiiusaaMMvrIzx1cJDhsSS3be/mRSe0j9dDL5SGaFhdOERERESKIJ8A+g9m9mGg2sxeBPwE+O/SDmsyM7vSzO4zs/u6urrK+dTzsmlFPdsODnHr013Ek+kFL98ALwOtEg4RERGRw5dPAP1BoAt4BPhz4FfAP5VyUFM5577unNvinNvS1ja/XsrltGF5Pds6B7npsQM01YR53rplCz0kr4RDGWgRERGRwzZnGzvnXBr4hv8jedi0oo7RRJobHtnPy09eRSi48O22GzSJUERERKQo5gygzexZZqh5ds4dW5IRLQIb/CW9Eyl3WIunFFN9NEwsniKZSh8RAb2IiIhIpcpnIZUtWbejwGuAORsSm9k1wIVAq5ntAT4KhAGcc181sxXAfUADkDazvwZOcM4NFPICjkQbltcBEAkFeP7G1gUejaeh2vtTD44mWVZbtcCjEREREalc+ZRwHJqy6XNmthX4yByPu2KO/QfwekovOvXRMMe01rKxvY6aqiNjscfMEuCzBdD37uxh9bJqjmqsLufQRERERCpKPiUcp2XdDeBlpI+MqPAI9oN3nkltVXChhzGuPur9yWabSPjn39/K5pUNfP8dZ5ZrWCIiIiIVJ59A+DNZt5PATuC1JRnNIrKq6cjK4jb4GehcAXQylaZnOM5t27p5pmuI9W115RyeiIiISMXIp4TjBeUYiJRWJgOdqxNHX9Yqhd+/axcfe/nmsoxLREREpNLkDKDN7G9ne6Bz7rPFH46UyngGOsdy3n0xb7HJxuow123dwwdesom6iCp1RERERKaarZ9Z/Rw/UkEaq70Auj9HAN0z7G1/1/nHMDSW5Gf37ynb2EREREQqSc4Uo3Pun8s5ECmthuoQoYDRMxyfcX+vn4G+cNNybn78IN+9cyd/dtbRmFk5hykiIiJyxJtzRQ0zi5rZe8zsy2b27cxPOQYnxWNmLKutyhlAZ0o4ltVW8eaz1/FM1zB3bJ/awVBERERE8lmS7vvACuAlwB/wejcPlnJQUhottVUcyhFAZ0o4ltWE+dOTjqKltoqr79xZxtGJiIiIVIZ8AujjnHP/Bxh2zn0X+FNAjYIr0LKaKnpnyUBHQgGqw0Gi4SCvP2MNv33yIB09sTKPUkREROTIlk8AnZl11mdmJwKNwPLSDUlKpbkudwlHbyzOspqq8ZrnN555NAEzfnTP7nIOUUREROSIl0+fsq+b2TLg/wDXA3X+bakwc5VwNNWEx++vbKrmhKMaeHzfQLmGJyIiIlIR8gmgv+OcS+HVPx9b4vFICTXXVtE/kiCRShMOTv7yoc/PQGdrqavi0NDMAbeIiIjIUpVPCcezZvZ1M/sTU0+zitZS6wXIfbHpvaB7Y3GaaycH0M2zdO0QERERWaryCaCPB/4XeA+w08y+ZGbnlXZYUgrL/AB5pqC4Nza5hAMyJR9jZRmbiIiISKWYM4B2zsWccz92zl0OnAI04JVzSIXJZJinBsXptJuxhKO5NsJoIk0snizbGEVERESOdPlkoDGzC8zsy8BWIAq8tqSjkpJoqY0A0zPQg6NJ0m4iQz1xvB9wqw5aREREZNyckwjNbCfwAPBj4O+cc8OlHpSURnOOEo6ezCqEU0o4so9f01xThhGKiIiIHPny6cJxknNOvcwWgUyN89QAunc8gJ5SwlGXu2ZaREREZKnKpwZawfMiEQ4GaKwOTwuI+zIBdK4SjhwBdNfgGLsPaaVCERERWVryqoGWxWOmxVR6hr22drlKOA4NzdyJ4//e8Djv/sHWEoxSRERE5MilAHqJaa6tomdo5gx005QSjrpIiKpgIGcJx+6eGJ2Do6UZqIiIiMgRKp9JhBHgVcC67OOdcx8v3bCkVJprq9jdM7nsojcWJxgwGqKT3w5mRvMsy393DozRP5LAOYfW2BEREZGlIp8M9C+By4AkMJz1IxVopoC4ZzjBsprwjEFwrtUI02lH5+AoiZRjJJEq2XhFREREjjT5dOFY7Zy7uOQjkbJorq2idzg+KWvcF4tPK9/IaKmbOQPdG4uTSDkA+kcS1FTl81YSERERqXz5ZKDvNLPnlnwkUhbNtVUk046BkYnVBXtjcZpzBdC1VfTMsJz3wYGJbf0jieIPVEREROQIlU8AfR6w1cyeMrOHzewRM3u41AOT0mipm76cd+9wYrxH9FTNtZFpkw4BDmZNHswOxkVEREQWu3y+d7+k5KOQsmn2l/POLJ6SuX3KmqYZj2+pq2I4nmI0kSIaDo5v7xyYCKCVgRYREZGlJJ+FVHYBTcDL/J8mf5tUoEypxiE/q+ycoy+WoKk2VwZ65tUIVcIhIiIiS9WcAbSZvQ/4IbDc//mBmb231AOT0pi6PPdwPEU8lc5ZA507gB6lKui9fRRAi4iIyFKSTwnHO4AznXPDAGb278BdwBdLOTApjanLc/f6v5fNMokw+/iMgwNjHNNay9OdgwqgRUREZEnJZxKhAdmNflP+NqlA0XCQmqrgeEa5L+YFv7knEWYy0JM7cXQOjrKiMUp9JMSAAmgRERFZQvLJQH8H+KOZ/dy//wrgWyUbkZTcspqq8cxzjz+ZMBMoT9XiTzo8NDS9hOP4FfU0VIeVgRYREZElZc4A2jn3WTO7Ba+dHcDbnHMPlHRUUlLZi6P0+QF0roVUGqpDhAI2qYQjmUrTNThGe0OUxuqwMtAiIiKypOQMoM2swTk3YGbNwE7/J7Ov2TnXU/rhSSk011aNZ5QnaqBnLuEwM5bVVk3qBX1oOE7awXI/gFYGWkRERJaS2TLQPwIuBbYCLmu7+fePLeG4pISaa6vYdnAIgJ5YAjNorJ45gAZvImF2Bvqg3wN6hR9Ab+8cKu2ARURERI4gOQNo59yl/u9jyjccKQdvee6JEo6GaJhQMPd80uYpy3lnekC3N0SUgRYREZElJ58+0L/NZ5tUjmW1VYwkUozEU/TGEjnLNzJa6iKT+kBnMtDtKuEQERGRJWi2GugoUAO0mtkyJlrXNQCryjA2KZGJ3s5j9A7HWZajA0f28dklHJ0DowTM295QHWYsmZ621DdALJ5kT+8IG9vri/8iRERERBbIbBnoP8erfz7e/535+SXwpdIPTUql2W9N1zMcpzcWz7mIysTxVQyOJokn04BXwtFaFyEUDNDg104PjE7PQl99505e/qXbSaTSM543nXY8vKfvMF6JiIiISPnlDKCdc5/3658/4Jw71jl3jP9zsnNOAXQFa85aXbAvlsi5iMrU43v9lncHB0dpb4gCE5MPZ2pl19ETYzSRztnm7g9Pd/HyL93BtoOD83shIiIiIgsgn5UI02bWlLljZsvM7C9LNyQptUwJR+9wnJ7huTPQ4yUffiu7gwNjtDd4WexMAD1THXTXoDfZcGA0OeN5D/i11LsOxQp9CSIiIiILJp8A+l3Oub7MHedcL/Cuko1ISi5T87y/f5SRRCrnKoQZE8t5ewF058Aoy6dkoGcLoHNNMsxs3+8H0iIiIiKVIJ8AOmhmmQmEmFkQmD3ikiNaQzREOGg84/dvnquEo6VuYtJhPJnm0HCc9vr8A+hcJRyZxxzoH5nHqxARERFZGHMu5Q38GvgvM/uaf//P/W1SocyMZTVVPNPlBdBzTyL0yjUODcXpGproAQ1eMA7QH5scJDvnxo/NlYEeGA+gx2bcLyIiInIkyieA/ge8oPkv/Ps3A98s2YikLJprq3imaxiYO4Buqg4TMK+EI7sHNDDehaN/ZHKdc18sQSLlLWA5U4cO7zF+AD2gDLSIiIhUjjkDaOdcGviK/yOLREtdFU8e8LpfLKudvYQjEPAy1oeG43T6AfRyPwMdDgaorQpOC5Iz2WfIowa6XzXQIiIiUjnmDKDN7FzgY8DR/vEGOOfcsaUdmpRSdtZ5rgw0TCznPbGMd3R830yrEXYOzB1AT5RwjOKcI6vUXkREROSIlU8Jx7eAv8FbRCVV2uFIubRkdd6YaxIhZAJor4QjFDCas4LuhhkC6K6hiazywMjMbewyj4nFUwyMJscnJIqIiIgcyfLpwtHvnLvROdfpnDuU+Sn5yKSkMhMDa6uCRELBOY72Sj4ODcc5ODDG8voIgcBEtnimDHSmA8fy+sisXTiW+cH7AZVxiIiISIXIJ4D+vZl9yszONrPTMj8lH5mUVLPfmq4pj/INmMhAdw5O9IDOaKwOTwuSuwbHiIYDrGyqnnESoXOOgdEkm1bUA7BfrexERESkQuRTwnGm/3tL1jYHXFT84Ui5ZEow5lpEJaOlNkJfLMHevhE2LK+btG+mEo7OwTGW10dprA6PLwGebTieIpV2HL+igbt39CgDLSIiIhUjny4cLyjHQKS8MoFzPvXPMLGYys7uYc47rnXSvlwlHG31ERqrw+w8NDztfJnjj1teh5k6cYiIiEjlyKcLx0dm2u6c+3jxhyPlkgmI8+nAARMBd9pN7sABXgAdi6dIpNKEg15VUNfgGOvb6mioDs1YA51ZeKW1rorWush4f2kRERGRI10+NdDDWT8p4BJgXQnHJGWQCYjzLeHIPm55fWTSvkz3jOxAuXNwjOUNXgZ6YDSJc27SYzIZ6IbqMEc1RpWBFhERkYqRTwnHZ7Lvm9mngZtKNiIpi2U1VTRWhzm6pSav41tqJ4LmmTLQ4AXFLXURxpIp+kcStNVFiIQDpNKO4XiKusjE2y0TQDdWh1nREGXXodjhviQRERGRssgnAz1VDbB6roPM7Ntm1mlmj+bYb2b2BTPbbmYPq7NHeQUDxu8/cCFvOuvovI7PzkCvaMwdQAN0D3mTBtvqIzREJ+/LGMgKoL0MtLpwiIiISGWYM4A2s0f8APdhM3sMeAr4XB7nvhq4eJb9lwAb/J8r0VLhZddcWzVeszyXZVmTDdvrJwfQDdVeZjkTJGd6QGcmEcJEzXPGpAx0YzUDo0mGx2ZecEVERETkSJKzhMPMjnHOPQtcmrU5CRx0zs0Z6TjnbjWzdbMcchnwPecVx95tZk1mdpRzbn+eY5cyCgUDNNWEGYmnxgPmjKkZ6E5/QuDy+uh4D+ipvaD7RxIEDGqrQqxo9MpDDgyMsr5tcos8ERERkSPNbOnH6/zf33bO7fJ/9uYTPOdpFdCRdX+Pv20aM7vSzO4zs/u6urqK9PRSqObaKtobopjZpO0NmUmEo95bo2tohgz01BKO0QQN1WECAWNFQzWg1QhFRESkMsw2iTBgZh8GNprZ307d6Zz7bOmGNe25vg58HWDLli1ujsOlRFY1VeNmuPpTu3BkSjha6qpIpNKT9mX0jyTGH3eUX1M9n04cNzy8n5NWN7KmOb/JkCIiIiKHa7YM9Ovx2taFgPoZfg7XXmBN1v3V/jY5Qn36NSfzmdeePG17JBQkGg5MlHAMjo3XV+eaRJgdQGcmJR4ocCLh8FiSq665n+/dtbPQlyIiIiIybzkz0M65p4B/N7OHnXM3luC5rweuMrNr8ZYL71f985Ftavu6bI3V4fGJgl2DY+O9ouujIcxmz0BHw0GW1YQ5UOBiKts7h3BuIuMtIiIiUg759IGeV/BsZtcAFwKtZrYH+CgQ9s/5VeBXwEuB7UAMeNt8nkeODA3R8KQuHG1+AB0IGHWR0Hh9dEb/SIKVTdXj91c0VhdcA/30wUHv+YYUQIuIiEj5zBlAz5dz7oo59jvgPaV6fimvxurJAfSxrbUz7ssYyMpAA/NajXBb5xAA3YPx+Q5bREREpGDzWUhFZJpMkOycm5SBzuzLLuFwztE/khivjwavDloZaBEREakE+SykUmNm/8fMvuHf32Bml871OFlaGqvDDIwmGBhJEk+lJwXQ2eUdAKOJNImUm5yBbohyaDjOaCKV93NuO+hloHtj8fFuHyIiIiKllk8G+jvAGHC2f38v8H9LNiKpSA1+BrpryMsiT8tAZy2kkr0KYUamE0fnQH7Z5OGxJHv7RjiqMYpz0DOsMg4REREpj3wC6PXOuU8CCQDnXAyw2R8iS01jdZjB0SQH+icWUcloqA5NykDPFkDvz7OVXab++ez1LYA6cYiIiEj55BNAx82sGnAAZrYeLyMtMi4TDD/T5QW2y+ujk/bNFUBnFlPJt5Vdpv75nPWtAHSrDlpERETKJJ8uHB8Dfg2sMbMfAucCby3hmKQCZZbz3u5nhqeWcIwm0owlU0RCwRwZaK+lXb6dOLYdHKQqFOD0o5cBykCLiIhI+eTTB/o3ZrYVOAuvdON9zrnuko9MKkpjVgBdFQrQEJ14azWML/WdpK1+IoBuqJ44pi4Soj4SyrsTx9MHh1jfVkd7gxeodw+pBlpERETKI58uHP8NvBi4xTn3PwqeZSbjAXTXEG11Ecxs2r7MRMKZMtBQWCu77Z1DbGyvo6YqRG1VUBloERERKZt8aqA/DZwPPG5m15nZq80s95rOsiRlguGuwTGWN0Qm7cv0e84Ezpme0PXR6QH0/jxqoIf8Dhwb2+sBaK2PqAZaREREymbOANo59wfn3F8CxwJfA14LdJZ6YFJZsrPJbXVTAujqyQF0/0iC+miIYGByM5ejGqMcyKMLxzZ/AuGG5XUAtNZFlIEWERGRsslrJUK/C8ergHcDzwO+W8pBSeWZFEDXR2bcN5CVgZ5avgHeRMLOwbE5F0XJLKCywc9At9UpAy0iIiLlk08N9I+BJ4CLgC/h9YV+b6kHJpUlGg4QDnoZ5akBdGay4EBWBnqmADqzKMpc2eSnDw4SCQVY21wDQGt9lQJoERERKZt82th9C7jCOZf/Gsuy5JgZjdVhuofik3pAw0QN9MBoEsgdQGcWU9nbN8LKpuqcz7Wt0+vAkSkBaauL0htLkEilCQfz+lJFREREZN5yRhtmdpF/sxa4zMwuz/4pz/CkkmRqnadmoKPhIJFQYFINdEN0egD93FWNBAPG756cvcR+28FBNrbXjd9vra8C4JBa2YmIiEgZzJauu8D//bIZfi4t8bikAjXmCKAz+/pjs5dwtNZFuGBjG794YC+ptJvxOQZHE+zrHx2vf4aJSYuaSCgiIiLlkLOEwzn3Uf/mx51zz2bvM7NjSjoqqUiZoHh5jgA60wd6YDRBY830ABrg8tNWcdWPOrl7xyHOPa512v5t/kqHG7MC6Nb6zGIqCqBFRESk9PIpGP3pDNuuK/ZApPJlAuiWuqpp+xqqw/SPJBhLphhNpGfMQAO88Dnt1EdD/PT+PTPun9rCDpSBFhERkfLKmYE2s+OBzUDjlJrnBkALqcg0q5dVs3pZNZFQcNq+xuownYOjWct4zxxAR8NBLj1pJb98cC//clmS2sjkt+i2g0NEQgHW+B04wCv9AOhSBlpERETKYLYM9Ca8WucmJtc/nwa8q+Qjk4rz3os28Iv3nDvjvoZoiP6RxHgru1wZaIBXnbaKWDzFTY8dmLbv6c4hjlteN2kRluqqIHWRkEo4REREpCxmq4H+JfBLMzvbOXdXGcckFSoaDhINT88+g18DPZKcyEBHc3dQPP3oZaxtruFn9+/l8tNWT9q37eAgZx3bMu0xbfVajVBERETKI58a6HebWVPmjpktM7Nvl25IshhlJhH2xebOQJsZl5+2ijue6WZ/1tLev3xwL/v7R9m0on7aY1rrtJiKiIiIlEc+AfRJzrm+zB3nXC9waslGJItSQ3UY57xFUmD2ABrg8lNX4xz84oF9pNOOT930JO+79kHOPKaZK85YO+14ZaBFRESkXPJZiTBgZsv8wBkza87zcSLjMpMGO3piwNwB9NqWGp63bhk/2drBA7t7+c3jB7nijDX888tPpCo0/XNfa12EO4YOFX/gIiIiIlPkEwh/BrjLzH7i338N8InSDUkWo8zKgx09XgY6VxeObJeftpoP/ewRdnYP89GXncBbz1mHmc14bGtdZLxN3kxdQERERESKZc4A2jn3PTO7D8gs7X25c+7x0g5LFptMxnl3T4zaqiDh4NzVQy87eSV37zjE5aet5oKNbbMem1n98NBQnJVN1Yc/YBEREZEc8i3FaAaGnXPfMbM2Mztm6uqEIrNpzCrhmKt8I6MuEuLzr8+v3D7TC7p7aEwBtIiIiJTUnGlAM/so8A/Ah/xNYeAHpRyULD4N1d5ntcGxZF7lG4XKZKA1kVBERERKLZ8uHK8EXg4MAzjn9gHT+4iJzCI761yKALrVXz5crexERESk1PIJoOPOOQc4ADOrLe2QZDGqrQqRWTww3xKOQowv560MtIiIiJRYPgH0j83sa0CTmb0L+F/gG6Udliw2gYCNZ55LEUBHw0HqoyG6h+JFP7eIiIhItny6cHzazF4EDACbgI84524u+chk0WmsDtMXS5QkgAZoq9NiKiIiIlJ6eXXh8ANmBc1yWDK9oEsVQLfWR+gqcg30WDLFzu7YjMuHi4iIyNKUs4TDzG73fw+a2cAMP8+a2V+Wb6hS6TKBc0O0NAtZttVFij6J8BM3PMHLvng7I/FUUc8rIiIilStnAO2cO8//Xe+ca5j6A2wB3leugUrly7Sya6wpUQlHfXFLOPb1jXDtPR3EU2k6B0eLdl4RERGpbHmlAs3sNOA8vE4ctzvnHnDOHTKzC0s4NllkGks4iRC8VnaDo0lGEymi4cNfzvsrtzxDPJUGvO4eR7eoAY2IiIjkt5DKR4DvAi1AK3C1mf0TgHNuf2mHJ4tJKbtwwMRiKsUo49jfP8J/3dvBKWuaALXHExERkQn5tLF7I/A859xHnXMfBc4C/qy0w5LFqOSTCMeX8z78VnZfueUZ0s7x0ZedAFD0yYkiIiJSufIJoPcB0az7EWBvaYYji9ma5hqqQgHa6qJzHzwPxVpM5UD/KNfe08FrtqzmpNVNBEwZaBEREZmQswbazL6IV/PcDzxmZjf7918E3FOe4cliculzj+LMY5pLOokQDr+E4yu3bCftHH954XEEA0aL+kuLiIhIltkmEd7n/94K/Dxr+y0lG40saoGA0d5QmuwzQEtdFXB42eID/aNcc08Hrz59NWuaawAt0CIiIiKT5QygnXPfBTCzKHCcv3m7c079vOSIFAkFaawOH1bLuW/dvoO0c7znBceNb1veUPwFWkRERKRyzbaQSsjMPgnswevC8T2gw8w+aWal+Q5e5DA956h67t/VN6/HjiZSXLd1Dy/ZvGI8+wzKQIuIiMhks00i/BTQDBzjnDvdOXcasB5oAj5dhrGJFOz8DW08vn9gXnXQNz12gN5YgtefsWbS9rZ6b4XDdNoVa5giIiJSwWYLoC8F3uWcG8xscM4NAH8BvLTUAxOZj/OOawXgju3dBT/22ns6WNNczbnrWydtb6uPkEg5+kcSRRmjiIiIVLbZAmjnnJuWcnPOpfC6cYgccU5c1UhjdZjbtxUWQD/bPcxdOw7x+uetJRCwSfsy3T1UBy0iIiIwewD9uJm9eepGM3sT8GTphiQyf8GAcc76Fm7f3s0Mn/9yuvbe3QQDxmtOXz1tX1uR+kuLiIjI4jBbG7v3AD8zs7fjtbID2AJUA68s9cBE5uu8Da3c+OgBdnQPs76tbs7j48k01923h4uOX87yGdrsjWegFUCLiIgIs7ex2wucaWYXAZv9zb9yzv22LCMTmafzj2sD4PZt3XkF0P/7xEEODcd5wxlrZ9yvAFpERESyzZaBBsA59zvgd2UYi0hRrG2pYW1zDbdt6+Yt56yb8/hr7tnNysYoz9/YNuP+ukiIaDigGmgREREBZq+BFqlY521o5e4dh0ik0pO2J1Np9vTGGE2kAOjoiXHbtm5es2UNwSmTBzPMjLb6CJ0DWkNIRERE8shAi1Si845r5Ud/3M1DHX1sWdcMeAulvPqrd/Lo3gHAyyxHQgECBq993prZTuctpqIMtIiIiKAAWhapc9a3YAa3b+8eD6A//j+P8+jeAd7/oo0EAkbX4BjdQ2M856gGVjVVz3q+tvoIz3YPl2PoIiIicoRTAC2LUlNNFSetauT2bd389Qs38ssH9/KjP+7m3Res571/sqHg87XVR7jn2Z4SjFREREQqjWqgZdE6b0MrD3T08ciefj78s0fYcvQy3v/ijfM6V1tdlN5YgngyPffBIiIisqiVNIA2s4vN7Ckz225mH5xh/9Fm9lsze9jMbjGz6atYiMzTece1kUo73vDNu6kKBfjCFacSDs7vLZ9pZXdoWHXQIiIiS13JAmgzCwL/CVwCnABcYWYnTDns08D3nHMnAR8H/rVU45Gl57Sjm6gOBxkcTfLZ157CyjnqnGeTqxe0c46nDgwe1jhFRESkspQyA30GsN05t8M5FweuBS6bcswJTPSY/v0M+0XmLRIK8pcXruef/vQ5vOD45Yd1rlwB9O+f6uQln7uVB3b3Htb5RUREpHKUMoBeBXRk3d/jb8v2EHC5f/uVQL2ZtZRwTLLEvPdPNvDO84897PPkCqDvedYLnO/aceiwn0NEREQqw0JPIvwAcIGZPQBcAOwFUlMPMrMrzew+M7uvq6ur3GMUobWuCpgeQD/U0QfA1p3KQIuIiCwVpQyg9wLZq1Os9reNc87tc85d7pw7FfhHf1vf1BM5577unNvinNvS1jbzcssipRQJBWmsDk9aTCWddjyytx+A+3b1kk67hRqeiIiIlFEpA+h7gQ1mdoyZVQGvB67PPsDMWs0sM4YPAd8u4XhEDktbfWRSBnpH9xBDY0nOPKaZ/pEE27uGFnB0IiIiUi4lC6Cdc0ngKuAm4Angx865x8zs42b2cv+wC4GnzOxpoB34RKnGI3K42uomB9APdnjZ50yN9X0q4xAREVkSSroSoXPuV8Cvpmz7SNbt64DrSjkGkWJZ3hDhQb/mGbz657pIiIuOX05rXRX37ezhDWeuXbgBioiISFks9CRCkYoxNQP90J4+nruqkWDA2HJ0M/fu0lLfIiIiS4ECaJE8tdVHiMVTDI8lGUumeGL/ACevaQJgy7pldPSMcHBgdGEHKSIiIiWnAFokT9m9oJ/YP0gi5ThlTSMAW9Y1A6qDFhERWQoUQIvkKRNAdw6Ojfd/zmSgN69sIBoOcO9OlXGIiIgsdgqgRfKUnYF+qKOPtvoIKxqiAISDAU5ds4ytu5SBFhERWewUQIvkqa0uE0CP8uCePk5e3YSZje/fsm4Zj+8fYHgsuVBDFBERkTJQAC2Sp2U1VQQDxjNdw+zoGh6vf87Ysq6ZVNpNanUnIiIii48CaJE8BQJGa10Vv3uyE5iof844bW0TAUN10CIiIoucAmiRArTVR9jbNwLASauaJu2rj4Y5fkWDOnGIiIgscgqgRQqQqYM+prWWxprwtP1b1i3jgd29JFPpcg9NREREykQBtEgBMp04Tl7dOOP+LeuaGY6nePLAYDmHJSIiImWkAFqkAOMB9JT654xT/e0P7ekrz4BERESk7BRAixQgU8KRK4Bevayaxuowj+4dKOOoREREpJxCCz0AkUpyyXOPomc4zkmrZi7hMDNOXNXAY/v6yzwyERERKRdloEUK0N4Q5W9fvIlQMPd/OieubOTJ/YMkNJFQRERkUVIALVJkm1c1Ek+l2XZwaKGHIiIiIiWgAFqkyE5c2QDAoyrjEBERWZQUQIsU2bqWWmqrgjy2VwG0iIjIYqQAWqTIAgFj88pGHt2nThwiIiKLkQJokRLYvKqBx/cNkEq7hR6KiIiIFJkCaJESOHFlIyOJFM92ayKhiIjIYqMAWqQETvT7RGtBFRERkcVHAbRICaxvqyUSCvCoJhKKiIgsOgqgRUogFAzwnKMaeEQBtIiIyKKjAFqkRE70JxKmNZFQRERkUVEALVIiJ65sZHAsye6e2EIPRURERIpIAbRIiYxPJNSKhCIiIouKAmiREtnQXkc4aOrEISIissgogBYpkUgoyMb2eh5TBlpERGRRUQAtUkInrmzk0b39OKeJhCIiIouFAmiREjpxVQO9sQT7+kcXeigiIiJSJAqgRUposz+R8JE9fQs7EBERESkaBdAiJbR5ZQN1kRC/f7JroYciIiIiRaIAWqSEIqEgFx2/nJufOEgylS7KOZ/pGuKhjr68jx8aS3LXM4eK8twiIiKiAFqk5C4+cQU9w3Hu2dlTlPP91TUP8Kqv3MnNjx/M6/jv3P4sV3zjbvb2jRTl+UVERJY6BdAiJXbhpjYioQA3PXrgsM+169Awj+0bIBIK8J4f3s+tT89dGnL/7l4AZaFFRESKRAG0SInVVIW4YGMbv37sAOn04bWzu9EPwn/87rNZv7yOK79/H3/ckTswds7xoF/ucfcsx4mIiEj+FECLlMElz13BwYExHjzMbhw3PrKfk1c3snllI99/xxmsaqrm7VffywN+lnmqjp4RemMJwkFTBlpERKRIFECLlMFFx7cTDhq/Powyjj29MR7a088lzz0KgNa6CD9611m01EW46kcPzLhYywMdXmB9+amr2ds3QkdPbN7PLyIiIh4F0CJl0Fgd5pz1rfz60QPzXpUwE3xfcuKK8W3tDVHe84L17O0b4emDQ9Me81BHP9FwgDefczQAd6mMQ0RE5LApgBYpk4tPXMHunhiP7x+Y1+N/9ch+Nq9s4OiW2knbz9vQBsBt26ZPKHywo5cTVzZywlENtNRWqQ5aRESkCBRAi5TJi05oJ2DM2Y1jNJGalqXe3z/C/bv7eKlfvpFtVVM169tquXVb96TtiVSaR/cNcMqaJsyMs45t4e5nDk07d+9wnE/c8DhDY8l5vjIREZGlRQG0SJm01kV43rrm8U4aM0mlHS/74u289mt3TQpoZyrfyHb+hjbuefYQo4nU+LYn9w8ST6Y5eU0TAGcd28y+/lE6eib3g/7yLdv5xm3P8tOte+b70kRERJYUBdAiZXTJiSvY1jnE9s7p9coAv33iINs6h7h3Zy9v+849DPtB9I2PHOD4FfUc21Y34+Oev7GV0USarbsmunFkOn6c4gfQZ69vAeCuHROZ6p7hOD+4ezcAP39g72G9NhERkaVCAbRIGb3kxBWYwXU5sr3fu2sXRzVG+fzrT+H+3X287ep72dk9zL27erjkxOnlGxlnHtNCOGjcmlUH/eDuPlpqq1i9rBqA9W11tNZFuHvHxIqI37njWUYSKV67ZTUPdvSxo2vmwF5EREQmKIAWKaOjGqt52Ukr+e6dO+kcGJ20b3vnILdv7+ZNZx3NZaes4nOvO4X7dvbwyi/fgXPw0ufOXL4BUBsJcfrRy7jt6Yns8kN7+sbrnwG/DrqZu/w66IHRBFffuZOLN6/g/S/eRMDgF8pCi4iIzEkBtEiZ/e2LNpJIpfni77ZP2v69u3ZRFQzwuuetAeBlJ6/kP153Cv0jCda31bKhvX7W856/oY3H9w/QNTjGwGiCZ7qGxuufM846toUDA6PsOhTj+3ftYnA0yVUXHUd7Q5Rzj2vl5w/unXebPRERkaVCAbRIma1rreX1Z6zhmnt2s+vQMACDowl+unUPl558FK11kfFjLztlFddeeTZfuOLUOc97/oZWAO7Y3s0je/pxbqL+OSNTB/3bJzv55m07eMGmNk5c1QjAK09dRUfPCPftmnlVw2yP7OlX1w4REVmyFECLLIC/umgDoaDxHzc/DcBPt+5hOJ7iLWevm3bsGcc0s3ll45zn3LyykWU1YW7b1s2DHX0AnLy6adIxx7bW0lYf4bO/eYreWIKrLjpufN9LNq+gOhzkZ/fnLuN46sAgb/72PbzsS7fzsi/ezlMHBud+sSIiIouMAmiRBbC8Icrbzz2GXz60j8f29fO9u3Zx8pqmaSUXhQgGjHOPa+W2bV08sLuPY1traawJTzrGzDj72BaG4ynOPraF049uHt9XGwnxks3t3PDwvknt8AA6B0f50M8e5pLP38pDHX1c9YLjGBpL8or/vKModdO/emQ///zfj+Xc//i+Af7uJw8RT6YP+7lEREQOlwJokQXy589fT30kxLt/sJUd3cO81V9u+3A8f0MbnYNj3Pp017TyjYzzjvNKPd6blX3OeOVpqxkYTfL7JzsBSKcd37trJxd9+g/85L49vPWcY/jD313IB16yiRv+6jyeu7qRv/6vB/nILx+dd3CbTKX5xA1P8J07duZs7/fVPzzDT7bu4XdPHpzXc4iIiBSTAmiRBdJYE+YvLjyOjp4RWuuqZlxlsFDn+XXQ8VQ6Zzb78tNWcf1V53KOH0hnO3d9C231EX7+wF62dw7ymq/dxUd++Rinrm3i5r+9gI+87ASaaqoAWF4f5YfvPJMrn38s37trF5+44fF5jfk3jx9kb5+3uMtM2eyhsSS/edxbSOa6reoSIiIiC08BtMgCeus561jfVss7zz+WSCh42Odb2VTNccu9xVZyZaBDwQAnrc6977KTV/K7Jzt56edv55muIT7zmpP53tvP4JjW2mnHh4MBPvzS5/DaLau59t4OeobjBY/5W7c/y9rmGs47rpVfPLiXdHpyF5BfP3qA0USaM49p5panOukeGiv4OURERIpJAbTIAqquCvLb91/Iuy9YX7RzXnT8cuoiIY4/ava2d7m89nlrCJjx4s3t3Pw3F/Cq01eP95LO5V3nH8tYMs0P795V0HM92NHH1l29vPWcdbzq9FXs6Z3eBeTnD+zh6JYa/uUVJ5JMO3754L6CX5OIiEgxKYAWWWT+5oUb+dVfnT/vjPbG9noe+ecX86U3nEZbfWTuBwAb2uu5cFMb371r17QJiLP5zh3PUhcJ8Zotq3nJ5hXUVAUnLSm+v3+EO585xCtOWcXG9npOXt2YcxVHERGRcilpAG1mF5vZU2a23cw+OMP+tWb2ezN7wMweNrOXlnI8IktBdVWQtS01h3WO+QTf7zzvWLqHxrj+oekZ4u6hsWmlFwf6R7nh4f287nlrqI+GqakK8ZLNKyZ1Afnlg/twzutRDfDq01fzxP4BHtvXP49XJSIiUhwlC6DNLAj8J3AJcAJwhZmdMOWwfwJ+7Jw7FXg98OVSjUdESuvc41o4fkU937rt2UmrGe7oGuLiz93GhZ+6hR/f1zG+7/t37yTtHG89Z934sa84dRUDo0luecrrAvKLB/Zy2tom1vn11y87eSVVwQA/PUImE06t1xYRkaWhlBnoM4Dtzrkdzrk4cC1w2ZRjHNDg324EVNwoUqHMjHeefyxPHRzktm3dAHT0xHjjN/+Ic44Tjmrg7697mHd97z46emL86I+7edEJ7axpnsiWZ7qA/Oz+vTy+b4AnDwyOZ58BmmqqeOEJy/nFg3sXtCf00FiSN3/7Hl7yuVvpHBxdsHGIiMjCKGUAvQroyLq/x9+W7WPAm8xsD/Ar4L0lHI+IlNjLT17J8voI37htB/v7R7jiG3cTi6f4/jvO5Norz+Kf/vQ53Lqtm4s+cwu9sQRvP/eYSY8PBQO8/OSV/P6pTr5zx7OEg8alJ62cdMyrTltNz3B8PEsN4Jxjf/8IY8n866/nq3tojCu+fjd3bO9mT+8If/bNe+jN0X1EGWoRkcUptMDPfwVwtXPuM2Z2NvB9MzvROTcptWRmVwJXAqxdu3YBhiki+agKBXjLOev41E1P8eqv3MXASIIfvutMTljpfdH0zvOP5cJNbfzddQ8TCQU445jmaed45amr+Nbtz/KTrXt40QntLKutmrT/+RvbaK2LcN3WPaxojPKrRw5w46P72XUoRsBgTXMN69vqWNdSS10kSDgYIBwKEAkFOHlNE6esbiIQyN1VJJlKc/eOHm54ZD/RcIBLT1rJaWubMDM6emK8+dv3sL9/hG+8+XSioSBvvfpe3vzte/jhu86kIeqt/Pj4vgH+9cYneHRvP19+4+mcvb6liFdZREQWmmXXKhb1xF5A/DHn3Ev8+x8CcM79a9YxjwEXO+c6/Ps7gLOcc50znBKALVu2uPvuu68kYxaRw9cXi3P2v/4OgO+/4wy2rJseJIOXNZ6pPZ5zjhf/x61s6xziy288bcYFZj5xw+N847ZnAQgFjHOOa+WCjW30x+I80z3MM51D7O6JEYtPz0i31lVx4ablvPA5y2mrj5JIpUmk0ozEU9yxvZsbHtlP91Cc2qogibQjnkyzqqmaS05cwfUPeRMcv/O2540vg/67Jw/y59/fysmrm/jUa07mK7ds5ydb99BYHaaxOsz+vlE+9ZqTuOyUqV/AiYjIkc7MtjrntkzbXsIAOgQ8DfwJsBe4F3iDc+6xrGNuBP7LOXe1mT0H+C2wys0yKAXQIke+u545REN1iM0rG+f1+B/cvYtv3raDX//184mGp3cE2dc3wmdvfpozjmnmxSe0j6+OOJVzjmTakUilGRpNcteOQ/zvE53c8lQng6PJacdHQgH+5DnLefnJK7lw03LiqTQ3P3aQ6x/ax+3bu2mtq+J7bz+TTSsm99j+1SP7uepH95N2EA4abz1nHVe9YAMAV37/Pv74bA9/f/Em/uKC9XP21BYRkSNH2QNo/0lfCnwOCALfds59wsw+DtznnLve78rxDaAOb0Lh3zvnfjPbORVAi8jhSqTSPNTRx3A8RThoVAUDhIMB1i+voy4yc2VbfyxBtCqQs8XfDQ/v59anu/jLF6zn6JaJVRvHkik+8JOH+e+H9vGa01fz+jPWsHll44wfDLKNJlJs7xxiX98I+/tH2dc/QtfAGKuXVXPK2iZOWbOM5tqZPziIiEhxLEgAXQoKoEWk0qTTjk/e9BRf/cMzgJel3ryykZNWN1IdDmJmBAOQTDt2dA2z7eAgu3piZP/vORw0WusiHBwYJTM38eiWGhqrw8STab8UxdsRChrhQIBQ0GiIhlnRGKW9IcqKhghmxr6+Efb0jbCvb4SqYIAXb17BJSeuYGVTdbkvjYjIEU0BtIjIAusaHOP+3b3ez65entw/SDyVxjlIOYfhBcWbVtSzYXk9G9vrWdNczVGN1bTUVhEIGMNjSR7Z28+DHX08vKeP0USaUMAIhwKE/cmRibQjmUqTTDn6RhIc6B+lc3B0PMCuCgVY1VTNyqYoh4biPHlgEIBT1zax5ehlDIwkOTQcp2d4jLFkmvaGKEc1RlnZVE1rXRVmhnMO5yDtwOG8oN55v13mN97taDhITVWQmqoQtZGJ2zVVQaqrguBgNJFmLJliNJFmYDRBz3B8/CccNFY2eddhVVM11VVBBkYTDI4mGRxNkEo7WusitNRV0VxbxWgizR93HOLOZw5x5zPd7O8b5dKTV/LGM9dy4qr5lRWJyNKkAFpEZAlLpx09sThp52itjUzqRLKja4gbHz3ADQ/vZ3vnEE01YZprq2ipqyISCnKgf5T9/SP0xhIL+AryZwbOQXU4yPOOaaa5JsyvHzvAaCLNyWuaeNVpq2itixAJeSU5VX6Xlkg4QFUwQCQcJBIKjG+vCgZy1q4754in0gTMCAdLuriviCwABdAiInJYRuIpDg17S7KbGQEDw/uNQcAMw/9tjAedY4kUsXiK4XiSkXiK4XiKkXiS4bEUsUSKgEE0FCQS9gLahmiI5toqltVW0VQdJpl2Xh143wh7e0cYTaZoiIZpqA5RHw0TMOgeinNoKM4hf8n4M45p5pS1TeM16/0jCX5+/x5+8MfdbO8cKvi1jwfZIS+4jvudW0YSKVJ+TU0wYERCAaLhIFH/d1Xmftj7PbHf2xbxj42Eg4QCRigYoCro/Q4FjKpQgJBfjlMV9H6HAgGqQjZle/bxNt66cbbgX0TmpgBaRESWPOccHT0jxBJJxhJp4qk0Y375SDyZZiw59fYM2xJpqkJGdXiiDCWddowl04wmUoz6pSijidT4trFEmtHkxO/RRGpS2UopRfxgOhAwnF9iAxAOBrIy7UEaqkMsq/G+eVhWU0VNlffhIzsAN/9Dk/fb+9AQMPN+B4ygGaHM7QDj+4I2sT9zbDhgNFSHaaoJjz9fpjwo7SCZTo8fP/5hLJmiL5agNxanL+aV7wQD3nMGA0ZLbYSjmqL6NkCKJlcAvdALqYiIiJSNmbG2pWbuA8soUwaSTDmSKf92Oj1xO+XG+5Vn2jImUl6de8Lfl0xn3fZ/e8F+avxDQCZwzgSjyXTmw4MXyA+MJNl1KMb9u/vojcXHM+vlEvTLimZ63kwQHk/N/WEjGDCOaoyytrmG1roI1WHvQ051VZAa/3amLj8cDJD2r4tX0+/V9mfq951f45+p9/fOD8FAYOJ35kOC/6HB+x7Gk3aOQ8NxOgdG6Rwco2twjEDAqI+EqI2EqIuEaK2PsLIxOl7j31Ad0rcGFUABtIiIyAIyM780ZKFHMiGddqSyAkhgvCtM5nfaecek045UOnPbC8zTaW9ibCrtvOPSk2+nnSOedAyMJujzs8kDowmM7GDUSKe9Xu4p/3d9NDSesW6qDhMKBkim097+lKNraIyOnhgdPTF29cR4ZG8/Mb90aCSRGp9IuxAaq8O01UdIO8fQaJLhsSTDMyz2BH7JUHCWuvxM/X4wgBmM+GVSI/EUiVR68jGTHjN9ezgYGC+ziiW8b1pa6qpY1eQF9Ec1VtNYE6bW/xCisiDPEfSfq4iIiBwJAgEjwOILkhIpr6RmIqBOg1+Skqnhn1SmYpPr/YHxDw2ZwH7Sz5SyWAOaa6toq4/M2Ps9lXZ0D42xr2+EfX3eZN2B0aRfLjS5lCieTI2XEI0m0vSPJBhLpHHglRKFg7TWVREKBrxvIBJpRhIp+kbi4+eZ/HviA4WZN+m2Ouxl5Q8Nj+X8sJEpl5n0Oqe8VTJZ+XAwMOm3V8Pvlf1kMv6ZrH/aL93JfCOQ6c8fDnmP/9qfnc7y+mjBf/NSUQAtIiIiS0LYD8rqo+GFHgrglZu0N3h92k9dW/7nT6cdiXR6WlY57Qf2e/2FnAZHEwyPeR86hseS0z4oTOIHwYmUG/92IFNylPS/KUg559fFZz6geB9SMhOQcV47zkTSm6eQSKUJBY6sunYF0CIiIiJLUCBgRALTM+OBgLG8IcryhiinLsC4KsGRFc6LiIiIiBzhFECLiIiIiBRAAbSIiIiISAEUQIuIiIiIFEABtIiIiIhIARRAi4iIiIgUQAG0iIiIiEgBFECLiIiIiBRAAbSIiIiISAEUQIuIiIiIFEABtIiIiIhIARRAi4iIiIgUQAG0iIiIiEgBzDm30GMoiJl1AbsW6Olbge4Feu7FQtewOHQdi0PX8fDpGhaHrmNx6DoWh67jhKOdc21TN1ZcAL2QzOw+59yWhR5HJdM1LA5dx+LQdTx8uobFoetYHLqOxaHrODeVcIiIiIiIFEABtIiIiIhIARRAF+brCz2ARUDXsDh0HYtD1/Hw6RoWh65jceg6Foeu4xxUAy0iIiIiUgBloEVERERECqAAOg9mdrGZPWVm283sgws9nkphZmvM7Pdm9riZPWZm7/O3N5vZzWa2zf+9bKHHeqQzs6CZPWBm/+PfP8bM/ui/J//LzKoWeoxHOjNrMrPrzOxJM3vCzM7We7FwZvY3/n/Pj5rZNWYW1ftxbmb2bTPrNLNHs7bN+P4zzxf86/mwmZ22cCM/suS4jp/y/7t+2Mx+bmZNWfs+5F/Hp8zsJQsy6CPMTNcwa9/7zcyZWat/X+/FHBRAz8HMgsB/ApcAJwBXmNkJCzuqipEE3u+cOwE4C3iPf+0+CPzWObcB+K1/X2b3PuCJrPv/DvyHc+44oBd4x4KMqrJ8Hvi1c+544GS866n3YgHMbBXwV8AW59yJQBB4PXo/5uNq4OIp23K9/y4BNvg/VwJfKdMYK8HVTL+ONwMnOudOAp4GPgTg/3vzemCz/5gv+/+mL3VXM/0aYmZrgBcDu7M2672YgwLouZ0BbHfO7XDOxYFrgcsWeEwVwTm33zl3v397EC9gWYV3/b7rH/Zd4BULMsAKYWargT8FvunfN+Ai4Dr/EF3DOZhZI/B84FsAzrm4c64PvRfnIwRUm1kIqAH2o/fjnJxztwI9Uzbnev9dBnzPee4GmszsqLIM9Ag303V0zv3GOZf0794NrPZvXwZc65wbc849C2zH+zd9ScvxXgT4D+DvgezJcXov5qAAem6rgI6s+3v8bVIAM1sHnAr8EWh3zu33dx0A2hdqXBXic3j/U0v791uAvqx/MPSenNsxQBfwHb8U5ptmVoveiwVxzu0FPo2XodoP9ANb0ftxvnK9//Tvzvy9HbjRv63rmCczuwzY65x7aMouXcMcFEBLyZlZHfBT4K+dcwPZ+5zXBkatYHIws0uBTufc1oUeS4ULAacBX3HOnQoMM6VcQ+/Fufk1upfhfSBZCdQyw1fBUji9/w6fmf0jXungDxd6LJXEzGqADwMfWeixVBIF0HPbC6zJur/a3yZ5MLMwXvD8Q+fcz/zNBzNfAfm/OxdqfBXgXODlZrYTr3zoIrxa3ib/K3TQezIfe4A9zrk/+vevwwuo9V4szAuBZ51zXc65BPAzvPeo3o/zk+v9p393CmRmbwUuBd7oJvrz6jrmZz3eh+KH/H9rVgP3m9kKdA1zUgA9t3uBDf4s8yq8CQnXL/CYKoJfq/st4Ann3Gezdl0PvMW//Rbgl+UeW6Vwzn3IObfaObcO7733O+fcG4HfA6/2D9M1nINz7gDQYWab/E1/AjyO3ouF2g2cZWY1/n/fmeuo9+P85Hr/XQ+82e+AcBbQn1XqIVOY2cV4ZW4vd87FsnZdD7zezCJmdgzeRLh7FmKMRzLn3CPOueXOuXX+vzV7gNP8/2/qvZiDFlLJg5m9FK8ONQh82zn3iYUdUWUws/OA24BHmKjf/TBeHfSPgbXALuC1zrmZJjRIFjO7EPiAc+5SMzsWLyPdDDwAvMk5N7aAwzvimdkpeBMxq4AdwNvwkgh6LxbAzP4ZeB3eV+UPAO/Eq4nU+3EWZnYNcCHQChwEPgr8ghnef/6Hky/hlcfEgLc55+5bgGEfcXJcxw8BEeCQf9jdzrl3+8f/I15ddBKvjPDGqedcama6hs65b2Xt34nXaadb78XcFECLiIiIiBRAJRwiIiIiIgVQAC0iIiIiUgAF0CIiIiIiBVAALSIiIiJSAAXQIiIiIiIFUAAtInIEMrMh//c6M3tDkc/94Sn37yzm+UVEFjsF0CIiR7Z1QEEBdNaqgLlMCqCdc+cUOCYRkSVNAbSIyJHt34DzzexBM/sbMwua2afM7F4ze9jM/hy8hXbM7DYzux5vdUDM7BdmttXMHjOzK/1t/wZU++f7ob8tk+02/9yPmtkjZva6rHPfYmbXmdmTZvZDf4EFEZElaa4shYiILKwP4q9ACeAHwv3OueeZWQS4w8x+4x97GnCic+5Z//7b/ZXtqoF7zeynzrkPmtlVzrlTZniuy4FTgJPxVim718xu9fedCmwG9gF3AOcCtxf7xYqIVAJloEVEKsuLgTeb2YPAH4EWYIO/756s4Bngr8zsIeBuYE3WcbmcB1zjnEs55w4CfwCel3XuPc65NPAgXmmJiMiSpAy0iEhlMeC9zrmbJm00uxAYnnL/hcDZzrmYmd0CRA/jeceybqfQvx8isoQpAy0icmQbBOqz7t8E/IWZhQHMbKOZ1c7wuEag1w+ejwfOytqXyDx+ituA1/l11m3A84F7ivIqREQWEWUQRESObA8DKb8U42rg83jlE/f7E/m6gFfM8LhfA+82syeAp/DKODK+DjxsZvc7596Ytf3nwNnAQ4AD/t45d8APwEVExGfOuYUeg4iIiIhIxVAJh4iIiIhIARRAi4iIiIgUQAG0iIiIiEgBFECLiIiIiBRAAbSIiIiISAEUQIuIiIiIFEABtIiIiIhIARRAi4iIiIgU4P8DmoMgv+q3nEAAAAAASUVORK5CYII=\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -547,7 +550,7 @@ "plt.rcParams[\"figure.figsize\"] = (12, 6)\n", "\n", "# fit classifier to data\n", - "opflow_classifier.fit(X, y)\n", + "estimator_classifier.fit(X, y)\n", "\n", "# return to default figsize\n", "plt.rcParams[\"figure.figsize\"] = (6, 4)" @@ -568,7 +571,7 @@ { "data": { "text/plain": [ - "0.68" + "1.0" ] }, "execution_count": 18, @@ -578,7 +581,7 @@ ], "source": [ "# score classifier\n", - "opflow_classifier.score(X, y)" + "estimator_classifier.score(X, y)" ] }, { @@ -603,24 +606,24 @@ "name": "stdout", "output_type": "stream", "text": [ - "normalized local effective dimensions for trained QNN: [0.79663244 0.80325759 0.80653351 0.82723511 0.83320702 0.84062917\n", - " 0.84641928 0.85045673 0.86276589 0.87134912]\n" + "normalized local effective dimensions for trained QNN: [0.456038 0.45843889 0.45960309 0.46636707 0.46810242 0.47013072\n", + " 0.47163132 0.47264798 0.47572459 0.47805338]\n" ] } ], "source": [ - "trained_weights = opflow_classifier.weights\n", + "trained_weights = estimator_classifier.weights\n", "\n", "# get Local Effective Dimension for set of trained weights\n", "local_ed_trained = LocalEffectiveDimension(\n", - " qnn=opflow_qnn, weight_samples=trained_weights, input_samples=X\n", + " qnn=estimator_qnn, weight_samples=trained_weights, input_samples=X\n", ")\n", "\n", "local_eff_dim_trained = local_ed_trained.get_effective_dimension(dataset_size=n)\n", "\n", "print(\n", " \"normalized local effective dimensions for trained QNN: \",\n", - " local_eff_dim_trained / opflow_qnn.num_weights,\n", + " local_eff_dim_trained / estimator_qnn.num_weights,\n", ")" ] }, @@ -642,22 +645,22 @@ "name": "stdout", "output_type": "stream", "text": [ - "normalized local effective dimensions for untrained QNN: [0.80896667 0.81612261 0.81966781 0.84219603 0.84864578 0.85651291\n", - " 0.86249025 0.86656428 0.8785217 0.88651616]\n" + "normalized local effective dimensions for untrained QNN: [0.71325369 0.72910428 0.7365995 0.77956818 0.79050175 0.80314811\n", + " 0.81232955 0.81841244 0.83564327 0.84679919]\n" ] } ], "source": [ "# get Local Effective Dimension for set of untrained weights\n", "local_ed_untrained = LocalEffectiveDimension(\n", - " qnn=opflow_qnn, weight_samples=initial_point, input_samples=X\n", + " qnn=estimator_qnn, weight_samples=initial_point, input_samples=X\n", ")\n", "\n", "local_eff_dim_untrained = local_ed_untrained.get_effective_dimension(dataset_size=n)\n", "\n", "print(\n", " \"normalized local effective dimensions for untrained QNN: \",\n", - " local_eff_dim_untrained / opflow_qnn.num_weights,\n", + " local_eff_dim_untrained / estimator_qnn.num_weights,\n", ")" ] }, @@ -682,13 +685,13 @@ "name": "#%%\n" }, "tags": [ - "\"nbsphinx-thumbnail\"" + "nbsphinx-thumbnail" ] }, "outputs": [ { "data": { - "image/png": "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\n", + "image/png": "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\n", "text/plain": [ "
" ] @@ -701,8 +704,10 @@ ], "source": [ "# plot the normalized effective dimension for the model\n", - "plt.plot(n, np.array(local_eff_dim_trained) / opflow_qnn.num_weights, label=\"trained weights\")\n", - "plt.plot(n, np.array(local_eff_dim_untrained) / opflow_qnn.num_weights, label=\"untrained weights\")\n", + "plt.plot(n, np.array(local_eff_dim_trained) / estimator_qnn.num_weights, label=\"trained weights\")\n", + "plt.plot(\n", + " n, np.array(local_eff_dim_untrained) / estimator_qnn.num_weights, label=\"untrained weights\"\n", + ")\n", "\n", "plt.xlabel(\"Number of data\")\n", "plt.ylabel(\"Normalized LOCAL effective dimension\")\n", @@ -733,7 +738,7 @@ { "data": { "text/html": [ - "

Version Information

Qiskit SoftwareVersion
qiskit-terra0.22.0.dev0+4749eb5
qiskit-aer0.11.0
qiskit-nature0.5.0
qiskit-finance0.4.0
qiskit-optimization0.5.0
qiskit-machine-learning0.5.0
System information
Python version3.8.13
Python compilerClang 12.0.0
Python builddefault, Mar 28 2022 06:16:26
OSDarwin
CPUs2
Memory (Gb)12.0
Thu Sep 15 14:10:26 2022 EDT
" + "

Version Information

Qiskit SoftwareVersion
qiskit-terra0.22.0
qiskit-aer0.11.1
qiskit-ignis0.7.0
qiskit0.33.0
qiskit-machine-learning0.5.0
System information
Python version3.7.9
Python compilerMSC v.1916 64 bit (AMD64)
Python builddefault, Aug 31 2020 17:10:11
OSWindows
CPUs4
Memory (Gb)31.837730407714844
Tue Nov 01 20:30:49 2022 GMT Standard Time
" ], "text/plain": [ "" @@ -780,7 +785,7 @@ "name": "python", "nbconvert_exporter": "python", "pygments_lexer": "ipython3", - "version": "3.8.13" + "version": "3.7.9" } }, "nbformat": 4, diff --git a/qiskit_machine_learning/neural_networks/effective_dimension.py b/qiskit_machine_learning/neural_networks/effective_dimension.py index 584878447..29a3fd70a 100644 --- a/qiskit_machine_learning/neural_networks/effective_dimension.py +++ b/qiskit_machine_learning/neural_networks/effective_dimension.py @@ -20,7 +20,7 @@ from qiskit.utils import algorithm_globals from qiskit_machine_learning import QiskitMachineLearningError - +from .estimator_qnn import EstimatorQNN from .opflow_qnn import OpflowQNN from .neural_network import NeuralNetwork @@ -173,8 +173,9 @@ def run_monte_carlo(self) -> Tuple[np.ndarray, np.ndarray]: grads[self._num_input_samples * i : self._num_input_samples * (i + 1)] = backward_pass outputs[self._num_input_samples * i : self._num_input_samples * (i + 1)] = forward_pass - # post-processing in the case of OpflowQNN output, to match the CircuitQNN output format - if isinstance(self._model, OpflowQNN): + # post-processing in the case of OpflowQNN and EstimatorQNN output, to match + # the CircuitQNN output format + if isinstance(self._model, (OpflowQNN, EstimatorQNN)): grads = np.concatenate([grads / 2, -1 * grads / 2], 1) outputs = np.concatenate([(outputs + 1) / 2, (1 - outputs) / 2], 1) diff --git a/test/neural_networks/test_effective_dimension_primitives.py b/test/neural_networks/test_effective_dimension_primitives.py new file mode 100644 index 000000000..0035dbc80 --- /dev/null +++ b/test/neural_networks/test_effective_dimension_primitives.py @@ -0,0 +1,230 @@ +# This code is part of Qiskit. +# +# (C) Copyright IBM 2022. +# +# This code is licensed under the Apache License, Version 2.0. You may +# obtain a copy of this license in the LICENSE.txt file in the root directory +# of this source tree or at http://www.apache.org/licenses/LICENSE-2.0. +# +# Any modifications or derivative works of this code must retain this +# copyright notice, and modified files need to carry a notice indicating +# that they have been altered from the originals. +""" Unit Tests for Effective Dimension Algorithm """ + +import unittest + +from test import QiskitMachineLearningTestCase + +import numpy as np +from ddt import ddt, data, unpack + +from qiskit.circuit import QuantumCircuit +from qiskit.circuit.library import ZFeatureMap, RealAmplitudes +from qiskit.utils import algorithm_globals + +from qiskit_machine_learning.neural_networks import ( + EffectiveDimension, + LocalEffectiveDimension, + EstimatorQNN, + SamplerQNN, +) +from qiskit_machine_learning import QiskitMachineLearningError + + +@ddt +class TestEffectiveDimension(QiskitMachineLearningTestCase): + """Test the Effective Dimension algorithm""" + + def setUp(self): + super().setUp() + + algorithm_globals.random_seed = 1234 + + # set up quantum neural networks + num_qubits = 3 + feature_map = ZFeatureMap(feature_dimension=num_qubits, reps=1) + ansatz = RealAmplitudes(num_qubits, reps=1) + + # CircuitQNNs + qc = QuantumCircuit(num_qubits) + qc.append(feature_map, range(num_qubits)) + qc.append(ansatz, range(num_qubits)) + + def parity(x): + return f"{x:b}".count("1") % 2 + + sampler_qnn_1 = SamplerQNN( + circuit=qc, + input_params=feature_map.parameters, + weight_params=ansatz.parameters, + interpret=parity, + output_shape=2, + ) + + sampler_qnn_2 = SamplerQNN( + circuit=qc, + input_params=feature_map.parameters, + weight_params=ansatz.parameters, + ) + + # EstimatorQNN + estimator_qnn = EstimatorQNN( + circuit=qc, + input_params=feature_map.parameters, + weight_params=ansatz.parameters, + ) + + self.qnns = { + "sampler_qnn_1": sampler_qnn_1, + "sampler_qnn_2": sampler_qnn_2, + "estimator_qnn": estimator_qnn, + } + + # define sample numbers + self.n_list = [5000, 8000, 10000, 40000, 60000, 100000, 150000, 200000, 500000, 1000000] + self.n = 5000 + + @data( + # qnn_name, num_inputs, num_weights, result + ("sampler_qnn_1", 10, 10, 4.51202148), + ("sampler_qnn_1", 1, 1, 1.39529449), + ("sampler_qnn_1", 10, 1, 3.97371533), + ("sampler_qnn_2", 10, 10, 5.90859124), + ) + @unpack + def test_alg_results(self, qnn_name, num_inputs, num_params, result): + """Test that the algorithm results match the original code's.""" + qnn = self.qnns[qnn_name] + global_ed = EffectiveDimension(qnn=qnn, weight_samples=num_params, input_samples=num_inputs) + + effdim = global_ed.get_effective_dimension(self.n) + + self.assertAlmostEqual(effdim, result, 5) + + def test_qnn_type(self): + """Test that the results are equivalent for opflow and circuit qnn.""" + + num_input_samples, num_weight_samples = 1, 1 + qnn1 = self.qnns["sampler_qnn_1"] + qnn2 = self.qnns["estimator_qnn"] + + global_ed1 = EffectiveDimension( + qnn=qnn1, + weight_samples=num_weight_samples, + input_samples=num_input_samples, + ) + + global_ed2 = EffectiveDimension( + qnn=qnn2, + weight_samples=num_weight_samples, + input_samples=num_input_samples, + ) + + effdim1 = global_ed1.get_effective_dimension(self.n) + effdim2 = global_ed2.get_effective_dimension(self.n) + + self.assertAlmostEqual(effdim1, 1.395, 3) + self.assertAlmostEqual(effdim1, effdim2, 5) + + def test_multiple_data(self): + """Test results for a list of sampling sizes.""" + + num_input_samples, num_weight_samples = 10, 10 + qnn = self.qnns["sampler_qnn_1"] + + global_ed1 = EffectiveDimension( + qnn=qnn, + weight_samples=num_weight_samples, + input_samples=num_input_samples, + ) + + effdim1 = global_ed1.get_effective_dimension(self.n_list) + effdim2 = global_ed1.get_effective_dimension(np.asarray(self.n_list)) + + np.testing.assert_array_equal(effdim1, effdim2) + + def test_inputs(self): + """Test results for different input combinations.""" + + qnn = self.qnns["sampler_qnn_1"] + + num_input_samples, num_weight_samples = 10, 10 + inputs = algorithm_globals.random.uniform(0, 1, size=(num_input_samples, qnn.num_inputs)) + weights = algorithm_globals.random.uniform(0, 1, size=(num_weight_samples, qnn.num_weights)) + + global_ed1 = EffectiveDimension( + qnn=qnn, + weight_samples=num_weight_samples, + input_samples=num_input_samples, + ) + + global_ed2 = EffectiveDimension( + qnn=qnn, + weight_samples=weights, + input_samples=inputs, + ) + + effdim1 = global_ed1.get_effective_dimension(self.n_list) + effdim2 = global_ed2.get_effective_dimension(self.n_list) + + np.testing.assert_array_almost_equal(effdim1, effdim2, 0.2) + + def test_inputs_shapes(self): + """Test results for different input combinations.""" + + qnn = self.qnns["sampler_qnn_1"] + + num_inputs, num_params = 10, 10 + inputs_ok = algorithm_globals.random.uniform(0, 1, size=(num_inputs, qnn.num_inputs)) + weights_ok = algorithm_globals.random.uniform(0, 1, size=(num_params, qnn.num_weights)) + + inputs_wrong = algorithm_globals.random.uniform(0, 1, size=(num_inputs, 1)) + weights_wrong = algorithm_globals.random.uniform(0, 1, size=(num_params, 1)) + + with self.assertRaises(QiskitMachineLearningError): + EffectiveDimension( + qnn=qnn, + weight_samples=weights_ok, + input_samples=inputs_wrong, + ) + + with self.assertRaises(QiskitMachineLearningError): + EffectiveDimension( + qnn=qnn, + weight_samples=weights_wrong, + input_samples=inputs_ok, + ) + + def test_local_ed_params(self): + """Test that QiskitMachineLearningError is raised for wrong parameters sizes.""" + + qnn = self.qnns["sampler_qnn_1"] + + num_inputs, num_params = 10, 10 + inputs_ok = algorithm_globals.random.uniform(0, 1, size=(num_inputs, qnn.num_inputs)) + weights_ok = algorithm_globals.random.uniform(0, 1, size=(1, qnn.num_weights)) + weights_ok2 = algorithm_globals.random.uniform(0, 1, size=(qnn.num_weights)) + weights_wrong = algorithm_globals.random.uniform(0, 1, size=(num_params, qnn.num_weights)) + + LocalEffectiveDimension( + qnn=qnn, + weight_samples=weights_ok, + input_samples=inputs_ok, + ) + + LocalEffectiveDimension( + qnn=qnn, + weight_samples=weights_ok2, + input_samples=inputs_ok, + ) + + with self.assertRaises(QiskitMachineLearningError): + LocalEffectiveDimension( + qnn=qnn, + weight_samples=weights_wrong, + input_samples=inputs_ok, + ) + + +if __name__ == "__main__": + unittest.main()