Files
ArtStudies/M2/Deep Learning/TP1 - Starter.ipynb

857 lines
413 KiB
Plaintext

{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Séance 1 - Réseau de neurones dense\n",
"\n",
"On se propose de classifier les chiffres manuscrit du dataset [MNIST](https://yann.lecun.com/exdb/mnist/) en définissant ses propres réseaux de neurones denses. L'objectif est de découvrir la manière d'entraîner ces algorithmes et observer en pratique les bases théoriques discutées en cours.\n",
"\n",
"## Exploration des données\n",
"\n",
"Commençons par importer les données."
]
},
{
"cell_type": "code",
"execution_count": 1,
"metadata": {},
"outputs": [],
"source": [
"import numpy as np\n",
"import pandas as pd\n",
"\n",
"%matplotlib inline\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"sns.set(style='whitegrid')\n",
"\n",
"import tensorflow as tf\n",
"from tensorflow import keras\n",
"\n",
"(X_train_full, y_train_full), (X_test, y_test) = (keras.datasets.mnist.load_data())"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne** : À l'aide de la fonction [`train_test_split`](https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.train_test_split.html), séparer le jeu d'entraînement complet en un dataset d'entraînement et un dataset de validation. Afficher les tailles des datasets respectifs."
]
},
{
"cell_type": "code",
"execution_count": 2,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(48000, 28, 28) (48000,)\n",
"(12000, 28, 28) (12000,)\n"
]
}
],
"source": [
"from sklearn.model_selection import train_test_split\n",
"\n",
"X_train, X_valid, y_train, y_valid = train_test_split(X_train_full, y_train_full, test_size=0.2, random_state=42)\n",
"print(X_train.shape, y_train.shape)\n",
"print(X_valid.shape, y_valid.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne** : Afficher plusieurs images du dataset d'entraînement aléatoirement. On pourra utiliser la fonction [`imshow`](https://matplotlib.org/stable/api/_as_gen/matplotlib.pyplot.imshow.html)."
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1000x1000 with 25 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plt.figure(figsize=(10,10))\n",
"for i in range(25):\n",
" plt.subplot(5,5,i+1)\n",
" plt.xticks([])\n",
" plt.yticks([])\n",
" plt.grid(False)\n",
" plt.imshow(X_train[i], cmap=plt.cm.binary)\n",
" plt.xlabel(y_train[i])\n",
"plt.show()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Les images sont en niveau de gris, donc de valeurs entre 0 et 255. Pour entraîner correctement un réseau de neurones, il est préférable que les inputs soit standardisés.\n",
"\n",
"**Consigne** : Standardiser les données en utilisant la classe [`StandardScaler`](https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html). On commencera par applatir les images en utilisant la méthode [`reshape`](https://numpy.org/doc/stable/reference/generated/numpy.reshape.html), puis on applique le pré-processing et on termine par reformer la matrice."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"scaler = StandardScaler()\n",
"X_train_flat = X_train.reshape(X_train.shape[0], -1).astype(np.float32)\n",
"X_valid_flat = X_valid.reshape(X_valid.shape[0], -1).astype(np.float32)\n",
"X_test_flat = X_test.reshape(X_test.shape[0], -1).astype(np.float32)\n",
"\n",
"X_train = scaler.fit_transform(X_train_flat).reshape(X_train.shape)\n",
"X_valid = scaler.transform(X_valid_flat).reshape(X_valid.shape)\n",
"X_test = scaler.transform(X_test_flat).reshape(X_test.shape)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Modélisation du réseau de neurones\n",
"\n",
"Pour le moment, nous travaillons avec des images de tailles $28\\times28$, mais nous ne savons pas définir (pour le moment) de réseau de neurones capable de travailler directement avec une image. Nous allons utiliser une couche nommée [`Flatten`](https://keras.io/api/layers/reshaping_layers/flatten/) dont le but est *d'applatir* une matrice de dimension *(height, width, channel)* en un vecteur de taille *height $\\times$ width $\\times$ channel*. Dans le cadre des données MNIST, *channel*=1 puisque nous sommes en niveau de gris, et *height=width=28*. On aura un vecteur de 784 dimensions.\n",
"\n",
"Une fois que nous aurons décrit l'ensemble du réseau, nous devrons terminer le réseau par une couche avec dix neurones : un pour chaque classe. Pour s'assurer que l'on aura une estimation de probabilité d'appartenance à la classe, on utilisera la fonction softmax. Pour un vecteur $x = (x_0, x_1, \\ldots, x_n)$ on a:\n",
"\n",
"$$\\text{softmax}(x)_j = \\frac{e^{x_j}}{\\displaystyle \\sum_{i=0}^n e^{x_i}}$$\n",
"\n",
"On veut définir le réseau suivant:\n",
"* **Couche cachée 1** : 256 neurones avec fonction d'activation ReLU\n",
"* **Couche cachée 2** : 128 neurones avec fonction d'activation ReLU\n",
"\n",
"On peut définir de plusieurs manières un réseau de neurones. La première est de la même manière qu'une liste à laquelle on ajoute des couches en utilisation le template de modèle *Sequential* :"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"model = keras.models.Sequential()\n",
"model.add(keras.layers.Input(shape=[28, 28]))\n",
"model.add(keras.layers.Flatten())\n",
"model.add(keras.layers.Dense(256, activation=\"relu\"))\n",
"model.add(keras.layers.Dense(128, activation=\"relu\"))\n",
"model.add(keras.layers.Dense(10, activation=\"softmax\"))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"En début de réseau de neurones on doit définir la dimension de l'input: ici (28, 28). Le reste des dimensions pour l'ensemble des couches qui lui succède sont calculées automatiquement.\n",
"\n",
"La deuxième manière est directement sous le format d'une liste:"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [],
"source": [
"model = keras.models.Sequential([\n",
" keras.layers.Input(shape=[28, 28]),\n",
" keras.layers.Flatten(),\n",
" keras.layers.Dense(256, activation=\"relu\"),\n",
" keras.layers.Dense(128, activation=\"relu\"),\n",
" keras.layers.Dense(10, activation=\"softmax\")\n",
"])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne** : Calculer à la main le nombre de neurones du modèle, couche par couche. Puis utiliser la méthode [`summary`](https://keras.io/api/models/model/#summary-method) pour vérifier les calculs."
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"784\n",
"256\n",
"128\n",
"10\n",
"235146\n"
]
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_7\"</span>\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1mModel: \"sequential_7\"\u001b[0m\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃<span style=\"font-weight: bold\"> Layer (type) </span>┃<span style=\"font-weight: bold\"> Output Shape </span>┃<span style=\"font-weight: bold\"> Param # </span>┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ flatten_7 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">784</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_21 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">200,960</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_22 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">32,896</span> │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_23 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>) │ <span style=\"color: #00af00; text-decoration-color: #00af00\">1,290</span> │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
"</pre>\n"
],
"text/plain": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
"┃\u001b[1m \u001b[0m\u001b[1mLayer (type) \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
"│ flatten_7 (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m784\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_21 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m200,960\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_22 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m32,896\u001b[0m │\n",
"├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
"│ dense_23 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n",
"└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">235,148</span> (918.55 KB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m235,148\u001b[0m (918.55 KB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">235,146</span> (918.54 KB)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m235,146\u001b[0m (918.54 KB)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2</span> (12.00 B)\n",
"</pre>\n"
],
"text/plain": [
"\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m2\u001b[0m (12.00 B)\n"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"print(28*28)\n",
"print(256)\n",
"print(128)\n",
"print(10)\n",
"\n",
"print(28 * 28 * 256 + 256 + 256 * 128 + 128 + 128 * 10 + 10)\n",
"\n",
"model.summary()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Nous avons décrit l'architecture du réseau de neurones. Il faut maintenant définir comment il va s'entraîner. Nous devons spécifier:\n",
"\n",
"* **Loss** : Quelle fonction de perte est à minimiser ?\n",
"* **Optimizer** Quel schéma de descente de gradient est à utiliser ?\n",
"* **Metrics** : Quelles métrique de performance souhaite-on observer pendant l'entraînement ?\n",
"\n",
"Puisque nous travaillons sur un problème de classification avec plusieurs classes, la fonction de perte [`sparse_categorical_crossentropy`](https://keras.io/api/losses/probabilistic_losses/#sparsecategoricalcrossentropy-class) est celle qu'il nous faut.\n",
"\n",
"Concernant l'*optimizer* il y a plusieurs possibilités que nous verrons dans une prochaine séance. Pour le moment nous travaillerons avec une descente de gradient stochastique par mini-batch [`SGD`](https://keras.io/api/optimizers/sgd/). Pour la définir, nous devons statuer sur:\n",
"* **Learning rate** : pas de descente, on décide de choisir la valeur 0.001\n",
"* **Batch size** : nombre d'observations à considérer pour chacune des passes. On décide de prendre 32 images par batch. Cette valeur sera à renseigner un peu plus tard.\n",
"\n",
"Pour les métriques, nous suivrons l'accuracy parce que la distribution des catégories à prédire n'est pas déséquilibrées."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"model.compile(\n",
" loss=\"sparse_categorical_crossentropy\",\n",
" optimizer=keras.optimizers.SGD(learning_rate=1e-3),\n",
" metrics=[\"accuracy\"],\n",
")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Entraînement\n",
"\n",
"Le modèle est maintenant prêt à être entraîné, il nous reste à lui indiquer:\n",
"* **Données** : jeu d'entraînement et jeu de validation\n",
"* **Époques** : le nombre de passes à réaliser sur l'ensemble du dataset\n",
"* **Batch size** : le nombre d'observations pour chaque batch, nous avions décidé juste avant que ce serait 32"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Epoch 1/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.6647 - loss: 1.2506 - val_accuracy: 0.8190 - val_loss: 0.7401\n",
"Epoch 2/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.8510 - loss: 0.5738 - val_accuracy: 0.8694 - val_loss: 0.4969\n",
"Epoch 3/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 933us/step - accuracy: 0.8832 - loss: 0.4251 - val_accuracy: 0.8906 - val_loss: 0.4074\n",
"Epoch 4/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 876us/step - accuracy: 0.8994 - loss: 0.3570 - val_accuracy: 0.9022 - val_loss: 0.3593\n",
"Epoch 5/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 902us/step - accuracy: 0.9094 - loss: 0.3155 - val_accuracy: 0.9109 - val_loss: 0.3273\n"
]
}
],
"source": [
"epochs = 5\n",
"batch_size = 32\n",
"\n",
"history = model.fit(\n",
" X_train,\n",
" y_train,\n",
" epochs=epochs,\n",
" batch_size=batch_size,\n",
" validation_data=(X_valid, y_valid),\n",
")\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Nous avons des informations disponible dans l'objet *history*, plus précisement dans *history.history*\n",
"\n",
"**Consigne** : Créer un [`DataFrame`](https://pandas.pydata.org/docs/reference/api/pandas.DataFrame.html) à partir de *history.history* puis inspecter-le."
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" accuracy loss val_accuracy val_loss\n",
"0 0.664708 1.250604 0.819000 0.740149\n",
"1 0.850958 0.573769 0.869417 0.496933\n",
"2 0.883250 0.425121 0.890583 0.407437\n",
"3 0.899417 0.356979 0.902250 0.359335\n",
"4 0.909437 0.315463 0.910917 0.327325\n"
]
}
],
"source": [
"history_df = pd.DataFrame(history.history)\n",
"\n",
"print(history_df)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne**: Définir une fonction `plot_learning_curves` qui prend en paramètre l'objet *history* et qui renvoie un graphique. Le graphique correspondra à deux graphiques côte à côte :\n",
"1. Le premier montre l'évolution de la fonction de perte en fonction des époques\n",
"2. Le second montre l'évolution de l'accuracy en fonction des époques\n",
"Dans les deux cas, les valeurs de performance sur le dataset de validation doivent être en pointillé. "
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"def plot_learning_curves(history_df: pd.DataFrame) -> None:\n",
" plt.figure(figsize=(12, 4))\n",
"\n",
" plt.subplot(1, 2, 1)\n",
" plt.plot(history_df['loss'], label='Training Loss')\n",
" plt.plot(history_df[\"val_loss\"], label=\"Validation Loss\")\n",
" plt.xlabel(\"Epochs\")\n",
" plt.ylabel(\"Loss\")\n",
" plt.legend()\n",
"\n",
" plt.subplot(1, 2, 2)\n",
" plt.plot(history_df['accuracy'], label='Accuracy')\n",
" plt.plot(history_df[\"val_accuracy\"], label=\"Validation Accuracy\")\n",
" plt.xlabel('Epochs')\n",
" plt.ylabel('Accuracy')\n",
" plt.legend()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne** : Exploiter la fonction précédente pour observer les courbes d'apprentissage du l'entraînement précédent."
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1200x400 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"plot_learning_curves(history_df)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Exploitation des prédictions\n",
"\n",
"On souhaite à présent utiliser le modèle pour prédire le chiffre présent dans une image.\n",
"\n",
"**Consigne** : Prédire sur le jeu de test à l'aide de la méthode [`predict`](https://keras.io/api/models/model_training_apis/#predict-method), puis observer le résultat sur la première image."
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\u001b[1m313/313\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 423us/step\n",
"[4.4860026e-05 4.9483305e-07 9.9898905e-01 6.3612009e-04 3.7012711e-09\n",
" 1.5404350e-05 1.0145640e-04 2.5940048e-07 2.1230943e-04 6.7945258e-09]\n",
"2\n",
"2\n"
]
}
],
"source": [
"predictions = model.predict(X_test)\n",
"\n",
"print(predictions[1])\n",
"print(np.argmax(predictions[1]))\n",
"print(y_test[1])"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne** : Après avoir vérifier que si l'on somme les chiffres affichés pour la première image vaut bien 1, identifier la classe prédite par le modèle. Vérifier visuellement."
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"[1.0000001 0.99999994 0.9999999 ... 1. 1.0000001 1. ]\n"
]
}
],
"source": [
"print(np.sum(predictions, axis=1))"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Quel est l'impact du learning rate ?\n",
"\n",
"On s'intéresse à présent à l'importance du choix du learning rate. On se propose de tester plusieurs valeurs pour obtenir les meilleurs performances.\n",
"\n",
"**Consigne** : Définir une fonction `get_model` qui prend en paramètre un `float` qui correspond à un learning rate. La fonction renvoie un modèle compilé avec les mêmes paramètres que précédemment, sauf la valeur du learning rate qui est renseignée par l'utilisateur."
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"def get_model(learning_rate: float) -> keras.Model:\n",
" model = keras.models.Sequential(\n",
" [\n",
" keras.layers.Input(shape=[28, 28]),\n",
" keras.layers.Flatten(),\n",
" keras.layers.Dense(256, activation=\"relu\"),\n",
" keras.layers.Dense(128, activation=\"relu\"),\n",
" keras.layers.Dense(10, activation=\"softmax\"),\n",
" ]\n",
" )\n",
" model.compile(\n",
" loss=\"sparse_categorical_crossentropy\",\n",
" optimizer=keras.optimizers.SGD(learning_rate=learning_rate),\n",
" metrics=[\"accuracy\"],\n",
" )\n",
"\n",
" return model"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Avant de lancer sur plusieurs époques, commençons par écrire une ébauche de la boucle de comparaison avec 5 époques."
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Learning rate: 0.1 - époques: 5\n",
"Epoch 1/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9270 - loss: 0.2625 - val_accuracy: 0.9582 - val_loss: 0.1941\n",
"Epoch 2/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 906us/step - accuracy: 0.9681 - loss: 0.1153 - val_accuracy: 0.9653 - val_loss: 0.1767\n",
"Epoch 3/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 922us/step - accuracy: 0.9783 - loss: 0.0744 - val_accuracy: 0.9657 - val_loss: 0.1971\n",
"Epoch 4/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 1ms/step - accuracy: 0.9861 - loss: 0.0484 - val_accuracy: 0.9660 - val_loss: 0.2301\n",
"Epoch 5/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 962us/step - accuracy: 0.9909 - loss: 0.0306 - val_accuracy: 0.9718 - val_loss: 0.2162\n",
"Learning rate: 0.01 - époques: 5\n",
"Epoch 1/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 931us/step - accuracy: 0.8757 - loss: 0.4551 - val_accuracy: 0.9313 - val_loss: 0.2545\n",
"Epoch 2/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 874us/step - accuracy: 0.9429 - loss: 0.1966 - val_accuracy: 0.9477 - val_loss: 0.2135\n",
"Epoch 3/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 892us/step - accuracy: 0.9574 - loss: 0.1459 - val_accuracy: 0.9524 - val_loss: 0.1883\n",
"Epoch 4/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 861us/step - accuracy: 0.9661 - loss: 0.1173 - val_accuracy: 0.9572 - val_loss: 0.1765\n",
"Epoch 5/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 901us/step - accuracy: 0.9725 - loss: 0.0983 - val_accuracy: 0.9619 - val_loss: 0.1678\n",
"Learning rate: 0.001 - époques: 5\n",
"Epoch 1/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 931us/step - accuracy: 0.6255 - loss: 1.3527 - val_accuracy: 0.8108 - val_loss: 0.7751\n",
"Epoch 2/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 866us/step - accuracy: 0.8473 - loss: 0.5952 - val_accuracy: 0.8724 - val_loss: 0.5039\n",
"Epoch 3/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 962us/step - accuracy: 0.8830 - loss: 0.4305 - val_accuracy: 0.8960 - val_loss: 0.4058\n",
"Epoch 4/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 888us/step - accuracy: 0.9010 - loss: 0.3574 - val_accuracy: 0.9075 - val_loss: 0.3550\n",
"Epoch 5/5\n",
"\u001b[1m1500/1500\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 870us/step - accuracy: 0.9112 - loss: 0.3140 - val_accuracy: 0.9150 - val_loss: 0.3225\n"
]
}
],
"source": [
"n_epochs = 5\n",
"batch_size = 32\n",
"learning_rates = [10 ** (-power) for power in range(1, 4)]\n",
"\n",
"results = []\n",
"for learning_rate in learning_rates:\n",
" print(f\"Learning rate: {learning_rate} - époques: {n_epochs}\")\n",
" model = get_model(learning_rate=learning_rate)\n",
" history = model.fit(\n",
" X_train,\n",
" y_train,\n",
" epochs=n_epochs,\n",
" batch_size=batch_size,\n",
" validation_data=(X_valid, y_valid),\n",
" )\n",
" result = {\n",
" \"learning_rate\": learning_rate,\n",
" \"n_epochs\": n_epochs,\n",
" \"history\": pd.DataFrame(history.history),\n",
" }\n",
" results.append(result)\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne** : Définir une fonction `show_results` qui prend en paramètre l'objet *results* construit précédemment et qui renvoie un graphique similaire à celui renvoyé par `plot_learning_curves`. Cependant, les différentes itérations doivent être présente sur chaque graphique, ici les courbes d'entraînement pour chaque learning rate, avec la bonne légende pour chaque graphique."
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"def show_results(results: list) -> None:\n",
" for _, result in enumerate(results):\n",
" plt.figure(figsize=(12, 4))\n",
" history_df = result[\"history\"]\n",
" learning_rate = result[\"learning_rate\"]\n",
"\n",
" plt.subplot(1, 2, 1)\n",
" plt.plot(\n",
" history_df[\"val_loss\"],\n",
" label=f\"Val Loss (LR={learning_rate})\",\n",
" linestyle=\"--\",\n",
" )\n",
" plt.plot(\n",
" history_df[\"loss\"], label=f\"Train Loss (LR={learning_rate})\", alpha=0.5\n",
" )\n",
" plt.xlabel(\"Epochs\")\n",
" plt.ylabel(\"Loss\")\n",
" plt.legend()\n",
"\n",
" plt.subplot(1, 2, 2)\n",
" plt.plot(\n",
" history_df[\"val_accuracy\"],\n",
" label=f\"Val Accuracy (LR={learning_rate})\",\n",
" linestyle=\"--\",\n",
" )\n",
" plt.plot(\n",
" history_df[\"accuracy\"],\n",
" label=f\"Train Accuracy (LR={learning_rate})\",\n",
" alpha=0.5,\n",
" )\n",
" plt.xlabel(\"Epochs\")\n",
" plt.ylabel(\"Accuracy\")\n",
" plt.legend()\n",
"\n",
" plt.show()\n"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"**Consigne**: Lancer l'entraînement pour plus d'époques afin de comparer avec la fonction `show_results` les différences d'entraînement. Commenter.\n",
"\n",
"Pour gagner du temps, on pourra augmenter le batch_size à 256 voire 528. Pour éviter de surcharger l'affichage, on peut utiliser le paramètre *verbose* de la méthode `fit` : s'il vaut 0 alors il n'y a aucun affichage."
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1200x400 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1200x400 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA/UAAAF3CAYAAADkXGsDAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjEsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvc2/+5QAAAAlwSFlzAAAPYQAAD2EBqD+naQAAvPxJREFUeJzs3QV43FXWBvB3PO5NLXVvqQAVihZnkUUW+JDissACC4uzLLBYcVgcFmdxFl2Ku5aWllKoQ92SNm7j3/PeyX+apEkan8j76zPP+OSfmzQz555zz7WFw+EwRERERERERKTTscf6AERERERERESkeRTUi4iIiIiIiHRSCupFREREREREOikF9SIiIiIiIiKdlIJ6ERERERERkU5KQb2IiIiIiIhIJ6WgXkRERERERKSTcsb6ADqDefPmIRwOw+VyxfpQRERE4Pf7YbPZsOOOO8b6ULoMvdeLiEhnfb9Xpr4R+CbPU2u9ls/na7XX6y40bs2nsWsejVvzaezaftxa831JIvRe3zFo7JpH49Y8Grfm09i1z7g19r1JmfpGsGbtx44d2+LXKi8vx6JFizB06FAkJCS0wtF1Dxq35tPYNY/Grfk0dm0/bgsWLGi34+ou9F7fMWjsmkfj1jwat+bT2LXPuDX2/V6ZehEREREREZFOSkG9iIiIiIiISCeloF5ERERERESkk1JQLyIiIiIiItJJKagXERERERER6aTU/V5E2k0wGDT7bXYGXq83em63a/6zKTR2LR83j8cDh8MR60MSERGRTkBBvYi0Oe6vuXHjRhQWFqKzCIVCcDqdWL9+vQLTJtLYtXzc+P8lLS0NvXr1gs1mi/WhiYiISAemoF5E2pwV0GdnZ5s9OTtDkMKqAmVMm0dj17Jxc7vd5jw3N9fc3rt371gfmoiIiHRgCupFpM0DFSugz8zMRGc6boqLi1Ng2kQau5aPW1JSkrnMwJ7/dzSOIiIiUh/VRYpIm7LW0DNDLyKNZ/2f6Sx9KERERCQ2FNSLSLvoDCX3Ih2J/s+IiIhIY6j8vh2FwyFULp8DR1ExgFGxPhwRERERERF094bOCIcQDgW5Fs6ch4N+IBgw52GeBwIIh3geuQ5eDoUAPpbPC0Wez5PN4UTCsIlwxCW22/egoL4dhSpK4c9bDWd+5+kALiIiIiIi0l6s4DgSYDOADkUCaxM8W0F0tWA6zOC6Kii3gnMTmFuPYXDewGvxPoRb9XsIluQrqO+qbO64yHnVjI+IdB4nnXQSysrK8Prrr9d5/zXXXIPZs2fjgw8+aPB17r//frzxxhv49NNP67z/yiuvxLp16/Dcc8+hIyktLcUxxxyDp556ymyzNmLECMyYMQNHHXVUnY9/5JFH8Nhjj9W4jc3eUlJSsNNOO+Gqq65Cv379mnQM3333He644w789ttvpiP8BRdcgEMOOaTB5zz//PN48sknkZeXhx122MH8nEaPHh29f+3atbjxxhvNz45r2I8++mjzunU1pvvf//6Hu+++u8bPbuHChbj22mvx0ksvme3oREREugOTpQ76EaosQyDkM5drZLV5uVoQXT2TbQXTkdsj59HsNy8zc96sgwojFAYCwRBCoTCCIV4Pm8suhx0J8S7zMF7fuKXMPC4Y5OMi57weCIWRmpyAwf0zTcY9bHfi0x/XI2BzIBi2Ixh2wA87AiEb/CEgp1cqDthlMGx2B2wOB25+eg4O3GMEpmbloD3pE0g7sjlc5peDwr4KACmxPiQRaSQGe5dffrkJKIcMGVLjPm4/9v777+PPf/4zuqrbb78dBx98sAnoG4uPfe2116LX2fBt0aJFJog+55xzTJDc2HXjHHeO72mnnWYC+88//9z8PDIyMjB16tQ6n8PJEx43vx4DeU4y8PnvvfeeeR6P54wzzsDAgQNNUL569Wr8/e9/h91ux4UXXljjtT7++GNcffXVyMrKqnE7X3fo0KF4/PHHzfckIiLSEZkgmqXjpnyc576twbTJXFdls2tc31p+HilF33ryeSsRl5eHspLl8Llc2/niYTaKMReDwRCKS32RgNoE3lZgHbmcluRBVnqkUazXF8T83/IRCNlNAO0P2eALInoaNiADU3boC9gdKK0M4r5XfkIgbEcobEMINgTBINxuzieN6YPph+xggu8Kfwi33vElglWPCVU9hs/habfxfXHlLpOiEwBPvfB2vd/aRE8q/th3WPT6L/kLMDnY/ts3xzyo51ZXzHzwAxozQcz+XHLJJZg4cWKdj587dy7uuecekx1hVmXPPffEZZddhrS0NHP/pk2bzG21NZRRai/84do9kV/SkLc8psciIk1z4IEHmuDwnXfewUUXXbRNwFdRUYEjjjgCXdGqVavw5ptv4quvvmrS8xgc9+jRo8Ztffr0QUlJCa644gosWbIEI0eObNRrPfPMM+b94eKLLzbXObHC9wEG0/UF9awWmD59Ov74xz+a67fccgv2228/vPrqq2aCgFUV69evxyuvvILU1FQMHz4cW7ZsMRMBDNC5Xzzfl2666SYzAcGvyWOv7fTTT8dxxx2HE088EcnJyU0aIxERkbqwpNxav83zaBbbuq0q4K4RbFc9ZuttVUE8TyxRb9HxhKNZ7UCQa9Aj27Da7HZUBOxYtKYEZb4wSivDKPGGUFwZQqU/jAo/sPuEfthn8gCT3NxYUIm73ptbFXA7EISrRvB90G5DcPLUseaxuYWVePC9j+s9pgMHDcC+YyZErpT7sMC3pcb9LqcdLpcdTocdvuQ+cFdlz23BELJz+sDjdsDtcsDDk7vq3OXAkJzU6GvY7TacfPAo2BnH2W1w2CPnfE2+fo/0+Bpf84azp6JXZvvv+BTzoP5vf/ubKYtkYM89rFlyyswJMyyDBw+u8dgVK1aY+/70pz/h+uuvR0FBAf75z3/ir3/9q/nAR4sXL4bH4zEfsqvPkHSUD1o2d+QHH1ZQL4JKb/3LUPgHk39oG/NYm91m/gg357GNxb3DWerN4K52UM+/V3vttZcJYJcuXYq77rrLTEAy0O/Zs6cJ9hj4tZZ58+aZyc1ff/3VlHzvs88+Jmudnp5u7v/5559x6623mqw4799ll11MuTsDamKA/u9//9tkpjkhetBBB5nJUQaxdXn66afNazDwbQ3W13FVzexzacMPP/xQ52PPP/98Uw4/Z84cE5BXx2O6+eabzQeN2jPiDM5XrlxZI+DnWHDCmKX2DOr5mmPGjKnxffE1Gchz7MaPH2/K8zds2GAmAvi+wp91bZwM4Ni+/PLLOPPMM1s4Ot1XKBTCAw88YMaakyeTJk0ySxvqW6bBny8navh/zVo6cd5552kZhIjEDN+PooG0n5lwX1VAXlViHm3AtrXkPJIJrxZ8m8DdFylTb/6BmMy3PxCCw2GDyxn53FNR6cfqvEpUhmyo9NvgDdrgY/Y7xMy3HWOH9cSYodmR4LvQh8f/twiVfqDcDxOcMwsehAMBOPDHPYdg9NAgkkaPQV5RAP9697N6D2dY/CDEDxxjLicmVaA8KRdxbgcSXJGg2u3kud1czunbA3aXxzw2JdGD4/YfYe6rHnSb57gc6JmxNXhOiHPhmesOjN7vdNjqzZYzIL/7or0aPZzH7Du80Y8dMzgTseCMdfbnm2++wQsvvICdd97Z3PaPf/zDZIOYDWOwXh0/iGZnZ5vySOuHdN1115kPzGvWrDFv/PxAzVJKPq4jsnkiDROUqRcBjrn63XrvmziqJ647c5fo9enXv2/KsOqyw5BMzDhv9+j1M27+CMVlvjofO7RfGu5pwh/y6jihyDJtBtU77rijuY2Tkt9++y0efPBBE8QzeN9tt93M47gumwHKbbfdZoLLUaNavusFA3YGwf/3f/9n/v7x699www1mwpNfixiwHnvssebrFhcXm8CIpeMMzjnxyXXld955J8aNG2fK2lkdxQkBBkR1+eSTT1ptaQGz8w899BDGjh2LQYMGRfsM1LcXu7VX+8aNG7cp/effeY45J3hZTl8dH09ce1/7ORyDhl6TGMgzqGclgTVpzKC+PtOmTTPjpKC++fh7wc8DnJDiz4XLLDie/DxQe8KpqKjIvPdz8p8/H/4e8PMDf6YM9EVEmsOs5a6R4fYhVHUeCbirzqvfZs6r3d7IhmthBt1WCXowZIJWK/j2+gIoKPaa0m9/2BZZvx22wxfiyYaBfTPQp1cabHYnNhR48d6sNSj3hc2p1BtGmS9kgvQA7Pi/A0fjoMnDYHO6sHF1EW754Nt6jylhxEBMGjLCXLZtKMbPBWvrfJzbaUfQ5gJske81My0eB+86EOkpcaZ8Pi05ckqMc5nvKzlh699wZrafvvbARo1RvMeJEw9qXEWf3W5DRkqkf1l3FNOgnh8iucaRH+4sDNZ54gfR2lhCuffee9eYdbEu8w2eQT0/MNZe79qR2D3K1It0VgyCmZVlkGEF9W+//bapMuKyH/4dOvnkk02wkZgYmcDj2myWiPNvU2sE9Wz6xjJ0BjDEv3esdDr88MPx9ddfY8KECSbIZXDat29f83fx3nvvNZlrYuaZfzd5H7PLPD3xxBNISkqq8+sxuOWyJn7NpuJzrXEin89nvg4rC1gZwPJ8spZPNaSysnKbwM66ztetjUFe9cdYWMnFHgjWa7JxX+37yXpMYw0bNsxMmjDbbH1f0nj8GfJ3+9JLLzUTJMRqlD322AMffvghDj300BqPZ8VEeXk5/vWvf0UndLhM4oQTTjCTUzk57dugSEQ6cPk6A26/DyF/JcI+L8IBL0K+SoT9XlSWFsO9ZhXKKlbDZ2dFub9JTdoYjFd4A/D5g/D5Q/Ca8yC8gTAqgnYMGdAD2ZkppoHayk3l+GjOWlT4mPkOmww4y82Z/fbDgf87cAT2GDfQ9OD6eUUhbnpvrgnKw9j2PeWs/iMwfFQk3vGt2IIPV+fXeXwMk8ptCdEu7FlpidhtXB8kJbiQFO9CfJxza+bbaceQnK3vxywhv+uve0Yz5HFuZ/QyA2j+DWZVG/G1zv3T+Cb/jKSLBPX8MMWS1eq4xpEZfGaVaqsrWGcJKUterQ+czNRzsoAfqlmuP2DAAJx77rl1rrNvCv4H5y9vS/nCkf+Y3tKiVnm97sL6gG6dS+cZOwZHDHSCwaA5VffSTQfV+zyuXar++Geu3b/ex9pqPfaxq/Zp9GPrY72pR9aQbX08e3NwMpJrwlnmywoiBtTEMm6urWagzzc6lrczmKdAIGBeh2NR+zVrf92G7ufrsRKg+v0MKLnEiBno3Xff3WTtuf6fAQ/Lyfn3jyX2fM6uu+5qAm2WKjPw4XUG2ZxwqOtrMqC3Au/a91s/1/rGjhMLDHStAJ+VA5zsYBUWx8p67tlnn40ff/yxzu+X97FKwArGq3+96oF77eOwgnk+pvp9DOTj4+PNbQ29Jpdb1PX91vez4fiw2oCTJ7WrBhqr9u+c9fvCY+J57ce2dxOetsTfXe4uUX25BD8jsBEhl0vUDur5OYFZ+upjbe1qwGUVCupFug5Tss5SdmbN/V4TjPMUCvCcATsDdT9CNbLpVevNtyPAKrHKUgQq4uDwRN43yir8yCushDdkR2XAhoqgDWU+G8r8MFnwaZMGmWDd5nTjx6Vb8MQnS+GHG352RQ9HStNDVYH4X8fuiKE79jeXvYs24bP3t10eaLdxeZgD/sRsuNIi1WJJaUBOnwyzZtvjqgqm3QysI0H1gN5bJ6RzspNx2fSdTfk5M+MJ8U4keFxIjHeaQJwBuCU7IwFXnhJpALc9fO7w/pFlfdLxdaiFZ1wXx3WfBxxwQHSmviH8gMgGe1yDx7WZ/ND8+++/m07E3BaKGaF3333XfCjkNkz1NVNqDKtrc0vZKorBPNCWjeuwvhVer7vhGkrpfGPH4LepmU+GMJWNeEOmcBs9lmof9/7772/WzPNvDzuhL1u2zDRWY7C4efNmnHLKKSbQ4IQl1wRzzfYf/vAH8zeEj+HfKQZkvFwXK5Cr737ex9eofb8VEPJ2ZiqPPPJIs7xp1qxZJoPJaoEXX3zRBLsPP/ywCaK4RRxP7FDPoIm9SmqzyuIZWNb+mtb3VB9mrNlTgHjOv9XHH3+8CdIZ7FuBN5cD1Pc6DP55H5/PpnbVH8frLM/n3//az7f6C7AygVUJFk4u8OfGx3NCmD+/6s/lUi4rSK/9mg397KzbmHFuaEya8jvHc+t9rS719UDojBpaLmHdV/v23Nxc8//F2n6QW0GSVZUSywn8WE+mdmYau649btwGLWwy5jxVIOSrMOeR8nU2eNu6vjx6udak5tYXi5Sve71B+AIhc5lryK1T3x6JSIx3mW7nG4oCmL+i1GTPywN2lPqrTj4G7VmYfvAITB7dH3C6MOfXLbj/w4X81F7nlx00uQ8GZ/U1nyds6W6UOPNMpjot3mUy4AymeZ2n7DRX9G9K/x5xuP6MiaakPCGOAbfDXGbgbrEem5Plwa3nTmlwLK3HOm3AxBG1J5PDQIjv0Y3/vNNVf+c6mqaOW2Mn8TtMUM+1iiy74/7FXOvZEH6Q5BpRZsiYjbKaJzFw4AdYvsEzy0Lcl5gf2lhe2pKgnh8aOVnQUuVF+di09iekJyUgbeQI2Gwq02wM/uIzKGW/BGbZpPOMHQMTBl/Milr/LzsD/hHlsfO4q/8xZdDBZUBcP83gkIE7S/Ktv2NcOsTt7awmcKwesv4+8fvnOV+vvrHg3y8Gw/XdzzXeXFdf/X4G6NbuIQxan332WTOxyc7vPHHClOf8PeCOI7/88osJ/Fmqz0oma095rmWuzcp4Mota+5j4PdZ1nNYEQ+3vk8E1/2bza3KSgY1SqX//SBajIRxnfh/VX4/X+Z5hrbuvjssKuGZ//vz50YowBsjsh8CJBb7OlClTTOND3m4tP/jpp59MNQGXWtQOmhv62bGxGx/flC3/GvM7x6/J8bGWBViWL1+OrqSh5RJc1lIbJ8q4Bp872/D3iB9uOXnF8aqvP0N7TuBbNBHdfBq7TjRu/JsfCsAW8MFmmsBFzm08rwrOI5e9kfsbKG/nPeys7g9ETj5zOQRfACgP2tEvOxGJSXEIO5xYsiGI75dXwg9nVZbcZbLkVrb88F17YESvJHbIxc/55Xh9bd0l6vT75kqkropMDJaVeDGwZxzi3XbEuW3mPMFjN+fxHgfiQ/lYtCiyTNgdDuPKo2tORm4VgL9kPRYtWl/jVv6560phsP6vtv24NWYSv0ME9f/5z39MB2OWhzL73tCB84MruyGzvI7rSPnGXp21jrU6lqZyrWlL8ANWXR8cm8psJ2GzmTKbeIcN9rj23/KgM2NQ2ho/h+4oVmPHAJUnBqtWRq0zsEqs+X+/9nEfc8wxZhKS5cHszG7dz0CSwclHH31kmn8yw8qggxg4WgF7Xa9p4X0MYphlr23y5MmmER/XDbMZGM9ZHWDtw86yfP6NnDlzpgkOWaXEr/fWW2+ZjDf/FnJCgMEQy/X33Xdf87W+/PJLU5Jf1zFxEoMnThywlL92YFn7OJnhZnWCpfZrstSf/VGYqeduAlbJ9PawVwGrD7jOmudffPGFWa7FyQHra3DCwjoG4ljxvYUTWuzdwokLjgubCPI5rAq77777TKNA/jyZ1Wf/AT6vrgmwhn52HB9OBLTkd7z275z1+8JjqT2R0JVK78n6/ljpUP175c+rrp8Ff6ZcXsIJ/ueff978beP/Rf5OtmS3m9aawI/1ZGpnprHrOONm1qSztJ3r0P3MqHMdemXVevSqbLu1Tr2u7dL459DB9z+gvNIOL9yoDDng9YdQFnSiLOBAsc+ByeP7o1d2Omcx8d3CLXjti9VmjXmgKji31pwzc37JHuMxbnSkRD1vwUYsXbzAZLuTE1wm4GYGPMHjNLeNGdMfw/pFdjfJ7FWBXr0KzO3MkMcxOHc7gbAfuRvXY+SwQUhMjHxGYvubA1u2ardb0P/V9hm3xk7ixzyoZ6dbfiBlN+fqXe3rwjd7lm1yFp2Zd2ZZqmNGnh2hWVpa/T5mpVrjTbo1MDMfdnqiHfDtVY0rRKTz4Lp1BhEMIrl/vYUTk9xmjhlvBtfMTHMCgFn9BQsWmAxxYzC7f9ZZZ21zO1+HHdkZyDL4POKII0yGmdVKDEwZkLDsnL1GuESAwSsDRWbkuQSJj+Uaega6bErGAJkBFDPZzOzXh8H/999/j1NPPbXG7XxNnmpPPFjr6OvDnimcaGXZPTv2NyYQ5oQEJyPYEZ3dzllBwMvVK7AY1BG3RiV+/8ygc6z4s2LlFo/XWofNLDDHkluj8rGc+LAarTUVq8Q42SDNY5Xds6S+euUGr9fXpJETRDzxMZzI4cQZ/+/VtwVee07gWzQR3Xwau7YdN65T5+fQUGVZ5NycIoE7S+JN4M5TVSd3dmpnNbr1Ob20zIfNheXw+rY2hysP2FDG0nafHXtPHYp+fbJgc3vw7aJ8PP/1SnjD8agMu+Az4cfWz/tD9xiJkcMjW64mFa9DbqgIiXFOpCR5kJroRmpVN/X05DgM6psR/f723HkAdt9pQKO2qR2YkICBfbfdaoxVPqUFG01Ar9+35tH/1bYdt8ZO4tvCTWnx2MrYyO6www4z6+e5NVN1/KBpld3xgxaz99z2iNtG8cMqPzhWx8ew7I4fzDgDwg9p/HD7yiuvmImD//73v9ES2abih3Gq3qW/ufjH47ePXkZ2kgvpY/eAO3tAi1+zO7A6bLKZl/5wdK6x4/pi/l9nKXRnKr9nMMxj5zF3pgqDtsCKAzYD/PTTT8069O3pbmPH9whOeHDSpTGd/Bs7bg3932nN96WOgJP2nKDh5BInwohLWdj9nlUprOqojtV6zNRzksbal55L8vjez21x69vNoT3f6/We1Twau5aPG4MF00guGqzXDN69pSUoLy0zXdvTkz1wVQXFGzaX4vd1RfD7rfXpDNbDkUA94MDh+47BgH49YHfH4bvFBXj+EwbqLnjhhDfsrNGl/apTJmHXcZFA/ev56/DQa/PNnuOpSZEgPaUqWGfQzi1s+/SI/J9lqT1VX2feXuOm37em0di1z7g19r0pppl6lk5y/RpLVXmqjhkPnlhyyfWh1tpHzkFY6zCrsx7DtaEM+i+66CLzgYClnXzTb25A3xbCLmbqQwhWlsX6UEREtotdxtlIj0ulLr744lgfTofDyoTTTjutRQF9d8eJe/Z9YE8dVlKwyoWVGOxRwGUSnPDIz883pfWc4ODvJHeC4JI9fk7gZa6pZzVfcwJ6kc4mHAyYQD1YUYJQRSkqCzfDvW45yipXozIUYGrdPG7TljKs2lCM0go/yisDqPAFEAhG7guG7dh/95HIye4BuycReSWFmLlmTSRQDzNQj2TVw1VZ9T17TMDoqox6pi8P/da4kJzoRkqCG0kJPGejOLfZk3xw30jZO+0+vq85NUZ7BfMiXU1Mg/pzzjnHnBpibQdlTQJsDxtXWWtYO6pI+X2FmS0VEekMmEFlJRS37Kvdobw743ILZtPrajIoTXPhhReaEnprNwQ2R+RSOy4rYb8DLgPh+zu3lWTgz0l8jjsnnFhBwn47tZeIiHRWkfJ4lsGXI8xzb7lJBoUqShCsKEVFSQlKyrwoLvOhpNyHwhIvikor4PWvxrSd+6FHeoLJqBcGw/hmTQkqw4moCLlREXabEni4E5CcnIA9h4xH8vDIGvVBycU4OGVIZF06t0fj1mjcIi3OabZKY8BuGT+8hzmJSMcQ8zX13VHYGQeEFdSLSOfBJU6NmVjtbtgU8PXXX4/1YXQJXHJw2WWXmVNt7KFQfZKfuPMBl9iJdEasPGWJfLCiGKHyEgTLixGqLI0E8iyT93tNl3iWyBeWes168jhP5GP78jWFmL1oo2kkVxb2oDzkQVk4GRXhTFSEXRjeY2cM32W42cqtz4ZijEndgJ4ZCeiRFo+MlDikp8SZhnG1ce/z6vufi0jnoaA+VuX3PiBUqaBeREREpKtiV/hQRVmN4N26HAr4oo9jSXxRidcE8IVV5wUlPhT6HKgMu3HA7r0wflh/2OOS4E724tO5vyA1PRl9eySjX48k9Ehzw1+2BRMnDEf/3pmw2SNl7ArURboHBfWxKr9nUO8tMzO1XW1rIhEREZHuJBzwRwL2akG7td6dPSHKKv0oK+e6dj/KKgPmvH+vFOTkZMOekIL1+SE8/PVvqAgnoDKcakrkuY2b3WZD3+wkVPQajviBkZ0dxmSF8PyMoYjjlmw1mm+VoXdmotali3RDCupjwNrSjk1OwgEfbKZxnoiIiIh0ZPzsFjQZ9yIEy4rMeai8GN6yEpNp97gd0bXn+UUV+Hr+epRUBlEaikOZKZP3oDScZC4fNmgsxkweYx6bkVeK0s8qMaBXJLM+qE+KudyvZzLctbZsY9DuqtZpXkREQX0s2B2wV3XAN3vVK6gXERER6VDCQT+CpYUIlOQjUJqPYEmBybwHgkFTIp9fXBk5FVWiqMxrsutjRw/EbkOGwp6QjPJKB979Yq653e1ymnXt2enxGJIWjx7p8Rg3ZGujOW7p9sx1B8X0+xWRzktBfYzY3PGAL7JnKJLSY304IiIiIt2627wVwAdL8xFgAF9ebAJ4rnf3VJW6l5T58OY3q1ESjENJOA6loWSUhHuYTHxiciJyeg5GwrDINsq9giHceH46emYmIC3Jo+WWItJmFNTHiM2TEAnqtVe9iIiISLs2rwuWFSMYzcDnI1hWaNa+F5X4sKW4EgXFleZ8U0kIfQfk4LADd4AzKR3J8an48vNPkBDnxtB+aRiXk4ahOanmcmZqfI2v43TYMXJgRsy+TxHpPhTUx4jdk4BwCZvlqQO+SGfZp/2NN95o8DG1t9xqrJNOOgl9+/Zt9l7n999/vzm2Tz/9FB0J9xz/v//7P1x//fXYYYcdsM8+++DII4/EBRdcUOfjuTXcVVddVeM2u92OpKQk83xudTZ69OgmHcOiRYtw880345dffjF7m3Mf85NPPrnB57z33ntmTLk3+uDBg3HFFVdg6tSp0fsLCgpw00034csvvzSZt0MOOQSXX3454uNrfqCnH3/8EdOnTzfHYdm0aZM5jldffdV8byLS9k3sAsV58BfmIVC82WThvV6fWf9u7g+H8f53K7G5NISCYDyKQgkoCmWgOBQPL1wY7c3Asf0ja9/pyX8ciJREtzLvItJhKKiPYaY+zFX1CupFOoW///3vuOSSS6LXd999d1x99dU4+OCDW/zaDCC5R3dX8+STT2Lo0KEmIG+Kr7/+OnqZmbMVK1bglltuwRlnnIGPP/4YiYmJjXodBt+nnXaamUz45z//iZ9++smc8/l/+tOf6nzO999/byYPGKTvtttueO2113D22WfjzTffxJAhQ8xjLrzwQlRUVODpp59GcXGx+d1g5+nbbrttm4D+vPPOQygUqnF7z549ze8NH3/jjTc2aWxEpIlBfFEuSjbnITe/DLkF5WYNfFGpDynJCTjsgB3hSM6EMzkDP3ybgt8rfEhOcGNoThp27McMfOTE9e/VpSapF5KIdCwK6mPE7o4HP+ap/F6kc0hOTjan2rf16LG10VFzpaWloaspKSnB448/jpdeeqnJz609pr169cK1115rMt4Muvfdd99Gvc4rr7wCl8uFG264AU6n0wTlq1atwmOPPVZvUP/vf/8b++23XzSbzyz9vHnz8Mwzz5jX4eUffvgBM2fOjAb5vP3MM8/E3/72NxOws0LhjjvuwPPPP4/hw4ejsLCwzuqMPffc0zxvwIABTR4jEdmKmXaW0Pvz18NfsMmsiedtcxdvwjp2la/wozzkQX4oCQWhbBSGEuCypeD4cXtHs+0XnpSMlEQPstLilIEXkU5H+2HEck29MvXSjfEDFzsLx+wUZq1M62L5+P77729Ks3feeWeTpSVml4855hhMmDABY8eOxVFHHYWvvvqqRoDH8v7qr2GdM8vNxzPr2xK//fYbzjnnHEyZMsUcG7PN69ati96/cuVKkwnnfTvuuKO5XH05wRdffGGOY/z48aYUncdbVFTU4FgwwB02bBhag8cTyYwxOCd+/REjRtR5ssZyzpw5mDx5cvQ5tMsuu5jvdfPmzdt8DWbU586dW6PUnjhms2fPjr4mJx2sgJ74NRgEWD8jZu35eE5qcCKivokcfh1m+0Wk6fh33Ld5LQoXzsKy917C7DdfwRczPzHl9fz77ohLxJpABr4t6o0vvWOwIXsqhu46DSdNPxB3XXEInr7uoBrB+5CqjLwCehHpjJSpj+Gaegr5Kk3HVZu965XeitSHH7hK5vPD15aYHYMzJQvJ4/dp9Q9wq1evRm5urinXrqysNGu5uYacGV9mmEtLS3HXXXeZ8m4Gym53ZD/j6jZs2GAy3Mz2slSca9IZqH744YfNOl4G71zbvuuuu5qMs9frNev3GXC+8847Zl03s8wjR47Ef//7X5NpZmn4+eefj48++gj5+fnmMo9h2rRp2Lhxozn+22+/3axXr8vnn3+OvfbaC61hzZo1Ziz69OmDSZMm1bkcorq4uDhzzuNkpry67Ozs6BhnZWXVuI+l9AzIWRlQ+zl8LWs9fO/evWvcz58hg3S+JqWkpJhJDbLO68KxfOSRR3Ddddc1ciREureQrwKbfv8Na5YtQ+GGddhSWGa2lgsxUx92IC+UjPH7jUN2/wEmqJ+ctQXjfUGMHJiOhDhXrA9fRKTNKKiPFafbBPIM6Jmtd8TXLOsV6fq6bjaEGfp+/fqZy2yQ9o9//AMnnHBC9H6Wdp911lnYsmXLNgEi+f1+s/Z71KhR5jrXhf/lL39BXl5eNChtihdeeAEJCQm48847o5MI9913n5lkeOutt3DiiSeayQgG/WzYx5J1rmH//fffTfaagazP5zNBNe/nicEo17vXhc/59ddfcfzxx6M5WClQfSx4POxhMGPGDPN91LccojZOqtSeNLEy/pzYqOvxVNdzrMdzLX1dEzHVH9NYrGLgZAEnA+r6PRARIOT3wbdlHfx5qxAoyMXCxZuweHW+ua8i5EFuKAuVcVno2a8fxg3MRFzv/nBUTeyNGZwZ46MXEWkfCupjhNk2ZuuDFSVmXb2Ceuluv//MkiMUiN1B2J1tVmY5cODA6GUG5qmpqWYdN4NkrulevHixua++oJiql3dbwSsD3OZYunSpKeOvHoyyhHzQoEHmPrr44otNIM8JAJaT77HHHjj00ENN93l+D7zM8n0+jw3kmGXm8oC6cA05s/3sNt8crHIgTnrce++95vyiiy5CTk5O9DFcY88qg7ocdthhZp07M/acjKjOCrytyYG6Av66nmN1tq/rNa3H1PWaDbHGh5M1CupFtuLfxkULFmP14qXIX70Ce47vjcy0yP/BzD69UVGahawBgzBuUA5GDMxQ2byIdHsK6mPIHpcYCeq1rl66IfMBzNE1yyGt8m9iUzWuT2cQzPXqDDiZ7WXmvSF1ZYOb2wegvucxo84sODFbf9BBB5klAd99953J5D/88MMmwGaZOpcM8Ji5jdu3335rOsTz+2E5f22cCNjepEVDrMZxPH/00UdNPwKOIbftS09PN/f99a9/NbfVxdomjmX0XApRnXWd6/1rYwk9A/O6nmM9nq/JHgnVMcjnREZTqyisrvjWeIl0Z4UllVj4629Y8csCFK75HQhuncRcsSWInPE7wJ3dHxPikzEhpkcqItLx6JNER1hXr6BepMvitm5stMZt67g3ObPc1trrtmjWVxc2j1uwYEGNDDMbxbFqgBUBzIQzs81KADbD4/r1t99+22SQOSkxf/58k8Xnnu38Hlh1wOvsRM/n1hUcc7KAW8q1FDPkXDbA4+UxWjIzM03QX9eJ9xHX37N5XfXJBR4zKxSsx9SeaNppp53M91zdrFmzMHHixOhrsmSeY2exHs9Jjqawxq45SypEOjvr7x/Xya/6eS4enfEvzPvfayhcuSQS0DvjkD54DKYc+X/Y68RTED9gjKoaRUTqoUx9DNnjqoJ6bWsn0mWxrJqZXXZNZ5aXAeK//vUvc19dZdzNxfXgzKLXNm7cOLO2/cUXXzTZ9XPPPdd8XTbCY9b7kEMOMdlpNrbjuno2n2Ommw3eGJizbJ/BPsvyef3YY481pebc0o3LDKzMeW1jxozBwoULt9k6jsFw7eNkZQNL/uvDBn7c+o2VA6x04L7zjcGvzQ70bKrH5//888+m2zz7FVTfeo/fn1UKz/4F3Jd+9OjRZss5Ng5kXwSrISC7/zPw53IFNjBkYz0uBTjiiCPqzP43hOPDPgUK6qW72FJUgfe/W4WflmzEqAw/jt0pDv78DUgKhZDp8cPjiUdCzxy4UlMwbb89TdNJERHZPgX1MWT3JJpzZepFui5uHccsM9ej09ChQ02WmwE2s+fV1863BLO+bL5X27PPPmsqBf7zn/+YDDy74LO0nxUDvG59aOb+7Az0mYnn8gCuo2dGvn///uZ+Vho88MADJrhnuTi3huNz6isd33vvvfG///1vm9u5Dr72Wng23vv000+323zwgw8+MAE5JwCsEvuGMBvPoJ4B+ZFHHmn6AbBrPy9beB8z7dbXZ0M+/nweeugh3HPPPebnxaaA1s+J2XyOA4/jlFNOMevwuWzhqquuQlNxgqexExQindnGLWX472fL8c0Py9DXnos+jgLYigFf/yH8TwVXShaOOXVHJPcdhEpfwEykVd+KUkREGmYLt1f9ZyfGD97E/aVbilkdvlnxA7PLX4qS+Z/BEZ+E1EmHtMKRdl3Vx62pzai6u1iPHTPIK1asMCXP1dead3Qs2eax85gdDm052dSxY8d8NtfjmvvW+NvZ1XBpAwN67j7AZQ11/c419H+nNd+XpG3f67vze9aaTSV47dNlmDdvCQY4ctHLXoQe6XEY0jcVPXtmIGPgcHh6DoQjMTX6HI1d82jcmkfj1nwau/YZt8a+N2katCNk6ivLzdoydW4Vka6CHf+Z9We5O5vsSU2snOCkhxXQi3Q14XAIX38xB2U//4gp7jL0zkjEmMH90GfIYHj6DIMroxdsNrV2EhFpDQrqYyAYihRH2N1xsMFm3vjCvkrYPJHtWkREugIuB2BXfa5l59p+iWAVw/vvv49XX3011oci0qoWr8qH2xFGX3sBKtctxZ7pBUjsbceowYPQZ9gIePqOgDMpLdaHKSLS5Siob0ebCytw+f1fobjMi2dGj4LN7oDNE4ewt8Ksq7crqBeRLoRr99lwT2piQz32BxDpClhpuOC3zXj5wyXYsnIp9ulTgrSdepn7EhPjsf9h+5nMvD7jiIi0HQX17Sg1yYPNRZVgF4PCUh8SExNNCX7IBPXsgL/tFksiIiIiHTGYn7NoE175eCk2rF6H0e61yPFUINmdArgTkNBvBDy9BsHmcMX6UEVEuryYB/WFhYW4++67zXZKpaWlZj9lbqlk7Qlc29q1a3HjjTdi9uzZprnA0UcfjQsuuKBGI6vnn3/e7A3NRkTcjumaa64x2xPFmstpR3ZaPDYVVGDD5jL07Zke2dauOLKuXkRERKSjm7s4F8/MXIi16zZjuGsjdosvwNCcVIwa0g9ZIyeYzDyrEUVEpH3EvEPJ3/72N8ybN88E9twPmJ0AzzjjDPz+++/bPJZ7CfM+eumll8wewdx7+cEHH4w+5o033sDtt9+Ov/71r6bsMycnx+w7nJ+fj46gd1aky+GGLZEg3u6p2qveZOpFui5ttCHSNPo/Ix1VXkEpAht/wz6JS7H/kDD+uOdg7LrXFPTZ43DE5YxUQC8i0p2C+lWrVuGbb74xwTkz89y25x//+Aeys7O32ceYuAZx/fr1JmgfPnw49ttvPzMpwC2TfD6feQz3E54+fTr++Mc/RveDjo+P7zANiXpl1gzqHdqrXro4l8sV3cJDRBrP+j9j/R8SiZVgMIRN+ZHfx0BRHiY7l+D40V4ctedATNxpOHpOPgCJI6do3byISHcsv09PT8djjz1WY989buvGU3Fx8TaPnzNnDsaMGWO2SrLssssupmyf+/0xK79y5UpMnTo1er/T6TQTBizX//Of/9yijElrBCVZKZEPZ+tyS8zrBcJ2U4EQKi6EXUFPvSoqKmqcS+caO/aPYMfvUChkJtk6w/aN/D/PyUJtN9l0GruWjRv/n3CPei4hS0pKgtfrrfOxGltpD2tzS3DPi3NRXOrFncf3QWjtQoQRxg7DeyNu4Fh4eg/W1nQiIt05qE9JScFee+21TTaeGfyrr756m8dv3LgRvXpFOqpamNWnDRs2mACeevfuvc1jFi9e3KJjZeDNiYMW81WaszWbis3r2bxl8OTlIewogNfdCq/fxXHSRjrv2LEnhjVxJyJ1Y8DOE4N7TsYxuK9vdwGRthIKhfG/r3/HM+8uRDDgx6TEdcj9ZT0y0+LhyR6I+CETYHd5Yn2YIiIS66C+trlz5+Kqq67CAQccgGnTpm1zPzMXnAiozuOJvKEwk2FlImt/0OFj6sp0NAXLH1nO31JJ6QX4fEExhvRLN/0DwgE/SitWR+4bNhQ2p8os68KfLYPSgQMHmkyvdM6xCwaDCAQC6Az494bLffr06YO4uLhYH06norFr2bj17dvXVLdUbwBb2/Lly9HVcBLjgQceMMvlSkpKMGnSJFx77bXo169fnY/fsmWLWWLHZXycBNl1111x5ZVXmi0DpWVy88vxr5fn4eflm5Fgq8RR/TZjr9HpSIz3IGHIjnD3HqLJWRGRDqTDBPUff/wxLr30Uuy00064884763wMPxxaa+ctVrDOTvjWh8e6HtPSYIZvXvwaLdWvF3DmgdkmoLdezx+fiFDAhzgH4GiFr9GV8efYGj+H7khj1zRcHsMAi8t9NG5No7Fr2bhx8np749YVA6qHHnoIL7zwAm699VZTlXfHHXfgzDPPND126qpKuOiii8wk4VNPPWWC+n/+85/4y1/+gtdeey0mx99VfD53LR56bT4qvAHkeEpxytgKDO+TaRr7Jo3eFc6UrFgfooiI1NIhFkH95z//MdvS7b333qbRnZV9r41v8rm5uTVus65zZt4qu6/rMR155l4d8EVEpDvjZDy3or3wwgtNpd7IkSNxzz33mGV3H3744TaPZ9+dH374AWeddZaZJOe2tWeffTYWLFhgtsqV5gmGwvjg+5Wo8Pqxb04ZrtwzhOF9k+FM7YGUnfZXQC8i0kHFPFPPWXnuO3/SSSfh73//e4PZB5bivfnmm6YxHpsH0ffff2/KFPkBgDP57KA/a9asaLM8zuKzwd4JJ5yAjiQQDKG80o+EOFdkr/qyQgQry6HiexER6W7Y96asrKxGo1tWLDBYZ6PbQw89tMbjWZnH935+Jpg8ebK57a233jKfAWov04tFU9yO0KC0uS7+00j8/OlH2KFHMNIDJbMfHAPGoTIQBgJt39C3M49dLGncmkfj1nwau/YZt8Y2xo1pUL9ixQqzHm7//fc3nek3b95c4w2bGfuioiJTwsmAnVvY3XvvvabkjqX6bLrF/e1PP/30aGkeL998880YMGCA6arP7vpcp3j00Uejo/jq12Lc8NKnOGS3QTj7iLGwR7e1U6ZeRES6H2bk62t0a91XHd/zWabPNffc4YYfePhYVv7Z7fbYN8XtQA1Kt8cfCGPhmnKMH5QIBP3wrPsZvW1l2JJvh7/HMAQrPcCSJe1+XJ1h7DoijVvzaNyaT2PX9uPWmMa4MQ3q2emeb6AfffSROVV35JFHmtPJJ5+MZ599FlOmTDFB/uOPP27WzR177LEm2GcG/rzzzos+j7ezwQ6Df5bg7bDDDma9XUZGBjqKeI/ddJVdn1dqrptMvfaqFxGRbqqhRrec3K8rc8Hge8cddzTr7tmEk+X6/Dzw4osvRqv5YtUUtyM1KG1Iabkftz0/D0tXFyEtLQN7Jm9CMCUBdncG4kbsCkdSWrsfU2cZu45G49Y8Grfm09i1z7g1tjFuTIP6c845x5wasqTW7DAz8Fx315AzzjjDnDqqzOTIsK/PK6u5pr5SmXoREel+qje6rb5jQn2Nbt977z2Tlf/ss8+iATx78rA3DxvlnXrqqTFtitsZGpSyw/11T8zB2txSJMc7MNq2EnZvGZzxiUgevw8ciakxPb6OPHYdmcateTRuzaexa9txa2xj3A7RKK+7yUyOrJzfVFAOfyBUrfxemXoREel+mtrolr1yuH6+ekae1Xu8bdWqVe1wxJ3bivVFuOz+L01An5XqwS2HxCPbVQabw4mkHfaMeUAvIiJNo6A+BpLj7fC4IiX4m/LLouX3YW8lwqFgrA9PRESkXbHZLQN0Nrqt3uF+4cKFpkluXbvhMHi3trUlNrhjrx2WNEr9fv19C6588GvkF3vRv2cSbjksGSn+zbDZ7EgavRucKZmxPkQREWkiBfUxwDKKXpmRQH795jLYXHGw2R0II4yQrzLWhyciItKuuJZ++vTpuPPOO/HJJ5+YbvgXX3yxCd4POOAAs2Y+Ly/PNL6lI444wpyzcS4fy9Pf/vY3swb/qKOOivF303EVlXpx81OzUF4ZwJjBmbjx8HR4StbCBhsSR+4CV3qvWB+iiIg0g4L6GOmdGSm5Z7M8Bvl2T2TNoNbVi4hId8Q96rlTzTXXXIPjjz8eDocDTzzxhGlet2HDBuy+++6YOXOmeSw73XNLXDbMO+WUU3DaaaeZx/G25OTkWH8rHVZKohsnHjgSowZm4OpDMoBNy8ztCcN2hrtHv1gfnoiIdNZ96rurHQanw+N2oU+PyHpArqsPVpRqXb2IiHRLDOIvu+wyc6otJydnm8a5Q4YMMc3xpPGYRDhk98HYZ3AYFcvnmNsSBo2Dp/eQWB+aiIi0gIL6GNl/cj8cPm1rx8NoB3ztVS8iIiKtaMFvmzGoTyqS4l3wbVmHyuU/mtvjckYirt+oWB+eiIi0kIL6DiK6V32lMvUiIiLSOlZvLMY/H/8eGclxuPmsiXAtn216+Hh6DkL8oHGxPjwREWkFWlMfQ8FgCBs2lyEQ5LZ2ytSLiIhI6ymv9GPGM7Ph9QWRnRGPuC1LEPJ74UxMNevoG7v/sYiIdGwK6mPo1Bs/xNkzPjb7xNrjqvaqV6ZeREREWohNBB98db75jJGZGoeLD+0Pf+5K0+k+Ydgks+uOiIh0DQrqYyg7PT7aAX9rpr7cvBGLiIiINNe736zAlz+tg8Nuw+UnToBzw8/mdk+fIdqLXkSki1FQH0NW5/t11YL6cCiIsN8b4yMTERGRzmrJqnw88fYv5vKph47BIEeu2WHH7o5H/ECtoxcR6WoU1MdQn6xIUM919SyD45staVs7ERERaQ5W+z3x9q8IBMPYdVxvHLpzJirXLDL3JQzdCTanK9aHKCIirUxBfQz17ZEYzdRT9RJ8ERERkaZi87u/nzYZB+4yABceOwHly+eYQN+d2QeuzL6xPjwREWkDCuo7QKZ+/eayWtvaqQO+iIiINE9qkgfnHzMBzoLVCBRvgc3hRMKQndTtXkSki1JQH0N9qjL1hSVes+2MMvUiIiLSXLn5Wz8/hLwVqFgZaY4XP3BsdJcdERHpepyxPoDuLCHOZcrj0pI8CIbCcHmqtrVTUC8iIiJNUFBSiXNv+wQjBmSY8vvwynkIBfxwJqXD02dorA9PRETakIL6GGN5nMVfGSnHD5YXx/CIREREpLN564vf4AuE4AsE4SrLRWneGlNub/akt6kwU0SkK9Nf+Q7EkZhqzkMVJWZrOxEREZHtKSn3Yea3K8zlY/cZjPLf5prLnr7D4UxOj/HRiYhIW1NQH2OhUNisgVu1oRg2dzzsTpfpUhssL4n1oYmIiEgn8M5Xv6PCG8SgPinYIanALONzxCUifsCYWB+aiIi0AwX1Mfb9Lxtwxs0f4b5X5pkyOXtCVba+vCjWhyYiIiIdHBvtvv3V7+bysfsOhW9jJGMfP3AcbA7tSS8i0h0oqI+xPj0i6+jX5ZWZDL1Vgh8sU1AvIiIiDZv57UqUVfjRt0cSJva1IeSrgN3lgStLe9KLiHQXCupjrHdWpOM935CLy3xwVGXqg8rUi4iISAOYDPh+wQZz+Zh9hyGwKZKld/ccBJvdEeOjExGRbtn9/tFHH8XXX3+N5557rs7777//fjzwwAN13nfUUUdhxowZ5vJpp52Gb7/9tsb9kydPrvd1Y8njcqBHejzyCiqwPq8MQ9OVqRcREZHt47K9W8/fHd/MX4+pI1JR9uP35nZPr8GxPjQREemOQf3zzz+Pe++9FxMnTqz3MaeffjqOO+64Grc99dRTePHFF3HqqadGb1uyZAmuv/567LffftHbXK6Ou66sT1ZiJKjfXIoRfbPNbcHKMoSDfq2HExERkXo5HXbstVMOKlb9gjDCcKX2gCMhOdaHJSIi3Smo37RpE6677jrMmjULAwcObPCxiYmJ5mRZuHAhnn32Wdx4440YMWKEuW3Lli3mNH78ePTo0QOdZV39/GWbsS6vFHZ3f9jdcQj5KhEsK4YzJTPWhyciIiIdzPq8UmRnJJigPhwOwVvVIM/Te0isD01ERLrbmvpff/3VZNHffvttE4g3xQ033GAy+0ceeWSNLD3L0QYNGoTOgs1taP3mMnOudfUiIiJSn2AwhOv//T3OnvExVqwvQqBgo9nGzu50w5WVE+vDExGR7pap32effcypqT777DPMmzcPb775Zo3bly5diuTkZBPwf/PNN0hISMBBBx2E8847D263u0XNaMrLy9FSFRUVNc5pSO9EHLHnQAzLSTVfI+CMg9/vR3l+LoIpvVr8NbuCusZNGkdj1zwat+bT2LX9uPE9iRPY0j199dM6bNhShpREN3pnJsK7fIG53d1zoBrkiYh0QzEP6puLa+n33ntvjBo1apug3uv1Yty4caZh3qJFi3D77bdj/fr15ry5GGTztVrLypUra1yfYCbWt2DRoi1wFG2BKy8PobIAfBVaU9/QuEnjaeyaR+PWfBq7th23lkxUS+cVCoXxyifLzOXD9xwCN/yoyF9vrqtBnohI99Qpg3oG6FyD/9hjj21zHzP0V1xxBVJTIyXsw4cPN+X9F198MS6//HJkZWU162vyNYYOHdriY2cGhh/Y2D8gPj6+zscES3qiPFxg1tYn1pq06K4aM25SN41d82jcmk9j1/bjtnz58nY7LulY5izahDWbSpAY58Qhuw2Cd9NSU7nhTMmCIzHy2UdERLqXThnUf/zxx8jIyMBuu+22zX1OpzMa0FuGDRtmzjdu3NjsoJ5ljizlby38wFb99fKLK7E2t8Ssr8/I7Ak/u/WHg4hzOWB3eVrt63Z2tcdNGk9j1zwat+bT2LXduKn0vvv6Yt5ac77f5AFIiHOiWA3yRES6vZg3ymuOOXPmmH3nGcDXdtJJJ+Gqq66qcduCBQtMpn173fVj6b6X5+HvD3+L2Qs3weZ0we6JfKBTszwREREhfyBoPifQ7uP7IFC4yWyBa3e64FaDPBGRbqtDB/XBYBB5eXmorKyscTu3shs5cmSdzznwwAPx1ltvmb3r16xZg5kzZ5q19GeccQaSkiJd5jtyB3xua0dWCR23tRMREenqQqEQ7rvvPuyxxx6YMGECzjrrLPM+Xpf777/fbGVb16n2xH5XsuC3LajwBpCREofh/dPh3fCbud2dPQA2R6csvhQRkVbQod8BNmzYgH333RczZszAUUcdFb2dgX5aWlqdz5k+fbopS3zuuedwyy23mL3qTz31VJx99tnoyPpkJZrzDdW2tfPnb0CoTJl6ERHp+h566CG88MILuPXWW9GrVy/ccccdOPPMM/HOO+9s0xTw9NNPx3HHHbdNA11O6PM9v6vacXgP3HvxXthSXAkEKuHfss7c7u6l0nsRke6sQwX1fCOvLicnx+w7X9v8+fMbfJ0TTzzRnDqTPvVl6lV+LyIiXZzP58OTTz6JSy+9FNOmTTO33XPPPSZr/+GHH+LQQw+t8fjExERzql7B9+yzz+LGG2802fquikmLITlpYAhfuWZxpEFeciacSXUnOkREpHvo0OX33YkV1G/cUoZgKGwy9RQsKzJv2iIiIl3V4sWLUVZWhqlTp0ZvS0lJwejRozF79uztPp8730ycOBFHHnkkugN+LvBujJTeaxs7ERHpUJn67iwrLR4upx3+QAh5BeXomZYMG2wIBXwI+ythc2tbKBER6Zq4Ow317t27xu3Z2dnR++rz2WefYd68eXjzzTdbJVguLy9vle0Jq5+3hhc+XIb8Yi8O2bU/+iVWorK4wKyjDyRlIdgKx9xRtMXYdQcat+bRuDWfxq59xo3vS43Z8UZBfQfhsNvQKzPR7D27Pq/MXLbHJyFYUWKy9XYF9SIi0kVZH25qr533eDwoKmp4GRrX0u+9994YNWpUi4/D7/dj0aJFaC0rV65sldcJhcL4ePYGlFWGMCDdj6B9JRwleQim9oZ/6TJ0Ra01dt2Nxq15NG7Np7Fr+3Gr/d5YFwX1Hcif9h6KQDCM/r2So+vqTVBfXgxXeq9YH56IiEibiIuLi66tty6T1+tFfHz9k9rr16/HrFmz8Nhjj7XKcXD726FDh7bKJAU/sHEr3YaOv7EWrSxAWeU6JMY5cdCuI+GdvwrhuB5IGLsnHF1sPX1rj113oXFrHo1b82ns2mfcli9f3qjXVVDfgew7qX+N646EFHPOTL2IiEhXZZXd5+bmon//re+FvN5Q47uPP/4YGRkZ2G233VrlOFjimJCQgNbCD2yt8Xpzl0bWz0/ZoTfifIUIOh1wJmUhObsPuqrWGrvuRuPWPBq35tPYte24Nab0ntQorwPbule9gnoREem6Ro4ciaSkJJN1txQXF5uu9pMmTar3eXPmzMHkyZPhdHbdHAXXU367YIO5vOvY3vAX5ZrLrsyuG9CLiEjTKKjvQNj1fvGqfMz8doV5E492wC9XB3wREem6uF5w+vTpuPPOO/HJJ5+YbvgXX3yx2a/+gAMOQDAYRF5eHiorK2s8j0E/JwS6smVrCrG5sAJxbgcmjMhGoGizud2ZkhXrQxMRkQ6i605td0JshHPVg98gEAxhpxHZ6JmeBJvNjnAwgJC3HI64rXvyioiIdCUXXnghAoEArrnmGhO8M0P/xBNPmHXua9euxb777osZM2bgqKOOij6HgX5aWtdaU17btz+vN+cTR/WEK1iJMm+5Kcd0pmTG+tBERKSDUFDfgXBLu0F9Usys/LLVheiV2ReOhGQEyopMCb6CehER6aocDgcuu+wyc6otJycHS5Ys2eb2+fPno6vLzkjAgF7J2HVcHwSKI1l6R1I6bA5XrA9NREQ6CJXfdzDD+kUyDkvXFJhze9W6+lC51tWLiIh0NwfvOggPXLYPdh/fB/6iPHObSu9FRKQ6BfUdNKhfvrbQnEfX1atZnoiISLfFkvvoevrUHrE+HBER6UAU1Hcww/qlm/Pf1haaxnnqgC8iItI9/bh4Eyp9AXM55PeaxrmkTL2IiFSnoL6DyemZbDrcVniDWJdbUq0DfjHC4VCsD09ERETawdrcElz/7+9x6g0fwucPIlC8xdzuiE+G3R0X68MTEZEOREF9B+Ow2zAkZ2sJvj0uETa7wwT0oYrSWB+eiIiItINvf47sTT9iQDrcLgcC1np6ld6LiEgt6n7fAZ140EjYbTYM6Ztq1tCxBD9Qkh/pgJ+QEuvDExERkTb27YLIVna7ju1jzgPFapInIiJ1U1DfAY0dUvMNmyX4Jqg3a+n6xey4REREpO1tyi/Hb2uLYLcBu+zQC+FgAMGSyK44ytSLiEhtKr/vBNQsT0REpPv4ripLP2ZwFlKTPGZin8vw7O54syxPRESkOmXqO6hvf16PX37fgj9MHYheCupFRES63Xr6Xcf1rll6n5plluWJiIhUp6C+g3rv25X4aVke+vdMRt+deprb2CgvHAqaxnkiIiLS9eQXV2LRynxzeerYqqDe2p8+RaX3IiKyLZXfd1DD+kc64C9bUwibOw52pxthhM3WdiIiItI1pSa6cf+le+Mfp09BZmq8Kbu3trNjpl5ERKQ2BfUd1FBrWzsG9VUd8Ekl+CIiIl2Xw2HHwN4pmDyml7keLC1COOiHzeGKfhYQERGpTkF9BzWsX7o5X7mxGF5/0HTAp0gHfBEREekOtm5llwmbTR/bRERkWx3q3eHRRx/FSSed1OBj3n77bYwYMWKb09q1a6OPee+993DwwQdj3LhxOOKII/Ddd9+hs8lKi0NakgehUBgr1hXBXjU7HypT+b2IiEhX9cTbv+CtL39DaYXfXA8UV62n11Z2IiLS0YP6559/Hvfee+92H7dkyRJMnjwZX3/9dY1T796RZjLff/89LrvsMhx33HF44403MHXqVJx99tn47bff0Jmw5H5ov63r6h2JKeayMvUiItIReL3eWB9Cl1NW4cebX/yGx9/6BQiHEQ6HtzbJ03p6ERHpqEH9pk2bcM455+DOO+/EwIEDt/v4pUuXmsx8jx49apwcjkhH+H//+9/Yb7/9cPLJJ2PIkCG44oorMGbMGDzzzDPobIZXBfVrc0u2lt9XliEciMzei4iIxMpuu+2G6667Dj///HOsD6XLWLkhUo2XlRaPpAQ3QpWlCPkqTNm9Mzkz1ocnIiIdVMyD+l9//RUul8uU1Y8fP75RmXoG63UJhUKYO3euyc5XN2XKFMyePRudzUG7DsTT1x6Ac/80HnaXB3Z3vLldHfBFRCTWTj/9dFMd93//939mydvjjz+OvLzI+m9pnpXrI9V4bJRHVpbekZyu7WxFRKTj7lO/zz77mFNjFBUVmcz+nDlz8MILL6CgoMCsm2e5/aBBg1BcXIzy8nL06hXpGGvJzs7Gxo0bW3ScLIHja7dURUVFjfOGePj+7UD06wadcQiUFaNsyya4nJEAv7toyrhJTRq75tG4NZ/Gru3Hje9JXKYVS+edd545cTKdy93YF4fL6HbddVf86U9/Mu/tnLSXxltRlakf1KcqqNd6ehER6QxBfVMsW7Ys+mFmxowZqKysxMMPP4wTTjgB77zzDgKBgLnf7XbXeJ7H42nx2j+/349FixahtaxcubLJz3FuLoKzMA8B/wIE8rvnh+XmjJtEaOyaR+PWfBq7th232u91sbLTTjuZ0z/+8Q989dVXePrpp3HRRRchJSUFRx11FKZPn46+ffvG+jA7hZXrq4L63pEld4Eiq/O9gnoREekiQf3EiRNNJ/v09PRohuKBBx7AtGnT8Prrr+OYY44xt/l8vhrPY0AfH9+yzDazDUOHDkVLMQPDD2zsH9CYY/rul034ct567DSyB6aNHofKZV44EhORMGoUupOmjptspbFrHo1b82ns2n7cli9fjo5kw4YNeOutt8zuM1wmx+o5vjd/+eWXprKOE/Es0Zf6cbcbbmNLA/ukIOSrRLCiJLqdnYiISJcI6ikjI6PGdX7wycnJMWX5aWlpSEhIQG5ubo3H8HrPnj1b9HU5icDXbi087sa8Xn6JH3OXbkZCvBuH7TIGwZU/weYrR7zbBZuz+5U1NnbcZFsau+bRuDWfxq7txi3WpfdUWlqKDz74AG+++SZ+/PFHxMXF4aCDDjLN85i5Jzar/fOf/4xbbrlFQf125BVWwOcPwu20o09WIgIF683tbJTLvjoiIiIdtlFeU7z88sum6V31te38UMHMBrPo/JDDDxI//PBDjefNmjXLZPk7o+H90qPb2tk9CXDEJSKMcHSdnYiISKy63//97383y9NuuOEGs70sg3croLeMHTu2Q0xCdHQ9MxLw8s2H4K6L9oLDYY+W3ru0nl5ERDpzUB8MBk0nXa6dpz333NN0uL/88svN+voFCxbgggsuMNl7rtuj0047De+++y6eeuopszf97bffbtbCn3LKKeiMhlRta7cpvxxFpd7oujrrzV5ERCQWTjzxRMycORMvvfQSjj766HqrC/i+/Pnnn7f78XVG8R5ntc73VevptT+9iIh05qCea/R2331386GBevfubRrwMFN//PHH49RTT0VycjKeffZZ0wyP+HhmCl588UUceeSRZrudRx55pN5t8Dq6pHiXKcOj39YWRTvgKlMvIiKxxAl27kLz4IMPRm9buHAh/vrXv+KXX36J3paYmAiHQ9uxNUU46EewrNBcdqYoqBcRkU60pv7WW2+tcZ1r5dlwp7oxY8bgySefbPB1jjjiCHPqKob1S8f6zWVYtqYA4/v3NrcFSvIRDgW1b62IiMTEF198gb/85S+mvJ7nxDJ7LonjrjR8r+6sS99i4bZnZyM1yYNj9xuO5GCh2emHy+7scZGJfRERkU6ZqZeIoVUl+GZdfXyyaZjDgD5Ykh/rQxMRkW7q/vvvxyGHHGK621tGjRpluuD/4Q9/wN133x3T4+tMyiv9+Hr+erz7zQq4nPZoNZ7W04uISGMoqO8EhvVLQ5zbAafTbrIgVgm+X+vqRUQkRti3hlVxdTXB4+2LFy+OyXF1Ris3RLayy0qNQ3KCu9r+9Cq9FxGR7VNQ3wmMHJiBl24+BFeePMlc17p6ERGJNfa0WbFiRZ33rVmzpsnbGbIR7n333Yc99tgDEyZMwFlnnWVepz7sun/XXXdFHz99+nTTGLczB/UD+6SaSrxA8ZYa7/ciIiINUVDfCTjsNnOyWDP3gaLNCIdDMTwyERHprvbff3/861//wmeffVbj9q+++srczvub4qGHHjKl/DfeeKPpqM8g/8wzz4TP56vz8ddffz1ef/110xz3v//9r9kJhxMBJSUl6GxWrI8E9YP6pCBYVmQCe7vTDXtCpBO+iIhIp2mUJ9sXDIXhSEqDzeGs6o5bBGdSZC97ERGR9nLxxRebrWXPPfdcuFwupKWlobCwEIFAAOPHj8cll1zS6Ndi4M7GepdeeimmTZtmbrvnnntMFv7DDz/EoYceWuPxzOAzkOfuNnwM3XTTTabsn533p06dis5k5foic87t7ILlkQDfkZha59IGERGR2hTUdxLzl+bh4dd/Rq/MBFx/1lQ4UzLhL9hksvUK6kVEpL0lJSWZjDq74P/4448oKioyJfnseM/A3G5vfDEg19+XlZXVCMZTUlIwevRozJ49e5ug/ptvvjFfa88996zx+E8//RSdTSgUjpbfD+qTilDlanPZHpcU4yMTEZHOQkF9JxEf58S6vFIUl3nNNjdcZ2eC+uI8oO+wWB+eiIh0Qwzc9957b3Oqje9Vjc00b9y40Zz37h3ZttWSnZ0dva86ruXv16+fyeI/9thj2LRpk5kAuPLKKzFkyJBmfz885vLycrRURUVFjfOGFJZ4Ee9xmkq8tAQbKjZtMf0C7DZnqxxLZ9OUsZOtNG7No3FrPo1d+4xbY99LFdR3Elxn53TYUFLux6b8cmSm9Ki2rr7xH5xERERay8yZM/HDDz+Y8nm+F1UPjH/66Sd8+eWXjXod68ON2+2ucbvH4zEVALWVlpZi1apVZh3+5ZdfbrL0Dz/8ME444QRzTJmZmc36fhhMt2azvZUrVzbqcX89rAcqfSEsXboE7rXLYa8ogs+xCaGSyJh2R40dO6lJ49Y8Grfm09i1/bjVfm+si4L6TsLldJiuuMvXFJr96nuO7QmbzY6QrwKhylI44pNjfYgiItKNPPDAA+bEMniuo+e6eqfTifz8fJPBP+aYYxr9WnFxceackwPWZfJ6vYiPj9/m8fw6DOy57t7KzPPyXnvthTfeeMM02GsOfg9Dhw5FS3GSgh/YBg4cWOfxN6SsfCVCPjcSRo+FIykD3U1Lxq4707g1j8at+TR27TNuy5cvb9TrtlpQz8Y069evxy677GJmzKX1DctJM0H9klUF2GNCXziS0822N8zWK6gXEZH2xOCZjelmzJhhtqLjZ4DbbrvNfB44++yzMWxY45eGWWX3ubm56N+/f/R2Xh8xYsQ2j+/Vq5cJ7KuX2nMygCX5a9eubfb3xKq3pm7F1xB+YGvK64WDAVSGA3C4XEhM7wG7y4PuqqljJxEat+bRuDWfxq5tx62x1djN2tKOb7InnXSSKXuj//znP2ZG/sILL8QBBxyAZcuWNedlZTt2GBIpJ/xpaW7N/eqL8mJ6XCIi0v1wHfthhx1mPnCMGjUK8+bNM7fvsMMOOOecc/Dqq682+rVGjhxpGu/NmjUreltxcTEWLlyISZMmbfN43sbqAHbft1RWVpqu+AMGDEBnctl9X+K6x77Dxi1lCFWWmdtsDhdszu2XW4qIiDQ7qL/jjjtMk5qxY8eafWS5pcyuu+6KN99805St3XXXXRrdNjBheDY4WbNqYwm2FFXAaa2rL94c60MTEZFuhhkGK4PAQJoZcgbWxCC/KRlzrhecPn067rzzTnzyySemGz63zGNGnsmCYDCIvLy86Ouzwz4/d1xxxRWYM2eOKU/k2nqHw4HDDz8cnUV5pR+LVxVg7pJcJMS5EKwK6h1xieqVIyIibRvUf/311+aNlHvDzp07F5s3b8bJJ59sZtq5jo1vsNL6UhLdmDq2Nw7cZQACQXbAz4INNgQrSszaehERkfbCiX1O5tOgQYNMQP3dd9+Z67/99lujGvtUx2q/o48+Gtdccw2OP/5483pPPPGEWee+YcMG7L777qYJnuX+++/H5MmTcf7555vncY39s88+i4yMzrMOfdWGEnOemRpn3uPZI4fs8drOTkREGq9Za+rZ1Zaz58TOtnzj5lp64mWrA660vqtOmVzjuiMxBYGyIrOu3t2jX8yOS0REuheW2J922mmmTJ4Ve3/84x/NhP+UKVPM5P9+++3XpNdjEH/ZZZeZU205OTlYsmRJjdtYrn/99debU2e1YkOks//A3pFeRKGKqqBee9SLiEhbB/Xs1sds/IQJE/DBBx+YmXJuO0Nvv/22uV/aB9fVR4L6PAX1IiLSbriu/bXXXosG29dee63pes8KvoMOOsjsGS8NW7m+2JwP6pNqzkPVyu9FRETaNKg/66yzzGw8y+KYtecbObH8jU1tuCZO2k4wFMayNQXISI5DGtfVr1+udfUiItKu2Cz3wAMPjK5h5+T+jTfeGOvD6lRWrK+ZqQ+q/F5ERNorqD/00EPN9jM//vijydIzY2/N2nNN3J577tmcl5VGuu/lefh0zhocf8AIHDct0uU3WFqIcMAPm9MV68MTEZFu4NFHH8WYMWNqbCsnjRcKhbFqYyRTP7BPilm6aGXq7crUi4hIWzfKo5133tnsQ2sF9Nxa5s9//rMC+naww+DI1nZzF+fC7ok3ZXphhJWtFxGRdsPdbrgTjjS/8/3gvmlIS/Ygp0cSwr5KhENB0/Xe7tGezyIi0saZegbwbIrDLWy4Ry33lWWGns1ymLm/7777kJoaWR8mrW/HEdnmnCX4xWU+s66e2+BwXb0ro3esD09ERLqBvffeG3fffTe++uorjBgxwmxxVx2D07/85S8xO76OLinBjVv/srvJ0HOs/KWRTvgM6G12R6wPT0REunpQz6Cd6+mvvvpqc/2mm25CWlqaefN+6qmnzD71N9xwQ2sfq1TJSovHgF7JZr/6+UvzMLlXD3g3rVSmXkRE2s0DDzxgzr/55htzqk1BfeNY+9GHKqzSe62nFxGRdgjq3333Xfztb3/DiSeeaPaiXbZsGW699VYcccQRJri//fbbFdS3Q7aeQf2PSzZh1xHDzG2BkvxI6Z5m+EVEpI0tXrw41ofQqfkDIbicW1dBRveo13p6ERFpjzX1ubm5GD9+vLn8+eefmy1srLX03L++pCRSQiZtZ+eRkRL8eUtyYYtLhN3lMQF9sCQ/1ocmIiIi23H+HZ/irFs+wsoNxTW3s1PnexERaY9MfXZ2NtauXYuJEyfi008/xahRo5CRkWHumzdvngnspW2NHpQJj9uB/GKvydj3SO0B3+a18BflmTX2IiIibemqq67a7mNmzJjRLsfS2VR4A1i/ORLEpyd7zHmwwsrUK6gXEZF22tKOb9TvvPOO2dbO2qf+5ptvxosvvohzzjmn2dvjfP3113juuefqfQxL/e+44w7Mnz/fVAhwG70rr7wSffr0MfcHg0HsuOOO8Hq9NZ53/vnn44ILLkBX4XY5cN6fxqNPViL690yGPxwJ6rWuXkRE2gOb5NZWXl6OwsJCsxRv7NixMTmuzmBVVXY+I8WD1CRPrfJ7BfUiItIOQf1FF11kutzOnj0bl1xyCU444QRz+4IFC3D66afjvPPOa/JrPv/887j33ntN9r8+BQUFOO2007DTTjuZwN/n85m1/GeeeSbeeOMNeDwerFy50gT0b731FjIzI1u/Ue2uvF3BPhP7RS+HU7LMeaBoM8LhEGy2Zu9WKCIisl2s1KsLe+1wIp19dqRuK6qC+oF9IjsFhQN+hPyRZIQ9XmvqRUSkHYJ6dmrlnvQ8VffSSy81+bU2bdqE6667zsz4Dxw4sMHHfvzxxyYLwEZ8cXFx5jZm7adNm4a5c+di6tSpWLJkCZKSkjBy5Eh0J46kNNgcToSDfgTLiuBMSo/1IYmISDc0ZMgQUxl3//3345BDDon14XRIK9YXmfNBvVPMObelJbvTbU4iIiJtHtRTfn4+nnzySfzwww9mf/r09HSTZT/11FNrZMi359dff4XL5cLbb7+NBx98EOvWrav3sQzaH3rooWhATyzBJx4DMajnB4rWxn1kOaHQUhUVFTXOW+rn37Zg1q+bMHWHXhgSl4JA4SaUblwNd59IOV9X0drj1p1o7JpH49Z8Gru2Hzdrb/OOipPrDb2fd3cr11dl6quC+mjpvZrkiYhIewX1GzduxP/93/+ZwH7ChAkYPXo08vLyzB71b775Jl577TX07NmzUa+1zz77mFNj5OTkmFN1jz32mAnyubaeli5dikAggDPOOMNst8PjOOWUU3D44YejJfx+PxYtWoTWwmUCreGD2QWYs6wMRYWF+OOwCrjy8hAq/RG+ogC6otYat+5IY9c8Grfm09i17bi53bHN6K5fv36b29jXhhV49913X5tMsHcFoVA42vF+UFX5vdbTi4hIuwf1LHl3Op2YOXMm+vXbuq57zZo1Zk39PffcY9a6tzWuq//Pf/6Da665Jtp9n430QqEQLrzwQtOF/4svvjAdehmUH3300c3+WqwmGDp0aIuPmRkYfmDjUoP4+PgWv14pcjFn2Xys3hLC0P/bFWVzi8HcTcKQQbC7t1Y0dHatPW7dicaueTRuzaexa/txW758OWKNE/J1VQuwioCT7Q888EBMjqujq/QFMGVML+QXV6JvdiSID1VUbWenPepFRKS9gnp2qL/66qtrBPTE63/5y1/Mmve2xA8M//rXv/Dwww/j3HPPxUknnRS973//+5/JFCQmRt4Yubae2YQnnniiRUE9P7i0ZrM9fmBrjdebNKYvHPafsSm/AsXBOCRl9ESgJB+u8nx40lo+CdHRtNa4dUcau+bRuDWfxq7txq0jlN7fcsst2xwHr7P0fsqUKUhOTo7ZsXVkCXEuXHLizjVuCypTLyIi7R3UM2jmGvq6MGNeWhp5c2oLzLgz887gnedcw19d9fX2luHDh5s1+131wwH3rF/w22bMW5yLfQfkmKDet2UtPH26XlAvIiIdw1FHHWUq47jszWpOy6V4CxcuVIVGE4WsRnnqfC8iIs3QrH3PRowYYfaorwu3kmMQ3VYuv/xyvP/++7jrrru2CejZLG/y5Ml4/fXXa9zOrfaGDRuGrmrHET3M+dwleXBlRnoOBApzo9vjiIiItDaunWe/Gm5fZ2FAz51xpk+fbvarl7rL7wPBUPQ6t6G1gnqHMvUiItJeQT33oWdQf/bZZ5vGeN988405P+uss8w6+9pb3TUXKwI4619ZWWmuM1jn61988cUmeOd91omPSUlJwS677GLW9HMtPdcmspEes/TcXqer2nlkpCnhz8vzEHInwJGQapYo+PM3xPrQRESki+JSO5/PhzvvvDN621577WXeqxnQc/JdtvXaJ8tw1BXv4On//Wquh7wVJrC32eyweVThICIi7VR+v9tuu5lGeHwj//LLL6O3Z2VlYcaMGdh///3RGjZs2IB9993XvCbL/Fhyb32QqL1u33oM1/hxb9zrrrsOW7ZsMd132YV3jz32QFc1qE8K0pM9iPc4kVdQgfQeOahYVQT/5rXw9BwY68MTEZEu6Ntvv8UNN9xgdsGpjjvi/PWvf8XNN98cs2PryNggLxyOLJ+r2fk+0QT2IiIi7bZP/RFHHGHK7n7//XcUFRUhNTUVgwcPxvfff49//OMfuPHGG5v8mrU75nP7Ou47b3nyySe3+xps0MO19jx1F2xM9ODl+yA5IbK9UaCUQf2v8BdsRDjoh80R+eAgIiLSWpildzgcdd7HNfVlZZGScqlpS3Gk+jAjJa5G53sG9SIiIs1hb2kwyUz4TjvtZM55nQ1zuE+9tC8roCdHYioc8UkIh4Lw52+M6XGJiEjXNH78eDz11FOmgW11gUAAzz77LMaNGxezY+vI8otqBfVVmXq+b4uIiLRrpl46Jn8gZNbTs2FecO1i0wXf3aPm1oMiIiItdeGFF5otZblMbs8990RmZiby8/NNnx0uf3vuuedifYgdtvyeMlIjQb22sxMRkZZSUN+FsOnOzG9X4Iw/jsW+o3NQuXYx/Fs2mIy9zV53iaSIiEhzcC39yy+/jEceeQSff/65aY7HveknTpxoGuqOGjUq1ofY4fgDQRSX+WqV329dUy8iItIcCuq7kMR4Fyq8QXz24xocMGU32N3xCPkq4C/YBHdmn1gfnoiIdDFsiscdZ6y19RUVFab8nsG9bCu/OLLVrNNhR3KC1SjPWlOvTL2IiDSP2qx2IXvv3A82G/Dr71uwKb8c7qy+5nZ2wRcREWlNXEvPnWaOPfbY6G3z5s3D1KlTcdtttyEU2roXu0TYAEzbKQe7ju1t+hCF/F6EApHMvSNemXoREWnjTP3JJ5/cqMdt3KjGbLGSlRaP8UN74KdlefhszhocPSUHleuXw5+/ProHroiISGvg9rFvv/02LrjgghqZ+0svvdTcl56ejrPPPjumx9jRZGck4JITd45ej2bp3XHaqUZERJqt0VEem6815tSzZ0+znk5iY99JkaZ4n8xZA3tyFuwuj8kEBIryYn1oIiLShbzzzju44oorcPrpp0dvS0tLw6mnnoqLL764yTvhMLN/3333YY899jDr9c866yysWbOm3sdzQmHEiBHbnNau7TzVadX3qBcREWnzTL262HYOu4ztjXiP05TfL1pZgEEZfeDdtMKU4LvSesb68EREpIsoKChAv351764yePDgJlfuPfTQQ3jhhRdw6623olevXrjjjjtw5plnmskDt3vrtq2WJUuWYPLkybj77rtr3J6RkYGOqrzSD7fLYdbUV8/UO7SeXkREWkD12F1MnNuJ3cdHmuJ9OmcNXFk55rJvyzpTSSEiItIaGLh/8MEHdd736aefYsCAAY1+LZ/PhyeffNJskzdt2jSMHDnSNODjxMCHH35Y53OWLl1qMvM9evSocbKa9nVEj76xAEdd8Q7e/vI3cz2ozvciItIK1P2+Czpo6kD0zEgwjfNcaR6zTi/krUCwJB/OlMxYH56IiHQB7LVz5ZVXmq3s9ttvv+g+9Z999hnee+89zJgxo9GvtXjxYpSVlZkme5aUlBSzRn/27Nk49NBD68zU77PPPuhM8osqwfn1pIRI5YE634uISGtQUN8FDe+fbk4WV0Zv+PJWw7d5rYJ6ERFpFUcccYQJxFk2Xz2bzgZ51157LQ4//PBGv5ZVqt+7d+8at2dnZ9dZxl9UVIRNmzZhzpw5pmSfSwHGjRuHyy67DIMGDWr298SKtvLycrQUt/arfm7ZXBh57UQPzNepLM5HyO+HDw4EW+HrdgX1jZ00TOPWPBq35tPYtc+48X2Ju6Vsj4L6boBb2zGo929Zi/CgcY36xRAREdmeE088ESeccAJWrFhhMvbMrnOP+ldffdVk0Zm1bwzrw03ttfMej8cE8LUtW7Ys+mGHFQGVlZV4+OGHzbFwDX5WVlazt+lbtGgRWsvKlSvrDOoL8tZhkXcj4tat5jeBylVrAaca2jY0dtI4Grfm0bg1n8au7cetrr4ytSmo78K+mb8eH89ejXOPGAOX3WHW7gXLiuBMSov1oYmISBfBiWKur//qq6/wxBNP4IsvvkAgEEBOTqSnS2PExcVF19Zbl8nr9SI+Pn6bx3OXne+++85UBVgT1Q888IBZj//66683eys9l8uFoUOHoqU4ScEPbAMHDowev9cXRKU/0pl/4oRRiIMXZUVLYLPbkbjDeE24NzB2sn0at+bRuDWfxq59xm358uWNel0F9V3YO1//jl9/34IvBmXgD716mWZ5zNYrqBcRkdbANfTcuu6VV17BunXrkJSUhCOPPNKU3jdle1ur7D43Nxf9+/eP3s7rbIZXl9pd7vnhiBMJLMtvLgbWCQkJaC08Juv1isoj6+c9bgcy01MQKNwEn8sFR0IKEhPVKK+hsZPG07g1j8at+TR2bTtujZ3wVff7LmzfiVV71s9eA2dmX3OZW9uJiIi0xPfff2/2ot9rr71w7733RoPyBx98EDfeeGOTAnpit3tOCMyaNSt6W3FxMRYuXIhJkyZt8/iXX34ZU6ZMqbH+vbS01GQ/WiPT3hbyiyvNeUZKnPmQZnW+d8SrSZ6IiLSMgvoubLfxfcx+uOvySrGqLN58iAiUFSFYXhzrQxMRkU7o6aefxh/+8AeceuqpJuA+77zzzPZ1DOYb28ynvvWC06dPx5133olPPvnEdMPnpAH3qz/ggAMQDAaRl5dn1s7TnnvuiVAohMsvv9ysr1+wYAEuuOACk70/6qij0BElxDkxbaccTBrd01wPVVrb2SmoFxGRllFQ34UlxLmw67hI9uSTeZvgSo9c9m6I7I8rIiLSFLfeeqsJwJ999lmzR/25555rAu/WWA/OPeqPPvpoXHPNNTj++OPNfvNco8917hs2bMDuu++OmTNnmseyMoATDMzU87GcZGCDPh4Xm+t1RIP6pOKSE3fGWYePrbWdnUrvRUSkZbSmvhuU4H/+41p8+dM6nLLHOCB/PXybViB+4A5m/3oREZHGOuSQQ0wm/c9//rPZU57r5/fee+9WeW0G8dySjqfauFae+9JXN2bMGDz55JPorEJV5ffK1IuISEspqO/ixg7tgazUOGwuqsS8DcDY+CSzjs+3aRU8fTrmukMREemY7rrrLrN2ndvGscs8S97ZgX6//fYz2Xp1cK9fabkPcR4nnA67WaoQrMrUO5SpFxGRFlL5fRfnsNuw98R+GDkgHfFxLnj6DDO3V65fbj5UiIiINAUb2rHknXvRM7hnp3uuq+d7ytVXX41//etfjd6Cpzu55enZOOqKd/DNz+sR9nsRDvrN7XY1yhMRkRZSUN8NnHjQKNxx4Z7YeWRPuHsOhM3hRLC8CIGi3FgfmoiIdGLDhg3DlVdeafamv//++81+9f/+979x2GGH4Y9//GOsD69DyS+uAOfSUxLdW9fTe+JhsztifWgiItLJKajvJtl6i93phid7oLnsXa9MioiItJzT6cT++++PRx55BJ9//jn+9re/IRAIxPqwOuSWdpkpcdHO9w6tpxcRka4W1D/66KM46aSTGnxMQUEBLrnkErNv7eTJk/HPf/4TFRUVNR7z3nvv4eCDD8a4ceNwxBFH4LvvvmvjI+8cSsp9+OzHNXD3HmKu+zevi67pExERaQ1ZWVk466yzop3qBSiv9KPCGzSX01PiEIxuZ6f19CIi0oWC+ueffx733ntvo7a8WbVqldnKhuv2WPJ3/fXXR+///vvvTefc4447Dm+88Ybpznv22Wfjt9+69zZuPn8QZ978Ee5+YS5+zw/DldYTYYTh3aBsvYiISHtk6blXfbzHubXzvdbTi4hIVwjqN23ahHPOOQd33nknBg6MlIXXZ968efjhhx9w2223ma1sGLDfcMMNeOutt8zrENfysQvvySefjCFDhuCKK64wj33mmWfQnbldDuyyQ2Sf+lc+XhrtfO/b8DvCQZVIioiItHVQn5ESZ86tNfUqvxcRkS4R1P/6669wuVx4++23MX78+AYfO2fOHPTo0cME6xaW4HMLnR9//BGhUAhz5841wX51U6ZMwezZs9HdHbPvMHC3oVm/bsRab6LZRicU8MGXtzrWhyYiItJl5RfVDOq3lt8rqBcRkS6wT/0+++xjTo3BbHzv3pFss8XtdiMtLQ0bNmxAcXExysvL0atXrxqPyc7OxsaNG1t0nNyqh6/dUtb6/9p9ANpDRpIDU3foiW8XbMILHyzG+XvkwL/6F5Ss+BWB5J4den/hWI5bZ6exax6NW/Np7Np+3Pie1JH/ZktNmWnxmLZzDvr3TEY4FETYGwnytaZeRES6RFDfFPygwyC+No/HA6/Xi8rKyJtk7cdY97eE3+/HokWL0FpWrlyJWBjfD/h2AbP1uZiYk4F+hVuAvDx4g4kIx6eio4vVuHUFGrvm0bg1n8aubcetrvdD6ZjGDskyJ2KDWva04VZ2Npcn1ocmIiJdQKcK6uPi4uDz+ba5nQF7QkKCCd6p9mN4f3x8fIu+NpcIDB0aWYfe0okJfmBj/4CWHlNzjALw48r5+GFhLn5a78bknXeGP3clXEk2xA3nvR1TrMetM9PYNY/Grfk0dm0/bsuXq8lpZxX2R5IMNpdb1RYiItL9gnqW1X/88cc1bmMAX1hYaErsWYbP4D43N7fGY3i9Z8+eLfrafOPla7cWfmBrzddrihMPGo0fF+chMcGDpAHDUFqwDraSPMQ5ALsnNsfUGcats9PYNY/Grfk0dm03bgoGO5fCEi8S411wOe3RoN7uVJZeRES6SKO8puDe9Fwbzy3tLOyGTzvvvLP5kLPTTjtFb7PMmjULEydObPfj7agG903FU9cegAuOnQB3SgacKVlmfaZ3Q/fe9k9ERKQtXHb/lzjqinewZFU+QtFMvYJ6ERHpBkF9MBhEXl5edK08u+MzaL/44ovx888/mz3pr732WhxxxBHRTPxpp52Gd999F0899ZTZm/722283a+FPOeWUGH83HUt6cqQDL8X1HWbOGdSzgY+IiIi0Dk6aW93v05LjEA5ElggqqBcRkW4R1LOj/e67746ZM2ea68zEP/DAA8jJyTFB+kUXXYQ999wT119/ffQ5fPwtt9yCF198EUceeaQJ/B955JEa2+DJVqs2FuOz5UHYPfEme+DLWxPrQxIREekySiv88AVC5nJGigdhX1Xne5caHYqISBdcU3/rrbfWuM7gfcmSJTVuy8zMxH333dfg6zBzz5M0bG1uCc6/4zM4HTaMOyUHHu8yeNcvg6fnwFgfmoiISJdgZemTE9xwOR3wqfxeRES6U6Ze2lZOdjLGDc1CIBjGOwuDsNnsCJTkw5+/IdaHJiIi0iVsKY4E9ZmpkWVv0fJ7NcoTEZFWoqC+mztu/xHm/L3ZG+FN7W8ul/8+H+FwpFRQREREWp6pT0+OBPHR7vfK1IuISCtRUN/N7TAkE2MGZyIQDOHd5S7YnW4Ey4vg27gi1ocmIiLS6eVXZeozqjL1W7vfa029iIi0DgX13RybD/7ffsPN5Zmz1sGfNdRcrlj1C8JBf4yPTkREpHPr3ysZe++cgzGDMmtk6rWmXkREumSjPImNCcN7YET/dCxZXYD/LQaO6p2EYEUpKtcsRvzAsbE+PBERkU5rlx16m5O1vZ21pl7l9yIi0lqUqZdItn7/4UhNciMzPQHxA8eZ2yvXLkHIWx7rwxMREekSGNAzsCdl6kVEpLUoUy/GxFE98fjf90ec22k+cDhTshAo3oyKlQuQOGJKrA9PRESkU9pcWIHUJA9cTjvC/qrO9w4nbHZHrA9NRES6CGXqJZqtZ0BvXY4fNN5c9m1ahUBpQYyPTkREpPMJhcI48+aPcNQV75jgPhxQ53sREWl9CuplG7N+2YArnvoVoZQ+CCOMit9/ipYLioiISOOUlPsRDEXeP9OSPVs73zvV+V5ERFqPgnqpgVvbPf3uQixbU4hXF7lMeaC/MBf+/A2xPjQREZFOpaAkEsSnJXngdLD8viqod0e2txMREWkNCuqlBn7oOP+YCebyzDmbsN6WbS5XrJiPcDgU46MTERHpPApKqvaoT4kE8daaertT5fciItJ6FNTLNsYMzsRBUweayw9+UY6w3YVgeTG8G36P9aGJiEgXFQqFcN9992GPPfbAhAkTcNZZZ2HNmjWNeu7bb7+NESNGYO3atehICkoiQXxGaiSoj5bfu1R+LyIirUdBvdTp1ENGIyPFgzVbvPhiQ5K5rXLVLwgH/LE+NBER6YIeeughvPDCC7jxxhvx0ksvmSD/zDPPhM8XCYzrs27dOtxwww3oiAqKI0F8ZlVQHy2/V6M8ERFpRQrqpU6J8S6cc1Rkv/rnfihHoc9lMgwVaxbG+tBERKSLYeD+5JNP4sILL8S0adMwcuRI3HPPPdi4cSM+/PDDep/HwP+yyy7DmDFj0JHX1EfL79X9XkRE2oD2qZd6TR3bB1PH9sZ3CzZgflkP7OVeD+/apXBn9YMzOSPWhyciIl3E4sWLUVZWhqlTp0ZvS0lJwejRozF79mwceuihdT7vkUcegd/vx/nnn4/vv/++xcfBnV7Ky8tb/DoVFRXmfGCvBOw5oTf6Z8eb160sK0HQ74c3EEKwFb5OV2SNnXUujaNxax6NW/Np7Npn3Pi+xO3Gt0dBvTToz0eOxf6T+2PiqJ4oW/QtfJvXomzx90jZaX/YHK5YH56IiHQBzMhT7969a9yenZ0dva+2n3/+2WT3X3vtNWzatKlVjoMTBIsWLUJr6Ztcjr6jHUBoMxYt2gzP2tWw+Srg86xBKLe41b5OV7Ry5cpYH0KnpHFrHo1b82ns2n7c3O7t92FRUC8NykyNNydKGDYRgZItCFaUoHz5PCSOmBzrwxMRkS7AyljU/uDi8XhQVFS0zeOZ9b700kvNaeDAga0W1LtcLgwdOrRVvh9+YOOxxcdH3kOptPQ3hAM+JI4cDXtCSou/TldU39hJwzRuzaNxaz6NXfuM2/Llyxv1ugrqpdEKK8L4YnM29kpaBe+mFXBl9IK7R/9YH5aIiHRycXFx0bX11mXyer11fui56aabMGjQIBx33HGtehwscUxISGiV1wqFw+COdimpHricDrMtrNcGhF0uJKSkwa696hvEn3tr/Sy6E41b82jcmk9j17bj1pjSe1JQL41S6Qvgors/N01/HFMSsXuvMpQvmwNHciYccYmxPjwREenErLL73Nxc9O+/dbKY17lVXW3//e9/TVZ/xx13NNeDwaA559r7c845x5xirawyhBvu/hoOuw3/ve0w2AI+hBE292lLOxERaU0K6qVR4txOnHbYGNz9wlw8PsuPvnvZMSjNj7LF3yF5/D6w2bSRgoiINA+73SclJWHWrFnRoL64uBgLFy7E9OnTt3l87Y748+fPN13wH3vsMQwfPhwdQUlFZKIhNcljAvtg1XZ2dqdb75kiItKqFNRLo+29cz+sWF+MNz5fjnu+teOfe/mQji2oXL0Q8QN2iPXhiYhIJ8WsO4P3O++8ExkZGejbty/uuOMO9OrVCwcccIDJxOfn5yM5OdmU5w8YMKDG861men369EFaWho6gpLySFCfUbVHfahqOzvtUS8iIq1NU8XSJKccMho7jcxGkd+Jx+bYUekNoHLVQviLcmN9aCIi0olxj/qjjz4a11xzDY4//ng4HA488cQTpnndhg0bsPvuu2PmzJnoLKxMfaa1R73fZ85Vei8iIl0uUx8KhfDAAw/g1VdfRUlJCSZNmoRrr70W/fr12+ax999/v3lsXY466ijMmDHDXD7ttNPw7bff1rh/8uTJeO6559rou+g+WEJ42fSJuOTeL7BwM/DWL/k4ZkcHyhbPQspOB8CuDISIiDQDg3iW0PNUW05ODpYsWVLvc6dMmdLg/bEM6jOiQX1V+b3eJ0VEpKsF9Q899BBeeOEF3HrrrabMjuV2Z555Jt55551ttrY5/fTTt+l0+9RTT+HFF1/EqaeeGr2Nb+zXX3899ttvv+htnOmX1pEU78I1p0/Bpfd9icX+HPgdZbB7y03jvMRRuza6S6OIiEhXVVIRqll+XxXU25wK6kVEpAsF9dy65sknnzT7zE6bNs3cds8992CPPfYwTXDYxba6xMREc7Kwgc6zzz6LG2+8Mdodd8uWLeY0fvx49OjRo52/o+6jX89k3HD2VHPu9hWjZP4n8G1eC9fG3+HpPSTWhyciIhJTxeV1Z+q1pl5ERLrUmvrFixejrKwMU6dOjd6WkpKC0aNHY/bs2dt9/g033ICJEyfiyCOPrJGlZ6aY+9dK2xoxIAMJcS44UzIRP3Ac/P4gypf/CH/++lgfmoiISEwN6xOHvXbsjYG9U2qsqVf5vYiIdKlMvdWt1tqf1pKdnR29rz6fffYZ5s2bhzfffLPG7UuXLjXdcRnwf/PNN0hISMBBBx2E8847b5ty/qYIh8MoLy9HS1VUVNQ47wo4Nm//EsDvswpx/MR4+Od/gfjRu5s97FtLVxy39qKxax6NW/Np7Np+3Ph3V0udOrYpI5IwatQo8zmkZvd7NcoTEZEuFNRbH1xqB9sejwdFRUUNPpdr6ffee2/zhlk7qPd6vRg3bpxpmLdo0SLcfvvtWL9+vTlvLr/fb16rtaxcuRJdRSAYxudzc7GhpDc8P67GPoPz4d78Fnx9xyHs2bpcojV0pXFrbxq75tG4NZ/Grm3HrSUT1dL+VH4vIiJdMqjnXrPW2nrrMjEoj4+Pr/d5DNBnzZqFxx57bJv7mKG/4oorkJqaaq4PHz7cNMm7+OKLcfnllyMrK6tZx8rXGDp0KFpjIoMf2AYOHNjg99jZXNNvMK57fDa+LuwHz6o1OHTHRPQM5iF+0CjY41oe2HfVcWsPGrvm0bg1n8au7cdt+fLl7XZc0nQ+fxAFpQH4A5FmeaTu9yIi0iWDeqvsPjc3F/3794/ezutW47u6fPzxx8jIyMBuu+22zX1OpzMa0FuGDRtmzlnS39ygnmWOVglda+AHttZ8vVjj93LrX/bA3x/5Bp9tyYFj3iocOtEJ92+zkTB+H9jdWydtWqKrjVt70tg1j8at+TR2bTduKr3v2FZtLMW/3t6IrC8K8dS1B5rbQtY+9ep+LyIiXalR3siRI5GUlGSy7pbi4mLT1Z771ddnzpw5Zt95BvC1nXTSSbjqqqtq3LZgwQKTaWf2Q9pOdkYCZpy3O7J7pOLTgn6YOXsjCjdvQekvXyIc8Mf68ERERNpFQUkkK5+eEgngw6EgwsHI+6DW1IuISJcK6rkecPr06bjzzjvxySefmG74LJPnfvUHHHAAgsEg8vLyUFlZWeN5DPo5IVCXAw88EG+99ZbZu37NmjWYOXOmWUt/xhlnmAkEaVtZafG4hYF9zwx8XtQfGwr9CJQWoHThN+ZDjYiISLcJ6pOrgnorS89/TgX1IiLShcrv6cILL0QgEMA111xjgndm6J944gmTWV+7di323XdfzJgxA0cddVT0OQz009LS6nw9ThKwLPG5557DLbfcYvaqP/XUU3H22We343fVvXFP3lvO3R2zft2IiaOTULLgc/gLN6FsySwkjtwFNltM55JERETaVEFxzaA+FG2S59bSCRER6XpBvcPhwGWXXWZOteXk5Jh952ubP39+g6954oknmpPETlqyBwfuMsBcThq9G/J/+hxFvy83AX3C8Emw2R2xPkQREZE2kV87Ux/dzk7r6UVEpAsG9dL1+eMz8fhPHvQo+g17B0Po5atE4uhdYVcJooiIdOHy+wxrTb0634uISBtSUC9tLhwGipxZWF7WH77ZqzGl1Ivhvkok77BHq2x3JyIi0rHL76vW1CuoFxGRNqDFzdLmEuNd+OfZUzFszAh8VzEYX/26Bd/NXoLCuR+bJnoiIiJdyW7jemH8oAT0ykyokalXkzwREWkLytRLu4j3OHHVKZPw2qdpeO19J/xrfkdhyWLsXl6JnjvvBVd6r1gfooiISKs4cq9BGJldiez0eHNd5fciItKWFNRLu2HH32P2HY4hOWm49z8e+AqWwTl/Nfb1fImEYZPg6TUo1ocoIiLS6kJqlCciIm1I5ffS7nYakY3bL9oXlTmTMWX3iQiHwyhb+gMqVv1qLouIiHQl0fJ7BfUiItIGlKmXmOiVmYib/7KHCeIrVy5AxZpF+G329+hdsBnpY3ZRiaKIiHQZ4apGeXaX1tSLiEjrU1AvMS/Jjx80Dks3efHVT+8jcfEmTFq9FiP23A+utJ6xPjwREZEWC0Ub5WnCWkREWp/K76VDcPUcjGXxY5FX7sAXPyzHh8+/iM2LfkQ4FIz1oYmIiLSIyu9FRKQtKaiXDmH0oEzcdumhyJh0ANYGM7FyQxHeevV9zPvf6wiWl8T68ERERJolHAxEJ6i1tExERNqCgnrpMOI8Tpx55I445c8nYGPyaJR4ge9+WIgPnnka/txVgJroiYhIZ83S2+yAQ6seRUSk9Smolw5n5MAMXHvJUei568EoDCejZ5oHlb/9CNemxQj5K2N9eCIiIo0WqmqSx9J79pERERFpbZoylg7J5XTg+EN2xLpJQ5BRsQYlv/0ER0kuln30Jlz9dsCYyRMjWQ8REZEOLFy1R70634uISFtRUC8dWt/sFABjEIhPhf+rmZi3cAMqflqDn2fNxa5/OBADhw2K9SGKiIjUS03yRESkrSnVKZ2CIykDZb0nwDVgPIJwoiB3E2Y+8yxeeeJF5OUWxPrwREREGt7OTkG9iIi0EQX10mnEeRz409H74KjzzkFSzlCEwzbkrViKl+9/CG+8+gFKyyMfnEREpPMJhUK47777sMcee2DChAk466yzsGbNmnof/+uvv+KUU07BjjvuiF122QXXXnstSkpKOmym3q496kVEpI0oqJdOJ6dPJk4550Tse+KJSMzoAVs4gPXzv8f6r/8H3+a1CKtLvohIp/PQQw/hhRdewI033oiXXnrJBPlnnnkmfL5Io7nqNm/ejNNOOw19+/bF66+/bp77448/4sorr0THzdRrTb2IiLQNramXTmvk6CEYPvLPmPftHBQsmYesuABKF34DZ2Ia5pdmYvDoEejbIznWhykiItvBwP3JJ5/EpZdeimnTppnb7rnnHpO1//DDD3HooYfWePy6deuw++6744YbboDT6cSgQYNw7LHHmud0NFpTL7EUDAbh9/tjfRgdltfrjZ7b7cp1NoXGruXj5vF44HA40BoU1EunZrc7sPPuUxCaMgHedUtRuW4ZSrbk4ZevZuGbDz5D4uCxOHD/yRg+ICPWhyoiIvVYvHgxysrKMHXq1OhtKSkpGD16NGbPnr1NUD9+/Hjcfffd0eu//fYb3nrrLey2227osOX3CuqlHbFqcePGjSgsLIz1oXRorAjixOD69esVmDaRxq7l48b/o2lpaejVq1eLtzxVUC9dAj8sxQ8cC0/f4Sj99SdkZ21GKK8IWDkLrz26ALbeI7HPtJ0xcXQvOBz6wyMi0pHwgw317t27xu3Z2dnR++pz4IEHYuXKlaYU/4EHHmhxIFReXo6WqqioiJ6Hy0sR9PtRGQgh0Aqv3dVVHztp/rhxiUppaSl69OiB+Pj4FgcMXRX/z7NSyO12a4yaSGPXsnFzuVyorKxEXl6eqabJysqq9/GNGV8F9dLlgvt+E6ag75gJWD1/Ln79YTZWbyhEaNNcfPLiYrwe1xenn3QARgyq+z+OiIi0PysQ4YfD6liaWFRU1OBz77zzTvP8O+64AyeffLLJ2CcmJjbrOPjBatGiRWgtnGzwrFsDW8AHb9xqhOPyW+21uzqOnTR/3Jg57dmzJxISEmJ9SB0agyX+nZGm09i1fNz4/5OZ+k2bNpngvj613xvroqBeumxwP3DiVPQftyNyF/+MX36Yg5Xr8pERWI60tXGosI+Ap/cQ5JeHkZ7M9SzK3ouIxEpcXJw5Z/bCumytOWSWsSFjx44158zS77XXXvjoo49wxBFHNOs4mDkZOnQoWoqTDAyuBgwYgFDRYpNpSRw9BnaPAqzGjt3AgQO3+7OXuseNAT1Le7mEpfr/J9kW/29aa5uVbW4ajV3rjBuvFxQUoE+fPnVOkixfvrxRr6ugXro0uzsOvcZNRvbIcShbtwwbFv8KV9iPilW/oHL1Qrz8QykWlqZhl8kjsd+k/uid1bzsjoiINJ9Vdp+bm4v+/ftHb+f1ESNGbPP433//HatXr4421SNmJa2MR3PxA1ZrZjbj3U54nZGPWokpabA59LGrsRjQK8vcdBw3BvU8cd1uazXh6sqNBK3/+xqrptHYtc648f8p/7/y/25dk3CNnTCxd7Z9ad9++23zBl/7tHbt2uhj3nvvPRx88MEYN26cma3/7rvv2um7kY4c3CcPGothBx6DpJG7wJmcgUqvD3Fl6zDa/zNWfTkT193+Ki655zO8+cVv2FKktXwiIu1l5MiRSEpKwqxZs6K3FRcXY+HChZg0adI2j//2229x4YUXmsdYGOQz2zFkyBB0FOFAZDs+m92hgF5ERNqMvTPtS0tLlizB5MmT8fXXX9c4WbP833//PS677DIcd9xxeOONN0wn3bPPPtt0xhXhByt39gCk7Lg/ekw+CEcftTd2G98Xo3uEMcG9Cv03f4Pv33sfF930Jp5/r/XWVYqICBpcLzh9+nSzPv6TTz4x3fAvvvhi0xH4gAMOMJkNrjdkUyFiN3xm5fl+v2zZMsyZM8cE+ZzM33vvvdFRhP1VQb0634uISFcN6q19aflGzBI6ztRzj1l2uuW+tHVZunSpycyzm2f1k1X28e9//xv77befaZbD2forrrgCY8aMwTPPPNPO3510dM6UTKTusBvG/fEE/OGoA3HkAeOwy6gs7JRZhl08SzHK9xMq1yxGyFuB3PxyfPzDKhSWRLYmEhGR1sXPAkcffTSuueYaHH/88eZ9/YknnjDr3Dds2GD2pZ85c6Z5LAN6632dj/3LX/5itr/j4ztSGWg4oO3sRJrrpJNOwlFHHVXv/fxbwd0vtuf+++/HPvvss93HXXLJJSbG+Pjjj9GdPf3007jpppsaPXb821u7gprbjrJq+tlnn23y1+d683/+858mMbvjjjuan0t+fsNNRteuXYs///nP2Gmnncx7xb333hstc7c8//zz2Hfffc3k7wknnGAqwer7+n/84x/x+uuv17j9/PPP79C/G87OtC+tlamv75eLWf65c+fiyiuvrHH7lClT6p0kEGHjIm6HFzdgB2QVbsIOm1Yif80KxDmB8hXzUbHiZ/y0Loz/zqvAg6EUDBvQA5PH9MLk0T3Rr2eymoOIiLQCBuPMvPNUW05Ojnn/r27QoEF49NFH0ZEpUy/SfJzku/zyy021be1lNQy83n//fRPItYaSkhITsPHvCiuHmSDsjriMiQnXd955p0nPu/rqq00Qb2EQ/uKLL+Lmm282W7VVv297rr/+elN9xQkFVnFdd911ZtL3P//5T727lpxxxhmmSSR/dvwe/v73v5t16nwesXr79ttvN5XhjDMfe+wxnHbaaWbJdkZGRo3fg4suumib9xviexMnmiZOnGgmljsaZ2fal5bb2rABDn/QLNnn2jnOtnCQ+Z+Qa+u4vyzL9RrzerHeu1Y64Lh5UmDrPw4ZfUYisGU9/HmrECzZgpRAMfbKKMaWkjXYvD4ZH61JxfPvpiIzIwkTR/bAUdMGIynehY5Iv3PNo3FrPo1d249bY/etldhSpl6k+ZiFZxDGAJOBVnUMwPm3srk7XdT27rvvmonF8847z1T5MvPLycTu5sEHH8QhhxyC1NTUJj0vOTnZVE5beJnBOJdIs8KqsUE947w333wTjzzyiAme6e6778ZBBx2EefPmmcx9bR988IHZ7eGVV14xxz18+HBs2bLFBPHnnHOOmRjg63GJFzPwdMstt5iJm1dffTU6MfTpp5+a37f09PQ6j427mbD/G6vE/vrXv6KjcXamfWm5bs76MDNjxgyztu7hhx82JRT8Dx8IBOp9Pc7otURb7F0rnWDcHNmwJSQhvmcuxiU64CsrxZYSLzYXr0d+6VrklSZh4Y9p2LFPJZxVv3e/b6xEUpwDPVKdHepDt37nmkfj1nwau7Ydt8bsWyuxpUy9dDSV3shn5brY7Ta4XY5GPdZmt8HTzMc2FjuBM8D83//+t01Qz8wrt7Bk8MiluXfddZep1mVswZ0wTjzxRJx++umN/lp8PfbsYnk2l/wwQPzb3/5W4zFfffWV2TqTlcYMHo888kiTCeZkAOME9gljQMosNSsLWDa+2267mQagXBbMfiHWREHt25gBZqaZr71ixQpce+21JpDlsmQGrdwJhLtBsLqZwbKVXd68ebMJXr/44gsTBzEQZtacQfaee+5pyuirT3xwnNho9L///W+dATUnN5g4bQ38DMz3KXZ3r/4914fZ8R9//NFc3mWXXaK3M3HLnymruOsK6pnsHTNmTI2JCD6/tLTUxG4cX76vVq8M5zFxrPiaVlDPiSL2ZGMG39oqtTZOTnD8OVlQ1/Zz3Taob+q+tBx8drLnDIoVLPE/F9fjc93DMcccE3296hqzz217712r/Vc737hxMilUUYxBW9YjmL8O3uJC5BZUoMJbjkEVv8PuzIQzvReeeX8zVuSHkZ4ch7FDMjBuSKY5T0v2dNux64w0bs2nsWv7cWvsvrXSQbrfuzQBIx3DMVe/W+99E0f1xHVnbg2mpl//Pry+muuSLTsMycSM83aPXj/j5o9QXFZ3k+uh/dJwz0V7Net4//SnP5mS6upZWjbNZGDKrDL/bjJ4Z/DMxzHAZvb1tttuM0HcqFGjtvs1WN6/YMEC85zExEQTVzDoveCCC8znf+LXZ+NtBnzM8q5bt85UCjM45ONYZs7gmwEfy7v5fAZ+b731VqO/Vx73HXfcEe0dxmD9s88+w6233oq+ffuaoPeqq64yCU2WlzOI5/fOY+CEAkvC+Vg2HOfSBH4fnGSwgnouU+YuYvw+6sKJAS6DZhV0S7G6meXyHFtrSRV/fszcN4QTC4zzagfMDVVd8/ZedVRpE/uxWJMKdVWGcxLFwp/r9nAiiZXhnHzYdddd0ZE4O9O+tFR93QPxgw9nYPhLwF9mzmLx+dXxOmd4WqLV967V/qudc9wSE4Es/t7ujGBZETI2r4V/8xoEyoqAiiL4SgowLX4dBiUEsbEyCYt+zsPXPyUhBDv69kjCtJ1zcNz+df9ud/mx66Q0bs2nsWu7cetIVUDScPk9f1J2Z8fK6Ih0FgwwWU7NilwrqGdgmpmZaTLRrOxl9peZeQbkxOz5448/boLgxgT1fD0GkdY6elYHMEBn5vYPf/iDue25554zzd+4xp+Yib/hhhtMmTczwq+99hr+8Y9/mOw6cfcOJoN4X2PxWA877LDodWaL+XpWGToDewaSrEwgJjr5PTKAZzabmJlnozuOCydEuJyAMRLjID6eVQR19Syjn376CcOGDUNzcDKDpevE75sJVTZAZ8M6a0cSZu2rl+jXhZM0dVWhNVR1zcrtlJSUbR5PfE5DleFNreS24k5O8iior2dfWiuot/al5bqH2l5++WWzroKzVtYHHv5nYWaDzTT4IYddD3/44Ydo1p74+tZ/CJHW4khMRTxPA8YgWFECf/4Gc9p7ktPMnm4urMDGLYVYt2Ujlhc6sTk/GaX5cQiHh5vfVX8giPte+QmjB2Zg9KBM03SPpW8iItJ1yu/5V13l99JRvHrLIfXeV/szyH+ujwSo9ZXUV/fE3/dv9GObisEpm2KyrJxZV2afWfrOrDyTfVyGyxJ9xg9skmZlX5mZ3h5+XuOab04QMCYhZrg5QcDMvxXUM5BmNUB1Vud9ZvlZfs+gvzqrfJ9xSGNwzXZ1hx9+uKlI4FafjHV+//13U5pvxTQ8JpacWwE9MXhnTwDi98TJD1YLMDvPJQZcXlDfenmW8vPxzcGJFG4/yvFk8znuRHLsscdGx88qkz/rrLPqfQ0Gyqzcrmtb84aqrut6jrcqWGe8WL0yvLGv2RD+znGsOhpnR9mXlgPEGSiWnVTfl5YzSlwXwh8Ifzn5WM6SsUEBZ2YY5PO51pYXLIvhLy5LX/h4lr9wPQXLYkTaiiM+GY6+yYjrOxzhoB/+wlwkbFmP3gUbMN5bAZ8/iM0FFYiPW46i7/PgTOuJNeUezJr7Gz7/cQ3f8pAQ58TwfukYMSByGjkwA8kJKtkUEen85fcK6qVjiPM4Y/7YpmJzM37+/+abb0ymlz22uPzWKsX/v//7PxMLcHcsbmfGDDfLpBuDJefMtjMrz9jBwhiEwTiDaAbNVgl3XawS/aaovd0aVV+KTFxXz4oBls/ze+PWnQyWmXmnho6JOOnB57LKgfEWv8d//etf9T6e3eLrOq7G4GSANSnBrd+sLvacQLCa5O2www5mQqYhjAELCwtNAF49s95Q1TWfs7SqeqH644nPqV4ZXn0XheZWcnOMOFYdTUyDemtmh7M63GuSQfqkSZOi+9Ky8yRnlNgUj0E7fygsKWGTB+5Ly/IOzppxD0SrzIL/mbkmgmtL2FyC6+DZ8bD2VhgibcXmcMGd2dec+DvKMv1AwUYkFm5CoCgPIb8XvrzVSCz34fzRxVhbFMLiLXbk+uKxdHkpflrGP0Q2nH7YGBw5LdLHoajUi7W5pRjcNxXxbfjGKSIirSfs9/LPubrfi7SAFbAzo87t0RgrWAEkM/QMAhn8WsG1tR0ZP4NtD3tycfnuU089VSNIXrNmjSldZ8M8Zr4ZRzAjXx27oPPrMw7h1+b9rEK2MFPNgNZao169FH97DVG5wxcrlBnLVO8cz2y9Va3MGIdl9qtWrYqOB5OhzI6zsoGd2lnl8O9//9ssH2CSlHFSfThh0loNbs8991zTWJBl+aws4Pp1TlrUrkaobeeddzYVFlyzbjW248QKJzL4c68Lb3/zzTfN+FrVFt9//72ptuDPg5MDnJjhJI31mow9WTnAKo+m4hhba/Y7Emdn25eW3Q25f2JDOCvVWltciLQEy+ydSWnmFNdvJMKhIAIlWxAozIWrMBfJiXHYIRzCgaEwisq82FxYiE3FAfxW6MDIhN4IFG+BIykNc5fk4u4X5oLLaLk2f0jfNAzJScXQnDQT6Cd20O30RES6LQYUzNS7XGqUJ9JCXGZ76aWXmrXTbExXPUvLNdNcV86AkEEvk4FUVxl3dSyhZuDJzvPs5cWYxMJ1/OyGz6Cf6+PZfI4BMjPdLItnIM0EItfzs4SbmXDexwkIrkvnGntmj9m4jgEgA3Hujc4u/nwuJxEawuCUQTi74zP2YeKTjed+/fXXaJk/A1RmvznpwKUJPA421+Mx8DnEYJZLk3ms/D6rf4+1cfKBkyMMqqtnovm1v/zyy20ez69Ru7rAwq/DKmnGY1xrzz3nG4OZc/Y0YLKXSVp+T5wY4M+CkxTWz5WTGawCYMDOXgj33nuvGVv+jjApzEpuNhG0sv28zOPhpAIrOfiz4PfF36um4GQLt89rjWaCXS6oF+lObHYHXKnZ5oQBMKX6gaLNJoPvLt6M9NR8DA0FYVZtVa5A8U8rzHM8uWFMSi3G6hInNuf5sDa3BF/MWxt93Zv+vCvGD480H9lSVGG61fbMTIRDa/RFRGIjFICVJ7Q5FdSLtAQzzAyMmZW31rITG8kx0GXwzEwtl/KyrxaDYWbOWdnbUIM8ZvOr9+Gqjkt6mXHmGnEG8uy2f99995nMNwN1BvS831o/z0CWAWhJSYnJEDNwHDx4sLmfy4u5hIBZd97HQJzl9PVh5p+TBPy+2DyPAeyUKVPM12EWnhMZDHgZrHMSg8fKRBK3cmOTwOpLAljtzO3+2IegIayG4PGzNwEnCyxcnlDXWnhWTzcU3LKSgDsAMKD/6KOPsP/+9fddqI6TAAzorTJ+LqdmkF997T3HnhUSHBNWaz/++OP45z//aaojOFbMwLPSwsLb+XNh8M/fIX5/nFip3YB9e9i3jRNL9VUNxJIt3JjalG7OKrepb8/Cpm7xwDX+7HCprtCN113GjZn8YGlBJNAvzjPnoao1mdY+sAUllcgrC2NtiRPLC+xYWWjHnVcehqzMSOOT/7y/CC9/tBQetwMDeiWjb48EuMNl2HnsEAzrn4XM1Dh1zm6E7vI71xY0dm0/bq35viRt816/eP6P6Fu+Cp74BKTtGun7I9unvx8tHzdmWa214PVlUmXr+mhmbDlODWWxOzMG1Wy49+KLL273sZdccokJirmef3u6w9jVxj3tOSnD6o3mqj1uvNzQ/9fGvjcpUy/SgTAr70zJMidgpJlBDpUXR0r2S/LhLMlHfFwhemeFYc2NMitv/+U9FMUnwZGUjriCAvRxl2Kzz4Olq4NYurrQPO6DuXPN+aNX7Ys+WZE1R4tX5aO03G9K+rPT4+FwdLzGHyIinVLQb87UJE9EYoHr0hksMqPN7fcag9lxZrl53tQsdlf322+/mQD7tttuQ0ekoF6kA2NGnVvn8eTpFSnhCgcDkWx+Sb45OUq2IFhZFj3t0xfYu48DpeUVyK+owPoSG5Zv9iHXm4j1pQ5kp22dBXznq9/x5bx15rLTYUfvrAQT8OdkJ6FPjyRM2ykHblf3mH0VEWlNNiuo1x71IhID3AKc6/DZC6D61nINYbb4jDPOMLsLNCZb351w+QTHhI0VOyIF9SKdjM3hhDO1hzlZ2FE/WFYYCfZLCxAsLUSKrQTJiWH0SfVjoKcIWT3ccDrCKPnuDTgSUuBITMNQVz6KeoWwYnMIxQEH1mwqNadZv8Ksx993Yr/o1/jPe4tMB/7eWYnRU5+sRKQnx22zt62ISHdnCwbMuTrfi0gssGkcT03FpoCyrYcffhgdmYJ6kS6AHxrtaT3hStu63yab8HE7vbLNGxH0/QJHcgrs/spIc76yQnPaqzfMiWX+FX4/Cv1ubPE6saHMjtJgHOArRzgu0VQMzFuaGy3lr87ttJus/n2XTIuu1V+6usBMCvTKTFRnfhHpnkJ+s52dOt+LiEhbU1Av0kXZHC6zNt/lTIC/wIuEUaNMp9SQtzyS1TenInMKVZQgwR1GgtuPPol+jDXLqMpQNPtds87fEZ+E03YIY9OgOGwstWFtMbAyP4T1BT74AiFUeAM1mu899uYCLFlVYC4zqOd6/ez0BPRIj0fvzET8cc8hsRsYEZH2Kr93ak29iIi0PQX1It1tjX5cojkhs2+NrvuhilIEy4ujp1B5EYLlJea+QFkR+riAPlxGVH0pkdONspAHXpsDFat/hSMuGfb4JKTG25Ga5EZRqQ9lFX6s4Gl9sXlKz4yEGkH9VQ99jc2FFchMjUePtHjTnT8rLd6cOBEwuG+kq7+ISGcM6lV+LyIibU1BvYhEsvFVDfmqC4dDCFWUIVhRYrL55pxBf0UpQr4KIOBDIngqQcXKvOjz/jICsO/gQdAZj5KgC4U+J7ZU2JFXZjNZf76uzRbptL9hcxm2FFVi45bybY6rV2YC/n311n1N73t5Hsoq/WYCIDMlzkwApKfEIaPqpFJ/EekwzJp6uxrliYhIm1NQLyL1YuDtSEg2p9rCAf/WYL+yNJLpZ7DPy75K07zP5vciBTCn/vEAeAJQ+PVS2OMSYY9LwC2HJqHIl4oCr90E/rllYWwqDmFLcaUJ3qv7cXEu8osr6zxWNu577Kr9otefeXchvP4g0pM95pSWHFd17kFakkfb94lIO3S/92hNvYiItDkF9SLSLDanC87kDICnugJ+E+iXIFS11Z4J9s15mcnUc0KAJ26wx1NPLslPiJxs2XYT8Ns9IZQt+QF2TzzsnkScf1Bvk+3PKw1hc2kA+UWVJsjniZn66j6ds6beCYC+PRLxyJU1JwB8/mA04E9N9iDOGUZhWQBeXxAJPC4RkWYE9Sq/FxGRtqagXkTaJuBPSgd4qoUBfdhbUSvQL0fIW2aa+PEUCfojmf/quBJ/CP9qpQH2LDfsHgb+CbB5UhF2xsG7cUXVBEACjt17EPKK/Sgs9aKgxIvCYi8KSytRWOI1WfvGTgD0+aYEj1arAHj4v/NR6QsiJdGNVE4AJLrN5ZTESBUAKwZEREz3e/49VFAv0ixXXnkl3njjjQYfs2TJkma99kknnYS+ffvi5ptvRkvcc889eOSRR3D11VfjlFNOQXf18ccf47///a/Z9u3111/HVVdd1eDPZp999sG6detq3ObxeNCzZ08ccsghuPDCC2G3N76iMhQK4YEHHsCrr76KkpISTJo0yewp36/f1q2ZaysoKMBNN92EL7/80vSc4te9/PLLTVNpy3vvvYf7778fa9euxeDBg3HFFVdg6tSpdX79s88+G+PHj8cFF1wQvf2WW25Bnz59cOqpp6KtKagXkXYv6beZ0nsGv9nb3G/W8XsrIkG+Fezz3FdRdb3cbMsXCvjMCWVbt9nzVXsd/sm1pbtg7xkXCf7d8bB50gFnHAJ2NwLFm2Fzx8PujsOf9hlqsv6cAGBzv8KSShQUR66nJNZcp//9LxuQX+yt83vr1zMZD12+T/T6TU/OQnGZzwT9yQluJJtzl7nOpQUTR23dgjAYDGlJgEgXEQ6FovvUK6gXaZ6///3vuOSSS6LXd999dxM8H3zwwS1+bQZqDoejRa/BQO7NN9/EoEGD8PLLL3fboL6oqAg33ngjnn322SY97/TTTzcnS3FxcTSITkxMxFlnndXo13rooYfwwgsv4NZbb0WvXr1wxx134Mwzz8Q777wDt7vuJVCcOKioqMDTTz9tvjZ/38rLy3HbbbeZ+7///ntcdtllJtDfbbfd8Nprr5nAnT/zIUO2Nnz2+XxmAuGrr74yQX11559/vpks2HvvvTFgwAC0JQX1ItLx1vFbHfrraXzPYJ7Z/kh2n+cM9isigb+3AmFfOUIBvwn+gxWRtf+1RXrxR+zpdMPWK84E/gzybe40+EI2rFizDv2H9jPb/tl4u9ONkw8ebbL6DNatU0nVOTv7V7d0dYGpEqhvAqB6UH/h3Z8jN788EvjHcwLAhaR4N5ISXOZ1j9l3ePSxy9cUgjsIsjFgUoIbCR4n7PatWwqKSGyFOeHIv2dVlUsi0nTJycnmVPu2Hj16tPi109IiW/kEg8Fmv8bXX3+NjRs3moDyvPPOw+zZs02GuLthMM9gtqlBa0JCQo2fJS8zCP7hhx8wc+bMRgf1DKqffPJJXHrppZg2bVq0gmKPPfbAhx9+iEMPPXSb58ybNy/6dawA/YYbbjATAX/7299MxcC///1v7Lfffjj55JPN/czS83nPPPOMeSzNnTvXBPSVlZVISWEHqZp4G7/+gw8+iNtvvx1tSUG9iHQ6dqfbbKdXu1t/dSabXyPQr4xcNtfLI9d5OysD+AE84DNb+Vn8fj/ceXkIhPJR5HJFJxx2dntgT4+DjRUALk4AxMPuSo9MBrg8CJQWwu5mcywPrjh5ksn2M+gvKa+aACjnJIAfmWk1lwDwMSzrr/RVIK+gYpsJgOpB/d0vzsWaTVsnKhjgJ8S5TJCfk52Ef561tTTsna9+NzsGJFbdnxQfOU+Ic5pJgx7pNZsRikjLhQNVk3mcMKza6UMk1sLhMGfFY/PF7U5T4tzaWOrNku+99trLlOpPmTLFBNksB3/00UexbNkyE7gPGzYMF198sQn0apffv/3223jiiSdMYM7X2rBhA4YPH24ytzvvvHODX5uPYyl579698dJLL20T1P/888+4++67MX/+fFPWvf/++5tlBbzMnwcDYmaY+TVZKn7uueeaIJDl3vvuu6+5n98T1b6Nr8PMcmlpKX766Sfz3DPOOMMEozw2lrczS73TTjuZwLN///7mdcrKyswxffDBB+bymDFjzGuNGDECe+65J0488UQTXFv4fbG0/fPPP4fTWTN09Hq9ePHFF3H99de32s+UZfjMoFf/nuvzySefID8/33wf1cviGUyPHj3aTLTUFdTPmTPHTCJUz7hPnjzZ/I7++OOPOOigg0zAznGpjuPOiQLLF198YX6n/vKXv+CPf/xjncfIypLjjz/eVJ1wsqCtKKgXkS7J5nDBkcDTtjOnFr6hMqO2NeCvjF5GSRFCpX7Y45NhRyTwt/oBcDJgu18fNvR1uZHj8sCe4IEtlQ2zGPi7YXMlm8DfX7jJbHfFRloPXjoNJZUBlJb7o8E/L5dW+JEYX/NPNZv5lVX4UFoRMA3++DmtrMJvTnHumuWE7323ssYEQHXcEvDpaw+MXp/xzA9Yn1dmgn5OAjDwj49zmsvsH3DEXlvf/FasL0IwFDaPsR7rcraslFGkqwj7qzL1Kr2XDoLvdyXzP0GgeEtMvr4zJQvJ4/dpk8B+9erVyM3NNWXRzJj+8ssvZl0zM6sMCBn03nXXXaaMmkFYXeXYDKoZvLJsm6XfDFIZ0DGAq+uYCwsLTUB5zjnnmPv/8Ic/4LnnnjMTARkZkQbCa9asMSX5DORZns+13jymf/7zn6ZM/PHHHzcZXD6HwSKPjceYlZWFnJycRn3vDMxZIv6Pf/wDcXFxJuDnBAVLyDnhwLHhffx6nOygiy66CCtXrsSMGTNMoM+eACyD/+ijj0xgykmO6kE9x5W31w7oiZlrlq5zMqClmHFn5vybb74xyyyIkyWsiKgPx3rhwoXRx1aXnZ1tKinqsmnTpm0ez98LVnDwd4HfEydMWMrf0Gtyomh7xo4da16Xa/ePOeYYtBUF9SLSbfGN2Hzodnm2zfqXl8MXTEbiqFGmRCwcCkYCfr93a/Dvr0TYuu7nZIDXnPMDfZj//F7A70Vji/sSnC4kujzoxUDf44EtiRMAHlP2793wW/TyjafsEJkccLoRCMEE/gzoeV7btJ1ykFtQHg36mbXnZEF5ZcAE6tWt2VTa4ARA9aD+odfmY/GqghqPcTrsJrhPT3bjtH0ipY3030+XYcOWMlNNEO9xmsfEuZ1m2QAnDaovQ+AxOuw2eNyONvnwJ9IurPJ7VhWJdBhd928qs+xWU7RFixaZQPaEE06I3s8SapZzb9myZZtgjgKBgAm2R40aZa6fdtppJvual5dnArna/ve//5kglOuliecsAWeGnCXc9Morr5hgjs3SrICYjdkYCHOShWXcPC4r0GP1ACcleCyNlZqaGv16xCCdAT3XcBOrEZh1fv/9983133//3QSXDPzZo4A4gcHMNhvH/elPfzJrzHmMO+64I1asWGEu87jrsmDBAvM1OBHSVKyk4JhZmJ1nfwJOclg/O/Y92N5yCyur7641WcOMP9f71/ecuiZ3+BxWH/DnUN9r8v6mGjp0qBlHBfUiIjFmszuqNfhrmMno+xng+yKBv89rJgNM4G/OI6etlyOTAOwDAJ5Q2vjjcjhNpj/F6UaqCfQ9KF/mjgb9h+/Ayz3MkgVet27n91PbJSfshKIyH8orOQEQQIU3EvxzIsDjqvl4dvvnNoJ8TIU3Mm0RCIZMlUHtfn+zft2IRSvz6zx+Vha8OmNradwd/5mDHxfngi0C4hj0VztxMuDGP+8aDfY//3ENNmwpr7rfYSYKeJkTAjwfmpMW7TXARoS8rIkCaQ9mQs9k6hXUS8fAv33MlHe18nvLwIEDo5cZmDPYfeyxx0wQu2rVKixevHi7a+irl2Jba/m5FK8u7PTOsnXr6+6www7mMgN5lsDze126dKl5TPUM9y677GJOLBnnhEHtxmrWOnKWnTdG7XXsXArAUv9//etfJiDnafny5dGybx4TTZgwoUagym711TPLzM4zqOf5uHHjTFBal82bN0crE5rquOOOMxMZ/Jl89913ppqCExAs/7esX78+OnFSl3fffddUKBAnWazLxOC7eif76vg4Pr42PoeJHI6J9Zq176/vNRvCMeJYtSUF9SIibdHh3x0PuOPhqK/bX+1JADb2qx3ss8P/Npd9kSUDVjVAMICg6bJd1vRJCpd7a7DvdKOX04XevJzuhi2Lt7lgdyVE7ne4zLID3saJhH+cEVnjRyzDr/AGzGRARWUAJaXl8BZv3arm4F0HYqeR2WaCIPo4bwCV3iCcjpof8thXgEJhmMfzZKmdvf9i3jrMWbSp3u/xzTu2rm+7+4W5+Prn9Yh3O+Bxs1IgMgnA1+Tlq0+bbK7TVz+tw6oNxVX3RR5rXeb56EGZcDkjMxf8XiLH5jQVBiI1GuU5VX4vHYf5++nomo0bqwdzbIDGwJpN07gm/rDDDjOZWWbeG1JX5tb0IaiFEwQs+eZ4ct129W74fPy3335ruqXXVa5ucVX16mmKuiYkqn/fxIkMlvQfeeSRZo05t1LjMgEGv9TQMVmYrWejOWbM2T2+eiVAbdx2jt93c3DixZqU4HZxzPZzeQKDamtyg1USnFioD++3Ki9yc3OjfQOs6+wTUBeW1bPvQnUM4Lmsgq/JCgseB1+jOl5vzrp4/uyaskVfcyioFxHpCJMAVcsAGivaD8AK8gOcDLAC/qoqgWD1+63L/shkAJcTNLI/QJ0TAia4d1VNCDjNeaLDhSRWDIRDWFm0Hv68RPiSUrDbUA9sjuTIc6zn1ZOxueXc3eD1B03Qb05VEwE8+bnWoBqW7WelxaPSemzViRMDZovAakF2hS+AUCiMMlN5sG2miksHqm9b+OW8mvvnVvfCjX+Aq6qs+sl3fsUH36+KvoY1AcDKBp6zaWF6Sly0smDs0CyznaG0fJ9hNsDi+ldmpfhhiY/nGljuCdxxgnpl6kXaG0u6uUadW6NZuN69viC9qbi1GYNyrl9PSkqK3s5mbcw8c/08g3pmtxkUM6Czts/junWuZefWbQweWb5evREct1ljkGpt9cZ+ABaug98ero/n5AW3XrOw1N76vq1qBH5dq7Ecy/0POOAAs56fmXI2luMa/Keeespkl+tqNGfh+n9WHbSGI444Ap999pmpMuAafQbknITYXlf9kSNHmp/DrFmzokE918Rz4mX69Ol1PofvF3feeaep4rBen5NBxIkgfkZhg0HeVr1knl9j4sSJTf7eOEZcWtCWFNSLiHTyfgBNEZ0MYHAfqBXwc8eA6pMANR7jrzkhYDLqkTVntbFc0ZWXh8pwEYL1ZCMiEwJO2BxVkwLWBIGDEwQuxDtcpseAzeWCLT5SHWBzeMwOBdZzWQHQ2HLOy6ZPjFYIeM0uA8Gq84CZRKge1O88MhvJCW5zn/U467G8Xn0pAp9r4fKD0gqetpZrVt9qkEsQRg5sXplid9CUfYa59pNrXvmhix/WmWHh8/h4dsC2SidjReX3IrHDoJhZWHY4598SBmIMFKmukuum4PP5N+nAAw80f39qYwDM+1laz3XhDPyvu+468/eKgR23NWP5Pf9GMfBmF3oGeyx1Z3d5ZtUZTDPg51p1rrtnWT8zyPwetveex++djeZYhs/Jzrfeess0+2PwTfxaDODZP4Br6Zl1ZnafZeXs/m4tPWBzP/5N5oRDXVu1WbjsgI/j8VnbBFq4dr82BuoNZbo5kcv94a+55hozOdKY7DbfH6ZPn26CdJa5c9z4/sGfPb9X4sQKx5/fG6sbuOyBPz82uuM4sCkevzYnFqzj48+MPyNWY3CSgUsu2K+BOyY0dcKa1R2HH3442pKCehGRbqS5kwFkZvqDgchOAAzwg9WC/WqTAP/f3p3ARlW1fxx/KAVkB3Ejr/xdAUXQgogFVwgSo/VVEUEUMSquCEYUhQji8koELSIaWeIWqCYmigYV4y7GBa2iuCEiiCKyCAi4VNrS+8/vlDvOdGPmdtqZO/1+krGdO9Ny+3jvPPec+5xz7O8/bXeRZ9ltDzBVqWuIgHtdX8vKG8HqQNDDrCj436JJn1wnwJ5OgUhHgd8JsOerOgeysq1VdhNrrects61RG72mCoKWZtlN3BAIf+mxAb3/zz3iMW54L7vhwpx/OwjUAVCypyOgZLdbScCX272jtWlJIy8Z6wzrgl0XYbpA9stPdRGnn9UyRNFLG6UC5fdA6uhut+4wa2Z60R1zTVanWeJ1hzp67HyidCdZDdjocd/RVO6ujkVVHGnyPn2u6bNJjUWVm2t5M62DLmqIakI2NdbVCaDGuz73/Ma1Pt+032oM6m6yxr1H34Gvin5Ga6irhF7l7Gq8+g14jU9XJZN+p9534403us9evUd386PHxg8ePNh1TuhrTXRXWw1ldZyooyNaVevMq0qhpt/ZoUMH93eqDF8dIopnvP/PS0tLXWeAYqo78fqb/GEOmtFeHRT+v69rIVWGKTZaoUCdLKpSiJ5bQBMJKlbqtND/Fx1HqoRI9PhRxYCqOPzJC+tKIy8ZdShpVG6nnhj1dlWcmVBLM2h5iyD0AeBPHFFbughRL48m8dBYDcSHuAVH7IIhbnUTO3eX3+8IUMPeb+xHnkdti3QGaJuel5j531vyU5cbVhDVCeA6DKKel3cURG1vXGFbVpMK2zQHQFadHHPJzEvpQGs5q8RRMzRHlyhqbV8ty6QLr2iaREoP3fGKXqJId1NmzZpV6eIyHsmM6ZalL9umtaus0yn/tTb/Cd6AaIj47K193HR9rAnSdC5VHHONWGo3qBGoOPkl8jA3i7+GL6hyoLq75X7s1NDVBHyazR6VqZNFwwFUSVDVMafvazpf481N2ZlWbqfxJmrQq9xEvT0+EgMApJ5rODdtbNY0+IWm64suU4N/T8N/z13/8o6B8m0W8zzqa9TPqOrAfe+V/dvhoEqCPaXTSft7/UZ+VrZlt2pvLbr2YRb+Cvx1f+NdZ1hrOFdcx1klpLogUmd/bY4tNY5qq7iofOLKXaXJ+X0Nib88lf8VicfNn7xMjYeaZnvHv2Ps9ZVYld9V1ooBqh5QNUJNcfFjpzvdWsdeN1414R3+paoOdVar3erHseIxp4fOV527VU06qPfFc82QnWnlditXrnSTJWjSBABA5s7grPL6ZHCN+UhlQEl5h0HUc9dJ4G/zOwr2PI90DEQ93LY9lQQVOwrKiv6w5kfklA+BQK3WGY6mC6aCggJXehl0eSV/Pgjd7aytptt3uobVz5u2mG3Z+/6jsngmBUP1cdMEY0HW026oiFU5zUMwc+ZM1xYbOnRoZL32mmiJN02yN23atMjcBSinagdNnqgb1xVj6R9z+qqhA+pMSWRlhrRq1GvSAI0xiB77pskYNCFBYWFhpUa93qc7+9GlCX5JiMoaRI362oyVAQA0LO5uelbjQPMMVF9JUN6Yj234l1hWs5aWRYO+kiDrDPux1kXk7Nmz7brrrnMXT7Wh8ZfVrceciL//09F+/nGNHXpE50BrGjf0Dh41TDW+mNgFi5uujTV+Wp1ilN/XTJ8h+pxRrKigMhs5cqR7JBo7LRuoB2JNnjw5rmNOnXCaub+qSV5/+OEHi0d2ppXbaUyHeju0PqU6DTSDocpCajvjYLJK8igrC4a4BUfsgiFuwRG7aI00BbqbjM+y9zRQqsklicQt3nK8sAiyzrDuqmtSo5dfftl9jXdCpZoopskaruc1be4apQz/C4bYBY+bGvV6aLwu48Rr5pdE69wnVokhdsmJmx46X3XuVtUJF2+uz860cjuN59B4BM2CqFKHJUuWuGSv5D9kyJCUl+T5KCsLhrgFR+yCIW7BEbu6jVs85XhhEWSdYZV7as3n/Px8O/vss+t5jwEASB/ZmVZupx579YBoGQf/QkElSFrWoDaN+mSV5FFWFgxxC47YBUPcgiN2dR+3eMvxwmJv6wxXXGNYMzMvXrzYNey1/JOWg/L57wEauhQvcAWgHs/T7Ewrt6sqkWs5nEWLFqVNSZ5QVhYMcQuO2AVD3IIjdnUXt0wqvY9nnWEtXxe9xrCuAUQT5+qRyDrIQKbz1+bWsFE6VoH05g/v9s/bUDbqk11up58dOHCgW7c+OqFrfb/OnTvX8V8DAACC0rjC8ePHu0dFmk9HE+H6tHIOgOrPpXbt2rmbZKJOwkzsCEwGVQH5s5AzLjwxxK52cfMnzNN5qvO1tjHMzqRyO82cn5ub65bF0xr1hxxyiFsaT3fp586dm8o/FQAAAKgXupYWv2GPqmkeLlUIafZxf0UtxIfYJSduatD752toG/V1UW43depUtybglClTbOvWrW55u1mzZrn1FgEAAIBMpzvzGuaqFaU0dBXVz2Wi9cFVMcxQhcQQu9rHTTekk1XlkJ1p5XYq59dYez0AAACAhopl7fZ+19RfeYsJNhND7Goft2Sem9RKAAAAAAAQUjTqAQAAAAAIKRr1AAAAAACEVCMvWSveZ7Bly5a5ZQc0W39t6fdowhJNBMjyIvEjbsERu2CIW3DEru7jVlxc7N7Tq1evetu/TEeuTw/ELhjiFgxxC47Y1U/c4s33KZ8oLwySeaDqdyXjgqGhIW7BEbtgiFtwxK7u46b3chGVXOT69EDsgiFuwRC34Ihd/cQt3nzPnXoAAAAAAEKKMfUAAAAAAIQUjXoAAAAAAEKKRj0AAAAAACFFox4AAAAAgJCiUQ8AAAAAQEjRqAcAAAAAIKRo1AMAAAAAEFI06gEAAAAACCka9QAAAAAAhBSNegAAAAAAQopGPQAAAAAAIUWjHgAAAACAkKJRX0/Kysps1qxZdsopp1hOTo5dddVVtm7dulTvVlqbO3euXXrppTHbVqxYYSNGjHAxHDBggM2fPz9l+5dutm/fbnfccYedeuqp1qtXLxs+fLh9+umnkdc/+ugjGzx4sB133HF25pln2iuvvJLS/U0XW7dutfHjx1tubq717NnTrr76alu9enXkdY65vfvxxx9d7BYuXBjZRtyqt2nTJuvatWulhx8/Yhde5PpgyPfxI9cHR76vPfJ9Gud6D/Xi4Ycf9k488UTvnXfe8VasWOFdccUV3qBBg7xdu3aletfSUkFBgXfUUUd5I0aMiGzbtm2bi+HEiRO9H374wXvuuee8Hj16uK/wvMsvv9zLy8vzCgsLvTVr1nh33XWXd+yxx3qrV6928VKsZsyY4b5/7LHHvG7dunkffvih19ANGzbMu/DCC73ly5e72IwZM8Y7+eSTvb///ptjLg7FxcXe4MGDvS5dunjPP/+820bcavbuu++6eGzatMnbvHlz5FFUVETsQo5cnzjyfWLI9cGR72uHfJ/euZ5GfT1QMu/Zs6f39NNPR7bt2LHDfQi/9NJLKd23dLNx40bvmmuu8XJycrwzzzwzJsnPmTPHffiWlJREtuXn57sLpoZu7dq17kP2008/jWwrKyvzBg4c6M2cOdObPHmyN2TIkJifGTdunLvgbMi2b9/u4rBy5crINl2IK5ZK+hxze6d4jBw5MibJE7eazZs3zzvnnHOqfI3YhRe5PjHk+8SR64Mj39ce+T69cz3l9/Xgu+++s7/++sv69u0b2damTRvr1q2bFRYWpnTf0s0333xjTZo0sUWLFrnSsWgqL+vTp49lZ2dHtqmEau3atbZlyxZryNq3b2/z5s2zHj16RLY1atTIPXbu3OliF338+bH77LPP1LFnDVXbtm0tPz/funTp4p5v27bNnnrqKTvooIPsyCOP5JjbC31+Pfvss3bffffFbCduNVu5cqUdccQRVb5G7MKLXJ8Y8n3iyPXBke9rh3yf/rmeRn092Lhxo/vasWPHmO0HHHBA5DWU05iShx9+2Dp16lTpNcVKH74VYygbNmywhkwXjqeddpo1bdo0su21116zn376yY3trC52RUVF9vvvv6dgj9PP5MmT3cWQxh/ee++91qJFC465GugC8tZbb7VJkyZV+mwjbjX7/vvv3QXlJZdcYv369XNjYt977z33GrELL3J9Ysj3iSPXJwf5PjHk+3Dkehr19UAfphL9ISzNmjWzXbt2pWivwueff/6pMoZCHGMtW7bMJk6caIMGDbLTTz+9ytj5z4uLi1O0l+nlsssus+eff97y8vJs9OjR7i4Sx1z17rzzTjdZzjnnnFPpNeJWvdLSUluzZo3t2LHDxowZ4+66aZIcTdikCa6IXXiR65OH8yA+5PpgyPeJId+HI9f/e88fdWafffaJfKD63/v/05o3b57CPQsXxa5iUvIPfPWyotybb75pt9xyi5sV94EHHoh8UFSMnf+cY7Ccyu9EvfbLly+3goICjrlqvPjii6507KWXXqrydeJWPZXaffzxx9a4ceNIPujevbutWrXKHn/8cWIXYuT65OE82DtyfXDk+/iR78OT67lTXw/8UpXNmzfHbNfzAw88MEV7FT4qU6kqhkIcyykxqUewf//+NmfOnEivn47BqmKnD47WrVtbQ6WyKJXfqUfVl5WV5RK+4sMxVzXd4dDSQLozpN57PWTKlCk2atQo4rYXLVu2jGn0SefOnd3yN8QuvMj1ycN5UDNyfeLI98GQ78OT62nU14OjjjrKWrVq5XpsosenfPvtt3bCCSekdN/CRLHSZC+7d++ObFu6dKkddthh1qFDB2vonnnmGbvnnnvc2J0ZM2bElPX07t3bPvnkk5j3K3bq4VdSa6g0Gcm4ceNcKZSvpKTEnZua3IRjrmq6K7R48WLXg+8/ZOzYse7OB3Grnnrpdd5F5wP5+uuv3cUlsQsvcn3ycB5Uj1wfDPk+GPJ9iHJ94HnzkRCtGdqnTx/vzTffjFm7Vms+omq33XZbzBI3W7Zs8U444QS3fdWqVW45Da3puHDhQq+h01q1xxxzjDd69OiYtTD12Llzp/f999+71++//363Hubjjz/O2rV7jBo1yp2Ln3zyiVvqRkve6Dhbv349x1wCope4IW7V2717t3fBBRd4Z511lltnWufj1KlTve7du7vjj9iFG7k+GPJ9fMj1tUO+Tw7yfXrmehr19aS0tNSbPn26l5ub69Zkveqqq7x169alerdCleRFa4kOHTrUnRT9+/f3FixYkLL9SyezZ892H7JVPRRHWbJkiZeXl+dipzWBX3nllVTvdlrQhdCUKVO8k046ya0nrYtwXRj5OOYST/JC3Kr322+/eRMmTHDHnJL4sGHDXNL3EbvwItcHQ76PD7m+dsj3yUG+T89c30j/CVhZAAAAAAAAUqhhD7ABAAAAACDEaNQDAAAAABBSNOoBAAAAAAgpGvUAAAAAAIQUjXoAAAAAAEKKRj0AAAAAACFFox4AAAAAgJCiUQ8AAAAAQEhlp3oHAKSHCRMm2AsvvFDt6/vtt5998MEH9bpPXbt2tRtuuMHGjBlTr/8uAACZiFwPZCYa9QAi9t9/f3vkkUeqfK1Jkyb1vj8AACC5yPVA5qFRDyCiadOmlpOTk+rdAAAAdYRcD2QextQDSMill17qyvfmzJlj/fr1s+OPP96uv/56W79+fcz7vvrqK7vyyivtxBNPtF69etm1115rq1atinnP5s2b7bbbbrO+fftaz549bcSIEfb555/HvOfPP/+022+/3fr06ePeM3bsWNuyZUvk9Z9//tn9bv07xx13nA0bNsyWLFlSx1EAACBzkeuBcKFRDyBGaWlplQ/P8yLveeutt2zhwoU2adIku+uuu2zFihXuAqCoqMi9vnTpUhs+fLj7furUqfa///3PNmzYYBdddJGtXr3abf/rr7/cez7++GMbP368KwVs1qyZXXHFFbZ27drIvzV//nwrKSmxhx56yG6++WZ7++237e6773avlZWV2TXXXOP+3enTp9ujjz5q7dq1s+uuu85++umneo4cAADhQK4HMgvl9wAi1AN/zDHHVPnarbfe6nrjRYlVib5Tp07u+eGHH27nn3++vfjiiy555+fn2yGHHGLz5s2zxo0bu/ecfPLJdsYZZ9isWbNc0tZEPfr39PXoo49271Ev/3nnnWeFhYV26KGHum09evRwSVzUy798+fJI7/zWrVttzZo17u7Baaed5rYde+yx7qKhuLi4zuMFAEDYkOuBzEOjHkDM5DmzZ8+u8rWOHTtGvldC9pO8dOvWzT1Xgj733HNdOZ5msvWTvLRp08b69+8fSdKfffaZHXzwwZEkL82bN7fXXnst5t9VyV80/czOnTsjs/QeeeSRNnnyZHv//ffdxcSpp55qEydOrHUsAADIROR6IPPQqAcQM3mOesv35sADD6y0rUOHDrZjxw77448/XPmeknBF2qbXZfv27e5n9qZFixYxz7OysiLlgY0aNbInnnjCXZy88cYb7u6BZu4dOHCgKxVs27btXn8/AAANCbkeyDyMqQeQsN9//73SNk1os++++1rr1q1dAo6e4Mb322+/uXFwovdt27at0nuWLVsWGYsXD1103Hnnna73XoleZYOvv/66zZw5M+G/CwAAlCPXA+FBox5AwlROF53sv/76a/vll1/cODj1tnfv3t1effVV2717d+Q96rV/9913IyV2vXv3tnXr1sXMkrtr1y4bM2aMPffcc3Hth2bP1ay8X375pbu4UHnfTTfdZF26dLFff/01qX8zAAANCbkeCA/K7wFEaMKZL774otrXu3btGpk8Z9SoUW7mWc1s++CDD7rkmpeX517XzLXqRb/66qvt4osvdjPaaiId/f7Ro0e79wwePNgWLFjgfoeWrmnfvn1k9lv9TDw0vm+fffZxE/voAkElfx9++KGboXfkyJFJiQkAAJmEXA9kHhr1AGJK5rT2a3VU8ub3vOfm5ro1ZWXAgAEu2WqcnqgX/8knn3Sz344bN85t189MmzbNOnfu7N7TqlUrKygocLPd3nPPPW7JmpycHJfsoyfmqYmWxdE4O83Ae++997pJdTSTrpbB0YUEAACIRa4HMk8jL3pBSgDYC61RK+p5BwAAmYdcD4QLY+oBAAAAAAgpGvUAAAAAAIQU5fcAAAAAAIQUd+oBAAAAAAgpGvUAAAAAAIQUjXoAAAAAAEKKRj0AAAAAACFFox4AAAAAgJCiUQ8AAAAAQEjRqAcAAAAAIKRo1AMAAAAAYOH0/xxLQm+fx2toAAAAAElFTkSuQmCC",
"text/plain": [
"<Figure size 1200x400 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_results(results)"
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Learning rate: 0.1 - époques: 50\n",
"Learning rate: 0.01 - époques: 50\n",
"Learning rate: 0.001 - époques: 50\n"
]
}
],
"source": [
"n_epochs = 50\n",
"batch_size = 256\n",
"learning_rates = [10 ** (-power) for power in range(1, 4)]\n",
"\n",
"results = []\n",
"for learning_rate in learning_rates:\n",
" print(f\"Learning rate: {learning_rate} - époques: {n_epochs}\")\n",
" model = get_model(learning_rate=learning_rate)\n",
" history = model.fit(\n",
" X_train,\n",
" y_train,\n",
" epochs=n_epochs,\n",
" batch_size=batch_size,\n",
" validation_data=(X_valid, y_valid),\n",
" verbose=0,\n",
" )\n",
" result = {\n",
" \"learning_rate\": learning_rate,\n",
" \"n_epochs\": n_epochs,\n",
" \"history\": pd.DataFrame(history.history),\n",
" }\n",
" results.append(result)\n"
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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",
"text/plain": [
"<Figure size 1200x400 with 2 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"show_results(results)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Pour continuer\n",
"\n",
"Choisir une ou plusieurs pistes de recherche parmi les suivantes. Il est possible de choisir une autre direction, mais elle doit être validé auparavant.\n",
"\n",
"1. L'initialisation des réseaux de neurones étant aléatoire, et la mise à jour des poids étant réalisées avec SGD, on ne peut pas considérer un exemple comme une généralité. Reproduire l'étude précédente en lançant plusieurs fois le même modèle pour être capable de générer un graphique avec des intervalles de confiance.\n",
"2. Nous avons vu en cours que l'initialisation des poids peut avoir un impact fort sur la suite de l'entraînement. En exploitant le paramètre `kernel_initializer` présent dans la définition de la couche [`Dense`](https://keras.io/api/layers/core_layers/dense/), proposer et réaliser une étude pour vérifier ou infirmer cela.\n",
"3. Les réseaux de neurones peuvent sur-apprendre. Il est important de pouvoir les régulariser. En exploitant le paramètre `kernel_regularizer` présent dans la définition de la couche [`Dense`](https://keras.io/api/layers/core_layers/dense/), proposer une étude pour visualiser son impact sur l'apprentissage."
]
}
],
"metadata": {
"kernelspec": {
"display_name": "studies",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.3"
}
},
"nbformat": 4,
"nbformat_minor": 2
}