diff --git a/notebooks/baseline.h5 b/notebooks/baseline.h5 new file mode 100644 index 0000000..e14b9da Binary files /dev/null and b/notebooks/baseline.h5 differ diff --git a/notebooks/baseline.keras b/notebooks/baseline.keras new file mode 100644 index 0000000..a5a7008 Binary files /dev/null and b/notebooks/baseline.keras differ diff --git a/notebooks/model_v1.h5 b/notebooks/model_v1.h5 new file mode 100644 index 0000000..64d0ba9 Binary files /dev/null and b/notebooks/model_v1.h5 differ diff --git a/notebooks/treasurebot.ipynb b/notebooks/treasurebot.ipynb index ca19ce7..d15cfab 100644 --- a/notebooks/treasurebot.ipynb +++ b/notebooks/treasurebot.ipynb @@ -1,432 +1,667 @@ { - "cells": [ - { - "cell_type": "code", - "execution_count": 1, - "id": "c8c27275-c1d5-46d3-ab33-8d3877fb0850", - "metadata": {}, - "outputs": [ + "cells": [ { - "name": "stderr", - "output_type": "stream", - "text": [ - "2024-08-27 10:05:46.987779: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2024-08-27 10:05:48.062327: I external/local_xla/xla/tsl/cuda/cudart_stub.cc:32] Could not find cuda drivers on your machine, GPU will not be used.\n", - "2024-08-27 10:05:48.594078: E external/local_xla/xla/stream_executor/cuda/cuda_fft.cc:485] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered\n", - "2024-08-27 10:05:49.074177: E external/local_xla/xla/stream_executor/cuda/cuda_dnn.cc:8454] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered\n", - "2024-08-27 10:05:49.268569: E external/local_xla/xla/stream_executor/cuda/cuda_blas.cc:1452] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered\n", - "2024-08-27 10:05:50.501215: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.\n", - "To enable the following instructions: AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.\n", - "2024-08-27 10:06:04.816315: W tensorflow/compiler/tf2tensorrt/utils/py_utils.cc:38] TF-TRT Warning: Could not find TensorRT\n" - ] - } - ], - "source": [ - "from tensorflow.keras.models import Sequential, Model\n", - "from tensorflow.keras import layers, optimizers, callbacks" - ] - }, - { - "cell_type": "code", - "execution_count": 2, - "id": "864dab16-8f23-4027-aa22-7793a2bf23b6", - "metadata": {}, - "outputs": [ - { - "name": "stderr", - "output_type": "stream", - "text": [ - "/home/msessini/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/keras/src/layers/preprocessing/tf_data_layer.py:19: UserWarning: Do not pass an `input_shape`/`input_dim` argument to a layer. When using Sequential models, prefer using an `Input(shape)` object as the first layer in the model instead.\n", - " super().__init__(**kwargs)\n" - ] - } - ], - "source": [ - "model = Sequential()\n", - "\n", - "model.add(layers.Rescaling(1./255, input_shape = (254, 254, 3)))\n", - "\n", - "model.add(layers.Conv2D(filters = 32, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", - "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", - "\n", - "model.add(layers.Conv2D(filters = 64, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", - "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", - "\n", - "\n", - "model.add(layers.Conv2D(filters = 64, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", - "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", - "\n", - "\n", - "model.add(layers.Conv2D(filters = 128, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", - "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", - "\n", - "model.add(layers.Conv2D(filters = 256, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", - "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", - "\n", - "model.add(layers.Flatten())\n", - "\n", - "# Here we flatten our data to end up with just one dimension\n", - "\n", - "model.add(layers.Dense(128, activation=\"relu\"))\n", - "\n", - "model.add(layers.Dropout(0.5))\n", - "\n", - "model.add(layers.Dense(14, activation=\"softmax\"))" - ] - }, - { - "cell_type": "code", - "execution_count": 3, - "id": "90fd8962-cf26-48ec-9b3e-b3650d491ba2", - "metadata": {}, - "outputs": [ - { - "data": { - "text/html": [ - "
Model: \"sequential\"\n",
-       "
\n" + "cell_type": "code", + "source": [ + "from google.colab import drive\n", + "drive.mount('/content/drive')" ], - "text/plain": [ - "\u001b[1mModel: \"sequential\"\u001b[0m\n" + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "yBfAW9x5jcHm", + "outputId": "4ad76587-678e-4b68-8326-b710d72ad9bc" + }, + "id": "yBfAW9x5jcHm", + "execution_count": 1, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n" + ] + } ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "data": { - "text/html": [ - "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
-       "┃ Layer (type)                    ┃ Output Shape           ┃       Param # ┃\n",
-       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
-       "│ rescaling (Rescaling)           │ (None, 254, 254, 3)    │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ conv2d (Conv2D)                 │ (None, 254, 254, 32)   │           896 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ max_pooling2d (MaxPooling2D)    │ (None, 127, 127, 32)   │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ conv2d_1 (Conv2D)               │ (None, 127, 127, 64)   │        18,496 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ max_pooling2d_1 (MaxPooling2D)  │ (None, 64, 64, 64)     │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ conv2d_2 (Conv2D)               │ (None, 64, 64, 64)     │        36,928 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ max_pooling2d_2 (MaxPooling2D)  │ (None, 32, 32, 64)     │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ conv2d_3 (Conv2D)               │ (None, 32, 32, 128)    │        73,856 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ max_pooling2d_3 (MaxPooling2D)  │ (None, 16, 16, 128)    │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ conv2d_4 (Conv2D)               │ (None, 16, 16, 256)    │       295,168 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ max_pooling2d_4 (MaxPooling2D)  │ (None, 8, 8, 256)      │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ flatten (Flatten)               │ (None, 16384)          │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ dense (Dense)                   │ (None, 128)            │     2,097,280 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ dropout (Dropout)               │ (None, 128)            │             0 │\n",
-       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
-       "│ dense_1 (Dense)                 │ (None, 14)             │         1,806 │\n",
-       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
-       "
\n" + "cell_type": "code", + "source": [ + "!unzip -q /content/subset.zip" ], - "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", - "│ rescaling (\u001b[38;5;33mRescaling\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ conv2d (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ max_pooling2d (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m127\u001b[0m, \u001b[38;5;34m127\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ conv2d_1 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m127\u001b[0m, \u001b[38;5;34m127\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m18,496\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ max_pooling2d_1 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ conv2d_2 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ max_pooling2d_2 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ conv2d_3 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m32\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ max_pooling2d_3 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ conv2d_4 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m295,168\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ flatten (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16384\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ dense (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m2,097,280\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ dropout (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", - "├─────────────────────────────────┼────────────────────────┼───────────────┤\n", - "│ dense_1 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m) │ \u001b[38;5;34m1,806\u001b[0m │\n", - "└─────────────────────────────────┴────────────────────────┴───────────────┘\n" + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "RogMbGCfd6Z5", + "outputId": "4d782643-a283-4ef6-fb40-2b24de93a32c" + }, + "id": "RogMbGCfd6Z5", + "execution_count": 2, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "replace subset/test/DrinkCans/DrinkCans_126.jpg? [y]es, [n]o, [A]ll, [N]one, [r]ename: " + ] + } ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "data": { - "text/html": [ - "
 Total params: 2,524,430 (9.63 MB)\n",
-       "
\n" - ], - "text/plain": [ - "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m2,524,430\u001b[0m (9.63 MB)\n" + "cell_type": "code", + "execution_count": 3, + "id": "c8c27275-c1d5-46d3-ab33-8d3877fb0850", + "metadata": { + "id": "c8c27275-c1d5-46d3-ab33-8d3877fb0850" + }, + "outputs": [], + "source": [ + "from tensorflow.keras.models import Sequential, Model\n", + "from tensorflow.keras import layers, optimizers, callbacks" ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "data": { - "text/html": [ - "
 Trainable params: 2,524,430 (9.63 MB)\n",
-       "
\n" - ], - "text/plain": [ - "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m2,524,430\u001b[0m (9.63 MB)\n" + "cell_type": "code", + "execution_count": 5, + "id": "864dab16-8f23-4027-aa22-7793a2bf23b6", + "metadata": { + "id": "864dab16-8f23-4027-aa22-7793a2bf23b6" + }, + "outputs": [], + "source": [ + "model = Sequential()\n", + "\n", + "model.add(layers.Rescaling(1./255, input_shape = (254, 254, 3)))\n", + "\n", + "model.add(layers.Conv2D(filters = 32, kernel_size = (5,5), activation=\"relu\", padding = \"same\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(3, 3), padding = \"same\") )\n", + "\n", + "model.add(layers.Conv2D(filters = 64, kernel_size = (5,5), activation=\"relu\", padding = \"same\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(3, 3), padding = \"same\") )\n", + "\n", + "model.add(layers.Conv2D(filters = 64, kernel_size = (4,4), activation=\"relu\", padding = \"same\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(3, 3), padding = \"same\") )\n", + "\n", + "model.add(layers.Conv2D(filters = 128, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", + "\n", + "model.add(layers.Conv2D(filters = 256, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", + "\n", + "model.add(layers.Dropout(0.2))\n", + "\n", + "model.add(layers.Conv2D(filters = 256, kernel_size = (3,3), activation=\"relu\", padding = \"same\"))\n", + "model.add(layers.MaxPooling2D(pool_size=(2, 2), padding = \"same\") )\n", + "\n", + "model.add(layers.Dropout(0.3))\n", + "\n", + "model.add(layers.Flatten())\n", + "\n", + "# Here we flatten our data to end up with just one dimension\n", + "\n", + "model.add(layers.Dense(128, activation=\"relu\"))\n", + "\n", + "model.add(layers.Dense(5, activation=\"softmax\"))" ] - }, - "metadata": {}, - "output_type": "display_data" }, { - "data": { - "text/html": [ - "
 Non-trainable params: 0 (0.00 B)\n",
-       "
\n" + "cell_type": "code", + "execution_count": 6, + "id": "90fd8962-cf26-48ec-9b3e-b3650d491ba2", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 705 + }, + "id": "90fd8962-cf26-48ec-9b3e-b3650d491ba2", + "outputId": "9e44e156-e24e-4a52-b1bd-82ae83c515b4" + }, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1mModel: \"sequential_1\"\u001b[0m\n" + ], + "text/html": [ + "
Model: \"sequential_1\"\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "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", + "│ rescaling_1 (\u001b[38;5;33mRescaling\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ conv2d_6 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m254\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m2,432\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ max_pooling2d_6 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m85\u001b[0m, \u001b[38;5;34m85\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m85\u001b[0m, \u001b[38;5;34m85\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m51,264\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ max_pooling2d_7 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ conv2d_8 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m29\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m65,600\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ max_pooling2d_8 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ conv2d_9 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m10\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ max_pooling2d_9 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m5\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m295,168\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ max_pooling2d_10 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ conv2d_11 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m3\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m590,080\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ max_pooling2d_11 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1024\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m131,200\u001b[0m │\n", + "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n", + "│ dense_3 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5\u001b[0m) │ \u001b[38;5;34m645\u001b[0m │\n", + "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n" + ], + "text/html": [ + "
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+              "┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃\n",
+              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+              "│ rescaling_1 (Rescaling)              │ (None, 254, 254, 3)         │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ conv2d_6 (Conv2D)                    │ (None, 254, 254, 32)        │           2,432 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ max_pooling2d_6 (MaxPooling2D)       │ (None, 85, 85, 32)          │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ conv2d_7 (Conv2D)                    │ (None, 85, 85, 64)          │          51,264 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ max_pooling2d_7 (MaxPooling2D)       │ (None, 29, 29, 64)          │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ conv2d_8 (Conv2D)                    │ (None, 29, 29, 64)          │          65,600 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ max_pooling2d_8 (MaxPooling2D)       │ (None, 10, 10, 64)          │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ conv2d_9 (Conv2D)                    │ (None, 10, 10, 128)         │          73,856 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ max_pooling2d_9 (MaxPooling2D)       │ (None, 5, 5, 128)           │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ conv2d_10 (Conv2D)                   │ (None, 5, 5, 256)           │         295,168 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ max_pooling2d_10 (MaxPooling2D)      │ (None, 3, 3, 256)           │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ dropout_2 (Dropout)                  │ (None, 3, 3, 256)           │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ conv2d_11 (Conv2D)                   │ (None, 3, 3, 256)           │         590,080 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ max_pooling2d_11 (MaxPooling2D)      │ (None, 2, 2, 256)           │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ dropout_3 (Dropout)                  │ (None, 2, 2, 256)           │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ flatten_1 (Flatten)                  │ (None, 1024)                │               0 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ dense_2 (Dense)                      │ (None, 128)                 │         131,200 │\n",
+              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+              "│ dense_3 (Dense)                      │ (None, 5)                   │             645 │\n",
+              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m1,210,245\u001b[0m (4.62 MB)\n" + ], + "text/html": [ + "
 Total params: 1,210,245 (4.62 MB)\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,210,245\u001b[0m (4.62 MB)\n" + ], + "text/html": [ + "
 Trainable params: 1,210,245 (4.62 MB)\n",
+              "
\n" + ] + }, + "metadata": {} + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + ], + "text/html": [ + "
 Non-trainable params: 0 (0.00 B)\n",
+              "
\n" + ] + }, + "metadata": {} + } ], - "text/plain": [ - "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n" + "source": [ + "model.summary()" ] - }, - "metadata": {}, - "output_type": "display_data" - } - ], - "source": [ - "model.summary()" - ] - }, - { - "cell_type": "code", - "execution_count": 4, - "id": "3fc17af9-0a6e-48d5-a177-43c06e443f2e", - "metadata": {}, - "outputs": [], - "source": [ - "adam = optimizers.Adam(learning_rate = 0.001)\n", - "model.compile(loss='binary_crossentropy',\n", - " optimizer= adam,\n", - " metrics=['accuracy'])" - ] - }, - { - "cell_type": "code", - "execution_count": 5, - "id": "3559e0d7-968d-463b-96c8-35092dc43a09", - "metadata": {}, - "outputs": [ + }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "Found 2929 files belonging to 14 classes.\n", - "Found 725 files belonging to 14 classes.\n" - ] - } - ], - "source": [ - "from tensorflow.keras.preprocessing import image_dataset_from_directory\n", - "\n", - "train_ds = image_dataset_from_directory(\n", - " 'dataset/subset/train',\n", - " labels = \"inferred\",\n", - " label_mode = \"categorical\",\n", - " seed=123,\n", - " image_size=(254, 254),\n", - " batch_size=32)\n", - "\n", - "val_ds = image_dataset_from_directory(\n", - " 'dataset/subset/val',\n", - " labels = \"inferred\",\n", - " label_mode = \"categorical\",\n", - " seed=123,\n", - " image_size=(254, 254),\n", - " batch_size=32)" - ] - }, - { - "cell_type": "code", - "execution_count": 6, - "id": "773cc524-f47e-42a2-a9a9-92efb5924c64", - "metadata": {}, - "outputs": [ + "cell_type": "code", + "execution_count": 7, + "id": "3fc17af9-0a6e-48d5-a177-43c06e443f2e", + "metadata": { + "id": "3fc17af9-0a6e-48d5-a177-43c06e443f2e" + }, + "outputs": [], + "source": [ + "adam = optimizers.Adam(learning_rate = 0.001)\n", + "model.compile(loss='categorical_crossentropy',\n", + " optimizer= adam,\n", + " metrics=['accuracy'])" + ] + }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "['Aluminium', 'Batteries', 'Cardboard', 'Clothes', 'DrinkCans', 'Ewaste', 'Glass', 'GlassBottles', 'Miscellaneous', 'Organic', 'Paper', 'Plastic', 'PlasticBottles', 'Shoes']\n" - ] - } - ], - "source": [ - "class_names = train_ds.class_names\n", - "print(class_names)" - ] - }, - { - "cell_type": "code", - "execution_count": 7, - "id": "6f8394ff-4ea6-4972-81ba-bf8ff5dcae95", - "metadata": {}, - "outputs": [], - "source": [ - "#MODEL = \"model_1\"\n", - "\n", - "#modelCheckpooint = callbacks.ModelCheckpoint(\"{}.h5\".format(MODEL), monitor=\"val_loss\", verbose=0, save_best_only=True)\n", - "\n", - "LRreducer = callbacks.ReduceLROnPlateau(monitor=\"val_loss\", factor = 0.1, patience=3, verbose=1, min_lr=0)\n", - "\n", - "EarlyStopper = callbacks.EarlyStopping(monitor='val_loss', patience=10, verbose=0, restore_best_weights=True)" - ] - }, - { - "cell_type": "code", - "execution_count": 8, - "id": "46df441c-6cd1-44b7-a07a-32d347c49804", - "metadata": {}, - "outputs": [ + "cell_type": "code", + "execution_count": 8, + "id": "3559e0d7-968d-463b-96c8-35092dc43a09", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "3559e0d7-968d-463b-96c8-35092dc43a09", + "outputId": "75a7d4e1-ed3e-4dc0-d398-6fa81908b5a7" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Found 1029 files belonging to 5 classes.\n", + "Found 254 files belonging to 5 classes.\n" + ] + } + ], + "source": [ + "from tensorflow.keras.preprocessing import image_dataset_from_directory\n", + "\n", + "train_ds = image_dataset_from_directory(\n", + " '/content/subset/train',\n", + " labels = \"inferred\",\n", + " label_mode = \"categorical\",\n", + " seed=123,\n", + " image_size=(254, 254),\n", + " batch_size=32)\n", + "\n", + "val_ds = image_dataset_from_directory(\n", + " '/content/subset/val',\n", + " labels = \"inferred\",\n", + " label_mode = \"categorical\",\n", + " seed=123,\n", + " image_size=(254, 254),\n", + " batch_size=32)" + ] + }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "Epoch 1/30\n" - ] + "cell_type": "code", + "execution_count": 9, + "id": "773cc524-f47e-42a2-a9a9-92efb5924c64", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "773cc524-f47e-42a2-a9a9-92efb5924c64", + "outputId": "9fdc7014-a9ee-4b17-fdb2-cf9881ef2499" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "['DrinkCans', 'GlassBottles', 'Organic', 'Paper', 'PlasticBottles']\n" + ] + } + ], + "source": [ + "class_names = train_ds.class_names\n", + "print(class_names)" + ] }, { - "name": "stderr", - "output_type": "stream", - "text": [ - "2024-08-27 10:07:03.511842: W external/local_tsl/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 264257536 exceeds 10% of free system memory.\n", - "2024-08-27 10:07:05.621110: W external/local_tsl/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 264257536 exceeds 10% of free system memory.\n" - ] + "cell_type": "code", + "source": [ + "class_val_names = val_ds.class_names\n", + "print(class_val_names)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "yb9H6wVr8P11", + "outputId": "f7a322a0-0529-43bd-cb44-61a5ef61fde7" + }, + "id": "yb9H6wVr8P11", + "execution_count": 10, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "['DrinkCans', 'GlassBottles', 'Organic', 'Paper', 'PlasticBottles']\n" + ] + } + ] }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1m 1/92\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m9:37\u001b[0m 6s/step - accuracy: 0.0938 - loss: 0.6927" - ] + "cell_type": "code", + "execution_count": 11, + "id": "6f8394ff-4ea6-4972-81ba-bf8ff5dcae95", + "metadata": { + "id": "6f8394ff-4ea6-4972-81ba-bf8ff5dcae95" + }, + "outputs": [], + "source": [ + "#MODEL = \"model_1\"\n", + "\n", + "#modelCheckpooint = callbacks.ModelCheckpoint(\"{}.h5\".format(MODEL), monitor=\"val_loss\", verbose=0, save_best_only=True)\n", + "\n", + "LRreducer = callbacks.ReduceLROnPlateau(monitor=\"val_loss\", factor = 0.1, patience=3, verbose=1, min_lr=0)\n", + "\n", + "EarlyStopper = callbacks.EarlyStopping(monitor='val_loss', patience=5, verbose=0, restore_best_weights=True)" + ] }, { - "name": "stderr", - "output_type": "stream", - "text": [ - "2024-08-27 10:07:06.317317: W external/local_tsl/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 264257536 exceeds 10% of free system memory.\n", - "2024-08-27 10:07:12.591927: W external/local_tsl/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 264257536 exceeds 10% of free system memory.\n" - ] + "cell_type": "code", + "execution_count": 12, + "id": "46df441c-6cd1-44b7-a07a-32d347c49804", + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "46df441c-6cd1-44b7-a07a-32d347c49804", + "outputId": "a6e8336d-1375-4cdc-ac09-ef6aafc25bc6" + }, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "Epoch 1/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 416ms/step - accuracy: 0.3067 - loss: 1.5516 - val_accuracy: 0.3504 - val_loss: 1.5105 - learning_rate: 0.0010\n", + "Epoch 2/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m24s\u001b[0m 129ms/step - accuracy: 0.3484 - loss: 1.4823 - val_accuracy: 0.4252 - val_loss: 1.3722 - learning_rate: 0.0010\n", + "Epoch 3/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 169ms/step - accuracy: 0.4524 - loss: 1.3676 - val_accuracy: 0.5079 - val_loss: 1.2569 - learning_rate: 0.0010\n", + "Epoch 4/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 119ms/step - accuracy: 0.4888 - loss: 1.2777 - val_accuracy: 0.5591 - val_loss: 1.2640 - learning_rate: 0.0010\n", + "Epoch 5/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 113ms/step - accuracy: 0.5338 - loss: 1.2229 - val_accuracy: 0.4882 - val_loss: 1.2480 - learning_rate: 0.0010\n", + "Epoch 6/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 169ms/step - accuracy: 0.5587 - loss: 1.1549 - val_accuracy: 0.5276 - val_loss: 1.1192 - learning_rate: 0.0010\n", + "Epoch 7/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 111ms/step - accuracy: 0.5927 - loss: 1.0217 - val_accuracy: 0.5748 - val_loss: 1.0473 - learning_rate: 0.0010\n", + "Epoch 8/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 111ms/step - accuracy: 0.6595 - loss: 0.9379 - val_accuracy: 0.6378 - val_loss: 1.0307 - learning_rate: 0.0010\n", + "Epoch 9/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 156ms/step - accuracy: 0.6679 - loss: 0.9421 - val_accuracy: 0.6181 - val_loss: 1.0177 - learning_rate: 0.0010\n", + "Epoch 10/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 113ms/step - accuracy: 0.6732 - loss: 0.8258 - val_accuracy: 0.6299 - val_loss: 1.0528 - learning_rate: 0.0010\n", + "Epoch 11/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 115ms/step - accuracy: 0.7465 - loss: 0.7060 - val_accuracy: 0.6890 - val_loss: 1.0320 - learning_rate: 0.0010\n", + "Epoch 12/30\n", + "\u001b[1m32/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 129ms/step - accuracy: 0.7431 - loss: 0.6977\n", + "Epoch 12: ReduceLROnPlateau reducing learning rate to 0.00010000000474974513.\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 166ms/step - accuracy: 0.7434 - loss: 0.6960 - val_accuracy: 0.6811 - val_loss: 1.0772 - learning_rate: 0.0010\n", + "Epoch 13/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 125ms/step - accuracy: 0.8163 - loss: 0.5128 - val_accuracy: 0.7205 - val_loss: 0.9507 - learning_rate: 1.0000e-04\n", + "Epoch 14/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 116ms/step - accuracy: 0.8203 - loss: 0.4903 - val_accuracy: 0.7205 - val_loss: 0.9296 - learning_rate: 1.0000e-04\n", + "Epoch 15/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m6s\u001b[0m 130ms/step - accuracy: 0.8562 - loss: 0.4024 - val_accuracy: 0.7126 - val_loss: 0.9316 - learning_rate: 1.0000e-04\n", + "Epoch 16/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4s\u001b[0m 113ms/step - accuracy: 0.8499 - loss: 0.3977 - val_accuracy: 0.7047 - val_loss: 0.9400 - learning_rate: 1.0000e-04\n", + "Epoch 17/30\n", + "\u001b[1m32/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m━\u001b[0m \u001b[1m0s\u001b[0m 127ms/step - accuracy: 0.8639 - loss: 0.3519\n", + "Epoch 17: ReduceLROnPlateau reducing learning rate to 1.0000000474974514e-05.\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 163ms/step - accuracy: 0.8642 - loss: 0.3509 - val_accuracy: 0.7205 - val_loss: 0.9587 - learning_rate: 1.0000e-04\n", + "Epoch 18/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m9s\u001b[0m 129ms/step - accuracy: 0.8770 - loss: 0.3378 - val_accuracy: 0.7165 - val_loss: 0.9665 - learning_rate: 1.0000e-05\n", + "Epoch 19/30\n", + "\u001b[1m33/33\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 127ms/step - accuracy: 0.8884 - loss: 0.3135 - val_accuracy: 0.7165 - val_loss: 0.9703 - learning_rate: 1.0000e-05\n", + "CPU times: user 2min 16s, sys: 11 s, total: 2min 27s\n", + "Wall time: 2min 12s\n" + ] + } + ], + "source": [ + "%%time\n", + "\n", + "history = model.fit(\n", + " train_ds,\n", + " epochs=30,\n", + " validation_data=val_ds,\n", + " callbacks = [LRreducer, EarlyStopper])" + ] }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1m 2/92\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m10:53\u001b[0m 7s/step - accuracy: 0.0781 - loss: 0.6427" - ] + "cell_type": "code", + "execution_count": 13, + "id": "c7ee7fcd-cbfc-413d-8a52-13434591172b", + "metadata": { + "id": "c7ee7fcd-cbfc-413d-8a52-13434591172b" + }, + "outputs": [], + "source": [ + "import matplotlib.pyplot as plt\n", + "\n", + "def plot_history(history):\n", + " fig, ax = plt.subplots(1, 2, figsize=(15,5))\n", + " ax[0].set_title('loss')\n", + " ax[0].plot(history.epoch, history.history[\"loss\"], label=\"Train loss\")\n", + " ax[0].plot(history.epoch, history.history[\"val_loss\"], label=\"Validation loss\")\n", + " ax[1].set_title('accuracy')\n", + " ax[1].plot(history.epoch, history.history[\"accuracy\"], label=\"Train acc\")\n", + " ax[1].plot(history.epoch, history.history[\"val_accuracy\"], label=\"Validation acc\")\n", + " ax[0].legend()\n", + " ax[1].legend()" + ] }, { - "name": "stderr", - "output_type": "stream", - "text": [ - "2024-08-27 10:07:13.799915: W external/local_tsl/tsl/framework/cpu_allocator_impl.cc:83] Allocation of 264257536 exceeds 10% of free system memory.\n" - ] + "cell_type": "code", + "source": [ + "plot_history(history)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 430 + }, + "id": "EKl71g9h1I35", + "outputId": "e180a407-60f6-4cda-9c10-1a09125c909b" + }, + "id": "EKl71g9h1I35", + "execution_count": 14, + "outputs": [ + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "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\n" + }, + "metadata": {} + } + ] }, { - "name": "stdout", - "output_type": "stream", - "text": [ - "\u001b[1m 8/92\u001b[0m \u001b[32m━\u001b[0m\u001b[37m━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m4:01\u001b[0m 3s/step - accuracy: 0.0787 - loss: 0.5057" - ] + "cell_type": "code", + "source": [ + "from tensorflow.image import resize\n", + "\n", + "def preprocess_image(image):\n", + " image = resize(image, (254, 254)) # Resize\n", + " #image = image / 255.0 # Scale\n", + " return image" + ], + "metadata": { + "id": "79YtiSkT1SAl" + }, + "id": "79YtiSkT1SAl", + "execution_count": 15, + "outputs": [] }, { - "ename": "KeyboardInterrupt", - "evalue": "", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)", - "Cell \u001b[0;32mIn[8], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m history \u001b[38;5;241m=\u001b[39m \u001b[43mmodel\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfit\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 2\u001b[0m \u001b[43m \u001b[49m\u001b[43mtrain_ds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43mepochs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m30\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mvalidation_data\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mval_ds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43mcallbacks\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mLRreducer\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mEarlyStopper\u001b[49m\u001b[43m]\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/keras/src/utils/traceback_utils.py:117\u001b[0m, in \u001b[0;36mfilter_traceback..error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 115\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 116\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 117\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 118\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 119\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/keras/src/backend/tensorflow/trainer.py:320\u001b[0m, in \u001b[0;36mTensorFlowTrainer.fit\u001b[0;34m(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq)\u001b[0m\n\u001b[1;32m 318\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m step, iterator \u001b[38;5;129;01min\u001b[39;00m epoch_iterator\u001b[38;5;241m.\u001b[39menumerate_epoch():\n\u001b[1;32m 319\u001b[0m callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_begin(step)\n\u001b[0;32m--> 320\u001b[0m logs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mtrain_function\u001b[49m\u001b[43m(\u001b[49m\u001b[43miterator\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 321\u001b[0m logs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_pythonify_logs(logs)\n\u001b[1;32m 322\u001b[0m callbacks\u001b[38;5;241m.\u001b[39mon_train_batch_end(step, logs)\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/util/traceback_utils.py:150\u001b[0m, in \u001b[0;36mfilter_traceback..error_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 148\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m 149\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 150\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 151\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m \u001b[38;5;167;01mException\u001b[39;00m \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 152\u001b[0m filtered_tb \u001b[38;5;241m=\u001b[39m _process_traceback_frames(e\u001b[38;5;241m.\u001b[39m__traceback__)\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:833\u001b[0m, in \u001b[0;36mFunction.__call__\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 830\u001b[0m compiler \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mxla\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mnonXla\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 832\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m OptionalXlaContext(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_jit_compile):\n\u001b[0;32m--> 833\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwds\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 835\u001b[0m new_tracing_count \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mexperimental_get_tracing_count()\n\u001b[1;32m 836\u001b[0m without_tracing \u001b[38;5;241m=\u001b[39m (tracing_count \u001b[38;5;241m==\u001b[39m new_tracing_count)\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/polymorphic_function.py:878\u001b[0m, in \u001b[0;36mFunction._call\u001b[0;34m(self, *args, **kwds)\u001b[0m\n\u001b[1;32m 875\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_lock\u001b[38;5;241m.\u001b[39mrelease()\n\u001b[1;32m 876\u001b[0m \u001b[38;5;66;03m# In this case we have not created variables on the first call. So we can\u001b[39;00m\n\u001b[1;32m 877\u001b[0m \u001b[38;5;66;03m# run the first trace but we should fail if variables are created.\u001b[39;00m\n\u001b[0;32m--> 878\u001b[0m results \u001b[38;5;241m=\u001b[39m \u001b[43mtracing_compilation\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 879\u001b[0m \u001b[43m \u001b[49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mkwds\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_variable_creation_config\u001b[49m\n\u001b[1;32m 880\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 881\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_created_variables:\n\u001b[1;32m 882\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCreating variables on a non-first call to a function\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 883\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m decorated with tf.function.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/tracing_compilation.py:139\u001b[0m, in \u001b[0;36mcall_function\u001b[0;34m(args, kwargs, tracing_options)\u001b[0m\n\u001b[1;32m 137\u001b[0m bound_args \u001b[38;5;241m=\u001b[39m function\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39mbind(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m 138\u001b[0m flat_inputs \u001b[38;5;241m=\u001b[39m function\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39munpack_inputs(bound_args)\n\u001b[0;32m--> 139\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfunction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;66;43;03m# pylint: disable=protected-access\u001b[39;49;00m\n\u001b[1;32m 140\u001b[0m \u001b[43m \u001b[49m\u001b[43mflat_inputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mcaptured_inputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mfunction\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcaptured_inputs\u001b[49m\n\u001b[1;32m 141\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/concrete_function.py:1322\u001b[0m, in \u001b[0;36mConcreteFunction._call_flat\u001b[0;34m(self, tensor_inputs, captured_inputs)\u001b[0m\n\u001b[1;32m 1318\u001b[0m possible_gradient_type \u001b[38;5;241m=\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPossibleTapeGradientTypes(args)\n\u001b[1;32m 1319\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m (possible_gradient_type \u001b[38;5;241m==\u001b[39m gradients_util\u001b[38;5;241m.\u001b[39mPOSSIBLE_GRADIENT_TYPES_NONE\n\u001b[1;32m 1320\u001b[0m \u001b[38;5;129;01mand\u001b[39;00m executing_eagerly):\n\u001b[1;32m 1321\u001b[0m \u001b[38;5;66;03m# No tape is watching; skip to running the function.\u001b[39;00m\n\u001b[0;32m-> 1322\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_inference_function\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_preflattened\u001b[49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1323\u001b[0m forward_backward \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_select_forward_and_backward_functions(\n\u001b[1;32m 1324\u001b[0m args,\n\u001b[1;32m 1325\u001b[0m possible_gradient_type,\n\u001b[1;32m 1326\u001b[0m executing_eagerly)\n\u001b[1;32m 1327\u001b[0m forward_function, args_with_tangents \u001b[38;5;241m=\u001b[39m forward_backward\u001b[38;5;241m.\u001b[39mforward()\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:216\u001b[0m, in \u001b[0;36mAtomicFunction.call_preflattened\u001b[0;34m(self, args)\u001b[0m\n\u001b[1;32m 214\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mcall_preflattened\u001b[39m(\u001b[38;5;28mself\u001b[39m, args: Sequence[core\u001b[38;5;241m.\u001b[39mTensor]) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Any:\n\u001b[1;32m 215\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Calls with flattened tensor inputs and returns the structured output.\"\"\"\u001b[39;00m\n\u001b[0;32m--> 216\u001b[0m flat_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_flat\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 217\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mfunction_type\u001b[38;5;241m.\u001b[39mpack_output(flat_outputs)\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/polymorphic_function/atomic_function.py:251\u001b[0m, in \u001b[0;36mAtomicFunction.call_flat\u001b[0;34m(self, *args)\u001b[0m\n\u001b[1;32m 249\u001b[0m \u001b[38;5;28;01mwith\u001b[39;00m record\u001b[38;5;241m.\u001b[39mstop_recording():\n\u001b[1;32m 250\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_bound_context\u001b[38;5;241m.\u001b[39mexecuting_eagerly():\n\u001b[0;32m--> 251\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_bound_context\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mcall_function\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 252\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mname\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 253\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mlist\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43margs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 254\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfunction_type\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mflat_outputs\u001b[49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 255\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 256\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 257\u001b[0m outputs \u001b[38;5;241m=\u001b[39m make_call_op_in_graph(\n\u001b[1;32m 258\u001b[0m \u001b[38;5;28mself\u001b[39m,\n\u001b[1;32m 259\u001b[0m \u001b[38;5;28mlist\u001b[39m(args),\n\u001b[1;32m 260\u001b[0m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_bound_context\u001b[38;5;241m.\u001b[39mfunction_call_options\u001b[38;5;241m.\u001b[39mas_attrs(),\n\u001b[1;32m 261\u001b[0m )\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/context.py:1552\u001b[0m, in \u001b[0;36mContext.call_function\u001b[0;34m(self, name, tensor_inputs, num_outputs)\u001b[0m\n\u001b[1;32m 1550\u001b[0m cancellation_context \u001b[38;5;241m=\u001b[39m cancellation\u001b[38;5;241m.\u001b[39mcontext()\n\u001b[1;32m 1551\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m cancellation_context \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m-> 1552\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[43mexecute\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mexecute\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1553\u001b[0m \u001b[43m \u001b[49m\u001b[43mname\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdecode\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mutf-8\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1554\u001b[0m \u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mnum_outputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1555\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtensor_inputs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1556\u001b[0m \u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1557\u001b[0m \u001b[43m \u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1558\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1559\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 1560\u001b[0m outputs \u001b[38;5;241m=\u001b[39m execute\u001b[38;5;241m.\u001b[39mexecute_with_cancellation(\n\u001b[1;32m 1561\u001b[0m name\u001b[38;5;241m.\u001b[39mdecode(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mutf-8\u001b[39m\u001b[38;5;124m\"\u001b[39m),\n\u001b[1;32m 1562\u001b[0m num_outputs\u001b[38;5;241m=\u001b[39mnum_outputs,\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 1566\u001b[0m cancellation_manager\u001b[38;5;241m=\u001b[39mcancellation_context,\n\u001b[1;32m 1567\u001b[0m )\n", - "File \u001b[0;32m~/.pyenv/versions/3.10.6/envs/treasurebot-env/lib/python3.10/site-packages/tensorflow/python/eager/execute.py:53\u001b[0m, in \u001b[0;36mquick_execute\u001b[0;34m(op_name, num_outputs, inputs, attrs, ctx, name)\u001b[0m\n\u001b[1;32m 51\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m 52\u001b[0m ctx\u001b[38;5;241m.\u001b[39mensure_initialized()\n\u001b[0;32m---> 53\u001b[0m tensors \u001b[38;5;241m=\u001b[39m \u001b[43mpywrap_tfe\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mTFE_Py_Execute\u001b[49m\u001b[43m(\u001b[49m\u001b[43mctx\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_handle\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdevice_name\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mop_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 54\u001b[0m \u001b[43m \u001b[49m\u001b[43minputs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mattrs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mnum_outputs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 55\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m core\u001b[38;5;241m.\u001b[39m_NotOkStatusException \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m 56\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m name \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n", - "\u001b[0;31mKeyboardInterrupt\u001b[0m: " - ] - } - ], - "source": [ - "history = model.fit(\n", - " train_ds,\n", - " epochs=30,\n", - " validation_data=val_ds,\n", - " callbacks = [LRreducer, EarlyStopper])" - ] - }, - { - "cell_type": "code", - "execution_count": 1, - "id": "c7ee7fcd-cbfc-413d-8a52-13434591172b", - "metadata": {}, - "outputs": [ + "cell_type": "code", + "source": [ + "from tensorflow.keras.preprocessing.image import img_to_array, load_img\n", + "\n", + "image = load_img('/content/subset/test/DrinkCans/DrinkCans_16.jpg')\n", + "image = img_to_array(preprocess_image(image))\n", + "plt.imshow(image / 255.0)" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 452 + }, + "id": "3ldsILbP1XAj", + "outputId": "d2de59c0-4256-4b65-9846-cd23ed62786d" + }, + "id": "3ldsILbP1XAj", + "execution_count": 21, + "outputs": [ + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "" + ] + }, + "metadata": {}, + "execution_count": 21 + }, + { + "output_type": "display_data", + "data": { + "text/plain": [ + "
" + ], + "image/png": "iVBORw0KGgoAAAANSUhEUgAAAbEAAAGiCAYAAABpkviEAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOz9eawtyZrYhf4iInMNezxDVZ2qulPfntz9eKJbaptLCyMxNGoaCQHuP2jLQpZBWELcluAKIVoCmraQWgIkjKEBCVm0rYfF8AdICKklaJBAftcGX7B4tvHQzTV9h6pTw6lz9t5rysyI7/0REZmRuTLXyrWHM9TdX9U+a63MGL4YvzG+UCIi3MM93MM93MM9vIGgXzUC93AP93AP93AP14V7InYP93AP93APbyzcE7F7uId7uId7eGPhnojdwz3cwz3cwxsL90TsHu7hHu7hHt5YuCdi93AP93AP9/DGwj0Ru4d7uId7uIc3Fu6J2D3cwz3cwz28sXBPxO7hHu7hHu7hjYV7InYP93AP93APbyy8MiL2G7/xG/zQD/0Qs9mMr33ta/yv/+v/+qpQuYd7uId7uIc3FF4JEfsv/ov/gm984xv86q/+Kv/7//6/81M/9VP8/M//PB999NGrQOce7uEe7uEe3lBQryIA8Ne+9jX+wB/4A/wH/8F/AIBzji996Uv88i//Mv/Kv/KvvGx07uEe7uEe7uENhexlV1gUBd/61rf4lV/5lfqZ1pqf+7mf45vf/GZvns1mw2azqX8753j27BmPHz9GKXXnON/DPdzDPdzD7YKIcHl5yfvvv4/W11cKvnQi9sknn2Ct5cmTJ63nT5484a//9b/em+fXf/3X+bVf+7WXgd493MM93MM9vET4zne+wxe/+MVr53/pROw68Cu/8it84xvfqH+/ePGCL3/5y/zZP/ubHB0dQaoRFaAjnIkIfVrT+KxPmkvzKKXqNEOSX7eOXVraMdLjGC1vWmf9OVBO+hlaBShEVKus9M8/d+G3z5PiPoRjk94PjYRnDqnxc0h4JyinfdndgRtog4votxMN5O1L7KE7Dodq1g/WxDs7gEmnPAUeNUcLxfRHWrcKPVf3eQevTv9165OtWTNQzuj3Aiodt0593bnm2mUN4elBAWZ3/fX8dYTZtxfvOE18jmbySvjdnYN1sfXzsI5cC43kc1xf+k8V8BmeLWl6L8OoVqW7xkaoCKtoNPSNT+8+NnLOiAhFUfD/+TN/mtPT04Nw6cJLJ2JvvfUWxhiePn3aev706VPefffd3jzT6ZTpdLr1/OjoiOOjo1GLbeyGo9T2ovPPf7CIWPeZc35xjSVi/rP5HTeHSLjSzSISsV3rPG1fzNeXfBsnNbiuXh4RC5zVIUQMQMVNeHv+defmLiK2tQHveb6Fzz58t98ke+p2HX4+ufp7JGJD6+dQItaUFf/6N+xW/oCvi9OwZsSkZsIaAhHaKGk6X0gkYpF5atZAxGG4T9tzXO1JnRCTprvr57vHrqpX4KGQjucgEdtTbBe3m5qEXrp34mQy4Wd+5mf47d/+7fqZc47f/u3f5md/9mfvrN4oTe376+Par9PJu+t4vaGPYHvcR5dAqx/jJlvvzp0U4f2u/qo/Q3p2pOuO56sfh+vVtUt78KbA0Lh4wtseh+35dv0xClMk/I2YKzSfWrxeIOoHNKBR6PheNXqD/nnav4cM4bI9x9XgHO/rk77nO/efHXiMXStDY6N2rLc+HG8DXok68Rvf+AZ/9I/+UX7/7//9/F1/19/Fn/yTf5LFYsEf+2N/7KXjopTq5Qy6IvObQHxuA/r646ZlKRrmLBIhidJJeI/aLYk1hdIqbz8OezUcN4TQjrsqXWIbBjjf1xJUjfNgijgHQvcpVN3Gl0Goh+qJcyv9TH8188kPTINzMtfq9nTn38iZu2eOK9XfV0PPbwP2l91a4aPKui14JUTsn/wn/0k+/vhj/vV//V/nww8/5Kd/+qf5rd/6rS1nj0Nhe/LthpRA9U7oHzAClkI6aWGsBLDd8y2GgKgmkeTX+Elfb3z0L/LDcL0tuOu5IWEzVG8OIYvS9kic/Vi+YgmzpTjY3rDTubXdnkTFrkAFlX0kbmMIV3uON6WOIWRpojEEQqGu1d+7Cdm4eXkX8/iVOXZ8/etf5+tf//rNCkl060p5cT9y/imM6bA0zSGb4N4JM1D3TTfaXunRvxiRufUx2ma4b0G23/eoiYaNUyi/6mt8+stvbEatcjt5+jjUvnR3BUN1XG/ZtreyIXvCrrE/lHMfmg+jNx4Zv0VGNVta9xDx2NWDXSIzhnj0qslIWaw2kUif1ykTXEUaVWCDQ+xnl5QwDH7/UkitWryeWrmvbW2b6348xpY7puy++XlbhOyNjp34utsHXlee+eUw8z0Lb1fyHUi1NtgbYPRmwe2rg9LPfc9vAt7fYTz+Sm3jcYj9JH13G+1Q4Z96M1bxd/wZCa9Kc3RL8Cnr9vSl66k72qyujf0+uD1TQZ89bzD9HS7cN8LF/hDY7kwZYlAH0l/f/nBInn1ify9eHrnedF3b07h6d/fNbcA49cbt1BPhuszNXUnNh9e/rTRNJZPe+XkAitdVu14nfRfP/jKCanmPpNiyR9HvcHBTUK1vQSpqsKdt+PKfjZQoTQHS2M88/gqlhiWxXkkZErXkIUzB/rUwRFS786xb3q60XdVmu0LujAN9oyWxcTBiol9LzH35MsF1luywZ1DkKLc5qe30sYxrIHAPNwChO8+6LuspQ/LmgRdxoiTW/YOuZDbsQTxc/njQSd061KkgeCfSPK9LbnBr/SWS2lhJLG2nl8bUaJXJrmTbUuruPrxtibz/x+3C50oSG+Ic9g5Mn258l07ZpzgYv5cBuzjfNmerErX+bieOhgMeJmSvu2r3TYWubafLZbc45jvH5QZ2sh5o5M5mXu223REkmjR3P34NWofh1+AU1Ypdx6QEHxILcMQprKvUM3GfJLbTS3LP2oypd63LtlTVwbcHj35pP0idvS3oB9X9cS+JbcPLNtiPg5eLxzav3oZBW8MIHX2fBHcPLw+GDPpdJ4xXhctt1T8kgfU6Xoy0Ld0GTl38us/Td0pptNaJlHOYaWGr7B11HgJDmpY+/HbbFlPZ8xC4+/n5RhOxLrwehOzlbvpjlkvvZkDUWByiTrwnaNeGa0/NkcTjdZj6h0KYvN152BCDbXXinaGyQ5WZpml97xDc5q8htqk6cdf66RLvLRJyC2svxXkfHrdVZz1m9+rE8XBox+9TkYxxZX0diKdS/aJ+2xCeqjkSzip5Dml74mKS+nzXmPameEjibl2rSDrm8rom1bb1DBHf7UMU23CdszC70h86wjefE2pHO1VwvU4P30Ifls0IJrjFf0Pevt+jFedqhy2/Qwz2nTFqVIrUv9tquXSeJu3ppO+Wfa29OM7FRL8oDaqJD0eyVyT/enziGT9p4dhOFX+EAlMnkUgEpXHqj+rNJkUgkB30035I+0Ulz1q496hvbwova1/83BGxYRjq0P4F9SZC3wbvF1BKwKS2hylRSFgNqco6EoDmWfp2HMRjzLuclZT4enS9ywwfOu96bY3H4/rp6mdDDTm8W0YmV8mO2dNaoT5HFAwn+B7vUT92TjelePgqpN5DwZt0UiJW76u3DC0GRVq1JYRCgZKRnSb1Z2vTVrCtcBreC0QNJOmO9dbYh/WimhXYEF7ptKNTeN1sqQ9L7wJfD4nb+pClKiVMQ0Rlt5XrUII2Zm3eNuP/uSJiw1JYv+Vo28MrGl/NrdR7l5zIkM56iBNtc8Ex1FPIoKBhNcO0lnh4WjUyweBC6IfY630EqJGUvD0hqovi4fVxbR5I15HCDhmF/pkypIXpZf23y4zzbLCcIeifh1tSVeTMB8vuI26erMXPdFOWwN57+xsEIXlggzpMPdXrdk9i50ulCk09LWsmjF1zUJK5HnEbwryvT9pR77sETZR4qSgRg+qlE50iWhJNI4m5gHw9E3bNGwVKdPdRR+pV9filSLZJUpdY3hIntguS4nYRq+jFeRvwxhOxfuNvZ5GkrObOsnZvlIeoKofUYUORJHalG4NDm/PsVxMMwbCgcb3wNIP1JGqltG6vLmlcrcdIYxG/PmhOWW3LJoMemOHfne0d0mP1Jm2fs0kZpVFw4OlQYfw8r9OPwoPDqW9ScHcdDKnqvTo8nMtKGK5eD7nu3lwn6Xryxfq6+0Gf9BHnTCIEd4esQ01VSBgje3S9I1MVaKuMPlDNR1f1F7/U/GbaN73zOKm39W68SqGrAu7CtgdzoxkYkvp22RhvAp8rx45Doc+Y+7rC1pS4OyHvpYKA51LjJvKajsV1uvtmi1aN/LtjuME829Z09EOfE0efg4UKxp9tR4quV2Msd6i+3Xjv8woc8kAcnLuJdNngtoNZHhjbMQz7frjbOdO0c3cf3ia88ZJYCq/j5ndbsNWyz0tTJaiTnIBu32d2OzC8EbXqiZtL0BXdBIM+KexlzM0QRXR8hqgXq/Vj3eetxDfCbV8fpJtenANb6aOkmThKtMvo4jkUkaZtN2vyJvrBBK/eKBY03bQthXWkSVRi3pOt99sNSQS3LalzfKT6oTl+p7BDndgn/94GvNlEbCTX3lWxpdCdfKkq4i7gVdjP3gSItp3b7oehsR9Uk6hxkfWb8verhPcRstvxBLtuzlpfSJsAdNV4B+ASEOq2e5dqsc67I32NZW3z6m9P+2B0X0LVW0aiEdsiXik+EvSE8exyV/3Z+8k2rzDUBx6/SNT7+2dY5bqdduv5LdnBeiXDpE/60x2oVh8BbzQRa8Im7afx+xbMy4Qhu8BBcFdszSuDcOtzsnEM2a8Ohe4c6Xcu8P9GO1pr2Q3W3+++3cu5D6hXbodo386mlPD/t1DW+PXVRyS64x/HUAb6vFtnu+7t9baNV2OISu1y3TyNLWqbKA1KSZGRGkF4fH0J8YqRdTpt6/bdUD9023iA2TTJtb3VDOMvLel0W2K8/U3rc2IT+1zt5v2w5aHwSrC4E0ib4py7I6n0Djtspy/Iyxqo12lC3AbTsd13MSbhWLXky4LdtrPkN9fAbSDpS21f+HxddUVvtCR2iOXiuhvjrUhNB+IyqCcfkCa3Eqa/OraG1ObQ5ZCinSAa0HGgdVBVjTTOd3Xg+/JEtU88XWOMGeyfQxZujQ/D/d3GVRruenQ9ic1lj5porJPDGFz7VUTQqzbtQ45AEJJf7RxxzjSNU2J78evHd8xx9HHEKH6X6JongO6ofCV+SCPFtDSk6WHjYTuZTzd+jccD+nUJifSztd4IZ8DYvruthYX4Sdh4UA7jM24/2MK464fZW1avd+FguVGHuF3uy4A3mojdFozx+hnrajqYn0afP5R+1wTs4zB7HRPSHx08h/T87XpihlSNMR5X/65jXelRyzR4+UoVCQHtKXMfDG7yY9fTHa67MWN7yOY5qI7q120yvP3EOdWU21aRhg0pUoZRBGwc7BrnIZVfqlbsNiPSuJpgKRL7TEQ/lruNzy41W79NrJt5e222CBnN+t+3j7Qu3RzppTjO/lqfzBws+3pjmmw+ffz3SEn1uvBmqxM70sSNJaVb3Mhuov17NXa6fQm66e8Ox1fRfl/xq6m2hcIN2i49f4PPA22KdsjdS+f2O+bQtZrayHpKC1KjBHVjaKX/UefdKfnRpB2J0RZ+Q3gf+vyVzf8OHunn6wxvNhFLYKy6ZifcwnjF2ncWtYfj634fm/86sF1n/EsTRe7tABwPwSH8+7IXTLphvOrFene49JfVqBkH9KGt/LeHz6FM55ZdSfX9bZ8V09pH34lpojpea4Xq+6vz7z6DFj9DysS5bHht+PS7x3bruTqs38fNn1SJvJ+I3u48vDtVx+dCnfg6uaePGvYdiboqvyH72G1CVAHuTcd2dIIhteT4ysNHUEEOezVds3iVVNIDbTfovuiDO0sf0ODdBt7j+rWjDO55P6xO7C+726abt2XIVb3vXTdd/N2M03512lYdycgKqj82oRr8saWqji72ocB2MX2qx1DkUDSSrXbWi+KwhT7G7T72xq4y+tpzABIDM+bumMQ3WhLbdk74fMCrVCfurDt5devSws6y+5RkB5Q9Npk6eN/oL+rAQg7mflVfT6iD/kSG8vhtLv27Ldgphe2xpTT9099HfVJTZGDqPFFy02qo6TvLbv2GQSmsjW+tZxh8v9VOleI/HvbOIQX7VKYvVTNxS1v3504S2+r8PkZ0l637sJoPSrtrQ7ixRHMN2F3nsFH59nGMDgWq9hJsv7s7aEthwzxkv8xyR7io6NHWhl2q6uv0Um+bBhuVvkgxOazmsWfHGnxUsH3H2sK/I8pIpbau5HMIDvs0I2Ofe5o6tozonTIGwbQgRuxvu8fstrUhwxXdTjFvOBHr48w7C0uxnWYMs1tvItLOUu+xzfORDsWjlvy+CTTOphAN9f3EqdaEdBZ5q0wFMU52YOCStu9pQ13TyLQqqr2SflfSJiuSfmxv58N17YpoEN83hQyQ7sEa+lQzjXt0Uuiu0U/blvRxOrwSNvMGn+1Caq+8LdTHq6Rb/RsQEkBHhZxSSfdLwLe7+frPuuqtCSGtcuJXlTRvCz2Vfqjt+d1a8sEbMB2CZALX3zsNF9VeE/65b51L25Tg30S/aCS/JmsaTd8las1YUZ2VGuHE81HqtuxeeO1Y9vtWndQSWV1J+jbuAwlug4G2B+dVh+HpLKqY7bbI4xtNxFQfgcJR36Gg0rRqqzMHy42bG/0DlT6XWHZno7zOWaf0Xcr99T3f0l03KTobfbeOZhK19sU6T1MvCpRL0g4X26kkqFpiiQMu001xSSCc6GVWlxM3QqmJQx/TsBut4b7oIq779gsl9N1zopJ/t6tsduTGzjE89s24Nhh32Kca4TZ+6Wi7Vro6d0+14oZxb+Z2g4FDN8XWxEHqAWrPR4fCbTEgdLLVm7WE3lHNdqnrjJLU1/RJPBOWQmNL6qwP1XypV8cWDZPevqrHIekTRXd8+sWfhiH18yfW3lpLLWKRdFUgNDWeMsyYpgG02+0dgqbSLtFL12vskNTmNOYc4xYXtYWP9KS7PrzRRGwQhjqn9XwkRXtD4fZUAZ0Fcqcg9Ncnnc+XPG4vq/mk47ZDcnvJMOwK0BUlrjtXugR+uIy0V25T3bWvrG1GsvFm3K96G+i9Aa1Lw/xFRiDcHDY0JZS79lTZqrvTzpustDtXRwb4fBKxUfA5JWDb4lVvEggccMK19k+6LgG5Szikjrsbv20BbaBPBzaVIa+znXWmaVSbvx+DrU87kOOgoduVuNszXWJ7N4Q3EcTG5xmw9+733huGbj7Bi1RDZfYdju7zUOw7GD0oxvagfZ17/9LIIY02s997shG8tz2Thw5ZHzL3bwpvNhHb42nzeYZBOw/jFqrX/aeqxesv7pcNTbifcSrcg8oeKLe3X6TO0ItHd5Hvgm1X/8Dtb6MznJ+QuKMSPWxEXx8JcAuSCTtujo+fz4fPfVXT8MaO1lZV1iaummmMz7dxb/0W2WILanNIrwbpcK1SvIAUBFGJsjtFutWObWmtj6ilafqOPdwFvNlEbB98vjWGvdDlqgbT9RCwNwbG7uzXL7z9ZKh/duz3h3p4baVXh/HXPp9uI/SKtK93CkrVzj9jVIBjvQl3SW59aVwMy9axU0Vnjrb9Kqof+zfyaPdu3im0ktbN0f7//g1NDpopda1Ety3VJUIBF4mHNxM8u8RsiJC9FO/GAJ9vIvZ5WrxjIBH/908eVWd5maL/7cDrMrC7bR1Dv/cXm8piY+WixFi/VVcfnm/COA+AUiPn+G5C1oUx0lhM01a0td+lhKz+ZLfKrpuX4EjTlsxvX5qppS/YJka1pLmt9twq58DntwlvNBFLDxveDF4PkW0MFnsX2Z607c112Hy2NfE6icdM2LuYunep7Gq663rqxCH7S/f7cP1RnRjtW128rreJjR7jveVsp99Xxi7JJlW1jYE+29i+OT6Upi/PIYRNBURqwhTUc8N2LiH6rfepE9u2tlqRvAfp+JGqIvsQ7eZplNVdCU6FdT5EcIdsf902jJnvt0Xc3mgidjgMkYkDVEg9OW9rU02xuHvblCDSPxmHYX9rIwe3K9V1uTO/GTQSR2/d3J3ufSzcSAqrM3LgxDrMCnaTPtpLjEczhGO262Tjj0+STXYMPmPgEEeQWlpSoOLhsjhgWyJY837fkKaOFt3620/bjGJ9hq/17/AsSJuohl5I876PoKX4dfHva9PQ523AGx126nAYt7hiqqir3k1Q7o7Y7K/7dmHsxNqL08DrtD3XbdeYXG+Cc8pOUIfPKgn2k7uYj4eVOC51av85pORU/VU/v+N10i1bRQpGE9Iq/UTR86maz54yW21J+yQhJkmttBSaKnmu9p1IbJfXqif562X1d+DchetI7deFz6UkduMJPYILrjm37ovANO3GoeGs+mSKXdzOdgnh9x4Vyk0nkCLuHfttDNdR5+ysWzXSV1N0uwf6PL3GegY2+Q5FjFHS0iESQypxXFfG76rsblxO0udDbWjGqE56K6DoH7+++TZGWtgF+1Rl23arkIZkKkhPXzAkzQ3M2SjhJaU3h7HjmHgpL9rMGl1r+hy2dhfV0RQkStp+TaRq5dm1r7wqm/rnkoi9UmjPvT2Jrs83q90VjCtDtTfu/ZOwWZwvf8LuaOtAV7xujioHqahVP43cbUDv2+z7iGdr2/1cwyEMVF/f9tk1UyLVJmhS93fj3JGGnuonXltlS882kjA3khAqumX1PB/Z+H7pac/7XXazPmbyUMZyDNwTsduGOOvuXKN10woatcahkkJM+9oQiS6zeUeL5aVBzVgf4mZ/oNJPEYjeazB+twhDzgeH5t/3LDIBfZLJoeaH3jUUhmaYiG6XMVatd9C6TYrs1j9GAu6mv4u1eU/EbhvewD0zws7JraJb80tF6SB4LQlsB0artghKJDXeTWJog9yu0zv1+BuQb1ft/CrgNlTJMW9fnl2SRV++Pk++2K2NdNaftqVOVMPt6Stj1/e+9uztD9LZsX02b8z3FIaI3U3hB5uIvXnrtQU3nwiHGsTvQp04voxtL63dcH0cd+dJN6QhrVxvCar10Z8+2lRDStXJMLwxtc0ldZVb9plY4M0J2FDqXSMkI9LcxomXtI+69quhOps8iVVStjffOl0Hx+tISb1l92h7h9bp/jql87y/rO1yJPkXAkWtcdmlItynVoxpb0sS+wHzTrw+jOVcXlfYhX/6qp1MOt+FGGX+cEhX5DWyb8Gu9tykgqG2DdsLRG3/XaeG1x1E4W0je9uoAB1cERS7Z0yjLhVJ+rTzF4d7X9/dfGPsr6EuVrXTqFBn/KT1u8FJKf+79TwpO33errd/sx9q512oz1O7WP07NZnsqbNJdjdepD8wkthQ191clhnJXb4EGNOWNkckwQgdc3e3kPA9YdyVeELmObpo3O6rqIuQ6nSQ9KS5Hbi5hNgeUaUG2iggmtorLZqYhjb4zv43WHcUOBXbZY2RLqPKaqj8BpuR9hLVtLE74beTRpcjHwJL4vUwSfb4XRC0RDIXEO9KDh08bme+jC/EC0aSzH+C002UVEKLVYNeVAkiifow5giD6lXFhKt/moJjWSTqxN34+YqaZF3G84B27kheRwzpjEF671isMn0U2xznvu/LdJ+5ObzRRExrjdaNMDk04J4v7BGhkZ6nnbxBnzMoto9H9yDYpT7Y9ZsBbmdbpJf6+Tbf2yZiUaVV51VxpkrNXYmk7/30HWK6mkUubcI2ojP94qhZ3FaZ/eOfsoy7S1YtKhP7QNWqurTrUm5UEsKVsAdbWMRNrb+dcVNMGAMVzgMl6A/O8a0Nb8zm1y6zzxbUlKXq/m7bgtJ6VE3sXNjCpM7fxUtCOkF3cVVNqjZKqv49yJR2+6A7/IM23+Rr18YW30tzSWyTrV2ek7ZXYtt7MY5rJHaEizjjummex3nVqART8t/DPKj2eA0TpaF12Y7tmBLFepRrkapTdsptKU+k0j7z+AUXJdedMzeHe3XiXrgr+Wp7eV8Hdovn1y+9X4VB3R0q+ffzB6m0Ej8HKTIgKHF+8YpDidQ5tnIODcmWTvJwrO/OE/Mm5e7Ouy139TQ86Y50Ox+s8c76YX/ZqkPod6n9un/t59R//jl0mYEhVHabDsbj31rjezudms/pa49zDuccIkKWZV74uCXnjjdaEnuz4eZkoGU03VHHvjL6YFiqabhGn3A/nm8KNE1JxaWo1onPCdxmk09FDj2qSxjq+YakbXVbUuauEvbBXXmAHYgFHYXSTmjwbKSBrgR6MAZK3RKb2CnzGn0bNRVdaaev3AiN9L87+G4qcd3WmDdekl69qXqLHBrbuF76vSSVUlhr770TXyqMYf1eYgV9br21yuOaZQy9rzFMvAJbE5PXnYaN6duhNKkM1XCj7S6LhKetfu3vlP2u8i0BrCsMpiXt4KZ7vej6U94WI3yr0HhZ9ktkflSGGa+Wt1xPmkOltH1rZShPn2t8nCrd8dlOG9vTTevn6j63+7Eu9H3Q207V1+ND66bfFT/+FhGKovCS2C1JzPfqxH1w5xqzQ9QtSa5kAlx3wna9hfrUG+30yffRtqZXCWPw268nSVVZ/jORErwxsP3HtjpxSFaOsMWGXLNr96mxXm9omIHrENj+tt9OP4xVE/anV9T2zZ73WuvWp5fYFFqnn01b2irG/bgOvd+XN6oGNZ5QpPNZK9Uzx/vb062vKAqqqkKc4zbgXhJ7zWHXUmmpD264ae1VldSLKFEnvoac/PUhUYHVh4AjS0z7s+0p4J9IMFwLA6owlXz0jNXIvjxE/btPYntdwEso+w/ppjDkhNKowmDfJO1zbtlX5z51Yq/KL9Yx8L6br60ibHseNr8lea+2yuhrY9rOYSeetJzQf5Gw1Y0YHqN0LPskQ6UUeZ6jtcZu5b4e3BOxPfA6Lfa7gqHJ31XNbNtx2g+7qs1dUmRfubeh09/Ov33Isj9dnZy+GIRN8pCf5kbcJhHUQQ/7FDBpudt0cDtPvzGix35yW3P0rnTncSOj9ryL9TWaQ5Vs3HeAwoEwtNmn74Zgi9gltGBbRbhdV+rZ6J+ndQ/93k9gD50nvcOwZ2z69omutifP81tZ6xHuidjnBMYSju7m18+BtfMppbxnbCeNXzuNxNIuv5nOu6SEmmmm4VSH8rRL3Q3t/ON2xdgqIfaNaxnNo/Y9XnBYk2tp2lK3o1unBJtAQCd9n7rjK51y1bfFq46Fw6hHqipqXLOD19zWfJHOBix1fxjVHLaLRO6QYFt3CXuPtAzANvHT4XlTTld6HJRuOpJMN3/KHA0fNbkeeCXobsmxheue8rTW5HmOiFCW5a3g+LkiYoMqiCGm+yWoW3aJ7bdZ/lh1yCE43JRbGhW+tlci2YHPiHr3Oawc2q6aOIlXF9aHX7ckl7B7SyNVtMtJdndJs6j291iMpAnHw91IaQfUHQkZXQm2zVhEYudtKTevt8WQtV+Oyh9hl0TT51DRB1t593GZSdn+09X6O99NqYZDQkGSqGGvuc8MCN8tqXDAgaOf6fGcyrA3ZfPutuy2nysitg/6uv12FCgvn2u8LcXPGD3/awUtGrCbS95lW+lvr7cvpAeOYxrnaBGWxu7SLXMIcUX7ZSOv1fRMAg2TSNeGx6NPqr6Jg0+fRH6zOdFsuX0E5g2YaS04tC9u3Icq6AS25kRHy6wSfqoHhwi71OcpvjuStGGgOKmZmAEPzTvYa36giFjfYBwyQLvK7ctyW5zGUJ1jIFXhdPXpQ8ZXn/b13WYa6W4b3+7nqPKStA5XG6dFfAQGEcGfZVakHvRC3Fh0okIbIJrJG5WiL/hDoDS2DRU5cBUjzW/jmm4EtzFWQ5LIvg1n7PvWUlCBtxfZCmN0V3AI09e3HvqeH2IbS+fN/jobbNPLMFWsM5QX/1RQbSvlDxXH8ro4Xmcso2Tdk7j3eZ9TU7fc2M402tJN4HNIxG4qoySTZCyo8Rr8QwlbvVFxvVa1idY1CngNoVkP/Rt8d8Gk3/sWVNPHghMfCik+FyEQsMYLzBM5r9p0cdMRIBBArx7b7mytouu983MmUq6uRhLCnHJ3ykyMdVq4HQkvqnIlTbDtHHNH0G3BPlVgnwTR931XGX04tISoQRVmc01Oai9L628RKRUsVz0EdhejOtTum4Dq2am65Wqt7yWxm8JugvB67vQ3xaorhdXlvmnqRKBvBHuNzH12iUg4EoKXEj8nPmStICFMjkrUiIk6EW+tcIHQRVuZtyEME7FIyBqJqwkzFFsVPx3Sa1RvpxrD4Ejrow/annGHzImuirRdXrTXNNJYPC+1O7bJ6wLXtaPeaF0pWvbkXcxGKuUN2d9f7hpvSHUfwR3LBBwCbzgRizJ1Cvs7Jk1xK6qYnmeS/Ls/9R7osb/sybBdax+3L/Hd/sk9pFV4mRC51PAr+TdJU38GQiPNHFGiECX+wsGkTOdCahGsEy+JASIOcZG3NEkeHQiWD3TrJBJAHx9uS6UShs8o1xAx1ahe6kOhRGO3x1erSCoTUGC0SQieNILgtian3SkDkG4m+zn3VIqNPzsqqN46/BtV61VvNqF6g3ffkmpylDqxVU+/+1IqWY2ps8XGJNqdPkLQyU1kFJry2HrWPB/SEG534BDzO8gUJ/+2cZUanzaDc3N4o4lYvR5asD1pesamF65N0AZUB+0vdeID1lmkMsM56jeq+Wi0bftqaibbGI47ErJos9lXz5h2HrrvDGwXRAO3SPxsyzApMavVL3ibV5SmnIB1CXEUQ4zO4ZLDzC7U4wLRi8Qyqh9rqhKJSyCQSnl1mpL2hqF1fAfUKkfQyZiqELVBicISIiYoUKpx3W7ksqR86ZF5lKplPBWlzNhxSTn1hhdzJ2pXEimx64Pq8aTdF0Q7GDVOzW0EHQlOpcQ5uasrmXutypoB8/gnk+rg4GhxirQeNg44qQwpnTxbe09bfG+Vq1RTTvPRsGB1KZ0iEnajjaHyuV3Ese7jduT9vvWzTfzGgPQy1+menLA7Tc/EdYrC3JIQ/kYTsT64br/cTCLrz9sfcezQenan35owcQMZXfbuHtuW0vaXfAvM8E6IG0q9RybcpZeIPIFJc2zhFNLaQLwkbJiu1R9hsw9p4nbdInoSN9tYf6eadIOIm3knjXY0xKvmUqMNTeq8WvsQQA4wOmwY0t44dN1BceNqNsa692pi1QSkjduyalIl+VSkQ1t8Vdwou5t+01vJxl1jlLptSztbSgPYnp3S+0a2uaGUqRs7IXvTqVafdKtoZUkIaboyh8ho/Tzt18G9pLd59Y+UyEVnmbT/ZbAj6pXULXU/7Em+LTy0idkt0bA3m4j1S2I93IT0PdxDuIbk5R4cdhRCl5SNXk8HEtVWHXHCDiGXFD3kBDGUMW567cL6iHWCW4+nVHwu27tAK89WvpRAS/NewqdzNHYtiR5+yfIJeZxzXpISEBe3YlDxdquESY4cbkMgqaWu+L2vfd3nLTVUktTVvxvpRwWnBxVUilprtBO0UmhRiOhaelN44iW62cz984bAqqTTfBVpAFapN/u6/p4ds2+r82uw7X2YEvNGgklliJBLBJStEw6rmcJKj5ewhjq7u2Q724G2lw4t3bWyW/aqmLUzR+uhTvqhW2y6RKO01J3baX0pXqm9zI9bS/ysCVutPWkeJ4xAXyd0JbzBbuhXSfY+8Eg0BMz/vlcn3gj6N94W3FIH9y3Hw8jTq4GWBPbaIS2N2jBsVi4SMOdwNK7x0Y03LnbfDEtpXSBezQWOSil0iB4RPRRdItnVEpvE+tvEuY+IjWESBu0EEg6nAVo5tPJqRGMUVoXgsCG5VorMKGwkaioEbQ3pavodiVpCkuL77iA3mDgEQ7rlNimiVCXtfD121i1mRjVl3AWMdYWPuPR0wUF17bKj7cqzK3+fV2R/ndv7VZ/3Y/p9V9l9MGLX3Al34dQBbzgRqxfo4TlvVGcKh6sh1RZ9fN29AlXggl8nNKOEVBOUVHJKEHXOs6OK5iCzc+Ev7OoNTx2Jly/PuuasWErEao/EwHKnxCFlv1OcWmz5FgSJNAobYUNtM/dR2vTfdYeIGa1QSteSmSjvxKJR6K7dqC60LUHFM0GqpWLaxjnaCVXcDGlrRSRQzL0OEnCzXTHFuweuJYmpYZTatqP9BGifW/sYj8F9rv6N9+d2fYN49dQ9po+2GPID995778TXAPo6PR2U63IqL4sTGltA71mU24YbNyaoKES800WUkFQ8V+PTxOd+s5WaOEUCVdsTotdgLW1RS3fedhaJoCeMUuPfyDSxrnYzGzwHWxJVeLVKM5KRRnyKxE2U4Kx3BtFK4YIg44IXpQ5qOS+1eduZ+GNptTpKRWRrhirhAqLitX7edHfzsys9Rby3N/mhud2okm+PI++vY+TcDU06BJt9ruP7PX63PUH7yhhT9hDhOtTtvrssb7xMOzjehav/PRG7RajVEdce9d2ZbzyZDijgztWJN2xMLYmh6ogXtWRGg26UntANkamcC8TJb9kuxCtUUWqJkpg0ThyNFOTVj5Eg+nBAUm/w7bXZSGwSXvZ1o1YEaTF2dWSKVNP3oXwVCKIRfyBWx81XCVZcLaGZQMhUIHZRFanCpx+C0IP1+LZVg41rSHB4UQ0O4KW9mN53QaTGbUnMP2qrtgICdw5jN8yWVHiDuX6IOjF9v09qG6NO7DKe8VBxt9woifWVvSVt7WnvWOjif69OPBD8+rwDaaIPbipdxG/XlIL2pW7KG9ahb022eoMaIS3G/Uk1qce2YYsr7Hz3BKrxhUslnxYRi9IUUfWnao/N1D1epHHYiJu4l+R8+VFaqwkiTbkS+sQ70ah6jrWb2pwTan+2oXGL7pxBilJidDdrRKTglZgY/AWclUCkwCnQGpQ0tjStVSBogcCFMnWcCxLd+lMdY/O7s4WGZ1KrLxnaCPdu7O25tV/d1DB7o9RgYzfMZO52cdlX/nXViX3ph571SWdD2qG0/NbvqDLuSXPIXjO2TX357tWJLxtuU55+Q2CcKiid/PHNMIFM4SZd6m1DumMjSiSwKLVI+32s1xOw5tNJI/mQpg9leM9BT6y2CFjSoLh9S1JQLKdVbk/LvUTnN5j42byMBExhkzNmwSu/XVrI6omWTxsPV2utMYFIaS2YED0kEklVe/41sqCu8VX15hdtgKm3Y0JS/G9JXehvBtsb9UtiRl8iHMqw7lqfQxJPKmnd3K7/esHtRGBM4N/4N/4NosNF/PuJn/iJ+v16veaf/+f/eR4/fszJyQm/+Iu/yNOnT28bjVGwc/B6VB61NDCgj+5CNHq3ikVa5fSVN6bsG8MIjqn50fpI0lyv6j6VRXzWddYRieGfwmc8jJzYwVwgGPEz/jkBURpRCifK28LEu9XbKIUFyc57Ofp03k0//nmCYV1QL7oYXzGo2URhRYWD0iGP8+Xb+BnrG/izDioHlZP6zzqhErAorGhsqMuFYK8OhUVRSfNn0VhRlE5ROEVhYVNBYaGwwqYS1pVjU1qKylFYobSKwkHhfP7KgXWxTu0jktBZK0rVg9/0XyoJ3+6mWJf3Zu+1oyAlOrv6csjm1Zcmfldh3OoIMTv+xsDrMhx3Ion9HX/H38H/8D/8D00lWVPNv/gv/ov8d//df8d/9V/9V5yfn/P1r3+dP/SH/hB//s//+btAZTRs6ewP3KEHCdlNcNhTdgpda8tObkva6cZwdV7LlaiMRqgfRikgr8NkB7FGiMSkUbvVqkSJ4xgkF1GJG35zNqvegGsJLEoTHrla+gqqQJ82SGYhvQRJqfcTVeM61L7aP1Ia9aQXfBr5BhKbmUgSCV+Sg8dBNRhCa3lbV5DEpPFodMoTYu2C84fxKkYnQbpTvh6jG0/adH7VU0s1B7elFl8jpjHJ8DxUrS99EmpH7XVdpmnMWo7l75mDfZLOPq2FL374XXx/Ww4Pfe1tVNXN3tbn5HEILocOxxvl2JFlGe++++7W8xcvXvCn//Sf5s/9uT/HP/AP/AMA/Kf/6X/KT/7kT/IX/sJf4O/+u//uu0DntYGodnldOJgujJtcaQteTWuk+yfNYeUm0E5EsZG0akKWECakIYR1+bL9WRPLWmprjp/WXZYQwoaANWrFwZ6KBFM1BCBVPzYyj+9vXSsJtguNdamEuIFgnPdkVEqCajSxn6HRWmGE4DbfMC3xe7phqRobiQkD4X5dZ/b1YYi5G5v2ZcI+54/6syf9y8J9n53wOnDr6kSAv/W3/hbvv/8+P/zDP8wf+SN/hN/7vd8D4Fvf+hZlWfJzP/dzddqf+Imf4Mtf/jLf/OY3B8vbbDZcXFy0/t5EeGWmtRHcZd/3+lkrbU+al9wwCSq+eKA5jaBR28qI0hO1/curEuPZL1WrClMCZV16uFmCCpJwtow6Ioh11OfNJL6v1Y3SqjdKcP1tSQhv2g5p1JJVqK8S8X8t1SP1Xxm/C1RO+XyhrU0eKC2sS2FdCpvKsSmFdelYl5Z1VbGurFc7VpZNZSmsw1pbq3UTml2rGpt2bGsFbjbWqUptFydwS9Azl/ep7vatn/j8kI37sPT99XfxrtWFnXp2pX8T4NYlsa997Wv85m/+Jr/v9/0+PvjgA37t136Nv/fv/Xv5K3/lr/Dhhx8ymUx48OBBK8+TJ0/48MMPB8v89V//dX7t135tJAZR3rl+ikM8b3YNdD9ns33Y+c6hKzDV6pv2PUTDnFhIq9oqiNiTL5P7jJtk12ZQEzBpHE2ERoqyzkeYd04SoiU1ofNlpOUlrvoSAwAnRLK1n0otjcSyouameRcx6mlTIlnVXqAquPJLDAkltWrQNakSNww/RlZRqxKV1AGewu9YR1OxsworDuWix6JDKR+jsdLRJV+Y6BD6SimM0SHCfsBbmpBISgVfxxtMiV2OCUPBsG++4Saq24GihrwCu+tn1/5xqFPFmL1IBaR31Z/iV8+bHimsT3LbV/8YfNN8Tdk7k46GWydiv/ALv1B//zv/zr+Tr33ta3zlK1/hv/wv/0vm8/m1yvyVX/kVvvGNb9S/Ly4u+NKXvpSk2E+4UhiT8vqTbf/Gnl7V8UrVD9fO9bJx3rYv1WeppDmEHG1IKUTCUt/QHAkXDeHz6RrVZJ1XkjLqNI1DScwX05CU19jGkvd9kOZpkaZYx7ZzUNov1IQvfRaLSUicBDIXik+27HAYWnAqdXNRwY4WbGpG/O8Qxkt0s+HrYGeJXL6Sdntvj2fbvXEO2ZRHQaIyTWWVIfvXLjy6MERcDiUEh7ivd8vqY1T3qRPHEKQx+A/14W1JenfuYv/gwQN+/Md/nN/5nd/hH/qH/iGKouD58+ctaezp06e9NrQI0+mU6XS6o5aeRXxrMG4xtAdUOp8pxNXSPVM0Doe7oHmjjLgqSixdka6bL55bCk4KaV9sVTGKnSCYlhLbVSAYqZop3XhUJGhd9V6zYFPX+loVlkpkTUtqYuek2RBirS4hpu1ekNZnX5ouCMlh4/oqGUkTbHVZm1SElwlDFdudqpFiRHwv1fkGqjC2jf1L0C4haiLhnJngjGCUP4emfYiQEKcRQihiRFyN1VCrU9K9D9rSXWhrX8atOdr3uy9fMn8OZNKa9dOZAz3FjCOu11/kXSmn0Qy0DzQLPc97HS924TKwv3Wed3HZnf9wuHMidnV1xe/+7u/yT/1T/xQ/8zM/Q57n/PZv/za/+Iu/CMDf+Bt/g9/7vd/jZ3/2Z+8MhzEcWls3TL1x+kz+dz/j0N6s2uX3nJZpqUO6uHRw2IHv7gnQo06IWSTFWHrofxKyBlBaIcEW1ERzEGrDjYRtS8WNX2oiEItPZdStdhI20vCrIVSNB6BIvKjSf3o7T0NovF1syz+zttVEt3gJUTpcvc5UQxzrvolbOI2EVxOw8DvhbndtSqlqstX+un+ClJROrM782S6zMw8bXWRsQCunJ0rxxJeq934nLqgB694GBKN0a66rkK90Pnq+Ut62aLQKV8g4/10rDNoTN5H6CtGUNER7apSIYwqlDA1T144aooSWswlK4ZSuibIO0rlSqpEA62ktXSR2wDYR6oOm7xsGqI9pjc+b961B62EI2+XvZyr7mac2LqpVXnMWsDlpWf8nkYlK2rCrPwbvONyVp43f7ZCwOyBi/9K/9C/xj/6j/yhf+cpX+P73v8+v/uqvYozhD//hP8z5+Tn/zD/zz/CNb3yDR48ecXZ2xi//8i/zsz/7s7fqmbglpsqY6dkqgLjoJBIw/2I4T28F3R1nN2c6uJftr6hVfm+ufR2g0kTtUDYkG1qzPfQVmGwaImy3fDBH531y7ihZWumzVhnSfJHIgRCJTPvTdd/V6sE41lIjJlCnaXBtdcZgxw5tQl3CFr/3q1aGytj/MG6btYdh5130cPTD21jVUntbZFsUgnUahw9zFcfBl+tzmFhDiEhce4x1uwtoa31V3G5pFmpDyOrRFAGlQaKyM45jtP95hNTW7BhHw/ZtqVtbijTP+wlSl7ANvd8uf2itbqeRAaK3XWeKZxzf7hGadJ9s/R6YmgdrAzvS3aHZh+DWidh3v/td/vAf/sN8+umnvP322/zBP/gH+Qt/4S/w9ttvA/Dv/rv/LlprfvEXf5HNZsPP//zP8x/+h//hDWvtcjqvB9yad88NmndrPdOhvrvOvySscIPE+KKbh0Qi0hTTV5Sr3yfSUkIsGgIWOfVGxVjXIXFDj/uolwTrsoVaPTrAfO/v6x39cBfngzye9bZEaj1L29AQPBBxdVQQISEiofeVAoOXbnWI+uGZHV1LxCh/xqxme1SsP+LTHXEd5RrS0Wwh17uWUjnv1e4A1zk/dtMx73MmuU6ZQ7axeK7s5jPzbuHWidh//p//5zvfz2YzfuM3foPf+I3fuMVaXx8CtpdwXYew3aB5t9sz2+TmZZ0vaSSqRl1ZS0/xe9wKI9GK3ojOS2hNnrhRRimssYe5eu/0+fzmmxBGlShcOs3ulTzjpp0Qk07LdrT5kH4dkvHjZtps80rRkm8b70Kpr3YhIStRC6SUhE1N1aGtjPbKKSX+klHtlL9vE4VROshM/ir6OG6qLjXZ9Ht6JU1Rf1fDc7pfBrv7uTlEsIYcQXY5U8Tnabr9dared4finDrINN6g/Xjcxrq/rZG5j514SzBW6rrpwO126b9h4bvqrXeP63N814eweUaxrCuS1dJa+1xYet7L272CDUyEcGUkrY09Fp+IKZF4RSIYN/H65U42oSFgbeVqs0VHB5R+OIwF6R+SSNib+Ih13eGdThgAaOSiBoWGAQgUsFW8OAl5FChNFWtQzrvlJ6dRYyDmVDWdYrplRR60vQw2teMpPA4OPSozRGh2PR+UdgbqG+ulWEu6CVHaRQh3EbCYp3nXfyRoSAV+yL7w2qoT72E3J3WXvGGj927DjQlnTxk3UV9cp+5Yy5aLfKLuaKUJRM+Fw8rNG0/cdLI5N5u0C84kceNPnEdadaikvGG5gB6X/7aMEYw5vekGSx0yUQxkaKQfL0iqDtaJOBvCVTkVCVtTVyO7BmlVhX5xzl9zE0N54ZAgjYkG4+U0jPLzM7IOnh6mGycRy5bKMx3/PsKX9kB/39ytNDZGChsiXvuczHa97xKaXbjsKqMPlxYhHFAnviwNzBi4J2K3DLdmB+uFoS1sd9rbW8YvRz3Tqi+y7tCyb0UPtxiIN0KLuMU/B2gVDg+DOIfTIbf4yBZSixpROqImeLFkUe0AN/t6ItKmHsGxpZIcFMYS1VkczZ1yX8+mEgm6p9l+UwpH3OuybPgdEVEClqhI9UiYqGd0XuXonNTqRSMhhJXzZWmlsFphjcaIwgSXfKOV92RM5C1PtnRwJAiOOULLsSBgRY+ctgderjpx6Hnb83n85r+P0DUEa1yefeUMwmtCrIbgc0nE+gexh0cbHLjrDdoYAnadkttc0lCaLWzavzrcFWwLAH34R859aD/oHlrsO4uy/aONs8R/VUBK6ictwhVTR5Vgc7ElSfqoQqSJNl+rCpNDy5LgkOJRn88KG2fUnqkoQ6R4q351lySENagSGxtD42lZ/xbf9lQNJkl3JMUOQmzfNipJfRGFmiR0OyGcVFPSSkfN7cdxCerDgCPh5minwlUvyZg5421lTtcnzrwbvgpny2Kf1rUTbwn1BXeaFJmN+PgumMY+1Vr8vi/fmCM83XK70CcV7a53mM50Dzvvgy3pTDWeoEP4d/Hta8e+dzeBN5qIxQ10b4cc2l+HCDxDRQzgJLe8ALfrGS6za7Adz6eqekNtXJuT82TJZI4T3z+POCaoSYpj7ItEPRgJTfwu220UaF2XEjn2SPT89SZpoN+GcDVei76s+lyatPuiVaNqy0DbCq821Ft9aGtdZ6xX0c4XOyrtMNVPlIZAWnglz3vUQSJexSfNg4aQ1dJfm9CJaw5Cx3aoWmRK0oV+dCqMBQ5vi4ylhUJ0IGEqzK2Ip+psmao9V/zN1sE1JDqr3MJ67UIyjRNUbk+Fts+edNO6xqoU07RdwhQZ3iFitctWmMLYdNeFN5qI3QWoqMd4jeDW9c/XnD+DWq+ufv3gOoZ3IUmkhIYwEG5gTg5Yh/wuEbOcSBBlosNHQ1hISqX+jM8TopMo8TyxU630amCu9EnG/ZJSD9Ss9c3n4oBc0GlvJETttjWU3atioxejUuF0mEqve2muj3HghSgDzvpxMC4QH6cQDU4HtaTy6kdVtzvedO3tc0EUrLGTBHup398+3KaA192wx67nQ2xcu/J3y4JtiWvQsSNhMvblHXJmGc53cJN64QeOiB3KARyiSrgLGHKB3YXTfm5IJWn7690qu9ZtbU/gLfzo3zyjADJuPbZFo1pYoE2I6NQlkkaOV000DjpSWcyXSGud2hOkmx/Sed9vpRkiVsmmWwsY+zqjp/xemt/PCOxSNflcUYXocYnEqo03xFMJXhqTmraY8FAhKEdC8vFEKOZV1DY0z5d4YiaACYGFdZzXHhWvbox6VdI+77bAv7yLJThWBTaU7pB94Tr2LF/fdnDu63zv++zCvudDBKvv+23BDxwRe1Phbh1GRtTfI3OM9ba6LuwqrSZE4Ut6AikSvOi51SVSPk03yE4qlanEFhVVYdt178QxUI9B4thJ10eUh8veUedIkPqfvro8GxLpR0rwFdRETilPuETj4zGqyF2HuIwJ8xCJHInk5g+UN84jSjVNaA4A9DQ76a4+td92Vxy+dobKHQO71upYCSymHeV4QcS3owrslDFUdnzeX1/i1TpSkkuf76rztriOeyKWQD8v++ph7ES+ezygVkEN6MdrRxBuQxlG4Nz9NhrVgS7e4EybmNV3W0GjbgxSW0PY4uaqY/FEQue2VBwpYWmkBLel2OqgnKhifB6p/+1tYqw05eZj6pGMgQzOjT45M61DIdGBIkhZcfRUjTk1IfcHxf3TeDog3gZtgnimtb+SpRKNCWlt6HxR4n1kBEQHVaJY0D4eIloHaU7V+HkpK1Ulc8BGeL1Z+IqXWsBhrDqxLYmNKWOnJiVN20PMx0hpY+u8DbgnYgm8BvO2hl0qw7uQesbBsDoxVSX0y23XAEk30fCI7pYkzfNWeumkiPj7z+ZUkSSbtH+eMKFhBfsHLikjqjZVepK3LrKv7ar3595xHLubHjgfoqdgUCbWat4oLMU3Edkm6HH0VvOykpfWBB3sU0pTO4F4/aL4vzrol/NptMI5T/iUNoj2TIq/q8zfNJ2CC4e1VaizxSDU3OfrtIJfHkRhfh+R2Pd8SAJUybMu7GOuD3EAuS58rojY7g692aZ6W4Sj4eGb3zCMXZ1eJcbvnvdtSDbwnoJbeVrvpf1oK3NH6aS2k6hQ+E6+sc6nWpulaiGWOEK0P+oKVKvyDjELUljc5ILskKRqHFBSqa5NgxoC1uiXYuOiSqyPWNJssiGfiPSfae7pxOZnOlPS98k8r/s6XGCZEnIl9T1iLpGQdZBIVZRyaFSfSS8Ok4TYceGHJ1ECaFTixajwFTWRQhoXHCFIbsGe5uPYB5cOLaTmw6440FpDiTSYIrwdoWQbVCt93bCdsG8fGOudNxbGaGHS+TK0JruCa5zOfQJtQxTjPGkexr2onnit5zRdmJZdYzdc503gjSdiccPaCYdqFO6SoVON4TytpltlSwxPVFNb6Xqe9UOHAG096SZtKEcjr/hvUXXRqCHixpo2JlktrVqTXypKQOE7iQwXA8vWm6RX40W1VOxDDa0IE91m1ASNhohJE2O9p1cM/SDJuDXSgArp4+bfsqepIO2Id/f3HnfdchNnEQktCvg2NqYk7dZcT7d0xcRaBEelHZXCX5/iFFUGlRZQwrwUtGT1nTRS4+ovxoxjpp3Ut0NXOhCglICJIsqnglfTxg1OKVcnEe1DWTkIrv3+u1X++haHJ75aPEom4KTDxZtaBeVvlPYCcYx4x/q7TN5uEtZ+k8aWHOPEdShhulvNSe/Mbz3ZVjdK53Poe8LQdDaNps9pdXZN+GKqXk59B5N0ILzRROy6TgXjN/42jKlnX9lj663HPSVm/sF2mr0YDdex9VbadbSL6OP0pPW8jxPcrlW1bBwNHg373UTN0Ijy543iPWKIC1t/vCokEA5p935sSuuQ816OJo3K4VopUxVprWVMRLe6jrjBal2fQ7OEyBZRgkta3nJxV6qWTsTZFq7O+TlojEHqtqpI96icYEqL0xaUw6HQGDQapxSV8fVp8dTCS2mqlqRscH33TIIn557uCSi73XOKQKX8uInvMt8XyqFViJLiFKLCDVahEOf8gWenYkR8X584wYi/syyTGGjYR/vQKrIfCcGhcTxI5L96AvhNto/wd6FZTWPW+atT6e+DdD0O4dclYF1y3yZgKfTImfXnFtOQCGz+59301xtNxIZAdbgzabMGuwlJ3Fg7su5Y19CGCVeNBqpTzhh98L5l12F+kvS7yWiXyKQp96keU0KVqiXSsutPGcKvr+R+EPqWURfhxMm9ThydwJs69i3niFJTYtqP0ppTdeK0wbXRTpKyktRRgoxIJrrFdAxqcqZUE6+wVikNYe+JuNMKFwiHj1SiQWlibAwvvahW3Z6wSKBF4oWzpAecash633aWEowWXiK1fU3TtCXmTD1DxSXR861DtKrVzUap4P0Y2Y8ogbXkqHro+2f+0HroPq93jF4iNdbdfgwM7S/d92MdIXYTrSaNL7O9llP1Xlu7Ep63Ctkuo/OqLY11KojzuLMl3wjeaCI2jqAcONlaO+L1urnmkW9rlF4D2E9yQrq+BacCxz9QwNZjiYspbvhRoupLH8M6tYlerayoET9kMDqehIlzhxc+uipAWos12oREXCMpiCctzbUniTSWhLpSaFS4wsR77PnnWut6Y3cuqOqiBCgapzTOaApjcApKoxCTIaIRp1Hib2IWUeBUTaAiTXMqSGI1IddUOqgjRXq7sLb3dfouDoYNUp+o4D0XpW8dbgNH+YPQOLQSjys+nJgLqlinFJnoxr4l4aB03WfB6UQpUgWVilLiQBT8vr2jtvUwzovuEGlsbFlDe9oh0uF1z5t16xnjXLbrbNkQ47/tCHYzeKOJGOwf/PHbb1++a+J07Zw9Zb0MtcVoer3tytt3PsS7XvuNLEqk/l2/tAdh31PRGaN55mlYI+XUAg/NQebGicO/iXaw+vqVgSZvP0lVfU2bJSIPIcp9c1lJ7VwiMb/zAW6V8kQsSGBSq0DT+oJsEQ2CqEDsmo1UXPACdG11jdK6lpAqW+G0RkxGqX0Q3kIUVKCsQotCO0UmhnjTpzOCKIcoh1MOpyT8Nb1QauPPfwloSWWpiMjQ3IybX00SQBrblhAJvb9UU5R4O1iIIaYDYRVRQcWpETKvegx2MqM8MxFvLIvj5FC1VNdMzeH5mjQlwb2dvmnj9Rnb7bIOzzPG63DoPFdf+kO9GPfh2CWG3XL60twGvPFEDMZxOX3wKnTa18HlzgnZyLlU86kJF9WLl6IOGZSqDxoiOFBBj0gm8bnIFgmoXxGJWbfshrPeRjE9zRY/YmndLAnX306VKN4Ccakpr/iYS+KjFCvx7uZ1e1JJLMpmSkfB00sVWrUap+u5E8pLsNMiYBspUKsguQUCqmPUDAm2qOAqI3i8osN99FyMeICXzlJs6zHodq2kvZ3oQYLuSCScsROpz5aJgNJNaidRFGx62CJo63yED2mihIBgtU+nY50xu0rHZUjq6kJq2x1yotldzhhpqQ+GzmwNPd+Xd2z6fXUegm+fJLYPl9uAN5qIpX0yRhzvwhjCcBfEYycBOCDNbcLOelT9T69Qu73gw27ZeqR684bKt+qoy5MgiSR1NwePg+diSuDiQehGz5dmDLip/vdbDdyWnUQU9T7bbkTATMA5xFnEVt45QwLBSLn9mpB5fDxj4AmPc4ITB9mkLlmpJsagc87TRqLk4pkDJRWaHFEag49v6C/6ClehqHDLMiA4LBaNJ3IoMNKo6ZxEu1raJdL6qMeuA6JUHXKqxp/mTjIXot5r8WRUh/ah/BUwXiIPa9nFs2jWq0NVc0RATEgTHEpNLUUm3H7KZPRoDdrj59OOUcsdQrx2u8cPE4F9ZfTl3aUlGZLo9qkwDyFkXUK4K8+9JBbg9fUSuh24rp7bw233S786cWsyJzWPwbsWNnrUid2c2zU0zxuHBpqoGR38oyddt8T273QDlgZHCNJUlJ78GSjlApEShxKLKwtsWSC29MTMWU9SVOJ+L40E5g8HK7Q2PgJ/ZSnKio8+e47SBpNlHB8fM5tNUUqxWFyx2WxwwXtxMsmZGM0sN1STEzBTnJlgXVkfAMg1GAxaGRQa7UosFqudDygvwRPR6qAUFQolWBVtTbZX0TosqzRSY5060SuLi04jChvGWeMJeLyqRUkj+eK8m36FP66QiyITECy5GMR46XNbZjx0DWzPrVcJ11Xt3STtbdQ5xITfNgGDN5yIDRkRb2MQr4tHF5/bhCEDaetZO8fWk2vVS0pY+rna1FhbR1EIz0d3RUgrQrCPbCUA0ph8qi7fSzAuhKQKZ9gkkZ6Cjsxn1bX0oZT2bvsqtMnFegKRQgX7XiDUgPbyiyeZzmKtJ1QiFdo5xFYgFVr8MxEHYlE6EoS4ZTdSllLan5gSobQF5WbN8vIC68Tbv5wl12dM8pxcKyocZbFhsbhEi5AhzBDWakI2P2NyfMZ6veB4ojmZGh7OphSlxVnB6RyTeQmmUg6VGYzWZEqTOwMYnDaApVSKSnk7Uxxy15p3NZmpx1mFPq4Fa2mvh6haJkhitudWUAFU8FrUgXGK37XzZ+hQgnaC1oJyCqt8NJAofynVnG4cD/2bscd7/0Q+NH0378tiyHfh2TgMHUbI9r0bInQ3hTeaiA3BIaq4axOszuq46YDsUk8MTbhWnjjxRtW1lW0AF9/IqO3r8t19+m6VqA1rxwb/ZgRmvkpPjKAd4qLZKLvSmPdyczXx8pdlJuGkROpI6jGrx0uF8EbOExKtcE5igqjpq9tC9BpU3ssQZxFX4qoKZyvEVUEac+gglflYgxbnKm/zUop0pATQyvgyAXC4asNmtWC9uKIoSkRgajRH05yp0cwyTaWFjStYXDynWC3RZcmkKHheGWZnjzh+9A7Ly884P8lxp1POH5ywvlpRFBWVmXA0P0Jnhg0V2SRHZRna5EyYoJQBk1GKw2nv9aiNadR04lBK11K5BJUvEhWwuunoOFJb6mZqJsNJcwmMUircAyf1LdLxjsx4JM1LaYATKucJmZeIBWUBrdEa6hN4PVNvyCbWfT/kcTcGdkkoQ2UdamMbquvQPbBLuMaoG4fgZWvGPjdE7K6MhsMVDjzfwfodzhW+atjNXfVxcFHiURy2kPqgP1eq3vNSnxMJ0laXKCcEtOY9VC1VeSIliFjE+cO0LkoJhGPAgYB7wlRTZ8qyoKoKyvWSTHkvOaMIxCvEF5FA2GrpLKGKAS9FQzi9SjFjffGCTz74gMtPLz0tVfDxZompCuz5GbP5BDZrMltwZIRPPvqAarlmUjmWkxMuN45PLzeo9SXyICMrcparGavnl2zWBdX8mOzh26gs57PlJUW5JteGB9Mj3j06w5gJ6Iw1FXI0xxwfofIJKsQ1NIDGey5aZ1uSt/et1IgYVNaNZtIZVJXmAYNXM/pDzX6cXCBaaIXGO7B4PimOlWuIpPEETwFOm+Z82y3aYfqIxZA96vpmgOE6hxw+dqXfperb5ZBxG/j2Pb9tifONJ2Iv2wFiL+wY+zeLgPXBcLTs1gKuVXDNk+tBUAkmf523NMeH06gcUY2Y5tPJmwYfa229KVprkTTslDQHjI0CcSUiDmsrbFUgtiJTFZnSfvMUTxCDPhTnooTmiZirVZV10zwukkYJ0VSbFbbYUK6W9ZmwQiueuoLL53MePDjHZArnLLl2nJ3MWYmwvlgjp+dIdgR6itErFKBthb38DHO1ZLKpPNGfH6EmUzKpKKo1ZVnx/LNnGDNjkk0xkylXE4U5P8NwBvkUrTUqRJvPjPFSU/DSUIEIozRKZSijwVU00e+TtZpIunWPSHDqoHHWMcp7S6LxdjPxh7KN1ySCA6t9hHzlHBofykoB2mmcDqG7uPnGDPvtOfscJO6qzn2mlEMI7U3UoYfWeVvwxhOxCNfplDFeQ73veFMI0i0R9qiTCcUNcXeN4R4fcy8QvG2Lx3hI5a4thWZC2ITtOlKymuqvamcNEaxzQaUYpciM1ujWi9vibIlzFbYscLb00pm2ZNoFZ0xBXFnnExuImLXBCcN17IWxjuZaGOeEqlyDLXHlhqqy3hsRR7m+YjHJcOWak5M5WW7INZyeHIGF5aLCPHgEeoaUGlUtyTNhYgS1eEG2XqI3lspkUKwRDUZZtFTYYsX6xRUvSsUky5nM5qyPJ2SmIssdLpujtfaETGlsZsKYg4pXqigNyqDMBIVBaUWMFqLCgNQ2U6AOVxUWVDOW/iRefSGma6YgBPVjSGtd8ObEH6621s87I454y7Rmv4fdEHSZ5L1zf+D5oYRvqM5dhKdPsurLdx3p7BDoqzN9Pqbth8DngohdV4987frutPTbhJuQj57Sko2mbwL6qBId0hE3rWhrOgSCOJU6b1Cr+3yCRp0YbTNtZw+vZgwENeRyzuGcw1pLaS35JPOETGu0NkEyEH8oWBy4irJYeenLVYhUmMDlG6qg+nKIdbiqJG7aVVVhywpnLU4cJvo6OOdxDhtwWZY45/GvKkexWmJwzIxiuS4o1hsES4Wj0FCtLuHJ25ycHnN8csT00TlmMud5NeXh//un2BSKxSeXTKh4/PaULz/OOP32gk1xQbFYk82OseUGawQymE0UzmlYKezzz1g7KLKMjT1GZxu0WmP1UbCDeZWoMZ6Y6RgiSsJYkGHyI/Kjcx48eECWT9CZoayaOJTRLSa6XfjsnlpFuiWAqMSxgxBDUYFNzosp5zAuxv+AigowGK0wSieHqw8nIt10+5yahtRyN5XCunXuU8sNSWdDZeyre18dh9R/21IYvOFE7DY6o6+M10Y1+ZpAQwr3R+zQOnj7JRJHAwcQMumXrmp8JD0bJs2bmshF9WLyjkgXHZvVkrIqKaqS4rMNJsuYTKecnAapyAnOliDWE65qA1KhxKLFBpWWA6oaUQ0YrRHnvHRgK696tBZxjspVnoBZ79HoRHDWUVUxsgdYJywXCxZXV0zyDH18xCTPubx6EbhooSo3fPbZpxTFEqPeYnJ8jJpMMI8f8c5XvszFsyWrz5aYzDA/nnNyOqHYrJkbw/F0xvOqxCrBZhoz1xTWgYFMKeyqoFqtKYsCo+YIFU5KlFTUtzGLw1oT7Htt6daJoSwrNoVFbMFsdsR0PiebzvBWLUU6B1JJuvnmGZN46aaP7RjOrxECHYd3SvyBZ40/vuBDVvl+dTqGu7pddeLQ80PLP1QKG6pzbNoxz/ukpqE9ctfeeRPp9FB4o4kYIq0tUep/Diujm20XBzJczMEVdz7bEMe3W+xozi5OlMEaxuBW15qQheZ7lMxUK2XzOzDtLXq2de6KJEPYIBsMkh2uhVIjicW4g43kFf46hCziofD2qWKzoig2lFXJ1eKKfDIBOcbOjoOzhfM2MGdBLLgSFaw2WkmIgRgPN4cdFa9WswLOOsqq8tJYIGL+7FiFsw4bHD6cE6yNOzKIU5RFwXq9xqgJxhhmU8Vmk+NchYhXTa5XS5Q4lvMZ2WyGySfMz+bMpxlrZTHlgrlxTDJBZwqnBZMp8gxyKcGWaKbMplOwgmSKPDNwecxGBFuUZFphtcIqQWPrA8zihBhyo3HmiSMSvEStsNa+35DKzwWToZRB6awexzRuiiSSPlDfhaZCnU6BaIVygA7OIBLUiSpI3RDUxIJzElSdsa5mNrfqqSfwbWsurieFHZpnl7Szj6jcNqiwKUR2tSUFd57fFrzhRIze3qg30ejiO8b21VqIdznYQ/JFP6jOwvbPhidkX8TxodZHoUUkXcjb9bVx9putkuZ56lIRb99FCdr6HE6BUlJH1micMcLeTxNuybmgeZSwKTlpntVeg4E6SrQxaf89VTsGXG1wc8/QGO2lK7u5YH35CcVmTWUr1ldX6JNj8iODXT7z6kE8wYuYKnG+j1QjKWilyHWOrSpqdZrgVYJFyeXVAmsDoaoqbFHgbBUC6sZLWgh2I98Z2hgqB8tVQbVZcHR0zHw24/HjR1xcPGe9Xvq+cY7NZs3TDz9kfnrK/OyELz46x37vbyLf+T6z7/4u7z8+JnOWy2LC5J0TivUVdnXJjIxqkZHline/+DYfyJqVWErneGAm5B9+BkuLm56yms0pZznZxtXrSevYD/izb/US8oektaow2kFZUlYLysUzNotTZifnTOen5LNjRKlaEtUmHD1Q8b44FWI2Ki/xKvEBsgKlc0qTozFKUYrzke+BzHj1oXUKKsEoh8o0og2EaCgi1DbQ9tqot9zO6mnDdYjBTQnIbRGgMU4bYxn4XTJUi4C1EWg9vy2l4ptNxDqgut+SXtqnNrx7TmVrSNlBWzuc4v7J16TpP1y8qwwVOdVDJm6Xa24ZhmnN1IFA4p2SW9Qn2Ua67Qqnf4L6rbbHSJqz4bpNHf3d28HKYsPVxXNssaYqVizWS06Ojzk6mjPNczJckNga2dFH6ZAmLiKxTkflVB1PyYmwKUrW6w2r1YrVch3sdRFP/GbaXLLSqIRimfjN3Vrv0LFcLCiKDY8ePeBoPscYxeXli+Dp6CXDstiQVxuOWJOtnpFnBQ/fOeK9h8cIlvLygrP5Eer4BNlUbBYLqK6QwnFhNJP3H8DRhFWWkTNFVwLriuLkiCrPKZUm00k4pzBfUE2orCgNG7yXoFE2xBoOZ/fKNatLYbNaMT95QDaZYrKcXGc4iZEcVbi+RQXVo+9aJd5po1ZFisYGZw8XpFenwFqF0f7Asw6qSyeEA+PBqWFoBnYndxz9A9Vwu/LdBMaq/vry3RSvvj5rSVgD5e/bU+/VibcEL0vMHuI79td96EDftrA+osZevbwK6rZG4huDVksKFn/+qzedpMrC8CkNoYsxFP1eq3wMPlthy5LNaoWzFc5ZbFUynUyY5HntJg/NJ/Gm49rOF/FLrkNxXjKz4iWwoigoioKqqprWSIy1TmAAfIfUKleCVjKo58R56cJar0IsNhtMpplOpyyXBn+2zUdArMoCV64x1YqpdcxzhzmdcTTRrMsVxXrNZD6H2Rw7L5DFmryyqNWa8tNn8GCGzhQqm+Byg5pPmZyfoI5mVFODyzSZayhVI3dTR5z3faGI5EMjdYQv/97byKwTNstLnKvI8gl5PgPjD3iJ0hCIlyhFPP6tQm/HvtRhXkTJ3hEkeOewKkRZic9F6r86RuNLgH3OF3dRH7C3zi5eY9zur4PLLvXmbffJG03EorvoTfL3eRa9nGm+De2BTeTKl4zQNve2O+0Wh0g4JxZ+BU+M1JKVFO7/idw8YSOP6sVaAosvgz1DaqLVVSHG7x11kQhVVVIUa5bLJUY1tpzZfEaWZ1jrMCoqEyUprDlrFImlN8x4Mm2tpbKWsipZrdY1AYtnvCAE6CWeO2sU3uBVcvFeGRe8HEUcWhFuPrY8e/YJb739mNl8xnwzZ7VaYK0FUWzWKyarjPlScTx9xHSmmUyOYLlCLhfIcsHxF8+QowdULmN9ueFoVcGm4urjT+FshthTVHZKoSCbG/LHp0zmM7LcMDOKShc4Z70jihWsC7piCVFPVFTz+iswvd3KX8qJ0khQ4TkpWV58SraZkuVTjuanmPkc8tzbyrRGnMI6f+bLBUrogv1M4W/IdiKoEH/RaX/rd2m9ilcrQQyBsQCcQ1kNJsztPh39AFxnfxnrjXcdteRt1Dm07/W9h8P3wz6Hk7QN8f29JHZL0Ovlw8uWZfogIQKvGMas+ZZqQ1GfE1NKgoFehYjo2wVFYtVVJzaSVSRaXeIVCZjUzwM2jTLQNYqq9WrFarmgqkpKW4ISZrNZfeFkJZaMrsrJhRLBiXeVF+ftY94tP2O9KSjKgqIoKcvSS2Ai9ZEDCVRWEUIoeV0M9Zkx8fYmoxRZlnN6doq1jk8+fBrsiyDiuLy4oCimPHz4EBDW6xVVVfhDyqri7bMcs3wOxlBpTe4q8uUK/WyBzBbkR1Py0wcUZytm609QVUmGcPn0GWIrjo4mlHOojIbjzMtEYsmcIp9kiBivGgznsqJNqz6ILIILh71FvMegPyANElSfKIXJQaSAsmRTrlGbGWo6RR8dI9NjhAxURiUqWkAJJLMOEqxEQAtGK68uxAcrts7PO+0UxvmD60ocVrlAUP0BanXDVT7Wxfy6ZdwmPn3pbipxHSLtxWdwL4ndOaSqsJdNxl6OSvNuYFt9AFtEuHs1ywA0G3uboMXfMRZiFN2idNS8DznqMFQuEAkoNms267V3d69KtNFMp7M6nQv2KH88V5Lag4u3dV6NJxIi7iucg6KsKMqKMkhfcUNXyWdUa6raSBjakTAISnnvxul0wunpCcuLCzabNZUtUUpRViVsAE7JMkOWGcpSKIqC9WrFZrVAz6aYTKGMwm5WmE1Bvi5xF5eo3KCmWXBQcWgcU2C1WiMXBvfiCp1plMlxmUEqf/eJdgqVhaMHSmFCIGMnnnB4yShcESM+uLJznsBo7QUyF5gJUBhjGiWws0gliLK4PDhh6IlXVdZ6StVI7EgYK/Hn+BT17Qde8lJo8XYwK4ISby9zYRyUAzG+rJuyhzdR290m3LSuIfWfyOF9NKSe7Et3W/C5IGL7OmSvw8INDLXXMVyOKetl6e7vAho7SPNA1ZHKh21c/gttu1j9LP2ZngFLVJH1vwkTEiLIo2C9XrFerXzg2KoiUxlZlgXpwt9sJeJaRDN6IyqlwrUq3kFEBQ2gFcumKGtX+qh2tNZ6j8a4OUii/pagGqvnXdxAfPdMpxMyk7FZnvP8uaNalBhjqKoCEeftY8aQZTkiQlmUrFYrXrx4zpfOH5Ibjco1V8sr5qs1801J9ekz3PEEk81xtsCqCmUcU9FMVxtECZunhux4iswULtdYsWjRPnah+IH0msMYyDg4VBAFSi95WmepKiEzCm1Aa6EK3qNKFFnmGyoITjkqsThbUW0EpxRkNkhvoJSPqt+okyWMUQxP5Z03XFA5OvEhqnT4jF6OPjSVoJRrNmcVZ8s4prXPOeoQieyunT/SOnc5fewjdmPUiUMqy75+6VMndp/fBD4XRGwf7ONM4rta9RMHr4dDuW24S+5sPBLcitayXjjIljqxXX4ipaX0JiwMb1UR0tDzMZnnxFVzoNhJkLbo3YdU0IXaomCzXrFZr3C2RKxF5Rl5HlzktUFpH8ZIwHPtKtSq/PeyLGuvQZSXLjaVo6qslxx05u1BStV2TC99CToEpFV4G1h6qaVvn7ctVWWJ0YY8Mzx58hZ5rslyzWfPnmGMwRjN5eUFxyfHTPIcsRYmGaui4ntPP+P98yecCOTzjNXFC443G45sRXWxpPpUURVT7PoFV7pATywnlTBDk1UO/dmC1dNn8PCU7NEDKiNo59BO+Yj9cRCNRmzT5ZkJobo0WOslWZ1p8jyEqUKhrKM+r+ds8D/0kT8cCpdZqim8qJYoJUwmE9xmjdI5kyynEut7KVJ6PJ9hXZScFVZD5UUycGDE30mmBU/lwtyrtA2XhAaVsJJeMnboJnsdG1d3X7kNqW0XARv77DbgZRBt+AEhYmPgpvrt26wzqf1O6r37atItQRE1aI1tbU+FkU2W7sNGJIvSUmo3qyH5HcMOFes1rip9FI3Kq+f8Buv3PBVUmM7f4xJQUNSB+0SoKhu8BZtwVzbYh1TtvBGJd9oNwU4T/OYk2LkUkcgFrzyB5eKKLJswm87QRjObzzipjllcXWGdxTrrrxsBtNGYzC9ha4WVCC+ulpg8I5sYZvmEXBdoqcix2OUF1mUYW1LNDKiMjCnqsgArTApLuSlR1gWVIWRak4nCZSR97TyxiIQ+OWIQD/lpA0q5esxEynpcggAUiKIPKoyDsljzpa/+PvTkmMpmfPidj1DOIVqa+IfiI+TXjkOhnGijs+GMmZLomeilNU3isejEX9US7JJq66LUlwt3aS9KoVvum2zCSOFzScQO5QDGqBNfFQyhsauNfWqP8IvDVqtPP2au9y6+IMk0qptoD6JFaFoYpZLZwPOwK7ZViC2VY3DNl0YS26yXuKpCglu9CRdBNh70Ejj7Rt2kwm4reOJWxRBSEu0yIE5FvVdsbgvdWiIL3xX+AHckkkopjM583Va4vLxkMvE3OM9nOdPpBJETXsxfsFwuqMoQdV8EpTSTyYSiLLFOqCy8uFwxm804Oz3idH7EJF+hlCUzQrG8otgI2WSKPp6hZ1Mm+Qm2fI6sSvLKMrV+U9fG4JQlV4aJMj5avLO1zc9hw+WYPsxW04c+SobSGoX1disEcVXTJ0GE8+pAH/XeOSiKDT/yoz9CPjvh2YsV3/+971FWJbkS8kyD04iWcBKtmSMS5qhXH3rbl64JGAHfLnFTKBFMg9XWfD4ErmNW6Oa/iTfj0H4wRBR3qRF35RsDu9SMNy27Dz6XRGwsDHJArwf9auCW1H2HF3JY+q4OParkotTkpQ7qiO8RIjFqPPlqka0XaoIljXdixDfNFkgwzlVcXjynKjeIqyiKNQ9OHjKZ5FTWorW3i4mtUDaGlIrleoJVViXO+egftRceGtGThEIpRFxw0NDeMBOcSrSKZQnOWYzxl3AqRX04V2vF5cULQHF1dcUX3n9CnmccHx/x+PFDnKtYBtf29XpNnuc8fPQWH3/8MbayoBWLdUlVVEys4snDB1CU2GLD8tknKK2YisK6DdN3H5E/fMD05JwXy4KKJW4lPDw7Q05PqGY5tnRMlWKmNS7XOGeIjk9VZbHind6Loggei95pw4qjchZbucghQDj3plBUzgWvUbDGYLIJZnrMo7fe5os/8qPMTx/y6Krgr/+13+Hq2We8ePGMB6dH5JMpRk28230gX1ECU0pRuWSOOalVjZXX/fr+FhVw9bYwpwLRRRKO8fDFdhsqwH2S2G3V0fd9KM3QOtxnTxtT/23BG0/Ebltiqjfd1wleN6I6FhLRJBrPvbotHkhN1IPSrBdpkbg+kFSzGJ+EAlLvSBUONFe1V2LQDJJlGcaYulIJqkGC+7YKKsMYzspafx1KJLR13Yn9NM4dhfcyFOUjWsQ4i9HLTisdri6h3nRFQtBaa6kqF6SyC46Pj5lOJ5ycHLNYXFFVpbfFbXx7jo6OyLK8juQ/neZo56gur1gry9QoskenlFfPmYjCoLBWkEJwlVBlhup4xrosKYoNJ0dTZGKw+CtqlDiUqzAqryPWK2VQCkzwALRRxCHcuyZSXwaaSs+x32LEfu/ynkE2Jz9+wMP3voSanaDnpxxPFO9+6Yf40Cmeff97LBZLZk7IZwpnJl4WC+pAl0weJz66h5LGwUPXkpm3j0U1o47ZWnPpcNXiGGeKQ2GorEPqGHJ13ydttRn63QzlWNjldn9TeKOJWN+ADnXM2OfXMc4OwedF57wFHcmwOw4KQoTxIKCE9CpsOqCC3Ul1yNWY/pLkM54N8wSiIWQQXfE9USgoiw0xuLBSYLTx57hCO6KEFG1jSmLUDC+JWXE1Bk6klr5qu1bdB02fKK19pHvlpdL40t/JJTWxA3yA4Mp7PnpPR8fV1SVZpslzw9HRnNlsymYzYb1eU2yKWl2a5xnifOSO2TTHOEd5cclSVeh5zvR0jsynqI2PZ6msQzYWu64ogHI+oSgmLK7ATjMk15RYUN6jD+fQkvkeV95lXkSBFlwV7V6eQVA4lFgIEfvDwNfj5eNgSvNc58jkCH18zulb72GzOTabkU0nPPnCl1ldLfns409Yby7BGMRkKG09cxDmjwvjHx2CVIjh6KQ58Gyc4FRyrrBWNfo/dSDx6qrsb7o5d9WJfWWNMxls4zlU5lgCN6QevM7zu7D7vdFE7KYwSNjutNbPAWHrIWDpdyFVGYbNoSZw8TBxok6MhIhmg9nVTY06Mf0dpbNkcQOb9Yr11RVlUQTCAVn0FAySkpfeHDa6JorflJ0LW6REz7pI0Cwm3Gwc1YitvogSWCTgEu7J0vEGZCirAq0VeT5FRCjLgsViSVmWiHivuWfPPsVJhRPL22+/zcnpiY+nuFz6yzOrihcvXnA8nzPVimW55HiiUZsVl89fYKVg/eQBx4/POPniF3Dfe071fIXRE9bP1rhKox6eU57NqTLYVBsucodQsrEVuRUmTqHE+PvHJHiDKh/k2DmHdY4yXNzpRKjKEA7KX5bm+1Ypb2sM2kWHRhuNNhlmeoQ+fUx+/oTs/AkLJmwKwbmSL/34T2J0Dlb4zt/8P9mUJYW9Inc5s+mEPMtqQUGQWgvt5V6NJRxsduC0NI4ezp8J1AgSD6RDPTNfBXQ3+F0M+jgpbFuA2iV59aW5TXVi9/m9OjGAqkOGpsoAvdXxbUtN9/m2yanm6FVUgcUNeWBAe2LHt1JKKzFREtkuJ3hLpRinu3ULZPBxLyTP1UCy1vN0wtHu4frbnomoAv1SUN/3BDGCB8QwQsPoRjlN1d0QlEZtlR6h72piqTxPbi1VsabYrFBU9UabTSaI8hH+tMn991CeTXDqusB7rl0RYwSCbhMshbeJEQhWLX01Eip41eRysfKHrSdzTySd7ykf5cMf0BZgtVyjuOD05IRJnnN0dIRzFm18jMHVYsnJ/AgzncA0Z4oit4IpHaLharVhfXnF8YO34aSAUmBjySvBrkrK55fw6JhsOuHorYeUWbgRwGqqoqJShkppf5A7MhgoKmt9dH6RduuCwBqjtMSzWy65FFUQL6VmGeQ5jgydz3nr3S8gWU6lDGqao03O2bvv8MX1j3L52cdcXTxns15TrhfkODKZYDLTrKlwfq2eQE6Fu8jEE1AV/6I3Y/TGD30vqpauh2ZkZ4b7f1WyXRwA0v0SF1rK9CVlRjV52sTmSw9+obxaA9Jsab6aFmGJmpH0uQQe9HYkMTp13qsTCVubtDdChetN2StfBbVQtH/EtQDNJnoTwamXWCQUU7G9hautb2MQ2F3KIU3w6+f6jRZJiYAXRYLmrXZMVGEhpg4efXawWigiEoMmpaR5lB9fpRRYWxOPqlhTFWtstUFrqEqLiCKfTBFlQBkfnULCZodGsB5/FWU61cwLgRiRgrDhSVCLefUh9Xw0qp5eQHOxdaRri8UKrTUnx+dkWoNoxEGW5eDKQDAURVEBK9abDbPZjOl0gvb6PJwTisKnzbXmaD5jIpA5H3ZJVHDAKCpcnqGOpuhNRVUuySpBFRXriwX6ZIqZ5UxPj3DBtR4LzgqVhlJD6RJboHjiFQPrSpC2vLrW461FE+JqEGMHK4kdCcoYdJah8xynM7J8yunZAxYm83EWjcEpmJ6d8ui9d3nw9js+RmVRYcsNTgfVoZqCidH0Q0VCHYsyTqTY7xLmpUggaHimRMJYNuzjmPU3gjPcCzVHlzB2A0X1Rr2RHXV3GNE6f5dB3f597ea8AnijiZjXw9v655DENUjEIGw6JCoFiBepp3t57bHWU3JS1BYu3UnSzKE98mGdxfW9Teocwijumv1zfB8PdOgErj0Lk/JDXFi/nyioz0gFaac+CE0SdaNmMxs5KO5Jjia8kHezAKcUojVKaYzW4ZyXw9mS5x8/RapLxK6ZTjTLdQUq48H5Ix/eKJuSz06wmwJshVaKipWfLULtzRZVj/6Qc1Qr+kgSyoekQGtFZhQbHEZBbjS2aKSwpo0KEc3HHz3DOSHPjnny9jsYwJXC2fEpS7VguVwiGKrS4VzJ1eWS6WTKZJpzenbCxYsrXGURZbi4WHB+POXdt95iZhXGaiCncJaJmjDN5qzKguPzGWZqWC5fMLcKU1iuPviYbJ6jHxwzeXBMpTU4FaJb5FQoFokEhuDjR0qI2IFLCEQ42CygnCDaX6AiSlDaoFzsV02WTzCzOWY2J5sdczI75mQ6o8o0Gw0FBaUI06MZ5++/x5d//CfJdIZywuUnH1CtLmG9xByfMD06Qml/d5wVhQrxE6m8NIoGcYJoqfH2xFX59PVx6eS6mdaqkc73BJRqS1L9q6P366D0lNY3uHAbxi5FoV1tX/my9Vx13m0TsvES012ecxuCN5qI7SBN42EHM9UqO+qqb1jdTr17S3Vw2EQYIoZ962uojbue+745ZDL7jF7Fl3jiRfFkx8KPDEXqOt/gst0vXoXhn/ublX1sxNV6SSYlOB9lPjMZOpswmU6p8BvpZDJjtS5QSmGyDGcD1cWroOKaT7e2xkEFtAp2GXyoqcxkGCX+As6IsbggpQHOebuXc2zWG773ve/7iBRVxYsXF6Agn+TMZMZitfF94YTlcsn5+SmzfMb5+QPWqwJb+U15s9lQGKDIKSsfS7GyG8jheDLldHLE5Xc+5Pzddzk5PeXi7AiREltaKmWxZUFmZ8wy0zAjUQIOG6QxWc2BRaIVPSIjUahHJojenshJOP8sgaEyzGbH6HzqnTp0xsMnT3jwzju4EGtKBUlOnI+Egsl4570vUC1XSFkiy0vK9QZbVTx//oJTFJP5FDXN/N1iOhxC1waNJ1SGRnJ0cT5GRghCeKq++dhZCaq7SxBUbrug//iO6nmeaBJ70ieYSJtgdDVz/fUFXNKV3EW8a5sbaNmus2z7zqzdNqHT+5O8YRAIzdi/1x9ePZaHYtCe+J0VrtTAwkiksfA7edPo6JsnLc1I7V2o4y3JEjz/wtks69DGkOUTdJZhsgyT5ZgsI84YrXWQJWjrn0g2lqC69Lugv2ZEKQ2ifB1aY3SzSUabWCR+AJvNBpD60suLFxdcXlywXC6pqgqtDfP5vPZc9GpDf70LwHw+ZzqdkuW5lxCtRZz1Z6KqispVlEqwRqGMJkNhr9bIpkCJMD07Rk0znFHYKDLrlCglfd+RHHy3NGlqs18XFHXcXgn5tDa+302O0jlKG5zSHJ2fMz8789emKI3Cj4OOkUyUYn56ytmjRzx8/DZHx2dMpnO0yalKx2azYbNeh8PsFYhFpCKe6fNSF7UdTJK5VuMH9b/NVO1QgJ0E7tXA6xKUYSzUZ0nvHTs8pK7NQ9DLXO0rt4e1GjJYNu8PrGQfDm0xcKDOwyod2xdbnFQrXyIV7ak/2r38+g92o/i8disTmosv20QjMvCtZ5I8q5MLNsRSnOb+PJPWcHp6wmZZUFQ+ZFQ+PSKfzkAZ8nxGNpmgTObtIVoH9Wfa0nh4NuprQvgobVDGoEwGOvOxEG2BrRxzozFICPxracLjKozxZ7SuLi7QSpEZQ1mWfPTRU5xzFMWGSZHx4MEDzs/PuLha4AqLtY71esNmUzCbW47mx5yeniGiubi4BOcwSjE1GVW58DclTwwy9YFv3aZktnasPn2BspYH7z/hxdJS2gqLZn56hJpOWBYblMnQStdrq9YiRumsNRaNCjkxP/lPJSFcYZDTFEwmEyb5DKcMSmc4nVOI5vjRWxw9fMSqdJh85i/IlOD8Yb0XZH58wsN33iXDsPz4U15kz9CXl2wKy3KxZFOsOVOOyfEcowWDt1s6MhTGR/NwPhixdaBMOOws8bC0C5h2WDCVzE3ChN4WX3aug0OdIPaVFfHav/4Or7PPQ7Kvfdc5ijR05u2m8EYTsTFwrW5SParFV6DrrZHp13hvwx4qdd0pE1WJh/SJf0fQx/nF79WJDSJpeQ2HHzfENoufelG1DhxL2CYl8tLhuhQcJvMVWeeonHB8dMxkfoLThpPTM7TJsVbI8inWViEwrcdMBWnLaINSujmgCyitPDE0OegJudG4UpByw2QyQcoVVVkgUhH0YyDe49yGizmtLRGxKCVsiqLus6qqMMZwenbG48ePeHFxwWq1xBjDYrFEKc1bbz3m/PwcpQxXlwuc8uVoA1VZohVMZzPyhzOcFRaLK85NzuKzCxbrFe+/9xbZ6TGZEuzqAjWboKY5YqRmMPxZtsaK6RIiFo9BtO2gqh5Mb6/0bh3eFurPzGWZJ2Ibq7FkYKacPnqb/PwBan5MKZCFoM62rHDW1QfPMZAdnXL2JOPJV38E+92cQhumtqJcXSFVwfLTZ1TP4eR4zvHjB4HRUUie18TKOXCaEHaqkelF2nNwa4O9wYZ76MHlXa70Q2e8DsFFeh1Ekvetsm9PYro/J9YDXUnsVolMx9V2mJu6vSqHURnZxhvOt0E9d6uKQ/tb0fKqitJZ9Emva2iz8rL9pmMP85JclMSiO3/0kFMqnAcSV7tSZ5Mp+XRGhSGfzlHaUK42mCwHkkO4SX8ordFKB4IptS1CZzk6m6CyObnxV7LYgIO/ndmC2IhpC89J3tjRvFrR1nNZaW+by/MJp6enFEVBWW7Isqy+cqWqLHnu4ypqExwxtPJeevizUQaY5N7TsbA+RFRVWWQDy6sFKjNkR3OMKpBMeweIiEOi8pVko48nw4fGPR0zF8XkSBTr83igshyHQemc4wePYDLFaoM2JkjZ/pB1WVQ+DqICcTBRmmw64+zJu7xYL1nZitV6gXYl4ixuvWRx9Ry5mnKC5ejROyiVJ2J9Is2HUWl7Km7PXVVzXVJPu23YL4nF+XST5+m7uuYBgrDTZjWgaeqWuUsS68NlDKRl30tiLwn6Bqr97O510odNltvFp8uN9TlWDGIS1n66FFStkknr6GcMo6SV7o5SlxTBq40iAXDOq++UgqoqsTYeWobJdMZ0doQtFbOjE5woFquSbDIDFfNGXJVXG4Y/jVdDoQBtMJMp2WTGZHpCrhwbV7FRChGLcxXWeoeSqJITfLipLNOcnZ7y/MUlalOQkAi08u7/We5tdQ8fPWS9WbNar8jzjCI4M2weFcxmMyaTCXmeU0mFzryKU6P89SmlZZrlVGVFIY6VrTyBsI5nH33Cg0ePyM6OmM287cw7ceiEiAUbmfPRSvylmNFLsa1ObOwc/rlTzfmxeLjbaH+EoKqE7HjGWjTaTHj45H1cNqEAZjF8VrhGpVhtvMONMaywzPKMWZZz/sUvclEVbBQsFhcoZ3HWUV284OPvfI+VgcnikpP5GdpMw+WY6VwKiEYClkyxVJux5SxB3+q6i/W2H64jzYyJ7HETnA7Nd1tCx+eAiI0ReYffdw2NtTFaDtqu6wm/m6MZhuEB3UdEm7oiLmmafi6v2XR2193g0GRrS2KDeTuEyasxAg1Ah0OowZlCCyp4BIbaPPGrxavYDs9Gx3vE6j+cjzvoHMbAZr1ktbyisgUOhzKGo+MTsnxKPjvi8aNzzh+/zXpT8OzFJcoYjOTgLIWKzgQQD0Nrk+OU4CqLU4p8NiObnTCdzzk+PuP8eMrieY7bXFIsPkHKAhUJYuB8vdOIvz7l4cMzNpuC5/kln3zyjODDDwpKa9kUBavNmtks5/T0BHBcXS0QFJui4oMPPuS9997H3xrjmM6m5LPcR6WoKrLKkWuNu1xRSUmphU/chtMsY6I1i6efcfroEfnJnCOVsYwOHkjt3GKkOfiq8McLoq3MO9G41hzzkU/itTZRHdsEQ55lMzIzResppZqgJjNm52/x3ld/lPLkFLIc0ZqJycAJVjTTfBJuFVBMZzMcwsJaVjiOv/AFvvjglHKzpKgs1WJJuS4531iq9YLnL57jioqzL/4Qj776I+TzGSbgIqVDKQNK1zEitSgq69BaAN9O50ClDFdn/t8U6mMb7FYhdvPssy29DLPHdepo7Ke3i9/ngIi11T9j0g1Bozjo7+TrGFP3Op7ckJu6jkjeUpOye2G0nu/hF1pG8J5mRUIU7U0kaisVbGb79LM9JD2o+cKfE4wxzOczXLXBlWvEVUzmc3SWgw6qxGyCqgRlcm9z0da7ZCuDVf7GR5NN0NkEbTJEHCrz8RbJp0yOTzg5PePxo8dou2aTG7RRWOeve0mPsUfpMR7RMEZzdnaKoLm6WrEpbR13prIVi3BL83TymDzPmM/nrFabIC0Ky+WKq6srPHPhmM+OmE5yHx0/M2jrkMpSLVYw1egsw80nWOclj6wKdivjbXuqKqltlnRUxqOm1/acN9r4KPJKkWlDZjKUMojSWBT50TGz03MmR2eUJgv3fIEYf3u0Noo8z1HWeqcM5c8AVmEOTrKM7OiI977wBRaXV6yuFjzbVBw7RWnBVSWLTz6B6QxzcsL0yTtk0xyjgsoyqGD9f03ose3VET53msh2q9h3qfb29myPKaG7Xg+Wyjqmkj5cmvU/vtguLi/Lj+BzQMRuBoP7cthQX51Dx+cIVGNEb/q1YWxVzeFKy/wQdT0tctAzFJ4QU9vBptMcM89BCsrNAnEZJ+cPkcyHmMonM1AZoiwmm3qDizi0rlA6A2URBdlkRpZPUdogtvA2G5OhJlOOzh5w/vgR7773Lp99+F1/DkyJd9bA1URM6gbGTdKhleL83DuWPH9+RXlxibOulnAWiytQjkcPzzDGeHf6LEMrg0jJZr3hxYsXKKWw1jKfz5jmGlcWzCY5urS49QZ3tcSYI/KTKcXZEbIqcRvLVGU+9iJCPpvByoK4cDwhMQ5F4XeHc5GXwpLNNkjNxoBzFUZpMmPIjMHhCZhVmvnxKUcPHmHmx+C0jz4frmtBqUDEMlDaX6NCOKQsikr5X9Ms5wtf+jKXz17w/NlzXmxKjtE+VJZTPHtxgcs/wk2nPDyZkatjtJ76c2HOoMTQHKqIYcV6W0lUUQf0Ou8OgM6GcxO7UJdgwLYmqPvsZcAuO929Y8eNIJ09iUptILXfV++m0z9P0CvFJc4cXroCNGgXDpZqUKL9PVqRoKkkLUB9VNhD9Ijz0kf6599rrTFGs16tIPe2oizPKMqC1XrDO++fsmbC7OiUr/zwj3KxLKCwZNMZViw4G0In+etBlM6YHZ36sFQopNKQZeTTGQ/eeZv3vvrDvP3WI77w5BHf/3/+Fqv1EqUcWaaR4OEhtf3FX/xojAX8dSuZVhwfzfnSl77A+ne/zWq9CRHYfZzCy6srPnz6lLOzM2bTOUdHRyyulkHahMuLS0CobOmvGikrWC3IZjliLeVmTb4uUNMMM8t58O7bqOcL9MUK/WLFuiwwtuRsNsGUa5wNql4J2s3Y7+kY+IEIa8K3TYdoKfXYhzHXSlEJzPKc46NjXGmADKdySgxvv/UOZ0/eY1XhiVaoQZTD6SAlZQqcIJUjU6AwGG0oNldcbVasXclJpnn7/CHzR2/zaTalnMy96lflnD8+5QJ49v3v8jeuXvD+F7/Iu194n+PzM7RzYMNh6ixrbKADG4JqEbL95onB/WIPzerPv81qDxGEIWJ2fW/GfsK+r6xd+F3naMEu+AEiYmrge0/KEXrne2hgq29i39X2LECCTSx6R9EwCikRC9EIfTHxH+kWnRx2Dg8bO6ZgbcWmcDhXhcCzoLRhNp1zenbGW++8y+K7H4A2ZPkUKdeo4IHoUCidYbQmn819jEUH2VQhJmd6dMz5o7c4PnvI0ckZ86MjSltSVgVOKkRsjbAKFkCUQdBBSoM8z0J4LPHSRmyRhLNRQc16efmCLPMb92w2ZzabURQlK7vyNqmQB+fQ1pItC6pTg+QKe5QzW1XIpqK6WjN95wFOKZwGXVVe8gqSn9EmOFRI7zEoP25xN2ur71Mvs1oqCGNitCbPcmaTCavShqFUmCDJHp09oAobdBNC20f4EOeoXOWdbZyPeJIpfx+YLhzGCso6FssF6vKKar1hanLy2YxKO9bOkeeGuYIzpyiWV3z8/e+wXlzyoz/5k8zONFmWIcofJlcIWjMMHeI1RMz2eRz2Fr1XYlI70w0Rrj53/F0q+yHv676t73rnzfolxZvCm0/E9thp2gnHlqHa6sReNdaYioVmy/4BgkT7VH9VtVLG/xttYqqxidUZIkRDcPwZVXQ1YZOagBGuTdFaY53FhQgXSvmQSVprJvMjTk/POH/wEP3hJyhtyPIcG65VESHcl+Uje0ymcyqnECdkZJB5Inb28DFHp2dMj46ZzCY4sd4WJj5yhgqR7FGRJPv4E35BC5nJ2ASvSa2Sdoj3UNRao7RiuVgwm86Y5FOOj8+YzeYURcVmU+BcRR1hwjm0deTrivLYIkah5hP02uKKCotgSxtiHgrKWUzoQmt9RHwjBmtLr1gLU1ugvt5ERdVivQmp+jPdjFR0A3SQaU2eGfIsYxVjnGpNPp0xPz1jdnpGhcKE8hUJI+IslfNRN7yE6G9p1g5M5dAOlBM2iyX64pJqsWRiMtRszkZbNsUGbRQz4x11nr1Y8uLjBc+ffcqTd59g8pwsz9GZdyRxuMT+15V6+j77V/WhKrx2342TlMZIOa9aEtuV7l6d2IU9FGIUjetJUKv4pYluL/XuOXYAfgAJWB8EQ7LUMesSLj79HmxHHStYB0L/BzfSyGD4T8f52Smr5QXLxYrVcsnZ2bn3SpzPePT2O5w/eotNVYHSmCxnMp1RrX0IJH8uW5NNpszm/mA0lUMqx2SimB6fcPbwIe+89z4PHj5kPs9wOE5Oj1kdzSiee7sOEohT8NKLYa2MMmjtO0BphRPL5eIqhMsCgwatvW1KQ1U6Xry4oCws89kJJycnaG24WlyhXLgby/rbmnNRzCrF9xdX5MdTTs7m8HyFrhysHZ89/RiqCl1aHky8s0g+nbIuSiaTCQbNuqySPk42VwjtSDdG/0brlOPHpxI/FrP5lEwbnHUYkyHaeyUev/02xw8eMjs5Y5PNcJsKsT5Ab2UtTixVVVJVFRmGSZ6RCVBZXOWYW6+e1UY4Oj7mw08+YfP0KdPckJ+ekFWaogBzOkfKNe7qkvNZjrtY8+LiBX/pz/9/+fKP/TjvfunLfOFHfjgwU7q2Y+6ZyozYUa4NfRt83x62j2C9ahhjF7steOOJ2L6uCMuLYI1pvYs6/jRtjDDQ6LKaz9Rk04ovl2y8+8+VjX83Brbzp1Hv+3TpzZtaOpIYmZ1O3qbNbdLSLmsbp/hSom7Jf9VBuo3qG+JZohhbMNXaqFpF6I3+1C71WOsjlYuCcOUHTtA4zo/nqGrFZuG4eP6cd7/wZc4ePqZgwsnjtzh5/JhCKazWYAwm0xhx6KqEYo3Ge+xNT06ZHJ9jNxVlWWGUYn5yyvHZCScnEx6cT8g0bFZr3n37XdzlZ1x9/9uIVrX04mIfKyEzoCRDAc6CyTO0EywVlgKTa45PTilLfyi5rCxWTVgXDnEr1ssleT5hNp1wfHrE1fISqVw9ZysF61xhiorcaHJlyGY5tlQ4W1FeXJFrg1EGN5tSmhwRg5QwmRp/yDqo9ZRWPvSTdSgVgio7V0vAtXdpGMUgSOKsl5YMQq6Fee7VspUIG6PZoCHL+eJXfojpyVkI2WVCJHznCZlYRCyusuQojAjKlRTrFa4UXCU4pzCZw1CRyQq3foZbfUbuCmaTKWY2xWYPsGcabZfkp1NefOcpJ6XFlEL57DNefPvbsFrx8OFDjh49IptNMYGQKfFOOHmWAYKTeJO0H9AxhCzdxOsDxtsrqMeenNaRMNE9er0+DOr09UIMaYPGog7AXb9u1nkf+Gr79rQ0T7N3xOUen6d41irzHqXLTeCNJ2KHwfaE6brTt2wCcdXWGhR/gl9CukbZJWmSXmLQrjvUvEWAusN6HQLXzdNV/4Rfqv12F9RrVg7AqKUW3MYtyly1PSwQNRWZiETFJqFeF9VZzqFE16X4YfLhpiZGkWlQ4lhcXZFPppw8eMiLlWN+ds705JRSwBkDmSHLDBqHchWqqrzacTJjfnxKPjtmQ4lWFcooZkdHHB3POTrKODk2uMrx7NmGs5MzLo6OMQqc8tfDOOXViCgVrmkBxEeCdyLoQECzicbk/jza8ekx1UZYrTZU5QpRGVVVgq1YLlacnWXeznM8Y1UusC5IQVrjMqGYGsxKyDYWo0r0JMMqQUoL6wKVT1C5QeY+QoY4DRUgCo13ha85Fg1i427ThJ9Kttma2ZMwLs4JRkOmIdeKiTE4pbACpTJUJiObzTl/5wmT+ZG3/6ER8TEMxQa7nHMo6zAosBZXVhTLFVXhsBU+eLAtEda45QWyvEBtrshciSFD8px8PkWOYCqKSW5ZWYeywsTB1WZD+ewzLrVi8eIzJsdH3p1fe29FwhVBtWo0zt02l7V/CWxJI21C1kuEOqlaOXrsbb3phxjjLbVev6pwG6Mx72Ur+ZbI4LnSGucxku8Y+AEjYl3YPdiqmyR5HglYa4qqzttmDxiQcnaJ/rerEmjh0JpdMnIy0y+ODaVryadN3igZt9SJNES1uQ0ZRHS9efrPELYoXC4P4a6yEGuPcsWLZ5+yWS2QsmJxtcRpw+T4lLOTKfPzh+j5EVdXG/RkwmQ2w9kSozWZUmQKTDbl+Pwhj955H/IjpplFW0c2zTl/OOfswQlnZ3NOjw1XF2s++fhjzoIDg1GGUvyBYTMxPvis8p56E60R5x08dKZZVyVZnvPOu++w2GwQUcxnp5y+e86nnz6nsh9RrtegDM5aPv3oYya54fjshPOHZyw2C5xYpFLkRzOMBskd0++uyZYVsi6R9x/jcoVs4GypqArPOOkvPaDMcpTzUlMZpLf5bM5qvfTlhnGIIbsa23AT6gskOIc0XL0xJvz5UapEUzrNBsP8wSNOn3yB00dvkR0fI/mEspAQVNKH6cqMCvYvRbG4olytKVZLVpdXlJsSV1boCo5MRWHXLJ7+HvLhU/KLC7KyZFFcsVprLqsMPZkzUZZpVXIujkocFcLRbMZqkmHF8uEH30NmU07FcXZ2Rm4mGKXRGZRl6R1KMrNFwruwrfO4GTTSy+5lV7/rlej2a3pupn4cmy+V9sZuNuPhjSZikYtvwYjZVE+MbQm9lWZM/T6t6uWA4qD1eer064uT+gcQGPL0GQP7pK++vugSuFE4DtTRRyz9Jp/EUqvH1Ks4a24tcHFRDyq1sOa8TQlBG8XV1SWbzZp1WXFy/pCT80ecPnyLBycPOHlwBtkEd7FiOplgnKWyBdr4CB0OmBwdcfboMY/ffZeLVcl8BlM0s6MpZ2dTTs/nHB/PASiKkqurBSenE2qeXenQBlXfNeYvfK6vWsUJ5JMJ2IrF1YLczMnynLOzB8ynRxSbgsXpEVdXF2i8dLNZr7i8uEA0HD065fT0lDzPsZsCk+WIAatnHB8dw3JFVWx4sVmT5RnZbIa5rBClkSynmOSecQjEYlOUMMmYzKZkWV4HTFZa+zu2QtfXZ/2ChiIG9gXrHWi0RmcKZQyYnI3TlA5KhFLB4+Nz3nr8BKMylAWHpVoVqGKDEYcB7HpNUWyo1itWF89ZLxasF1dslgvseoMrNuTFGlGKfL3m4q/+VbKnT5ksF2i7QR0b9JFmZjMuvrfGWgVWc24Mk8ePMG8ZlpOcxz/xY8zef4/PphP+9tOP+fDFZzx5+wlfef99zGyKs8FTNN7sKskm3LMZ79pyhpSAfUEVYlzDsUEV+g4W7/u+K+9YSPe2dtlsL/6BPe/eO3EIRvRLTDJ4kh62dts+99VekZ/tCdZ9Hr/3GzhvxtMNToxbZBVrdcBg/0k7cfwq/f1Uuz+oGMEjirD+T4Wr5qPnWh20NRYoDqMVucmoyiWboqCsLI/eepvj03OmRyfMzh+QT/xlmCKCMRrJjL/mXpyPcK6E2fEJ87NTjs5OWcoChUYZw/xoxtFxzuxoRj7JKMs1ZVngPelcfRWM0ia2rpY0fduF2l4p/jxaVTqurtYUhUWpHBF/PctsPuXs7JiPngI2SETOsl6vMcuM+cNT8myCTASHRhsDGYjJ0bMZUllcWbIqS+YmI89ytPZSoTMGm3n7jhYBpamsI7OuVnN6F/cqSM5e5k15iEiMfdtczYRkmfbqWZ3hVOYJmEAJOKOYTKbM50feG7C0OFsimzWUG3AVzjnWVxdsVkvWVxcsX3zGZrlgvfQu9K5cQ7VhWq45RmOuVqy/+3ucXF2hyg0ia0yeM59OONJzpsqhlWGKZj6bkYcILNYo5menzE5P+HC54Oknn3C5XFGWFe88fsx06u1jNb2iCQTcsoft2ISv452Y5u06bnT3jm4ZXSePPvf6bt5xxEsNNrO37AHB4C5c6yMcTMT+5//5f+bf/rf/bb71rW/xwQcf8F//1/81//g//o/X70WEX/3VX+U/+U/+E54/f87f8/f8PfxH/9F/xI/92I/VaZ49e8Yv//Iv89/+t/8tWmt+8Rd/kX/v3/v3ODk5uZVGwcCefUsbeTqpamcPGeaO9nnqdJ7eHME+uMVi9xeVKkO6kG4GeIN5iLHXsAXdfDGKuncA8Ld0SdzfQSzzWcbZfM7zZyuKTcl6U/KTP/3TPHzyPpPjU2YnD7BiKKqgUlOCwuFsRVEWFLbEKnj4zjucPnrM9PSUvIJpnpHlOcfHE47mmvk8I8vgs+fPWa4WHJ8es15fstqsKWyFyQyE26HjFTHKufqsk9L+3qrVcs3ziwXf+85HLDcbZvMZ1sLxbMbJyRGzmeHDD77H6nJBVRRMTMZqtcIinLz10Lvna0M+zcizCSYTnHLY4yPExputN+Rmiso0+fyYjSspMk2eeQcTryfUWFdSlBXrzYYsz0ALUkq4ZyvEG3SpXSzOdX/OLDeGLMt8DMd8SukU61KxqYQKqFCgNZnOmJiMcrlCKoXDIOsVqlxSbdYsLi/47OOnLC4vWLz4jMXzZ9hig9gCg4CqUKrC5IKuhMnyitmL73JuK2auQrk1s3LGKec8OX6bR199H5GczVr47NlzVmXFVVVxUaz45Nu/y+J7v8dfefoR3/n0GUXp+O53P+CHvvgVf2XPbIZI6eeeCM2B7jtanwlEjcUY1/g+YrfPvX7o/Njh0thhebfPE74iSWyxWPBTP/VT/NP/9D/NH/pDf2jr/b/1b/1b/Kk/9af4M3/mz/DVr36Vf+1f+9f4+Z//ef7aX/trzGYzAP7IH/kjfPDBB/z3//1/T1mW/LE/9sf443/8j/Pn/tyfu3mLAvR2zy3PP0/AYrDTIRXheHWifzGA5w0J8Njst63b3wdKNZKtUgTiQk3Qos3M4+Y3FOscThSIQomQScU0yzieT3juKsqypKwcbz35Asfnj8iOTsnmRxSVUFT+vi0rFltsWF5dcHV1SWUrpvM5733pq5w+fAz5hNnZCflsymSSMz8yTFSFyb0b/WLhicv52SkfPP0uq+XSR593E5yqsJXDVcHe45wnZPXdaobPPnvOs88WLBYbRBvWq5KnTz/i9HjK0fGUPDe8/97bfKLgRVV66SVcnPn0w48oyg1aKU5mc9z8CKMN2mSsjyc4meFcyXRpYVVSVCtmDx7iXAWZItcTPGqOqrIY7Z0vNmVFPpmQ5ROU1qzX6zAGLfKFMu1QU9PphGySM5lOfKR/J1TWb8RaaXKt0drw6Ycfsl5VPHr3EslmWDRlWbC5fMZ6dcXl8+esri6xxRpbrDCuJBfrvUcpIQOTKx9C6qOPya4+4QtHC754OuPByTmP3vkRzPQMWxnWl47n//czNs6xtpa1Unx4ecUHVxf87mpJcXrKZjblk03F5eWa9WrD1SeX/I2/8TuIwE/8vh/1d44pMAnDGiXsCHfjzq4CIRsuexchOoxpvp46sZt3pzqxp45X6mL/C7/wC/zCL/xC7zsR4U/+yT/Jv/qv/qv8Y//YPwbAn/2zf5YnT57w3/w3/w2/9Eu/xP/1f/1f/NZv/Rb/2//2v/H7f//vB+Df//f/ff6Rf+Qf4d/5d/4d3n///Rs0Z2jgh0XiIXG+L90hKoKhMtLPXqI2NLY78B/FBbV+7VgcQw9lF3IHQmeipw4eHoLNRSRJKG1iRug/BOdKlMvQWMRWEDjnfHaEziagM1CGqlpTFiViS6SqsGVBsVlRlBsUwmQ24/T8nMn8KAQKnjCZTcinGdlE+8j0yhPSzWpNVZZMJ0esVwuKYuNtQlrjlEbw6jnvGREivotDnAL8Tc3r9QZbCRh/fMDakovLS5R2mMzb3pZHMzaLCcWqBAFrHcvlkqoqyY2ByRScP7aAhmqaI1WOFFPMcgUWKrFsNEg+QU18iCWvnsUH6TU+WokNMcGMUWSZwVYV4rz060hCTSl/c7bS/pqUyST3EmiQzJxTIN71Xmmpb9q26yVLnjHJZ5ROUzmhLAvWixeUmyWrxQIqfwNAbkvmmXc80TiwwclCax7mmmNVcWQq3nrnlPcfn3ByckR2fsrVJmdVwtXGUq4t66pk6TY8t5YPr654ulxwibBeF6wrYVE6ykKoKqiKiu9/8JTz83O+8pUvM51pGvfyqEGIyu9t9VzqUp9+Di6DIXX8ns1+6NmQ+jEt91B1Ykt9OoBjC6+oltpZ5itWJ+6Cb3/723z44Yf83M/9XP3s/Pycr33ta3zzm9/kl37pl/jmN7/JgwcPagIG8HM/93NorfmLf/Ev8k/8E//EVrmbzYbNZlP/vri4uE20e2EUcRDo3o2V5ofdOuld9b0uhxZh2+Z309L6uEzP2Yc/COGpwvIJLs+1qUz5u78Efy6pKFbYUpBSY6sCrWEynaKyCaIznGicg816w2a5pFqvkKLAFiuK9YKy2DDJDPOTY84ePEDN5lTaMMkN+Swnnxh05qD0gYIRx2qxwBaOk5licXlBsVqSG4PDL+R4pk2CFCaEizIVWKtYrzcURRHuOnMoJSgtPHv2KVpbZvOMo9mU09Njqk3Bp6tnCOCspViuUAoyFEYpjHNoq3GAnefAzNsJny9gU2Kt5aIsyI7PMEczb/MKKqvKOXIMgsI6b2/Ms9yHxrKe0NtKsNFmqfx1MtpoTGaYzaaYzNsZC1tSFBZbabTLUOLtaUaHoSs3iHMsPoarxYr1ZsOmKHB24/FViqNpTp4r8knG2TxDSQlujS18H00zx5emivkETk8m/OS7P8TDdx5Q5Zq/fbXib370nKsXUF1NmZNTVCVX6w1/85OP+bQqeQGUDx+xRLPYCJeLgqoywBRlMv72732HyXTKj/74j/Lee2+hjYJ4QzfURAzpd8y4zTV76B5wiEoxhevgPOQ8cgiOr6Vjx4cffgjAkydPWs+fPHlSv/vwww9555132khkGY8eParTdOHXf/3X+bVf+7UbYNYoycZ0XNy0u1xWd7AOGfo+Y2wsN312qMg9SkU5lHd0yvTw5diSd0t76VulYnCm8Kfw3LvzZ8d0XV7yJw4VnAoyCigd5cJiN0uO50ecn75NNpujTI4IFJsVq8vnnvisN6yvLlhcvGB1eQHimM2OOX/4EKNzQKMEslyTZQptBOsKsuCFlynF8nKJlJb8oWV98ZzV5Qvc6gpjK3+aObRQK3ygY/DegfhDwavVitVqDWhEXC3VLK6WaO2lyydvP+b45BiD4erFwl/ZEiK6KwSjFTOtMc75v8xQ2AptNNnxnOz0GKdXVJuC1eKKyWzCJM9weRZskSrIOTqUaFkXFWVVobEcTTNynSO5QU2mzYBpRZZnKB0lTk8Ay8KrJ50VlIOpydDaj+V6s6AoLdY61tkzKutvbZ4bw9GJv2ssU4rZJMMgGKnI2ODKFVWxYKILzuc5j45n/IH3T5mYd5ivHvLFd97lOx9+j6dXC75tDcsnX2L6hYc8mb/H//E//S88+/Qznj//iI+wrCYTNpMZpZmxEU1pHevVBiTzml5X8OyzC77zve/zV//aX+f8wR/g+HjmD4g7CVJZvIQV+nRn+9fg9RT219EY7ZP0djme3RYx3qWRui14I7wTf+VXfoVvfOMb9e+Liwu+9KUvtfTycItcULSs9r7qDMCeOblv8h2qUuibePsm7RjYlTetcnx/Nws87c6hrq2LVY3KJub3qrj459VbSgVCJhUn85yZEaTa4KqCyfyMo5NjrBOMc4izbBYLNldXFMsFFAXl4opyuaBcrUCELPNBdnEOV1U4rTCSoUKkF++B51EqNxWucriiYnN1iSvWSFngyhJVlf7AbmyTimpQP1FEhKKssJUnSCi8m7qSOgjvarVBKTg9OWZqcubzOccnJ9irJVVR1IOinZAphV2v0TIhy2cYBwpPENXRFKkqxFa4ygfSBaFShKjwHh9/kaW/CaCyjs1mQ7VZMnv7EUaBCXd7xbkgCDrLEOUvkrSVpXIOG6XPMMDFxjMXbErWpa2DMecaZiZcFJoppoFZyJRmmim0OJS1KFdgdMVkCidHM959fMK7D0548iiH9RxUxtVa+N6nBU/XjquTM9zsjJUzLJ99wkeXz3mxXnBVWVbTjE0+oZxOqUxOuXEUpfgbB+J5DTSVtVxeLvi973yX/9eL30eWaY6OpuC8fU9vSR377VftSX/YGt21P+xz+Oj+HqPe7JOuxhDQOs0em9yu39eFWyVi7777LgBPnz7lvffeq58/ffqUn/7pn67TfPTRR618VVXx7NmzOn8XptMp0+m09904eJmuCgH6iNv1mLBBuIln0d3CNocavdlE2u9Te1hUV8VPb7dpJC8fksh/+tiEDuUKHp7OMLbArpdIuWE2yTk5OaEoKjJr0VXFcnnF+uIFxXKJsiXF1QXF1SXFahGIWM5sNseVFZUDq8Ec4bluNNoojFPgHOvlGqnAbkouP/0UKTcoWyBVSVWW3tmnPi+GPz6AILVas/QxFvHcvckCMbEOxL8vi4KzsyMenT7gaDbn7MED1oVlU1Y+wLBzKHHkCorVEpwlm0/IlKC0v1hSncygLD1xLQu0eMJVKakDALvgKKPChaCVtawWSy5efMpbD0/9JZtaMZ9PawJWWQvKBHOfP2dWOYt1gvW3zQCwXK6wAlYUlRPyPGeS50yMMJ/l/o40o1F5uD9MKTIEJQ6oELdmmvm077x1zI98+R2+9OQBj8slq6spyxV89/sX/O4Ha55VoGfnOI55cXnBd37n/+bDZ0+92lZBMZ1SzmZU0xnWTNhUKzbrCuV83wsC2kcOuVos+d3/+2/z0cefMJtNOD6eI3iimxlD6aph0/XQWjxAJ3+oeg5uxsDvVg0eSnQhemq/rL3pVonYV7/6Vd59911++7d/uyZaFxcX/MW/+Bf55/65fw6An/3Zn+X58+d861vf4md+5mcA+B//x/8R5xxf+9rXbhOdVwt9Yz9iPlx38Mfb8G7w/gBIVbINWlGlu20z9K7cIdqFFn+nlEokNKRF1LRyiJRIueZ8/hC7XnNVLVB2wyTXHM1nrNdrsuUKW1Y8/+QDls8+o9qsMdZSLa6wywWyXjHNcia598pbXy0p8Qd0rZoizJjpKfP5HKMVbrXhxafPmeoptlzwvd/5HdRmRWYrXFV4Iqu0d4TQwZU/SFjiFFUlLK7WVFWFyRSnJyfMj09Zrdc8e/YMo3JELM46nn70KTgN54a3336X0oJow+XiEqMcM6M5mWQUiyt/H9pFxvTRMRWOwllMbtDzCXlVUi0dxnhJorIOp3S94VTiHUMyo1DKeznmWU5ZFNiNQ4llkmWYPEcpjRWhKgtKa1luytoTUbShqByr5YaLi+es1msmszmzI29rnM0mTCcZk1wzzQxGg3MlJjNesrZQ2hItFoPl+CjjwdmUtx8d8cNffcIX3n/Eo7Mpn/7l/4Onn17wwXde8M3/5du896M/w9njh3x0WfJXv/WXuHz+CZuLZ94jVGvcZEKRGwqt/dgWG1arFZv1xhMlaxEcKIU2GaV1fPzpp/yf/7+/gnMVjx6eo0WwLqgT8cQfkfp26FErIjBmo9ZPvW6GJa3b8iiMz/rfH1w6KYP6Mpjrg4nY1dUVv/M7v1P//va3v81f/st/mUePHvHlL3+Zf+Ff+Bf4N//Nf5Mf+7Efq13s33///fos2U/+5E/yD//D/zD/7D/7z/If/8f/MWVZ8vWvf51f+qVfurFnIty+vvVlwhgPo112ur2qyX1dc8tdFxdB1Kb02dW8JObq77p2IGju1VI0NggVbEwESURhybUDLMqWZAZvQwtXzRebNbJZsXzxnGq1xBUbLzGtFrjN2ksw2RxjMkCxvroKRMzhJiX5XKOOchTh/q3K8vyz5+AUYh2LF8+pVitcsfFlaYW3iEVvvhh1RFDKIAKr1QbnLFlmODs/YX58DFpQnxFUWwZQbIoNV4sluZkwf3TK8fEJlRVW6yWZduSZIVNQWYuuHEqtqM6nVBqqcAmpVxcKLtdYo9DKoSoL2kQdIiJ+a3ae6yDLc+ZHR574hutlyqrwpwO0pqosReU8MRSwViitZb2pWC7XVBVYDLOjM6ZHR8yPj5kcHaMzhWhFJYJ2lXckcSWVWB9fUmdkGq9WNJrTkykPHxzx9ttnvPv+25wcT6GyvPj+Bd/59gd859vPeHa1QD37BLUs+HRdIFXlA5I559W1RjVRNxSA8+GrbIly1hMhHUZMewcVv66EDz74kEcPz/nyF9/jyduPAO9Ykxnjr7XZMe+3QSJXN2rt1O7qA4vyplLOLkK25TK/o4ytZ4nafFe624SDidhf+kt/ib//7//769/RVvVH/+gf5Td/8zf5l//lf5nFYsEf/+N/nOfPn/MH/+Af5Ld+67fqM2IA/9l/9p/x9a9/nX/wH/wH68POf+pP/akbNyae1+rCy9K0BYXZyIQxXUdXXoswyautMhsnlX0TrSEiL0/dqABpGb1VTcjqBC0f+yidBacO5YPmaqXC70btGMvy265F4zA4rFiUWDLjo1E469BaUaxXlGXB6uIFuiigqnDFmmq9xBYFyvlo5UZrHzFisaAUoVQOO6k4eTD3kS2cj5RfFSXPPv2MuTO4yrK8vKRcLb3Kzknw1KM+KJyY+kBrEGG1WuOsYzqdcHp6zOzoiE1RgPK3NsfAwWVlWSxXGJ3z+IEwnx8hKD57/im5g0lmyJT3TvQ60DWlLalygzVgSgnR5wWba6z2BF6XFjKHxGtfoCZkgiLLMsx83oyZ8jdIeybChCj7PjSVc4qisqw3BZeXSxbLDVpPmMy8XXI6P2J2dEQ2zRFXeQnRedd9jQOpkMr54wmzGcbkTDLDbKI5O53w8OEpj996wKO3HqKLgs2zBZ/9Py/47u98wO999xnLUlN++hHWXHBRVN5+l2VstKLyPhiNmhq/DsrAyCiJd5w5ok7bVZ7pUFrx8cef8MEH53zw4YcNEXMOnefBROsYcmJqS2dhQXfn/QCI7Nj4pRuv9XYI2fD74bz9+Pl/Xmt14t/39/19O5FSSvEn/sSf4E/8iT8xmObRo0e3erC5qfz2ixxXrUtoz34y5s1C0dZDYjvBT9LoUq4CUdwqMEyOWN9OozJhJ+onhDuRTJJsq/T3GIljEZ2F0Lr8cktd4ncSpYSaeVbRFVdCPymQDGVXZFIxMxUT1mAck2nO9OgcUTlFUXEiBVdXS5aLSzbPn3lnAueo1kvcegVVhcGRa41yjs16jS0qKvFBN6q8QuxjjPZnplxRsri64Lt/+9u8NT2lvPz/s/cnT5YsS3on9lMb3P1MMWbe6d03Vb2aga4G0OgWsikUIaXZUlxgAy5rg0EE/xZ2WFKw4gZCUgjhhhSQQBNAja/qvXenHGM8kw9mplyY+xkiTmRG5s1b3fehLCXyRPhxNzN3NzM1/VT10yvqm9fEeokh4auKumlQMb2NSTfvFPJCLZKYL+eEFBg5w2Q6JqRISh0pRmyvheXdLCxXNV2XOD26ZTrNnIk/+OxTaFdUknCVRa1CE6BZ0S4rjBsxqirKlKhjIsVIGhekwoG1+CFSQCFntJY+3U12zrCqGBHEWMrC44ygKdF0LUmhaSMxGboIi2XD1fUtddsRQmJ6fMZofMxkdo4rfIbzENZNYLGc09RLSpcYF5bCGYpC8kbEeypXUnlP4YSygLPTGU/PT3h6foq0gS//41/z5X/4S/6n/8t/5suLK67qjnU1Y9Xc0uiCi9sF3ji06+jqmnI8Qa2lkz5BTFJSCqyXKyTmcdXFQPJZmIs1pLbLD8ZaVsuGL371NZKU3/zxT5hOxjjr+li4nPfM2IFm7DEL9bst5g/a3fJE6m1571PzW9r9X5yN/c3le+Gd+Oby9oe9r5bn83e95Q5ec+cXEUFTFgbD2rsD7O19vs3sZHrBpHvd6iGnwQuPtwym4bjuC877Z+980z8HM8B7gOrd3g7OF9pTJzE8gDu7y/2cR/tlo3/k3Vjf3SGnEdrnEhPNQKKRvGXOydxyjJgqzmSTUEpZO9sqqw7pAseV4cfnx5yO4WUbWbYBxh+hfkJIUF89o1s3pHWDiy0SU3Z/DzXEOrchlspZJCXa5ZLYCZ0KwRh8UxCjQdURQ8DEkINxQ81qtSbMr5CwwttcbdMp82XHqq5pQuCzzz7KwkCkT4IZCLSoZAoq07PfN6uaGDKkal0WGCElrHFoUkJIvL68QIxhMh4xGVeYymCJBJPgeAy2Jswb7O2cksQYwWl+/h1KYQqsOkiWYAYP0MzJaIzdvLPY5xATsYQkmCS9BiaEqMSYaEMO1m7ayHLVEFPCWotzBbPZjKIaYSx0XUtIiS4lkia6tgGF0pdMJ2OKwhLDCkPOJGBweFPhJGFSg8aa0KxY3xbcfHPBX//nb/jln7zg2XXkqvEsxSOzU9zsGBAmGLrbBcRAoRA00RpPU1YE44lJSFFJ0WxS+aQe4tWU2V+k15Y1KhFhuah58fyCL375NZ//4BOePDlFNYJkD1mVuJ2K/YTutyAb8mRRJQ1z5d78vF+Gob5dGnbXrO28H+zEeU5vsXp9YN3YIiTbMszH3T3rXSBoL3eibs/YreqQ/W6ztOz2R7f1PQzIvlv5XguxfcP/m8vuO32b982uzBsWbu1X/c3iv/sCNPWL/Lt1ZFcI7g6Ct7vM66Yfu3VtyIH2kIzhxGHg7QxAPUShIzv92e3vPtXQm/o56H27k1DuHBt+yRzo+e/dCSZkuh/T/+xCc5oE6VrGU8MPn0wgLXktiTokdDol2ZKYlHZ+QWgCqY3Y2IHGTGwbMuGsKDhje00s0tVZmLQqBHFIe0QKoNGgRkhdIHUthJp6viYubyDUOZg3CTHBctVydbtgtVrx8dMnGD8I4IFoOKAmISpYY7A2Zz5OMSEoRZHhutRl5wvILBi3t7dMJmMKbxkVHiMGNBBijZmMspdh3SDrNc4aSlfgyhIlcwh7cVi1oIYoJoc3q/aQWL9wa3aRTyYz0oeomzgvwRBjoAuJtg2s1jVN01HXHYrBWk85GjMajTAupzlpmoYuRrqYMNYiKN7aDRFw4S2rVYOV2Asxi8FieztoDC3r1YobEV5/ec2v/uolX/zykteLyFwdbeGoxjPsZIaoUtQNnd4iKQdOt0AwhtZ5kjhSl4hdQtXkH6Rf8OkX8rQZyyklEkJTB25uFnzx5TdMJhPOz896J5Aeph+W4h0BBhloEe2JrTUfyMgEjyqb0/YkirL3v+r9NafHgA9ugHfn0D488vBc7f/bnj/M+bsN7/TtziTX3qaxu4Zur/j25XstxN6lfCgV+cGo+APnHmrtvt7T/7fZbenOW74/SDeC4149w7bv4X4f7t2bZ9UAW36XRTTzCorpf/IKwNapY6vNoEps1nSrC8zJiCdnT3j1/JIUAqqGkBIaO+jWaGoIbSB2kdh1qAaIgdQ12X6GAQtGs4YVNOclC2rojMc2Le2qpVsHJlXBfLlicX1FPb/BrNZoPc8OAgLGOIrCcXUz5/XFFYvFgpdPX/Pk/JijaUXQ7KItBjRFfJH5EUmQYkBTRFQ5Oz2haVoWiwXreg09XLxezrm5KkETo4/O6Yn9UQQ7qjApERdr4mJJWNUE4zLlVlRSSOR0j3l/H012oFEFSVkj1p5Oa1jBlOww4mwOiEYDXRtY1zVXt3PWdUsICTGetusYjQuenJ+j1tC2Lct1y818gbGOoqw4f3KO7emnCgPWugyHJSiKgsoXVM5A6sAKrqy4Xdcsltd80b7i9V+94os/+RXf/PUzVvOWbjJG+pxwQSC0HYubW2KX3d/FW4J3BGuJvTdQFwLrdUvWk/Kx/bG9RRtUM7waotB2gf/3v/v3+MLz8acfUVWSg+DFgsYd5Wh/W6m70mBvB/eO5a4sGqrbEQzCu61vD65j73j8fdr60HDlfyFCLI+eD/UQH+NFuG11vxwE3mSrEaXeEJ93xQljzP75Ox5Eh47fbeF940j2vJYO9PuDlt4NvV9aNl6J9AHGIlkrsyJ4K1gvMErMJonpFG6KAmOKrGURUa0JMRCbRAox0z2lsP2hdyowmT5JNKKxIcWQ04OoRUzCaUK6SGpaUg1XL15y8eI5EltCsyB166zJqIIYoiYWi0WfTNHyzbOXWGPxrqAsKlQVayyl3ybLtKI5uFezJmatZTadMh6N+OrrL4hRsaKoc6zXK0CZjAqqMrNhgGCtwxYVfjYjdF0m862bbN8JEZsUb0yfdTpDWxsYadBCUobQMP1bULDOgWSHl66tWa3XrOtM/zYajUgKbZsYEuTc3NyQneMNSQ3Hx8c4X+CLEmdt7+IPmjpWqxWiEQN44/DGItqhCiEZ1sGyxmCChXXk1Ytb2jpRFiPWI4c/msBsTCuJZrkgrmpS3ebF3BoaZ2i9o+upwFJU2q6jaVsEmzWD+8OQbS4FQTURYmDdKMt6zZfPv+FP/vIv+Af/zd9FScQU+q3BPhy3N19kR4I9QFF3bzo85py9tUf2hNpj17fHCKxdR5IPIXzetma+T/leC7G78NZbzn6U4Hlze/dfoogcrOvBl/0G2HGLfe8LsMf0NavxyqHa797v28bhYffbt3bhWxbtHTqU2BsEBuvCoI0ZBCvgTGI0tRxNLaMRfUCuy7YyIppaVAIaHBqzi7ik2O+as1eDEUVMZqMQDb1rXoTUIeoQDCYlUtsS1g2MLfOra24vL0mhIYUajdmjMDNtRGKCuq4JIQLCfL7mdr5iNJpQnB0DGTYbVRUh5iSQpndi6cEtSImyGuG959XrgrZpiSG7gocQaOqa+e0cOZ5SFDZTPwmIc7iqxBYeukjXBUKThZhRcn4sI1mASR4TA3+iDJQdqtlGusHpEzHG7BgSY/49Zdtd9jY2xLgmauqZRtY5p5ktcl6v0QhflFjnM5wooJro2pbUtRgSs3GRhbAxiAZUlJgsIQqIRzqDNpH5TUMMgi+yPTAUnmgNXezQdUNa19Dl556MpbVK5wyxD2AOMdKFSIgRsdtlb3+D1m920QErJKUc3F13LZc313z1/Bl/J/w+hZUe0tU9+bQVXlvb+QAjPnrN0cN/vGlD+tiN9abWBzbBD0GQj3WZ3/c/eFyb37Z8r4XY48t9TQzeXTs5VMfbzssNbbrwoFazq33FGDd/24330xvqZzt4BtvY3XOHNh7d591jm55/N2WgkTKa7TGbjM6SF3krihXBmRznZFnzG5/P+NEPSibT1AfLekRL0ICmLpPcdrM+7X3IkGHKvIaiMdMpGfBOQEN2aFDBSdbUBEG6juZmztoXyNRz+ew5r776CrOcI2GNaIuY3lckZKhttVr1tiRHUOXlqxuaNnF0fJbb8wVPzs+4ur7FSk5MadHcH1Hq1YrZdMb5+Rm383MuX18yn8+ztyOGGCLPnj3H2E+Zzib4Imsa6jwyUsrJhLBY0a3WrOdLUoh4DKVz1Mb0GsjOAtuPM02JJPlx5bQulq5tqeslXbvm/DhnklaEsK45PjrCWM9y1QApC9i24+jsCaPxhNHkCOM8xrocPF0UdG1DU9fcXFxAClSF5+PzUwovGIkkbUAgqqNtDaV/QowtzVKZX3eU0TGqHFY9t9qxWi2Q1OIWLbYO+JBQZ+mMsPZQO0NASBHWdUPbBZJu2UoOFwHMxt5Fr72uu5aXV1e4rwu+fPmST85POR6PIXQ9wwj9RmBnXEPv3JA3X4/GM/pF4qG14v4adFgTe5Pm9NBaeK9u1Xt1755/uPMPfPMdaGHwPRdiD2lBd8sHhF837b5tV7FvOL1//d3zhmPW2r2XffceH9oR6YEd26HzHyvI/ibdbPMU7O1ie8e3lFQWxaF0oaG5fsGP/sFTPv24AGn4+tlLrq8tQgmxI2lHEoUwhhgyE7p0kDq018iMcVijOMlkuyoGB6h2KB7B4WOHrlfU144L01BfXZFWSyqJGJs97kIXcc6jJFwQZrMx63VLFwAMq3VLiAu++vo1Hz2dUpUlH3/8MaELGGMyBJoiBsX2ObzatkWT8vHTpxAzHLpuMtO7kqWv9Q7rHCoQehjWOkMxneZM2G3MaWeUHsqz2SY3bEqG9ba3Sw1amTGZkLiuO5Y3V1gDhS8oioLxZELbBX75qy+oRhOqakyMEWstZTViOj3CFBXWlZu2Yq8B1W1DXa9p6zWqyng0YjYZUY0mWPI7SjQkUaIIyVbY8ozF5QWvny8p3BSvLVaV0yfHjCpDZ4UmdiwWz0ltwHVKNNmG14nQ9RkMIsqqbnL4wEYL24ETdzab0muhWWs0ZDUWuhhouo75quY//dlfIr/z24w+G1HSw/2iW2G2mY39gj/At2TP4LeWd4ACH3PeftVvXw8ec/xtAvJum98luvO9FmLDLvLt5f2f1nexkL/JxrsruB4rpPsrD2Luh3ZaeQXLnllv2hx+aGeYh7/nDuyyPTgEPkPEipKItGHJtPqIUSUogZvbBav1CBhDbLIgkrQDIeZc0PR2J+m1sEwJFfuUIVlcJgk4sahRTOqgawjrJRfPLulWC0wMWElZEGp2RzcGnDV4Zzk9ngELwnwN4ghRaZqOq+tbplOHL8aMxxOm02kO2dA+Jov8DEIXCCEQYmRUlUwnE5p1nePP+ueVBZLtmSjykhlRggi+KLBlQfSe1ITNLtrs/GQXhCGliPRb/m08XwiR0K6JKVF4T1mWOOcoigJFaNqW5WJBjHn+FYWnqCrG4zHJOBRDjDETA8c+9sw7UowYYyjGI0ZlQVlWiJhsoyKRMAQiWIevpogWhEZYLwMT9b3YCSQVrLFghRg6XFJiVLzkmDQVIRlHwBATfT9iTqTax8UNRXd+G8BENp+y+U4RuphYNQ2vL6+4vl2wOKkpxlU/9bZE0bpzvW4G+H5r71LuCg/gwY3m2+fa/gb3rRrWATjxsW2963nvW77XQuzxZSs2HiUU9D4kd7c8pp6DtjJ4q0jdve6wEDpUcs13IenD120Xrt2TH7PLeqifu9fvdeERml1mywA0kWRg6ci2K2uymzkp4GwCEwm6prAdzlgU5eJmwWJtURlsYB0qAVKH1czqsUmPIvSu7TnhYYoZDhPpvfdsQIxHrCJdg7QrQmz5+tkv6BZzPAmnkRDaTDNls8ZhnGBGBT/8/BOU58znS6zNxLddiLx4dclsVlCWjqPzU56ePyH0FEnZvVxIIRI10DQtbdNSzTyz2QxNysXV9eY5FkWRHVJk67GZgBZlXJa4LqKjjtgu8ijunTWMGKyx2aGiv19V7QV4LilBva5Zzm84PZkwnoyZTUYURX8tAVXl8uqKYlUzGk0ZTyYbO14k8yc2bcN8uaINgRiVk7NTysJTjEeczMYYTVjJAtO7vGkIaqlRqmLE0clT6htDWCvdMuYwByyRxM3NHDoHXghti+kCDqGwlkYMiEOtp03QtYF2nUMDssAcBMu+/SofMjsjd8Dzsp1SSkcbI/PViqvbBa8uLjmeTDke/SCTLkveFJh+A6ZkCoTBi3So7m3LRp4j/fzsNxuHILg9zabv7t3v39bOu6AuD9n97x+/v/H+rhGd/0KE2DuWHTD6bxJW2zT/Adp8lLDkcXvDx5733mWY4Jt/ptdwcjCukCid0DQ1hQ08+fSIs9MjfCHcLOdEUxLF08U+qNT0S0hsQBJIT62+s5psmFBUMZrbQITCZVYLREipoZ5fEmKkXV7itcE6pQQwOSty1ETpLQpEkzg9GRO6MwTlr3/5HLEl3hd0XeD5i9e03ZqqKimrESVK7DoK7/E9AfG6UxarmtdX1xTlKb4omR2fMJ0dsZwviTFiEJyxOGuzl5ymvNZiaEn4smB0fMy8brODkLMb+NE5Q4XFp4SkTGorkjNSW2u5ub1FiIwmE6bTI7w32XFFh2Bsy+npKatVTVPXTCZHVFWFtY7lcsntqmZddyzXmd3DFfleQwgIvQPMuMyxZyKEEGmMBWNpbEV1NMMXM5J6Fs9eUb+6xKzWlEVJ6CJNk6HOrl6hGnApIU0HmgjW0lqhswZsgaaUWUii9tKjtwn2w2ADAQzDcIMqZs0ry7Ssais5bq6uO66u5vzqy2doVD4+O8t516zgTXa5zxnJEyI2Z2oTw8AP+qiZtOlWrzX/z7AGfZflQ9+Pefspvw7l3eHED218/O7b7HE42fz1YJ2yUdfebITdfg6Vfrtn8tD9SW9M3/yIYSAA7iUNzgkpthgCJ0cVRVEQo3B5XdOpIQJRY+YejJIjqLUF7cjpWzbuDCSya/ngGj54LGZrimC05xgkELsVXTNHwwongcIOiTq3rBcb5xOT8BYm44KzkxnjkcdaYWAlXNVrrm/nXF3fEJNixCKSA4WtdT1zhqFpA7eLFU3TkciEvNm7L2sKztkNI/3AH5WdCISgoNZiqxJblUjhUWsRa/oULYK3Fium18ZMDyuS7VddhwJlWWFsFmBd122+iyFycnLCdDqlqnLYQNu0rOs1y+Wy987M9j5fFDkX2mSS4T/2d+VZyckcjA2G2lYcffIjitkZV1dzlq8vCTc3yHpFShGMQcoiexeGhDYB2g5SJKG0FlpnCMbmIIqYvQtz2pse3tM3j3vd+xzmVI+GJCUGpak7bm8XXFxec3F9Q912fVqa1I+1/E4Gl/3tv8Nz4uAcfWMv31zPt1lH7tYhb6j7od/fVveHLt9rTeydbUbvUB7rrvrQhuLBa/Q+gefQ3vD3Yz149s85DDc+XJfsfb7JUymjG28WZI/dWR2ER9X0cVJ512p6eMaYfhetkcIJKdSINJwdV3jnmdctz14uaGOfYkMjKWwXHtWaHKi7q1rn3zL1V4aKtMf9RdNWoKWENSFnFq7XSFzjveJF0S4O+mLesw9JOiXiJDIde4yZcXY24+q2YbmOiLGs65qYWp69eMnRZIIbjaAXUtZ5RCxilKYNhNsFy/UR1nu8dQzC3RhLWRY4M6RS6Xf+ImifJkWtxXiLm42J6zp7u7odISY59YlKymz2SGb86O1xZVFRjXoWkBDoUsfIFqgGEvD0yROKomJVt9R1x3wxz5yKTUfAYF3JdDTG+oLJdMZoPGGxWubn2s9Z1cx1kdTQRgjW0vgRH/3097h9ccWf/7u/hmfPiJc3mNWCzjnsOGu1ZRPQNrOr2BSyR68InSWnXHE5Vi2ETNkVUmIIYhgE9r1xvHF0YSu4tph4P2azebVrsh3WGeGbly+ZjAuqymNTzDA42mtf+2P+IUG2e87QlwHKfGg92Ifut04q7+uYdcjWNkCVd+t6yC73pjXrbr/ebe1+c/leC7HHlwc0gDe86McOBpE7guwxON5b+vJ+GPUWRz903n0D8Na8/zbj8KC4HSC5ee+yNxG014EUDC670RshmkiOHUs4E2nXt3hbMxrNqFcNL1/P+dO/fMnNuqIJiaihF1imF4gN4FAyPx6yjTeLqXfyMCA9OS9i0J7kTiWS2jWpWyJpzXSkVD5BDKzapleuBDTStWucs3hvSSaBAxlZfvqTH2C+fEmINzRdZoHvQuLZ89fMRmPOT095cnaKi+Ccx7oCbwxtVJqgfPXNMz4OkaPZDMRQVBmGOzk+xrns2y8pZtorEaIYokbqlJOHuqMJYsmxbjqAZH1wNQJiMU6yU0jXsVwv+tguR9t1XPSu8E6UkTkBBLGW2fEJXVQUQ113oNmD8ejoBFuMMK7AuBKxFmM9Yh2yXlEUZSYUdg4NXdZcDKxjpBif8tO/9/cJs49Zv6jp1hF9/gy3WDIODaErmZ0+Yfbxxxx/0vHy53/J/MVz2vkVnVFab1jPHM1oRCeONhrapqPr4ubds7PY7w7lfX+orcYhxvaCnkGZzprnqmVtLNfG8J//4i+YTUdUpWc8q3ApbPhP9aD294j5KX2f3tFm9V04Ye0CroeE2bsIzPcVsG8r/4UIsW9X3umhv9UQdVfqvWc7B6p952v6C1V1b7Du9kUGG8J3XLIgYyNoxEjP2Udm9ZdECA3JtFQjT1JhtY5cXde0oST2O3tRyeSuIoiE7ULSuy/068tmQZeY16cMm2THBnp/vxADKdaIthSFYiX1kFEOqt0sSzFmO5xC4TI/ZQKm45KTkxltUF5c3OYswgghRq6ubzAizMZjEIP1nqKsWNcBY8EqrOua2/mSmJQuBBDBO98n6ASR1LvGpx5OVOJwt6rZ6cM7DNl2ZzSzEmpKCOaeppFS1pRijKzXHaGLeCcURfZQzM9NMgTYe1AaY6hGFUVZUZajbIuSbCMMIaIhkbRhiHn03m3GlenPG89mTM6fcvrpj7itI/N1hxGHtjWuW+NiSx2U29WCdjmmkAoYgt8FrCE6Q1saWm9oVeg6zfnO0uAoIWwYaR+cLNmzUYTMam+yRsVAVK3kdDxdpGlajIPrm1tevX7NbFTwZPZZDzGzsfOmjQR4y/jvlwW5OxEfUza39eGExBaFkb2/v60g273uQ5XvtRD7tirp2575rrx5Azr41jre7fwHvJG4P7bvg4n358rDc2iA3Pq6DwjX3Ym1QTgO9voxqugOseiO4NybtdoTEw+CTLIgywhfyJ6EGhiNC6IKdZO4ve1y6hTIcFVvEM/CLNGDVuSlfXAXZts+fdoX6NvSXigoXduiqUHo8M5gNJPE6g4kLH27Q+Zm7ywqStDEqPKcnsxIarm4nm8WQgVubuYYhLPjE8bTGdYVlKMKmiUiBmsMTb3kdrGk6TqaNuBtdr6oyhKhQ1PWEmLUTcUJiJqZ640YcDm5S+x7bPqFOCNmOYHnYLvpzY+EEIkh00t5VzAalVSjUXabT9lG1rYtoctZmcfjMUVZYV1BSL1HZtfRpZw4M6SEL3zPdJ/zilmTbXqqMDs94/jjTzl68hnP/vwXzOc1TiwpNJhQY1JHiIZ6Oef20nI+fUJIMW9EREimF2Le0LicTaCNiRjTNj/b3pg8rBVtWNeNZA198IwdsnP3l8Qu0rYtmMR84Xj56jWzUclv/fBTBuh9f87sLvoHpkbfJ5GeMWWQgLq/2D+IGu3cyWaODcfeQ5jtzdMDdcrOWnF/47tzdIvgb/58LPz4LuX7LcR4PHJ32GX+bS/47vdvOv/NPRkGgby1zTtV3V0wH+rLsOE8WNWhu++XdAE1srcw983uXZl6+8/2+/2BOOQJy0Jxt89b4TVoP8M5PT6DGTQjSSRiL1HAGIu3BSZ2rK8vmfmOk4nBFsLLi1uurhuMTjFa5U0ya9R0yEZwFWR3xd5m1efqUt3ukEVypuGUEqHLwjJ7MyqxW+NtwjvFqUKM2UlAlGjy4mbFEmMiJEhtoqoKEME5RdrA6WzEqPDcXo15fb1m3WT7WNMGLq/n6C++5Ge/8zvYouT49JiX15fZFd4VRD9i2SQW6yWElnHpGJXZWcRIzo/VdTnGCgWJWxZ2RWhTJiY2hSP2KUckKW5wnEGwpk/0KDkZZte2WZMTw/n5x4xKz6jM3Iahi3RNx6Jes1qviAqTo2NGsykYy7KuubyY09aRrlaqkym2tLjCcnw6oXIeL6DRgliSONqi5OS3/pCTz3+CpILl1y9Yf/016fI5McwRasTC9OScOYb1zYLb5YrVek6rCY2WxibqJKwTpE5JTaBetGgUBIuRzJ2oqqAJ491myuQNjWwXE9EsxJzDWIOSPWTpE2BqT1QdkqJdYr5s+fLrlxiF3/nJT3hyNKJ02ebIZpwnZLCV3ZvN+wlJBugeZd+Ue2DBHwSCsl1Xht91r62dFUDZO7qRzFnC7PTjXq+2gmyY+3f6cajsirrN+Tt1fYjyvRZih8phHeBN5dup3W8qu+PuXV7YIQ3rUdcdHBn307Zs29m/YH9Hd8cBhQHjv9urQ40egCd3+jJM5t15k+WWIhLZcCaKxVmHIqxur/HSUfqCiPLy4oar6xWkAoPrd9EBTMNmBUgFg/jNbSS0hy110D5EehdyQBIphV5LUUgdzgmFFUpraELK0KHkAOekGaZL/QSOEaSLWOtxzlN4iAlEDZ9/ek4XLkhxRYj0fH7Ksm65uLymKAusd1mQp0CKinGjzD6SUs8AnzWE7QZk8OK0vT2Rvd279poZkuHURNbEomZb4JCjbQu4gmDw3lB6jzWeGJQ6NgRXYiUHdGcNKrv1G2dZ1SuaLnJ5fUvXQmxzthvbdQQ6ugTrtcePppTFiCSGpBaxJaPzT2B2TiqnpE6JV9eEywvCzSUp1kCO26vGU3wIdF2LC02GUp0h2gL1gDeoWAhZuGjIIRMalRRzvjPpY+tCShlq3ehJO0LMQOYAs/1LztRTmXUju8mrJMCSEjR1YL1qWC5qrq5vORlXlG4wom2FymbTtpkVO9rZ3l/b7e69OfSA3fzevH1o0Thw/rCRfKjsanR3Nb7d7w8JJhW2GuyBev9WiPHwg3hssN3jjJFvPlc2W6fHlwehyU1Nhx0rHlX3nZH0kADbPWHz/V389O49D1jcprebg5tje1Xs3QA7AuzQDi1rNlkLMuRYsRygGxRW81tm44B3ngRcXM25mTeoOgSLEPO10vXV2r6enV2p5ttKO7elmmmXMu9dTlwpkoOtHRFnLIUx2eEiZY5BI4L2NrAYduwlaA6qNYozgvcOCdnZ5OnZMRfXa9ZNYLlsNsKzbgNXNzdMphOmswnOGlRjTvHiJ2Rcq4dWrenZS7bPLdtszBYSZPs5MNqo0Aswyb9rD7DKzlLZP35rDIUrGFUVqmQi4dSRJi6TJXvfE1P3daMsVyvWdcvtfEHhRoDt7V3a84AGQteg5agfyzkZpXUl0yefIKMZQTyhaYnzOfH2lrC43WQcyPHLHpMUpyAha4tYS3QevEFc3pBoSGgX0dhbOlXRmBCfNxbWGlLTbCZh0s2D6IWY9HBiD0GKubM6x83Yzc8n0raBdd1wO18Q0pMNE45u5svORnFngh4mBxiODwjH9tq7HsR7v+/Vp/fquysQDwm0xygAu+fsmgU2Pe7/u3f8QCUfyiz2vRZijytv2GV8YC+Zb1sO6Tl/E9fCYcG/e8zcMfS+S9kdyPcw8f5LFdPPK9muKRIxJoI2XF+/Zlo5nLFYN+Ll61surzrgKBvhN8Gk2/VIBgne/+wKT9PHXGUG+n63jYAMqVUSZWkZlY6qMEgKGDLLhHeO1MW86DuHMX1AcFJCiqSuIaRINRpneDQlXCl8/OkTbDXmL3/+y+xk0Ws0L1+95rjtKKsRZ0+eslgsWCyXiIbNDyngTEHhXYa4egGVJDNZaM87ObDMDw4aQ4zXEMxsrcXbrLkmye817byjqiipyoLCey4uLkhdi5OIeTqmLAsQKFY5DCJ0La9fvSThsa7kk48/wZoSb0sqN2atNbfLG5brmtPZKaUrSUmIWJJzFLMpP/nt36YpC9r1ivXVNe3tLe3tguZmwZEtSES6pLy+ugDnEYHVzQ2dOpJaQukJpSMVgjNw2yyo20hUIFmMZAFnjMH5TETsioK6bei6Lr/rId2RJsSaHJNnTYYgkY1zx0ZV68fIoI12XUtdr1nMb4kh5O+GJyp3HevfPn8GW9TWSHd/7uweg+18fZOTxYOa3Bvm9EYQHXDo2K3nMW1+V+W/ACF2bw/y6PI43HYgC32vJh6ocWd39J0OgkODbve47v0vG0GwAyzu9W3DdbAHRm6hh516e5tBtjGYQRnIk14zAZCxCrEDbRECVTHCOc9yFViuI3WrRLLwy2aNHBM2CLAthLO7S+zTxm92vENOrXzM9mwfRjITR2EFb5QUAkYjluwI4oztufliL4Azr2PoWfJDVKwPWO+pnGO1XjM7mqK24upmwdXVLW0XESIpwmq15tXFBUdHU0KVY8XWbYclZe0sKVXpqcqyF155zMWUAdONtitsnGNC6jkDYySEsBFmbuJQskbWZ2DZvC8rFg1KExtiG/HOMa4qRqMSMTkgGs0pZbyzqHWMpydYP8K4Cu9KUEMKkdVyjobA2JeU1mPI9GLRWEw1ws9mVKcnqC9YzVdcPH9OmC9xIWCsx/sSPCRnSZMxISVi20IXEXH5nLNjViYSicTU0nSBLkRUDTLk9OltviFkLknjLLtByRu4QqBPZZ21us0zlSzgMJu5oJp6BxlD6FpC1+ZcaZpIGjdEv++7+gzz8L4mtLWBDTDf/nX7jmGHYrneJZRnX4t8wOnsgCB793bev3yvhdiHCJg7dP1dw+VD523Pl4MKykM7k8N19OcekJyPvcdD6POD174BQxgUrl3Fa+vbt+1jHri7/dd7Qm6/MzvX6J3z8srL4KIsKMZAlxpCqDEmZXhODPNFQ9MpXeydMjTHGw1ruQxrUg+l3e2L6bUu3bMH9O32KWEsSumEwoE3ECRlm51mZ/3Uk8623RZC1T7ebXiXISYKl7VH03YUtmIiyunZKctVTYg1MWUh2nYd88WS2dERzhdU1Zi6vsnPQbKPpXfZRT0volmDCjH1iFUmn919qdkJRXq2j9zngb0kie6kc+zfab9qp6jElPkVC5+9E723xBiyzRDFWYv3YFzJeDTG+golB2yHEGm6lrZtsNZQlaO8cdD83JMYfDXCTSZIWWCNJcXA/PUFYbFAmo5SbIaUrUGKktQvhClFiIpYybbH8yfMmyXa1cRVRwjZKxFAVEDyvYu1ID2rRs/ksT89s7ATGQSY9Nr5nfHZD6jBSUSN9MlUQz8PBk1+p94HpuCb15T7l26JB7bLxO7ofZMmdEjzekywst6p+23C6aG6v8vyvRZi32V5nBYGH1wT+xYyWe4uSm+q684W8Y2CUjP8tqdzfYBBuoETzdDfHq7RvHA7k7hZXDG/fYX3Qll4YlR+8cVL6mAJQBsCKnlhFQuiFtGUF03y512mobwObQWo0C8OIhgC1iQKA5PKUHnwVrEKNZlj0ZqCxfyGZd2xahXnXR/s7PBFuam36fJiK4WlHM1IncEDP/zx56zWDcgNt7dLxHsSwmq5Zr5YMZlM+OjjGcvba1Ls+hxoAe8Mhbf52fekyXXXYazFYvokjVlw5YzMSlGWVGWJt26Tpy6EhPU5Tmx49CBoEkIbe4VVOZ6dMBoXTMYeESXEji60+IHZ3sN4dgKmAJMJmC8vr1nVa9b1GmMtR9MTzk9PaVYt1hmMF5J1VKenjM7OWKWENUpqGi6//orls+eU1zeMVVitW0xV4EaGy5urbI+MkbGCYHHVhCe/87vMnz9jcXlBfTknxux9apLi+3etxjKZjFGyJjlfLDbjYLMLM4JxLqMC0ruKDwiBZsaPQZtXNaARJeX3ox40EUOL9oHmeTznpzsQC7+NVHxnZuxsDu/MF/Y3x8Mc2oX83hbTda+1N8KJcg9O3D3/kOZ39/jfwolvKHc1scfEUdy9/qFrH3qt921H+ey74+BNL+5RfT5go3pbuQvsoY/U4u6ecmerdyheZFdy7yafuG9EVvaF5fbLXbBy05YKhtTDMh23t6+5vHxBjC0xKnUdeXG1ICbfs7NnOiXpbULS19FjLb1wGnTE3Vvd1xZzTBo4iRQWRl6YjRyVVwyRRdvhbHZDT1R8/eznvLy45XYZMCbn6rIu8xoOAm00rphOxozGIybTKZ0qsdczn378EdYVzJc1G5FqDDe3c8qq4nw65en5OevlLW2zxo88k/GIsiz6RdVmXsMQMo2U7e9OBondhxIkJYRICqlPsCoslytG00km90UxOsTVZS3MGYN1jqIaAUrddLRd1uyUTJPlfURSTgvTtB1N23C7bFgs1kSNYOD09JTRaAR9ShQjFjUetZ5idkR5fEyrCbNeU99cs3zxnPWrV9h6ReENCyzVaMrRk6eINSxvb6nnt4DBFiP88Rmf/NbvceFHzNWx/quvSDqkvMxQqYigNm/AUk8IPIwHEVAzOM4YjHMMwfEJepi732Xp7pDqA6GBHENY4p0hdDkjwm7OMO3pvQ5kSdobe5vz72k2O3UNHWBXqOzvVh+yXQ11fxtN6THnPyRod/8efv9Qwu17LcS25fF604dt7cO1+13tWA5h2NtG2REwdwGK/q8BTtQH7vTADuHQU8nHdE+mbfamOxlxty4amW6qadbU9bJ/PkIXYLUOhOhRTO9JtrXXDbUO70dE9lYC3elN/4D6a/OOWbSjdI7JyDEdOQqb+9ZYwVmDTQai4Xax5vpmyWKdFzmR7P5urcE5g3OW0ahhsWwZjWpm60AyFpUseLuQeQizvWbbt6ZtqZuGtmk5OT6idNDUjsIbqrLAWUOIMfd5WDCG59prEEqPaGV//J7xo6MsS6yxxJSZR1LP9JHzjG2JgI3JucNsH5gcYiBqpj1GTCYJ7vGuAVaNMVNZOWuxYhGfWVcGPsyc+ywT87YpUU4nTE9O8FVJe7GgmS9YX1+T1mtMjLjSgXOIL7DliNIItVn0GagFKSvcZEZ58oTx2ZrqckHbKap93ByDs06GmwcBFmO8Pwb6cSw9jDiMT92MnexEIxuVfkvoaxSskRwCITkVy9YDcbeNwxD74bn50LoyCLB3EwDfZm3RO315CEJ8E6z4XZfvvRDLj/htguTxNit4u/ay80r7eg/vpN7VXvcme9nbBuJWMNyHLd4kyMTc3yHlL3a1qzxxhvxTu84bw1TVXutJen+ybs7brNbbv6XvfOxXXisus5Kr4h2Ebk3brJiWRc7SG6BphaZLxCRYZ/t3oNAvypKGyZcw4jaaZNppOzuZac4z1mchFhRSzaSa8fRswvnxCCuBFCF0BU0KtAptk1j0UKJSkZTM2BEVCQpNBAKvr5Z5gbOWclRii2zjwVgUQ+hySuXsOJDFaIyR6+sbUgz817/3U2I7o2trvM2ejCmlPowpaxfWWNCeSYSeAJiUNVqbwwxSTCyWK6yxuCqnZEmaiCHirGCNQ03C9P+KomA6PUKNzWlekqBiMTZra9e3V/0zs6zrhhAMzpV89NEZTdvl8F1JXF7f4F3BZGKxhUetIwA3qxXT01M++eEPMZMJX379iuXFaxYvnnMSOkprsjt8OQJfEERyWpWuI7QdxliK6RHu5Jw4PmL29HOmFyuaGrAuv0cT0JgZ7Luuw3Y53i7EsDcOUYXeZjjMoIFsuZdIefzEzQDKsG3KULW3OWDcGWE8KnMYwlDN7vyDXNej972H5rre+X337/1KD8F7u3+/tfXddWzw3typewjfeFv5m4AVv/dC7FHj4TtW0r7NC3rM4HrMQNgoRLsQ4Bv79NB3B47vqmQH+vNtjbkiYPoFxfYLh0ZlMb+hrld0MeD8lNtlS0iWLmR7UNKcClI2GYV2NBIGB460+X6HxzUHCKmCZBePHOOqlBI5njg+fjLmB5+eINoRQosaaE3Hoqv51bMXrIIQTIGqy7RYbFO9bFA9dUTN6TvCKlIAxmVexhglxyhZmwk3eixUEeq2Jlw3fPmF5dNPPuLp06cs59eslgu6rsVYQ2wTUaEoLG2IKIK1jmTTnvaZekeOrutoug6xFu99XkxTtucZBauCt56qGjMaTRiPp/jJhMXyhtUqoXhUIk0MPHtxQVlVVKMxp2fHjMaTrF3GyHK5ogstIXSsu4ArWnzTUhZF1jJTy1os1nmqUQkOnv31X/PNn/8lzOdMnWHsssbqpkfctIHnv/oKJ0q9nNPVNe7ojNGnnzH7/MdIdUqTGupQgIw3EDeaiJI2gRd1XffCPtsTMzKXd2didrT1Qdkygg5OHgy7OJO9XlUxVnBiGBXlJkv4eFRusgsImjcnu3OIh+CM9yubuSZbOrW949xfB95kNzs4jwe79Qfo93cl0L73QuxDlQ/hpPCYWI3vsmwAjEf14QAO+IBg28iwYUzvft67al8T2wIruvf97t9mF7JJYDEkERbzW7qu6RcRy7oOPSde7wGoCsSseu1Zu3Kvtw4dQ5t3WBB6m8IGekTwDkalYTb2TMcuB1sHw3zdUKyFJDWvrm7oMGA9qiZrQb0dbrORgJzmpF84o0IXUh864PoHKBvhpwMGaPO9hRi5vrlhNh0zrgqMMYTQ0dQ1xmXNCGOwxoEmUsxQpPbUUyrSO3+kPnash8EG+6bKkEmshwEdoyrn/iqrEWIdtihxocLFljZ0KEoXlBAUExI25Fxg0t9jCBHnLEKBFUOHISqs2pYoHasu0mF48sMfU1ZVfl5dZHl5zfLyCpqGylm8zcTAfjKhiB1d26DrZfYaFUNwlursnNknn2KLKataWawjuAp6fk00k49tIcEBdt0ZvLDRtrZQTf+M+iDyLZ9ito+JCsQeOjSm12QzpFgUvg9G3xuOB1GgN5d3gQrpx5g8ON/f5ujxxuN37uXblofc9L9N+bURYncV7a0rwluu29mFfAh3/UMaymP68DbX+7fVqQd+G67b/Tx0xd1z7/eBLUSiO5+bY3fE2O4E1n0exX0AJP9t+/M1ZaFijSEhXF1c0LZN31vDYtXRBkPQqoc1e0bHLLm5m+P1LuCyFW9b4TFoY4NNpPTCeGSYTRyTscE7R0yOm3WDXygBeP76gkAB3qGaY49Ue+aP4ZEIbL3TcjNd1yIJRpMKg82a15CSpBeoxmWvQVXl6uaaqnSgkafnp7Rty2q16PlsLc57xrMjhJxKpa5bnPW9fSYLuBiz2zmSNTVrPSkEnLO5GlUsDucNrnIcHZ9mJgwRsBY/GjMySt28IqVA00TElSQsXcxOH1EbhszHo/EY23uYptWKDpjXDetkWdQd4kv+2z/4PaazKTEEYkwsXl+xvrxC6prx6TGlc0SB6vgIbwzjFJl/9StcV9ApLKxl/MknnP3oJ4TqiOvbluvbBvwUwhpih0oWYiJgerqplEB3nnU/6HvG+sE2mceRiEEHZuhB2CfNP5J6AUb/I3iXbZamh6U3Ic5yaFv3fmWYnnfl8I7Z7SA6kq99u2v8mza931YZe5Pd7NuWXxshdnddfRcB9m1bfoxHzhtreAOk+Fiobjse3kWQHtLGHu7foGnkRXrjfMvmy6HOvo+HBOtdOZhRtGznEWOy+7cTiMqzb77JMJBIn2MLuiC9hx+9AT1kIZQBQRTb76whmTvwzUb50+3fO7cvAp88PeXTj075+MmM6djjfOYcPI9n/PzFVyzWNVeLmrUW2cHAKkImQ9RNAHfWcTbCSdnAWCKGGBTrDdYZKvE0XUOMgRg7knb5mfT3dH07J8XID37wMZPphBg7VqsFJydH+LLMcFdV0HaRdR1Zr9e9EwJMJhNUE2JM9igsPN572pgIbUAJSJcoxo7CF8ymM6xz1DGyalrc0RHGFThRXn4zx1rBWuHzH/2E28Wcuq559vIFZ+cfMZlMOTk6JjTZtubFcnoyYq1KrYlOHPWqwaTE7//dP+D4oyckgb/6i79i8fqCuFjiY0RiIFkI4pDCg3WYPjbMaA4y1/GY8aefMP30B7xcGS4ullzetLiTj0j1HFKdBYcziLPZBtgzmaDak1xKTzFlspAzZsMziRGMsb3nYh4ixpjMaqaKcQ7vDN5ESDVVOWEymTAaVZmjUWSj3G21/rdOs0eXe2iIZH36bXDiobXk7vpwbyP+aHXgMf3+8FoY/BoJsQ9Z3v0h7wqv/og+DkbQnVF+6Pz8vb7xnP0e7A/yQVTsXqePmFn7rrn7x++70T9QBw9pYbvSIwfgCgZrhKApszqEjtVySUgBY7TP85XZz0naE+HeqW9HeEr/IA5qqJvVZXCTVgyKFTg7m3F2dsTxyRFlqRibCXPLETRdzbpe5l17yN6SIqnX5AYnFSVzaAhbD7nc9+wpB10IiPWZGMJkmqPBiy5nBMt9GqistP8sioLxeETTrHIwcgz4osTZ3oXd5AVigLpCzMwazjlSjBsVuSgKTIwYVbxxlL6gLEqKomTddrQxElRxZZG13dSRVLLbh7WU44Krm1vaNmCMp/AlIpblak1sI0YthfGY6RgngtVEE4VyMqaaHlGNJxhjaOqGqxcvCIsFJoRMqaXZjiW9i38dI/V6RQpd1twMTJ88oTo+xowrlpcdq3WkbQXnpwRxqLgM2Y5cTv8iLm+GhncPm1U5r/9Z4qhuUYscPL89d6PDG8GJxbvM5KJdovCOqipwzh1cOwYw89tKsoNTXw4Lr90Jeh8u3Aq/wxvnne83fX+wB+92DweE6rct328hprq/wuaDj758TyXfOXawjruHdjQf6eGfPG7uAptv6cPmzJ1z9c4JCht+oEfUtx14OzrPvUt17+NAh+7XPQzue8Dg4bIvgLe/333uSTXT9RoDkvNkxdBQr1eICYi3ZD5Xm2EezawaA//fbv26N+Hu7CF3XPk3XVOyfUjBGXjy9JizJyccnR0jqSZnzUz4kdKFNU27ovAOG0w/0XVje5ONYOw1QOlZ86VngiCRYmadsC6BmOwEZzP/oSERU9w8p5R0I+RijJRlgTBmsbih61oUKKoKqyZrsuQ4NWMszuWF29oC6xy0bWbcTzAqK0yMWFVKLFVZUZYVzpc0ixVtSkRn8KMRoWvRpkaMxTqL9Y6iLLOjSNMynR1TFCNAuL6+gQQWi5eS2WSMMdIzckQmxyecPP0Y4z0pKM2q5ur5S+JigQsdoyKTOycRTFFSjCfUizmr5TJ7JoaAFp6Tz35AdXYCZcntcs5qleg6h/czonjEOKwrkJHDicGqUK/XO7DzzoCWLW0yvS0RGfLa3Z0A+cf5XoiJEtpIUXiqqspCrIcgN6EpbL15HyqH1qFhCN1tf7vs9Bfdmdr3YMZD0+Hep+5cfKcTm483bVt15/OAEH8D0vQhyvdbiN3Z3Tw8UA4/PHNooPbnH75it63tLi3v+rXvjW6ETnqHl7YvzHY1CtmyYYs+PI726hoG3/4+6nCLd+CEA5su2fltENRDGpPhhNQnhkyaSPQxSJoYbE2byofHw/Z+Usp5m0Q7rA+Edk1o51TekJJDotAu636XbhFc70ghOQOwxn7xMf29DxpWn+UZA0QiIUN+xiCavfJUoTLCyBlmleUHP/mIo4+OkXFBChaVQNIWKzWf/XDC7yzOeP51zV/8ZeA2BOqiJPQekCYZrLaIBJAOsYGglqCWlHrHgB42bboOSQlfZKcNI+DIUBwp5bxfxlEWFePRpM/5BUXhefr0Ca9eX9C1HaIOITtwtG3LZDbJzhUiLFdzVDzGWZouwKohBEFxeFFGxjC1I6bVDOM96xgBiyk8flrReke9XLC8nTOeThmVBmuVxc0lhIBJUC9ann31ipgS8+UtJ+cnjMoJRVlQL+YkaxHnqCZHfPyz3+Kjn/wmz25qRstAfXVN980LipvX2GZBUTp0PKWzni4aTnyF0TmxXhPaJepL/NkTfuu//98x+/QHNEb4xYsrFssRGs6p7JjalETJaVnM2qCSE38iBUJANQAxu9Vbk2FDzQusugJ1DrE2s6BYSySHf6TQ5dAGb6kqg0stJmZHlOlkxGQyyiiCFZLt33U/X1y/4XqTINhDT3aUqXtzc3cqDef1Nj7dvVj315HtmqZbwb2zrmw2nHubeCVzke5sjXW3/kNrxMNL1IeGEYfyvRZiD8qgvhxSgu/uFQ492I0jw951bxIFdwSpHK7jDRX07R6C6e5oLw/Mg3v3uLOpussW8Jh+PXTOrlfh3fM37cn2OeRTdW86bTrV34/2k0qMYBKs2jWL5U1P4tvz1ZG1HiF7MypDYOq2TmX7DAeBO8xr7TWVob3Uw3SoYklUZcHp8ZjxZIwvK7AlSUGkQ7AUVcuPfvIZzs8QPqFb/zm/enHFszogtgAMJLvTk4ARxfbwoEpABwd/1UxPRMwMGa7IbBlOskCXzKyfUsI7y6gqNtmnFcWY7E0YVYgpi2wRgzHZEcXYjLU6n7MpixHE9DFjKtkdRgQxjlE5whclai0xdjRNg/VjprMpKjlZKDHhnKXtGlJds16vmE1zbrDLqxX1usZ6z5MnTzk6nVEWY6pigmggGkMwhovVChWhmkw4OTumvl6wvF1w++oVzfUVZr1kNJ1lBpKiZHZ6mh18ukC7XFFYR+cdWpUcf/IZWpTM1w1fP39N3YJKSdIOW42xboJzOTN3jJGQ0vZ9DwN045W43fJsDFnZGwSMy3/2m1IjEWcShRNMm1CNOQDemJ6xxW4GvYhs0+PsTabDM0v7Dc7gXCIPiYK74MLuNNvZAA/o0P7s2P3cmzV7ZpDd8+QNeuSho/ta4Zv9Av4WThzKYQ0W2H259499d515//I21/ht7MY7duPgaHvDg3trxfsa8HBMRBnYCowISXf6u4PVbzaAMuzshkUYjBjapma5uAW2Aimfk59B1rd6KqH+nLSBEh/QlgeNUMjXJnpvSBBJlKXh+GhEORphigo1Zd7ZGosYizMNH3/8hPH4hFGp/PzPXrLslrx8kfodsEOS61uPQEfhXW/XghizUMp9jkTNkjUFRQo7+BgQzZDvS1ENOGeoqgJjBI1DxmpwzkGEEOIm95U1duOJp6o453LAs/SBz2JALGIcxoL1BWVR4ZwnCGjMRMRjI0ymEzpNm6zGxhjWdUPTLOnahuPpKbESLi9XdF3AFQVnZ2dUk5LCjyj9GI0tyRpaMTTzK8Q6qvGY2WzK6tU169s5q5sb2uWcsq2p7AmrLuDIwk5TIjYtoW6ojEW8h6picvaExnqWdcvLV1e0sRdicY0tRhg/pnCR0IVMWhxCTmS5AR8GuHAQXnmkbUZ3r9Vj7AZtEANOBG8i3iZUshAztiet3jzjvkrtBdnOtHns6jBsvA7Nzl2Wlrv26X2Hj31htt+D3Z7c2YzKrkAdtLY3ezYe6uPfZHjR91+IPbgOP26Rfp+l/Lss9zx4Njukdx9Eb8Sihwn8zmPtkADbbzt3O7stp5Rhxrua7GBX2xKM0ruFGxbLBa9ev97UJyK911efH0oMCdujtkOM1e5uO9dth9Wkhy6z7SlrOyKCmIQ4RVkzqiY8eTqmHM8QOyHoiC4ZrGTyXTERMS2jkfJbvzPjf/w//i6nn5W8/L9ec3mTiEHBeroGhIS3wo9+8AmOCKFjfbtkHZQ2Km0I1KEjaiTGhrBucq4vY3E2P+NEtp1VpWE8KkC7DJumRIoJ5z0xRa6urhiPj1GybQ3N0G4IAWP6mLOQsp3IF7iyYjQ9Zlp6ps5T2BGpZ2YviwIRqArP6fGMb24viV2Nho6GluVqRdeuODudMRmP6FrFeYNg8YVFRLm8fI2zFePRMYaEH48x4zFnT57wox//hJ/+5DdZ3Kx5+fUzXn/zDT5F1EAlUEUlIHRNzbOXXzO+nbK6usK3kYDiZsdMPv0Mc3xMGwvmdcPLizki59iqIKzmYAuMlJRlR+xaWqO0dcqbhkETzmo/YrdxYLqRNnnhTtYjbpSv0JzVYFJ5TkrBrl8TtSNvVuzGbT9TbmXWE+mzBOzOGuGBucidObs7//ccMuTg+bvMOYc8E981dnX//K1mCbx1XdnEIb5jm9+mfP+F2INlDzTcs+f+jfXgHRu9F0fBLkT3OK+eN7nW3unddvv2UF28m4A/7JmVBcldSHO/7uyhmDSzZmSngbrPIJy1NGsNYmwO8hWL0ewSvRFiKfNyDMki0axpqYl5F66K0GsjmvNziWZUyZpENRJOTkpcUSC2RKkQU5IDqTtUG0ajQFnUtG3Dz37rlGA6nt8u+b//P/+MxapFbUUMgGaNR7F8/PSUs0lFc3NNo5ZOYd121KElpEiXcu6xHkUitIHQBULbQSqYjAqcVVLKQgzN/H8pZKb0UTUGGRJgtiijHMPkPGm1xphBQ7Ak+vAE6/DVhNIXODzRshH2OSGmw2gidS3S2+JWq+y674uC6XRC13bUbcdkMmaxrmmaNS9evSBqxPuWrhOqwrMMkbBaE4/OKIqSUVXy+vkl9c0N7e0tcbmkNFBZg2k6JpMJHM0wT0+Jy4ZOoVTDWoXRZIo/P6cRy6IOzFctqAPjciJv6+miErqGsL4mdjUxhJz0lDioRzm9i7X9ZmiYA5rf9QAluoLkfIbkYqR0BePSMKlgfVvnvHI924oRwfaM98Oma5CJA5w4xEu+KR50d+GXXejzzhy7v07cx5weEmBvFUB365bcwmNjvAbY/rFtfojyvRdi/0vTpL5Nubd76QfQVsX/wKr8ruHsTrkrZPavY2eHuKMx9hfJzmUbBOee1W73tyyIUoq9HSZuEjiqZq9F08fzqPS2nZ5ZXDSRdGBjzw4cg5E6JbJ9qW8l74xN9hjsPeONgLVKWRgmE58XJuNQPGJGfe860BXe5RgmTS1Pnlb8NJzxX//BT/iTP/kV0LJqI+oETYaIoQ2RwpecHM0QL3RiaRXWbUsTAkGzEGu7kFmwgK4NhDbQdR0ptEzGBd5CSqF/WNonpqTP0lwSVAgpEDWSUmKIU0obuNSgYrINTSGJoajGlEWFbRNqlCQRUrbxCErsWlLvfGLowwKMwfsCay2rWBNiYDIdsawb2q6jjS2+KjC297I0JV2I1DExqkYUZYmzjnZdE9Zr4mpFWC4pNOEEbEhY53CjiuLkiJvFC0xK+ARLY3DTGdX5OUEs8/Wa20UDmjcmKqDWgVhiUkK9BtoMGQ9a2AAhGrtHNaXDXICM6dpeiFmPxjxQqqqkKqCwgTp1WYgZIYaISNbsM7mw9kJrGz8q/WZxN/D/rWV3BzscGuo7tE7ow9rPu2hF376OtwvdD12+90LsuxZgf9NCcjswhwH77ojf2wfc2+9od2+3J8wGt6hdScUwjwZ2igFyTL2NbGDt2RrX97H6PlmhJtLmfNlQ+EhPomutzVmUBxuZQlKLDgIPkGgZBFlKOQPyluTYgtp8vNcwvDVUhTAZG2ZHrmfDMCAeyywLQo0Yo8SQbVJl2aKp4fNPp/zR/+bv8PKbV/yHP/2a//AXL3DFhBgNMTmevb5h4g02NPzk6REaAykmChsp/KAdQdCUveFcgfcVIllA315fbBw66nVOUgnQNS3laIa1JYiniQkV8KFhtVr2z8oRQ0SL7MARU0OXlCSJOignZ085G02Iz17hSwHNlFapa6mXc64vXhPa9cYLETWMxmMKr1xeXxK6iLWepx894fJmTt01iDGcnJwwHh8xGZ0wmc5YdB2LmPjJ7/8+s+NTQheRrsXUDSyXzF++oFitEBXKUghiKIuC2cmMl3/+c7rlEmkDTCtmn/6Apz/7bYL1fPPiJb/81SWk7JkpAM4yOj6lM9es1woaeo7M3uBnMoRofKbsAslCrudIRATxHlNUmGpCxIN0CImn58eM4hzWcwqJGQRXaEOOxRMRlssFR9Mx3uYwh8EhKc+P3nvwkXDiZjf4iPN37eQPBTq/SzkEJx5s89C13Ic1v+vyvRZiu4vibnlnGI+Hl/WNJvEGGODgdY/sw5sGA7AhMH1MvY95FlsBI/e+P3g9W23pTeJ0uHbw+APdmKP267uzwwOwlqSBlCJdlxNceufQwucUH2Jwvduzis1u9prXp9yW7V3pEyKxn0Db+xeEkCKFtYCD1PRiMAvaUeUpvIHUobFBbYexQ9CxR/Ggx1jTAQ4lUXjFpo5ilPjf/3e/y7j0XM9v+bOv19Tq8nmm5PXtCmLg/GSGsxbnJN8rgaRKtu4BfdbkqJoZ3K1lMvbQC9zY5ntSYFQVFGWBGEcXet4+75lNp1zf3NA2LSgU5TjTTCVQyTRRqjCaHTE7PmVajLjlEmsMXcg5wZaLORTZUtk1DS5GnDH4osKYRIgtL1+/5uzkhLIqkRyghnOOajLi7Pycqpzg7RhXFBTOM7GOH/74Nzg6PgZVllc3LF+/ZvX6FWl+S+waonEEp9Rtx/r2lusvv6Rbr7ApItZhRhP80SnlyTlgeP3iim9+9aLXtFqKouCTjz/iyPwei9eGXzVf0i3WW2cfIxuGDnq7zU5mFRCD9R51HnyBlGOIWaN1Enl6ekS8WVLfrPBGiF0kxGxjExE0Ja4vrzg/OaYqikwf1gvQYcO2hS7fDufJ9uCDc253Tg2n3oXvDntf61vn/bbu/Sn8ruvg30T5Xguxt5bHqFH6qHHyvSjvjj2/j555qG69/zkIsgcuUdh42RthY2CPMWycFKyzPYImiJUeTjQYzQu6qCIpa2ya7rOZDPI0e54NAcfDbnLQ9sB713v/BTS2kFowg+HeITiUEmFMjjqaYE3EugZf1vz0szMurm752RfnfHX5DUqiDYpGw6rpuKLmYllzNi0pfZ+TrPf6SxoZGBaz/aXLJjUDhbekmEghs/unmOONvHNYOyRzzOPXOkthc8xZ6rHJsigzjBgTIWoW/q5gdnzKaDTBG5th1V6TiCHQhZwrzDkHmtPLaFKs9YRY91yMAesc3vs+t1jaQLbW9h6RQN00dMaCLzl98pRqNEZTYnlzw+rqmubmBmkaBo/W2P90bUd3c4O2vU3OCn4yw0+m2GrCetlyezFnfnEDsUIIOO+ZHU+YmmPCegbGs7cED1Ci9FJri3P3EOMAIzpwBepKEMVZGAHjwlJLYh2a7Bd7ZwOdUmK9XueAbE0bB4edRngcRcDOJe8iF76FJvZdxW/t1v9dCrlfXyH22PX5wDnv8lIfgzG/y/nDNfe8+d5RQL3VTf+9yhYKzH3ZHhvsWtyZujs6Xz5nuF63J6Q+2661hrbNi4AxJsOHSVHNgsr57CwRYo4ng2zzGu7L9HmPNsJLIcYMtYi1m2VEU8JbizcG7yzeZWtZ13WkdoWaCijArMn4ogH1KOP+ZjK0Z+wSVyU+PYe/+9ufEgz81deXPLtouVkEmk6oAW2VP//qBb//k095Wk6wLiJJ+6zLoX92vZdZ6jYoWFHkBKFRM5tIF7M4dtZunFjyuqxYEYz1jEYVmsCIoxpNWdUd63XLug74yYjx7IjPf/xTxpMJUjd0XcvIZBf+FDNbiPeOyWSCv7mmCx3dqkEKy2K5pmnmjMaZK9AXntevb2jalrYNRJYsV2tCAEPgerkiFBXlmeH840+wvmI5X/L662dcf/MNq5cv8W1LMSqwriRYR/KeAKyWK8q2RlJErGH2ySdUJ+eoG/HNFxdcfPWaxcsr4BRXQFUUTI8qdCE90/5WG8+mUNnEhmmf8iZvnHpXemOJxmL8CIoRyZWIKOOy4qOx4OloQg1dnV32UUQMpofXU4jUdU3oMmS8O8R3QcXHSSbZfDy0Eu3N4UcsVw85WTzWTvbWPryhzccef9/y6yvE7j3399E6PnQfDpzygFq/JcO5w/z+CGF2yCh7+Jp3eR4PwYkHtDD6xXV3EdGtcB5Mfpl7UImp5/yzFlXtGcItMW6zA9s+RYmSEOlJVuntXSlrVUn756aQYl5cQhSSgcJa2rbrn2ZkiLNx1mA0EdtIPW+IywUOl7W/YtTHFyVERigOZQQDcz2guqTwhk8+mvH3q4L/4X/1u/y7//gF//HPnuNHR4RkCSnx9fWC0bOXtM0RP/38U9ara1Qj1jqIYevqrYkUOtqYKL3HCRhnKYsCTZmSyxllkylLeh5JMWAM3nusWJwr6dpI12Xvx3I8YXb2hCcff8bHn32ONDVt06Ipslzc0sYaa2A8GlEUBYIQU04qGUMiGku9amnalh9/8pSiHBFD4vrmmtOzM7qo3M4XXF5e4e0Sa0qi81QnY47On3B5s8C6jnq+pJ7P0dUa13QcWce4nDCaHFGdfszpDz9nFWv06hlVVZEIaOn4+Ld+i3J2wmLR8Gf/37/i+uuX6GKFcZYUblnqDV98scQ1NyyvbtBoIPQ7mYEHsZcoeyNZLFgH3kM5RkYzpJqSfAU0nJ5M+d0fnpG+/PekegGhoQsREdc7dERCCH0aHAhd1/NUsueRO9i273rufdflIc3sQ9rO9n6XfZPBm9r8UOV7LcQGd9ZHnv3B2t0Vh29sf88B4uHzD73YXQ5Aecu5d797qK194/HD3X58uVvJHTyfQVjtfu7i9cPZ23qsNXjvKApP2w3OHZnEVpGeiJaNK+9AfyX05w5wEbm9hEDKaTi6rsuTzGRBBqZ3lhBSgLaJpKYh2RVJLGIWOVOwld5jsdeY1AEeKEmmRHyiEuFUhN//2Q+4uVlz8WrON68jiiGJoe4SV7crSiN88tHTTFLrsgBWTb3WkL0Hs603EkN2aDEI3mWbkaaQnWBEQbPjjEAfoJuF+eAt17Q1XReJSTHeYZ3HFQW+qgjLBV1T9zyViRg7tOdtTCnRdiELsJS1whgBcThXUhZV1nKT4ouSajTBdAHmS7ouYPAU3lKMJ8yOjzk5O8semE1ivVjS1Q2xrqFp8SkzxosvYDxhcn6OaZYsFpc4k3OHRe8Zn57QiWF+u+Ti6+d08xWmixBXOG8prGBtyOEHUSEZEEf2Skz7QmwzRGQDJYp14EpwBbgS60uMwHQ85vxkxvOfL0ndGtG4cSyi30iFEGibBizZQzHtb0bzfLuvhT3WLvW+5ZAjxl172aHj79PGto79OLHHtPlty/daiL2xfIeK16OrfeRLeij2I9/C4zWxhwbLbhvffgf4SDhz+G9HgN3t51Cb9B4giuILx2g0YjyZsK4XfWCyoSgKQp8iXno+N0m6J8TyemQ2m5tBMCQ1hA4SLWKUovRIzA4kBgvJEIPQrBNhtcIJiGYXcSkVsQms39BKJbEoHjUluAlWBGtrxhL5+3/wU7o6sp43vL74a5ItUHGsouFivkS7jo+e3PLkbEphPaFdYkkb+DMTBGfIs60jRVHgnaf0BTGAJggxbIJ3h0cpPUY7fMYQWC6X1EGI6pAihyVEFcR4Vus17XIJmgmOU8xu/XlBblmtVlkARlA1dEEpitHGi7LtOlJMnJ89IVGQUp0ZWpLgvOfo6Ijy5JyzTz7j7LPP6UJitVpxe3lFu17TLVek1QobE6gl2YIwHjN58gS3KllcPCcYIVoD3lMeHzEPkYuXF1x88YwwD7hOiTpnfDZlNhOenI+5blbUYhF1qC3yA9N2s7nZsroMQk0y1Ow8FCXJVlhf4UcTKvUcH005P57w5fKG2Kz6cWHRAWZG6JqG9WpF9NmuuOuBK4MiyDCn328Ovuty9qA7/s7333Y9eNe6P9watF9+bYWYvgFPfs8a+TY1vu3qw4JscI14N1z5Ubudd9bGDsCJ0h9XttjJjva5Hxez63ixAz3qTlcUyrLk9PQEZ5W2XXN7e0OMKTthZMUFSX1AqcmbbIxgkqCGDEM6JSUhhID0ecZy3JJiDVSlJbUpc95Zg0alaxLrZcf6+pbYrHHVHJcibtpgaRBnSZSouJzFUx3JjEj2LDuNGCil4+lR4h/+wU95cnTO69ctv3y94MWiwfpsV1u1iT/5i1/w+7/9Y06OxlS+zPHXSTcM92ogkehCm7cySSl9ReEcIHQh5kSXvRAzCLFnwBeBFBMacqblwo8pywnBjUiaXcJdUbBarGhu50yspagKYtNR1+vMNRgzDJlpw/KPdY6ymmFtx3Kxoqo83pdY6/jm+QXz5ZqYlNFogjOO5XLJyjhOjeH8o484//Qj/vxPf86zb57TLNc0iwWyWlFimIyPGJ8+5fiHP+K2S1xfXPHVr75ktpzTGkMtwsVyxetV4tU8cPXNS7pFgbQGdM3i1SWrW+Hym19g5Ji0bihGUyIjUowkDdnZxBmwgtqcdHXjWm9M/+OhGuMmxxydnfPDkxFPx5FueUO7uiaslzkA3M16gZ3F4mKxIISWqrDZrprjMvany7DJeE848UOsZd+FjeohV/8Hv985/qHK91qIidxZi3Xz37d76XuD76Ev9npy76Uccv8f1Ox3gxEO02/qnlDYbXenV/cG1O73g1jVO98fGOQPeFXdFa/7f293o3uw6iDzZHs471jztlXEUJQVk8kRZ2dPAEPbtpTlCG0CidRn1+1tYn07A7xoekLWZBMhbL3mUMEZh7fgrSVIi5BAIylBCImmCaxXkYTBa4eWS8SXiLVYNwYzQaQAqRDJvHqi0nszKsZFyiJxelwROvivfu9z2j//ikXXsEoOotKGyM265uXVDUri0/NZ1gbJsUepzzumPQQVE0iMWJvAZNugsYJEzd6ZIohm9g7VgGhCUnZ+FDLruisLsGPEVggejYHQ5JgwX7i8E0gZN/Q9aTCasveoQDKCGpv5AjHECEYyzLlYLunaDlXwRYX1ReZLTBEfBWNKvJ/QtJHF7S3zi1ekxS3S5gSZznmcLbDGoZK4uXnN/OaSsF7TdIGm8NTGMq8blgnW8452uUa7hCaDSk1oWyQJscvaYs7b40mac4shLnsdWslCzMBGP5LsCqrGgS0xoxluPKGqPB+fzxjHGxa3l7RtRxczNLudaHl0NW3voZlchjI3w38Y9z1xdR5xe04fu/Nna0DY/3yo3HXJN+zM751d86adPU+XgfJtK2zvySDt15kNQ+m2k/tYys6ngsru1nv4fbseDA5gH0qMfa+F2LZ8aDz57nB6v6s/RDmshx3u2VY46N5g2b9C9wXL3cp30qXs1ix36tido1kR22KHotozeO/0a/hdNk30thyyy7wM4KnB+wozNTxREONZr2u8r4hpmTnrJPYkwInBLmH6e3LGkKwhJSHrbTlAWRC89RROKIwDFKvZfpGSpQuBugms11kLihqRco3xc4zJTPPGRbCTDC1KieAxWgA9a4MDV7RMJ2Ap+O/+3o+5Wt3y+uaKRTQ0IRFSousi37y+Imnko9MjPAbTw6mZYT4/n4TNSTRjQmLA9fY5Y00v8LVfihU05yozZMcZjZlRwjqDKz3JzBA3wdoRMdTEdo3GFj8a0cU1KUQk0cOX2b1+yNkWLSSTSZNTUgpnsOKQlJhf32QmfuuwvkJ8SSIRYkdhKqydYO2Em/ma24sLFq+eU95cYpsaCzhf4SQ/gRgbbi5fsrp+hbQNdYg0RUnjSxZ1w6qN1LctXd0gKedjU2o0BFCDUqEmQoSUPDFl26W4CM6iDtTQ2xOFIZZBjUWMR/0YOzmmnE4ZV5ZPzsZwdcnlxQva0NElJSbBDZuGlMds23XEGCDFnANOB2hXoWeMGQKfLQOm0XvqMjCIZlHxpvn9UNkVisPvu8IpT7zeoYotBdwAoGzm8u4lup3f24SvD6xte3n6ht/l3gXbft73ZP425fstxGR48t+VEOttLrmxx3drt4b3MGLq3nbqvkb1pnYT+4Is1zfUNfwM5z+kdemdY/u/bQa/3t1PymYi7fX/Tl17V6lidvqpCVQtYkYcn06oRieEkAODX716xXyxoLuZE0V7OCezVRgyc74vbE9ArtR16p0VBFXDqJwwKiyu9y40RCQGVDxNUG5WcLU8Y6qOkVrEdhhusbFGjGKrgPiAUqK2wqjHRUdQg0pFlAJTdBQyx7mWP/z9M+rwMyazEf/n/9ufchWEII5ohZfLNW1MTMqS3/vsCd4YYoh4YxjQqCRDBBnUXYsXsMZSVJ4uBqR/LlGzdppCorKerlO6LiEkutjQtUuic5ydfMzpyccY7Sgk0kkkmkDXtIS2JdUNXWFxoUO6gHZNhjWdslivINQUEvj0vKJbB6wkPj4/ZZ0sdYDbWmmTIN7hxiU//c2/y8nJ59RNwdX6lvb2Gnv7mvjFX2EW13gS/uiYwldMfMHZSUl3U6NhzmJ1w1It5nxG8dmPqJPh+uKWi2/m+c3JGiWAVZASkiPNI+YIwCPlMdTHWUg5Q6osahI5yWkHsdddXAm2RN0IqhOqJ58yPRlzWtU8qRper17y1S/+lEXdZfus8djYZdYXQIwjaMqQdBexkomcBXoHopytWzQTAzNsV3RDR7yZC5u3vZ0ch6b5/tzcn+R701F34fzB6DqcNGxAt8riZl4fLLqzdmzayjtl2RxSVAcL4KE1RHthqnf68+3K91uI3S0PmX/esZqDms8DlTz2NQyu428q9/HjQe1/RP07/Ry8AHcNzLkP+8d3v9v2sz/+mMaGOu6dfXdHmSfmQ96TeRIM973tY4aoCpwv0JSYTKbEpCxWa1IIvQbWO3BI3gUOrvgpGYaEogJ4byi8wzlDCjVbRvOsbahAVKVuWqzVnH6lAOc1B0SXNZY1JhUY1ggliKDG9bBVATLG2CmkhImRcSX8+AcfsQ6O//DnX/OL50sub1uWQRFb0SThq5c3fHQ043RSMqlGmW2DHn7S3cWBPo6LTd4wyKlTjMnwIkmxXlAjuJ5ZSfuf0NMjWTFcvn5N29SQEiGGTZye9562D2aOMRC7DmsdlfMs1zUhdDSpoVkr5ThnjLYGlquOmMA5T4sQukiTAsdPnjA7P6OcjFg++4a0WmPbjtQ0SIx50+UMLYl5vaT58kteffU168srUGgRqqqiPM6eiet1w/xm3nNs9uSXw9BLWbMKQXPwtiszkbPpoEgYZ0h0/VqcPVPFOLAFan2GGwvP0fGU0+MJJ15oF7esbq5Y3VyjIfYMHDnsYOOhuDvc+zFszOCWtf3ZzJADmsl2ouzU1yMTuzPrIZvSQZPEAIw89P2BMiAj+bqtEWEPDtzp893+P4S+sHts10P6A5VfKyG2u6t52yPaZCfevfADlw/xot6nird5AQ0ebB9Im3+g7Ozc3nAP0sOP3OmzSE7jkrMUZ8E0Ho8JMVB4TxcCSBZi21xiWRvb8C5KD5+I4pzFe4uzQtvGLUTSe60lJAuxtsHYiBiHKwTrMizn6wZvaqwWYFYYKcAakilJYkl4EMWaGWIimEDplU8/yl6Mv/uTcxbrRF0n1nXCOE+XEs+vlry8XWO9YzKdkroWSJkVIvZ50vp3OAgxay3W2RzsHMMm9UdmiqCPsxOsyU4MagyxDTlAW+Dy4jXStjjNzh+pf96FL6jXmfk9ho4YO5z3FGWBoSGFQOwa6rVyNClwzhFR2m5FiIL1FSiEmGi6wOz0jMnJEcWkZHl7kz0/246ubSEl1BiSFVqTaOoV6y+vuPzmOVo3WIRgDTIaUR0f04qlbjqWi2VmpTeaVRdgswvBEGJOmmp23OWlUMSDJNCooJEca+gQ60nWZbqpwjGbTTg9mnBiIuvr5yyvL2kWC4ixtz32MXqDUwhbaBDyWDEi+wv8nXnx8HeHdJj3LLvC8h28Au/yitz1cnzo+K4AfLDuD+yVOJRfKyH2LsDf3h7nOxBg71v2dyp34br3r+/u75ADje9pVW9w4X980Tufd4/fadPozkZi6JOyDftKxBgYTyoQ5XY+p26b3htP+lQbvYu9CFYM0WQuxYGEuChMr2FFUmz6Rd5irBBVSG2kDYmyWBLVEZPDGN/bmwRj1qRY4CsAi0WRIpJcSZIqu5mrz2urcVhb4ArLkayxVvk//Y9/nxj+f6TuG9oWFq0lCFBY/uMXz7mu1/iRx5uEMYlCEx0KsbeVpZ7lX1NPE5UZTQZ2/zYkuq6lEcFSUpQVPjbgHckZYtdSecukLFje3HBiLFVZZWFpHc4XlFUJ6+zV2azWFMb1ZMKGqrA0mmjblqZRyrLElwUvnn3D7aIh2YKqmBK7hC8qprMZ1dkpMqmoNfCLP/0T/DdfU87nUDeoZkGeJgX2eEJIkcXLl6RFQ2xbmpiQHzxh/OnHnP3oR6wvAykJdU7jvNFUMpuKJRskRyRb9fyHFh1PoXAwGSMSMN0KUnaEMcYhxhONA+eRsqA4nnJ+XPHRUcVTGr7+n37BzTffYJsWUszogECSgSlF+szXmTrMFhbvbL/xymP47UKDne20foAZv1P3wbn/9sXuIW3pbceHOfi2peNvXey/4/L+j/Ytg3VYkBm0wO3xvVqUnYHQC5oDA+9t7vVvCzaUfut0v/03qfq6ge72HUPe7andaxPZmfTbexYRkvZJNft+Oe84OjridjEnpUQgZSN/X7GQGTqGHE+ZDSThHaRYE2NEJKEaUBUyY4MHI6gITYhIq9mOIQMlFNmpQlaZ0slYks2m+GhLcAIUZI+4cb4XZzHaYjVRlS2fPh3xD/7gRxhTcnn9n4hiaAK0UVi3a26XNa+urvnspMRJ3g+nLJVJiZzAsbdxxBDI+cro2ftzUHRZlNmZA4u1ntlsRussrQFvYFR4xmVBs0w5gaNCCC2oEmKkbpqct40cwGutwahCFymMJacdyxuKLgSkhdv5HKTccCaG0OB8QVGOWYRAt1rR1TVhfoteXMKr17imwXhHMR4xOT/j/NNPCW3L+vaSkAAsdjLh+Dd/g49+4zc4/+Hn/OriS7qYM2QjlmEbqpj+bw+2QMoROEc0ICdnUDYwatGwghpMStD2mpjJOdbUF/jxmJPzY47HjomL2PWa+asXrK+vMKHLThuDzt8Lsc08UEWsUBSeonD4XogNGgp3LMV3J8NWaG3BuAdtU+9YDpoPDoAwd+HJt7F73N3sSr9oKW8noBiu/9tg529ZHtqTvN8u6BBk9/DZ9x0q9pDv/vq7qnvu8YPCa6cXDw207bkDFHCn5Ttw3u7xgw3t9Pd+eftT3NrEhh3o/n0aYzIDwk5/nLWZt895Ohs2/IGD0Bs8vQatLFsvEtYoMbQoATO4lCMoLjtQaM5d1iaFEEkaEc0M7gah8gXG1KDgnMX5PmeXGyGmQozBUKC9rUyMQc0c42o8juOZ52c/fkrbCf/+P/+c+kqJuTdEoI2Rum4xFPTE8H36mv4Pye72aGbUECPZdiE5jssYS1kWmBCH0ymrgqgpp6oRKKyhsIa2965LqsQQMWQ7T7avZaeEGAK2KCApSsAbgx0WXE10MUAfi2ZKsyH9jSFiEogUtKqEtqFJEZo1cT6nu76hCAFblRRVyejkiNHJjG5VUzmPTSanz6kqzn/0Q84+/wHT86d08QtC6rd/sjN2tM8xJy7HefkyZ0UQRWbHaNVC2aBrIAUkdGDqHLDcbwQoPG5ccXQyZVpaSgmk9Zz69oqwWmB7lhTQ+7a4fhMnIvhegDlrNsJib7wfmBV3jw2a2YfE+vc3tsPRx8/P3TredHzYRO66w8GB9ecD28V+PYXYI7TmvzkE8TGDcX+ndFhQffuB/U5q/IPPsLd17Wpjw+G757ytqm3PNsbjQwPcmMzY0TQNxliOjo4YVRVd1xFTJuOVPnFmzkuWnc+ssaTYYYgYE2nbFUYDI9/DUZLtYO060EWlC4r9aJQdE7pIu06kALFVvFhSjIS2gdSA1riuRkgU1mFtQk1BkingSVKgssD4DucCRbrmZz8+ZjYuuLj5O/zr/8d/onu1QtwY1HE0GfPk9JRCIl4Dtr+HATEbnkfq3dxT71wgIsSQsMYym0xplgu6pqNp59ijCfV6xe26I3UnEBoktKRmzXzRYNoODS3TcdG/p0wurJLtb6aH0CBS2ZLKGzqXF+hVvaak5PzpUxZNJCqEpiV0EW0Cy3WHGY+IRlkvFkxSpF0u0OsrnCq+LClnR0yenDMPNfXyhrhusWoIURxetQAAxGRJREFUxtL6gp/+4d9j+hu/hR6fcnG7om4TxhYomR5LNg/Hbxw0ki+zOz0R+/QUrVqiWxFvEoaUk6guV70JLWu6Mq4oTmY8/fiMkzLhVjdcfv0L0uoG29X4pLQx21FVsldipmPshZUYnLGMypKi8Dhvcrze3ubszWU7Ax4o7zj1H2LLeJ9r3/f4+7T9PuV7LcQOBRQD31pCvVUdfocmHqNav6086py39OHN2tSBNuTOcdlqboN37B7+LfuxH1u0ZYBU7tvJBsg0G+h3ghl22h5gxhB6rz2TtdSjoykpRdq2xdrNBVvY0VqsG+LFlK6p8RKxRjGSiDESSWgS1I348pvn/MXPf8l/+w9/j6dnM44nFW1oqVvFSsDbVW9DVJCEWMWnSGkFKBEfMM4gLtNMRXEkN8PQQOpIdsyobPno1PDf/Fef86uXF4xHr/jl1zfgAsclnI1LRtLgFESFtl+sjWomN7aGZCB1cZNnzojD2hyEmzRSFD4/ToX54pY2dIgaxlWJpEio65wt2VqsF3AWX7icOdoY2rbBOIMvCrx1xKR0ITC/XWBSYjqqiGmFdwW+KFm3HdZ70KzVlGXJ6OiY848+JWiiXsxZXr5mliJrjTkBqDOU0wm2LPnq2XM67dDFGqkbRCxuVGLOz/n4N38DPXvKRQuvX12zXtUbaDlzRAoilmQcWI+WIyg86jIrvTs7JlaBKB5rAhBylgIr6JDauzC42Yjp+TG/8ZPPKJbXtFevuHn+Fevba2K7xkhGBQQFGUJC8pzK7vSGsvR8/PFTisKRuTDj7uR4wE60g8n0dT4Iz0ueIbvz9JCjxZvQlAHRUb2/Lh3SjN5V8AzrwbC8POxUdv/3b1O+10LsvctjNLU3POA7r/pNldxrRu8O0juwxNtavDcw9M4pvXQ5hFnftYnJA00+RIF159Y2guzufQ1w1vD73bi3uzewgRE3z3xofwsVDnBOT/nLqKqoqzp7oon03s/5GoPkvGPS5ypTJYUOXGTgaRTJgiKp4Xax5tXFLV9+84pPvn6CtY5RNaFQRxvAElkZpSxsXvhMxBUGBFxhSeYGGx2mHCHmmGggYkmmQBkBDWpGGNsyquCHnx7xOz/9mK4LXL68wCgclYZZaSmjze7yqljRHNuUs3+iYshOJtofGnYWvU1RU84z5oToQUPMnpXG5kSNqmjoMJpw1uEMkGJmAOk12Tp0OHEUApISoorRRLteYazibSbL9d73pMz5rRprMNbjg2E0nnB6/gTnHGm5oFssMOs1tmtJKZCMYgqPKUu6pCwWc/R2yahpcGWBmU7R02PK4xNqV7C6XnN7s6BtAtlTNe4Mvkx4rCbnAlNjwFkoHTIZIWUAIiZO0NUt6mxm7EhZIOFsTlFzPOX8eIZcvyAsbljfXBKaNRpyZuftNOvbRDDkZzZAzCenxziXo73QtJ03OuhYuwv4/RmxBdPJjC135t2bTATbeh+2We07X9yH+A7V9aa27py8085+Xx7q5xttLu9Qfq2E2KM1pAdPehcd6z3bOOARuIXnPmA7w9d3dmi7TT4WF9d+B/r48r7QweGJdX+XmBiNKuq6oigccR16p4deIBrBDGBTP6k0dtkwbxWs4L0H8QQt+fP/9Bd89fyKdWf5f/1//pS2E0bjMz6ajqjbmth2PUdjouk8UUeoMYSYMBJxyWHKhFGDuBlRJwRToq7AyCxzI7oFqZtjTOSj8zH//T/4bY7GJd/81V9SacFHx57TUpDg6FqljVkgacqLtUZIvcD23pO6SERJu7txyPmtrKEsHEd2QinQSYEzoyy0YocTpapKHJbUNSABMQZflrTXHUqiigVtDBhjsQiEhpTAYjh9csxoPAJniGRNzRee4+Mj6rDk6PiYz3/8Y06OjulubzGLJfNn3xBvr4ldzUoi48Iznh7x5LMfcf2fXrC6uYblmieffo58/ITus09pXcHtquPVy2suXlzTrgNiCyR2eajk3Dt5bBgBm8k0pTSYsylMKtQH0IhJNVqVUHqSA7o+TrB0zM5POXt6xsnIc7u8pr18xfLiJcQW1UiXIkGFKHkbZbA4cVjjsFhCzA4xHz19QlE4RHqvWPL5WzeuD7i+fKDyXUN9fxPl10qIffvh8Tc7wD7k0NlDIw59f08gKG8K7LjLy5bLrq3rTZ93fu7az+6Vhyf3oIkN9WuvcRVFwWhUMR6NWK9r6JcK2UlFYozZOEBojGRXCtAodImc9Vjgxesb5ssOU8wIEvnl1zd04c/53/7Dv8PYOjBKEzvMOhAVTFGCU0KKxFSTwjWjUYKoFH6CLc8o3DGdjMhEQyO8P8ekOWItmiwfnRX87k8+4//wv/5DTB0wCax2tJL7FYzHaQeRHN+kabNDN84RNDN0bMILjGSvxpShNqxQWA8GLC5rDSliYkflPYX1GLV0MbBazunaeuOyj0IKHdbYDZVSIULU7CAymUyImrLtreuYzE4oywnOOW4Xc45Cx2g6w6pimwZ7O6d99QpWS4xVqidPmD39iNHshOX1ipkpKcox0bSE0jH76Jwf/P0/RIuS1dWSm1c3EA0aQUPCDONh0EYHRnmhF2IWdzZFqgKxgqQS6zzJWpIAoc2akrWIRj59esZnZ6d011csXjxj+eo5zfy619Sylh9TDsVQBaemF2J+M2qdtZyfneGs6Z2GUnbK2YLkD47x+4P+8J7xQwqcQ/DjhyrfZd2Hyq+VEPuftRzcbO1CZNtDG4cz7qjqsnP5A+/9IZjzuxgm+7Eluy3ogb/ffnwHTNlrR/fOHdruv7vzCAc7qDE5x1hZVZnwV3WzrklvP5ABahyuSz07R8r8iEEDrXYsVy11m0hSgTpuFx2GG56/uuGT05JibOlShwkJ2kTZaM7Mojnw1UmNqMEah6mvwDqMLxAtAEGSw8kEcUeoJCQkRlXiyekRv/+bPyTMl9SLNbc38+xiroAabDI9DGWyZyK9NtZDf2I0C7kN9CR7GxljJRPuQybFTSFntS4MznmMGkIwtF1H13XZxmMthpyp2BeZQ5EYsQIxZa5J59wmYab1jtFojHNlz/QR+3xn0K6WxOUSWa8wdY2mgFihPJ7hxmOSsVy+uiQs10iIOGcJRnCzCec//JxiXKIsaJYNmoQNqeRmkb8zFwSwgniDGRfgss3M4jaeqpnXLNvDBMWkyNlkwul4RDe/pbm5pp3PiW2DkkiiROlJkFPvCUqmlrLGMmQhd84xHo+y5t9rYbBrs5e9j7eVQ/P8QwiDvCc8YC54F+jwbW3cM118uLoPlb8VYu9d7ryQ3RfUr6Ry93hfDnEWDhc+tNC/rTwGjRwGkfYL/mNa2MCJff8Oa2McOD4A43pAC3tQXzzQPncmxPa4947JeIzr2SuGxXNgATHGYHrsXVMf49N3LcVEGzpu68hq3VG3QrKZHWS+7GjrJX/yZ39N+fs/5mh6SquKdkokYdeBZCI+QJEUk9akGEA7TDHCOcGUBZIqUIuoxckUinNS8sCKwnc8OTGc/t7PWF684vWrV/yqm7MIgdQn0rRhsK9kLkjV7O5vjMXaiE2pfz9ZgBmRnk/y7jtJGU7tAoSAtzlTtKihaVd9AHODoaMoCjR2hBiZWJvzY8WYufVTIIXeIzJFksJ0MstMI0m4upxvxkvd1axfrakvL+F2QdF1BI2IN1Rnx0hVUXeRX/38F4zDDZUmpkVJawUznfL0Jz+mOp3gvriiXTW9iSkT9g5psDf20gGhF7LgKi127EgmB75bdZikSOo1VyMYzd6KLgY+mk55Op6w/NUvWF9c0Nxek7qWmAJRE0Eyj6UikAQnDmc8znra0OCdyw4t41HuU8pCcusqnwXmh+Nt//blXVg83rledux7cnAJ7MuHafe/ACF2CKr6ENj0rthIB75/qI2HBdj9v9/MtfimHm1qOeDNtKGJOdRDGY71wuudB/i7D8yHBLDZnRCq279Nhte8tcxmY6qqRMmkt9nhIS8azgip18RyfQYjWSMz1lO6kqNyxI9++ENeXq65nHd0wZFU6LTjr371DVWRaNo5P/vxk5yKJMJyHVCTU400CpJC5iCMLfgXeMAnwR9XGDPGSIFRIcgR0ZSIX+HTHJKg5QIZC+m0IqYzbr68pl1F6rVi1fRap+Z8aQwjLfX0WgaRPi6sv2dMTg8jmoWNNTmfWhs7Ymzogid0kXVcEaNyfX1N2zR0dUPXLCkLSxJLl3KgtzOCLRzOHhHniUazxuYLn4N6fYExlrpuuL29oRpVjKdTiqrii5//JfUXX9A9+xrW68xm4j3ii0wp5Qt+8OkPWH+zwqeOo5MTuqfnTJ6c4qczXl9FfvXFJX/xF7/AqMNIIPWQsJEMG+fx2Tv9WANVgYw8UmauRELEdA3dYk6Yz4nLBULOVWOt4dPPPuWT4xOOreXly+csLl6xvr0htm32YNUswELM1jBnLIUvKIoCay1tqBlPxhwfzRiPKpzr38OOZL2LT7zPXPguyncjyAZVeTD/Z/KCYQO69V78cHf5bqsk8G//7b/lH/2jf8Rnn32GiPCv//W/3vv+n/yTf8IQjT38/NEf/dHeOZeXl/zxH/8xR0dHnJyc8M//+T9nsVi8e+/1MT+y0Tq2P72P0QPXbDSot/48AGvAZrd4t8iBnuz+2+JBB6CSvZvm7k2xYfXfuZkNEq/b3wfPRNmpt3f02vncppIQSb0T3BBIvN0JD7DJUG/+Qjd1DXe53917d7xdiHd+GH6/e5s9Y4IxQuEd41FJ4S3ZhJ4QcqCylezoYCRt7iXT7GWmbRHwFj7/9JSPn4yZlHl3jkJUw7pTnl3c8stnFyw6aNUSMHQh0LUtXZfjotZ1jotarFqWq5p6taRd36DtNRLnGF2SqHOuMB2jTBEzQlyJKR12JJQTw/So4OxoxFFVMhILKQtu6zJ0KEYxJqF0GBMxJmFEsWj+lD4I2gq4/HwMYFRxpgPJzi3JjKjbltVqzmJ9Swg1hA7TBkwSEEtyPjOfGPBWKMejnBhUe9cG43C2wLkcYxZCYLVcMp3NmB0fU47HtMtb6stX1K+eE0ONs5ZRMaaQAmMtyUI0iTYpHQZTFZw+Pefo+AQjJasmcTmveXGxJA1QYlZLSZuFt9+i9AqalA4pLLgENqG0hG6NbRtM22K63sNRBOMsJ+fnjKzBNQ3x5oqwXhDbGlQzfNjDmNkbEcQIxrue4QXECqOqZDSqNmlxBqRlM7r7iaB9WpZdrsXNz7CmPFJfe4jx4vHCaGcd2XPV364Rm2Nsl5+H+nZvfqpunsV2Puc4PUib+f0hyjtrYsvlkj/8wz/kn/2zf8Y//sf/+OA5f/RHf8S//Jf/cvN3WZZ73//xH/8xz54949/8m39D13X803/6T/kX/+Jf8K/+1b96p74MCcI3ZaNaDA9nF5y7r3s8qODr/kt84JTtrmnPgLtt+iEBt1f3zu9bDWlnnyI758tmnA+V3yvmjnq1m4xu286dbsnux86AHpjedzuDMGQU1r4fm52V9oJvs2kYGrkbw//IcsfzboCqomYYLZNEWKaTEV3bUK+Wm3tJPUuHNYlkeuqqXsQppodUE9ZGfvrDc6wJLOevWK+gI9s+OnV8c7FgHTp+6/d/hnEl1gkm5oVRcBhTsg6BGCAEiysbklmCuWY0vgBpwYxJUqF6ilKi6sB0iG9BHSYJXoRxsnx0MoW2Id6uuIgNxhrEWIzJLz4BMWUyXyuKEDGSWTYMCRWTF3jT52kLZGFoA8Z0qE2oP6WZP+P/z96fBNuSZHe98M+7aHZzutvkzayqrJJKKklPKiEe8CE+7GGAZGrQBJMmmjFiIJMGgBlgMMCQaaAJIxjABEMawIQhE9EYJiaUaGQfH0ISElUqVWZW5s3bnG53EeHNegOP2Hufc/Y599wuK7Mq17V9z94RHu4eEe6+fHX/1SxOmS1Psb5FB0/Rga40WI04TbRQBHAomIxQ55bYkRH+jUMbB9rR+URoOxaLBZ8/POTgzhHVdEpczvBPP6T94F2cXzEejZnU+4yoCcbQGWERG5ZBEKNIleWNz7zJ0d37GEoWTcvxrOPhSYNOrN+ZGIvEDhHBqrTRMCpBVw5VGpKO4BLRt0Q/Z9Q1iO9IPhC1QUiosuDowRsUIqjZjHTylLCaEX2bR3nU6zXC9ps3o7JkioZExBjFeFwxGdcgMUdg9Pw2Daps1JauJq1HtMhgctied3p9nn5e7YoH2/6dA/yfhyFsMZArzlusF7ZhjsvFwztn8qZMZlxR0nqTOtyDYpPTTASUxOfo8/X03Ezsp3/6p/npn/7pG8uUZcmDBw92nvv93/99fuM3foP/9t/+G3/6T/9pAP7JP/kn/JW/8lf4R//oH/HWW289b5c2pK58ua7AS9E1POBiS9e9bS6rC24oeB3dVPyGc7drSbb+Ctm3HPp0uDd3a1AbXDn+ar2qjDG9g0eeZGVZUJYO5wwhDOlKFIXV+Dai8FinkZQy2oXW2YOPhMSO0sCbd0a47/sci+X7zFaB1g+ZoQ3HZ5Hf+Pf/lf/nz36Zt988ZGwSxrdEPKJidqsWhZLIYtmSOCfGiHWO0q8oRhOK0T5KlWuEfaMLkDGiDtAyw6KpRXNnFdDJYZOhjR1tCIQUmdQVXczBwsScnFFEcKZ/tsMCL6pndZmsMoiyBA1RKzplaGVMbBJxmaVJCo0rKop6DMZSaNBWKGxESYeIR2nBlZYylZtYIFFYU/D4yWNWrefeGw9wVYm2FqsUtUSUgVHhWAHGFrhyzMH+HT7oOhZ+TuEUK2eJWjgn8Mb3fpH9z3+O5Cx//M0zni4ManIE5y0olVVUfeLJvMNXrBHlk0BVkoqc5cD7JbJaQLMkrhZI26J8bxusLG465bu+6/PE5YKTs2MWx49oe09NSWQv1348JwSjNa4wVKMKyJuJ1eqcO3cOefPBGzitURIvCRiDi/1HpSR8Bl3qyiubm/3iktJWfBwbBqkurCv576tZjV9AnXgb+s3f/E3u37/P933f9/ELv/ALPH36dH3uK1/5CgcHB2sGBvDjP/7jaK35L//lv7yO7rxyuszAdn2AjWry8vHhZH/mhYbQrovkGedvpFcxpDYi3Q7Z9MZrrnuOVz/qgipFqQF4NQffrmtVCudsBrTt1YeZL0s27g+qG8lee6Uz3DmY8vbbR+zvGZBlVlGKwXea2Szy3ntP+eb7x2BKOkm0IdCFQIyJECLeB5qmoVmuWC0WtKsFvlkS2hXRr0jhHAmnwIIszRqUHqHMFO2m2HJCNS4ZTwv29h2TsaUswOiEVeC0wersVGBUj2Cvh1VJ1g8+S2UZ6SMztgRa40WxCjBrIk5V1GZEihqqCne4z/TtNxnfOaIaj3EYxGf3fZwFJThnqcoiP3th7UyTAOsK9vaPUMYSQqBZzjFthw0xu9pDxld0lkXwPHn0iA/fe4/Tx48JviVIZJ489mAfNZ2yTMI77z3i9GyJdRWiDaKzGjCrmXtJX5msHlYatMKUJco6QkxI20Hbgc+OK75rM3iyZLWrKxyHe3uEZsn89IR2uchQZjFyxZYsfR435zKCf2EzwHTwTCZjDg72N5KLyJags1Hb9cNvozm8fga9MtqFkKEuHb9NHdvzbXeZS+vipXYvX3+dOvRF6JU7dvzUT/0UP/uzP8t3fdd38bWvfY2///f/Pj/90z/NV77yFYwxPHz4kPv371/shLUcHR3x8OHDnXW2bUvbtuvf5+fnwNUHcWFH8QICzhXq63hWVc96Gde89s23F+nrTvHv4vfL82TNUHf2d+hErwC4BRO87Aaf/6r+fnq14iU325cngR61YXj/zrkeQWJI/p6PW2tz4sagkTg4QOSUJsboddy5iKKwlqIY8fm377Bs5hyfdDg3oW0VIUDbCN/85jFKEl/4/F2SQJKE9oHCmryopkTXZAkBhG61wrosmRhX5F29WWLdFFQBaNAjMFO0FWyRKEeJkQ94b5meOmLqiEH6nI9ZbzYslEYHjFZ9iha1RvQYmFhWBmcmlpTK7vtBoI3c0TXWjCEZVD3CHe2zd/8B/niGOZ2R2o7kE8kpxDk0icJZRJVkwIu8GYgppzVxpaOuJ6AydNXi7BS1XKFaj4oJIxptHVJYztoVTx8/5unJKWoVqNAoV7FIEfYmxLpmFoR33v2A09M5xjiCzlBSaI1KoWdiGpQF1Z+zFlOW2Z4XA3T9J0a6toWug+gB6RmS5WBSc/zoIfOzE5rVghD8RfXcwJQUGJMxPIuyJISOGDwpBibjMXt7Uzau6z3Tkoy1mAPx19Xt2GC+kLL9Yg3Xhd5cctwYwjDY4QI/lL9Yb77qJpXmpQavLbNLFfoq6JUzsZ//+Z9ff//yl7/MD//wD/PFL36R3/zN3+THfuzHXqjOX/3VX+WXf/mXn1nugmi8Vja/xIN61duij7id51NivKjKQ20xsE2qFrUVSP1qvZ/UBdk1S2IFVVUxGo1YLBZAdvwoCst4VKM1nJ+eYPprJEV8FzHa4lyJSmGtjntwryKl+4xGht/7vac5UFYVRK94+HjFsmmxZeJP/onPsz+uaaOn8IJoUFpomxYlCaOEdrVAaUWMntA2FGODq0qsugP2EFElmBplD9DYzJB9R5080PJWM6F0UFo4Pm2zOlKZftubE0N6m9PN5MgkgxbWhnQjCVxBMI7jWUMTOlSVKA/28a1HS4MzU4rJIfX9e+x/73ez+sZDnHK4JnB+3pB0ojOKIkWK0mFKm7MA9BudECLTg0PakDibNxjdED98TAiJ8N4HdE+OCfMFtS0Z7e1RHB3wbjOjUIY7riJ0K3zniZJI0zEnzjKLwjcXLe/8n29wftyhfAGmT3IZO0zb9KETFjEOsRYpK/ThAW46RaYl0ZUE7fN77VrEt5ACw05mUhUcjmoKCYTFKcuzxyzPT0lpY6dJSUiSSH08XFmWjMdjyqIghQ6VIqOqZFzX1GVFijGPsSEuavhPDRkT4DqHr5eaETfMryseiGrYND+/Z+KtykpGkRliOQeb3avbxF6l16JO3Kbv/u7v5u7du3z1q18F4MGDBzx69OhCmRACx8fH19rR/t7f+3ucnZ2tP+++++4tW381D+6j4mWffFIXvt5+4D7HE+6LDpiJWmuM1pRlwWQ8ympFs8FNLIqCuqpwzjEglShAYiTFQIqxt3skFAkJDQfTmi987i3u3z1gNHJonZ0HoiiWbeIb33zKO++f8/ikJYqlC4KPQhRFDIL3gbZpWZydMzs54fzpU2anT+kWp8TmHPFzUlwiNCQVEWPAOrSrsGVJUZdUo4LJxLE3KdibVNSFxQImCU4bnNY4oylcTsSYPRgNZrC5qZzmLHQti8WMpycnPD0743ixYIlm5SpCNWU8ukNqFaFJJKWZdx1NiihjwViiMXjdo3VohbNm7S6tdM7vhlJ0IXE2X1GOxhilWD59TPfkBJmvMAkm9SSfG40o9qcc7R9wdzzFdB4rQlE46sMjWlty5oUPn87pzhvivCMtO4yyKG2zJKZUL33ZHrXeoeoSe/cQ6gLKLJGpIntBOiRLYanHzpTI/nTM3YM9/OKc1eyEZn5K1+as0dKrSaXP5DxI9UVZUtd1b5PN5+8cHjAaVThn1hLXRXXhJe3Qy+n8X4ierQp89vx7Vh0DhRDouo6u665ct0ul+CrotceJvffeezx9+pQ333wTgD/35/4cp6en/PZv/zZ/6k/9KQD+43/8j6SU+LN/9s/urKMsyysejrenV6FXfPU09OraHRQfzRDfDKRnqBC3OrSrbxfViRclpZvVidu+TzdTfmZDJzb6fa01hXOMRjVl4fBeiDEvMlnFmON6fL8wZZVinzE5xoyz2Pc7hcioGlFVFffvz/HxHB8afMggsK1PPD5e8v6Hc4xyHIxqrISsYjOQohB8RCGsFgtCCNi2JUmkKmucEyQ0YBtIOjOw3qVNmax2pCwgloxGLb4tiD4yqzokChJz2WQ0SRmcGHxUSNQIGlLPpFVWJQbfsVp6ZnNNExdo27AUYeUqDMIoHnLWnZJaQaNZdh34QIEimZxcMulIiqn3lFTr16U1KGOIndCFyKrzVPUYi9CensL5DNW0GBRVWWOrOuMXdonKOZJ16BAw1mCdo5ruEWzBvEs8Pp4RmoA0AaJBK4OgieTdidAzMVtkdWdVYPYnSGkQq1HW9DneQMcIocsSd5+OZTqqOZiO6RYz2vkZzeI8O3T09rBBpSj9GLbGUriCsixzItKUkT+O9veoywKjNSJhayhvx4ddHuNXf8u2/l8Nx25PN6kEL5TboU68XM91x26jfuy8p+s6tNY71+xXb154ASY2n8/XUhXA17/+df7H//gfHB0dcXR0xC//8i/zcz/3czx48ICvfe1r/J2/83f4nu/5Hn7yJ38SgB/4gR/gp37qp/jrf/2v88/+2T/De88v/dIv8fM///Mv5Zl4/Yv7+DEwuF2vPm49V70uIk+4NRvmMlsbTGKvvv3+f5WzKmddfXb3L8sCYzTT6YTlckHTNIQoaJUhgSbjMfPe008JGGMRAd95tAUjCuMsSmpSsCij+eEvfx/GfZ2kPuDR8YwYc9xQbB2/94dPmc+FO/v76KlFa7Axx3Eln5DkWeklbdthnaNwBXHliDYQyxXazFDKI7bN8UY6q7Gsq9EJtBj29zODtcaQouX4acNs4Vl2MUskWoO2+NAnd1SKEPK7EYFlu2I+m3N21hDjlCieJJ7Tbsnp3j7GjLk7KmnfnzNaKQ6o+d/zFc18jl4twRqSzY6psXdSUlr1JiiFMgZlDOfzM+ZLjzYFRwdHFL5hdfqY2XKBdB1aFLYaYUdjOlfwta/+PndPW6p5Q5EiQTmcKylHB4gecXrm+cPff5fYWUxUWA9iWENvRZOZmBgHZQ3jGsYVTB3RJZLy+OChXZGWc+T8FNoVElpUCmhJHE7G3N2bMHvyiPOnH7I4fUr0DSGEDLoMvRpMo42m7GPBqqrK7vMxoiXx1oP71GXRxz9dDNrZ8KRnzGS59EPUK9c6PksVeD3Y9sXrd9WzDQV3fn7OfD7HOcdoNMIYc6Xs9t9XQc/NxP77f//v/KW/9JfWv//W3/pbAPy1v/bX+Kf/9J/yP//n/+TXf/3XOT095a233uInfuIn+JVf+ZULXPlf/st/yS/90i/xYz/2Y2it+bmf+zn+8T/+xy98E58EFOYL8uDHUzi8JQ0qOfWce8WXoyvP7+IXIEsGk8mEIeh7ucxYfxqoy5JUVXQIzcqzju3T2QU6iiJFOD1veXL8iLPZnLtvvcVkWvD5L9zn8dkTrCkRLDEWLBvDh4+X/I/f/So/+n9/fw7ebTt0kevUSmemJwmItKuW5axA4Sgqj7FzFC3KtGhTZIlBgdYOTAIrlFWJ94kYYW9PZwalNOGsJSaPJqdGcUb38Tf9/aSMVHLy5ClNG7HacLA/oR2NCCPLbHXG070pylSMomGsRrglnHz9fcRHxGp8ZXP6GkmoKBm4WNFnys5PPqVIt1rSrFqCB+tKUueJywWcHJOaJVoSrnCYusZUNbYecbh/SLF4CrIi+g5vc4iCtSO6RnP6dMl7X/8QQkbQX4POA6is+M2OHCXUExiPkVGJp8WKyUDBsUM1S1jMkfl5Tgiach7tUVUwLh21NcTVgrCaE9rFWr08aBRE8pgyxlBXNWWvll6tMsyYQrh7dEDhsnpxM0DVFb50WQa7aYRfTtvyLHodwMAwrKvqwrnLXpsD0HZKifl8zsMPPmCxXPLd3/3d2XM1ZWzJgdG9DnpuJvYX/+JfvLEz//bf/ttn1nF0dPTcgc0vRM8YC89Sce26/EXFYHXtj939ulauvMEL6XnKPy+p4b8tlcd2zTeNz5sBQG+nOL32LtZ2hlxHXZfEmL3Guja7bkPOWFwWDmKgbTJgcL5CZ6zCKITgefxkxgcfHnN8eoLXmv07h9Qjx/5+zapReK+I0RCCZr7wvPfBnKdnKxQ109Lge6apVSL1AbpCZLVqsaZEaUc17XAuYbAYG1BqhFIWhclu98aijcMWBUUZCCExGkHbRmJMLFcdvkskEawyWK2R7FFAUhAQYswJQxWGwlnGdYGYSEwr2mbGLEVKFJ2yTN0IGzvOP3iSoaGswTtNjNlobgC0RgY32kHdJakH/U0IGusc0Qf0ckk4PUFFn5mAc4hzRDLO4agakeQJPnQ5vEspks4ZmtuVsDzvOHsyQ5Iis7HUv17FGj9R52zOFCXUNVQFoiIS28xQfAurJdIskdUSYgcpM566LCiswSJ0qyWhbYi+Q/pM1gMT6wdvVleXBc45jDE9yHHEAnvTCc6YjYvu2oFjM2jVjQvR9rmt79vz7Jr587qBdTf1Xz2+SxqbzWa0XQ5Cr+t6zbxep1MHfJthJ14ZKi/47IZ6vrXC0idaXNvJm16tl6Jeq3CUDMG3kr0RFVij8L5htWjwIbdZlhVaKZq2ZblqczoqbRDlWKxaTs5m/P/+5zdougxW++Hv/D5vfu4N7r1xlz/9Z/4kv/M7X+Xx43mf2VfThMjDkxW//btf5Xs//yZf/tIXaMIM0QIC1gtaAzHQNKe0DayaiC4Uo6QpvKWkogCMqTC6QnRW01FYTCwpcyeRkBmvMRl8N54G6DI4bV0UmJABjpNourZlsVhQVnV28Xc1MxSPn7zP0/YR+k3H6fKzGDOmK2sm+0fExVMeff0b1N99B7Gwko7Q5hQsFoNY1qpb0YNKNzvXGGNw2mJGI1LX0R4fM//GOxQaClfgypKVVvjFAk9kpAsezs/pzk+4OxnR1CNSUdJ2ivOnLeePV6yeLnGxzhKf7mP71g4dBbgRFGNwNWY8QY8rtBWkmyGxy+rD08dw9gTmp+AbSB3aCAd7Y0qjSW3L7OlTuuWC5DsUcskBIdtbjTFUVUXhCrTWdF1meIXV3L9zlBOOMmB9Sj/uda9Sl+dblJ5n2n8MlojBdti2Le+//z4H+/tM9/a4f//+WhKLMa49Fdeu/t9Km9jHmS4/lhd9x9/KcbHp8/W9eNmx+0rH/o7KbtoA7GZkz1a2XKBEts1t+XhkQNi8Sy4Ki9YjQtzDGUu7bGiXDVFrorG4skL3arqEJorhbNHy7sOnNBGCsoiyWGM4O23w4ZjJ/pvcvfMGZbHPh4/OWK0WeZdpK9798BSlDaO65k98zwOcjhg6bKHRJnvyRR/oQkSWK8zTiOgaiQUmkVWDpUMVOZOz0hHRERVLdBKsQDkKjIIBLClVeAnoRcf5wmOUwWoodUT0kKrFcHh0h64LNF3H6fF7xEbjpCLOPqQ9Paezh7gHdzlePCaFliDCQVHS+UDrW6rCUUuilIToftOgBWMd2ljQlsqWGNvhsIzHYwqBuGpRp6doA8ppVGHR+2POlktOT04g+uzZOKk4Wc5Qb76BPtinCYrz44bVWYBYkLRFXK5D/AqRwZukBFtnRqYKSldinQMCqZmRuhVpsaB9+hTOTmE1RxEwOuGs4mBvgtUK3zScnxzTLBcE35FDM/R6XK3T/ZQlVVmhFHRdhtdy1jLdq6grlzcqPQNMSdZqyHXWBckbkVvNuueZmN/ChWpwfhnQc5xzfOYzn2E0GlGUJd77dX66yzFmr5qRfVsxsct04yP6iHcxt23uo3D4eKW3vbOyzU52m64fvM/hoSh9BmfZdivp2WbvIql1RusY1RVEwaJRSeg6T0qC6dV1GsEnTesT81XH2WxBTmavsqoOR9sJMg+cPJ0xGk/R+wWnp2eEEAkCSTuWXcfJ+YpvPnzCFz9zB1sbnHUktcnrq7QhiiAhsFgERiMwCE45gonoFDEqIS4gxoMKvbeiQ5Lgypaysr0KzzFuCkISlk0iiCIpjdUJo3OCRmsdIURiiviuJfkGkzROAL+AZUtsAp1SRC0oq1CFzdBcg7pMa2w2z+GBDAatUNqQfXuEFBOkhDZQugJCRHmP9QEpDBiFdg47GaFjZuJhucpv3Gq8ShSjCjUakZTj7HjO/GyZPTdVVpOKUohoCMM7tmhdgC5IojMEVUyk1RIJC2iXqPkMFjNoltkzkR4sWWtGoxqjFCl42lXTBzhfxfFTSmONoSiyKhF67zvvmYwd08kYozcbsAtIHWu78bdcWHpttC1dKaWYTqeUZYmx9ooN7LLjyLfUseOTSjsfmlxdaF8XXWjmed/fKy//mh0y1M6vV35t+nI7SSx7PW4FbZIZWBp2u5J6LylAK0ajGqctvqwprGM+WyCiMGaFdQVRgYqK2WzO6WzJ8WxJ1BU+CTEKSZVoNG3SfO0P3+eHf+SH2J9OqKpvgoYmwDwotK04XbT8wde+wRceHJLu7+MOR/gQiCqhtWC0IZGIqWM+b6lcBJ9wscIFD2OPJiDjBlEeXMDYCVp6AN7QgUSMySqc/TBClGXZKsI8IH2uLi8ZhqushNMPH9Esl7RtS2WFLgZILSYuicuWOGt5ulpSl4qKgrEds1guaMMKJYJTCpsUJkBjs7NKhilUpJgIKbH0Hu87jCkpCkdYrNBtxxiYk8BpXF1RHx4wVRafFMenZznNiRJU5VDTMWo6xpQ1773zIY8etxAV4gzJKpJJpKQQoyFk2G9jSrQpaaNCfCAsW9rlE7ScotoVejZDnZ/CaoGKPjMxDc5q9iYTnNZE72mbhuBzMk9Z21bzeNRa44qC0WiUnWxCoFmt6LqO8b097t45QiSheykrxsG5Y8sZQmSTQP2CEfnGob4pcF25j8iZ7bpm1olZe+lzYGIDZJe1GX5s8Fq8TB9r2KnvPHq5vdZ1y/dzKtguducl+nLRq2pbMbidB2CXZ+KQN+hF7YnP13F16XtK2ZnBGYsQkZQwaJR1WJWDg61RWKto2wXz1QpBEGV5cnLO8fmCVSuIS3zmzQfcObjDH/3hH+eEyGLoouZ3//BrHB5N+PKP/CC/8zv/neZshaEgBGGlhBjhv/7e11mFz1ONp0gR0QQMnqqyiGRvRR8D52cNyRtKHdDSZonCaozxZDT0uLZBYQymsBRSorQmiSYkg9Y2B6fFM1ZNoA0Jr2ARGprlnNC1ZHgqTYod+5MxR9UE6jEP21O6k/d555uR/+u7DimiofvgKe3xCcnCpK6JzZLgBR0zAohWCZ0gxojvAp1PLFdZEjRaY7UQHz/GzeaMqxGUmqIa4VzB8vQU3XrqFEmLc6J02aGjqvFViRQOk+CPv/rHHJ8D0SLG904jgZRahBxaYFSJ1RpFgO6McL6EpiV27yOmQfmWtFySljN0aNASemaToaOqQkFY4ZsVoZmTUshxdUYTY+/uIzmI3hqNsxqlMlh0DC2lURzt73H/zp0tyLgcg6i1A7VJgXlxdbhurdg+nvr5dZMjyMtR5rPPIw1dWhkkS5qDrUvrrMrP1SqQPB/pHWSssTkr+GuQwuATz8Q2XmkvW8vLs6GXo+uG9vNe/+JPY3vnp9Zef4Oqbv1vyxa13aoaSis2Bu3nbfs25XqN0uV5tbGLwTrzLxqjcyYoMZG6ciAFq6Zk1ljSKtA1ifliSdMGUI7D/T3uHe1z92DKBybSCHgRgijmbYNaKuarFdPxCAkKfxrwyhBRtBgezTvefTJjMj3hS5+ZUOaEXoTUolQB5Bin1oNpA/NVg3UtqlOopTAqDRqBpMBkmCStQaxFp4QWhSuhLBMpQBhHlnOFSoIPHokBFVusBKwG5QzJGLQrwDpEKZarU6T9kOgV8/OKmKbZNpgSShROaYwtWaU5ESEqBURUyo40q5UneiEGhRaHshrtDE4l5OSYNDsnxkTpRlhdIAkWjx7jfSA0LSo0SPIko9DTKVKURDTLVcNyPqNbKogjIOTUMTaixZN61YlWjpQ8+Ai6RVYaFTpUOEdrD6EjtSsILRI7koQcV2eyjavQYFIHYZVtbT0TSzpnxh7yhzltKYzFWY2klpRaSC06BUZFwXQ07jdzaWvDt5lHoljPi+vHvdr5/SK4Wj/Gd2wdX2bGP8u78aKLvdpqatuLcphrinXsaP8Y1OCtKZtyyCYt08sjRmb6hDOxTM+SSm/m/Lsf5etyC70qpexuZ9jJ7coZvbP84OTwrHIXylx1k1Wo9d/tSam2ht6GuW3ZstaV9qlAdjzyXY/0AjzPMzvf90Vv2tx2idZGg2zcsTUKVE4oGbVQ1xkrMTGiCQ2iG+Zty3w+p20D2lZ87s03eevuIXtVxcTkuKGQFF4pEhppG772jXf4wt0DRrbm/OQREUVQWeY6buGrD09Z+cBb938QXWmMBp9WWG3QqkCpEh8iyyai53OKqiLpQJAVZXWIjhrlNVQdyuagZu0KlCg0Bhs1ZZtQSdBBEybZ5jdfdqR2iUmR2ibqQudEnNpR1GMWq4b5csXJo3fojCIWHf50n3b1gMJk9JLaFFhrsaZknoQAGKtQEjITi4HzdoVOJUaVVOUIW2lM6ShVpHvymHB8zLJtOXBvIKrAt5Gz998nxo6YPCa2SAiIKigOjgjVGI+iOT2jW86JTU6BIj6icsoylPYMUWrGOEJYEkMDdgnLCDZi1QqtIhI8qWsgNkj02XGmdmhncUVBaaCILV1YIO0MkZ6JGUNKMSe3jJrSWipnqQpDjCtSzHWa0DEuHfuTMdkWxhqGK3PBfvEedlxb6DJXWZOwQf+TdYkBDfO61eJinjF1ewlnx253+9pdwchqYETr67YyBfa/B4ants4N0pkMUtl2PeQZ+iro24KJvSytQzy+A+j5b/OT8mDUeveqev46yOkiskatL6zl6GAfV9SMxnOa9kP26pLFvGMVWz73YJ/CCMvlMU3s8KKJ2lA4g0fwTcfD9xZM0YzHY77vh77EH/yfP2bVdkg0qKQ56xq62Sn/627FD759h/07Y0YxEZ0DY9CFIXQtPgROTk7RJOq6pB4VWJttedWoRMRjC4OxFm0s1tgMkZVAxiVGgYSO+w+OKMcVYjTzxQxJgjUFo8k+IRnaAA+fnHJ2ds5ssSSGgO/OiVIz0sc0p08oCkXtDtHpmJQi7XyOw6F1REzCaYuElhASMQmTvSmjao+yPCDogCIRzk7w83OkWRKiZ3pwyKLznM8WTPcmnM1OaBYtXiI4hx2NmR7dp3FT5p3i5NGHtLNzYqvIKP+J1EDSGuVKlFjAEOIxMcwQGtSoI7YRFSNad0SJpOCJqxUkj1KSMzGTc69VhWFcl/jmnK5Z0jYrQkpEpfrs0ZKlBQmMq4L9Sc3h3piOhqSFZGHv/iH7eyOK0q43mx8nugzt9Dzqu2uRObakq20HrV3fb6p3+/enNrFXSN8pDOxbTrv0tmo48Sppk3NsmDhaG4gaVMJoTVUUTEc1dw73uX9nn6YNdJ1nVAQUio5AJ0JUGpTBID04bESicHrakHAcTSfsT0dYtWK1yMHFSkdSEM7PFzTnE1JZU2tHqzShtxnowbYVPMvViiQRITKfL7PSSAtGZZtYjscy692+NgpjNbYwVKMSVzgwCi+J49NTFstA4xVtciyayCp4YuhIMa7brgqHHhn26hYdlqArjJsi4QyCR6KnNAXoDiESQyL6SAwBUxTYwmEKhy0sI61IviPOZqjgcz8LRxc9PkXEKCaTPRbdgrTqwxqMwThHMRoTcEiXWJ6fIWHRp8ixvVStAJMxI/uA8GQ6JC5AZa9DYpffiwkgAfEBQguSYaOynSbgTEFdWqrSEZX0TgisMRYH3YMWQUugLg3jyjGpC2btio5sqzzYP6KuCvTHbN24jpHcBBl1Uz2DfYveRJAdVDZOVZBDCLL1QLYUN9e0cVFhc32556RPmdgL04tb0nbtQC7Aubxol16EBC4nNNuJnbYu/5KeI6+T1FWVxaCON8ogqbfvicIZw7iuuHfngM+8cYdm1bFaLKh0RyIb8luBqE1Gz7Aa4wMxJSQpzs4akrZM7nkODyZYEdJ8RfbUzsZ533jaWYd3La6wBK1IGqLuPdp0DmBetW3vxCHM5zmVjNaKSuu1gsaYHOyrUGtGZguDVhUpJKwzaKM5Pt7jvGiZLQPnK8UyBaJvepikDKFUOEs5qikmBfvjFhsWKO2w431Sm6UWFQJlPcITCUkIXSR0gZgiZlyCNWAVyihG1hJ8R5zN0Snm/rmCRbuilXzPo+kYc14QtSIqQ7QW5QpcNUaLJbUNq/MzJDS9TbUH2U0GYkawV73TRIozkBWYgEJnNV/KHppIRELIecNEZ4APpUEizsCotNSlY0nGP8ywSSon7eylMC0JTWJUaMaVZVIXNF2WzkiBw4MJVek+Nkwsm56uB+nNZS4xpkurzLVS22DiUqw9LVWvuhp41sXju/s4KEo3CtBXt8p9WzKxl3PUuC29vhYu+Sy8HD3rYaxH6M1FXnkXXvFLGuwHWZ2o1nYyYdtmZiAN1orEqLTc2x/z5/70l7l7uM/YCSbOSKpEGY03FdqOGI33+MHv/Txf/d+/w9nJKcqMWUXNycmC89/73/zoj/wIE1ehVoHz+ZwkkVIM3//2d6FOTnnnm1+jjYH9H36b8s19osp+GyklkoD3cb2waK0JIeC7jkNVk2JBCjmhpzYZmd1ojaodVBarDc1igdKBovE8uDvGqkTXruiWZ+ikqQvNtC5BNGWleDC9i1QHYCw6PcIvRiAOc/BZvK3QYYVFqIwmJWgk4ZJBa0dEOD0/p0uacUiY/ZpJWeFD4PjDR9S+ywy/Lnh6ckybBA+sugWn81O6GAjWYMYjiukUsRVdE2nmK+ZnZ0jKMGGipLcvFWhdUajMpEQiQY5JtKAidBpkhahIcuRNVswI86iiN0kJSjompeZoWlE7haSMtm6cw9CrnEOAlDASKHRiUsG0VkwqOJsLKgUktjx4cMRoVPR2q48DJ7uBYcGtVX6Xr92uY82whr99k4OE9qw1ay3EbXX1VWnAvi2Z2MdhWG3T5fX6tmkTXgnd5mEMA/K6UfWSfdxZ66t+SdfMIq01gmRvtj6WLP8FoxSF1RxMKz734A6x+wKlmXPWwKJLKF0QkyJF4WBS89a9Qyod+fDJAm0KktZI1Dx89JRRWXP/c59h9Udfw2nD3qhkFBJxvmB5csKx79DnB6R9hzUVQXJAsaSctTnEhA8R7yOt9milqZc62/ZSzn5uHSgjaEOfP0xhlIZGUDpiTeRgr87XiOLRkzmdEpy27I1HVLUhYJFiRAtE6dB+BWkBcUXTNaCqbI9KAqntQXEFJbq3y0FtNCEGFqsFlZsxNhrTtKTzGZI8mPwy2qaljQmfhBQ9oc8xlVBU1YhiNKYJgfmyY7FY4psuJ7nMOj0AjFZYrdDS9UHYHmEJ5Lg5FTNSh1IRfD8AUl5c1SC5KrAkageT0mAIhK7PFi+sE19KTBmw2ORyRwc1B9OScWVwCkx27WF/b0JR2KzKxFwddN8iug4N48Lx/tiNDOcaaW77/ObHprLnxXV9VfRtycReD72E+vByTR9RoOJ1bV7ckd2uL1mF/Rz97tEzbln41v247urcZO//1VeVJ2JWKaWQk16uDfdk1HhnFJPKcP/OHlZ9hmb+kHjmOV50KGWJkd5d3HD/aA9Hx5PjM7TuvcqS4fGTU+7eNRy8dQf3vmNqNfcnI9yqJS6X+PmcmW8YLxe4ZoIdl8QYSJJ9TwVBJQh9LjKvIlp5mpVm8BItioBSCqMEUQpTOLTpd9o6oQw4p5hOSpQyCIa6fEiIgohCj2uSqUnKsUyK5D3Kd+jYIqyQuKTtVlRmhNYZUivGBokBYg5TUEqjtKWuHbNVQ9t1rJYLxBWo1QpZzCF5RGcvv+y8kpmY0Me99ffjqhpXjTITW61YrBbEEDMT1SrnRTMaoy3WKsS3iHgktsAK8FnuTqBIiEpI2tS/7q8ClOCUUFnFuNQQO0LX0rUNSbL3XEo98ghCYRST2nH3cMzRfk1dWZwWrAZnNONRhbP6+cbstcuHuub7rt+Xzu6QrJ7X7nUbGqby88d4vVjfnpe+I5jYizy8zZgbvj2bgV3eiTwPRtjrRqS+3B/pF9BbhSfIZV32s1USu9q9mZ6DkQ3192676AFsdSsN/NB2H2SZ3e9Nf42ARIyARqGVcGe/4nBacfIElPOs4grSH6FEgSTOT55w73DM/tSx8p4/fH9G14LTFTMVaJ+ecBxWvHF/jy9O9/ju0Zjw3jtwfoJNDaHwiAWlM8KB0RYk0oYWaw2iFCkpui6iCCilOT9dZuSQpFBKU0uiEIctDcoo0OC7BmWgGhfsV4csZy2uEKpqxJe+53M8fDzn+NyjykMWHaw6wYeADZkROFFEmePDCW3zmDc++70kk1iev0vTnICuqXSNJTFvl3R0HB4ekZSm85HFcsZsscIcn2GWS1Js8dK7yHcBnQQDlErjXInTsPCBohzhqhEnPvDw6WOOz1ZIOYFYQTSgNWWtMSYz9FVzBskDHumWqCKHHkgXwKQ85rTJ9kOtsdqSrOttYpGRU+xVmmkJ3eKUxfyMxXyen2+/qSmMptCa6cjyxt0xP/h9bzOZjGhD4GtKmNY1o6rG2hzg+1x72hvLXlIHbq03182IC2q/HXXfOOf6qXYbjdA2GPJt6t8ud7HIJiRg+JvkKtTXi9Anmond1k3zRdIBqB3fPgp60d3Ks0T5ywN2A8x5i+xFzyVVXb3upntSl8tv951Bl/58batLsTn0GIYyLA5K9/cj2QWbtA7n2Zvu0SGspOPzb97j8fEZbbfi3W++Q12+yXhc8uAz93m8Sphzj19qupBYti3drOW+GVGlEQeSmD19ivZLtI5U9w5wpUNSwrcd2CwhOlegTQ7KNlqThCz9BaHrBL3skATGWlAZLWNsKkLTgoEogaJy6GgwraeoVLYbhcCdowOSOIxrOVslCquJAjYlCpPxDrV22dYjS6I/pShKfFERdNGr1wSjFW3b5ogmrVicnTPa32dcW1ZnC1bvn2CenmA6T1EXJIHOB0gx5wlTOiN9BEEMjEZjtC2IaNqYWLUtbedB1UCB0gWmKNA2kNKSEFpiXORUKhLJ6JbbUUb6kkq8T9dCjllUSqid4mBScG+/RpYrku9IKZJE9+MkB/JriVRlwRv393nj/h7OWU7P58SuoypLqtGUGBPO9qrqLV+Gl1kpNkP/4ibsss1tp/chzyMT3kahuGs9uay52dbsXFeLXPp+fR0vQ59oJvYpXabr2dG2y/mQqA56Bn9N+ctuuRcZu+z4fvHn7SbX9aXUM7nrhmTr//X12wFj66oGRjZIc5mRQdZiVWXFNCmOQsHn3jjCtw3HfsnJ6Qmz5R6usuwd7HOwPyOGFWeLgAApBrwP1Hqckd99x2KR0dN1pRlNx1ib806FLqAwGenCGlAK1WdqlpTzkIWQMk5hG0EFqjb0/RSK0qJsTkGTUeVtxrGLYCxr5PxRXTKdCj4ZFl2DTeASWC1YLdmcY2yf0ia7rSeJiNJgSyT2ar0UCSmibU4TE5oGs79P4Sy6LAnzJWm+oBLBOEMKiRhDrz406wUxpURUUFQ1GENA0YVIFyIhZvuSMgXGlFhXAouslvQtkjpUDx8FGUIqpz5Ra2kkb1OyGlFgCzVNKJ1iOio4mFQ8PTsjRZ+9H9HrcaL6sVAWhjtHU/b3KgDOZwnftVTjmr39g96k2rc7jKWPIE7nW5P89zIj2vV3m27L/J6t0bktfQcwsW/Fi3919GK7rK0jW2rKgXEN3nvXld3+vWZyWyq8i8yy/75t612fuurl9FwTUb3E21tL6VkKQ6nexV6vsx9nLL6+nwjohDaGsXa8YQr+Pz/4BZzq+Bor3n96zDsPH7NKwvd87/fy9mfeojCnnD7+Jk5n1Z7Tiu974x732oA8eUKxahALuigZ12Ocyagb3ndE0ahocMpl1SAO5yySPCEmJErvUg5CYrFoScn2zg0de3pMMXK4IrvEozWUNdIKUXJ8ltYwrkvAcbYIJCUkhDIqQsro794VKOVR4lHpjKdP38NIwk6OkPCYtPLE7hxVG2yZU7A0vmF1PoM68sbhfT5Y/T4sVkysozUKHxKd94golAFlsnONj4FOoB5PiMaxSsKsi4SgkWhBWVxVYV1J4QyL5YLYzUndHNQ6v0Bm3CaHGSSjwPRMTCS/Ty39h97LURhXlnsHE966t88H/+f/ELqmR653a1sqIlirmE4rPve5e+zvl6xWLcE3zM5nTPbuce/uA6wteka5hU5xYeDfQM/amF17/kZXjGe3+8KkuIgbdJsZeRPjum0dt6fvACZ2lQ1sj5PXmXX0Op3z7dpU6z+7St+OGWT38hgjTdPkNAnrHD+DTewWfeljQi76yF5mZPTn8nG1bUe7xmtq08t83Q7W+MIuH5tFJX8y8n1vjJfehXsgnR0+lEBUXVYpOcUXPzNmtbqLMYFWB06XnsUHp9jqMZOiyskQXcQSqYBDrXm7rChPn7B6+IhaWdoQ8cvAyXsn7JUVpdWYUUmUnCxQvCKFREo5+7SVnOpdUkJFQfqFeD5bkqIjRoe2jq71OT+kzalRBNUDAyswlqIoKVyfEMTAnaME5w1JtTRe6IwhJaErQCmHTZaCyKNHX+POnTf57Ntf5I/e/xquWVJKhysPc+ZkSdzbP2ThO2LTsprNofXYILjC8ng1pwuBpBJRGXSvvU0S6CTgMdSFpdXCPAZO5iuCN2hlKcoaV4KkBavFjNA9QcIKUoMhre2z2gna5k/Sqc8xljNNK0PepGgh6cz0lIKD6YiDac20LljOTgm+zWOu3ygNdZelY29vxJsP7lKWitlsxfn5CRmZvaCuRhRlDSKkJBmvc3vMXVIH7h6YL3K+nyM71pFXwRKuXwfkmg3v0KcdV3zEcsN3ABO7Sh+tlesqw3keG92LLuLbV2dPsyH1+jVqwOHoJcZ7e0y2TX0DA3lee5a65vvtaXs5GZaULSiqwS1FwQavLq0ZswiIiqAi1igOJ5o3705Zec83TmYsT2Y0Hh49OcceaGIMYCN1oTmoDA9GBSPfIasVfrnMea76PFjtacPybE4qDaOqyMxJcj6upISgI94HjHHQp5uJEZSW3McU0Dqru+qRwfuA7sAUar3RUVERBVAGYx3OhUEOZTyqWHaRNgSsUThtCAbEAsmglMbExHJ1zAF3qPcOESqUzDEq4Ek50FkLdVkQkYz/eH4OIWJ6sXnlO3yM6Mw+EHLgcBcjUYSkFThL0Jo2CvNVR0oGrQzGGJR4Ylzg22MkzqBXI2rMEBmRn0n/kT6xnKhe6tKZ8Ssta3uY1orpuGZcF5RW0ayWhODzfFAD4npCSZbEi8IyHleIRNpmxez8jMKVFEWFMQVa295hKG5UibeVwj6lV06fcCb2PHrVXQu23i3lXFP+ZlI7f+3UGqvLZ26eANtnr8qUt+iZGrL96rVDh9a7VYqXr7tgM1NZwtr06vL3q3d9XcyJyMVy25e99FxXO36u685xQ5t0lbrXJPUqKeVROqGTMK0sn39zH1fX/J/HC1oz4Wy24pvfPEY3gRBbkum4f3DIZ6djvjidkB49IZ2cQttllZ1yWNEsTjuO339KEVve2h8jbkDsSKA0KQpt21FUNodIKU2I5BxkQUg6IDGQYmA8LWlWHVECSUVcjCixpBDRMY9r6xxVJaASicRkXLHyEZ8S80VDsJqAIARIJSoYbILgTxA6inpCWRxRxgVFmnG+WqAsqMLgrGHfjlmtWt792jschohVmhAjy9QSklCII0jEiMYklZmbNSRroCwJxtAEODtfYmWM1RYjgm/PCN0ZqXkEpskpYFCYNEIwiNIkfJYKlSKKkLmWykZULfQGM4SYn4XV3D3aZzqqsBrm83N81/X24X6DR8SS0GiMUZSVo2lWnJye8PDhhxwe3mcy2cOYAumNbdtOF2vJ/yUH71U3qxercDM7t66/7V50u/Vdro/P25drNsKvysb3CWdicMWYv4shXCvODIjTV4u/WD92KbQvOU5cHiRb/18+uuuCZysQLj0PRYYGqiusGdQuudizoF8GFQvQM68bDLmyzcDSNffQ3+32vJLh/PZLGrbc25JVb4FQWxUMa4boTeJB8mKWkTqGuCENxP6S/vigTiWnRslGelCDG36/IE5GmjftiP/n//4S/+33/pj3PkycMOXh6RlNt2QVGu6MRnx2POUL9YSTd96l6Rb4CRzeOUJ3oJpEebyifbog+I6TsmT8+QdoU+JjZGwsOgn4DooMzZTIwdgpJgJC1AkfExGhbWHZrrCFZq8zoFcUxjG2NYVz/XMSqECpiNKRkAJH04rCKGLbgu5IbWAkgBY6JXQIVoTZkw/4w//1Wxy+ucfy6YTj42MI2aaqkyIlKK1GIbjlAmUiwSZmIaCSBRFaUWhJfSqUnEYlFiWprlnZCZ2eEBFULHBao1PEN3NCOEVkiTERJVmWy96mYc2ktFOZOUvGuUxRQBTKZoBgeikQVYIKODrePio4KBSp6bJaWITWKELI0rCSiFEL7u/d497eCGsqHj894/0PZzx8MudLP/DD7O9N0DqsN3ZKX5qd0qvS16LxpRmgpJ9Hmu2glVtvTbdNC1s7M3VpPvU4NTtWol21b9upnr3y3eSWvytm7TINtvmUbpuf49n0bcDEnk278/AMdN2ZF92BvOju4rrrdh+/Rht9DZtRGLPlhnxje7dp51lXXLeTvJ6Zbc7LhiFemFc3ybbD+YFJZ4YrSmU10fqadKG82sqFNEhl2XG7Z8QKjIG6ULx5Z8Tbb+yDJIKPLJcGokInGDtHkYRwvkCRw5wardD393EtsPCEsxU2CLIKNE/OKI/2sVpjSk23WGKVojAGJTndSFKgeggmyMjxIQUSiVXjCcljOoVRHdYqlNXEMoJ2a1Og0QZrwSXBGkVVaCQ59icVixBpU6RoBa8TSWk8QmEssWs4P/6A+597m66p8WclBYJOoBIkEYxkhme8R4gEFYnRo1MOXwiS2xUtSMowW7oo0PWYqAsSPWyTKVAxQfKksEJiA9Kh1ea9ZQYQEZXVf7qPkVNq8FAcJOzBtT5/RBk0EasShxNHoYXQdrRB8CJERfZQFEFJwqjAXl0wqSuscTyatczmHV0HdT2iKByaDGmV0UCuSSVySS9+VcmdB/ZFprI9K29gKDsPb8qrLRvW5Vl4/Tp4+03xtaVeJAzmFdEnmoldXi4z7VZdPe8ze1XPWK3/6/ty6fduq+muAbir4u1qZNfhrfoubwtvpmG3ebl325Pwela6zXDUljf7szYMQ70XVSDr97nWWl5igoMap1dbbP/r3Q8vLBHbCQcvMjBAzPoMKttznFHcnRZ83+fvMa5LzmdLGj9BLYW0WDItHDQtT5+cMC0LhIJGIsVn71C2oM5bVu8/pUyCtInZo1PKo30qoDqccvrkKaVzVAeZSWZkR8nu7X2/RYPvOjoP57MVSULemMQV46pEFxGfPMk4lNEoozJkkzGIA2c84jRaLHcOJsy6ljZ0lErwOjtINChGZYEPnsX5I6aHX2K5HCPlCOebbANKiSg5eaaJEes7EoEogTb4vLiL6u1M+R4wiggUdY3dO8DbgpQcQsK4CmnPkZQZmEodENBDVuv+rcnAxDSg7VplqLUh9U47SmnAgNI5TACD0gpn4e60olDCatHQ9ghVsR9EkvITt0QOJjX74xFGlxyfLDifdUQcVVXjnEURMydXz4Kb2lY5btjdZl3ZzOpdzGwjXl1SWe6gvGfbnltXpbD11FmX2JbArvbpwrXXSFTX0U1gB6/Dke4TzcRenG4nOn9cqn5NPb25zR1xYi/ao2c9kguBns/jTHIbWrtPwzaDzCofRbanDCpQxYCFJ1pl7VVSWKAyigdHe9TlCKULfu9r3+DsvKJbFexXDlkseXp2SldoZOQ43L9DVY1xpUKVFZP/67M073xIOJ9TNND88YfI6ZzqrXscv/ceprR0byx5MHLoukC5rOKMIRCCxwePRtBKeOe9dznY36OuK5Za58SdXYd4j9KaonTYwmGtQRvBiKJwFpEAkj31HqSEKwq69pjBCccHQZuCLgg+glIJpQVtFKqLEGOOZwuJFIXUdsSmQ9qO2GVA3WT6MI4+i0okO5t0SlO6gnJUY+uCroVl6oiLY2iXEFskNdnVn5Db3oyKfo/So1PYnKVZaYOyBi1kqdv04RPr/VXEWZiMCt588wFp3vDhyRO6zpNizkYgMQdQK5W9Q8uqRpTm6dNj3n33PWaLBQcHB4zGE5zrXesHSUy9Siz2G+g1LlcvQ9thM68LUuo29IlmYooX5eyvcUR8DAfbi9LFODFeWFP6Qm/oeRFWrnEg2WxwVW8H7Bc8FFuGtPxbbaSyfImgdPYVMJIyqntl+dwbhzSrBYv9itROOWwjzfmMJULrAzZaCjFIl0jOoEqLu79HPJ9DiMiqgXmLCHhbUGNwRUVV1VmqiCnDUxmdXfFTomvbDDqr1MbTtMf863xAJdCiKcqOqBSl1iiT7UNaawrnMsRSzNdMRyVRhJPRgsZHvE8UBkRSdnJBcX52QgqeuiqRxTkoydmkUyKGQLdqiN4jIWfARpFBjVHZ9VzpbAtLIIVDlxVFXVNMJ8yaGbGZocKSlHoJTDwQUH3ers3+o/+ipHefz5+sNVSb96vzniRfk22f1ihGVcF0OuF03jBfLHIcXspcVqWUq9EaYy3GWmIUTs/OOJ/NSUnY29vHOYfR+Xmup8FLzInnok/ImvI6w5Vuok80E/vW0uveHl2t/1u2IVNqt9pzF71wJ/OKsHNHd8s6r5ca1eb8UJH0i6Ma1D5kTyxlNtcoWZvgrUQcMC4s1d0JhLu0qwkqdKzee8RJ6Zg5Q2g82gt0gl+0yF6JqSz63pjiZA/dJdKqRVYe5SNtEvbuTykne0z29ogCEhPKKBQxe8+lRNt1GJOR5LU2vaZOSImceLJPAW+bLify1AZrsxeqUpmJhRBJIeCJTOoClOZgWjNbzvGdUJocu5a0RkRz/OQRRmkm4zGLxx+iVEIn0DHhVw3tYknsJUBJCa0hhuw1aLVFa0VM4EWgqLB1TTkesb8/4d33H9POT1BhiaQWkYDC958c36W33xd585ElLkXKWsNeq9e/xx7PsLeIgkQKo5nWBePJmOP0mPPzOSnK+nkpcr+t0T0EmCPEyMnJCbPZnLKacHh4iLWuz4gAnxiu8hrp4yKFwadM7CXo5Qbys9flHbrpl2rx9vRSA/QFGdg6jmtXm89R5+VrBxvNxiOsd9xQveVpYGYMEtqGiSmdDf6khCRPrYWYIotmwduHBU2VOHl4iinB3T9gar6Xd373q/hlR2hOqUcVo88cUt4d4yvF+LN3KEcjfOeR0znEQJitMAcjtDGU0wnnqcmegJJQVvAhq+k67wGoUsmdu4doozNCfdPirMuxZtET50uaEOlCtq2VhcUZgzGaqrAYJGd5JjIpFF948y7NKqClIUkiLBtiUnRBcXYauXd0lztHB3TvWoJvs1t/F1idnNIcn4CPqJRycLvW9KAwOeZKlwiJCIwOjhgfHFJPp6yWMz5874/48J13s0NM7zKvdcp1kePhBjvu8H6UViijobC92lD3aCCZuSmdbWECpARKAuNqxJv39hmXJatVw4ePnjKEWRgRtEoU1lKVmnrsUMawaj3zD+d0PrC3X3Hv3v08NulRYPqAtZyB+jubbjY7fDT0yWZig176tUsJz/a+ueB6eotmPnl7udenO3mVWogrKsVt+7iojcF8iPXpJbFhhy2SvTgHc/wAWeWMyjBFCkYuq82USYTKMA8rbKG4+8Yd5g+PWZzM6JYrlo9PUZUGJ9h6Qqwcek9RPbhDGyN+ucKHjoPJCFuVeARdOHoxEaUUIQSatsH3TMzonKgSkz0pRYQkuf8xgfYZAV8rQ1kW+bzNqWQUYEzOz+UlYJXhYC8jWfiQaHzDso0Eo/BRkXTqpcFAUThiaEkhELsOv2rxTZsZwbCY9+7TPdLTRtrVinoypqhLtFGcnJ/gm3nO4tynUkHlVDlq8EqU/hWRJcm196HROat0H2As/XNQKqtPU5LB0x1NDkQ/mtZoBW3bMVsss8QtoEQwSvoqNUXh8D6yWK5YrmYobSjKmno0ZnvGDjnKNgNriz5mE/s6uLfrmM+z1rmbkHeuW4tfGEDhlvTJZmLPSxee+0XvoFc59j5m4/i56VpEkedRK96CXiYf0vPQ+v0qtQ5U3bhp9TawwROht51lPxANffbenMoloBCcNfguoHSCkeMDAsYVjKsxR3eP0F3kbL6iPZlhxgZVKab3xgSn0ZMSd++A7nxOSoFu6XGTEbou6Uho6zIaRMyOJjFGfOfxPsdEeWOJMYHL7uQZhSVLCSJC5yNKBbTuaNouezsmg1YFRmXbjzWa6LMnYVkVHEwrOh+YLVoKk/D9op4MSAp43+IKR9tA6CKh7QhtS+p8RuqANRqMHsB3ZXDGAGU0o8kYW1gSkfn8lOgbdPJZrWcGBHm59MJ6l/nBnV1n+54yZs3gRA+u9QZtHEhYj1GFUBeGw0mFQui6jsVytbWv6ZmYysk3nXN4H0ix43w2oyhLyqqmLOuNWlNdDHIexuxw7lXSznVJ4LmQsbdol5biRefai2QGeV30HcHEnuVh9/F4FdfTt8IWdmGwX/zvFuVvjszbplc1ES7vJi/Aa/XMS3onASX9wjeooSSiROcosmHlXTt9pN4NO9toQJDksTphS0VdTvmeL32B48enPHr/Az77+TepoiDnC5aLGauHx6xWc6r9MdwrkNqh9hzqs3cw05Lw9Clxb0SoixwbFgNGZSeDELNKUPcOGiEmQojEkPAhI7BbY+nB2EFrupjzeImAVgu6wlEWFgWMqgJrDEVZZNVhEnyz5MG9A4y1nJ3PWXqNkN31PYFmeY5frTgc1XTtkti1zGfnpK5Fp4RRCh+zyjUH//boMMbgNRhjqKqSO/cPWKSW06cPaVcNSgLO5ISjUW28QRV2y7s8MyelNQmDcRopDFFnmKwBmFHpbCc0tsxq1D6Q3Wk4GBd85v4+MXqWTct82faqxhw+URqL1pI99o3hfL4E8SwWc7701mc5ODhCG4tIzlU2SJsDwxpG72VNzKugnTNjxzy8rr3tPt0EwP2izOy5IOVeI8P7tmBiu3YY2/StNDo+i9ZIEZeOX2Eit6hnF73qe78NqPHzqF4v0vP39Tq1yPq36iUtBh3XwLiyNKYGKWZ7dyuwHWuUL+8zQ0PeCfcMLUlitDfqvQph9WhONJ5iUrBqFSom0jJw/McPKbTBHuxRlQUyrVEZgYm2UAQSOkWs2A2eg8pMwLkC50L2oDMOHyLGB0Chtd10iR4nMwk+JNo2rB9p1wWsMeAMyhiMK0g+sGpX1HuHHOyPuXfvgLPmCV1Q+GSZtR0hRIIEvNMol5Hsu+UMvEeFgI6xh4aS3llQr9WZioRRoIzk/FtEUvTMFzNCGHAdc6zXBvBF90hg/SYjJz0Dem9LY1E651YTFIhGkiJJtgmm0OshtcYgjErL0XREs1qyWq1oWo8yFicJLREjCaNzULvWGh8iSCSJ4uDwiMl0itIa4ppdMcR+fVxXlW+lhPS8MWWvgj7RTOzjIs7eRLulqIsL5ovcxk7Gt7OtbwG9PvPZ7uZuo4sfnDXYSo653ckBvWP7Aa7RHwS0RgbAD5X6dC7ZC64oHePJCHziwyfniBPM2GIXtkeqFxaPzoj7e5TGUk33SJVDtGAKRWcUloRNCZsg6bxEJgVKa4yxWOcw/fcYJecbUwnnWNuQhnvIjCz1qsVs92u7kPOZqQxnpbVFaSHEBqMVdVVw52iP9z48ofFCmRSzlYckJIFAAqPRzhBThBBRIaJiduoYlvWhvczMBJ0hIjEqMzStUgbgTTFfobKb4eZdDU41pvce1T1eYt9nYwA9+Fb09ztI3yG/o37jYhRUzrI3rnom1tD5gFZ1ltwkYcJGnZidZTJTNs4xme5RVaNse+z7ptgaNh+LyfYpfaKZGFzdiW+nJ3hlY+wlFuTdfVDPKnC1/VvYjz9Oc2rtMLFDWnvendnV288M6Drp6+LxflHsF7ZeFttU3JdRF1zNehWkEgTLkCWYPhUJSkHKCBIDIHJVF5RmHz9fEJJn4ZfslfeZny1YzFa0py2zrz+kPV8y+h6LlIY4KoglGSREBNujXKSYMrCtyT3V1lBVFdaYjFCRoPMR0BQuu4grwGjpJZTsft+FQEqJ4HNCzRADZWmpygJrHNoqjO1o2xbjSr7w9lu88/4jgqwIEpHYYGxN4SxNDDk3mDVoa+iCR9oWHfwac3fw2NPaYIzLgLpGoRwYGkZlhTeWZrUgppSlrB4OTdQWg1AGpS1JNm71qWdsStschiBkFbGQ30mv+cUYwKDQOK2Z1iV3D8YcP/oGZ+czmjagSoPJiku0StnZxRrKsqSZz6kKw917D5ju7VOUFb03/pX59RHv1T6la+gTzcSGRXFXoOuVAfcyUpta78FeCV2ZEM/iuOpimZuKXzgn1565Zcdennapdq++C+nPXVPHpR+DNeLy5uW6vwMj29SmoWdGm7gxtVV3lrCGHX2WAui92rJbfj6QQCI6ZogkZRWHDw7xRDortOeB8d27xEXk67/7VdKZh+6MY/Uu488/gElBsoYBsJWY0fMH+OQYAklSBkuVHgtS9aVFCDHSth3WGYwAOmGMXT/flIQ2eFpJQCRETxUK0AonWfpxZUnnOyzg6pq33noDMScs2xOm45omKDrfgtJZZagVZVXhtcoI/H1OrST9U5OMCp9iRGzCaINzmtAuCCoSkrBs5tn7EYMoyyA8GWPyayHHuaUY1yrHbB1UaDQxxPX73+ghswrRuQpQxCSUzjGuCqajig/PzmjbFm0sRlu0ZJgxo8Bqlb0XO0+SnHn6zTffwrmSIUv0x2uL+Clt0yeaicH1NpHLZW5LeS5ev796pr3tFozguRjYjos2O9ZLZS6rJre2ittZaK/QUJe6euhFSF38b1PnDgb2Yvryi5LYTXYx1sf7a/pF8YKn4potDt82trN+bc5qr/4MylzwbdU9socSKEclo8MJkxTwaUGVakylmO7t08zOCEtPnGekCxUdYvWaMUpMGcdPK5RWSI+uIalna8O77NVnKSW89+t3rmLqUSXI95cSMSYkRdrO51xbCGVVANkZIqvtPDFFfNdxeLDHfOUpn8woC8H3qsM1GqUC62xGIu/b1T0bRnIOrxxInEMQlDJoDW3T0CA0IdE0LSEWmYmhe2/5DCOVUlq7wKc0JK0cshL0nwuJhvu31jt4GFsAkLoOpxWF1RRWs1wsCSHDZunewzBLjaoPCM/hDM4a6nrEwcEh1uYNgaQtpyFebEP7ulT9n0qC3wZMbDe9+KvdrPuX69js0W9s83lH6vPqJOSa77do5sZrLh2/ehuvXnnyYrVt9+z6TcsmnoWeuQ9WG3p+sM3ALkrwmd9d3BFI7+wB2fdgWNg0YK1CUiRJhFIzubePno54ev51RByuKvnCl76H9//gD1nMz7G2RHwihQhVkRf/JNnZwQnGGqyzRIn9ot4v6DIglAtJBIkx16EEh0JpsEbW6bW2YZDbkIhNh08RV5SkZHBWsE7jrCPGxNnJMffe+jydh0ePzzlbnNEG8BF8Sn3SyaxSNIVFrEXRre1hIokkCZHYI/xHhJwz7Xw2Y7ZYcNIl5oslkjSIBVEYZXqPP0MXmo3k2TMxtCKRoND5Y4YXq/LLUCarIE2JKytSiviuwdqENQmjIrPZgq4LGG223nrO7mBtZrS+67hz54g7R0fcvXMXZx2spcDLmccv7fp2js9njdTrr76gDX9G+at1fyuNdh89W/1EMzHpJ8wwsW93Ebd4t7vqepG91FUpTQ2r5BWeeNEp/XrF6OWaNwN2l4S2vWscWnhR2efKsetsXOrKzV1b57aq5qIKUHKPd1Sttq4ZVFhqnYJlu+3BiWMjRXD5KSuFwjCkcBGJ6xVEQUai6KUt+tin/NksYl1fWrRBSFitqUvN937P5zn+8IzF6YLirRF0R6R5iRxOkcqRRPBNiy4cUSs6pViGgFOKQhSFKTDKkHQkxpjvJEWM1tmJAVBK8EEQNCIWrRLWJpTNbu6iIMYMTZUCRBHO5ytS0lSFUKsiI0UmQcdIWC3YH5X84Pd9F09P///4LhJ9JLUKYy26NEiwFJMRRRsoWyE1K1IKYLLdTMeAFvBosDWqnrBKJR5LlIQER/AJSR1WayQFggKvhBDTIGqiU5+XWgnKJAiJ1EUwDq2LLEWaCooR2ALlHI0KIC2Yhr1xx6T2OBM4nbWsWo8iUetEjILSmmpSo63FWkNVOj7z5n0e3L9L6cpe4uuldxVZ65uV3uBvXvjore/9CBpiD2859243cy7SgJICG+aXg82v5uxSmi0V7EV6FV6Eu3w2854w2y0H8IAB0u1V0CeaiW1e9YuIJC/a3kWd23Wayp0DYlD7XKhCLp/eQWrd9FD+Jia3ZlzbdjQZVGm7k+Xd7rGoi32/NnpfrlUnXmlQbdjsVdXg5lltq++u9Kov21d3yalja85eKLRhoBtpbag+O3oM0lb2uuuFs0vPYxODprJ3g2RVoFOa6WRMs2zxPgc113f3UHsjgtV407PWmD0JhxsNSdAxkbRgjcYonfEBZVgIZB0HNXQmScyLMorQ24vW6BYq94eYs6KQhC5k9aJGUbicrgTJDKNbrbBlzd3DffanI1of6XyiG6QRBViNLgt0VWLcCjqd1XMIpOzWrxJIykj8xhYoUwAGkQBJ9/iFCckyFgmIKvWScmZim0Ss/QZiPd3V+h6VsShXItaRtCbGFlJAEahKTVlojFY0bSD2tkutUvbCV4ZqPALAWcNkVLO/t8dkPMYYc2mxl37+XSd9DXNUXTy2vYnMa/fOq7dpGOsvtNlUwzC/Mljz+WEd2dWPW7jH38Y56+r9XFynN0/lUyb26ul5ha2XYYg72rq++Ru45U20SzS7rtgt6ZXo9tXOr5tjO+ybu5n2DRPpmQGcg0fi9nKxY0Ow9lpU64VlAxwMm1QueWrmuCeNRkOZODjcxxjLV//w6xy+eR9jCx6fnHLWLZA+6WUMMSOzK41BY5QQtWABpTRGKTBZpZiSEGP2qBvc2TfqN9Da51xeKMCgtcKYwdaU1tdnNA8oC4t2pmdisJjPmLqCwztT3rh3RAhC1ybaBXiJpASusOi6QtceVTisL0ghQcj3YnpE/RTze3DWUZU1TRAyggiQehR+1dsDh1xhPcPauNz0GwQFoiz0H1EG0QbjLKZ0iHG0ISDBQ+gwMTCqSqqyxFhD23li6gOV+8B15yzTvSkpRgpnuXt4wOHBAZPJOMN7yZZksx4Pg2x2kUF9Ss+m14Wv+B3PxC4syi8yJl90Vd+1S3qewi/T0AvVcVkCfIFanrGLuw0szm3avyjNrWWErauHc5kBDYHP62v6l5odQ9QVqVErBcowpCzOuH5xcHhEkhAloo1iNC5wzvC93/cFYjT4CPfcAd2TDvG9h2TvzCB92zEKUSdiVD2z0tlzvL+LlBJJclqUzMhYx01579cOEDFqnMt5xay1pJRtbF3XEWPKMVEqMakKrM0SixJomiXHTx/zXW+/RYrCcrGiXSqWKeJF0LZAjSpoAp017O3vY5qC86crnMoO7kap7DHpI6nzTOqapvFY5XulW/9eegkrO3D0GIqS098MMV+CQbRF7AhVjKGqME5jrMEVBViI0iF+BX6JCg06BfbHh9RlTRJN03piTGij6bxnPKnZ2xvzxhv3c5oba3nzwRvs7e1RlmX/jPvRoj5lWC9LV0KgRF4ZQ/u2Y2LPGzF+nSRw+wZv34+PIz1fP1/NoLsJXeS6uL+d/bhiL9uNxbhRYGwlV5Rh8d/sQtRaBbqtb9mWAXtmuO6TzviJonqJLCFrHMacOFEbcIVmujeiaRPaJ6KyjMcVqRH8atXXbNYMUFTO+5XtYDmxZWZWG5T4bAveUuduLbQp5ZQqkNbdd4VlYMwp4y5BjKzaDquhSIaisIAmeE9cztm/8waH+xP2pyNOT1t0yBJf0mDKAqqCWFgUFhMzoPDQi8zINBIjvu0oyXDKBkUfzraRtLZeZWZgGVQYUSSVIacwBRQ1VBNUVaFdfrZoIYnP+cxii0oeLREtiXFVU1hHCCljIqaU1ekKRqOavb0pdV1RWEPpCvb2phRFgemzRSu1zsf8ikb+tw9du25c0Gx8NPRtx8R20WsFlX3uk98Kul7y+TjSbcImbn+tuvAZdPHrclfUkzkaSdTGTpUPy9b1G6bYhyP3T7iHw1WSsQAzS0MpGI8LlI4oHfCi2JuOEC3MFjO0zlBTqrerSK/yC6EfRipDIg2MTCl6B4iBCfc2qa1dboxZ9TeYlVyfUHPwFhQRJCaWTYdRQipsRtYwNqdqCYG9ScWdwwknR3t88PApRkBFiAi2dKhRRSrLLNF6h1UWuyW1G6VIIdItVxAiOuUnlJ0cFQO4r2xdkxmYoBO5XnQOb7AVlBMY7aFHNcYmtAqkuCTEhhQDxAZFQJPhpKbjMc4VeB/wPtvEELDWMJmMOTjYpyoLVFlSlyV70ynO2d6GKFv5zLZ7+Mmjj3o5uq69y/P5U0nsJei6h/w8L/vGch/hiLnemrNNn4wp+KpQ7W9mZLB5HqpXEfYMgYxav35Wa2+OIbYs9UzF5DxjQPb37oOdBxVJbyZLEtc5yZIkijI7IkQMQTlE14R0xNl5ziCs+nixKCp3Q2c7lpVEURRrqVIphYW1nSvGRCKhlWCtXUtrKSUgAELb5pxiWmuKosCLEHs39qbzWdUYI1VVUJQVo7rk+PFDJlXJD37pizx82BHOZvhmxcw3uKLCTWuqewecv/cY3XZMJ1P8ckFKMatTkxC6gF+1LM/OCdgcc5YSvQEsM+7e5qXRKEkoyRJb0o6kHZgSqjF2coDZu4OqCohzYgiEbkWMHRIjKI9WAaMChU7cPTigKkoWi5ZV09L5jiTC4eEhh0cH7O1N8V3LncMj9iZTRqMRasgMsH7/G1Xtx2tjenv6qLt9ub3LZoRXqUqEbxMm9rwSxXWlP55j9Nns6Va1XCPdXKva26r7tjasrRNbtVwsf6GNW+7KroAL7yh7nb1t41U4ZGscJKwhRFf6c329Sq/FHyVb3nKQ7VbrcoNxP/W2nYFJ6n7tyzgTa1uiBmMzM3SFoYiGWDj2xjVN09K1gRhj7xUna3zCIcg3g/+a9X1m1aIipR7dUTaOH6B6Rpa9NmNMdG2HcxZjLc7Y7EgpgsSQUeglf1yRY8ZCFxBZMho7RlXN/bsHzELLvFsCkagEYxRmVLOSDF5cKoVThkCGzVKpR6ZPQrtcEUyFBOnViduOMsMjzlIlvZSWMIh22X2+HuNGY9yoppNI9J7UNaQUkRTIKVgCEluQiDWK8XiEMZbVqiX2SUKtNRwdHVJXJcYoClsyHtXUdZX7029O1NZYyjy23/AMG4l+U5Q96Pt3P7wbNnbUjX11I1Vf5IiX/26pWV/HgvSa97PqFvUPDkmvShP0bcHEvj1pk+0YXo3ofTEIeMcA2hLrdg+vqyP0VahqX+Wu7Pr+DI4aA5Mals908V4HnETpGVDGmyK7ePfMSlK2lyh6iWJwCBkMVpAdRnSPjj9ozrIEVThLEXJ8o9SKulhlV3vvUaZnrSkhPq6ZtjG57qxWHBaC/DsDemQGNoASy2ZNRSQ7fAx2M+f665QgUWUXf8meFBlcOAIdOkSqYoQp4f69Qx7PzjieK3SXHVei0riqJKiciRoUVpucD61/vIPDoV+1xEIjSffKz+FRybqT+ZI+4SUGwa6ZmKlH2LrCFQXtak7oWlLXoFTMDCwFlAQkeujxEDMTM6xWS2JKaKUpyoKjO0dUVYExilFdUdc1VVHmfiS58OAGqK/NVLy4+K5Z0NYgusJ8ZPv89ou5ysC2f38y9CeXSW09vus3v58yse8Aep3mqhsHzwu0exPjeNY0/GjT5GykGCSuLWBXy2xDVXFxpeqluEHVlM9phsSUFxagPkvxOkRaMsxRVZWIUlibszXfOzpgPl9xIue0XZf3+QM2YST3p80xYBlhwq67orXCWpvtaPQ4i30/rLNb3ou9K7/00FFFnaW7HsGC3o62WDSURaSsSrSOnJ+d0rae73r7c8zaBU1oOWse4buGLhgmdYUqM3xWirG3AeYwg3VCUa3xIdBJRxdzhmzB9uFeA5NXaFX0aVUMSTnKeoK3Bu8so/0pSSWWizPaxQn4BSp1qNQhPktfojICiSYRVcfdN+7ibODpBw8RDONpzaje497duzgHhdMc7E2p6xJrdY5LW0u6u8bFDRmduXz8JSfwy15+45x8ffQ8tX9qE4Mr3PzGh6KuLlfX0Ys83BfFBHxuVehr5W7Xtbm70PVqSdkqpoYjz1RPXmxz9yQc1IO72t3tnn/JCzHridbjYaPG2mqAoRGVF1lho0oamBj03vfbd6Y3IWN9ZKsMj2JQO/X5tkpxKBQpCiEIsYqE8QiRZcY77CWb7KQhoAI6QuwlsqwazqC51mbGPMSDQRYoUp8tc/MsYs57BqAs1lqMUWjM+hmECDoIxiesVXTeAys0gTsHEz7T3uXdR09Z+d7DEUE7ja4KapdjsKSLqNRnYbYWXRQk61gJhBh6JesG/UT3yteM4ZClLzFVRvuwCmWytBu7JV0XwM/RqUGLhxjWbvpZGk6gBVsa6klNXJ3x5OkJ1WhM4cbsTY8YjWvKQlM4zXhU44zpE55e1vRtS4yXxuGOY8OJQZ246dOm0mum0oWD2/Xeen3bVdOOteJ5l7abPIlvS9dlsviUie2gG123ubiQvkg9r4peDQjuq6Urz+bSgds+u+vo2n3rTe/smkl4XRjFbvd8WbvT54L99bJZhNZjQ21LUz3DGuLE+jHEsCithbSBjfWMYrhmkOjIbt0o6ZExspRljUEclDHRdpFYOEJdsmoakESI6YKUmGIi9Wo7rfWaiQ1jxxiw2mwYlrB21x+ez5DROALaBBRgtOtVo/malDIj8yGhtIGQ8HhCaJiOS+7fOWRcFsS2I8aMHiJGoQtDoQriaomOGh0ysK42BmNtBiYeAI17dedGm5ZZWEIhyiG6BFsjulhDI0oKRN8RU4NKS7R4dAqk4NfvZkCk0U5TTwvKcYVfHnN6dk5VVYxHe+zv71NVJVVpKAtDWbrsKXlBLu8DrNej4zlHfr9rGRjYxvr38aVXwaxuSxsHj1dT37cNE7vNIvt6WdOL0xWp42U5xov04RkHPupnd60kxu7l4Hq3fL212KdLx4djvZPH4IkoWWIabF+DFIPOKqcLcEhslr6MBjHIFoMqkSx9SUYIUWSGpESwSlGVZYaMUjk78WJpyIpByfah9ZPP8WiS1DqgeVB7GmNyyhPrcM6htVkjsyM5+/T2U0tJ6NqWGELuV5GvUcaiJGeGXjUBwVAU2Yb19OkHHN17k9H4Lp+9e8R73Qkz3+B9S4geg2AKR0tmtsZZdC9zpZSyowq6B/pVa3R6pQWVBohdBW6EsmN0McVLlqq0FZrFOdG0KN3iWKJ8h4SIdAG0yYgnArqE6dEeX/rBt6mmNYsPAk+fnjEeTdk/2Ofg8ICqKhnVlsL1YyPlZ6t6l3+2nvqLOldsHIpek4PGR0SvC2VjyMLwKujbhondNE5e14t4HdRrrr4t6IIKkednhDvf2wV13+2vXdu4FAyByXld1/SGpyvXSs/IMg1Mr7+fXk2Y800NzglDfawZyLo8A8PsmU9fxmhFXdcZrBdYrCqSZDSNmNhSmW+1f+neM+xUL3mJrBE6rB2m93D9cLlAjKQkeDq0ZHBfYy2iN+qezmeQYUTQqqNbLShqy/d/zxdZLf4Qv/R00hGCR7qG85hQfQZoA6iUc57FtsUbS9IuPwXJWatFK4zWaImIAmMLTDVFmRGiK5BIko7kWwgBkRXoFaQ54kPOvxZNb7s0KGeoR469w33uv3WfxrfMFgsWiwWHh4eMxxNGo1GGojKsNzFKbbuaqCvqxLWG+Prhthk7W+rzywzxU9rQp+rENW12wxu6avt6kUd124H3alnjZXjRXb2Qnb9uVpfedDfPodt+Rk0X2pOL2v2r93W7pWGXTeCCWm99+aDK25LGBueLQWLa0dwF5sZGJTWokdaL0rZ2SbbvZ/NUFPRqqAxllb0VdV7YVfZylK03plRmec5mBPq6dIyqAu872q7NqBH0QdBq2+trWB8vHouSUDHmdVhrTM9pN6gleb5sx+vEEAg6o3mgc06voc4YBa0jXoEJkaZZonTJm/fv8vW9b3J+ck6Yt0iKhOBZ+cRIgek9N/XapheJIoSUCCJreTgHaPfPSFmMq3HVCFEVIWqEgEgghRaTssckqQNpkRhREbQMCTkVylhsXVDUFUVRslqsaJYrgo/UVUVdlpSFw1mDUZnhDm95owZeD4zNC98x6C+P2mHzKcP7Ai7Dbd84d7bHcf9ehw3EjpauXL69WdzZwa1yF2rY2mupK5UMX6+bo1cKXkBpWzdxjRDxKRMDWO9ut+nKI7wyQC5/vU0r1xW9toot28Sm0DAkdojRV+CtLy7AuwfSRaZ3PQPblkgu9mUXbTPGyzXdnvLu/+ZnNyzpF9Vdt6ubC9esv205dOxi8etJqfJsUyKgB5XhICX1bvPrpiSrFntInfX7Ey62M5Ttx+XG6aN3xhiYqe5Vi9KD4MaA08KkLkj7Y0ge3yyIPq7X0MxON6o4YJMPcmhaQUiR5GUdCJ2xEy05VU0fTB1jtqspsgNJ9EQSVkW0LjHa5HQvKZBiIpBofCCentB64Qd+8Lv57IM7dIsl3ck5Wjzet6w6mLoRVgsShKXWBKXpFIizrHxi3nlSz7S0sigxRFFoPaIc38NN7+AjNIsFShZImqHSjCI6YmqJ0pFUyGpdFEYLYiEVGkYOu7+HuIrFacPxN56wfLLAYjiaTpmOKurC4BR9/NqQEFOzwde8NBKvHfT9eFKDRLc5fsHxiM2G4/p6NpumdR23Z38XOvysOTq40IgaNpoX+3/lm+yu87KD1cVEUrvKbyT8T4OdL9AuSWzXwxkWEnXx0LV1Plseehatl7YLTGP7c91VW+W3ENSv9vG2tIslPWPAPUft17eXa7q5rkFdcxOjvvn63dPnOglPXfkrffoPGaS4XjWnUdkpYr0779E8cuGtGXx5k5Q2tjYlvQPfMP50f7lkDwpA62z5EsmZXKajAgk1Kk7wfpaTX6oB4SL1zW7ls1K9NCOCSMi9kKzGS23+a63FOZcBflVOAhkkImtJpO9LgqZtKKzFlAVG5+cYk6CCIHhUs+Dxk/f5/GfuMS0czaMnfKASKQU0Ft92GDSF0qgICSFphaoKum7JoutQxqF1j0afNAmLNmPK8V0oxtCuSGmFljOQOVotsbFAEUEiUZGZPwISSQWIU8RS4+uCRhRnj+c80Y9IZw2Tasy4KqgLQ6kFs73BkEuS9jNG25UDg/R1eXMoAkpvyejPos26oC5822zAdtYiF/5caO26GTAwsqtVyXovnYP6h7r0lbK7NtfDNTfZQz71TrxE23uX25R91SUvXKU2+25g7RF5sd6b9yvb736nKeiac7fr38td/xwt3b6EekGVwmW9mmw/eVhLWmsB6dJzX++M+13zxgrPoMqBHt3+gjppMwG3F5W148jgkr0lCKp1gf56pS55WGZXdEkJ0VA4x6iuCCEwmnf42GdxTooo0qvOLmyBe6a5tTnqq85AwGzasxZt1BoTcKglSU5AGVVCUiKoHJNm13iNiiQZLqqLnvPzU+5M73Bnb8x+6XAp0YQIYggiBASnsmu8NgbV42ANwMTboTGDR6KyFa6o6XrJlNShpEPhAQ+pd7QR6WPo+nehDViLOAdFQTSaThKrVcP5yRll11FXNYVzOT+b3s5poC7uWW859beGVv9bba5fvx91TbXXNLI9P7cP3ZguSK3n0OU2duUNhK1hfrnNtQf3NiPt72NHRRemXt/ry8Wu8yLe9f1l6BPNxG5Ll0Xf10O7B82VvvBseeNZ51/KUeU5L7sql76ifmzXc5XNPN/113kyDkawLcT6y2Phgju+bDYjQO9ROOxCI0gf0aTkwpJyxb0fyFC3fTZgEZTKXpCZ+hgw8qjRKqNUpJSwpkQpg7EFi1Zo244uBEJMtF0gxNhf16cwEQWpx25UPfL6mollIOGYcn+jgBWDc9mtXm2538eYkCRorRCy92PpCgrn+vizQFJCDB1Pjh9xdzRl4gx3yoLSexZdSzIWb4bNpWDcJmWKhIiECCFldHsgKUh99mftaoqyzBiLqzkqdBjdQ0kRiSnHuGVPywyXjFZgK5QbocoaRmOiUnQxsAgdj49X3Cs196YZnT7jSu6SKp4xvvr3dHEiDDLWNqvafN/Agz13cy9PLzElL6P6PGt6vwhY93UQcS9K3xFMLNNr52K3aHOYCM9W561LXN72rQ+/IAPZyUWvZ1XPmoMvzcjWm9gXB/q96fuFNrakoG272cYRhI00BX3ed8lcTzTo3r0+AX0+4hwDltV5+TqT1XN9KhbWTFOv7TjSu8rn3Fm9SrWvU1AYa6h1xf17h7Rdh/ceH4W2bQkhEBP4kBma9yG7r0vee8fUrbdTSveI7EoRUiR20IWIDRHnDMZm9/zM4BIhJMqiyPnMQtf3SaO1pShHNHQESbjUcvLhe1QtfK4s+Gxdo9yCeQyM7j6AEFnNF6hJlaU+EdpVg29bkvcoyqxmRMBYXLWHLSfEEFjNjkl+Sa07VGyI0hHxpGiJZEastMnvxlgoJuh6D1XXUNX4uKTtGlbdEj8qKSb7HB0drT01r4s/fMZI29i1ejWugnWyzjy2NmNNbV33+mnX4nDx8C4Z7ia6OJduX/6m57oT8u5TJsYFtcTHj+T6AXCLPl/c9O0Wy1/dvd+unpuCjG9Dz2JStw243N7J7ZocFySjQQXIZlJu1HlyaR5dwqvs/1urBBnsH4Ossb373nzbHO+Z24Yr9naoHEw7OJCIpP6awW6bx3VZOrQGZw1RhLIwxBgJUei8J8RA1/mcdiUKISZ8kF5i2agZhcy8hZR5b1SoPveZApTOSCNKKSRJv1Znr7+cEiZmFH1tyB74kbBaEOYBdT7jfl3TTkbMTmZEk9vzRmGszs+3x3YkZkzILMn2D95YtKtAW9pmhYQGlRoMHRI9igB93FxWPQLKINairIOiRLkSjMsmy7YjxYbUrSinNVVZ5BAGrW+12N5IWwxrS2N8UeqSzZjYeJBelWhu0nA8f6eevSl+Zi1bz+Q2ktVlaepTSewF6TomdvXh3LRDuHrspmd7ufy2TvhZ9eZSF3XM177IS6qL9QJ5eTdzDb3quLjr2nueBeG64OVL29dryz6rb9cxu/6p3yi1reO61rvE/HVLQbSR4ga8v0tMrO8EQ1xXlsYA6eGQlOpBgYdm+sV8kAoHsOG+3sJqjHZIYbP6LRWklPBR8L4jhEjnPTFEfAi0baDtVGZmMW18PmXL0iGSAX99JEUgSZ9Dy6C1JorkrMw6B1rHKHgfkQjaaJQFLZ64XOBPV3QPP+Qz0ymxifzx8TEtHtEKb6EwPROj9+yUnMMMk+88qewWb1wFyrBcziC2mNShZYXEjoTPDFeyR50ohRhLBj8sUVWdmZg2pC7nFJPYQFgxKQsmdUVVVWs14nNL+/R86YrVadiIbJdUW0N5lzrxxWQ0ufRjR3deCz2POvHy99vQp0zsY0Wv3p5zocwL1/7ibX4S6CZb2IVAZzY7ZunFq+3vl65mzcG2VTJr5tZDNDEwnL6O7Ze01t8oBgzFzEA28E4DE2PLzqO1XucekyRYqzGiEEmEEPpMxgprFYV1pGSI0SCSnR1jhK7ztN6z6jxN62l9xMeESA+AJT1CvorEJMTgSbHsPRgLtDY5CDp5xIIzDqMNs9M55WFFWTqmStE8epezP/qAp//9d/mRH/7/MipH/K+H3+SknRP7XGHTSY1EoW0Dadn0bv9Z+k3kR6NNgVKGFBOr+Tm1iSjpiM05hg6lImLIiPuGjK81KmFUo8oSW48wRhOjR07PKUzDSHkOFTzY2+NgPM6IJsbc2iNuAyW244zasXFhw6wus7rd359NN8lXLyPF3cY/4HnXhxcpD58ysVvTx22x3jU4rx8EuyfMK+nHLVV3Hyd6ltR3WZ2YSW507BiuW9vEGJiXsP5/+7jKcWQi6eKWeOfKMtjU+nJr/tgHQotsOWPI2q51AZ2jh6raFtKUkFO2KJWdJCQ7eCSjMEZhnaEoHFUZ6UKkC4muVzdmR4+YJaKeYUbfZS6YBGtdxjvUBoAYAx5FoXXOb9YI2iSak3Oap6eYLrI8PcVVNT/y5R/kf7cLZsuO5axlb38KTccszEmDoKIUrOGdssSXks8RB8oj0qCkRUnsn00v0WiNchaKAjWqoHIop4mxQXyLQqiVUCMcaM29asRBVVM7d6O0sK5/M1o2v7ftX1cG2+UDzzxxLV0Z14PkfHl8vRJ6Tmba9+HjvC58WzMx2d4pX0u7Xurty1+vNry+5p0oFOrSYnjrMXM7s+21DGCroy9jL9h1T6+Kbqp7167uwj30jGdbErt50zBcxAXVYtYtpkG3lBnPwOgGhnb5pctQPJ8YmlRD6uesJMwu6L3xKMkQzHwxADu7xed6En1smVboIROxKETrnOjRGWKCWiBEwYdE0wVaH+h8wHtP8JEYs7dgih5JkRgDklJmZEVOmeJ7FWBVjcAnokREJZrjGc3JnFpZZk+fUr3xgD/1J36I1Qfv8PDpKU/iGXt7U1rmqPm8f36qRwXRWSolu+Dn9hNKZXuWSi1axY1aVglKa3ThoC5RVYkU2dEmrhaoAEZrJhPHWBR3nOPBqOSgrqmtA7J7/3V2sY2LvFpLYRdFq+eYE335y1Fdm+Z213V53g2sdWsr9Vz9uDqPhzF4HbD2dap41nNmV7nr27u5zKdxYtfQi4jZLyOa30QvXOdzX/iSvb/h8tf1bK524KPY5eV2Ljp25OOXJ7YMiB1CZlyDnUMNyBvpQr2DvSwvgunCkpOPG1TvwIHKqr2hjowW0dvG1jbeoQ7DOkZI9YEIImi1aX/D5jITROuM+QiINr1Th6ILGRk/xEiMidVqwapZMTs/Z7ls1irHeTgDldHnq2pEVVYZa7ANTMcVzigef/N9zt49Rp+2fGZ6yLJpKELL/TsTvlS8xf50wn4xJnRLJHW4wlGONMwagnQEFGiHNiVWaUJYEWMH6ZwkC6DrNx6GqCBphStL7HiEGVeEwtJ2M2JocJ3n7mif/XrE0f4EFwJv1Y4v3TvicDRBF5ZW3W6R/aTTzfP1W3f/2xv1nMQ10XUds/n8ldT/XEETv/qrv8qf+TN/hul0yv379/mrf/Wv8gd/8AcXyjRNwy/+4i9y584dJpMJP/dzP8eHH354ocw777zDz/zMzzAajbh//z5/+2//bUIIL30zL7L+q61l4PJHLh9b76pv97ly/frz0dOLtLrLzPMydO1CsuPw8zqS3Fz37oDNzQZcXWBqqt+Rr6UH1OaCPvOzUlvnVQ9dNKifLhxXF4+zUaWts0irLJ0otf0xMHy0yWWVydiG5PObsjmAWSvQKqF71BBNREtEE3E6UppE7RSjQjOtSw6nY+7fPeLenUOO9veYjCrqMgcFxxA4Oznm8YcPefjN91nMzmnPZ6yenvP4a++jVkKla2LSYAxN1/D+u3/MxCjKGJg9fszs5CmKxP7BHmIUSSuiUiQMyjiMcRnHJDUoWaKkAeVBC1hNxIApcdWYajTFWgcxIYsFNnpqLdwdOw5sYE8aRn7OvlMcTWru3T1CG7V+v98J9HG/y23kehEhxfiMK25Hz8XE/tN/+k/84i/+Ir/1W7/Fv//3/x7vPT/xEz/BYrFYl/mbf/Nv8m/+zb/hX//rf81/+k//iffff5+f/dmfXZ+PMfIzP/MzdF3Hf/7P/5lf//Vf59d+7df4B//gH7ySG7qOLq05bHueXXvNy7Z5w7mPmpW9iIT6MtdfV5/aWthf5HNdHdfWvcXAtpnJ5Wu3r2dgYPRy1taAUWqrnuHfVgoPts5tmODm+PAZ8PoU6gID2zDE/qPNJYY1lMufoX3VM7FsbRM0KeceI6IlYIk4nSi0UBqoS8ukrjjc3+PoYI/D/Sn7kzHTyYhxVVJYg+9alos552endKsly9MZ88cnnL73BFaCoyBhMGWJaDg/fcrYQJkS7fk5s9MTSJHJdIyyhqQ1UekeOzFDTylJKOnQqQFahIBoQYwhaQu2wBY1rqjQKtvldNtRSmLiFHdqw6ET9kxgojxHo4LD6Yj9/SnoXeBK3yH0sjd+i+svqjqvp+15tnHu+RalYvmN3/iNC79/7dd+jfv37/Pbv/3b/IW/8Bc4Ozvjn//zf86/+lf/ir/8l/8yAP/iX/wLfuAHfoDf+q3f4kd/9Ef5d//u3/F7v/d7/If/8B944403+JEf+RF+5Vd+hb/7d/8u//Af/kOKonglN3aBtjbTV+g604hcLKK2bBuvqkvX0sdg5r3qXd21SsMLNofns3ftOn5Fz67UVrW71YnbNjIZmJak/tq0tk+wpQLMknZCDXmJB3zDdWDUDhPZto1tONurE1ECSdB6yGsmaOk96pDeNJSdP9B9/0goHXt1aE7ACTlGLINPx9xO355s9UNrlXNwKUPlpshehnIKSeh8pFl1fPjkCavFEt92aJV4/4+/weqDY9wHCxZ6RFWOGL9xj+qopjisGX3mEFuXzCvHG6Mx//Wrf8SD8ZT7X5xSn8wwxwuSbUFZtCnRFMTOI/4ckQXCgqgFowu0rVF2hLIO0ZYuRmLXQPK8MZky3tfUdeJQtdw3joOq4u7de9x58y77o5qiLjNKiOKFUDo+8fSy69UtLlNb/9+GUspettbaNTN7FfRSNrGzszMAjo6OAPjt3/5tvPf8+I//+LrM93//9/P222/zla98hR/90R/lK1/5Cl/+8pd544031mV+8id/kl/4hV/gd3/3d/mTf/JPXmmnbVvatl3/Pj8/X3+/rcnzWmPmrgsvvfsLRdTV86/SeLRmmLJ95FL764VpB61X6RvKXK3wlj275np13fnLTOnmbmxCk7ng/n7ZyLz7+NVj6+N9F3ORy6rDIUvyRfgpVPZAXP9eMx3WCR0ZDO8Cmctsco8NThubJyFbILOKwd3+YpvDtUNCTcOA8K+Gd9pDVql14s58TAabWz82LqAjDp6PA0MU0FlWY+MRmZ9Lxhe0FNaCOsLvTejajsXDp4SmIbQtpdKs2panXUBU4sgeUuuWmVkhTz8kNPDFt97gf7/3Hr5Z8fTJY1xZop3LMV7KrjcC0XuUhHxfatCaKrTJzh+ihJg8BYq9ccW4nPBWPWJyYJhOFJ/ZszwoKyZlyWg8wU5HFNaQVCLpi2Nht1pxcKdXF459Mkiu+X5dmdfR7rPObW0QhzEoOT1P6/0r6c0LM7GUEn/jb/wN/vyf//P80A/9EAAPHz6kKAoODg4ulH3jjTd4+PDhusw2AxvOD+d20a/+6q/yy7/8yzvO7EZjvkx5jb2m3HO84wtrtVw+8WK03pz3q+GlacflDm5kltsM2muY9JXabqaLYKKXb1xu5Km3Jrm8kDyj8C1p+wledrWGQSrb+ru+aEt8X3drAAzeOjhshHqk+rXTR19mUx+g+gVTthha36i6MLjUuv3BkzEj2ffL7aCm7Jntul/X3H/f81y/ZIao1k4oagvoWGUMj97LcTquiKUjdAXx+JSqLpBxiekiHR2SAlb+3/a+Psauo7z7N+fut7279nq9XjsfxgkfeY2dUNLg7otIo8ayk0YVFP6gENFQoaCk66qQNIqMKIEgNVUqtVKrlP6X9A9CW16RRrUAYeJ8KMWEEhLlq1jYCjgFbwxJ/ZH4Y3fved4/5nvOzDlz7j333t31+VnXe++cmWee+TjzzPPMMzPnwc69jbNvLWA4OYf+gX402AAmBoewbnQEb6ULePONN3B+aB2aSEBJH/haHwGUIm3OgyXiahDWQJIACWtwYUZNsCQF62MYG2BYu2oQE6sGccnICEbX9mNstA8XrR3C+sEhDPX3ozEwgHSgn4vk1N4CYckvpgVX9vR6ZsXL9gGn/d3oFYMJwtqz1Xn/HItRFEHf3kqExxTTThK0qJhckPymY6ckJlrgU66m2PtYBVoWYrOzs3jppZfw9NNPV8JIHvbu3Ys77rhD/T516hQuueSScALZv8x+5qn5UJ9rpS/GDqth2nYXsgc1cqPCPIQ2SKVQgCVFkQwyZHy8XNlpzAHATZFJyIxPES/GfV4xcDRSzlfD+K0Z4sdUSTMH/1hTAumsQcLVngQnhuarz9OTWpoUHpKIMFMad5Lxe75kfrqOG6wBSvl+rqYQbFwAJaBECiQGIrFXDABSqW2lSMWdZeKnqkE+iJP8BcbIGA+bQi4ThvoJrI+BDfRh9NKNmBofxZmTb+HXr83hrf89BVok9K1Zh1/NHUf//wLTbALvvmQd6Mw5nPr1a3j/5Rvxk1+fwE+PHMbrows4eSYBGqtB1AcQP6k+Tc+h2eAmQ0oGMdAHNEBopPPow1msGhrE+PgI3jE9irWr+rF2pA+Xrx/G2olxrF49jFWDfWgQlEZJqdIrjTbWWrQsP2BciSkmGFyEJ8YaqO6X8oQOFWaQ0/1Kuta7/Tmub2swRclS0AGjn4jOwwzBYmRB9n82de+La4ocTwIyqs+TVltIjCPFxJ+UCE0Ryhr8xJrFNMVCs4ea2J49e7Bv3z489dRTuPjii1X49PQ05ufnceLECUsbe/311zE9Pa3i/OhHP7LoSe9FGcfF4OAgBgcHsw9U31BNrYKtbxR3wrwmE4hN2UfmLD8mfiZKocwxjWympmDHJ+N/3+QxQNr31Yng5JLJNF98m9VCZPOnaWRf8hDveugtoY25bSqKpW3ynJ69jwzK1GglkmJG1jEZc+PEeADxXf2U6pY5sGU4VeGkknDDoNoQLfenCe1JDRkM/EirJBXWwwRIU0vj06UV7vqwZ/aydHrmTapehkcG0T/Yh9G1oxjfMIHFc/P8mKcz8xgcG8LC22dx8tTb+Omrr2LdyAg2bpzC2339WMv6MEF9+MXJeZw/n2BhvoG+oRGguQCiRTA2j4ZgspEAg0gx0CAM9gPr145i/bpxTE+txWXv2IQ1qwYwOtyHyZEE/f19aDQSQJzqD3ANNVGqsiiNI2Qg6tN2wIH+HVKnvIO3Sdtu1vC7FzESWeSMd58oEyX0FsheRJkw/28KxAkmBgzB5f716GymFQHcIrLYC+9EIsKePXvwyCOP4MCBA9iyZYv1/Oqrr0Z/fz8ee+wxFXbo0CEcPXoUMzMzAICZmRm8+OKLOH78uIqzf/9+jI2NYevWrS0Wo8wsx4bVCYrIeJ7nJsl7GD8GOxM70UmcCZ/77sXXiBioXAHlUmG+50WFiCgkc36QU7DgJxbhRnM9G7N/Tdd8Yzgx1tR8dFwaqoHkMybiyZfaeCa9Gq20SES49oJkkg9D85PahLUNwMhbad4WL/ZHy3uylZEGQ99gPwZWD2HVxBjGNkxgbMMEhteNYXzjJEanJtAYHcbp5jxOLpzH6bSJZl8D6y/ahPe+7yokfQmImqDmApA2QekiiObRYAvoY/MYYAsYbjQxNpRg3dggLlo/jssvmcLll6zHZRetx0WTY9iwdhTrxkcwPNTPz5VkXAhbnqhmDzHr2Gp346clwHT78mr1v1RO8+vHrQ9DLcPons4bYmjaZjwjvH34bUF5kP1fvgNVoJQmNjs7i4cffhiPPvooRkdH1RrW+Pg4hoeHMT4+js985jO44447MDExgbGxMfzZn/0ZZmZm8Du/8zsAgF27dmHr1q341Kc+hfvvvx9zc3P44he/iNnZWb+2FQtDaYhQgBTKVmPGcaBk+lDGsQ0ailfuNHnBgDNZ0gOYE9/9YQiBMvA71ziZRkwkmPNa5iPcG0KndthsSicN6Y1Ihnej1K5kLmL4IHl/GIN27mDgR0iZ3pAknovN1UJzYOa6GkuESZDfOaYvSOTnLJISTnLgEs4dicyamx2JcQ9GrZpYf+zaInl9va67RXGAMRjfF8aogb6BfgwMDWFgMsHC2+cwsGoYx39+FL85ex5vzv0S/Ze+A1fs+L/4vfftwL4Xv4JfnzoBLM5j8fxb6GOLaKCJvuQcBhqE/j6G4YF+bFq/FlOTa3HpRRtw2aUbMD46jLFVQxgeTJAwvtG7OT/PD99lXENtNPhhxWlT3zCQ7VOuQDd+Q08sdJ3oiYiluWUEHlQ8O2UF8HRd7zuErKUp5LMWGrDyxpUqYO+VBBqNRmWe6KWE2Ne+9jUAwHXXXWeFP/jgg/j0pz8NAPi7v/s7JEmCj33sYzh//jx2796Nf/zHf1RxG40G9u3bh9tvvx0zMzNYtWoVbrnlFtx7770tFcBnAaykE0V2IEcOhJJ2HIyZazBFcflfbwf1MM5MshUXTI2VbdPJO0rKn4HpkagnAbKAUiBwGkTigkstHRT/KjoaIMjjkqRnob5uhV95woR5myAPBubrWlzYJABIHhosbjIGI6AB4YCRgIiBURMQa2kk7i+DOH5KmW4SfpI+yf04kpaxJpftu6T+Vxo/AaxfiVmk4LdQswbDwEA/zp5fQGNsAFPj78Caizbg/JnzOHvqDE41+nEmaeKt+bfw1S/vxdf/33fwvccP4vhvTqCvHxjsB9asSrBx7TDWrx3F5s2X4OKNU1g7vhrr1o5iuJ+hPwEajRSsOQ9pHmR9fepdNI8vsvb5me1uaqSQ5llXqPF2VuZF2XWAjMDSja/7kQ6q8AXpgWaXYYEx4fXaBjOyXUiMOQlDf38/hoeHK+GxlBCLkcpDQ0N44IEH8MADDwTjbN68Gd/+9rfLZB1EK1UbJWTaabPWk7aF8HAdhrVss6wQWdqCaD5BJi/M1GtjXDhwUnZcKeC1MJPnInJhJIU0Y6YDgaGdKc1OCCPrGCq1eGdohzycKYGVGuuKqY6j/mbX4vg3qf3Z8FaVmsXo9UB+LQrQZATq5+ZOSvrQYCPoGxxA/+AAxgaGgH7g1Kk3sXZsMybHhzE5NoiTb5zDmtWrMD46hE0bVuOyDWsxtW4cF1+8EWvHRjE82I9VQ31ooMlPH0ETjDXF/jcgZaYQM0plCDA1aFoCiEGaGMmKDxVfUTNmxm6d2M/IDq9GcSkFa5KZE9ZeDhVQMdogSaQG3T5WzNmJwQNgPVhKg3bVanzoPcrutZLx/Uu/JlumG3o0HzltEOIlnrb6ZtAJmFMtCeM+sjN318WIEiHAUi24RI1pa6KucRKegxBCiKm9ZoApNDgNqR1xwSWf8dPeSVUMMVLPZKaJLBaJUZrEqfqprBNHy5IDtOGWxuCfXTNKs8vyYn+ZXE0hRsoLcx6LGBgcABHw9uIC0MdASQNsaBXWr9uAM4vAG2/8CgPnE6xqnMfF64bx618u4OL1I9i0aRJXvOsiXHHpNCbXjGLN2Ciai/wwYjTnkVAKhhSMUjQScd2M4FxrX4A8/UQLH11uLW+yGpYm4LQ/zPjM+mgNzkljTRQ6g+BYkWbXuYJbYAsmdDpeddJY9yVuHQhvD2oNK0aIrTQET6DIgVxliYsptZBs+FJG+WGieHqstK9MNDlAJUpAEUmjWnaPIhf0XGgmQlAxJi+GFGtTJA/3lYJLXLsi1qGShCmhAfmdAfKEDn59seBNrbsJ4Zow8CudU7ENgEApAyXCC0zwQUob9JtfGelBkYgfhNxPhFTIwiZj4rumQgAoSdA3MCDoM5xZfAvE+jAy0Acs/C/+z+YJTK1+Hz70/ndjzeQoRseGsGbNEIYThgYDmotnAWry8xT7GFgqHFU4V2AJkDBm3A3Gy6OdMMyPMShbSpYURInZxDqNEFCmtqWqzt89Ch44vDiJ/BfFMo+OnI9Oic+ywkx7LNrlNU29i2mKhYUFnDMOsGgHtRBrE50e9sNrPR4+Kpw9XZBw5J39U76MYmBXPwC5D8lV+rQ5Ui1TQd74nJGtTCpK/JQK6eSRMfmZ44MaMKR+BnBTowyV5kmYY7uRNCuEmaChhaPggVLD/YQTlLeUK1NeIonIT4qENfkGajqPidV9GOkbx/mJVRhc1Y/BoQaGhhOwRal5kuKVZP0BAPjFn3oPnuZXiDcnTLcXmKQqTMQikDGzZhmMKJqexQwi4EZ0E3k038D7XTz18mTtSx8K7yHSNEWz2cRir0/sWF5wPc66mHOpjPVLEHNeoJ20TNf0vfRFfGXLEjVLY6z4/S/9ZpVIYA5KBuz1L5c2FH3LfKgElXGCAgNfm1LfZTipQV7nJfOQziEMxFIhvKQUS7mjh3EpJuclUd2D85wIDU08V6ZCRzCpNTHzkbxmxtTd7Tqym1oKGC4JtS+kFFbSdV/S4eWW3oQJFpHgPMZHBjE2PIRmSkBfE2ikSJImFpkx4BqspkpAMXUTtOLW03H9LvHi3Tf37xkyihTf0ALZrQ/m1o7W20JyyuZFzyCijkpz83Diu/C/DSwwJpgm1s5CTkLkOyS1NCXEen1ix4pHwewrenJWCu5gUyJlC+bHKETY0PMu1GOSRk5lmXP+YhhTZmtRPTSjjRN4WshkB0Ie0lDrW3KtTBt9xP1dyrXe4VQKHum0YZ0iwpQ5kZsRdZ7qwGBwE6HwqBARUjBK9GHAwt2eO3yIBSQ0hWwUgkwJRoClTaVTmfUmz8q12jZNwRr9Og7jZj7l5i6EGYHx+8wgxW5T1FETjC0CxM2Y/MjHRaTNJpopgWEI3P0yW/FKNCsPJN9Rc3pNTBNhWhKb2pnUEsWVOGbvMPQ0JQC1YdUWduZamsVzIaofOaSrii8nH6o5Oz7AizGpA/xva8JY8H1tBbUQC6Ggn3V0IpM37haMyXGdo0TniZABhXlGqGLRjiN5wrCEIM96I8oxzxRmcjgWYlbd5mx4FxIswSXjKu1MURC8ye9KuhtZMICl8vwBAksaghZpU5f0uiOAn0KnpA4XZnKQFwMtX4OTJ/Izg7axVqeEGVQ6q/yNBCmZZTTWqZhct5LWjsT4LHAdSglPHpeLshSJqEt9Jk22cZUQsRQjfd6InUoLMGuDs7keZThm+DQeSxNjdrtpur5OWGYS1h1UKSja4MIQ/rzuGn196BOfKrDyhVhBG/JXITs7MkM6o3W1Bua80CZC5om28zRnsh3MM46GNI/ZrRL2TrWP7TLj+wSZHoxh52G7vfGPsTam176Yii5d9c0+qCx70hVfCAfertIsKNzuEwg3fYJyJiS+94xrajCm1XKYle754rsQVATt+i+FjebRNEUmahGehGu/3Oatq0WWX9SF9A4UGg5DAwkaSBkBrMm9GcHEJEAIPGrw2iXznA2zJEZbGWt0ugWybZpVjIx3xW0+SC3MiONsBA/Rtpw+3LjZE4W7Av9BAqEDEDop2JhaIzbDZLUkCe8rjUYDSe1inw9VjUWai/F/Njz7fSkjShOpuP8W5hkzA5ANFaWJmQIsK7gyps1AB3BnqcqcaEUXmhfTglCviel9YjAEhLW52RGSciYqhYMUhvwuMvC8Ev5dDezS9CgVNCkwCdCb/Lhuw7eNCaEk/PATcVsLQZ8Swliq6su8aVcd38SkIFYGRyyKa02Y4I2l0ognbpkWvCXUAKM+JNQPvm7Hr2tpsgR8A3gi+G4AxJDwe55VOxhWVrUOJp9oNxO7hQVH6rtqecZM5VNpYeYpHK5olLUp61VqznpfmYiXUch6N0owuxBGeK80sfzRk18CW119LW8hRnb3U+OlnCHHkEBF3c/tK0y8DL5OZCsKXjDrsWcQ9miO8pvZP3T20qQDWEsy0VItK+5N3sJ9Mp++NSzldWzduDDLoh4LIZAhUcIUygcDUvJU8kZWfCNjrkog4zRAEGqUNOORLpv5VeZl7DiX16Jw7SNRJ3aQdOwQp4Aoz0UGcU2LpK3rh0FqQGLwVk4g0rFEmhVTdWqILcBkR2EijaxTJn4yMDR4Grk2RuIeMEpArCEEkXk8ltTWoE2RhqXSHI9VPam6kbyYsUUERV+H296MkggDSUcUyDLoYkId6GxveJaNx3k2NGwnTvi9yuuInsGjJB233/PXIfs+kP2fk6s7SSDnr01It5WOZ1kx1BFpTLQdibVahnSxiXShduwAALWnhVeVXyT5xjUWeFYZcqSjLzjUxX0Ltvkpsul9MUPhYfRiRmcgU2mx/PjjZbUw+4W155KBqYQ1c9Kainp31bmLPEBGsz0b5WOZBzOIaC60FpcY6cgapPnkRGqOkmMxiMjD70FG20tTptiAaggwQdEoql57Y6bZjWkHCbnuRsS4rwlLxFgvNSUtPPh6muHoEoIhh8hajzInDtI7MrG1KuMKFjWtZXapspnpspk9Il7pMmNTINyN73LhOw0xbywoh/A8z6w9YdLOHSfMzQvZsup1S9Jb/cXGbKQpqKJT7Je1EGPGrNw3Fwqny4ccH/IiFgnCUNKQPmPOQPOZ88/1LIpW5r57gvx52jz7ZoMUiBGuqHI6cevxmPdVbAHKtJfJwAq3jz0iHUnYdvSt4cY5hMqcxwCklpKuWoSlilpDqQdSuMm61M4f3J0wFTNciGUgeYQVQTp7cAEo+gIRbCsGibFeCDyz2ML01k+GJqb2CRtvgDRPMi48+AZrBkIDjDVgrX4ws63EJu0oyLfH1qR06+tT/o2qE1EYpPlVn5tiT1UkP96cmfnXmHB4O5tPeyo3XU7UqSsR6UK3uAfCzepWfUIHqD5izdEy0MKNOeEcqTU5ZOAHBRAREmJI0iZYLcRE34ztHyX6kTGxzo8D5De0MCNllYjQQFyMoOAqER4WXEa41dGL+QrFj6vysi95lqGY8ufBEkoBVlwHFy2onARKqRFnLjLVFXQU4aZvOzyLuasYbJkxIGtNRq63ibvOGD/1AwzqiCrOET+MWJo1lWOH5JkaAAl6zmDn0w0YGrkVw1mW7vbSgcMz6yenpSKaXQ+WQhOzbt1mStOTplM1/zcVN2Vy1PWqeJDxFR23eCzzVxcjPPUrQsh6Hnx/8uJnK9qbhjmPM6TddVx/loXaqa8MKoqftZaxrIVYjaWC8jPNMJ2VAfu0DmOtCTAGCejBQv6WAztBaXX84k1zINXXwZA8hooxsMTZHqDW5RKlBWqhqa+YkZpYeLIiBFPouaWmcGGRmGtoAhSaIQRuKTdyd77ZWphUiLQgM6pPRXfzDQtk35OMIwJjQQXowobos4wZEzhPLVVYcctfiJWzRHSdBVdTzPMWqto13qIt828hn3b4ihNvrfVoy6RbQd2VuZOtFVrSMSG7r8wQeMKBg8kr4aWWQ/LgVAIoAUvE+Y3EzYlyozEj4WJPAGPcE5DHS6HOdZRXazBp0iS4mmK2QEluQ2otpWFpYnYc8grKphSkRbBc4M0UzKprLsic6X6uIHMMqTkVYU1GlMDL7zOVjNdVzRMjYHvTloVuY2WBiGvdlrH8hVjlyO8thX3JjVCyH1Q5kPrQpfegID+v/cMKy7PF59N28g+4GfvC5ewxdtjJo+2lr1SsRJv1zPUtN7Zwk1eKGUSyxDCZ8Qy5MEu5SVF7NBL04cLQ3olyg5m8XoaEs0eOJsYcoUTGF+XFp8oTahnmlQ/K6zAa2lRJas+ctB1qbRAgg6y2LZKVnxRDMo38q+HuhZTrhAwsp86M8qECQdaFF9fcplLknh9+bmtf0su1k1rryhZiEbOXbJT8BIV9qc3O1kkBFsjQsJMXd7O8cxzjJ4vFsTIxSsxEXR5DZz76wrNu1eH8vbT5A0U/cyqInJUyGC+2sW4mnslrX6SZj1l/tTiUvzkZ87ZnKZhSkVci1r5IZyw3P0NftOITpvyTZELtZSGm/4KBKFuH3qolmX8EVOXoAC7AJD88b2lOND0NTW8n3Wa2JgYzjZmtLwymyTL73OwuttBc+ojRxELPLeFFbj13BitHiPkGuYi663TXqnKzYfyLHo8qy++lVZUZpASNojpvaROoGpGQO7XmYxpzXmZjY7QUTpDmKHEQsGHO0wKMKU0nu44m2bCPw1KaCYn1L7keppxIhBam1sSQI8DMUnlOVxCCUK5DAWJzsbHvjQwKpL4ZBES6qOY1iSnBIwUVU7/yzInZZmfGY5sWkO1LsZPMXomsLlodvZCTrW5i5QixDrZctztGKL88swRzBg0drk0EvvBQWDvC1+rIRRXHcgaGDpogWjYnmoNiJHPMahwtDblDRUM5a/D1BPkX4uowLZz0oN8QD03TJAGk18S4FiZcHdQ6mTxZhKfJHjlVVODAo2yBoYQkSep+05NdJ2Ug96bx//KawnyftOaUo41FoExc06s1/rWKqBNL3YNWhqN4yo8Zet7KuMCttMLcTSmSJEGz2cTZc+dK0/Jh5QixDqJqAVbYgVpI60xSdXjAdOajFz5/sCQvBf08zItDQ23aDVIy4ufb723+ypkTyzrj5JpiMsF89MlOPsyBUmtNioayoZERmfHTOxRZfWwWiK+PcWEmhZc0L0I8D5bSx3h+PzW0y6BXoiCSt9c5L0PKPJJrVdK0mNX9LHKGWTEUs1Xzvv1eGRxGTBTtLHPis8B3FPMdztvfn9sCZb5UihUjxNzXRP1uVY0qSBfML55EDQVS/zNPePZBZ2q146aQjPbGMo80DyRm1o6pUfyvXZhTZ5+Q3D+mXe9NQcbBr26REoQfEJKn9patbz1gK+urLJMvZgmt1k2rpzkyT4OUGpDziGfboDwXNfLAm57aF4YBrBgh5nYlQ4PPFSbBZyw/jnvElfWcrGWB9rCsJKFm1icQymmgFHrQMoqrMuBVWMLDMS88N3dXsSIuwPjRUpJemhly1XqUOvNPHivFtCYrN0FLL0R5KacQLPokj5yqKQEGfjqiPDyJSHqneeoqN8+Qx6Tdz7SmyGw1Rsxi+ckazEhjxFdRzcN+Y8rIFCc1isFP68iGVYEVI8SAwCBFyDGTtDM+Fg9IlaBNQt31drTzKlp30yjozBGCPMr8GRFXOk60g6A5UQ24gXSGUZgxqEsx9YTJGGBVv06U6RXijzw9g+TGZsaE16JIBwKxxBCDFFPF0WAif5Ckq02WQUHmybxw75oSXDAEkH2Vjul04vKoaejv/ot7/NBnQvYWVa5fdQtUoWa2ooRYkUYVQpFpsGvdNPMy6/US5nu8pBErwAyEClhY6EqHYLQ7v47TxMwWdYSXsA/qq1AAPUzDEFpMCTPSEkoM5qSOr+KpHc1BWdq0xpZf6vg6Ue3M+Mn5ZKrlLpkW5jRWewsBxcAMV3vFiBLQZmZaE8syUqb1y/UUt619z21eOoHKxxDf4BmIZHUDInUNULtY9kKsikbxd+eKEcNo5jmzgpePAGsRLRewupoJrYt19m4m2c4MhKZyoedCQAon6YrP7wMDQpqKceYd46d8EOm0UDklwvpmmnnyylfiGdP6SVG394kTOdZL82h+KmlC5KfiB8dUY7uCTac9FImluBxa61fl6JtjSYX9OGBwkNNv1ePkZINpLaxZHwAsZqzSZNEBs1nuWlrkgKZnpeXTZmjExAVa7qPBFzJukUB/ZaEkVQsBP72Ml2MpihS8nDfrzRim4vXyUiOzp6ZJvvLSMcNMx9PIY6P40VTaPMhJigGDNP/mJmhRAMh9aj7u8roZIW/W7Kx3MG4KlRolGUOade0Kyei+kVBsDfBqbk5nE7T8h1cZ938Z3og+EyNKmBNNv1lLaJIdQzm0WKcRmyLeS9z7o/xkmwLf3R5otomvBvUjvnWD1DhjTTSs9pRbPcQDeWA1GJKE7zmkNFD+kljWQqwQbappVYvF5WAOzOMvxhKUF796IdYOKhCz7Vsedb5iUJUamHSDl4O+DJcTIGkAJDFjkKEkRs7skCXHf0OEqa0GOk5wguU50FczTzDPFZJCV5WLGEgJ2QxbcMWYTp/a4XLPo+9wYcm7o2nx6igSXjostknjm56Mv0UmRT9PraIoJ6Z4iuCItJOOS0NOnvhv2b9kvyWodlQetTx62RsNQ1jZQmyJSYwlxk5plB2zKxzjy2VaiJAA6xa34XyU2VK6xpMd7l4DIue8QlZALgzJcLtCtDGJueO9GaVI+/GUhhkCVMsmuSbGI/E/LJM23FHcQ4eZEvZeGt7CdMZKY+dehn5MHyPwDe1tTHuLpVIJWiEtjpzfUohBCTaGVEzEUsjN9pJcWmtiyxed0MhitKLCPAP7ArJL47789RNrst2iaa+qgcdHpuWlLZdYZuavIgbSA/7BQx/Ey7PJHltls2HUtRRscNqA8uuQsYDhLFSmAClrg7ixSGcLUZ4XhTavO53T35P0Q5dKTikLY7jxy5gTfVvr7NM58g/S7axoNfVh3/N4Xvw9toQYJKmHaq00TdPasaNaVCdWXEr6t/7GPPE6DduNOZA78z/p9Ey2jFtzh1hQ2kaB0uHEL1k3AV9yv/CSZjBytDA7rj7SSruTF7umFz/PxFf/2Xy7J5+LJyINU62rWtnNV/BqvTNGGZ2o/vBAfM15cWHtSUBE5RDUVobMo1AbBeJ1E0thSYO7MlTnYp9j6L6Q4OmIFVHSMxZ70dnzLsflTXmxKPzImjqxYCbd7+AlBVjZhold4PB9D9Fr2U7qJy6vbpHfZVxr367x3P3khReyU+YT4DubJ7Pi2OXy8BCg62U3ED+aeGHMyDQBAZbPT2vxyqCoW8Z07zL0WoH0mG02a02so1CWnwr6Wcz8LnocZXmxWPhRYSYdnKNVSbosnTjbUBmLU8uCLDZJyJyYP+gxqAswI3JhwaMyyg9bXNuQF2vKgSnfDGqFG2t/MfG9G6aDWpj5N8u3Gze6jcDUWp/3uaM9GwpzZfBp3O2+ZuFJeLtQqitAhDSt94lVhtzxK/CgjBocOpaoDMoc1hkmgljpWD0qIB1iXy8otwFX9gfMVZn4ZdsR4bvNJL3sfUzZdZXsAGkMlKRFWCsTfcusZ4Xn9XnzfEfbvFh4ySuV47W88TmrRvomBdKc6K4tBvmw+DboFIwNcTdFxGpyUdG6C+FGL4sgHUCkh6g+4qw6IXbBmxPL9oOlfJRLLryaVxdQUTZ5yuXSepc9Bc4ExVWKz5zo/rb/2qbFIuJm3VkCXHyYFSffzqjztG92Ljwvk5WbDJQXYL48/abKDHr1qi+tDt0GzIkX/632DtabnbuPTgqvmIX46tGlDLtYrsoNoi0Q9OoJGZtMa1z6BJnP4QMocnbIsqf+Wo4i4rc4VCCPr1hvSl/enbAQmzHjTmDpTEfNjht2p4o7Caa77himtbyVXEkIK7XR2zClpimh0QchxBYr4XdZCzE5+1umupHCUjQLxJk9WqdZhJYu32uTj0yObZrjMg88Cww+U6Hih3J49XrAucIsLMgIRTMnkV5ah0LHmECb+Eg4UgP8CKhi6LWwKBOeKk8EaZgmvzhzopDaOmJUPq1rhiFzq7kPsHwe7aNjuTJzTlSviVlYgjKgMrQ+G2pvNlU5Q1XREem6OzddevBpEqbgKlyLKpAE5h6vXA8GQAkweXK+yYdF03eGFANY5IRFXk0TuymdD5ge06FPW/RynMsMGBVPoO3N6ZGk1XpoeSzl94IZfbR2sXfRYVWsLPkWl0C8aLVDdnI21VM6rFo2uov4NZq8cPe5GS/W1b6o/lQ6xkrZ/JizJualafCg19uiiLtfChMEPfszD2R9RVP2suHbLpE/lwhsJ2jFztpaki5BTFjEBIJvdq5m4F4RmlinW67sLM27JlIBlvIsayUjT5iUmU26nmwmDa/Jr7Q5MYHpr5m3Lha+tJVMK6KysPkHban1aTMRXxVE/sjtgIUuFPNGBtwLafMgz+rLhvvq3L5FO5cuYF11Y9IF7HaJ2fBsPxdnDPKvmbjLE3KzO0OaolJNbGUIMbQ3wKvX3iTSa7OZB50QYJ0WjEtN8LbDT557fCSFzAAZFmDhcMmLPQDyj+36XciOQzw7WXOVHzOJmVdm8I8RHKr+GAqueHZ4CkpgL29m5OBpIIH44QzMiUB+v3AFlBkvPHlx42uvPi8zLtQMJNiikaDALN4f7n2/VKD0YeACLK2FmI12BkqvlaIlgp4m7NAI3mur3lKhXxax/HRe+JbPITMcKUGmhZjpnaif+waLkJlRrm8ZqbJfpItFAYdxIJZGJaU28ugmfF6j5YmIA3N1AHpadgZj0kGecN062sHHiEdS4+bxiQhUO3ZolB0OKh2gyKSVT5WbZsIL077UzLqHyEvRk6i3osPKvWj8DBUh/Kg0YukE5zDq3XUpeVQXmb6wCfLNS744ppnOPzhmBwX70kuTVk6tyIFJnnDrmeUxgF+volQYQF1kJhfvAUsbUNfHQNAXv3m54lrJLzyLEvhaNuvYkQ3Nh6FTWRkKnYnHYR6eicey/V+ceolw7DDP2eTkNR9GTbupAEoivY8lfdl+JLRuu0TylBiCYRUgoTE7fBARWMIPg16kep+YQtkhu5TAi7CRlxWgUSOfM9nJIaa/tiK7WLFzs9eenzMTUJfmhehZr3/oBTIuM2wDKdqX6UEeKcyd/9pJcn7D0px8VFqFsd0rvvxqVDJMRcx5ZsJrqTISkJywMTPISsqv6giU1GOqymcoBN800zEBsoBuGTwtx5+T6vvGc2vOpmW39dCs8ryXK9RfuKAxhYWh+VgMwmoHSTNmr5o+Wox0WUTeluA2rgMSKQEwpEp48xvH07QWYl1Br/dwlRl/WtFcWi5eV+plqRkjq4WlH5Q0QVVisqqAdtG6nRtuh/Ghj6n/7fRha2Vxv2DOQL3UEKpbJlS3GNYVja68Jh5TYvC77zdvE0Z8wzOltWOHhaj5eqU2xCyKSLfTXDFsL+H3tRpEtF8VTWzRaINgK0k7IZhapRXDS+5A7MDrxEB8li6NTm76rLYBAPH7rjSdiLiWccxHIy7TcHwmnttCPnjSCdP8mBSkyVHSYcqMWCxEyoNFm3lzoUzKvEwp8bvEaiFmIGqwWNmT+p7BN1gXn8wRGOLzRv5QuG2tikcgL8tDtciM3EE1vYh27AG7hZueA2nK8JJHw+XRCocUHvGH+uZtO/DFlXkVxlX/25yUOb7LTBPyOpS08gSZR37xnwzWTdlq7bICgeUvnzQSVjRFlqbTNEVau9jXKIUOaqGtkQ2kamlNryUGygvLquBpC9ejUH7PQ0g4hOKVQSxtk/ey+Zp727g50V7P4WswWa3LXOsrKEWJuEpP4vE9WqHkOQa+01QkP0VamCyz3Eag/UT1wV4M0pkCcLxDqoWk3S55p4vIW53rY6ciUZV5qFJ0mw9z5tZRZC/KaGUQKJtnVQWLpmRqfzlrQl7kZJDd++XJOkdYheLHay724N0qLz7eQpqZ9mJjRnz+wNJK4DojFJXFzr8IluDyrc/F0smpM6lFunEyZltlIrT1VDN9J9ZCs3xXpINJIkyIYuliX5HwXRlCTAwqoUYliMZhVvRqYEyEoun2QpAG8mzFXJKXSfeLVl2OQeUss15RWZbRCK09+cK7dbJDGS0wqG0Kl2y3Sn0ktWZVXD6lRGgf96IU8DsjlBAWFBffjZM53cPihAxlSNalFGj+uiicRDkC3oxvp5WChorp5uSlmoAMsVibEx2UHFQillcyEik4yJudsRwbHUOeMM1ddjJmxzGFqaITZuu1tSlGrit0K2s6DhfR2gzkUoV/QDQpm3nI72VPBemkpltsTjTKElhH8w3Y6rvxzfQfkJeHMkcA6VPsizdfkIjA1zhj6shPMby+5ZOyXBybZbbLHjZtWu0I3UOkaTUbX/LGM47V0H3rhJJfMgQLqbU2EpVYom8JnpgyoYoPCE3Drb6q7royDgCuCMzzo0uT2kqR93IvWU1RovTp3a03UF5KHxdufF/6Yu59g3i1Vd5JhxMnp2ryzLS5MC+GwtHbLtppZErdtfZ0YZt526UkBVuVpkSgFmKF6Fn/WcLIm8u2jRgN0PreegOVTekbUpcS3Nl1J+i2Ek9pVdkHgHqmP/KfiBQIL+JFKgTMCQ/wGKCbV6b8/Jk3nhserBuPAOHVlT0l36XTTttnaOSQKtXfmOafa3zVja0rw5y4xLA0/EcC5hFvaDkEzZFt0i2E6PmuCQ4Iv0S9UqSDJqgKGqDIiSNmnTN2f5dJNw9unj6zaIaG4sEeyIObpaU5MbICCX5zordtAm7+eebEIocX24mFWaY8N73PnOg6cpgw18UA5NKORWZtTr9cwXJm+pv3hdMTEsYY90qs0MRVa2JQlt/K0HsBBoS4WBq82fDVvf9dcF7kDuRbNm7pfuNhuqq+V8VMPI9uO3FyNTFPXF/8eD1MxodXEwvT9oS3oImF0/jjZgSUFd/c0BySJ+F74xQiO5lNR6hPBVpqvKYOJcRaFbQ+1EIMVVp+I0HOxxe+AhBbpyFjSjQKnLFaeRYbt4p+04m+14t1lKJBLciTY04Mf0ozVOzE5IaXiRshyHQcXoZYM6Ofpv9vFI1MUITDkJWmrCBzHH0Ay+mlyjWx5W1OlG4vUXE7ykjAJdgwF+SxULX9MbNDND+6etVbVvHddEaGXpo58VtB4GXm2VPXJwWhobPUi1somH15cPtSxhxHxvNi8nGmQDfngDkx5LWo4svSeLpMyPoYo4+ZuYY8OG0TnmHaNDwCjVCHfti0aXlRUvZgLTkW+DQwFafALGg9J5tPaRolFPV9/ZzpEG2qzGTqTerl335gD3AppYJ+NYPe8hZiDqqYdZcZ7+T8MHbsTwCAmN8Bj9prUgbeV8h71lmBqUf2SBYTO4ZqwN03ELuaffthdF8n8SORA0sJqAHPKEVReZyDk1SOprd27qSqJKRJrBUXf3XyROBpIMdY4qWQ0SV8A3kEfSUQjOdy/5ebkFkh/D00hRy5hAIsyA3j5l1wLBOPDAEtBWtWYwKEIFO8h95QKciNSTzLKhZMEgSAtImF+fNopou1YwfA68sds9utmNLJWxgJkrJu5CWie6NG2Z+NWVmXTVH2i1wORUpslYN1FShTs+bMvVX6xpxcvSudqo+QxrOcoPuirjdvvNy61L1OX8nmHCzsoafjeSw4Uj0K5qf1c6KAGCPzbXDXMbJc5b+Xvgow8yTrI9knIjSbTX4hZi3EzKYzQN0dhIteVYsXR3Vvh26GttmpYkziuZm718iXJVAiK0GaX0EUYSbyzfIK0DLrZcsdFT+OoB7KyqjHnrhknrenHxNY9ISvSMvymR+jaXqi8gHPRyNerPMyZmmEyuLececTA+U40RwU0crmaWpKon4dn3RtSiQjTOfLjL4gTZqSG9uj0CSRneyGtFFdLp9QzC9rmjZztLvyuDAdO3o1SWxpNPXNmKrOo4CDFmiW5HppgsXzrsaPTqOiyuzWPE+aGs2PHcFfbV4PwoBnYV7eZcLd5614ILZCKxPP/BTkZzpgaIeP4nKX2uMVyzds06E1CQMgbaXNZrOyw3+BC1WIxbZZ5IAReuFikZ8NMyJlaUqFvS0UEAjNxPLCWOD7ckMs750uo6rbrL0wP35FKCsQ3EHSFEDmXz7oVZNnJ2i0I8h85Y2FjBkjeKx3jUnzHRnfAW3Ws018Zjh/lhqfuNHFFcBZzvQdBQwMzbRaIba8zYlFM7N2zWAl0rY1m2kjUiWDZwtEvLPnUGRPO7TaNGXruWx874GqMHj12If8ZWm1hP7KChajjX5RaqLVwr4ed9C1N9LKW4lZsHytbDSOiRtzOr9tcvPzkEfDjGMiJk8GpszrIV6y4WZ+Ol8Zbj6XLLjhuXAVaIMPX1x9/r7MSz9OU/ucxnaxMjWxVlbEQzTagGro9klVhq7zUsUaXY/BfD9Y4HlBaMnc7KAqG6/DkwEzXXBvlPx0WRMrmvzGmhNjzJuW1hmbpxIC2efedJEaX4iHwvrMeeyWT28a13/1rI9/TXtpTrzvvvtwzTXXYHR0FFNTU/jIRz6CQ4cOWXGuu+66jA38tttus+IcPXoUN910E0ZGRjA1NYW77roLi4uLpZkP2toj+7h5cnPmg5xnFDeTqEKWxvMP9cmL23XhEfN+tMhUmYEkNm5lKGHnje5XBawHfdd8Axey9RL6mHSqqEedVg9yIbqxvLTCT1FZQ3F8POaXs1yevvi+7yqO+k9PCJghP6Rg5DC1NB/fvOPKf6VnTg4fbp4A0BQndlSFUubEJ598ErOzs7jmmmuwuLiIL3zhC9i1axdeeeUVrFq1SsW79dZbce+996rfIyMj6nuz2cRNN92E6elp/OAHP8CxY8fwx3/8x+jv78df/dVfVVCkJQTHo2gpooOOhyXROS56VsYuZ+pmZ61RuiY146+XzTYqzTRzVY0ytFvhoRO8F9F0nzOm/RN9qTImWRlXJhB/VXoG5cJvg8T/7ZU3Uz4v41ojq9qxo5QQ++53v2v9fuihhzA1NYVnn30W1157rQofGRnB9PS0l8b3vvc9vPLKK/j+97+PDRs24H3vex+++tWv4u6778aXv/xlDAwMRPMjZybLdU9KtSD7a+QAVHacCpFudWYunH7bU8nayL8TdMj1SxaVlre20gnwKvXP9JvQg184cQF9b5vJE8qrb8vgwcBOHbZbp6a2E9KMTR6qaENmqlCkPYL1iSbZcU4JMrW9Rkouo//pY06gzQN6c7JKm2lGGR4+GNnLP5gYiuz1OfWcgIWFeTSbzcre2bbWxE6ePAkAmJiYsMK//vWvY3JyEtu2bcPevXtx5swZ9ezgwYPYvn07NmzYoMJ2796NU6dO4eWXX/bmc/78eZw6dcr6AFkbcNdMRT1Aqdekg9XgsUpUh5U6F+lxt6y8WoOukqGw0oTRCte9HAdCJsayvLQyl+PLYuT8BYAU2htRehsCpjDTz1Lnt/6b1xLxrSQnTYxvdm7BUSiElr0T0zTF5z73OXzwgx/Etm3bVPgnP/lJbN68GZs2bcILL7yAu+++G4cOHcK3vvUtAMDc3JwlwACo33Nzc9687rvvPnzlK1/xPuuVJtZtE9WSE88RDJl1FFVfPShkLl9lG7mDnaId0q2mC+bZsTKWOVxLpvEjdlyIqddYWnlrY90YoxjTKxi2edIXnvVkDH3Pq5+YVnLN2lWfYt+yEJudncVLL72Ep59+2gr/7Gc/q75v374dGzduxPXXX48jR47g8ssvbymvvXv34o477lC/T506hUsuucSKY9qJXXSiAy05odIhVDV4VlZfFQuWXFJlmW5jDclF3skkS6ePVyu1W6EkTabuHV7yu4uYE198pcqjFRJSZXmpAm6eRTx2DQShMorNzhUKsZbMiXv27MG+ffvw+OOP4+KLL86Nu2PHDgDA4cOHAQDT09N4/fXXrTjyd2gdbXBwEGNjY9YH0Ob+ItV9JZsZY9BO3w3VXOdfB38OvtNDcs0drA1eyyassFJKm6EK4nfIzaILecQh5LmXFy+DkgXw5el6Hfo8C8300VlH8ObzbvV5dPYGpNaFFxcXQWkKllSzw6sUFSLCnj178Mgjj+DAgQPYsmVLYZrnn38eALBx40YAwMzMDF588UUcP35cxdm/fz/GxsawdevWMuwA8K+Ltet6u9LQiSrofK0GJiTRMfWzlnntgiYW48Idk64DrGVQNI4upTetpXpl1p9cOiF3+DJ8ebIu5M0PLbjKbLDuBRgYKK3yNrGS5sTZ2Vk8/PDDePTRRzE6OqrWsMbHxzE8PIwjR47g4Ycfxu///u9j3bp1eOGFF/D5z38e1157La688koAwK5du7B161Z86lOfwv3334+5uTl88YtfxOzsLAYHB6P4kA11+u0z4rcd7ovvPYmhK3ZqpwNRXn/khgyvd2ohbBt4ND8x8SKsRu14JxIC19ME4rdrTcw0e8VrWVH9qiBPq886cX2DYN7+Mnm/lAnpnRhT9LLvSV58a7A1HOPi1lbi+MjlN2ewLwuTRtmxJ++ZdKngYFZ8/d2sS+GA4ZQt2EdIX0qZx5tGVtcJ97VEvNQpGPGSqGOQkwaABGfPn8f8/AKazTSXVjSoBJB1ayEA9OCDDxIR0dGjR+naa6+liYkJGhwcpHe+851011130cmTJy06P//5z+nGG2+k4eFhmpycpDvvvJMWFhai+XjttdeCvNSf+lN/6k/9WT6f1157rYwYyoAJ4bSskKYpDh06hK1bt+K1115Ta2Q1bEgHmLqO/Kjrpxh1HRWjrqNi+OqIiHD69Gls2rQJSRvrY8vyAOAkSXDRRRcBgOXoUcOPuo7yUddPMeo6KkZdR8Vw62h8fLxtmivzAOAaNWrUqHFBoBZiNWrUqFFj2WLZCrHBwUHcc8890R6NFyLqOspHXT/FqOuoGHUdFaOTdbQsHTtq1KhRo0YNYBlrYjVq1KhRo0YtxGrUqFGjxrJFLcRq1KhRo8ayRS3EatSoUaPGssWyFGIPPPAA3vGOd2BoaAg7duzAj370o16z1DN8+ctfzhxMesUVV6jn586dw+zsLNatW4fVq1fjYx/7WOYWgZWGp556Cn/wB3+ATZs2gTGGf//3f7eeExG+9KUvYePGjRgeHsbOnTvxs5/9zIrz5ptv4uabb8bY2BjWrFmDz3zmM3jrrbe6WIrOoah+Pv3pT2f61A033GDFWcn1A/A7DK+55hqMjo5iamoKH/nIR3Do0CErTsy7dfToUdx0000YGRnB1NQU7rrrLiwuLnazKB1BTP1cd911mX502223WXGqqJ9lJ8T+9V//FXfccQfuuece/OQnP8FVV12F3bt3W6fiX2h473vfi2PHjqmPecfb5z//efzHf/wHvvnNb+LJJ5/Er371K3z0ox/tIbedx9tvv42rrroKDzzwgPf5/fffj7//+7/HP/3TP+GZZ57BqlWrsHv3bpw7d07Fufnmm/Hyyy9j//792LdvH5566inrrrzljKL6AYAbbrjB6lPf+MY3rOcruX4A4Mknn8Ts7Cx++MMfYv/+/VhYWMCuXbvw9ttvqzhF71az2cRNN92E+fl5/OAHP8A///M/46GHHsKXvvSlXhSpUsTUDwDceuutVj+6//771bPK6qetkxd7gA984AM0OzurfjebTdq0aRPdd999PeSqd7jnnnvoqquu8j47ceIE9ff30ze/+U0V9t///d8EgA4ePNglDnsLAPTII4+o32ma0vT0NP3N3/yNCjtx4gQNDg7SN77xDSIieuWVVwgA/dd//ZeK853vfIcYY/TLX/6ya7x3A279EBHdcsst9OEPfziY5kKqH4njx48TAHryySeJKO7d+va3v01JktDc3JyK87WvfY3Gxsbo/Pnz3S1Ah+HWDxHR7/7u79Kf//mfB9NUVT/LShObn5/Hs88+i507d6qwJEmwc+dOHDx4sIec9RY/+9nPsGnTJlx22WW4+eabcfToUQDAs88+i4WFBau+rrjiClx66aUXbH29+uqrmJubs+pkfHwcO3bsUHVy8OBBrFmzBr/927+t4uzcuRNJkuCZZ57pOs+9wBNPPIGpqSm85z3vwe2334433nhDPbsQ6+fkyZMAgImJCQBx79bBgwexfft2bNiwQcXZvXs3Tp06hZdffrmL3Hcebv1IfP3rX8fk5CS2bduGvXv34syZM+pZVfWzrA4A/s1vfoNms2kVGgA2bNiAn/70pz3iqrfYsWMHHnroIbznPe/BsWPH8JWvfAUf+tCH8NJLL2Fubg4DAwNYs2aNlWbDhg3qLrgLDbLcvj4kn83NzWFqasp63tfXh4mJiQui3m644QZ89KMfxZYtW3DkyBF84QtfwI033oiDBw+i0WhccPWTpik+97nP4YMf/CC2bdsGAFHv1tzcnLefyWcrBb76AYBPfvKT2Lx5MzZt2oQXXngBd999Nw4dOoRvfetbAKqrn2UlxGpkceONN6rvV155JXbs2IHNmzfj3/7t3zA8PNxDzmosV/zRH/2R+r59+3ZceeWVuPzyy/HEE0/g+uuv7yFnvcHs7Cxeeukla625hkaofsw10u3bt2Pjxo24/vrrceTIEVx++eWV5b+szImTk5NoNBoZD6DXX38d09PTPeJqaWHNmjV497vfjcOHD2N6ehrz8/M4ceKEFedCri9Z7rw+ND09nXEUWlxcxJtvvnlB1ttll12GyclJHD58GMCFVT979uzBvn378Pjjj+Piiy9W4THv1vT0tLefyWcrAaH68WHHjh0AYPWjKupnWQmxgYEBXH311XjsscdUWJqmeOyxxzAzM9NDzpYO3nrrLRw5cgQbN27E1Vdfjf7+fqu+Dh06hKNHj16w9bVlyxZMT09bdXLq1Ck888wzqk5mZmZw4sQJPPvssyrOgQMHkKapehEvJPzP//wP3njjDWzcuBHAhVE/RIQ9e/bgkUcewYEDB7Blyxbrecy7NTMzgxdffNES+Pv378fY2Bi2bt3anYJ0CEX148Pzzz8PAFY/qqR+WnBE6Sn+5V/+hQYHB+mhhx6iV155hT772c/SmjVrLA+XCwl33nknPfHEE/Tqq6/Sf/7nf9LOnTtpcnKSjh8/TkREt912G1166aV04MAB+vGPf0wzMzM0MzPTY647i9OnT9Nzzz1Hzz33HAGgv/3bv6XnnnuOfvGLXxAR0V//9V/TmjVr6NFHH6UXXniBPvzhD9OWLVvo7NmzisYNN9xAv/Vbv0XPPPMMPf300/Sud72LPvGJT/SqSJUir35Onz5Nf/EXf0EHDx6kV199lb7//e/T+9//fnrXu95F586dUzRWcv0QEd1+++00Pj5OTzzxBB07dkx9zpw5o+IUvVuLi4u0bds22rVrFz3//PP03e9+l9avX0979+7tRZEqRVH9HD58mO6991768Y9/TK+++io9+uijdNlll9G1116raFRVP8tOiBER/cM//ANdeumlNDAwQB/4wAfohz/8Ya9Z6hk+/vGP08aNG2lgYIAuuugi+vjHP06HDx9Wz8+ePUt/+qd/SmvXrqWRkRH6wz/8Qzp27FgPOe48Hn/8cQKQ+dxyyy1ExN3s//Iv/5I2bNhAg4ODdP3119OhQ4csGm+88QZ94hOfoNWrV9PY2Bj9yZ/8CZ0+fboHpakeefVz5swZ2rVrF61fv576+/tp8+bNdOutt2YmiSu5fojIWz8A6MEHH1RxYt6tn//853TjjTfS8PAwTU5O0p133kkLCwtdLk31KKqfo0eP0rXXXksTExM0ODhI73znO+muu+6ikydPWnSqqJ/6KpYaNWrUqLFssazWxGrUqFGjRg0TtRCrUaNGjRrLFrUQq1GjRo0ayxa1EKtRo0aNGssWtRCrUaNGjRrLFrUQq1GjRo0ayxa1EKtRo0aNGssWtRCrUaNGjRrLFrUQq1GjRo0ayxa1EKtRo0aNGssWtRCrUaNGjRrLFrUQq1GjRo0ayxb/H0HQGI9+OLysAAAAAElFTkSuQmCC\n" + }, + "metadata": {} + } + ] + }, + { + "cell_type": "code", + "source": [ + "import numpy as np\n", + "image = image.reshape((-1, 254, 254, 3))\n", + "res = model.predict(image)\n", + "class_names[np.argmax(res)]" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/", + "height": 53 + }, + "id": "wm6Sl1LC1dyk", + "outputId": "7d31513e-ae00-4da8-8efc-e7ce32f70744" + }, + "id": "wm6Sl1LC1dyk", + "execution_count": 22, + "outputs": [ + { + "output_type": "stream", + "name": "stdout", + "text": [ + "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step\n" + ] + }, + { + "output_type": "execute_result", + "data": { + "text/plain": [ + "'DrinkCans'" + ], + "application/vnd.google.colaboratory.intrinsic+json": { + "type": "string" + } + }, + "metadata": {}, + "execution_count": 22 + } + ] + }, { - "ename": "NameError", - "evalue": "name 'model' is not defined", - "output_type": "error", - "traceback": [ - "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m", - "\u001b[0;31mNameError\u001b[0m Traceback (most recent call last)", - "Cell \u001b[0;32mIn[1], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mmodel\u001b[49m\n", - "\u001b[0;31mNameError\u001b[0m: name 'model' is not defined" - ] + "cell_type": "code", + "source": [ + "model.save('/content/model_v1.keras')\n", + "model.save('/content/model_v1.h5')" + ], + "metadata": { + "colab": { + "base_uri": "https://localhost:8080/" + }, + "id": "mb7uOOi2_seQ", + "outputId": "aebbd0ab-3ef4-493d-eae6-45ab7d7ee840" + }, + "id": "mb7uOOi2_seQ", + "execution_count": 23, + "outputs": [ + { + "output_type": "stream", + "name": "stderr", + "text": [ + "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n" + ] + } + ] } - ], - "source": [ - "model" - ] - } - ], - "metadata": { - "kernelspec": { - "display_name": "Python 3 (ipykernel)", - "language": "python", - "name": "python3" + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "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": "3.10.6" + }, + "colab": { + "provenance": [], + "gpuType": "T4" + }, + "accelerator": "GPU" }, - "language_info": { - "codemirror_mode": { - "name": "ipython", - "version": 3 - }, - "file_extension": ".py", - "mimetype": "text/x-python", - "name": "python", - "nbconvert_exporter": "python", - "pygments_lexer": "ipython3", - "version": "3.10.6" - } - }, - "nbformat": 4, - "nbformat_minor": 5 -} + "nbformat": 4, + "nbformat_minor": 5 +} \ No newline at end of file