{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "-wZA7P-S6xl4"
},
"source": [
"**Import dataset from Google Drive (EuroSAT)**"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "WC0dXoHCrlbz",
"outputId": "1e152f3d-b44d-4ae2-e138-753cf9b11fc9"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Requirement already satisfied: gradio in /usr/local/lib/python3.10/dist-packages (5.6.0)\n",
"Requirement already satisfied: aiofiles<24.0,>=22.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (23.2.1)\n",
"Requirement already satisfied: anyio<5.0,>=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.7.1)\n",
"Requirement already satisfied: fastapi<1.0,>=0.115.2 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.115.5)\n",
"Requirement already satisfied: ffmpy in /usr/local/lib/python3.10/dist-packages (from gradio) (0.4.0)\n",
"Requirement already satisfied: gradio-client==1.4.3 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.4.3)\n",
"Requirement already satisfied: httpx>=0.24.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.27.2)\n",
"Requirement already satisfied: huggingface-hub>=0.25.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.26.2)\n",
"Requirement already satisfied: jinja2<4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.1.4)\n",
"Requirement already satisfied: markupsafe~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.1.5)\n",
"Requirement already satisfied: numpy<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (1.26.4)\n",
"Requirement already satisfied: orjson~=3.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (3.10.11)\n",
"Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from gradio) (24.2)\n",
"Requirement already satisfied: pandas<3.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.2.2)\n",
"Requirement already satisfied: pillow<12.0,>=8.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (11.0.0)\n",
"Requirement already satisfied: pydantic>=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.9.2)\n",
"Requirement already satisfied: pydub in /usr/local/lib/python3.10/dist-packages (from gradio) (0.25.1)\n",
"Requirement already satisfied: python-multipart==0.0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.0.12)\n",
"Requirement already satisfied: pyyaml<7.0,>=5.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (6.0.2)\n",
"Requirement already satisfied: ruff>=0.2.2 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.7.4)\n",
"Requirement already satisfied: safehttpx<1.0,>=0.1.1 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.1.1)\n",
"Requirement already satisfied: semantic-version~=2.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (2.10.0)\n",
"Requirement already satisfied: starlette<1.0,>=0.40.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.41.3)\n",
"Requirement already satisfied: tomlkit==0.12.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.12.0)\n",
"Requirement already satisfied: typer<1.0,>=0.12 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.13.0)\n",
"Requirement already satisfied: typing-extensions~=4.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (4.12.2)\n",
"Requirement already satisfied: uvicorn>=0.14.0 in /usr/local/lib/python3.10/dist-packages (from gradio) (0.32.1)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.4.3->gradio) (2024.10.0)\n",
"Requirement already satisfied: websockets<13.0,>=10.0 in /usr/local/lib/python3.10/dist-packages (from gradio-client==1.4.3->gradio) (12.0)\n",
"Requirement already satisfied: idna>=2.8 in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (3.10)\n",
"Requirement already satisfied: sniffio>=1.1 in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
"Requirement already satisfied: exceptiongroup in /usr/local/lib/python3.10/dist-packages (from anyio<5.0,>=3.0->gradio) (1.2.2)\n",
"Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (2024.8.30)\n",
"Requirement already satisfied: httpcore==1.* in /usr/local/lib/python3.10/dist-packages (from httpx>=0.24.1->gradio) (1.0.7)\n",
"Requirement already satisfied: h11<0.15,>=0.13 in /usr/local/lib/python3.10/dist-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.25.1->gradio) (3.16.1)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.25.1->gradio) (2.32.3)\n",
"Requirement already satisfied: tqdm>=4.42.1 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.25.1->gradio) (4.66.6)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
"Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
"Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (0.7.0)\n",
"Requirement already satisfied: pydantic-core==2.23.4 in /usr/local/lib/python3.10/dist-packages (from pydantic>=2.0->gradio) (2.23.4)\n",
"Requirement already satisfied: click>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (8.1.7)\n",
"Requirement already satisfied: shellingham>=1.3.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (1.5.4)\n",
"Requirement already satisfied: rich>=10.11.0 in /usr/local/lib/python3.10/dist-packages (from typer<1.0,>=0.12->gradio) (13.9.4)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas<3.0,>=1.0->gradio) (1.16.0)\n",
"Requirement already satisfied: markdown-it-py>=2.2.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (3.0.0)\n",
"Requirement already satisfied: pygments<3.0.0,>=2.13.0 in /usr/local/lib/python3.10/dist-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.18.0)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.25.1->gradio) (3.4.0)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->huggingface-hub>=0.25.1->gradio) (2.2.3)\n",
"Requirement already satisfied: mdurl~=0.1 in /usr/local/lib/python3.10/dist-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
"/usr/local/lib/python3.10/dist-packages/gdown/__main__.py:140: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From (original): https://drive.google.com/uc?id=1TfLNUsHcLcBsVRRoG9azevxoutUsGlud\n",
"From (redirected): https://drive.google.com/uc?id=1TfLNUsHcLcBsVRRoG9azevxoutUsGlud&confirm=t&uuid=06bae63b-03ed-40f6-b07d-38aa8c8046e3\n",
"To: /content/EuroSAT.zip\n",
"100% 95.4M/95.4M [00:00<00:00, 114MB/s]\n",
"/usr/local/lib/python3.10/dist-packages/gdown/__main__.py:140: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From: https://drive.google.com/uc?id=1yxLHauQBxiuOEcUe-_XkVtOfVAm9UySN\n",
"To: /content/resnet_image_classifier.h5\n",
"100% 59.2M/59.2M [00:00<00:00, 68.9MB/s]\n",
"/usr/local/lib/python3.10/dist-packages/gdown/__main__.py:140: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From (original): https://drive.google.com/uc?id=1zh4TiRD_4E67-wGplP85JLmKjybU9LbX\n",
"From (redirected): https://drive.google.com/uc?id=1zh4TiRD_4E67-wGplP85JLmKjybU9LbX&confirm=t&uuid=c10e6af8-165d-4625-b861-e79d45820160\n",
"To: /content/history.pkl\n",
"100% 266M/266M [00:06<00:00, 41.6MB/s]\n",
"/usr/local/lib/python3.10/dist-packages/gdown/__main__.py:140: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From (original): https://drive.google.com/uc?id=1vVM3a7qQwkynp-6gMqOvbApC0P57pLky\n",
"From (redirected): https://drive.google.com/uc?id=1vVM3a7qQwkynp-6gMqOvbApC0P57pLky&confirm=t&uuid=55f08957-6f3e-420a-b896-fa393e8a756d\n",
"To: /content/history_resnet.pkl\n",
"100% 266M/266M [00:06<00:00, 41.1MB/s]\n",
"/usr/local/lib/python3.10/dist-packages/gdown/__main__.py:140: FutureWarning: Option `--id` was deprecated in version 4.3.1 and will be removed in 5.0. You don't need to pass it anymore to use a file ID.\n",
" warnings.warn(\n",
"Downloading...\n",
"From: https://drive.google.com/uc?id=1-j-kYSD6SeO5xu3MKVX5ES-Tk1GwMyNf\n",
"To: /content/cnn_image_classifier.h5\n",
"100% 8.26M/8.26M [00:00<00:00, 28.6MB/s]\n"
]
}
],
"source": [
"!pip install gradio\n",
"! gdown --id 1TfLNUsHcLcBsVRRoG9azevxoutUsGlud\n",
"! gdown --id 1yxLHauQBxiuOEcUe-_XkVtOfVAm9UySN\n",
"! gdown --id 1zh4TiRD_4E67-wGplP85JLmKjybU9LbX\n",
"! gdown --id 1vVM3a7qQwkynp-6gMqOvbApC0P57pLky\n",
"! gdown --id 1-j-kYSD6SeO5xu3MKVX5ES-Tk1GwMyNf\n",
"\n",
"from zipfile import ZipFile\n",
"with ZipFile('EuroSAT.zip','r') as dataset:\n",
" dataset.extractall('EuroSAT_dataset')\n",
"\n",
"! rm 'EuroSAT.zip'"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "e7y0h6T0e7J-"
},
"source": [
"**Deep Learning Algorithm - ResNet Architecture**"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "82qTsWVxo4nS",
"outputId": "6c19b762-d7bb-4377-d7f9-4af318af593c"
},
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1mModel: \"functional_9\"\u001b[0m\n"
],
"text/html": [
"Model: \"functional_9\"\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┃\u001b[1m \u001b[0m\u001b[1mConnected to \u001b[0m\u001b[1m \u001b[0m┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
"│ input_layer_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m64\u001b[0m, \u001b[38;5;34m3\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ - │\n",
"│ (\u001b[38;5;33mInputLayer\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;34m64\u001b[0m) │ \u001b[38;5;34m9,472\u001b[0m │ input_layer_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization │ (\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;34m256\u001b[0m │ conv2d_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu (\u001b[38;5;33mReLU\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 │ batch_normalization[\u001b[38;5;34m0\u001b[0m… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ max_pooling2d_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ re_lu[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mMaxPooling2D\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;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │ max_pooling2d_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_1 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m256\u001b[0m │ conv2d_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_1 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_1… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_5 (\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;34m64\u001b[0m) │ \u001b[38;5;34m36,928\u001b[0m │ re_lu_1[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_2 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m256\u001b[0m │ conv2d_5[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add (\u001b[38;5;33mAdd\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_2… │\n",
"│ │ │ │ max_pooling2d_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_2 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m16\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ add[\u001b[38;5;34m0\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;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │ re_lu_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_3 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │ conv2d_6[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_3 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_3… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_7 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m147,584\u001b[0m │ re_lu_3[\u001b[38;5;34m0\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;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m8,320\u001b[0m │ re_lu_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_4 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │ conv2d_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_5 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m512\u001b[0m │ conv2d_8[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add_1 (\u001b[38;5;33mAdd\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_4… │\n",
"│ │ │ │ batch_normalization_5… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_4 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m8\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ add_1[\u001b[38;5;34m0\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;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m295,168\u001b[0m │ re_lu_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_6 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m1,024\u001b[0m │ conv2d_9[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_5 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_6… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_10 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m590,080\u001b[0m │ re_lu_5[\u001b[38;5;34m0\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;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m33,024\u001b[0m │ re_lu_4[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_7 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m1,024\u001b[0m │ conv2d_10[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_8 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m1,024\u001b[0m │ conv2d_11[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add_2 (\u001b[38;5;33mAdd\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_7… │\n",
"│ │ │ │ batch_normalization_8… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_6 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m4\u001b[0m, \u001b[38;5;34m256\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ add_2[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_12 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m1,180,160\u001b[0m │ re_lu_6[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_9 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m2,048\u001b[0m │ conv2d_12[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_7 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_9… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_13 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m2,359,808\u001b[0m │ re_lu_7[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_14 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m131,584\u001b[0m │ re_lu_6[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_10 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m2,048\u001b[0m │ conv2d_13[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_11 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m2,048\u001b[0m │ conv2d_14[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mBatchNormalization\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add_3 (\u001b[38;5;33mAdd\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ batch_normalization_1… │\n",
"│ │ │ │ batch_normalization_1… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_8 (\u001b[38;5;33mReLU\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m2\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ add_3[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ global_average_pooling2d │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m512\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │ re_lu_8[\u001b[38;5;34m0\u001b[0m][\u001b[38;5;34m0\u001b[0m] │\n",
"│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ dense_2 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m5,130\u001b[0m │ global_average_poolin… │\n",
"└───────────────────────────┴────────────────────────┴────────────────┴────────────────────────┘\n"
],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃ Connected to ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━┩\n",
"│ input_layer_1 │ (None, 64, 64, 3) │ 0 │ - │\n",
"│ (InputLayer) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_3 (Conv2D) │ (None, 32, 32, 64) │ 9,472 │ input_layer_1[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization │ (None, 32, 32, 64) │ 256 │ conv2d_3[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu (ReLU) │ (None, 32, 32, 64) │ 0 │ batch_normalization[0… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ max_pooling2d_3 │ (None, 16, 16, 64) │ 0 │ re_lu[0][0] │\n",
"│ (MaxPooling2D) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_4 (Conv2D) │ (None, 16, 16, 64) │ 36,928 │ max_pooling2d_3[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_1 │ (None, 16, 16, 64) │ 256 │ conv2d_4[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_1 (ReLU) │ (None, 16, 16, 64) │ 0 │ batch_normalization_1… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_5 (Conv2D) │ (None, 16, 16, 64) │ 36,928 │ re_lu_1[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_2 │ (None, 16, 16, 64) │ 256 │ conv2d_5[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add (Add) │ (None, 16, 16, 64) │ 0 │ batch_normalization_2… │\n",
"│ │ │ │ max_pooling2d_3[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_2 (ReLU) │ (None, 16, 16, 64) │ 0 │ add[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_6 (Conv2D) │ (None, 8, 8, 128) │ 73,856 │ re_lu_2[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_3 │ (None, 8, 8, 128) │ 512 │ conv2d_6[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_3 (ReLU) │ (None, 8, 8, 128) │ 0 │ batch_normalization_3… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_7 (Conv2D) │ (None, 8, 8, 128) │ 147,584 │ re_lu_3[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_8 (Conv2D) │ (None, 8, 8, 128) │ 8,320 │ re_lu_2[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_4 │ (None, 8, 8, 128) │ 512 │ conv2d_7[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_5 │ (None, 8, 8, 128) │ 512 │ conv2d_8[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add_1 (Add) │ (None, 8, 8, 128) │ 0 │ batch_normalization_4… │\n",
"│ │ │ │ batch_normalization_5… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_4 (ReLU) │ (None, 8, 8, 128) │ 0 │ add_1[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_9 (Conv2D) │ (None, 4, 4, 256) │ 295,168 │ re_lu_4[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_6 │ (None, 4, 4, 256) │ 1,024 │ conv2d_9[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_5 (ReLU) │ (None, 4, 4, 256) │ 0 │ batch_normalization_6… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_10 (Conv2D) │ (None, 4, 4, 256) │ 590,080 │ re_lu_5[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_11 (Conv2D) │ (None, 4, 4, 256) │ 33,024 │ re_lu_4[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_7 │ (None, 4, 4, 256) │ 1,024 │ conv2d_10[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_8 │ (None, 4, 4, 256) │ 1,024 │ conv2d_11[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add_2 (Add) │ (None, 4, 4, 256) │ 0 │ batch_normalization_7… │\n",
"│ │ │ │ batch_normalization_8… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_6 (ReLU) │ (None, 4, 4, 256) │ 0 │ add_2[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_12 (Conv2D) │ (None, 2, 2, 512) │ 1,180,160 │ re_lu_6[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_9 │ (None, 2, 2, 512) │ 2,048 │ conv2d_12[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_7 (ReLU) │ (None, 2, 2, 512) │ 0 │ batch_normalization_9… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_13 (Conv2D) │ (None, 2, 2, 512) │ 2,359,808 │ re_lu_7[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ conv2d_14 (Conv2D) │ (None, 2, 2, 512) │ 131,584 │ re_lu_6[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_10 │ (None, 2, 2, 512) │ 2,048 │ conv2d_13[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ batch_normalization_11 │ (None, 2, 2, 512) │ 2,048 │ conv2d_14[0][0] │\n",
"│ (BatchNormalization) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ add_3 (Add) │ (None, 2, 2, 512) │ 0 │ batch_normalization_1… │\n",
"│ │ │ │ batch_normalization_1… │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ re_lu_8 (ReLU) │ (None, 2, 2, 512) │ 0 │ add_3[0][0] │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ global_average_pooling2d │ (None, 512) │ 0 │ re_lu_8[0][0] │\n",
"│ (GlobalAveragePooling2D) │ │ │ │\n",
"├───────────────────────────┼────────────────────────┼────────────────┼────────────────────────┤\n",
"│ dense_2 (Dense) │ (None, 10) │ 5,130 │ global_average_poolin… │\n",
"└───────────────────────────┴────────────────────────┴────────────────┴────────────────────────┘\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m4,919,562\u001b[0m (18.77 MB)\n"
],
"text/html": [
" Total params: 4,919,562 (18.77 MB)\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m4,913,802\u001b[0m (18.74 MB)\n"
],
"text/html": [
" Trainable params: 4,913,802 (18.74 MB)\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m5,760\u001b[0m (22.50 KB)\n"
],
"text/html": [
" Non-trainable params: 5,760 (22.50 KB)\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "error",
"ename": "KeyboardInterrupt",
"evalue": "",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mKeyboardInterrupt\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 149\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 150\u001b[0m \u001b[0;31m# Train the model with early stopping\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 151\u001b[0;31m \u001b[0mhistory\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mmodel\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfit\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_train\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_train_one_hot\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mepochs\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m10\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbatch_size\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m32\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalidation_data\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mX_val\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my_val_one_hot\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcallbacks\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mearly_stopping\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 152\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 153\u001b[0m \u001b[0;31m# Evaluate the model\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/utils/traceback_utils.py\u001b[0m in \u001b[0;36merror_handler\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 115\u001b[0m \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 116\u001b[0m \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 117\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfn\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 118\u001b[0m \u001b[0;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 119\u001b[0m \u001b[0mfiltered_tb\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0m_process_traceback_frames\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0me\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__traceback__\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/backend/tensorflow/trainer.py\u001b[0m in \u001b[0;36mfit\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 280\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 281\u001b[0m \u001b[0;31m# Create an iterator that yields batches for one epoch.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 282\u001b[0;31m epoch_iterator = TFEpochIterator(\n\u001b[0m\u001b[1;32m 283\u001b[0m \u001b[0mx\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 284\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/backend/tensorflow/trainer.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, distribute_strategy, *args, **kwargs)\u001b[0m\n\u001b[1;32m 666\u001b[0m \u001b[0msuper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 667\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_distribute_strategy\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdistribute_strategy\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 668\u001b[0;31m \u001b[0mdataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_iterator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 669\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdistribute\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDistributedDataset\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 670\u001b[0m dataset = self._distribute_strategy.experimental_distribute_dataset(\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/backend/tensorflow/trainer.py\u001b[0m in \u001b[0;36m_get_iterator\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 675\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 676\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_get_iterator\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 677\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata_adapter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_tf_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 678\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 679\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0menumerate_epoch\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/trainers/data_adapters/array_data_adapter.py\u001b[0m in \u001b[0;36mget_tf_dataset\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m 234\u001b[0m \u001b[0mindices_dataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mindices_dataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mmap\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrandom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshuffle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 235\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 236\u001b[0;31m \u001b[0mdataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mslice_inputs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mindices_dataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_inputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 237\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 238\u001b[0m \u001b[0moptions\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mOptions\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/keras/src/trainers/data_adapters/array_data_adapter.py\u001b[0m in \u001b[0;36mslice_inputs\u001b[0;34m(indices_dataset, inputs)\u001b[0m\n\u001b[1;32m 195\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 196\u001b[0m dataset = tf.data.Dataset.zip(\n\u001b[0;32m--> 197\u001b[0;31m \u001b[0;34m(\u001b[0m\u001b[0mindices_dataset\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtf\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mDataset\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_tensors\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0minputs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrepeat\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 198\u001b[0m )\n\u001b[1;32m 199\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/data/ops/dataset_ops.py\u001b[0m in \u001b[0;36mfrom_tensors\u001b[0;34m(tensors, name)\u001b[0m\n\u001b[1;32m 739\u001b[0m \u001b[0;31m# pylint: disable=g-import-not-at-top,protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 740\u001b[0m \u001b[0;32mfrom\u001b[0m \u001b[0mtensorflow\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpython\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mops\u001b[0m \u001b[0;32mimport\u001b[0m \u001b[0mfrom_tensors_op\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 741\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfrom_tensors_op\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_from_tensors\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 742\u001b[0m \u001b[0;31m# pylint: enable=g-import-not-at-top,protected-access\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 743\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/data/ops/from_tensors_op.py\u001b[0m in \u001b[0;36m_from_tensors\u001b[0;34m(tensors, name)\u001b[0m\n\u001b[1;32m 21\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 22\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m_from_tensors\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;31m# pylint: disable=unused-private-name\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 23\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_TensorDataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtensors\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 24\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 25\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/data/ops/from_tensors_op.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, element, name)\u001b[0m\n\u001b[1;32m 29\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0melement\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 30\u001b[0m \u001b[0;34m\"\"\"See `tf.data.Dataset.from_tensors` for details.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 31\u001b[0;31m \u001b[0melement\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstructure\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mnormalize_element\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0melement\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 32\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_structure\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstructure\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtype_spec_from_value\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0melement\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 33\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_tensors\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mstructure\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mto_tensor_list\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_structure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0melement\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/data/util/structure.py\u001b[0m in \u001b[0;36mnormalize_element\u001b[0;34m(element, element_signature)\u001b[0m\n\u001b[1;32m 132\u001b[0m \u001b[0mdtype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mgetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mspec\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m\"dtype\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 133\u001b[0m normalized_components.append(\n\u001b[0;32m--> 134\u001b[0;31m ops.convert_to_tensor(t, name=\"component_%d\" % i, dtype=dtype))\n\u001b[0m\u001b[1;32m 135\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mnest\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpack_sequence_as\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpack_as\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnormalized_components\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 136\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/profiler/trace.py\u001b[0m in \u001b[0;36mwrapped\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 181\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mTrace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mtrace_name\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mtrace_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 182\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 183\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 184\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 185\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mwrapped\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/ops.py\u001b[0m in \u001b[0;36mconvert_to_tensor\u001b[0;34m(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)\u001b[0m\n\u001b[1;32m 711\u001b[0m \u001b[0;31m# TODO(b/142518781): Fix all call-sites and remove redundant arg\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 712\u001b[0m \u001b[0mpreferred_dtype\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mpreferred_dtype\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mdtype_hint\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 713\u001b[0;31m return tensor_conversion_registry.convert(\n\u001b[0m\u001b[1;32m 714\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mas_ref\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mpreferred_dtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maccepted_result_types\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 715\u001b[0m )\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/tensor_conversion_registry.py\u001b[0m in \u001b[0;36mconvert\u001b[0;34m(value, dtype, name, as_ref, preferred_dtype, accepted_result_types)\u001b[0m\n\u001b[1;32m 232\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 233\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mret\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 234\u001b[0;31m \u001b[0mret\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconversion_func\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mas_ref\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mas_ref\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 235\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 236\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mret\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0mNotImplemented\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/constant_tensor_conversion.py\u001b[0m in \u001b[0;36m_constant_tensor_conversion_function\u001b[0;34m(v, dtype, name, as_ref)\u001b[0m\n\u001b[1;32m 27\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 28\u001b[0m \u001b[0m_\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mas_ref\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 29\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mconstant_op\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconstant\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mv\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 30\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 31\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/ops/weak_tensor_ops.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m 140\u001b[0m \u001b[0;32mdef\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 141\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mis_auto_dtype_conversion_enabled\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 142\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0mop\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 143\u001b[0m \u001b[0mbound_arguments\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0msignature\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mbind\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 144\u001b[0m \u001b[0mbound_arguments\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_defaults\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/constant_op.py\u001b[0m in \u001b[0;36mconstant\u001b[0;34m(value, dtype, shape, name)\u001b[0m\n\u001b[1;32m 274\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mcalled\u001b[0m \u001b[0mon\u001b[0m \u001b[0ma\u001b[0m \u001b[0msymbolic\u001b[0m \u001b[0mtensor\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 275\u001b[0m \"\"\"\n\u001b[0;32m--> 276\u001b[0;31m return _constant_impl(value, dtype, shape, name, verify_shape=False,\n\u001b[0m\u001b[1;32m 277\u001b[0m allow_broadcast=True)\n\u001b[1;32m 278\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/constant_op.py\u001b[0m in \u001b[0;36m_constant_impl\u001b[0;34m(value, dtype, shape, name, verify_shape, allow_broadcast)\u001b[0m\n\u001b[1;32m 287\u001b[0m \u001b[0;32mwith\u001b[0m \u001b[0mtrace\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mTrace\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"tf.constant\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 288\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0m_constant_eager_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mctx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshape\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverify_shape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 289\u001b[0;31m \u001b[0;32mreturn\u001b[0m \u001b[0m_constant_eager_impl\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mctx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mshape\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mverify_shape\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 290\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 291\u001b[0m const_tensor = ops._create_graph_constant( # pylint: disable=protected-access\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/constant_op.py\u001b[0m in \u001b[0;36m_constant_eager_impl\u001b[0;34m(ctx, value, dtype, shape, verify_shape)\u001b[0m\n\u001b[1;32m 299\u001b[0m ) -> ops._EagerTensorBase:\n\u001b[1;32m 300\u001b[0m \u001b[0;34m\"\"\"Creates a constant on the current device.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 301\u001b[0;31m \u001b[0mt\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconvert_to_eager_tensor\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mctx\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 302\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mshape\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 303\u001b[0m \u001b[0;32mreturn\u001b[0m \u001b[0mt\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;32m/usr/local/lib/python3.10/dist-packages/tensorflow/python/framework/constant_op.py\u001b[0m in \u001b[0;36mconvert_to_eager_tensor\u001b[0;34m(value, ctx, dtype)\u001b[0m\n\u001b[1;32m 94\u001b[0m \u001b[0;31m# memory with the input array. Without this copy, users will be able to\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 95\u001b[0m \u001b[0;31m# modify the EagerTensor after its creation by changing the input array.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 96\u001b[0;31m \u001b[0mvalue\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcopy\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 97\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mvalue\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mops\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mEagerTensor\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 98\u001b[0m \u001b[0;32mif\u001b[0m \u001b[0mdtype\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m \u001b[0;32mand\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdtype\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mKeyboardInterrupt\u001b[0m: "
]
}
],
"source": [
"import os\n",
"import numpy as np\n",
"import pandas as pd\n",
"import json\n",
"import matplotlib.pyplot as plt\n",
"from tensorflow.keras.models import Model\n",
"from tensorflow.keras.layers import Input, Dense, Conv2D, MaxPooling2D, Flatten, BatchNormalization, Add, ReLU, GlobalAveragePooling2D\n",
"from tensorflow.keras.utils import to_categorical\n",
"from tensorflow.keras.optimizers import Adam\n",
"from tensorflow.keras.callbacks import EarlyStopping\n",
"import pickle\n",
"\n",
"# Paths and constants\n",
"dataset_path = '/content/EuroSAT_dataset/EuroSAT'\n",
"\n",
"def load_label_map(dataset_path):\n",
" \"\"\"Load label map from JSON and return mappings.\"\"\"\n",
" with open(os.path.join(dataset_path, 'label_map.json'), 'r') as f:\n",
" label_map = json.load(f)\n",
" label_map_inv = {v: k for k, v in label_map.items()}\n",
" return label_map, label_map_inv\n",
"\n",
"def load_csv_data(dataset_path):\n",
" \"\"\"Load train, test, and validation CSV files.\"\"\"\n",
" train_df = pd.read_csv(os.path.join(dataset_path, 'train.csv'))\n",
" test_df = pd.read_csv(os.path.join(dataset_path, 'test.csv'))\n",
" val_df = pd.read_csv(os.path.join(dataset_path, 'validation.csv'))\n",
" return train_df, test_df, val_df\n",
"\n",
"def load_images_and_labels(df, dataset_path, label_map_inv, image_col='Filename', label_col='Label'):\n",
" \"\"\"Load images and labels from a DataFrame.\"\"\"\n",
" images = []\n",
" labels = []\n",
" for _, row in df.iterrows():\n",
" image_path = os.path.join(dataset_path, row[image_col])\n",
" image = plt.imread(image_path)\n",
" images.append(image)\n",
" labels.append(label_map_inv[row[label_col]]) # Convert integer label to class name\n",
" return np.array(images), np.array(labels)\n",
"\n",
"def preprocess_data(images, labels, label_map):\n",
" \"\"\"Normalize images and one-hot encode labels.\"\"\"\n",
" images = images / 255.0 # Scale pixel values to [0, 1]\n",
" labels_encoded = np.array([label_map[label] for label in labels]) # Convert labels to integers\n",
" labels_one_hot = to_categorical(labels_encoded) # One-hot encode labels\n",
" return images, labels_one_hot\n",
"\n",
"def residual_block(x, filters, stride=1):\n",
" \"\"\"Define a residual block.\"\"\"\n",
" shortcut = x\n",
" x = Conv2D(filters, (3, 3), strides=stride, padding='same')(x)\n",
" x = BatchNormalization()(x)\n",
" x = ReLU()(x)\n",
" x = Conv2D(filters, (3, 3), strides=1, padding='same')(x)\n",
" x = BatchNormalization()(x)\n",
"\n",
" if stride != 1 or shortcut.shape[-1] != filters:\n",
" shortcut = Conv2D(filters, (1, 1), strides=stride, padding='same')(shortcut)\n",
" shortcut = BatchNormalization()(shortcut)\n",
"\n",
" x = Add()([x, shortcut])\n",
" x = ReLU()(x)\n",
" return x\n",
"\n",
"def build_resnet(input_shape, num_classes):\n",
" \"\"\"Build and return a ResNet-like model.\"\"\"\n",
" inputs = Input(shape=input_shape)\n",
"\n",
" # Initial Conv layer\n",
" x = Conv2D(64, (7, 7), strides=2, padding='same')(inputs)\n",
" x = BatchNormalization()(x)\n",
" x = ReLU()(x)\n",
" x = MaxPooling2D((3, 3), strides=2, padding='same')(x)\n",
"\n",
" # Residual blocks\n",
" x = residual_block(x, 64, stride=1)\n",
" x = residual_block(x, 128, stride=2)\n",
" x = residual_block(x, 256, stride=2)\n",
" x = residual_block(x, 512, stride=2)\n",
"\n",
" # Global Average Pooling and Dense layers\n",
" x = GlobalAveragePooling2D()(x)\n",
" outputs = Dense(num_classes, activation='softmax')(x)\n",
"\n",
" model = Model(inputs, outputs)\n",
" return model\n",
"\n",
"def plot_training_history(history):\n",
" \"\"\"Plot training and validation accuracy and loss.\"\"\"\n",
" plt.figure(figsize=(12, 4))\n",
"\n",
" # Accuracy plot\n",
" plt.subplot(1, 2, 1)\n",
" plt.plot(history.history['accuracy'])\n",
" plt.plot(history.history['val_accuracy'])\n",
" plt.title('Model Accuracy')\n",
" plt.ylabel('Accuracy')\n",
" plt.xlabel('Epoch')\n",
" plt.legend(['Train', 'Validation'], loc='upper left')\n",
"\n",
" # Loss plot\n",
" plt.subplot(1, 2, 2)\n",
" plt.plot(history.history['loss'])\n",
" plt.plot(history.history['val_loss'])\n",
" plt.title('Model Loss')\n",
" plt.ylabel('Loss')\n",
" plt.xlabel('Epoch')\n",
" plt.legend(['Train', 'Validation'], loc='upper left')\n",
"\n",
" plt.show()\n",
"\n",
"def summarize_history(history):\n",
" \"\"\"Print a summary table of training and validation performance.\"\"\"\n",
" print(f\"{'Metric':<15}{'Train':<15}{'Validation':<15}\")\n",
" for key in history.history:\n",
" if 'val' not in key:\n",
" val_key = f\"val_{key}\"\n",
" print(f\"{key:<15}{history.history[key][-1]:<15.4f}{history.history[val_key][-1]:<15.4f}\")\n",
"\n",
"# Main flow\n",
"if __name__ == '__main__':\n",
" # Load label map and CSV data\n",
" label_map, label_map_inv = load_label_map(dataset_path)\n",
" train_df, test_df, val_df = load_csv_data(dataset_path)\n",
"\n",
" # Load images and labels for train, test, and validation sets\n",
" X_train, y_train = load_images_and_labels(train_df, dataset_path, label_map_inv)\n",
" X_test, y_test = load_images_and_labels(test_df, dataset_path, label_map_inv)\n",
" X_val, y_val = load_images_and_labels(val_df, dataset_path, label_map_inv)\n",
"\n",
" # Preprocess data (normalize images and one-hot encode labels)\n",
" X_train, y_train_one_hot = preprocess_data(X_train, y_train, label_map)\n",
" X_test, y_test_one_hot = preprocess_data(X_test, y_test, label_map)\n",
" X_val, y_val_one_hot = preprocess_data(X_val, y_val, label_map)\n",
"\n",
" # Build ResNet model\n",
" input_shape = X_train.shape[1:] # Image shape (height, width, channels)\n",
" num_classes = len(label_map)\n",
" model = build_resnet(input_shape, num_classes)\n",
"\n",
" # Compile the model\n",
" model.compile(optimizer=Adam(learning_rate=0.001), loss='categorical_crossentropy', metrics=['accuracy'])\n",
"\n",
" # Print model summary\n",
" model.summary()\n",
"\n",
" # Define early stopping callback\n",
" early_stopping = EarlyStopping(monitor='val_loss', patience=3, restore_best_weights=True)\n",
"\n",
" # Train the model with early stopping\n",
" history = model.fit(X_train, y_train_one_hot, epochs=10, batch_size=32, validation_data=(X_val, y_val_one_hot), callbacks=[early_stopping])\n",
"\n",
" # Evaluate the model\n",
" test_loss, test_accuracy = model.evaluate(X_test, y_test_one_hot)\n",
" print(f'Test Accuracy: {test_accuracy:.4f}')\n",
"\n",
" # Plot training history\n",
" plot_training_history(history)\n",
"\n",
" # Summarize training history\n",
" summarize_history(history)\n",
"\n",
" additional_details = {\n",
" 'X_test': X_test, # Add entire test dataset\n",
" 'y_test_one_hot': y_test_one_hot, # Add test labels (one-hot encoded)\n",
" 'label_map': label_map # Label map used for decoding\n",
" }\n",
"\n",
" # Update the history data with the new details\n",
" history.history.update(additional_details)\n",
"\n",
" # Save the model and training history\n",
" model.save('resnet_image_classifier.h5')\n",
" with open('history_resnet.pkl', 'wb') as f:\n",
" pickle.dump(history.history, f)"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "CeBrzsP-ezxd"
},
"source": [
"**Deep Learning Algorithm - CNN**"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "k2gA54WN4Rju",
"outputId": "d7e4aa73-fdd7-4723-d611-bc0b3ae2c304"
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"/usr/local/lib/python3.10/dist-packages/keras/src/layers/convolutional/base_conv.py:107: 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__(activity_regularizer=activity_regularizer, **kwargs)\n"
]
},
{
"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",
"│ conv2d_15 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m62\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m896\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_4 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m31\u001b[0m, \u001b[38;5;34m31\u001b[0m, \u001b[38;5;34m32\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_16 (\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;34m18,496\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_5 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m14\u001b[0m, \u001b[38;5;34m64\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_17 (\u001b[38;5;33mConv2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m12\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m73,856\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_6 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m6\u001b[0m, \u001b[38;5;34m128\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;34m4608\u001b[0m) │ \u001b[38;5;34m0\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense_3 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m) │ \u001b[38;5;34m589,952\u001b[0m │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense_4 (\u001b[38;5;33mDense\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m) │ \u001b[38;5;34m1,290\u001b[0m │\n",
"└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
],
"text/html": [
"┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
"┃ Layer (type) ┃ Output Shape ┃ Param # ┃\n",
"┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
"│ conv2d_15 (Conv2D) │ (None, 62, 62, 32) │ 896 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_4 (MaxPooling2D) │ (None, 31, 31, 32) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_16 (Conv2D) │ (None, 29, 29, 64) │ 18,496 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_5 (MaxPooling2D) │ (None, 14, 14, 64) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ conv2d_17 (Conv2D) │ (None, 12, 12, 128) │ 73,856 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ max_pooling2d_6 (MaxPooling2D) │ (None, 6, 6, 128) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ flatten_1 (Flatten) │ (None, 4608) │ 0 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense_3 (Dense) │ (None, 128) │ 589,952 │\n",
"├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
"│ dense_4 (Dense) │ (None, 10) │ 1,290 │\n",
"└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Total params: \u001b[0m\u001b[38;5;34m684,490\u001b[0m (2.61 MB)\n"
],
"text/html": [
" Total params: 684,490 (2.61 MB)\n",
"\n"
]
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m684,490\u001b[0m (2.61 MB)\n"
],
"text/html": [
" Trainable params: 684,490 (2.61 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": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Epoch 1/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 237ms/step - accuracy: 0.4012 - loss: 1.5295 - val_accuracy: 0.6624 - val_loss: 0.9417\n",
"Epoch 2/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 231ms/step - accuracy: 0.6863 - loss: 0.8707 - val_accuracy: 0.7328 - val_loss: 0.7435\n",
"Epoch 3/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 234ms/step - accuracy: 0.7501 - loss: 0.6883 - val_accuracy: 0.7391 - val_loss: 0.7452\n",
"Epoch 4/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 232ms/step - accuracy: 0.7771 - loss: 0.6150 - val_accuracy: 0.8254 - val_loss: 0.4944\n",
"Epoch 5/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m137s\u001b[0m 231ms/step - accuracy: 0.8028 - loss: 0.5390 - val_accuracy: 0.7587 - val_loss: 0.6423\n",
"Epoch 6/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 231ms/step - accuracy: 0.8395 - loss: 0.4480 - val_accuracy: 0.8141 - val_loss: 0.5024\n",
"Epoch 7/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m136s\u001b[0m 230ms/step - accuracy: 0.8544 - loss: 0.4071 - val_accuracy: 0.8143 - val_loss: 0.5170\n",
"Epoch 8/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m135s\u001b[0m 229ms/step - accuracy: 0.8652 - loss: 0.3714 - val_accuracy: 0.8506 - val_loss: 0.4313\n",
"Epoch 9/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m146s\u001b[0m 235ms/step - accuracy: 0.8894 - loss: 0.3115 - val_accuracy: 0.8300 - val_loss: 0.4798\n",
"Epoch 10/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 233ms/step - accuracy: 0.8935 - loss: 0.2945 - val_accuracy: 0.8511 - val_loss: 0.4502\n",
"Epoch 11/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m143s\u001b[0m 235ms/step - accuracy: 0.9113 - loss: 0.2479 - val_accuracy: 0.8381 - val_loss: 0.5168\n",
"Epoch 12/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 232ms/step - accuracy: 0.9323 - loss: 0.1996 - val_accuracy: 0.8617 - val_loss: 0.4189\n",
"Epoch 13/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 231ms/step - accuracy: 0.9400 - loss: 0.1621 - val_accuracy: 0.8622 - val_loss: 0.4555\n",
"Epoch 14/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m140s\u001b[0m 229ms/step - accuracy: 0.9488 - loss: 0.1474 - val_accuracy: 0.8628 - val_loss: 0.4781\n",
"Epoch 15/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m144s\u001b[0m 232ms/step - accuracy: 0.9517 - loss: 0.1340 - val_accuracy: 0.8602 - val_loss: 0.5021\n",
"Epoch 16/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m141s\u001b[0m 230ms/step - accuracy: 0.9604 - loss: 0.1168 - val_accuracy: 0.8693 - val_loss: 0.4885\n",
"Epoch 17/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 234ms/step - accuracy: 0.9672 - loss: 0.0953 - val_accuracy: 0.8504 - val_loss: 0.5708\n",
"Epoch 18/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 228ms/step - accuracy: 0.9709 - loss: 0.0846 - val_accuracy: 0.8233 - val_loss: 0.6797\n",
"Epoch 19/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m139s\u001b[0m 236ms/step - accuracy: 0.9631 - loss: 0.1052 - val_accuracy: 0.7789 - val_loss: 1.0682\n",
"Epoch 20/20\n",
"\u001b[1m591/591\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 229ms/step - accuracy: 0.9663 - loss: 0.1034 - val_accuracy: 0.8615 - val_loss: 0.5991\n",
"\u001b[1m85/85\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m7s\u001b[0m 79ms/step - accuracy: 0.8690 - loss: 0.5764\n",
"Test Accuracy: 0.8685\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAA+kAAAGJCAYAAAD2VnIMAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAAC21klEQVR4nOzdd3gUVRfA4d/upocUQjoEQi+hd1ApAtKkKB0VpKkIKqJ+ig2wYEURsSsCSkdAlF4FpIOU0EsIEFIIgfS6O98fNwkEEkjZZFPO+zz77OzslLOBZPbMvfdcnaZpGkIIIYQQQgghhLA4vaUDEEIIIYQQQgghhCJJuhBCCCGEEEIIUUxIki6EEEIIIYQQQhQTkqQLIYQQQgghhBDFhCTpQgghhBBCCCFEMSFJuhBCCCGEEEIIUUxIki6EEEIIIYQQQhQTkqQLIYQQQgghhBDFhCTpQgghhBBCCCFEMSFJuhAllE6nY8qUKXne7+LFi+h0OubMmWP2mIQQQghRfMl3ByFKBknShSiAOXPmoNPp0Ol07Ny58673NU3Dz88PnU7Ho48+aoEIzWPNmjXodDp8fX0xmUyWDkcIIYQosUrzd4dt27ah0+lYtmyZpUMRokSTJF0IM7Czs2PBggV3rf/nn3+4cuUKtra2FojKfObPn4+/vz+hoaFs2bLF0uEIIYQQJV5p/+4ghMg/SdKFMIMePXqwdOlS0tLSsqxfsGABzZo1w9vb20KRFVx8fDx//vknEydOpEmTJsyfP9/SIeUoPj7e0iEIIYQQuVKavzsIIQpGknQhzGDIkCFcv36djRs3Zq5LSUlh2bJlDB06NNt94uPjeeWVV/Dz88PW1pbatWvz+eefo2lalu2Sk5N5+eWX8fDwwMnJid69e3PlypVsjxkSEsLIkSPx8vLC1taWgIAAZs+eXaDPtmLFChITExkwYACDBw9m+fLlJCUl3bVdUlISU6ZMoVatWtjZ2eHj48Pjjz/O+fPnM7cxmUx89dVXNGjQADs7Ozw8POjWrRsHDhwA7j3m7c5xdFOmTEGn03HixAmGDh1K+fLlefDBBwE4evQoTz/9NNWqVcPOzg5vb29GjhzJ9evXs/2ZjRo1Cl9fX2xtbalatSpjx44lJSWFCxcuoNPp+PLLL+/ab9euXeh0OhYuXJjXH6kQQghRqr873M+FCxcYMGAAbm5uODg40Lp1a1avXn3Xdl9//TUBAQE4ODhQvnx5mjdvnqX3QWxsLBMmTMDf3x9bW1s8PT3p0qULhw4dKtT4hShsVpYOQIjSwN/fnzZt2rBw4UK6d+8OwNq1a4mOjmbw4MHMnDkzy/aaptG7d2+2bt3KqFGjaNy4MevXr+e1114jJCQkS1I4evRofv/9d4YOHUrbtm3ZsmULPXv2vCuG8PBwWrdujU6nY/z48Xh4eLB27VpGjRpFTEwMEyZMyNdnmz9/Ph07dsTb25vBgwfzxhtv8NdffzFgwIDMbYxGI48++iibN29m8ODBvPTSS8TGxrJx40YCAwOpXr06AKNGjWLOnDl0796d0aNHk5aWxo4dO9izZw/NmzfPV3wDBgygZs2aTJs2LfNLysaNG7lw4QIjRozA29ub48eP8+OPP3L8+HH27NmDTqcD4OrVq7Rs2ZKbN2/yzDPPUKdOHUJCQli2bBkJCQlUq1aNBx54gPnz5/Pyyy/f9XNxcnKiT58++YpbCCFE2VaavzvcS3h4OG3btiUhIYEXX3yRChUqMHfuXHr37s2yZct47LHHAPjpp5948cUX6d+/Py+99BJJSUkcPXqUvXv3Zt7EeO6551i2bBnjx4+nXr16XL9+nZ07d3Ly5EmaNm1q9tiFKDKaECLffv31Vw3Q9u/fr82aNUtzcnLSEhISNE3TtAEDBmgdO3bUNE3TqlSpovXs2TNzv5UrV2qA9sEHH2Q5Xv/+/TWdTqedO3dO0zRNO3z4sAZozz//fJbthg4dqgHa5MmTM9eNGjVK8/Hx0SIjI7NsO3jwYM3FxSUzrqCgIA3Qfv311/t+vvDwcM3Kykr76aefMte1bdtW69OnT5btZs+erQHaF198cdcxTCaTpmmatmXLFg3QXnzxxRy3uVdsd37eyZMna4A2ZMiQu7bN+Ky3W7hwoQZo27dvz1w3bNgwTa/Xa/v3788xph9++EEDtJMnT2a+l5KSorm7u2vDhw+/az8hhBDiXkrzd4etW7dqgLZ06dIct5kwYYIGaDt27MhcFxsbq1WtWlXz9/fXjEajpmma1qdPHy0gIOCe53NxcdHGjRt3z22EKImku7sQZjJw4EASExP5+++/iY2N5e+//86xu9qaNWswGAy8+OKLWda/8soraJrG2rVrM7cD7truzjvbmqbxxx9/0KtXLzRNIzIyMvPRtWtXoqOj89X1a9GiRej1evr165e5bsiQIaxdu5YbN25krvvjjz9wd3fnhRdeuOsYGa3Wf/zxBzqdjsmTJ+e4TX4899xzd62zt7fPXE5KSiIyMpLWrVsDZP4cTCYTK1eupFevXtm24mfENHDgQOzs7LKMxV+/fj2RkZE8+eST+Y5bCCGEKI3fHe5nzZo1tGzZMnOIGkC5cuV45plnuHjxIidOnADA1dWVK1eusH///hyP5erqyt69e7l69arZ4xTCkiRJF8JMPDw86Ny5MwsWLGD58uUYjUb69++f7bbBwcH4+vri5OSUZX3dunUz38941uv1md3FM9SuXTvL62vXrnHz5k1+/PFHPDw8sjxGjBgBQERERJ4/0++//07Lli25fv06586d49y5czRp0oSUlBSWLl2aud358+epXbs2VlY5j6A5f/48vr6+uLm55TmOe6latepd66KionjppZfw8vLC3t4eDw+PzO2io6MB9TOLiYmhfv369zy+q6srvXr1yjIGbv78+VSsWJGHH37YjJ9ECCFEWVMavzvcT3Bw8F2xZPc5Xn/9dcqVK0fLli2pWbMm48aN499//82yz6effkpgYCB+fn60bNmSKVOmcOHCBbPHLERRkzHpQpjR0KFDGTNmDGFhYXTv3h1XV9ciOW/G3OVPPvkkw4cPz3abhg0b5umYZ8+ezbx7XbNmzbvenz9/Ps8880weI723nFrUjUZjjvvc3mqeYeDAgezatYvXXnuNxo0bU65cOUwmE926dcvXPO/Dhg1j6dKl7Nq1iwYNGrBq1Sqef/559Hq5zymEEKJgStN3B3OqW7cup0+f5u+//2bdunX88ccffPvtt7z77rtMnToVUNf7hx56iBUrVrBhwwY+++wzPvnkE5YvX545zl+IkkiSdCHM6LHHHuPZZ59lz549LF68OMftqlSpwqZNm4iNjc1yR/zUqVOZ72c8m0ymzJbqDKdPn85yvIzqrUajkc6dO5vls8yfPx9ra2t+++03DAZDlvd27tzJzJkzuXTpEpUrV6Z69ers3buX1NRUrK2tsz1e9erVWb9+PVFRUTm2ppcvXx6AmzdvZlmfcVc9N27cuMHmzZuZOnUq7777bub6s2fPZtnOw8MDZ2dnAgMD73vMbt264eHhwfz582nVqhUJCQk89dRTuY5JCCGEyElp+u6QG1WqVLkrFrj7cwA4OjoyaNAgBg0aREpKCo8//jgffvghkyZNws7ODgAfHx+ef/55nn/+eSIiImjatCkffvihJOmiRJNmICHMqFy5cnz33XdMmTKFXr165bhdjx49MBqNzJo1K8v6L7/8Ep1Ol3lhyXi+s8LrjBkzsrw2GAz069ePP/74I9uk89q1a3n+LPPnz+ehhx5i0KBB9O/fP8vjtddeA8icfqxfv35ERkbe9XmAzIrr/fr1Q9O0zLvf2W3j7OyMu7s727dvz/L+t99+m+u4M24oaHdMR3Pnz0yv19O3b1/++uuvzCngsosJwMrKiiFDhrBkyRLmzJlDgwYNLNq6IIQQovQoTd8dcqNHjx7s27eP3bt3Z66Lj4/nxx9/xN/fn3r16gHcNW2qjY0N9erVQ9M0UlNTMRqNmUPYMnh6euLr60tycnKhxC5EUZGWdCHMLKcuY7fr1asXHTt25K233uLixYs0atSIDRs28OeffzJhwoTMcWSNGzdmyJAhfPvtt0RHR9O2bVs2b97MuXPn7jrmxx9/zNatW2nVqhVjxoyhXr16REVFcejQITZt2kRUVFSuP8PevXs5d+4c48ePz/b9ihUr0rRpU+bPn8/rr7/OsGHDmDdvHhMnTmTfvn089NBDxMfHs2nTJp5//nn69OlDx44deeqpp5g5cyZnz57N7Hq+Y8cOOnbsmHmu0aNH8/HHHzN69GiaN2/O9u3bOXPmTK5jd3Z2pl27dnz66aekpqZSsWJFNmzYQFBQ0F3bTps2jQ0bNtC+fXueeeYZ6tatS2hoKEuXLmXnzp1ZuhwOGzaMmTNnsnXrVj755JNcxyOEEELcT2n47nC7P/74I7Nl/M7P+cYbb2ROO/fiiy/i5ubG3LlzCQoK4o8//sgcSvbII4/g7e3NAw88gJeXFydPnmTWrFn07NkTJycnbt68SaVKlejfvz+NGjWiXLlybNq0if379zN9+vR8xS1EsWGZovJClA63T6NyL3dOo6JparqRl19+WfP19dWsra21mjVrap999lnm1F8ZEhMTtRdffFGrUKGC5ujoqPXq1Uu7fPnyXdOoaJqaMm3cuHGan5+fZm1trXl7e2udOnXSfvzxx8xtcjONygsvvKAB2vnz53PcZsqUKRqgHTlyRNM0Ne3ZW2+9pVWtWjXz3P37989yjLS0NO2zzz7T6tSpo9nY2GgeHh5a9+7dtYMHD2Zuk5CQoI0aNUpzcXHRnJyctIEDB2oRERE5TsF27dq1u2K7cuWK9thjj2murq6ai4uLNmDAAO3q1avZ/syCg4O1YcOGaR4eHpqtra1WrVo1bdy4cVpycvJdxw0ICND0er125cqVHH8uQgghxL2U1u8OmnZrCracHhnTrp0/f17r37+/5urqqtnZ2WktW7bU/v777yzH+uGHH7R27dppFSpU0GxtbbXq1atrr732mhYdHa1pmqYlJydrr732mtaoUSPNyclJc3R01Bo1aqR9++2394xRiJJAp2l39AkVQgiRrSZNmuDm5sbmzZstHYoQQgghhCilZEy6EELkwoEDBzh8+DDDhg2zdChCCCGEEKIUk5Z0IYS4h8DAQA4ePMj06dOJjIzkwoULmRVlhRBCCCGEMDdpSRdCiHtYtmwZI0aMIDU1lYULF0qCLoQQQgghCpW0pAshhBBCCCGEEMWEtKQLIYQQQgghhBDFhCTpQgghhBBCCCFEMWFl6QCKmslk4urVqzg5OaHT6SwdjhBCCIGmacTGxuLr64teL/fPzUGu90IIIYqTvFzry1ySfvXqVfz8/CwdhhBCCHGXy5cvU6lSJUuHUSrI9V4IIURxlJtrfZlL0p2cnAD1w3F2drZwNEIIIQTExMTg5+eXeY0SBSfXeyGEEMVJXq71ZS5Jz+jy5uzsLBdtIYQQxYp0yzYfud4LIYQojnJzrZeBb0IIIYQQQgghRDEhSboQQgghhBBCCFFMSJIuhBBCCCGEEEIUE2VuTHpuaJpGWloaRqPR0qEIMzAYDFhZWclYTyGEEJnkWl/6WFtbYzAYLB2GEEIUmCTpd0hJSSE0NJSEhARLhyLMyMHBAR8fH2xsbCwdihBCCAuTa33ppNPpqFSpEuXKlbN0KEIIUSCSpN/GZDIRFBSEwWDA19cXGxsbaX0t4TRNIyUlhWvXrhEUFETNmjXR62WUhxBClFVyrS+dNE3j2rVrXLlyhZo1a0qLuhCiRJMk/TYpKSmYTCb8/PxwcHCwdDjCTOzt7bG2tiY4OJiUlBTs7OwsHZIQQggLkWt96eXh4cHFixdJTU2VJF0IUaJJk2I2pKW19JF/UyGEELeT60LpIz0ihBClhVyhhBBCCCGEEEKIYkK6uwshhBD3YDRpxKekEZ+sHnHJxsxlW2sD7Wt5WDpEUYjSjCYSUoygA2c7a0uHI4QQogyQJF3kyN/fnwkTJjBhwgRLhyKEEHmWZjRxMzGVmwkp3ExI5WZCKnHJacSlJ9jxKcbbEu+MJNyollPUcnxyGompOU/RVcfbSZL0Ui4uOY1LUQk42FiVyiRdrvVCCFH8SJJeCtxvDNbkyZOZMmVKno+7f/9+HB0d8xmVEEKYh8mkEZuUxo2EFG4mpnIjIYXoBPV8IyGV6PTnGwkpRKe/fzM+ldjkNLPGYaXX4WhrRTlbKxxsDDjaWlHNXf5Glnb21qoAWVKqEU3TLDbuWa71QghRdkiSXgqEhoZmLi9evJh3332X06dPZ667fb5QTdMwGo1YWd3/n97DQ1qHhBC5o2kasclpJKUYSUxNf6QvJ6UaSUwxZa6/c5uk7LZPNZKQbMxMvE1a/mNztrOivKMNrvbWlLOzwtFGJdqOGY/0hPvWOsOtZRv12tHWClsrvRSmKoNsrPQYdDqMmkZymgk7a8tUDZdrvRBClB2SpN+Hpmn37OpYmOytDbn6Qujt7Z257OLigk6ny1y3bds2OnbsyJo1a3j77bc5duwYGzZswM/Pj4kTJ7Jnzx7i4+OpW7cuH330EZ07d8481p1d4HQ6HT/99BOrV69m/fr1VKxYkenTp9O7d2/zfnAhRIkQnZjKzrORbD0dwbbT14iMSy7U8znYGCjvYIOLvTXlHa1xdVCJd3kHG1wd1Ovy6c+uDtaZ2xr0kliLe7vftV7TQVKKketxKZR3NG+Xd7nWCyGEuJMk6feRmGqk3rvrLXLuE+91xcHGPP9Eb7zxBp9//jnVqlWjfPnyXL58mR49evDhhx9ia2vLvHnz6NWrF6dPn6Zy5co5Hmfq1Kl8+umnfPbZZ3z99dc88cQTBAcH4+bmZpY4hRDFl6ZpnAqLZdvpa2w9HcHB4BsY72ji1uvAwcYKO2sDdtZ67K0N2NsYsLM2qOU7X9uobezS12dsY2djwMHakJl4uzhYY2sl8x6LwiHX+qzkWi+EEJYlSXoZ8d5779GlS5fM125ubjRq1Cjz9fvvv8+KFStYtWoV48ePz/E4Tz/9NEOGDAFg2rRpzJw5k3379tGtW7fCC14IYTFxyWn8ey6Sbacj2HrqGmExSVner+FZjo61PehY25OmVcpLl3AhLEiu9UIIUTpIkn4f9tYGTrzX1WLnNpfmzZtneR0XF8eUKVNYvXo1oaGhpKWlkZiYyKVLl+55nIYNG2YuOzo64uzsTEREhNniFEJYlqZpnL8Wr5Ly0xHsC4oi1XirtdzOWs8D1d3pUMeTDrU88HNzsGC0QpjH/a71SalGzkXEodfpqOvjZNYbUXKtF0IIcSdJ0u9Dp9OZrRuaJd1ZufXVV19l48aNfP7559SoUQN7e3v69+9PSkrKPY9jbZ11LJ5Op8NkMpk9XiFE0UlMMbL7QiRbT6lu7FduJGZ537+CAx1qe9KxjietqrpZrHCWEIXlftd6e2sDDjZWmDQNg15fbH8H5FovhBClQ8nPPkW+/Pvvvzz99NM89thjgLrbfvHiRcsGJYQoVCaTRlxKGjGJas7wAxej2Hr6GrsvXCcl7dYXcBsrPa2rVaBjbQ861PakqkwzJso4nU6HnbWBhJQ0klKNxTZJv5Nc64UQomSSJL2MqlmzJsuXL6dXr17odDreeecduUsuRDGnaRoJKUaiE1OJSUolJlEl3Go5lejEtMzlzPeT1HJ0gpo3XMthKrOKrvZ0rKPGlrepXqFU9CASwpzsbVSSnphixLWEjPKQa70QQpRM8i2sjPriiy8YOXIkbdu2xd3dnddff52YmBhLhyWESGcyaZyNiGPPhevsuXCdg8E3uB6fclc19fywtdLjZGdNTc9ymYl5Dc9yUvBNiHvIGDueYKFpWfNDrvVCCFEy6TQtp3aV0ikmJgYXFxeio6NxdnbO8l5SUhJBQUFUrVoVOzs7C0UoCoP824ri7s6kfG9QFFHx2Y8btdLrcLG3xtneGmc7K/Vsb42znTXO9lY421nf/X76Oic7qxLTVbcsude1qaTbvn07n332GQcPHiQ0NJQVK1bQt2/fHLdfvnw53333HYcPHyY5OZmAgACmTJlC1655K+Ka0880v9eDxBQjZyNiMeh01PN1lptaxZBc64UQxVlervXSki6EEBZgMmmciYhlz/nr7LkQxd6g69xISM2yjb21geb+5WldrQItq7rhV94BF3tr7KxlmjNRcsTHx9OoUSNGjhzJ448/ft/tt2/fTpcuXZg2bRqurq78+uuv9OrVi71799KkSZMiiDh7tum/d0ZNI8VowtZKbnYJIYQoHJKkCyFEEchrUt66WgUaVHTBxkpvoYiFMI/u3bvTvXv3XG8/Y8aMLK+nTZvGn3/+yV9//XXPJD05OZnk5OTM1+bu1q3X6bC31pOQYiQxxShJuhBCiEIjSboQQhSC/CTlDSu5YG2QpFyI25lMJmJjY3Fzc7vndh999BFTp04t1FhUhXcjialGXAv1TEIIIcoySdKFEMIMktOMBIbEcOBiFPsv3uBgcNRdSbmDjYHm/m60ruaW2VIuSbkQ9/b5558TFxfHwIED77ndpEmTmDhxYubrmJgY/Pz8zBpLRvG4xJSSUzxOCCFEySNJuhBC5EN0QiqHLt1g/8UoDly8weErN7PMNQ6SlAtRUAsWLGDq1Kn8+eefeHp63nNbW1tbbG1tCzUeexuVpCelGtE0TWpDCCGEKBSSpAshxH1omsaVG4kcDL6VlJ8Oj71ruwqONjSrUp4W/m408y8vSbkQBbBo0SJGjx7N0qVL6dy5s6XDAVR3dx060kwaqUYNGytJ0oUQQpifJOlCCHEHo0njZGhMlqQ8LCbpru2quTvS3L88zau40dy/PFXdHaVlTQgzWLhwISNHjmTRokX07NnT0uFk0ut02FnrSUxV49KlsKMQQojCIEm6EKLMS0o1cij4BgfSk/L/Lt0kLjktyzZWeh31K7rQwr88zdKTcvdyhdu1VojSIC4ujnPnzmW+DgoK4vDhw7i5uVG5cmUmTZpESEgI8+bNA1QX9+HDh/PVV1/RqlUrwsLCALC3t8fFxcUin+F29tYGlaSnGHGxt7Z0OEIIIUohSdKFEGVSXHIaW09FsC4wjK2nI0i4oxCUk60VTauUz0zKG/u5Zo5HFULk3oEDB+jYsWPm64zibsOHD2fOnDmEhoZy6dKlzPd//PFH0tLSGDduHOPGjctcn7G9pdnbGCABElOleJwQQojCIUm6AKBDhw40btw4c35af39/JkyYwIQJE3LcR6fTsWLFCvr27Vugc5vrOELcz82EFDaeCGf98TC2n43MUujN29mOllXdaOFfnub+btTycsKgl67rQhRUhw4d0DQtx/fvTLy3bdtWuAEVkF1GhfcSmKTLtV4IIUoGSdJLgV69epGamsq6devuem/Hjh20a9eOI0eO0LBhw1wfc//+/Tg6OpozTKZMmcLKlSs5fPhwlvWhoaGUL1/erOcSIkNEbBIbjqvEfPf566SZbiULVd0d6Vbfm+71vWlQ0UXGkwsh7sve2oAOSDOaSDWaiqw4pFzrhRCi7JAkvRQYNWoU/fr148qVK1SqVCnLe7/++ivNmzfP00UbwMPDw5wh3pO3t3eRnUuUDSE3E1kXGMa6wFAOBN/g9ka8Ot5OdK/vQ7f63tTyKieJuRAiT/R6HbbWBpLSx6Vb2xdNki7XeiGEKDukLOn9aBqkxFvmcY/ugbd79NFH8fDwuKvLYFxcHEuXLqVv374MGTKEihUr4uDgQIMGDVi4cOE9j+nv75/ZHQ7g7NmztGvXDjs7O+rVq8fGjRvv2uf111+nVq1aODg4UK1aNd555x1SU1MB1Z1x6tSpHDlyBJ1Oh06ny4xXp9OxcuXKzOMcO3aMhx9+GHt7eypUqMAzzzxDXFxc5vtPP/00ffv25fPPP8fHx4cKFSowbty4zHOJsunCtTi+3XaO3rN28sDHW3j/7xPsv6gS9EZ+rrzRvQ7bXu3AugnteKlzTWp7O0mCLoRQ8nitdyAZXWoCiQkxcq2Xa70QQpidtKTfT2oCTPO1zLnfvAo29++GZmVlxbBhw5gzZw5vvfVWZuKxdOlSjEYjTz75JEuXLuX111/H2dmZ1atX89RTT1G9enVatmx53+ObTCYef/xxvLy82Lt3L9HR0dmOX3NycmLOnDn4+vpy7NgxxowZg5OTE//73/8YNGgQgYGBrFu3jk2bNgFkW6U3Pj6erl270qZNG/bv309ERASjR49m/PjxWb6YbN26FR8fH7Zu3cq5c+cYNGgQjRs3ZsyYMff9PKJ00DSNU2Gx6S3mYVnmLdfpoIW/G93re9M1wBtfV3sLRiqEKPbyeK2vlP4wC7nWy7VeCCHuIEl6KTFy5Eg+++wz/vnnHzp06ACo7m/9+vWjSpUqvPrqq5nbvvDCC6xfv54lS5bk6sK9adMmTp06xfr16/H1VV9ipk2bRvfu3bNs9/bbb2cu+/v78+qrr7Jo0SL+97//YW9vT7ly5bCysrpnl7cFCxaQlJTEvHnzMsfJzZo1i169evHJJ5/g5eUFQPny5Zk1axYGg4E6derQs2dPNm/eLBfuMuByVAKL91/m76NXuXg9IXO9lV5H2xrudAvwpks9LzycZHo0IUTpItd6udYLIcoGSdLvx9pB3eW21LlzqU6dOrRt25bZs2fToUMHzp07x44dO3jvvfcwGo1MmzaNJUuWEBISQkpKCsnJyTg45O74J0+exM/PL/OiDdCmTZu7tlu8eDEzZ87k/PnzxMXFkZaWhrOzc64/Q8a5GjVqlKWQzQMPPIDJZOL06dOZF+6AgAAMhlvTYfn4+HDs2LE8nUuUHEaTxrbTEfy+J5htZ65l9g61tdLTrpYH3QK86VzXCxcHmbNYCJEPebzWG00aJ0JjAFXnokDF4+RaD8i1XgghbidJ+v3odLnqhlYcjBo1ihdeeIFvvvmGX3/9lerVq9O+fXs++eQTvvrqK2bMmEGDBg1wdHRkwoQJpKSkmO3cu3fv5oknnmDq1Kl07doVFxcXFi1axPTp0812jttZW2dNxnQ6HSaTKYetRUkVEZvEkv2XWbjvMiE3EzPXP1TTnYHN/Xi4jieOtvJnTAhRQHm81hsAG3uN5DQjSTo7rG2K7gahXOvlWi+EKP3k220pMnDgQF566SUWLFjAvHnzGDt2LDqdjn///Zc+ffrw5JNPAmrc2ZkzZ6hXr16ujlu3bl0uX75MaGgoPj4+AOzZsyfLNrt27aJKlSq89dZbmeuCg4OzbGNjY4PReO95ZevWrcucOXOIj4/PvMP+77//otfrqV27dq7iFSWbpmnsPn+d+Xsvsf54WOaUaa4O1gxs7seQlpWp6l4ybpwJIUove2sDyWmqwruTXdEl6XKtF0KI0k+qu5ci5cqVY9CgQUyaNInQ0FCefvppAGrWrMnGjRvZtWsXJ0+e5NlnnyU8PDzXx+3cuTO1atVi+PDhHDlyhB07dmS5QGec49KlSyxatIjz588zc+ZMVqxYkWUbf39/goKCOHz4MJGRkSQnJ991rieeeAI7OzuGDx9OYGAgW7du5YUXXuCpp57K7P4mSqebCSn8vOMCnab/w9Cf97L6WChpJo1mVcrz5aBG7JnUiTd71JUEXQhRLNjbqK9Qian3TkjNTa71QghR+kmSXsqMGjWKGzdu0LVr18xxZW+//TZNmzala9eudOjQAW9vb/r27ZvrY+r1elasWEFiYiItW7Zk9OjRfPjhh1m26d27Ny+//DLjx4+ncePG7Nq1i3feeSfLNv369aNbt2507NgRDw+PbKeGcXBwYP369URFRdGiRQv69+9Pp06dmDVrVt5/GKLY0zSN/y7d4JUlR2g1bTMfrD7Jhch4HG0MPNm6Mmtfeog/xrblsSaVsLM23P+AQghRROzT/yYVdZIOcq0XQojSTqdpuZygs5SIiYnBxcWF6OjouwqdJCUlERQURNWqVbGzs7NQhKIwyL9t8RKfnMafh68yf28wx6/GZK6v6+PMk60r06dxRcrJWHNRhtzr2iTyJ6efqbmuB2kmEyfS/37V83HGqiDF44RZyLVeCFGc5eVaL9+ChRBF5lRYDPP3XGLFfyHEJacBYGOl59GGPjzZugpN/Fwz5/4VQojizEqvx8ZKT0qaiaRUI+UkSRdCCGEmkqQLIQpVUqqRdYFh/L4nmAPBNzLXV3V35IlWlenfrBKuDjYWjFAIIfLH3tpASpqJxFQj5YqweJwQQojSTZJ0IUShOBcRx8J9l/jj0BVuJqQCYKXX8UiAF0+0qkLb6hWk1VwIUaLZ2xiITkwlMUWmBRNCCGE+kqQLIcwmo9V8wb5L7AuKylzv62LH4JaVGdzCD09nGScohCgdLFk8TgghROklSXo2ylgtvTJB/k0L17mIOBalt5rfSG811+vg4TpePNGqMu1qeWDQS6u5EKL4MMd1ISNJT04zYjSZMOhlXLolybVeCFFaSJJ+G2trNZ4sISEBe3t7C0cjzCkhIQG49W8sCi4p1cj642Es2HuJvXe0mg9qUZmBLSrh4yK/R0KI4sWc13orgx4bg54Uo4nEVBPlbCVJt6SUlBQADAaZslMIUbJJkn4bg8GAq6srERERgJrHU8bMlmyappGQkEBERASurq5y4TaD89fiWLg3+1bzoa38aF/LU1rNhRDFlrmv9dakkZyWRkxcAlaaFMG0FJPJxLVr13BwcMDKSr7eCiFKNvkrdgdvb2+AzIu3KB1cXV0z/21F3iWnpY81l1ZzIUQpYM5rfUxSKjGJacTZGIh2lCTdkvR6PZUrV5YGFiFEiWfxJP2bb77hs88+IywsjEaNGvH111/TsmXLbLdNTU3lo48+Yu7cuYSEhFC7dm0++eQTunXrZrZ4dDodPj4+eHp6kpqaarbjCsuxtraWFvR8On9NjTVfdvDOVnNPhraqLK3mQogSyZzX+j0XIpmyJpAqbg7MHpH99xdRNGxsbNBLXQAhRClg0SR98eLFTJw4ke+//55WrVoxY8YMunbtyunTp/H09Lxr+7fffpvff/+dn376iTp16rB+/Xoee+wxdu3aRZMmTcwam8FgkMROlEkJKWlsPBHOwn2X2HPhVqu5j4sdg1r4MaiFn7SaCyFKBXNc6+v5uRMSayQ0LhaT3goHG4u3fwghhCjhdJoFS2G2atWKFi1aMGvWLECNJ/Lz8+OFF17gjTfeuGt7X19f3nrrLcaNG5e5rl+/ftjb2/P7779ne47k5GSSk5MzX8fExODn50d0dDTOzs5m/kRClEwRsUlsPhnBxhPh7DwXSUqamvM3o9V8SMvKdKgtreZCFJaYmBhcXFzk2mRGRfkzbfnhJiJik/ljbFuaVSlfqOcSQghRMuXlumSx270pKSkcPHiQSZMmZa7T6/V07tyZ3bt3Z7tPcnIydnZZ51i2t7dn586dOZ7no48+YurUqeYJWohSQtM0zkXEsfFkOBtPhHP48k1uv13n52bP400qMaiFH76u0mouhBD3Ur+iC1tORRAYEi1JuhBCiAKzWJIeGRmJ0WjEy8sry3ovLy9OnTqV7T5du3bliy++oF27dlSvXp3NmzezfPlyjEZjjueZNGkSEydOzHyd0ZIuRFljNGkcDL7BxhNhbDwRzsXrCVneb1TJhS71vOhSz5taXuWk8I4QQuRSfV/nzCRdCCGEhSTehNldoUpbePRLS0dTICVq4NRXX33FmDFjqFOnDjqdjurVqzNixAhmz56d4z62trbY2toWYZRCFB8JKWlsPxPJppPhbDkVQVR8SuZ7NgY9bWtUoEs9LzrX9cLL2e4eRxJCCJGT+hVdAAi8GmPhSIQQogw7vwWunYKoIOj+GRhKVKqbhcUid3d3x2AwEB4enmV9eHh4jlNleXh4sHLlSpKSkrh+/Tq+vr688cYbVKtWrShCFqJEuBabzOb0buw7z0WSnD6+HMDF3pqH63jSpZ4X7Wp5UM625P7xEkKI4iIjST8bHktSqhE7ayk8K4QQRe7KAfVsTIbr58CzjmXjKQCLfUO3sbGhWbNmbN68mb59+wKqcNzmzZsZP378Pfe1s7OjYsWKpKam8scffzBw4MAiiFiI4knTNM5fi2PDiXA2nQjnv2zGl3ep602Xel608C+PlUGmpxFCCHPycbHDzdGGqPgUTofF0sjP1dIhCSFE2RNy4NZyeKAk6fk1ceJEhg8fTvPmzWnZsiUzZswgPj6eESNGADBs2DAqVqzIRx99BMDevXsJCQmhcePGhISEMGXKFEwmE//73/8s+TGEsJjwmCRe/+Mo205fy7I+Y3x553pe1PZykvHlQghRiHQ6HQG+zuw4G0ng1WhJ0oUQoqilpcDVw7dehx+HBv0tFk5BWTRJHzRoENeuXePdd98lLCyMxo0bs27dusxicpcuXUKvv9Xql5SUxNtvv82FCxcoV64cPXr04LfffsPV1dVCn0AIy/nryFXeXhlIdGIq1gYdbau7Z44v93aR8eVCCFGUGlR0UUl6iIxLF0KIIhceqLq5Z74+brlYzMDiA1LHjx+fY/f2bdu2ZXndvn17Tpw4UQRRCVF8RSek8s6fgaw6chVQXwy/HNSIGp5OFo5MCCHKroxx6cevSoV3IYQochnj0e3dIDFKknQhRNHZeTaSV5ceISwmCYNex7iONXjh4RpYyzhzIYSwqPq+Kkk/FRpLSpoJGyv5uyyEEEXmyn713Hgo7J4FMVcg8QbYl7dsXPkkVxAhSoDEFCNTVh3nyV/2EhaTRFV3R5Y914aJXWpJgi6EEMWAn5s9znZWpBhNnI2ItXQ4QghRtmQUjaveEVwqq+XwktsDW77dC1HMHbl8k55f72DOrosAPNW6CqtffJAmlUvmnUEhhCiNdDrdrS7vMi5dCCGKTvx1iLqglis2A68AtVyCu7xLki5EMZVmNPHVprM8/t0uLlyLx9PJljkjWvB+3/o42MhIFSGEKG4ykvRjITIuXQghikzIQfVcoabq3p6ZpAdaLqYCkm/6QhRDF67F8fKSIxy5fBOAng19+KBPfco72lg2MCGEEDkK8HUGIFCKxwkhRNHJGI9eqYV6LgUt6ZKkC1GMaJrGb3uCmbbmJEmpJpztrHi/b316N/KVuc6FEKKYa5Dekn4yNIY0owkrqRkihBCFLzNJb66eveqr54gTYDKBvuT9LS55EQtRSoVFJzFs9j7e/fM4SakmHqzhzvqX29GncUVJ0IUQJdb27dvp1asXvr7qZuPKlSvvu8+2bdto2rQptra21KhRgzlz5hR6nObgX8ERRxsDSakmLkTGWzocIYQo/UwmCDmkljOSdLdqYGUHqQlwI8hysRWAJOlCFAN/HblK1xnb2XE2ElsrPVN61WPeyJb4uNhbOjQhhCiQ+Ph4GjVqxDfffJOr7YOCgujZsycdO3bk8OHDTJgwgdGjR7N+/fpCjrTg9HodAelTsR27Il3ehRCi0F0/C8nRYGUPnund3A1W4FFHLZfQLu/S3V0IC4pOSOWdPwNZdeQqoLpKfjmoETU8nSwcmRBCmEf37t3p3r17rrf//vvvqVq1KtOnTwegbt267Ny5ky+//JKuXbsWVphmE1DRmX0Xowi8Gk2/ZpUsHY4QQpRuV9KnXvNtopLzDF71IfSwStLr9bZIaAUhSboQFrLj7DVeW3qUsJgkDHod4zrW4IWHa8i850KIMm337t107tw5y7quXbsyYcKEe+6XnJxMcnJy5uuYGMtMg9ZApmETQoiic+d49AwlvMK7JOlCFLHEFCMfrz3J3N3BAFR1d+SLgY1k3nNRNNKS4dJuuPgvlPeHhoOy3nkWwsLCwsLw8vLKss7Ly4uYmBgSExOxt89+GNBHH33E1KlTiyLEe8qcK/1qNCaThl4vNUWEEKLQZLSkZ1R2z1DCK7zLNzMhisDNhBS2n41k66kItp2O4EZCKgBPta7CpB51ZN5zUXg0Da6fg3Ob4fxmuLhTFVLJsPsb6PYRVGtvuRiFMINJkyYxceLEzNcxMTH4+fkVeRzV3B2xs9YTn2Ik6Ho81T3KFXkMQghRJqTEQ0R6Ep5TS/qNIEiOA9uS9bdYMgMhCoGmaZwKi2Xr6Qi2norgYPANTNqt972d7fikf0Pa1/KwXJCi9EqKhgv/qKT83BaIvpT1/XJeUOUBOL9FXdzm9Ya6veCRD1TruhAW5O3tTXh4eJZ14eHhODs759iKDmBra4utrW1hh3dfVgY9dX2c+e/STQJDoiVJF0KIwnL1P9BM4FwRnH2zvufoDuW8IS4MIk6CX4vsj1FMSZIuhJkkpKTx77nrbD0dwbZTEVyNTsryfi2vcnSs40nH2p40q1Jexp4L8zGZIPQ/lZCf3wyX94FmvPW+wQYqt4YanaF6J3V3WaeDhCjY9hHs/wVO/gVnNkDb8fDgxBJ3x1mUHm3atGHNmjVZ1m3cuJE2bdpYKKK8a1DRhf8u3eT41Rj6NK5o6XCEEKJ0yhiPXrFZ9u9714dzYRB+TJJ0IcqS4OvxbD0VwZbT19hz4TopaabM9+ys9bSt7p6emHtQqbyDBSMtIzQNTEYwpYEpVT0b09JfZ6xLf9+Y/r7JeGvbXG1/28OYevf5TEa1Hg3sy4ODOzhUAAc3dVfXoYJ6WBdwer3YsFtd2M9vhcSorO9XqKES8hqdwP9BsHG8+xgObtDjM2g2Ata9AUH/wI7p8N986DIVGgwEvdxMypExTcbz50JcXBznzp3LfB0UFMThw4dxc3OjcuXKTJo0iZCQEObNmwfAc889x6xZs/jf//7HyJEj2bJlC0uWLGH16tWW+gh5Vj99GrbAEJmGTQghCk1O49EzeAXAuU0lcly6fLsQIg9S0kzsvxiVnphHcOFafJb3K5W35+E6nnSs40mbahWwszZYKNJSLCoIVk+E0KN3J82mNEtHl3vWDukJvJtK2h1vS+YdbkvmM9ZbO8CVfemJ+Za7q5XaOKlx5dUfVol5Xrqte9WDYX/C6TWw/k24cRFWPAv7f4Zun0ClHO5Ql2UJUfBNSzVMoOtHYG1n6YiKrQMHDtCxY8fM1xnjxocPH86cOXMIDQ3l0qVbQzKqVq3K6tWrefnll/nqq6+oVKkSP//8c4mYfi1DQEVnQCXpmqah00nxOCGEMCtNy0WSXl89S5IuROlzLTZZJeWnIth5LpK45FuJoJVeR3P/8ioxr+1JDc9y8mWsMB1ZDKtfgZTYvO2nM4DBGvRWoDeAPmPZSrWEZizrrdPft8ph+9uPc8fDcNu++vQ/rYk3IOE6xEeqpC7hunqYUlXxtuhLd48Xz/2HAt/Gt1rLK7VQMeSXTgd1eqou8bu/ge2fq25kPz8MjYZC58ng5J3/45c2RxdD/DW4vB+sLD8Oujjr0KEDmqbl+P6cOXOy3ee///4rxKgKV01PJ2wMemKS0rgclUjlCtKTSgghzComRI031xnAp1H229xe4V3T1HedEkKSdCFykJhi5Ltt5/j+nwukGG91Y3cvZ0OH2p48XMeTB2u642xXgMRI5E5SjErOjy1Rryu3VUXObJ1uS7LvkUgXpz/KmgbJMenJ+/VbiXtC5G3LUemJffrrpJtq33Je6S3lnaFaB9XKbm5WtvDQRGg0BDa/B0cWqMfJVfDQK9D6eWk11jQ4OFctNxtevP5/iWLBxkpPHR8njl6JJvBqtCTpQghhbhnj0b3rg00Of2Mr1FTfD5NjIPoyuFYuuvgKSJJ0IbKx8UQ4U/86zpUbiQDUr+hM57pePFzHk/q+LjLvbVG6vB/+GAU3g9Xd0g5vqGRRX0KHEuh0YOeiHm7VcrePMVXdqHBwK7qE0NkHHvsOWoyGtf+DkAOweSocmguPfKha3ctqcnplP1w7CVb20GCApaMRxVSArwtHr0RzLCSaHg18LB2OEEKULhld3Ss2z3kbKxvwqK2GCIYflyRdiJLq0vUEpv51nM2nIgDwdbHj3V716BrgLd3Yi5rJCDu/hK3TVKVy18rw+M9QuZWlIyt6BmtwrGCZc1dqBqM2wrGlsGmyGq+++Amo2h66fazGs5c1Ga3oAY+BvatFQxHFV/3bxqULIYQws/uNR8/gFZCepAdC7e6FH5eZSJIuBJCUauT7f87z7bbzpKSZsDboGP1QNV54uAYONvJrUuSiQ1Thsos71Ov6/eDRL1Xrsyh6ej00GqRaz3d+Cbu+VpXgv38QWoyCDpNUK39ZkBQDx5er5WbDLRuLKNYaVFR/r45fjZHicUIIYU7GVAg9rJZzk6RDiSseJ9mHKPO2nopg8qrjXIpKAOCBGhWY2rs+NTwLaZ7o4l64IiUBLmxTf/TKeRT9+U/+BX+OV+OwrR2h5+dqfHRx/pmVFbbloNM70PQp2PCOGqe+70fVyt7xLTWVW2mfkuzYUlX0z702+JXBXh0i12p5OWGl1xEVn0JodBK+rgWcdlEIIYQSHghpSWDnChWq33tbSdKFKFkuRyXw3t8n2HgiHAAvZ1veebQePRv4FF6LR1IMLBwMMVdV4bO6jxbOefLrwj/w14uqS7PeWsXX7Gnwb1f482WnJKjpvw7+ql77NoF+v9z/j68oeuX9YdBvELQd1r4BEcdhzatwcA4MnFe6/80OzlHPUjCu7MnjDVY7awM1vZw4GRrDsZBoSdKFEMJcMru6N7//3+WMadiun4PURLAuGX+LC/lbtxDFT3KakVlbztLly3/YeCIcK72OZ9pVY/MrHXi0oW/hJehpKbD4SQj+F24EqXG9i55QXbstLfEmrHoB5vVWCbq1o5om7PgKmNcHvm4CO76A2PDCOX/YMfixQ3qCroMHJsDIDaU72SsNqraDZ7dDzy/A3k3d2f7pYXWzpzS6+h+EHQWDjerdIcqGq//BwqGwaUqed63vq8alH5dx6UIIYT4Zld3v19Ud1Mw4DhVAM8G1U4UblxlJki7KlH/OXKPbjB18vuEMSakmWldzY81LD/Fmj7qUsy3EjiUmE6wcq8bxWjtC81FqarBTf8M3rWDvj6pQmiWcTI/h0Dz1uvkoeOUUPLtDVfa2dVaJ++ap8GU9daPh3Cb1mQpK02DPdyqxizwN5bxh2EroMlVV5BTFn8FKjUt/freqsJp0E357DPb/bOnIzC+jYFzd3mVnDL6A2DA4vVr1okhJyNOuDSqpcemBV2MKITAhhCijclPZPYNOVyK7vEuSLsqEqzcTGfv7QYbP3kdQZDweTrZ8NbgxC8e0ppaXU+GeXNNgw1sQuEwl5oN+g0e/UC2QlVpASiysfQ1+eQTCAgs3ltvFhsOSYapFPy4MKtSAp9eo2Oycwach9JyuEvY+30CllmBKU2PGf+8HMxvB9s8gJjR/54+7BvMHwLo3wJgCtXvA2F1q/m9R8jh5w9OrocFAVY1/9SvqYUy1dGTmkRwHx5apZSkYV7bUfARcq6gbUMeW5GnXAN/0JF1a0oUQwjwSoiDqvFqu2DR3+2R0eZckXYjiISXNxHfbztNp+j+sDQzDoNcx6sGqbHmlPX0aVyyaaru7voY936rlvt9BjU5q2SsARq6HHp+r1uqQA/BDO9g4Oc+tNXmiafDffPimJZz4U809/uBEeO5f8H/g7u1tHKHJkzB6o0qiWz6rqqzfvARbPoAvA1RX0DPrc98b4Nwm+K4tnNsIVnbqZzB4geWmGRPmYW0Hj/8InSYDOtWa/vvj6oJa0h1foW6ouVUD/4csHY0oSnoDtByjlvf+qP6G5lJdHyf0OoiITSYiJqmQAhRCiDIk5KB6rlAj973aMlvSi7AxrIAkSRel1r/nIun21XY+WXeKxFQjLfzL8/cLD/LOo/VwsrMumiCOLIaN76jlRz6AhgOzvp/x5W/cXqjbS7VA/jsDvm0N5zabP54bwaor8p/Pq1Yh74bwzFboPFklWPfjFQA9PoVXTsNjP0DlNirm06thwUCY0RC2fQzRV7LfPy0Z1r+lWuLjI8CzHozZqn4GUoSrdNDp4KGJMHi+GtoRtB1+7gTXTls6soI5lN7Vvekw+b9aFjV5EqwdVJHE4H9zvZuDjRXVPdRMIYFXpTVdCCEKLC/j0TNkJOlhgXm60WpJkqSLUicsOonxCw7xxM97uXAtHvdyNkwf0Iglz7ahro9z0QVybrNKhgHajIe2L+S8rbMvDPodBi8E54pwM1i1QP4xWnULLyiTUY39/rYNXNgKBlvoPAXGbAGfRnk/nrU9NBoMI9fBuH3QehzYl4eYK7DtI5jRAOYPhFNrwJim9ok8Cz93ht2z1OsWY9T5veoV/POJ4qdOTxi1AVwqQ9QF9W9/dpOlo8qf8OPqS4HeCho/YelohCXYl791k3XvD3naNWO+9MAQGZcuhBAFlpmk52I8egaPOqDTQ2IUxBVSEWQzkyRdlCprjoXSafo2/j4ail4HT7f1Z/MrHejXrFLRdG3PEHIIFj+lxnDX7w9d3s/dfnV6qFb1VmMBnZqTeVZzOPRb/u/8RZyC2V3V2O/UeKjygOq2/uDLYDBDjwKP2tBtGkw8paZM839IVdA8ux4WDYEZ9eGvl1RX/rCjqgr4kEVq/vMSMg2GyCfv+qqnRuU2kBwDCwbA7m9LzF3sTBkF42r3gHKelo1FWE7LZ9TzqdU59xbKRkBFGZcuhBBmYTLd6u6em6JxGaztVfd4KDFd3iVJF6WCpml8/895np9/iPgUI00qu7Jq/INM6R2Ai30RdW3PcP28KoiWGq+KoPX9Lm9zjNs6QfePYcxm8G6guqWvGg9zHlWt0bmVlgLbPoHvH1R3HW2c1FRZw/8G9xp5/VT3Z20HDfrD03/D+IPQ9kU15UVsqKqKnJqgfh5jd0Ht7uY/vyieHN1h2CrVXVgzwfpJarq/tBRLR5Y7qYlwdJFaloJxZZtXQPpNSCPs/yXXu2VMwyZJuhBCFND1c5AUDVb2t7qw51YJq/AuSboo8dKMJt5aGcjHa9Xch8PbVGHZc22pn956UaTiItILZUWqbuSDfs//VGIVm8GYbaoV3toBgneqYmvbPlFju+/lykH4sT1sm6bmO6/VTbXQtxiVtxsG+eVeAx55X7WuD5ijxtt3/QieXAHOPoV/flG8WNlA71nq/4BOD//9BvP6QHykpSO7vxOr1BcCl8pQ7WFLRyMsLaM1/dBcSM1dIbh66Un61egkrsfd52+3EEKInIWkT73m2zjvvUFLWIV3SdJFiRaXnMaouQdYsPcSOh2882g9pvQOwKC3QGGn5FiY31/NKV7eH55YplrFC8JgBQ+8CM/vgRpd1FRl26ap1vHgXXdvnxKvCrP90hkiTqiW7H6/qO7lLhULFkt+WNlAwGPqZkWb54vmBoEonnQ69X9g6FI1m8GlXfBjx+J/scwsGPeU/P8VasiDcyVIuA6Bf+RqFyc7a6q5OwJwXOZLF0KI/MvPePQMGUl6UU53XADyjUOUWKHRifT/bhf/nLmGnbWe759sxqgHqxbt2PMMaSmw+EkIPQIO7vDkcvOOXS1fBZ5YCv1ng6MHRJ6BX7urbsOJN9Q2F7apwnC7Z6luxQ0Hwbj9qgu6VKMWxUXNzjB6k5rKLPoS/PKIKjBYHEWeVZW8dXopGCcUg5XqkQSw74dc11fIGJd+TLq8CyFE/uWnsnuGjO7ukadLxJA7SdJFiXT8ajR9v/mXU2GxuJezZfEzbega4G2ZYEwmVcX9wjY15dQTS6FCdfOfR6eD+v1g/H5omj429tA8mNUClgxX3YdvBqtWnieWqfmqZd5xURx51IbRm6FqO0iJg0VDYccXxa+g3ME56rlmV8v0RBHFU9PhaoaM0CNweV+udskYl35cpmETQoj8SYmH8BNqOS9F4zK4VAJbF1XUOfKMeWMrBJKkixJn66kIBn6/m/CYZGp6lmPF821p5OdquYA2vqOqsOutYNA8qNi0cM9nXx56z4QRa8G9NsRfgxMr1XstxsC4PVCzS+HGIERBObipHictRgMabJ4Ky5/J9TjfQpeWDEcWqmUpGCdu51gBGgxQy/tyNx2bTMMmhBAFdPWwKtzp5Ju/G+c6XYkqHidJuihRftsTzKi5+4lPMdK2egWWjW2Ln5uD5QLa9fWteb/7fAM1Ohfduau0hed2wMNvQ/VOKmnv+XnBx8ELUVQM1tBzOvT4HHQGOLYE5vSA2DBLR6am2Uq4Dk4+qh6EELdrlV5A7sSfEBN6380DfFWSfikqgeiE1MKMTAghSqeMonGVmuX/GJlJevEfly5JusibqAsQtKPIT2syaXy4+gTvrAzEpEH/ZpWYM6Jl0U+vdrujS2HD22q5y3vQaHDRx2BlC+1eg6eWq6RdiJKo5Rh4agXYuar5T3/sCFf/s2xMGQXjmjypxiELcTufRuDXWnWbPPjrfTd3cbDGz80ekC7vQgiRLwUZj55BWtJFqWQyqnHPcx9V46+LSGKKkefnH+KnHUEAvPpILT7r3xAbKwv+9z2/BVaOVcutn1dzggsh8q9aexizBdxrQexVmN0djq+wTCxRQel/43TQ5CnLxCCKv4zW9AO/5qoIUf301vRASdKFECLvrmS0pBckSS8507BJki5y78JWuHlJLf/zaZGcMjIumSE/7WHd8TBsDHq+GtyY8Q/XtEwF9wxX/4PFT6n5x+v3g0c+lOrpQphDheqq8nuNzpCWCEufzvU0V2b132/quXpHNbOCENmp21sNh4iPuFUX5B7qy7h0IYTIn+gQiA1VQ+N8Guf/OJ511XNcGMRHmiW0wiJJusi9/+bfWg7+Fy7uLNTTnYuI5bFv/+Xw5Zu4Oljz26iW9Gls4QrLURdg/gBVkbpqe+j7ncydLIQ52bnA0CXQfKR6veol1bJdVIyp8N/varnZ00V3XlHyGKxv/T/de/8CcplJurSkCyFE3mR0dfcKAJsC1KKyLQflq6rlYt6aLtmFyJ3EG6qQEkDl9LHPhdiavvv8dR7/dheXoxKpUsGB5WPb0qqahacTi7sGvz2uqql7N4BBv6sx4UII89IboPtnasxvSiwsG1l0c5qeWQ9x4eDoAbW6F805RcnV7Gkw2KiCRiEH77lpQPo0bEGR8cQlpxVBcEIIUUqEmKGre4YSMi5dknSRO4F/gDEZPAPg8R/UdGNB/8ClvWY/1fJDVxg2ey8xSWk0rezK8rFtqeZRzuznyZPkWJjfH24EgWsVeOIPsHO2bExClGYGK+j3syomd/UQbHmvaM6bUTCu8VCwsimac4qSq5wnBDymlvf+eM9N3cvZ4uNih6bBiavS5V0IIXItczx6PuZHv1MJGZcuSbrInYyu7k2eANfK0GiIer3dfK3pmqYxY9MZJi45QqpRo2cDHxaMaU2FchZurU5LgSXDIPQwOFRQczs7eVk2JiHKAlc/NbUhqOkOz24s3PNFX4Fzm9RyU5kbXeRSy2fV8/HlqsfVPdwaly5d3oUQIleMqbdmfDFrS3rxnoZN5pUR9xdxUrVk6a2g4SC17qGJcHiB+kIbchAqFmDOQiAlzcQby4+y/FAIAM+1r87/utZGr89jQTZjmmr1T4oGNNBMoKU/3/46y3sZr7PZTjNB6BFVzd3aAZ5YCu41CvRZhRB5UPdRaPkM7PsRVjwLz/0Lzj6Fc67/fle/8/4PqSJ2QuRGpWbqGhhyEA7Ogfav5bhpfV8XNp4Il3HpQgiRW+HHIS1J1axxM8O1OSNJv3ZK5Q3FdJrV4hmVKF4yiijV6gaO7mrZrRo0HAhHFsL2z2HIwnwfPjohlWd/P8CeC1EY9Do+6FufIS0r5+9g/3xi1tb9THorGPhbgW9GCCHyocv7ELwbwo/BimfgqZVq3Lo5mYxwKL2quxSME3nV8ln1f/PAL/DgBFVULhv1K6phUtKSLoQQuZRRNK5ic/MUay5fVTW8pSaogtAetQp+zEIgSbq4N2MqHF2slhsPzfreQ6/AkUVweg2EHgWfhnk+/MXIeEbN3c/5a/GUs7Ximyea0r6WR/5ijQqCf79SyzUfARtH0OkBnXrW6W57nf7I9r1sXtd9FKq0zV9cQoiCsbaDAb/CD+0haDvs/ALa5dxamS/nNkPMFbAvD3UeNe+xRekX0Bc2vKWmCDr5F9R/PNvNMrq7n4uIIzHFiL2NmW82CSFEaZNRlNMcXd1BJfqe9VQxuvBASdJFCXVuk6pm7uihEt/buddU84QHLoPtn8Gg33J9WJNJY97ui3yy7jSJqUZ8XOyY/XQL6voUoBjb+jdVcbtqHdUUTjJ3uRClh3tN6Pk5rBwLW6dBlQehShvzHT+jYFyjIeqmgBB5YWULzUaonlz7fswxSfdytsPDyZZrscmcDIuhaeXyRRyoEEKUMBkt6eYoGpfBKyA9ST+e499rS5PCceLeMrq6NxyUffe9dq+q55OrIPxErg556XoCQ37aw5S/TpCYaqR1NTdWjnugYAn62U2qRV9vBd0/kQRdiNKo0RD1t0gzwR+jICHKPMeNDYPTa9WyFIwT+dV8pLoGXdqtepfloL6vdHkXQohcSYiC6+fUsjmHnJaACu+SpIucxUfCmXVqufET2W/jWRfq9lbLOz6/5+FMJo25uy7SdcZ29gZF4WBj4P0+ASwY3Rov5wK0XKWlwLrX1XKr58Cjdv6PJYQovnQ66Dld1cSICYE/x6cXfiygw/NBM4JfK/CsU/DjibLJ2efW9XDfDzluJhXehRAil0IOqWe36uDgZr7jloC50i2epH/zzTf4+/tjZ2dHq1at2Ldv3z23nzFjBrVr18be3h4/Pz9efvllkpKSiijaMuboEjClgW8T8KqX83YZY0MDl0Pk2Ww3yWg9n7zqeGbr+foJ7XiqjX/eK7jfac+36i6boye0f71gxxJCFG+2TtD/V9Bbw+nVsO+ngh3PZIJD89SytKKLgmqVPh3bsWU59vS4laTLXOlCCHFPmV3dzTQePUNGkh59CRJvmvfYZmLRJH3x4sVMnDiRyZMnc+jQIRo1akTXrl2JiIjIdvsFCxbwxhtvMHnyZE6ePMkvv/zC4sWLefPNN4s48jJA01TrEuTcip7BpyHU7gFosGN6lrcyxp53+0q1nttbG3gvvfXcz82h4HHGhKrx8ABdpoJdAbrMCyFKBt/G8Mj7annDW/fsWnxfF7fDjYtg6wIBj5kjOlGW+bUC74ZquqCMOgd3yEjSz4THEhmXXJTRCSFEyVIY49EB7F3BxU8tR+RuuG5Rs2iS/sUXXzBmzBhGjBhBvXr1+P7773FwcGD27NnZbr9r1y4eeOABhg4dir+/P4888ghDhgy5b+u7yIfQI6riocEGGvS///YZrelHl6jpDIDLUQkM/XkP7/55nIQUI62qqtbzYeZoPc+w8V1IiVN32BoONs8xhRDFX6vn1LSQxhRYNgKS4/J3nINz1HPDAWBjhhuHomzT6W61pu//Rc3BewdfFzsa+bmSZtL4ftv5Ig5QCCFKCJPptsruZk7Sodh3ebdYkp6SksLBgwfp3LnzrWD0ejp37szu3buz3adt27YcPHgwMym/cOECa9asoUePHjmeJzk5mZiYmCwPkQuHF6jnOj3VlET3U7Ep1OgCmhFtxxfM263Gnu+5oFrPp/YOYOGY1lSuYMYvwcG74dgSQAc9PjPP3IlCiJJBp4M+34KTrxrusiYfU7LFR8LJv9WydHUX5lK/H9i7QfRlOLP2rrd1Oh0vd64JwG97gomIkSF7Qghxl6jzkHQTrOxuFXozp8wkPdD8xzYDi2U1kZGRGI1GvLy8sqz38vIiLCws232GDh3Ke++9x4MPPoi1tTXVq1enQ4cO9+zu/tFHH+Hi4pL58PPzM+vnKJXSktOTX6Dxk7nfr/3/ADD+t4AfV23LbD1fN+Ehhrc1Y+s5gMkIa9O/lDcdpsbNCyHKFscK0O8n0OnhyAI4sihv+x9ZCKZU9ffDp2HhxCgylZkaNNb20Cz9ps/e7AvIta/lQbMq5UlOM/GttKYLIcTdrhxQzz6Ns59hqqCkJd18tm3bxrRp0/j22285dOgQy5cvZ/Xq1bz//vs57jNp0iSio6MzH5cvXy7CiEuo02sh8YZqoareMVe7mEwav13xZJfWACuMjLf+O7P1vEoFR/PHePBXCDsGdi7Q6V3zH18IUTL4P3irYOTfEyHyXO720zQ4mD5mWFrRC12Zq0HTfJS6eXRxR7bTk+p0OiZ2qQXAgr2XCI1OLOoIhRCieCus8egZMqdhO6G61hczFkvS3d3dMRgMhIeHZ1kfHh6Ot7d3tvu88847PPXUU4wePZoGDRrw2GOPMW3aND766CNMOfxwbW1tcXZ2zvIQ95FRMK7RYNAb7rv55agEnvh5L+/8eZwZKX0BGGT1D8MDrM3bep4hIQq2fKCWO74Nju7mP4cQouRo9xpUeRBS49X49LRcFOO6tBuunwVrx9zV3RAFUuZq0Lj6qeFiAPt+zHaTttUr0LKqGylGE99szeXNJSGEKCsKq7J7BrfqYLBV3x1uXiyccxSAxZJ0GxsbmjVrxubNmzPXmUwmNm/eTJs2bbLdJyEhAf0d444NBpVEauaYK1eoaunnNqnl+1R1N5k0ftsTTNcZ29l94Tr21gZ6PNoPrXJbdKYU+Perwolxyweqpd8zAJqPLJxzCCFKDr1BdXu3d4Owo7Bx8v33ySgY16CfmtZNFJoyW4OmZXoBuaOL1TXrDre3pi/ef5krNxKKMjohhCi+UhJudUMvrJZ0gxV41lHLxbDLu0W7u0+cOJGffvqJuXPncvLkScaOHUt8fDwjRowAYNiwYUyaNClz+169evHdd9+xaNEigoKC2LhxI++88w69evXKTNZFAR1dBJoJ/FqDe40cN7sclcCTv+zlnZWBJKQYaemvxp4//UBVdB3Su54emgux4TkeI19Cj6qu7gA9PlW/YEII4ewLj32vlvd+B6fW5Lxt4g048adabvp0oYdW1pXZGjT+D4JnPUhNgP/mZ7tJ62oVeKBGBVKNmrSmCyFEhtDDoBnByQecKxbeeTK7vEuSnsWgQYP4/PPPeffdd2ncuDGHDx9m3bp1mRfyS5cuERoamrn922+/zSuvvMLbb79NvXr1GDVqFF27duWHH7IvzCLySNNuVXVvPDSHTTR+3xNMtxnb2XX+OnbWeib3qseiZ24be161PVRqqeaJ3TXTvPGt/Z+6iVC/n/oCJIQQGWp1hdbj1PKfz0N0SPbbHV2i/j551VczU4hip1TUoNHpoOUzann/T6rgaTZe7qxa05ceuMKl69KaLoQQmUXjKjZTf0sLSzGu8J7nJN3f35/33nuPS5cumSWA8ePHExwcTHJyMnv37qVVq1aZ723bto05c+ZkvraysmLy5MmcO3eOxMRELl26xDfffIOrq6tZYinzrhyAyDNgZQ8Bj931dmKKkdFzD/D2ykDiM1rPX2rHiAeqZh17rtNlVnrnwGw1zZE5HFuqxpFaO0CXnL+oCSHKsM6TVSXYxBvwx+i756m+s2BcYV78BVDGa9A0HKgKnN64CGc3ZrtJc3832tXyIM2kMXPL2aKNTwghiqPCHo+eoRhXeM9zkj5hwgSWL19OtWrV6NKlC4sWLSI5ORdFekTxd/h39VyvD9hl/XITnZDKk7/sZfOpCGyt9Lz7qGo993fPoXJ7jc5qWqPUBNg9q+CxJcfChnfUcrtXwaUQu74IIUouK1voPxtsysGlXbD9s6zvhxyEiONq3tWGAywTYxlTpmvQ2DhCk6fU8r6ce/1ljE1ffugKQZHxRRGZEEIUXxkt6YWepKd3d48KguS4wj1XHuUrST98+DD79u2jbt26vPDCC/j4+DB+/HgOHTpUGDGKopCSAIHL1XKTrAXjImKSGPTjbg4G38DZzooFY1ox8sGq967crtNBu/TW9H0/qYrsBbH9M4gLA7dq0GZ8wY4lhCjdKlSHR2eo5e2fQtCOW+9lFIwLeAzsyxd1ZGVWma5B02I0oIPzWyAy+5byxn6udKrjiUmDrzadKdr4hBCiOIkOgdiroDOAb+PCPZejO5TzAjS4dqpwz5VH+R6T3rRpU2bOnMnVq1eZPHkyP//8My1atKBx48bMnj27ZN3pFnDqb0iOAdfKaiqjdJeuJ9D/+92cCovFw8mWxc+2oVkVt9wds3Z38GoAKXGw57v8xxZ5FnZ/q5a7faxayoQQ4l4aDoDGT6oaFsvHQPx1SIqBwD/U+zI3epEq0zVo3KpCrW5qOYfp2ABeTm9N//PIVc5FxBZFZEIIUfyEpLeie9VTvZEKWzEdl57vJD01NZUlS5bQu3dvXnnlFZo3b87PP/9Mv379ePPNN3niiXtP3yWKmf/Su7o3fgLSuxieCouh//e7uBSVQGU3B/54ri11ffIwxk+ng/avqeW9P0BSdN7j0jRY9waYUqHmI6owlBBC5EaPT6FCTYgNhZVjVV2L1ARwrw2VW1s6ujKnTNegaZVeQO7wAnWzKBv1K7rwSD0vNA1mbJKx6UKIMqqourpnKKbj0vOcpB86dChLF/eAgAACAwPZuXMnI0aM4J133mHTpk2sWLGiMOIVheHmJQjarpYbDQbgYPANBn6/m4jYZOp4O7HsuTZUruCQ92PX6QUedSE5Gvbm3IKQo9Nr1bztBhvVii6EELll4wgDfgWDLZxdf6uuRdNhUjBOFK1qHcG9lupZdmRhjptltKb/fTSUU2EWnuddCCEsIbOyeyHNj36nYjoNW56T9BYtWnD27Fm+++47QkJC+Pzzz6lTp06WbapWrcrgwYPNFqQoZEcWARr4PwTl/fnnzDWe/HkvMUlpNKtSnsXPtMHT2S5/x9brVaE3gD3fqAJwuZWaBOvTxyi2GafGmQohRF54N4CuH6rl1Hh1w6/REMvGJMqe26dj2/cj5FChvq6PMz0b+AAwY6O0pgshyhhjKlz9Ty0XeUt6oOrBW0zkOUm/cOEC69atY8CAAVhbW2e7jaOjI7/++muBgxNFwGSCw/PVcpMn+evIVUbP3U9iqpH2tTz4bVRLXByy/3fOtYDHoEINNSXS/p9zv9+ur9W0NU6+8NCrBYtBCFF2tRgNdR5Vy3V7g2MFy8YjyqZGg8HGCa6fgwtbctzspc410elg3fEwAkPyMUxMCCFKqogTkJYIti4qdygK7rVAb6WG5caEFM05cyHPSXpERAR79+69a/3evXs5cOCAWYISRejSLpUI2zixMK4xLy76j1SjRq9Gvvw0rDkONlYFP4fecCvJ3jULUnIxvczNy7Bjulp+5H2wLVfwOIQQZZNOB4//BL1nQY/P7r+9EIXB1unW7Cn3GP5Vy8uJXg19ARmbLoQoYzLnR2+WWSOr0FnZqlo1UKy6vOf5048bN47Lly/ftT4kJIRx48aZJShRhP5TrejH3Tox6a/zaBo82boyMwY1xsbKjL8cDQZAeX9IiIQDuehlseFtdSetygNQv5/54hBClE02DtD0KXDI5ewUQhSGFmPU89kNEHUhx81e6lwTvQ42nQznyOWbRRObEEJY2pWD6rmourpnyOjyHnasaM97D3luJj1x4gRNmza9a32TJk04ceKEWYISRSQ5Fu3ESnTAO8GNAXjh4RpM7FILnbmLKhms4KFXYNULsGsmtBgF1vbZb3vhHzixEnR66P6JFHgSQghROrjXgBqdVUHU7dNVy7oxVT1M6c/GFKqb0pjmf56jl65zbPm/NGrhe9v7qdkvO/tCu/+p660QQpREGS3pRVU0LoNXAByjWLWk5/kvua2tLeHh4VSrVi3L+tDQUKys5MJQkhgDV2BITeC8yYdDWk3eebQeox6sWngnbDgY/vkUoi/Dod9uTUmTJahUWPu6Wm4+ShV9EkIIIUqLls+qJP3w7+qRg8HAYGvgBrAhl8f2qC29z4QQJVPiDbiePsSnUlEn6cWvwnues+pHHnmESZMm8eeff+Li4gLAzZs3efPNN+nSpYvZAxSFIynVyKWNP1ILWG5qx/QBjenXrFLhntTKBh58GVZPhJ1fQrPhahzI7fb/DNdOgr0bdHyzcOMRQgghilqNziqRvnJAzTZgsFZFi7IsW4PBhsCwBC7eSKG8kwMP1PJVreR66/T3rW8tXzkA5zbC8RWSpAshSqaQ9K7ubtWKfmhaRnf362fV7FLW+ZzVyozynKR//vnntGvXjipVqtCkSRMADh8+jJeXF7/99pvZAxTmF5uUytuzV/FV0jGMmo5WfcfRrrAT9AxNnoTtn0PsVVVVvvnIW+/FXYOtH6nlTu/K2FEhhBClj14P/WfnalOXqAQmfL6NtCiNxQ1b06paDjMThB1TSfrZjWqqU1snMwYshBBFIGN+9KIejw7g5K0aCBOj4Nop8G1c9DHcIc+VwSpWrMjRo0f59NNPqVevHs2aNeOrr77i2LFj+Pn5FUaMwoyuxyUz9Ke91Li6CoDYiu1o17xR0QVgZQsPvKSWd3ypurdn2DwFkqPBpxE0HVZ0MQkhhBDFkJ+bAwNbqO9WX246k/OGXvXVdEVpSXBmfRFFJ4QQZmTJJF2nu22+9OLR5T1fg8gdHR155plsxhOLYi3kZiJP/bKXi9di+cluBwCubZ8u+kCaDVfTq0VfgiOLVMXlKwfhv/SxeT0+V9O2CSGEEGXc+I41WHbgCnsuRLHrfCRtq7vfvZFOBwGPwfbPIHA5NOhf9IEKIUR+adptReOaWSYGr/pwcUexSdLzPcfWiRMnWLduHatWrcryEMXTuYg4+n+3iwvX4unjdBZvroOdK9TuUfTBWNvDAy+q5R3T04vFvaZeNxoCfi2LPiYhhBCiGPJ1tWdIS9Wa/sWGM2ialv2GAY+p53MbISmmiKITQggzuH4ekm6Cld2tIm5FLbMlPdAy579DnlvSL1y4wGOPPcaxY8fQ6XSZF4uMKbuMRqN5IxQFdvTKTZ7+dT9R8SlU93DkQ58jcAY1d7mlCiM0H6mKx90IgkVPqGIRNk7QeYpl4hFCCHGXy5cvo9PpqFRJ1S3Zt28fCxYsoF69etKjrgg937EGC/df5kDwDXacjaRdLY+7N/KsB+61IPIMnF4LjQYVfaBCCJEfIeld3X0aqULTlnB7kq5pFp8COs8t6S+99BJVq1YlIiICBwcHjh8/zvbt22nevDnbtm0rhBBFQew6H8mQH/cQFZ9Cw0ouLHs6AIfza9WbjYdaLjAbR2gzXi2fTR8/1/5/qnCDEEKIYmHo0KFs3boVgLCwMLp06cK+fft46623eO+99ywcXdnh5WzHk62qAPDFxhxa0zO6vIOq8i6EECVFRld3S4xHz+BRB3R6SLgOcRGWiyNdnpP03bt389577+Hu7o5er0ev1/Pggw/y0Ucf8eKLLxZGjCKfrtxIYOSc/cSnGGlbvQILxrSm/IVVYExWd9x9m1g2wJZjVJd7gAo1odVzFg1HCCFEVoGBgbRsqYYgLVmyhPr167Nr1y7mz5/PnDlzLBtcGTO2Q3XsrPUcvnyTradz+AKZkaSf3wyJN4ssNiGEKJDMonFFPD/67WwcwK26Wi4GXd7znKQbjUacnNTUHu7u7ly9ehWAKlWqcPr0afNGJwpk+oYzJKWaaF6lPLOfbkE5Wys17RlA4ycs3o0DWyfo8h44V4TeMy3XvUUIIUS2UlNTsbW1BWDTpk307t0bgDp16hAaGmrJ0MocDydbhrfxB+7Rmu5ZFzzqgjFFdXkXQojiLiXhVlJc0YJJOhSrCu95TtLr16/PkSNHAGjVqhWffvop//77L++99x7VqlUze4AifwJDolnxXwgAk3sFYGdtgIhTauy33goaFpOxas2Gw8QTUKWtpSMRQghxh4CAAL7//nt27NjBxo0b6datGwBXr16lQoUc5uwWheaZdtVwsDEQGBLDxhPh2W8kXd6FECVJ6BEwpUE5b3CpZNlYMorWlcQk/e2338ZkMgHw3nvvERQUxEMPPcSaNWuYOXOm2QMUeadpGtPWnASgT2NfGlRyUW8cTp/irGZXKJdN0RkhhBDiNp988gk//PADHTp0YMiQITRq1AiAVatWZXaDF0WnQjlbnm7rD6jWdJMpm9b0gL7q+fwWSLxRZLEJIUS+hNzW1d3SvXyLUUt6nqu7d+3aNXO5Ro0anDp1iqioKMqXL59Z4V1Y1rYz19h1/jo2Bj2vPlJbrTSmwpHFarnJE5YLTgghRInRoUMHIiMjiYmJoXz58pnrn3nmGRwcHCwYWdn1TLtqzNsdzKmwWNYdD6NHA5+sG3jUBs8AiDgOp1ZDkyctE6gQQuRGZtE4C3d1h1tJ+rVTKncyWFsslDy1pKempmJlZUVgYNbB9G5ubpKgFxNGk8bHa04B8PQD/vi5pX+JOrcZ4iPAwR1qPmLBCIUQQpQUiYmJJCcnZybowcHBzJgxg9OnT+Pp6Wnh6MomVwcbRj5YFYAvN57BmG1runR5F0KUEFcOqmdLVnbP4FpZTQltSoXIsxYNJU9JurW1NZUrV5a50IuxPw5e4XR4LC721ozrUOPWGxld3RsOsuhdISGEECVHnz59mDdvHgA3b96kVatWTJ8+nb59+/Ldd99ZOLqya9SDVXGys+JsRByrj2VTwC+jy/uFbZAQVZShCSFE7sVchZgrauozn8aWjkZ1ty8mXd7zPCb9rbfe4s033yQqSv7oFzcJKWlM36gq7L/wcA1cHNKT8fjrcHqdWpau7kIIIXLp0KFDPPTQQwAsW7YMLy8vgoODmTdvntShsSAXe2vGPKSK9c7YdIY0oynrBu41wauBKsZ06m8LRCiEELkQvEs9ewaAbTnLxpIhM0m37DRseU7SZ82axfbt2/H19aV27do0bdo0y0NYzi87ggiPSaZSeXuealPl1hvHlqhuGz6Nb/3HE0IIIe4jISEhc9rVDRs28Pjjj6PX62ndujXBwcEWjq5sG/GAP64O1ly4Fs+qI1fv3qC+dHkXQhRjsWGw/k21XL2jZWO5nXdGhXfLJul5LhzXt2/fQghDFFRkXDLf/3MegNe61sbWynDrzf/S50aX4jFCCCHyoEaNGqxcuZLHHnuM9evX8/LLLwMQERGBs7OzhaMr25zsrHmmXTU+XXearzafpXcjX6wMt7W91OsLm9+DC/+oHnWOMmWeEKKYMKbC0hEQFw6e9aDDG5aO6JZiMg1bnpP0yZMnF0YcooC+2nSW+BQjDSu50Kuh7603Qo9A+DEw2ED9fpYLUAghRInz7rvvMnToUF5++WUefvhh2rRpA6hW9SZNmlg4OjG8jT+/7Agi+HoCyw+FMLCF3603K1QHn0bqe8DJVdB8hOUCFUKI222eCpd2qSJtA38DG0dLR3SLZ131HBtq0Rucee7uLoqf89fiWLDvEgCTutdFr7+t0v7hBeq5dg9wcLNAdEIIIUqq/v37c+nSJQ4cOMD69esz13fq1Ikvv/zSgpEJAEdbK55rXx2AmVvOkpR6R2FfqfIuhChuTvwJu75Wy32/Bfca996+qNk6QXl/tRxhudb0PCfper0eg8GQ40MUvU/XncJo0uhU24M2Hslwei1s+wQWPQEH56qNpKu7EEKIfPD29qZJkyZcvXqVK1euANCyZUvq1Klj4cgEwJOtq+DhZMuVG4kMn72P6MTUW2/W66ueL+6AuGsWiU8IITJFnoWV49Ry2xehXm/LxpOTYtDlPc/d3VesyHo3NjU1lf/++4+5c+cydepUswUm7sNkghtBnDv6L41Ob+QJmyDahl+FL67fvW2FmlD94aKPUQghRIlmMpn44IMPmD59OnFxcQA4OTnxyiuv8NZbb6HXS4c8S7O3MTBzcBPGzDvA3qAoBny/i7kjW+LjYg9uVcG3CVz9T3V5bzHK0uEKIcqqlHhY/BSkxEKVB6FTMR5C7RWgZsawYPG4PCfpffr0uWtd//79CQgIYPHixYwaJRcAszOmwrXTEHZUjS0LPQphxyAllhpAjYx/xSRAZwCP2mocmndD9VyxKeill4MQQoi8eeutt/jll1/4+OOPeeCBBwDYuXMnU6ZMISkpiQ8//NDCEQqANtUrsOTZNjz96z7OhMfx+Le7mDOiJbW9nVSX96v/qS7vkqQLISxB02DVi3DtJJTzhv6zwZDnNLToFIO50nWapmnmONCFCxdo2LBh5p324iomJgYXFxeio6OLZ2Xa1ET1HyL0iHqEHYXwE2BMvmtTo96GY2mVOK2rRvcuXXGu2kxVSLS2t0DgQggh8qu4Xpt8fX35/vvv6d07a5fEP//8k+eff56QkBALRXZ/xfVnWpiu3Ehg+Ox9nL8Wj7OdFT8Oa05rt3iY0QB0eph4Cpy8LB2mEKKs2fsjrH0N9FYw/G+o0sbSEd3b9fPwdVOwsoM3r5qtsTMv1yWz3MJITExk5syZVKxY0RyHK7vCAmF2V0jJ5kaHrTN4N8hsIU/1bEDX38O4EJXMS51q4vxgraKPVwghRKkWFRWV7djzOnXqEBUVZYGIxL1UKu/AH2PbMmruAQ4G32DYL/v4clBjelZsDiEHVJf3lmOKPrCwQFjyFDQfBW3HF/35hRCWc3nfrfnQu7xf/BN0UIXjrB0gNQGiLoB7zSIPIc9Jevny5dHpblUP1zSN2NhYHBwc+P33380aXJmz/TOVoNuXB9+mKiH3Se+y7uoPt439+/3fIC5EJeNezpZn2lWzXMxCCCFKrUaNGjFr1ixmzpyZZf2sWbNo2LChhaIS9+LqYMP80a14ceF/bDgRzviFh/Bo0J6WHFBd3os6Sdc0WD1RfdHdNBlqdlHD8oQQpV/cNVgyHEypqpBl67GWjih39AY1FVvIQTUuvSQk6V9++WWWJF2v1+Ph4UGrVq0oX768WYMrU66fV3e4AZ5efWssRDZiklKZufksAC93qYmjbTEe0yGEEKLE+vTTT+nZsyebNm3KnCN99+7dXL58mTVr1lg4OpETO2sD3z3ZjCmrjvPbnmAmHK3CLjvQgnehiwkFZ5+iC+b4cri8Vy2b0mDNqzBsFdz2XVIIUQqZjPDHSIi9Cu61oM+skvV77xWQnqQfvzWdZRHKc3b39NNPF0IYgl1fg2aCmo/cM0EH+G7beW4kpFLdw5FBzf2KKEAhhBBlTfv27Tlz5gzffPMNp06dAuDxxx/nmWee4YMPPuChhx6ycIQiJwa9jvf6BODtYsdn6+GgqSbN9GdJO/4nVm2eK5ogUhNhY3oF56bD4OgSCNoOgX9Ag/5FE4MQwjK2fKB+360dYeBvav7xksTC07DlOUn/9ddfKVeuHAMGDMiyfunSpSQkJDB8+HCzBVdmxEXA4QVq+YGX7rnp1ZuJzN4ZBMAb3etiZZDpb4QQQhQeX1/fu6q4HzlyhF9++YUff/zRQlGJ3NDpdIzrWAMvZzvWrmhNM/1Zzm2dR8Umo3Cysy78AHbPgujL4FwJun0CLn6w9UNY/xbU6lryvrQLIXLn1BrY+YVa7vM1eN5d26TYy6zwbplp2PKc4X300Ue4u7vftd7T05Np06aZJagyZ+/3qnp7xeZQ5YF7bjp9wxmS00y0rOpG57qeRRSgEEIIIUqq/s0q0an/MwDUSTnO2O/+JjwmqXBPGhMKO75Uy12mgo0DtH0R3KpBXBhs+7hwzy+EsIzr52FFem+dVmOhfj/LxpNfnvXU881LkBRd5KfPc5J+6dIlqlatetf6KlWqcOnSJbMEVaYkx8L+n9XygxPuOVbjxNUYlv93BYA3e9TNUhtACCGEECInbRo3JN6rBQA1Izfz+Le7OBdRiNPmbnkfUuOhUotbX9Kt7aD7Z2p5z3dqilkhROmRkgBLhkFyNPi1gi7vWTqi/HNwA+f0mcsiThb56fOcpHt6enL06NG71h85coQKFSqYJagy5eAcdXemQg2o3fOem3609iSaBo829KGxn2uRhCeEEEKYwzfffIO/vz92dna0atWKffv23XP7mzdvMm7cOHx8fLC1taVWrVpSrK6AHJuqoYr9bPcRcjOR/t/v4mBwIUyld/U/ODxfLXf7OGsDRM3OUOdR0IyqiJymmf/8Qoiip2mw+hXVPdzRAwbMASsbS0dVMBbs8p7nMelDhgzhxRdfxMnJiXbt2gHwzz//8NJLLzF48GCzB1iqpaXA7m/VctsXs0yxdqftZ66x42wk1gYd/+taAsd1CCGEKDEef/zxe75/8+bNPB1v8eLFTJw4ke+//55WrVoxY8YMunbtyunTp/H0vHvoVkpKCl26dMHT05Nly5ZRsWJFgoODcXV1zdN5xR3q9oa1r1PfdJpOvilsvgpDf9rLzCFN6BrgbZ5zaBqsm6SWGw6CSs3v3qbbx3BuMwT/q4rJNRpknnMLISzn4Bw4sgB0eug/G5x9LR1RwXkFwNkNFikel+eW9Pfff59WrVrRqVMn7O3tsbe355FHHuHhhx+WMel5dWypmpagnDc0yvkGh9GkMW2N6mbxVGt/KldwKKoIhRBClEEuLi73fFSpUoVhw4bl+nhffPEFY8aMYcSIEdSrV4/vv/8eBwcHZs+ene32s2fPJioqipUrV/LAAw/g7+9P+/btadSokbk+Ytnk7ANV2gLwXZPLdKrjSXKaibG/H+T3PcHmOceJlXBpN1jZQ6fJ2W/j6gftX1PLG962yHhPIYQZhRyEtf9Ty50mQ9V2lo3HXCxY4T3PLek2NjYsXryYDz74gMOHD2Nvb0+DBg2oUqVKYcRXeplM8O9Xarn1WLCyzXHT5YeucCosFic7K154uEYRBSiEEKKs+vXXX812rJSUFA4ePMikSZMy1+n1ejp37szu3buz3WfVqlW0adOGcePG8eeff+Lh4cHQoUN5/fXXMRgM2e6TnJxMcnJy5uuYmBizfYZSJeAxCP4Xm1N/8sPI8bzzZyAL913m7ZWBhEUn8cojtfJf8yY1CTa8q5YfnAAuFXPets14NbPN9XOwdRp0/yR/5xRCWFZCFCwZDsYUNZTlPjNVlSiZSfoJlbvdo9ezueX7TDVr1mTAgAE8+uijkqDnx5l1EHkabJ2h+YgcN0tKNTJ9wxkAxnesQXnHEj62QwghRJkSGRmJ0WjEy8sry3ovLy/CwsKy3efChQssW7YMo9HImjVreOedd5g+fToffPBBjuf56KOPsrT2+/n5mfVzlBp1ewM6CDmAVcxlpj3WgJc71wJg1tZzvLbsKKlGU/6OvecbiL6kii21ffHe21rZQo/0InL7foSwY/k7pxDCckxG+GO0mmrRrRr0/faeRbBLnAo1wGADKbFw00y9jXIpz0l6v379+OSTu+92fvrpp3fNnS7uIaMVvfkIsHPJcbNfdgYRFpNERVd7hrf1L5rYhBBCCAsymUx4enry448/0qxZMwYNGsRbb73F999/n+M+kyZNIjo6OvNx+fLlIoy4BHHyAv8H1fKJP9HpdLzUuSYfP94Ag17HsoNXGDX3APHJaXk7bmwY7EifF7lz+pRr91P9YajXFzQTrH5VtVQJIUqOfz6F85vV8JaBv90zpymRDFbQ7jXo8blqWC1CeU7St2/fTo8ePe5a3717d7Zv326WoEq9S3vg8h51Z6b18zludj0ume+2nQfg1a61sLPOvoufEEIIUVy5u7tjMBgIDw/Psj48PBxv7+yLlfn4+FCrVq0sXdvr1q1LWFgYKSkp2e5ja2uLs7NzlofIQcBj6vn4isxVg1tW5senmmFnrWf7mWsM/nFP3uZS3/I+pMSpKdca9M/9fl2ngbWj+l50ZGHu9xNCWNbZjfBPesNtr6/Au75l4yks7f8HLceAY9HOYpbnJD0uLg4bm7u7XFtbW8v4r9zaOUM9NxoMTjlXU/16yzniktMI8HWmT6N7jOsSQgghiikbGxuaNWvG5s2bM9eZTCY2b95MmzZtst3ngQce4Ny5c5hua1k9c+YMPj4+2X4HEXlUt7eqwHz1EEQFZa7uVNeLhWNa4+Zow7GQaHp8tYNtpyPuf7yrh+G/9CnXun6Ut+6uLhWhw+tqeeO7kHgj9/sKISzjRrDq5o4GzUfJDA2FIM9JeoMGDVi8ePFd6xctWkS9evXMElSpFnESzqwFdPccrxUUGZ9ZafXNHnXR60vR+A4hhBBlysSJE/npp5+YO3cuJ0+eZOzYscTHxzNihKrJMmzYsCyF5caOHUtUVBQvvfQSZ86cYfXq1UybNo1x48ZZ6iOULuU8wP8htXxiZZa3mlQuz/Kxbanr48z1+BSe/nU/H605mfM49cwp1zRoMBD8WuQ9nlZjwb02JETClpzrDgghioHUJFgyDJJuQsVm0O0jS0dUKuW5uvs777zD448/zvnz53n44YcB2Lx5MwsWLGDZsmVmD7DU2fW1eq7TE9xr5rjZp+tOkWbS6FDbgwdquBdRcEIIIYT5DRo0iGvXrvHuu+8SFhZG48aNWbduXWYxuUuXLqG/rWqun58f69ev5+WXX6Zhw4ZUrFiRl156iddff91SH6H0CXgMgv5RXd4ffDnLW/7ujqx4vi3T1pxk3u5gfth+gb1BUXw9pAl+bneMNT/xJ1zapcakds5hyrX7sbKBnp/D3F6w/xdo8iT4NsnnBxNCFKq1/4PQw2DvBgPm3nOGKpF/eW5J79WrFytXruTcuXM8//zzvPLKK4SEhLBlyxZq1Mjf9GDffPMN/v7+2NnZ0apVK/bt25fjth06dECn09316NmzZ77OXaSiQ+DoErV8xwXxdgeDb7A2MAy9Dt7oXqeIghNCCCEKz/jx4wkODiY5OZm9e/fSqlWrzPe2bdvGnDlzsmzfpk0b9uzZQ1JSEufPn+fNN9/Mcfo1kQ91e4HOAKFH4Pr5u962szbwXp/6fP9kU5ztrDh8+SY9Zu5gzbHQWxulJsHGd9TyAy+BS6X8x1O1HdTvD2hSRE6I4mr/L3BoLqCDfj+Dq8yiUVjyNQVbz549+ffff4mPj+fChQsMHDiQV199lUaNGuX5WIsXL2bixIlMnjyZQ4cO0ahRI7p27UpERPZjoJYvX05oaGjmIzAwEIPBUDIqy+/5FkypUOVBqNQ82000TWPampMA9G9WiTreUvhGCCGEEGbm6K4SY7iry/vtutX3YfWLD9G0siuxSWk8P/8Qb604RlKqUX2vuXkJnHzhgftMuZYbj3wANk4QcgD++63gxxNCmM+B2bB6olru+BbU6GTZeEq5fM+Tvn37doYPH46vry/Tp0/n4YcfZs+ePXk+zhdffMGYMWMYMWIE9erV4/vvv8fBwYHZs2dnu72bmxve3t6Zj40bN+Lg4FD8k/TEG3Bwjlp+cEKOm60/HsbB4BvYWeuZ2KV2kYQmhBBCiDIomyrv2fFzc2Dxs20Y26E6APP3XmLE139j2v652qDzFLBxLHg8zj7QMb02waYpkBBV8GMKIQpu7w/wd3ov4FZjod2rlo2nDMhTkh4WFsbHH39MzZo1GTBgAM7OziQnJ7Ny5Uo+/vhjWrTIW7GQlJQUDh48SOfOnW8FpNfTuXNndu/enatj/PLLLwwePBhHx+wvDsnJycTExGR5WMT+X9TUJJ4BUKNztpukGk18su40AKMfrIa3i11RRiiEEEKIsqRuL9BbQdgxiDx3z02tDXpe71aHeSNb4l7Ohj5Rs9GnxnPdtQFaXqZcu5+Wz4BnPUiMgs1TzXdcIUT+7PpajUMHVfS6Wx5ncBD5kuskvVevXtSuXZujR48yY8YMrl69ytdff12gk0dGRmI0GjMLx2Tw8vIiLCzsvvvv27ePwMBARo8eneM2H330ES4uLpkPPz8LjJ1ITYS936vlB17K8T/2ttPXCIqMp4KjDc+2r1aEAQohhBCizHFwg2od1PJ9WtMztKvlwYbBrgy0+geAMeH9mLDkKHHJaeaJyWANPaer5YNz4cpB8xxXCJF3O6bDhrfV8kOvQpf3JEEvIrlO0teuXcuoUaOYOnUqPXv2LBbFW3755RcaNGhAy5Ytc9xm0qRJREdHZz4uX75chBGmO7wA4q+Bix/UfzzHzY6FRAPwcB1PnOysiyo6IYQQQpRVuezynknTcNsxBT0aZzy7ckRXmz8PX+XRmTs4diXaPDFVaQsNBwMarHkFTEbzHFcIkTuaBts+hs3vqdcd34JO70iCXoRynaTv3LmT2NhYmjVrRqtWrZg1axaRkZEFOrm7uzsGg4Hw8PAs68PDw/H29r7nvvHx8SxatIhRo0bdcztbW1ucnZ2zPIqUyXhr2rU249Ud4hycClVd8ev6SLE4IYQQQhSBOj1Bbw0Rx+Ha6ftvf/IvCN4JVnbUGjqdxc+0xtfFjovXE3j8u3+ZvTMITdMKHleX98DWGa7+d6umjxCi8GkabHkftqXPf95pMrT/n2VjKoNynaS3bt2an376idDQUJ599lkWLVqEr68vJpOJjRs3Ehsbm+eT29jY0KxZMzZv3py5zmQysXnzZtq0aXPPfZcuXUpycjJPPvlkns9bpE6ughtBYF8emj51z01PhamfYR0fp6KITAghhBBlnX15qN5RLR9fee9t05JvdX1t+yK4+tHc3401Lz3EI/W8SDVqvPf3CcbMO8CN+JSCxeXkBQ+nn2vzexBfsIYhIUQuaJr6Hd+RPuSk6zR4aKJlYyqj8lzd3dHRkZEjR7Jz506OHTvGK6+8wscff4ynpye9e/fOcwATJ07kp59+Yu7cuZw8eZKxY8cSHx/PiBEjABg2bBiTJk26a79ffvmFvn37UqFChTyfs8hoGuycoZZbPnPPyqdxyWlcikoAkGnXhBBCCFF0ctvlfc93cDMYnHxUjZ10rg42/PBUM6b2DsDGoGfTyQh6zNzBvqACVmdvPgq8GkDSTdg0uWDHEkLcm6bB2tdh9yz1usfn0GacZWMqw/I9BRtA7dq1+fTTT7ly5QoLFy7M1zEGDRrE559/zrvvvkvjxo05fPgw69atyywmd+nSJUJDQ7Psc/r0aXbu3Hnfru4WF/QPhB4GK3to+ew9Nz2d3oru5WyLm6NNEQQnhBBCCAHU7gEGG7h2EiJOZr9NXARkTLnWaTLYlsvytk6nY3hbf5Y/35aq7o6ERicx+MfdzNx8FqMpn93fDVa3isj99ztc3pe/4wgh7s1kUlOs7fsB0MGjM6DlGEtHVaYVKEnPYDAY6Nu3L6tWrcrX/uPHjyc4OJjk5GT27t1Lq1atMt/btm0bc+bMybJ97dq10TSNLl26FCTswpfRit70KXC8d4v/yfTx6NKKLoQQQogiZe8K1Tup5Zxa07d8ACmx4NsUGg7K8VD1K7rw1wsP8niTipg0+GLjGZ76ZS8RMUn5i61yK2icPrRx9UQpIieEuZmMsOoFOPgroIM+30DzEZaOqswzS5IushF6BC5sBZ1BFYy7j1NhUjROCCGEEBZye5f3Owu/hR6FQ/PUcrePQX/vr4/lbK34YlBjpg9ohIONgV3nr9P9qx38ey6f48o7TwE7FzWf+/5f8ncMIcTdjGmwciwc/h10enj8R2jyhKWjEkiSXnj+/Uo9BzwG5avcd/NToaq7e10pGieEEEKIola7OxhsIfIMRJy4tV7TYP2bgAb1+6mW7Vzq16wSf73wIHV9nLken8LTv+5j1ZGreY+tnAd0elctb/lAdb0XQhSMMRWWj4Gji1WjYv/Z0HCgpaMS6SRJLwxRQbe6i91WWCUnmqbdquwu3d2FEEIIUdTsnKFGZ7V8e5f3U6vh4g6wslMt2nlU3aMcK55vS8+GPqQaNV5a9B9z/g3Ke3zNRoBPI0iOho3v5n3/25lMcOMinF6rqlj/MRq+ewB+6Qox+biJICAhCpY/o36WqYmWjkbcT1oKLH0aji9XUzAOnHerN40oFqwsHUCptHsWaCY1vsun4X03v3IjkbjkNKwNOqp55FwBXgghhBCi0AQ8BqdXqyS941tgTLltyrUXwLVyvg5rZ23g68FNcHe0Ye7uYKb8dYLr8SlM7FILnU6Xu4PoDdDzC/i5MxxZCE2HQZW2995H01Sre8QJVRAv4/naKUiJy36fub3g6dXg5J23D1mWXT0MS56Cm5fU67RkGDD3vsMihIWkJcOSYXBmnSoYOeh3qNXV0lGJO0iSbm7xkaoCKcCDE3K1S0Yreg1PJ6wN8gdNCCGEEBZQu5vq8n79HIQHwvmtcCMIynnDAxMKdGi9XseU3gFUKGfLFxvP8PWWc0TGpfBB3/oY9LlM1Cs1V8n5obmw+lV4druqAA+QeFMl3+HH0xPy9KQ8MYdp4Aw24F4LPOuBZ11wqwob3lWffW5vePpvKOdZoM9cJhxeCH9PgLQkcKkMcWFwcpWaMu+R9y0dnbhTaiIsegLOb1a9YwYvgBqdLB2VyIYk6ea29wf1h8q3Cfg/lKtdMiq7y3h0IYQQQliMrRPU7AKn/oZ9P8LxlWp957unXMsPnU7Hi51q4l7OlrdXHmPhvktExSfz1eAm2FkbcneQTpNVEhhxXLXeGlNUQh4TksNJ9eBWTSXiGQm5Zz21zmCddVufxjDnUYg8rRL14X+p8fDibmkpqlbB/p/U65qPqKJjZzeqcc67ZqobH81HWjbOkiQtGS7vVWPFPWqDc0XIbU+T3EiJh4WDIWg7WDvAkEVQrb35ji/MSpJ0c0qOUxc1UHecc/mLlVnZXcajCyGEEMKS6j+ukvSMau4+jaHhYLOeYmiryrg5WvPiosOsPx7O8Nn7+Gl4c5ztrO+/s2MFlaj/PQFOr8n6nnOl9CT8toTcozZY2+cuMLeqMHyVStSvnYR5fVSifp9pdMucmFBYOlwllADt34D2r6vu7Q0HqvH+Wz9UvR1cKkPNzhYNt1iLCoJzm9QjaDukJtx6z6ac6u3hUfvWs0cdcK1yqwdJbiXHwoJBEPyvOu4TS+8/XERYlCTp5nRoHiTdBLfqULdXrnfLqOxeR1rShRBCCGFJNbuClT2kpRf/ysWUa/nRrb4Pc0fY8My8A+wNimLQD3uYO7IFnk5299+56XA11jwhMj0hDwDPOmqatoKqUF0l5nN6qtb6eX1U4u7gVvBjlwbBu1WCHhcOti6q9bx2t6zbtHtNJZ9HFqjiZCPXgXd9i4Rb7KQmQfBOOLsJzm1UwytuV85bFXGMuqDqJlw9pB63M9hAhRrpiXsd8KgF7rXVOutsfn+SouH3/nBlH9g6w5N/gF/LwvuMwiwkSTcXYyrs/kYtt31BFTjJhcQUI0HX4wGp7C6EEEIIC7Mtp4pInVipCslVaVNop2pTvQKLnm3N8Nn7ORkaQ//vdjNvZEv83e9TRFevhw6vF1pcuNe4laiHH4Pf+sKwP8G+fOGds7jTNNVbdP2bYEpTPRUG/a5uatxJp4NeX0H0ZTUzwIKBMHozOPsUfdzFQdSFW0l50I5bN8BATX1WubWaWaFmF/Cqr35+aSmqHsS1U3DtjBqCce00RJ5V+0ecyDpVIqihHeX9VcKekbi7VYMNb0HIQXUT66kVULFZkX58kT86TdM0SwdRlGJiYnBxcSE6OhpnZzMmxUcWwYpnwdETJhzL/k5Wdrtdvkmfb/7FvZwNB97uYr54hBBClBiFdm0qw+RnWgDRIaoVtMXoIklMg6/HM2z2PoKvJ+BezoY5I1pSv6IZWsULKuKUStQTIlWtoadWgr2rpaMqeikJ8PfLcHSRel2/H/T+GmzuczMl8Qb88ghEngHvhjBirVlqGxR7qYlwcacan39uo0rSb+fkq4YA1OgM1TrkrQeIyQTRl25L3G9L4pOic97P3g2GrVTTGAqLyct1SVrSzUHT4N+v1HLr53KdoMOtonHSii6EEEKIYsGlouqyXESqVHBk2XNtGT57HydCYxj84x5+fKoZbWu4F1kM2fKso1rU5z4KV/+D3/uplki7MvSdLSoIFj+lehToDKpie+vnc1d3yb68Gvv8c2cIOwrLRqpq4nkdT10SXD9/Kym/uFMVkc6gt4LKbW61lnvWy39BOH16a3l5f6j1yK31GdMNXjulbopcO32r9d3RQw1L8AooyCcURawU/pZYwNkNqsuJjRM0H5WnXTOmX5PK7kIIIYQoqzycbFn0bGuemXeAPReiePrX/cwY3JgeDSzcRdqrnurqPrcXhByA+f3VmF7bIvzelngTtn8GR5eo4mENBkC93oXfy+HsJvhjlKq35OgB/X+FqrmbuShTeX9VRXxOTzi7Hta9AT0+M2/VcktIilHJ+IWtKjm/EZT1feeKt5Lyqu0L/8aOTgdOXuohFdtLBUnSzWHnDPXc/Ok8d4OSlnQhhBBCCHC2s2bOiJa8vPgwawPDGLfgEO/3qc+TratYNjDvBrcS9ct7Yf4AeGJZ4XfdNhlVUeItH6gu9wDxEWqc9+pXVALYoD/U6g42DmY8rwl2ToctHwIaVGwOA+epHhb5Uam5asldMlxN2eZWDdo8b754i4IxFa4cUEn5hW1qWTPeel9vreo31OiiknPPuiX/RoSwKEnSC+ryPri0S/1yts7bHxxN0zJb0qWyuxBCCCHKOjtrA7OGNuXdPwOZv/cSb68MJDIumZc61URnyaTHp5Eakz6vL1zarYqhPbH0/uOy8ytoB6ybpLqZg6rk3fFNNb3ZsWUQHqimoDu9Bqwdoe6jUL8/VO949/zveZEUDSvGwunV6nWzEdD9E7CyLdjnqdcHurwHG99RxedcK6uYiytNU13FM5LyiztVtfXbuVVXY8prdIKq7Yq2d4Uo9SRJL6iMsegNB4Gzb552DYtJIjoxFYNeRw3PMlBIQwghhBDiPgx6HR/0rY97OVu+2nyWGZvOcj0uhSm9AzDoLZioV2yqxqT/1lfNN71gEAxdYt5W7BsXYcM7cHKVem3nAh3ehBajbiXfD74M4ScgcJlK2G8Gw9HF6mHvpqryNxgAfq3yNn1exClY/ISaFsxgCz0/h6bDzPfZ2r6guoUfmA1/jIYRq4tXpfHYMJWQZzxiQ7O+71BBdV2v3lEl566Viz5GUWZIdfeCuHYGvmkJaDBunxonlAdbToUzcs4BanmVY8PLMn5ECCHKKqlEbn7yMy0dftt9kXdXHUfToGcDH74Y1Ahbq9xNc1toLu+D3x5TLavVOqgx19b2BTtmcizs+EJN52tMVtNpNR+pEnTHCjnvp2mq6/WxpXB8OcRfu/Wei5+qxN6g/62pvXJyfCWsfB5S48G5EgyaVzgJtDENFg5WBdYcPWH0JihvoeEMyXHqZsuFbXB+K1w7mfV9KztV8C0jKfdqkLebHkLcQaq7F5VdXwEa1O6Z5wQd4GRoRtE4+fIghBBCCHGnp9r4U97RhpcXH2b1sVBuJKTww1PNcLIrQJfugvJrqcak/95PJXiLn4RB8/M0u08mk0lNbbZpKsSFqXVV20O3j3JXjVunA78W6tF1GlzcrlrXT6xS85T/O0M9POqoZL1+f3Cremt/Yxpsngq7Zqafu50qEOdYSJX1DVYw4FeY3V115V8wEEauL5qp7UwmNV/4ha0qKb+yT835nkmnhjVkJOV+rfP3byqEGUhLekGc3QQ7v4BOk6Fyqzzv/sLC//jryFVe71aHsR2qFywWIYQQJZa0+pqf/ExLl3/PRfLMvAPEpxipX9GZX59uiYdTAcdJF9TFf1W199QEqNkVBv2Wt7Hbl/fB2tfh6iH1unxV6Poh1O5R8KJjqYlq9qFjS+HMBtU6n6Fic9Udvlp7df6gf9T6ti+q77RFMUVadAj83El1Ka/aXt30sLIpnHMlx8GRhbD3e9WV/3auVW4l5VXbg4Nb4cQgBHm7LkmSbkFdvviHsxFx/DqiBR1re1o0FiGEEJZTnK5NpYX8TEufY1eiefrXfVyPT8G/ggPzRraicgUzjgfPj6Adqtp7WqKqsj5w3v2TzegQ2DRZJdCgpvBt9yq0HlvwAm3ZSYqGk3+r8wX9A5op6/vWjtD3GzWWvSiFHlEt6qnx0PhJ6DPLvBXRb1yEfT/Bod8gOVqts3GCGg+rpLxax6y9CoQoZJKk30NxuWgnpRoJmLweo0ljz6ROeLtIdxohhCirisu1qTSRn2npFBQZz1O/7OXKjUScbK2Y0KUWw9pUwdpgwbHCF7apInJpSVDnURgwJ/sK6ykJsOtr2PmlSurRQZMn4eF31PzWRSEuAo6vUAn7lf1QoQYM+l1NGWYJZzbAwkHqxsHD76ibFQWhaaoS+97vVeX7jBsSbtWh1bPQeKhUYRcWI0n6PRSXi3ZgSDSPfr0TVwdr/nuni2WnFRFCCGFRxeXaVJrIz7T0iohJYsxvBzly+SYANTzLMaVXAA/WLKRx1LlxbjMsHKK6ldftDf1n30rUNQ0C/4CNkyHmilpXuQ10+xh8G1ssZGLD1Vjwwmi9z4t9P8Ga9OS83y9q7HxepSaqsfh7v1fT02Wo1lH1UKjRRYq+CYuTwnElwMnQGADqejtLgi6EEEIIkUueznYsH9uWpQcu8+n605yLiOPJX/bSLcCbt3rWxc/NAl3ga3RSLdKLn1DTpy1/Bh7/SRVHW/sGXN6jtnPxU/OFBzxm3q7d+VFUrff303KM6pq+exasHAvOFaFKm9ztGxMK+3+Gg79CwnW1zsoeGg2GVs+BZ51CC1uIwiRJuoWcClOV3ev4SJcbIYQQQoi8MOh1DG5Zme71ffhy0xl+2xPMuuNhbD0dwbPtqzO2fXXsbYp4qrZaj6gx6YufUtOhXTsFEScBDawd1PzmbV8o+HRtpVGX91WifupvWDQERm+GCvcoqnx5v2o1P7HyVoV250oq4W86TArAiRJP+n1YyKmwWy3pQgghhBAi71wcrJnSO4DVLz5Im2oVSE4zMXPzWTp/8Q9rj4VS5KM6a3dXY9L1VhBxAtCg4SAYfwDa/08S9Jzo9arngW9TSLyhqubHX8+6jTFVdWn/6WH4pTMELlMJeuW2MGAuvHQEHpwgCbooFaQl3QI0TcucI11a0oUQQgghCqaOtzMLxrRibWAYH64+ScjNRMbOP0Tb6hWY0juAWl5F+H2r7qMwZLEqztZitJrDXNyfjQMMXQw/dYKoC7BoKAz7E1LiVHf2/b+oKdsADDZQ///t3XtcVHX+P/DXmYGZ4X6H4TKAV7yjoSJeKpW8taVdqXXVzGxz1bXYvl91NyXru9HtZ+2Wabmiu1/7pt20i4YZiqWilKihAnlB7sNF5S4MzJzfH8AkCSgKc84Mr+fjMQ+ZM59z5v2Zz9C7N59zPuehplPapbyun6ibcOE4CZRU1WH035OgEIDTa6ZZ/nQsIiKSFTnkJlvDz7TnumowYv2B89hw4DwMjSYoFQLmjAnBc/f0h5tDG6uuk7yUZAKbpjTdNs13cNO9zVvu8+7sB4xcAIycDzjz9sVkXTqTl3i6uwRaZtFDvZ1YoBMRERF1IQeVErH39EdS7F2YNlgLo0nElsMXMfHNZGxLzYXR1KPmp6yP7wAg5j/NlwycbirQA0YAD3wAPHsKuHs5C3SyeSzSJZDZsrK7P/+yT0REPcO6desQGhoKjUaDyMhIpKam3tR+27ZtgyAImDVrVvcGSDZH5+mIDXMi8L8LRqOvrzMu1xiw4vN0zFp3CGm5V6QOjzrS+24g5sOmWfMn9wAL9wPhMYCdSurIiCyCRboEWlZ2H6jl9ehERGT7tm/fjtjYWMTFxSEtLQ3h4eGYOnUqSkpKOtzv4sWLeP755zFhwgQLRUq2aEI/H3yzbAJW/W4QXNR2SC+owIPvHcZfPj6Jkqo6qcOj9oRNA363FggeI/3t6ogsjEW6BFrukT6AK7sTEVEPsHbtWixcuBDz58/HoEGDsGHDBjg6OiIhIaHdfYxGI2bPno01a9agd+/eFoyWbJG9UoEF43th3/N349GRQQCAz9LyMenNA/jg+6Zr14mI5IJFuoUZGk04X1oNgCu7ExGR7TMYDDh27Biio6PN2xQKBaKjo5GSktLufi+99BJ8fX2xYMGCm3qf+vp6VFZWtnoQ/ZaPixqvPxyOnYvHIVznjur6RryyOxPT/vE99p4pRoORxToRSY+3YLOw86XVaDCKcNHYIdCd98okIiLbVlZWBqPRCD8/v1bb/fz8kJmZ2eY+Bw8exKZNm3DixImbfp/4+HisWbPmdkKlHmS4zh07Fo3FZ2n5eC0xExdKa7DwPz/B3dEe0QP9MH2IFuP7eUNtxwV+icjyWKRbWKa+edE4rSsEXl9DRETUSlVVFebMmYONGzfC29v7pvdbuXIlYmNjzc8rKyuh0+m6I0SyEQqFgEdG6jB1iBbr9p3Dp8fycanGgE+P5ePTY/lwVtth4gBfTB+ixd1hPnBU8X+bicgy+F8bC8tsvv0aT3UnIqKewNvbG0qlEsXFxa22FxcXQ6vVXtf+/PnzuHjxIu677z7zNpOp6RRkOzs7ZGVloU+fPtftp1aroVaruzh66glcNfZYOWMg/nvaAPx48TIST+mReEoPfWUdvjpZiK9OFkJtp8Bd/X0wfagWkwb48X7rRNStWKRbWEbzyu5cNI6IiHoClUqFiIgIJCUlmW+jZjKZkJSUhCVLllzXfsCAAUhPT2+17YUXXkBVVRX+8Y9/cHacuo1SIWBMby+M6e2F1b8bhJP55Ug8pcc3p/TIvVyLb88U49szxbBXChjbxxvThmgxZZAfvJz5xyEi6los0i2s5R7pnEknIqKeIjY2FvPmzcPIkSMxevRovP3226ipqcH8+fMBAHPnzkVgYCDi4+Oh0WgwZMiQVvu7u7sDwHXbibqLQiFgRLAHRgR7YMX0AcgoqkLiqSJ8c0qPsyXVOPBLKQ78Uoq/7UjH6F6emDZYi2lD/KF100gdOhHZABbpFnSpuh4lVfUQBCDMj0U6ERH1DDExMSgtLcXq1auh1+sxfPhwJCYmmheTy83NhULBG86QPAmCgEEBrhgU4IrYKWE4V1KNPaf1+OZUEU4VVOLIhcs4cuEyXvzqDEYEu2PaYC2mD/FHsJej1KETkZUSRFEUpQ7CkiorK+Hm5oaKigq4ulr2lPND58ow+19HEerliOT/mmjR9yYiIvmSMjfZKn6mZAl5l2ubC3Y9juVcafXa0EA3rJk5GHcEe0gUHRHJSWfyEv9sbUEZLae683p0IiIiIqun83TEUxN647NFY3H0r5Px8szBGNvHC0qFgPSCCjy6IQWbDmajh82JEdFtYpFuQZl6ruxOREREZIv8XDWYExWK/1s4Bql/nYx7h/qj0STi5a/PYNHWNFTWNUgdIhFZCRbpFtRyj3TOpBMRERHZLi9nNd79/QisuX8w7JUCEk/rcd87B3GqoELq0IjICrBIt5BGowm/FFcDAAZyJp2IiIjIpgmCgHljQ/HJM2MR6O6AnEu1eHD9Yfzf0Vye/k5EHWKRbiHZZTUwNJrgpFJC58HVPomIiIh6guE6d+z683hMHuALQ6MJf92RjtiPT6KmvlHq0IhIplikW0hG8/XoYVoXKBSCxNEQERERkaW4O6qwce5IrJg+AEqFgB3HCzBz3SGcLa6SOjQikiEW6RaS2bKyuz+vRyciIiLqaRQKAc/c1Qf/91QkfF3UOFdSjfvfPYQdx/OlDo2IZIZFuoW0rOw+UMvr0YmIiIh6qsjeXti9bALG9fXC1QYjntt+Eis/T0ddg1Hq0IhIJlikWwhn0omIiIgIALyd1fjPk5FYNrkfBAH4KDUXD753GBfLaqQOjYhkgEW6BZTXGlBYUQeg6Zp0IiIiIurZlAoBz93TH/+ePxqeTiqcKarEfe8cxDfpRVKHRkQSY5FuAS2nugd5OMBVYy9xNEREREQkF3f298HuP0/AyBAPVNU3YtGHaVjz1WkYGk1Sh0ZEEmGRbgHmU921PNWdiIiIiFrTumnw0dNj8Mc7ewMANh+6iEffT0FB+VWJIyMiKbBItwDzonH+PNWdiIiIiK5nr1Rg5YyB2Dh3JFw1djiRV457//kD9meWSB0aEVmY5EX6unXrEBoaCo1Gg8jISKSmpnbYvry8HIsXL4a/vz/UajX69++P3bt3WyjaW9Nyj3TOpBMRERFRR+4Z5Iddf56AYUFuKK9twPwtP+L1xEw0Gnn6O1FPIWmRvn37dsTGxiIuLg5paWkIDw/H1KlTUVLS9l8MDQYD7rnnHly8eBGffvopsrKysHHjRgQGBlo48ptnNInI0res7M6ZdCIiIiLqmM7TEZ88E4W5USEAgPeSz2P2v44iq3nih4hsm52Ub7527VosXLgQ8+fPBwBs2LABu3btQkJCAlasWHFd+4SEBFy+fBmHDx+GvX3TAmyhoaGWDLnTci7VoK7BBI29AqFeTlKHQ0RERERWQG2nxEszh2BUqCdWfPYzjmZfxtS3v8fgAFc8MCIQ9w8PgK+LRuowiagbSDaTbjAYcOzYMURHR/8ajEKB6OhopKSktLnPl19+iaioKCxevBh+fn4YMmQIXnnlFRiNxnbfp76+HpWVla0eltRyPXqYnwuUCsGi701ERERE1u2+8AB8uXQ8pgzyg71SwOnCSvzPrgxExe/DE5tT8cWJAlw1tP//wkRkfSSbSS8rK4PRaISfn1+r7X5+fsjMzGxznwsXLmDfvn2YPXs2du/ejXPnzuFPf/oTGhoaEBcX1+Y+8fHxWLNmTZfHf7O4sjsRERER3Y4+Ps74YO5IXKkx4OufC/H58QIczy1HclYpkrNK4ay2w/QhWjxwRyDG9PKCghNDRFZN0tPdO8tkMsHX1xcffPABlEolIiIiUFBQgDfeeKPdIn3lypWIjY01P6+srIROp7NUyL8uGsfr0YmIiIjoNng4qTAnKhRzokKRXVaDHWn52HGiAHmXr+KTY/n45Fg+Atw0mDkiEA+OCEQ/P/7/J5E1kqxI9/b2hlKpRHFxcavtxcXF0Gq1be7j7+8Pe3t7KJVK87aBAwdCr9fDYDBApVJdt49arYZare7a4DshU8+ZdCIiIiLqWr28nRA7JQzP3dMfP+Vcwedp+fj65yIUVtRhffJ5rE8+j6GBbubr172dpfv/YSLqHMmuSVepVIiIiEBSUpJ5m8lkQlJSEqKiotrcZ9y4cTh37hxMpl9vQfHLL7/A39+/zQJdalV1Dci7fBUA75FORERERF1PEASMCvVE/IPD8OPfovHe7DsQPdAXdgoB6QUVeOnrM4h8JQlPbvkRX50sRF0Dr18nkjtJT3ePjY3FvHnzMHLkSIwePRpvv/02ampqzKu9z507F4GBgYiPjwcALFq0CO+++y6WLVuGpUuX4uzZs3jllVfw5z//WcputKvlNhn+bhq4O8rvjwhEREREZDs09krMGOqPGUP9cam6Hl//XITPjxfgZF459mWWYF9mCVzUdpgx1B8P3BGI0aGevH6dSIYkLdJjYmJQWlqK1atXQ6/XY/jw4UhMTDQvJpebmwuF4tfJfp1Ohz179uC5557DsGHDEBgYiGXLlmH58uVSdaFD5uvRtZxFJyIiIiLL8XJWY97YUMwbG4pzJdXYebwAO44XoKD8Krb/lIftP+VB5+mAmJE6PByhg9aNt3MjkgtBFEVR6iAsqbKyEm5ubqioqICra/deJ/63Hen48GguFt3dB8unDejW9yIiIutlydzUU/AzJbqeySQi9eJl7EgrwO70IlTVNwIAFAJwd5gvYkbpMGmAL+yVkl0RS2SzOpOXrGp1d2uTyZl0IiIiIpIJhULAmN5eGNPbCy/ePxjfnCrCth/zkJp92Xw6vLezGg9HBCFmlA69vJ2kDpmoR2KR3k1MJtF8j/SB/vwLPhERERHJh4NKiQfvCMKDdwThfGk1Pv4pD58dy0dZdT02HDiPDQfOY3QvTzw2SofpQ/zhoFLe+KBE1CVYpHeT/CtXUWMwQqVUoDf/CklEREREMtXHxxkrpw/E81PCkJRRgo9/ykNyVglSsy8jNfsy4r48jVnDAxEzSochgW5Sh0tk81ikd5OM5vuj9/Nzhh2v6yEiIiIimbNXKjBtiBbThmhRVHEVn/6Uj+0/5SH/ylX875Ec/O+RHAwOcMVjo3S4f3gg3BzspQ6ZyCaxeuwmmUUt16PzVHciIiIisi7+bg5YOrkfvv+vidi6IBK/G+YPlVKB04WVWPXFaYz++3eI3X4CRy9cQg9bh5qo23EmvZtk6luuR+eicURERERknRQKAeP7eWN8P29crjFgx/ECbP8xF78UV+Pz4wX4/HgBenk74dGROjwUEQhfF97Kjeh2sUjvJhnNi8ZxJp2IiIiIbIGnkwoLxvfCk+NCcSKvHNt/zMOXJwuRXVaD1xIz8f++zcLUwVrMjgxGVB8vCIIgdchEVolFejeoqW9EzuVaAMAAzqQTERERkQ0RBAEjgj0wItgDL/xuEHb9XIiPUvNwIq8cu9KLsCu9CL29nfD7yGA8HBEEd0eV1CETWRUW6d3gl+IqiCLg46KGt7Na6nCIiIiIiLqFs9oOMaOCETMqGGcKK/Hh0RzsPF6AC2U1+J9dGXhjTxZ+NywAfxgTjOE6d86uE90EFundIFPfsmgcZ9GJiIiIqGcYFOCKvz8wFCtnDMTO4wXYeiQHmfoqfJaWj8/S8jHI3xWzxwRj1vBAOKlZhhC1h6u7d4PMopZF43g9OhERERH1LM5qO/xhTAi+WTYBny0aiwfvCITKToEzRZX4245TiHwlCS/sTDev4URErfFPWN0ggzPpRERERNTDCYKAiBAPRIR4YNW9g/BZWj4+PJqL7LIabD2Si61HchER4oHZkcGYMdQfGnul1CETyQKL9C4miiJXdiciIiIiuoaHkwpPTeiNBeN74fD5S/jwaA6+PV2MYzlXcCznCl76+gweiQjC7yND0MvbSepwiSTF0927WGFFHarqGmGnENDX11nqcIiIiGRh3bp1CA0NhUajQWRkJFJTU9ttu3HjRkyYMAEeHh7w8PBAdHR0h+2JyHoIgoBxfb3x3uwIHF4xCX+5pz8C3DQor23Axh+yMfHNZPzhX0eReKoIDUaT1OESSYJFehdruR69r68zVHb8eImIiLZv347Y2FjExcUhLS0N4eHhmDp1KkpKStpsn5ycjMcffxz79+9HSkoKdDodpkyZgoKCAgtHTkTdyddVg6WT++GH5ZPwr7kjMTHMB4IAHDxXhme2pmH8a/vwXvI5VFxtkDpUIosSRFEUpQ7CkiorK+Hm5oaKigq4unb96ejr9p/DG3uyMGt4AN5+bESXH5+IiGxPd+cmqUVGRmLUqFF49913AQAmkwk6nQ5Lly7FihUrbri/0WiEh4cH3n33XcydO/em3tPWP1MiW5V3uRYfpebi45/yUFZtAAA4qZR4bHQwnhzfC4HuDhJHSHRrOpOXONXbxczXo3NldyIiIhgMBhw7dgzR0dHmbQqFAtHR0UhJSbmpY9TW1qKhoQGenp7ttqmvr0dlZWWrBxFZH52nI/572gAcXjEZbz4SjjA/F9QYjNh0MBt3vr4fz247jtOFFVKHSdStWKR3sV8XjePK7kRERGVlZTAajfDz82u13c/PD3q9/qaOsXz5cgQEBLQq9H8rPj4ebm5u5odOp7utuIlIWio7BR6OCELisxOwef4ojO3jBaNJxM4Thbj3nwfxh38dxfe/lKKHnRRMPQRXd+9CdQ1GZJfVAAAGcSadiIjotr366qvYtm0bkpOTodFo2m23cuVKxMbGmp9XVlayUCeyAYIgYGKYLyaG+SI9vwIf/HABu9OLcPBcGQ6eK8MArQuevrM37gsPgL2S849kG/hN7kJni6thEgFPJxV8XNRSh0NERCQ5b29vKJVKFBcXt9peXFwMrVbb4b5vvvkmXn31VXz77bcYNmxYh23VajVcXV1bPYjItgwNcsM7j49A8vN3Y/64UDiqlMjUVyH245O48/X92Pj9BVTVcZE5sn4s0rtQhv7XU90FQZA4GiIiIumpVCpEREQgKSnJvM1kMiEpKQlRUVHt7vf666/j5ZdfRmJiIkaOHGmJUInISug8HRF332AcXjEJ/zU1DN7OahRV1OHvuzMwNn4f4r/JgL6iTuowiW4Zi/QulFlUBQAYoOVf74mIiFrExsZi48aN+Pe//42MjAwsWrQINTU1mD9/PgBg7ty5WLlypbn9a6+9hlWrViEhIQGhoaHQ6/XQ6/Worq6WqgtEJEPujiosntgXB5dPxGsPDUUfHydU1Tfi/QMXMOH1ffjLxyeRpa+SOkyiTuM16V3o15XduWgcERFRi5iYGJSWlmL16tXQ6/UYPnw4EhMTzYvJ5ebmQqH4dd5g/fr1MBgMePjhh1sdJy4uDi+++KIlQyciK6CxVyJmVDAeidBhX2YJPvjhAlKzL+OztHx8lpaPu/r74I939kZUHy+e7UpWgfdJ7yKiKOKOl/fiSm0DvloyHkOD3Lrs2EREZNt4T++ux8+UqGc7nnsFG3+4gMRTepiaq53BAa64s78Phga6YUiAG3SeDizayWI6k5c4k95FSqrqcaW2AQoB6OfnLHU4REREREQ91ohgD7w3OwI5l2rwrx+y8cmxPJwurMTpwkpzGxeNHYYEuGFIoCuGBLphcIAbenk7Qalg4U7SYpHeRVpOde/t4wyNvVLiaIiIiIiIKMTLCS/PGoLn7umPxFN6pBdU4HRhBTKLqlBV14iUC5eQcuGSub2jSolB/i1Fe9O/fX2deXs3sigW6V0kU9+yaByvRyciIiIikhNPJxV+Hxlsft5gNOFscTVOFVbgdEEFThVW4kxhJWoNRvyUcwU/5Vwxt1XZKTBQ64LBzafJDwl0RX8/F07MUbdhkd5FMptn0gf687o3IiIiIiI5s1cqMCjAFYMCXIGROgCA0SQiu6wapwoqcaqgormAr0RVfSNO5lfgZH6FeX87hYB+fi6ICHHH2D7eGNPbC55OKqm6QzaGRXoXySjiTDoRERERkbVSKgT09XVBX18XzBoRCAAwmUTkXanFqYJK86nypwoqcKW2ARlFlcgoqsTWI7kAmuqAsX28EdXHC6N7ecLNwV7K7pAVY5HeBeobjThf2nTvVs6kExERERHZBoVCQIiXE0K8nHDvMH8ATXd1Kqyow8955TiafRkp5y8hq7gKmfqmR8KhbCgEYEigG6L6eGFsH2+MCvWAo4qlF90cflO6wPmSGjSaRLhq7ODvppE6HCIiIiIi6iaCICDQ3QGB7g6YPrSpcC+tqseR5kXoUs5fQnZZDX7Or8DP+RV4/8AF2CkEDNe5I6qPF6L6eOGOYA9e007tYpHeBTL1TdejD/B35b0WiYiIiIh6GB8XNe4LD8B94QEAgKKKq0g531SwHz5/CQXlV80L0r2z7xxUdgpEBHs0z7R7YViQO1R2XEGemrBI7wItK7sP5PXoREREREQ9nr+bAx68IwgP3hEEURSRd/kqUi6U4XBz4V5SVW++/dvavYCDvRKjenmiv68znNR2cFIr4aiyg7PaDo4qJZya/3VW28FRbQen5m28NZxtYpHeBVrukT6A16MTEREREdE1BEFAsJcjgr2CETMqGKIo4nxpTfOp8WU4cuEyLtcY8P0vpfj+l9JOHVulVMBRrYST6tfC/toC39dVjTv7+WBUqCdn6q0Ii/Qu0LKyOxeNIyIiIiKijgiCgL6+zujr64w5Y0JgMonIKq5CyvlLKK6sQ42hETX1RtTUN6LWYGx+3rSt1tCIGoMRhkYTAMBgNMFQa0J5bUO77/f+gQtwUikxvp83Job54u4wX2i5jpassUi/TaVV9SirrocgAP39nKUOh4iIiIiIrIhCIWCgv2unJvwajCbU1jcV8LWGRlTXG1Fb31TA115T5GcVVyE5qxRl1fXYc7oYe04XA2iaXJwY5oOJA3wxQucOO542Lyss0m9TVvP16KFeTrytAhERERERdTt7pQJujgq4Od74Xuwmk4jThZXYn1WC/VklOJFXbr7H+3vJ5+HmYI87+/tgYpgP7urvAy9ntQV6QB1hVXmbzCu7c9E4IiIiIiKSGYVCwNAgNwwNcsOfJ/fDpep6fH+2FPszS3Hgl1JUXG3AVycL8dXJQggCMCzIvWmWPcwXQwPdoFDw7lWWxiL9Np1pWTROy+vRiYiIiIhI3ryc1XhgRBAeGBGERqMJJ/PLsT+zFPsyS3CmqBIn88pxMq8cb393Ft7OKtzV3xcTB/hgQl+fm5q5p9vHIv02ZTYvGjfAnzPpRERERERkPeyUCkSEeCIixBPPTw2DvqIOB34pwf7MUhw8V4ayagM+S8vHZ2n5UCoEDAtyQ6C7A7yd1fBxUcPLSQVvZzW8XdTwdm76WWOvlLpbVo9F+m1oMJpwrqQaADCIK7sTEREREZEV07ppEDOq6VZxhkYTfsq5jOSspln2cyXVOJ5bjuO55R0ew1ltZy7YvZr/bXpcW9A3veaitoMg8HT632KRfhuyy2pgMJrgrLZDoLuD1OEQERERERF1CZWdAmP7eGNsH2/8dcZA5F2uRVruFZRVG1BWXY+yqnpcqvn157JqAwxGE6rrG1Fd34iLl2pv6j1c1HZwUCnhqGq6v/u1/zqplXCwb7r3u4NKCUd7JRzVza+pmvZr+bdlm0algEqpsOrin0X6bchovh49TOvCBRWIiIiIiMhm6TwdofN0bPd1URRRVd9oLtgvVTfdqrq0uahvet7yswHV9Y0wNJpwqdEA1HRtrIIAaOyU0Ngr4GCvhMZeCbV96+caewU0dk3bHVqeX9NG3dLOToEJ/XzgoLLcafws0m9DRsv16FzZnYiIiIiIejBBEOCqsYerxh69fW7c/qrBiEs19aipb7q3e63B2Py45uf6RtQ2NP97zes1BiOuGpruE3/V0HRP+KsNRjQYRQCAKAJXG4y42mDEFTTcdt8Or5gEB5XlzpxmkX4btK5qDNe5I1znLnUoREREREREVsNBpUSQqv2Z+VthaDShrtGIOoMRdQ3NPzc0/Xy1oeVnI+pbPb+2XfPzhtb7OaksWzazSL8NT4zrhSfG9ZI6DCIiIiIioh5PZaeAyk4BV4113ypOIXUARERERERERNSERToRERERERGRTLBIJyIiIiIiIpIJFulEREREREREMsEinYiIiIiIiEgmZFGkr1u3DqGhodBoNIiMjERqamq7bbds2QJBEFo9NBqNBaMlIiIiIiIi6h6SF+nbt29HbGws4uLikJaWhvDwcEydOhUlJSXt7uPq6oqioiLzIycnx4IRExEREREREXUPyYv0tWvXYuHChZg/fz4GDRqEDRs2wNHREQkJCe3uIwgCtFqt+eHn52fBiImIiIiIiIi6h6RFusFgwLFjxxAdHW3eplAoEB0djZSUlHb3q66uRkhICHQ6HWbOnInTp0+327a+vh6VlZWtHkRERERERERyJGmRXlZWBqPReN1MuJ+fH/R6fZv7hIWFISEhAV988QW2bt0Kk8mEsWPHIj8/v8328fHxcHNzMz90Ol2X94OIiIiIiIioK0h+untnRUVFYe7cuRg+fDjuuusufP755/Dx8cH777/fZvuVK1eioqLC/MjLy7NwxEREREREREQ3x07KN/f29oZSqURxcXGr7cXFxdBqtTd1DHt7e4wYMQLnzp1r83W1Wg21Wm1+LooiAPC0dyIiko2WnNSSo+j2Md8TEZGcdCbXS1qkq1QqREREICkpCbNmzQIAmEwmJCUlYcmSJTd1DKPRiPT0dMyYMeOm2ldVVQEAT3snIiLZqaqqgpubm9Rh2ATmeyIikqObyfWSFukAEBsbi3nz5mHkyJEYPXo03n77bdTU1GD+/PkAgLlz5yIwMBDx8fEAgJdeegljxoxB3759UV5ejjfeeAM5OTl46qmnbur9AgICkJeXBxcXFwiCcFuxV1ZWQqfTIS8vD66urrd1LKmxL/JjK/0AbKcvttIPwHb6Yiv9EEURVVVVCAgIkDoUm8F8fz1b6QdgO32xlX4A7Isc2Uo/ANvoS2dyveRFekxMDEpLS7F69Wro9XoMHz4ciYmJ5sXkcnNzoVD8eun8lStXsHDhQuj1enh4eCAiIgKHDx/GoEGDbur9FAoFgoKCurQPrq6uVvtl+S32RX5spR+A7fTFVvoB2E5fbKEfnEHvWsz37bOVfgC20xdb6QfAvsiRrfQDsP6+3Gyul7xIB4AlS5a0e3p7cnJyq+dvvfUW3nrrLQtERURERERERGRZVre6OxEREREREZGtYpF+G9RqNeLi4lqtHm+t2Bf5sZV+ALbTF1vpB2A7fbGVfpC82cr3zFb6AdhOX2ylHwD7Ike20g/AtvpyMwSR93shIiIiIiIikgXOpBMRERERERHJBIt0IiIiIiIiIplgkU5EREREREQkEyzSiYiIiIiIiGSCRfoNrFu3DqGhodBoNIiMjERqamqH7T/55BMMGDAAGo0GQ4cOxe7duy0Uafvi4+MxatQouLi4wNfXF7NmzUJWVlaH+2zZsgWCILR6aDQaC0XcvhdffPG6uAYMGNDhPnIck9DQ0Ov6IQgCFi9e3GZ7OY3H999/j/vuuw8BAQEQBAE7d+5s9booili9ejX8/f3h4OCA6OhonD179obH7ezvWlfoqC8NDQ1Yvnw5hg4dCicnJwQEBGDu3LkoLCzs8Ji38h3tzn4AwBNPPHFdTNOmTbvhceU2JgDa/L0RBAFvvPFGu8eUYkzI+lh7vmeul9d4tLDWfM9cz1zfnZjrb4xFege2b9+O2NhYxMXFIS0tDeHh4Zg6dSpKSkrabH/48GE8/vjjWLBgAY4fP45Zs2Zh1qxZOHXqlIUjb+3AgQNYvHgxjhw5gr1796KhoQFTpkxBTU1Nh/u5urqiqKjI/MjJybFQxB0bPHhwq7gOHjzYblu5jsmPP/7Yqg979+4FADzyyCPt7iOX8aipqUF4eDjWrVvX5uuvv/46/vnPf2LDhg04evQonJycMHXqVNTV1bV7zM7+rnWVjvpSW1uLtLQ0rFq1Cmlpafj888+RlZWF+++//4bH7cx3tCvcaEwAYNq0aa1i+uijjzo8phzHBECrPhQVFSEhIQGCIOChhx7q8LiWHhOyLraQ75nr5TUeLaw13zPXM9d3J+b6myBSu0aPHi0uXrzY/NxoNIoBAQFifHx8m+0fffRR8d577221LTIyUvzjH//YrXF2VklJiQhAPHDgQLttNm/eLLq5uVkuqJsUFxcnhoeH33R7axmTZcuWiX369BFNJlObr8t1PACIO3bsMD83mUyiVqsV33jjDfO28vJyUa1Wix999FG7x+ns71p3+G1f2pKamioCEHNyctpt09nvaFdrqx/z5s0TZ86c2anjWMuYzJw5U5w0aVKHbaQeE5I/W8z3zPXyGo8W1pjvmeuvJ3VeYa6/ntRj0tU4k94Og8GAY8eOITo62rxNoVAgOjoaKSkpbe6TkpLSqj0ATJ06td32UqmoqAAAeHp6dtiuuroaISEh0Ol0mDlzJk6fPm2J8G7o7NmzCAgIQO/evTF79mzk5ua229YaxsRgMGDr1q148sknIQhCu+3kOh7Xys7Ohl6vb/WZu7m5ITIyst3P/FZ+16RSUVEBQRDg7u7eYbvOfEctJTk5Gb6+vggLC8OiRYtw6dKldttay5gUFxdj165dWLBgwQ3bynFMSB5sNd8z18trPADbyffM9U3kmFeY6+U3JreKRXo7ysrKYDQa4efn12q7n58f9Hp9m/vo9fpOtZeCyWTCs88+i3HjxmHIkCHttgsLC0NCQgK++OILbN26FSaTCWPHjkV+fr4Fo71eZGQktmzZgsTERKxfvx7Z2dmYMGECqqqq2mxvDWOyc+dOlJeX44knnmi3jVzH47daPtfOfOa38rsmhbq6OixfvhyPP/44XF1d223X2e+oJUybNg3/+c9/kJSUhNdeew0HDhzA9OnTYTQa22xvLWPy73//Gy4uLnjwwQc7bCfHMSH5sMV8z1wvr/FoYSv5nrlennmFuV5+Y3I77KQOgCxr8eLFOHXq1A2v0YiKikJUVJT5+dixYzFw4EC8//77ePnll7s7zHZNnz7d/POwYcMQGRmJkJAQfPzxxzf1FzY52rRpE6ZPn46AgIB228h1PHqKhoYGPProoxBFEevXr++wrRy/o4899pj556FDh2LYsGHo06cPkpOTMXnyZEli6goJCQmYPXv2DRdVkuOYEHUn5np5Yr6XN+Z6eeqpuZ4z6e3w9vaGUqlEcXFxq+3FxcXQarVt7qPVajvV3tKWLFmCr7/+Gvv370dQUFCn9rW3t8eIESNw7ty5boru1ri7u6N///7txiX3McnJycF3332Hp556qlP7yXU8Wj7Xznzmt/K7ZkktSTsnJwd79+7t8C/rbbnRd1QKvXv3hre3d7sxyX1MAOCHH35AVlZWp393AHmOCUnH1vI9c30TuYxHC1vK98z115NjXmGul9+YdAaL9HaoVCpEREQgKSnJvM1kMiEpKanVXzivFRUV1ao9AOzdu7fd9pYiiiKWLFmCHTt2YN++fejVq1enj2E0GpGeng5/f/9uiPDWVVdX4/z58+3GJdcxabF582b4+vri3nvv7dR+ch2PXr16QavVtvrMKysrcfTo0XY/81v5XbOUlqR99uxZfPfdd/Dy8ur0MW70HZVCfn4+Ll261G5Mch6TFps2bUJERATCw8M7va8cx4SkYyv5nrleXuPxW7aU75nrryfHvMJcL78x6RRp162Tt23btolqtVrcsmWLeObMGfHpp58W3d3dRb1eL4qiKM6ZM0dcsWKFuf2hQ4dEOzs78c033xQzMjLEuLg40d7eXkxPT5eqC6IoiuKiRYtENzc3MTk5WSwqKjI/amtrzW1+25c1a9aIe/bsEc+fPy8eO3ZMfOyxx0SNRiOePn1aii6Y/eUvfxGTk5PF7Oxs8dChQ2J0dLTo7e0tlpSUiKJoPWMiik0raAYHB4vLly+/7jU5j0dVVZV4/Phx8fjx4yIAce3ateLx48fNq6C++uqroru7u/jFF1+IP//8szhz5kyxV69e4tWrV83HmDRpkvjOO++Yn9/od02KvhgMBvH+++8Xg4KCxBMnTrT63amvr2+3Lzf6jlq6H1VVVeLzzz8vpqSkiNnZ2eJ3330n3nHHHWK/fv3Eurq6dvshxzFpUVFRITo6Oorr169v8xhyGBOyLraQ75nr5TUe17LGfM9cz1zfnZjrb4xF+g288847YnBwsKhSqcTRo0eLR44cMb921113ifPmzWvV/uOPPxb79+8vqlQqcfDgweKuXbssHPH1ALT52Lx5s7nNb/vy7LPPmvvt5+cnzpgxQ0xLS7N88L8RExMj+vv7iyqVSgwMDBRjYmLEc+fOmV+3ljERRVHcs2ePCEDMysq67jU5j8f+/fvb/D61xGsymcRVq1aJfn5+olqtFidPnnxdH0NCQsS4uLhW2zr6XZOiL9nZ2e3+7uzfv7/dvtzoO2rpftTW1opTpkwRfXx8RHt7ezEkJERcuHDhdQnYGsakxfvvvy86ODiI5eXlbR5DDmNC1sfa8z1zvbzG41rWmO+Z65nrpepLi56e6wVRFMVbnYUnIiIiIiIioq7Da9KJiIiIiIiIZIJFOhEREREREZFMsEgnIiIiIiIikgkW6UREREREREQywSKdiIiIiIiISCZYpBMRERERERHJBIt0IiIiIiIiIplgkU5EREREREQkEyzSicjiBEHAzp07pQ6DiIiIuglzPdGtY5FO1MM88cQTEAThuse0adOkDo2IiIi6AHM9kXWzkzoAIrK8adOmYfPmza22qdVqiaIhIiKirsZcT2S9OJNO1AOp1WpotdpWDw8PDwBNp6etX78e06dPh4ODA3r37o1PP/201f7p6emYNGkSHBwc4OXlhaeffhrV1dWt2iQkJGDw4MFQq9Xw9/fHkiVLWr1eVlaGBx54AI6OjujXrx++/PLL7u00ERFRD8JcT2S9WKQT0XVWrVqFhx56CCdPnsTs2bPx2GOPISMjAwBQU1ODqVOnwsPDAz/++CM++eQTfPfdd60S8/r167F48WI8/fTTSE9Px5dffom+ffu2eo81a9bg0Ucfxc8//4wZM2Zg9uzZuHz5skX7SURE1FMx1xPJmEhEPcq8efNEpVIpOjk5tXr8/e9/F0VRFAGIzzzzTKt9IiMjxUWLFomiKIoffPCB6OHhIVZXV5tf37Vrl6hQKES9Xi+KoigGBASIf/vb39qNAYD4wgsvmJ9XV1eLAMRvvvmmy/pJRETUUzHXE1k3XpNO1ANNnDgR69evb7XN09PT/HNUVFSr16KionDixAkAQEZGBsLDw+Hk5GR+fdy4cTCZTMjKyoIgCCgsLMTkyZM7jGHYsGHmn52cnODq6oqSkpJb7RIRERFdg7meyHqxSCfqgZycnK47Ja2rODg43FQ7e3v7Vs8FQYDJZOqOkIiIiHoc5noi68Vr0onoOkeOHLnu+cCBAwEAAwcOxMmTJ1FTU2N+/dChQ1AoFAgLC4OLiwtCQ0ORlJRk0ZiJiIjo5jHXE8kXZ9KJeqD6+nro9fpW2+zs7ODt7Q0A+OSTTzBy5EiMHz8eH374IVJTU7Fp0yYAwOzZsxEXF4d58+bhxRdfRGlpKZYuXYo5c+bAz88PAPDiiy/imWeega+vL6ZPn46qqiocOnQIS5cutWxHiYiIeijmeiLrxSKdqAdKTEyEv79/q21hYWHIzMwE0LQa67Zt2/CnP/0J/v7++OijjzBo0CAAgKOjI/bs2YNly5Zh1KhRcHR0xEMPPYS1a9eajzVv3jzU1dXhrbfewvPPPw9vb288/PDDlusgERFRD8dcT2S9BFEURamDICL5EAQBO3bswKxZs6QOhYiIiLoBcz2RvPGadCIiIiIiIiKZYJFOREREREREJBM83Z2IiIiIiIhIJjiTTkRERERERCQTLNKJiIiIiIiIZIJFOhEREREREZFMsEgnIiIiIiIikgkW6UREREREREQywSKdiIiIiIiISCZYpBMRERERERHJBIt0IiIiIiIiIpn4/zGVGv+3c5iDAAAAAElFTkSuQmCC\n"
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Metric Train Validation \n",
"accuracy 0.9705 0.8615 \n",
"loss 0.0890 0.5991 \n"
]
},
{
"output_type": "error",
"ename": "AttributeError",
"evalue": "'History' object has no attribute 'update'",
"traceback": [
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
"\u001b[0;31mAttributeError\u001b[0m Traceback (most recent call last)",
"\u001b[0;32m\u001b[0m in \u001b[0;36m\u001b[0;34m()\u001b[0m\n\u001b[1;32m 138\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 139\u001b[0m \u001b[0;31m# Update the history data with the new details\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 140\u001b[0;31m \u001b[0mhistory\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0madditional_details\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m 141\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m 142\u001b[0m \u001b[0;31m# Save the model and training history\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
"\u001b[0;31mAttributeError\u001b[0m: 'History' object has no attribute 'update'"
]
}
],
"source": [
"import os\n",
"import numpy as np\n",
"import pandas as pd\n",
"import json\n",
"import matplotlib.pyplot as plt\n",
"from tensorflow.keras.models import Sequential\n",
"from tensorflow.keras.layers import Dense, Flatten, Conv2D, MaxPooling2D\n",
"from tensorflow.keras.utils import to_categorical\n",
"from tensorflow.keras.optimizers import Adam\n",
"import pickle\n",
"\n",
"# Paths and constants\n",
"dataset_path = '/content/EuroSAT_dataset/EuroSAT'\n",
"\n",
"def load_label_map(dataset_path):\n",
" \"\"\"Load label map from JSON and return mappings.\"\"\"\n",
" with open(os.path.join(dataset_path, 'label_map.json'), 'r') as f:\n",
" label_map = json.load(f)\n",
" label_map_inv = {v: k for k, v in label_map.items()}\n",
" return label_map, label_map_inv\n",
"\n",
"def load_csv_data(dataset_path):\n",
" \"\"\"Load train, test, and validation CSV files.\"\"\"\n",
" train_df = pd.read_csv(os.path.join(dataset_path, 'train.csv'))\n",
" test_df = pd.read_csv(os.path.join(dataset_path, 'test.csv'))\n",
" val_df = pd.read_csv(os.path.join(dataset_path, 'validation.csv'))\n",
" return train_df, test_df, val_df\n",
"\n",
"def load_images_and_labels(df, dataset_path, label_map_inv, image_col='Filename', label_col='Label'):\n",
" \"\"\"Load images and labels from a DataFrame.\"\"\"\n",
" images = []\n",
" labels = []\n",
" for _, row in df.iterrows():\n",
" image_path = os.path.join(dataset_path, row[image_col])\n",
" image = plt.imread(image_path)\n",
" images.append(image)\n",
" labels.append(label_map_inv[row[label_col]]) # Convert integer label to class name\n",
" return np.array(images), np.array(labels)\n",
"\n",
"def preprocess_data(images, labels, label_map):\n",
" \"\"\"Normalize images and one-hot encode labels.\"\"\"\n",
" images = images / 255.0 # Scale pixel values to [0, 1]\n",
" labels_encoded = np.array([label_map[label] for label in labels]) # Convert labels to integers\n",
" labels_one_hot = to_categorical(labels_encoded) # One-hot encode labels\n",
" return images, labels_one_hot\n",
"\n",
"def build_cnn_model(input_shape, num_classes):\n",
" \"\"\"Build and return a CNN model.\"\"\"\n",
" model = Sequential()\n",
" model.add(Conv2D(32, (3, 3), activation='relu', input_shape=input_shape))\n",
" model.add(MaxPooling2D((2, 2)))\n",
" model.add(Conv2D(64, (3, 3), activation='relu'))\n",
" model.add(MaxPooling2D((2, 2)))\n",
" model.add(Conv2D(128, (3, 3), activation='relu'))\n",
" model.add(MaxPooling2D((2, 2)))\n",
" model.add(Flatten())\n",
" model.add(Dense(128, activation='relu'))\n",
" model.add(Dense(num_classes, activation='softmax'))\n",
" return model\n",
"\n",
"def plot_training_history(history):\n",
" \"\"\"Plot training and validation accuracy and loss.\"\"\"\n",
" plt.figure(figsize=(12, 4))\n",
"\n",
" # Accuracy plot\n",
" plt.subplot(1, 2, 1)\n",
" plt.plot(history.history['accuracy'])\n",
" plt.plot(history.history['val_accuracy'])\n",
" plt.title('Model Accuracy')\n",
" plt.ylabel('Accuracy')\n",
" plt.xlabel('Epoch')\n",
" plt.legend(['Train', 'Validation'], loc='upper left')\n",
"\n",
" # Loss plot\n",
" plt.subplot(1, 2, 2)\n",
" plt.plot(history.history['loss'])\n",
" plt.plot(history.history['val_loss'])\n",
" plt.title('Model Loss')\n",
" plt.ylabel('Loss')\n",
" plt.xlabel('Epoch')\n",
" plt.legend(['Train', 'Validation'], loc='upper left')\n",
"\n",
" plt.show()\n",
"\n",
"def summarize_history(history):\n",
" \"\"\"Print a summary table of training and validation performance.\"\"\"\n",
" print(f\"{'Metric':<15}{'Train':<15}{'Validation':<15}\")\n",
" for key in history.history:\n",
" if 'val' not in key:\n",
" val_key = f\"val_{key}\"\n",
" print(f\"{key:<15}{history.history[key][-1]:<15.4f}{history.history[val_key][-1]:<15.4f}\")\n",
"\n",
"# Main flow\n",
"if __name__ == '__main__':\n",
" # Load label map and CSV data\n",
" label_map, label_map_inv = load_label_map(dataset_path)\n",
" train_df, test_df, val_df = load_csv_data(dataset_path)\n",
"\n",
" # Load images and labels for train, test, and validation sets\n",
" X_train, y_train = load_images_and_labels(train_df, dataset_path, label_map_inv)\n",
" X_test, y_test = load_images_and_labels(test_df, dataset_path, label_map_inv)\n",
" X_val, y_val = load_images_and_labels(val_df, dataset_path, label_map_inv)\n",
"\n",
" # Preprocess data (normalize images and one-hot encode labels)\n",
" X_train, y_train_one_hot = preprocess_data(X_train, y_train, label_map)\n",
" X_test, y_test_one_hot = preprocess_data(X_test, y_test, label_map)\n",
" X_val, y_val_one_hot = preprocess_data(X_val, y_val, label_map)\n",
"\n",
" # Build CNN model\n",
" input_shape = X_train.shape[1:] # Image shape (height, width, channels)\n",
" num_classes = len(label_map)\n",
" model = build_cnn_model(input_shape, num_classes)\n",
"\n",
" # Compile the model\n",
" model.compile(optimizer=Adam(learning_rate=0.001), loss='categorical_crossentropy', metrics=['accuracy'])\n",
"\n",
" # Print model summary\n",
" model.summary()\n",
"\n",
" # Train the model\n",
" history = model.fit(X_train, y_train_one_hot, epochs=20, batch_size=32, validation_data=(X_val, y_val_one_hot))\n",
"\n",
" # Evaluate the model\n",
" test_loss, test_accuracy = model.evaluate(X_test, y_test_one_hot)\n",
" print(f'Test Accuracy: {test_accuracy:.4f}')\n",
"\n",
" # Plot training history\n",
" plot_training_history(history)\n",
"\n",
" # Summarize training history\n",
" summarize_history(history)\n",
"\n",
" additional_details = {\n",
" 'X_test': X_test, # Add entire test dataset\n",
" 'y_test_one_hot': y_test_one_hot, # Add test labels (one-hot encoded)\n",
" 'label_map': label_map # Label map used for decoding\n",
" }\n",
"\n",
" # Update the history data with the new details\n",
" history.history.update(additional_details)\n",
"\n",
" # Save the model and training history\n",
" model.save('cnn_image_classifier.h5')\n",
" with open('history.pkl', 'wb') as f:\n",
" pickle.dump(history.history, f)\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "ocK4ele0RTKn"
},
"source": [
"**Model Evaluation (Confusion Matrix & ROC Curve)**"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 1000
},
"id": "zKyoLXs2cj3m",
"outputId": "77e2115a-0e01-44cf-dee4-8cb1677c9637"
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
"WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[1m85/85\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m5s\u001b[0m 57ms/step\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[1m85/85\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m11s\u001b[0m 130ms/step\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAqIAAAJhCAYAAACafdLpAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy81sbWrAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOzdd1gU1x7G8e/SO4pUFQF7QUCxVywRFVvUqLFiL1jQWGNvUWPsvcQSjS2xRo019t6waxDBDlhBUKl7/+C6uoIKUnaJv8995rnZqe/sDuvZc+acUSiVSiVCCCGEEEJkMR1NBxBCCCGEEF8nKYgKIYQQQgiNkIKoEEIIIYTQCCmICiGEEEIIjZCCqBBCCCGE0AgpiAohhBBCCI2QgqgQQgghhNAIKYgKIYQQQgiNkIKoEEIIIYTQCCmICiG0Wv369enataumY2jEtWvX0NPT48qVK5qOkinCwsJo3rw5uXLlQqFQMHPmzAw/hkKhYMyYMRm+3+zK19cXZ2dnTccQQkUKokJ8pYKCgujevTv58+fHyMgICwsLKleuzKxZs3j9+rVqPWdnZxQKBX369Em2j4MHD6JQKPjzzz9V81asWIFCocDIyIgHDx4k28bLywtXV9dUZTx27Bh79uxhyJAhyY75dtLV1cXW1pbmzZtz/fr1tLwFaZKR5/WhNWvWpFgIK168OD4+PowaNeqL9psaYWFhDBw4kKJFi2JiYoKpqSmenp5MmDCBFy9eZNpxAfr378/u3bsZNmwYq1atom7dupl6vKw0ZswYFAoFOjo63Lt3L9nyyMhIjI2NUSgU9O7dO837f/XqFWPGjOHgwYMZkFYIzdHTdAAhRNbbsWMH3333HYaGhrRv3x5XV1diY2M5evQogwYN4urVqyxevFhtmyVLljBs2DBy586dqmPExMQwefJk5syZ88U5p06dSq1atShYsGCyZX379qVs2bLExcVx6dIlFi5cyMGDB7ly5Qr29vZffMzPyYjz+tCaNWu4cuUK/v7+yZb16NGD+vXrExQURIECBTLsmABnzpyhfv36REVF0bZtWzw9PQE4e/YskydP5vDhw+zZsydDj/m+f/75h8aNGzNw4MBMO8br16/R09PcP3WGhoasXbuWwYMHq83ftGlTuvb76tUrxo4dCyT9CEqtJUuWkJiYmK5jC5GRpEZUiK9McHAwrVq1wsnJiWvXrjFr1iy6du2Kn58fa9eu5dq1a5QoUUJtmxIlSpCQkMDkyZNTfRwPDw+WLFnCw4cPvyhneHg4O3bsoEWLFikur1q1Km3btqVjx47MmDGDGTNm8PTpU3777bcvOl5qpfe80qp27drkzJmTlStXZuh+X7x4wbfffouuri4XLlxgyZIl9OjRgx49erB06VKCgoKoVq1ahh7zQ+Hh4eTIkSNTj2FkZKTRgmj9+vVZu3Ztsvlr1qzBx8cny3JER0cDoK+vj6GhYZYdV4jPkYKoEF+Zn3/+maioKH799VccHBySLS9YsCD9+vVTm+fs7Ez79u3TVAD78ccf01x4fd+OHTuIj4+ndu3aqVq/atWqQNItB+978OABnTp1ws7ODkNDQ0qUKMGyZcuSbT9nzhxKlCiBiYkJOXPmpEyZMqxZsybZemk9r9WrV+Pp6YmxsTFWVla0atVKranWy8uLHTt2cOfOHdXtBu/fw6evr4+Xlxdbt25N1fFSa9GiRTx48IDp06dTtGjRZMvt7OwYMWKE2rz58+dTokQJDA0NyZ07N35+fsma79/eonDt2jVq1KiBiYkJefLk4eeff1at8/Y2B6VSybx581TnDe+atD/0dpuQkBDVvLNnz+Lt7Y21tTXGxsa4uLjQqVMnte1Sukf0woUL1KtXDwsLC8zMzKhVqxYnT55M8XjHjh1jwIAB2NjYYGpqyrfffsvjx48/+r5+qHXr1gQEBHDjxg3VvNDQUP755x9at26dbP3Y2FhGjRqFp6cnlpaWmJqaUrVqVQ4cOKBaJyQkBBsbGwDGjh2rev/enqevry9mZmYEBQVRv359zM3NadOmjWrZ+9fX6NGj0dHRYf/+/Wo5unXrhoGBARcvXkz1uQrxJaQgKsRX5q+//iJ//vxUqlQpTdsNHz6c+Pj4VBfAXFxc0lx4fd/x48fJlSsXTk5OqVr/bQElZ86cqnlhYWFUqFCBffv20bt3b2bNmkXBggXp3Lmz2j2ZS5YsoW/fvhQvXpyZM2cyduxYPDw8OHXqVLrOa+LEibRv355ChQoxffp0/P392b9/P9WqVVMV4IYPH46HhwfW1tasWrWKVatWJbtf1NPTkytXrhAZGZmq9yI1tm3bhrGxMc2bN0/V+mPGjMHPz4/cuXMzbdo0mjVrxqJFi6hTpw5xcXFq6z5//py6devi7u7OtGnTKFq0KEOGDOHvv/8GoFq1aqxatQqAb775RnXeaREeHk6dOnUICQlh6NChzJkzhzZt2iQrUH7o6tWrVK1alYsXLzJ48GBGjhxJcHAwXl5eKX7effr04eLFi4wePZqePXvy119/pemezmrVqpE3b161HzXr16/HzMwsxRrRyMhIli5dipeXF1OmTGHMmDE8fvwYb29vAgICALCxsWHBggUAfPvtt6r3r2nTpqr9xMfH4+3tja2tLb/88gvNmjVLMd+IESPw8PCgc+fOvHz5EoDdu3ezZMkSRo0ahbu7e6rPVYgvohRCfDUiIiKUgLJx48ap3sbJyUnp4+OjVCqVyo4dOyqNjIyUDx8+VCqVSuWBAweUgPKPP/5Qrb98+XIloDxz5owyKChIqaenp+zbt69qefXq1ZUlSpT47HGrVKmi9PT0TDb/7TGXLVumfPz4sfLhw4fKXbt2KQsWLKhUKBTK06dPq9bt3Lmz0sHBQfnkyRO1fbRq1UppaWmpfPXqlVKpVCobN2782UxpPa+QkBClrq6ucuLEiWr7uXz5slJPT09tvo+Pj9LJyemjx16zZo0SUJ46deqTGdMiZ86cSnd391StGx4erjQwMFDWqVNHmZCQoJo/d+5c1WfxVvXq1ZWA8rffflPNi4mJUdrb2yubNWumtl9A6efnpzZv9OjRypT+aXr7/gcHByuVSqVy8+bNqs/jUwDl6NGjVa+bNGmiNDAwUAYFBanmPXz4UGlubq6sVq1asuPVrl1bmZiYqJrfv39/pa6urvLFixefPO7b83j8+LFy4MCByoIFC6qWlS1bVtmxY8cU34P4+HhlTEyM2r6eP3+utLOzU3bq1Ek17/Hjx8nO7a0OHTooAeXQoUNTXPbhtXb58mWlgYGBskuXLsrnz58r8+TJoyxTpowyLi7uk+coREaQGlEhviJva9TMzc2/aPsRI0akqVY0f/78tGvXjsWLF/Po0aM0Hevp06dqtZsf6tSpEzY2NuTOnZu6desSERHBqlWrKFu2LABKpZKNGzfSsGFDlEolT548UU3e3t5ERERw/vx5AHLkyMH9+/c5c+ZMhp3Xpk2bSExMpEWLFmrHtre3p1ChQmpNrZ/z9n148uRJqrf5nMjIyFRfB/v27SM2NhZ/f390dN79s9G1a1csLCzYsWOH2vpmZma0bdtW9drAwIBy5cpx+/btjAkPqntLt2/fnqxG9mMSEhLYs2cPTZo0IX/+/Kr5Dg4OtG7dmqNHjyarde7WrZvarQJVq1YlISGBO3fupDpr69atuXXrFmfOnFH9f0rN8gC6uroYGBgAkJiYyLNnz4iPj6dMmTKq6zW1evbsmar1XF1dGTt2LEuXLsXb25snT56wcuVKjd5bK74eUhAV4itiYWEBoGqCS6svKVimtfD6PqVS+dFlo0aNYu/evWzevJn27dsTERGhVkh6/PgxL168YPHixdjY2KhNHTt2BJKadwGGDBmCmZkZ5cqVo1ChQvj5+XHs2LF0nVdgYCBKpZJChQolO/7169dVx07L+5DSvZNvxcbGEhoaqjYlJCR8dH0LC4tUXwdvC11FihRRm29gYED+/PmTFcry5s2bLGvOnDl5/vx5qo6XGtWrV6dZs2aMHTsWa2trGjduzPLly4mJifnoNo8fP+bVq1fJzgOgWLFiJCYmJhtqKV++fGqv3/4oSMu5lCpViqJFi7JmzRp+//137O3tqVmz5kfXX7lyJW5ubhgZGZErVy5sbGzYsWMHERERqT6mnp4eefPmTfX6gwYNwt3dndOnTzN69GiKFy+e6m2FSA/5uSPEV8TCwoLcuXOna4D04cOHs2rVKqZMmUKTJk0+u37+/Plp27YtixcvZujQoak+Tq5cuT75j33JkiVVHZmaNGnCq1ev6Nq1K1WqVMHR0VE1RE3btm3p0KFDivtwc3MDkgohN2/eZPv27ezatYuNGzcyf/58Ro0apRoiJ63nlZiYiEKh4O+//0ZXVzfZcjMzs0+/Ae95+z5YW1t/dJ3jx49To0YNtXnBwcEfHby8aNGiBAQEEBsbq6qByygpnS98+ofFWx8rbH9YqH47fu3Jkyf566+/2L17N506dWLatGmcPHkyTe/vp6TnXN7XunVrFixYgLm5OS1btlT70fS+1atX4+vrS5MmTRg0aBC2trbo6uoyadKkZB3xPsXQ0PCjx0jJ7du3CQwMBODy5cup3k6I9JIaUSG+Mg0aNCAoKIgTJ0580fYFChSgbdu2LFq0KM21olOmTEn1cYoWLUpwcHCq1588eTJv3rxh4sSJQFKHDnNzcxISEqhdu3aKk62trWp7U1NTWrZsyfLly7l79y4+Pj5MnDiRN2/efNF5FShQAKVSiYuLS4rHrlChgmrdT9V0QlKBUkdHh8KFC390HXd3d/bu3as2fWo81YYNG/L69Ws2btz4yWMDqg5jN2/eVJsfGxtLcHBwqjuUpcbbGscPe+N/rCm8QoUKTJw4kbNnz/L7779z9epV1q1bl+K6NjY2mJiYJDsPgBs3bqCjo4Ojo2P6TuAjWrduzaNHj/j3338/2iwP8Oeff5I/f342bdpEu3bt8Pb2pnbt2smuw89dM2mRmJiIr68vFhYW/Pjjj6xduzbd45wKkVpSEBXiKzN48GBMTU3p0qULYWFhyZYHBQUxa9asT+5jxIgRxMXFqQ3J8ynvF15DQ0NTtU3FihV5/vx5qu8rLFCgAM2aNWPFihWEhoaiq6tLs2bN2LhxY4o1wO8PwfP06VO1ZQYGBhQvXhylUvnJ+w8/dV5NmzZFV1eXsWPHJqs9UyqVasc0NTX9ZLPruXPnKFGiBJaWlh9dJ2fOnMkKu0ZGRh9dv0ePHjg4OPDDDz/w77//JlseHh7OhAkTgKSxTA0MDJg9e7baufz6669ERERk6HiYbwftP3z4sGpedHR0snFUnz9/nux99fDwAPho87yuri516tRh69atasNAhYWFsWbNGqpUqaK6fSWjFShQgJkzZzJp0iTKlSv30fXe1sC+f26nTp1K9sPRxMQESF5g/xLTp0/n+PHjLF68mPHjx1OpUiV69uyZofckC/Ex0jQvxFemQIECrFmzhpYtW1KsWDG1JysdP36cP/74A19f38/uo23btmkaZP1tk/7NmzeTDZifEh8fH/T09Ni3bx/dunVL1TEGDRrEhg0bmDlzJpMnT2by5MkcOHCA8uXL07VrV4oXL86zZ884f/48+/bt49mzZwDUqVMHe3t7KleujJ2dHdevX2fu3Ln4+Ph8tkPPx86rQIECTJgwgWHDhhESEkKTJk0wNzcnODiYzZs3061bN9UThTw9PVm/fj0DBgygbNmymJmZ0bBhQwDi4uI4dOgQvXr1StV7kFo5c+Zk8+bN1K9fHw8PD7UnK50/f561a9dSsWJFIKkmcdiwYYwdO5a6devSqFEjbt68yfz58ylbtqxax6T0qlOnDvny5aNz584MGjQIXV1dli1bho2NDXfv3lWtt3LlSubPn8+3335LgQIFePnyJUuWLMHCwoL69et/dP8TJkxg7969VKlShV69eqGnp8eiRYuIiYlJ9Q+rL/Xh+LwpadCgAZs2beLbb7/Fx8eH4OBgFi5cSPHixYmKilKtZ2xsTPHixVm/fj2FCxfGysoKV1fXND9m9vr164wcORJfX1/VNbdixQo8PDzo1asXGzZsSNtJCpFWmuiqL4TQvH///VfZtWtXpbOzs9LAwEBpbm6urFy5snLOnDnKN2/eqNZ7f/im9wUGBip1dXU/OXzTh94OK5Oa4ZuUSqWyUaNGylq1aqnNS2nIqPd5eXkpLSwsVMPrhIWFKf38/JSOjo5KfX19pb29vbJWrVrKxYsXq7ZZtGiRslq1aspcuXIpDQ0NlQUKFFAOGjRIGRERke7z2rhxo7JKlSpKU1NTpampqbJo0aJKPz8/5c2bN1XrREVFKVu3bq3MkSOHElAbXufvv/9WAsrAwMBUvWdp9fDhQ2X//v2VhQsXVhoZGSlNTEyUnp6eyokTJ6qdv1KZNFxT0aJFlfr6+ko7Oztlz549lc+fP1db52PDc6U0bBApDN+kVCqV586dU5YvX15pYGCgzJcvn3L69OnJhm86f/688vvvv1fmy5dPaWhoqLS1tVU2aNBAefbs2WTH+HCIo/Pnzyu9vb2VZmZmShMTE2WNGjWUx48fV1vnY5/32+vvwIEDyXK/7/3hmz7lw/cgMTFR+dNPPymdnJyUhoaGylKlSim3b9+e4vt3/Phxpaenp9LAwEDtPDt06KA0NTVN8Xjv7yc+Pl5ZtmxZZd68eZMNRzVr1iwloFy/fv0n8wuRXgqlMo13XAshRBY5cuQIXl5e3Lhxg0KFCmk6jkY0adIEhULB5s2bNR1FCCEynBREhRBarV69euTNm5clS5ZoOkqWu379OiVLliQgICDNTa5CCJEdSEFUCCGEEEJohPSaF0IIIYQQGiEFUSGEEEIIoRFSEBVCCCGEEBohBVEhhBBCCKERMqC9EO9JTEzk4cOHmJubZ+gj9IQQQmgXpVLJy5cvyZ07Nzo6mqmXe/PmDbGxsRmyLwMDg08+TU1bSUFUiPc8fPgw0541LYQQQvvcu3ePvHnzZvlx37x5g7F5Loh/lSH7s7e3Jzg4ONsVRqUgKsR73j7Osdr4regZmWo4jbpVHTw1HSFF8YnaOQKcga523nmko6OdNe3xCYmajvBRIY+jNR0hRQXtP/34V015E5ug6Qgpio3Xrmvs5cuXlC7u8tnH+GaW2NhYiH+FYYmOoGuQvp0lxBJ6dTmxsbFSEBUiO3vbHK9nZIqesXYVRC0sLDQdIUVSEE0bKYimndkbXU1HSJGFhXYWRA20tCAao2UF0bc0fhuWrgGKdBZEtfNbOHWkICqEEEIIoSkKIL2FYe38fZsqUhAVQgghhNAUhU7SlN59ZFPZN7kQQgghhMjWpEZUCCGEEEJTFIoMaJrPvm3zUhAVQgghhNAUaZoXQgghhBAi60lBVIg0cHUwZ2z9IqzxLc1uvwpUdMmpttxIXwe/qs6s7lCKbd3Lsfh7N3xK2Kqt09fLheVtPdjWvRzrO3kypn5hHHNk/rhvP40fi7mRrtpU2q14ph/3Q8eOHqZVs8YUy+9IThM9dmzbqrb8ry2badqwLvnz2pLTRI/LFwOyPCPAkkULKOfpjr21JfbWltSoVondu/7WSJaULJw/jyIFnclhZkTVSuU5c/q0RvNow/W1YPpPuOezUJsa13g3/u6T8DB+7NeVmp4FKV/Enpb1q7Jv59ZP7DHzafpzPHb0MK2aN6ZYAUdymuqx469370dcXByjRwylUlkP8thYUKyAIz26+PLo0cNMzTR72hS8vSpSII8VJQrkwbd1M24F3lRbZ1C/XpR3L4qznQXF8+emw/dNCfz3RqbmyjRvm+bTO2VTUhAVIg2M9HW5/TSauYeCU1zevbITZZxy8PPeILquucjmi6H4VXOhgvO7AmtgeDTT9ictH77tOgA/NSpGVgwvWax4CW6FPFBNe/45nPkH/cCr6GhcS7oxdcacFJdHv4qmQsXKjBk/KYuTqcuTJy/jJkzi6ImzHDl+hupeNWjZvAnXrl3VaC6APzasZ8igAQwfMZoTp8/j5uZOIx9vwsPDNZpLG66vAoWLsf9soGpasXGPatnw/t0IuR3IrF/XsXHPCWrVbcigXh24fuVilucE7fgcP/X3+OrVKy4FXGDQ0OEcPHaG39b+wa3Am7T+7ttMzXTi2BE6du3Jjn1H2LBlJ3Fx8bT81ofo6HcPNnDzKM3M+Us4fPoS6zbtQKlU0upbHxIStHMM1U/Tedc8/6VTNi7OyT2iQqTB2bsvOHv3xUeXF7c3Z++Nx1x6GAnA39fC8SlhSxE7U06GPFfNeyvsJaw8dZ+FrdywMzfkUWRMpubX09PDzt4+U4/xOd941+Mb73ofXd6qdVsA7t4JyaJEKavfoKHa6zHjJrJ08ULOnDpJ8eIlNJQqyeyZ0+nYuSvtfTsCMGf+Qv7+ewcrVyxj0OChGsulDdeXnp4e1rZ2KS67eO40wydOp6RHGQC69R3M6qXzuH45gGKu7lkZE9COz/FTf4+WlpZs3r5bbd7P02dTq1pF7t27i6NjvkzJtHbTdrXXsxYsxbVAHi4FnKdi5aoAtOvYRbU8n5MzQ0eMpWblMty7E4Jz/gKZkktkjuxbhBZCC10LfUkF55zkMtUHwD2PBXlyGHPubkSK6xvq6VCnqA2PIt7wOCo20/MF3QqkkEteShYtSOcObbl3926mH/O/ICEhgT82rCM6OppyFSpqNEtsbCwXzp+jZq3aqnk6OjrUrFmb0ydPaDCZdlxfd4KDqF2mMPUruzGsb2cePbinWubuWY7df20i4sUzEhMT+Xvbn8TExFCmYpUsz6nNn+OnREZEoFAosLTMkWXHfBmR9P2ZI2fOFJdHR0ez7vffyOfkQu68jlmWK8N85U3zUiMqRAaafziEfjXys8bXk/iERBKBWQduc+XRS7X1Grja0aVSPoz1dbn3/DXDtl3P9EdllilXjoVLllGocBFCQx8xaeJ4vGtV59T5Sxp71rK2u3LlMjWrVeLNmzeYmZmxdsMmihXL+vtq3/fkyRMSEhKw/aDWz9bOjps3NXePnDZcXyVLlWH8tAU4FyjE4/BQFs2cTMfmddm49ySmZuZMnb+SwX6+VHNzRk9PDyNjE2Ys+Z18zllfg6atn+OnvHnzhjEjf6TZd62y7JHDiYmJjBw2kHIVKlGsuKvasuVLFjJ+9DBeRUdTsFBhNmzZiYFBOp/Zrglfea95KYiKTLFixQr8/f158eKFpqNkqcZu9hS1M2PUjhuEv4ylZG5z/Kq58DQ6lgv3I1Xr/fPvE87fi8DKRJ/mpRwY7l2I/puuEpeQeYXROu81v7mWdKNM2fKUKOzCpj830KFj50w7bnZWuHARTpy+QGRkBJs3/Un3Lr7s2ndQ44VRbaQN11eVGnVU/124mCslPcpQr5Iru7dvpmmr9sybNoGXkREsXrONHFa5OLB7O4N7+bL8z10UKqrZ2y20XVxcHB3btUKpVDJt1rwsO+7QH/py4/pVtu06kGxZsxbfU71mLcJCQ1kwZzrdfFuzbc8hjIwyv/OnyDjZtwj9FTtx4gS6urr4+PhoOkqaxMbG8vPPP+Pu7o6JiQnW1tZUrlyZ5cuXExcXp+l46Wagq8C3giOLj93hVMgLgp++YtvlMA7dekpzj9xq676KTeBhxBuuPHrJhF2BOOY0pnJ+qyzNmyNHDgoWKsztoKAsPW52YmBgQIGCBSlV2pNxEybhWtKd+XNmaTSTtbU1urq6hIeHqc0PDwvDXsP3Z75PG64vC8scOLkU4F7Ibe6F3GbdisWMnTqf8lW8KFK8JD36D6N4yVKsW7kky7Nll88R3hVC7929y+a/dmVZbeiwgf3Yt3snG//aQ+48eZMtt7C0JH+BQlSsXJWlv60nMPAmf2/fkiXZMtRX3jQvBdFs6Ndff6VPnz4cPnyYhw8zdxiNjBIbG4u3tzeTJ0+mW7duHD9+nNOnT+Pn58ecOXO4ejXlnsixsZl/32RG0dPRQV9Xhw9b2BOVyk9+R7xdpK+btX+OUVFRBN8Owt7BIUuPm50lKhOJ0fA1aWBgQKnSnhz4Z79qXmJiIgcO7Nf4/avv04br61V0FPfuBGNta8ebN6+BpPsw36ejq4MyMTHLs2WXz/FtITTo1i22bN+NVa5cmX5MpVLJsIH9+Hv7Vv78azdOzi6p2galkpiY7PNvhkp6e8xnRNO+BmXf5F+pqKgo1q9fT8+ePfHx8WHFihWqZQcPHkShULB//37KlCmDiYkJlSpV4ubNd+OvjRkzBg8PD1atWoWzszOWlpa0atWKly/f3cPo7OzMzJkz1Y7r4eHBmDFjVK+nT59OyZIlMTU1xdHRkV69ehEVFfXR3DNnzuTw4cPs378fPz8/PDw8yJ8/P61bt+bUqVMUKlQIAC8vL3r37o2/vz/W1tZ4e3sDcOjQIcqVK4ehoSEODg4MHTqU+Ph41f7fbte7d28sLS2xtrZm5MiRSV9OGchIX4f81ibktzYBwN7CkPzWJtiYGfAqLoGLDyLpWikfbrktsDM35JuiNtQuYsPx289V67csnZuCNqbYmBlQ3N6M4XULEZuQyOk7zzM064d+HDqIo4cPcSckhJMnjtO6RVN0dHVp3qJVph73Q1FRUVy+GKAaH/TOnWAuXwzg3r2kji3Pnz3j8sUAbly/BkBg4L9cvhhAWGholuYcNWIYR48c5k5ICFeuXGbUiGEcOXSQlq1aZ2mOlPT1H8DyX5ew+reV3Lh+nb5+PXkVHU37Dh01lkkbrq9pE4Zz9uRRHty7Q8DZU/Tv2gZdXV3qNf4O5wKFyeecn/HD+nE54Cz3Qm6zcvEcTh45QA1vzbQuacPnmOzvMeTd32NcXBwd2rTgwvlzLF72GwkJCYSFhhIWGpqplQRDf+jLxg1rmL/0N8zMzAkPCyU8LJTXr5N+TNwJvs3saVO4eOE89+/d5cypE3Tt0AojI2Nq1ambablE5pB7RLOZDRs2ULRoUYoUKULbtm3x9/dn2LBhKN6rchs+fDjTpk3DxsaGHj160KlTJ44dO6ZaHhQUxJYtW9i+fTvPnz+nRYsWTJ48mYkTJ6Y6h46ODrNnz8bFxYXbt2/Tq1cvBg8ezPz581Nc//fff6d27dqUKlUq2TJ9fX309fVVr1euXEnPnj1VmR88eED9+vXx9fXlt99+48aNG3Tt2hUjIyO1wvHKlSvp3Lkzp0+f5uzZs3Tr1o18+fLRtWvXj55HTEwMMTHvhkyKjIz86LoAhW3MmPrtu/sDe1RxBmDP9cdM+yeISXsC6VTBkSHfFMTcSI/wlzGsOHmX7VeTmt9i4xNxzW3Ot+72mBnq8eJVHJcfvaT/xqtEvI5P6ZAZ5uGD+3Ts0IZnT59ibWNDxUqV+efQcWxsbDL1uB8KOH+WhnXf9RQePmQgAN+3bc/8xcv4e8df+HV/d09h5/ZJBb8hP45k6IjRWZbz8eNwunbuQOijR1hYWuLq6sbW7buoVfubLMvwMd+1aMmTx48ZN3YUYaGhuLl7sHX7LuzsUh62KCtow/UV9ugBQ3t34sWLZ+S0sqZU2Qqs2rIfq1zWAMxd+SezJo+hb6eWvIqOTiqYTl9I1ZreWZbxfdrwOQacP0vDeu/9PQ79/99jm/YMHT6Kv3f8BUC1ip5q2/319z6qVPPKlEwrf10EQFOf2mrzZ85fSqs27TE0MuLkiWMsXjCHiBfPsbG1o0KlKvy19xA2NrYp7VK7feXPmlcoM7rKSGSqypUr06JFC/r160d8fDwODg788ccfeHl5cfDgQWrUqMG+ffuoVasWADt37sTHx4fXr1+rCm5Tp04lNDRU1ZN18ODBHD58mJMnTwJJNaL+/v74+/urjuvh4UGTJk3UCn7v+/PPP+nRowdPnjwBkndWMjExoWvXrsya9en767y8vIiMjOT8+fOqecOHD2fjxo1cv35dVeCeP38+Q4YMISIiAh0dHby8vAgPD+fq1auqdYYOHcq2bdu4du3aR483ZswYxo4dm2x+zan70DM2/WTWrLaxSzlNR0hRZvf2/1IGWXyrQ2rpZMWTC75AfELWN0+n1u3w6M+vpAGFHbRztIk3sdo5qHtMvHZdYy8jIynkaE1ERESW3ff6vsjISCwtLTGsOBSFnmG69qWMjyHmxGSNnUt6aOc3tUjRzZs3OX36NN9//z2QNHBzy5Yt+fXXX9XWc3NzU/23w//vz3r/SR3Ozs5qw6k4ODik+Ukebwu7efLkwdzcnHbt2vH06VNevXqV4vpp+b3j6an+y/v69etUrFhRrda3cuXKREVFcf/+fdW8ChUqqK1TsWJFAgMDP/mkjWHDhhEREaGa7t2799F1hRBCCJGxpGk+G/n111+Jj48nd+53PbCVSiWGhobMnTtXNe/9Zu63BbPE927Gf3/523XeX66jo5Os4Ph+r/aQkBAaNGhAz549mThxIlZWVhw9epTOnTsTGxuLiYlJsuyFCxfmxo3UjY1napp1NZGGhoYYGqbvl6gQQgjxxRSKDBhHVDtbWlJDakSzifj4eH777TemTZtGQECAarp48SK5c+dm7dq1GXYsGxsbHj16pHodGRlJcPC7Z6ufO3eOxMREpk2bRoUKFShcuPBne++3bt2affv2ceHChWTL4uLi1J4h/KFixYpx4sQJtcLxsWPHMDc3J2/ed0N6nDp1Sm27kydPUqhQIXR1dT+ZTQghhNAYHUXGTNmUFESzibcdizp37oyrq6va1KxZs2TN8+lRs2ZNVq1axZEjR7h8+TIdOnRQK8wVLFiQuLg45syZw+3bt1m1ahULFy785D79/f2pXLkytWrVYt68eVy8eJHbt2+zYcMGKlSoQGBg4Ee37dWrF/fu3aNPnz7cuHGDrVu3Mnr0aAYMGKA2FMvdu3cZMGAAN2/eZO3atcyZM4d+/fql/w0RQgghRKaQpvls4tdff6V27dpYWlomW9asWTN+/vlnLl26lCHHGjZsGMHBwTRo0ABLS0vGjx+vViPq7u7O9OnTmTJlCsOGDaNatWpMmjSJ9u3bf3SfhoaG7N27lxkzZrBo0SIGDhyIiYkJxYoVo2/fvri6un502zx58rBz504GDRqEu7s7VlZWdO7cmREjRqit1759e16/fk25cuXQ1dWlX79+dOvWLf1viBBCCJFZvvJHfEqvefGf4OXlhYeHR7LxT9PqbS9G6TWfetJrPm2k13zaSa/5tJFe86mjNb3mq41EoZe+x5Iq498Qc3i89JoXQgghhBAitaRpXgghhBBCU77ypnkpiIr/hIMHD2o6ghBCCJF2X/mTlaQgKoQQQgihKV95jWj2TS6EEEIIIbI1qREVQgghhNAUaZoXQgghhBAaIU3zQgghhBBCZD2pERVCCCGE0BRpmhdCCCGEEJqRAU3z2biBO/smF0IIIYQQ2ZrUiAqRgrWdymrd83pzlu2t6Qgpen5mrqYjiAygp6u99RLa+kx3bWVkoKvpCCnStlyKeH1NR0giTfNCCCGEEEIjFIoM6DWffQui2vsTWAghhBBC/KdJjagQQgghhKZ85eOISkFUCCGEEEJTvvJ7RLNvEVoIIYQQQmRrUiMqhBBCCKEp0jQvhBBCCCE0QprmhRBCCCGEyHpSIyqEEEIIoSlfedN89k0uhBZbOH8eRQo6k8PMiKqVynPm9OlMPd7ATnU4unoQ4Ud/4c7+SWyY3pVCTrZq67jktWb9tK7c/WcSYUemsnpKJ2yt1J9Y41E0L9sX9ObR4Z+5f2AKc0d8j6mxQaZmh6x/v9JCW7NJrrSRXKlz9MhhmjVpiEu+3BjrK9i2dYtG83xI296vDPG2aT69UzYlBVEhMtgfG9YzZNAAho8YzYnT53Fzc6eRjzfh4eGZdsyqpQuycP1hqrf/hQY956Knp8v2Bb0xMUoqRJoYGbB9vh9KpZJ63eZQs+MMDPR12TirO4r/f4E52FiyY2Efgu49plq7X2jsN4/iBexZMq5dpuUGzbxf2T2b5JJcmSU6OpqSbu7MnD1PYxk+RhvfL5F+CqVSqdR0CCG0RWRkJJaWloQ9jfjiZ81XrVQezzJlmTk76RnsiYmJFHRxpKdfHwYNHvrF2dLyrHnrnGbc+2cytTvP4Nj5IGpVKMrWub1wqD6Yl9FvALAwM+LRoZ9p0GseB07dpFPTyozq5YPLN8N5+7VQomBuzv7xIyUajeH2vScpHiu9z5rPrPcrI2hrNsklubKCsb6C9X9uplHjJpqOAmT8+xUZGYldLksiIr78+z493v57Y9RwLgp943TtSxn3mjd/9dbYuaSH1IgKkYFiY2O5cP4cNWvVVs3T0dGhZs3anD55IstyWJgZAfA84hUAhgZ6KJVKYmLjVeu8iYknMVFJJY8CqnXi4hJ4/7fp65hYANU6GU1b3q+UaGs2ySW5vkb/5fdLoVBkyJRdSUFUiAz05MkTEhISsLW1U5tva2dHaGholmRQKBRMHdic4xeCuBb0CIDTl0OIfh3LxH6NMTbSx8TIgMkDvkVPTxd766RfzwdP38QulwX929dCX0+XHObGTOjbGAB7G8tMyaoN79fHaGs2yZU2kuu/Qd6v/y4piArxHzNzWAtKFHSg/dDlqnlPnkfRZvCv1K/mypNj0wg7MhVLM2POX7tL4v9rQK/fDqXrqFX0bVeLZyemE7LvJ0IePCX0SSTKxERNnY4QQvy3KTJoyqZk+CaRIXx9fVm5cmWy+YGBgRQsWFAjeV68eMGWLVuy9LjW1tbo6uoSHh6mNj88LAx7e/tMP/6MId9Rv6ortTvP5EH4C7Vl+0/eoESjseTKYUp8fCIRUa8J3vsTIbvPqdZZv+ss63edxdbKnOjXMSiV0LdtTYLvP82UvJp+vz5FW7NJrrSRXP8N/+X3K0Oa1qVpXgioW7cujx49UptcXFzSvJ/Y2NhMSJc1DAwMKFXakwP/7FfNS0xM5MCB/ZSrUDFTjz1jyHc0qulO3e6zufPw4wXHpy+iiYh6TfWyhbG1MmP7ocvJ1gl/9pLo17E09y7Nm9g49p+8kSmZNfl+fY62ZpNckutrJO/Xf5fUiIoMY2homOIv00OHDjFo0CAuXryIlZUVHTp0YMKECejpJV1+Xl5euLq6oqenx+rVqylZsiQHDhzgypUrDBo0iCNHjmBqakqdOnWYMWMG1tbWAPz555+MHTuWW7duYWJiQqlSpdi6dStTp05V1c6+/ZV54MABvLy8suR96Os/gK6dOuDpWYYyZcsxd/ZMXkVH075Dx0w75sxhLWhZrwzf9V9MVPQb7HIljQ8aEfWGNzFxALRrVIGbwaE8fh5FeTcXfhnUnDm/HyDwzruhT3q0rMbJi7eJehVLrQpF+cm/CSPnbCUi6nWmZdfE+5Xds0kuyZVZoqKiCLp1S/U6JDiYiwEB5LSyIl++fBrLBdr5fmWEr71GVAqiIlM9ePCA+vXr4+vry2+//caNGzfo2rUrRkZGjBkzRrXeypUr6dmzJ8eOHQPgxYsX1KxZky5dujBjxgxev37NkCFDaNGiBf/88w+PHj3i+++/5+eff+bbb7/l5cuXHDlyBKVSycCBA7l+/TqRkZEsX550n6SVlVWK+WJiYoiJiVG9joyMTPc5f9eiJU8eP2bc2FGEhYbi5u7B1u27sLOz+/zGX6h7i2oA7F3qrza/66hVrP7rFACFnW0Z16cRVpYm3Hn4jJ9/3c3s1f+orV/G1YkRPXwwMzHgZkgYvSeuZe2OM5mWGzTzfmX3bJJLcmWW8+fO4l27hur1kEEDAGjbrgNLlq3QUKok2vh+ZYSvvSAq44iKDOHr68vq1asxMjJSzatXrx6FCxdm48aNXL9+XfWHNn/+fIYMGUJERAQ6Ojp4eXkRGRnJ+fPnVdtOmDCBI0eOsHv3btW8+/fv4+joyM2bN4mKisLT05OQkBCcnJxSzJOae0THjBnD2LFjk81PzziimSUt44hmpfSOIyqEEJqgLeOImjVdmCHjiEZt6iHjiIqvW40aNQgICFBNs2fP5vr161SsWFHt117lypWJiori/v37qnmenp5q+7p48SIHDhzAzMxMNRUtWhSAoKAg3N3dqVWrFiVLluS7775jyZIlPH/+PM2Zhw0bRkREhGq6d+/eF569EEIIkXaaGEd00qRJlC1bFnNzc2xtbWnSpAk3b95UW8fLyyvZMXr06KG2zt27d/Hx8cHExARbW1sGDRpEfHw8aSFN8yLDmJqafnEPeVNTU7XXUVFRNGzYkClTpiRb18HBAV1dXfbu3cvx48fZs2cPc+bMYfjw4Zw6dSpNHaQMDQ0xNDT8osxCCCFEumXE8Etp3P7QoUP4+flRtmxZ4uPj+fHHH6lTpw7Xrl1T+/e4a9eujBs3TvXaxMRE9d8JCQn4+Phgb2/P8ePHefToEe3bt0dfX5+ffvop1VmkICoyVbFixdi4cSNKpVL1i+3YsWOYm5uTN2/ej25XunRpNm7ciLOzs6pT04cUCgWVK1emcuXKjBo1CicnJzZv3syAAQMwMDAgISEhU85JCCGEyM527dql9nrFihXY2tpy7tw5qlWrpppvYmLy0eGx9uzZw7Vr19i3bx92dnZ4eHgwfvx4hgwZwpgxYzAwMEhVFmmaF5mqV69e3Lt3jz59+nDjxg22bt3K6NGjGTBgADo6H7/8/Pz8ePbsGd9//z1nzpwhKCiI3bt307FjRxISEjh16hQ//fQTZ8+e5e7du2zatInHjx9TrFgxAJydnbl06RI3b97kyZMnxMXFZdUpCyGEEKmWkU3zkZGRatP7nXE/JSIiAkjesff333/H2toaV1dXhg0bxqtXr1TLTpw4QcmSJdU6i3l7exMZGcnVq1dTff5SIyoyVZ48edi5cyeDBg3C3d0dKysrOnfuzIgRIz65Xe7cuTl27BhDhgyhTp06xMTE4OTkRN26ddHR0cHCwoLDhw8zc+ZMIiMjcXJyYtq0adSrVw9Iak44ePAgZcqUISoqKkuHbxJCCCFSS6Egzfd4Jt9J0v85OjqqzR49erTaCDUpSUxMxN/fn8qVK+Pq6qqa37p1a5ycnMidOzeXLl1iyJAh3Lx5k02bNgEQGhqabMSCt6/T8thVKYiKDLFixYqPLqtevTqnT5/+6PKDBw+mOL9QoUKqC/5DxYoVS9a08D4bGxv27Nnz0eVCCCHEf829e/fUes2npg+En58fV65c4ejRo2rzu3XrpvrvkiVL4uDgQK1atQgKCqJAgQIZllma5oUQQgghNERBBjTN/79K1MLCQm36XEG0d+/ebN++nQMHDnyy3wZA+fLlAbj1/wce2NvbExam/sjVt6/T8thVKYgKIYQQQmiIJoZvUiqV9O7dm82bN/PPP/+karSZgIAAIGnkGoCKFSty+fJlwsPfPZ1v7969WFhYULx48VRnkaZ5IYQQQoiviJ+fH2vWrGHr1q2Ym5ur7um0tLTE2NiYoKAg1qxZQ/369cmVKxeXLl2if//+VKtWDTc3NwDq1KlD8eLFadeuHT///DOhoaGMGDECPz+/NA2LKDWiQgghhBCaosigKQ0WLFhAREQEXl5eODg4qKb169cDYGBgwL59+6hTpw5Fixblhx9+oFmzZvz111+qfejq6rJ9+3Z0dXWpWLEibdu2pX379mrjjqaG1IgKIYQQQmhKBjxrXvkFTfOf4ujoyKFDhz67HycnJ3bu3JmmY39IakSFEEIIIYRGSI2oEEIIIYSGfElno5T2kV1JQVQIIYQQQkO+9oKoNM0LIYQQQgiNkBpRIYQQQghN+YJe7ynuI5uSgqgQQgghhIZ87U3zUhAVIpt4cHSmpiOkqPmvpzUdIUXrO5bVdIQU6Wjpvxfa/A/ZueDnmo6QolJOOTQdIUVxCYmajpAtxMQlaDqCQAqiQgghhBAaIzWiQgghhBBCI772gqj0mhdCCCGEEBohNaJCCCGEEBrytdeISkFUCCGEEEJTZPgmIYQQQgihCV97jajcIyqEEEIIITRCakSFEEIIITTka68RlYKoEEIIIYSGfO0FUWmaFyKDHT1ymGZNGuKSLzfG+gq2bd2ikRzHjx6h9XdNKF4wH7nM9Nnx11a15X7dO5HLTF9t+q6JT4ZmKOFgzqi6hVjZ1oPt3ctRwTmH2vLt3culODV1t1etk9vSiBHehfi9fSk2dPRkSqNilMxtnqE5P2fa1MmYGeow+Af/LD1uSqZOmUSViuWwtbLAKY8dLZp9y783b2o6llZc981ruFOlsFWyadqYQap1rlw4Td/2jantnpc6pfLh19qHmDevszzrkkULKOfpjr21JfbWltSoVondu/7O8hzHjh6mZbPGFM3vSA4TPbZvU/+eUCqVTBw3miIuebG3MqOxTx2CbgV+tblExpOCqBAZLDo6mpJu7sycPU+jOV69iqaEqxs/T5/90XVqfePNtaB7qmnJ8tUZmsFIT4fbT1+x8OidFJe3/e2C2jTz4G0SlUqO3X73SMfRdQujq1AwfPsN/DdeIfjZK0bXLUwOY/0Mzfox586eYdmSxbiWdMuS433OkSOH6d6zFwePnOCvnXuIi4+joY830dHRGs2lDdf9ko372XrsumqasXwTADXqNQaSCqE/dP6OspVrsPjPvSzduJ+mbbug0Mn6fwrz5MnLuAmTOHriLEeOn6G6Vw1aNm/CtWtXszTHq+hoSpZ0Y+qMOSkunzV9KosWzGX67PnsO3QcExNTmjaqz5s3b77KXJlCkUFTNiVN80JkMO+69fCuW0/TMahdpy6169T95DoGhobY2dl/cp30OHcvgnP3Ij66/MXrOLXX5Z1ycvlhJGEvYwCwMNIjTw4jZh+6TcizpFqrlafu0aCEHU5Wxrx4EJdsnxkpKiqKzh3aMnfBYqZMnpipx0qtbdvVa80WL12OUx47Lpw/R5Wq1TSUSjuu+5xW1mqvVy+eSZ58LpQqVxmA2T8Np3n7brTr7q9aJ1/+QlkZUaV+g4Zqr8eMm8jSxQs5c+okxYuXyLIc33jX4xvvlD83pVLJgrmzGTTkR3waNgJg4dIVFHbOzY6/ttLsu5ZfXa7MIE3zQoiv1rEjhyjinJtypUrwQz8/nj19qrEsOYz1KJvPkj03nqjmRb6J597z19QsbI2hng46CqhbzJbnr+K49TjzawAH9OuNd7361KhVO9OP9aUiI5IK+jlzWmk4iXaJi41lz9Y/8GnWBoVCwfOnj7l28Rw5rWzo0dKbhhWL0LtNAy6ePanpqCQkJPDHhnVER0dTrkJFTcdRuRMSTFhYKNVr1FLNs7S0xLNsOU6f0tz7pq25xJeRGlEhvlK1anvToNG3ODk5Exx8mwljRtKiaQN2/3MUXV3drM9T2JrXcYkcD36mNn/EjhuM8C7MH508USqTalFH77xJdGxCpub5Y8M6Ai6c5/Dx05l6nPRITExk0MD+VKxUmRKurpqOo1UO79tB1MsI6jf9HoAH90IAWDZ3Cn5DxlGoWEl2bVmHf4cm/LbjGI7OBbI845Url6lZrRJv3rzBzMyMtRs2UaxY8SzP8TFhYaEA2Nraqc23tbUj/P/LNEFbc30pqRH9jwoJCUGhUBAQEKDpKOILHDx4EIVCwYsXLzQd5T+r6XctqefTkOKuJfFp2Ji1f27hwrmzHD18SCN5ahex4eCtp8QlKNXm96ziTMTrOIZsvc6AzVc5GfKcUXULk9Mk8+4RvX/vHoN/8GfZytUYGRll2nHSy7+vH9euXmHl6rWajqJ1dvy5mvLVamNt5wCAMjERgMYtffFp1obCxd3o++NP5MtfkB1//q6RjIULF+HE6QscOnqSLt160L2LL9evX9NIFqE5ChSqwugXT9n4JlGNFkR9fX1p0qRJsvlSCEmdsLAw9PX1WbduXYrLO3fuTOnSpbMsj7OzMzNnzkzzdl5eXvj7+6vNq1SpEo8ePcLS0jJjwonPcnbJT65c1gTfvpXlxy5hb4ZjTmP2XA9Xm++ex4Ky+XIwZd8trodFEfTkFQuO3iE2IZFaha0/srf0u3D+HI/Dw6lc3hNLE30sTfQ5evgQC+bNwdJEn4SEzK2NTY3+/Xrz984d7NrzD3nz5tV0HK0S+uAeZ48fouF37VTzctkk3QvtXLCI2rpO+QsT9uh+luZ7y8DAgAIFC1KqtCfjJkzCtaQ78+fM0kiWlLy9fzw8PExtfnh4GLaZeG/552hrLvFl/pM1orGxsZqOkCXs7Ozw8fFh2bJlyZZFR0ezYcMGOnfurIFk6WdgYIC9vX22bm7Ibh48uM+zZ0+xs3fI8mN/U9SGwMfRBD9TH0bHUC/pK0qpXklKolJJZl4aXjVrcer8JY6fuaCaSnuWoeX3bTh+5oJGbl14S6lU0r9fb7Zt3cLfu/fj7OKisSzaasfG38mZy4aKXnVU8xzy5sPa1oG7wepD/NwLCcI+t2NWR0xRojKRGC3698vJ2QU7O3sOHfxHNS8yMpJzZ05TrnwFyZVB0l0bmgFN+5qULQqiR48epWrVqhgbG+Po6Ejfvn3VhipxdnZm/PjxtG/fHgsLC7p166ZaduPGDSpVqoSRkRGurq4cOvSu2TEhIYHOnTvj4uKCsbExRYoUYdas5L9Gly1bRokSJTA0NMTBwYHevXurlr148YIuXbpgY2ODhYUFNWvW5OLFi2rbL1iwgAIFCmBgYECRIkVYtWqVallKtxC8ePEChULBwYMHAXj+/Dlt2rTBxsYGY2NjChUqxPLly4GkWs/9+/dz9+5dtWP+8ccfxMfH06ZNGxITE5k0aZLqPN3d3fnzzz/V1t+2bRuFChXCyMiIGjVqsHLlymS10p/6HLy8vLhz5w79+/dX+6N4+vQp33//PXny5MHExISSJUuydu27ZkRfX18OHTrErFmzVNuFhISkWCu+ceNG1efg7OzMtGnT1M7B2dmZn376iU6dOmFubk6+fPlYvHhxss8zs0VFRXExIICL//9MQ4KDuRgQkOwzyoocly8FcPlSUo67d4K5fCmA+/fuEhUVxejhQzhz+iR374Rw6MA/tGvZlPwFClKzdp1P7zgNjPR0cMllgksuEwDszA1xyWWCjZmBah1jfR2q5LdKVhsKcCMsiqiYePrXyI+LlTG5LY3oWMERO3NDzt55kWE5P2Rubk6JEq5qk4mpKVZWVpQoodl7Mf37+rFuze+s+O13zMzNCQ0NJTQ0lNevs34szPdpy3WfmJjIzk1rqNukFXp677pBKBQKWnfpzZ+/LebArq3cv3ObJTMncud2IA2+a5ulGQFGjRjG0SOHuRMSwpUrlxk1YhhHDh2kZavWWZojKiqKSxcDuHQxAIA7d4K5dDGAe/fuolAo6Nm7L79M+Ymd2//i6pXL9Ojii71DbnwaNv4qc2UKGb5JuwUFBVG3bl0mTJjAsmXLePz4Mb1796Z3796qwhjAL7/8wqhRoxg9erTa9oMGDWLmzJkUL16c6dOn07BhQ4KDg8mVKxeJiYnkzZuXP/74g1y5cnH8+HG6deuGg4MDLVq0AJIKkQMGDGDy5MnUq1ePiIgIjh07ptr/d999h7GxMX///TeWlpYsWrSIWrVq8e+//2JlZcXmzZvp168fM2fOpHbt2mzfvp2OHTuSN29eatSokar3YOTIkVy7do2///4ba2trbt26pfpHp379+tjZ2bFixQpGjRql2mb58uU0bdqUHDlyMHHiRFavXs3ChQspVKgQhw8fpm3bttjY2FC9enWCg4Np3rw5/fr1o0uXLly4cIGBAwem6XPYtGkT7u7udOvWja5du6q2e/PmDZ6engwZMgQLCwt27NhBu3btKFCgAOXKlWPWrFn8+++/uLq6Mm7cOABsbGwICQlRO/65c+do0aIFY8aMoWXLlhw/fpxevXqRK1cufH19VetNmzaN8ePH8+OPP/Lnn3/Ss2dPqlevTpEi6s1xb8XExBATE6N6HRkZmarP5FPOnzuLd+13n+2QQQMAaNuuA0uWrUj3/lMr4Pw5Gtd/19t7xNCkQb1btWnHLzPncfXKZdb9voqIiBfYO+SmRs3aDBs5FkNDwwzLUMjGlEmNiqled63kBMC+m4+ZeTAYgGoFcwFwKOhZsu0j38Qzeue/tC+Xl4kNi6Gno+Du89dM2B2YrPb0a7Fk0UIAtWsMYNHSZbRr76uBREm05bo/e/wgYQ/v49O8TbJlLXx7EhMTw5yfhhMZ8YKCRUswY/km8uTL+lrlx4/D6dq5A6GPHmFhaYmrqxtbt++iVu1vsjTHhfNnaVj33ffE8CFJ3/3ft23PgsXL6DdgENHR0fj37kFExAsqVKrMxq07Mv3eaW3NJTKeQqn8sNEr6/j6+rJ6dfLOAAkJCbx584bnz58zcOBAdHV1WbRokWr50aNHqV69OtHR0RgZGeHs7EypUqXYvHmzap2QkBBcXFyYPHkyQ4YMASA+Ph4XFxf69OnD4MGDU8zUu3dvQkNDVTWGefLkoWPHjkyYMCHZukePHsXHx4fw8HC1f7wLFizI4MGD6datG5UrV6ZEiRJqNXMtWrQgOjqaHTt2qHJeuHABDw8PIKlGNGfOnBw4cAAvLy8aNWqEtbV1ik3wAMOGDWP9+vUEBQWhUCgICgqiUKFC7N27lypVqmBlZcW+ffuoWPHdsCBdunTh1atXrFmzhqFDh7Jjxw4uX76sWj5ixAgmTpzI8+fPyZEjB126dEnV5+Dv75/sfs8PNWjQgKJFi/LLL78ASbWpHh4eaveXHjx4kBo1aqiO36ZNGx4/fsyePXtU6wwePJgdO3Zw9WrSANDOzs5UrVpVVeOsVCqxt7dn7Nix9OjRI8UsY8aMYezYscnmhz2NwMLC4pPnkdVexcRrOkKK2q8+r+kIKVrfsaymI6RIR0trLrS5ae9c8PPPr6QBpZxyaDpCiuISEjUdIVuIjIwkn70VERGa+b6PjIzE0tISp15/oGNokq59Jca84s787zR2Lumh8ab5GjVqEBAQoDYtXbpUtfzixYusWLECMzMz1eTt7U1iYiLBwcGq9cqUKZPi/t8vfOnp6VGmTBmuX7+umjdv3jw8PT2xsbHBzMyMxYsXq5qSwsPDefjwIbVq1Uq237fZoqKiyJUrl1q+4OBggoKCALh+/TqVK1dW265y5cpqGT6nZ8+erFu3Dg8PDwYPHszx48fVlnfq1Ing4GAOHDgAJNWGOjs7U7NmTW7dusWrV6/45ptv1DL+9ttvqow3b96kbFn1f7TLlSuX7FxT8zl8KCEhgfHjx1OyZEmsrKwwMzNj9+7daW6u+9j7GBgYqNZxxM3t3dNvFAoF9vb2hIcnb/J9a9iwYURERKime/fupSmXEEIIkR5f+z2iGm+aNzU1pWDBgmrz7t9/14MxKiqK7t2707dv32Tb5suXT20/abVu3ToGDhzItGnTqFixIubm5kydOpVTp04BYGxs/Mnto6KicHBwUN3L+b4cOXKkKoOOztvOGO8qpuPi1J8WU69ePe7cucPOnTvZu3cvtWrVws/PT1WjWKhQIapWrcry5cvx8vLit99+o2vXrigUCqKiogDYsWMHefLkUdtvWppgU/s5fGjq1KnMmjWLmTNnUrJkSUxNTfH398+0DmX6+upD+igUChITP147YGhomKFN0UIIIYRIPY0XRD+ndOnSXLt2LVlhNbVOnjxJtWpJj72Lj4/n3Llzqs5Gx44do1KlSvTq1Uu1/ttaQkjqsODs7Mz+/ftTvJ+zdOnShIaGoqenh7Ozc4rHL1asGMeOHaNDhw6qeceOHaN48aRBi21sbAB49OgRpUqVAkhx7FMbGxs6dOhAhw4dqFq1KoMGDVIVRCGp01LPnj1p1KgRDx48UN03Wbx4cQwNDbl79y7Vq1dPMWORIkXYuXOn2rwzZ84kO9fPfQ4GBgbJhrU5duwYjRs3pm3bpM4AiYmJ/Pvvv6rz/9h2H3r7Pn6478KFC2u0B7MQQgiRHgoF6R4FJBtXiGq+af5zhgwZwvHjx+nduzcBAQEEBgaydetWtZ7rnzJv3jw2b97MjRs38PPz4/nz53Tq1AlIqkk8e/Ysu3fv5t9//2XkyJHJCmBjxoxh2rRpzJ49m8DAQM6fP8+cOXMAqF27NhUrVqRJkybs2bOHkJAQjh8/zvDhwzl79iyQ1FlqxYoVLFiwgMDAQKZPn86mTZtUnYGMjY2pUKECkydP5vr16xw6dIgRI0aoZRg1ahRbt27l1q1bXL16le3bt1OsWDG1db777jv09fXp3r07derUwdExaTgSc3NzBg4cSP/+/Vm5ciVBQUGqc1i5ciUA3bt358aNGwwZMoR///2XDRs2sGLFCuDdfWOp+RycnZ05fPgwDx484MmTJ6r3eO/evRw/fpzr16/TvXt3wsLUx35zdnbm1KlThISE8OTJkxRrMH/44Qf279/P+PHj+ffff1m5ciVz585N1qlKCCGEyE6SCqLpbZrX9Fl8Oa0viLq5uXHo0CH+/fdfqlatSqlSpRg1ahS5c+dO1faTJ09m8uTJuLu7c/ToUbZt24a1ddJA2N27d6dp06a0bNmS8uXL8/TpU7XaUYAOHTowc+ZM5s+fT4kSJWjQoAGBgUnj0CkUCnbu3Em1atXo2LEjhQsXplWrVty5cwc7u6RHjzVp0oRZs2bxyy+/UKJECRYtWqRqQn9r2bJlxMfH4+npib+/f7KOUQYGBgwbNgw3NzeqVauGrq5uskHsTUxMaNWqlVpB+63x48czcuRIJk2aRLFixahbty47duzA5f/jD7q4uPDnn3+yadMm3NzcWLBgAcOHDwfeNd+n5nMYN24cISEhFChQQFXTO2LECEqXLo23tzdeXl7Y29sne4jB2w5pxYsXx8bGJsX7R0uXLs2GDRtYt24drq6ujBo1inHjxqn1mBdCCCFE9qLRXvNCe02cOJGFCxd+dZ133vZilF7zqSe95tNGes2nnfSaTxvpNZ862tJrPn/fP9E1THs/l/clxERze3bzbNlrXuvvERVZY/78+ZQtW5ZcuXJx7Ngxpk6dmurbH4QQQgjxZTKi17s2/5D8HCmICgACAwOZMGECz549I1++fPzwww8MGzZM07GEEEII8R8mBVEBwIwZM5gxY4amYwghhBBfla+917wURIUQQgghNERHR4FOOm8eV2rrzeepoPW95oUQQgghxH+T1IgKIYQQQmiINM0LIYQQQgiN+Np7zUvTvBBCCCGE0AipERVCCCGE0BBpmhdCCCGEEBohTfNCCCGEEEJogNSICpFNGBvoajpCitb5ltF0hBQN3n5d0xFSNKl+UU1HSFFCovY+n9whh5GmI6QoIVGp6Qgpio3Xzs/SxFC7ihx6utpRF/e114hq11UhhBBCCPEV+drvEdWOnwNCCCGEEOKrIzWiQgghhBAaoiADmubJvlWiUhAVQgghhNAQaZoXQgghhBBCA6RGVAghhBBCQ6TXvBBCCCGE0AhpmhdCCCGEEEIDpCAqhBBCCKEhb5vm0zulxaRJkyhbtizm5ubY2trSpEkTbt68qbbOmzdv8PPzI1euXJiZmdGsWTPCwsLU1rl79y4+Pj6YmJhga2vLoEGDiI+PT1MWKYgKkQkWzp9HkYLO5DAzomql8pw5fVrTkZg6ZRJVKpbD1soCpzx2tGj2Lf9+8MWjKQ8fPKCLbzvy5bbBJocp5T3dOX/ubKYdr2AuE3pUdGRivULMa1ocNwdzteXtPHMzr2lxtcmvcj61dUz0dfAtk4dfGhZhaoMitCntgKFu5rePvXz5kqED++Na2AW7nKZ841WFc2fPZPpxP3T86GG+b96Y4gUcsTLVY8dfWz+67oC+vbAy1WPB3FmZmun35YupX70c7vntcM9vR/N6Xhzcv1u1/HFYKD/06kz5Es64OlvTqFZFdv21JVMzfUxCQgLjx46iZNEC2OY0xa14IaZMmoBSmbVPazpx7AhtWzShZGEnbC0M2Lld/XMMDw+jT4/OlCzshJOdJS2/bcDtW4FZmjEl06ZOxsxQh8E/+Gs6Srq9bZpP75QWhw4dws/Pj5MnT7J3717i4uKoU6cO0dHRqnX69+/PX3/9xR9//MGhQ4d4+PAhTZs2VS1PSEjAx8eH2NhYjh8/zsqVK1mxYgWjRo1KUxa5R1SIDPbHhvUMGTSAOfMWUrZceebOnkkjH28uXr2Jra2txnIdOXKY7j174elZlvj4eEaPGk5DH2/OX7yKqampxnI9f/6cb2pUpWp1LzZt3YG1tQ1BtwLJkSNnph3TQE+H+xFvOHHnBd0qOKa4ztXQKFafe6B6HffB4xx9y+bF0kiPuUfvoqsDbT1z833p3Kw48+DDXWWoPj27cv3aVRYtW4m9Q242rP2dJj51OHX+Crnz5MnUY78vOjoa15JutGnfkfbfN//oetu3beHs6VM4OOTO9Ez2ufMwaOQ4nPMXBKWSjetX06N9C7btP0HhosUZ2LsrkZEvWLzqD3JaWbNt03r6dG3Llr1HKVHSI9PzvW/GtJ/5dclCFi5ZTrHiJbhw7iy9unfGwsKSnn59sizHq+hoSri68X07Xzq2aaG2TKlU0uH75ujr6/Pb2o2YW5izYO4smjeux5HTFzX2vXHu7BmWLVmMa0k3jRz/v2DXrl1qr1esWIGtrS3nzp2jWrVqRERE8Ouvv7JmzRpq1qwJwPLlyylWrBgnT56kQoUK7Nmzh2vXrrFv3z7s7Ozw8PBg/PjxDBkyhDFjxmBgYJCqLFIjKkQGmz1zOh07d6W9b0eKFS/OnPkLMTYxYeWKZRrNtW3737Rr70vxEiVwc3dn8dLl3Lt7lwvnz2k014xpP5MnryMLlyyjTNlyOLu4UOubOuQvUCDTjnktLIrt1x5z8eHLj64Tn5hIZEyCanod9+753XbmBpSwN+P38w8Jef6aoKev+eNiKJ55LbA0yrzf969fv2bblk2MmziZylWqUaBAQYaNGI1LgYL8umRhph03Jd9412P46PE0aNTko+s8fPiAIT/0Y9Gy39DT18/0TLW8fahRuy4u+QviUqAQA38ci4mpGQHnklokzp85SfvOPXEvXZZ8zi70HjAUC8scXLl4IdOzfejUyeP4NGhE3Xo+ODk506Rpc2rW+oZzZ7O29aRWnboMGzUOn4ZNki27fSuQc2dO8fOMOZTyLEPBQkWYOmMub16/ZvOf67M051tRUVF07tCWuQsWkyNn5v1YzUoZ2TQfGRmpNsXExKQqQ0REBABWVlYAnDt3jri4OGrXrq1ap2jRouTLl48TJ04AcOLECUqWLImdnZ1qHW9vbyIjI7l69Wqqz18KokJkoNjYWC6cP0fNWu/+eHV0dKhZszanT57QYLLkIv//xZMzp5VGc+zc/helPT1p17oFLo72VC7vyfJfl2g0E0Aha1Mm1y/MqG8K0MrDHlMDXdWy/FYmvIpN4O6LN6p5N8KjUSrB2co40zLFx8eTkJCAoZGR2nxjI2NOHj+Wacf9EomJifTs3IE+/j9QrHiJLD9+QkICf23+g9evoilVpjwApctWYMfWP3nx/BmJiYn8tfkPYmLeUL5StSzPV75CJQ4d+IfAwH8BuHzpIidOHOObOnWzPMvHxMQmFWIMDd9dbzo6OhgYGnLqhGautwH9euNdrz413vuOzfYyoln+/03zjo6OWFpaqqZJkyZ99vCJiYn4+/tTuXJlXF1dAQgNDcXAwIAcOXKorWtnZ0doaKhqnfcLoW+Xv12WWtI0L0QGevLkCQkJCdjaqv9x2trZcfPmDQ2lSi4xMZFBA/tTsVJlSvz/i0dTQoJvs3TxQnr37c/AwcM4d/YMg3/wx8DAgDbtOmgk07WwKAIeRvI0Og5rUwMalbClVyVjfjkYjBKwMNLjZYz6DfmJSngVm4CFYeZ9rZqbm1OufEWmTppIkSLFsLWz488Nazl96gT5CxTMtON+iVnTfkZXT4/uvbKumRng5rUrNK9fg5iYN5iYmjF/xToKFSkGwJylq+jbtT2eRfKip6eHkbEJC5avwzl/5tW+f8yAgUN4GRlJGffi6OrqkpCQwKixE2j5fZssz/IxhQoXJa9jPiaOHcEvM+djYmrKwnmzePjgPmFpKGhklD82rCPgwnkOH9f8Pffa6t69e1hYWKheGxoafnYbPz8/rly5wtGjRzMz2kdJjaj4rBUrViT7VfQ5vr6+NGnSJFPyiPTz7+vHtatXWLl6raajkJiYiHup0owZPxF3j1J06tIN305d+HXpYo1lOnc/ksuPongYGcOlRy9ZcPwuzlbGFLbR3L20by1athKlUknRAo7YWBqzcN5cmrdohY6O9nydB1w4x6L5c5i3eFmWD7TtUrAwf/1zko27DtHGtyuD+3Qj8OZ1AKZPHkdk5At++3MHW/YcpXOPPvTp2o6b165kaUaATX9uYMO6Nfy6YjVHTpxl4dLlzJ45jd9Xr8zyLB+jr6/P8tUbCLoVSGEnO5zsLDl2+BC1vqmb5dfb/Xv3GPyDP8tWrsbogxaB7C4jm+YtLCzUps8VRHv37s327ds5cOAAefPmVc23t7cnNjaWFy9eqK0fFhaGvb29ap0Pe9G/ff12ndTQnm8uoREfKzAePHgQhULBixcvaNmyJf/++2/Wh8uGrK2t0dXVJTxc/Y8z/L0/Xk3r3683f+/cwa49/6h98WiKvb0DRYsWU5tXpGhR7t+7q6FEyT19FcfLmHhszJLuc4x8E4/5BzWfOgowMdAlMiZtQ5ekVf78Bdi59wAPn0RyLfAOB46eJC4uDmcXl0w9blqcOHaUx4/DcSvigo2FITYWhty7e4eRwwbhXixzax8NDAxwzl+Aku6lGTRiHEWLl2TF4nncCb7Nql8XMnnmQipXq0ExVzf6DhpOSffSrFq2KFMzpWTkj0PoP3AIzVu0ooRrSb5v3Q6/Pv5Mnzoly7N8inup0hw4dpZb9x5zOfAu6zdv5/mzpzg5Z+31duH8OR6Hh1O5vCeWJvpYmuhz9PAhFsybg6WJPgkJCVmaJyNpote8Uqmkd+/ebN68mX/++QeXD74/PD090dfXZ//+/ap5N2/e5O7du1SsWBGAihUrcvnyZcLDw1Xr7N27FwsLC4oXL57qLNI0Lz7L2NgYY+PMu+/tv8TAwIBSpT058M9+GjVuAiTV+B04sJ8evXprNJtSqWSAfx+2bd3C7r0HtKbgUqFiJQI/+KFzKzAQx3xOGkqUXA5jPUwNdIl4k1TIvP3sFSYGujjmMOLe/+8TLWxjikIBIc9eZ0kmU1NTTE1Nef78Of/s28PYiZOz5Lip0fL7tlSvUUtt3neN69Pi+za0buebpVkSlYnExsby5vUrgGQ1ebq6uiQqE1PaNFO9ev0KHR310oOuri6JiVmfJTUsLC2BpA5MARfOMWTEmCw9vlfNWpw6f0ltXs+unShcpCj9Bw5GV1f3I1uKlPj5+bFmzRq2bt2Kubm56p5OS0tLjI2NsbS0pHPnzgwYMAArKyssLCzo06cPFStWpEKFCgDUqVOH4sWL065dO37++WdCQ0MZMWIEfn5+qbol4C2pERWflVLT/IQJE7C1tcXc3JwuXbowdOhQPDw8km37yy+/4ODgQK5cufDz8yMuLg6AuXPnqm6KBtiyZQsKhYKFC9/1/K1duzYjRowAICgoiMaNG2NnZ4eZmRlly5Zl3759qnXHjRuntr+3PDw8GDlyZHpOP836+g9g+a9LWP3bSm5cv05fv568io6mfYeOWZrjQ/59/Vi35ndW/PY7Zv//4gkNDeX166wpOH2MX19/zpw+ydQpkwgKusWGdWtY/usSunXvmWnHNNRVkNfSkLyWSV+WuUz1yWtpSE5jPQx1FXzraotzTmOsTPQpYmNK9wqOPI6K5XpY0hh7YS9juRoaRevSDjjlNCK/lTEt3O05dz9SVVjNLPv27mbfnl2EhATzz/69NKxbi0KFi9K2fdZeX1FRUVy+GMDliwEA3AkJ5vLFAO7fu4tVrlwUL+GqNunp62NrZ0+hwkUyLdPUCaM4feIo9+/e4ea1K0ydMIpTxw7TuFlL8hcqgpNLAUYM7MPF82e4E3ybpfNncfTQfr6p1zDTMn1MvfoN+GXKJHb9vYM7d0L4a+tm5s6eQcNPjEKQGaKiorh8KYDLlwIAuBsSwuVLAaoWiW2b/+TYkUOEBN/m7x3b+K5Jfeo1aESNWt9kaU5zc3NKlHBVm0xMTbGysqJECc3e555emhjQfsGCBURERODl5YWDg4NqWr/+3WgIM2bMoEGDBjRr1oxq1aphb2/Ppk2bVMt1dXXZvn07urq6VKxYkbZt29K+fXvGjRuXpixSIyrS7Pfff2fixInMnz+fypUrs27dOqZNm5asav/AgQM4ODhw4MABbt26RcuWLfHw8KBr165Ur16dvn378vjxY2xsbDh06BDW1tYcPHiQHj16EBcXx4kTJxg6dCiQ9GVZv359Jk6ciKGhIb/99hsNGzbk5s2b5MuXj06dOjF27FjOnDlD2bJlAbhw4QKXLl1S+8P5UExMjNrwFpGRkel+f75r0ZInjx8zbuwowkJDcXP3YOv2Xcl6F2a1JYuSCvnetWuozV+0dBnt2vtqIFESzzJlWbNhI2NGDmfKT+NxcnZh8tTpmdppI19OY/yrOateN3dLum3i5J0XrLvwiNyWRpTPlwNjA10iXsdxPTya7dfCiX9vLNEVZ+7TwsOBvlWcUAIBDyL542Lmd+CIjIhg7KjhPHxwn5xWVjRq3JSRYyegnwXDI70v4PxZGtV713N5xNCBAHzfpj3zFmtmqLKnT8IZ2LsLj8NCMbOwpGgxV1as30YVr6Ta2V/Xbmbq+JF0bfsdr15F4eRcgKlzllCjdtb3VJ86fTYTxo7ih369efw4HHuH3HTs3I2hP2btD+eLF87xrc+7QuWoHwcB0LJ1O+Ys/JWw0FBG/TiYx+Fh2Nk70KJVGwYMGZ6lGf/rvqRpPaV9pEVqHpxgZGTEvHnzmDdv3kfXcXJyYufOnWk7+AcUyqx+jIPQKr6+vqxenfzm74SEBN68ecPz58/ZsmUL/v7+qpuWK1SoQJkyZZg7d65q/SpVqhAVFUVAQIBqvwcPHiQoKEjVZNKiRQt0dHRYt24dSqUSGxsbFi5cSPPmzSlVqhQtW7Zk1qxZPHr0iGPHjlGjRg1evHiBiYlJitldXV3p0aMHvXsnNXnXr18fZ2dn5s+fD0Dfvn25fPkyBw4c+Oj5jxkzhrFjxyabH/Y0Qq3noTbQ1j/VhETtzDVkh/aMUvC+SfWLajpCirT1cwR4Hh2r6QgpsjFPffNjVnoTp533S5pk4ogSXyIyMpLcNjmIiNDM931kZCSWlpZUmLALPaP0dYSMfxPNyRF1NXYu6SFN84IaNWoQEBCgNi1duvSj69+8eZNy5cqpzfvwNUCJEiXU7ttxcHBQ3dSsUCioVq0aBw8e5MWLF1y7do1evXoRExPDjRs3OHToEGXLllUVQqOiohg4cCDFihUjR44cmJmZcf36de7efdehpWvXrqxdu5Y3b94QGxvLmjVr6NSp0yfPfdiwYURERKime/fuff4NE0IIIUSG0K6fJ0IjTE1NKVhQfQzC+/fvp3u/HzYVKhQKtRvxvby8WLx4MUeOHKFUqVJYWFioCqeHDh2ievXqqnUHDhzI3r17+eWXXyhYsCDGxsY0b96c2Nh3NSUNGzbE0NCQzZs3Y2BgQFxcHM2bf/zRg5A0xlpabqoWQgghMtKX3OOZ0j6yK6kRFWlWpEgRzpw5ozbvw9epUb16da5du8Yff/yBl5cXkFQ43bdvH8eOHVPNAzh27Bi+vr58++23lCxZEnt7e0JCQtT2p6enR4cOHVi+fDnLly+nVatW0ttfCCGEVtPE8E3aRGpERZr16dOHrl27UqZMGSpVqsT69eu5dOkS+fPnT9N+3NzcyJkzJ2vWrGH79u1AUkF04MCBKBQKKleurFq3UKFCbNq0iYYNG6JQKBg5cmSKw5x06dKFYsWSxqQ8dky7HnkohBBCCHVSIyrSrE2bNgwbNoyBAwdSunRpgoOD8fX1TfPTLhQKBVWrVkWhUFClShUgqXBqYWFBmTJlMDV9d/P29OnTyZkzJ5UqVaJhw4Z4e3tTunTpZPssVKgQlSpVomjRopQvXz59JyqEEEJkMk0M36RNpNe8yBDffPMN9vb2rFq1SqM5lEolhQoVolevXgwYMCDN27/txSi95lNPW3tbS6/5tNHWzxGk13xaSa/51NGWXvNVJu/JkF7zR4fWyZa95rXrqhDZwqtXr1i4cCHe3t7o6uqydu1a9u3bx969ezWa6/Hjx6xbt47Q0FA6dtTs4PFCCCGE+DwpiIo0UygU7Ny5k4kTJ/LmzRuKFCnCxo0bqV279uc3zkS2trZYW1uzePFicubMqdEsQgghRGp87b3mpSAq0szY2Fjt8ZraQlubroUQQoiPUZABT1bKkCSaIZ2VhBBCCCGERkiNqBBCCCGEhugoFOiks0o0vdtrkhREhRBCCCE0JCMGpM/G5VBpmhdCCCGEEJohNaJCCCGEEBoiveaFEEIIIYRG6CiSpvTuI7uSpnkhhBBCCKERUiMqhBBCCKEpigxoWs/GNaJSEBUim9DWe4ASEhM1HSFF0xoV13SEFBXy36rpCCkKnNlY0xE+ykDPSNMRUqSdf5Fgbqyv6QjZgq6WtGdLr3khhBBCCCE0QGpEhRBCCCE0RPH//6V3H9mVFESFEEIIITREes0LIYQQQgihAamqEb106VKqd+jm5vbFYYQQQgghviYyoH0qeHh4oFAoUCqVKS5/u0yhUJCQkJChAYUQQggh/qu+9l7zqSqIBgcHZ3YOIYQQQgjxlUlVQdTJySmzcwghhBBCfHV0FAp00lmlmd7tNemLOiutWrWKypUrkzt3bu7cuQPAzJkz2bpVOwdqFkIIIYTQRm+b5tM7ZVdpLoguWLCAAQMGUL9+fV68eKG6JzRHjhzMnDkzo/MJkS0tnD+PIgWdyWFmRNVK5Tlz+rSmIwHakevY0cO0bNaYovkdyWGix/Zt6j9glUolE8eNpohLXuytzGjsU4egW4FZnvPokcM0a9IQl3y5MdZXsG3rlkw/pl+dQmwfVI3rv/hwYVJdlnYtR35bM7V1JrVy5+jo2gROb0DApLr82q0cBezU1xnbvCQ7Blfn1owG7Brqlem536cN19jHTJs6GTNDHQb/4K/pKCxZtIBynu7YW1tib21JjWqV2L3rb03H0sh1nxbafH2JL5PmguicOXNYsmQJw4cPR1dXVzW/TJkyXL58OUPDCZEd/bFhPUMGDWD4iNGcOH0eNzd3Gvl4Ex4eLrmAV9HRlCzpxtQZc1JcPmv6VBYtmMv02fPZd+g4JiamNG1Unzdv3mRpzujoaEq6uTNz9rwsO2aFgrlYeTiYxr8cpvXc4+jpKvi9d0WMDd59116+94IfVl+gxoT9tJ13AoUCfvermGwcwQ0n7/LX+YdZlh205xpLybmzZ1i2ZDGuJbVjZJc8efIybsIkjp44y5HjZ6juVYOWzZtw7dpVjebSxHWfWtp8faXH217z6Z2yK4XyY13hP8LY2JgbN27g5OSEubk5Fy9eJH/+/AQGBuLm5sbr168zK6sQmS4yMhJLS0vCnkZgYWHxRfuoWqk8nmXKMnP2XAASExMp6OJIT78+DBo8NCPjakWumLgvHykjh4keq9dtpEGjpOecK5VKiuZ3pHe//vTx/wGAiIgICjvnZv7iZTT7rmWq922or/v5lVLJWF/B+j8306hxk3TvKy3PmrcyM+Di5Ho0n3GUU0FPU1ynaG4L9v5Ygypj9nLnySu1Zf3rF8HbzYG6kw9+9lgZ8az5zLrGEhLT9M9UMlFRUVQp78mM2fOYMnkibm7u/DxtZrr2CRn/rPm89rmYOOlnOnTsnK796GTQ6OYZed1nhIy+viIjI7HLZUlExJd/36fH239vGs8/hL6x2ec3+IS411Fs7VVdY+eSHmmuEXVxcSEgICDZ/F27dlGsWLGMyCREthUbG8uF8+eoWau2ap6Ojg41a9bm9MkTkusz7oQEExYWSvUatVTzLC0t8SxbjtOnTmowmWZYGOkD8OJVbIrLjQ10aVkhH3eeRPPwuWYrAbT5GhvQrzfe9epT471s2iQhIYE/NqwjOjqachUqajqOVtLm60ukT5of8TlgwAD8/Px48+YNSqWS06dPs3btWiZNmsTSpUszI6MQ2caTJ09ISEjA1tZObb6tnR03b97QUCrtzfWhsLBQgOQ5be0I//+yr4VCAaObu3I66Ck3H71UW9a+qjM/NimBqaEet0Jf0mbuceIS0ldrmF7aeo39sWEdARfOc/i49t1LeOXKZWpWq8SbN28wMzNj7YZNFCtWXNOxtJK2Xl8ZQXrNp1GXLl2YMmUKI0aM4NWrV7Ru3ZoFCxYwa9YsWrVqlRkZhRZRKBRs2bIlWxx7zJgxeHh4ZFoeITLTxBZuFHGwwG/52WTLNp+5T93JB2k+4yjBj6OY36kshnryxOYP3b93j8E/+LNs5WqMjIw0HSeZwoWLcOL0BQ4dPUmXbj3o3sWX69evaTqWyGKKDJqyqy/65mrTpg2BgYFERUURGhrK/fv36dw5ffe0iMzn6+tLkyZNNB1D5eDBgygUCl68eJGq9R89ekS9evUyN1Q6WVtbo6urS3h4mNr88LAw7O3tNZRKe3N9yM4uKUuynOFh2NppT87MNv67ktRytafl7GOEvkjeSevlm3hCHkdzKugp3ZeeoaCdGXXdHTSQ9B1tvMYunD/H4/BwKpf3xNJEH0sTfY4ePsSCeXOwNNHX+JMADQwMKFCwIKVKezJuwiRcS7ozf84sjWbSVtp4fYmM8cU/ocPDwzl37hw3b97k8ePHGZlJCDWxsUn3x9nb22NoaKjhNJ9mYGBAqdKeHPhnv2peYmIiBw7s1+i9X9qa60NOzi7Y2dlz6OA/qnmRkZGcO3OacuUraDBZ1hn/XUnqujvQcvYx7j199dn1k3rMgoGGa0S18RrzqlmLU+cvcfzMBdVU2rMMLb9vw/EzF9RGftEGicpEYmJTvh/4a6eN11dG+dp7zaf5m+vly5e0a9eO3LlzU716dapXr07u3Llp27YtERERmZFRZAIvLy/69u3L4MGDsbKywt7enjFjxqitExgYSLVq1TAyMqJ48eLs3btXbXlKNZoBAQEoFApCQkIAuHPnDg0bNiRnzpyYmppSokQJdu7cSUhICDVq1AAgZ86cKBQKfH19Vdl69+6Nv78/1tbWeHt7A8mb5ocMGULhwoUxMTEhf/78jBw5kri4uAx9n75EX/8BLP91Cat/W8mN69fp69eTV9HRtO/QUXKR1IP50sUALl0MAODOnWAuXQzg3r27KBQKevbuyy9TfmLn9r+4euUyPbr4Yu+QG5+G6e/VndacFwMCuPj/zpkhwcFcDAjg7t27mXbMiS3c+LasI31WnCP6TTw25obYmBtipJ/0VZ0vlwl+dQpR0tGS3DmN8XTJycLOZXgTl8g/V9/VFDlbm1I8jwU2FoYY6etSPI8FxfNYoK+buf9Yacs19pa5uTklSriqTSamplhZWVGihKtGMr01asQwjh45zJ2QEK5cucyoEcM4cuggLVu11mguTVz3qaVt11dG0VFkzJRdpbmzUpcuXbhw4QI7duygYsWkXyEnTpygX79+dO/enXXr1mV4SJE5Vq5cyYABAzh16hQnTpzA19eXypUr880335CYmEjTpk2xs7Pj1KlTRERE4O/vn+Zj+Pn5ERsby+HDhzE1NeXatWuYmZnh6OjIxo0badasGTdv3sTCwgJjY2O1bD179uTYsWMf3be5uTkrVqwgd+7cXL58ma5du2Jubs7gwYNTnS8mJoaYmBjV68jIyDSf44e+a9GSJ48fM27sKMJCQ3Fz92Dr9l3Y2dl9fuNMpC25Lpw/S8O673q+Dh8yEIDv27ZnweJl9BswiOjoaPx79yAi4gUVKlVm49YdWX6P3/lzZ/GuXUP1esigAQC0bdeBJctWZMox21dzAeAP/ypq8wesOs8fp+4RE59IuQK56OyVH0sTA568jOHUrSc0mXaEp1HvatJ+buNBxULWqte7hyWdR8VRe7j/LPN612vLNZYdPH4cTtfOHQh99AgLS0tcXd3Yun0XtWp/o9FcmrjuU0uur/+mNI8jampqyu7du6lSRf2L8siRI9StW5fo6OgMDSgyjq+vLy9evGDLli14eXmRkJDAkSNHVMvLlStHzZo1mTx5Mnv27MHHx4c7d+6QO3duIGmIrnr16rF582aaNGnCwYMHqVGjBs+fPydHjhxAUo1oqVKlCA4OxtnZGTc3N5o1a8bo0aOT5Ulpe0iqEY2MjOT8+fNq6ysUCtWxU/LLL7+wbt06zp5N6twxZswYtmzZkuJwY2+NGTOGsWPHJpufnnFEvzbpGUc0M2XkOKIZKS3jiGaljBhHNLOkdxzRzKKtlVAZNY7of522jCPaYvHRDBlHdEO3Kl/HOKK5cuXC0tIy2XxLS0ty5syZIaFE1nBzU3/CiIODg+oJFdevX8fR0VFVCAVUNeBp0bdvXyZMmEDlypUZPXo0ly5dStV2np6en11n/fr1VK5cGXt7e8zMzBgxYkSam4+GDRtGRESEarp3716athdCCCHS62t9zjx8QUF0xIgRDBgwgNDQd2P6hYaGMmjQIEaOHJmh4UTm0tfXV3utUChITExM9fY6OkmXz/uV6h/eo9mlSxdu375Nu3btuHz5MmXKlGHOnJQf7fg+U1PTTy4/ceIEbdq0oX79+mzfvp0LFy4wfPhwVcem1DI0NMTCwkJtEkIIIUTWSNU9oqVKlVLrkRUYGEi+fPnIly8fAHfv3sXQ0JDHjx/TvXv3zEkqslSxYsW4d+8ejx49wsEhaViYkyfVn2xjY2MDJA2r9LY2PKVmcEdHR3r06EGPHj0YNmwYS5YsoU+fPhgYGAB80RAqx48fx8nJieHDh6vm3blzJ837EUIIITQpI3q9Z+de86kqiGrT2JMia9SuXZvChQvToUMHpk6dSmRkpFqhD6BgwYI4OjoyZswYJk6cyL///su0adPU1vH396devXoULlyY58+fc+DAAdWjYJ2cnFAoFGzfvp369etjbGyMmVnq7pMpVKgQd+/eZd26dZQtW5YdO3awefPmjDl5IYQQIotkRK/37HxbcKoKoil1NBH/bTo6OmzevJnOnTtTrlw5nJ2dmT17NnXr1lWto6+vz9q1a+nZsydubm6ULVuWCRMm8N1336nWSUhIwM/Pj/v372NhYUHdunWZMWMGAHny5GHs2LEMHTqUjh070r59e1asWJGqfI0aNaJ///707t2bmJgYfHx8GDlyZLIhqIQQQgihvdLca16I/7K3vRil13zqSa/5tJFe82knvebTRnrNp4629Jpv/etxDEzS12s+9lUUazpXypa95tM8jmhCQgIzZsxgw4YN3L17N1nnkGfPnmVYOCGEEEKI/7KMeFZ8dv7pkeZe82PHjmX69Om0bNmSiIgIBgwYQNOmTdHR0ZFmUSGEEEIIkWppLoj+/vvvLFmyhB9++AE9PT2+//57li5dyqhRo5L1qhZCCCGEEB+no1BkyJRdpbkgGhoaSsmSJQEwMzNTPV++QYMG7NixI2PTCSGEEEL8h6V3MPvsPqh9mguiefPm5dGjRwAUKFCAPXv2AHDmzBkMDQ0zNp0QQgghhPjPSnNB9Ntvv2X//v0A9OnTh5EjR1KoUCHat29Pp06dMjygEEIIIcR/1dsB7dM7ZVdp7jU/efJk1X+3bNkSJycnjh8/TqFChWjYsGGGhhNCCCGE+C/LiKb1bFwOTXuN6IcqVKjAgAEDKF++PD/99FNGZBJCCCGE+CpoorPS4cOHadiwIblz50ahULBlyxa15b6+vslqXN9/oA0kDdfZpk0bLCwsyJEjB507dyYqKirt55/mLT7i0aNHjBw5MqN2J4QQQgghMkF0dDTu7u7Mmzfvo+vUrVuXR48eqaa1a9eqLW/Tpg1Xr15l7969bN++ncOHD9OtW7c0Z0lz07wQQgghhMgYmmiar1evHvXq1fvkOoaGhtjb26e47Pr16+zatYszZ85QpkwZAObMmUP9+vX55ZdfyJ07d6qzZFiNqBBCCCGESJuM7KwUGRmpNsXExHxxroMHD2Jra0uRIkXo2bMnT58+VS07ceIEOXLkUBVCAWrXro2Ojg6nTp1K03GkRlSIbOJk0NPPr6QBZZxzajpCtqKtz3TffyNM0xE+qnohG01HSJG2PtM9PiFR0xGyhf/i++To6Kj2evTo0V/01Mu6devStGlTXFxcCAoK4scff6RevXqcOHECXV1dQkNDsbW1VdtGT08PKysrQkND03SsVBdEBwwY8Mnljx8/TtOBhRBCCCG+djqkv3n67fb37t3DwsJCNf9Lx3dv1aqV6r9LliyJm5sbBQoU4ODBg9SqVSs9UZNJdUH0woULn12nWrVq6QojhBBCCPE1yYhxQN9ub2FhoVYQzSj58+fH2tqaW7duUatWLezt7QkPD1dbJz4+nmfPnn30vtKPSXVB9MCBA2nasRBCCCGEyP7u37/P06dPcXBwAKBixYq8ePGCc+fO4enpCcA///xDYmIi5cuXT9O+5R5RIYQQQggNUSggvbcbp7VCNSoqilu3bqleBwcHExAQgJWVFVZWVowdO5ZmzZphb29PUFAQgwcPpmDBgnh7ewNQrFgx6tatS9euXVm4cCFxcXH07t2bVq1apanHPEiveSGEEEIIjdFRZMyUFmfPnqVUqVKUKlUKSOoHVKpUKUaNGoWuri6XLl2iUaNGFC5cmM6dO+Pp6cmRI0fU7jn9/fffKVq0KLVq1aJ+/fpUqVKFxYsXp/n8pUZUCCGEEOIr4uXlhVKp/Ojy3bt3f3YfVlZWrFmzJt1ZpCAqhBBCCKEhGdlZKTuSgqgQQgghhIZ8SdN6SvvIrr7oHtEjR47Qtm1bKlasyIMHDwBYtWoVR48ezdBwQgghhBDivyvNBdGNGzfi7e2NsbExFy5cUD0+KiIigp9++inDAwohhBBC/Fe9fdZ8eqfsKs0F0QkTJrBw4UKWLFmCvr6+an7lypU5f/58hoYTIrtaOH8eRQo6k8PMiKqVynPm9OksPX5CQgLLZk3i+1ql8XbPS5tvyvDb/F/Ubk4/vGc7gzo1p3H5QtQoas2t65ezNOP7Hj54QBffduTLbYNNDlPKe7pz/txZjeUBOHrkMM2aNMQlX26M9RVs27pFo3k+pOlr7FV0FIunjKRjHU+alnFmYNsG/Hsl6cEn8XFxLJ8+Hr9vvWhWzoX2Nd2Z9mNvnoan7dF/GaFE4fyYG+kmmwb0653lWd43dcokqlQsh62VBU557GjR7Fv+vXlTo5ne0sa/x5/Gj032GZZ2K67RTBlFR6HIkCm7SnNB9ObNmyk+QcnS0pIXL15kRCYhsrU/NqxnyKABDB8xmhOnz+Pm5k4jH+9kT6HITGuXzGbr2uX0HTmZlTuO0+2HUaxbOodNq5ao1nnz+hWunuXpNnBUluVKyfPnz/mmRlX09PXZtHUHZy5c4afJU8mRQ7PPsI+OjqakmzszZ8/TaI6UaMM1Nmf0AAJOHOKHn+Yyd9MBSlWqzoiuLXgS9oiYN68Jun6ZVt37M2v9Xn6csYwHIUGM79M+y/K9dfDYKW6FPFBN23Yk9Qb+tmnzLM/yviNHDtO9Zy8OHjnBXzv3EBcfR0Mfb6KjozWaS1v/HgGKFS+h9lnu+eewpiOJDJDmzkr29vbcunULZ2dntflHjx4lf/78GZVLiGxr9szpdOzclfa+HQGYM38hf/+9g5UrljFo8NAsyXD1wmkq16pHRa86ANjnzcf+HZu4cfldq0Wdxi0ACL1/N0syfcyMaT+TJ68jC5csU81zdnHRYKIk3nXr4V23nqZjpEjT11jMm9cc27eDkbNX4FqmIgBteg3i9MG9/L1+Je36DmXCkg1q2/T48ScGfF+P8Ef3sXXIm+kZ37KxsVF7Pf2XKeTPX4Aq1apnWYaUbNv+t9rrxUuX45THjgvnz1GlquYel62tf48Aenp62KXx8ZHZQUY+az47SnP2rl270q9fP06dOoVCoeDhw4f8/vvvDBw4kJ49e2ZGRiGyjdjYWC6cP0fNWrVV83R0dKhZszanT57IshwlSpXj/InD3AtOenLGrRtXuHL+FOWq1cqyDKm1c/tflPb0pF3rFrg42lO5vCfLf13y+Q2/UtpwjSUkJJCYkIC+gZHafEMjI65eOJXiNq9evkShUGBmbpkVEVMUGxvLurW/07ZDR60b7iYyIgKAnDmtNJpDm/8eg24FUsglLyWLFqRzh7bcu6vZH9EZ5Wu/RzTNNaJDhw4lMTGRWrVq8erVK6pVq4ahoSEDBw6kT58+mZFRiGzjyZMnJCQkYGtrpzbf1s6OmzdvZFmO1t368Sr6JR3qV0RHV5fEhAQ6+w/nm4bfZVmG1AoJvs3SxQvp3bc/AwcP49zZMwz+wR8DAwPatOug6XhaRxuuMRNTM4q6l2Hdouk45i9Ejlw2HN65mRsXz+KQL3ntWWzMG5bPmEC1et9iYmaeJRlTsn3bFiJevKCtll1XiYmJDBrYn4qVKlPC1VWjWbT177FMuXIsXLKMQoWLEBr6iEkTx+Ndqzqnzl/C3Fxz15RIvzQXRBUKBcOHD2fQoEHcunWLqKgoihcvjpmZWWbkE1rA19eXlStXAqCvr0++fPlo3749P/74I3p6Xz4U7cGDB6lRowbPnz8nR44cGZRWABz8ewv7/vqTEb8swrlgUW7duMK8n4aTy9aeut+20nQ8NYmJiZTyLMOY8RMBcPcoxfVrV/l16WIpiGqxHybNZdZIfzrU8kBHV5cCxUpSrd633Lp2SW29+Lg4Jg/sBijxGzlFM2H/77cVy/jGuy4OaXwWdmbz7+vHtatX2HfgiKajaO3fYx3vd7fJuJZ0o0zZ8pQo7MKmPzfQoWNnjeXKCDqkv7ORDtm3SvSLSxEGBgYUL/7f6LEmPq9u3bosX76cmJgYdu7ciZ+fH/r6+gwbNkzT0QCIi4tTG8VBU6ytrdHV1SU8PExtfnhYGPZZeG/Twqlj+L5rP2r6NAUgf5HihD28x5rFM7WuIGpv70DRosXU5hUpWpStWzZpKJF205ZrzMHRmckrtvDmVTSvoqOwsrFjysBu2OfNp1rnbSE0/OF9fvr1T43Wht69c4cD/+zn9/V/aixDSvr3683fO3ewd/8h8ubNuntnPya7/D3myJGDgoUKczsoSNNR0i0jmtazc9N8mu8RrVGjBjVr1vzoJP6bDA0Nsbe3x8nJiZ49e1K7dm22bdvG9OnTKVmyJKampjg6OtKrVy+ioqJU2925c4eGDRuSM2dOTE1NKVGiBDt37iQkJIQaNWoAkDNnThQKBb6+vgA4Ozszc+ZMteN7eHgwZswY1WuFQsGCBQto1KgRpqamTJyY9Ot969atlC5dGiMjI/Lnz8/YsWOJj4/P1PfmfQYGBpQq7cmBf/ar5iUmJnLgwH7KVaiYZTliXr9G54NHbejo6KJMTMyyDKlVoWIlAv/9V23ercBAHPM5aSiRdtOWa+wtIxNTrGzsiIp4wfnjB6lQoy7wrhD68O5tJi7ZgEUOzd77uPq3FdjY2lK3no9Gc7ylVCrp368327Zu4e/d+7WmQ1B2+XuMiooi+HYQ9g4Omo4i0inNNaIeHh5qr+Pi4ggICODKlSt06CDNaF8LY2Njnj59io6ODrNnz8bFxYXbt2/Tq1cvBg8ezPz58wHw8/MjNjaWw4cPY2pqyrVr1zAzM8PR0ZGNGzfSrFkzbt68iYWFBcbGxmnKMGbMGCZPnszMmTPR09PjyJEjtG/fntmzZ1O1alWCgoLo1q0bAKNHj05xHzExMaqHMgBERkZ+4TvyTl//AXTt1AFPzzKUKVuOubNn8io6mvYdOqZ736lVsYY3qxfOwNYhLy4FixJ4/TJ/rFhAvWatVetEvnhO+KP7PPn/2I53/9+xycraFisbuxT3mxn8+vpT26sKU6dMomnz7zh35jTLf13C7HkLsyxDSqKiogi6dUv1OiQ4mIsBAeS0siJfvnyf2DLzacM1du7YAVAqyeNcgEd3Q1g2fRx5XQpSu0kr4uPimDSgC0HXLzNq3ioSExN5/iRpaCkzyxzo6xtkWU5IKqiv/m0Frdu2T9ftRBnJv68fG9atZcPGLZiZmxMamvR3aGlpmebvwoykrX+PPw4dRP36DXDM58SjRw/5afwYdHR1ad5Cu1p4vsTX/ojPNP9FzpgxI8X5Y8aMUasJE/9NSqWS/fv3s3v3bvr06YO/v79qmbOzMxMmTKBHjx6qgujdu3dp1qwZJUuWBFAb4svKKqmGxNbW9ovuEW3dujUdO777h7dTp04MHTpU9YMof/78jB8/nsGDB3+0IDpp0iTGjh2b5mN/ynctWvLk8WPGjR1FWGgobu4ebN2+Czu7rCvc9R0xiWWzJzNr3GCeP32Cta09DVt2oH2vgap1jv+ziyk/vutgOH5AVwA6+A3Ct8+QLMvqWaYsazZsZMzI4Uz5aTxOzi5Mnjqdlt+3ybIMKTl/7izetWuoXg8ZNACAtu06sGTZCg2lSqIN19irl5GsnPUTT8IeYW6Zg0q1fWjfdxh6+vqEPbjLqYNJ43X2ba4+UsNPyzbiVrZyluUEOLB/H/fu3aVdFhbUP2fJoqSC3fvXGMCipcto195XA4mSaOvf48MH9+nYoQ3Pnj7F2saGipUq88+h48mG58qOFArSfY9odm6aVyjff9RKOty6dYty5crx7NmzjNid0CK+vr6sXr0aIyMj4uLiSExMpHXr1syfP58TJ04wadIkbty4QWRkJPHx8bx584bo6GhMTExYunQpPXv2pFy5ctSuXZtmzZrh5uYGfLyzkrOzM/7+/mqFXA8PD5o0aaJqnlcoFKxevZo2bd59OdrY2BAVFYWurq5qXkJCglqeD6VUI+ro6EjY0wgsLCwy6B3MGCeDnmo6QorKOGt+oOuU6Olm55H1st7+G2GfX0lDqhfSzsKGrpZWQyUkZsg/6/95kZGR5LHNSUSEZr7vIyMjsbS0ZNjm8xiZpu/+6TfRL5n0bWmNnUt6ZNg39YkTJzAyMvr8iiJbqlGjBgEBAQQGBvL69WtWrlzJ48ePadCgAW5ubmzcuJFz584xb17SU2hiY2MB6NKlC7dv36Zdu3ZcvnyZMmXKMGfOnE8eS0dHhw9/H8XFxSVbz9TUVO11VFQUY8eOJSAgQDVdvnyZwMDAj16bhoaGWFhYqE1CCCFEVpFxRNOoadOmaq+VSiWPHj3i7NmzjBw5MsOCCe1iampKwYIF1eadO3eOxMREpk2bho5O0m+aDRs2JNvW0dGRHj160KNHD4YNG8aSJUvo06cPBgZJ94klJCSorW9jY8OjR49UryMjIwkODv5sxtKlS3Pz5s1kOYUQQghtJfeIppGlpfpTMXR0dChSpAjjxo2jTp06GRZMaL+CBQsSFxfHnDlzaNiwIceOHWPhQvUb2v39/alXrx6FCxfm+fPnHDhwgGLFkoYGcXJyQqFQsH37durXr4+xsTFmZmbUrFmTFStW0LBhQ3LkyMGoUaPUmts/ZtSoUTRo0IB8+fLRvHlzdHR0uHjxIleuXGHChAmZ8h4IIYQQ4sulqSCakJBAx44dKVmyJDlzaud9YSLruLu7M336dKZMmcKwYcOoVq0akyZNon379qp1EhIS8PPz4/79+1hYWFC3bl1Vh7c8efIwduxYhg4dSseOHWnfvj0rVqxg2LBhBAcH06BBAywtLRk/fnyqakS9vb3Zvn0748aNY8qUKejr61O0aFG6dOmSae+BEEIIkR6K//8vvfvIrtLcWcnIyIjr16/joiVjngmRkd7ePC6dlVJPOiv9N0hnpbSTzkrZm7Z0Vhq97UKGdFYa26jU19FZydXVldu3b2dGFiGEEEII8RVJc0F0woQJDBw4kO3bt/Po0SMiIyPVJiGEEEIIkTpvOyuld8quUn2P6Lhx4/jhhx+oX78+AI0aNULx3ngBSqUShUKRrAe0EEIIIYRImUKhUCtPfek+sqtUF0THjh1Ljx49OHDgQGbmEUIIIYQQX4lUF0Tf9mmqXr16poURQgghhPiayDiiaZCdq36FEEIIIbRNRjwZKTsXz9JUEC1cuPBnC6PyrHkhhBBCCJEaaSqIjh07NtmTlYQQQgghxJfRUSjQSWeVZnq316Q0FURbtWqFra1tZmURQgghhPiqfO33iKZ6HFG5P1QIIYQQQmSkNPeaF0IIIYQQGSQDOitl40fNp74gmpiYmJk5hBBCCCG+Ojoo0ElnSTK922tSmu4RFUJoToUCuTQdIUVRb+I1HSFFptn5pikNqFXUTtMRPspz9B5NR0jR6dHfaDpCihK1tAHTQC/NTxXPVHq62pXnayUFUSGEEEIIDZFxRIUQQgghhEZIr3khhBBCCCE0QGpEhRBCCCE0RAa0F0IIIYQQGvG13yMqTfNCCCGEEEIjpEZUCCGEEEJDdMiApnkZR1QIIYQQQqTV1940LwVRIYQQQggN0SH990lm5/sss3N2IbTWwvnzKFLQmRxmRlStVJ4zp09rOhJHjxymWZOGuOTLjbG+gm1bt2gkx/GjR2jzXRNcC+XDxlyfnX9tVVseFRXFkB/64lbEGUcbcyqXcWPFr4uyPOfUKZOoUrEctlYWOOWxo0Wzb/n35s0sz5Fdcmni+upSzYX1PctzelRNDg/zYnYbD5ytTdTW+a5sHpZ3LsOpkTW5OrEO5kbJ61/mtvVg36CqnB9Ti4NDqzOpuSs25oaZnv+taVMnY2aow+Af/LPsmJ/y8uVLhg7sj2thF+xymvKNVxXOnT2j6ViAdn63ivSRgqgQGeyPDesZMmgAw0eM5sTp87i5udPIx5vw8HCN5oqOjqakmzszZ8/TaI5Xr6IpUdKNKdNmp7h81LCB/LNvDwuWruTY2ct079WHoT/0Y9eOv7I055Ejh+nesxcHj5zgr517iIuPo6GPN9HR0VmaI7vk0sT1VdYlJ2tP3uP7hafouvwseroKlvh6Yqyvq1rHSF+XY4FPWHLo9kf3c/r2Mwasu4TPzGP4rwnA0cqEGd+7Z8UpcO7sGZYtWYxrSbcsOV5q9OnZlQP/7GPRspUcP3uRmrW/oYlPHR4+eKDRXNr63ZpeCoUiQ6bsSqFUKrX0qbRCZL3IyEgsLS0JexqBhYXFF+2jaqXyeJYpy8zZcwFITEykoIsjPf36MGjw0IyM+8WM9RWs/3MzjRo3Sfe+0vOseRtzfVau+ZP6DRur5lUt50GTZt/xw5Dhqnm1qpaj1jd1+XHUuFTv29RQ9/MrpcHjx49xymPHnv0HqVK1WobuOz0yKldG/kOWkdcXpP5Z8zlN9Dk6vAbtl5zhXMhztWVlXXKyoktZKoz/h5efuWZrFLVhdhsPSo3eR/wnHtye3mfNR0VFUaW8JzNmz2PK5Im4ubnz87SZ6donQEI6Hjb/+vVr8thYsvaPzXjX81HNr1apLN/UqcvIMeO/eN/pfdZ8Rn+3RkZGYpfLkoiIL/++T4+3/94sPHAVYzPzdO3rddRLetQoobFzSQ+pERUiA8XGxnLh/Dlq1qqtmqejo0PNmrU5ffKEBpNlH2XLV2DXzr949PABSqWSo4cPEnQrEK+a6ftHP70iIyIAyJnTSqM5PqStuTThbbN7xKu4L96HpbEePu4OBNx98clCaEYY0K833vXqU+O97wtNi4+PJyEhAUMjI7X5xkbGnDx+TEOp5Lv1v0w6KwmRgZ48eUJCQgK2tnZq823t7Lh584aGUmUvk36ZxYA+PXAr4oyenh46OjpMn7OQSlWqaixTYmIigwb2p2KlypRwddVYjg9pay5NUChgiE9Rzoc851Z4VJq3H+BdiO8r5MPEQJeAuy/o9duFTEj5zh8b1hFw4TyHj2vXPY7m5uaUK1+RqZMmUqRIMWzt7Phzw1pOnzpB/gIFNZbrv/zd+rU/WUlqRNPJ19dXdX+GgYEBBQsWZNy4ccTHf3lzZXbn5eWFv79/iss2btyIl5cXlpaWmJmZ4ebmxrhx43j27FnWhhRaa+nCeZw7c5rV6zez78gpxv70M0N+6MuhA/s1lsm/rx/Xrl5h5eq1GsuQEm3NpQkjGhajkJ0ZA9df+qLtlx0JofncE3RZdpbERCWTvsu8gv39e/cY/IM/y1auxuiDmkdtsGjZSpRKJUULOGJjaczCeXNp3qIVOjpSZMgsinRO2ZlcVRmgbt26PHr0iMDAQH744QfGjBnD1KlT07yfhIQEEhMTMyGhdhg+fDgtW7akbNmy/P3331y5coVp06Zx8eJFVq1aleI2sbGxWZwyfaytrdHV1SU8PExtfnhYGPb29hpKlX28fv2aiWNHMG7SVLzrN6CEqxtduvvRpOl3zJs9XSOZ+vfrzd87d7Brzz/kzZtXIxlSoq25NGF4w6JUL2JDx1/PEhYZ80X7ePEqjjtPX3Ei6BkD11+iehEb3B0tMzhpkgvnz/E4PJzK5T2xNNHH0kSfo4cPsWDeHCxN9ElISMiU46ZW/vwF2Ln3AA+fRHIt8A4Hjp4kLi4OZxcXjWWS79b/LimIZgBDQ0Ps7e1xcnKiZ8+e1K5dm23bthETE8PAgQPJkycPpqamlC9fnoMH/9fefcfXdP9xHH/dJDJkSQgxEkkk1EiIHVuktVqCam2xilq1qa1GqzVLUStoFUVjq1FixCaJVSNCokKMEgkZkvP7I7/cuhJKk9xz8Xn2cR+P3nNO7n27rpvP/c592p8LDAwkX758bNq0iTJlymBmZkZUVBQuLi5MmjSJTp06YWVlRfHixdm0aRN37tyhefPm2pbEEydOaB/r3r17tG3blqJFi5I3b148PT355RfdVpJ69erRv39/hg0bhr29PY6OjowfP17nmgcPHtC9e3ccHBywsbHB19eXsLAw7fnx48dToUIFVq5ciYuLC7a2trRp04ZHjx4B6S3EwcHBzJ49W9tSfO3aNY4dO8aUKVOYPn063377LTVq1MDFxYX333+f9evX07lzZ53HX7x4Ma6urtrWgqioKO2f3cbGhk8++YTbt29nyrVw4UKcnJzImzcvn3zyCQ//P35OX0xNTfGuWIm9f/zTepeWlsbevXuoWt1Hr1neRE9TUkhJScnU8mJsbIyi5y9piqIwcEBfNm0MYvvve1T9JfwsQ82lllEfvUeDMgXpuvQEf/39JEceM6ObM7uTa16knm8Djp4KJ+T4ae2tYqXKfNq2PSHHT2NsnLMT7f4rS0tLHAsX5u+//+aP3Ttp8mEz1bK8zZ+tGQvaZ/f2ppJCNBdYWFiQnJxM3759OXz4MKtXryY8PJzWrVvTqFEjLl++rL328ePHfPPNNyxevJhz585RsGBBAGbOnEnNmjU5ffo0TZs2pWPHjnTq1IkOHTpw6tQpSpQoQadOnchY9CAxMZFKlSqxdetWzp49y2effUbHjh059twaa8uXL8fS0pKjR48ybdo0Jk6cyK5du7TnW7duTWxsLNu3b+fkyZNUrFiRBg0a6HSdR0REEBQUxJYtW9iyZQvBwcF8/fXXAMyePRsfHx969OhBTEwMMTExODk58fPPP2NlZcXnn3+e5WuWL18+7f9fuXKF9evXs2HDBkJDQ0lLS6N58+bcv3+f4OBgdu3axdWrV/n00091HuPKlSusXbuWzZs3s2PHDk6fPv3C58uQlJREXFyczi27+n8xiGVLFvHTiuX8eeEC/fv05nFCAp06d8n2Y2dHfHw8YaGhhIWGAnAtMpKw0FCioqL0nuNMeChnwtNzRF2P5Ex4KDeio7C2saFGrTpMGD2CQweCuX4tkl9+Ws7aX37SmVmvD1/078PqVT8TuOJnrKytuXXrFrdu3eLJk5wpdt62XGq8v8Y0K82H5QszbM0ZHic9pYCVKQWsTDF7poAsYGXKe4Wtcc6fvr6oRyEr3itsja1F+hQJz2K2tKvuxHuFrSmcz5xqbvZ8+6knUfceExr1IFdyW1tbU7ZsOZ1bXktL7O3tKVtW/bG+u3f9zu6dO7h2LZI/9uzio0YN8Cj5Hh06qfsZZqifrdn1ri/fJJOVcpCiKOzZs4fff/+dtm3bsmzZMqKioihSpAgAQ4YMYceOHSxbtowpU6YAkJKSwg8//ED58rpr1jVp0oSePXsCMHbsWObPn0+VKlVo3bo1AMOHD8fHx4fb/++WKFq0KEOGDNH+fL9+/fj9999Zu3YtVatW1R738vJi3LhxAHh4eDB37lz27NnD+++/z8GDBzl27BixsbGYmaUv5vzdd98RFBTEunXr+Oyzz4D0b6GBgYFYW6cvN9GxY0f27NnD5MmTsbW1xdTUlLx58+p0l1y+fBk3Nzfy5Mnzr69jcnIyK1aswMHBAYBdu3Zx5swZIiMjcXJyAmDFihWULVuW48ePU6VKFSC9GF+xYgVFixYF4Pvvv6dp06ZMnz79hV03U6dOZcKECf+a6XW0/uRT7t65w8QJY7l96xZe5SuwccsOChUq9O8/nItOnTxBQ7/62vvDhw4CoEPHzixaGqi3HGGnT+Lf5J+Zr2NGDgXg03YdmbtwKT8G/sykcaPo1a0TD/6+TzGn4nw5diIB3XrqLSPAooULAHReM4CFi5fSsVOAXrM8y1BzqfH+alMt/fNgeY8qOsdHrTtL0OmbAHxS1Yk+DUpoz638rKrONYkpqfiVKUSfBiWwyGPMnUfJHLx8l4X7wklJfTdXN4x7+JAJY0dx868b2Nnb06x5S8ZMmPRKn9+5yVA/W0X2SCGaA7Zs2YKVlRUpKSmkpaXRrl07Pv74YwIDAylZsqTOtUlJSeTPn19739TUFC+vzAsZP3ss4x+Zp6dnpmOxsbE4OjqSmprKlClTWLt2LX/99RfJyckkJSWRN2/eFz4uQOHChbWLAYeFhREfH6+TD9LH7UVERGjvu7i4aIvQ5x/jRV5nudrixYtri1CACxcu4OTkpC1CAcqUKUO+fPm4cOGCthB1dnbWFqEAPj4+pKWlcfHixRcWoiNHjmTQoEHa+3FxcTrP81/17tOX3n36ZvtxclKduvV4kqL+L9aatety59GLl9cpVMiR7xcs0WOirD1ONszx2oaaS433V9lR/76+6A9/RPDDHxEvPH/5djxdl5544Xl92bFrr9oRtFp+/AktP/5E7RhZMsTP1ux617f4lEI0B9SvX5/58+djampKkSJFMDExYc2aNRgbG3Py5MlM432srKy0/29hYZFlk/qz3zwzzmd1LGNy07fffsvs2bOZNWsWnp6eWFpa8sUXX2Sa7PP8N1qNRqN9jPj4eAoXLqwzjjXDs13nL3uMFylZsiQHDx4kJSXlX79VW1pavvR8TjIzM9O2/gohhBD6lhNd66/78/v37+fbb7/l5MmTxMTE8Ntvv+Hv7689rygK48aNY9GiRTx48ICaNWsyf/58PDw8tNfcv3+ffv36sXnzZoyMjGjVqhWzZ8/WqXFexZtcRBsMS0tL3N3dcXZ2xsQkvbb39vYmNTWV2NhY3N3ddW65McPv0KFDNG/enA4dOlC+fHnc3Ny4dOnSaz1GxYoVuXXrFiYmJpkyFyhQ4JUfx9TUNNOsz3bt2hEfH88PP/yQ5c88ePDghY9XunRpoqOjiY6O1h47f/48Dx48oEyZMtpjUVFR3Lx5U3v/yJEjGBkZUapUqVfOLoQQQrztEhISKF++PPPmZb0l77Rp05gzZw4LFizg6NGjWFpa0rBhQxITE7XXtG/fnnPnzrFr1y62bNnC/v37tUP4XocUormkZMmStG/fnk6dOrFhwwYiIyM5duwYU6dOZevWrTn+fB4eHuzatYuQkBAuXLhAz549dWaVvwo/Pz98fHzw9/dn586dXLt2jZCQEEaNGqUzQ//fuLi4cPToUa5du8bdu3dJS0ujWrVqDBs2jMGDBzNs2DAOHz7M9evX2bNnD61bt2b58uUvzeXp6Un79u05deoUx44do1OnTtStW5fKlStrrzM3N6dz586EhYVx4MAB+vfvzyeffCJLewghhDBY2V1D9L+sJdq4cWMmTZpEixYtMp1TFIVZs2YxevRomjdvjpeXFytWrODmzZsEBQUB6UPmduzYweLFi6lWrRq1atXi+++/Z/Xq1ToNQq9CCtFctGzZMjp16sTgwYMpVaoU/v7+HD9+HGdn5xx/rtGjR1OxYkUaNmxIvXr1cHR01GlmfxUajYZt27ZRp04dunTpQsmSJWnTpg3Xr19/rcHgQ4YMwdjYmDJlyuDg4KCdNfvNN9+watUqjh49SsOGDSlbtiyDBg3Cy8tLu3zTi3Jt3LgROzs76tSpg5+fH25ubqxZs0bnOnd3d1q2bEmTJk344IMP8PLyemELrBBCCGEIcnLW/POrwCQlvf66upGRkdy6dQs/v38mldra2lKtWjUOH07fTvXw4cPky5dPpzHIz88PIyMjjh49+np/fuV1ZpEIYaDGjx9PUFAQof9fOua/iouLw9bWltv3HmJjY5Mz4d5y8YmGuYuYpZlhrMX4pjDk5V8qjfv3SUlqODbufbUjZCk1zTB/refWuqz/VVxcHIXy2/LwoTqf9xm/b5YfvEheK+t//4GXeBz/iM61Mg9DGzduXKb1wp+n0Wh0xoiGhIRQs2ZNbt68SeHChbXXffLJJ2g0GtasWcOUKVNYvnw5Fy9e1HmsggULMmHCBHr37v3K2WWykhBCCCGESnJy1nx0dLROUf0mTMaVQlQIIYQQQiU5OWvexsYm2627GfMqbt++rdMievv2bSpUqKC95vllG58+fcr9+/dfe16GYbWTC/EfjR8/Ptvd8kIIIcS7ztXVFUdHR/bs+Wc71bi4OI4ePYqPT/p2qj4+Pjx48ICTJ09qr/njjz+0k5Nfh7SICiGEEEKo5L/Mes/qMV5HfHw8V65c0d6PjIwkNDQUe3t7nJ2d+eKLL5g0aRIeHh64uroyZswYihQpoh1HWrp0aRo1akSPHj1YsGABKSkp9O3blzZt2mh3k3xVUogKIYQQQqhEo0m/ZfcxXseJEyeoX/+fLXkzdhjs3LkzgYGBDBs2jISEBD777DMePHhArVq12LFjB+bm5tqf+fnnn+nbty8NGjTQLmg/Z86c184uhagQQgghxDukXr16L916W6PRMHHiRCZOnPjCa+zt7Vm1alW2s0ghKoQQQgihEiM0GGWzcz67P68mKUSFEEIIIVSiRte8IZFZ80IIIYQQQhXSIiqEEEIIoRLN///L7mO8qaQQFUIIIYRQiXTNCyGEEEIIoQJpERVCZIulmbHaEbKUmvbipUnUlJSSpnaELJmbGubfI8DJCR+oHSFLds1ef81Effh7U3+1I4jXoMmBWfPSNS+EEEIIIV6bdM0LIYQQQgihAmkRFUIIIYRQybveIiqFqBBCCCGESt715Zuka14IIYQQQqhCWkSFEEIIIVRipEm/Zfcx3lRSiAohhBBCqES65oUQQgghhFCBtIgKIYQQQqjkXZ81Ly2iQuSCBT/Mo5S7C/mszKldoxrHjx1TOxJgmLm+/WYqtXyqUtDehuJFC/FJqxZcunhR7ViULemGtblxptugAX31miPk4AHatfanrIczBazzsG3zRp3zBazzZHn7ftZ0veZ81vRvv8bKzIhhg79QLUOGgwf208r/I1ydi2CRR8OmjUG5/pxDPqnMwVmfEruuF9dXdWftmKZ4FM2X6bpq7zmyfWoL7m7oze11vdg1rZXODlcVSjiwZbI/MWt7cmN1D+b288XSPE+u5wfD/KwAw82VHRr+6Z7/7/+9uaQQFSKH/bp2DcOHDmLU6HEcPnYKL6/yNGvakNjYWMmVhQMH9tOz9+fsO3CYzdt2kvI0hY+aNiQhIUHVXPsOHeXKtb+0t01bfwegRcuP9Zrj8eMEynl6MW161ttJnrsSrXOb88MiNBoNHzVvodecGU6eOM7SRT9SztNLled/XkJCAp5e5Zk1Z57enrN2uaIs2BJO3UFr+XBUECbGRmyZ7E9es386Iau958jGr5qz51QUtb9YQ60Bq1mwOZy0/+8AW9jekq1TWhBx8wF1Bq6h+ZiNlCluz6JB7+d6fkP9rDDUXCJ7NIqiGOaGzEKoIC4uDltbW27fe4iNjc1/eozaNapRqXIVZs2ZC0BaWhrurk707tOPocNG5GRcg8iV0x8hd+7coXjRQuzcs49atev858fJ6b3mhw8ZyI5tWwk9dxFNNvrBsrPXfAHrPKxYtY4mHzV/4TUd27QiPv4Rv23Z+VqPnRN7zcfHx1OrWiVmzpnHN19PxsurPNOmz8r24xrn0JRgizwa1qz7jWbN/XPk8V51r/kCNhZEr+6B37B1HDp7E4DgGZ+w53QUE1ceyfJnujYqy9iOPrh2WEzGP7GyLvk58UN7ynZbztWYhy98vuzuNf+ufIbFxcVRKL8tDx/+98/77Mj4fbPtZCSWVtl7/oT4OJpUclXtz5Id0iIqRA5KTk7m9KmT+Dbw0x4zMjLC19ePY0cOS65XEPcw/ResnZ29ykn+kZyczOpffqZD5y7ZKkJzW2zsbXb9vo32nbqo8vyDBvSlYeMm1H/mfSbAxtIUgL8fJQLgYGtB1fccufPgMXu/a821n7uz85tW1ChTWPszZnmMSXmayrPf854kPQWgRtkiuZbVUD8rDDVXTsh+t/yb3Tkvhah4oWvXrqHRaAgNDX3hNfv27UOj0fDgwYNczxMQEIC/v/8rX/8q+XPa3bt3SU1NpWDBQjrHCxYqxK1bt/SW43mGmut5aWlpDB0yEJ8aNSlbrpzacbS2bAri4YMHdOjYWe0oL7X655VYWVvzYTP9d8v/unY1oadPMWHSVL0/tyHTaODbnnUIOXeT89fvA+DqaAvAqPbVWPr7WZqP2UjolVi2TW1JiSLp5/aF3aCQXV4GtqpIHhMj8lmZMalLTQAc7S1zLa+hflYYai6RfVKIvuECAgLQaDRoNBry5MmDq6srw4YNIzExMduP7eTkRExMDOX0XBC8qICcPXs2gYGBes0i9OuL/n04f+4sy3/6Re0oOlYELuX9ho0oXCT3WqJywqqVgXz8SVvMzc31+rw3oqMZNvgLli7/Se/PbehmfV6PssXz0+nrHdpjRv//zbtk+1lW7rpA2NU7DFt0gEs3/qbzB2UBuBB1nx4zdtG/hTf3f/ucaz9359qth9y6n4CSw8NOhLoyZs1n9/amkuWb3gKNGjVi2bJlpKSkcPLkSTp37oxGo+Gbb77J1uMaGxvj6OiYQymzz9bWVu0I/6pAgQIYGxsTG3tb53js7duqvpaGmutZAwf0Zfu2rezaE0yxYsXUjqMVdf06e//Yw89r1qkd5aUOHzrIlcsXWbz8Z70/9+lTJ7kTG0vNapW0x1JTUzl0YD8L58/j/qNEjI2zPwb1TTOzd12aVHXFb9h6/roXrz0ec/8xkF5sPuti9H2cHKy099fsu8SafZcomM+ChMSnKIpC/xbeRN568fjQ7DLUzwpDzZUTNP+/Zfcx3lTSIvoWMDMzw9HREScnJ/z9/fHz82PXrl1Aelfn1KlTcXV1xcLCgvLly7Nu3T+/UP/++2/at2+Pg4MDFhYWeHh4sGzZMiDrlslt27ZRsmRJLCwsqF+/PteuXcuU5+DBg9SuXRsLCwucnJzo37+/zgxoFxcXpkyZQteuXbG2tsbZ2Zkff/xRe97V1RUAb29vNBoN9erVAzJ3ze/YsYNatWqRL18+8ufPz4cffkhERER2X85sMTU1xbtiJfb+sUd7LC0tjb1791C1uo/kyoKiKAwc0JdNG4PY/vseXP7/928ofloRiEPBgjRq3FTtKC/184qllPeuSDnP8np/7nq+DTh6KpyQ46e1t4qVKvNp2/aEHD/9zhahzXxK0GjkBq7fjtM5d/12HDfvxlOymJ3OcfeidkTFPsr0WLEPnpCQmMLHdUqSmJLKntNRuZbbUD8rDDWXyD5pEX3LnD17lpCQEIoXLw7A1KlT+emnn1iwYAEeHh7s37+fDh064ODgQN26dRkzZgznz59n+/btFChQgCtXrvDkyZMsHzs6OpqWLVvSp08fPvvsM06cOMHgwYN1romIiKBRo0ZMmjSJpUuXcufOHfr27Uvfvn21BS7A9OnT+eqrr/jyyy9Zt24dvXv3pm7dupQqVYpjx45RtWpVdu/eTdmyZTE1Nc0yT0JCAoMGDcLLy4v4+HjGjh1LixYtCA0Nxcjo1b5jJSUlkZSUpL0fFxf3kqtfTf8vBtGja2cqVapM5SpVmTtnFo8TEujUWZ0JJIae64v+fVi7+hfWrg/CytpaO97L1tYWCwsLVbOlpaXx04pA2nXohImJOh+X8fHxRF69or1//XokZ8JDsbOzp5iTMwCP4uLYFLSeCVOmqZLR2tqasmV1h/DktbTE3t4+03F9i4+PJ+LKP6/ftchIwkJDsbO3x9nZOVeec9bn9fi0XilaT9xC/JMUCtnlBeBhQhKJyakAzFx/itEdqnHm6l3Crt6hg19pShWzo93kbdrH6fWhF0cuxBCfmEIDb2emdK3JmMAQHiYk50ruDIb6WWGoubLLCA1G2exbN3qD20SlEH0LbNmyBSsrK54+fUpSUhJGRkbMnTuXpKQkpkyZwu7du/HxSf/G6ObmxsGDB1m4cCF169YlKioKb29vKleuDKS3Vr7I/PnzKVGiBNOnpy+UXapUKc6cOaMzBGDq1Km0b9+eL774AgAPDw/mzJlD3bp1mT9/vnb8WJMmTfj8888BGD58ODNnzmTv3r2UKlUKBwcHAPLnz//SLpdWrVrp3F+6dCkODg6cP3/+lce1Tp06lQkTJrzSta+q9SefcvfOHSZOGMvtW7fwKl+BjVt2UKhQoX//4VxkqLkWLVwAQEO/+jrHFy5eSsdOASok+sfePbuJjo6io4q/6EJPn8S/yT8zhceMHApAm3YdmbtwKQAb1q1BURRafdxGlYyG7NTJEzrvreFDBwHQoWNnFi0NzJXn7Plh+hqqu6bpfkb1mLGLn3ZfAGDuxlDMTY2Z9llt7KzNOXP1Lh+O+k2n271yqUKM7lANKwtTLkbfp+/cvfzyx5+5kvlZhvpZYai5sutd75qXdUTfcAEBAfz111/Mnz+fhIQEZs6ciYmJCYsXL+bcuXOUK1cOS0vdGZbJycl4e3tz9OhRtm/fTqtWrShZsiQffPAB/v7+1KhRA0jvmnd1deX06dNUqFCBFi1aYGdnx9KlS7WPtXHjRvz9/fn777/Jly8fVapUITw8nDx5/tn9Q1EUHj9+zPnz5yldujQuLi706dOHoUOHaq8pX748rVq1YuzYsZme99k/64MHDwgKCgLg8uXLjB07lqNHj3L37l3S0tJISEhg69atNGnS5IWP86ysWkSdnJyytY7ou8ZQP0Jyeh3RnJKddURzU06sI5pbcmod0Zz2quuI6lt21xF9VxjKOqK7T13H0jqb64g+isOvYvE3ch1RaRF9C1haWuLu7g6ktwqWL1+eJUuWaFsFt27dStGiRXV+xszMDIDGjRtz/fp1tm3bxq5du2jQoAF9+vThu++++09Z4uPj6dmzJ/37Z/4gfLYb7NlCFUCj0ZCW9nq/oD/66COKFy/OokWLKFKkCGlpaZQrV47k5FfvtjIzM9O+FkIIIYTeveNNolKIvmWMjIz48ssvGTRoEJcuXcLMzIyoqCjq1q37wp9xcHCgc+fOdO7cmdq1azN06NAsC9HSpUuzadMmnWNHjujuClKxYkXOnz+vLYz/i4wxoampqS+85t69e1y8eJFFixZRu3ZtIH2SlBBCCPEmyYkF6WVBe2FQWrdujbGxMQsXLmTIkCEMHDiQ5cuXExERwalTp/j+++9Zvnw5AGPHjmXjxo1cuXKFc+fOsWXLFkqXLp3l4/bq1YvLly8zdOhQLl68yKpVqzKt6zl8+HBCQkLo27cvoaGhXL58mY0bN9K3b99Xzl+wYEEsLCzYsWMHt2/f5uHDzEuV2NnZkT9/fn788UeuXLnCH3/8waBBg179RRJCCCEMQU6sIfrm1qFSiL6NTExM6Nu3L9OmTWPkyJGMGTOGqVOnUrp0aRo1asTWrVu1SySZmpoycuRIvLy8qFOnDsbGxqxevTrLx3V2dmb9+vUEBQVRvnx5FixYwJQpU3Su8fLyIjg4mEuXLlG7dm28vb0ZO3YsRV5jIXATExPmzJnDwoULKVKkCM2bZ95X28jIiNWrV3Py5EnKlSvHwIED+fbbb1/jVRJCCCGE2mSykhDPyBg8LpOVXp2hfoTIZKXXI5OVXp9MVnqzGcpkpT9Co7DK5mSl+Edx+FZwlslKQgghhBDiNbzjk5Wka14IIYQQQqhCWkSFEEIIIVTyrs+al0JUCCGEEEIl2pnv2XyMN5V0zQshhBBCCFVIi6gQQgghhEre8blKUogKIYQQQqjmHa9EpWteCCGEEEKoQlpEhRBCCCFUIrPmhRBCCCGEKmTWvBBCCCGEECqQFlEhhBBCCJW843OVpBAVIiupaQqpaYraMXQkpaSqHSFLpiaG2bGSmJKmdoQsWZkb5sduYrJhvr8AEg3s32KGe0H91I6QpTaBJ9SOkKXVAZXVjmCY3vFK1DB/gwghhBBCiLeeYX41F0IIIYR4B8iseSGEEEIIoQqZNS+EEEIIIYQKpEVUCCGEEEIl7/hcJSlEhRBCCCFU845XotI1L4QQQgghVCEtokIIIYQQKnnXZ81Li6gQQgghhEoyZs1n9/Y6xo8fj0aj0bm999572vOJiYn06dOH/PnzY2VlRatWrbh9+3YO/8nTSSEqRC6a/u3XWJkZMWzwF3p/7pCDB2jX2p8y7s7kt8rD1s0bdc736dmV/FZ5dG6t/ZvqPeeUryZgbW6sc6voVUbvOUIOHqB9a3/KeTjjYJ2Hbc+9XvHx8Qwf3B+vUi44OVhTs7IXgUsW6j3nwQP7aeX/Ea7ORbDIo2HTxiC9ZwA4dHA/bT5uTukSTthZmui8v1JSUhg3egQ1qlSgqIMNpUs40at7ADExN3M9V8b7vqyHMwWy+HssYJ0ny9v3s6bnerZnLVo4n6qVyuNYwBbHArbUr1OD33dsz/XnLeNoxagP3Fna1oug7pWpVjyfzvmg7pWzvPl7FtJe8+OnnpnOt/RyzPXsAAt+mEcpdxfyWZlTu0Y1jh87ppfnfRuVLVuWmJgY7e3gwYPacwMHDmTz5s38+uuvBAcHc/PmTVq2bJkrOaRrXohccvLEcZYu+pFynl6qPP/jxwmULedFu44BdG7XOstrGrzfkO8XLNbeNzM101c8HaXLlGXztp3a+8Ym+v9oevw4gbKe6a9XQPvMr9fYkUM4sH8f8xcvx8m5OPv27GLYoH44OhahUdOP9JYzISEBT6/ydAroSpvWufOL4VU8TkignKcXHTp1oWPbj3XPPX5MeOhpho4YRTlPLx48+JuRQwfSrnUL9h48mru5Hqfnat8xgM5Z/D2euxKtc3/Pzh0M6PMZHzVvkau5nle0aDEmTpqKu7sHiqLw80/L+fRjf0KOnaJMmbK59rzmJkZE3nvM7ot3Gfm+e6bzAT+H6tyvWMyWvnVcOHztb53jq078xc6Ld7T3n+hhS91f165h+NBBfD9vAVWqVmPunFk0a9qQsHMXKViwYK4/f27JyblKcXFxOsfNzMwwM8v6c93ExARHx8xfIB4+fMiSJUtYtWoVvr6+ACxbtozSpUtz5MgRqlevns20z+XI0UcTQgDprWfdOndg7vwf+ebryapk8PugEX4fNHrpNaZmZhQqpJ+WjJcxMTGhUBYfiPr0b6/X8aNHaNOuIzVr1wWgU9ceLF+2iFMnj+u1EG3YqDENGzXW2/O9yPsNG/N+w6xz2Nra8tuW33WOTZsxhwZ1fIiOjsLJyTnXcv3b3+Pz7/ftWzdTq049XFzdci1TVpp8qPueGT9xMot/XMDxo0dytRA9dSOOUzfiXnj+wZOnOverFc/H2ZuPuP0oWef4k5TUTNfmtjmzZtClWw86BXQB4PsfFrB9+1aWBy5l6LARes2So3KwEnVyctI5PG7cOMaPH5/lj1y+fJkiRYpgbm6Oj48PU6dOxdnZmZMnT5KSkoKfn5/22vfeew9nZ2cOHz6c44WodM0LkQsGDehLw8ZNqN/A798vVtGhA8GUcilCVe+yDB7Qh/v37qmSI+LKZTxci+H5njvdOncgOipKlRwvU6VadXZs20zMzb9QFIWD+/cRceUy9XzfVzvaGyHu4UM0Gg22tvnUjqIVG3ubXb9vo32nLqrmSE1N5de1q0lISKBqdR9VszzL1sKESs627L50N9O5luULs6JDBWb4l8HfsxBGuTxXJjk5mdOnTuL7zGeqkZERvr5+HDtyOHef/A0SHR3Nw4cPtbeRI0dmeV21atUIDAxkx44dzJ8/n8jISGrXrs2jR4+4desWpqam5MuXT+dnChUqxK1bt3I8s7SICtVdu3YNV1dXTp8+TYUKFdSOk22/rl1N6OlT7A8x7LFLDfwa8mGzFhQv7kJk5FUmjR/DJy0/5Pc/DmJsbKy3HJWrVmXBoqV4lCzFrVsxTJ38FQ0b1OXoqXCsra31luPfTP1uNoP69cKrlAsmJiYYGRkx4/sF1KhVW+1oBi8xMZHxY76kVes22NjYqB1Ha/XPK7GytubDZvrtls9w9uwZfOvUIDExESsrK35Zu4HSpfU/PvpFfD0K8CQ5LVO3/JZzsVy995hHSU95r6AVHasUxS5vHpYdvZFrWe7evUtqaioFCxbSOV6wUCEuXvwz155XH3Jy1ryNjc0r/Rtr3Pif3gwvLy+qVatG8eLFWbt2LRYWFtnK8rqkEBW5LiAggOXLlwPpXbDFihWjdevWTJw4EXNzc5ycnIiJiaFAgQIqJ82+G9HRDBv8BZu37cTc3FztOC/VsvWn2v8vU86TsuU8qeRZioP7g6lb31dvOT54pnu3nKcXlatUo2xJVzasW0vnLt30luPfLF4wj5PHj/HTmt8o5uzM4UMHGD64P46Fi1C3fgO14xmslJQUunRsg6IoTJ89T+04OlatDOTjT9qq9m+1ZMlSHD52mri4h/y2YR09uwewY/c+gylGG5TMz/6Ie6SkKjrHN539Z/b09ftPeJqWRu9axVl5/C+epinPP4z4F4aw13y+fPkoWbIkV65c4f333yc5OZkHDx7otIrevn07yzGl2SVd80IvGjVqRExMDFevXmXmzJksXLiQcePGAWBsbIyjoyMmuThBJTk5+d8vygGnT53kTmwsNatVwjZvHmzz5uHg/mDmz/se27x5SE1N1UuO/8LF1Y38+QsQefWKqjny5cuHu0dJrkZEqJrjWU+ePGHyhNFMnPotDZt8SNlyXnTv2Qf/lq2ZN2eG2vEMVkYRGh0VxW+bdxhUa+jhQwe5cvkiHTp3VS2DqakpJdzd8a5YiYmTplLOszw/fD9btTzPKlPIimL5LNh1MXO3/PMuxSZgYmREQWvTXMtToEABjI2NiY3VXUIoNpeKo3dNfHw8ERERFC5cmEqVKpEnTx727NmjPX/x4kWioqLw8cn5oSNSiAq9MDMzw9HREScnJ/z9/fHz82PXrl1Aete8RqMhNDSUtLQ0ihUrxvz583V+/vTp0xgZGXH9+nUAHjx4QPfu3XFwcMDGxgZfX1/CwsK0148fP54KFSqwePFiXF1d9dbiUc+3AUdPhRNy/LT2VrFSZT5t256Q46f12uX9uv766wb379+jkGNhVXPEx8cTeTUCx8Lq5njW05QUUlJSMDLS/cg0NjZGScv92cJvoowiNOLKFYK2/I59/vxqR9Lx84qllPeuSDnP8mpH0UpT0kjS05fmf+NXqgBX7iRw7f6Tf73WNX9eUtMUHubi5CVTU1O8K1Zi7x//FEdpaWns3bvHoMbV/heaHLq9jiFDhhAcHMy1a9cICQmhRYsWGBsb07ZtW2xtbenWrRuDBg1i7969nDx5ki5duuDj45PjE5VAuuaFCs6ePUtISAjFixfPdM7IyIi2bduyatUqevfurT3+888/U7NmTe3PtG7dGgsLC7Zv346trS0LFy6kQYMGXLp0CXt7ewCuXLnC+vXr2bBhwwsLwKSkJJKSkrT3n1/64nVZW1tTtmw5nWN5LS2xt7fPdDy3pRd0/7RuRl2P5Ex4KHZ29uSzs+fbqV/xYfMWFCrkSOTVq0wYMwK3Eu74+n2g15xfjhhKkyYf4uRcnJiYm0z5ajxGxsZ8/EkbveZ42etVzMmZGrXqMGH0CCwsLCjm5EzIwf2s/eUnJk79Vu85I678k/NaZCRhoaHY2dvj7Jx7s9GzyhEZ8U+O69ciORMWSj57exwdC9O5/SeEhZ5m9bqNpKamcvv/kxzs7O0xNc29lrPn/x6vP/f3CPAoLo5NQeuZMGVaruX4N2NHj+SDho1xcnLmUfwj1q5exYHgfWzcsiNXn9fcxIjCNv8s51PQ2gxXewseJaVyNyG9CLbIY0QNV7ssx3yWKmhJSQdLzsQ84klKKqUKWtG1uhPBV+6RkJy7PT79vxhEj66dqVSpMpWrVGXunFk8TkigU2d1J5tlmwp7zd+4cYO2bdty7949HBwcqFWrFkeOHMHBwQGAmTNnYmRkRKtWrUhKSqJhw4b88MMP2QyZNSlEhV5s2bIFKysrnj59SlJSEkZGRsydOzfLa9u3b8/06dOJiorC2dmZtLQ0Vq9ezejRowE4ePAgx44dIzY2Vrs+2nfffUdQUBDr1q3js88+A9K741esWKH9h5WVqVOnMmHChBz+0xqG0FMnad7knxmmo0cMBaBN+458N2se586eYfXPK3n48AGOhYtQ39ePkWMmvHDNudxy868bdOncnvv37lHAwQGfGjX5IzjkpX9vuSHs9En8n3m9xoxMf70+bdeRuQuX8mPgz0waN4pe3Trx4O/7FHMqzpdjJxLQradec546eYKGfvW194cPHQRAh46dWbQ0UG85Qk+d4KPG/7xeo0YMAaBt+06MGDWW7Vs3A1DHp5LOz23evptaderlXq4X/D22+f/fI8CGdWtQFIVWH+v3y86z7tyJpUe3ztyKicHG1pZy5bzYuGUHDfxydxUGdwdLJjUtpb3frXr6cj9/XLrLnP3XAKjtZo9GAwci7mf6+ZRUhVol7GlTsQgmxkbEPkpi89nbbDyTO7vuPKv1J59y984dJk4Yy+1bt/AqX4GNW3ZQqFChf/9hoWP16tUvPW9ubs68efOYNy/3x3VrFEWRkcUiVwUEBPDXX38xf/58EhISmDlzJiYmJixenL6Qelaz5suWLUvHjh0ZMWIEe/fupWHDhsTExJA/f37mzZtH//79M83se/LkCUOGDOGbb75h/Pjx/Pzzz1y+fPml2bJqEXVycuLmnQcGNZ4NICnFMMeXmpoY5gifRD0ssP1fWJkb5vf/xFxuzcqOVAOdAGNhaphDbdqtOKl2hCytDqisdgQdcXFxFMpvy8OHD1X5vI+Li8PW1pZTl29hZZ29549/FEdFD0fV/izZYZifiOKtY2lpibt7+i4eS5cupXz58ixZsoRu3bKeFd2+fXtWrVrFiBEjWLVqFY0aNSL//8eYxcfHU7hwYfbt25fp556d4WdpafmvuV6264QQQgiR63Jg1ny2u/ZVZJhNGeKtZmRkxJdffsno0aN58iTrgfDt2rXj7NmznDx5knXr1tG+fXvtuYoVK3Lr1i1MTExwd3fXub0NS0AJIYQQ7wopRIUqWrdujbGx8QvHn7i4uFCjRg26detGamoqzZo1057z8/PDx8cHf39/du7cqZ31N2rUKE6cOKGvP4IQQgiRbWrMmjckUogKVZiYmNC3b1+mTZtGQkJClte0b9+esLAwWrRooTMeVKPRsG3bNurUqUOXLl0oWbIkbdq04fr16zJoXQghxJvlHa9EZbKSEM/IGDwuk5VenUxWej0yWen1yWSl1yOTlV6NoUxWOh1xC+tsTlZ69CgO7xIyWUkIIYQQQryGnNxr/k0khagQQgghhEoMYa95NRlmn5oQQgghhHjrSYuoEEIIIYRKVNjh06BIISqEEEIIoZZ3vBKVrnkhhBBCCKEKaREVQgghhFCJzJoXQgghhBCq0JADs+ZzJIk6pBAVQgghhFDJOz5EVMaICiGEEEIIdUiLqBBCCCGESt71Be2lEBVCCCGEUM273TkvhagQWTA20mBsZFj/sE9G/a12hCzV9nBQO0KWrIxl5NHrMDE2rPf7s8xNjdWO8EZZHVBZ7QhZqvbVHrUj6EhNSlA7gkAKUSGEEEII1UjXvBBCCCGEUMW73TEvs+aFEEIIIYRKpEVUCCGEEEIl0jUvhBBCCCFU8a5v8Sld80IIIYQQQhXSIiqEEEIIoZZ3fLaSFKJCCCGEECp5x+tQ6ZoXQgghhBDqkEJUiFyw4Id5lHJ3IZ+VObVrVOP4sWN6ff7U1FQC53xNx/cr86G3M50bVuGn+dNRFEXnuqiIS4zt0xH/qiX4qJILfT/5gNibN/SaFdR/vV7GULMZWq4pX03A2txY51bRq4yqmZ5laK9XBkPLdfDAflr5f4SrcxEs8mjYtDEo15+za+3i/PxZFUK+rMveobWZ2caL4vnz6lxjamLEyKalCB5eh8Nf1mX6p57YW5rqXFO2iDU/dvbmwIg6HBhRh/kdK1CykFWu58+ujFnz2b29qaQQFSKH/bp2DcOHDmLU6HEcPnYKL6/yNGvakNjYWL1lWLv4e7asDqTv6Kks3nKQboPG8uuSuQT9tFh7zc2oSAZ2+AgnV3e+Cwxi4W97ad9rEHnMzPSWEwzj9XrTshlqrtJlynLl2l/a284/9quaJ4Ohvl6GmCshIQFPr/LMmjNPb89Zubgda47doOOiE/RccRoTYw0LOlXAIs8/JcrQRh7ULVmAoWvP0HXZKRyszZjRxlN73sLUmB86enPrYSIdFp0gYMlJEpJSmd+xAiYGtl3z8zQ59N+bSgpRIXLYnFkz6NKtB50CulC6TBm+/2EBFnnzsjxwqd4ynA89jo9vI6rVfR/Hos7UafgRlWrW4+KZU9prls2eStU6DegxZBzuZTwp4uyKj28j7PLrd+94Q3i93rRshprLxMSEQo6O2luBAgVUzZPBUF8vQ8zVsFFjxk+cRHP/Fnp7zs9/CmVTaAwRdxK4dDuesb+dp0g+C0oXsQHAysyYFt5F+O73yxyL/JsLMY8YG3Qeb+d8eBZLv8a1QF7y5c3DvD+ucv3eYyLuJLBg31UKWJtROJ+53v4s4vVJISpEDkpOTub0qZP4NvDTHjMyMsLX149jRw7rLUeZClUIPXKAG9ciAIj48yxnTx2lSu0GAKSlpXEseBdFXUowsscntK5Vhn6fNuLQ7m16ywiG83plxVCzGWougIgrl/FwLYbne+5069yB6KgoVfOA4b5ehprLEFiZp8+jjnuSAkCZIjbkMTHi6NX72muu3X3MzQdPKO9kq73/d0IyLSoWwcRYg5mJES0qFiEiNoGbDxL1/4d4HZocur2hpBAVb5Tx48dToUIFtWO80N27d0lNTaVgwUI6xwsWKsStW7f0luPTHv2p18Sfbk1r0NirCJ+3akCLjj1p8NHHADy4d4cnjxNYs/h7Ktfy5etFa6jp14SJA7oQfjxEbzkN5fXKiqFmM9RclatWZcGipfy2aRszv5/HtevXaNigLo8ePVItExju62WoudSm0cCwRiU5ff0BV2ITAMhvZUry0zQeJT7VufZ+fDIFrNLHiT5OTqV74CmaejlybHR9Do+qR033/PT5KZTUNCXT8xiSd7wOlUJU/OPOnTv07t0bZ2dnzMzMcHR0pGHDhhw6dCjHnqNevXp88cUXOfZ4ImvBOzayZ8t6Rny7gB/W7Wbo1O9Zt+wHdgatBtBOWqrh24hWnXtRorQnbXr0p1q9D9iyZrma0cUb6oOGjWnRqjXlPL3we78h64O28PDhAzasW6t2NPEG+bJpKUoUtGTYurOv9XNmJkaMb16a0OiHdFx0nM5LTnAlNoG57ctjZiKljiGTdUSFVqtWrUhOTmb58uW4ublx+/Zt9uzZw71799SO9sYoUKAAxsbGxMbe1jkee/s2jo6Oesux6LsJtOnej/pN0sd5uZYsw+2bN1i9aA4f+LfBJp89xiYmOJcoqfNzzm4enD11VG85DeX1yoqhZjPUXM/Lly8f7h4luRoRoWoOQ329DDWXmkY2KUmdkgXouvQksXFJ2uP34pMxNTHC2txEp1XU3sqUu/HJADTxKkSRfBZ0XHyCjMVBRqw/y8ERdan/ngM7zuq+zobkXd9rXr4mCAAePHjAgQMH+Oabb6hfvz7FixenatWqjBw5kmbNmmmv6d69Ow4ODtjY2ODr60tYWJj2MSIiImjevDmFChXCysqKKlWqsHv37tfKMXz4cEqWLEnevHlxc3NjzJgxpKSkvPD6iIgI3Nzc6Nu3L4qikJSUxJAhQyhatCiWlpZUq1aNffv2/afX5L8wNTXFu2Il9v6xR3ssLS2NvXv3ULW6j95yJD15gsZI95+3kZExSloaAHlMTSlVrgI3Iq/oXHPjWgSFijjpLaehvF5ZMdRshprrefHx8URejcCxcGFVcxjq62WoudQysklJfEs70CPwFH89N6bz/M04Up6mUdXVTnuseP68FMlnQVj0QwDM8xiTpig8u0KdoqT3/hh+kZYTM+YN/g/5QtIiKgCwsrLCysqKoKAgqlevjlkWS/i0bt0aCwsLtm/fjq2tLQsXLqRBgwZcunQJe3t74uPjadKkCZMnT8bMzIwVK1bw0UcfcfHiRZydnV8ph7W1NYGBgRQpUoQzZ87Qo0cPrK2tGTZsWKZrw8PDadiwId26dWPSpEkA9O3bl/Pnz7N69WqKFCnCb7/9RqNGjThz5gweHh6ZHiMpKYmkpH++ecfFxb3qS/ZC/b8YRI+unalUqTKVq1Rl7pxZPE5IoFPnLtl+7FdVvf4H/LJwFgULF6O4eymuXDjDhuULaNiyrfaaj7v2Ycqgz/Cs7EP5qjU5cXAvR/bt5LvA3/SWEwzj9XrTshliri9HDKVJkw9xci5OTMxNpnw1HiNjYz7+pI1qmTIY4utlqLni4+OJuPLPF9RrkZGEhYZiZ2//yp/jr+vLpqVo7FmIL34JJyE5lfz/H/cZn/iUpKdpxCel8tvpmwxp5EHck6fEJz1lRJOShEY94MyN9M/swxH3Gfi+O182LcUvR6Mx0mjoWrs4T9MUjkf+nSu5Rc7QKM+vcC3eWevXr6dHjx48efKEihUrUrduXdq0aYOXlxcHDx6kadOmxMbG6hSp7u7uDBs2jM8++yzLxyxXrhy9evWib9++QPoY0QoVKjBr1qxXyvTdd9+xevVqTpw4AaRPVgoKCuKHH37gww8/ZNSoUQwePBiAqKgo3NzciIqKokiRItrH8PPzo2rVqkyZMiXT448fP54JEyZkOn773kNsbGxeKWNW5s+by8wZ33L71i28yldg+sw5VK1W7T8/HsCBy3de+drHCfEsn/M1h3Zv48H9u+QvWIh6TVrSofdg8pj+swj0jvWrWL1oNndvx1DMpQSd+g6jRoPGr5Wrtkf2l3vKjdcrpxhqtpzO9TQ1LVt5Ajq25dDBA9y/d48CDg741KjJ2PGTcCtRIluPC2BinP3Ou3fl7zG79gfvo6Ff/UzHO3TszKKlgdl67Gpf7cnyeNiEBlkeH/PbeTaFxgDpC9oPbuhB43KFMDUxIuTKPSZvvci9/3fNA1R3s6dXPVdKFLREUeDPW4/4fk+Etlh9XmpSAue+ac7Dh9n7vP+v4uLisLW15VrM/Ww/f1xcHC6F7VX7s2SHFKJCR2JiIgcOHODIkSNs376dY8eOsXjxYhISEujfvz8WFhY61z958oQhQ4bwzTffEB8fz/jx49m6dSsxMTE8ffqUJ0+eMHjwYKZNmwb8eyG6Zs0a5syZQ0REBPHx8Tx9+hQbGxvtAs/jx49nzpw5JCUlMXnyZJ2JT1u3buXDDz/E0tJS5zGTkpJo2bIla9asyfR8WbWIOjk5ZbsQzQ2vU4jqU04UokJ92S1Ec1NOFKJCfS8qRNUihahhkK55ocPc3Jz333+f999/nzFjxtC9e3fGjRvH559/TuHChbMcb5kvXz4AhgwZwq5du/juu+9wd3fHwsKCjz/+mOTk5Ew/k5XDhw/Tvn17JkyYQMOGDbG1tWX16tVMnz5d5zoHBweKFCnCL7/8QteuXbX/6OLj4zE2NubkyZMYGxvr/IyVVdbbvJmZmWU5DEEIIYQQuU8KUfFSZcqUISgoiIoVK3Lr1i1MTExwcXHJ8tpDhw4REBBAixbpM7Xj4+O5du3aKz9XSEgIxYsXZ9SoUdpj169fz3SdhYUFW7ZsoUmTJjRs2JCdO3dibW2Nt7c3qampxMbGUrt27df6cwohhBBqkFnzQgD37t3D19eXn376ifDwcCIjI/n111+ZNm0azZs3x8/PDx8fH/z9/dm5cyfXrl0jJCSEUaNGacdvenh4sGHDBkJDQwkLC6Ndu3akpWXu7rtz5w6hoaE6t9u3b+Ph4UFUVBSrV68mIiKCOXPm8NtvWU+csbS0ZOvWrZiYmNC4cWPi4+MpWbIk7du3p1OnTmzYsIHIyEiOHTvG1KlT2bp1a66+fkIIIcR/IXvNC0F613W1atWYOXMmderUoVy5cowZM4YePXowd+5cNBoN27Zto06dOnTp0oWSJUvSpk0brl+/TqFC6TuDzJgxAzs7O2rUqMFHH31Ew4YNqVixYqbnWrVqFd7e3jq3RYsW0axZMwYOHEjfvn2pUKECISEhjBkz5qWZt2/fjqIoNG3alISEBJYtW0anTp0YPHgwpUqVwt/fn+PHj+fabE8hhBBC/HcyWUmIZ2QMHpfJSq9OJiu9HWSykshtMllJV8bvm+jbf+fIZCWnQnYyWUkIIYQQQry6nFiO/s3tmJeueSGEEEIIoRJpERVCCCGEUMs73iQqhagQQgghhEpyYta7zJoXQgghhBDiNUmLqBBCCCGESt71Be2lEBVCCCGEUMk7PkRUuuaFEEIIIYQ6pBAVQgghhFCLJodu/8G8efNwcXHB3NycatWqcezYsWz9Uf4LKUSFEEIIIVSi1l7za9asYdCgQYwbN45Tp05Rvnx5GjZsSGxsbC78KV9MClEhhBBCiHfMjBkz6NGjB126dKFMmTIsWLCAvHnzsnTpUr3mkMlKQjxDURQAHsXFqZwks4T4R2pHyFJcnJnaEUQOkL3mRW5LTUpQO4KO1KTHwD+f+2p59Cgu27PeHz1K/50V99zvLjMzM8zMMn9GJycnc/LkSUaOHKk9ZmRkhJ+fH4cPH85emNckhagQz3j0KL3Yc3d1UjmJEEIIfXj06BG2trZ6f15TU1McHR3xyKHfN1ZWVjg56T7WuHHjGD9+fKZr7969S2pqKoUKFdI5XqhQIf78888cyfOqpBAV4hlFihQhOjoaa2trNNn8ihoXF4eTkxPR0dHY2NjkUMLsk1yvR3K9Hsn1eiTX68nJXIqi8OjRI4oUKZJD6V6Pubk5kZGRJCcn58jjKYqS6fdWVq2hhkYKUSGeYWRkRLFixXL0MW1sbAzqgzyD5Ho9kuv1SK7XI7leT07lUqMl9Fnm5uaYm5vr/XkLFCiAsbExt2/f1jl++/ZtHB0d9ZpFBt4IIYQQQrxDTE1NqVSpEnv27NEeS0tLY8+ePfj4+Og1i7SICiGEEEK8YwYNGkTnzp2pXLkyVatWZdasWSQkJNClSxe95pBCVIhcYmZmxrhx4wxujI7kej2S6/VIrtcjuV6PoeZ6E3366afcuXOHsWPHcuvWLSpUqMCOHTsyTWDKbRpF7XULhBBCCCHEO0nGiAohhBBCCFVIISqEEEIIIVQhhagQQgghhFCFFKJCCCGEEEIVUogKIYQQQghVSCEqRC5QFAVZkEIIIYR4OSlEhchBS5YsoVy5ctpt28qVK8fixYvVjsX+/ft5+vRppuNPnz5l//79KiQSb6vExES1I4j/KCUlBRMTE86ePat2lEwiIiIYPXo0bdu2JTY2FoDt27dz7tw5lZOJ7JIF7YXIIWPHjmXGjBn069dPu0Xa4cOHGThwIFFRUUycOFG1bPXr1ycmJoaCBQvqHH/48CH169cnNTVVpWRw+fJl9u7dS2xsLGlpaTrnxo4dq0qmcePG0bVrV4oXL67K879p0tLSmDx5MgsWLOD27dtcunQJNzc3xowZg4uLC926dVM1X2xsLBcvXgSgVKlSmf4d6Et4ePgrX+vl5ZWLSbKWJ08enJ2dVf08yEpwcDCNGzemZs2a7N+/n8mTJ1OwYEHCwsJYsmQJ69atUzuiyAZZ0F6IHOLg4MCcOXNo27atzvFffvmFfv36cffuXZWSgZGREbdv38bBwUHn+KVLl6hcuTJxcXGq5Fq0aBG9e/emQIECODo6otFotOc0Gg2nTp1SJVeFChU4e/YsdevWpVu3brRq1Uq1nVy8vb11XpeXUev1mjhxIsuXL2fixIn06NGDs2fP4ubmxpo1a5g1axaHDx9WJdejR4/4/PPPWb16tba4MjY25tNPP2XevHnY2trqNY+RkREajeaFw3Yyzmk0GtWKwSVLlrBhwwZWrlyJvb29Khme5+PjQ+vWrRk0aBDW1taEhYXh5ubGsWPHaNmyJTdu3FA7osgGaREVIoekpKRQuXLlTMcrVaqUZbe4PrRs2RJI/wUXEBCgU0ylpqYSHh5OjRo1VMkGMGnSJCZPnszw4cNVy5CV0NBQTp8+zbJlyxgwYAB9+vShTZs2dO3alSpVqug1i7+/v16f779YsWIFP/74Iw0aNKBXr17a4+XLl+fPP/9ULVf37t05ffo0W7Zs0emlGDBgAD179mT16tV6zRMZGanX5/sv5s6dy5UrVyhSpAjFixfH0tJS57waX3bOnDnDqlWrMh0vWLCgql/wRc6QQlSIHNKxY0fmz5/PjBkzdI7/+OOPtG/fXpVMGS0+iqJgbW2NhYWF9pypqSnVq1enR48eqmQD+Pvvv2ndurVqz/8y3t7eeHt7M336dDZv3syyZcuoWbMm7733Ht26dSMgIEAvLWrjxo3L9efIrr/++gt3d/dMx9PS0khJSVEhUbotW7bw+++/U6tWLe2xhg0bsmjRIho1aqT3PG/CUA9D/OKTL18+YmJicHV11Tl++vRpihYtqlIqkVOkEBUiBy1ZsoSdO3dSvXp1AI4ePUpUVBSdOnVi0KBB2uueL1Zzy7JlywBwcXFhyJAhmVo31Na6dWt27typ04pmaBRFISUlheTkZBRFwc7Ojrlz5zJmzBgWLVrEp59+qnZE1ZUpU4YDBw5kKrTWrVuHt7e3Sqkgf/78WX5ZsLW1xc7OToVEmZ0/f56oqCiSk5N1jjdr1kyVPIb4xadNmzYMHz6cX3/9FY1GQ1paGocOHWLIkCF06tRJ7Xgim6QQFSKHnD17looVKwLpMzwBChQoQIECBXRmob7qeL+cNGzYMJ1xadevX+e3336jTJkyfPDBB3rPk8Hd3Z0xY8Zw5MgRPD09yZMnj875/v37q5QMTp48ybJly/jll18wMzOjU6dOzJs3T9vy9/3339O/f3+9FqKpqanMnDmTtWvXZlm83L9/X29ZnjV27Fg6d+7MX3/9RVpaGhs2bODixYusWLGCLVu2qJIJYPTo0QwaNIiVK1fi6OgIwK1btxg6dChjxoxRLRfA1atXadGiBWfOnNEZN5rx+aDmhKEHDx6wbt06IiIiGDp0KPb29pw6dYpChQqp0gI5ZcoU+vTpg5OTE6mpqZQpU4bU1FTatWvH6NGj9Z5H5CyZrCTEO+CDDz6gZcuW9OrViwcPHlCqVClMTU25e/cuM2bMoHfv3qrker6r7VkajYarV6/qMc0/PD09+fPPP/nggw/o0aMHH330EcbGxjrX3L17l4IFC2aa6Z+bxo4dy+LFixk8eDCjR49m1KhRXLt2jaCgIMaOHatq4X7gwAEmTpxIWFgY8fHxVKxYkbFjx6r6Rcfb25srV66QlJSEs7MzAFFRUZiZmeHh4aFzrb7HPma8pxYvXoyrqyvHjh3j3r17DB48mO+++47atWvrNU+G8PBw/Pz8sLW15dq1a1y8eBE3NzdGjx5NVFQUK1asUCUXQHR0NGfOnCE+Ph5vb288PDx48uSJzpAj8eaRQlSIXJAxi7NYsWIqJ0lXoEABgoODKVu2LIsXL+b777/n9OnTrF+/nrFjx3LhwgW1IxqUr776iq5duxrc+LMSJUowZ84cmjZtirW1NaGhodpjR44cyXJCR257+vQpU6ZMoWvXrgbzfs8wYcKEV75W313SBQoU4I8//sDLywtbW1uOHTtGqVKl+OOPPxg8eDCnT5/Wa54Mfn5+VKxYkWnTpunMUA8JCaFdu3Zcu3ZN75n69+/PnDlzMh1PSEjgww8/ZO/evXrPJHKOdM0LkUPS0tKYNGkS06dPJz4+HgBra2sGDx7MqFGjMDJSb/+Ix48fY21tDcDOnTtp2bIlRkZGVK9enevXr6uW61nPd02qSe1u2xe5desWnp6eAFhZWfHw4UMAPvzwQ9Uym5iYMG3aNIMcq2eI4x0zpKamav9NFihQgJs3b1KqVCmKFy+uXfNUDcePH2fhwoWZjhctWpRbt26pkAi2bt2KnZ2dzheLhIQEVSaciZwnhagQOWTUqFEsWbKEr7/+mpo1awJw8OBBxo8fT2JiIpMnT1Ytm7u7O0FBQbRo0YLff/+dgQMHAukLfdvY2KiWC9KX/vn222+5fPkyACVLlmTo0KF07NhR1Vw3btxg06ZNWY7F1Ndks+cVK1aMmJgYnJ2dKVGiBDt37qRixYocP35ctXVOARo0aEBwcDAuLi6qZXiZkydPalv9y5Ytq+oEqgzlypUjLCwMV1dXqlWrxrRp0zA1NeXHH3/Ezc1NtVxmZmZZrit86dKlTOsQ68vOnTupXbs2dnZ2fPHFFzx69IiGDRtiYmLC9u3bVckkcpAihMgRhQsXVjZu3JjpeFBQkFKkSBEVEv3j119/VfLkyaMYGRkpfn5+2uNTpkxRGjVqpFqu6dOnK3nz5lWGDRumbNy4Udm4caMydOhQJW/evMqMGTNUy7V7924lb968Srly5RQTExOlQoUKSr58+RRbW1ulfv36quUaPny4MnnyZEVRFGX16tWKiYmJ4u7urpiamirDhw9XLdf8+fMVR0dHZfDgwcqqVau0f5cZN7Xcvn1bqV+/vqLRaBQ7OzvFzs5O0Wg0iq+vrxIbG6taLkVRlB07dijr169XFEVRLl++rJQqVUrRaDRKgQIFlD179qiWq1u3boq/v7+SnJysWFlZKVevXlWuX7+ueHt7KwMGDFAtV1hYmGJvb6/Mnj1bqV69ulK3bl0lPj5etTwi50ghKkQOMTMzUy5evJjp+J9//qmYm5urkEhXTEyMcurUKSU1NVV77OjRo8qFCxdUy+Ti4qIsX7480/HAwEDFxcVFhUTpqlSpoowdO1ZRFEWxsrJSIiIilEePHinNmjVTfvjhB9VyPS8kJESZPn26smnTJlVzaDSaF96MjIxUy/XJJ58olStXVs6fP689du7cOaVy5cpKmzZtVMv1Ivfu3VPS0tJUzfDgwQPFz89PyZcvn2JsbKw4OTkpefLkUerUqaN64RcSEqJYWloqvr6+yuPHj1XNInKOTFYSIodUq1aNatWqZRpU369fP44fP86RI0dUSvaPK1euEBERQZ06dbCwsNBuJ6gWc3Nzzp49m2kx9MuXL+Pp6UliYqIquZ6dCGRnZ8fBgwcpW7YsYWFhNG/eXJUJG+L12drasnv37ky7YR07dowPPviABw8eqBPsDXDw4EHCw8O1KyD4+fnp9flftLXt9evXKViwoM5MebW2thU5Q8aICpFDpk2bRtOmTdm9e7fOdoLR0dFs27ZN1Wz37t3jk08+Ye/evWg0Gi5fvoybmxvdunXDzs6O6dOnq5LL3d2dtWvX8uWXX+ocX7NmTabldfTJ0tJSOy60cOHCREREULZsWQC9bym4adMmGjduTJ48edi0adNLr1VrEXRDlZaWlmltWoA8efLoddmtDC1btiQwMBAbGxvt9rsvsmHDBj2l0hUdHY2TkxO1atXS2ZFK3wxxhyeRO6QQFSKH1K1bl0uXLjFv3jzt/totW7bk888/p0iRIqpmGzhwIHny5CEqKorSpUtrj3/66acMGjRItUJ0woQJfPrpp+zfv187wevQoUPs2bOHtWvXqpIJoHr16hw8eJDSpUvTpEkTBg8ezJkzZ9iwYYN21yx98ff359atWxQsWPClv5w1Go1qi6BPnDjxpefHjh2rpyS6fH19GTBgAL/88ov23+Bff/3FwIEDadCggd7z2Nraalv5bGxsDGKFiOe5uLhQq1YtOnTowMcff6zaDlSGvOKByFnSNS9EDkhJSaFRo0YsWLBA1Za8F3F0dOT333+nfPnyOmsDXr16FS8vL+1yU2o4efIkM2fO1M5qLl26NIMHD1Z1ZvPVq1eJj4/Hy8uLhIQEBg8eTEhICB4eHsyYMeON2DNcn57/u0pJSSEyMhITExNKlCihWtdpdHQ0zZo149y5czg5OWmPlStXjk2bNhncuqeG4PTp06xatYrVq1dz584dGjVqRIcOHfjoo49UXZlBvL2kEBUihzg4OGiLFUNjbW3NqVOn8PDw0ClET5w4QcOGDbl3757aEcW/MPQvO8+Li4sjICCAFi1aqLoUl6Io7N69W9tLUbp0ab2Pd8yKr68vGzZsIF++fDrH4+Li8Pf3548//lAn2P8pisK+fftYtWoV69evJy0tjZYtW7J06VK9ZzHUrW1FzpBCVIgcMnDgQMzMzPj666/VjpJJkyZNqFSpEl999RXW1taEh4dTvHhx2rRpQ1paGuvWrdNblri4OO3apVmtV/gstdY4HTt2LPXr18fHxwdzc3NVMmTFkL/sZOXMmTN89NFHqkzuSklJwcLCgtDQUMqVK6f35/83RkZG2iEXz4qNjaVo0aKkpKSolCyzU6dO0a1bN8LDw1UZ/mHIW9uK7JMxokLkkKdPn7J06VJ2795NpUqVsLS01Dmv1iLokD6RqkGDBpw4cYLk5GSGDRvGuXPnuH//PocOHdJrFjs7O2JiYihYsCD58uXLcpxcxmx+tcY8Hj58mBkzZvD06VOqVKlC3bp1qVevHjVr1lR1X+sOHTpoN014Ezx8+FC7+5O+5cmTB2dnZ9XeQy8SHh6u/f/z58/r7FaUmprKjh07DGJr2Rs3brBq1SpWrVrF2bNn8fHxYd68eapk+fnnn1m0aBFNmzZl/PjxtG3blhIlSuDl5cWRI0ekEH3DSSEqRA45e/YsFStWBNJ3IXmW2pMSypUrx6VLl5g7dy7W1tbEx8fTsmVL+vTpQ+HChfWa5Y8//sDe3h7AYPeI3rVrF0+fPuXo0aPs37+f4OBg5syZQ1JSElWqVOHgwYOq5DLULzvPL1mmKAoxMTGsXLmSxo0bq5IJ0nc7+/LLL1m5cqX2Pae2ChUqoNFo0Gg0+Pr6ZjpvYWHB999/r0KydAsXLmTVqlUcOnSI9957j/bt27Nx40ZVx0Ub4ta2IudI17wQbzlDHlsYFRWFk5NTpkJdURSio6NxdnZWKdk/Ll26xN69e9m9ezdBQUHY2trqfQmnDPXr13/pebUKe1dXV537RkZGODg44Ovry8iRI7V7quubt7c3V65cISUlheLFi2cq3NWYRHX9+nUURcHNzY1jx47pbJtpampKwYIFMTY21nuuDE5OTrRt25b27dtTvnx51XI8q1SpUqxYsYJq1apRq1YtPvzwQ0aMGMGaNWvo168fsbGxakcU2SAtokJkU2pqKufOncPDwyNTt+2TJ0+4fPky5cqVw8jISJV8efLk0ekONCSurq7abvpn3b9/H1dXV9W6VX/88Uf27dtHcHAwSUlJ1K5dm3r16jF69Gi8vLxUyQSG24IcGRmpdoQsGeJalBkti2qsY/oqoqKiVO/BeV6LFi3Ys2cP1apVo1+/ftohKlFRUQwcOFDteCKbpEVUiGwKDAxk7ty5HD16NFNLxtOnT6levTpffPEFHTp0UCmh4U6kMjIy4vbt2zqtQpDealSmTBkSEhJUy+Xg4MDgwYP5/PPPsbKyUiXH87p27crs2bMztTAmJCTQr18/VWY0G3IuQ3f58mX27t1LbGxspsJUn2uvhoeHa78s/9uXVjW/iGU4cuSIdtLeRx99pHYckU1SiAqRTbVr16ZPnz60adMmy/Nr165l7ty57N+/X8/J/tGvXz9WrFiBh4eHQYwtHDRoEACzZ8+mR48e5M2bV3suNTVVW9TreyJVhqCgIPbv38++ffu4cOEC3t7e1KtXj3r16lGrVi2dvPpkbGycZQvy3bt3cXR05OnTp5IL+Pvvv/npp5/o3LlzppUXHj58yIoVK7I8p0+LFi2id+/eFChQAEdHR51WSI1Go9dhA8/O4DcyMkKj0ZBVaaDmBMKsxMbGsnjx4kw7s4k3i3TNC5FNFy9efOluO1WqVNEu1q4WQ5tIdfr0aSB9LOiZM2cwNTXVnjM1NaV8+fIMGTJE77ky+Pv7a7t1Hz58yIEDB/j111/58MMPMTIyIjExUa954uLiUBQFRVF49OiRzpJSqampbNu2LVMR+C7nmjt3LuHh4fTr1y/TOVtbWw4cOEBcXByjRo3Se7YMkyZNYvLkyQwfPly1DBkiIyO1vRIvG2ahVg/Fi8TExDBmzBgpRN9wUogKkU0JCQkvXQ/z0aNHPH78WI+JMjO0sYUZebp06cLs2bNVbZl6kXv37hEcHMy+ffvYt28f586dw87Ojtq1a+s9S8YyVxqNhpIlS2Y6r9FomDBhguT6v/Xr179029qePXsyZMgQVQvRv//+m9atW6v2/M96dkZ8VrPjk5KSmDdvHtOmTdNZbkqInCCFqBDZ5OHhQUhIyAvHTh08eNCgZqvfuHEDwCC2N1y2bJnaEbLk6enJhQsXsLOzo06dOvTo0YO6deuqNj5u7969KIqCr68v69ev11mKyNTUlOLFi2v3UpdcEBER8dJ/cx4eHkREROgxUWatW7dm586d9OrVS9UcGZKSkhg/fjy7du3C1NSUYcOG4e/vz7Jlyxg1ahTGxsYyMUjkCilEhcimdu3aMXr0aGrUqJGpUAkLC2Ps2LEMGzZMpXTp0tLSmDRpEtOnT9fuK29tbc3gwYMZNWqUajP6AU6cOPHCrfs2bNigSqZevXpRt25dg9mRp27dukB6t6mzs7PBzGo21FzGxsbcvHnzhct/3bx5U9X3PIC7uztjxozhyJEjeHp6kidPHp3z+l6kfezYsSxcuBA/Pz9CQkJo3bo1Xbp04ciRI8yYMYPWrVuruqyUeHtJISpENg0cOJDt27dTqVIl/Pz8eO+99wD4888/2b17NzVr1lS9JWHUqFHaHXlq1qwJpLfUjh8/nsTERCZPnqxKrtWrV9OpUycaNmzIzp07+eCDD7h06RK3b9+mRYsWqmQC6NOnj2rP/TIXLlwgOjqaWrVqATBv3jwWLVpEmTJlmDdvHnZ2dpKL9PVDg4KCXjh2+7fffsPb21uvmZ73448/YmVlRXBwMMHBwTrnNBqN3gvRX3/9lRUrVtCsWTPOnj2Ll5cXT58+JSwsTLUvGBmTGl/kzp07ekoicpPMmhciB6SkpDBz5kxWrVrF5cuXURSFkiVL0q5dO7744gudyThqKFKkCAsWLKBZs2Y6xzdu3Mjnn3/OX3/9pUouLy8vevbsSZ8+fbC2tiYsLAxXV1d69uxJ4cKFVRlfCOkTbQIDA9mzZ0+WS+v88ccfquTy9PTkm2++oUmTJpw5c4bKlSszePBg9u7dy3vvvafaUAdDy7V+/XratGnDzJkz6d27t7YlLzU1lR9++IHBgwezatUqPv74Y73mMmSmpqZERkZqtxe1sLDg2LFj2h2N1PBvGzhkMLQx8OL1SCEqxDvA3Nyc8PDwTBNKLl68SIUKFXjy5IkquSwtLTl37hwuLi7kz5+fffv2acdn+vr6EhMTo0quvn37EhgYSNOmTSlcuHCmFqGZM2eqksvKyoqzZ8/i4uLC+PHjOXv2LOvWrePUqVM0adJEtYkkhphr1KhRTJ06FWtra9zc3AC4evUq8fHxDB061GDW1E1OTiYyMpISJUpgYqJeJ6WxsTG3bt3Szp63trYmPDw8065ZQuQ06ZoX4h1Qvnx55s6dm2lP8Llz56q6jZ+dnR2PHj0CoGjRopw9exZPT08ePHig6koDq1evZu3atTRp0kS1DFkxNTXVvi67d++mU6dOANjb27905YZ3MdfkyZNp3rw5P//8M1euXEFRFOrWrUu7du2oWrWqKpme9fjxY/r168fy5cuB9GXV3Nzc6NevH0WLFmXEiBF6zaMoCgEBAZiZmQGQmJhIr169Mq05rNa4bfH2kkJUiGyws7N75fFT9+/fz+U0LzZt2jSaNm3K7t278fHxAeDw4cNER0ezbds21XLVqVOHXbt24enpSevWrRkwYAB//PEHu3btokGDBqrlMjU1xd3dXbXnf5FatWoxaNAgatasybFjx1izZg2QXsSouQqCoeZydHRk5syZWU5MioqKeuFkJn0YOXIkYWFh7Nu3j0aNGmmP+/n5MX78eL0Xop07d9a5r+ZOcFm5ceMGmzZtynJSo7435BA5S7rmhciGjNaMV/H8B70+XL16FVdXVzQaDTdv3uSHH37QLq5funRpPv/8c1WW18lw//59EhMTKVKkCGlpaUybNk27dd/o0aNVm3wzffp0rl69yty5cw1mJjikF0+ff/450dHR9O/fn27dugHpE+ZSU1MztXi/67letOPTvXv3KFiwoKq7BBUvXpw1a9ZQvXp17fhoNzc3rly5QsWKFVVt4TY0e/bsoVmzZri5ufHnn39Srlw5rl27hqIoVKxYUbUx2yJnSCEqxFvs+V/En376KXPmzKFQoUIqJzM8LVu21Ln/xx9/YG9vT9myZTMtrSPdk2+GZ7eufNb169cpU6aMqjsF5c2bl7Nnz+Lm5qZTiIaFhVGnTh0ePnyoWjZDU7VqVRo3bsyECRO0r1XBggVp3749jRo1onfv3mpHFNkgXfNC5ILExMRM3Udq7B70/PfM7du3G9Q2fYbUYmVra6tzX83lo14kKirqpefV7GrOYAjv/YxlfzQaDWPHjiVv3rzac6mpqRw9epQKFSroNdPzKleuzNatW7XbkGa0vC9evFg7fEaku3DhAr/88gsAJiYmPHnyBCsrKyZOnEjz5s2lEH3DSSEqRA5JSEhg+PDhrF27lnv37mU6r2Y3YAZD6wB5UZ6kpCS9L3llqLs8PcvFxeWlQwXUeo8Z2nv/9OnTQPr768yZMzrvJVNTU8qXL8+QIUP0mul5U6ZMoXHjxpw/f56nT58ye/Zszp8/T0hISKZ1Rd91lpaW2i83hQsXJiIigrJlywJw9+5dNaOJHCCFqBA5ZNiwYezdu5f58+fTsWNH5s2bx19//cXChQtVWyomYx/w54+pLWPMoEajYfHixVhZWWnPpaamsn//fu3GAOIfGQVWhpSUFE6fPs2MGTNU25QADO+9n7GuZJcuXZg9e7YqvRH/platWoSGhvL111/j6enJzp07qVixIocPH1Z17U5DVL16dQ4ePEjp0qVp0qQJgwcP5syZM2zYsOGFmxaIN4eMERUihzg7O7NixQrq1auHjY0Np06dwt3dnZUrV/LLL7+oMjvdyMiIxo0ba5dk2bx5M76+vqovyZKxNuH169cpVqyYztaBpqamuLi4MHHiRKpVq6bXXBm8vb2zLNg1Gg3m5ua4u7sTEBDwygtu57atW7fy7bffsm/fPlWe3xDf++LtkbH+q5eXFwkJCQwePFg7qXHGjBkUL15c7YgiG6RFVIgccv/+fe3C2TY2NtrlmmrVqqXaGCZDXZIlMjISSN85ZcOGDarNjn+RRo0aMX/+fDw9PbVrTh4/fpzw8HACAgI4f/48fn5+bNiwgebNm6ucFkqVKsXx48dVe35DfO9D+pCBr7/++oU7ZF29elWveV5nJrwhtuKqJeO9Bend9AsWLFAxjchpUogKkUPc3NyIjIzE2dmZ9957j7Vr11K1alU2b95Mvnz5VMlk6OMeM7pQDWV3mQx3795l8ODBjBkzRuf4pEmTuH79Ojt37mTcuHF89dVXei1Eny9kFEUhJiaG8ePH4+HhobcczzPE9z5A9+7dCQ4OpmPHjlnukKVv+fLle+UMhjCm3JA8ePCAdevWERERwdChQ7G3t+fUqVMUKlRIuy2peEMpQogcMWPGDGX27NmKoijKrl27FHNzc8XMzEwxMjJSZs2apXI6w/T48WOla9euirGxsWJsbKxEREQoiqIoffv2VaZOnapaLhsbG+Xy5cuZjl++fFmxsbFRFEVRLly4oFhZWek1l0ajUYyMjHRuGo1GcXZ2VkJCQvSa5VmG+t63tbVVDh48qNrzP2/fvn3aW2BgoOLo6KiMGDFC2bhxo7Jx40ZlxIgRSuHChZXAwEC1oxqUsLAwxcHBQXF3d1dMTEy0nxOjRo1SOnbsqHI6kV3qNz0I8ZYYOHCg9v/9/Pz4888/OXnyJO7u7nh5eamYzHCNGDHCoHaXyWBubk5ISEim3ZVCQkIwNzcHIC0tTfv/+pLRgpzByMgIBwcH3N3dVWlJTktL49tvv2XTpk0kJydz8+ZNxo0bZzDvfTs7O+zt7VV7/ufVrVtX+/8TJ05kxowZtG3bVnusWbNmeHp68uOPP6qyAYahGjRoEAEBAUybNg1ra2vt8SZNmtCuXTsVk4mcIIWoELmkePHiMoj+XwQFBWl3l3m2y7Js2bJERESolqtfv3706tWLkydPUqVKFSB9jOjixYv58ssvAfj999/1vhbls4WMIZg8eTLjx4/Hz88PCwsLZs+eTWxsLEuXLjWI9/5XX33F2LFjWb58uc5aoobg8OHDWY51rFy5Mt27d1chkeE6fvw4CxcuzHS8aNGi3Lp1S4VEIidJISpEDpk4ceJLz48dO1ZPSd4cd+7cybSYPaRPMlFzPN/o0aNxdXVl7ty5rFy5EkifELRo0SJtC0yvXr30MhFn06ZNr3xts2bNcjFJZitWrOCHH36gZ8+eAOzevZumTZuyePHiLPd317fp06cTERFBoUKFcHFxybRD1qlTp1RKBk5OTixatIhp06bpHF+8eDFOTk4qpTJMZmZmWU70unTpEg4ODiokEjlJlm8SIod4e3vr3E9JSSEyMhITExNKlCih6i89Q1WnTh1at25Nv379sLa2Jjw8HFdXV/r168fly5fZsWOH2hFV93xBp9FodDYCeLZg1/cEFzMzM65cuaJTOJmbm3PlyhWKFSum1yxZmTBhwkvPjxs3Tk9JMtu2bRutWrXC3d1du0zZsWPHuHz5MuvXr6dJkyaqZTM03bt35969e6xduxZ7e3vCw8MxNjbG39+fOnXqMGvWLLUjimyQQlSIXBQXF0dAQAAtWrSgY8eOascxOAcPHqRx48Z06NCBwMBAevbsqbO7TKVKldSOaFB2797N8OHDmTJlinYbyMOHDzN69GimTJnC+++/r9c8xsbG3Lp1S6dV6tkvFOLloqOjmT9/Pn/++ScApUuXplevXtIi+pyHDx/y8ccfc+LECR49ekSRIkWIiYnBx8eH7du3Z1oXWbxZpBAVIpedOXOGjz76iGvXrqkdxSBFRETw9ddfExYWRnx8PBUrVmT48OF6313G3t6eS5cuUaBAAezs7F46NCBjnUx9K1euHAsWLKBWrVo6xw8cOMBnn33GhQsX9Jrn+Q0TIOtNE/S9YcKzZNmft8fBgwcJDw8nPj6eSpUq0aBBA7UjiRwgY0SFyGUPHz7k4cOHascwWCVKlGDRokVqx2DmzJnaGbkzZ85Ufc3JrERERGS5Lqetra0qX3SymtltKJsmAISHh+Pn56d9fXr06IG9vT0bNmwgKiqKFStW6D1PuXLlMDIyIjw8/KXXykob6a399+7d48MPPwTSN0iIiIhg2rRpPH78GH9/f77//nudL0LizSMtokLkkIz90zMo/19sfOXKldStW5dVq1aplMxwvWinGY1Gg5mZGaampgaR53lq7XpTp04dzM3NWblyJYUKFQLg9u3bdOrUicTERIKDg1XJZaj8/PyoWLGidtmfsLAw3NzcCAkJoV27dnov3o2MjLh16xYFCxbEyMgo03jfDBqNRha0Bxo3bky9evUYPnw4kN67VKlSJTp37kzp0qX59ttv6dmzJ+PHj1c3qMgWKUSFyCHPj4nLWOPR19eXkSNH6qx/J9Jl/DJ+kWLFihEQEMC4ceP0Mgv73/JkUKtIuHLlCi1atODSpUvacYTR0dF4eHgQFBSUad3Td52trS2nTp2iRIkSOoXo9evXKVWqFImJiXrNc/36dZydndFoNFy/fv2l1xrC8ldqK1y4MJs3b6Zy5coAjBo1iuDgYA4ePAjAr7/+yrhx4zh//ryaMUU2Sde8EDkkY/908eoCAwMZNWoUAQEB2j3djx07xvLlyxk9ejR37tzhu+++w8zMTLt+Z256dsF4RVFo0qQJixcvNpixhO7u7oSHh7Nr1y6dCS5+fn4GOZRAbYa27M+zxaUUmv/u77//1rb8AwQHB9O4cWPt/SpVqhAdHa1GNJGT1NjOSQghFEVRfH19lTVr1mQ6vmbNGsXX11dRFEVZsWKFUqpUKX1HUxRFUaysrLTbCYo3T7du3RR/f38lOTlZsbKyUq5evapcv35d8fb2VgYMGKBqtsDAQGXLli3a+0OHDlVsbW0VHx8f5dq1ayomMxzOzs5KcHCwoiiKkpSUpFhYWCi7d+/Wng8PD1fs7OzUiidyiHTNC5FDEhIS+Prrr9mzZw+xsbGkpaXpnL969apKyQyXhYUF4eHheHh46By/fPky5cuX5/Hjx0RGRlK2bFkeP36s93zPducaij179rzwPbZ06VKVUhmmrJb9uXXrFj4+Pmzbtk3VZX9KlSrF/Pnz8fX15fDhwzRo0IBZs2axZcsWTExMVF1pwFD07t2bsLAwvvnmG4KCgli+fDk3b97Ujh3/+eefmTVrFsePH1c5qcgO6ZoXIod0796d4OBgOnbsSOHChaWr9BU4OTmxZMkSvv76a53jS5Ys0Y6BvHfvHnZ2dmrEMzgTJkxg4sSJVK5cWd5jr8DW1pZdu3bpLPtTsWJF/Pz81I5GdHS0dkxvUFAQH3/8MZ999hk1a9akXr166oYzEF999RUtW7akbt26WFlZsXz5cp0JjEuXLuWDDz5QMaHICVKICpFDtm/fztatW6lZs6baUd4Y3333Ha1bt2b79u3aPd1PnDjBn3/+ybp164D0faY//fRT1TIaUrG3YMECAgMDZXOE11SrVq1Ma6+qzcrKinv37uHs7MzOnTsZNGgQkL4z1ZMnT1ROZxgKFCjA/v37efjwIVZWVhgbG+uc//XXX7GyslIpncgpUogKkUPs7Oywt7dXO8YbpVmzZvz5558sXLiQS5cuAelLtgQFBeHi4gKgl/3cM7Rs2VLnfmJiIr169crUhatWt2lycjI1atRQ5bnfVIY6lOH999+ne/fueHt7c+nSJe2WnufOndO+90U6W1vbLI/L5+3bQcaICpFDfvrpJzZu3Mjy5cvJmzev2nHEf9ClS5dXum7ZsmW5nCRrw4cPx8rKijFjxqjy/G+afxvK8Ntvv6mULH3Hp9GjRxMdHU3v3r1p1KgRAOPGjcPU1JRRo0aplk0IfZJCVIgc4u3tTUREBIqi4OLiQp48eXTOnzp1SqVkhu3AgQMsXLiQq1ev8uuvv1K0aFFWrlyJq6urwXWnqm3AgAGsWLECLy8vvLy8Mr3HZsyYoVIyw1S4cGGmTZsmQxmEMGDSNS9EDvH391c7whtn/fr1dOzYkfbt23Pq1CmSkpKA9NnOU6ZMYdu2bSonNCzh4eFUqFABgLNnz6ob5g1g6EMZ5EuYENIiKoRQkbe3NwMHDqRTp046SyWdPn2axo0bc+vWLbUjijeYIQ9lePZL2MqVKzl//jxubm7MnTuXbdu2yZcw8c6QFlEhclhycnKWEyOcnZ1VSmS4Ll68SJ06dTIdt7W15cGDB/oPZKCen0SVFY1Gw/r16/WQ5s2RmJjIjz/+yO7duw1uKMOkSZNYsGABnTp1YvXq1drjNWvWZNKkSarlEkLfpBAVIodcunSJbt26ERISonNcURQ0Go1q+5MbMkdHR65cuZJplvDBgwcNahF5tb1o1rB4uZcNZVB7WS75EiZEOilEhcghXbp0wcTEhC1btshi46+oR48eDBgwgKVLl6LRaLh58yaHDx9myJAhBtmdqha1Zum/6fbu3at2hBeSL2FCpJNCVIgcEhoaysmTJ3nvvffUjvLGGDFiBGlpaTRo0IDHjx9Tp04dzMzMGDJkCP369VM7nhC55kVfwgYPHszYsWPVjieE3shkJSFySJUqVZg5c6bMdn0FlStXpnv37rRr1w4bGxuSk5O5cuUK8fHxlClTRnZLETnmxIkTrF27lqioKJKTk3XOqbmfu6IoTJkyhalTp/L48WMAzMzMGDp0KCNHjsTCwkK1bELok5HaAYR4W3zzzTcMGzaMffv2ce/ePeLi4nRu4h/ly5dn2LBhFC5cmE6dOhESEkKZMmWoWrWqFKEix6xevZoaNWpw4cIFfvvtN1JSUjh37hx//PGH6uNuNRoNo0aN4v79+5w9e5YjR45w584dbG1tcXV1VTWbEPokLaJC5BAjo/Tvdc+PDZXJSll7/Pgxa9euJTAwkAMHDuDq6krXrl3p3LkzRYsWVTueeAt4eXnRs2dP+vTpo10ezNXVlZ49e1K4cGEmTJig90xJSUmMHz+eXbt2aVtA/f39WbZsGaNHj8bY2Jg+ffowfPhwvWcTQg1SiAqRQ4KDg1947syZM/Tt21ePad4sERERLFu2jJUrV3Lz5k0++OADunXr9krLFgnxIpaWltq92/Pnz8++ffvw9PTkwoUL+Pr6EhMTo/dMw4cPZ+HChfj5+RESEsKdO3fo0qULR44c4csvv6R169YYGxvrPZcQapFCVIhc8ujRI3755RcWL17MyZMnpUX0FSiKwvr16+nZsycPHjyQ10xkS7Fixdi+fTuenp54eXkxcuRI2rZty+HDh2nUqBEPHz7UeyY3NzdmzZpFs2bNOHv2LF5eXgQEBLBkyRJZaUO8k2SMqBA5bP/+/XTu3JnChQvz3Xff4evry5EjR9SOZfD27dtHQEAAAQEBpKam0qNHD7UjiTdcnTp12LVrFwCtW7dmwIAB9OjRg7Zt29KgQQNVMt24cYNKlSoBUK5cOczMzBg4cKAUoeKdJcs3CZEDbt26RWBgIEuWLCEuLo5PPvmEpKQkgoKCKFOmjNrxDNaNGzcIDAwkMDCQq1evUrt2bX744Qdat24ts4ZFts2dO5fExEQARo0aRZ48eQgJCaFVq1aMHj1alUypqamYmppq75uYmMgEPfFOk655IbLpo48+Yv/+/TRt2pT27dvTqFEjjI2NyZMnD2FhYVKIZmHt2rUsXbqUPXv2ULBgQTp37kzXrl1xd3dXO5oQucrIyIjGjRtjZmYGwObNm/H19cXS0lLnOjWXlhJCn6QQFSKbTExM6N+/P71798bDw0N7XArRFzM1NaVp06Z069aNJk2aaFccECI3xMbGEhsbS1pams5xLy8vvWfp0qXLK10nu2mJd4V0zQuRTQcPHmTJkiVUqlSJ0qVL07FjR9q0aaN2LIN248YNChYsqHYM8ZY7efIknTt35sKFCzzf5qLWkmpSYAqhS5ohhMim6tWrs2jRImJiYujZsyerV6+mSJEipKWlsWvXLh49eqR2RIOTUYQuX76crVu3ao8PGzaMfPnyUaNGDa5fv65WPPGW6Nq1KyVLliQkJISrV68SGRmpvV29elXteEIIpGteiFxx8eJFlixZwsqVK3nw4AHvv/8+mzZtUjuWwSlVqhTz58/H19eXw4cP4+fnx8yZM9myZQsmJiYyTk5ki7W1NadPn5axx0IYMGkRFSIXlCpVimnTpnHjxg1++eUXteMYrOjoaG2REBQURKtWrfjss8+YOnUqBw4cUDmdeNM1aNCAsLAwtWMIIV5CWkSFEKopWLAgv//+O97e3nh7ezNo0CA6duxIREQE5cuXJz4+Xu2I4g129+5dOnfuTNWqVSlXrhx58uTROd+sWTOVkgkhMshkJSGEat5//326d++Ot7c3ly5dokmTJgDabRmFyI7Dhw9z6NAhtm/fnumcWpOVhBC6pGteCKGaefPm4ePjw507d1i/fj358+cH0mc7t23bVuV04k3Xr18/OnToQExMDGlpaTo3KUKFMAzSNS+EEOKtZG1tTWhoKCVKlFA7ihDiBaRrXgihmv3797/0fJ06dfSURLyNWrZsyd69e6UQFcKASSEqhFBNvXr1Mh3TaDTa/5fuU5EdJUuWZOTIkRw8eBBPT89Mk5X69++vUjIhRAbpmhdCqObhw4c691NSUjh9+jRjxoxh8uTJNGjQQKVk4m3g6ur6wnMajUYWtRfCAEghKoQwOMHBwQwaNIiTJ0+qHUW8oRRFISoqioIFC2JhYaF2HCHEC8iseSGEwSlUqBAXL15UO4Z4gymKgoeHBzdu3FA7ihDiJWSMqBBCNeHh4Tr3FUUhJiaGr7/+mgoVKqgTSrwVjIyM8PDw4N69e3h4eKgdRwjxAtI1L4RQjZGRERqNhuc/hqpXr87SpUt57733VEom3gabN29m2rRpzJ8/n3LlyqkdRwiRBSlEhRCquX79us59IyMjHBwcMDc3VymReJvY2dnx+PFjnj59iqmpaaaxovfv31cpmRAig3TNCyFUU7x4cbUjiLfYrFmz1I4ghPgX0iIqhFBVcHAw3333HRcuXACgTJkyDB06lNq1a6ucTAghRG6TWfNCCNX89NNP+Pn5kTdvXvr370///v2xsLCgQYMGrFq1Su144i0QERHB6NGjadu2LbGxsQBs376dc+fOqZxMCAHSIiqEUFHp0qX57LPPGDhwoM7xGTNmsGjRIm0rqRD/RXBwMI0bN6ZmzZrs37+fCxcu4Obmxtdff82JEydYt26d2hGFeOdJi6gQQjVXr17lo48+ynS8WbNmREZGqpBIvE1GjBjBpEmT2LVrF6amptrjvr6+HDlyRMVkQogMUogKIVTj5OTEnj17Mh3fvXs3Tk5OKiQSb5MzZ87QokWLTMcLFizI3bt3VUgkhHiezJoXQqhm8ODB9O/fn9DQUGrUqAHAoUOHCAwMZPbs2SqnE2+6fPnyERMTk2nP+dOnT1O0aFGVUgkhniWFqBBCNb1798bR0ZHp06ezdu1aIH3c6Jo1a2jevLnK6cSbrk2bNgwfPpxff/0VjUZDWloahw4dYsiQIXTq1EnteEIIZLKSEEKIt1RycjJ9+/YlMDCQp0+fYmJiQmpqKu3atSMwMBBjY2O1IwrxzpNCVAihqgcPHrBu3TquXr3KkCFDsLe359SpUxQqVEi6T8V/kpaWxrfffsumTZtITk7Gy8uLVq1aER8fj7e3t+w9L4QBka55IYRqwsPD8fPzw9bWlmvXrtG9e3fs7e3ZsGEDUVFRrFixQu2I4g00efJkxo8fj5+fHxYWFqxatQpFUVi6dKna0YQQz5FZ80II1QwaNIiAgAAuX76ss798kyZN2L9/v4rJxJtsxYoV/PDDD/z+++8EBQWxefNmfv75Z9LS0tSOJoR4jhSiQgjVHD9+nJ49e2Y6XrRoUW7duqVCIvE2iIqKokmTJtr7fn5+aDQabt68qWIqIURWpBAVQqjGzMyMuLi4TMcvXbqEg4ODConE2+Dp06c6LewAefLkISUlRaVEQogXkTGiQgjVNGvWjIkTJ2qXbtJoNERFRTF8+HBatWqlcjrxplIUhYCAAMzMzLTHEhMT6dWrF5aWltpjGzZsUCOeEOIZMmteCKGahw8f8vHHH3PixAkePXpEkSJFuHXrFj4+Pmzbtk2naBDiVXXp0uWVrlu2bFkuJxFC/BspRIUQqjt06BBhYWHEx8dTsWJF/Pz81I4khBBCD6QQFUIIIYQQqpDJSkII1fTv3585c+ZkOj537ly++OIL/QcSQgihV1KICiFUs379emrWrJnpeI0aNVi3bp0KiYQQQuiTFKJCCNXcu3cPW1vbTMdtbGy4e/euComEEELokxSiQgjVuLu7s2PHjkzHt2/fjpubmwqJhBBC6JOsIyqEUM2gQYPo27cvd+7cwdfXF4A9e/Ywffp0Zs2apW44IYQQuU5mzQshVDV//nwmT56s3X7RxcWF8ePH06lTJ5WTCSGEyG1SiAohDMKdO3ewsLDAyspK7ShCCCH0RApRIYQQQgihChkjKoRQ1bp161i7di1RUVEkJyfrnDt16pRKqYQQQuiDzJoXQqhmzpw5dOnShUKFCnH69GmqVq1K/vz5uXr1Ko0bN1Y7nhBCiFwmXfNCCNW89957jBs3jrZt22JtbU1YWBhubm6MHTuW+/fvM3fuXLUjCiGEyEXSIiqEUE1UVBQ1atQAwMLCgkePHgHQsWNHfvnlFzWjCSGE0AMpRIUQqnF0dOT+/fsAODs7c+TIEQAiIyORzhohhHj7SSEqhFCNr68vmzZtAqBLly4MHDiQ999/n08//ZQWLVqonE4IIURukzGiQgjVpKWlkZaWholJ+gIeq1evJiQkBA8PD3r27ImpqanKCYUQQuQmKUSFEEIIIYQqZB1RIYSq/v77b5YsWcKFCxcAKFOmDF26dMHe3l7lZEIIIXKbtIgKIVSzf/9+mjVrho2NDZUrVwbg5MmTPHjwgM2bN1OnTh2VEwohhMhNUogKIVTj6emJj48P8+fPx9jYGIDU1FQ+//xzQkJCOHPmjMoJhRBC5CYpRIUQqrGwsCA0NJRSpUrpHL948SIVKlTgyZMnKiUTQgihD7J8kxBCNRUrVtSODX3WhQsXKF++vAqJhBBC6JNMVhJC6FV4eLj2//v378+AAQO4cuUK1atXB+DIkSPMmzePr7/+Wq2IQggh9ES65oUQemVkZIRGo/nXnZM0Gg2pqal6SiWEEEIN0iIqhNCryMhItSMIIYQwENIiKoRQRUpKCj179mTMmDG4urqqHUcIIYQKZLKSEEIVefLkYf369WrHEEIIoSIpRIUQqvH39ycoKEjtGEIIIVQiY0SFEKrx8PBg4sSJHDp0iEqVKmFpaalzvn///iolE0IIoQ8yRlQIoZqXjQ3VaDRcvXpVj2mEEELomxSiQgghhBBCFTJGVAihuuTkZC5evMjTp0/VjiKEEEKPpBAVQqjm8ePHdOvWjbx581K2bFmioqIA6Nevn+ysJIQQ7wApRIUQqhk5ciRhYWHs27cPc3Nz7XE/Pz/WrFmjYjIhhBD6ILPmhRCqCQoKYs2aNVSvXh2NRqM9XrZsWSIiIlRMJoQQQh+kRVQIoZo7d+5QsGDBTMcTEhJ0ClMhhBBvJylEhRCqqVy5Mlu3btXezyg+Fy9ejI+Pj1qxhBBC6Il0zQshVDNlyhQaN27M+fPnefr0KbNnz+b8+fOEhIQQHBysdjwhhBC5TFpEhRCqqVWrFqGhoTx9+hRPT0927txJwYIFOXz4MJUqVVI7nhBCiFwmC9oLIfQuLi7ula6zsbHJ5SRCCCHUJIWoEELvjIyMXjoZSVEUNBoNqampekwlhBBC32SMqBBC7/bu3av9f0VRaNKkCYsXL6Zo0aIqphJCCKFv4lMwUgAAB9BJREFU0iIqhFCdtbU1YWFhuLm5qR1FCCGEHslkJSGEEEIIoQopRIUQQgghhCqkEBVCGATZSUkIId49MllJCKF3LVu21LmfmJhIr169sLS01Dm+YcMGfcYSQgihZ1KICiH0ztbWVud+hw4dVEoihBBCTTJrXgghhBBCqELGiAohhBBCCFVIISqEEEIIIVQhhagQQgghhFCFFKJCCCGEEEIVUogKIYQBCwgIwN/fX3u/Xr16fPHFF3rPsW/fPjQaDQ8ePMi153j+z/pf6COnECLnSCEqhBCvKSAgAI1Gg0ajwdTUFHd3dyZOnMjTp09z/bk3bNjAV1999UrX6rsoc3FxYdasWXp5LiHE20HWERVCiP+gUaNGLFu2jKSkJLZt20afPn3IkycPI0eOzHRtcnIypqamOfK89vb2OfI4QghhCKRFVAgh/gMzMzMcHR0pXrw4vXv3xs/Pj02bNgH/dDFPnjyZIkWKUKpUKQCio6P55JNPyJcvH/b29jRv3pxr165pHzM1NZVBgwaRL18+8ufPz7Bhw3h+qefnu+aTkpIYPnw4Tk5OmJmZ4e7uzpIlS7h27Rr169cHwM7ODo1GQ0BAAABpaWlMnToVV1dXLCwsKF++POvWrdN5nm3btlGyZEksLCyoX7++Ts7/IjU1lW7dummfs1SpUsyePTvLaydMmICDgwM2Njb06tWL5ORk7blXyS6EeHNIi6gQQuQACwsL7t27p72/Z88ebGxs2LVrFwApKSk0bNgQHx8fDhw4gImJCZMmTaJRo0aEh4djamrK9OnTCQwMZOnSpZQuXZrp06fz22+/4evr+8Ln7dSpE4cPH2bOnDmUL1+eyMhI7t69i5OTE+vXr6dVq1ZcvHgRGxsbLCwsAJg6dSo//fQTCxYswMPDg/3799OhQwccHByoW7cu0dHRtGzZkj59+vDZZ59x4sQJBg8enK3XJy0tjWLFivHrr7+SP39+QkJC+OyzzyhcuDCffPKJzutmbm7Ovn37uHbtGl26dCF//vxMnjz5lbILId4wihBCiNfSuXNnpXnz5oqiKEpaWpqya9cuxczMTBkyZIj2fKFChZSkpCTtz6xcuVIpVaqUkpaWpj2WlJSkWFhYKL///ruiKIpSuHBhZdq0adrzKSkpSrFixbTPpSiKUrduXWXAgAGKoijKxYsXFUDZtWtXljn37t2rAMrff/+tPZaYmKjkzZtXCQkJ0bm2W7duStu2bRVFUZSRI0cqZcqU0Tk/fPjwTI/1vOLFiyszZ8584fnn9enTR2nVqpX2fufOnRV7e3slISFBe2z+/PmKlZWVkpqa+krZs/ozCyEMl7SICiHEf7BlyxasrKxISUkhLS2Ndu3aMX78eO15T09PnXGhYWFhXLlyBWtra53HSUxMJCIigocPHxITE0O1atW050xMTKhcuXKm7vkMoaGhGBsbv1ZL4JUrV3j8+DHvv/++zvHk5GS8vb0BuHDhgk4OAB8fn1d+jheZN28eS5cuJSoqiidPnpCcnEyFChV0rilfvjx58+bVed74+Hiio6OJj4//1+xCiDeLFKJCCPEf1K9fn/nz52NqakqRIkUwMdH9OLW0tNS5Hx8fT6VKlfj5558zPZaDg8N/ypDR1f464uPjAdi6dStFixbVOWdmZvafcryK1atXM2TIEKZPn46Pjw/W1tZ8++23HD169JUfQ63sQojcI4WoEEL8B5aWlri7u7/y9RUrVmTNmjUULFgQGxubLK8pXLgwR48epU6dOgA8ffqUkydPUrFixSyv9/T0JC0tjeDgYPz8/DKdz2iRTU1N1R4rU6YMZmZmREVFvbAltXTp0tqJVxmOHDny73/Ilzh06BA1atTg888/1x6LiIjIdF1YWBhPnjzRFtlHjhzBysoKJycn7O3t/zW7EOLNIrPmhRBCD9q3b0+BAgVo3rw5Bw4cIDIykn379tG/f39u3LgBwIABA/j6668JCgrizz//5PPPP3/pGqAuLi507tyZrl27EhQUpH3MtWvXAlC8eHE0Gg1btmzhzp07xMfHY21tzZAhQxg4cCDLly8nIiKCU6dO8f3337N8+XIAevXqxeXLlxk6dCgXL15k1apVBAYGvtKf86+//iI0NFTn9vfff+Ph4cGJEyf4/fffuXTpEmPGjOH48eOZfj45OZlu3bpx/vx5tm3bxrhx4+jbty9GRkavlF0I8YZRe5CqEEK8aZ6drPQ652NiYpROnTopBQoUUMzMzBQ3NzelR48eysOHDxVFSZ+cNGDAAMXGxkbJly+fMmjQIKVTp04vnKykKIry5MkTZeDAgUrhwoUVU1NTxd3dXVm6dKn2/MSJExVHR0dFo9EonTt3VhQlfYLVrFmzlFKlSil58uRRHBwclIYNGyrBwcHan9u8ebPi7u6umJmZKbVr11aWLl36SpOVgEy3lStXKomJiUpAQIBia2ur5MuXT+ndu7cyYsQIpXz58plet7Fjxyr58+dXrKyslB49eiiJiYnaa/4tu0xWEuLNolGUF4yCF0IIIYQQIhdJ17wQQgghhFCFFKJCCCGEEEIVUogKIYQQQghVSCEqhBBCCCFUIYWoEEIIIYRQhRSiQgghhBBCFVKICiGEEEIIVUghKoQQQgghVCGFqBBCCCGEUIUUokIIIYQQQhVSiAohhBBCCFX8D6fQF/Of+5iJAAAAAElFTkSuQmCC\n"
},
"metadata": {}
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"image/png": "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\n"
},
"metadata": {}
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"import numpy as np\n",
"from sklearn.metrics import confusion_matrix, roc_curve, auc\n",
"from sklearn.preprocessing import label_binarize\n",
"from itertools import cycle\n",
"import pickle\n",
"\n",
"def evaluate_model(model, X_test, y_test_one_hot, label_map, model_name):\n",
" \"\"\"Evaluates the model using a confusion matrix and ROC curve.\"\"\"\n",
"\n",
" # Predict probabilities for each class\n",
" y_pred_probs = model.predict(X_test)\n",
"\n",
" # Convert probabilities to class predictions\n",
" y_pred_classes = np.argmax(y_pred_probs, axis=1)\n",
" y_true_classes = np.argmax(y_test_one_hot, axis=1)\n",
"\n",
"\n",
" # Confusion Matrix\n",
" cm = confusion_matrix(y_true_classes, y_pred_classes)\n",
" plt.figure(figsize=(8, 6))\n",
" plt.imshow(cm, interpolation='nearest', cmap=plt.cm.Blues)\n",
" plt.title(f'{model_name} - Confusion Matrix')\n",
" plt.colorbar()\n",
" tick_marks = np.arange(len(label_map))\n",
" plt.xticks(tick_marks, label_map.keys(), rotation=90)\n",
" plt.yticks(tick_marks, label_map.keys())\n",
"\n",
" thresh = cm.max() / 2.\n",
" for i, j in np.ndindex(cm.shape):\n",
" plt.text(j, i, cm[i, j],\n",
" horizontalalignment=\"center\",\n",
" color=\"white\" if cm[i, j] > thresh else \"black\")\n",
"\n",
" plt.tight_layout()\n",
" plt.ylabel('True Label')\n",
" plt.xlabel('Predicted Label')\n",
" plt.show()\n",
"\n",
" # ROC Curve (Binary Classification)\n",
" # Binarize the output\n",
" y_test_bin = label_binarize(y_true_classes, classes=list(range(len(label_map))))\n",
" n_classes = y_test_bin.shape[1]\n",
"\n",
" # Compute ROC curve and ROC area for each class\n",
" fpr = dict()\n",
" tpr = dict()\n",
" roc_auc = dict()\n",
" for i in range(n_classes):\n",
" fpr[i], tpr[i], _ = roc_curve(y_test_bin[:, i], y_pred_probs[:, i])\n",
" roc_auc[i] = auc(fpr[i], tpr[i])\n",
"\n",
" # Compute micro-average ROC curve and ROC area\n",
" fpr[\"micro\"], tpr[\"micro\"], _ = roc_curve(y_test_bin.ravel(), y_pred_probs.ravel())\n",
" roc_auc[\"micro\"] = auc(fpr[\"micro\"], tpr[\"micro\"])\n",
"\n",
" # Plot ROC curve for each class\n",
" plt.figure(figsize=(8, 6))\n",
" lw = 2\n",
" colors = cycle(['aqua', 'darkorange', 'cornflowerblue', 'red', 'green', 'yellow', 'blue', 'purple', 'pink', 'lime']) # Add more colors as needed\n",
"\n",
" for i, color in zip(range(n_classes), colors):\n",
" plt.plot(fpr[i], tpr[i], color=color, lw=lw,\n",
" label='ROC curve of class {0} (area = {1:0.2f})'\n",
" ''.format(list(label_map.keys())[i], roc_auc[i]))\n",
"\n",
" plt.plot([0, 1], [0, 1], 'k--', lw=lw)\n",
" plt.xlim([0.0, 1.0])\n",
" plt.ylim([0.0, 1.05])\n",
" plt.xlabel('False Positive Rate')\n",
" plt.ylabel('True Positive Rate')\n",
" plt.title(f'{model_name} - ROC Curve')\n",
" plt.legend(loc=\"lower right\")\n",
" plt.show()\n",
"\n",
"# Load the saved models and history if needed\n",
"from tensorflow.keras.models import load_model\n",
"cnn_model = load_model('/content/cnn_image_classifier.h5')\n",
"cnn_resnet_model = load_model('/content/resnet_image_classifier.h5')\n",
"\n",
"# Load existing history.pkl file\n",
"with open('history.pkl', 'rb') as f:\n",
" history_data = pickle.load(f)\n",
"\n",
"# Load existing history.pkl file\n",
"with open('history_resnet.pkl', 'rb') as f_resnet:\n",
" history_resnet_data = pickle.load(f_resnet)\n",
"\n",
"# Evaluate CNN model\n",
"evaluate_model(cnn_model, history_data['X_test'], history_data['y_test_one_hot'], history_data['label_map'], \"CNN (3Layer)\")\n",
"\n",
"# Evaluate LSTM model\n",
"evaluate_model(cnn_resnet_model, history_resnet_data['X_test'], history_resnet_data['y_test_one_hot'], history_resnet_data['label_map'], \"CNN (ResNet)\")"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "u1crAuKtXKfE"
},
"source": [
"**User Interface using Gradio**"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 750
},
"id": "NMh1sY1WWk2T",
"outputId": "82b5672e-53f2-4c38-c97e-ceeafd9bbe1b"
},
"outputs": [
{
"output_type": "stream",
"name": "stderr",
"text": [
"WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
"WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n"
]
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Running Gradio in a Colab notebook requires sharing enabled. Automatically setting `share=True` (you can turn this off by setting `share=False` in `launch()` explicitly).\n",
"\n",
"Colab notebook detected. This cell will run indefinitely so that you can see errors and logs. To turn off, set debug=False in launch().\n",
"* Running on public URL: https://56a8d1f40a4ee43129.gradio.live\n",
"\n",
"This share link expires in 72 hours. For free permanent hosting and GPU upgrades, run `gradio deploy` from the terminal in the working directory to deploy to Hugging Face Spaces (https://huggingface.co/spaces)\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
""
],
"text/html": [
""
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 79ms/step\n",
"\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 353ms/step\n",
"Keyboard interruption in main thread... closing server.\n",
"Killing tunnel 127.0.0.1:7860 <> https://56a8d1f40a4ee43129.gradio.live\n"
]
},
{
"output_type": "execute_result",
"data": {
"text/plain": []
},
"metadata": {},
"execution_count": 13
}
],
"source": [
"import cv2\n",
"import gradio as gr\n",
"import numpy as np\n",
"from tensorflow.keras.models import load_model\n",
"import json\n",
"\n",
"# Load the saved models\n",
"cnn_model = load_model('/content/cnn_image_classifier.h5')\n",
"resnet_model = load_model('/content/resnet_image_classifier.h5')\n",
"\n",
"# Load label map (assuming you have it defined or loaded elsewhere)\n",
"# Replace with your actual loading method\n",
"with open('/content/EuroSAT_dataset/EuroSAT/label_map.json', 'r') as f:\n",
" label_map = json.load(f)\n",
"label_map_inv = {v: k for k, v in label_map.items()}\n",
"\n",
"\n",
"def predict_image(image):\n",
" # Preprocess the image (resize, normalize, etc.)\n",
" image = cv2.resize(image, (64, 64))\n",
" image = image / 255.0\n",
" image = np.expand_dims(image, axis=0)\n",
"\n",
" # Make predictions with both models\n",
" cnn_pred = cnn_model.predict(image)[0]\n",
" resnet_pred = resnet_model.predict(image)[0]\n",
"\n",
" # Get top 5 predictions for CNN\n",
" cnn_top5_indices = np.argsort(cnn_pred)[::-1][:5]\n",
" cnn_top5 = {\n",
" label_map_inv[idx]: float(cnn_pred[idx]) for idx in cnn_top5_indices\n",
" }\n",
"\n",
" # Get top 5 predictions for ResNet\n",
" resnet_top5_indices = np.argsort(resnet_pred)[::-1][:5]\n",
" resnet_top5 = {\n",
" label_map_inv[idx]: float(resnet_pred[idx]) for idx in resnet_top5_indices\n",
" }\n",
"\n",
" # Final predictions\n",
" cnn_final_prediction = label_map_inv[np.argmax(cnn_pred)]\n",
" resnet_final_prediction = label_map_inv[np.argmax(resnet_pred)]\n",
"\n",
" return cnn_top5, cnn_final_prediction, resnet_top5, resnet_final_prediction\n",
"\n",
"\n",
"iface = gr.Interface(\n",
" fn=predict_image,\n",
" inputs=gr.Image(type=\"numpy\"),\n",
" outputs=[\n",
" gr.Label(num_top_classes=5, label=\"CNN Top 5 Predictions\"),\n",
" gr.Textbox(label=\"CNN Final Prediction\"),\n",
" gr.Label(num_top_classes=5, label=\"ResNet Top 5 Predictions\"),\n",
" gr.Textbox(label=\"ResNet Final Prediction\"),\n",
" ],\n",
" title=\"Image Classification with CNN and ResNet\",\n",
" description=\"Upload an image to classify using two different models.\",\n",
")\n",
"\n",
"iface.launch(debug=True)\n"
]
}
],
"metadata": {
"colab": {
"provenance": []
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} | |