{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 41,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: matplotlib in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (3.9.2)\n",
      "Requirement already satisfied: tensorflow in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (2.16.1)\n",
      "Collecting gradio\n",
      "  Downloading gradio-5.9.1-py3-none-any.whl.metadata (16 kB)\n",
      "Requirement already satisfied: contourpy>=1.0.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (1.3.0)\n",
      "Requirement already satisfied: cycler>=0.10 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (0.12.1)\n",
      "Requirement already satisfied: fonttools>=4.22.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (4.54.1)\n",
      "Requirement already satisfied: kiwisolver>=1.3.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (1.4.7)\n",
      "Requirement already satisfied: numpy>=1.23 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (1.26.4)\n",
      "Requirement already satisfied: packaging>=20.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (24.1)\n",
      "Requirement already satisfied: pillow>=8 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (11.0.0)\n",
      "Requirement already satisfied: pyparsing>=2.3.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (3.2.0)\n",
      "Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from matplotlib) (2.9.0.post0)\n",
      "Requirement already satisfied: tensorflow-intel==2.16.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow) (2.16.1)\n",
      "Requirement already satisfied: absl-py>=1.0.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.1.0)\n",
      "Requirement already satisfied: astunparse>=1.6.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.6.3)\n",
      "Requirement already satisfied: flatbuffers>=23.5.26 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (24.3.25)\n",
      "Requirement already satisfied: gast!=0.5.0,!=0.5.1,!=0.5.2,>=0.2.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.6.0)\n",
      "Requirement already satisfied: google-pasta>=0.1.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.2.0)\n",
      "Requirement already satisfied: h5py>=3.10.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.12.1)\n",
      "Requirement already satisfied: libclang>=13.0.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (18.1.1)\n",
      "Requirement already satisfied: ml-dtypes~=0.3.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.3.2)\n",
      "Requirement already satisfied: opt-einsum>=2.3.2 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.4.0)\n",
      "Requirement already satisfied: protobuf!=4.21.0,!=4.21.1,!=4.21.2,!=4.21.3,!=4.21.4,!=4.21.5,<5.0.0dev,>=3.20.3 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (4.25.5)\n",
      "Requirement already satisfied: requests<3,>=2.21.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.32.3)\n",
      "Requirement already satisfied: setuptools in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (75.1.0)\n",
      "Requirement already satisfied: six>=1.12.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.16.0)\n",
      "Requirement already satisfied: termcolor>=1.1.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.5.0)\n",
      "Requirement already satisfied: typing-extensions>=3.6.6 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (4.12.2)\n",
      "Requirement already satisfied: wrapt>=1.11.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.16.0)\n",
      "Requirement already satisfied: grpcio<2.0,>=1.24.3 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (1.67.0)\n",
      "Requirement already satisfied: tensorboard<2.17,>=2.16 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (2.16.2)\n",
      "Requirement already satisfied: keras>=3.0.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (3.6.0)\n",
      "Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorflow-intel==2.16.1->tensorflow) (0.31.0)\n",
      "Collecting aiofiles<24.0,>=22.0 (from gradio)\n",
      "  Downloading aiofiles-23.2.1-py3-none-any.whl.metadata (9.7 kB)\n",
      "Requirement already satisfied: anyio<5.0,>=3.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from gradio) (4.6.2.post1)\n",
      "Collecting fastapi<1.0,>=0.115.2 (from gradio)\n",
      "  Downloading fastapi-0.115.6-py3-none-any.whl.metadata (27 kB)\n",
      "Collecting ffmpy (from gradio)\n",
      "  Downloading ffmpy-0.5.0-py3-none-any.whl.metadata (3.0 kB)\n",
      "Collecting gradio-client==1.5.2 (from gradio)\n",
      "  Downloading gradio_client-1.5.2-py3-none-any.whl.metadata (7.1 kB)\n",
      "Requirement already satisfied: httpx>=0.24.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from gradio) (0.27.2)\n",
      "Collecting huggingface-hub>=0.25.1 (from gradio)\n",
      "  Downloading huggingface_hub-0.27.0-py3-none-any.whl.metadata (13 kB)\n",
      "Requirement already satisfied: jinja2<4.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from gradio) (3.1.4)\n",
      "Collecting markupsafe~=2.0 (from gradio)\n",
      "  Downloading MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl.metadata (3.1 kB)\n",
      "Collecting orjson~=3.0 (from gradio)\n",
      "  Downloading orjson-3.10.13-cp310-cp310-win_amd64.whl.metadata (42 kB)\n",
      "Requirement already satisfied: pandas<3.0,>=1.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from gradio) (2.2.3)\n",
      "Collecting pydantic>=2.0 (from gradio)\n",
      "  Downloading pydantic-2.10.4-py3-none-any.whl.metadata (29 kB)\n",
      "Collecting pydub (from gradio)\n",
      "  Downloading pydub-0.25.1-py2.py3-none-any.whl.metadata (1.4 kB)\n",
      "Collecting python-multipart>=0.0.18 (from gradio)\n",
      "  Downloading python_multipart-0.0.20-py3-none-any.whl.metadata (1.8 kB)\n",
      "Requirement already satisfied: pyyaml<7.0,>=5.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from gradio) (6.0.2)\n",
      "Collecting ruff>=0.2.2 (from gradio)\n",
      "  Downloading ruff-0.8.5-py3-none-win_amd64.whl.metadata (25 kB)\n",
      "Collecting safehttpx<0.2.0,>=0.1.6 (from gradio)\n",
      "  Downloading safehttpx-0.1.6-py3-none-any.whl.metadata (4.2 kB)\n",
      "Collecting semantic-version~=2.0 (from gradio)\n",
      "  Downloading semantic_version-2.10.0-py2.py3-none-any.whl.metadata (9.7 kB)\n",
      "Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
      "  Downloading starlette-0.45.1-py3-none-any.whl.metadata (6.3 kB)\n",
      "Collecting tomlkit<0.14.0,>=0.12.0 (from gradio)\n",
      "  Downloading tomlkit-0.13.2-py3-none-any.whl.metadata (2.7 kB)\n",
      "Collecting typer<1.0,>=0.12 (from gradio)\n",
      "  Downloading typer-0.15.1-py3-none-any.whl.metadata (15 kB)\n",
      "Collecting uvicorn>=0.14.0 (from gradio)\n",
      "  Downloading uvicorn-0.34.0-py3-none-any.whl.metadata (6.5 kB)\n",
      "Collecting fsspec (from gradio-client==1.5.2->gradio)\n",
      "  Downloading fsspec-2024.12.0-py3-none-any.whl.metadata (11 kB)\n",
      "Collecting websockets<15.0,>=10.0 (from gradio-client==1.5.2->gradio)\n",
      "  Downloading websockets-14.1-cp310-cp310-win_amd64.whl.metadata (6.9 kB)\n",
      "Requirement already satisfied: idna>=2.8 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from anyio<5.0,>=3.0->gradio) (3.10)\n",
      "Requirement already satisfied: sniffio>=1.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from anyio<5.0,>=3.0->gradio) (1.3.1)\n",
      "Requirement already satisfied: exceptiongroup>=1.0.2 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from anyio<5.0,>=3.0->gradio) (1.2.2)\n",
      "Collecting starlette<1.0,>=0.40.0 (from gradio)\n",
      "  Downloading starlette-0.41.3-py3-none-any.whl.metadata (6.0 kB)\n",
      "Requirement already satisfied: certifi in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from httpx>=0.24.1->gradio) (2024.8.30)\n",
      "Requirement already satisfied: httpcore==1.* in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from httpx>=0.24.1->gradio) (1.0.6)\n",
      "Requirement already satisfied: h11<0.15,>=0.13 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from httpcore==1.*->httpx>=0.24.1->gradio) (0.14.0)\n",
      "Collecting filelock (from huggingface-hub>=0.25.1->gradio)\n",
      "  Downloading filelock-3.16.1-py3-none-any.whl.metadata (2.9 kB)\n",
      "Collecting tqdm>=4.42.1 (from huggingface-hub>=0.25.1->gradio)\n",
      "  Downloading tqdm-4.67.1-py3-none-any.whl.metadata (57 kB)\n",
      "Requirement already satisfied: pytz>=2020.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
      "Requirement already satisfied: tzdata>=2022.7 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from pandas<3.0,>=1.0->gradio) (2024.2)\n",
      "Collecting annotated-types>=0.6.0 (from pydantic>=2.0->gradio)\n",
      "  Downloading annotated_types-0.7.0-py3-none-any.whl.metadata (15 kB)\n",
      "Collecting pydantic-core==2.27.2 (from pydantic>=2.0->gradio)\n",
      "  Downloading pydantic_core-2.27.2-cp310-cp310-win_amd64.whl.metadata (6.7 kB)\n",
      "Collecting click>=8.0.0 (from typer<1.0,>=0.12->gradio)\n",
      "  Downloading click-8.1.8-py3-none-any.whl.metadata (2.3 kB)\n",
      "Collecting shellingham>=1.3.0 (from typer<1.0,>=0.12->gradio)\n",
      "  Downloading shellingham-1.5.4-py2.py3-none-any.whl.metadata (3.5 kB)\n",
      "Requirement already satisfied: rich>=10.11.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from typer<1.0,>=0.12->gradio) (13.9.3)\n",
      "Requirement already satisfied: wheel<1.0,>=0.23.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from astunparse>=1.6.0->tensorflow-intel==2.16.1->tensorflow) (0.44.0)\n",
      "Requirement already satisfied: colorama in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from click>=8.0.0->typer<1.0,>=0.12->gradio) (0.4.6)\n",
      "Requirement already satisfied: namex in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (0.0.8)\n",
      "Requirement already satisfied: optree in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from keras>=3.0.0->tensorflow-intel==2.16.1->tensorflow) (0.13.0)\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (3.4.0)\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from requests<3,>=2.21.0->tensorflow-intel==2.16.1->tensorflow) (2.2.3)\n",
      "Requirement already satisfied: markdown-it-py>=2.2.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-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 c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from rich>=10.11.0->typer<1.0,>=0.12->gradio) (2.18.0)\n",
      "Requirement already satisfied: markdown>=2.6.8 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (3.7)\n",
      "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (0.7.2)\n",
      "Requirement already satisfied: werkzeug>=1.0.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from tensorboard<2.17,>=2.16->tensorflow-intel==2.16.1->tensorflow) (3.0.4)\n",
      "Requirement already satisfied: mdurl~=0.1 in c:\\users\\anway\\anaconda3\\envs\\anway\\lib\\site-packages (from markdown-it-py>=2.2.0->rich>=10.11.0->typer<1.0,>=0.12->gradio) (0.1.2)\n",
      "Downloading gradio-5.9.1-py3-none-any.whl (57.2 MB)\n",
      "   ---------------------------------------- 0.0/57.2 MB ? eta -:--:--\n",
      "    --------------------------------------- 1.0/57.2 MB 5.6 MB/s eta 0:00:10\n",
      "   - -------------------------------------- 1.6/57.2 MB 3.5 MB/s eta 0:00:16\n",
      "   - -------------------------------------- 2.4/57.2 MB 3.7 MB/s eta 0:00:15\n",
      "   - -------------------------------------- 2.6/57.2 MB 3.8 MB/s eta 0:00:15\n",
      "   -- ------------------------------------- 3.7/57.2 MB 3.4 MB/s eta 0:00:16\n",
      "   -- ------------------------------------- 3.9/57.2 MB 3.5 MB/s eta 0:00:16\n",
      "   --- ------------------------------------ 5.2/57.2 MB 3.5 MB/s eta 0:00:15\n",
      "   ---- ----------------------------------- 6.0/57.2 MB 3.5 MB/s eta 0:00:15\n",
      "   ---- ----------------------------------- 6.6/57.2 MB 3.6 MB/s eta 0:00:15\n",
      "   ----- ---------------------------------- 7.3/57.2 MB 3.6 MB/s eta 0:00:14\n",
      "   ----- ---------------------------------- 8.1/57.2 MB 3.6 MB/s eta 0:00:14\n",
      "   ------ --------------------------------- 8.9/57.2 MB 3.6 MB/s eta 0:00:14\n",
      "   ------ --------------------------------- 9.7/57.2 MB 3.6 MB/s eta 0:00:14\n",
      "   ------- -------------------------------- 10.5/57.2 MB 3.6 MB/s eta 0:00:13\n",
      "   ------- -------------------------------- 11.3/57.2 MB 3.6 MB/s eta 0:00:13\n",
      "   -------- ------------------------------- 12.1/57.2 MB 3.6 MB/s eta 0:00:13\n",
      "   -------- ------------------------------- 12.8/57.2 MB 3.6 MB/s eta 0:00:13\n",
      "   --------- ------------------------------ 13.6/57.2 MB 3.7 MB/s eta 0:00:12\n",
      "   ---------- ----------------------------- 14.4/57.2 MB 3.7 MB/s eta 0:00:12\n",
      "   ---------- ----------------------------- 15.2/57.2 MB 3.7 MB/s eta 0:00:12\n",
      "   ----------- ---------------------------- 16.0/57.2 MB 3.7 MB/s eta 0:00:12\n",
      "   ----------- ---------------------------- 16.8/57.2 MB 3.7 MB/s eta 0:00:11\n",
      "   ------------ --------------------------- 17.6/57.2 MB 3.7 MB/s eta 0:00:11\n",
      "   ------------ --------------------------- 18.4/57.2 MB 3.7 MB/s eta 0:00:11\n",
      "   ------------- -------------------------- 19.1/57.2 MB 3.7 MB/s eta 0:00:11\n",
      "   ------------- -------------------------- 19.9/57.2 MB 3.7 MB/s eta 0:00:11\n",
      "   -------------- ------------------------- 20.7/57.2 MB 3.7 MB/s eta 0:00:10\n",
      "   --------------- ------------------------ 21.5/57.2 MB 3.7 MB/s eta 0:00:10\n",
      "   --------------- ------------------------ 22.3/57.2 MB 3.7 MB/s eta 0:00:10\n",
      "   ---------------- ----------------------- 23.1/57.2 MB 3.7 MB/s eta 0:00:10\n",
      "   ---------------- ----------------------- 23.9/57.2 MB 3.7 MB/s eta 0:00:10\n",
      "   ----------------- ---------------------- 24.6/57.2 MB 3.7 MB/s eta 0:00:09\n",
      "   ----------------- ---------------------- 25.4/57.2 MB 3.7 MB/s eta 0:00:09\n",
      "   ------------------ --------------------- 26.2/57.2 MB 3.7 MB/s eta 0:00:09\n",
      "   ------------------ --------------------- 27.0/57.2 MB 3.7 MB/s eta 0:00:09\n",
      "   ------------------- -------------------- 27.8/57.2 MB 3.7 MB/s eta 0:00:08\n",
      "   ------------------- -------------------- 28.6/57.2 MB 3.7 MB/s eta 0:00:08\n",
      "   -------------------- ------------------- 29.4/57.2 MB 3.7 MB/s eta 0:00:08\n",
      "   --------------------- ------------------ 30.1/57.2 MB 3.7 MB/s eta 0:00:08\n",
      "   --------------------- ------------------ 30.9/57.2 MB 3.7 MB/s eta 0:00:08\n",
      "   --------------------- ------------------ 31.5/57.2 MB 3.7 MB/s eta 0:00:07\n",
      "   ---------------------- ----------------- 32.5/57.2 MB 3.7 MB/s eta 0:00:07\n",
      "   ----------------------- ---------------- 33.3/57.2 MB 3.7 MB/s eta 0:00:07\n",
      "   ----------------------- ---------------- 34.1/57.2 MB 3.7 MB/s eta 0:00:07\n",
      "   ------------------------ --------------- 34.6/57.2 MB 3.7 MB/s eta 0:00:07\n",
      "   ------------------------ --------------- 35.4/57.2 MB 3.7 MB/s eta 0:00:06\n",
      "   ------------------------- -------------- 36.4/57.2 MB 3.7 MB/s eta 0:00:06\n",
      "   -------------------------- ------------- 37.2/57.2 MB 3.7 MB/s eta 0:00:06\n",
      "   -------------------------- ------------- 37.7/57.2 MB 3.7 MB/s eta 0:00:06\n",
      "   -------------------------- ------------- 38.5/57.2 MB 3.7 MB/s eta 0:00:06\n",
      "   --------------------------- ------------ 39.6/57.2 MB 3.7 MB/s eta 0:00:05\n",
      "   ---------------------------- ----------- 40.4/57.2 MB 3.7 MB/s eta 0:00:05\n",
      "   ---------------------------- ----------- 41.2/57.2 MB 3.7 MB/s eta 0:00:05\n",
      "   ----------------------------- ---------- 41.9/57.2 MB 3.7 MB/s eta 0:00:05\n",
      "   ----------------------------- ---------- 42.7/57.2 MB 3.7 MB/s eta 0:00:04\n",
      "   ------------------------------ --------- 43.5/57.2 MB 3.7 MB/s eta 0:00:04\n",
      "   ------------------------------ --------- 44.3/57.2 MB 3.7 MB/s eta 0:00:04\n",
      "   ------------------------------- -------- 45.1/57.2 MB 3.7 MB/s eta 0:00:04\n",
      "   -------------------------------- ------- 45.9/57.2 MB 3.7 MB/s eta 0:00:04\n",
      "   -------------------------------- ------- 46.7/57.2 MB 3.7 MB/s eta 0:00:03\n",
      "   --------------------------------- ------ 47.4/57.2 MB 3.7 MB/s eta 0:00:03\n",
      "   --------------------------------- ------ 48.5/57.2 MB 3.7 MB/s eta 0:00:03\n",
      "   ---------------------------------- ----- 49.0/57.2 MB 3.7 MB/s eta 0:00:03\n",
      "   ---------------------------------- ----- 49.8/57.2 MB 3.7 MB/s eta 0:00:02\n",
      "   ----------------------------------- ---- 50.6/57.2 MB 3.7 MB/s eta 0:00:02\n",
      "   ----------------------------------- ---- 51.4/57.2 MB 3.7 MB/s eta 0:00:02\n",
      "   ------------------------------------ --- 52.2/57.2 MB 3.7 MB/s eta 0:00:02\n",
      "   ------------------------------------- -- 53.0/57.2 MB 3.7 MB/s eta 0:00:02\n",
      "   ------------------------------------- -- 53.7/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   -------------------------------------- - 54.5/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   -------------------------------------- - 55.3/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------  56.1/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------  56.9/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------  57.1/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------  57.1/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------  57.1/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------  57.1/57.2 MB 3.7 MB/s eta 0:00:01\n",
      "   ---------------------------------------- 57.2/57.2 MB 3.5 MB/s eta 0:00:00\n",
      "Downloading gradio_client-1.5.2-py3-none-any.whl (320 kB)\n",
      "Downloading aiofiles-23.2.1-py3-none-any.whl (15 kB)\n",
      "Downloading fastapi-0.115.6-py3-none-any.whl (94 kB)\n",
      "Downloading huggingface_hub-0.27.0-py3-none-any.whl (450 kB)\n",
      "Downloading MarkupSafe-2.1.5-cp310-cp310-win_amd64.whl (17 kB)\n",
      "Downloading orjson-3.10.13-cp310-cp310-win_amd64.whl (135 kB)\n",
      "Downloading pydantic-2.10.4-py3-none-any.whl (431 kB)\n",
      "Downloading pydantic_core-2.27.2-cp310-cp310-win_amd64.whl (2.0 MB)\n",
      "   ---------------------------------------- 0.0/2.0 MB ? eta -:--:--\n",
      "   --------------- ------------------------ 0.8/2.0 MB 4.2 MB/s eta 0:00:01\n",
      "   ------------------------------- -------- 1.6/2.0 MB 3.8 MB/s eta 0:00:01\n",
      "   ---------------------------------------- 2.0/2.0 MB 3.3 MB/s eta 0:00:00\n",
      "Downloading python_multipart-0.0.20-py3-none-any.whl (24 kB)\n",
      "Downloading ruff-0.8.5-py3-none-win_amd64.whl (9.7 MB)\n",
      "   ---------------------------------------- 0.0/9.7 MB ? eta -:--:--\n",
      "   ---- ----------------------------------- 1.0/9.7 MB 5.6 MB/s eta 0:00:02\n",
      "   ------- -------------------------------- 1.8/9.7 MB 4.6 MB/s eta 0:00:02\n",
      "   ---------- ----------------------------- 2.6/9.7 MB 4.3 MB/s eta 0:00:02\n",
      "   -------------- ------------------------- 3.4/9.7 MB 4.1 MB/s eta 0:00:02\n",
      "   ----------------- ---------------------- 4.2/9.7 MB 4.1 MB/s eta 0:00:02\n",
      "   -------------------- ------------------- 5.0/9.7 MB 4.0 MB/s eta 0:00:02\n",
      "   ---------------------- ----------------- 5.5/9.7 MB 4.0 MB/s eta 0:00:02\n",
      "   --------------------------- ------------ 6.6/9.7 MB 3.9 MB/s eta 0:00:01\n",
      "   ------------------------------ --------- 7.3/9.7 MB 3.9 MB/s eta 0:00:01\n",
      "   --------------------------------- ------ 8.1/9.7 MB 3.8 MB/s eta 0:00:01\n",
      "   ------------------------------------ --- 8.9/9.7 MB 3.8 MB/s eta 0:00:01\n",
      "   -------------------------------------- - 9.4/9.7 MB 3.8 MB/s eta 0:00:01\n",
      "   ---------------------------------------- 9.7/9.7 MB 3.6 MB/s eta 0:00:00\n",
      "Downloading safehttpx-0.1.6-py3-none-any.whl (8.7 kB)\n",
      "Downloading semantic_version-2.10.0-py2.py3-none-any.whl (15 kB)\n",
      "Downloading starlette-0.41.3-py3-none-any.whl (73 kB)\n",
      "Downloading tomlkit-0.13.2-py3-none-any.whl (37 kB)\n",
      "Downloading typer-0.15.1-py3-none-any.whl (44 kB)\n",
      "Downloading uvicorn-0.34.0-py3-none-any.whl (62 kB)\n",
      "Downloading ffmpy-0.5.0-py3-none-any.whl (6.0 kB)\n",
      "Downloading pydub-0.25.1-py2.py3-none-any.whl (32 kB)\n",
      "Downloading annotated_types-0.7.0-py3-none-any.whl (13 kB)\n",
      "Downloading click-8.1.8-py3-none-any.whl (98 kB)\n",
      "Downloading fsspec-2024.12.0-py3-none-any.whl (183 kB)\n",
      "Downloading shellingham-1.5.4-py2.py3-none-any.whl (9.8 kB)\n",
      "Downloading tqdm-4.67.1-py3-none-any.whl (78 kB)\n",
      "Downloading websockets-14.1-cp310-cp310-win_amd64.whl (163 kB)\n",
      "Downloading filelock-3.16.1-py3-none-any.whl (16 kB)\n",
      "Installing collected packages: pydub, websockets, tqdm, tomlkit, shellingham, semantic-version, ruff, python-multipart, pydantic-core, orjson, markupsafe, fsspec, filelock, ffmpy, click, annotated-types, aiofiles, uvicorn, starlette, pydantic, huggingface-hub, typer, safehttpx, gradio-client, fastapi, gradio\n",
      "  Attempting uninstall: markupsafe\n",
      "    Found existing installation: MarkupSafe 3.0.2\n",
      "    Uninstalling MarkupSafe-3.0.2:\n",
      "      Successfully uninstalled MarkupSafe-3.0.2\n",
      "Successfully installed aiofiles-23.2.1 annotated-types-0.7.0 click-8.1.8 fastapi-0.115.6 ffmpy-0.5.0 filelock-3.16.1 fsspec-2024.12.0 gradio-5.9.1 gradio-client-1.5.2 huggingface-hub-0.27.0 markupsafe-2.1.5 orjson-3.10.13 pydantic-2.10.4 pydantic-core-2.27.2 pydub-0.25.1 python-multipart-0.0.20 ruff-0.8.5 safehttpx-0.1.6 semantic-version-2.10.0 shellingham-1.5.4 starlette-0.41.3 tomlkit-0.13.2 tqdm-4.67.1 typer-0.15.1 uvicorn-0.34.0 websockets-14.1\n",
      "Note: you may need to restart the kernel to use updated packages.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "  WARNING: The script tqdm.exe is installed in 'c:\\Users\\anway\\anaconda3\\envs\\anway\\Scripts' which is not on PATH.\n",
      "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\n",
      "  WARNING: The script uvicorn.exe is installed in 'c:\\Users\\anway\\anaconda3\\envs\\anway\\Scripts' which is not on PATH.\n",
      "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\n",
      "  WARNING: The script huggingface-cli.exe is installed in 'c:\\Users\\anway\\anaconda3\\envs\\anway\\Scripts' which is not on PATH.\n",
      "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\n",
      "  WARNING: The script typer.exe is installed in 'c:\\Users\\anway\\anaconda3\\envs\\anway\\Scripts' which is not on PATH.\n",
      "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\n",
      "  WARNING: The script fastapi.exe is installed in 'c:\\Users\\anway\\anaconda3\\envs\\anway\\Scripts' which is not on PATH.\n",
      "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\n",
      "  WARNING: The scripts gradio.exe and upload_theme.exe are installed in 'c:\\Users\\anway\\anaconda3\\envs\\anway\\Scripts' which is not on PATH.\n",
      "  Consider adding this directory to PATH or, if you prefer to suppress this warning, use --no-warn-script-location.\n"
     ]
    }
   ],
   "source": [
    "%pip install matplotlib tensorflow gradio"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "import numpy as np\n",
    "import tensorflow as tf\n",
    "from PIL import Image\n",
    "import matplotlib.pyplot as plt\n",
    "from sklearn.preprocessing import OneHotEncoder\n",
    "from sklearn.model_selection import train_test_split\n",
    "from tensorflow.keras import datasets, layers, models \n",
    "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau\n",
    "from tensorflow.keras.optimizers import Adam\n",
    "import seaborn as sns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/jpeg": "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",
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAgAAAAIACAIAAAB7GkOtAAEAAElEQVR4Aezd65dlS1bWfwUEr6ACzUVsG7ziBRkOx/Cf96VjONThDUHlojZ0tzbd4gVU8KfI77PWN3NW1Np718k8lVWVWbnmizgzZjzzmTNiRcxYe2dmnT/0h045V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhU4V+BcgXMFzhW4uQJ/+ObIOXCuwANW4A//4etb6A/+4A+uet/CXwU/Q+Oted1K9dZ8H8tzi/+0nyvwPivwPe/jfPqeK3CuwLkC5wq83BX4vpeb+pn5c1iBx77h3sI/h7k8JIfHvrnfmu9jeR6S24k5V+CxK3D98/tjWU78rMCtAz+AF6p8z/dc/7D4VIUsfmwRWsZW8v/9v/93dcUavRzK/dJ+y/JYnsfib8W9Zb+V/624T8VzK+4t/lv53OK5Zb/Ff9o/zgqcnwA+zjq/mCi3DvaLmcCZ6LkC5wo8eAXOC+DBS/U6gOcF8Dqe8znLcwW2FTgvgCfeBy+9gN7K/9ZH+Fv4J17WF0t3a30+9HreintrIR+LfyzPrfne4jntH2cFzgvgbp2f6gB8nMf2fKKc6/buZ3FrfV5bQby1Du9evQ83+trW/9ZKnhfA3co81QZ9Kp5bD+y0f94rcGv/PLZgPZbnFv7Wat/K57E8t/g/tP1W/h867nPjPy+A5/ZEPnE+58H4xA/gDH+uwEdcgeu/2/cREzhDnStwrsC5AucKfJoVeNV/B+Dj6sj55vtpNuB91Fvr7wHdQx7031s8t/6O4bH8v//7v381j8fy+PuGXKZNufV3D1eDMt6a7y38rTwfy3OL/2XZZ9ajvKz83z/b8yug91/Dk+EZrcD3fu/3Xs3m1gm/Zb9K8oRGhfhQiz9VJk84qZPqxa3AeQG8uEd2JvyUK/Cpyu58IimBaQ+3wlNO9eQ6V+BiBc4L4GJJTsOnWIGnKny3vkJ5Kv6n5Znr57wAPsWmO2Oefwh27oHnsQJPVVinpD5wWp8q7gPTO2HnCnzQFTg/AXzQ5T3J33cFHlug56uVQ+Cn+mTw2AvmkMZ0DzyPnebwnMq5Au+zAucF8D6rd/q++BU4FOKPNp/5LaAidgFoP1U+H23iZ6BntQLnBfCsHseZzPuuwK03/Vu8jy24T/WqPnGHMGXstxI+7ecKPOEKnBfAEy7ma6Sa+vWoyfMayfF//+//zeILnO/7vu/rVzn/zy66IVX2fgdfF+D//t//C0xUTENaOjsehPvI90BWT2uNkgN+BdDrYoizVregaCUVD4vRFcACOQy6CcsgWZBoIVfZAu//E80ZqgszSmzjtTn8wR8Mfuyncq7Aw1fguBEf7vkZIDtRtc7SZzCjjz+FxxYghXuSbOXr/ok/8Sf+v116EF0D82imzjaqZamSpiP5I3/kj/DSku///u/X6hK6NmN6tNVxjjG4XRR3KciQ7iKh/97v/R5l9Kr/JMN3vWnQTkoYSNkyHmJhaNaXLZKM+dJHKe1xYSeDH/uXU1B9OccX7TWzHuVFT+dLJH9eAB2r87vXL7F53uVyqzD1Dr6et3Rl9+5J7P9Bzd7QlEsjlXUl9U/9qT+lmv+xP/bH/ugf/aNa9wcL/Qd/8AdhKD/wAz9AIV0G2pCUyY0SuUDqtRy6hOj//b//d9X/f/7P/9kd8L/+1/9i+R//439QGH/7t3+b0m2hhW8t9ty3DyhdDIw4hSDNpcsAbFwOizi5hW8dVvLBA5DBj/3LKai+nOOL9ppZj/Kip/Mlkj+/AvoSi3a6vFmBWyfnVmHyNs25+ggTDIm63GsyvVpMSRTxP/7H/7j6/kM/9EN/dhfl/itf+Yq6/yd3McpCFH0v+8jnxR9/b/Q4uwAM0b3Ls+MH3rO4a2Ziynov/gZggKv+/+k//aff+Z3f+S//5b+4A7oJ/ut//a/0Lgy3Ai/keLoGCqcrVlTaiXIq5wp82hV41Xvx7tDv/3E+P+2TeKHRb62bonl1RoqvIcVx6mAMWmJUy9F9oNwr7wq9mv+TP/mTlD/zZ/4M/Yd/+Ie95qvmLgblFX5e2+nqLxLkLgMkdNVZ7fYiz4VwUc25KNNezF0bbYOyMkrobhejZUJn1O0a6GIoz9/93d91Gaj+v/7rvy7Qb+7yW7/1WyyuB9Ex4DdfDFok3T26V9dnjPHrjlKeK8AQ41jeR5ko70Py4nxn1qO8uCm8Z8JPs3veM4lP5d6Jqn21O+ADLf6twqQuizh1cI2uzirxVfkf+7Ef+4mf+Anl/i/8hb/Qi38Vudd2lVRB13JXjtX3SnyjyEVX68ViUYuVZjWdBYlbwbNWmsEoLoB59Ot+iDwLnRdRtd068fexo0y8+CvrcnAZfOc733EL/Mf/+B+1/+2//TdKXyXJZJ0snrU7+iRzqZTMioRhHMv7KBPufUhenO/MepQXN4X3TPhpds97JvGp3NcD/2p3wHsu/mMLkOopYi1FGVXfVeGvfvWrP/7jP/4zP/Mzf/7P/3l13zu+73yMqtQejeqpjKqwfSmvq+AqvgSV7rxrc0Hb67zcwFTnbgv3gTtA5WXH2dPHQIHnxYiH4PQRgR0zd6/5dEkSDH3J4zLQdaNg4Nj9xJF0Gaj+Ev73//7f+0DwrW99y3dH7iGZ4Awm4qWgyniplPC4ABDGsbyPgup93F+o78x6lBc6kS+d9tPsni8d/tM6dqJqX+0OeM9H8NgCpPapmN6mVc8f+ZEfUff/4l/8i973vemr+z/6oz+qkiqRiiykuuyd2nfuiqkqrKuIq+AU9VeLSv6eXZyGFGh2WUWi4CrHqNwc+0v89xuFJzAhUfV2jwpY6eeLEEAaElDB3QrupD/9p/80fnVcPmCS8SWViYjLgkfyYARMiO0y+f3fN+RzwDe+8Y3f+I3f8E2RFqcQV1eeV/ZLRT5kvADIapmhL6Gg+hJeL91lZj3KS5/RY/N/s58e6/lC8Q5MD5vS+TeRz/jxP7ZA3MLPovXcdZNZTxWzolnV07a8Q1jXNzy+0Ff0VXzV3/u+7/RVUqNKvIKrMlIUWa/eCrcuKrXVBwLlFRsRCL4HZ7RiCkPYS0OBxqDtImEES8cgeRZ1H54RFd8+HHQH+CTRkGS8yPM1Wp7e5b/5zW9K1Vx8atHi+e53v8sRDK3qT2JzqxkVEd6kfEHkDsDw7/7dv9Pqii60BEwETNB4KE0HJ8HWgrf+kAmvLB+5lcxHjvghws0sRvkQUZ4z53kBbCvwGT9+ZeJJ9l9V8r7svOFU71pAawiTsCigypZaxk73I1x1XzX8uZ/7OV/uq/te/9VTo17SK7Le9Cu1kYilAgL0oo2EBWeFsm91KpHrBMEUfdW20s9FJSW8clSaq/uMkgdbJyWcEBIwCobNCz6FHdJ0lH5JKuVCKMoAriWKHIyaiFuHois3Ipyry2cCs2it8ID5TODboV/4hV9wE/zn//yfTScXLVgzlUlGvrzolyLVS+NHsFiQjxDlQ4eYWYzyoSM+N/43J/m5ZfaB8nG0etiVBq1An/Hjb4IPX8xbS1GhwUYUxxS06qCCRehTuAHoFe555f/Lf/kvK/2+8VcxDSnHlcu+1lc0WTgqplr1DnO12BcvvWXrEhmSXqtLQ5c7vFYlJXQAsXxFUzLqMl95Ktmiy1Y4SRqFrIKzEBYwuTEq3P32Ebxf9yTe2eVPWMpfqniA8bOYjlhGRSEImxGM+6BfZuUuZ18Nff3rX/+VX/kVd4B75dvf/rafV3OUgGvD1EwHZxZdSi2Fe20K/SPLp4r7tNOcWYzytPzPn+28AM4L4K1deuskjL2aO61Sq66pmAqcgoVLPVX41DjlXtH3bY93f+/76rji6915CiVftOojBu68+uYEj1JIVFJGdZyACao4CqGqVqN9aEDolbxPD+qv71WM4hHUj5SVb14C+eZdpRYOoXAsyLWYXRLqcjeKoV7q5cDRLHxDJXOOvrgnjH5igRxMrffNDyMqSHFNTRTt3CtS0nUnweDEDykW6YcH7D4BuAn+9b/+1z4T9OUSEoFKNVrrw5JYAfmwaFneen4fqyP0xwr1AePMLEb5gMGeJfWn2T2fcCkcmB42xSnt/HzGj/+xBeLWUlR5FR3PDgZtoqKxqHFV/35z3wv7z//8zyu+vurRKmQAqm2lsIqmjacLQEEsBB4C2SZRfIVQ7oWDN6RiqrwKpRvCr1oqwV6lGRVZowoumNr6Uz/1U+4eFw8exn/7b/+tBATFJhCwa4NFHZ+3cplI1Vs/dwJpOi4A0zEEjEcavsjy1T8YNhePNNgB5Eyqy1o6gEDykcPMDo88dYXAL2K+5uJDwC/90i/17ZB58TJxAK0JCt2aaHEm0Y79oymif7RYHy7QzGKUDxfreTK/2VLPM78nz6o6gpbi8HSoPuPHv1aNhyzmraVQDQ2paySeVk8tE0L5VklV25/+6Z/+q3/1r/65P/fnKIVWBxXBqp6CSLgwFghG+eNemcOpqzJ6MfemrPDx9Y5fkdV6wVf6+yrGkPqr+EpJeki0fMXCj0dKjMJVu+e7GrDS0PKFAZZJUzOq2zWg+rvAzMslEUaG8HIjFBnOauTOAoNZUBlSxNWyExi5TWsRTNxkhZOAVH3F5JeO/sN/+A+//Mu/rKVzF0Is4ESXUtwWOf1jtpPAxwz65LFmFqM8eYhnTnheANsKfMaP/6kKhKKmbJHWSjfB7wVZxe+3evxij69HvLZ7YyVqt1bJA64C0pXFLIqa8qdkE0ZUiqxq6DsWDDDq+y/+4i/6BUq/R0/3ZQtFiVRbK744udB956Mi0xEa7Yt4d4OSqvjKWZJ0+cMo8eVD6VaAES4JVjKukNLTCgEvChKj9Ea1OPsSyeggBSWQ0pASfVu+/bdg4X3+MGV2U2gdGAldMlxMs2ugvyTAw9eQNloWs5DzJykxcvgkcZ826MxilKflf/5s5wVwXgBv7VJl5a3+fccJIaoPQ6Wngv6zP/uzvmz563/9r/+lv/SXvCkbUtSI0q9V47iolUqbasVXacajmCrxXntVzwS4qq2Ce+8G8PLry5B/8A/+QT8jVZcJDJ7exyv6yBFW5fEriHJgUdlxFl1VJdzBuBPJC4SBkUt2SfKls7i3MGjV4hkVqxXAQOeu3PdRgO77HNeMC6w7gAWhQJDmqButtqJvLpGzSEOGHGUVOV8JuPB8eeUHGP/8n//zEtOa3TaHXczx/hF91P/K4aPG+zDBZhajfJg4z5f1+ml/vvk+XWadn4qFU025yv3YnXGL5yr5O4zxiF4CumN5h9f7D6lNSgyhVBArT5jVJrVMl65G+wGv932tL0m8sxvqlV9dU5XK3CIjUdqwWWS03BVKX6OrleqdSSlzxPf4fdXjzlANve/3ZYhflORSPmpo1RYtQiFwGuUuYqWcjjMADKV1kzMkDC+pSmmmA8Yy4BT4bRXuhSNmDOxNjUIkYAiKF8HZhwBTU/RF8dMCV50lMmX5S4Y7x0q/FeujjyGpxtOtaX14ScznHj8ldhf+k3/yT/7pP/2nPjr0XITmQpcVaTUwc8GGf8vvwVJWD4a/+X2kg8tjeQ7uH7k7e0PayUdO4JOHu171PnlaHyEBh4d0IJ2l2QqH0LbFwfLu7i2ed3tdjsYzm1J3LJfgp7UoW8qKYqQSVZJ0lTlR1Djl26/3/LW/9tf+xt/4G979VTeYSr8qDFlhBbaq8ueiJFlqMIJcFwYSRp3yzb47Q+uVv294ukIquOqpiXMvKzoS9U6s2kp/sRDqbs91EUYifzbJbOu4V+GerDSyw2QJIC4LnQtMU2ARaGLlIg0pubEoc0nwaqZ9LLBibgKfkHw+YDF9Ii6XFhk/lyGUrSiMbpE+T7gDfBXmBwO/9mu/5qshXWCFHkbQwBHybdkBHi7N/eF4K3MV/FieqyQfzTizkHby0UI/k0DXn+IzSe6DpuG0EDvAg3d+Ziscgho9WN7dvcXzbq/L0XhmU+qO5RL8hJaZ76yPxSFqjcrlxb9fglT6FTXVH17N7TdqlDwFTunky6K6caQrdoYqvoyKvlEVU+vHud5w1y579wQejr4mahG07GJx1yp8yFkIZV2BMte2aM1IWVTHpcGeYy7m1cLigZFe4YBZ6EarzhVobYQUdmwTesLhR6UuY1DfYSAFslxWz7p5u/dTE1PzXRYeMMKLSKBA3LvMLLs7QOZGLZdvhHwO+Df/5t+4L4HZuwB4NbVyblJyK9tJ8pbyQNi4D/9YUh7Lc3D/yN2ZhbSTj5zAJw93XgBfcAHcekK2y9Wh2VJXRx9ujGc2pe5YHk7yJZDqiLKi1gi3vvn6hU7vsJWtPZftd+SJulaBU4mUKhY5q1w+E7BjQ0JREPu6w1cZXva9wM7vbiqR8CogWoUST1JFA5ZPGJWOXq1UPcGEc0nwErS0hcOTb9M3F6ORy4TOQpF5vmCMMpRGdwBLurY6npcW8xAiIYwEW8njbMrlySh5N5zpy9CoVfJe7wa1nn5yrlXf8aAlYC2vVhpcSsmdwUt0VH4VyueAf/Wv/pWfjlhG0fdE3kzNyvBibwVGqXu1fQhmdSy91ZL+WJ5Lho9pmVlIO/mY0Z9DrPMC+IILYLbI4Wk5qwdL3Vv4q+B3GOOZTak7lnd4PXwotks8u1qm0Kh9KpcK28u+Vp2a+s5R1wus76mBeUlVsSOGlC0liZHQfbnvux0/yfS77QStt3j1kWP1mm9FkwUDL2XXF0GQ1V/lDL4QqhsMfsn4wOEmKOEKbqWwFg+XHLPILRgG9RRDCbB7oFJttLQFLXrPWosNhrBXl8OwcLFi5kWPXFbIpWdSonMHMCklnjuM5F2ofo6i9a/g6XIxtAXYf9iAs4R1MRgl0ta6BnwIIP/sn/0zy+tjU4tThmLB8yUs0+6G602w62PXrOV2OfJYnkuGj2mZWUg7+ZjRn0Os8wJ4pRfAFIjDLqzWqFnqrJLUj3lVKHXHkHqnuDg26leF2NcaKc4PqqlZShLxg1yi6PfKr/xNoacQeI7KLgV/hVWXolwKh9xQgr87Q3QWrVKoiBMKNpNKwAiMbBNUWYRjQcWdmBcXCrChArHUzVKXC0dJarsn6lay3VVm5/OK0pwljKCmIAqhIGEnvszRYvaBwM8G/O6sK7Y/OzAXSKFxWgQKWC3FkHsXxmUjnD8c8yfE/+Jf/AuLjNwilKe4FF6HVveqhLw6dNVofa7aH8tzleSjGWcW0k4+WuhnEuj6U3wmyX3QNJwl0jl3kmcrHILesnM5IOvewl8Fv8MYz2xK3bG8w+vhQ+Z+FVx1U618O/G3/tbf8lddylP1qGQAiHpKlDDfaQArwQgVx6qS0u99vx/q9sqvHkHiUe/oBJtC2Tt+VdUEGZGjlVuw7SHtsofd1lxPvZ6UeKl6yLsDDHHUEkN5aVVnXb7amTidF3x20Q0xkjDFAtCVFUHLKLqIxFDL4jXcgpgRsQi6SrzLwNTYtRjgfWyyAhQwcyczpPr7TSF/vUzxcwKwlkjQSYluLoJacFR43BC/+qu/2k8F/CFx07QgkE2n9ESv27wu23ePXuJniQ5Dj+U5uH/k7syiVXpZyT/JWr05DE9C94JIHGNiB3jqDtVshcMUbtm5HJB1b+Gvgt9hjKd9CaY7lnd4PXzI3K+C1Q7fWvjG36/2q/6+oVbsVBNSvVPdlDaFhjtwBV2e7L6P9u8Z+GUVreqvxvUCy1HByr0zhg1effR9CB2VKCqau8Q0OSqaypxqy0uqPSNrTmcB5sJR9cw98LQS6wLgCMBRLK0ufkMEmN4eoAxbTxazITCxtMKxEBNBrjVxCRstPa1RJEIQ+Zua+u4DkNBWxqVoXoJyJ77TpxMuhmAwmL7qb8ingf4VDVGApWe5yl/LhUUOpcHio4BfEPpH/+gf+bs5dw8XGDmXzKrQrwrkVfstowSuDj2W5yrJRzPOLFqol5X8k6zStrNfofTge97a2QeXS3FrT7zD5ZLkS1gm7gQay6PYeKkyigsvRaHqFqcixVh9MRRS3fkrf+Wv+Eeb1SClllGtN1qZo6hrSHw7pPrwVeO8ePrRrjd9P5z0XT9AnF6u1bJxVB+BlSok1UqKBKQH79djtEotci4ypBAW3a1S7sJOeCmm8ELIENtK2HdHyJtRjozYisjR1AhlfIEjB6N3AwmdSxY6NgBIilGianchcZFVeHYYIQyxmHifCdydFMICYA19n0PAZAhpJf1bF37R82tf+5o/svM5zJUAZqb4ZduKyQeDa0PXJeEnMWK5kHxc85cT/pcDCCUDJs+Sl3Z609TyZSTBdB8uXB4OPpHPdgWuX+PPNt2nSmzOAOWz38od9ZmmrvKkOvR66/wrJXQv+755+Dt/5++oxUTFUW4qphReMERlMYTBxaCQKVh+F8W/adyX2sEUVkVtry13vxBZdfP41DiZgFWFK204deHVOEgiYgmLpWwVWlAMFSxKJThOeHY6LyESOpckAHuOW/nff31I3MBlPpzYOBolovNiITIMyV3yqn88Wnju8Fp4ETG7DrlYYUK3Sj4bWTeKRwCGpC9zWgRzh+Rr4qq5n8H4N037zVG0QuPkCNC8kHMsE/N1B//Lf/kv/XDYR4F4eJEWk0v5i5uwJ4bubQ/6L68H4Z43yHqW4P0yfA6TetSSv9JPAI9aoxcNtsWVrY4rXS3Qjuw1bfsdfxX/b/7Nv+nd33fQCopyoBIpNACmX3XgRUHlxdOLvJd97/79JqKKZlTRV8vgFSnubgglj65aEWVUIB8d8Kub9AKVQ4UPXlAhyhCVrz7k3AXAaAghF77sJcZCDBFGXpAUXbp2RtlZeBGcinUYRkIHaFQISqEr8flWVU2Hopj2VRhHM/Im7hOPWkyKzs5oapB0Yun8PFz199VQl0E3hNUg8knBbx18FPBHEpAuAP/SBnK/LAQgc9FNSs5cgNFKzw/k3RYycW1IoA9kkMFEb1KUJpvCkbCc8gpX4LwAXstDd8gVBW2FQAFVldQO3/j7nsG3DX3jD8NY9VcBq0pc4JUP1UpZ8QNeovqr+77dVvSVnl6BYVQcVVt5AkbFURHUuh7AhNNVpKw7gIsEgzLKi4hbUHgAJBgo5ZySLpC5AM8oO5Hw2A2BEXatriFijlV/USrNjDtwa4yiVX8ZwcyrWWSPCmwLtv8c22g3QTCcFENh6BRUeFwM7j/v9aZZZVfifSAwcQx+EgBslcAskbWSg8ru6yCr7ZOW38VyQ3tYMDK0yHhkSISzmALx9ZNkUUT020FgfLsqWMBYwAjdgsyasNQ921e1AucF8Jk/bufcyVe8tESXdP4ZVQqv/H7bR2VROCorypCSAVzNAtPl5Y3Vl8te+dWUfrfH2vVTYop6RPKtcGNQqry3qmUVPl9n04vi/lDdVD1VDJ4IoZYJ2oWh/KmMLD2hqVBopaRistMJZSZFwU+y84pZYvFoMesaEssbdHaOCTv3LgAwQm8BIbFh1uUoN7qWzoWRr0nBKMfNCyeAa8mdJ2dTsybWgaXFcYm6/6yDm8B1yF04DBZKNUfLYh0su/UHI/6pbasqeREZwbovOcoQM7uPAowUXc+rTyrYAORMJJauPeXVrsAr/ejXGajtJHyuO8DsVAEnvzOvQjVrJcYbZS/+vjFQbqyACqLWANCrHUobo3LmXVUdUYbUKTURBidRhtT9yhajoqPiVBBx+sqiou92oXj9N4TBr6z4ktpbrfQqZOIKhDkGVGoW2oqsLpFVLQWyByeHjLpmp9VtymBjrHADUBjRqptCu5nAQuaLkPssFDbCS8TxlaSJIMkROEJVnq9CbzpadqshSkUZmCMMybd8MJusO9XHAlesj0QmDmkBXRIUKRnijsqSugBc2/50wHXimjGKRzj5A8cMKW1e/mD4H//jf+xXRd0cAWayzVc3S8oDW74PRD5nmCUqPdNJnnO2HyK38xPAh1jVZ8RpW8vGRq/WUNQI1UE59tbv3d/3y7rqiAqiEhEljCh2ypDirl6T/lV6tQkbvCqDkLgVOKpBiprvgpR4P05QpPpXQpUwCajsCFVMbb8n6gJAKKg3WV6yQoK5BNLVUJKXcGRmIW61GHn1uqE9o+2Go7BTcLYCtbqJbpaZL3uWHHv7lrCuISlJRoszI0eWAoWxVmU+aQBLuwVHAq/QW0MMbkTL6GIw2rq5itRorXvRqvb1mqWzpNZWi9yKuYkx+EGCnwr052PYighArExJ8vL5TG6ieNzuAJ+6pC0TALKvwbY9mjjllNe2AucF8CqeuBOuLhDFoorj3/L04q9S66oypCICoDRAqjXqkXrtO2glSXWzUr3PGjXUl87cvYcqT0RFU/H9AQFyv07qy27Vx58FqPUKFhflzzupnyKwqGKKIEyvsexyEEUavVzLWfUUVEqYicTULzBlruILIwSAtvzlBqab0HvAHFnqarmIIvlqX3Z6JJCGtGGMcuciNKWriILZEKTcrAx3xqQhDFaJY9/SFKX81WIF2txrU1T/aj28NbdofUEkhPUUQmhfE1nA7C5mbG5cvwaKwfIKJwHRhbZKHC3y3/t7f89V4QH5nwr4hFEaWtJ8ZU5voc72Va3Aa7wA9p1/13jYdv87DsBjDwYqnOM1SvYPurea0ppA81KAFA5HXXGUgLdC7/7e0JUbZULNVUQgYRQyFhWE0TcSyjRRZZQSlV01EaJ3WNeD4qgkKSuqD04Ar/N952MIwGusKu/+8L6vnIkiE4WbUTIKE7yUlDmcftdFDhy7FWQiBx9BhJazrPjyohdXiUQoipYYapqSDBa+IWkLZIJ4RAEwR4pRU4AkmNkJMJi4chCFhSMjnYjIkTDyhQxPgYyHZSPaFxyP2bGo7GXOUXT5WAoTFBftdn/ub/rsuj6WIfeALA5R9EVkV+V9KSQxmfstLLcmKjw4uYsiRNGtHgVMXOIC+Lt/9++6Kv7+3//7HqifHAhUthKg4GfR8tLV6pqCeQFcCsCl8R0WzO8YPYc+1Qo87il+qiyfNq69O4LZLm/fX40CedV+y9hGH69RPvQBwF8xqu5IzzEm7J1kNcJXDQqB7/19g6xqV7NUEEka1VYClBvvp97ciWKNRAXRqmVeMNUsRRBeMULo75V8veACUPoVLPVX0QH7+te/rvApNOH5ErG4cFeetLqzjPiVfun1N00Y1CmZYDCjlhGely4wR0ZigpgRqoMAhgBMrVLIUrehlogLRzpRVbkQOjtaSrQYlFoz2nC7cYu37wctCy/rQOj4+cawozYARW6UYPC5N2tDpmO5eAGo+OXcQjHK3DpYAe/7noVM3LJWW868LC93l6g/2fMbXH4w4BEgsQ4NlQyLOwMzo6fpV4Pcx1qXR1Pw0CVvphTCq/xnOmV7aNeJHIaudkvm6tAnNM4spJd8wmQ+SejX+Angkyz0hw6qWMy5LZausuJIKygs6rXfDFH9vf6r10YVTUWBoxqhuOj6lsb7pq99fNFMUX3A1I7Kh1GVCCGq3vRVc1Vb7UBS3VdifEFBMKhEKpSqh18mqMDcB+qOwyYcNnZUvgjqX8T0iiqW2tRPREWUfBNhr4BKAAPZ0tp/hwdG/s2oueMHo9dS+DJWpiG5a1lkSJ/SzEgalS28POPMCBle5oJiMMoiUL4ADcmN0grjEShkDN2pHDEIUdU2VFBIi2ad1XdILYDlsizW2Yq5Awh3V7UQhlyW/i89LgNx+WoLKq7EPCk8nlSOSPxIgFd7Q1yYWhMhEtAl6bqnfJYrcF4An8ljdYDVDpPp3NIpjKqAMuT7AW+I/Z97lQ/VQdVwtmEUBQLmTVPh9v8bUcSVaUPe6BEqTy4DeApaRr+KTpR+FVARcU+o1K4NXZVFkYLnrtbEoMqwC6Fgaen4qz5eaSXmZvIdt2wN9SNQ94d8FC9lS7ak11jlslIlMYouFzDhiMInT+FEIT3ayrFkWCBVUi58WdAapZPAWpymiSodWwsreUIHFotj7pSGdpq7n/oiiccoJUeEIbXA3PFkkRgYAH7PRbdZNH3LaImsia99PB1DrgQ13RSAiUXrs4Jv9jwaqyp/hKJ7auYrUGnzsuBcPCzP2sNi78GVTGmXTDOS1Smf6wqcF8Bn8mRVEwXOua2gbPVv/6JZQVHx/caI10Nf1ygcLN4WlRjHXlV17CFVW1/Z+wmhrxowuBKqIFVqYF7wLhI/OvYNks8QiotKVB0HU1PUCwkoN3zhKzq6RpUhQ1xUNF2E1l1dw+P1Xxp8lTa3iJJEAa5As0Niw4+Wsa+eJAmD1t2j9pk+GAtyYIrozQK5qieKbI26nAhHOYBh0xKBcGoJKmtCaahRXQDk5YOtKYdnJGFMs7tBDvi1lo5U8WGIiwpbAo8KIXLro8vuojIvaVTo2d24uhZc5lbJxK2Gb4R4sXum/gUIrTl60H2T1v2BGaFZQAptyEpaHIn5Nzz6GQ8GgEKzQw6+qR1aowfL2X2JK3BeAC/xqV3JWXHp0BqrInSeFb7+1Mt7n1JoVGVRQRz1SlLVROl3AfgEoFKoGgqEwq1QqsWQahAjweZrepVIwVKJ1CCCgUxFqN6psInqo+gwEtEVNXaK6u9mUozYla2+6RYOlblIVXoVQZlwUdck4AbiKyXuUqVErq1cUpqayutFWKpyLhZmXy55Wcas6unmVebY9hzvvqY3QRYA4bQlT2fMom3Bc6ePPUdexCoptZIh8mdBxQUmmK58emSCmjKMKVgEOgG2hkh6fOyStyDytzKQrgHPq+XyjZA0LOPP//zPu+yJoNzV9+6YcpCMj1yMovt5gA8WvIhYW9K70GUlyYbO9rNcgfMC+Eweq7PauTUfR12rait8vvZxAfhmQOlUCBQUo459hUDlVTIq/UqwIXYnX1lXYoCVFSTKKHdVQ0kF8PaqrimmYIpIZQJSsUjHUJlrVM0i0jOqNmmB1SZvr9iq78JJjy4HXhQFXQKUSOgwQrsJlEKZ9BGhyeLHKegeavsSHL/SL0QXAHsVE5tiapRilUwEg5SIrlbyhD51MF2pxU/YtZVvQwS+7jwClqhMqrjyl7DQMgGWLUBUdMrgjXJvSJLckcBw9AgK1PdjXDwFtFbDmgBAurY9Vhm6qvsTP7okgVtbClpL5AcGAtHFwhNAu8/pbl6jn8pnuQLnBfCZPFYn30wUKQXCOXfmFQU/WfVPvDnnXrQZlU5lCEYZUlDUU8XCr2l6/VcH1QJFgbviooJQ1JTqPnylH0C9MMoRDEPFBVuhkQgkE2WLzi4xIi674kIg1X33UwXLELAaBJ+je0WhV/pZ4A1BoqIwimsiviySGxJ2WUlDHZSwIZnDk3IrurfmrjqVDi2wi00mk6H0CkchfIUTnW7KFKFZiCGOhEJY2kPiJrrw2AgAvevNpIQjjHIGQ0KxvEj4aq0MvJx1TUEblTXRNSptwst0MgLDoPKMtKJ4QP5XkWYqeW/64UWRj9UuYWwW0N4wO8v4D//hPzTBbeb3P81uUmf7ea/Aa7wA5rDtJ/Tuy1/6kzxpJ/ZRPJ3Gh7vAl3Yuuomuk0wUF7pS6Ht//7azXxBUFBx7dUFbEVE+dH3h41dBVH91pOlz94auWsXg9VlN8dapXBLMakSVVImBUVNQqWgUzMqQUs5dS8qk+ssRngVY3cGslZiI1S8t4VueqDADUHhRtGZqeSladcpHBGkI7XrzRl8ORrkUC4NAMncrmKM/NTBlXjHjxGN2wJi1LSz32Qx0WZlLxZGdRc7ylAD3EqOwa+PRWg1RpIQ/r3hEByNdA9pgJUPnGAChKNImHhyjqUnDkzUj357RZSINzJ4ahcWqRkL3ZVep+gjoY5BYEiO5yAohvB8vWyVGvx5qM1gHSF0J9EzTOcpBy074Qr6/ILxKMo/g6uhTGdcoMiGm9lTkL4LnNV4AL+LB3ErSabRNG9137NbostvNWqVEdXCqfe3jqxv1OpgT60VPSbLFFURf+/QvEusqKHznKxcMLF4b+wSgOtD5qjIKqPdKNRonKrWmAspdtaqaa+WDAbMypHhhBoAnftGTFzbVZPCQdHUWGNJ7rhpUKTRU3ZlZSI8IB6Ct/PECgBTCqBXw6aefMEsGiasCp2zjsVDCaS0L4YKNUJAkkPnKjRTCXOZKMDu6FhVfAHhCgWfU6uIsBEKZBGsNWTjK2XJp6c1XAjvT9ldvhrh7ZIZEZ8/S3eYhtm6WwmcjMzLKyxqK7mH92q/9Gi+fA7zsc8FcejKntGGE9rtDkhHIBwtUhnS1gopIL58wYNkznu3LXYHzAvhIz26O0CGeM3aw1H033qiTvGKceYfZsVRe1T6/86NVeiqpFHZ1nJdvbxzyfs9SWZEAoyLiTVMFUQtUSS/UwEqJosmimsCgAgDjwoIQLb1ipw5KQLfcCq30CFFV8mGid3/lAyavypApy5wFUkShIc0Im6AN4Sd0mRD8RG5cREHIEd4FI23Frq+/YfrKSBow0VaaheaLgVdrTmGJHwk80ZUw8vR+AC5V7niEVsopfOVGYqME0LaAWjPaIVsjsVz4mpeaK4RAVrWIrZLEOBpiFJRAarfJ77/dm8U3eNJwQ2PrtnbFtjIyZO9HHabg4WKTiXZf0e03ROn+9tgzLUM/EzYELM9mLQ3ZlnDrY6hFO9sXvQLnBfCRHp+DdDXSrYN0C89OHMKUjqW2quF4q/u+/FH+FAIlQCEzpFioLFy8CPtFT6//fo9QsagIUtRHFQSPAsexb1TkpnxAakl1BJVKoWQAc2cES1jKTUScShUvluq+109VqYjwVR8ZAqhB7IwVI+SVP4R42JU5NwHhxWglUTW1qeAYwCRvpn12wSMBF54vQ1wDspK5/Cm95FKwyUEI7jJJ8KuYdAB6EenEXFgoeIhY1pyv3PBIALiEZS5bLQs8NpMqHCTZ6PYEGEsepjTYgZXjouiab4sAgFZriF10K9ByuZvNS3pGW8Mek9ysAHKAfonLUzbE0ppzt5gsfEVh98GCl9EmK1BLpCXw7Kd8BitwXgBP/BAd5quMDtVV+2ONnb3YxEqQKDSqmy89/ENsXv97EQZWaBQIB1h99+Kv+vvnfSiOdyQcFXGF0vlXF9wfqicq59ytQHyNgB9eLIQqESRahLzUFOQVIzB2hHwN6UKqyL6Axsk3TnEpCo06ReFuCPkUu5hRxROAFwAkWhKDbna1EpskJVz+KqOiJj0XmDtAZcyCTYbaImqxISGMCb31MUpkom3IWhkVV0RSPkblFsOe3bYOLACKNUcAhIbY5amVQyRNCtJjogObWgLGToe0XNwporAjDGOFeWlTzBdzIdxVHqhF0GXsj8i8AXg5QOuOx8aX6BLM8dB/6Zd+yZ3RTdOMtACEIvoYT+VFr8B5ATzx47t1Nm7ZO1EPT+LyBCoZ3JUP1d8/8+D139kWzrF3th1yACfZO50f+foneigqrFdXFURZoXvbBVD0OSrWSgZHdqMKh8qFCk8iFnCltiqJv6wQGiIVIFcFNleRSmRIFAJJSg8/O1qcqjOe7Io1QdKoerRVqb04tlAx0MOYOwuwbrXeHTAXAEtfbWFQ4FRPSMJFROTDyZKRxWpo5QOfS0P5sojVgrBDaoFTWhBZIbeYXOBNlvBqfWQCv6/W9iWMcJ4IF3owLa9ykDkStIRe9HhYUPGlyIG7K9CQiwoDoyiMWg+LIwtwvy8kPXbujAIJQQe2+H1vppUwLzDk8aeUG69TXvQKnBfAR3p8jtDVSI7TVfstI54EoAPpxDrAXutUf7/06eefAMo3uzOv+HoZ9xbvax+v/34m7EgrIg4/jGKhdZhZVJ8KEDYWVcCoCwAbMKGoLDhVFoKnBLJX5ugSA55v/JUbVKL0cqrSwQQWpWoiVaHpLIYkM1VpUkJriLQyQgAn5YZWF1VIGXZ7aemVSEMwusCiEPlEu7Zg4mqbDqVFtjLsw1DyMEl4PACQXCZJQ4SR8NJ2KVpD6WktNUfLO/y6YFVkvuz3ce5qMSOLuaQAu3FZKBbcQ9f2TY7rkDsq80VryDagWBP3E+GIBFU3ui/r/PKYPPsDEdNJyrxw2lM+gxU4L4AX9hCdW4dc6zQqMVqnmuJF22/++F0O51+p7aw6t7oOvFc5L8LsHKutjrr3ce+JMOqUOqgkaRUjbIyV7EoSF470qhUdLYHEw8WQVlBIZQWhfJQVOoDo2BrlK/8KCh2D/OFVH93smDk2BbonlIu2p8WINjudANeVQFLJq8ZVGeMXSBRgcWEofMmQZDEjRjovkq6lS4OS8NIl2IAxW4fmAmB2ukYNmSMLXdAAjABh8vKkwIQwhBnSaDyRlzkjGIDWE4FnlwCLai4EALw1R2hU15rkhRPAfcMF2Gc+S8TIXVbEqAvDr5AxGuolAA+8IdIsxBLilJe+Aq/xAnASbOI2dPvYIWF5qmeJamXr2DyWHEOOlYOdcmscVGcem8PvuKqD3tcc17/9t/82Rde82J1e1dxMuSsE/mzK9/4uAPMlAL4ZZ0elNHD0q/SOPbxR9drdAIxKOEbhVChgIgfkLGIRhRKMgInYD5ApFTKfPNwxMOWDjXtxBRIaT0WnV+DqS0EBJI95m/Z9fQdg5yUEXT7IMSR7IhuewtIK6IoulikoZN6LDfGF4duMcDb3LdL9ToBp8Y1mLB/RxwJDWKbQGxJrp9meoHVIh+EuNIWlpaADKMQy6Q6AMRp/GSKRJE7dGS1bLbtRghCPLqP5IuFoVTH3dZBH445nZPFwfUWm+ovOLhx3yXRncwfDRmwGnwP85MBotHKgS0ZLIFdF3LoPbMf9gfinhU22ozS7p43ynNle4wXwnJ/H5OZgJCx25yrVjgqNY+xf/vK9v2/b1TtGO1gV6KyqKX6Up/r7/X2FT2kw6vArwQ42Ti6+q/GjQopAFUReZIoCF12Vi7tXQidfF5IwaoVTWWRCAHT5imLUDYEWOelKqPojgWmyHTmt+UpJFELJMtM3ml47i6NLB+ZiZTDrmmxVTwLFkgxFtpLnAikfosuRMCZrIEkaYtkhG6bcDngA/CHvae7+m2P4fLXwmEW3XFpdFbzb1Pq0vCwUOavC3F1dHAne5mgKddsPSMxOi9CDAKP3CPhSCMD+KLZ/kshjwm+hPCnJKP0sRnFSJmHvDSx8rSc8TszFvZvh+Z+XvALnBfBMn56T1mFzFFepXBqiOLR+4V319w+9KcFgSoPWAVYUnG0v8n7w2z+x6Qw758qKtznVX9cloVL0BfEURwAMkCTCyo3aYaXolSruRhUCP3JQofCoHYICKGRVLi0YjNG+hDFEGPfJvXlz5DVBp66ZIPs8HgDCUVsmu2FrwAjFxFs0Rc2dJ6WQOAUlopsIpCpZFWuaG8tODh+D0ZKsyw6g7aZJ170qjQ4mHl2CVjK8xK3gWj0WmGYhc/XaM6LI1n0gYV6BSxtyXRzumD0XSHMExulSBxYFFUJD2skEAAkXUSRjn3gPIO0i4NLzVvFzP/dzwDB+fcBPDriUvARaGaEPCsApL2UFzgvgmT4pB0xmW814Wzpshrw8+pVNP/j1419F3MnPRVknuo6rv/by+d3xVkrUBUbfCRClWUHBoHYoBFWBjrRokM6/ECxGY6arCy4VLQxfdQGJ7450gSENJXQVv3yUoUpeXeQx1wqUpSKIioVQElQpJk7hRSix1TUExks+dAkrdqasK0mpUiAVL0NEShjyinyYGUm0GUNm0ZYPpdHA2mADblQrz43x/uOLJM03e/nIs8XUWgRfx7F7ZC5ponx7Xla10gzg4XKPATnLdME82VbP+iP0JY9wMKLIuaeDn3iUkPBCwPhDsNbQ4liillfafpZDJwXyU+VgLOLOvEaZhTqVF7EC5wXwfB9TB3vaEtV1blUBJ7b//brXNEZlwjFmV/KcVV1ntT/37cRqFXpfyncZAONxbtWCmHUZva1jY1cFKigcARx4yG4OZcUXx1XVkOzwVQEkiggXhCWPpxxY8MesxQks20LDJHjY+WorNPSS1MZZrLr0BA82unwUOMKdpYsBuW6JFXTYKAlfSmz3treGyoeplAY/Wa2pDozXIBnlWTLl00WlZFMUXNe5ck9Rmj1E4j6ANx2PwNqCedCUVg8znnSK52ttrYA5kj57Cbqvx+9KD0YCvGC6dfjaNqTHqmuICOp5+TDhUybHHlzfrSEkTRYVpQlmP9uXsgLnBfBMn5QTtUpZOrrOpMPvTPrq3zc/XsAdcmfbkVYXfOmhLigBfufHj3kr94a4+zLBZwIXAx2D480R4USpgiABcNQFUrhVnDAUFvXCFwXeUpUVGIGEhu/wC4StFn9GLUd2zNxlaKgQMUtDaDqklmCgx8MRuJaRMqJLwAAIXWsUoUUogQi1XUIwYsmEUODNIi9tCgwSLtqMWsZkojekyz6wMQbTFSVA7dgpTZO9m9WjYZSPmtu3MW4CFdlqG/IrvJ6gK9xEJO+GIGaKpBVjpJu1LhKcom/z3HcFo6dglHtJlo/0bAYYlw1FaM/ITcDuU5SHC28xvWRw7wpB3ocGPDMpiuTHUoizff4rcF4Az/QZVSlqS9EZpjiZqoPq7594VBoYVWGHU2HtJDulvv72jzz78Z2SARDGi5tuDNreHzu0uhTlowpC5+JIo3X+K5EsQqhH1R1RlBijeWmj4rLF26tnrSFUSYFMITzjxA2sa1RLgBlzqWXkQicYxIphwJGYWkEBsAGXFZih2klgCCMBHmUlX2EBasNsCe3VcHyzTLd8GFkStZuv9ORGLLJW/j60qcKKr49ZbtmKrycOqfq7wl3qVh6gFbjn2669+Eu1FiEFCU5IGL4CtTHgDSn3qOwiG8YDpfhqEd7jZmfBwFE+XjhcIdzZfShZw9FPeYkrcF4Az/SpzcGmSLFSqFWCfTngAvDvOzqiziejY1z1p3s785s//c2X0+7oKi7qhbdIo2BKCYu3S8cYefWdkV4hSHfsCRcArbrvY4crByE2FaRC0PLluy4lWN3YMOhy0aJdkVliMBFdaWi5QLLTtXlRyFgYgYUIjJ+esKhWdHg6RUqRcKEAs6Oiw9RGHoyeDCDwRKcQowHqHtqmnDG2dDmITsadhVhYCy5zV6xn1L0ucz/tZ/EU1Ov+dSYP1NM3ZNFaN8xC0BmN4iFCmDsjKqMsvFR5MssFY9QFw0toYPuExScD941Rjj4Z2Hh2lNKPoQtgJgtgItM9lZeyAq/uAnAYbOgez+xayhM+sI70gbAQM6Q7lgNyup2oYDt8e4PzFuaf+vGL/14PncPOsFFdR9cv/PTvPTjMqkmTVTiUbCcfM04VxNl2yPkysoRETrE4BJVagARALeDiHxGjALtgEIqoOuDHGQ8L9/LUsiOEx0ZnoUuYolVH2AsnFgU4NrCEF7tWVwgKiZ/CmI6H3hAG0pqYI4UUCLh8csRMGHPXpsSjxQNJ6CQFnn26+8jWsE87RoT0wccwhIboBZVJXrpWld3zskrW38qrvIx9e6YEe9A+EKjLPg0AmKC3dRbz9YAspkemRajE05H34Fg89D5V0D0Cj1LmpG1AAWD3UYCXf1nEfYNWMp44F2kw9jmSi68ZfazMDt9cZoIHBTnkpQzsMPRY/MH9C7vF1d4K9IUMnwfg1V0AL+ixOdvKh7LVqXbIfePvB79e/72MO3Lm4mwrDTCOpaLgd378zNBxdRoTdt0qL5jz70hzyR0DxcE25CQ4DyIC8+oVUkVQX3ixy0cmUbFX2jB0hLRJzOkIyaw5XVa6whHIWpZga4she8qQpEwsLhOr0NFKj6hTWhZxg8VZNx0DoRdomBudljIScvVKHwAlzFimG3/20WWIQdciG5KeLtG14KbgQVM8CM/ONtBu0/ve7/Um7mE1cU/Wo2Q0ayQUz6unpoVhydGobkNuEeHwu2wkwEVZ91xYPGXG2qjw23v4eUlv/yCxfZKgI6FwbGpn+yJW4Hxaz/QxOYoyc0oJxdF17P1TP/3Nl8Ppvcx5c56dT2fPgfTVv29+/O6gbl6OpVtB4ehkKh+quSPtlDrDO/dW/ZHQnXBvf8BKv3dDiii+hejLaFQsfW8gIi8ZVmgolyJnxhaX74hMmo4ZSQPGkIQHQBk2WTUUz6EFa5q1MeDPjpxv7vKMU1AAyNLgmBdmgFrGYZ5RQ3RtLpSR7LoxjH1Vhpxy0OsCN4vafEvVc4FR5T1xj6+38t4APDhTA/C8gPkClCGjydLZYVoH3dY8fk8zX8zsHrTWkG3AyyOGt+soBFgOMhECMxctpM8BSPDPFCI/2xexAucF8MSPac7ze/J2VrWOlpPmq//+JyfKN2Yv9Q6k40rUZeffi7+vhr0PwvNyMh1RGALvACvlfVEgQxUBgK8SbwgADCcjBoojza4i+PUPBx7SWyFjVUa3aa4tEnG1jNVNCmHRrQA1WttQo+FrWYhRbIRxkOxXkQDEkCgkPXDlzxL1emsl2RnBKAnHFI4FTWEs3Ao2RBqqrRtD7aWFfXPbRQj/HU56o7VGB0xJpAHmGXkEnpHn6KF4OnYFuxJM7AHPhXimpgnZXFgowpk1abIs7GAsFgfYl4ddk/aJIbW+XyKguGxEzCV+WflBsVYyGLxzIAmge5f0+Z+XsALnBfDET6nz/P6kDpLDhsex9NHeV/B+8V8V01UIHDav4aqAd0Dv+Kq/3x5RAuCdasfSBwJ2pRxJSMfYy6NRRuTOPLtRFQFY3XdhICdIMMOr/j40qB0iGjW12LTVL5Zq02HWdbUpCEfPt3qkDRAJWBK41kwZ6TCEXss3ZRhYSAwbdBcztRrsTVb0CE2TsRC5rO3BzgVZoSfcim+UpdHauqW0WnIcl/ESBZidAq8lgbXKukdGPL6MLgAPFNKkPB1Pn7i2PWLg+XAAzFICs6l0xbIILGXY2z0kca8wep/w2wRErfeTJz//R8uR4LQ9tPKxvITCpaHSO9sXsQLnBfBMH5OT6fw7USqXQux3fpxAh5PduXW8XQZOu3Lg7c8F4PCbCaNi7UA6z4YoMAqEo0tByBfAaOQOLYy3e+6GGNWULgz1xTWAE8/8cogE8DACa3W1W0nYiwI29YseuaHKXG0YyfCFJCHBRlgyxlC3FgkxfWDKuOzmrYvQKDB9HMeuQslWdBYuwDmGH8KM0x22vLQp7BjW7qXL6hsy33TuZLwyRsto+llS2Jt4C94jA7OSbug+qNG9hrvL7Q2PWxH3lM26d3M8xbIC6bWMMFr8NoZtwJ2Izt1z75NBPzfyOQCzQMQmkYwpuHsIS5ukFS75s33+K3BeAM/0GTmfzqTzpvr7R559AnD8nEy1QAlW6A05sUq//9OTXwgBdiadZPXaMdaaGIuWCwFQOJx2XlpDSgMLpAMM0OcJ1cQZRq4FIEbhnXaYdbEqKBv1LrojYFNf6OxhGMuHQhi1AWAaytgoS4DclRtK+JQA9IppCTCaLAvFEAa6KTQpXaO6gQEKHW1G+EkAgBhNDOmCrcYYxkJJuFAO/CzsBZqhjOxrATVaOHZPCkZWlV1PzSw8Sr8XZF5+OQdYsVa1PVmwPu0Z4oukiNoevSjYMBCOWhitIm53YXB/aJEY9aUQHpx0XhIwhErLa7aHH0H1S0GGTnkpK3BeAM/0STldnVX/2povf1R/b2FqtEPoNNIdRYW+P/dVHZxeR1RFcAh9+UOpXjjPpAPvuHJ3gFm8sinuHLWMCJX+vv/laFEMbW96+7cEmDFUI7S6YVo7OkFCjKYbyqINlpcuQNdJbV7yBwuz0S01d7qrETLmRhtiqZYZXSupURMxyi4ooUi1xGqNgmmbAmOWmLUpjMTodEdfFfoI5Hgx0seyUoV3xwee9ICJnNm1NgbF3jBTT1nJ7kOA5+W7eF27YvfYXGyVNlJPmaMbYnvD33+JyBIRVGKN+DKQlzcMbx7tCneMHdiNAsYFgJcoQoO1/YQgUpqJn8rzX4FXdwFUODpj83hs5dEPCuTBUveWy2PxTinCvHBWmJxtukPodzD80qdPAL5ydfAcP7W7EuDNS63Xcmcx5Oj6KECcw5Jk7LZAxVEsJEad2F7cxAVwrxCHGcYBnhpaudR12hFyJzi1eJRUVJilSgBmbbkAsOA3xE7qanf4VhMxYKMk7BTkAbhQALS8kvTsLJR77624WwfCTmc3Kg0WuhZzLqZsyAp4jwaIQaBGDRFT0+IhFEOXEoC7ocKxkLoWIWPd3AdcOOSrfZBIyrbR2j2XN/OSoXKvLhv1+NToirJt4FtBDMp3hd4zIj1062DZzd0ieNxguh66dZCwrgwtC+Y+carvkMVC2NJJvlWVEkCzQILKpxDgeWop5tJ81+mMLiiZrgSSsXwIZY2IX8SilOp0P0ToZ8X56i6AZ7X6kunUUexI207XUem0ONt+88e3/64B1Xk7Jfs5sUchO6VaB9uR8+VvX9qqAkYhq31ah1YhEMKxJ862Vghn2FDVgVIyDnPuGAqEYc/ozdcvumWidebXwlQtmNEUzJfSUOEmImPC0iLo8tXNwjh6QzE3qtUdl4Z0RdEabXnl3LJbgQghJ/Pc1+fCkoCVVVEKV5RD+46hkAgpYCHrlsOBqm4wWekCz+Io9z1i1VzJtgcMqcUUbCZotOnTbYNWAAlYc7QBAGwhO8fKaG0P7xbtGRZ7Q+lH7sOoci+QITAkhvjaJ7q9jthd7BKQsDyNUmbRDJ3yrFbgvAA+8eNwNjpC8qATCotvY5T+n/3Zn/Vv/vhyxinquIZxRH3542XfOXd03QEKAXENOLEY4B1L59bxdnk4sc6kw+mUUlCpC4y+6jVKr6awC507CwY6oYuipZdAupaLWDtqg3HXkiz5rt1BNqTlTiZWgIx0uaUXd1rGkMgDaI0yymFcpJelxABYVKuQyI1OenHm21IYWqWIuQQePZju2Ad8VZGPHIoVSRkewGjHAq/LpbWiUzx0djNSi7VmRGBsDAC6VsmOHJ6wmJ19wlG3SyI7CzvfooDZUYbsIp9BDQHbjVqxJGYIuW1Gqeh7I7EtIW0YRnFnjjORU3k+K3BeAF/wLJyWL0C837ATkqBx3pxAh1Zp7v/04n/z20dsp8tQyThjqr+fufX71w6bUUbn1k2ADQOqDmc/wePoxIKRGXJuVf/e/YcckkgGTwoe3Y6xFpIYZQSgNxo449gpI3yNJhnve9t/WdbugNkLLVDr09DQ5jh4iVV3wnMxxKhmEQoLaQp8GWMQnZEYzWWYdZPJU7dsYehazGMMPN11XqNzIboD00UyAEqAlAFTuGhNU0vc6x59td5TZqGrv7YEJMUXRMq0qdkqhWiausB4CBdC2Zdn++nCcHIJaVu6CayY9wZZISkT5Cx+EM3i1QReK5OmtqV4v0/W2Z36c1iB8wL4gqdg715FtLmvDj3WiKqz5OzxdcZ83Pab1z4B9NU/+35It0LsZHrpcwF4l1fuOWqdVUfOUUfVMWZ3LImuo6gWKBMDUPSVfheAw9yBN00hHF2OojRrbBTCjscQ0Z25N7QhdjHaXPRmEe7G3vZqdIWtnOMyJNFqSekdMHXLU6tr1kRKVTer2vcVahkGPIYo5qXNhReFNKpbrLraojBm1zLuvTcrxjLGhq62Kyba2rFP9NzNouVll+GM9tnOrmAxQdPpysfTVqno54Wqp4yh9TFKMWp9GBu1JRgr5TjbRTaPLQdm2wjKmC+7xIgd5TeVvbjw9YNo29IQDHJydRFO4ydfgfMC+MSPwEEdkYqKrOj70xu/99lvZDpC7M6bM+ZI+3zdb/50bp0xH9KdTCUewPmH7K1W60izY3AaKVxQhVEmOvMY2HNZD2pZZdHyUhfqTgGCYUlmHRnpjJdtQyEDpBdr8CkDaLSWcaKDzdD4yhNmK0j7Cy+7BVGw+prCFLgMGMb04RW+ap82BmsSsrZYWtFZuIydzp6McZT7keN/AQjfprOSgNZdW8YJzU5iMCOz0PUETVO9Zpc8OxdvBnRztAhdDwXVNl8Yo3YIAKMQpq/Liy8SMEuHn2KngbVz/GoQnZ07kQOAjxp+XjUXT3+KiFYUo9pTntsKnBfAJ34iDobDIwlnj/jBr+rvf/Tomx+vVA6P2s3uKPrCx69YzP/isZKtrHvbcjIdWke397VKP04ns0JWmRCo04gQklA4yoFvUXhVXCjARJcYpTMSOst0M95qIQ0NnkJYxn2U7PEcjGtXdNJctCkTfaffcjNlYmrqlBJmsroma00oGArHnQJPYYQnLHRGEnO0o6/29NgANp97r8nqUhEuo0CU3C8ds2tnaJBmgcR0DHl8ieSx4fT2AEkBg6maWwSwwqXwRRKPFj4eC0XsPbuLwl4O+G1COiovENYWGxhfjnZsPyoQEYb4fST3Acwpz3MFzgvgEz8Xx8YRlURnzwXgHcrnaC9TzpjzqYIbdaL8Q2+/8iu/4k/z6d71fNx2wJyuvvzBA8/uiHZcO8AVO8bsCMmcc4ozXJcdGKwV0V2XRiywLNvJvi9JTn661ug2sEvu1Iwr1WoBCzlxjWapnaB5IWQh4m6e99+ezShLDAHgezVunS1m1apZG905tsbcE+TslbZoh5ydPpL7dFcF4QG8jtIDwIyMMST7qmwp3k8tpAl6xOZFYWlN6CwW06xz8YpgysTcjboLh5YLMDHxSjZHXb4swADtIu52l66LxHs9Bp8D1Pp+IFwCjHKm890Dbt9MEgwDKPTZPp8VeEUXQCdt9uIcsB5Gp+vhD2bcxzFl7AeqgTlFDYXsDZ3F2fPVv+/9/bKdQ+gCkKpjSTfqIPVrP97I+qRv1A8DfCPkDuCrYGkZiRB0EUdhFKhYCIG1dcFkkpd3OsY1c6PE6LRxcsmSQqcIypeu1U3oubMTcbUsRcGWqBoHL13Ita0LSSHCEUuk3DAqW+al3ea5C18WlUsLrxIRLnLQGiWUnWxrSlg+FF1Jkuxc2IExzLw2n3sxOlMYBoOMReRFT9hhSoBuiD5euumMRsuhuHlFmz0qIeK3GXL3Mm7WyjQXvq2SxbF5PGXTsWjA8oGfDIHpAPC2nMuDS14RAnvhEBoGLR4//u21Axs8BneMi6H3El3/SpXPAZ4Czsl2FrY5srca0wo0+qpcItfRh+u3+DE0tAZiWbsPj/L8ka/oAnieD8PechicOu/+vvf/6le/6rcp3AROF3t7sZPMrqx58Xd0KQ6bn+s6dXS70yF0Gp3VdnCOjp8hPHs93GAdZkeUwu78t7ODpcfQcrX1tQlAMlF0DQVe24y1MDOURWJZdOlawjLKjK6O8YRkn0ysHhIzomRvXpDshGLRFCCrWskrEAaWXAoETMkxS22htQFmKPt0L5Wisw8DJT2wWJTalNHHawUcfCfV7NoWwXx5Kbuesk0ye0YdB1C+tZai1bBzOGq7LDlWvnnZZpCWjtE+pDcj3zoi8ZrCiyINgoQAdAeIS1wk3PE0C7A23nQpp3yqFTgvgE+18ndxHRhHwsFT2VV/f/TrE4AT5cx00jpgLI6NE+hzgPcp38P6JE7cAc4wjJOpJQhZgLezuJPrVv6EFMihJcpltwKkBMQCplNmRdhHp8RGGVhFZMWMPjy8MlIITkLJSA+5m98qhQHEGs7BzFCj5oKk2oTZfLs+WTLCMyZcGFmwZY9tLOWmTWa0bl6Mug2tsEanNURPgo0X4zCnB2McJXCOYcYCZsq6s87mpTtU9o/NYMMAeNC6ajpRiLsDvDGwd/9ho0NOlIJqc1Tu4Y1qiQVkV9l9HhXC+jMCywF/9wSMBLhgxu9zgBaABZJ+ynNYgfMC+MRPQVVyYLz++6kv8ZndsWF0Gh0homTTHdSOjYpPfPmj+jt+KnvHTwtsMs4bAe6ksdMzCuSgejvTNupAEhGFABOXvRUZpa7RMBQujLqEDknYQ95yhxnA6DlqEwBKsAiHNvsKE9qoHMzRFPIyU2tFzKV5sZckpCWib3nfF7uVNvJasAgnGbFIi0zJHrjuSmV0jNnHMo4AMxRPbYDaNVD6aoHv+Zrs0Jpa02QBtgg2FYAZuQDsHKPEHjCktVaG6MBgIe0rRvzYWHhpXQNtVBvJEIwdyLH1p9ir1p/CSwuD3JWAWWj71p2BtlFGAN11vqf+kVfgvAA+8oIfwzkG3u699fvZr9Pl2LB0KpxSJ43utzyJv/zy+k/6TO1AOl3oHD/HuI/hjp9jqe2MaZ2xIYQEmxulk48BBnLNjGXt0juuYPKhkwCrY8aDb90xcl8tuWhXY+FqDTUKEIY9pdlZMfMqMTPqAmgBY6ATgJHc0bKnaxMueY3CPjp8+hjzwozNUPbaLOO7dldYDGvLBfggucRWoCyFDtx0mqadYzX6HGB7+FI+jCps51glll4FwAg27onurFV1nAvHvtIxxGgXdQFwKSsfK5EYAmDRyoFRoD5G+NjqMojc3i6fmdGpfJIVOC+AT7Lsb4IqXr7x7//34udpzsz2erb/TM8Zo3jtcnL88k//3K5z5eSwUwgFAy9gR8tpdFYBnENGAGcvC6Tq7+M/fCVA68TuNHef/el83yR3/xrLkh2A3pnPgiFlurnrGkovCguJCs+MZhyvVdk97vIZfIBJu4ojJUUt4VWeXOitSV7a4Ylcu1oAmh3j2BkDpwxJGLGKstrpJHJtesrktkO2fJK6sQ2eS9KoNvfpNhqDITJ6TxnSE1frbQ+W7Wug/Z/v59iW0NKNcoTU0glHeEM4YaxzQ24Cuo3Um4Sabovi1+1TBZd5EDahzx82IUJsXT8AFllLZiKn8klW4LwAPsmyvwnqd+n8TY0LoJ/9OoH7Kd5esugOknd//+K/C8Ax01XEHZ7exZwoGKfO2WN0xgAofFkMCePDOyNF1yklRjkyOs8OdiVjjiIjcN3tgN4fUbQl1mhD2hXfEAvJMZ19LLkUlJ0MVd3ajKsFQ+CMs0qmIDfTUWW8kxbXZCkwq0vJMHIhABwtRfbhX0NnLGLMtSwNYcuCKlhsA2NfLem14YdqhljGfTDxCDdsMMRDZ6EMMoUFmDRH87VP1GI7x0bqldxNsK/EtgdaB770WkO2Cn7CuNZ3jn79zIuL+i46X4QeAQxLLuxtOa81ksEGJjq7j7DAZXhI++x+5BU4L4CPvODHcP0ytbPkcCruhjuxnT1HxUnrR77sGb1zKevEiar6a53JDmGHDbIjxwiW0eF0RNkdURZHka4taJnVpQMko1OMVlMMZV/xAbQkAAUgjDYjBnqFBsC8aoPlO6F1VxkSiuSVGEorpqYQtE1qEkgBIw1prQ9ajlwa0kKWTNHHcRLIDjmWfEMyrkNhZmjYclkZVseVoXA5ahuadcvu4UZYFxXFLMKbJoDHbcoc7RPlmIXAuC/bEmBdmYyEL7zdyKVvFFnsHDAMhnT9n4jE9TkAHhsYwdYXQYxNEK1ReN3uHjBrrmXBbzTk2X6SFficL4A5S+0/XRsu/XKtB3w5dNVyyRPDpT13dieHLgetuuxEeev3z7j7sy+/AsSo3DtjThGkURgWn5odmEicZKfIleCvgp0ch60fGzACQzpXzi3BANC7mBatk++acSCxwWsFak0AnNh07eUUGDnCQBolZsEoqznAuiPZYQidvfwpSGKYGjFDKyyMFiweilgEjMV8Tco02ekVFOWpEGYnVbplZOzNlxd3YHbT0aWIXpTSoFPYR7KL0pBWUAKQBU+WwaxUQwg2dkZgXQqe2LQw7IlUKTAAWpMNb14ZyzD+gVFyzEuXcGHEYNYWxPbwukAKzU5mNSAtJrGGdHusDeNzgw3Tt5RGDflxlOg4fay0UZug1mqzwNtmwvkZQFvadDhaf28womMoAST0JjILO/NqCk/e3uJf1+3Jgz5Dws/5AnhWy+1gOGbOwGx0R8vrv9/8caicSQdJwloC7NA6P86JA8POtwPJ0vGzU7eDe/8zt2g5Jh22jjELfi9rVXyHreLYXr91Elq9OQ9go48Cs+q5ZIQfkczARhnwqhgdrxTZ5q4ljKYDptVtKaxMdkbFhV5BmfVhaWGtAJ0Iyn0NTc+eUp7alMAlMLCGwpdVsAC769YYSkKGaZSloQqf7kOEb7AhOUQ0OjOt+gtK0VoHQ+qyJbJulosuB1RItPR8gVnafhTSDoRX3/0ussX3ImIbx2BnFguyHzXtTttS237YUHlfcR+4LVD5DSKtiQMICkyppZzycVbgvAA+zjrf/SuM9reD55h5LVX6+0ffXAO6zoBUnAdlC8Bx8kbvkDgtDk8nxJFjMcQC5qASQ7qVPO5OuNZRdLb5siP37k+cQyGACfdmvh45cTOOorsCSpIloxYyPceVcwPdv8LPaAzTvarkJUkKwHTp3GVugsW1IGaqjugaIhakFQamQ+IBg9G2Ss1uzbxAxdKmABCcWfhSsGWpzZGxQOPIwjdHLfDguZCYs2u3SAt+HA/KYHb4G5fVzmVGBUIuGUqt7aF8q8Wmo7VD2gk2CUezaF/xamGbl24LaFPZruq4xbQ/dX0e9QZDEPpaEklzdwfQvcTgkU8Xj9AuABZgYjMHLuFtXXaZ6WA45YOuwHkBPPHy3tq7NrZItrt97zA4Hn71089+fflDn/KRO5gq73h4w+pHdrw6rk4sBZXXLofWcQVmcT4Zddnxb8drd8Gs7vtULopRSJk4z+zastJ2AjFkKQ1tXfZktXd0h+EesjGAIdcmq+/ADgoky7BR8EelJUZxVkdMhKU6QmEfNpO1FIQ7I4wVU62IBdFlNHcM5RYs96Ic9BILrIVJwFrAyTMMO0Akhzb3jIExSIaeF8f0g+PaDZC7tliXEc10qAIjSbFD7IdWr001Q65Mo0Riajd8S23ZTRO4oq/cuwaM9scodqm3GV7m4krgu3NsXV54rLwnAu/puDzoYHY4u+0N0zpIgw6ma2id9al/oBU4L4AnXljb9yqjDW2obe0Y9OVP1d+py8u+J86AE+KkeZ9yB1AcPI5zZvBzUf07qEadsQ5Y9bGagsrppYPB81IEo2Ikgq6F45A5dy4A8tEeRg0d3ANrE6FTwJIhvIdc/69YI0LLsy4SDITCs65RegBLBL+KIcuiNcSRksTA695wN5eDPYB2IlKKNb4sq3FGB5BFVmJBUrLsfm+acWSarFZltefWjGJewxUIprXKcYKq++w2T1/u21SWqM+U7N7QbRX7057R2i2ELxJLLRakkq2Iu0IA7Df3q19ScCXkgr93F1QwXbTW3yi9rYjHrkbC3tZlaVJlW7tO/9Q/0AqcF8AHWtgj7ZxwZ0D19+NfL00OofPmYHRWKY6ZI+dQVfqdTyeExQnR9loXzBnmy5GxlyynkUzFpMBowZwo59x5i4rXwKY0yBhMoJKZQ5iinSk0NxYCX7cyMdNGwjJdSLp2Nc4oJfKUaSlybmgLtpOYLyM9KhORQ2mwhDfaHCtnWmLIIpAYuMBbTFFGWIqSJdoZxTl2Q7NQXGIrJd2RMOwAjAEYE5Yhf6ASM/cUk8ox5tHNN8zEbWV0bRJD3QFIrAajss5It57WhLuNqkb3y2YA7Mitns2pfPtAiaHXeV13AJ1LGF7dJajcE5h9AykufnseGxL3hJztcKG9mtDBJv+Us/3QK/DW7v/QwV4zf5vbKXIwfPnjl39cAw5Mx1jbwbNEqnnVn+LAEKfOmXFCYAgqZ8kR1TIagqFEgmErcvsnbvzECazMRcJdV6ubhUtpzANau/TIjY4L9zDyMWpImxJbVGNJWWkDTFsh2yh2yQ4vIr2cpZ2FEb4cjPIIJhmKlrF6R9G1CMAZMVBIyUx3jNjStdh0V2T4Ih6G4qwdl+YVYfgykRXMTAEgO0zgq23Rp43hlsvwmwVBmGK3iEVsDBjFt/1jVDlmh1SmrbY9ZrvaS7kIRFe71Xdf5dt+ffXfd5V+KQghMWU8vhfC0IcAhKjcGXvY7Te4ACr6vZGghZEMKUndUz7CCpwXwEdY5C1EB57ivcmx8ULkaDkhtnsHeHa/uu+VSutUGOUCQByeKiAkNro2QG2nC9Jx5UsBcCCVP8fP6MZyz7PltAsLwvvem/9mNMpUbpvzfamljJ2yj2zN+K+W7BKQp3Ywq7L6rnZ40bXmSwwhIdbH7IhRXXYY3Xi0VkAlIuyEArYb7n69Eph98DPfUXAaJSWgTclYC5M9cLpWd2TwLDFom8sgKWAAMhzHq0ouq2O+k09e9gDFEClWi6PsthTZ7Y1gMGoxUd9ZsNmfSrwKbqnZ4dn5enO3P7V9fgVzH7D4abAS78daYKKzcLfCNjxfJLp2Y58bfPnJi9FNANlPAsCI0J4UBc8pH3oFPtsLoJ00y2cjfpwt5ZjZvkRoh0q3cqyVg33v3/v0p78Oj8PgSHQ8FGjimPVTX0i+zqo/A2aJag4GcufWFYLcR28YQ9x7z+1EKX+Yheijt7nzcnohCV2LFgOZVdoH70ZhWjEtaQG1KwahobHg2bFbI4HReSUsgbV0Ri50sSzFmmFUAIXInREmabLsUTFSgNnvIduPUhgVGkXN+rDDN186sEXOyB65tlh807UzEfpIDLpGtaXRKJ0Sj7ZumAAHvS4YgY+QMd+601LSVy+OjKaWi9zIVs733xcYPBdiyG4kdC72icJNt9+UdUVZa/oUi8ne1rKGXOgWTb1WtfkC2MleaGxCwoKqm8PygoXv4ebVHH1f5BSgkpt82upa4dYV0D0I94PlabvrWk2sUZ421nNg+2wvgE+1uPbKdvj26lnbyXQ2lGNf+/js7MA4Ng5e1crxgLH7nTFnTwVP6iIEc5AcSISONJ2vw+OU8qpUIRfCEQXr2KNlxOwosmu5WxYHTPuFe7qToA254ld91nnwlGSGUvIyVHcww78qqz6LyTE7ZcoEyxhxmmb8VsMKtFZ0YhFC0ouOpDXJZVowy1s3pFZX22oP8guVVhus0JNqbLfcCwo8ccPXveXFzoUMoK45ZtRaBKNWwOLIjdJKtj2mIrdnwjBaRhOPx5A0bFGbkBGDUUh2t8K3v/1tm5xksYfBAMoEhoscjLoqbFQ/DGMEqy29W89l5nUqT7UC5wXwVCt5x9NGn/NmWxtwYJwTb0YOhp/9ev1xKhiNdn7seKXf+amgK+K+V/VK5WA4fm4LrSEHxiHsvR6DQwiJxHFCbqhbBMyoa8MZ4+jIETBRdLWkxG5NvkIzbZMCHuWWY5PlOL4pB/t0R5l1G8XQiKmtCTcFo4ErTIxiadlN05q0tqoPIyQG9cXQwBgnRHqEAMTQVSWXAOkrzxCmyGFGV0XOwzP21XdCD+yg6F51zM69Ua1YhEKMSsnitD5D0upZIlvFKhFKSFTWcIw9CHvPBrMzbTwbUtcG9mGrDeaLIzsQkgUz6SVGGu1h0Z0C+SC3h211DNs23T+0MUrslI+wAucF8MSLbItjdHJsekqnhc7iVPg3n4lPAL0TqdcOj1EnwQFQ7h0PZ4Dumx93gFPnjHHsQLJ3cvr+Zz8v2zct2NgdJIJTDsIxEuR88VNgCOUdc7569hgxkEvHA143EYUCv3bTIxk9pXUrSm2wQ7bAWSgAg59AClB2SuugS7GwKpRWJeJrHYLFQ69buyYAkBgaBaCu9guFFwwXyjhmXNsAsWU30/CMK/JqRMjAKbNuHNNbYdO3NxJDjAmLFbMb7VjS2wYqOrtRe4nRloOXAD1R6C0mx7pKuXCMhbDgtp9tadur+JDYWLQwFA/Fa0p/HowBP5erEzyNH2IFzgvgiVe1Q9hxcnhscQEcib709M/++P0fBd3ZM+osORJ0J8RJUN/hXQNVfyfBKLBD62zAsPgAkUUX3oERCwBVhwctL5aY2aUkBBiLg6dbVrdmDmxo2maUJaocAWZo8GbKXsUZWBYtWV0CvLuVdkFxRhsPr6tUlSdD4bnDM1q66gt7a3I1bpxawvGAWY2XowdwXS6U2lWhHxh0wUI2dNWy0kaSy9h3jrsf5GTEY9ZxtivoLQJwiraNxCVCy2WD2U7tJQw2j9bmASaGrCphdz30yu9TLIshPIo+OyRjHxTcE10VQshBMrzsZ7s6Wo4+NLx7fzaps32SFTgvgCdZxjckHTPnhNj6BhwPm77/5Yu29yBDAEa9/jgMDptjo8vu1Hn31+p6/Qdg9AM0GAfGu5Kz1DlhpDhCjhnFBaCVgBMrIjCGMbITsZwuxqIDXBVI9rU9wBrCRkJSGAlm7eBXnXH3uPPKNwsYRZus7llWWkhrwh4DpRy0lnHsKprFb9RQdwkLZaYfg3YEkj7huCeFCMaimyXlVgtvqHZVYqidUd10yuh56R5CjNcAWPKiWJ8Vv9HtDGOvq20p7AqKPaPNvX1iPVkIttbTHkNilEIAimsfYrNviX8r1A70OdVvPfR2wqULWAjblTvxLPrqsl0K4KrwAkQRa83/1D/QCpwXwBMvrKNir4/odhK84zgMCrpDYruL6hg4DA6POu6V37GhEyfKpwHHw6jqD+ZIuBIcNpcHHoQwXpTAsDl4zhh8QUXU7Vao5ME0SYBC6I7xMH/2q0MZa5GMl7iMLFqSnSJWekO6+/iGTIxSaimNTptvo2Ok4LEOgnIxUxZtYPqqsCeQvCymVsWxMlpD7GQCrQo7AEuc2mT4AVhWl3frwMUaZcUPFQypO8ZBjgVmjAdlhsr/MKrbgzCKbQjZ6Vvs/VeHLZEt6iOmduxcrJtlZLT+anRbTsvdqI1qv/l6UxHn6/fTvKzY81pe8DatbewI2J9cPEfkvQAhQWuf+wbJcdA1CnPKh16B8wJ44hV2EipSeDtstrsPuX78q3w7Wja9/e2oODBef7wr+QVqrTPDYqjvdhxF540vQha1HqHD44BhcJyIQxIGjL6f3+13/zuoWjr3MtECaLmza+kPlwfiwUIWK3569hlqdMUEgB8lrxVJb22t0hBSzHGo1BqWVp7CDqy4WA3GFie87tXpc8mxUTpl+FeXhlbLpX7ARB7sMHTLt9BfCB5mCrEOQ6g7ulmb/mwMQ3ZOywUzo9xJ+wRe9PEqE9UcmLvWClteAq+g67oD+hBg29u0xFb3ymLTgnUHF0sXSc/IJu+HAUL4V4Ym51P5cCvwWi6A9QysZ4k9sb8ftcq8ruI7KoY6GGq6ku17f9+HugYcNm/6DoBPxxj8m7rOid+cczYcEufHKxJxTvDsB+dP9oHay5Gz5K9sfInUQXIC4Z1SPE4Oo1PnIPES0XmTg8InDVTSaIK6xFD515Zz57xRFtIEYUijtblDssth2LgAhDGU+/CkGB3aHNmRNHqIPr6Q6w2HxEyFgA+Trq2gsMMn5Ymh0gOfL4XApExbVpP/KOyk2UmYkp492IBHEQvzAWmUsOerzaL1QKfbKF/21Viq5kWGBKa5wPdQcoEZchY7gQsLuy4dOOEuW3Y5+JRpU3kZbwtB2rR8jW6vHvvrP4DNqeIbQgiJgSNOir39zW9+kwu2n/mZn7FdCXecMrQ/PQ5xUVF4Cd1XRrY6mM1siNJ0KEKUsPZSGr20c884gFEuwSwCyZ/XRLwK+2yMr+UC+GgPzD6ec2j3K8deatTuzknHz763vRwYr/a2uw1n1Dmx430EdgE4Vw6DcyXtjo0TwuIzBEch+NrHTg6vNitjFiHYca472BCZRaAD6K7tDrmDZQ9/iRkeQ40OMovWHMe4Kmsaw0PJnvvol4Cx4N9y3QuZdhisTHrTtzgtUYXJEDuMlj7ZprAkCKdw3Nvu1mq6lOKulqt6SRoSZU2VznJw8RxDrvZga7jhaWh4ViV+ExnwJfNEsWnXDYPHClu6SGbRwGIDYNQlSERhMcSFYqPazIq4fx/iN37jN1D5+0ejwPZ2pd/2jiQeJHwdBK8vYD4BsHcHgBmduJPzqbz/CpwXwPuv4RUGm9Wu9c2M3az6EzeBrpPA7rSoQUq/E8IZxtZ38v1v3/0wwItVRm9JeBwY54FOuDsYxD3hYtB1lmCwOSqYVX+VTouBF5nkOj8OFYV0qLQpYIa0DWnpUwQPmDgzHtpBwoy+KjHHcLUFJgfYoQsgNwmPTEqQuRsyfTBLpNaoLCwWyroNuAlu8XbJXqyG1rggAKtl7TYaw9qycxF6jJfIOGsHCTaSr+6QUOBzuTrKGP7gtTJEEkDc2HbWbQ3tSevWi4WVZIGhBNOlW0xLymKRG7UniZce5Hxt1K9//esAjkB71X6GDGaj0hN4XTeHtyK670V54Z9wnki60VOeagXOC+BLrmTH5tK5XW6n2uLOj699iNo99vaxet0naPW6UTveaVHcHRsWXk6gw0DEQuWc+FjtE7RveyAdP0ZR4LFpheCo0nUBwMMASLKTo02yoE3qztCMUgC0yb333SfxfBkbfQcyDMCA7ymP/41zpYLIa3wbrUCbI8B4UdjrWpBGWayMpWihrBUdxspoDxmsseh1wwSOPMvl6IFNt8ctk5IZEl06hixRTZfjaq8bvhCQIwNuSNvQ2DmSRg0N7GAJBlBu1sdGkr/lWgkH1npWo2cx8/Wuo+Jbat9wesvRernplyAA2L399D5kD/fI7HYWT6oH5/Ouq8UZwS9iyyhh7of8z+77rMB5AXzJ1ZsTdfBvg9qvNnSfZ3v3bwc7SB0Vu7wyBIbBRndIvvWtb/kE4AxwZAdW/cEcEveEk6DuQ2Z0WpR7vrrequTjuLJACsFrMinDOcNrwowzkRSWFfCF+soAfDXKF5KsAGlMJkM+Wc1oLroWlk5pYU1cN3xG62kxrYYhNcXKG+VlFJKRkp7j+FKSAPS8BgyfS8rVtue+DsWWIx3tOmoWDU3bc2RfkZGsmaQPZpQJsYLXiOktI104okvsqPJh4Z6uNYS/C6CXD6MWWVv5NqqriBu1P7212NssPuziZPEgDNnDTkfbW9cON6olkHa1r0MhRZfYu/O/nNFpecgKnBfAQ1bpERj7Fdo+VogdAG89Wrrd7+QQ9ciG7pww2tY2uq9Kv/GNb/gQYKgfGzhjVauOlq5j470JOQYnp0uCUQkjqBwkF4DQXDozws2xmYqAgXG6kLoJ43Sb88DqBkvXzii7rpYlo4QzZs+FpcTqrm1eK886Sr8KmCgcSaukhde1JlZDa8W4C03X0mGCRVtbFDoxmpIeOSMlci0xmvLuNvcBj5KXbqILSa/VpdeWdl2jSVPIi4VCwlzV81oxA75j3EnE0m2b2VHVa8jAhsS1ge06ldooscN7f7dp27e6Ft8HWcjeb2xsHwt8O8TOyMvjyKvnIq6htjHYXAARFrd5ne1TrcB5ATzVSt7xOCTKrm1t6/fj3z4B2NmOjUOltaHtfoeHj5Pgvd4HZL83zTKHxHY3pEXI7v2IlyPHHb9DIgR3FsemiBmFYCF8navS0r3Lby8x9O0079K5mlZQo7rEeF4Ucem1Yxxk+OzaHGuHZ5SBXSowjLFN9CEM3+joYCH3SW/TrCtVYjXgW7ccrRWAIV3glS3OQxtgJ3vz2zX5FmgiHhzrzsrnossrR5aUcdSV6tpNh8xRl04oUoJnz5KRnZEYzbeWBaCWJX0F4IkQJoCFIrYxsL1HYAwFyFe2dqb6bu9xt9oB7CIwe777A8Ym9yFAF6etC+BjQc+lz6ws0/WTAL/tJqKvj7SQjsAat+hn+/4rcF4A77+GbzHY3/MW4yW9V3Jng91BIvaxPb29Nf3e7zkwdJ9zfbmvdcAcBi4Vd0McGR0wegfAOeFFJw5MduRqPaneNSoWO3ddelnSJ93RU2CEG+QKAyCGEkNZxjiO1QgAucXAZVUg6z62LdZQrV26uIRiEbRE3LKSiQJEV0SsHtikBDaZx2z0kFhTBrOYrSfAMNCRHFzWrugxhATeEt3v7BU2ugwjH6+6XAq0jsqKfXxXJdhY+OY+llUxFM+OunvQVXO70boB22lyE7EnGz88u+Ultj0jixYbGJ3RlraBiY+53m8Udy9GOAEQumBg0AqhtfMBKGh9AvCNqE+9gbFZ/6KvyZ/6+6zAZ3sB2C6zLnbkCPs6BNPQwbj6jr4qHVS+Nqt9qWWxa+s6Nj7t+v7H/nYAeje30TE4CfY0GKPdzMULDkHleBAlDIwd0hsQWl0nivBC0pmBN+RsOHtcGAlFl6/RqVamxhcJd3oHD1J3mHf67Q9lWUaanTbJ0agu39wREplorw5lj5Njud0x7v9paGCRB2hIbkZHhko+DY0LDEu+9J6ILheroctF2tYwY7Nm6QlyYWcE40LfJrkLnZFA0gsEGYzRgwivTSnPaYF5ERZ4UvRI4tEGwDB6jrLIyL66tFsGTIHUSnXL421BbnRLYp9pLQh8LUVidEOWC1hrV3iVYfHK0jQtoG0GzCgQo73KSzIqeEaOWRjt6v2F5/f8yYttD2CvouVoh4MB4GQpnCPTPvc5AIZwNyQikRWZ1asrjUYPbevAKIpW6Nq6B3CwhrQk/CiX+JdueevAv/TJfMz8bTvh2nztj/aK7e60KP32rjvA64yuTW9zA9jEdvO6We1sZ6nNDdPOhvH6YwiSF2m7C+RgCOGUGiLsjCwZZwUYUYFh5s7OUtuQ0bGMV8jprsqWxM6zGunZG0J4kNXFELw5aoNFtfqOJeMMybYhSmLilAE0qjVlxkR38rEOxIq1dFpDWhg85aaljyXfwgUwdBCBGspxRtnTRxmGVaGTFVNKK4+Z6oYBpu9Om5KuNZqMXj4rEsCoFRgMZWRNA1LQWoqtVb324kJsV/sTPxctmEudYIaEZzeL0qbbsY4Ar77Tdweo75COhqE1AWAktr0o7LYKpLtB9F6bykpEkiMXynSH7VQeuALnBfDAhTrC7DziABBjbU16O1v1J36TQenvSAMrQPaxY0CxZe11p8Lvffryx6ZHUnE3pAvpmG1F614K5w2rGurIocIwjgDSANfS2VGVGH0kHi0B0EqbApAjC72h7OObMoBc1lFDja7tClgZ6PgL0TKuyMlqNe70W3qNFmUAqIZnlEvMHnObODkUXF7jWJRgdIq2bCfiKKvXihmd+2BWY/ws8YfRXaW4AcLXsmcE9uyCZTzMK7YA9FVZadmTtg2kUVtOFSb2tt3Vewn+BLLibqsTLqYAaX9GQid0G94nXd92guG02wk2+5nCq0lB8mUEU/qRw9jqjBSjMpycm1czus/9/O8jVuC8AB6xWCu0LchCsbMdDLoj4csfdd+7v71rWxtt69vfCrrdbB9DMtrTfqO//6ejIdudL4E0iirfvIRwZmDYAZBw73WsA8aOVhqGuOfLwlGrqx3RRdLxZtQllE7vwDpXhlJqZzT8YHaOt6KsyNFXKvqIWQwmpaExHtKQ/yEiPHCt0QC6VoC0PsPcEmHIMl2WHNkbvRqlQMWKgVfGabOHiaRnyiLc+HKkFyuXQxvzIauJEs+wTbZ5BVsxo4/LKMClwSLDxJbzaOw9hJS2X8h0YHWZ7jWfiyG61j60G3npEhvb5mfxLHyz3+O2twFYxOXb9vbWz2KIMcU+7186EQhz6XFssrqkzI2e8qgVOC+ARy3XW2DbTl/bUbHLnRN13wWg7czYpt5lbHdbmQD3/u4w2NZ+79MnANsawBsWL+ekw6DtfacLQNd1YjR3VB0whHydGXaxOoEUIrc95vatd3mX8Ftz2M+8zA0lh1Fd9qvug5fbyOCFzjiE4SeZsafIHD495PBT2KedOR4YClfRsSbEvICrOxTCZaKkM06gcosn2KpPDmvcfLWtoaGiHDDxwFAmYsZhiH+SobBICSwlzuxFGXAY7a3lzUsLU1s4bb6RH1pDRCxr6IWD2HUs1lagxIITu1QLyQgQuT3QkM1J7HChbXufA9oe8IzwRnN0amxmCyUio3Dwtj2Y1olgL8lmwZdySPvsPnwFzgvg4Wv1FrKdZ/ORTqNTYY8SO7h3f0N8IIkdr2uXs1DsbC81Pg47VEbtb9dGdRzAAXBy2LWQ+B0GxopabIwUgXgRQ7plQtHFw11LWEj51KXXZS8rvrnvHlsTYLopO9PdCQeoO0aYSLQzFNUWby+UuoZiyzgAdpa6AaY9DG257gIwbINhNCmLBmIRLJ2v1EJWaIYWgC5ovuXDqEsGlq4Nn71UB3NQNv8FL26h8zIUnrIGbXRl3lh2gZ/RXGrZjSNPoVMmz8EwJgDxhLw335EzEisWoVE70BoqxITO0kRCohLL9k4Y64IhITGwd0BcFZ4FQielH4+FZ297e2p9FMDsPmiH+4FBvxIKnDQF5Ji1p3y5FTgvgC+3btu2O+w8m1Ud9+WPv/yys+3mjpD92hFyQuhaXWfJb0a7AOjKN7zWnnYfSMix8aZDjDLqOhXCOTYULcHDLoQTQvZ0tioAoDUUJl2LVnRsISmE0VCj60I0BLkq6QcY3wgDwxRlHAfPkmSBp9QeFDC0eMZ3yA0xalvMuiwzBRPX5Zs7e3chPBJSwkNCIQ3Vxsk98DDrBq6d0KOwj74SHvgHNoSUwnGX/5b68rkkzmGmjF6UlZ9eF0PKgPeRt66QLLWTDLwpkyG3dAlkQ7orW0iOghrS2nuM6jjRVdyJqdmo6n4v8o6A74L8ukS08EWxgXuIHhxxrJwO7v1UrMtDrEQ+aybpZ/vwFTgvgIev1VtIO68zxmrv6tq4truf/fbXvzYuox3czu4O0BKV3evM9rufv/M7uQezy50NO9s5cRPQO0gdCeH4QnainBZIIYgQdFS1uvTwUgrDkrFsjQKH1JK6MQSe9qrRaC65B2ZJxtdoyCzNKJeGskuSwsJdKz2WqILd8e7/gQRIjAaorYBCTTWxevDsO/Du/bRRDI02FAMwd0PTbYXZbwn85VCcfKM6hAhfCO5rrIZkSDlkskbJpXVjrzuEa0qjG5VMtGOM87DaulYsIy/JVIs9PgykQPlO0IZg4DsOyn0uNnyv86q5/Q9ge/sK9Gtf+5pMBCIlpqUDoJWDuPYwngQtvNHJYaKXzNk+agVexQVgi9hS9s26aWbfdBLqXl27AA2BJfYli42YKNm+w/nxH/9xr/8+rtqsAJDVFwy9znNhdBj8VaRv/40SF4aPDr0W6UpV9XcZYIbX5aKly7+gLM4GvbMRzPXgsIUXkcBo8WjHne82tp+6OeQdXUajkIkupaAl0Gh2lgSGhUBqdcHoRos19ixDDgyQbP4XAmlhM0eiNZ0hbxHAWitKQwJRKjQYfLrSNmphLW8w7pQWQRp0AlZKFKFZajNiLh/doo89X6PDAAxTwmWYO2MwyJGGJoEwwbQ2xiBX39FHGRiFMWkW9KGlr0gACYgCwK5r9bSkrmkCaE3EGsZjVSks9l471g7snR2VWm9/Wm0v+2GAnQunw24nDoL/ZwCXZucxUXTlhlBc7n4wRuFOkZLD5eAYlQwBNspLYpR3yDrfd4DBjAbQ5rX6viPESxx6s6teYvafMGd7sc1nF9rT9roNqo7TWWwde51ia84Rkq19bN/7vU9HQteO91eRxEGqfDP2otTxa+dt+3Hfi9wdJ0gCWWlDwkUyAoUXV/TxSoGn1KbQ4cna5btaYFZpSDvGdG3KUOEJsw4ZHXujLImpsdDHHuEY74F3/x2eiZuSvTWPisVT0PLUCmRxenYTIuShPUTUHQB94mb0RFiSFSmcZCafALqDSZkuAMLpUli0wzA5pAwy5ozpDbUg2mGmYKs9sI2RMsLXrrZowKZpA7O0vYUgkbsAfD/jNcgQAbbIjLMyBTVkxzovABbHt6Cejg1sVHFnRNjz0roASsNxgJEGX9teREhSaC51z/axK3BeAI9dsTu8/Up0bGg70kuNPW132qOMhmzctqljYPt2ThwGX/v4m3jffsJw8f/4dXNsXPs3PLywkfY9I7b2Nx0VBseGOB7C8RUanqUQczZ0CZ5VKXsWSiHWtlh5pedOn0xYdEey1412yEeJRFdulmtlYCTDRrm0rKMD6OTXPRDqkhLT0sEorYw2hYVUqg4hJkrJhC/P2AKMF6PnEiCXAXsukwy8iFqWYMNAyQKfsW5IlrGvLvRyA8tOWXWj8WgDSCCMljHwYGZoVZC0qxn3vbn9U27YdNt1kdPdDUXR6roP7HwKYRE6pfd6XXgYvw3hINjPHSUhRKQndIEg7XMb3iXBxUeH7pUyn6Cn8tgVOC+Ax67YHd5+tS9tYlvQ8ej1hM5oa/aW1O50Bry2w9vKdNtX9XcN5MLXcYI3FJsAlMhT8IyRvVPUBeAsYQBwWmAMlQMlqcvLaG0WLRmjoUZZSEOrIhNdmBkKP5bsM5py4LQC7GS1r1EM6a6WVoCFy0jdDXdvT9Hu9BtJUSyCx6E71SRCVBSjrRvAVUFSzldHL41F1xrCn0KnFHEszaXuGK8SZoSPZzDj2xB7nLW30jZlALkRCpKQttMEGh6W4ckFHtKu82rPMtdeMKO2MZ2jQN0TdEheWl5G2/kK/ZD4QKy4s9d6KEZnglx0e93Br/r7BQrk5Y+foj3lS6zAeQF8iUXbXNrxFNvU7pzX/yqOnc1YabY7ge3pjoQLwHYPwF3pZ3dD2NntckjnymlpW2vTBcITJ51CgI0GmGNASfBTgLX0ullQZZl2ha3GdKNjPCgTIswBqbsK35KZlLLADO2qm1oA+FxSRj+M9lwwUGCsrYW1nhUdy1WUAUzQg8K3NLQpxR33gzHmjDCT3ua8r//B3bzYD0HHcezxTDdlHEcZx4kyQ2OJaraWbmulJQp0yGlxIjFE4UXsUmXXTF0A7PYwscIA3R/wLHQYPG3LSOxtQ9ztfy6MBCwLJenUIFfuuRvNC5jF67+n2adeCh5RZu6UUx67AucF8NgVu8Pbmu0/m9WHU7/96csc3+bbxx0Ayr7Jt11uW8M7P779J/Zuu1/L6Gi5BvDa4o4WWuAKH6MtzkKJtpYjTszsHTMkHQYWIivCgqo0GHVHN7oD70oV+61uQwd8bLkEODAYYiHjuPLLhGS5bG8NYYt2ddmZ7hp22h52a1oZq0dxAeQLICVLxxjhyjZ6jEN4F2DPefgDN8R4wBhlbPqN9hwP7oVYqcayEtIj0QauaxaDpzQKHGZVYpMDJS+YduksCDsZryFk3G6A/bcMhIC359t+NrM9Btk618J4O9G2/SBx2rq6Cjq2Rll0iZd6FvvfT9FEAcgxNuSQXQlenlwDxMEhkEaRN3H6KY9agfMCeNRyvQF3SGw7hdgrid/k+cpXvuJXgOx1lr6ZgbGb7W/7WIn3udU//OCnXs6M7Q5jW3eo8HJ0rrjY+ozxZ9EVCCBMYDojGGn313JZu8EYeY19MHzfTGkH3LLEUKww2AYcM6qxFI69oexaPOnsY5zcxpLCXtyYO+05jruhEV4Tjl53W7V9bcEy4iH0cbxUABhn1uM4+RxcPGKYaOUAJigMoy4pHIChLEYp8cQfvjaq2kjC55vj8IzjYCiXAi86znGHiaS2NNagdC7EXm0ZWXix6NrGgYuFBEMA+Omy0MNbKLJTbt8FwTsOdrgDoqBr67IUESYwEqLr07YT50tUGDKLcznf0/KFK3BeAF+4RNcBbUrbet5cvLwQu9NGJzar3ewDrw1tx9upftjlN9hcA64EMPcEX6MCYEMF1u53B7StO0LsMPBg7IXWllm+qHSNZqRIgB4YDz22LAdwo9q8KCT8+GactgynuyqTxsF3dUkfS7GQsIzoNq/sMAnAipycG50hisliGBJIi2l5EzyqDNilTA4UtABjqbu6GEKoxa8V1GjrrAuvPchKsg6tgbAlAPC5pNQC22lrJmEi0Q6MgiR8mLqrb14TsS6YibRKLRqANdTOUPtz3/VvvpAUpXWARNVqeBCRGA2PxNFwIux8F4AXfGKr+4Qh6P7o7v4vFzAsxB3g5QkGA7amcHU6DZ3tO1bg+u5/h8NLGZodTyHSri1/2+WwYw7dmaZN1nZnsYmRQLan7UUbsYrfJrYdge1aMPvVhtZmdBOo/r7/4WvvuipscV74Yci+t7cfFLez7XKjgsJj67RQ8EPCaDPCCEHfpnRfg9In59JmjIqdrGB2kjG905sFskO+ub0twMXSzghj7iUfs1EYM200Y8zaFm28OIrIbhGGTZcYIozJWPCzzFDhjFocrfVEaDRaywWwEe1U4hJGo4TR8mYBY4m8NdfFKRY8DEWb14Gzeic6MQRG6grBkhEDhSXmwPvg5iIogIhZDm3rA0BmCMNq0Y08BazRPZ3trjJqr1IASIo2pQWk23UyLEn1mheBb1kovsnRgsXcKAtp4uICs9sG2h56W1fdFwLMuSDek/xGKQB8acwoXx+1JSwH71jyKTEAItaqrMuSfR1dLaNLLC9taQ/nYD4b5bO9AJ7qCc2ztxtItIxOhZpCXAD2qy2YUWsDBbOzOwz2qN/8adPbUvY0eyfBJgamo/Itp7bz4Kqw+zsA3HGKiKEvjuDbmm1WiYl7kHIIAKy7z+CuAQ5waCEHtg7dwq+YVUeiW5u99Ia8oRJbyUcHoFuNeHI3ncQKxKBtKQZGAQ5GN4oELOREBGDJK+Wg615K1RD/uMBMnj2pQjPqyjNAVIzDGclYKATtMKdMdxw3xL0093wB7s3b5ZRRDuvo2GOTal4wKUOSBT/OwA1hMCnroJs7BZjFbWRIRBiHotXIDmMIW4CoMEN2djAYtcPdIr3gz1IHdhbYvTmhVf3BHD1fBNHF5Qt2ymNX4LwAvmDF2uIdA61tmnCzlW1B7yl+JKV228qBtTDpHR66beptpZ3KMbAuiQcDofO1xe3+YUAyRgAHhgwzhZSVVmK1TazTGIZllPBhGFO0HaQsWrD0kolhwA9UilXbSuY4UYYHZnQKQPmsxvThKcNJO4ZimTvFkOS11pzkqCX5HtJ4R1ChcZZYaWBOel50gCz4YUTUllUu6dok2H3vbrXlQMLnDlB3tbPUzX0AY5RM+bAk8gksyQlaCJnAaFMC0BsNrKsQg6Flh9HizJJL+9kvRDQE2T7na4h7KSGksHjp0dKJM+LdH1vvVVaVF6Q22LwSQar+ZMiFO+WxK3BeAF+wYjZfp0JLdHOwEXtnb6fS25rtV1vZ3iV2p9Lv+5/+QXMvOEhsdySGbGJd7zV+qKXly6WrwgsOrz40AIMZzVcgF0Dnx5FjB9AdKUNgitFEF4ClUxpGG2y6o8S2dkOy33IZ8FWl6LUBVn1cGLNPuBXMSMxo8LqjUxqKRGFqfcbouUTOHo/uypC+WlZyevgA2PDU+iRnSJdQhCYeNH1luOzCS+9gnzTYk0JPSwkjyoFfPoZspBzxr14Dzn0lh8QmGULBQwByN0roRtvA+QbGFoAxGAwSu5oCYycbosSg3Y7H/k0aHdIoDEv4XvCdkYbwsxOE8M6Ic5c4JrwYT/kSK3BeAF+waPalzZcMVHd/C98aG9S2JnanriEHwI7s8GhtVu8p/fEXu9f83mUgeanmhK6CAAO4FUiHYY6c0MBiTbg5aWWoXdOj4yRbZruw5BK+0Vzo455S3CFMaSiw9jB66A7hwR5z0YdkwJSEV5jBs7OYipY+tKs+xtwDt2IWGRWpWEQOwJJXPEVhuUWLjW+AnhdCJEpVicWwL/nWRD5tvgf+iWUUVe24zGheuqslfOEGwAiDh13CUe1+b/0sB4DEtnKuLm1jozgTbLyKqI0BwDr0utNut8kdh15iWpzSy5cOjxxnhLqOgG459+fBzs4seLG4Z9H1TN0HpNsFzymPXYHzAviCFbPhEji700ava/PZ33Y5oe9vJ1szRyWk1u70Ay4XgMNg19qv7gC+dJxctACKPn5U+IfQXidISAcgryx3me1nmM6IilI7oznmEqZ2YCkztCKHkJJutFgFyn7ZmssBUJd9wFFNl1LosRQoe0aWjMOjO3iKmpIFle6G3sUisPCqoula2BYT7BB3JTzosTHiUbM83AjHHr5A+AthNPsoujMFeu61JVP+DWnxjH2GIpkhCoZgUc0cGYUj1eJGuY9EApB7VFpzzHJovX3bw1N5LYKdnLud7Gsc3fkxAB4iFli6Ub7wDgW7fOhZ6DDOi2Pi+1VRCAu7HLo2KCzs0vBZwT3Bd+ZyKg9fgfMC+IK1aucBzQFgITaf/e2rG3uU2IhuAsbo7ObEeVPcnQd71N6t9Nv92ABqYQiALV7p7wxoSYQptRxRbWP3b0POVd0B19VmmXC6jPLnkl4LwK4dESXfqFZY9ne33AukzTd83dEP5NnlkF0rVV32tdVdHWGGMFiAVbdiLfjqCzCYEq47xmgP7eZz/3May3hwNASvZTdqS0g1hpRagNVOT8yFY768GKeIr2ncw7cPjhOOAmwLXS5aWeUVbWzsSS7FRRJnQyGnhWGHsY0RTpfFZHUZZWU/A6BlhG+/aY2yOyx04rnEDMnuILDwdQE4X/6+spvGUCT44zTq3AG7QuDPC2Ae0KOU8wL4guWaM9Nh0HJgtK29y7sA/EaajeiXE3SdPRuUgGntZm9DfSLW5eWQELqtX2tn88LJTq9e2M376bhr8l0zYXEMkiZgVFBt6QXOWM5awiIQR9TjmIvRFG16gGlzb7RAM3SpxFArHEAu40hZJdpph5AvkoMYNQvuwVofOgv7GFOCeRZ112TQZqytezCuAHqjIia6zQJ/SpbxKvrVljG2GaWQjJdDOAOYQqJbGl1vAPZSIh9DnnJDwxaDduZiCBJhSnsOQJeEnNAUwu69e4ZY6G3gCjESCQhtP2Oe8s0ORuABpCo0tqbDjorFEH5vTio7ndEQO6Hw8iLlxOE36vflHD0t2CmPXYHzArhbsXU3r4tok3lbsUcZbVNdSBV//3P0H7TzDDFqU8A6Qm1iLzL2sSF27zJeWwJ4RQJAiBwhxc7mCEy30TPSKdy1bf0sSMIYGl/GhJGkB+NOxtdoZxJG0AHrhjTKMRlOCmSAjKPHUMtotPe+XPBk1LLrtkTaeLQixibJ8VoJB9ko3/C6VoZetrkzUsgkFoCdAm8onvIswzHyGseN5R7MRZ5CFwuVIU+/bi4sMIqUJ6vlQgB2yjf3DRh3yOwAaOkhuUhSC0PYtUVh5ItZS2wqG6ntBEZvZaICDq/lLtVSMkr2wS0Q0dX2FCDx7JG3DBEm7BQkWjufIq6Kzxct91Jib89TpIdBIKO8cMLAG2JRxA1NzjgtmqLfS30XAK8yzzdHSEcJEjkXUVhkYhQMPxeKEJSm+fCWiyRLW27Y4nw4wwtCnhfAFzwszx7CJmgf0Fkyau0wG4XQAew/J6FRG9eO9AnANiW6wJ0QSDx0Fi42XL4cCbt2wLtty4HQA9ODUfgyGtoQF5L7ob1AbYayigq5LslRlz2vsaTADBvL6Lv31mShNIqHzGg6DEWUkeFZOVcdcjAUQ8Si0QuqO0EZZ53ZwxcLZnLIMYvRjfFeuJCGBp8RhIKfi51gA7hUtJMhryT8rRYPmNEIawe8BgXTFZFSnu1ARqIoa3NEYk20YMkQjoLkasSSUQEFqgpnwcO3qj2BKEjKx5BtLw1ekN7WpVd0MMbCsVAsFC8yOQCr6UhcA7479WqvvlvS8KZD8KBV9FtqLa8WBFWxZoKn8o4VOC+AdyzONtS+pNhYde0/u83mswWTNiL7gG1Q1d8O7pMshcW+7CR0MNqm7Nv234UFiSMhEIWEiTaMXQ7AkpSYIUj6iNGDfrBwGQAlckp5NhpnOQz+LvBeU1ZH9jAFwtOodiSANoUdrOJCN1/rQ+iCxlM7DCmM2fFMoLId5lFCcixWDMD7Am//8CpLYC1w+hZgkYYg12rISNDWIvRoZjNEu0OOt2A51AoCM7ouvblkjGEwGVu0NkN4LjDV5TYYe2wTohUYI4WXlrSMXJDoTjh20qx34Jv0dLl7XgAc90d391e+Nr8c1GWOMBQYeLA1Nxa1PvtEbBkx+ATgH87qo7b3fTwFArDIAE4fJaGL5dYpf5wUIuIp71iB8wJ4x+JsQ7M7bT47zy50yO1a+9IHWPvS/rO/SXXZCYS0F70E2cGEout4hMGga2tiphNR2qkwSIhuQxOdBa3Dw7djADC7nCWe8JP2NoH7KTQ0gCIGqM1S3NiycCGjU+qOUoi6E45yAAyMEn8TaV5a0tDMZY1rKBkj/vGaIaN0Q2OhMHp2wJ5OWVnq7LFpybiEkcbYKXEWcVpPJKn8adskqOBzSY+cZQJl0RYl++h1BRqShoZnY99XgF3QpJzpOQLAa9s2UqXDgxGwfOmHi3Bys2lhsGXZ/bZlaQUQImk/QzoL6rJuF4CWiMiLkRcZ5jK0YkPVEAwjF9XcJwBfonqL8mdlLOVPEVQ4x1DddwZ9RHAYxfKm1ZRhop1wp3J1Bc4L4OqyvDHum/bNC5Gt2baz82xB+8yGqwQo3MB0e93eVfptXF/+2Ii8nA2Obff2cYcBg2AwlIS9UxqA3lZG65QKqjtDbxJdtEZrcS4jd2qHpA6Y7oijNbpAMOUW2FCWvAoxPCm14sYzGAph1MIAiGUpdvNd1TbaZI1mb7LjNQytYWBscY4ST5k01LqhtYZ8Sb5FyfGgD1s8OClawt3jiCSLGtSMGi0ofZRIdDPO0NhDakfC6FJmQcKXPLscai0mAa4FYCex8YI0lEUXYQIQp7ZYMPRalqga3WLsr0FzlYK1DlbYEVCOKcB+kZ9Q4LWGdte7DFnaz/HIhKXcnBG6Uq6gO0S+AtLS0YLBywdVZ8qy+0UMRmfNm5YWkvspD1yB8wL4goVaj4T9Zx8r5X0g7WzYx/Ycu1H70u5k6QLw+z8uAAHs3an+Niu8vQ6vhQegaBEOp9G6jYI5Zp20LLnQCaTuoZ0hyoBXBT5MrSEiRInRBdWCNbXh2XD3pc0QOwxZ2TKOywCCTRsztvCtXjwWczK5JG/dJsoK2LO7a9iR1JaqgVnMLEYngXRtOWSn39HteXJPGq2ueSEYmDUssWEenuy6EyLLtKWku0YEnlQbyjIYW47AkILGr1utpORYbvIf38k2gDYFgGIPR66Lyj5XebFVpkUhAYDZf/InfxKS17e//e3vfOc79r9rgJdfljOa6KLi1THZ4u2Cir2LRCkPgMrnAPeBd3yHqGyFANbtAnCgjLonBmCCKIVLuQtw/udiBc4L4GJJbhvsJ/veJnPaKfZxm7Ujwa9zZY/OJwBvJewdG7uWvW+EWLajs79eaWGQ2/0EjOCkMzYKkH2UugFg6gauZRlfXjlOuxveNLlrVwB3IgSRT5hOVHrgYNroVpKBvYl0f13NEEcz1WZx7IUgrQDHYV5JshtqdIJGEgNd5lkObQBPqgXHFqAQq75a2DnWUoSexzTrc/DVjVxbqhFOyxgmS91Ixj6OY4ltwPmOF8XED0ZdOWsH1lziLP9Llyxjt2LhS6np90Ljzcaz85v7xAFR/X/5l3/5m9/8Jrw9b7T9rLX5E+7yrND3ixICsThWLgy6a4D81m/9li+CWDp37FxkIofh8U5m1MuZI2ZUUKOzCFxOuboC5wVwdVmuG20p29eute16qbfn7DzbTrdS0uZrT9v38+EAo/PmGNigdicSbKQ6YqdGqzVqc5MOjCESbE0LLDEaOTaWwdTVjoUSQHuwh2HHZqiWkV4aAaSxkmScFjhm7UijukbJ6s6om705mnUzbchos4sk9xjGaziLiCHl0G4LupNnj4Qu3GphzzJRBjmEAIRdaM/Lo9fqZhm2LLop72jxgDWRYIUY4wytbGOcJaIQmGBaPFoTR9v0AegBKJEMVdGnBVPNbWbbOPd82dVrVObOV5TuAO9GdC5f+9rXvvrVr1oWG94Pco2SNpKWnZcWg7PjmKBFCFy2WuVeXEPOy/5l0m8D+LaHCzuktnmV0twEANyJEGTmcipXV+CzvQBmB7QJ9i3x5ijOzhjlEmCIsNuC1q6uHa/o28SV/g6AURZiU8LbtbasD6Qc7VEYAmPXEjB7tN1Ph6fbvnQY58QoPKr2tC6BCYABP10CjLLiRRy8Mqy7Tocdw4xWFPAjYdTFqeXIQhEXuZYFjDCSlTl+LZfItQARak1c2yj74BmDsWTHnJfuga2gw1MgMFI9GkC0RTGqWz7aJLzWdFgsHV94OnzJbLz3V05ZNYtoaz1TDHTro3hpS34ywTDJ0MeeUZvEb75byF1wMmr1yplSUG2Z5MtOCTkuYXT5GpWkNh2ePa8Uel1tK0DhYvvZDBzNSzWvFbqvVvgahYFs78mfYpRiyNu6r2uM6trDfVNquwqh9S0NI3cYYPeEL3CAjQrR1/2+6iklvkhkwuITwHe/+92f+Imf8KNga14sD4KCEwO9EL4vwo9B29Jh0L2UVu+qHRUxWZjcb4Ev3V+c5bO9AL7Ek/CwL580Y3a7rfOgOFYf26AC2St2IbHt7Fdb2XbXjU0LUKVABb9TboeTOD/a7JADQM5eO6MRYnNgyOZ/7wvZlAMXRTs5pIRpdIaKktHBk1LZ7nO6e/vLEXn8Kel4KCs/vcSCTTh2nONLASt6y7WeOqM5ppTAtIWboBTCfbzGkr250Au6Ldy+dFyG8zLQWMASYI54ctfNzjI8KVkO9oNxRlOEK2LtgHV7vtvwfUVL0YIlk0DGcitP7jHYNuzwtZRW3talqMsA3Am8lvvY88qu5hpFAuACUIitAwWD+u6bH6fgW9/6lv8JklvBdkLLPUI6mJPCUkF3oFwGc3bKHCG7Fl5l99PgqCTAC4aCGYnkYWxdYsjpY+QIU5KUU66uwHkBXFmWNs3sbwpRFr2/2JE2mc1K6Ha8LVgRr8TYo6TX/3Y831EE03Vm7F1exMbVZYfR2rV1A2gJlwAdhg4kOxctEi4rBphk0YJ1GMbOyIWRpBcUwHTSO6UOqnBgGQ8TKWde8RRLd2AsurUpuYwdbV61RqMar6bJnrCPrBY6RwIPcIfe/6OLvNLGIKIVAys0lwBDW26NpofRWhMWQ8AYGi10JPQxsuzx7yzxs6Q0r5izcMxXlzLI9IJuiPsLIC8MWYqlZSHxG4pnc9vF04xfL7BuipYMbZNVWy2dct9GRdt+o4SUmFPQ5mf02Vf1dweo19/4xjf8JMBxAOiC4cIdWLe3dREdK7vOFdJrk1iGIJVyf3LPlx2JzwG+AqrEMwLwFbGPGhjgjTqVTp/ZAdRSTrm1AucFcLcynYdapnUDZbTRbTI7zz7T2nY2nyF2SufTIbF9fVnpXYbSBm00woKNCwWmIYfWKAslWvpIGGAhnB9n0pCulBqqy5eRMGYXPYt2nVdGeI4VxCwOW766AglXVjCUMLWx4c8+LWUEkq4tGXo8hQgWm/UUi11QllZD2+qF0Q5zytAOFRey4mGG0GR14+SSPUBUtYZg6NMdBYNR3UmsiK0/+ySZwnKQUq0tVXqJQc5o+rCxr6O6DbVoeZUJi6HWOd1o/NrmRSGRAHPsWRtt/cXKqGuzEV0u2bWOAMdZJRaxwPrGX1cRdw2oxewC2VdOhAItMeIC0DVEqumo1G4wlj3g/3EluADERVXrDvjhH/5h7naL6J01x42XPEXphGph5NB02E+5tQLnBfBmZewYu0r7xnSvtZlsrPaW7WVH2qm2nVOhy1HXtma3fW1NLW94mzW8IYKKi63ZCcxSaPhJYCylwN7odFkysgATCs6DPcylcSz5arPIHMl042QhUZVAXoXOYpTxYNHNa4asRsbCDWcXQIGqQQGsT5zDoJtkoVMCUyoE0a4uFny8RMkl8ju6i/9EogWLX4uHL4kwzDBTDGnZKdpi0SkTgX2V8PmuKcHkEpVuyuBZ4BlJyEiGvG6A1tbrS+B8uZPwgc2LhR6gSlryMaRXgrMAtxoW36/rqMiU6jsApFOgRnsrUuJ9dJ7jI5AbYsvg/iOmoUYREni+FL4OlxvFZWAKjNLrnsBsSA5i8V1PHAz7Ke9YgfMCuLI4HZjOia1pG9mCNpadR7z70G1Nyr5dtwYAzB3QW0mvJHlpbU12pwJbXeThWegAkwd7Q9iKrmt0N28lIHxKXgGyaAdvFIN2BUdVXMmUT+SMMgEOEw+dVFjTYQhHSEkyDrJA2jIPXxstL+BGRwFAmO/Ovf1UkAQYEt1IWCi645iF7+QZcsXTpyuBXDzKlGkpRPQUUfZcti53+ac0WjvJXw5lGQA2wqidRZis9sFtNEst38B5aVPigUkYKYHp9mSWRtkJ3fo0HUoFVFcmRuFHINPjXNlKUsvF6s0DRUL3FZByTJDz6p6g6CrinZ1a/E1BAr12SCmLIeTseHCWGwZXiwvDxwIAoZFLj4vQXQNzQkVkuZxXkzrbWYHzArhbinbS7PusuvYQ3S60axX9vmS0z+xCrV3YLoexEe1RB8D3lW0+G9QoElvZkP3dISkKnRhCzn09gVHlAjCnAgxJZyPfqGBkwk5YiFFe48jONxmjuHOAMeRyiWRHmNf4ZtHCjzF+xhFDjY6lKNqJGCZA+WtnmjN9APy1M5G65bzqAQZGEUVQsubDnm/IlTyXcgtmdIpR+EavMgAbrQ226lm0eNiHLaWWnYTRynwdHZeJHl6X0GsHhsFK6tqcqCyvLok/WAy14wgMVvRoDfGyOZ0IC2KH606hj1DLxWixIlG+7TeHCLihaBEWQnfcZejCAOPVSxVHoutWABO3i4RisjCExakEo0CibSJne2sFzgvg1src2duRNqK92/uFtn3WPnYq2u72pbrvgPVxlT8vQpnztgbLK/45WgCdwFw6EjCE3agoWrQ2PWNHK52x0wiZXcsYYe4709Yg4dUFUKyMXAzRKWS88GRc2xjgc5lAlFJqKDsLpaKDOQUbAdMFaF5gOWYPU7vao9XGEAADzOqSjn+C5sJOETT8MKes8w1ZOGs1/CGzw+jSM067riFjyTAOIPeGMmaZNqOCO+TFYmdJ19JbYS2RZ7FMnE4wFHfcPX0bpj1gXxWxTCDJkNMLh7k0xlIOWivG6Oe0IiaMLHS+HCWgRgvECBxP4SYlxqRs2WXY2z0GXXZzoehGAkBpLimdU8ez0EKccmsFXt0FYHutazE7j5FOANrl9LavnUTsM0NaAtA+phCj3Fl8PrVB6bbj2JGgauPu8G3jwrBPMnRilCNjuu1rr0OyD54+XrHVFR2tQJ1nxuwcOxXAaDs8jO4wE6FwJKUNIygSdjqMVpfENpwp7JAkADC7KHXFrRsnXUSjuoSS77jwypElX/iM4fGzN1SsdDzRalnSGfE01KxR6QJYolklzNknNC9StwTCZKktbjDhGLW6+NMpZZtlln2j3gUDJAEIk2JwJiv6LKk9BlwsmMDacmNvaAiLmBGJ+SqLgsLrYo680Lw8a9VZqbUTdGGIQCww6dwpzR3PvorbV0CM0rP5gb39YLCjkBCjhFKeQvgSH9g9kZ1Fl45k99hOCqOgEpY/Ti9VWcD6yTB3+cevBYbEUEqGcNKlIe6+3tsDHYFf11D31cqruwC+xJO2V+w8u8qW0ibtKmx2nsNmn9mptindkP1nO0JqO4R0+2+8ONJrU8Bi081FN2HBQ0eCWVsmZdWQuLykoUsa4siuKzQl6Sh2GLjkhXyiNMSLhdwlcfGfq0N8A1IwF3pcWegrpi57bHml15qI0ew5sh9yYx+pfqENM/ZI2KOlJFbjXr3+3xgm89wz5rDqQwEWsvzpwXbz3VAAdl7ZR1m7GWNuPXPJUjv4Mc5+49KGac8o9DAYTLxKrbUxtCwUo0Vpxew3lvi1rWpdAKJM93NdX7wIwYLcQaCAmT73DbcL/t429IAJC5jQAfgmLIQvjBx4uVp0/Su8/hzM7wK5CTgCh2zDN1Nz5MJilEsthXBJOdtW4LwA3uyE2SizS1jaWPaTjW6La+k2JTtxHvK3QX3n6A7gAmCbIjFqW9ugjFy0ZMg50pFkMRRYN8XZILkzYrO/5cClja4lhojQCKVhVCxnQKp0yWCboy4KIylzQ2RL6/73VQzVjfbN6txr7GU+LXyDlEazaJEHo083vdZoCUw+MehStOZiBcLE1pA8AQiGmI0mjJYlQNVhouwed16MI/FoS4OCs3ayDQwwFsowrEpsLJSWusTCMJJbvoNJAQNO107osTR6gBltY8hWAqQFaekkY1/ZKvYM6a1FlxcAZLBC6K6xttR3ETEXG4y4A2w5gtzv6vT9OyCq2OAN2YfCCcrXkyXs7XAKARaRAJcPTjy6PmFg9pdl/oTYZeACyN1ceNntyJ2OZuRndRzxlCRmbHhq91DXn91M9pUob57uK5nwrWm2RYwedok9ZJ/ZTPaW1l53nGDarLo2n51nF9p59j17YBg72xDF9t2P4fYyq0smEHdDvNrxpUG3caOlM3LpGMtnJ9gY+JLYKHHqcimuBGQot06drrmwyBAbPOaQvMqhZAwljGNnCdYQndzhdqpDVxqltwM3JAuRBkGbPS/tHmpbh+zb3PZywFFWZmEoXddQofMqSYBcTNNCNQSWMrQp7CmHNvtkyLdAYMi1sYm1DrEHG3C0XGZGg4eJZCyU8EPLkp69fLLkW8TWIX1CU0xfm53X1MHhoVjSmWb7AR5hQi/QSss4kjtwp8Cm8t5TUN/zqNfIjcJr21cysRWV7373nyOxA0sPBglMIdrqjGq9FglOSO4OGlhzbOnoLIYQIsFPdJHPLKJtOowpr7w9L4C7DdCGmM3NOluE0fZK6PZZW5bFvtQ6Cfal3UnsOfvP+4j9igQ4Hm0KBvZaChgxhErLvuH21yK+AYRgUdQIY77h2Qth37uivIjBOHjdRlowJGBIdoLtAognX6MEZ8KoW1us+LPs2DdgLuwJPcd7wx0PuwkaisfSpRROe5g495Un932RtkpaAlr2A7IhSIQmS7EOXLQkHkOkfIYqNgCSMS/dkALtg1tzGZSRV5ioIslltYyvoRYhxzATJXftpF2IsV8qA0iJH4yClghXRHp2Q7aBzWCOdFtlX6ftYl4xdKMJZKunS/Eo7Xy12N9n8fW1jAvA6zm7PwN2EBwHOrDHIZC442JUgWY0OrlF6/hQgIXGT5wmRtk2JFW/a6fFII2eNZcw+bLzciIEkpsQ2bXNDv8pVuC8AK5sg9kl9oqtA2E/VT0pObSrAIhtba/3+z/OA/c2Zb7wYWzlmLUT1RB9Cg2dF/KxR8VOkQN7QzFAEsxGiRPoDnAbOZMOiRcxzA6GkzB3Esc+9ceglU9VoPTi1655DjjFULLaDy7xgM3sTI1x7A2tXZYIGVu9ophaXfYseWlHOB7cLUsVxxLty7M1zXSicM+rdtiEg9SFnEwC185oVIe2JGsjmYgUloy1WYDrjtdgWGw83TDjdQiqC5CxyhtVloYqxFGxoDWRxLZpYxhtytkjoQfWslhJVKIQtVjFt8Gq6V7YXQYOgvWPkG9bFy3hwi5cJ8LTYRSUAhk5PAARzpZGXnSnzFnzRdCP/MiPCCQHjrzMEUBW3LNgsPMZm462ddCu+hhfp3JeAHfPvT3RXp+twGhvtdd7v7bFiY3FSCBtYgfAi4bWzrYj7TxefG1oYhPb7oRuO3IpCkCYQjAaYnEYqlzwgWOjGypoh6G93nFil4OiryuiQ6LFtmW5CxJ4nEiS0she9Mlt4mbHw5LkNfoMUS7BYPjXQ1i4wPAUIh+YYR4jZRisKh1yGHRDUsY3IxjFMlIMIb9fhu0CGC+YVSYur/QybNEK4flSeMVDgZw2tpDBtFcjMuaVey4s48veLGIY5pRpwQCmmx5JxgCFY6E0u1bGKEtilQgLWEFr62oNkdXRQeDb9nYHcPcTWkvkc4Dj0ImweiRk/Bg8GsLOUhR6iekyEszBBPX4JGAPgLkD+v9E2urZuTTqbDqnnUERuzbQGk32GdxN4d72qv97XgBf8PjtMPuptxvby0tHP++yOyv0dqRtai9ScPkFNTvP9lV/dRkdD29DAHNyJmTHCZjSJs4CCU8wdyrauBztb7rovLgYFQKSRZRClJJRqcrZEF0+UemS6ik7HW1xtdGyGEoAiq6dzBuariGW6R6UFdxkZTIYOmFnWUkKmlEOAGAAdG3JrG2+2pRx9AS5JM2OVw8Lhh1eG14Iyohui0nhBdm65VWghsZlVWIGoIweAEOETcEoe23k2RnrFuUyFpdBriSt5wxRjJJ2VDy6yENSitUS6WYpW+4jTUcLYG0JTptcXQa2+YmN5y8lfQx1K8we3uNvTVTlEAlHdpbCbbEXGUejMAi969jzeKBig/FonA4b3mk16vqRCYChaCHpg8/4ytvzArjbAHaPo25/tGPoNorNzW4buQPgWIyyEF37jMU+s/X9foJNCdYHBTwVDhtR5VWatYxcYNBybLt3DHQTeDy+utEGsN0ZxeWoJUKjMtqbF7b+nXTkTi8jPJ0dkgWS5DXHWzgWrTwpSbR0CgmzdkuyFicMdylZEG1sEo5TwuzSgBzjZHIXcs9QVsXaw97FzRJnsZoRTL6ixMadhV4yWlLaJWaodUvBUFbIrVXuAMPMd+LSDRG+xLPG2ZbIUSx2PCEPJD273C0CJF30MuSSNNl0Q0jAtITRKF96RhY8jCSX2tWy4jk2xGtj3F+xx9FQYJZWuDzpZppLcSF1G6UAsMuWWApgLYvWKcBmrXwkdTQsgv0cBsAWtcNdEv6vL9VoABZHSW7tc+4Ii2iUomtXw9PB+tJVVxosvLjoCg1WOF0vZC4hB9Co0FpgLQbtpbADmF0TSTfBS+TnYTkvgLvnONuiHaCbxfZKbF9DtkKv0rZj28J5YCG6ADar3Ua37expXdvdKBIMtikFzA7DTxF+DhUveOB2vCGA4vKyrYk9DR8SM4APJS4A/w8mo7r9qlxnySbGNju1cGs7Q6M06+mOsi3HLizDQEkYDTZUwkLLWctewhaKDr9yjj4MV5UVlo5tjPgTy0IEJQIVGqxuoctzfA/56AauzAGTqCLnqGtqIprpBFrz4RI/DGQwSHZPlhF4jTvJrMoWeA99QDKusFt6T4HvuOfIvvHuwrdRLUOJyc1MN7f9SdlUhiBzYcRA7D0wLiyVXQW9HWiOBABMOVap26gx8DKqdTdwtD5ai+NAtaqlQZcJF2AHCkOv9sC2tKGMAJByAJOkiHgIwnKmEABIFkIn6Wd7XgB3e6D90c6g24VaW8eGq+y2WQHs3YZSbE17kdiXdp6u3Um3v219PESMNrrzAKOLARV+5FpdwlHhRqXtzJRP21oCBFtHqMqu+vs/JZGf/umfNuoYAItLEAq6bnFsETKOsgJK7GCpuyf4pvTsTFtzebokwCh0QxI2L9JylRK2YqXQUY2+KuxX80HbEDCd5NVaiWJURMJdJgDxBKstw3gAUhhD1p3RLcZOoo0ZEk9UhySz8yVgrQbjzrG5tw0OXms32iEvK12Ea3qrC31Gw9cdkgN4eMCIrHpS7LnLlm85pxcC2KvMLIK59O2ozWz9bV37EBW7F3CfA1iA9yDbUyYs3pAoNi1M56INLBBfulHh7PP28xzDrgTuxGcImQgaGF5QvoE7ki1++ZdDswM+5a0C8ZqXw/5oc2htpro2iv1kh9lPib3FYqHsOUjbWrG2xe1Rexqeo9FxpzMmbc02Kwt3WxMtjB2v27HpDmAxykWbQudrT3fw6Hz9uoUfuPnlH9GJT77+QXY/InP9mAUXRws/8lpKovv+ggqJQIRyz739twlaB9maS8sSvrh55aiFj2raYLfaqDhiJrpWyZqoRC0ao7WypBiQt8KDz2Xy0S2TwrE3VJsRYDDwmCtq2ct/sl2RYOwsvAawMo+RgifftV0Bw8yI5NAd5PADNDsKkYwWTAszso3tYsgyWkOZGA1vZJiDtW+NkllnjyDmnjgSHwuILc1iCCFysLwcHD8nQNizc9BgOgWQEiCSt6vtZxEZdYVD6BeBiP3vSHJHYggtjLio7HwWXt0QdBijie7M6DUr5wVw9/RtDrvN5mgnsdqpts6+CbevNW0yXWLDgdlkjPur//ZP1FJsXKNg8dh/qKrXseXCd7os8HZtUQzRHZX2sSGxiEBkmIFLw+uP6o/EQfI2JAfnhKIrGS5t+maIfITlSxwA7mYUW+2sVfb4mz7+8JODrqHV/X30ZmehmohFsFAtiyGBrEDpaUlGEVthlqLLqgyHKvvutDVNquRnSYGHIWTlqbk3VFspxKkrEEdUeIpy2bZEw0BJn6woGGopFda6IRtl2V3fqv6MLVc5aEuYoqQ2KRY7bZZrxSBsChRvG3RinQmY9fcUuDPqikVQOQg+p9qWuQMgJ7ocfWPZPndzF5q7TAh3MKMOkSOGwVBnzVb3rHvrgoQBpsxqS4BwF71T2UIJ2tCW3Cke0LkIswKzM+wzxvauTUkGQ2fX2lU2k2PT63/vOCwber9InAc7EhXB3PFo3+tWsLQOkv1NHAYkFF4AvLCJq42BXRcGiXKj+v/Yj/2YtjSU/gSPBBwneUJO5jM7FvrYH6jgnHy4lBXj6h6gbMeuSy86fN0sg2mU+yGxCAe2KqgsCIGxjIn5WkAkolDWh2JB2HlpuXCcPHXpCZ0IlKKFRzu+U0fgyyc8wphzqQUAK8nww5PXOqP0SKZlpGvDj1cTaWhI6h7wXJLh55sMUm6WC+x+5G6VuEh+wABNR2ubze6CUZH9xAshsBaSkWBwUlRh5VuXIy+jYXTtf3UcgMUZMYqhuCz2MHdrLj0HjSO80Fl6vvCePmMTxMArfnjMDstYwhhNOdvzArjbA7MnbBrCalfZOjaQfdkGCgppk2ntOXvXvvcRtbrAaFPakQHavm1oBQgbO/K2bNvdqbCniSPUXUJ3MMBw0rXtaXj8fCm+NlX6tXQYmSQc16DA3HmRST59LHfzv/9Pc7/vvfkvKuT1B8NyYDOUQF6GMBTDDI3yJtLDNKFNzephkFvpWQqVgtGQBaGUhlFDHqiV5GhIt9GJdp/4XfVHC8kYP0ckdCRcDDWq1QXDVg4wyTAH0N6PbP/NccWkj33W6hIzFjyjp2RZ7fRmMUaKVAm7hSKSF9fOaYnYdbXEEIlEiLH3Wt1+BoC0gS0+2jksvOBZ2sBGrTzLsCGkMzpHrTBaxj3y3cpLiZQnBjpMD1fEueO5oCqrkjEqFiQX5NFqT1lX4LwA3qyGDaTT5qPYNLZOhdvG0gUg29HZD4+9Zf+17201LkZt5Q5SMI4V+qnLHSddAoPftuauJLlIYkPFyyh7+YhO5OMbVS5KP0U4Cbg2+nTMC2fI7dTeF0d2sqW+1ItVD1Ar3NodHX7yYQymFXEwlEnY0BbvPuJV2hmNcO2O5aqj0SYoXMvI4nEkigUFQMJWQ0ssMioLyAVAV1uSfAEmehGzBDCEp0DDUCwAgbTwzR3byHAaZZwu5GAOyjuGDshhu2pvtKwmOmOzlrBAMrcOxFy8ncxenQXEbOKBmx0GgtCPnVoTXTz2oZ1vK85CwSAsNB6rJ0rLBbPTbE38huz/XtULZ4gSAKZlYbH5S3uCOjIeSotAIfDYiOgS68FFCDZKLq+8fev0fn5r4WH3vG2dnv2tOQLYUto5gflq7Sdb2e4k6vLspzknXAAw28f2HDsq3QmKxMbN4rxR8NipPl7wVfcB+NqsHH1h6o9oiEAY7GNDwLkI5Ox1DL773e8a5aUVFC0pf2lIW1c4On56+eiOZXNYBGCGVhd2OYy7xDjNNAXiVTjRTUHLHT4BBtAy8op5bQ1BThsyF1RDwi4K4ctuTbKMIxfrEzOdok2RlYVSoUqPOy9SqrXwuWhbN76iW14AD6uIpk8RyJoQQzCtf6nuNNv0GypQbckASIMFZkbTtWH4EsjCtdqNssAEsBqUIWePFjIxSmEsK238CM3LNI0iJGakZbchDWG25WY9S8bE7T12PE2/iQBDomIvGUo5C0HHzJelfOjSgO+5cGk9wdInZxZSrB69A8JS8n7fwdsPX8IIwBGzJJ1Wj1tor0o+LmPwYT3awyqVsBaY1IVsYXMZzGemfOYXwMOf1jz4FJvJHk1sd5upLcVuQ9jH9lC72Q4mjDYf/Gxr+96ey26okm1LVVm4GJWecBUm3+D3LuN3On/qp37qq1/9qj0NZov7xR4YzKL3O3Mcgf0Ajb0NuubP0t6N31BZtRq6JD3AtJTOJ0C0LKME27039zi1YaQ6XhQ8WkMJkngsEct0M9ayD0MYXbLiW2pGSxGeXl2oq5VSWaVrC9fUJjQ72QLc53lIxihLXuJ63B6ZnZBRt2TEimEPe9fw5Ri/lkSeUZd7Xlv4RfJnGHwLWxrsfEcfGHBDW6S3Zewp+I1jQFsyVo94LgBNk51OmmkpdRbsSStAt/2IkqoQI/Q4kLQ4xedelNZtYrFDNhoAv4XtvODfstn/xzUwhD45w5QbiyHZ5sXokDJKWDgplZ6bjBFD6Q3t2yv0qnvnBXD3+NtkdpW+jTLbvervJYJ4BzRkk9mv8O3a2YJc2mf2pSG7UHXG1ptj+5XdaOQsNi6YbepVhcBjENE7/o/+6I/2+UBEIfCIyNEZ4wjp7HFhl5jbpa2PvxAw8CRHXSKc7iqMumuLZwXQx7JR7JKLxOoCkCHPqMtIX9lYVsK1C1l3dckyDLoJi0phduXQNBuqRtBLIzZdyz6+3BsdZopR7WEWK8zQkNAVGsKrHDy48tEWlGI0PX5eCTsqxsC1xZqWsXC1opDhyReGskqzqGWPjbJa6KVh1GZL7CuBWr0ctSwETOgW3JTVVtuPtG9tYKPctRYB8xprEogTpsnqlgP+LGhlgiEqo+Ni23MUiFGGdVsfaWRnFEt6CLWlIROEhiRPSg/tKbMC5wVwtxT2k+1C9Nvxtott19axh+q27cBsRGLz2YIUew5ytrv9117kaEP3hWmbEoPK7mNsR646jgcnd8pv/uZv0tECAE+hV+WFMOTg+bjALq4z0/6278uqOwBVW98UJitTK8o8ft2MY0kZWIAw8axti2ZeCTALgDZL5UOX5MgyIVLYD0rhahsdDGM6HiHKsyRrTT9lguquEgOSeIoCMEpgqxrGAhrSEhajWuS69ElDF4wESNdGcjDKPHvtgMES9nxnyNMUVFfEmWOwMKtjlgmhSweopUiA0Rxtxd5s8CvBMYM1HcielzYv+5Nub8NQpISBL0FY5S0cgFEhdCn2M4VEha1utOIC9PMzYLu6DOkyQYLfbucrAcY94N2/QcQeuIgl7+yYlxl5SQJ2cJCgMioiKfrZnhfA3R6wq2yj2Ultpjbf7Bujtk5DNiKxw7T2/b6ptnMFrLVTtTjtPCdE7WbvSmBsLwLw9Q2maq6mY7BTYVwAvvb59V//9XYto63s9/11CS9BeXGhy94XQXY5WiG0wuEvAWx0CZOrm760a1GVw9VTEYk2mHa1yGSoZohFGrrNVys9xzUGo+PFQiLXGtJtdB95K1bI1jyXMMh1LVHuwYoiDQo5sMGLMiQrIBecSWsLSegeCrCyZTpaYHZIbEIY0i1W3YkbDwBlAClFb8VYmn60wGoiIwxhbLRu7RpxmHMPMMZ4DKEl5qK1nuZiQ2rhWcJTdE2NUtxm3bJY7R4rsMwJcJkESNfallHBrFMDKx9xbWnJEEYwdo50FoFKTHRLkR0PIwFmlwkXeIpwXQAOi27SpHgF055yXgBv9sCck/bc/bbZ3j5YBtfms+fsPK8tdh5LGAxgdljb14ZDYihAB6lR+9KRU/qV8io4jF2uRds7vo3u5vDzK7vZZwgvNUYNeVFyUOmdBAnoCgTpiyM/JBAIxkcEUYSDJOUmvVHSdUfWOaavjjvN3QXAxZqwaOkzNErkRaeDJeYC3yJYpSQGsHFnKYEhn6HsdadFnm4dkFvbe+7tdZXgGYlh+KeLBKaup6Bb1WNhR0tB64ESQ9osjEbjZ+GonYTjrGUs1cCHlhcZKqPwBSo3gTIOSS5a9rWd6ANoFNvKb/PYUe1ku4XeBMFILmIR3TjpFtlQ3djoLDvwrf0Qg9ZzNwqMnzRxXkUBMGQb98EXP3vg4u5Lvn2/lMDn0ueGplB0nD0Xp4lvjvS6RoVGAhzJK2/PC+BuA7Qt7Iw2jdqq4Nq1FNIGspnaxMBqimNDuNivBAagDQqAhxEDOy+bviGOlW/nzZt+ZZoxmGwiofD1l+7+2ov4yghGWe+2wIZcYmDOsCFdmK985StcRMdsrxMfDrR3k7wvE7owY9yBd5jAq8sKy3F8c+zgMRJ6RpPVpbNYCo5ylqfZ7cCtYQQwSofPUZu9WBHS647v2FkqKAUqFpI4W/OSyaJFtcY6dEtAqoPJEomnhkEsXkMb52QY4SFDYPaSjFl3ZBiKpQtPCsRojsSzZuTVNCmQJB5K7kM73cEYYhx3bGooo9a2tJ8jEQuMDCcLvXaGthSXeaHNpSj0UexP7laVIOngsLDngoe9zUx3HDbqXVrJ2jg5ElTStsM7RKJ3iFrkji2jEOzazm8MEjvFCpwXwN02sNNsKR37o02zFf79p1JtoPaQvXW3K+/fZbgAQALwtbM7JEhcIV7htYbUbnbC3cYFs3cTRuB2ZwCZsPD1zY+a7h/7xOw1py+LHBJBZQJGJzjdFoyRI4lZteLInsCTdEiKUXI4WiwNaeF1xyvfjWW3I9n87z8HZAxjqK6J4GeUp4mH103Jt9Ecb7VbyPuySLGku+HOiEcgHXMXJZEDKRa7UV1tlkmAcmnxOMpN8skWaf9zpzhLwKR6ZDDxlH++Wi4sWrAURhJs2rHgCbalvieva9SMWkBULSkjQPzDc6nErA3JhV62DW1hdimQFpJBRADTbPotbLNgiS2G2kKzzxA7ka0hhBQnhdj87CzYdA9xc7f+RmF2vrtNC9n6UNgBtH1wseGdQWwAPTvnjkVQwkIoe0bHxcf2auXzvwAOG0jXJuh50yntb63dRrK0QTsD257d318MUWAcRQXdb2f6AgeGHb6KwGJ/s6jIvrfxRSS9j6jsItqUhuxd3QQhO8tsbrpACG1iuxbM25mXeiIcCxIRwRJGmFJyEhD2zRKLfS8B/E2NF2ZGMOF0mz4FLGRKbXatoEiSyRMnKQdDuetmj5+v9FiMIjEakj2ZNHK/i7E/pjW3OI0iYbc48IzIh5C9QFm0AWDEqhsAEg+jpRi77tiRJ2PhKHlxSauq29QwEPjAMbNwSQxZdvwUdg8rcBG1m/8u6UYLUdfTbwqYiSjsMchBN9rAWsKIr+gUgIwULkQ3tg29714RJWmIV76RrDx04Ni0Ixl1+Wp180rHLH/rhhC/kl0IdkgyLkYdLvNtUgCSNDpitEMhVUO6Xv+/853vOFOFFqV5gTl93qKEZtHlUlaOj0A4Cx25IUKv3fO6S4yecdL4bJTP/wJ44KPaHv5yTtpDtex25GxT+4mwqKG2MgUMxv7r8IjIYu+S2WFG6ba11q7l66OrAk3h1RASOgG2j+1dOxiJEMCQAOwJF0hUkoE3BODfR/QpgV1iukYlA0koMJTy7IBlLLcdtcGuSiEwGI2HEptuUpTc4x9OALo2OyUe7UTPWKBIVsIshxbAUjMOPwVDK6Pdn9X2nYO48ZeSLimlSLL0xOnqBR5SRAoS0rNGyx65IQzDVrcotaUnOkxstZMz2NhLMpfaRuNPn4kAsIzLkFwqE4vSpDjGaVJNJ7aSDAbZ8halQPSk7mWsRg92xTcLwuLq4p8Q2MqkLa0LlkA6BV1O3CnEUHXc25V/UtQFwGLUkUnhwnh/XO7+23QEOqT3arvnBXD36O0Je87ebffYYW0ZXUMVX7vHnrNlIdVuRdnmc3hgsFBU6mpu7rZg7vs+384SEQKsH/96eaGzQGoF4t6R8Omhf+0HQ99yem2kuxUip0MK2m6WIXLuI4bkWXrA+AkLL9my0OuyB9DeOgmBG92Ztka3qRmdoXeQwBSXksu02bFNoKJEO+2EBksv3PBgsCBlNWyNwrf+40iBKSs8FrZCQzdk6ay5NrYSY6fM2oqlC0+a1BCKxVKsfENmpIePkD7SkO5g6Ph1mxEXltoUQ/FMy36Q2EoPzEwJTBuGwkikLdasYTNlzB0g5IF8jAGmG4yvtaWLXlyEMQu0rd2+enQLnhjNJSoALiSk1mi/78DL511do44npTtgm8y+sYHDGyVOnDRYyu2Vt+cFcLcB7FFiW9hG9hDpAmjPtZnopENoG9mpXGzoPl2y99INg4edF4ANajfP1qfwdX+4PLpXgAmko9i+9+bi93n8axByYAQTC1s7GBKMi0AACIWQcJYOjJY9KXmjjHxrGcOwZCyHFQZAGo0kyxBShB4j32gHnO9lm4t28GFYKCQGLX34A+dlaoMRVxdSWz4sFsQjsFDBrNUaLk4tFy0vUtweHEcrb9m1az45HhJjLE9sRKyCTmLlxghZG14XPkvMA6gbTCu9qzDZDhUXOpg2Gc6GtEaJDFufZi0H8804ybMgafo5xhaDIUptlgMm8NoC61oTIQhl1pweG0vLTulBcJkodKOOjxPhTej/Z+9emi3Lkqved24fUSpAhV5g4v0wYYDRwfj+bYxHByRQIalUVZKgdY0OZve31v+cETP3ORGZWaCL6uzwhqdP9+HDfc7la629d0Rmuk3A2Pr3DnB38BCfnBACxy+Kgafbp6kQ/SpO4OsL4GUMmk5TaDT39Pd47XcYf8Gm8TI9PY5NFaRHP39RfgPntjFqpIHuOUJb5oRpgjnVVuKGX/9hiTwm2J/69m8CG3fvCRrmumnu20YhDDyQWkXYXRG/QnrjwSYEEL9ce2yb3zr6NQ82PJJlbS/VailaA8E4l36XfXmO6y0/wCndpUI5IxlyywHgz/SQnITdrhkOwVn1qg6jGZhaopF01dgdZjCJO8MVKkTz7DxjQ8JfaGcFlrOiLdOVZiclBs7mh0l4GPO3XAhygBnhS8lOXzN0/z5ps6K2Ob/Z5hTlsR37cgIxNELZdAZYpefJP82InKHQljVQoRjoSlRaXdV5tLTDhCeupjsCjLh3ADjZviVLqYr7kbg3afevn0Pb2l4Au1haenL5+gL4NABNoVlJ3AzE10nfNP0gk9PoGEGf300bfG+FHsSGzyyi290CYzS7l5pjGI/v/uSAn1MJKWDAPJZG1md/nPxmXS33AyRy2rNMA0hGiJNTLqNaGgOm9cxILCtEs1UkOWlsdDIY48HO8zkdIX1mXWVeP8Wf/khea778FLMGzhLS+Xmmg93E1ye7hcriacstO5PeAR1y10UUgwM/nXIdmlAHgmdFw1eUPpfsCXwYtGya8MRzpkvhfJCQc1pKD3nui3PXGmbVZ5xObC3pNujRyWmuCCq2SW7CAQwSpJBD4ywXBvl4LMlC7ErPeOikXcC3i2pZ8qfhhbLVravAhfSssdpzXzCW6yikaBjAc//+f6T+yNNfSrePOw7Akrimqrztcw0/lfH1BfByuRsIU0WMiAHtIWLJNjcMc9OomTMj2EdLTxCTJ72RbbJ7cPAQWWrwsCFNpE8rJhIJv0SAhA2mliEW5TS1qrBVr1EMeMB4NEOa+8jhZWlJlNaMrOUKRULD0yqK0pMBHoxy08CMaBkkNikt6aWfNqeseQKHZKMVJTwIyZBjY4DRYAFKLJffydCORfQ02JAX6S2WpZTuoBhyS2djgLEUqmJOGkFXwXUBi6fEaOnSi0rhIfFIPz2cyTaeQfMvSwpP08Uf/836qCABVCn9Mfy6KQx20XTB6B9/Wi47EcLzOaqiKxFs4G0TAFuwjtRGeEIqJ9QGMzTmBnEXkHKB27u7A544fBoDEfWBifZxjaEEZ3ivAb8ObXec2TXzVX99AbzMgInZqF0z9SoeqW4VoyZKd+MZNc9x4jXAD9vtRG/COM00CRAGW98AGCZ4mGBoSQPqzpTYI6YGaDD3hie7G0OuKJ4eRvAARHqCCgMNSa5WbuEkzABCYfJ/Ti+XcfNdhCdtgDzdme9SOZ+QNMCQsdVMicFGEjPNQ5MTYNl2RDsHzATGkiF6loB3SrSoEDvd5UPiYOMU4uRBwtMVQcUgDFG5BGZSacv2y5BbVEpUlrVULptHPxnDl1WfbGAhDKUXnS53+oFkzPxsk2ObqDRpLzlRtWWPWhh1I49qzNpgP/BDvvWUjrMog7SLQjurlVDUC8BXYe2ZdvjR3tnXZ6mMjo7WrUe/f2/m13/91/0ZgCgSMIn6ZBDlIIXab9WfXH/YF4DL3IXvqtMtDURD02QbBR7DYdlw9AG8nwtpnykAPF732O2v7vQC8O/leqADuJeIEtLxYLPkV5euimh+mlhu+NhgHut9b3U3ugFgrmfM/UWh3mxKP/zI3Rv0ePgt+0AnhA2YtFkbrBw/I7tbIl2fnZIUDZeIv8NxFLICC41HiWrdrC8AnpAMEp6Bv+3UwIqGCcaZPyckI9FVUdpm4Ttty5qkw+uqU6LlQvYccTI8JB6EUl7pr/YsMfPUJyOAQk4Aj8tNvPg75POg1r8UVJZkdlumuyj8olVUSyFUpM+8opospVZlWSptMPLzEPuyvPd04SeoRNHynCPkqbrdsWFsBADM8OBXriwGcqdRe+uwEvXfFuZhIKSBiShbOomNh79tcnYhUBHIdkqXpR/V24UmYSoXTLpuRbH1wd8vPz/84Q+9A/xgyy8qxR0K6dpxSnTb8rh8V8mbUDo/jKInf1U+vP50R32wrW6eDFxbm7Gd8iQ8r+b1T3Ng9A2NzxTu/J4d/GBoidExu8EAhO5xum57wk8YnLRZ3NKckfwVio0GU4jExlMuPzGmQgx1pbsxPAhQYeYXlXUDr9uP01I6iSc7vWYsB5sxJM+c2fEHYOMhmlGCtCmelnTpacsSZ7SMOcxKjyGSdzGBKwrmWJwGDay3DoTtoCB1VQkhRni5UnhWlyEaeFvL2flHQsvqSjEIcJoxtniUmEfdbAx1yKMNonOt8vdKGyFAcjLzxDOjaO29JNzMuoIUHdJjEYyH5mQ0V56wJa7bYDHrsI20hBFNTjxPoQEyKidauTbLJmuMXbooJ60iYdzAF4VQVD8l2qCb1AugvzONwX3hJ1bHK2Qp6nFvKZ8+b+fKIXxm+eAvANc4cY1NDLvReXV/+ieAhaFxP5gST3+fxUyPpdER7S5F4kbt05+okaKBTaoQiQQPm7MlhgbahxrCj5ATDC0BZqtL+Hngm1ee2IK5gVXXw2rpkBSVgpmomwG2Jef8M84oO9obeKn2nsEmAGox1FJXJ3ULs1rBaoA/o2j6IWQJFhKAtB0GqoUYPMD0wA6qBjLuw7jeiJww0uEdID+AboWcYW0D8AeDJGxSe9UqHQM/j0Q8nDfwEzhPDKWLWXat86RHm0GvfwB4HTYGivJ0FNmBx2NJLNWqQ3bttX3R2riBl2omr75ft8mQq9UwGM5d4CFLr1aYwUR5yM36eI1O5jDKtccOswsnFxKgckLm3M0CGV5IIUswmJayXEFfZXx1dhtyegH4ju4AedzC/gaHF4Cliw7JA8awBP4qH/kF0DjSXeaMRnlOoTxGylgYlI1IdwV/d1QklkaHGCOz2PAB+F5p8hgNqBk1wW62pl+uEI9EM83WgBBh4OwWkqsBuvYY3i76EZVojmlVsAEI0QkAA5uesUWYwVnnACWmRfPMmVFLbNLJ1BvmRPNyt4WQJzja1S391Espa22cJCstGoAeScbShSpHO0Ci1Q6fh7hMPiTK0rbHimN0LewiBgB4GkCWEFglYqZ5uqB+Q+hg6VIgGTATtOzIXUQAUjl6y/CW0kkYDTAKYeDPZkRYlLYk54UISYtOll4D9cMmMJHQjmieLnQV6c4EGJUlgY+/9PEwkBQFm18iv1bT/N04CjGaalGJkHE6bXeKadcwzHbh4gpZysXjapKuDqSopUSXyY3D493gTsHQpty2/GDaW6uRV/fZ9Id9ATRMLrOru7lkd4E3mgzSKACbDCNCGxfIjUgGTUybIQMwWD5feLJ4NPvW2RQar4qGRIK/kLkkxldIJ8HWDw/Oxl2IwePec3tIdycQ6fDBaICqAITnIe1IiAGfM93yQW/JiJZROp3hWGoYD4/GiL24tW7IC0xFslp4CE8GLbRlhkxO5Kc/m3+JPKfkDyBX25F3DhrrsYLc1ZS4KhqGpDlL7zzZduSQaeA4C0E6eYTEpbesekadR5WHtqwl/VgilOIyZadh5NY2ow5hGLRCmtQ8QRVSYrk1ECceztqY/8SvEGZUNUPLCg/AmG7XOo+EXz8kTLBIrm5edxeYXmicDP6QjheD28TtA+nG8bd0bJYAdGhV5HHgtg85Khh2HbLDgPm8749//QEAQv+aPb93gMSQtAbo80jtqENQjsSM/KnkKV4ArvR5dV3sxrErLWQOOJsVI3I+TDkJPAC/8YVH2LOPJzwqJPyQgXniZPBfz/5b2DVAR8VA4glLjDsbA2ZI09zzKDYDzS+LVK4JFg2AKhugKqgK5aeFTk8pSwx2FbgFf1LbRePk0dvwGXSJDm0eBn7+1QpDh3+oXuKcwUJqptw4YTRDukYMAJfGc9xb2XmvopPMlh4JMI8n0XWB77cpjx05f4CcaUtUfQMr66zuihBZ2OqNZhNgYgmPJCebwAduSVt2pAxgiWFujqvVkNEGEJJSLk8ATpjIR1VpGr4QcMhCDi1wuUI7gTwjZFQoPbYMbWREiweMPTCD07Gbdn5VlPbI5pfIIxqJa+E5TvTMIwRgyQ9DOi7por/zO7/zu7/7u/5n2v5zWL/3e7/3k5/8hN+LQSFIJ6kQw5W677OXTzN19cz6I78Arhm556/ZSjfW/IaGx1QRxn0Xv3zksQQwNGaFJpZgcs0cMVseBzx9Quk52GzRYEJS2OVK6ekPaYiFYBj8lTamvkkQFWVxigLLKgVP74Z6yLktICS1rXTVIVGx+Sdos09/dhqAzA6MXCfKaQOnTgAcgjZsgU1gygUj7BUVZafDWAaAHGzGRfcq4ynx5r7IxeMMYNkJWGpMt54UwLrl0WQwKTGE70oFKMTjWsjCxqblIiTtlKfWqg7TpZESMxgD58grXUU2I11XbFLu7IyVQM6eRKUTAjk/g6flmgE4G1Y0ACcjHWb++BXtBEq/q13KEr5CD9VDnk6eqjjAEqslPXKz1GnnYa9DWzBgzZgsS6EIa5Wn62Lppx7//ry/COTy+UrRX88TdXWkoCUq0iq6y9qIxLqFIdE+lf7GYH2knXdFz4v6MHlCedImo5mwJGyD0scHNnE4UhrK62PJ/S9J9lg3lwC9LXbP8DRwshpiMOmRV53N0xPEp3vl2BL5za4QGBKlawADESVCemZ01QLQ/EnVkQQYMgMmf8aWFS1E88esH0u2DruXhIitcSaYS+cfw2ncGdcZ1gM9A0PIckPSZ//hp8PHEH6esjoBWlTbomNj17PzZMfJgHTdSQC6bulIIBn8hIEEfyV4wBAuhXEDL35gAlnD5ifwCFEVAou2wdAMYzDRSl90r1enKvMwmhN+iQlnsNLPEMAa245c5S70tb37DGe0QYQns8RK5KcnYOYHoKLSSQdVSxWtHLDEmGGCtZTlKBpFiUJ7Pfhvs/uPpfue52D54YXY7kpsda4KUQVJvYHVwNPqD/sCcGnNgcvs0jYBXWy2sZizC28sRE2JySBuOY9jnymIpd8TwDjlmp6eDmwpqEQrJGTmOHloAEhO80p8YyBeGKgqZ5rZAAn8dVu8/lCgLlqAOPmRrM9uyE1/PJztAlIuHbPcqAAwAJMVkkJ4NCBKGJacMPOjQuIbD+1wbM2vrqI+aoHphJYyEoAY8leCXSeWSYWqQic1QJNX4Df+CabPDqHqaCHgOX2R8irVahfaI6CnAAyRWPq11def2vg755w0D2aCxwXtCxB+uVWxQbT02gBGEg8YI3C6WpqsVto1kiXUpWm/jhptUicmB4lcmnASy3IZJKcoJzE/bH5tqFLPMAxysdxyp16qpUS23mjg5ocherO+zINuYUphkxjo+CUWDcbJAEOFJ0JgtpCdutHGLxfAgevcyVvavpEjDpzH1gIj5LS7P/qjP/q3//bf+o9C/8f/+B99D+h6SQRQF7+R8EcCOA2GuXVN/emdxDpRiAHcQdW59rZHTbbBQh9Jf9gXwK5iF2/XL4PeRZ3H9SZGoSnp6d+owQiZD7NijDxZLI0RvyXd44ZhjDCTRorB+SBy+XUIY5oNaLpcYKE0I4aM/LHliSc/toSzbhHyiNKy2ksp7BjojArRydqIMwwnZlu21DN+d2CPGIcTJwwGdhXT8IyRMCaV25IRQ56ysiEZdM5KqE4KibpqGnbzE5dJV8AMrZbLz0Okk14ShSIR6gKNE4yHgHWx9ujnUV3KeDpzVRhEAzAEBiEqeFQMTjDOrhEnDH5O/I6XARO4qxCYvSwpBBsNLKQoHRsDSVEATp6QtcTekgft/GVJJzgjTIeUOHzGGBhkzAwkSoOFrLHsQvAq8pO2IMrjuJytkeMkjoUziZ+2/Hf/7t/98R//8c9//vPf+q3f8p/SAiOYhfA4VUdqCWwLnKLY7javXStKi9I5n0R/2BfALmRTssvp2mfzn2Ia7tm7hs+seAcwgBtHbCaG5iEYaPe20fToh2mqABgSJzyqGGIipYoM/qTRVK4nC2fkNHCt0vlb8sdgqbRl0fpXyN1Ca4/f0NeMlHoIFnm69NmWeTKykTDsjqAideWsEFoiD1mTPAjJjPzpQjHIaheFThIeyNMvyjNM/DXTo7bLBMCZ8DN42ngMdtFpYLA1p9RBqQXMiae6tBTCyO9i7cOBAYiHjr/Thr+P6nqmk9IBYjuRbFHpQkprQ+mmQqjOUcFYRs6omfT471Ivx1VieH7LhC0rGX7G/IGrqzQRGiwPfbKVG3LgALR9tZ1IaL3ZKWOTr5wlhtq21IaTcYv5UB/evCEfEi08ZgC/ArF5fCjxMZ8hXYjhknEqVHu0Jf967khbPpX+sC+ArqJ5YpiDBsuFb6Y52UXTm5KG0lPD2MH48gjMafIgOZtLIRKP6REilqKWQuY1vwnuIwyDnzN/ubvbTacUJHUrmlxl7kKWd5EXZXmG2GgxaACnWnjsggjx02UyAKpCr8rJD5NfygD4wyjBaBeoWiox5NLz0G89A+MhkXCqCFyrSx+YEVWwbOnL8ivweYD8lnmAw3Mql/D0pHgoISWwffXQcaQSPTg8TYiiXrQ39zVdPPRbfuT54bsKMMTl5klqTz+dIacsB2spxF+V/GFw5m+JsP75A8/TiYERUaMYcpqTBFNizdivlAZpALScwcZwGtW9Kb+hZG0v8Gj138zbKcEpgb9t0iSkngk8WJ3Q2Dqlcp2/UYfBIEuI5hFt6SKytSHkIpIuAZ7zrICfSj74C8C13BiyXekGqNkq1PUWMhDGwnwYo2bOxPhkYUQasvzeAf0GAinF5GHYs6Aq9/Re47sUPGx+WWrhFG0cecjZUk2mI6STtiC9EtsRg3Bq1ayrZfrBbCR/6QNYwnR7F+o0OFueTgyWVdQqGzh+p2F51b6fpIXoSaH2wm7jjABFs4dhnIBRMebHw3aARM+WRKILoU9OfdJS+DsN0Rv1ooQgczoHbOyy+KXQnD2kHGn8jpcIRSulNiTGu2XMNRCMJsHQClkqrRax1DA/UYKNiqhFIHlINnxUAAzOkHUVM4ylqFC5tNCDiM7DJlKuhl7/XET06uAuMWRG4PRC0oklXQPsdj1tbOzRocml3URO2D3SQ1xp/gSJIyJyebTRXirRkvYTv1wABnJjj1bddsEoF1Jd5dzpKqJakwBgzyYf9gXQ5XR1k/O6Ci2a3xLMNBiaxsuUmA8SMqcpNGTNokTgMIbMc4cmEg1ZWUYW3jiabFmVKAqAs1lEUhYABlnIaymDFqJJfss8FcqWKJ3HE4TBqTpZRR49E+XAhKSUi5mRnb6rvag7cilU2pY7fvvqcGjREk4GYEt6hOyQ+elkgJPkTDwBpXRW/JZsgtm97Y/4aC3ZY48D3ww6210+zMRpRFs6Hk4kwPxt1nGJVoKzaDwx5IEppcdZuRpAFRigcwPLwMlYIh6dK0cwC5FaMiSiceZZJwwe0TXD7iMzrTSAbZoKGsaSjqTSMRRi16dE5UgDw5nYUYXKok9Be0ohnnIZPGz3C1rkLpPGfM8m/rC3g7LrNgsAbNkxSudxFDmB2zVnOwXD3N+24HSM/LpNVKwojaQXLfJ6i+rcyzPYH/YFsMlrHC0Nwa7obNGGo2loaPzC68+RiDvZfDRnpsQwGS9DVhawSZIOkJ/N2STBLMUzaKX52TBG0PQTVUwqD57GEQDPUhiYl4g2O0Chhlg6Hrm2o0/CT8PXFS2r9FJoDFHxsydnaImi+Gm1CCNC4HV1GrMrQcffsqwTwwZIw1SXwUMyaCcml+ghI4CNO09PEwebH0MXBYDBGUlttBc2GKk0TMs0PH+JdBVp/qW7dmXx6M3FZQCAqSudPbF0UbZUpSyJmjdUPFWRWxRhzUQFEzMeRtUDo8VGzoZj43Qs1cUTPtic/DyTweSGkZW0pC3f6pxhkBD90zzNeXeTfuza9fJf6/ThnVNpuW1WUbbmbVOozWKoGTxsnDAY3IOyON1upEswHoX8wYDPAQSVot3y7PqBRKt6PT+J/uAvgIer2PzRGZtRywbRBLi1mhWvAXbzYfKADSgxW5ZCwIbGxFgSgDycCC2FujlFOXlyikIaQYXc8CaVrVXRblQA+DUfW0v2/KfRbSMdFXIyhjq05GQn1TL6lkIrwSB54odkLFeIWPITtigDT3jpedJCpz97WcD1k6eolEgs+cfAyKbdvZp3z3f3roTG5DqHfk/oYsE7ZIWAXbgqLgVeFYl0dQHA2C0hMeAkjKWLru1y74yXZ1xn619KKlFWPEtfUYZyOrSpeOqNtuxRBcBO+C11QsyPQ7BZ2rIG6AC06ioK1Y+REx0/42FZCL4+lw7WRT9z2ZDTMzjz80hk00T/tOXILdHahcacgIa7lQbGAKz56x67P+DDtyO9IQQgDE6HsJvU/Qvp9HB2htL70/uOUVQoBrkjufmeRX3YF8A1gK/PEdfYPLmkLrNLzmjsujNFzUcXvJTmhpNhaGiJHiXGy39o0C1tHElvCE4isUliAMfj5eHbKK2cdIREocCG3seWSOTKAtNeuXQt1Xm63HR4diF429EqKsLZe8X9EBVPIUuyG7tuC0nfLRGMlkicQ4ZEe2dDemBJsbRHfs54dMUfEr8liZCffTrPLJgbe4HboOhy2RNFYXakwDyJLXdFNACjIolNw46lxoAZ/Hqu6Mgts6Wfu+AM3ylZnr0J1baLvpBmYhNKgikKU/91yD4PX7TjzU8vXS6krE7baMXgGrWjmpTCD9lPIqI68W9LGTzCD0zQ8jNqiU0w9O50XAD1XAMB2FUXcpJVVO6mvE4VTIl6YKtuaVMDSw8G00Xx2VyrkMYJWAn4isrqboKUKMXh6JDTXtxEstIY/AsB/dehwTDoClgthk4Qtuu+JnaB+DkVZTyVPN2G3726zVmzYggalJbmxsTQRtDA9VHL88VIGURsARjwpeQ3T40ycAPdDcAvRYgfm4GWuykXtYyB8TlR6CGk50jSldAzQmIJUFZG+E28EAzO0msgfB42NiLxfoBcP1tx2kKJ9QNsSVvOGE9Oep7Iy+IvsajlPMEsl5hBJxpm6E2HbdmSk8ji1O1Fd3cFwOOiMHhk0SEZ9eDq8CA5S190txPslErzdNQMHiLXWdEdRVF+AP04/Em0kAZjJSAlymJ0vQCqC8Mm8LSoQcIG3AlwhpSbPyRAJWpyPBhqrMR01dmMsYGFzHNqyBGyiXI0TLYou70wakZ77iYH4glOnHycqkASsJC2hocfD7wsSxsnbLdn5KIwQsRmOeufluWK+LaBsCz88ELA22YNPIP+yC+Ajelbo4t9DcjrJ9x70q6PS8DmzDARUX5jwWMufULxDcAjz9IMNVj3cL48taXHg4S/RzwezxqTN/xd9lIwdMM3Y+P75fnbpi6i4/uH3ojShIFcFYY7QYqhB8bMVki3bJ56gOSJmU4K8YPxuNP8QWXPNfvCLAsmTgAwkpPBo1AGPWS74yFs+DzxSHkABBuGwVOH7UIKcnYtWTpzS07kgU+S5cJ04XjQwoMhwSCUM5u2FD3loaXSc4JhpmXxR1VIbycnpyZ7RitKRDnl1n9b4KkBTgBRfdKltETC6dLUCZhaQkSI8BdyKSW2RBtz7QEzCt2pl6o6Qkghy0L5W4oWsmQApAeW25kI6bMP4LI4Pf19KvcRvuY5tad5DO2IXS1+eFItVOxKO6gqXvu5/19+ckkAc6uEQ+Bhux1wgq09xlPJh30BdFFdy7dGQym00YQxCkaE0wB5xHvQmw8A4wLvIW5SfX3uPzLViIg2SQwMDaUpJA33nsJVpIlchZRLJOZEIoQkBgNalbd6KQzRm/W6zVpqyf3T20shu4Dh5LE1IXY3lRS5ZaUhOfXA4Mk5fv7un35HdiDeiA/3W3uXwh9520FIeOqzEE8l7uAnlfMqfzxoPoXvLDx5UBF2Rs0rWnR71E+EtO2D9fmx9mh+DG2nJsMXYksh7QuAVCLYuV9+y8QMWI4qEpzOMAYhgJUODMa/3hgnGIa03+xIaFecn1P1DLk94zDkNADswPAAISOkK40k2kpMBxY68aL5c26ZsZC6HT6PCdePEYLRhsthuhyLvYtqkpNoTy1goys3Kh4iEUPTLt2Eu3PhGd0+0p2/opZsGO8Y9x0blSVdiU4GebSYn0Q+7Aug69flPC+qa/xWAIwCLWRciIGgecwHbRz99O9fNPcfmzVe3TMA8I0OTPc2g+SXRXQSCUNIrhE0iGa9d8ydcaV895krZXi5PD01euvQPaz9X1JtzU3i7eWtpufupZovMbZx1gmdURXbtAti6QTsy822o+CUbmuEIRGekf/BGJgxOWtFRRN9DnMa4elJl6weaIl2Tcejc8aio6pPIZ6BS3GebSdwheAZkDR/yOGrIuR8wvQkwtPVWd1y46xuvcFjC99EpVcuGA2GREUtyYqK5i8lWhhL2hiEBGZco3k/ZCNsX2ng+Otkm60EZ36wPIwkJBLGq+/TP+uH1g8GAel6MKuuVJ+H3BfmFoAToDZoNloC2YObE6yN8zMINpw+mvQ1nW3XtFOSRSC70yPnJ3gk8pAay34G/WFfALuQbw0D4dLSGSaJBKNNiUdzg2gWg5kPU+Xjv/9wuRkCaG5EpZAYGA0Nv0GXBcw5sChbOlFIVoAlAkgk8XxOwycAdWjZfYWzrDz+NMytpUrIjO6Tmq/zsk7OMcdWV92r2cD2ImpZD3TgeHJuL0ULTYenNU+PYf4H40yMnyfD/W93TpVHYzlH2DaFHqp050dbLUgicc6o1gk/QMsIaRXzF9q1MEj8hTJK9EMHDGmphMTBRg7ggYV8czJMbJUT7SpIDCCRh7+NxNNGPEPtuscl5uYQmATASfDUxjqMiq5KKdnA5Y6k9kZSFjCAruIsGg/bTeEvg/qB0b1W50I6JLrFQHuya9iNqcMe7pYdEc1pRKX3Uy0q0UiCwRCEGoghvwMBU2IN1+GH1x/2BfBw5XZdu+U2jvzmIKcUk+GONYV++TEZQsYiquZvzwvDCizK0zyhGq0UE2xeCSd+VAwYtMbXQ9kg8ncz8CcwBC38wxa+sCwLFRIwtAyN+X7tP5CiVc76VJQNuS3L5YFXkbZM10bRmi8xP4xdt/F2quc2KwRJQraXcUY4zAz9CE1Kv2k+qcB0hsBbuxCNkNxX4OUPQka0dB7t0eqOrXOAYZBheIjLx5OsW4ZanHnALCFp1/rOu5Soco6LZgsV9UTuV4sSg8EE46yTi+KQeihU9TWAYX7lLIVcrGXz8Kt7X8NLYahu4FGdhnRLzBmF6HO5EvwJQiIrw6aMoqWoou3RZbI0nO47d19/DACGDbL2IPXM2Y74CYYqZtOiXhL7EuBGiyQYvOviHveFXrm+djAk7rRf+n6Of3zwF4Cr/nAdXWmD6GILpc0EZ2LUzITbkiHa900hI8LDiFAKGE93EVjTE2EYVUTJ5l4nQrGZwjiNPmc9MDAQKQ9tf2EZWCGJYJY14Jni0xBt3NXip70MGO4iDVQIeCI0kqh4GAA6pHcC/ERR5wBQ9TYLVgpAJWiJIwS4s7/xaassfrCQ6fy371JbnsZsAOdZM52wkCXpnGPgTCw7Bx0m/Jy67XLX9jTDGUbS7mQhpyVm80cOnJN2erJKudv5X7/6q7/qYUf4fVz1PPLYwjCMLAyWlYshZpqTVAusbvPUD7sGLtwtloSpSo/RjqXm8WdEjnkihU3XEpLaCBA+DSPKv2UYzPVf9Qh5gDuNrpqly+HuM6V0uZzRIiE5Y2BLV8sNSBflaexxAvCXUtSyEqo7NFfTcqcHUzn8TyIf9gXgqr97CfexAqCZ2FV37Y2FETlvDCQ+kvTFk+F558NFU0U31jiJSRKN1tIUNp342YYMmMgydh7KwEKWRJWNqSx+nkLTbQeMZ2Na8zzdAzDlKucG0IYQw9IdpTqYXK2q0n5HVQMts6tVbxgw58EDFkYJxumpT3rOGOYf7TwBtCpFVG88ShDNZ4uGB9AJpNIExnmWKORKQWJgEylsJJwJfEZs1VoJ0dqmwQKLolKUoBoDgNIdLIBmXGgnPE4A/lNjwMZDDICJcrAEbbn8rk60tBBP27ly7pbqsP7x1+o6ZAjJBWaT+rmzr+9t0fqUrWGhzhBMVlvTZBVzlngeBf/OJwwNxikXktTetBBOUpUAwJqhXTW/r7KdifPsBJyk3kSJREdEQ3o9MGj4PuUojbA+FeIHtkFddTksJfp3+/FLhGG4kTFfvd7vIWB1edbzMxgf9gXwfS+eSTJ5Bq45O8caVRNmbq6b9f4B0WCFMTFN3jQ/kqjY5dKNnQ99nv5GrbErvRL08Bl5aBI//5azeXRliY1YIldCRcJ2S5BsPJCBIRnzWMLQSf5ssFf39c8tYU7/Uk6jlqQQ/snJIxRPxgW9hRP+LMG9RCFLj4OBW85j78A2VVHLjBiiYs/PyI6wzk8wZmxkyLXH02zALJFRxdXFRsybD/6cqDybjFPplq4UntoAYHDiLJEHJycpvV1wVpdBkACU0ihyQubHT0wppyxiKSqFp8TzBBRCRWewwSKvDXb4nIPlp22wkL2I0onXXhg96JMTYd8ALDlF4avC4ETVTVqiumAB7AImqt3INUbDgzkBT3+FriO4X4cdeLVgnkqe8QVgFEzJw2XmyWkOSHdLs2XgLD1P/bdEfvCDHzQ3TSESYInNH80jy/ABNMENOr85M9lI/NmUd4BEsOay2+lu4UXln17o3bbBVEFCSulGCtzQ67+bH4BEWLenFrIsGuxC3xLbqblbwp/+06klyxeK1z/qPPGRjOrexJVSYkc6/Hjy0GCOkZEEcLYR2jK/06BREUb9xF9WoaIBMLQLehiGLDAzEGchWjn+yjGkx5+OhBaK1tPfO8AvP124Pa124SQiwSylrO2dH6weGJZCdPPWxgOveQZCAo+zB9+epHLrfLnws7fHOk/HX0h7AzM4YdLzK1HDIwFos2GcgBdhie4OtwmPHemZE5JAdlsJcaqLk11RgCZcrd19tYGEk0S1yyTdfUEYatUJzPPI070AmpVdafORmLm+y5sSI9XYmQO2DymGw0T+5m/+Jv2zn/2sv2NgyBoUg4hkQ4OcNHN0d2/D2jfQvuRiRlsifAYdmzZumkud5OwtGaLVvd2Xkp4znee+fS4lqiWhqqznGUJSxhmJ5dhOJOcOKn8wem3Mz5mf52r09UHMyZPOuHCvDMEiOTWAUNvpxmYnYIXojBKL8liu7QCdz4V+7SqbLmsAuWzPC349dJiclsC1bTDypzmTyIEZrj7xyFsJfjBOWiJDIY+qlgwAfsIgonTMnGbJoDqKCPWwcnoDhuQBYBNbIDmHvIkvlUdUbkuenGFqg6eNL6XokAwknPpXTl2JttZ483Py5PSjDYMH2Eclh8O2kTXJAJBLYwbz7K40j05qZpj4a0AWKqL6AEi0VG9rVdbzyNO9AFza5unhGjedQubDvSTaILqpDKLp8f8a/dGPfiT6h3/4h7//+7//4x//uPvN9Bi7aMeJJ8ljtjz0iReAkW3gGtkBYEgTTIsK8YzzNG7sdWsFoNkAEg10SAwk5KlhSiyFzigrO/zpOf2iQlfa8fvywPlhMkIWpctNzzl/nhKnPwfmT2Rts3aX9Ixji6KKefwMufwArzTX4Q/mSvHz4CErxDAYhFHRyANLNzz85qT+2as1D8MwCDFKVKhoT0YhhrphaDAARs8voVqVCNnQerqx67kUWVXPaWloea4t3X8fhicbnr8epsuFmfCcwm+ZnrFlyGH0kK0WYevWg76zYvtKRHePOOHuFOe5fmQBtFk2wjgB+NmMtWcZCSe7F6TNquIQkEgR0gYnJAzOpT+J8XQvgC75eXVNADETZrEJE9383R8ark/6Pvv7l6pMp8e3bwD+P9QGSBTSAJkeJAwaOJ4mzxzL8sd9+P0BAM0DGWz9XE28Psc3iDxgE2D2nOHTQotqBoyexxInKXcpPHfep1yh0isUA5tRFnvCicFyKRfRLTELWYWXTpZ72jDnkl3WzfQpXa5Q0TSP0g4T0uVQtCXddRmsugA82YxdOB4MZ7Rr5Fp3TYXiz5CrhJQMuicIDypTwUNg4CtXiE6EAIRu4KVOf1Ee6T0f42mpE4A9Bzk93ZJCEhkRRlLz8zAwbA7ZhTqHwc726ra95D/B7JOkULA2iLMedMvjVPsYNFqAHsoAbLndgw6zE+AhSOy0uxJDrZaS5tEJfsJIVOEvVzrC+cF2C8dWoSfRT/cCcF1d5l3dzZ+Z4DQN7grSnc9jqhqXUoTOP8I1TNiaISMli4YnZtTAma1+0PQvZDH8+u9F4h0gC7N0Wg+y6orOwKmiEKl0/i1zpnMCdA9Y1glabcRTdOkz+BMexmgD0CRAPAM8OIfUA4y9D/mQ+K5fev6M6Z2PqO0MA1AJTrZmei4AOPNtpChdt2l44oQzpPDXdp40gDc3ka5WTyIfFIAtO+q6Gn9UVWGTGkAYJiet27NWABVJ/qooxDBO4bMtYYQIAxuDMx2DZQzrM1pReCH9NOQAw/CvQ3jLsqqSDiNdVlSDtUfLEQJwRsWvw8Cu0apzjootpaJadfgOfDOcPx5IJGspIx623OrWiZT2FYOQexCz2xk5HsJ5th3+w+unewE0f+nz6poYE3n/TnMptqghS+ANit8oDUp3mkkyLqJRmZ4Y+HlgerjzY/PQ7y//ZDR2YDAYYMpSkbMp5Ky9hYpaMmgCHCZPAOk14+bR7QgXlcgWgmQQGMKI82F5Qz6rrj7upxsdSPW20DL/oshnj5RnzuzBamzLBxgGniqyHaaTJ/CJ62iny8oJKYW4ZGu104gNAIlEAMeIRJTmVCI2HoKwlDPRZYUUrdAADE5aFqMeLEnDo0SE7UUtMNpSM/AMHsJQgsdYSm9f/DEzhNKQbPxtx9995En4l/vq+8Y/r85eL+uMEHfk2o5lPfNU1PIbLPc1Ur0zEQUjMXSka1W0i1i3DoQMLMVGLPGXfhHdb3eap7q372VrnWF4/s4Bp7uyK1uhUuh29ND/B15+2BfApqGL9zCUojw52caiyfBoJobSfWI+PK/5fXL3r9T6e8o+NfjzAL//4CyXdrcbJmPE6edF6XLhTZJcIwXDVgWh14CvApw//elP/VclSjeOkGzDSrN52FIgabKK3Sr08DDBYHRO66e/8oxE8/77RV5dqmuSBwa+njHrWcN9DtK8dBJ/tGm5dyMv91gASE72ug1sC4S/0E358sxtLzz6n2YML0UILAA/42Z6eWLyqFJFXYm6BERK/XfO7bcSMLKyo6ItyfyVQ4jE+TNohWBoS8hOrw7jKetmug5fG86TMID5scEI0Ulg/jg5RQMLcdoIYQulGRXl14zGMkT5azJPPajO4NGzC20Gdrl5DAPBefZQA6hknaXXGOf8jGCMzkEiZtpS9V5L+DkValnWimIQ2h+DWyYYfDavlnSbjYQfoK2x5b5mvMykViHxi+qkU7JxftKBmAoYdl8snENvRE4nDxazJdEDJCohhuXHkw/7AvjCpTI3b6OuvTF165oJ157tkhPzJGTsDJwQj7+6l8GDhyb3wLwMHwy8rEItIU0kNvPEcz8lrseERONFdNX8MSQ23PHXbWwG1BKJZf5FC6HyovJHDl42Qt5bihp3UeVowq8WElKhigo195Yw0xk1wH92YvmurD0lADBEUvXs/KXzj3/RQi0XzajPsoLFZu9ucrc9rTRAGDpY6Tivzd/b5wnj6JxVv9EBJA7K6UEGKwVVPCWO2ZJYdlkDxzM8AFuHMEKGIXF1TF1+nSARhSmRXrds0ZM8JA8pavs5TV1OVWQ1Awyik0ZOCnBOOoa05Rl6wGw5A7jmr4O4H+XtThsdLw2jbqWX+K7xtvRbT4mOjoFT2/ZbrW7eWsqvpbvy/3ILuwfZRbsWMCd/J5B+t70P4HzGF0CX7bzSPJbNq7vdTbh70iS5l4SMi8/1PrD4a6D+y5puJFlGjTYiBsi0QRosUyWdUzRaS3YA+L5G0GjV6t7gn8hde80ffRoSgWEmW270ewLqWV0ihegkpCYbegz1if908o+TQe4WXlSeL+i67XwGw6mHqB46VzrqwFVnM6LKEwbJnowSyy3RTjvPSsMDxxAgzlUPUFec0r04iXRn5SrTJLxc+Dqho606hgSmS6ANwlkuzUaFUwpMxx6A3i6ELG3wbLW6FWVvCRYPTxe0Ji0ZVWSbatqy6mzS7sBIx8XgT2eoaJnOyD8kI+EvVOe2s82q6yjsy0zSQp7XdbKeX2leaqFaaUYSP42QtJQoutAr9uV9ZlldMBh1HQWpASQ2rjfXnQEAH2H9RAvW8uPpp3sB7AJ3sTcupsQEEBPJpo2pQaHZHtMMP/78yZ/8yU9+8hMvgPxGx0yYj+YMEq1QgxVVtDiB2TjxeC67ARpNzkhkratGrfljM7Lrn2edz6iokOH2+5JCQmy6d5gbst4gGURpUX0yOMmqZNAAwdbGMEKc70qYJYaJbXjLPLRm5o/2XXJITQpdmbctkUfualnatc1ywtDwXd88c1omAARDJGxnEi0Nf8cvpVy2RLYqJAyPdEdtWpTrVbTc8C6Kjwja8/qvpQBsAHbnwKgTuqsTuaXQWuIUDaArnQRAQniEgBk0Dw0gi0TCEOUkmAnPjKJ0RlF2gGkM2Thv7MtGTDh/j/6+mTkTnh79DO3JLeXUczImJ6ByPEUZ550o6ihUcdpKiHYOjn3VXSPRNi5K2NjerSLr9H8k++leAC7ew2Xucm4U3MCG1TyZZncp8GbXVPk93TcAj1cAIgvMrdWINHk9fdgVMltu7z77YPD09yNST+ecMQh1/8BLzNbbw/Cp2BZgHkaWR66otuMHMOgYFKI1htaNEW3M8UhsaS+z66EqYKvLeLDzPOhSQp61eCwnLdVaiVLy029luQxZjpcRLMNhtrQX0YRN4O2x0wYuxEnYNivk256Ly4AsxB+hJUOihgEcJgkmxQOO4FEoXT80CSwdXokwMdPwMFXBnA2DcEUHqAdaIgxh05Awert9lwLg4V+hSgQra4mW/CRMdbPpyFsGC0kvpIrqNmjY7NfSBBJ//y0Mv+G0QSFb7uhW4qGKlGRFLZVTglS9ELbasGSgVb2BV6uicu3UZeoGh/E5LBIhDJHz5FzRjA+pn+4F4Bp3IU9jF55hKM2rJya7e9vQ9KSW6L71BPcHR35kN0nAprlxpI0aAI+BM17wJslgScfJEOp3JGC5GBiQCXBdXQN4y2aOP2nQ58+AxcPWKntt9+xQRZYS/KJ4znRL0SQeNgA7AWCUUg9Ln3+eGZFYRsKobjr/ouMZZlmF5pcy4VRlhPltM0OikEN2CJ0A3VWAcSGI61UIrBNwgE6yy9eRIuHcmUBiFlpdBoFRyG9HSuDMqRMlgNtOiXsw1ee2IIXHMpgsEkMhJUoJwOa3Fyl1SGfwENF0tJYB0MpCEsCO+HUFxkmqIkqy0ws9IFuGWVYGLauLQqviBqH1cJIva1SyAhQ6wULSa2aJ9d++CtWPq+xq+khEu0DdidJ5fIyDkUIYqByX3EkMZ+k8H0k/3QtgF9Vl3vTk5GG4GQyK25jNY1bIwGbFLU0MnGHqzhEl8KLmrPme0+PAX8MAVs44ugGkd2fCwIfkwQBjiWfpOWs1TCGeQnUYIS2Xh7YFH7uIJi29eLoZJPa8iyESiWASV44xO9o8OTsTncz5YEgRDVZK+tzX/IxR1VWwnNvp8DyYaVVI6cDrP2cAftu3OxfCRz8X19IJyEpujpdnqJR4MthRheQk7LQQWjbttIkXQFMhMWkYNKboTkMohjVseUothad7ukUIllFLrikDnp+2r14/sniEgFelhi01QwLQGdHSEcYZT84qpvPQ5VaI1iqPQ9aGXAJj4H1mYuTBHLkeYrs6eH3ZxHz6F+LMjipMWgmh+EUDpO+9XjeUllwjNyOPFwCwLMI4ma/kbw722cBZ9APYn26DD7CZ77iFdy9nE4mBYVDcxmxzYDjgG4glMppdBhGlww95zfgt2Dx3PCMAmkWGZZPnhgnWo6SKisYDSe4iL6pQI1tdNim9NixlqesvtPimAmbclfawUI5fxehu+oufRxYdZwZPSwDdLoWTFIWM5EED5wlcCbreOFeaMX9ZRUscbaHA9LoNbGmDaQ9B4BrLqfl2TXsEgBGv3i4HcIK2jWfA1ANjAKGc1YUXcvge/X3AVILnKnBcxMD88MAknjQnqYRW2QFqT25UADVWA2weu4C3ZVIi46StdIloUaGVVSEMluHpB6klTsZ4wmzJKJo2YH1+onks+/RNS7x2fr+JZbU7PT8UfXeJan65xDJdiM7gb4/47bGKO6LGAEBjDoGGiSf+2TNGuwY+kvFhXwCfu2zdSy7hNS+vU+ViGxRTYmhMqgcluwnmYVj2yd3dBclpkmQ1QA0ZtiaPTngkQnqdMDghMZg5iTza4MFDinKWNecM/mAMWbR0nlKkY7ZsoBW11CePWnbEH7MsYKGlMwgnjES2LFoVWlbkNClEE8vaKKVy9SNqSeJZw2Pgh7xpLqRuhRgBahWAQE7CW2YAFxpteEsihAcz8Q4mnv7boPvfsayiROBOL4MHeJ2vtPNsGMDMRhglzlaBMWMD1oYQgJY4KwTAIFdzr4Kwnrc7DHUIee4UVRjR+FtGyKNDHoRXjddzxsYzckYe+Ppk1APjOsHXy11WztKDpXkG9km/77s7urYgl8QDzHawna3SMM5Anx0aQleqjZcCYwkDCSYRhpPmt1SOQVxWGqzms5HoyrdhMFn+HP7P/uzPGJauYPf71c0ttdfWaEtsd/sfUH3YF8D3vVautKtvIAyZ3GbLXXTN1OsfKDVbAKbzuqvuezJ93gPsBI8oPPH0scRgmBCaqmZLUWChBo4tRCTyRB4PHZIOzDMnT9IQs8EU6tHf/QCMMKlQnYRUlJGwY7grvFQplOel2P2PPKJWw197eH18LHEAHkiAPHSekY/nc8aoTgCStm+P7Pi7rF3Z7V06u7qDSSHOivhEzxbCP6elZ0cAub3XewfQCuGEByNgu9DAk12gdS6L05DQYFcTr2NgyYkNmL2e6wE/JNtVZojS0VZuJfgTVAz+qMDYeQZ+14A8YQ+2ZYJWCf0g0bnezDwP/0n70F5tDNCSPpsUVSKdER7MEpIukd15uuiMBLjbQT9+Du3ScAIThiZ1G+fz6K8vgJdrbXTcgW5pugk2Db0Amg8zbenFABkMUrLxiqIBMoWETRc1hfDeGb0/0HbfNoKNL2RVGDxzMiK/WS/CefJP56cbd4YeVOzfS9C8ckW1Tapek2sYYIVmVKIdha9VYFJL/NnrJzzNH9XAnKREVPzb++fYRjtDVsIT/6p0ApZt2aPZ4bsEPQ7UElpdhitCZCHUmKw4hQib03UnYL4gSudEGCdyJUj9xBAeVV3BEyHCQNvYSLGEYeR0aYLVPH8MdPsCA8BfOTBdiTLWQ2zlVjFAVJCKvsVwvhWw0xknD6r8GVvqQYfaq/8qph+opPPUXnawbKHziDhFtxdGwk+AO5Zsy910POtBSxpzU7gdpPOXKBeMp5NhP498fQG8XOsGrplzRxkU8yHWiPAzXobuvoe7GwFMT8gGaNO2XLPYnSlkwmgp0hlS+qyE3J1fLZp0/0RCR1s50Tx0UvTE8NtFg64Km1aXKFT1GljWXfZScZ5V2CtxArAVSr90c/9jsNM5OzaYifY4AfJkDP/WWOJCcTo3G9RYDHbqAe3rv6vQCYeXXvMMnlVn40HSfyFgUQBO2knCoO0kcSY7UjCYwPAYaOMUgysSg37O/YIleBi1AdBGLNetaH51Q6rVuNYSZ2AwIpcw1pJOeGDewm7st6iKpkEZyOkM+yr/qv1aXegkvbGX4qyZd6Pa4wcbD3BZPOwtR8Uj5AxJ16XL0fk4+e5EUSllwZMKVfFs5sPbH/YF0EX97tevabiH6uVWb0ow+PXG3AgxuutMFX8phqZadPO30kIJqm4/Ke4QjyRLMBPp80hNys0ZT+T0DH4CnM5/+y6n9EI8QjRP3znCWPLXD4NUV5SRJydMywAtI8kTni43Y3aFTsJlRQKQAbOsjBoY/mE5/xcMR9rNT7tqxNPfhbMLWaqozqg9zjx0iVvWW1ethksvETkxDDQSUqvSA9CcUsr1ACIuB2GotR4waNKXCVPR01NKbDTCOLExhBLpVwd39ThFdctTaXrIeERJJHEiSSxfzXf+KX3eIdvdljDB8o8WIEz+wQD4Le/4p/dcYP57cy/vQhvJL6sqlu2uY+FsaYOMjkWIn8hq42n+LpwQcCkwspy/w2Q/j3x9AXy61psqk9H8mRXS/WlQPErcpUJyjA78NV/3hKXHNWcG5Dl8CHmA6X5SwBYSLOnPDCIUKkp7fGTHEIDNWUs8bMI5z5z87PCncWd8us+DlUW/KzVAnxIP3ZtSomi7C1ZL7JOzUEVX+gS8tWOgh2eQTk+VrppjdMk6cOA66bLqkMTM30PZMk5XeSU4a5tRFQwA8ZQCHH6YkCUKaUwJ4grWpPR60J4mtdoDiF8uDba6VaHzBKC1QecXwr90y7ICDHZ3+o3zB/uclLWopfTTuSUnUTRDCoMGoLtrxpOTzghcw+ydjGibKhRztDwEwJLedR9hubtMTga+I82+CV5UDai7Dp/E+LAvgO97/YwLkdXwuRUZBsXEuGONkUkp1JQUaqybyHQk7MRSInB4bNlIKqFiMxiSzcgWYuABTthf2Ned94KHHMlSzpYCF4q2Wvmza4AuMVgpAEWH13meVSnUjmj+aEMGK+XM5alQJSzflaIRRpX2SHVWbEZPVY9XHicPrFBRFw7AJaDrTRWXBgagS4OEwQ+wy2cZeYXiFG0LgbvKe9BzKtdLSMhSVv2oxSbSeTCzAfjpJCRbtOZfI5/+KUs5JM0qmIrRPmTFBpkfhkGq+4nx89bA8QfkXAY/mb+e29FCpwG59CV2gTrYeoYhsZVuF5ZsfjbJvoHXjiTu0iAM7Ij8EEd82N/ZAku33C6exPj6Ani50CaAWBgUtz3NNhDGhd9wMB7GhbOxhjRzp24EeQgYMYik4fOHyR4fjXgPIICqM3Aq1FfRnDzhW+JkVHEeSzaptBRUYe4urg63XDn4oiVe+YdUiH6gWsqMklrOKSvhqTSYXdN57o4ev7isSUbIk3a20JBz8uAntk+7jruUYWSVGNKpei6zXRetdn0tpUssypDbtaM9OCwBeq9g45TLKZHOg7DnC49OUElhj+Hq4/WhAyxXdUi0YKToywke761VEYJBS0usDXZLPAAVFZVVaLoS9Aivqp+R0tNBqh4bj1C1wvAH45zMudx3q2EgepbIkBX+dn96BVY6zuzYwCSyc/YXN9icO4fury76elDFGW75JMaHfQGYg89dwoUyDIdrD9zo5DQu7ny2qFD3rZvf0CT7iQZSOicww5AZr6hkBfYvnfuRl+2hkEcoGPxDnwgJPww8znpgRFurZa3DOfOUwj6z2MHwZ0eSE7jlOBmQOeFxkmCFOO0ijJCGgT16bJbTAZ53Go/nYLVoeNHIW9IIMZP5GS3pq/zr46Bzs1S0vQBUIjxngoGfkwSgZcllwDA0hjA2Rr/Ic9oCwaBVS1k0G1XbLOqayl3PbLRgXXEpCG+m649/Kt3ewbrEkGBK++unkL0GtLftg4ny0PWz3UnUD0LziRxmtTj9xihXSzBySa3Sp5ENgxwDI6nPG/vy2q4l1QHyl5sH/9IhC22zMKXDlMvD5oTp1tA8j4PiFLUjhj2yiaKiqnRcliOsYbooAGQARqekKI/LIasoj9JdFJ6VqPM8nDjpnHI/jHzYF8AXrtDDVbQkLjBxvSXmMSiWZiW/KWmGAIzCAz9wUm5jFBWbdJ/zYMMTjDb0EhVK2DFXF1IuGOdNc/3bXgEsM6qbTQdOt4xznmUt5fSsgYwtH9JjzrlOOigd2otHmChP5LbJgBQqN/8DrXJJ0WE4T6QlKjpAKTvAwAAuGV2iOzw8pyz9uCJElF+u5w7Dseuf5ulKMfgTIU6cGGyQWGLmQcUZjLHS+Nk9mvl70AQTknhKRWEITCTRChHOLZXmkc4zZy8PjfmXnkRtUxWyfi6W159NGBGWnp7HUiL9rqh+E1/qBEhPcrIB6BPDXm49vOS83gjIeWxN24mUMB1X6ScnD2RHxxhsl8yZeLliFqolRnhG5Cfhk9jP+ALYpTUHp91U0Zse9nW73B8frtv9FveYqVpihgEKORKGEN0E99OBZciyAjd80jNyAnSHD2lYm12AjKjOrPinGUufAc+eDtNy/neNGNKyHgSDk+lw7EWUh8ETm3PgZKdntNz2ZZGqnBhOSJIxwIW+peNiFtrjQANCOZ2bZ6KT9Lz244CLAt8zwrXVA4H3AqhQDbAZSAhASzCCEBsebDDYAGgY/rbMULTG+DnZLeOvK/7I6wcAmK4ufTbDD1aV1eXh708+/FdA+G1TdVLdSkQVMy1EajsqzmrRnxN4oXJPTLk0ES3EyLNluTZe3TYOw7ALB6tJ3ercFhh1KEtKMvKyKlcITHrMjEKW9xW7/p5PBwXc5wBaieXW5JPoxwfZh992s5g+N9tvhYYgJ8PwNYLmxvQ0QN1d/jrQmWvCkmCFeCyz8fQIaM5yimrDT0llwfM3hfzwNSlqXmlPKFF/P32YUiotF/7Ulnkqt1CGG+OMjmrOt8YDjzZsB4xBa8/h9Bjl8UzUM1raATLau1NlvyXnPKVaYCGFZgtZpjPClOKsLPOrWFH96KGGHSzDU0CHbOdARCUydEtLp8PTEbad6g4misTwIFxIupTmhxOG1CTdkh8J2Rby1978GZqBL/esIppfCKZB9fbqKlSCP9GPEsqdMtqoFlq3AO8KZBhGgHeNBwwkT0gGKTe7U9JJA2PpVEkzU4cuqBQMCSeD7vKxbVa6QyAMJFKQKCFkRC07EDxsB45/Uj/Po5/uBeDSNnYPw2dETEMD1Kg1OuaDc48VIdNjiafhE42KQTjnz64iNoY5U4UgEeVBVSJtOYlTVv7wbLlCtBBhp2MrK42KkUhkRM6IM2e2UAa29XAag+W8at8Sv+putl4A3LYZniainRhbtAbOfs5C79qy+KUv6kCy46E7mZ59FeXUSTc/v0vpoW/ZPd8Z6hmVKOmQO8mRB4twegaY3mBIKUKkfjhx1iEnAJtIsXRiitJsyLpia4AOGSfNk7ABEp44ESrkkOmkfirEX5M95jCPtmaARxgnLWWwt0bRUcGzaRKYsShjclINI4qQMHTSTWHpYhGGTV3UN3lGGpix5pGzHSlBwr5I75e0Pwsh3go5EXZclrJg6vBs7xnsZ3wBuK4utrmhH64xJ49pcEuw9yCD5LGkE7eu0Wl6IolN1oPwRxgze0UhzfcDXhStAV0bMfBD7r9Row397FkmBEYy0ivEnx1gNqPQss7QooyHncrapoTcb9cnrvsHdC3BOx8AsElswHksT+G0TL/1L6RPdjrYyVZFUVUqpBmA+zFyPfd9VCfODbJ0nUPqVvNsx87vbL0qxnyWA7YEI1eNe1lKzYuSPFXJH7KQqKWivv+py1ZRk3W7dE5IJGTpjNmiNSlFP9EyLPlpAuxJZ4lNaPsSgifxi9bnnfRyyEKDBZ4OvBRGyNNgT6piGcOqnISV06QLwa8lB9LF6pVwgqOa3r2A5D6ha8w4e8oj5LckdRKMn8DHzOjMV+jDG0/3AjAW7860sevyu0N8UjAWPcLcn/CyTEZidCzDb455zMp0GEvClmiUmzOaxClEYDZnhUQZ/OPH0Oz2vFCdGO7hr0rf7OH04Fl7GYtWulx2yDnPZc6FYqB14qx8lHZoK9RZ6Tlm/nbavpZ7GpgDn4VWblEMbPyrtRI8zlkbWoJR0dUkIS2vB8D9Fo+2rmgnKavzxEBk1RskwGQHzhNJWkptAKhelFYuP+ckz4rml6iH9qXVCBk8SnS27b2K+fGrgpAeP5sEmx0VJBGaPyQ2fnYbXG7G53S5Y7O86V/mOVvdmDOAKwHMQ58iZBc2K6WG2yaMxJz8yXquPUsyNmBLhM7ZfxQdrZDL6v/H1//TyRu3zkMCM6J6Hv10LwCXtsv8cLENCo/bydO/KTQQwGbRtLGbORhjBJA0l42LEBmMAdNSOmaDCGkQwRiFOBnx55eFlhNmVSwxgHkuSNnHVe0FM9kMDHLTlvNkp4cputCZOLuWhjkNoQRYS8TWapvfMWqYSLELUTB2+uTJlsJIP0QXWi4DM00CZyvET3csHaxDw1Bj4QHi3JKHzSndSWq+8+RP4p+u1Wi7dq5LnfSgkRV50fA5Owq5kDyFgDvATkwWEdI2JMEPU0rM+WnLSYBVj7xzwOCRB885/OzKxcn5rYLhxIywcy60DivaskTasu3XrcRIbMFRiPKQcsuKIX+apxCSIdlI9MADxvZN66/8lb/iM4o/QoN3cX/605/SzsTGaeLkgc9NPYP9kV8ADcTGwuV07Zs5dhPTiLj8fhngSQxK4oOtR4kB8sDl8df5MZgSOryQuSESOavF2ZLGYJqVk1WUAd9s8WRDygpAE3O5Wtpj1z9/DPATJbTnsWW+jTW/urQsBjYphBEPWzTCOjl1eDrA9qK0buMRZfNUhaHJHrsacFB0YM6OUSKPVkusGf0wiBMGIC0VrW4eWjNCNFsWqefsNIBox4VQLf56A46QLrFCAPqpebna9t9PtXR9pWseoOqWxJK269hU8XCB99PcDh9zVcqtUBoVwXA2z4bMI8rGrzSbk5br2Y2TXenAFVozUvRjacsA7cV27IUHrb8a5L+EbL/EckMSP11pulqyOKs1LcquN0bLYDHMLgUgjMZmlwipBD/DBtn9JgamQ+fpozpDM4kNQpLORIjB2UZw1rDj7b/aAtl+3R1O5ld+5VeA//t//++Qcp1Pb0TkKtISGx4AuTSp+eyPpz/yC+B7XS0D4do3QCbSSBka49h00uaj/8EWv9HsAQFmPopWrmHibEybVCEechrh5yyU88Ge8/THz9Ok6oGYe4Q9oYRUtymAZDwV3fJd4wHjZDqcgQGIErTSitq7QgCvBd95dkRSCjwwhjmRjD+ec3naGCzpjELqomLTaBkac40UajnYDsRTQBSsjTguYhhiPsnzeIIA13kavznpiyNaubRCqaLoAwAA0jZJREFU4cPEsygMgM2GrDfaUvU1mZ+TYUf1KYvUAw9pSeuEhLcvI6orGmeFMEtUnURuOxnTjNM+T6DG0m/9ZfGv1okMnwaYeARz2gW9g0UFcPVxG0LDM4AxM+gSacgYkPRK8MR3OzgHIYfwP/7H/3BEbK8EB+I8T+lM6Hp+Hv2N++15tm2nDVAG22S4/N38JqN5MjF5hEyVCXODmTZLg0tMG4YGV5RsiOOMil0UeAY7edfzGvz0zzXMFXl66UrfT4CXv1iic2L0w38i+qJVFZwzSreRPGVXehiHQzTgZBxdMjyD1CeeMeTviDi7mcHYJwMYT/50YHoSxlIiDJ0Hp8a6jjz8uyIBPCJ5CENiGDzZYVryYENVn2cJG0+EYpMITxoYRq3WgGhIS8Kuc/4O0JITp3JsfsOGhAe/FH7SEvI+/utvYXFCwvjgTzzsPAFji0duU8GA9JREiz/hlIsWmM25znlOyQ/AWW7RPOwA09jYdHgGAc4Qar9NEUzHKBptWZED37u/FD/NY1OikeifwY/NBlE5VV8mquXPAFzr7EKiGbTEVXwG43lfABspc0MsXX63BPHQdPNc83XfTuajwTI3bEgDR2RJyeZsdAxf8ydEmi3TBlbiNOOUAPPE37L2HgBX03fbw6y0TorSu4WkJ8Ov1mmME/hE5s/ZzUPbYI/XNPy2PJ6TRLojFUqAi/LzIKSzXxCvy8EY9ZDOT4dn4O8c2AjBJmFqnl2uC8Tm7AUA7PSIHWXTXVAaedEqyiX3k/b/bS+7BPEDV52fwQlGaoxRk0UBailyuT2dPdqEaH4pSCbxSOeBkQLT811XvqcSHQLoXAi+CfdW4IckSx9tBkIi611ZCBhgOv+iW7bZqOLXjKUXZL1B6qRB4tG/3jQJ3L7gSxR1Mr51kerKBe5wcEJKtFPbROi9yOa3ZGBueTYTT56n0k/9AnClG6m0ATI3xDCZFa8Bc2Yomz9+zwhOYFMFbOyMGk0aIMgJgGic9HefKmyBZ7ybW89tgdZzdwjdLa3h1b1avCWq5b7L/K6zdIn4AWhi6YiIA+FU0bmdt6Is/pVj1Fu5cXZisoKdPQtZRhJ4veWMnLaUznC3y1KF5+7x5dWrN0tsOeOJU6Lq83i+SG+JCoa25MxfLVQNiU/ZnrNtHKxHGKNEz5oSkSg0wtrgwQOgKBElWo2nbw9sYDppm+ya9xDsax8SVMppRksGddcCMoZ6xh8JzW7pIlomI1/iS+1v/uMVfv1TJP1NyKeVaA1zMWg7pZscjREeobSli0JKpJNS7Lpf+cHqXzTm0u23Z31bcLYKCQGDAQcrpcZ4CM9TyfO+AF4G6vUfTVLDZAJymwx3VzNkntxUxFAC52Q0NwZOCqfcPDS2aJvjaKdnSGzySp+fkYfO4CHwGdlCPDWgnFp5OMmV+SplcS79rbGUhS6W161h4rek9WzZfdjTx+F4R2pAMyGHzyMRRm7+kaByi8J0sJWLvzsWfimySD1kF0r3GNWPEEISMiMbMoMOGaHlqrDv7EvpKpuTnb5G4d6vLXvUklrVNk48GfphEyXonLRTyjMnZIm1tI/GwDD1xhCFFO1N48+lerTpsA8ofuvol58Nc1tQTvP1vw6RtzVaiZarpRy/xLeSH3IhYHZ6zgGqKHoCiqJyGrqF4SGatOSs21IKscHIRfT6bl6T+ncyXg/eZ6JI3LaMjmgnrD0pBGe6ziF51vwzGE/3Anj3Gjdzps00dNWv6bhFSMpGIRvSdLK7FYtyFqUNIuHHwd+t2GzRGaLZ8GDhV2gY0VMgLUXTwWj+chlFW+5WaSmUrNBbA6CKQgNXN7Dovb9PLwDL8wU5hngsl87Yfcgm3fwYyspQSKgGaDzTYA/+hcCKhg/2loef8ANrZmBO9v14ub72kWBdwa54bH269AJwZQkYHqEGgyHXQwdbJApVjpGoIiSr5/jOhBOgNtgNFWNskKQsJDoJ7w3UC8BPHGz+5QJosrpro11zap4AqFLdMJaF3tUwpz82HlnjtMymYxuMJ4FBRSptawwhHv2TquSJn+a3QQbwnf0J7GT8jSzvRe+AdgT2UuyVtpG7rtz9EQ1bJGDATyVP9wJ4e3V31c8pMRkmjPhJIYDRZPvAa7DYPmdtvBpuMzRyc0ks5W624qlKyNnARcfQMhJ6tfIMVuJg8zPmZCQrd8IebBjgt043ST3UGJt4AHUaUnZikDCi6+Gs6+Z0ixJR96FHVXfjS4uvpTs0+m0z9VYbKxGsNmhRelKKZQbammSEXLcMF9e+gNmlhLdBHg99KbRfWoxHDYD51MneKyFCPNikT9Z2h+D0CDu8KPzZLY8QAVOF4CQMIbT+UqPPvABK73dzrZJ6o6sOT3rY7RrhqVweyxO8aJhTo2o5TMaWA8yAz1aCkdY5WxajrzXn7mBknZxseLuzX1FgAIZrYZAY8XSqQm7YtiaLIfG6q1//G3nXMX3zHSBd1vPIR34BbG5cTpd/2tC4zM0WA8wQWJoPGNpTyScI49gTCsCjn7jJ/Vd2yZ/+6Z+6aaUkUhhg2BSS61b0cYwHg+/jppBfXbc3Z7PYkMnlyeZnJ/zYSG1vKQoWvmjVswMHoMnwDFG6e6ZQnumlOxBIwtMebcSW5VqKKuces68OEyyRwkPj19ir+/onvDPsJwvnIOqIwLaL7kxIUSRELbDagDzZ2Pyk9KLDMKS3BADbQ1bzri9m0XJvmksNL7fNBgCut5Baaknz2JfBsDX/uimkF4N/DUJIIdpeDBJYswQQOY/TIwx7UWizYakTohASwhBlSA+PmQ3JacBC0jkjLBFPJyAUjNG+aFFLgt8yUSI/jepdgSyRhreMQYkTL0R4wObPKYXHadSVJZuIqms27FGILUQiYcDQYIxuQxg27Vr4hBFDV7xXMpuzL0Z4RqvnvXWuGjctJMGmZ7pl2lI6myYts39J9Ud+AXzhkpxXjk0Mh5kj7uTuNOmNI21KDIfZcqsbJiEzZA6E+KXzNEyWQjDlwvCIdgNwgpG75qU2TDCfk/iXkrFExuwYLEvJKMpz+nO+rZh/ulo1z2aQkdtaSFve46aUPPgtOwpgG6cxOG0Aoc7TcfXnll6ceMrCTDq97Lqtepzrv6J0KQxVivIw8EQlkXQJhILFTy9aqzyVWyF4PB40NIxdCOnZ0pAQz3Sb6ld4YAxCaKOCzGPMeirFT0cFzPC28PibdCaVXkV10XLKxakZGpKHePAB8MAwcsqtE0tZJaoI0JKRSGSkhXJmnBqgdAY/2pf87/wPWUS6xhyIXUi1izbCn6yB8G2nXQhx0pDSXQJXp5NxjHjo0p1nHudwV7jerEmEdRL4SfSTvgAerq7LbyDMh9sm2RMKsrEwWwbLeJkzQ2OS2ObMDSCdk+HO5xTt3m52pSPnHI8sy8YXphJ0dkvgZFF4dkuhyC27A/PTI2EnwAz+stgzXhDf9MQQbX3SkDWcx2nYRRpbtxkdZrT1XLlCPeKdHh4MHpcehQ7N0YHxg4VE0h7PHcHw09t1S56ygDEXLTHNQ9iQ6tIksF2QAEKa2ZMIBltZNAEgDCm0aalnGzEedmE7f/Wv/lVfAojNRiUFvw6laJjd8GyPANXqIUV3mFI0wOYBAEMoi5OOFicRJfDlagySqLWQFJ7zMpWLJ8L1k99SLk063pZzDgZQlRt7KaHZXzCiBdaYA3SqPO6+bkD+rkvkaQDdkoeKkNKR9HKNJ7ANMrIlMhwCuWm+8dnlC61+yNAzvgA2N82opYFgNxbuZ7dQI9jTnN8SrIkJwBY1c8bCGNEYzJ85BqYtpfBDuhsbO8ucDNLNiZ/NXz935FI8ZEbgltOlVGvpsmZDnrLQW0C18tOEh2hP82u1zVraLGHwdGJ2Cq8c7ZajRfHwwDiWSBwgG610KZaOC4bTkl8iqW0pGXTOO/hyyRZiVKhoek6hdRLPAC6iNnocw2TrJ4C2CTsqAI94tiZrdQDNtx0b70uAH7tcd78ItQV4YLkkD6PGpPAE8GdLDgS/Qhj4vUWQ+NWxk+FRiLaMsFalN5l0/u0aUi1VCKMl3YlxMpZSV/QpnUCFSpcygSxE58zDHslpz8mIzXaceTeUk7Rl38XtSJb2RLUHGX/pFRLi5EmPxxEBSCE5vRhgXJH8yIvGzD7Jzw4/tv10LwCXf+PSpXXhu/xGgViSB9tQ8hhKd5eokeq2YTdGqCLpCdJnmdjobumL9x5WSHgkzSJnHgbnQ3tbXsmff7KDTdpjOuZsgBkDPxhKzHMXfNmgxJaimrRNdyzhV8IGiZ1aEhhORgfVMlgPXKEOx8E61cCVXkrlembBW6axlU6fkj8q9iRMS1F1ifufR6hPizbSg8a+CBuSwNRG1cNI98LTtqcJzHaE05NLOlqE/utj/rio/kvBZilqjwSyA+SXi5B4AbBxauyHP/whw3/DAMC/v3r1fc9nbejBmdN3py/7qmfk25FcIoWH34FrgKd9sdvajXp5IXGSYQqB5UkHKDSA6gqFBHhgPsGzw8giUmxQh154tHPg0XNUpVhOpLA7k53Mdf1e/wwJIBIe23dcSCA51Z10gEIKrbEnMZ7uBXBe1warOXAjGRHDAWCqaH664aCFaCnuTB/NDKjxGoxf1ITd4/f/+PjmHbBRYxCETTkMsKWsTTCqBxF98FjmLNeSkYRcyoPxsDx5SkSSQUcoZczZhdh20TZpGHtxR9kgwArxWAJ0SvydarmW8B6gfdZz+KJCDs0jT5SsenVp8jbEs5AUFVElgbO7dnXb4S8r2JhFAwBfl+0WJAC0S2xrrr6eAcxMv2KxEUr08JLRe6UdxVO6kGV2b47YHIU/NnAavVQA+Amjp7ysRAkktAYKqStEa08/isqi80PWPA/pqAFIWdHCBCtU7gngIaLpwSxjyF9K5NNCnxMYdTXGsF9bcwhEn2xZkVSCHQ/j3s2nb062yWN+nLyDZd8bevnZrUPruDq3mCM8+/9cnx/V/6QvAJe8a08bDks6o9uAbRxNDIEhDZzZ8kfBfuT1CIBpLJo2dncXw31IZMUZVX78DRyn6M19jTUnndReoexFOV9RLylISG0XCvNWi57pLcdcriW2OdknTDrxkLW7Hu7u0kSKkKMoRT8RtqRFeey6Z7SllHJFORPMSNZGieXSpEJ0jdHZNHGBlCaQQhm0UEh+SyUy2JMAKuqKrdWkHsBkmQdUbN2mVSSW/JDE88tznKcqFbJkIEQOU1EpBqlHv4//svArbZB88AfGwCmU31K014+odIK2WqIMzDxEIRhGtWi5RfOUC8B/JbyK5U18bYedCDJooYz8IXPyMMKED/MFDaZtAmOPerZZG9S56tHSbEjCJsAtGVIcF4Cr4GXsw5nXAMKQDKHOynXpJHnWEphlUhsLPYPxjC8Al9z0PFzdhxvDxJhC915POngA82HpI0Y/8hq78wZDaBZluQkjN1U87CabIZ3wSxTSCVp+RinTzXd9ntG3nYuS+TMelmgf/Ct0GlFNS4mZoecYenakA4SvBA9h9wVIqFuLZpfVbbasHl5OleEeFsVQuaggI6/VnOk8UaXX3mAMEkk8lYBkVJ1hGVva1VnnDIByUZXOgKH5AfCwGa61wTAG4flJbwglwrj6SOKH7NHfLEkXovv/lsDXWCmGh6fJtCPMPPB3kZcvW+1UFn5gbQC0zMNOIAHCZGRLIaIkOz1ky6I36gUG0DIk+yQ8qWYDrBl7tHHC0Oq7/PNjqJyrAA9sm755uzfNXiFgJxMbmHND3iFIr1Wah+T51obX+ccwPuALwCUkTc8uEk/2jAEu9P2/ZjQrnvjEDBkIE2Nc6P5mMRsMRsgkmar+XTCfODgXEuVHYhyTJsxDAQPbs0BuQx9bjVURj5BEGHayXTD0s2VbgIGXzs9etCU/Z+V4pCQn83LrB0CVCkWIX4gfctGyhOzILWfLvRHzdFzVrVZUssCQW3p4OeoOs245pdRhtVqyC9FFaXYiFyBR11NASy2l6wcsTM8Cuflp/mwwKRqDoWFQEQBsBKAzCcYfM3J+TssmQa6lXMYIVWFzxu+XIngkV43XP7aVbtg4T5GFx0FF22DYoyWYk8+gIXk6EzC2tnEqJOrYiTbC12rknAS4308w6F8658gtkzwBXn2f/inl0+J13njKEu1azNMh6BaglmAG68QshaRYhqF3ReQSGH/i4jQQOkNLn/fV8nLlCRObeatDTrYz6RCA0WqD2B0Ntm5L+Xj6A74AfrGL1GcrM3G9Af7n/3QnmABj1AcKk+Eu3Vjwm4wETJaii5qn7FfI9VDrZwFItjHFz8ZpmTRwdIbc77URWVLO3BjqAVWhOEe+lKXXTFlLCU+LDrn+B2PY+EPbi/LHczbD0yOgrBhoIkQe2D63HFKiHibwhfLrWYhz/IxJ4KvqXZfWWzoDoDHoElv2PIJxMpbIhQjOSHZx78fv9c2g6I16edlIxN/Di01qCZty9cwoRO8ahZweIEMDSVdNCd1iE32NvLwXa/5tep72QlumH5DfZanimV4DJcZpsxlCNbwl2BouCsDofJyMw7Q1t7C3glAeR42hC8QAbmLpjF0Cy6rTaL/Ldj4M5usL4OVSuvCmxEyYHtLodE82akLmA9pI9emj2TJw/EQKsRxSoqUU2ic+0kcwL5UKhRQlY0AipUHMbpmH/a5ctY+HJnB4zIVoifnpwG+phKSUW6IlWPhsUd26bdxj3mSWSfiB35IXkrsQQvetk+SM3JngAcDJc4KXFQ/A6SmlHmRl0AjDM7rVSxwAeJhIADjpXeh6k4KhdLrmYfTfFkyOMyGNUO3JYrj0Po3Slp7FKoL5qKGQMUPiJPsUUhYAMLs+25HlqjOIfsKH5JlRYlGtKjrPnXop0WyhkOmcs4ueutwAD7knz2wNgCU5eSJ5db+8MlvaL1htBKOlcLYXGsYR7W71rchnfyfJ7/QIjCO1dEoEMmEHmFZ0rT6V8fUF8HK5zUTj5T7pkcTg8Qd0BqgxMoLuc7drPzKwzc05nRtlpPyFOBtBd3u3dN/fPQ48AtQ9hy+7RCRn6MtzCblyjC1zaiAqO0qM/gMhQJiaZ4dhSKE7EISWNE6AUuKs7jzxc54iSiRyVsgxrpNCddsDC4xzgIw89BnNphPIumJs+6UDFKKRiPZEYJSltA5F23LlLEU9XwpxilqaB+MRgwvqq16XFVghfjCGS08s8dShjccGye/ZVGOYSR5aFJKRn+ZJnwb7lIG3C20ALJFdGwwY/ho7SQBKYZyJ5RbKfohyPsioQlZ6TkcaXtQ52GyXbLBlZWiVyALucrin/L1bfzvDpyshDLTrUoku8cmMJ/IRakBKy4fmP/Dy0733gTf5XbZmYoyLmyRtDjyvfWbvtvHprHnqpnXf5jd8EvEbJgBzliFqueHDRtz/ng60EEKC32ugWUcSjAGQTdd8VNnfqmXBlxuVlJzLBRhmTsaaKWpJkAjxtC/LPEJOIOacq+KgamDRq979c/npz0k7dv7Y0LJpRdGKllKfZzpbNH8dblkiPTxAXcFsI22BToCFiH54pPC4xDmxsfn1WbmyLHu776UuWgNqZWDYmchiGwBR8yCrdE4eFRH2aLPUCf+aESX4SeDsBx2MVl0uZPiMGNI8BEyHtfpA1RLmrZ9zJBlvMUsf4Kr32g/nxNmybdyZMIJp6eTkt6xPpwRp6X70//v9wQ9+QDtVGFSinRvDMo+jiGFatLNVLudZ7sPbX18A37jEDYGZ8CHO01nMZwqaf3eIaTNkzZb71tB0i4KxwZJup5z8GHD6zwP4I2L/1TDpeMiYYdStVpqHZINFlcF+EP4zdN7zIU9AtPyl3HU+vTM4NY/BRrRUlJ0hiyFKRN2B8Dxjq9CYqw6Qf8sMJCWqGIYmnLTo/GfiAFWJgc2vJdLhdyHOEjzxMMKLyirRM0LUpSE9nS2FenbE5iLyxNkp1SR/HzDR9sshkqqUiIRnz3ofV/vjJVn+xqfBcJI6t0QI3FKKz7YIq1jzSkyk5Hyr9ckpkWiVLWtdiRIe7YkyOrR4hGbMjgGScTpPu6y3Oozc0gNwzs8jlEfDATrA/Hk0mXB2XPzuI49+0t/XcC06PRjg+wBePlJUTgpntZA4bUu10hV6Ev31BfByoQ2KcenGM0BuOfPB40FgvDziATI8vj33+U0MfPdPk7rxksiTsNUQkuVW99/v9VLxNxbciqrgNHZ4GseQ9LJmM74gai1aG+n8sdEkP2P4DP6cUmyW071BulWG4YkkLQrcLYSBSC/UMh0zEsuoshfFAyPXsQTgYXCSz2WNKgPSA7QG2kK5kY+NgdBGRgtgC21NCgahmokhJFt7ywIgsa0cDLuBKXqjLkIz01kZMOW0ig3eDPSI1wBPG6+fYBgQVohO1sar4xv/rPTp4pGilrqkM1m3kHqzJDHTs0XvyDUzDFr6GjhhQu9K4JGE4Wyz/NrTgCXdDNRwG4FMugc7tw4Hnjhb4pQ4601iuWrVMwOJKKkiHW0A9rvNf2Dn1xfAy8U1Ky6/6dlnB/Pkr3g2cA0ZmxMMpmlrpBqmps1sxcg5vxT3tizfKvyhgjeBjyo4zbGRLQWAQCab3e84fGqFlF5X55J9t/MJ0zJwyPTZs/YcSP3Ez67bbqGW7AkSTuBCNFl1sLNWobSQLRPHwmMZybo6wSfJg+2QJZaLrcYcLDt/+EpUhScYHYz2iITXjAvEECrRkzojtmmE9wW8Po93ZYU4aWw8dOdpBjj9NX9jQIR2yBh8MpDFw+/rAk/tmb31XLeW1cqoq3RF2ULtiIfw2I42OMuqN572bhnDODPKFbppXqaIPVhZX9CQ5Y6qXHV5zjbqMNgJDq9V4nDUkuug5IINyc+DhHaTbh4CIJHlVGOgwUhZlfjCLj5e6GO+AM5peLhmrrFol1zINBBON5glgzAAzJC73Rdwhjlz33oo8HP6CO/7ptfDT3/6Uz/rw5gkiZgNnAHttQHMI0SbORr4Jz/5iXRiOi19n+jfG5AOr1D9dOdL4c/Dbvmwo5Y1kN0W0nJLrJkBooJhyK0EDVZFDWiGHiYGGj4b3uGEBHu3h9LVzUhLJzl5CCrpjo6BUFdhar428vMECwlmydnSyWeXGDk7Aya8FNUt7ZHBCQBWD3ShHh/2GB5yeJ6cpoKz2cAAo0+CBK3legAD0KEff/zmY+kRr5Aq0sHgiVxOifiVbpbYnAmAKCrCzpAu2i54JIbhgUHLWUtx+haShxOGMyQtcbkSs2/fpQKoNQ+jHooChAlQ6ASwl+IQgNsX/7X/u1UAZ6Jzt1u9iWqVuHHYHdouEL8UuTROS+eGWS5w18iWvXGloKUVhezQ6uFsG8+EH8mWH8n4mC+A73KFXNHzemff43fNkLEwIu5PH9jdruZpE8BwN3r68xsvw0TgVxRVbDyzMbANoheJH4L6kwBvDiOIpGglwLDxjPC7GFVMfw4vul3XcLXoRKK90N1IwN2NjMRSY8QSTBYewljRV+zL36ScP/y5nH2yvbRyE7JroH6qEv9yHwznWYquhLIZW7p2BAm2q/UbtqJ1skR+B4KEUchUVLGWpPdw8S7n6XBoTx/CI11L1WJ4AEVofiKX3i9C+CX6ZpAfjMFTubvTa0dg9cMGyFNv+QPQRekkZB1CkjyLWp7Cj0TdUZ3GifwudueMIfCM+B+covwa4B8y27XTuWjHLuqc3YneCvydNg3csXfgNHHtOEUrij/7LJRdP8+gn/cF0NU1QKRRMEAMYj56+putbtTdhyamW8hHeH+O5wne3WuweqxgwxxPRtMmSy6YN4r/tC+Ri1yUE4mUcpvRmsGQM13PX9Z4AkiZzRP/PIy3Ala34fWgbTBUpCUPI4CQbumHG2n4CGkClpEe7ZY8qtNk+OyqZwvFTw/Pzl8nhfLQGi5F8y5Tm9J5m73qHcIpJCWfZRedh3ju5Elb9lhxBU2La+oTK1jRuuq6Q5KYPa0ALH3C4CGWslTkKWvNRyWaR/Ptjh+ek+YpPUxLgDD133aEio7QUtYpEeYpiw02P+PEfxdbJ4NVMR0/O4G5u375bL4UhoZdOyfcFwLH7gCdhpvIzdintOuI7wsEbNfEixmhq0OEeGpeOTZPh29ZCc6z6Ie3n/oF4KpvGhgGxeU3EI1Fhmkj7m0DJ2qMzBbxW61fb/yU33d5oZByozI68aOFN7vVAvAp78///M9/7dd+rb+0INeY4m8EgaUAh49nmvGuDHxGzw2efuAmPn2G5mEQzcRMZ3DCs7XdibEzaNFg7YIOnJPO87ZiJANbki0Z1T097LdS1vq5aa72em7SGQFcCwzsJDBta7RWCbwr6/IRy9qAd70MA03gPfeJx5BrCokWgxGSAswIzI5TCicNCc8fs1o82yxjPGwiPXJa1gO45TAA0jkVYpOKco4tIxg9gz/7LMH+xSQqnNLZI8+g61l7O1IwziFdCLeh46Vtx3kCOzovAB/F+IG7c5UokSGLRkIn7JZI1ELy4H8FPsU/n/oF4ApvGgxKI2jsiJClu7FlN4/xMnZmrrvdzBm+xtEwoRKCb6TGPLYeJZbGzvcAVPjNLlpvET8NqSKr2c0+O/xe84gHvtKnMZIALdmQgWtg/jME0DlwMnqm3Hkvfk7Nk1HhAV7RBwMMeID4IwzJ7mDD0IueWTl5SNXrc7orUgjGhaBFJRZirDe2kIsSks0gtdrlBtYYD3EREfo0YCr6fGo5NjCEtELn4yYPp6ixiZAzWzkeWjQRUqvOGbqqBMMyMA2cLks0T+UQ6sHWLPklknUbMtpI4JOc7BkYhvwuRrknQ1kaaC9CGtCe32r6o5EAnETUOfvmRLPdOzA2wpM4fH5ddSAdlERXBMw5iwoRTsw0v3LnRmC+y14+EubpXgANk0u4i51hYu7b4UVZJp7UzWizZZIYkZgttz0Nw2+2IGU1UhE1apXjcXuDAXjcG3Q8vkmYZu8SfyrQ40A/VSxrfVp+QVC9jcrN/y5J0enSTyRbJzHQpOb5GROJ2WGmR1gJS6Hxz+bJWeKyMjDr4cTEwxngIYu/C7T2LLtqLg0elyCRzuO7V4T189AJ56IIi/LUj3TPox5JHkCVdlnj52F4xCCBZOfRD6pa8gyqjbNunbRr2jKBJGy6Bh76ERrPkFfO6wXqKFQPCVwVgGhv7KcSnAA5p1d0nu9ilLXcGV2mqijnQBygOyLOYHXrnH3BCuPp3+3jSL0AhBwvcNcIG7HsinfgPe7plpBsEvkKfZe9fCTM070A3l68rr2xyAhgPtyi7l7L7mfDZKosGx1zY/h8AzB/XgAmCV6omUMFPFsWj5TIgT13DLGUxtproBcAD1hS1jRn6b+AlnvuzlKr4zmZ+Ydsv5ac82dIKat90aRWs4vmSfOEsTztRRlktLMZEmvmwfnAIxqAX5/0pKtTbzAMABc9fB4l+KVYihayDNbGPXcY2LriosbDhbakpVgC8NNELjDN3/eDyM2MK+7HQA+7SBoY9uoy9EMT/mQdMqRw0skr5GVOTkBZ+mEQ+BJbss8Sd8EXJYUFFoAR+MR8d1tuVEvpfBydEGnpxGqsovwA7hT3GltLAAxLn8BIfwAAXNaaZAR2Izvnfd63/fzK4bGs0Lp6HuPZXwCblZ71xqIJcz+71c2cyeMEYxsLs2JoRMGaSL8J8JtIIuStAMxDJ9l0zE3exhEhHo8G0+yVANNQwv/viwYQjoc9D5ssxGiZfmn99bFrCZAeMszFct+Tw8x/pjzkCk2WGFV+Tkt2bHR3KQ+/IyorcMhsx0uCnQxsftdIIoNGQtBaMiK0DBkmGM8APa+jKt0AAGDu06jr2JvAkBgqb3qDxHaVPac8rcC01zNLCCE2HlkP1dtR/dQem+TnIVImQlExhMCE6GDzhIdhcDJInKfmLMoZoGU8J/K72CfDiXeG5CxkC5Wu0BJ7BxTFYOmofXLyIcztE5gmUsAy4r9uzvvzmUS7lutegyE8kLQswngq+QgvgK6fy9b1szw9D07Xfshuj+uyf/M/G7uh6UHvXjVn7nPj4n72642BQ+JOFmLTPdDZ5kwJ4t5G67bvQeADIFsUubqc/hz4Zz/7mfFFZZT7Fah3gFqVbkCxSWEjzCOlPW6n1VWFcEIqBJxtKQVP+KjYaAPkAWsJTNgJv+YjSfMHsFxLhUYeYDyn0clHok8GDfBWcLYRtHVLE0vbga8cDCeeLkFgzt7rSIQ4nSqnvQDLzR+bqBAYycMYZo11BWl4Tpiy1HXVErSuozkxFZAEpm4xq25gpOvNn/309RFAqM3SpOqVKMRD6jOAaw0gyo+B5OdZw0IttSHXCdCEs7m6it0XMSM83RKyHngmPEUfDEv89wx++ou2YThrr7rS9QOMk8eZODqeXpac7HanAVEvTjcIG0k/n4o6c373Jtte1ipyZ3sdx/FHL116zRA2AFElD0MWHqXzPGhRHlFG9pYPyF+u5Ud4AfwCJ/72MpsezoamOctGbmk+jKkLH4xtXr0A7v8Aya/4It8w0T1cjCNBSGoPmyw2P80G7keAPjOaZoYHx+rK3ajNiO2tNrs4SwEmWiWME1w/38osK+Ryx3P6c/K0tcCW5MGe80TCDHn60U4CWDoWGoxwOkYeRnsczziBt322e76QC2R5wtg4aX48UWVkC03KtQwgUSc02h4fLqunWA8ysC63TlxZnx5ccc8vf/JveFDJYqDao+dtxUoDP0jIM5EnjHL8nVgeJKcxzhmL5pkf1VrKtsyTHtISSVfnQtwzkIYRSq9QhvOB0a2ou8zpkS5WABpgtAEgnVsfm2jpYNpLsruP5H4uxF/zz6yf7gXQQJyXnIcYnc2N8Wp6aEjaRMJsCjPMrqe2j/A+0PXnwBLhIU0kAasQj5ClEkXZPh76N8J+/vOf+1vMPt00zR4cymkm8Nnnl23lMMO0kfZCJ4XoDORgwKI89BfI76QLkzFkzC0Rkrc8S2GE7Ejz51xoy3MLPUCHicSSVLE23pbmwVO5MHJl5b8JLptsCy07mQCF0iHTlabv63x9/IzZnBDPes8p0fMLgSvrcvdZQdQ7gJblHaDJStM8lauB+TlnZwTrfM7E/Kp3jNtODDnhg73LGXKhkA8af7A1XA/8ZM0z8scWSbZOiL3bAo8bxBG5KRwgPxK6XLZz7pDBAjg3H/+JGwct/0V33MWYu+kY11V5/ePf/JbA21S7UG6eJzGe8QXQpd3Fblg3AcbCiDwIJ4AplCWEwec4uu/vDWjzRPcs3sjGL1GItoQ3zZY+Evpvw/Hk7x3guWA6uwEeWm35OR0/qmS5lmeKcpZpxqLz5IxEG4GRZwQreubynyFgMkBL2tZoSMzTPPiv/NfHH0+5/M4KmJRY6NxsNoD0Ncbp/rfMWXqYPGX1WMGZcLq+sly+V99LJ/VTh7HJnfRA4ZeuLpiQpecUHk7LWjI5XgxCCCGFOpPw/GArnQEpipOIkjXDw07Y0mlZdEb2/J6wwCf/a/b1z6UA5D89F+MtcYanYxPJLpFenwB31y+fOQLw2Lt+HJHdsd0OtYdKw/XABggj0Vl1mD4zeYn2+w9PtQDqTVbpXirex3QXqK4cu0KyYJKaFy3x1f3x//lpyj/+Xt/bYdebTkAakeaVNjfErJhIUwhmdPgNK7/fcC05RSUaLGKaSa+BahYFa+aas/B4RPk9/Rm+TBhWIir3nNH32v/kU9dCY3NtR/OchmjLCmVzbjlDKKqHaAxnRciy6IxyR87YgzWMDZ7ICo0ng7O3KaRyJTICL4Xh2BEyJIaknaolnZ9mk9gs84x21XlOu6VETlIi3fIek5eviTD8SruO/Gzasr3jMTM8jHterncAjObHFn8abNF6oGe0zR3jW5Jrq6+CR+ka/pw+e1BFam3wn7IGxjMPo64yymIT4AyAJKf+HYjeGDCKdinZDO9Ltx7bcblfYHzz9vT31dkLQIi/xHLpidetFOJzlYr8KsKvVp41yVjuMxhP+gIwBF3ptIHbcDSX5ikxKMT0GJoGogGiZXlqG0EA3+5NsBQeE0lEiRQlGFVk4yGRS+lZryiPp79EP24SeLn8jOwvj6P0AVRJqj4d4CSM+YE/AIbwGW2Bp4Oas2UpJw87zJwZjotBNCw3sXSfI2fwZNAx0KrTAxfKuSqWSC7q+9IAM2ITcua0xOVmTIsC1wYj2gv9KjfxywORryUk5qrw8EskdncPzst/cC18DzJaFZicDKVJL7nPXUfgyVXgzmq/qhPVkcAI0Xla3vBLrcPTz04GY7z6rn+2fIhGRT8YJeZfD5yzF7JTYtR7L7oXCNjKRWVTtkk7Z0fqUe4W88vPr/7qr3oBeBMIRV6HspTggSe9AHwJQF6rnN3RqldiOsCWz2A86QvgvLQNXHN5z+T1FT6xNCump6/tns4NlpkztZ7XBrEvoX7JIfBeFWYaP0xVxs+TE7lxjJlHaWyypJt1VYy4aAP9HYeyKqU87K4QZ3uku81iPvkht2TM5tenrKTdXZt5/S0LUoiugfTZxmkPU0uFODE4AYcTFT9nNz9mJ1aoonfx661Qk1KG52QHZifwGUKBaVLPZ7SKYBOYYDzZaekaXi5DrpDSxmBPGU9815cfAIOla60ZHrorLkSipVeawV8h4Pw39vo+SnjaBc2GyaBJVBm6GjPYKdGWnj+bXsqMwJZ5MmbrLYY84wwW4VI0xuMMXVx3mRMT2jlcGzg2BeM2RO6+8/T/a3/tr7n1nJ59CclaYxFimwBwysXv0vTNLPKytuuWz6O/vgA+fWJy1c2EQTmlm9nEGNDuW9HG1Pz5IZIW/YM/+AOzWOI5WBsvKYasMQUwkaYT525jAH4APJ4RwN9rCmM+bwOEpKEfVc78c67JB8/84aNi889Txc6kUJ1/rn9nJYXYpscizQa2944a1fgRAohydp/zdDjVClkUD6d3JzxjV8GycsBsOjxCBqRogDUDFjJ+GiBCWgo5+QGIxjDwu7ieMsiRuMRFLTl5ALBFIsTTHnlgArP5k2zdyuIBqNsmh58Thp9eV9ktA7Dxq1WJyLPnYeSPsEQ2Q3qhAcLQSSRrMliEnAywMK8Z1z+dCW0XDiq7ROXIstiihsc96K9d+Nt3Pns58BjcSr4KsOHvvJdZ4rflPEWrlb9mnlx/hBdAl3YX0pIYo4xs0U3kkBnB3E4MHhPDMLK0gfNA6Vtnk2T+hNh9SLckXgM+j/h7/T/+8Y/x+Kt+Hm0MQ0mADbdhNeX4GTyeEcj9EUKfDavL79MNflm+3op229eMObYFeOB6nuZxY1vCsAmkLJqHkQfgDl5PEKFsOj/N2cNIlqV+RIEJuwaWmOfsp+rB6BIRZqCS6zZ2Gu5AtjO0XwcC4BgB4nQyqvNzCjGQSHFoPe8sgRMpdY6QdMiF2LVRk3QGpywYPHIDM+ocCc/pZ28pFEBjjLbGwIxTk5Erbac17HNrrwEkpoLTRAHA0zHLwoxNVpz0VfVVWlZd20RRWfB4CKAoKSNCy7q9I5fNj0q3NKfElZbIpqvFJpAnIYakkxRCEjLYlpxsYH525dg8bHV17hyKOgcSTJQ4SemkGTASUgyMW8O99qMf/cj/AdghdOD8gZE4XpwYFJJS/2w8/K5FVDxSaM6JrHieR3+EF8D/katl+MyBCWCQbgwe49KcGSx+gEbK7PK39ITyR1I+knicgZ2Td5NdbJD8ieVmLoNHIVFLbAx4/ARDGywXwHLp2fRggdPBZsdP86QZDxh1z+hycwJHMn97UV0oZ8w6Z2zXw/PboKVb1xk6Lre0G7gHimiPyJ0YfxXxdyaWyoHlzykqhXR6+KPyRODsMSFLCkKhbRMAmJ/O2Uby0IQngSGzhaSQMIVUIWgnYe7Uq0R+KcG0xxCNhB4PO+EBYytNw9N4si1rybIqlhnzWM6eMZhoDHnqJ896a5vRnvokGc8JyJlH6aqjJXLtwtYIu4MCYItK4XGxLAF4hH74wx/6/ce9ZgBOv8sKANYLIHIMjNmVLqt+vuqvL4CX0TcljYsZ6hZt5syTjyoTjyoT2VB6rPhroB76nObyr//1v+6PAXwPkC7LRBpfY0oj5+QhqrA3uwweGpsqEn2f6FMPsHTgejO+ZPi3xuemOeSiLW2huvmHqRZn5cKIWrLby5kiRMKnSzw1fxj6Przr+auQj2O27JyJnQp1YuxKRAiZiDoTzJadYTCerkhULSHhAbqCUlTnKUqX2xXJnoYcgDOb5l9ozrLqMDuYZnbt8o+h/mkYuhL1xpaerlaFco6hEsHO0oH5T5lzhmjkJ2ycYKTTQ94yJDujfs70BxtyhEKVi6qNd7H2bm7aXUdR5yYqa7cPp34s+7Pfvih3v2DuWneYaU4ptKvfVag0T3Ufun3a5VO/AEzDpBmlm79GULTbwNCYVF/kjSCngfOY7l8CMGGcfrHpBeBTrbmkYXwa9XtlH+0xGO6msHtDIU6FLFVho6LrBCc8kuZY0U0wAHsNx2b5fWV7n4GhKukIi9Z8ADpngJy1tHRtFz3J2QCovOGKdv/TTsxxCcE4DQZhWHZKDB4HwiCuhRIEZmfFrg2ACsHLYkM6aiecTd80128y7Lawhhmipw6cMxg9qjxFObUxsSQAedoUj36GF80fRsiWq8i+CV4+9QOURceQZ7Cy6ufU9cATW6HAEeYRRVgzeZwYo3LlngyFQqbPBiAflsjBXIie3d1lNe9KmQqlhfgl1gyjHrqbfF8MBmNsHNS6RU4sleBHS2PLFkLFJnLPnp/Zft4XgGlw4elkY21pPohBKWSSjKAnjk+sxqux9gIwUvye74bSRxIvAL/+++He/+2rF4BvBv2+sTsB4Qo1oBg4TT+/gSZK8CCkG26dlEU3xw8jO87552G0zYUyVMd/ygNgS5jsjAjn0duQM6K1XO7KMTxz3cwO0PnYrwN0CM4tvw1KBLAkS+S37HA4nbAsAszvoeAMYUhFaa1aooLxIJA1fNeRn7Oz2r4YcvlFSbYlg6iSv9A0Ix4VGfCQtLqyggXIHqFoFflJjV2V7h7A8lsyLAMveuYCLFpWHs6Mcxlh+vTrXw8NJD+jJ6Y7ourrUDQZieUafg1e/wTQQ4LHmbjuPZpFK+cKEkuAUnTCiBDGtPjlh+6CgpGY6ebQJKjCj1+iEqsCw29pBoQix//k8mman/Agmh4bPw3DYVBMCd3omxUPKbNFDJ8RZDRYAD2yfdL3JeDXf/3X/bv+wH4Iot08cu+8C78xVdGYNpGNY/cGjyW7oZceMs3PyIbMoLOvwOelcotLUYJO8sefzn9WrCWeBICHreHRWs62cZg8saW7UfntzkvOPc/wcu2/kdA5O2F+705H50GPivSYAK40ABJsHaBmXBrRHiLaqD0YJHItS3RZsUESRgden/TZanvJw85AtT3GmZ99dXkLQIRCOizEFqQt9RBhDKsLoKvSOROYKsotq6Xo2UzgQm/1ooxFI7TMSfPMmd+p1q2lTmDaY85SRtiSLjeqm/Llxze2xL31HY4tkF1uUU4aySkw3Xp9brAEA2Co1SGzd4BKVIhWlF/z7kGTdk7sOn9a46lfAK5608kwTGyGYWKYFaNDzA2PofFsMqa0kGdKYLerxG4Mo+kHyt/4jd/wRaEPILIAgIWipatlIjFIhCEKCdG9JyLsCdhtUDl6xprPY5mHlpKdcQVe3xMD18lF9/ouCUznpNlEq7TeGHhu38XfFnJeBW6J7XX18k8pp0dp28zppnWqtEPgJPbu0GiiaM1Ib8ngYctaPx0gQqGeAkIt4dmcXirXQd/ft4R4iGhXMHxVqkhbQlaFnaesMKI6YddbhQrpvHJCdZIOzMbDRhszWMacMJUucQAwHlLP+fPQS2dYXuy3BGDOGXL4/JYNRm3DN+qiGqYBwtAt45/mP6uwr4Rjp07G3UG6Ft0g+1yveueG3AaLdrA82NaGDvkJp5SaofmRqNI4MQDA+HncvzxR8X+Vp3sBNCgPF/4cULYBaoboJixnI0X7MMK/j5bNk2H1yPZ31PwE5POs14Aswu+jrj8wuFk//Zijh4a1Wuay0edH6A7BL7dWN7IIeaavAsfdFTjAUnIGG3gkS2FIIRfjq7T9Oe/4dR8y0j0gRlKeJWPgopGw7ddO23tfp2h/s9sROYROA0BpKTsiiezuZ4aTIV4DbLXoqkjkr+3VtYQE64TrTdTTxKWpz2pxiib5a2OEQtEOqWHV1wAAW6GmBcnwK8TTg6yiUgrxS2Sv6ADxVz0wBjD4+DkZ6TzTp5N9bmGYDFXq36Z42D0uFUr4CZjqoifzA9XDMqQU6ThJO+JH5ZLRC4kqV8iAsddMGLuWHgCnKH/9METvCpfirHOG5RIf2nva5Ud4ATRbjQhtSVxv0nXNMBmF5uTJnodhXMxWHxb62Cir28xzX4oPEZZ+8DG14QH6M0lPE78F/c2/+Tf9ou23Cw9xADB/SRTG70L9KQJPJUQV8uDD3OsEjMekuh/iZAjxKy300DMGoXQGe3Kfwadz4IcJFk82f0hGmwrZTajVh6Jl0bKEaPiEU8PZcZ7RzlYJzp2AlF4DPYudLY8TiAq/rE5ACr9DgOkbACq/C2MD46QhVY8Eg1xLAF2pQvfZs4toKSTF+QPHrwRj5yBdqIZp0XYHo5wlYcSAMHCY8PG3d80D8EgHJgzd0lLylItTOlti/mpJt9RehcKAMbIDRJIHOWeSJx0mrQdGxzW/FDawZuqHTTgLnciBkZCQNL+lHvRMO3+HINFStL1k8xMYzvD86roRkPh0BW+JLbuv45zYHI6UysFExRmzELsJqShMzZee5omBse3kVDT8B9Mf4QXwF3FJTIwRMTQufKKKpcEyRjx0Q2NYm5UMDwIPMv96MN3AAZvCbgM2nhKzm0t3hYrILQGAh4mWZyP7ffcbW4RV58nIaZlwnh0+FBrD6V+i6CvN9c+3YE6JtiPUvWppU06JkZMBpodkdgcIQ4SQOKidTOBu9Q4QLKqY8QCD1QMnmB6IM7cUqgSYJb/GgO+CL18vbvinryBCPPVTSx7rSDhdTdKEcOaHwVwDsmpgJYQIP82ZxJ+nEvwwZNtkX5lvBPLB99ZzAmrv9GQ/8H+ZRIqeS3xA4umGokm0tBMju5Q8ZCTZqLqtfLryvvfu5xHqTJRjexmglUicvHdGdxNnncAk8A+91fCpB6jQGfpg9tcXwDcuqBFpzXCPdRubTtJg8TBavgzU/Q9Zu+HNqL8R5D8PZwrhjaARN0k3zfV8qQqPCa4KpHRiCbaxYySyZtThgxZ98GxZOcsaZgycRxs8dHIi37VLj1ZKmJx0wvlWCnX/Sy/Xlh0pmwawfTa9dHbPCAASPpvGBrkUDNtmfiFONo0n2spBukB0WdMquhYwgelxMlaaHyaRy+CR6Gp2QYF9DlDUO+Akx1/bOSOfFuUn7a4lXfMSnUCHUAP0W5HOSaO9uF6XnDzhTyPAWx49zDmSB/B4IOFFeZLlMnTuoUwYwSDtKwkpS4i22ao4VafnO/Tf+Bt/w78A7KdC+A4BsjNnlM5w/q4pqZCDigpndc+W3trbWoYsmDnf4n/ZPV9fAC9X0DXuYrfeJPnRhsecGTuzZaqEjFSeDInEqNFg/sjXnwR4AfghqFkUQiIEf2OvqcJASvT5RTSGkDRRq9xGMEyh76g3x6srka0T5CPRCXLSOZw6PB1Vy9kPyBFW7iwaEkBdfhX1QOZn1INQTntnSOGHdAMX4mREhY2fJ/FREXlt8IAlnsiMMB4o7dSy6+vKIpHFIwSZZqxKtB0aWJ1HTvPrFsl+l6iE351E4aWXpcP2klMigwZovyWqy1M5tpRaCly3/J+TyEUZJ6Zd8Lw1TtjswfJgS+Z/MDqx+Gv+NeP6bdPtYI+ldHRnOnwivSjtuHyf9uj/7d/+bT+ueqGOJxgGWao4Hx42j/PJ4BGieZTOuaL8byX8/JZfxg/5y2g83Qvgc9fyvMzZxqVRc+/1izOP25t4XphLsASnwWrCeIR8Cei/DuT54g+EPX34TXN3/kbTxPBLb15pHnMcgN7dwkkw/J8asqiUJvXGQyrNqVB6Fc/lCWC3LAVbRv6F5leCbTsexCQwJ4/zCWbpkG2fcwwR1k/+PJ2bxCQA23boZWXQANWiA2NI4PVACmmjMehCiMKjHQYsJ6TBcKHNDIDnFA1sGISQ0zyEhwjp5LXspw/1AGt4zMAaoHkIzOq2HaG3Aln0TrrUMPnPXO0t+tY4kW954AdwMi15CPC67cbpJHMCB+uIuuLSZeVneIP6y3X+grWnv3vKKwQYki7dGbasVrmqdOYwarF5CFr8X95sDdAZpbT8ePrrC+Ab19TFNi5cjOasW7SJYbvD/dte3gfu4YYYuPHaVPEbO19a/RDkBSDFHwh3xzayQ6rSgFYOz9iaV1lCickm32j3WMAcq2+Yhc7c7HnOLeuNVDGWkzl/ifnzpMOPdqGzG07liI2396KK2iw/zeOW7q7miefu66U3JTjBGA8i6wzFWTn4kZRL++NETllF5Vq6EGjZrkKPdQAePPAM4FqlW1aUVvF+wl+fD2JDyCAVjQesy21JhIaBz1MJMNLD6wyF4Zf7VkQRhlnUEkPL+mFnbDlwhh5KASCW9APmjrw4XVP4hH+n0XXRrb1I14lQA1Cr7ZGuSgyQvQD8/uPHHwfrVopBrk8PbG9ctPj1Bs9wyQi/aJ8wcnZWlXvYwpai2Rltds7BPozxdC+Az125htiVTlo2XsbO6NByGWbLY92fR0GaQvrkNGrE2PkM6AOLee3/A24cwXbbsyvRPRBDHiVwwldxd2Bzf9Y6bbnn8l27rQkx3GCMsmhLur2wqzV8yKLLOg32w7K7Mf80Bv7d+fzdk8sV2ncCyFUMsCaF6nwdhqT5k4raSBiXg4ctFw9xwpb9iWJ+IXgt0QB42K4mW8jlAHbd45EC0EHxgFnC8NsFseSXu7q13ZZ7eIUBlhVMNFpg/hjqSihnfiHIEtlvpQ7f+k9PDfDMOKNsJIq2TRjSaawuz1KywwTrRvAQ9z2YxxZQAUgnNuLEugU4hciKqlu6//AnQSLakx1YiODk7Bpx4nfH+Wt1PnXxY8jZhzCw6nKu57cGzOm0/DL+BP/S2V9fAN+4ZK50l7+rbukrpznrtjRP/M0cD2HL59w9bOz4IY21h4XvAX7B7F8MLj1+zAln/lfHyyfQyE9mtUjp32j6Xkh/66y3QiXSGfoMb1lpS4aNqHKmvEv7rc6qnLA8+J0nLXSd4OsHWNHOIQ1Ash+oQu4oLHVbzwzHTtvdPKV73Me5dAA9eDSc/lqKAbIqHlJ6djW9RWgYjxKEdIXwmBM8YHqWDlMDaVRECFKWqEQwIkvPNFs0P4OEl4gk4QQuBA8c5kJ/H6nWmaHKuZydvx44S6Tf4hdi6DaMbr01fW3y52E8HZfcoozOtl2UVchJJnKdOUHlkHsBOC4p8XQ5gOOHIZy6BcPJ5nG9VJdCKrQ9vjVgcjLQvgV8GM9HeAE8XCHLZJdwV4t/9oNhJrrqpmSJ8ObGzHlMmFRi7AyTD/U+j8CbMAD+fhlgy626efWllW30ffxx2/tsIt1DRAmcVWmU+SERnvcAm5hs/p41MJCJdFG6ZRMf57ta7lIy0JLARePn1BW/ZSUWtWQvq9yQNP9SLGuMR28SRUnbEeXhdxRq7aEWFRinU7UEwMMD7xBIDViKTi7q1ycsQP48tcFGRS7cjcRgCUxrQGMqCvG4jq4vQ24XqKcYQPhGQjMKAZAeQHFy4uFkIKdl0Rn1gDmPFEjM/Gj7iYNTS5xgdQV89f26R4BxFpqOturBIBMhfjaeeRil3PSXKlTu5irCkACi4dk6t+ycHR1DiDbq/iu5/jzM0t+MEHIfDVknCKUL+VbtPOPMcKRuK5/9fYrCphN+IqUSqGrPWSEhojSSJoqhihvWwdISLcvC0F7SkBnt/Qw9AN6Gfqk9H+EF8Bd6Ae65uj7UmxvDoZZZYZinhq/R4WFkN2HsJthrwG3gxo4khqYfkrAbR4AYYNS1JBvlMPVwagxfOIFFz5R6uNp9nXtGW0h/gfAhVCJn/Bfjq3B2enrgs017ofl5ulEdUQIQMz8qAtlj0cY5pZCzUPhTywJ+rX8Rzo4fILwlZEsNeL4THk8QmtTe0i1dcZpow3WhwSoxznOZc6GVzlO6A1Hdy6adwnQ+tbfqjPbOeOCxfOvMIzRZM3ksF2Is+t2NM8s5qBhn58N2nk0+o6d25CHZsmy/pd0l0eYEcCwOh0A6c+8JMNFO/r4a1+WIWe51w7yKKCSn6nxj5iSlfNVfXwDfMgNGxwA1Q8YR2sCZLQ/0fhAwmjxghrIhay7ZQn2E8enGlwYYWfyNPliJYG57Q8nPqQR7dYUIpyh/AEs8yZenGSYwneSJUy7JI/oW/Jr02X9KL1Futj4JZ+dgI0I95R0gTLsOz+MBIZoTmCH93vT1wojE+TOEpMdAnz1hIzx3/FL1sCUjQDpkhXoBeMpwikIyPGvqoUTV9ZBNE7kZUjS23jjj4RnbDKHETtVlb7Ns+yWM+CsRHgMjLcpIir7VVX9FfXrErz2hCDPyv+U5PSHnsZRF9Mm+juB+FvPYhQ/+/uTW34MQ8iV424QpkQesOeR0IA5ZCD8GWtTt4xdU3x6cVd+6YNhypVy35eu/RC1FLpKcDRKnpUsZDIBglp6xvTyt8fUF8C2X3qB085shU2WkaAMkzWAJMWBEczaajbKnG/Hzpf9uhG+ynv59b4Ax940gtgzO5r6G+JtdtwE/PB05g5x9Y3jwnFH2Gc2mM4rWA8+MB4bPLUspi9Zh0gnwAPDYBbGL7v/wITHvhG3ZElIImFh2DjDh17bQGmavB/aDCCWqC+GRmLB5kLs0ov0I0y8VtQpWLgPSI4kulyGUBuas4Xk4e8oPyUgkKhqnHiCJnWJgiBYCrvoKvRJ8+mehrSUuZcYZzT4J2Ss35IMRnnNGtkT9c2rbjuzXG90ju/9zi+F3sACuqZDbwR7NNrB0uaRETunrhB8YDwZnjgHA1QFgE1knVScfVeT1L8t9uopCGEjRr/rrC+BbZqBRM0Pm2ESaSwkGyEA3Z/c0Xg+Rpsr0N8eWDH5zb459Hfb/C/M9IGc8okgSniQqsESUZyGGijw505y34x018ENsKYzdDzMewF9YSimLPqm0zaO6O5M4LiTtKCSwKJiDFeptagksVArd3UvLcv48DAIJlljW4R251NlwS3jClnJGe+54lPCLdqE5NZwncBuh+cEmi/KIkvhbip7lOMMz2qZCxLHUALuUZUGSOhdiLzQjzgd9531Si3K9tb9MBb+sGVLGrr0wnK6Rz+zX39r5wQ98RW6bjsW5Cbk7ZL1M9v2VTqL0c9SBOSUCY+jp3xE5JaEOmaejW0uMXeJI9DNyUUtZwQJge3L5+gL4lgFohnoumMiGj1Oa2eqONayx8LNJoxbM6Pt5wTvAKLsHDPFJIrFR3sjmQWJSiSWeqFS05Gw5LbeQ6LsSstCoMu4in9TSH1LqZNEZy8xj2T1GY9DYfR4vB+K4ADgTttPQOSONRFaJGVKEyEIrnREsBh7G/EMuylPpIWsJYDxe2GxtQzIgaTY/p4Zjq1Bs6RhWtCw65PwZqBhOiTA6JcZIGCFzLjRA0TrPXgrjoejD8gHf8ls1kvGslkvD2fkYdR/YfdbxlddrwLTjLMqwR2dov+4mWYzrun7z6T9aSLebG0cWpGPfvaYWWLnh2QBJ58kPprRlI7Tdca7KnE9rfH0BfPulb/J8UO1hUYJp80OBX3U81s2oactvuHtSWBo1o2na3AlGmZhpgCaYJmBmlBMJm6fJbtkcB2uaRS3PCT7teji1LMsNPXCenCF5CGYagJwMX7bLgpElnWE7nIzYSmc7PaHOahvnKYtfFuGBdLwScwKEjzP+su5mX7r9XNv5VwUnQdXVLBpPVWiAirIDMBIdtqM0GOGMs+U0TOlLEcpWHaEofTV0iyXAS6X7H8AtVxeGjJCx5VtjsIXmORPZa+wEnPYJYOtHYyWyPfrdCD7l+ODvL+0Q025PQi6le8dVA5bCSfNHyJ+01Cdh943BrSSr9PPEAIhQeGzuIPcjpHKR00QWUaLqaVlC7K/y9QXwLTPQoJghg2WMjJ3pMcF+jjSdXgCGnmFem0WDiNGU03KbPCGA5L7Tr0/EBM89yS8/FlnWzTncwWhsCUzIYLVU4lstRe5bf7n52RNgdv53Ex+oBuYvN49tMqqen+00dG754AF2OLt1KwHfNoF3MpwEz81x7YsRfsbpLDQAns5fb2xU6opaRsggeWhOsJzADOmLWtZMyBPGk6zzV8fLP82J0jUzQ7m2JqvS0DBNEZuzfIZy5/KMhnlXL+WMxnZ6vmCrK5qWmGjSE9/Hf//yY7/b8NiFzj2U/SUIhrMCbmtl4elUT7ZKg3U4Qs5KOoNHVGgNzFYFzAj1uEebbCllRWV1n1brmfVHeAG4rl3Cc4yy//cvLXL3J7bm2HDjNFU8PnH4C/4+1PuADwNpTJvR9WPODCK8mXN7+Gos0WujntlElqW3CAxbbmwSDTSxJJbA+OlsWUkpnKTS9GAMMJ6BGW1BKCmkAQw0GfgE5FwI59kP5BJh6gShWiHtEZ7H65OGD5YtF4BNnC0pi74aup8I4elyVwUm23FBsmnOml+hjhe/EJsfHjixFOKnz30VLStaHgzEciVKbwlQG7J4IHlwMoIZm0gAjJYj6mOEJb/LXXrNSAHgrCJAJLVkSd42Bkwgk8AIw9MBaKE20pnwREjLTUdSiEeKoytq/vvs7+/8GPK2CSmqbQJs5i2ldFm7ZezIroXMA06JwBI7Cj8iOaWb4PoIzwBARWBoKWXhYYRRBaylct49jjdwWWyYjovnQYQePJ9bKvG50C+R/yO8AP6ij9tMEHPThNEmLOe0aSBNnn4aspyWYMtlN/cMrwd6/cNnS0fFjmH+E7ysnPhlkWXlL/fLDMMwesowyEqwH0pvyUgqzb5TX55HMXAygo1zoQp157NtvL2XhXaJonvMnZwBrs2/fmmo3GpVwlJ6ImVO/tMuqx6AhRZdJ6W0nC7xAY8hPwOnKLw+PZsiOcn5A9NgQrVBdz6uslBdhXm4XjUzkprhLItWIufqxlPinIyy1FWuinIJvGg2wzPa3/j0ycZf+/HLT3sUFSIMDObcU7jmS4+Tdg5EaJ1zdoPQbV80BhiectuLEFGld4aKMJac6mJuF8Bf5d0T+PoCePdYHp3GyEiZJ3Ns4oUb7mv67vkDMJelNYLshjUMbYiJqGH1gykANktSIt0Ez2mZCOUcmL+sPIY+4dwdEmGwEzyShcbWLVetooXOFPbwioLRDwBOGJKfTkKyVzrb+QDv9mYHcBsLLXe0jBLpNh5zD8TwMUTFw+hkaMtoOUnIkQdbiDFCVcLz1MOM8EUL0fD0pCjNb7MDA5zMOIVIj0JR3V5Pyvsnjp6MoueFrsT6rCsY/lMHO3XIVccpOqfzVy4GzsFg2EK+E3v0+1cd+90f/iSHMeQ+hvuML1TPkbAJv03Z3bIcC1p3mW8J7pRdLDANSAmJBCEng7+22ajybAuWUpb4YK/u9zXOZr5v7l8e/NcXwLdfC1eaGCOPb19gjaZpM6ZNW/dkQ9awBm7g0jzdwBggjbWqnKafn0HqgwGQzlh/F+gVdjqzgZMNOmM2zNIjOUOiN/ZStoAHho65UHY8PA+d8AyQcQKy41zuA8Ay0QBxvAS4R4BbXfShRM3MXw9yX4hufM5pRvKQFbMQfwzslRthWfQDyTxyS1zKHoh5KtHZ8iiRh53zTMcG0OO+x1/z08kMmbEtZHQRs8+QeYNPFq03y/XPjgGy3s4ONQBJ3Av9677+7JctS5+irhqRq5xfePyLYHXOcxYVdT5rVQlRGAx23cZVKYW/EC1FIZxtB4YxAeBBQjijjeS018l3MXAO9guTjOEvj/H1BfBdr4Wrblh9nCE+m5iwTaFBNI7mNS7ICU/jyDCLYDQPBgbNExjbZp1HdCJ0zt9Dx6VXqFp4CFtI7onnOZfZkdMEfrJooSW+JRmgEE04pRSaBzl7VIyWYEK2bKl5h+kJ4gZ2REKcorEtZTwAkHGyH2CnXwqph+zwYUqsnOicIYcvxTLksiyJ5ksMrxbhsbQ7Rp4HWGyi20h4SwY/5nKRmEPpMWC7y35SYEQWEc3ImeaJbcsz+mC7CvBdFyH9JBhcIz/T++xP/PSvlmF2d/hO4KpJdF/4iOPjv/88J5KVyw7PbnnWXXtCYIRhv0qjZXQfdZ6cPEPKtYxB4jofp0Knfdb9vvbbzr8vw/91/NcXwLdcAteYmBhinsw0cQcaRMteCabc3BtEt4ThG+Nym1H+JpLB4ybxFyf6EpC/EqUbXIKfMO7612TXzEMJSwAaYFJ1euCMkPO3jJ9Wq8Qzi2dZGaIxtJxz/rOWlmwwDONkni0aAO1Og+1Iqx6A3rJaZZ2a/2FZCt3uiqqSfz2ciUupimViL+FXgiFEk8AZt+PlRy2Akc8GyN6ZWOKnhXJquI8IPfI4iZEAM0IVCh9/HrYoJCPNSALQCed64MnOacnAU2nL3srBzK2fMT3r/QGAPwEGc1+4C0QNtm8DqHz297ckvABqWEgzuwQAUmh+sk7YdkcYbVZIlqUGiCWxdA8GRgI5qhK1vZurlGkA4C2/iyEF7PtmfRfm/7uYry+Abz9/156YyMbRYBnopoFhae6J0QSg3QyRWhK5OTHwG2WaDeY+EULCSTibMCmWkVcOmJNGGPn0UqJFAsnmv+tfeJ6cM85RzplW91zGEwM9KZ0m8KdfUc4abss8GWBCgZeVJy2rRFEezbiHGYSnrRVic1brjn+jDZhghWi04TtnPcilwd7t6mzypCrlYr8FZ54VGqAtQwm9oF8Pasuy6iR82+fXZzIbs2mhx9ymVpEBTBOcJH56FTnZYejwdOdZIh0mpzZkKd3negPpwc3p+esbgBeAzzFmlfB7GRCD7Wcf/+r7n/3Zn7mCNawKjETkbZPNSVZOaSG1vFrQ9oi/dnJfLDyQ8AzNdBrVdQPW1ZpHziMRfs5sy19Mqv6L5f7lzPr6AviW69J0Nnku/z2KL581hCyvwb9fAzQuyIQNQCzNNGFwNpFmN39OsJi7E4KZ4KSUkNEOZpkHQ7YQGeH8ovzDZLzV8DfB9bQtykNOZMu03sJXlLNu7Te/xEIPxsgZZd2HdKnw9s7vxi6xu12oREalKwdZ6KHuoqsCGfg0qjjmwJxkzvCW+QsNUKElOr1gdpGTh7DTjEQiGU/9nyEMAYQ8EEtnOxDS1JWuQ4n16TGdkbMssKjqrSoBUFmKtmRLAcNfA5aqq9uj1gPa099P//7+j99/fMyP09O/fzVSA94B/tsnjPpEjopYRq4WJ2HUId3W4vGUt9QMciECnC1UwzfB9ddMvWna9fgBMBMp7Ikl55bPbHycF8CuqKtLzErXdf4Z3+t64zGyhsxUYWAYMneFDxc8lsbO9JtXtrow8EoY3KTbxg3jb0n7P8X3e6iQdDCflXrGSSc86TWJM3A7Uvfa3utnqMAq8gA0+vXJSXiEsKUZRUtkz19FtfIIBV4KflF6DEgsTzxwgLQGok3DY6ATPKQQkqhiY7cXRw0cEhsDAxnhmS7rfCAKYSPwSCwZVcxP82evuiWkq5w//mWBZZe4rEqoLlotiYF5iObjXErMEgmAJYzxAOBZdZz8nCPEPwlWz0jmP22JABgiqW7ONLDT7njntySqa9sMG2Bd+UsQJtDD1wf/f/JP/snf//t/3+TD+KTvEezRD4kK7E/+5E9+8pOf2I6W8MO4U+TqwczTkdMAitawPjHggaF9CRAC4KeRSGQQzWiD4R3jTaO6qFxOYHXV4iGWBD9hIFSU/l5SOv29sv7ygz/OC+Av6KybmMi7/HRTy7hH8fpcw4A0nebPaO6xG4bfX5bwoO9/EumFgVBIikE3tW6YITlJnO49tw0AfA9EeLVEhaScwt8jJnKheGgNcDLoU3iSeAqVOJglG4xWomUYtPph64eILoud8FQdjKcbkscpEbT56ZOfX5TnxESOBLh+6IxCkWQ/6GBLFL1TX9Tb9AInSeSnnz1A218DDKJV/WfQAzPKpfPPkBLMES1FtEcnJ5sIudaKsk9adlk9HJ02DA+YXBKYh7CXjr9lGFGhop7Cfag3pZ6z5tBn/3/4D/+hp/9v/uZvms+f/exnQhIhvSdswRPZr//AaC21wYZk1EBVUG2/+dPq1t5a2jDYdYRC2Up0DnV7bew++a7ISfvVfnsCX18Ab8/kG57rJjjuMbNlsJo8g2jJNtnm2+gb6x7TZTWIwdwb/fsyfhiFN7WQxlpW6e4NSAxEOi0drM9Qohik+MBVf6KE3SNSKM+0EJ7dG9tFgKI506pzirZkWCY5z8T8kN1m6WCcmu/BB2ZZh2HsyFK3JH/nAybdNlflOoj7hfrSxOs/AoSPn85Jz/NgLDQDgCiRkY7nwV+HhdSd5KEBerSxi2Jgj0eVllWhwWYzSmQ4JTbZ5XgAlwgWEgz5jtRnBTaPadGS4SSQkfC3F56M/Dh5RAlbSG4Y2tOfaMknGCG/+fzWb/3WP//n//zv/b2/Z3r/63/9r338V9FvQRow4T77//SnP+2Pf6XoYS8D7SnKmSiXcCpB66HBYJOinOw0AxKnG0d7Mdd5IfqV/vpYZplky2VU6zXyvP/8+gL4lmtvVsyWcdnEmDlPMRMmk7b0JdTc+8wF485xJ7hhGmK5GZAeef2yyQlG+/iMH14uTyX4ORFiJqZcrhDd14taAqh1yzwwwSCFWhZtOadQ92HRkGnVgwkti5HkZC9Fe5aySM/09tuO2jUbxuMDuLr89lt1e7TMXxXkPO5wS9HI02sAIPA8tbTlgyEKH2aJlmhbBghDP/hLHGbkPDqk9cMpiybh8YjGnxZiBMgTZ3qedjcnw+UuC2HiAMHY17v09X+92xdKbfAAOEMCg6HeOC1psp6FspUQldKEy/JMx6mxnv4++/+tv/W3/tE/+ke/8zu/Y8j9pPnHf/zHP//5zzEIeR/4KmD5R3/0R14DqPiRII9fV3mU0ADN05m0d1EeA2O/jYT081j4eaQgxKBPwpAFX5VS6AzgJJ6v+jyBry+A8zTet01PgebJkJm5Zte8mnIec+8OcUvQgZtgcynancDjDnGfgMHHhsG4ewfgBNvIAgupwknDawMVQqHGHdjoE/7zAaoBoWT+lgvt7noFXncpW1F6Ww6f7i4qVKtShDRjC6SeAwNA8vDvZyJFOYVqmwEAT9SdwGAmVbFMwPR2w98x+MGKZmy5lIf0B0CwL2tdyeqIaB3enb48/dtCDPwALis8KZQNIDFYLaV5wNjlMoZnSHFunQlkR0eTPnM4aunRGpgas3Ts/OkmKlqAKlZUufj5ecL42moLfs8x2Kr89m//tp/+/+k//ae+B/jg//u///t/+Id/KOS3Ta8KDH/+53/uFyGhbgQe6aS20RJFLRNdwdSzipamxW2iln3xtIvA7QWGvyy6WaL5wRaK89SFvgA4wU9if30BfMuFbs4MTXcLNE9PZA8+IhQFw9LgGnEY+EaNYTpDirqj3CruqL7AGneD25ujm1YuCc+oIgZ3lKWbnEeJ88bgX3v1M10zAEQiPw+tKE8k9B1/qVVu+LY2O2MkqOxFqz39+d2BWkXoi7lcVeiy+DNE2ULucLlkhHO2Qfh2zajJdBuJWYjMw0jaBfvBGDh/y9ek65/v+jnnlzJbP7Wk8w52oRnjPKusbsa5ZEcLj5Mg9wx1aAZP1NLYOD2GzxMBlJNlqEI6N55CYA5ZoiVNzk7YOeNHAtbDV8jPOH6ENJkK+dT/r/7Vv/oX/+Jf/O2//bf9wuNjvqe/cmag/wqQqf7TP/1Tn/1dfTzS9SNdM8QSM93J0LoCWz/VdS/0RbkeTBRMOnC7kL4mcfYJidFepldLiFgKpfM8uf76AviWAdh0hmt0jKOB9jmlJQxPSI/4xpR24zXxbPcJgGj/2Sw3iVvL1HofgPG7pXFCErUw82e4MzkxqMLvtgGm3QAMtx8tRGD6iCdR6aqrK52OUyJmAp8/XS2aBM64HZcCkzKSeJSukBSliV1ouBsemAeyTizD17z73BnaBfKaUSKBLMXJCBGcpGbUEqWBaRKY5gmTxpMR3hKYJz+NeXb+lvOfYCFyF3xRS6kByxoobOmcpYiSM5ctCpbBTtq+6kJSpDsfxyUaA3zX3Uu3Y4TscFz9hwGQLhHnjo6npRK1ugbKVQU/Z7R+3gTzfPezz7/+1//6n/2zf+bDvovrs/9//s//2ed942ekXVYPfX/zx8d/zj7cKCqdqMVWmrzs8/6HKmuj3SntihsMhOyaX5/S4Un7Fe0A5cIkOBkwLWHaYPou+1V9OoGvL4BPZ/Gu1YQ9hMwWP8lv2jzm7rvv+ltuzZ+QCbYkDSXDpxt/ddpnIh+U/E2JUji7kwEa3I2siVeFkzAw+9UV2O3hPvHykOt/ve3+dE+669xsfeACvu62+78iWWIeJXSFwZJo8rxPqst/3i3BQmqjLSPRg2fQ3drLDdnT36Y4FYKU615td1ISMEXl9kFPk2D67wHEkMsZA5hoR8ogehOi2XVVoZy1d/afRzR8OgCtPYAtGdkn7OQsqp8AQvUZhp+xENveb8oXWp5y46FXKEM/ACRC5J2ec3BudctjSYv6DOG0hYpKjKdPJ1XhDMBw1QC6agyi0NXc/aoGu4bmHhuXw7WA9Ij3kf9f/st/6eP/r/3ar3m+/7f/9t88/WlZ/Q8A8Bg8v/z4ZNMEosWgPbq93NVe3tl5pNfwVf6+rNtsuwMrq6jGGA5Bn6PNxqNVWgo9qdCpMbTr0/m09kd4AXQ5z+vqxjABLqoQ/2lsuaw84SFbTvM/IFvSHrieaG5FYLeKBzob3t/41ACPIW6wWgL39dbSxyW3iq/M7hZUnuZCUjzBMQCYb2yJubesQx43ACQnmEe/P5TztzI4ff76gz/4AyG3RGDMMBFq0lIIg3LwQjxtGZv7RxUAfhI+QDyQYDalVc+RUoTc5L7NSJRSopDNwiutELH0SPIo4VSlJh0CWwgeSUht4IwKmJ+2JAwiilYKw1JFuiiPpSi5oLdwEqZQAswT7KQNBsmZfzyWcmkYWvWRPxh2YQswDipYWe0OmJNg5k9wSiG1pFCPP9o5O22XTNSSrklIZ8huftCyJUalFluiCy3kkCVWFyGPZVcBskTkOBtRALTGG4nSf+fv/J1/82/+jY///tIn/3/6T//p3//7f+8v/+D33wE17bK8FfwcZJ4ZNuVa91mkqUCIqgZoy/rUhqItefQgkSD04YZHOg0jSxSzhm1c87I4hQjMNqIQWlH+di1KLKXzAxAe9lv5gr9Cb1N+qT0f4QXwF3cBPjcNKpotUZNkLhlmi8douisaek4Tk8D3mIN3R3lq+9zk3wvz3PQaOG8SSCmmGYyNllSCnyfaDKFuDORuG3eF+7PPXO5eeOUAbo4LSfJU0VKV7iuEEvljpsuqf0V5VAGWQuRyEll2vdOohFwhToSEc61qAKf2ZAlZRhsGjEdubcRDJ5z5M05nnhLDsAlMLamVR3XO7JONfRKGiXYwWaUPOZ7RxlOK6GoBDMywzZO2rJwarme5spxVZxjeqSYRwnRilq+Rl29peSKRCxYy/jUmSz+GR9TrwSVW0QSCGea/+3f/7u/+7u/+43/8j31z9e3zv/yX/+IF4FmP0Bc4ThiX0uPe0x9AorppmOThHGrpPI1gGlBUA0airlqKlrItA/DAd1mBq4iz6paEHwbypY/7HzDn8rvbeH7h3O9e5f9n5NcXwDcO/GFWvhH75sLkGS8+M0obOx4fad1CptPYcfasxAkDDOPWMt8wPjp5AbhnvAPce0I+rHX7hcSGBFguabJxGuvKgRFL6Z7Civp87ecgiZx7r0iULgWbfpTQj3L8jG6P+C2rQsMTnoTdvnr0W7b9dqRcbMCo9IxWV5xCMJzJ2HSOwWnwwGjecwQtGE/t1YwlPyk3pyXjdn9SslqEtFSFXWlVRMOcnOM5nZD8eRgkD43H7pITkJ+HiJalnOrZ05xspzRMBvJypXSGkE7J41XIeLQRYPtqZvhDMvJrg4GHR7pcS+C2j4HTRZTF1mcwWoqrQAB6ARgnH1P8hZ9/8A/+QR9Wfu/3fu8//If/8OMf/9jj3qSJ+vUfs2Hzk6anvy/BlkRdwlA9cgZBbkmy6VrNqR+N6YHOI6rPK/POtfFsSH4YhM2/WkU5O7RGNJisCOkYtvyOhk4kpr9jyi8F7OsL4OUynYPIdU7MuxfS5Jm5hkxug2jaPNB7VvL4PE6j4mEkwD46ubu8A3xf9rOpCSYwxH2OU0UeSIPufmBko+qmZWCDVMJfuxZ10/oSgNPN4w7H44bsTl6KO4StCrz7M4ac/EQtKTy1iiqB13P3Ure39mD0yQkjt2WJ8EnpvTYkIte5tsEAIgzJg4SHaAAYEn9+RrAMocSSvK6uf4IpioS/jbTBG/jp5h+blEI05+yMebQRss7fgq/ad3UpNsKOAZ6RrmicnRh/snI6FyrFIRD9Y+N04YqOh1MUmAcGVT04AQOQ02m7WHgsgRlgLjQkOzwGw0NDukZmQ/qPfvQjv/n8xm/8hsv3/7V3N7txPcmZxuG5gBmMd27DXjR8/9djL2wY8KZhez2rmcb8znnIUP6rWBIpUhKrlLEIRUa+8ZGRmXFOFSnJ7/z46e4///M/+80ffrR+Pwzw+i8B3d9fBXCMvYWULXNvQog3/tuLcosLhEwhHhpyS26BCTSmxiS8JaQxJMtWXESmCS8uojHkhD5XeZhwCa/kPKBCvNLkLmD7AfCd2+QoOO4dNafWoeSoY+eguDOugYeBownmQtLgrFxIR9MF86+oe5NyeTRxYEp+3My8cUiT0n04j99x/ph3CjuODD1FuslurAeAa+krJg8YPw9waaWUQwIw/666WSaGXtnq+HKTv9m6s+j8i6vp1L4JkmHiYlsUQNnSMzSs0WRuCjHkcC5zd7VyW4IpIfiMy4eGlSECWKl86DMnZGg4YBomhpxUsbKalMZhTnCaka+HTRV0osxejGFTeASAzIrOf9zQ7KyuIQ1hsmqI01gLQzUhwCD6qGFWYcgizvJtpUral/wISsP2zOuAIU7MUkLaJgK84+ooKpcT8vd///f+oq+fLXnw+5zqLPnax9/vFbFvL737cwvf7332QbaEnbT1kLRqbgsqbksYLjq5PPkkSFViLWq2zxCSObIEmZjqcSUuDwC4KXo5AHAFXKCikE8HT4+Epl7DmUfj8DVWnx+zHwBPe2R3k2aDE0Z/sZdmO2oOXxgHrqvl7PpCw3E01Y1i69pQOpFg2qgHgGumWbtILg+NU9vRx8enKPBcoUmvxGg632w9SPzQzKF3fzwD+HRvwboJvHUfcL3bFFsYhgQ5l2Sr4AGerSmy7iDVUsqch1JtFgyVpwzZStiwxwZDbisUK4JhDwYcvikm9BxyNSY0aDyXEgArPBOAKQsBBvGZEzBkKCsCwOADjyY921VPmT6+TpElgKOsRGyIhxcRBgWghCmNkryYzTzbAVAyQfnPJG5dYAiGTEkAU0ak2qboUXpTESQlnw4qDQFAJ7W/9I6Hvq/7++UCZ8krghbvNQV3YJxhGRbUue1rH0eCOQLgAU9YlzxW2YpIM0ppSMZJQw6G/GlgeOs0ljkNYtUSmiXz2SpasoW0fH4qS4bv4WeyT4ftPX4+m+1+ALy8I3NMX54+738nz8lwOsM7kbU5Gm/ZbGuaPiA730jT73p0oA19u0rT5eGQHoxVcTl0soUwjHe36UVETEQ05Sry5t3fX9jx2cI1NkUvtMeDu8ozJwL120rAXvrguYJ0hxPikOIiQhqGspIqMH3eupxSCikfeCRudxiMuQyZ92xogTgTrvjEYZplmGezZMQbt+VgiozT83/OHwAe4hWkiKUUGMBU+HymoeSHLSLjuSKUQIKpvOUEH3MAxCdASrxAYChAAj6GkjSVPvOsJlB1AGgWnpwVjUNSxOqWW3pWebBT4U0hyvzjnLCC5AQP5gDIx6/0ePf3pb+/8euE2Di/6+kI+ZrRDsLXnXkz5b3Bp0/H6fi65//8nyLyQxBCoMD8C8eEIBMcTTJkcc06jSJGHgPpD+gChmQILO1KwWHLacpQLAk4VwwhDYsVAH8n8cbzO518HvP9AHjai7fu63Ewny+nJuLkRe4JMuVAO39kxxF3Q1KCdXZZOeg+BLhIvkjtzrhjiKEhkpzE8GIRzHbBzDrcyFWkd0vdCk8dDn0/6ya7A6aEC1aS7qeHASeQ3uZcUQKHMGfAo1kzqRqCUrauApWS9EzVu3lAHIKVrTTEwhENwy4kQIYDA4DkUzizrTEMToko4ZvKMG4KBhlmG28V8Gf8g8EYmh3DvOEJ9IQL3jD/OPM4fVMCZXWmeSRDD9awzMftKsAgdZ4lsI1oOCHj+anghoNXsYhP5PDAcEi22DwkpySP8gh8PnR5s2U2Tqw2CDf0yq/1I4Kj0k93fQXkAHPiSDstjpaPj1mJ7jjFpcGnU2FKwpI05F+snMuE/oLkwzMYMP9uBI7oIUs+AG5Inx9DAEPOEQ/0SBppzGZSxPDxNG/iDCMh3mT4ycGP8ACwMWuVOwSUzgRyRLoh7R/kCOTjyJwEmZPxlp55rtJTzhF0Kxx97yzOq9n0rg2lQ+82xt0Zs72Sm3U6IfVEN8QUc9/eeBPnDZWqq0iWDyRNocuWhmEaGEhDsbyIAViF++mv7HPrRwK4CwkMgNxqabjPEvPAMPRZAYaHWRcPMiwNMLY0ZvFidbvikqlonPNjOfS1AAIn9AxRq+CBYErmBR3//DDUTQBMIQINk3IzrBp8sqIsEMEwYgXDv8w1FEgEQGNKiDzgY0VmK8Nm6ZnQEChzSx5DriBpcHSs7aSQuDwRIT8thHkwJmwzp0QAUVNszUreTumG/FiLlTowDg+ioVcWtpI5fRxLYJKe3BS3ghrmmfKM/KV/9VICUKq+pfTu/+c//9lWerX3g99e8CumQ+5oeb0wy6Gd8njo8yW3PEjSttILxCcqIrBMDEuDUDizFUqSAPLn2edXS7MumErRLNsWqw4MpVQsBZkd4cRsn0h4E0hKxSqZEqOBLDchEgCitka4qIrhooz8PPmHB8wo70t4hAfAixW/2K3n/f3Do2I1hIdZNcnOXwJAwriicSycOdypRQBOHk7pJtSheKDsIOZh/BC8hiO3CwbecYQPXEQc0QOPnEZcNwE50KxcBj/19ZvafnOjduzR4p6QfZAHk7m24lbLTYbC4bqGBPouSNw0OSwiztDqiu7OcAVGTy5zs/ywkpJMzPreiUDT2sFaAisCDw1xziEJ/OccBtEzLyi3AGGa7eqmhET0wM0SWi/BoviHD0MmhCQIkSFX+QRAhgl4ACbIEE+Tw2TcEIUn0KQsgdP66UFCHgBMoRMyx1mpqurJyvJtbn4qRUfFFCu1VXw7ixgCmEUlUyARRcHNwthxeuZ2ioYTrwLe6/kx1Nl9o+hrH+8KyKw0RNGdhSDz41zZYjCcCeJKkqbgI3LR48/qpz8pI1sgrlMqK84pGbYXqwll+nEuqF1GBOnRh0kYziG5WASkFAnXnIfw11MPqXnwB8DsdNuP2+BbG/ni3nchV6s0Tm2Hz01w2Zw/Gv67Ht6tyN1Ph9vJdpmn19AjQ67cKC/OCMYVoqdcW4bQrYKQ3FooJSC6iEz4Zy4uW6/2rpP/r6N3OrlRutW4HzmYJfd3edxY1WAOzxWHnJMRvVkO3S6yVYAhOUhSUOHgTcmEhp5/5l1LNaGxRhyYOQ0YADwl3kJyWxTcFBhX9FWMEjIT4ZolRKYSAFA+cTAZimL5EiBwOOBgNGxZCREZCo2YmyXkc/VMji7iGnKbz9yCGaaRQCEIZinNjgfhMsHLTWjLlzkyi3eQlJGHbPNvgc6P7kywIz6AArSV+b/gYJ09GFFkJZl+rVMIx4AH3d8hISOzYCWA59yDQffHO+pcqXav/y2hoDJsOSVMHn0wGj6dN/lbhQSqeWsMjzNXBKmyApBSaY/b6gmzFqdZnAcUxhAmuRxKaXj4GT628MgPANvcxse/vpEv7vp6aAB4GIcOkKED59x3J/MP4Gj2vuaauWwOd/3dQc+ky9kldOI9A5x+sF7My4T/jrLheqbZMuySkN1PboERpNA+lf/Lv/yL5wHiGfk7O26p0PKk7LIBUyIeOOx24eSoNIS2QHpDeuZCcyUcwaxmYciJZCyzNZryPKssUsphIYARbzgYPw1zyyHKhCvUFuBMTAHnh08yylUCuSW0TSGFWJ1Q8kPDuaCGSETZ4gPmaihvccpicTIyTbnBkNHY0vOJRkloGPian/CDcSKl0pOto4IKWjIwBFw1rMUWOEK+A8HtiEA5n9BsAxMqoA3tcPpux+dFUWy3zo6cjfDFypV8eEYeD6KIWD70ZDxYJuIW2nDqE55+MDJxTRwYq5NPa8mVbBEwcxp7pBrZ0hw7d57MMAFwISZKMj7h0hjmZ5CG65ThUOAZPpLwsA8AmzRbO/s3mhe3sNk5GauHa3wHmokD5+ijTiHumBqacpqdaS3Y4e61ixU9DlADcm9hPACQT9N9iAbgB1IyOCqBEcrNkB+30dC1qTvz4N9p4aFnj7/K76M9P66KfyyIiXDAhr4vql9Qop5kptx85nVkw1akrUiYT5yGebfR8hFzmbDSTZiAiSgTBEmfbcrWQm4VZgMYEsITDGFalGR4yDCrM+Uvj+SUrOTGSg5MJkNgiZmVqjxxsy2N2/LHOYFB8Pzkireo6NJLMDs5EFjRQzbbFF6sQQKcjp++kmqY/7jEOjYSY2VT7K+FGKJaJMz44R95DB9d+fxdAzVvjWWC8zOcE7aQOemQOCHIKZUbb2bFJRgybEOFZiITp9SLv48IzgkApXDweBEpW8u66nKgD4OHAZaSJSOCWIgQ3iwCNlR5VOaGoqPyBFB/uZmVRraFIEcTcYY0KROGA4y+hNMM4JGER34A2KfZSxvZxV6P4LqRkNdTWQWbWciIPoCT57Y4wYamBEJk5xg5wWlwJs43MJiTasrQJfTy5Qa6Wr27OejMUSFWPvehHLqu8AWC5NaHAHpPlH687EcCf/rTn2iQq8sQ2A/0XB5DvcNFYoUAumBW5IMCmNzSm5JPQS2EIBNc1+AHdf3gu8kyAWPFvOXUvCAzxxPMIn2Ew3zS0xRRDuLGYUwddTl/NJo5mZVwkklzunnSpM8VPXAa4Aw9nmVIZhsFEGvA9MmmovLkBJmlJOCrHJLGVKE5GbfkyTNkGlWyWKeCUtqqWm2dDfr1AVDEMJq+jQMugQIBhOGKQJnAhE9DUcqHZ/tINtV+nabH04uJPMW1swSGzowDhkOCiSi0IyR64Flsa6cUqwQmB8r0PAvtsOFOTinxIJkATFai50pomUiPXDgaRSgNcccEAKUJeUZ+2q/kVQPMdtWTrzUXgPsdPuwDwJ6dW39cS0TGnYMO1qn7BssDE7j1BIwmpVbVneHZReqQFRrSbDcTprPuInHotpjCnXjn3s9gnV2Xyot2b82cR53IZIb842xxJISbwLnQEuCcQ7M+wvsX210qQQ39g45+yufpAiMEE0E9AyTAv9/38Im+G9UUJzwLKgRAS04gywGZBSsiWQ7IYqcIBFFER+4qMHLVBYXkDTHkShSaADIUImIIfEZ76gj8mMohc4Zlws/p72Bmk03x2RCHaY8KSi60ITJMQ0lo4fwk4BGHwOTT6HhswOOGBSXP7KokQwaGzBwHZpItebJVSUrrbclHcZ//Y7isIIuFk1FxW0VLWD2bRXxSIpmUEm7o1OFiOYdgNs6QT37sI0354E6pg3QGPHaHhq1jA1/oPLciSrYlTFiJEjkPPpx5U/G+4mFcLFameIAncEhoSghBO6tgTcFII1KlMqFE5JbcMId5Lhl6wqpJPxzgK7MDu1PhwR8A667YxbdupL130Ds6c1Dy0ynn3wmDodQadFtCyLkhMDSuFt5rDoGVk0pp1smmdw1cgPppx3pNnskQW5TbksFdQtERV8y9MPqGxzWO9PrzU/7/dklcHly2rhwn8nTnPRXkY8pQPjwgUbrh8GbdPVYcAhDCGIK1FjzP3NIH7q5mzoMLz1DCAlkRDW6op9AzzC0NGWfODwqWIR5RgiECYiuQYc4J+QRWak4MJYYDC02QsClkFaeP46lmgeIyf47z5TFglh4BDy9Km3JOPgHoeZCMqYJmRVMyhqYQGBm3FwlcpDRkK1tJ2g62TWWYHwDrogc+Yp/E3J94QsqJZY0OW9Uw5XfDcljpHCSuRIQhqKq+T5CAnWo3yQBkXAizs0YCb0UvLg6AVqUh/06sk48ElRVX5bAaWn6VZ1JcfA3NxBBVn8JJg9CSE/hpCn89lfbr8XeEvPsHgL3pfK+bZOMdF+eyo9l5AugWJeDIVmXeySB3cGeWwFsE3GECo2ESnlIgh6/OaIjI9WItRjdxXrnqfCfgYHKbQ+kyeAz0IaDjbrYQwFFBy+Q5r+OUCyGQiGTJMGfrH2/Jp08Y/nIA534gTC+Z8oHvk4EP9ZKhhBeCOQ5ZfyTzKdwEonFdgQHIbq88PXUUAYYG5wSGoKmlNxSRKwD4VgSA6CkjhjAoK5xeq1I9gjRorHddvuQ5zCdvpUqgIePy5AEZVpw2pdnqzLmUaHhLf3g82yhXZnM4PCEM/2xp8sAcpSFwiJSXzI+6Ga6eG5ZGmMwPs+dDkmcYGoGKVYiGK4cpsYSZqrCmFFMaNo6HNk56CmtI3yyuVsCCwlgjTNEhKQ29eeCsIOVcbc2KaIjAUNUr2xYuihd/5OfP3k5kIhw8/+EBWJ3Wx5L5FKj87Z1DNWego2IIzIkopWe7aWRS3DI/k3r6GQx5UjIrMfnDE9AULcwMH0m4+wfA6zdj3VHy6zf1OAvPXyMKx/Di3DhkDhzqIAJoZ04S7hB75zXl7JJNdSKdNnLnO+d8AtRVHWIARGkWEhWUklwas3YYsgvgC31BIXmgFNfXO/4VX9cMwN/wdM08DCDdW5oujJc7nwaEpqdkSC8QWYYWcsY/2JHTeT/XHMgigrlv3U+X0xCSnpPAhlOf0jOkhJzuIDRNy2FFbwl4/rMKk8/kohSIt3GSn/QwhtaVMnNTK7gpCZiVW7M4GvwIlPBDLSEkzMAADvsrSo+HXJcAS18a5NPZU+UpkVmU4QhrhJTj+UAvpETIsXTeKgufzidS7aKDq7ZF4fQOhj31AGjLzKokMKIxLEm2nZw0k5JZIfIckltH0anr7x94NXF4TDGEzMnkVtAWbqohbxXNsDQA0AQtXMM8z9SkR0iZMLDR0wCMfjw8jPCwD4CLHb3Y5hnOTt/a0U6Ag0VI7tjFmZtyBM/r8/TXVsEMuy2OOAKmwVEmMGRBmdMYuo2QvqvxCcBlgy9cGcYnyaYuAHo6b8h1csHKijf/lGPtSQj/wpcobpEXOubALp5UPQOY6wvuUokxBxC3nPULVmZxyqGWAMkPbzoFQ8+h3v05FBo3xYQ5ZG2FH2B6Gtm2tGDJrAjAEgDgPz8lVpJ8ZsIJTc7TjCtKflpFq+Mnc3qwwsU5JLS68ZmHFTCYkPg4HHBTIbMdD6bW9JgMha/IKXlG4RmOw/zDEEI2FYY8PmmY54ErlbSbyHmAoR/DttjZUyhvEtXcNtlQ3/yofEGZQDo2vf5T2qYyoecNGSYMLw0JADseTqnT3q+fikUJmf+EEpOJfLhFEsBLDzIYDYwkcSYTd4RJYNUkTziYNAXNhCYq0Ph5JOFhHwCzSc+bePlNUQcIDGDAt4QOCqTju56JnHQEnT+CO0PpbvixqlNuiDvftd1OMJhzls8aHLdeiGgc7h4ArhyYfCjnUM5ayrlhfgLT8CAKt/SZc+g/8egBg/sEACYxJjDS6x+kI7uTfnqcB5wGD8YhK5nkOdmShaBBuipXhpqC24gzty69G5hAyRWH9V+z9GVIjgwRMAyfCaYoiygBRGMqE8NM8lYs5oM3C2MoOmHcjoecG+bKEAXLm6FYZvGWTGMqfbzhKMstWDJuNjlXZAAy/UrytIMlU2HlBpC3kOQot8+jL0rmWWU4cXuUdjJbsimC88C4rRc9wWkhOIpeFwhcySdXdX9cQSjLylQZrEFTFsusqY6Kw+ZSlAllNRkATbE6M6IgidE7Wkg+mbStMjFbbi2cq8kntziafBLi3JrCxyRNysPsQelhHwDrRs5eUr4oj/LFXWaFmkqG735SZuvwIcpOLb1+p/N6z3LcTTnondRM8kAPT9MVAvYYQATPDBgAVkhczp1sNEELbdisQMjQ3aAJnAdf8bvh3DLxW6FCaAQyRPBy8xdBIWFYSRt1wShbaTmYZYjzn6aFcCK0KXomyIcYSg41ERSMK1O4IaRVc0WmNIRHNMgUbxXHrMuf1YTLA6sMcQCGwRgiMlt5EgIQhDhszpMQPjnDc+bIxJQQKLzZ1iuTdTZAGDzipIgEZRmfBHgcTHr4OtVwlKUKX2IFwkssJ8AzG4AmqqSBn3XHn6oqJXoerIiVTOKG6SsagMXS6LbaqyFbHkSkp3R4IHM+0eHThCzPmRXLYXD8vIV4/cedPW6L21rI8CWZf5p2U4ZCS2b9iMwKScbshCZwskZPpk/Ah1ar301+5AeADZ5D0ManSW4KN1xhL56AAXRoHDhChp145/Lopuf/uOJAa3zdfPfEO3W/4lJ0J15zN+u8dtPgUaecYQDf2sOcZ/u4b5N5QSdtw5Kh4YQ5wQ3Rvmu+ZnkWSBq+C6Jk4kfBLiEYgj9b9PFPfQnkXU9i9HhRCKLT8EMTp+SZW8NyM+WWGgpBwxVSEKugMdWSKc0ieJryzw+ZeVRoGnGtBQmXkwCmhnJYHSjBEBgnpujzRmOWLHlECJMfcmCcJnmEnFOilPkkJ+TQcOjCJH3mZGsfD5QDLiv5h18zpBmT8caWMlqV+aSZVVcTcWmEk3Cz2doCRG9YKRqC2TLyWNkR5GDTF3FCTBqzIoDi0gjtpHnx1/d984P87Ld3HUe3cGCoHCRDaej8IOEE6sHjPEiMQ5wsn84Vw1JKyBXN6Js9Ypz7eDFFeYEEGGS2D8Yf9gEw+2RH0ewiuU290Az+Wsj88HLarpckpWPqFHorcUxper/mv8ujCQagcRnIzjGYIWJIdgFws860B4BLwpvZ45Hy/BdeTvjhoQzhEWXDbPF84uXJM6WIAvkcwDky6+6FiQNI3jPAPx9E5tNNk6roBLY4fa4IiCGYHHArLRncEpIlwKrZDCUzVmEY0iDD3IbMioe6j0zCtKjT4kt04DScIMM0CRxSApQzgRMrEtoUogmZk3geIEcZptUV5ToWDWIyAjlXNBOFIHrrxQ3NTikMUw5eGiMT1gzJ1WQA5dwwcIFKIM9lRWP56atzrmqsah6VGCQBQLd1KhSQzBvzyTZXpVcarGw64pOs3ev+x6/+/M//6Zp4HqTPT+Zx5lISS9A8lAaewBsrGDfFl1TwFksjeh5a+9SBslXH4WnQAEo7zYokr7DBP4bwsA+AtnA26bu3sO1fzWmQ88c5fUOH0q1wXjustYkuEkzgzmjHdxJzx3gwdHYRcw3aPWGLaEwBZEsGwNd8AgwY8rgiz/+WGW+c8CA9U2AuXuauH2+U6buffivDLHKvmLhaMuy2t9JZeG4N04soE8qIFY37WXpi8WkKHhFYmc12DJuFpJcVnom0yWbXKVYr5Qo+Q8ghhmYNcYmJK7dj2c8fDvjJPE5fhulxw7xxdREUmGZiJfDDZMwTSiCupFxZl2GzTLjCDVGw8sEh0+OjJJdqvKHZGdLwgyRT9TJPT4NaaVZ44DbdAWiPKEPyrHRgeMrwHOaTngAGQ+Bc5t4tdHweHGyC95v5qS884gQeESK2cujQplEx9yvPNNxybgjjEzbbEsATTn+XvTtYPBhXhMA4n4f9qRl+Kh6TfTlVd7q+2cvJv+PiZNC0u00dh/28vUzoM8QTBjlCerYjTAiC09lZMcstK+fYV+decBq6OXqoxqcF67MOvZQQpCnHl6EzXQtO42diXQxKZ52ybsWq0CIWVwjmIuIcwhfUEMGb4gG4x4k0yML5Ish/75cT4dxGmdCLlR+ufDZ3Y/0Q268GQbJ1x+jLRw6Q5ZMQFxd4SmRIj7OSjyk+xUKU0qNBpqZ68IgHs/RgyCxNU0KjhvIBQzBZ0Z8Wf2gENPQXBE8/IXKbBtJQkgQAZJj/iZIALzoAJE3KhoUbt+WAR83iJa8IbE3R4KwCpEkZ+AzyJXND4OojLm8BUk5lglHObLICOhtWCimHeqspeueBxqc3B9isEBUkpA0lpGlFhpPnRCl/ME2/jk92vA0dPBpDURg6XTxkmEOyKCVgacF60/fXG2k6MwBOab8uwYQrVNz8GK47cs4fLDBMmY+eIK7ZKVd+OHF6gcOPebFW87uT7/4BcKvibXxbhUfAbeEtq3fqHQin2Vlxi5xROQiH09f+Ori4E0ZJEJHg2NEYIm/orPz+fk8OGlM0YFwhGsvpjFKWc8PJnx4Buzar0l1yYXiQjy98XHV3EoyeT3pDcQvBA71rBqZB5JA3SnIJE2jYDi+c633k+vwmmK1VsAUwJCMCyhUn8OnByCEPL+eDk0+JATMhnKZPyy+B8BfcELFNYE5gKxAr3JT9IvMpkFkcIPx4bgqeh5wAmI0Cj1XD8UAPFp8pmlV+0XYAt4QLtznBE7Iil3xgy7Teluzg2dz2FzgkZVsMHyzDw+m5EMOpAM1EIajPDAVCIXFHztnW/fvyh4ZtXHp8MowTOgCGiE9Dr/n1+nJgIu05JwV9Py/imsmF/P4Qn8rDIz8A7OXF5qVZN4BmTvCqf418YWjoUDqm7oy3ZifbwXVGPRIMKb376K08gyH4MOSOMo3+C+mS6M4+TzBx6AFY8QaAyO4VzhzvyJLRLAcsfA8AetcP50qGrg1ZYmB9NqfJMy6oNHgDpgfDWwhOyTMuB04mATITw5V4i7IiF5pAM1NMCkeJYJBZ+hEunIcEELfQqzezlGZzgpdtSnpLQPS6P8+E8c/WcDzkJCU9K67yZioatw3BCPEXAaO8MDRcrYJ9hQfOSbY0Ul39Nzv6ku9AUnquOyFtbhVQcDuOPAYAKk67MEWgv8hqNAmCKqwoDhLeI5bssPmI7IDRQKLSVlWBELdk4ZxSWQ1AMlL1LtLq6GEM5Ql/kcyHDAvNVRl+iM9P6ORhHwC2DVVxe0mYw3SxDQO70De8Nbvqk/l3Oh1KXd4Rd9N46II57k6zFtxBh6fBmTjBjnIvYsyRKbyPyd6VXBtWkIge5zYND6K4NvWj0jAbJjDPQgSQADBbSfouCN7lpPHIAYbEgYVG0vA5vdxy5ReEwuQfNwu2FmpyEIVVhiVsiolwYeI0BASPQ2ZFCJmyIc0o85x5SpiIkoCvxE+wMUzIP2TDCmtYxfJjCmwoP5kA0ANMHegnerN4BPks/uHPTFKt8h9Az4+6UYYsq1VJjyRJWUTDAJR2HPU24Ew6n8i2wlQBSsejpwKNLTbVbhIKx48pPvOMjzAAt8Dp7csfB6xLMc+DSTtDrvjMrQSQt5/yp4Qp3Ak51mUIsz4AWqmpd9L4mcQ4HOU7nX9C84d9ALjAldtGDn34XvLc4cCL4sI4mm6UQ0+jn3qXcXB9Wem8ugA6hRtIAOhA09R35r4xHBgkJ3zmv3VBMrGc+g4/pUEPNucsE7ZmUeEowbpgzA09rsxSIu2g/D0DXFo/D+BNUFP0eTAkXAcq7hnq6Vf7WYGlIQNYdUO8TLLiM43heKax/Gv9YEwN5SfOw1A54KWdLStDmIbT4AxbY4VlZQpY2pompVlK+6saqNmUEzqfcbbpLzh9GV7oSymrZIDVCRmNLfnCwwxP4MHyIHlLtteOH6UlOJC224kFqBpkhy19TwVTYlVDVlYKOSGanWQIYdTKxun+ThFB6F5lCDBTtMmNz9yWVZ29jYCR1Tyl8lCeo1zz+RBZkuOnJGf4YMLDPgCcnjmX9swJxmnoCbOpI6xbvu7xAFblyFnls3AOt77gFtUvOrsdbjdBS9VKcPo+CHPlTIsShlzmOJj74ysg92G+ygcTqAtJEA4S8TBKMk25UUYzLBwlDFkCnMiNZ+RSCVcIQ3q/MApmRS4nDlC4ikBDKJPimk1TxGA5JIu7phcSLyuCZAJDGgJH18psmyXPMCE+a2eOrAje1LHU50cOTbP0QzaRrSXbKQB1sKG6mB2xZJviCUqo/qwIY7sKPM+w0A3TX8cd8ItCqc7UOFl9wqzUlMXKvzcPG9SxtNEtE56rmq+TVmNtRaZ4aE/xoUzKf3hKsRzdXv9x51zoft3ALgNP0XgzhCewpZdD1O7YAhl2/mUFwNUo1Z9c0KnJO4XVm9wMOYy/0/PnNH/YB4CToeIdzbZwtjP9OzeVeSHWfaVxRh1Zh1XLmPbqTDuszq4cAOqhDr17QumseyrgprpgYO6qXuP/72XoAvTFPX0nvjvTivCaVCsybL1cEeAjs2lqtSJKw+/5VA2YSVi2HOJc+cYW0h32d8cIyHdHeoSsGE4azIsbFwjyKfC5EROFW1aGqHwIcmvtLSFOz9vUyjCHWcUhVzC84fA8GDKcWIUzRDI5HRxMAnJDlsYEKYKtxK3Fdtgs1UDz9bRZxEl9Lc9crQI/hisFOCN8YWMFSTaRZjVMpkdZpiET4gTrukDCy1D+SLZW2qFSW+s1y4TgmHmw9eUPb5QFCoBHa6wCDWfFv1p599fx+wTgGSCuYTAAxJWhfRlbWSmmatPIVnSzMpRq70BtYiezR0LJczVrH2/fLZQYhygZT/hun5/Z8MEfAFP62UX7OsoRzL6oH8AtYU4JQB4c086oA03Z0THlQOv1OimlgxvRaC61D4ZMcGAEaegCaDd6rkvFhK0hfFcoJD5WpSGocMl4awfjkBNCAEPENnNp9zQyJAuNk11jEf0FMbPcMjflrpqSFVc0yFCsCdeiChHAVLCc4KVRetZlUawMISd/sdb1rrNHsOcKE4oyhufkwehxelSshrnVmyhhrEhxcBEJVi15Ag5pm2j8ZJ4AAG9Kb4I3W4icD6fM85HE0tbTpyQPAa+wABd8dWgq2xEmdLAcmiVYuzztF5PW1dLsWuAeCb3+U9qLygV8FO6kApm9iDsa+uMhc/4MTN9HjjHu3aLzDCBcp5fniU5AzlvhnDQwQ7xscVb0nb0qn1JqbOW26TsqcPcPgI7vuvJOJ/2qHNlZuZhqOErmgRPmbAE4agPOT8Mw5FqYpuDN2mGtNZjtpNLDuIRgNPUOGBcGGJmld+47+vS+gnfWNUfnnpJbOUiMTGDb6TcE6Fki+SIGmLXA5NxV7HHCj4jABKQjuKiIIaL35sXK25beV/uTkuSBhZaMHwvTcGKIAyOCtYhFQLkqimQMTRGaMixDyRPAGoqCkuHVChIGESSQfzI/DWkyp2ErpRwWGiYlE0mWgzxVwxIofaVjOUpdLHhL9r5P8FHsH/7hH/7u7/4OuNbjJzpIzRmKwhsBCZHACtFXGRhZtZymcEP4hJLEg+EXZHfMovyrQ+vNG1cjTBShLdDqkB0nm2Jl+bxVBEPE1vItBxlWKAnQC4fDG5JTSgMGLy4TgpTUx/k5Pyb9L0Xz1o88AGRSFLDWlZBDGq6EUHlZmWqNnkadMbbtplkZ2iNEmTlbGbK6IG5pXpy6QK7D8JOkqZa5RhmfYCOvTu5IvvsHwK1at/3Xs+vWNvuaLcxqDsdXTDrB8ATkVnS4HVwHGrGlaZbSoe+KdprxmgJBeu6ti+QxwLD2pB2HEaJDSXA9yGkIXTZDSFMipiGIK6IpQVu+i+c6kc12zyWQq5TlYyGIlY8CZt3zWsCEEygkjS4JAIYMuS0HckHj4YPhMAC42daI05iiIUjeLCUaZT7TU4Y3REUJyYRGJoQwoluR9qTIlMBqa0d83lIiZAmeAVqYfy3Vv6BnF6zRv6dkCpIrHti2Ch5QsSb0aNIL0RSeUIb4ANKss6YMcZQHQ0uwp7gQ42S1larVSQ9p/YbZ2hprLP+idCQsZz02E46wRp9YRTcE4BzvGOv+HgNCH+V4/pKNh3GeCXyC6lmF6D1ZwUylcSzlqdopOUEugvzhyZARmcnktoXXV+C3ewA4lFXHoSEMH/1F7S708Jk4eRfIhg5rl6024Sa4fk6nU+uF2tB969B3ZB1xN6dXJxyYZwBHnEN4XzvQAHsA9JomJZRSMmT4goJJIM/lSW8YrNm5UTzkhEZWDF1CrgRFplgh91Ay9PJxvfvPm7RFnoX2XwmyYm6WBoyMGB5ZnlRlcD7x8gEgwIeZcJQhaVAAghxkiOApFSoPOQfID2UafijHFUFWzJutXMARb4jSwgmeAWStU/H98MM/leqHMTQKZRORNsQVwLzecp7nHBY6DU65zhqWHtiKJGeeyTl5rMsQN0webwHGv2FI/FzQ0+u/RdHIUFDnzVFE8ofHyZZjFmVeLHIEVsT8p5w87UXkGCuIp6Zj7MHpxUVxpAHP8+AJ/DAZb3a2rCQzMEfdwZOY2RLghExvFwjWwkmpsjJ8Snf/8ZYKPOwDwJl4sQ4du5lNmOG1yRzTC+ToXzQBdqYdUPfBHXBMadw0H2mdY1eFsuNbK8k5JaEz7TLwLEq3yPn2nQNzeh7wOfEJaz5kfhAYb/x03yAR80g4BEwJXJKahZwLyootMIBGTwDzDKjrUeqJSLtsXcCc5KdnSWtklQDg9uI0BW2KzEomEQBqjQCmypPtLFwywZgk4MANCTO88NmUiNXEuizHqq3LU63OValrYb3PWo7Wo/XD94FJSrU8fngrH8JkVdzRiLuSWUNLgy/nNJR5KH+cB1OQ1ZCcTxrghsqSYTsC2Yt/J40THdMSFLAaAiPKur+zmgaS24jGsKwIiKYhAaahiKqHi4iEVjFvCYrZrslNIIAcjqscSgBJACaNSiKvOxJmWzI0hi6L4ncGZBJ+dZvzzV9fgYd9AMzFu6iF83Sh+fpwvQCD/MqZg0fOqJsmlpOtn7ohLgal43se7/+r3eg1plCXthsibc5hcMSqjkzWZLsS2hO3orhgQjDh+Qx7sBaYn64KDT/8y59nNw03ZVhoVobuIS6QzGmYMGyKHmVr1vV21X0lgrvt/tUKYDe2TLjNah2WA9ixqucvBAjlCW+ZDAuaviI0Jc+SkbxMIAn5BEA09AwpccPhzfLAuShlBayYpsAo8wnjYUC2LkobZHUcqnatx/ZZJueeDXprQYvL7QQlHDmdVBpNkYckY97Q1NAMTa3KrCglQz8C2VQ1xM0ipwJZSOulaePsr70rT0qyRaH2Pbd5voheJuVWJngVUyW1ikREDraD0U/LxUWZ8Jnb+OSsnrYSlQC38olgpkr8SBU4h5NSfoTIbfrNX1+Bh30AOBMvVuFC/81zc4HP51esHFkmziXSYrwzuh4uRnrHt37hiroqmohvGNzG8DBkznUiTrpjBHod509/+pMpzYg+LhmaiDJbQ4IphohnnJKTeMgVD2yINIUowx5O+S9JGHcVRvKaYxxMI/jv//5v91Ni1ligI/xzAswbVsC8TZLBCoTT49UkJJkgSlNnssdjgBJHOQfL3HCUydVW2WHknxLY1liIWf3FRxm8ZuR7f3oEQ9/rv8bErQ3lpxdS64Xnrbj4CJMAIQIbetYdf1KunAfryo+p6oDDNJUmOVuyJTg2Eis9m0Jp1na0p4SIUs4y9zyzIt4qYw4LndsjuefaJuOTj1gOcI9JhfJaoO/r/mTJ8KyY/IDZOM7Z4oiygyQfaXBIIy5BYgx7TwrMSv5gvOE5ibMaEpFy01sr8LAPAKfnxVo4ZOtU8qp50co5Sw858ovIATiRYnkAJNC7n7ij73yT+wTQP79cR6v1uDAuQ82OphdVeLeL3vUgy0G35Z8hn0K4S4aTJCUyBAA2SwYjc0JAXTlTlBEP+TEUurutoYjInFIyMN3SfhigBRB48zDw/w14DFhyiWUiDUO2a4amUBlO6DQpyWeOT58YRJStKUQwy4qMV4E0uFj0DZulicahoSmLkry0LdOUz1X+nVQfs1TeU+Gf/umfNDJTQnsAmPUMEMuTOD9CVAfe6Hkrt/KcBAQiRwAoDSFlQzyBkgckCplnJAT5tD6sWk4ecKGdGXi87t9+MZSh7mnXegYwdH4oa6b0ghaLwBUZn0zEIkfJE12VPGN8z4MqlN8O8JMSp1QU/jm34zKRGLcMUTkDyEcmMJJMLwo8zeizguRN8XV/gHF1+nt6duY2zeZvqsDv+ACoQHNoEpy/Fwt3rR/DF/GUTGCcVIfbaSa4A24mpSva6dclnWnK//qv/zKbkq2WpPu4XQieB4eeQ3oal83/6j5u+/jMylTh+Ck6n6jbAo9MpSw3HJLzGRK4gtQgPKLMIkp3mH963gxdSICyooSh9wzQBcBE4QTGAoHLgRKd/p5+DydXRYRHZnEw3CxiC0AjlkD0eaNE5BwCpMFZ5SFNALaUcq5RUpJxYNuBpG1oOzwA+pGAp7J200awsk0wtkAOvE04OVQZGlMlcKT+/HGH2/DN4ogSz+RUPCnp0erKRMuhF0g4dGGb0ipq/cEkUP+tn9oONeSKHxr91O4QuIK3wBK+SOlI648PgNEQOqgekIjsYeAAeDpy6MwXjmyK/2Nh59LiagJQbjLPrfQobQ0iQNIgG+GcO5BWEXLyhKGZYbObv6kCd/8AmIO1Cm6Fo1MhOiXki+PScGZvVe2tx8vZZcKtBHBXy3H3CukmkI9+c77gC+cS4l0Gh5tgSotn5SIBm3V58G6LG64luV1//vOf3bd//dd//Y//+A9vrC7McVGeX97hJWCIM1eKhtwiUXhG9IaBDSERJE2upFdWJ/xIhpBbMNeSuWtZC5CwlHxJZfiXv/zF5wBgNxyMiVicr9HNFotbRLaKZFNp4MOsS5h1lYzKWBEkyjCZh0LEKTmprSiyxpQVb6YsU6oeAH2Fpc708jFFQMr+j//4jyrfcgi94QJYlxC88WnIypCynEsjPzhqRTi59SbQRIMZAIe81Uxxq5CwrFI6MBJWfLxMqkkt3rr4oee8tGWeuSRRp9Hs1L+4E52+QCJWE0Nkx4VWGU6AVYD/TmMJVGfH3jJzzgOYWSQHXFyzFoVLTP3zkBKm7m+Kh+pjaihz0ZE1pk853NTgV+GWfsWsMv/yZ8Xz2I6wIu9LvvsHwHW52/tr/c/RuBsdEcdFREfEoSfU7k25qLhZF8aUK3rexKP5kt0BHtwN36XSkJ08TgiRT9maLJkHN8cPYH07oRHTiNI9IXQhDTk35AoREG9RytyWg1iuXLcUBrgbSCPtwTBsdu4wpKsuH6+B/YfDWpJ76z7LDQwVWojiGpZSnHM+LQrlPHxgvDqYajaBXv7JOFupMkT02VaZkDIUSGdB6i83+2JpDMG0M05kDiN5heWNHrV85j4iFGUWZeGaHW/0ESuCHHhjSxD9yOmZ6C3HiPCsO/40LOdV5oHSFLdZCddeEHRhWcmBBsC6ZO4gIbsvjQwN6REAGP9tBEC5TT7wK3EbgBIGKQUSV3QhODRl+XwWTsJSoiTgraUDAICqD1d5ZsuJvXDYJgrPcqaUM4FVOePXlJ9rfdGv9e/R/Aif78nnnbYP+AB4Z0Xead6F75R00Dk09ILpTNN4dXJdnX7HvQvZ67M7093QkiC7ZjgkPQ9s3RMd1sUDRp4EbH0O8D2SSwIT0n1IZkLgQVbdt8FAgtHHJQnQbYdxXXNFaSjPfucHePzAmPLEkq07bFEaKJJVSbq9mqmOCdMdZo4qCIH5DGVSREo0mUtpdqSpSYztJANPjyjxkGaLhfOPqqfM4RGwJAmiSNWjy3dZMPLnQdr2qCarznmzBdZbiBKgB6bhZ/RrGqKHXPOXzLqukYsyftJTCposHxXGkbR95865KdHtguU4PwQecmKxcraD9HYBjDfRC1TmZE7IhUiZ+WgoYQRVHEQAEE5imc/yDSXWkHlrp+QBHWk9P+NNMZdbpWYSGC9n/s2yGidsSwmnz39C8sx+rDAhPtbtL/f25Xb98lS+O4GLvXFW0Hd7+xDDNQHpIXfS+SaYchl0GUOXU9+k6V6Zrb/g9JqOi4Tou8ZyI9Aw8QrGj5tsFvctU+YAYKbKgRJ1bdK0wPRNNcsJkgmlBChdTiaGGgd9nmnA0pvqngPoL+5qTwLR5X/6OxyS54aHn3zGT1kZsuXWEDIwJaKhZxjRBEtPbui5KM8MIWeWnmeUBjcLWa+UIYBPVwDKS7Yis+rAlWeDUqCezfmHtEBOIMEmw4koH7NgR/YnTegz2aeEKWc2IUP6maIX1FBu6ukH186GIyQBStE9qJC1SEaePNDjZHptFG8tXLGyQIL0jhI/H8sjoTPnBB5WgmfVbgotEBiA0nnqez/we1POpFpR8ilhAAmjbCVAmZ4mjMRUFdFDKpespO0smZoocjbFM0O80ISIMv2z4gvgQj+A7xBeLMt3+PlUJo/wALgu6Afu+rXzr2uc47nzBIdGMh1rU870eSOOg44ca7fCWXejDN0uYDDn3ouzG9K5bzkuBoJ3DxG8y6ZnwTPMg5uj1TKUJFtElgOOyuQIfFIOmTclMXieDQlcmeKHuSn51Adx4QDCu/8AkOFxmQjkJREAmEMc+TpIh1IB4EJzDkkuQz6R1OgD4JN2RYBEAIhg9lQ8acI0RW8YheFN9cwSioXLCpezDOVcYQFsgTwZmgKwFoZmCabyow6GlgzfouQDJujkkKHhBYWkfM7xMlU+m22z+CkNQY838LO8AJq7fFRVbWUiYXjIkjTroycuPQHoy7msKKUhEKvSS4i3iraj5CwfzQbV97V+n0LIFSqfrQ5YON6Ui945R4b0wslW2lp/z+BWZ9YQzDFuCyBNFZTbBMqSJJQn4UUa2Iuzr1de+xH3Wvl6h58E+YAPgK8fiB9d9+7tXBvhyFLCHZeuQbM6jpvglNMDMHSrnfWGLka29JD0XRt4+i4tPy6eNy8A108vzoRtVy5XlISRxUJaAA0/Uoq7kBy6sWbFSl9PcfEC4zQwhSOwZcXEFBNxCYZksxITyFcWcqB0sfG6Z56BEf8oTMUho2YTGKJT/eXOD4C+WW4rjqGiIQ7B5FOgvNUByR5skNarkn21EkyqZi0Bki0MgOXIk3+zNiJDGIKGBR8ZIn4gCZTk4YRmA8crI7nkw4BJ3hIInQ0J2GUaKVkpXnMvQ3rm9CpMr5PKKgCHFmKZNo43VEqEguJRenJCSwDjnLnF4lzp+35Xyj+R5PhJaSLq6cDSBqMnSAM5k6YUjZ88k5VReoYtk0AJWdpKTcMbIsgEjTmNJE0NfzH/lNc8w2v9VzRFXAEltmruTn7AB4A9+I7d/aiduz4lc1I7Li6Dc3w0vP/3//QUdwmA0qxb5H7SILOU2hOlz/t6kymnvwucB4aQZt00NxM3xP1IwDdC7pJFQVaQasLkjPz0aYBDs9oHGHxgyq4uE0p4GFwmzHGx9CPKyLBr6RqDkRlqQ2Sem5WYxRZOI+CHrXCIDJ+VIZNnx8ezkxwYR60Ch8wqsKnD1/PLrCm2gubWbGvMQ1MyjMqkWAwtWeURjTpYr4VA+rBlCX5IQC9QP9Shz5vWTAnJGyf5FK701qHZAM3iCczBSgOHkbwlIMNe+eXTk0AgecoNtzQCjqStgeKK3Cy3/NS7uSKXJy7umcvRXq9TKitcdFZC++rJ8nGL1fp94WNIFkjEHjlyaMdZkZnLpFkRKa0RXt3gTcEIHZhe8grrwVAl6ScxgjRmOIWlQWU7yovh6N8p/CC378zqPeaP+QB4T0XeadtxxPnpuAxP6WQ79y5Dt9F1csphuif6e2+ablGXBGeSbVeLZ+b07gOidL0L17XhLZNisV0vUjdf42CFmoJ0/dxGGolJgwBJ3zVuFocXkXIiwgAblg8OQ5NPgXp0cauJ5G04jGwRE+FQnsuZEpltiiBKpSATikXJDwwlzcDYlqQpYHqUZ3pKjclayHJDpkTXfeqhhmSYuIJ7550funLuKWvX+CQzl0PhVl4+5VZ0szyjI5uTmqVH6mYqh2TEMydqKNU+AdBUwAw7JzJR6skWoFkesm2BFapZgUSMiygXwzUlsqCii6vd+yG53/T1yu+dQ+vnEMDbupatYnwyh89EIMlQdoBbGleyopctcpx4qBRgVZ6eLO0SKyVchog5+Zpycq3/KI08P8rVp/Jz9w+AdePbpFXz/lq/deMd3Akqk0nGwXX6nWCzZNfDnXHQ9cT6o0BzhWi6+ZCU/XK0D939kI1PruA56RYZIrOUQrD1nug3RPsAwQkCKDRzgBp6eCZ567qaheGBgEQXhWCW3vUm9MWCGzu/kcI/P9xqFvKHFK6glsmksjAnCIdzawmsahmSBEOUKExti7eSpATDmVCGJNCUQFFwsOkvbDVHJnKDJCO2TOTmiYtg5FMvYyiuWRzM74NWZ3r7Baw4BAAVto+qwXm5lZ4pGuYysaIqAIAEkjDYEEwLxBki1U7ggR8kYgLzurziW0Xv3b1NGwpULM7Z1vq54rmStnAplQlvVcyQCT1eMszNIs88rd8/iep/RND97TiH8H1RozKsOIFnKHNTClUmBLNCy98s5xKQOQJgRU+wImVE9HmDrCyll21K/lH6ZLOjSf9N/nU8hxN3daUaRaT8uofV6jPLd/8A+GzF7VjM4RhhjlRHx5XoAmgubpRXqu4PvRvinNUFuoSuBLBLzhs/7hgyBWzKrehi8Kwrua7MA+h3vg6qOwDTl0b4eD5nyjA9/5yUbbHkYCpeXD6RLiOQ9iTnbCkJpcGJoORxRTArUGS9vKEAAw5DeUFZwUMGxgczeuaRWYI0alvlxslh/Dd/05ssQavShnBgQ0uOeKZUw//8z//kXMPyJLZfluyJC2z5asItn4az9swprR2nnyQJNHiBAOQGT0AExWwHk3E7y7k0JKPntqdkHRNXQxwAccsJz/nEDeklL4eo6KVxGj19eTX6IsrBF189AHz66QsfVmL5Zz847DAUS5QctlgYeQIYAuBkSgmrM9tSpVy7fw75ibJ9Hu0/P74Cj/MA6JCpkEODPr5Ur/PYsQ5bGi8mQ+kyuI0ukkMP773SXbWKrgeNXoO6V8C+cHDtGUJqQF1yw+6SoUurK7m0rGDIYIb9Ez16BJ/8R2KxRRKmyRve40dT40TT6a3TTfY5gLlZObMiE7q9YHLAxSLQy5ZgCMln6xKFFROCKekVHR6lD4zLivIrxRw8MMo5/0M0UdmKaEg+oz19Uy8xadNYl9p6A5U5TG2XieUbIhXwqNa8KG2Qb8AZ+vrOkK08rRestMnSkBX/ZqUKhsJIw1T5k2GEM4uTZ0gA46dV8CO6l25JSkCeeca5RUJLALgK8JZDGnqANiVvVYzMCqkAzCgJFu69xCnytNP3kbNEyY9SIJkUThTJly0N4hDMAiNROCzheW7BDDhv1sWq9baElQPzs2q2/CEVeJwHwJSjgzXDnyw4phJYg6YpK3LU0MXr0BuS+zqF7Oa4YLhZvZg3s66Qq0J2/w1dTvfK3SO7TvQ8H/3j+V2SkkzvipJ1cM0CmIYhJaE08DyMK4a1flwg4BqNlIAFYsuELMOcEIBlSw8PWb9IT4O4tYrilrw2ypxed6Mfai0wJZYeklA4+tIwXGVRWJkKFh4XN6U1SmlMtCSpKqwEwszCEyYoGIB/L4ithL0RA/TEpUHF4hxV51ZhCixlMMjZiPbiLM+RuQ3FASCZiCgucF+P4DbClKxaiFnDqAQqiwwJMKaAJzr/YGEqUQCaMiGw9fj3ePMRxwZZpikwoZHjp1Yw+TGVt/zgUiqrHgzlwIRh1a6kzE1B0nMrQ5rSJvCTf+DJNg2+6aMqcPcPgA6TI4LmYI3wUWV6vZ81k0mJ4KzLCpGd8jnfPDv9XZKmuv8uRtejN3Em9C6JL6nhzZJdUZczGD/5LFX6PiUwrKfgfWFdJjoOpIjcyopteniChpje/S/53JIRzLmUox0zlIwhLmiJ1TI0L8SV0DRc1RFYweNC0JAlUwIWhciUxSrucPqoWXLentXHn9yaJfCDAAy5HROAHMJ40JqStlXTlyc+HRlGktUBUgvzXRBzu+C7EUgh2OafPtmQoaFaieu5iCYlJs0CmC1hAmXFLCWdESkgpbjVEyafYXKVk3yOtxILMFOEAhGkipqSniVbKXNc63e6LNDj3wk029JwDnEwhjlPgyPKzieA4kDKn8ajS/6tLlv509ADkFtCR0tWDBFvZUsmnLrNPrICd/8AuC6GQ4Ou9T9TM6d2Dbom5g40RXAr3ASdyOk3dN9cRYJb0Y3iTQOqJXmTcmG4AnBRfWgwG5jDbk5Ifjh0CRGkl1CC5qWVcNuVA2CeB5weEucHDMaQXjgaw+IKRMBN4fDdeQuJWHn8mEIMKdmSWdVKknGZy5YfuYEBF4tPSrMIDNGvVOh4eiYElRwlDcOqWgc3tToxCy9EFYOUuQzxM/LR4yoUTRVgomfxTG8vcmtotkAApgzLh2eumuItJA4WlQ+ZgMuHuVIQ4mnGNiQPwQj8TzUIk0YYmTAZfcO8lUYr1ehbvoQdFd3f1z4eA3jVAL5wVWjO0cRSE2nzz4pDemejQ1tN2gIYx9jjzQtN5Ro/TBAYouTqQgi5+YdU4KEeAA6K4/IhdfluJxKYHFbBZThnDtaBjrsVBORK+JbGsNcuDZHSTXD/dRx6V1Rv0nHI7owG7Y7xRglZwoVg1a0W1BOC7FYT3Gfkn+p0IX2jzQQeOFtOSjJ913I88yBubsPjhjgP+WFCwOkZSg/VAa2utVhOTvCyzRsYYTRijRxg5aYMhSDgyDCHwcaWkmekShKQG44yx2UIjFt7MJUnFAKSBzDD/NNYggL6OGVRwAzRBCLAyB9npc1lTqaJck4fGabBe5TW9IEBMiklAMNxnhVMSRKqhmEFTDPOCVE+zVq4E2UVmj6rho6Kvu8ZQKBpRe0gmQdRWnXhaMwi5W299GRHlFKtNHrDCR3MqT4+4Jz/ipxMUID8N+TnReFAb/qICjzOA8BZcXTUpGP0EcX5Hh9d2jIpmbx0i8oNn2zh3W3Xya1wGXAyDXycpqtF3/2kSemCdSFrQ6tP9x+B9fndlOeH7m/oqvcL7GFwOQAg3jQggQiG8mw5lkCDN5U+PGUCJRkekT1melzVQRhqDfLUbqzLFLnkgRGZPm/AllxiNBcETBMXullCck4mDUOB5KAN8amxIrPArRHgND0eV7KKKJWOHrL8yXnmp7QVSg6UGZZ/G0E/CVRkoRGf9GV+kXZDU0iGTgJDypIk5JCSk6ZUSThymxKGOSHeGmdICUxJgyPOeehIUM4SaPrmp7eNCc3DGIYvNLdnXY+v+8hqQg9sFTSmKOERpfz7TNCDYXw2i7fkMTnMNv2wCjzdnx/m/xc47mQ7WL8g9ttDynaaAtnNcX/cAf+/km9R3EMuXRjc6xiN9zIASBdJT3GBaXR2U5So64ozMVSHSsEnwTPDq6vP3f/+7//uSydt2sOAK2ChEczp5ulpSo9omBNylSbYMX3qTbWQMPCIQ9kiXRKnOUfHUOYIgJIrTsYhP1JCugAlh0OWrKHgmRwxTvOxTc+QOVh1gLFMcnqCuHq9NMRNruv1fKKUZ0EzOdM52reOhjc0RQaD50oUrqLJyuwkwwoe5R8fKpYhcCZgBMvJlVWbpclkhPJsijIyhGeIwuMSMwRIQ2brbcDCrZqyYWcMN0XT2TNbJgQZIt7aU3nCIKvjvPqrvJPWX6og03MlIkMv/vYChw9cPp+cS7XaTgGryTr85Et4Mb3H+QTw4vLuS+kwuU5dDN1Z8q6ZPuXymKLv2rixyHUyS+mm1Swg61+uWQvv0ub2uLXndzh9tGcihAeM54qLOi/IYk3RGEY0bjt5plYhfXy90tkKhIRmImeBYGQu0BC9zEdJQB4PPLDNTzJ9i6LnMGX+k7UtgrLogN5AdZ9CAwfDhVMrNRSUUD7CVWqzwFkVS54ExBaMc261vB5FkCLaBVbBhqeZJA0jgMkqDQwi46KgU/HlAfBkefUHZFbxnJAVykLQ6pBeaMuxm8haqgAZXumOrwjPj4k0MkQWywpVeeZ84uKa5VwpPBTxPJutPooDQMmQOSSNojkAOPNclf8ZYbNfUIEvt/0XBN8hn9/pXIaurvuQ4OcBLhK9C6kxuUWuU30HwNV1XV22rmgPhj4uuNJdLTBCMqRic97lN+TQVfRVrx85+IsCPhb0vRD8bEsyzlUXtdwAKKMBr1OjnOtttnagCzTLXA6Tj2QMrQvVjwAgWRU9ria1XUIaIchgiOypVmKjL5wlDymRN9x+1qKMkGx5AygoWZOSDw1eGgQwGjmHLJDo46EcmM8aTTXEw8dTTrjBMCRHM5s3ymtBxJQXUyVP+ezs+NPQWVJhFUBkpUZWROmk+WtffcSsztfL4bb882wvPGURZGWxXs8DB9ITsb1WK6HJSkqPegDQl/Pmv7AC+wHwC4t/hO5aEroPM3SjelmmcTNd1wD0Lph7SE9JqPu4V6YovdEP2BSqF7jhBI8Q5Db28z0a9x8eaYUuLeKnpsaboC48gXLNlmYawbGM85GwcnFhhpiPqxP+tHCApmQFIB8UcmAwvDUEhsRRGnyikGXOg0VxEpUnjGGdzru/Noc8MpWlguCicJu3nDPhbV2pZgeGAHiLMxGRUnREoMnKMIfDs+UZoCg4GYAQz3blWQ1ghNHTrMS2NHBkKFtrsWSp2uu6P2V6mshsfpi0duYlT2jKUP4qppXjlJCUzpXDiZxGMk1pqKq6Oc9OV92fHgGsOW/551dgPwB+fs3/ELFL0n3AZ47etXGRjuv717/2uqpNd8HcIkItzFVkhbty3n+B2ULSdMFcUXJXXQhuu5yU2l+fG1xg959PnwO6q/javMYbn7kVlLDmvMoXCzElsaLjUame/v7gh2amioIzKQdTljAaStQsrq8ZWg4AJCpbK1UB3S2iVAQYxUFkPinZUqLD6emWT0NTUVbkIvL2PHNokhkGoBE0ZcnEmz3jHCzDhJY2UwnwqzBDylUOwxuhhZtF8rF8R6LXfykRkukJVjFf+vcAw/lhqJKTM1f0MkzjhKgGDM9gZBrnx+EkFxey8vbiT04/SSaU+eY/vwL7AfDza/5yRDdhvQxuVJfNSxMDU24a7va6XYgSBrl+lAT49KZcMxebktXR4c63Zredhp6yRsOQec51AVfXY8CbWj++64bzCcyWz24+TkYlhg9R8jacPliCKa4KJ4f81FBklRP4MVnNs8q5tE2NH66QIWUyni1X9EiDo6wghoJapvVaVwnAc4tgAFQMp2zJMJEqjeeZogFGbGfWMPME0SWTCWH8wwwFaMjKcKZyYjjKhFt6SFNVw6Lssp2tyJZQ36fxYaiPQT5lVjTLlJs8K1fVKJlZr5PWuzyBT94AWDkw3iF4kFuJkRWZXrXJPJSV9MgDm2Vu4SdXYD8AfnLBL8N162jdB7xrE4js+tG7PAFcJI2M0pU2qzV7sTLlJnfVgd0319Jt7J3O5cwbpfvWfQaGJBO40hGSCYZdaa2h+9xVZ4vc4bwxT7MmTGM2zrMp8gAS+M9D5uQLJBhNmDyELNWcpAk5vCnLJCB4i0ItSokoS6+sZAJDLhY5Oq2fkK3XYiNg9Sw6jVg4c3zVG4YxZTtwPkcTHh8yNXJCqZKzwqduAcZkkIGHWzgTa2/5uAxTElQD1f1xGgBpWy/KOU4uHF5xCJSViP8Ea2TrlE73Lw31cYScHxyGQ2Sq+hA2/fIK7AfAL96CLnB3o+tRQq6ZC4YILpJbZNYtcg9dXS90DXtZI7vGrjdbYPeQHpL53FW3zlQfEShNTb8jMxSIH5xcFGC32vMAny+XYFBJ3uIAQgwHK40EmUSjF05cmNGseMpoHBJ4CM82fRi9jEYp4jW+6vDs5lgdTV1PrdKvy+eQIT5xhWtYUPrJMH01JKNWl8M2BZ4+TbNjniuzxZJbmkyGNzuwhjj8qhxZXEtwVGxf1RDRrCHqAwGuCDIHsNclBlNuDXHD8UBAlM4bbkUOlWOpjIiTEsBNGab3ADCcnMPMcAu/sAKP8ABwQKtgB6vj+9ZDNk4uNuOtfi7Mvzkc/6U9eENTXRs3md51QpRe7X377+pS9mzA3TEad9t9hndLgX0h22131adDsarLEHiL4DULhiLScAiP6pKmmLjnyLVnCCaiEIZ5AEDSpkFlbgoY0Zsl8HwqDk1C5g3xKFdkmAE0TDNOjqgnNWu9psisWktCGCuyUjKl/OtZJczKFIBZMttMyHmQ+TjMBDeFsk04FQcrHz7JDCNOsipDU4bML4ieJg6Jyjk8TgNwzhyMBqVp932lYy3kZnFnQHGQ3fS1j6FZbiUgNzt7OFrcypxDW5wTGLL8BQIzi1Mqo5cDlSSn5xBx6K3FqwPBVFXlcNOnqsAjPAA+VUE/Kpnuc5dtOOduWtfMr/H0+kbpfZ+S0OV38w1ZubH56bpSIrcR0UyDY0jfhfeLoUL0tU+3XaeAJOMMCZCUSFw3nFIUdx7vnvNWXJ6HAMimRrMK4XGAMFyNwxWZk7oSTJQJLr3D/rmRjaGceZNwz7CjRT237wQAPovInLJAOKU1HgaLyTqEAZhY8EPVMPCYDzIBeNXMcBUqcrBZHWG2HlgpbL0W32PbkBKG0mbV9E2hMPQwLTafk0+h8TlLEkBOlIgWwoml6f6IQMMW3ixyhGr98K169b8udsu/tgL7AfBr638zejdwphu6Re7V3DefA9xPUzQpdTEEhlw8pN+ZgvGZfZqmm8wzJQrMikY7OPvD8RsjDJHLnDmNFz0eJADJCgfmAQBsfOY5TM7JCBLP8FT8gUl1HTe8Bc5PzWvFlMzom2qI83k0p3NFsi0fPFIBq0OVogSeJ7/8WcHNotHKR6crXNwUJX4RqMybiq9OaFJeC/zMSkfIFpjGAuVmm2y0/i69nNBT+tSIvPszsUBKREDjJPyETq8ghE4XwSzPFisfvC5vlj688lL2mSD96nbLn60C+wHwtCMd7s+zPXPJS2mG8nTxvKG7wJR9DnCNXTz9GtisC+/eAhjibqzr6ja6/1oDcK91ZnPLZ2BDMLY8dMO7w2b9j4D8++0gf2XMPyTnhnv140G7EZpDSCbFmmJyGEGmnCmalcDWYTLwEA05TrBMJhKLJooczFLmQT6GrYVQeikNYaTdsPythStTdUZTzUKWIVfk0eeEhr4cJhNKFGBgNPmhuaZ1dmwJKKt4GuYEla8CbatHMg1ZhsC20qbX/XsDsGumZGu9kOVgmLfxPwKwmiCxBOLQFP9++8BrPmoqPLBDcnwoOP8ONhNInB7f9AkrsB8An3BTjpSmhV3k59LSuL1asHvr+vkc4JLTu2bdya69C68dkLuWTIApgSnzMz0IphaAu8xFh0GceGz4O6KU2u5f/vKXf/u3f/NPCXkSGMqhbCE5qbOIVYM2lUM+81+nuFiU4aonN8RLLCfByCj/+guSGDqNjqfIuhZDyZilBAhGyUMws6e/Y9XZNttyYILlHFfDsc0QHg2AIEqaeLALK7DRr34OXy+RZYKZWbmh3Tlr8FSEVirJtt7XPrp/fzcQDN7W81D0+r4FEqqMqZIvEFhb2btFx4aSKyGQ2WwZkpFXE92fkod8niV8+kdVKTd9qgrsB8DTdnSvrvfGcb9W/gTNGnfNrUbgUrmTbqCbBgngnV1WXeauX31BIzN0M2vWTAi6g9bAKmJIKKJL7t6GhyTzYMpjA0GSPXv6l6t73eOf2+55CeA+K+SWTBjibeRVKPqqSc7tpAdGLsq0KsgAOanvBBs9gT4iyxmNcx5MMc8DgArgADgCaLbhyifPAKuf3OIFyltcHa6dFIW+NPKM03CLs005Ufhpo3FWI/ubg/ZL60ee3/DF7QGQEw4tk14p6AtEmUDfFEy1woWg7HgYBk7jMDgwPhkEbglrzgXd/FNV4OXb+KlS/G2T6XZZ/tzJKQUNctO88vd3L/3Wh7aOuuo6shcxl5AGR2wpu7puu9m8mdI16iO1lTUKvK90BfLiXx/pbx7094bMuvYIRiaGekG5ccKKRtA6Qm7Njv8XBYCyTVgdkk3lfzqgIf3qyhSiyZYJojFE6ZPZGsYJ8sw5zmSmBkBz8QALRm+lE4WAKKN8ikiI04uFN0UYk9Uw8+GBcZjZsh7YVkdDtt1eBXD/YyWhT4E8iFsImELQtF9m2TYbUoj2DiZqltJu2m6Nvm0tN7Lj5AzgZObpJ+GGm3/CCuwHwCfclCMlF6/Muk5zqVxa+qPDnT3OnexDN7ymrEe74TDIbcyJRoBcck7gKc3q1241JzoakwzJrMg6iPdHs912nL42URfwAaIPBFx5JPipAG8whqUNXLOgr1lcLCTYymeNBFamcHJkSIgTWn5DKc0Uk1aaLUDU0NojSpqIphD8yD+ACjybHn+O/+TwoyfI59nf05+UKEMCLV5uhMmZPBQmPkoeaJ7yPk+FWPzYtR7bZmnIcva+3w97cUNktvoTWImLl60Q2RoWhYYAw0QpSjJDmPzo/nO0gBGkE9LXj2CICX2FneGsaAufpwJf3lM+T07vzMThQ+908t3mzv2Ltm9N6a1+tANN2Qd/jwHtXrhpGYbaAX0t2wVGrqU8WdH7KYKm3zWmZ+jmE1B+DM2WEg1915ueEzffFz6+F+odUC/QKehb8nSHeTxMYgCofgTPJ0oYcwDyNYW81n8F39TKmUsmJxd6aUsMmRULDIex9gm65gDQbH7GZMAXQjUEi8xmWM1nmBVMRSMA2LWau/RYaf1922Mr+8KHHiAnTwGe/2AOz4NZ29cOFhoXxd45HpYPwM8cFRo72NtGTwJ45pTeAGw9pSAl/Hhc3doCS6tchAdY7/4E8CBn1el0CZ1IF7V3wLqD5enIHVazHgZagylXF9c4kO6PTHmEuOGmIDnEnXukZSBDxFUXAMyUcLpJ75vM5cBDnxgAEHDvocC6iTZBE/FGKNBkSED0F0LD7+bjMA+FvggxGILiIDmTZThxa53MSzteWWCuhTG8EFSGhvOIYbaGIRuOVUP5lJjtkAnexqk/qvtTgq3+OTm8n5T/ZikaloO12E3UbGvHaWycPW37WDWV3gOAngn9ZLuFe6nAfgDcy059I0/Xz1VELqrb6Err7HNR57WuzwfTRMDg3Xx9pCeBtkLJW7faFA0/qGYnjwAJPANo8boP2QPA+6DPBH5HKM9gZiM+ZciPDFG9hkDDJ2RNJHkNRP4oEuJWLCEmdN0fX+OatVgeJEwfN0TBCKvz0a9OkmfJ8JmkL+Lh8aSUAOofr/VXT7KHrsr75IdTBoNUVTya6M9ej7cEU8emnh9o6OXTIcHLDU9vy+wpvvoMP8/7wAJxO+G28PkrsB8An3+P3pZh11VrYKatd8ldXc23HxfX6PULgF7iTOk7NFFdg6b7DwNJWfsg1zUIyYbAADjSIvkBlokGsT4GTElMs5BP7cZsUWocwwkRcIE+kIs43kQhx0c5Qsh4+ZAjGMIF8lp5y/N03kzaJmBNvPqsC6dXOrWt+5PtLCL04u8xYAiWFaHcCNHkqfIzJahZGls8ZJYSt0Ep+3LfMLwQqM21vwTD8b+F+6rAfgDc137dzNaN1SBME9xY3O3V6/0eiK6hO7il7rBv6vVcQ0i9RgehhG+K3m+P4IgVh3oBpB6B88AtzegpecDpm2WlJcHQe64I56njd0YFBdNBACAJhihv/BeCH9TUD+UTpQUaXgiSLAFTyQDIougp0+OG9ANOSDn6UY6ghlUMP/w+t/hksDPCkVVtVz2Rr+mQ3Umwg35+kwxmx8dbgXJC5mc0DXMLb+stii09ZafIfiEHwxSA3aE3y2F4e2oKZiJOrAJtfhcV2A+Au9imbyc5V9SF7NK60nV2zwDkAqOj0Z5v3y6w10bN2kOC3nscPEP/PaSGYoqJ/mKq3sFqknDVU+K6kqFZ5gR4Gl2eOaU3RK5oPAY0Dh4o6yOQ+QEm9NCSPDKM4IEn7ioArMPXy6vhRLk2lwZlgGSLLfP0mYw3syOPt6o0w1UwNcStaiClUMYqAJxe9UzZi/bFfiGyCnsS0INxpbCILXkNlDy5jQBsR4SL04uSq5SOhP6OmypVghPSW79Hu2Hhivhi3OtMtuZTVWA/AD7VdrwrmS4kzgvu6rrb7rlr7N7qF7Vms244gnFp02vTtQ96YBh3W6Ppo0CdCBgm5zWpPNAESImDcUjJOfKNkB8J+E0hmWgfZiWGAIQbV7yZikZ5q60Ai/vdNOYjXLiil4PohEi2CSHJq8nkmd4wWjGrbJkA9Vw8Yfyb8jCwX73sE5SxBwBuiAi6fyZTNCFoZM4hWc5crXENAeDtcrtgCABfze2IkzO/7dMsDszEcxplyxX/RSyEISdruC1/8grsB8An36DXpre2p669S9tl7p67md73tQwCvQuvFwfQrPX63iVpdAfcPRe79gGs4xiyRdMUkoUDQABshWPOGxO8tiWEzxZeGw0BzjZyfE91+jtahgTIDNG0MwBk9gfRtfP640W4FVZBAqSPKwLlBXIFX/i0TBWry1c6tirQPuKmdP/zAXq86feruqpHzxXAbE01PDbg+TtArswOrdkyrLwexnaBXKzRU+r+uAwZ5hNM03dgkMeDoan8l/aaUuE2v4sK/OHt4C4yfmWSDvQrkb8WtraM92TiNr5oXk/phbGXcb1YX9aF4UV3ww378W/9hdKsC8/WFDxDHiBFMYVg6u96ARnVDpiY1TuYaFXaOiLw5kunfkFIB9FHtBg9SK/xVCBzbss44ZAHUzi5NpRzXKDSJtf4cBrD0uMk/WpSehnmodk0mcfpE0QfeQAEUSbu6qrkaczWH2kQOYGtqTGh5CoyhQpnvb31qzxSPVujmGRgXNl7BnCFKDNvmB+uxKURseg0k5i9sAV4GCYhAURXeVMEJsisUsxToSlKbvHfh5Ritu+RVr0/ATzSbr68FgfXHa5B4O52naUeRONWa80EHUGv0VN0GcM6tVlt2qcHfYchqxoQGIyLgQtBqNfUpESklJBZHQ3nUzszKwTiFnkS8Ky/SAC+ljQhCPBskVmUgJvivKD4CKNPiWc4pRl9gmrM1BHm+QNHa5ypYuEB2Ap0wp8eSNMxKc1mGGyGOWFIwz9SQ7IMTdGjuv98JrP8ikYPiSDhA6cpjUkGYGQAsr1QWBniat5sHrgaPSFkyQAjgLapZ0ahcwu26d4rsB8A976D38hfi3FpkWvsPrvhbrJe7Ld9NJeaOCWCSdBxtBsNwj3XFLwSatN4zahZzQtA7NP3wcg6y9nWjn88jiFqliAQgLily9anDbNebz0A5OYLIiHqMgIxkUyGYDIno1pSseKCJpQDQBo5TIaUJdBUOcTDJK+zq36dHec1QcNIdCYFpWFCRsU1pExT37fGakUvPVOKg5QXqQluGIYTshCocBwKR2+46vmZQGQwztVNhdUzOcMSY0tvthd/MqumyJSIYF8IwByWPyV5071XYD8A7n0Hv5F/Xake0W3HXebeNMndZ13DlcZNeR/3BqpBazrM6TWOngFmNQvv7zOrubCaJDgkayLckk0FqFXlP32NRpuTCf/wuowo/NenpunAp+GKjApX3DQAaMIByNywJhg3jDJPaY0NcZqUoyEwGU4QLtgg82lYYyWMZsWwNVQHEZEHQEJ4eiVFKq8gVZiy7YMhtMZZflm1fFxQMESPMkzfEmiQEKVnqs5uu2vuFdCsKXIPYx/+yFU+zwGSN7/3Cjwdl3tfxnX+zvq18hNqupzvT2xu/oWrizpMOC1Go9FuvIPrwnqNax+RTfVurk9Ruv9ac7McUuojMCFptO8ChRFFd5tY5WZolozXa5gjhpQ9WjSdnjceAyL2DABG9NJAZB4Y5j+3xcXrZQQ+8wwQ5kKoUPyUHj5kigf4i2KmB7v2nLIiFChMHnIFU+kUpxd8w6ME51OBRlXbCwDKyYdg1VzlOSHPTbXeTMLQoKNwZ/sGzptdUyJNH1VepVZbO8iQCRkA9SS2CxOuVUzchN+Eq57irBV4jIXvTwCPsY83V6FjOrtrM+ocz7s2S41D6wFLBtAasnLizTL3wOCqZuH7euZaBvrbv/3bulghuiG4vsNDTkqO0hC4KVwgU+klwFuz9NqQiMLpU4bA5LUxSSa3eRhZtqYQk5SCEnogcSVc1OzAGpoKX27J8QD8E1Y9DSvKtchkegQZpdF/tXjLtDqzsopoEJky/yX5bH18pUZeQ8gQ0Ux0MlsrQmp1luHpl32bMktpc/tpvJJC5gfnxyzDHr2maOgnB+aByxDfdO8V2A+Ae9/Bb+dfKwlXs3Clu96935H7qaMW3G0HM6UL4zUsU3qTNo3rIKaQtoIA9IVeXRnWpyatIk5cLcYUDD91E9HT4LzFhROLlX6EQwpHFrroeOZ4znPCMBjOs1l6gDy3upBkQtHzMH4u8FnFVzzzcUtYnVudhi4ZZCpBf7eo6mk28x4AAOUzCY+3sqIPEG8JPCMySpaeCvfgVDFDeiGYG9KjKonzPGSIzuoevyDECVuzPK/ccBI4om668wrsB8Cdb+C30p8GEXBtK2SX3Je8bj7B0GPAbSfg0w5M+TrI0Nsr0tpyRQPmlzjr6ZSaWm0IprgAWg+OAIpoFhXFbI0mbyFNAWhb2qKIhmzBJiVCHYpQt8qwHHSxnJvin9LsJGkqkiFBlGwhERkPwDBMi6KkwcPgA8hPVji8Usg83loEopkHANvC9WxgIsMoD+MtmGEmoy83yqihrDiZDq5o9AD0noj22ieq8s+PKf4jUz4ZsM1hMOYJKVkViEmaze+6Asepekjq3D/k0j5kUS5wLcD1JmhM/TAAV7oatEBmCwegnfniwgusXkapuSDtJj8aWT0OrKYGY0qgnPBZN0mP11nqPpA0NReyqbqhEBzmk7KIGQL0JAipczVL8Azw2UVHqxWGbxY3FKJ8Sqkc6MvNLM84KqW4WeZkC5xZw3FFUIQSxg2rZ8UxVWXYmipcU2Sp9qmloBMx2OzXZBjM7KxaHQxLDKz6cJtnNbEoIUwhMJxbs5D+rY78wJzzT5hgoxmhrGY4wi38AO5UsC61urXqO12UtPcngPvdu3dl7kDXYup9ugNBx9QFdC7tfl726UXybqhVaR+QngEoAHz9xdsln5SmeMDhtbk6XZcHuAZRn+JWDmjaVtdMD+IThzdLibp7g9RMkXClB4lqebg8S5UTQxhDQm7TVL48lx7nKP0IZ/CDlUkritPUvnF4XN0iuRmykiF+YUUzEaVtKGgLmfXSHNk8UxijkMDI0Ip4aJmGzIUWTlzLpLdf1r7WM5d5oG+2oSmBcFGKSNj0wBXYD4AH3tyvLW0uuWYB5/7rFEg30bsN3X9NRENBwLoJ0iw8JAD8orp3W81OuwE2Vb/OA5+GzAE8DKZ58VO4IuJrlxHIsMRMQSIe6An0AkmPAFaGhF60c1gm8VIqKxqZs9XvEKVZSla8IbLZIRryOfPUCssB19bPvA5GtkakCFzhfUKalCiZ4EiqaAQRi1sUU4T4YMKvAFZI/pEkCbjl4GLJAV5inNgLT2XU2vMjbR7gEVtTYGpS6HJgG5XA82j/+YAVOE7kQ9JcvIdc3fsXpQsokXbgkh9N5fkrXYKOprn7eUDtWzepmFoMAjDU42p8/iuS/OCmaitgYXgIZhjVm6a1MYnqpzCGzC1QCKSl6ko0tarpZWCcsILR9chglFWmZscqymdchinDwI9eQ9QKAfKDRwUSS3rCtZAStrqqxI+llYwpQ1GEWPNJjvNZJjA5pCdLwJAHRAALz1u1leQIlDAlOW4LCqNWvgfrkdwszi0PlKj14vkZzGuEWdoFeBK+0N/70LrU+daq73d1+xPA/e7duzLXONg703lxviMavaMfBtbd+krH80DvqNfg9Q73AVgH9MDQqbU/Q350Mf2lHnR0svObcd60SLwhDlk4OUw+mhGlng7JJzLksKCsShiMuWFdEp/LSZ+3FghpKk5AXCECADDBLJJwwgF6/lgACSZQsSyBSSRKeeIMUzLkhwkBT5hwhsFyWBQc8YbyTwDL1hTBB69qXj4A6mMKLACMHBQKsodlK8pzMHJb0w9I5EmDzHKLozIsNL7psSuwHwCPvb83V6cBufPI/Q/U5aen0Sa0G01cKyHrNZqFKZ0O16Rg9BfmvmGARJAeAKb0Jo+EPNeSgCnZmvU4IQAgQnoAU0zyiUuJw6KQaeqqYEiqNGZneeSGnJgl89wswbDV0Ry452cAMG+lmh4MHq85TpTREyJ43oDPjJ6chA+Qn2CT57P18ScAGkBTaliSVUMaiKxlJzCZzxlM7BEPLQHA0I54BpALegY5osAgj3aFBbCtA+BnXemkNGlv4VErsL8CetSd/ca6aj06wsVtp2dJmb6mr8d5BuBaDyHZlMYxjcaQXluvxWeurQB4PASDzzYkcL1smhT8pJR/QVlJ6ehe58t44JBpACZtmvB4QoWQTxqcfPg6SZRn8TCsm1PKGSxaS5mTSsSQMPkApxllsdI3lTle3FkFzRQBnv54qJ6PVdxQAfPQ4xMXhcaDIRgM6gVfi68gMIhD5pSQHg9kSLaTDAAKPNzsyNfCNT7M162u/dyLxrpU7Naq72UV13nuTwDXNfktNFpA69SJahadb/yiE0E6/XoHvb4zXb5WTgmgp/ShgeyShDFVPyWIVSMzy5tm5F21pwUOFsaUfBABEhW3VMuQkiCTYpED42BsA+NpcFRPFGXodH8kk5+GZADKzAn05GYTxjOhlMrnGkbD2wQaISReIAJqVp4EaVRSVUWG1YS3BLMqYwrvrZ/AkJ8KAkZgiExV8NPZlxd/3sJnUg44WhNLs/lDVuBrD/m7XvA0gm5F3Ioe9WTPAt+5a7fqk3+zuobXdl/N91tA5Ew0kcqrmys+0tn95MDDgIk2pGfB+PKhxoTTm+UKz0Rbn88EuWVlik9DJqhM2BIQz7hZtpD0wWavT9QBgzGLTFEGo4zS5CrYaAhrVcOnyQmAJeCIZsCQXF3kM8PA8Rq6Tm02TbCGOaxENHXzwAzhrW7wE92UZ0M/EhjPwAPYwpsqoHSPV739CeBNZ+D3BXf0zytw/IRAIcgEvw+qO9e460H1sml8Wk+PBBpChj0PQvq7xL7HoK/R9wCAhNdACZFZQ7D0yQ17BsSLW7ZkBBOMSU5aRdnOFCGrA33+1CGhQBOO1arPP0P63K4ckmGaM5enZOiVpeUTphoEeMiWDNYUXra98nsAIOY84+WDhykTrd9Ur/zT/WFmIWO1hd+5AvsB8Dvv/pvXXjvTWXQZXcnbJd6bPq5zaUl1q/qaBqS5a2faundkzwkyJ4Ta0/RBhvSIk15165g0mdcTGSJys3gmY05A0qNPOBUH4xant+x6Zd0zV5Rm8QCVhhw1BGDyrHv69JzV2JolD82wWPxUn/4JjaoETJ/JrIsgSVZaeVUCoCHPMCshEoCbFULZgQmIAFDahE27AlOB/QCYUmzhaxXQPuq2ukmkudPoOH7qi/smR5fXZClxGg2rfsQvTR3cl0KEYPXxompe3OpWBJ4pa1hedYGn7xM8SBjiBcIT8l83zLypGivPpopLU1BcuJFXK7YNm5XbWI1QrIm44snBxFWEXtjrxbny7ARAAs0jjZXZbPV9VmAEBWFL3xQrgrjIqpnU+uEDG8Kf7g8WUiDC+Dmdbfa7V2A/AH73E/DW9esj01m0npqajqNV+RAQ1a+1G87D1JI0MqRnrQ3dY4MGINIua15seahlc8JQg6MBlgMrcgRjKDTOs/TY9th4hjw1vqaYt2rCUBp8NOsy6RtyO8hxTiN5AHlGlYXc+7vMrSvnWVlFQwLidsy5YhVVjXwylBskoWTSh1d/pEplAlmewIR4ms13BaYCTx9jZ/wwwlxUV8Wi4oRHvQmzwHfu4K366DU811bqPhVz+gtBI9OF+6EuwRbQBCg9sr5Wh23Wi3yNG7J2hgOHgSfHtVTdsO7WGk1lAqDv56cp5jSeB6iTwJySnGe2ESsaHhjS4AEInLOKyopyEgDOCj49jNmSZJUJTXJJykoOZOstAbYEmAx7VOBaOSVkOQ/4Al9EeNTToqzirOCjNM+j/eebK7BuwZuNP6vB/gTwWXfm8+U1HaS2Yrhqpl3qXNpc3/jHtbBIr9T4rIwHsEjnooRsxTDAecbJNAQm3NZMITU7vOG0WpoadIbcolzlBMAwDRn5Smr8d8PNppmmzD/kaXf8Jedgq7IpeNFLYPDylwOHZy7H2hkiqx58As9s8w8gSm4Lx7B8cBQSVwdgAiUBDDFklXwhyCT95rsCKrA/ATzIMZh7/s716B23PKz9SDitBGlA9ARWlOlD9hjQ2XsTxzVBSph6lrbFqhZPk586JmT6TFgZApQbobhnwMPb+CEY6oYh8cJJIzDeVEkaSp4cDE8vbu0VL7fyMWuIIBFX4UdPw6GEESeQhi0HXt/3RY2PQWsTp88h7gEAH/F5xDhnyaYY4mwzx1tLMDJhNAkXnJ8LzR6+sgJT5Ffi7wL2sKfBFfqhGzA37Z1Rbl3Ij/L/zvTG/FaeA7gl6JtaoW9atGB90N8eoKkhMtHydDGc/2QLJ2fVJhoSsjr76tM/IMHc1MzCNMRN8ZND/skeP3hUxPTcEnR5ZJYhP4gtLk+cQ8PIMOdFxxOCkQl8RmQ+Patq3Ho3MhSLYIpPvCXkgTx6s+WGe2wkMyfAFBfmyODVlOE1vKJd6380/jpimrfGveXno/RvrfNHxf3RfvZXQD+6wr+p/xqZa6xb1cj69l/j01XnM8Fzq3z6C1zASMmYs2I+QspprDyYQuOB0BDXTFGlTzBrWFshc57/5OLSZHL4PT33oMpD+D55BAA+vDznaUiP8waWXq8n9wAgFwhfsx1DQoaDzHwc8km2CiQWzmTTrsB3V2A/AL67dNvwaxWY3qRnwWlbobXCHgB9JvCxwEu9Dut3SfHabsiaaZ1uGp+pYPwAIMNoHQqBNFlTTEx58ODJOLdDKYERpWEatpmErKHzQw+J01tXZHbANPo4JAGmJp45DA0+JFYYYJismM8zIP8w6EztKb2Rt7Ar8N0V2F8BfWfp1tv4nS5OM43gRfOP8v+i8+9Q3srzliu9zFRtLkwriuueGnTf5xAMfTUEXG/VXpMZ0qzmyfhFfQxHM04Ik3YNOrej5KdWDhmNf213YGzrwgR9OSfwpUGJtGx6RGk4eDBDueUfgBwgJIeIOcpqbFtR5sCn+ydmiADCNHwNv4Uv82sPPxp/HTHNW+Pe8vNRervwUa4+lZ+Xu8+nSvH7kul+fp/ta6xuHdDX2K6Yt1681fZnyrfyvJWDC8PELuBIuarYtDOG9NMWa8R4b+49AwB81UPGPS0IrHKVfLh+dp6+uKu+iLoq5YQjlzmrlKWaE3xmyTzUlMljOPkXSxMvtwyD4QxDBjPU6M+ef3wdtLb+8izcJCCr3Gaeq0LADCzNa/gtkxK+9vCj8dcR07w17i0/H6W3Ox/l6lP52V8BfarteJxk6qfW4yZPazPUuGlQS21K99EW63EZTr8z9EjwTVFfFtWnmPeVEW8IBhULD0PgHCV4flz4D68Fw3CoHZ/wo9cTPHIAorIVgiAcnolZPieB0ROKhZPRhPANz/x1LUrRhQPIFfxTyPOPhs1SJLC6xqyaLe8KvL4C+wHw+lpt5BsqMM1L26pzZZzc7NrvdPkT+IfeykR/1Hk1zYtPBv6tG52XMv24MiQfD4Tl+580+NCkBC/KZBWAhvMSjg++IedjQpAkMkWOtOk6dVO98ve+7xnQcPwLSi408/STSW6LmM8ALXDwKTffFXhTBfYD4E3l2uDXVqBWNe1JO6th6X1crM0uDA2B1WpC2Rt3rZMH1Bu3BwC57k/InK0PCuuDgWxKRJjitoCi4H4W3SxYFEzjNoukVFYNcbBxAtasX/AXoigw9HI2VbuPj5/M8dLjcA00swUyRRNmpgSqDj45jXILuwJvrcAfPnK+1fgz47uKr8+wa3aNn9t+MfVW/IX5DG/5GcCFcCufC9h3Dz9bPm9diK9ujjZ89sd5PBhefMVEo5LIAyPhsHkmGs1aE2dV7+55IBkQJUIAKIG+BxuBZuV+W8nw81Npvz9PpXu/k0/owV5/wqzen9L+BPD+Gm4Pn6gC3sRlMz09gcYFTl45/TwA6DX3mdX6mWjrWv90/zzrlbXLmsIMzaKm4oYcnurNdgU+YwX2A+Az7srO6bsrsPZfjftFPzXluJ8uhJnWb0jW3LmKr4Ca/rXbvNFP6x+ra/DW7Ap8kgrsB8An2YidxsdUwFs8R7XjacoEffmiNRfvxYfEGGZiODROaCbQrdQHfAuw9bsCv7YC+wHwa+u/o39wBeq5eA2ad8JFI16H/RYQ2CgT8IT8JJ+6F34ku5pfrGfSuNDv4a7AZ6jAfgB8hl3YOXxYBfoEwN006760Gf3XI9XoYTTutXePt1X5oqsBJIzDF8FbuSvwayuwHwC/tv47+gdXwC9H1nNr2fh0ZJGSR0Po8TBtegRTUfmlv/A2YJh5wLDKJOHFr5gCbL4r8MsrsB8Av3wLdgIfWYH5dcxxOr2bpqY8fDr42rVT9mCgj8bJCOP/Qgifknwxu4e7Ap+qAg97QOcedgnn3v6qO1kCr9/7W3m+1c/rI4a8FfeWn1v53PLzVvytuL+b/q11u4W/VbeP2q9bcW/5v5XPj9bfytMnuabipY0/6ie541cmNu0K7ArsCuwK/IYV2A+A33DT95J3BXYFdgWOCuwHwD4HuwK7ArsCv2kF9gPgN934vexdgV2BXYH9ANhnYFdgV2BX4DetwH4A/KYbv5e9K7ArsCuwHwD7DOwK7ArsCvymFXjYvwg2v3e8/sLvKH/cbq/h1ii3Qt/Cr7ar/FF+Vp/vkT9bPu9Zy2ewvXUebtX5M+T8mhw+27pu1XPyXAGjfM1K7wuzPwHc137tbHcFdgV2BT6sAvsB8GGl3I52BXYFdgXuqwL7AXBf+7Wz3RXYFdgV+LAK7AfAh5VyO9oV2BXYFbivCuwHwH3t1852V2BXYFfgwyqwHwAfVsrtaFdgV2BX4L4qsB8A97VfO9tdgV2BXYEPq8DD/j2Aj6rQrV8BXn9N+D2xbvm5FfdWrFt+buFv6X903Ft53op7C38r/3vX31rvR9Xnlv9bdfso/K38b8W9pX+rn7fmfyvuo+r3J4BH3dm9rl2BXYFdgW9UYD8AvlGgPb0rsCuwK/CoFdgPgEfd2b2uXYFdgV2Bb1RgPwC+UaA9vSuwK7Ar8KgV2A+AR93Zva5dgV2BXYFvVGA/AL5RoD29K7ArsCvwqBXYD4BH3dm9rl2BXYFdgW9U4G++MX/n034LuF8E9uvD/QZxw5+/rI+K2ypen/9b4/4q/2/N8/UV+D7kW+vw1igftd5bed7yfwv/1vxv4d8a9634W3F/tP5H1+1H53/L//4EcKsyW78rsCuwK/DgFdgPgAff4L28XYFdgV2BWxXYD4Bbldn6XYFdgV2BB6/AfgA8+Abv5e0K7ArsCtyqwH4A3KrM1u8K7ArsCjx4BfYD4ME3eC9vV2BXYFfgVgX2A+BWZbZ+V2BXYFfgwSvw4H8P4PPs3v/4H/tZ+3l249uZvPX3vm/9Pvu3I23ER1Tgr3/960e4+e187P8Q5idt+VsbylvTemsDupXPW/28Nc+Nv68K3Don97WKne2tCuzX0luV2fpdgV2BXYEHr8D+CuhBNvitb+633uze6udByreXcaMCt87JDfhW31kF9gPgzjZsp/tzKvDWB+FulD9nX3aUj63A/groY+u5ve0K7ArsCtxNBfYD4G62aie6K7ArsCvwsRXYD4CPref2tiuwK7ArcDcV+P+b2MvqIkqQ5gAAAABJRU5ErkJggg==",
      "text/plain": [
       "<PIL.JpegImagePlugin.JpegImageFile image mode=RGB size=512x512>"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "file_1 = \"./Train/glioma_tumor/gg (1).jpg\"\n",
    "Image.open(file_1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "data = []\n",
    "result = []\n",
    "\n",
    "classes = ['glioma_tumor', 'meningioma_tumor', 'no_tumor', 'pituitary_tumor']  \n",
    "base_path = r'./Train'\n",
    "\n",
    "encoder = OneHotEncoder()\n",
    "encoder.fit(np.array(range(len(classes))).reshape(-1, 1))\n",
    "\n",
    "for idx, class_name in enumerate(classes):\n",
    "    class_path = os.path.join(base_path, class_name)\n",
    "    for r, d, f in os.walk(class_path):\n",
    "        for file in f:\n",
    "            if '.jpg' in file:\n",
    "                img = Image.open(os.path.join(r, file))\n",
    "                img = img.resize((512, 512))\n",
    "                img = np.array(img)\n",
    "                \n",
    "                if img.shape == (512, 512, 3):\n",
    "                    data.append(img)\n",
    "                    result.append(encoder.transform([[idx]]).toarray())\n",
    "\n",
    "data = np.array(data)\n",
    "result = np.array(result).squeeze() "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "((2870, 512, 512, 3), (2870, 4))"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape, result.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[1., 0., 0., 0.],\n",
       "       [1., 0., 0., 0.],\n",
       "       [1., 0., 0., 0.],\n",
       "       ...,\n",
       "       [0., 0., 0., 1.],\n",
       "       [0., 0., 0., 1.],\n",
       "       [0., 0., 0., 1.]])"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "X_train, X_test, y_train, y_test = train_test_split(data, result, test_size=0.2, shuffle=True, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\anway\\anaconda3\\envs\\anway\\lib\\site-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"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_4\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential_4\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ conv2d_28 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)              │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">126</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)   │           <span style=\"color: #00af00; text-decoration-color: #00af00\">896</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_14 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">63</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">63</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_29 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)              │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">61</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">61</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │        <span style=\"color: #00af00; text-decoration-color: #00af00\">18,496</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_15 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">30</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)     │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_30 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)              │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">28</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">28</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │        <span style=\"color: #00af00; text-decoration-color: #00af00\">73,856</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_16 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">14</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)    │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_31 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv2D</span>)              │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">12</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)    │       <span style=\"color: #00af00; text-decoration-color: #00af00\">295,168</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_17 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling2D</span>) │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">6</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">256</span>)      │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten_4 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">9216</span>)           │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_8 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │     <span style=\"color: #00af00; text-decoration-color: #00af00\">1,179,776</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_18 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)            │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">128</span>)            │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_9 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">4</span>)              │           <span style=\"color: #00af00; text-decoration-color: #00af00\">516</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ conv2d_28 (\u001b[38;5;33mConv2D\u001b[0m)              │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m126\u001b[0m, \u001b[38;5;34m32\u001b[0m)   │           \u001b[38;5;34m896\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_14 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m63\u001b[0m, \u001b[38;5;34m63\u001b[0m, \u001b[38;5;34m32\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_29 (\u001b[38;5;33mConv2D\u001b[0m)              │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m61\u001b[0m, \u001b[38;5;34m61\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │        \u001b[38;5;34m18,496\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_15 (\u001b[38;5;33mMaxPooling2D\u001b[0m) │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m30\u001b[0m, \u001b[38;5;34m64\u001b[0m)     │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_30 (\u001b[38;5;33mConv2D\u001b[0m)              │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m28\u001b[0m, \u001b[38;5;34m128\u001b[0m)    │        \u001b[38;5;34m73,856\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_16 (\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;34m128\u001b[0m)    │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ conv2d_31 (\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;34m256\u001b[0m)    │       \u001b[38;5;34m295,168\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ max_pooling2d_17 (\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;34m256\u001b[0m)      │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten_4 (\u001b[38;5;33mFlatten\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m9216\u001b[0m)           │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_8 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │     \u001b[38;5;34m1,179,776\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_18 (\u001b[38;5;33mDropout\u001b[0m)            │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m128\u001b[0m)            │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_9 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m4\u001b[0m)              │           \u001b[38;5;34m516\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,568,708</span> (5.98 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m1,568,708\u001b[0m (5.98 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,568,708</span> (5.98 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,568,708\u001b[0m (5.98 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "None\n"
     ]
    }
   ],
   "source": [
    "model = models.Sequential()\n",
    "\n",
    "model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(128, 128, 3)))\n",
    "model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n",
    "\n",
    "model.add(layers.Conv2D(64, (3, 3), activation='relu'))\n",
    "model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n",
    "\n",
    "model.add(layers.Conv2D(128, (3, 3), activation='relu'))\n",
    "model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n",
    "\n",
    "model.add(layers.Conv2D(256, (3, 3), activation='relu'))\n",
    "model.add(layers.MaxPooling2D(pool_size=(2, 2)))\n",
    "\n",
    "model.add(layers.Flatten())\n",
    "model.add(layers.Dense(128, activation='relu'))\n",
    "model.add(layers.Dropout(0.5))\n",
    "model.add(layers.Dense(4, activation='softmax')) \n",
    "\n",
    "model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])\n",
    "\n",
    "print(model.summary())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m281s\u001b[0m 4s/step - accuracy: 0.3723 - loss: 239.7168 - val_accuracy: 0.5383 - val_loss: 1.3286 - learning_rate: 0.0010\n",
      "Epoch 2/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m271s\u001b[0m 4s/step - accuracy: 0.5520 - loss: 1.1053 - val_accuracy: 0.6655 - val_loss: 1.0482 - learning_rate: 0.0010\n",
      "Epoch 3/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m273s\u001b[0m 4s/step - accuracy: 0.6578 - loss: 0.8619 - val_accuracy: 0.7108 - val_loss: 0.8734 - learning_rate: 0.0010\n",
      "Epoch 4/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m277s\u001b[0m 4s/step - accuracy: 0.7055 - loss: 0.7317 - val_accuracy: 0.7352 - val_loss: 0.8233 - learning_rate: 0.0010\n",
      "Epoch 5/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m278s\u001b[0m 4s/step - accuracy: 0.7188 - loss: 0.6944 - val_accuracy: 0.7683 - val_loss: 0.7679 - learning_rate: 0.0010\n",
      "Epoch 6/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m278s\u001b[0m 4s/step - accuracy: 0.7651 - loss: 0.6090 - val_accuracy: 0.6725 - val_loss: 0.8872 - learning_rate: 0.0010\n",
      "Epoch 7/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m277s\u001b[0m 4s/step - accuracy: 0.7650 - loss: 0.5725 - val_accuracy: 0.7038 - val_loss: 0.8128 - learning_rate: 0.0010\n",
      "Epoch 8/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m279s\u001b[0m 4s/step - accuracy: 0.7981 - loss: 0.5045 - val_accuracy: 0.7439 - val_loss: 0.7510 - learning_rate: 5.0000e-04\n",
      "Epoch 9/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m277s\u001b[0m 4s/step - accuracy: 0.8331 - loss: 0.4415 - val_accuracy: 0.6655 - val_loss: 0.8726 - learning_rate: 5.0000e-04\n",
      "Epoch 10/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m287s\u001b[0m 4s/step - accuracy: 0.8243 - loss: 0.4394 - val_accuracy: 0.7805 - val_loss: 0.6960 - learning_rate: 5.0000e-04\n",
      "Epoch 11/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m286s\u001b[0m 4s/step - accuracy: 0.8204 - loss: 0.4440 - val_accuracy: 0.7596 - val_loss: 0.7163 - learning_rate: 5.0000e-04\n",
      "Epoch 12/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m279s\u001b[0m 4s/step - accuracy: 0.8574 - loss: 0.3721 - val_accuracy: 0.7561 - val_loss: 0.7048 - learning_rate: 5.0000e-04\n",
      "Epoch 13/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m287s\u001b[0m 4s/step - accuracy: 0.8526 - loss: 0.3543 - val_accuracy: 0.7700 - val_loss: 0.6706 - learning_rate: 2.5000e-04\n",
      "Epoch 14/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m284s\u001b[0m 4s/step - accuracy: 0.8777 - loss: 0.3301 - val_accuracy: 0.7979 - val_loss: 0.6135 - learning_rate: 2.5000e-04\n",
      "Epoch 15/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m280s\u001b[0m 4s/step - accuracy: 0.8830 - loss: 0.3015 - val_accuracy: 0.8014 - val_loss: 0.6026 - learning_rate: 2.5000e-04\n",
      "Epoch 16/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m277s\u001b[0m 4s/step - accuracy: 0.8894 - loss: 0.2870 - val_accuracy: 0.8188 - val_loss: 0.5736 - learning_rate: 2.5000e-04\n",
      "Epoch 17/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m282s\u001b[0m 4s/step - accuracy: 0.8881 - loss: 0.2995 - val_accuracy: 0.8240 - val_loss: 0.5225 - learning_rate: 2.5000e-04\n",
      "Epoch 18/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m281s\u001b[0m 4s/step - accuracy: 0.9002 - loss: 0.2509 - val_accuracy: 0.8415 - val_loss: 0.4885 - learning_rate: 2.5000e-04\n",
      "Epoch 19/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m281s\u001b[0m 4s/step - accuracy: 0.8915 - loss: 0.2701 - val_accuracy: 0.8415 - val_loss: 0.4896 - learning_rate: 2.5000e-04\n",
      "Epoch 20/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m282s\u001b[0m 4s/step - accuracy: 0.9021 - loss: 0.2525 - val_accuracy: 0.8397 - val_loss: 0.5043 - learning_rate: 2.5000e-04\n",
      "Epoch 21/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m280s\u001b[0m 4s/step - accuracy: 0.9090 - loss: 0.2155 - val_accuracy: 0.8328 - val_loss: 0.4927 - learning_rate: 1.2500e-04\n",
      "Epoch 22/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m283s\u001b[0m 4s/step - accuracy: 0.9256 - loss: 0.2017 - val_accuracy: 0.8415 - val_loss: 0.4638 - learning_rate: 1.2500e-04\n",
      "Epoch 23/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m280s\u001b[0m 4s/step - accuracy: 0.9299 - loss: 0.2030 - val_accuracy: 0.8293 - val_loss: 0.4771 - learning_rate: 1.2500e-04\n",
      "Epoch 24/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m283s\u001b[0m 4s/step - accuracy: 0.9271 - loss: 0.2020 - val_accuracy: 0.8467 - val_loss: 0.4553 - learning_rate: 1.2500e-04\n",
      "Epoch 25/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m282s\u001b[0m 4s/step - accuracy: 0.9164 - loss: 0.2171 - val_accuracy: 0.8502 - val_loss: 0.4508 - learning_rate: 1.2500e-04\n",
      "Epoch 26/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m282s\u001b[0m 4s/step - accuracy: 0.9318 - loss: 0.1790 - val_accuracy: 0.8467 - val_loss: 0.4484 - learning_rate: 1.2500e-04\n",
      "Epoch 27/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m281s\u001b[0m 4s/step - accuracy: 0.9421 - loss: 0.1579 - val_accuracy: 0.8502 - val_loss: 0.4423 - learning_rate: 1.2500e-04\n",
      "Epoch 28/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m280s\u001b[0m 4s/step - accuracy: 0.9322 - loss: 0.1713 - val_accuracy: 0.8554 - val_loss: 0.4280 - learning_rate: 1.2500e-04\n",
      "Epoch 29/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m283s\u001b[0m 4s/step - accuracy: 0.9332 - loss: 0.1755 - val_accuracy: 0.8711 - val_loss: 0.4111 - learning_rate: 1.2500e-04\n",
      "Epoch 30/30\n",
      "\u001b[1m72/72\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m280s\u001b[0m 4s/step - accuracy: 0.9351 - loss: 0.1770 - val_accuracy: 0.8624 - val_loss: 0.4169 - learning_rate: 1.2500e-04\n"
     ]
    }
   ],
   "source": [
    "early_stopping = EarlyStopping(monitor='val_accuracy', patience=5, restore_best_weights=True)\n",
    "lr_scheduler = ReduceLROnPlateau(monitor='val_loss', factor=0.5, patience=2, min_lr=1e-6)\n",
    "history = model.fit(X_train, y_train, batch_size=32, epochs=30, validation_data=(X_test, y_test), callbacks=[lr_scheduler])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [],
   "source": [
    "model.save('Trained_Model.keras')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'accuracy': [0.4102787375450134,\n",
       "  0.5374564528465271,\n",
       "  0.5905923247337341,\n",
       "  0.6302264928817749,\n",
       "  0.6842334270477295,\n",
       "  0.7238675951957703,\n",
       "  0.7565330862998962,\n",
       "  0.7713414430618286,\n",
       "  0.7935540080070496,\n",
       "  0.8061846494674683,\n",
       "  0.8231707215309143,\n",
       "  0.8140243887901306,\n",
       "  0.8305749297142029,\n",
       "  0.8562718033790588,\n",
       "  0.8601916432380676,\n",
       "  0.8858885169029236,\n",
       "  0.9011324048042297,\n",
       "  0.9102787375450134,\n",
       "  0.9046167135238647,\n",
       "  0.9359756112098694,\n",
       "  0.9416376352310181,\n",
       "  0.9303135871887207,\n",
       "  0.9429442286491394,\n",
       "  0.9381533265113831,\n",
       "  0.9385888576507568,\n",
       "  0.9486062526702881,\n",
       "  0.9429442286491394,\n",
       "  0.9416376352310181,\n",
       "  0.943379819393158,\n",
       "  0.9464285969734192],\n",
       " 'loss': [3.8498194217681885,\n",
       "  1.0519925355911255,\n",
       "  0.9116196036338806,\n",
       "  0.7942551374435425,\n",
       "  0.7058664560317993,\n",
       "  0.6376798152923584,\n",
       "  0.5742128491401672,\n",
       "  0.537481427192688,\n",
       "  0.4814664125442505,\n",
       "  0.45523715019226074,\n",
       "  0.43295857310295105,\n",
       "  0.4163340628147125,\n",
       "  0.38703423738479614,\n",
       "  0.343332976102829,\n",
       "  0.3320065140724182,\n",
       "  0.2693008780479431,\n",
       "  0.24446584284305573,\n",
       "  0.2214226871728897,\n",
       "  0.21324677765369415,\n",
       "  0.15497058629989624,\n",
       "  0.14663465321063995,\n",
       "  0.15099403262138367,\n",
       "  0.13991765677928925,\n",
       "  0.1487230658531189,\n",
       "  0.14160653948783875,\n",
       "  0.13295046985149384,\n",
       "  0.1368006467819214,\n",
       "  0.13607431948184967,\n",
       "  0.1319786012172699,\n",
       "  0.13551731407642365],\n",
       " 'val_accuracy': [0.5400696992874146,\n",
       "  0.6167247295379639,\n",
       "  0.7142857313156128,\n",
       "  0.7595818638801575,\n",
       "  0.792682945728302,\n",
       "  0.8310104608535767,\n",
       "  0.796167254447937,\n",
       "  0.8501741886138916,\n",
       "  0.7874564528465271,\n",
       "  0.8397212624549866,\n",
       "  0.8275261521339417,\n",
       "  0.8675957918167114,\n",
       "  0.8658536672592163,\n",
       "  0.8588849902153015,\n",
       "  0.8693379759788513,\n",
       "  0.8815330862998962,\n",
       "  0.8641114830970764,\n",
       "  0.897212564945221,\n",
       "  0.8989546895027161,\n",
       "  0.900696873664856,\n",
       "  0.9059233665466309,\n",
       "  0.907665491104126,\n",
       "  0.9094076752662659,\n",
       "  0.9024389982223511,\n",
       "  0.9094076752662659,\n",
       "  0.907665491104126,\n",
       "  0.9059233665466309,\n",
       "  0.9059233665466309,\n",
       "  0.9059233665466309,\n",
       "  0.904181182384491],\n",
       " 'val_loss': [1.1121315956115723,\n",
       "  1.0064079761505127,\n",
       "  0.7459136247634888,\n",
       "  0.666300356388092,\n",
       "  0.5333437323570251,\n",
       "  0.4853013753890991,\n",
       "  0.5103662610054016,\n",
       "  0.4536955952644348,\n",
       "  0.5251930356025696,\n",
       "  0.43876469135284424,\n",
       "  0.4716733694076538,\n",
       "  0.4264422655105591,\n",
       "  0.40492185950279236,\n",
       "  0.4092591106891632,\n",
       "  0.40695080161094666,\n",
       "  0.38106316328048706,\n",
       "  0.4501107633113861,\n",
       "  0.423921138048172,\n",
       "  0.3954177796840668,\n",
       "  0.45985710620880127,\n",
       "  0.446707546710968,\n",
       "  0.481725811958313,\n",
       "  0.4620593786239624,\n",
       "  0.4799121916294098,\n",
       "  0.4792037606239319,\n",
       "  0.4813311696052551,\n",
       "  0.4866402745246887,\n",
       "  0.488707959651947,\n",
       "  0.4873705506324768,\n",
       "  0.49090835452079773],\n",
       " 'learning_rate': [0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0010000000474974513,\n",
       "  0.0005000000237487257,\n",
       "  0.0005000000237487257,\n",
       "  0.0005000000237487257,\n",
       "  0.0002500000118743628,\n",
       "  0.0002500000118743628,\n",
       "  0.0001250000059371814,\n",
       "  0.0001250000059371814,\n",
       "  6.25000029685907e-05,\n",
       "  6.25000029685907e-05,\n",
       "  3.125000148429535e-05,\n",
       "  3.125000148429535e-05,\n",
       "  1.5625000742147677e-05,\n",
       "  1.5625000742147677e-05,\n",
       "  7.812500371073838e-06,\n",
       "  7.812500371073838e-06]}"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "history.history"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "import json\n",
    "with open('training_history.json', 'w') as f:\n",
    "    json.dump(history.history, f)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [],
   "source": [
    "with open('training_history.json', 'r') as json_file:\n",
    "    training_history_data = json.load(json_file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x20b6e767a60>"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "epochs = [i for i in range(1, 31)]\n",
    "plt.plot(epochs, training_history_data['loss'], label='Training loss')\n",
    "plt.plot(epochs, training_history_data['val_loss'], label='Validation loss')\n",
    "plt.xlabel('No. of Epochs')\n",
    "plt.ylabel('Loss')\n",
    "plt.title('Vizualization of Loss')\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x20baad4b370>"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "epochs = [i for i in range(1, 31)]\n",
    "plt.plot(epochs, training_history_data['accuracy'], label='Training accuracy')\n",
    "plt.plot(epochs, training_history_data['val_accuracy'], label='Validation accuracy')\n",
    "plt.xlabel('No. of Epochs')\n",
    "plt.ylabel('Accuracy')\n",
    "plt.title('Vizualization of Accuracy')\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 63ms/step\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "array([[1.0000000e+00, 2.6264210e-11, 2.8887794e-13, 9.8005941e-17],\n",
       "       [1.7551682e-09, 1.4627087e-05, 9.9422275e-09, 9.9998534e-01],\n",
       "       [1.0000000e+00, 5.4916844e-09, 5.1528248e-12, 7.0176991e-14],\n",
       "       ...,\n",
       "       [1.0000000e+00, 6.5567041e-10, 7.7513090e-10, 5.9424465e-13],\n",
       "       [1.3561352e-16, 2.3509569e-06, 9.9999762e-01, 1.9798518e-17],\n",
       "       [3.7013725e-03, 9.9628651e-01, 1.0284391e-05, 1.7575430e-06]],\n",
       "      dtype=float32)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred = model.predict(X_test)\n",
    "y_pred"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(574, 4)"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "y_pred.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 3, 0, 0, 3, 1, 3, 2, 0, 3, 1, 1, 0, 0, 3, 1, 2, 0, 2, 1, 1, 3,\n",
       "       1, 3, 1, 0, 3, 1, 3, 0, 1, 2, 2, 3, 3, 1, 1, 2, 3, 0, 1, 3, 3, 3,\n",
       "       2, 3, 3, 1, 1, 3, 1, 3, 1, 1, 0, 3, 0, 3, 2, 1, 1, 1, 0, 0, 0, 2,\n",
       "       0, 0, 1, 1, 1, 3, 0, 1, 1, 0, 3, 3, 0, 0, 2, 0, 0, 2, 0, 1, 1, 3,\n",
       "       2, 3, 1, 1, 2, 3, 0, 1, 0, 1, 3, 2, 3, 0, 2, 2, 1, 1, 3, 0, 3, 1,\n",
       "       0, 3, 2, 3, 3, 3, 3, 3, 2, 0, 0, 3, 2, 3, 0, 1, 1, 1, 1, 0, 0, 0,\n",
       "       2, 1, 3, 3, 2, 3, 1, 1, 1, 1, 3, 0, 1, 3, 2, 0, 1, 2, 0, 2, 1, 3,\n",
       "       0, 1, 0, 2, 1, 0, 1, 0, 0, 2, 1, 1, 1, 1, 0, 1, 1, 3, 3, 3, 2, 0,\n",
       "       0, 0, 3, 1, 1, 1, 2, 1, 0, 0, 3, 1, 3, 3, 2, 2, 1, 2, 0, 1, 0, 2,\n",
       "       0, 0, 3, 3, 3, 2, 1, 0, 0, 1, 0, 3, 1, 0, 3, 2, 1, 2, 0, 1, 3, 0,\n",
       "       3, 0, 3, 1, 0, 3, 0, 0, 0, 1, 0, 1, 0, 1, 0, 0, 3, 0, 1, 1, 3, 3,\n",
       "       0, 1, 0, 0, 1, 3, 3, 3, 0, 1, 0, 1, 1, 0, 2, 2, 3, 3, 3, 3, 1, 3,\n",
       "       1, 1, 1, 0, 3, 0, 1, 0, 0, 0, 0, 0, 3, 3, 2, 1, 0, 3, 3, 0, 2, 3,\n",
       "       2, 1, 0, 2, 1, 0, 3, 0, 1, 0, 2, 1, 3, 3, 3, 2, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 1, 1, 2, 3, 0, 1, 3, 0, 3, 0, 0, 1, 3, 1, 1, 0, 3, 2, 1, 0,\n",
       "       2, 3, 0, 0, 3, 0, 2, 1, 1, 0, 0, 0, 1, 1, 2, 3, 0, 0, 0, 1, 0, 0,\n",
       "       0, 3, 1, 3, 1, 0, 0, 3, 3, 0, 2, 3, 1, 3, 2, 0, 0, 3, 1, 0, 3, 3,\n",
       "       1, 0, 1, 0, 1, 2, 0, 1, 3, 0, 0, 3, 1, 0, 1, 1, 1, 3, 0, 1, 1, 1,\n",
       "       1, 0, 2, 2, 1, 2, 0, 0, 2, 1, 2, 3, 0, 0, 1, 3, 3, 1, 0, 2, 2, 2,\n",
       "       0, 1, 0, 1, 0, 1, 0, 0, 3, 3, 0, 0, 3, 1, 0, 0, 1, 1, 0, 0, 2, 3,\n",
       "       0, 3, 3, 0, 3, 3, 2, 1, 0, 3, 1, 1, 3, 1, 1, 3, 0, 3, 3, 0, 0, 1,\n",
       "       0, 0, 0, 0, 1, 3, 1, 2, 3, 1, 0, 2, 1, 1, 0, 3, 0, 2, 1, 3, 0, 2,\n",
       "       3, 0, 2, 3, 1, 1, 1, 0, 0, 3, 3, 3, 0, 3, 2, 0, 3, 1, 1, 1, 1, 3,\n",
       "       0, 1, 2, 1, 0, 1, 3, 1, 2, 3, 3, 1, 3, 3, 3, 0, 3, 0, 1, 3, 0, 0,\n",
       "       3, 0, 1, 0, 3, 3, 0, 0, 3, 3, 1, 3, 0, 1, 2, 1, 1, 3, 3, 3, 3, 3,\n",
       "       3, 0, 3, 1, 3, 3, 1, 0, 3, 3, 0, 3, 3, 0, 3, 0, 0, 0, 2, 0, 2, 0,\n",
       "       2, 1], dtype=int64)"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "predicted_categories = np.argmax(y_pred, axis=1)\n",
    "predicted_categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([0, 3, 0, 0, 3, 1, 3, 2, 0, 3, 1, 1, 1, 0, 3, 0, 1, 0, 2, 1, 0, 3,\n",
       "       1, 3, 1, 0, 3, 1, 3, 0, 1, 2, 2, 0, 3, 1, 0, 2, 3, 1, 1, 3, 3, 3,\n",
       "       2, 3, 3, 1, 1, 3, 1, 3, 1, 1, 0, 3, 0, 1, 2, 1, 1, 1, 0, 0, 0, 2,\n",
       "       1, 0, 1, 1, 1, 3, 0, 1, 1, 0, 3, 3, 0, 0, 2, 0, 1, 2, 0, 1, 1, 3,\n",
       "       1, 3, 2, 1, 2, 3, 0, 1, 0, 1, 3, 2, 3, 0, 2, 2, 1, 1, 3, 0, 3, 1,\n",
       "       0, 3, 2, 3, 3, 3, 3, 3, 2, 0, 0, 3, 2, 3, 0, 2, 1, 1, 0, 0, 0, 0,\n",
       "       2, 1, 3, 3, 2, 3, 1, 1, 1, 1, 3, 0, 1, 3, 2, 0, 1, 2, 0, 2, 1, 3,\n",
       "       0, 2, 0, 2, 1, 0, 1, 0, 0, 2, 1, 1, 1, 1, 0, 1, 1, 3, 3, 3, 2, 0,\n",
       "       0, 0, 3, 1, 1, 1, 2, 0, 0, 0, 3, 1, 3, 3, 2, 1, 1, 1, 0, 1, 0, 1,\n",
       "       1, 1, 3, 3, 3, 2, 1, 1, 0, 1, 0, 3, 1, 0, 3, 2, 3, 2, 0, 2, 3, 0,\n",
       "       3, 0, 1, 0, 0, 3, 0, 0, 0, 1, 0, 1, 0, 3, 0, 0, 3, 1, 1, 1, 3, 3,\n",
       "       0, 0, 0, 0, 1, 1, 3, 3, 0, 1, 0, 1, 1, 0, 2, 2, 3, 3, 3, 3, 1, 3,\n",
       "       1, 1, 1, 0, 3, 0, 1, 0, 0, 0, 0, 0, 3, 3, 1, 1, 0, 3, 3, 0, 2, 3,\n",
       "       2, 1, 0, 2, 1, 1, 3, 0, 1, 0, 2, 1, 3, 3, 3, 1, 0, 0, 0, 0, 0, 0,\n",
       "       0, 0, 1, 1, 2, 3, 1, 1, 3, 0, 3, 0, 0, 1, 3, 1, 0, 0, 3, 2, 1, 0,\n",
       "       2, 3, 1, 0, 3, 0, 2, 1, 1, 0, 2, 0, 1, 1, 1, 3, 0, 0, 0, 1, 0, 0,\n",
       "       0, 3, 1, 3, 1, 0, 0, 3, 3, 0, 2, 3, 1, 3, 2, 0, 0, 3, 1, 0, 3, 3,\n",
       "       3, 0, 1, 0, 1, 1, 0, 1, 3, 0, 0, 3, 1, 0, 1, 1, 1, 3, 0, 1, 3, 1,\n",
       "       1, 0, 2, 2, 0, 2, 0, 0, 2, 1, 2, 1, 0, 0, 1, 3, 3, 1, 0, 2, 2, 2,\n",
       "       0, 1, 0, 3, 0, 1, 0, 0, 3, 3, 0, 0, 3, 1, 0, 0, 1, 1, 0, 0, 2, 3,\n",
       "       0, 3, 3, 0, 3, 3, 2, 1, 0, 3, 1, 1, 3, 1, 1, 3, 0, 3, 3, 0, 0, 1,\n",
       "       0, 0, 0, 1, 1, 3, 1, 2, 3, 1, 0, 2, 1, 1, 0, 3, 1, 1, 1, 3, 0, 2,\n",
       "       1, 0, 2, 3, 1, 0, 1, 0, 0, 3, 3, 3, 0, 3, 2, 0, 3, 1, 1, 1, 2, 3,\n",
       "       0, 1, 2, 1, 3, 1, 3, 1, 2, 3, 3, 1, 3, 3, 3, 0, 3, 0, 1, 3, 0, 0,\n",
       "       3, 0, 1, 2, 3, 3, 0, 0, 3, 1, 0, 3, 0, 1, 2, 1, 1, 3, 3, 3, 3, 3,\n",
       "       3, 0, 3, 1, 3, 3, 1, 0, 3, 3, 0, 3, 1, 0, 3, 0, 0, 0, 2, 0, 2, 0,\n",
       "       2, 1], dtype=int64)"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "true_categories = np.argmax(y_test, axis=1)\n",
    "true_categories"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                  precision    recall  f1-score   support\n",
      "\n",
      "    glioma_tumor       0.91      0.93      0.92       179\n",
      "meningioma_tumor       0.87      0.82      0.84       169\n",
      "        no_tumor       0.86      0.90      0.88        70\n",
      " pituitary_tumor       0.95      0.96      0.96       156\n",
      "\n",
      "        accuracy                           0.90       574\n",
      "       macro avg       0.90      0.90      0.90       574\n",
      "    weighted avg       0.90      0.90      0.90       574\n",
      "\n"
     ]
    }
   ],
   "source": [
    "from sklearn.metrics import confusion_matrix,classification_report\n",
    "cm = confusion_matrix(true_categories,predicted_categories)\n",
    "# Precision Recall F1score\n",
    "print(classification_report(true_categories,predicted_categories,target_names=classes))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[167,  11,   0,   1],\n",
       "       [ 13, 139,  10,   7],\n",
       "       [  2,   5,  63,   0],\n",
       "       [  1,   5,   0, 150]], dtype=int64)"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1300x1300 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.figure(figsize=(13, 13))\n",
    "sns.heatmap(cm,annot=True)\n",
    "\n",
    "plt.xlabel('Predicted Class',fontsize = 10)\n",
    "plt.ylabel('Actual Class',fontsize = 10)\n",
    "plt.title('Brain Tumor Classification Confusion Matrix',fontsize = 15)\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "anway",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.15"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}