assignment_1.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "c91aaa1f",
   "metadata": {
    "_cell_guid": "b1076dfc-b9ad-4769-8c92-a6c4dae69d19",
    "_uuid": "8f2839f25d086af736a60e9eeb907d3b93b6e0e5",
    "execution": {
     "iopub.execute_input": "2025-03-10T06:16:49.233437Z",
     "iopub.status.busy": "2025-03-10T06:16:49.233155Z",
     "iopub.status.idle": "2025-03-10T06:16:50.404496Z",
     "shell.execute_reply": "2025-03-10T06:16:50.402838Z"
    },
    "papermill": {
     "duration": 1.17711,
     "end_time": "2025-03-10T06:16:50.406364",
     "exception": false,
     "start_time": "2025-03-10T06:16:49.229254",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# This Python 3 environment comes with many helpful analytics libraries installed\n",
    "# It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python\n",
    "# For example, here's several helpful packages to load\n",
    "\n",
    "import numpy as np # linear algebra\n",
    "import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)\n",
    "\n",
    "# Input data files are available in the read-only \"../input/\" directory\n",
    "# For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory\n",
    "\n",
    "import os\n",
    "for dirname, _, filenames in os.walk('/kaggle/input'):\n",
    "    for filename in filenames:\n",
    "        print(os.path.join(dirname, filename))\n",
    "\n",
    "# You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using \"Save & Run All\" \n",
    "# You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "5981ad0c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-03-10T06:16:50.412487Z",
     "iopub.status.busy": "2025-03-10T06:16:50.412047Z",
     "iopub.status.idle": "2025-03-10T06:16:55.754908Z",
     "shell.execute_reply": "2025-03-10T06:16:55.753980Z"
    },
    "papermill": {
     "duration": 5.347448,
     "end_time": "2025-03-10T06:16:55.756550",
     "exception": false,
     "start_time": "2025-03-10T06:16:50.409102",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Requirement already satisfied: wandb in /usr/local/lib/python3.10/dist-packages (0.19.1)\r\n",
      "Requirement already satisfied: click!=8.0.0,>=7.1 in /usr/local/lib/python3.10/dist-packages (from wandb) (8.1.7)\r\n",
      "Requirement already satisfied: docker-pycreds>=0.4.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (0.4.0)\r\n",
      "Requirement already satisfied: gitpython!=3.1.29,>=1.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (3.1.43)\r\n",
      "Requirement already satisfied: platformdirs in /usr/local/lib/python3.10/dist-packages (from wandb) (4.3.6)\r\n",
      "Requirement already satisfied: protobuf!=4.21.0,!=5.28.0,<6,>=3.19.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (3.20.3)\r\n",
      "Requirement already satisfied: psutil>=5.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (5.9.5)\r\n",
      "Requirement already satisfied: pydantic<3,>=2.6 in /usr/local/lib/python3.10/dist-packages (from wandb) (2.11.0a2)\r\n",
      "Requirement already satisfied: pyyaml in /usr/local/lib/python3.10/dist-packages (from wandb) (6.0.2)\r\n",
      "Requirement already satisfied: requests<3,>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (2.32.3)\r\n",
      "Requirement already satisfied: sentry-sdk>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from wandb) (2.19.2)\r\n",
      "Requirement already satisfied: setproctitle in /usr/local/lib/python3.10/dist-packages (from wandb) (1.3.4)\r\n",
      "Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from wandb) (75.1.0)\r\n",
      "Requirement already satisfied: typing-extensions<5,>=4.4 in /usr/local/lib/python3.10/dist-packages (from wandb) (4.12.2)\r\n",
      "Requirement already satisfied: six>=1.4.0 in /usr/local/lib/python3.10/dist-packages (from docker-pycreds>=0.4.0->wandb) (1.17.0)\r\n",
      "Requirement already satisfied: gitdb<5,>=4.0.1 in /usr/local/lib/python3.10/dist-packages (from gitpython!=3.1.29,>=1.0.0->wandb) (4.0.11)\r\n",
      "Requirement already satisfied: annotated-types>=0.6.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=2.6->wandb) (0.7.0)\r\n",
      "Requirement already satisfied: pydantic-core==2.29.0 in /usr/local/lib/python3.10/dist-packages (from pydantic<3,>=2.6->wandb) (2.29.0)\r\n",
      "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb) (3.4.1)\r\n",
      "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb) (3.10)\r\n",
      "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb) (2.3.0)\r\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests<3,>=2.0.0->wandb) (2025.1.31)\r\n",
      "Requirement already satisfied: smmap<6,>=3.0.1 in /usr/local/lib/python3.10/dist-packages (from gitdb<5,>=4.0.1->gitpython!=3.1.29,>=1.0.0->wandb) (5.0.1)\r\n"
     ]
    }
   ],
   "source": [
    "!pip install wandb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "06b9e12b",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-03-10T06:16:55.762290Z",
     "iopub.status.busy": "2025-03-10T06:16:55.761950Z",
     "iopub.status.idle": "2025-03-10T06:17:14.201025Z",
     "shell.execute_reply": "2025-03-10T06:17:14.200126Z"
    },
    "papermill": {
     "duration": 18.443554,
     "end_time": "2025-03-10T06:17:14.202532",
     "exception": false,
     "start_time": "2025-03-10T06:16:55.758978",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mwandb\u001b[0m: Using wandb-core as the SDK backend.  Please refer to https://wandb.me/wandb-core for more information.\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mcs23m071\u001b[0m (\u001b[33mcs23m071-indian-institute-of-technology-madras\u001b[0m). Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Consider setting the WANDB_API_KEY environment variable, or running `wandb login` from the command line.\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "from keras.datasets import fashion_mnist\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import wandb\n",
    "wandb.login(key=\"1b74d87eef0c8dff900595f1526e95e162049f6a\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "5d27c6dd",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-03-10T06:17:14.208393Z",
     "iopub.status.busy": "2025-03-10T06:17:14.208123Z",
     "iopub.status.idle": "2025-03-10T06:17:16.826449Z",
     "shell.execute_reply": "2025-03-10T06:17:16.825665Z"
    },
    "papermill": {
     "duration": 2.622566,
     "end_time": "2025-03-10T06:17:16.827832",
     "exception": false,
     "start_time": "2025-03-10T06:17:14.205266",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n",
      "\u001b[1m29515/29515\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n",
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n",
      "\u001b[1m26421880/26421880\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 0us/step\n",
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n",
      "\u001b[1m5148/5148\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n",
      "Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n",
      "\u001b[1m4422102/4422102\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 0us/step\n"
     ]
    }
   ],
   "source": [
    "# (train_imgs, train_lbls), (test_imgs, test_lbls) = fashion_mnist.load_data()\n",
    "(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3e056d87",
   "metadata": {
    "papermill": {
     "duration": 0.00357,
     "end_time": "2025-03-10T06:17:16.835605",
     "exception": false,
     "start_time": "2025-03-10T06:17:16.832035",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "id": "62b21373",
   "metadata": {
    "papermill": {
     "duration": 0.003365,
     "end_time": "2025-03-10T06:17:16.842610",
     "exception": false,
     "start_time": "2025-03-10T06:17:16.839245",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Question 1"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c117415c",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-03-10T06:17:16.851103Z",
     "iopub.status.busy": "2025-03-10T06:17:16.850801Z",
     "iopub.status.idle": "2025-03-10T06:17:17.479503Z",
     "shell.execute_reply": "2025-03-10T06:17:17.478740Z"
    },
    "papermill": {
     "duration": 0.634413,
     "end_time": "2025-03-10T06:17:17.480677",
     "exception": false,
     "start_time": "2025-03-10T06:17:16.846264",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA94AAAHICAYAAAC4fTKEAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuNSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/xnp5ZAAAACXBIWXMAAA9hAAAPYQGoP6dpAAB2z0lEQVR4nO3dd3wVdfb4/5MAKaRSAiQBEiCEKsalqEhHRESwYV9FFHv/WlbX3bVg14/IWnFdsfdeqCoKShORKkjvkBAgARJIKPP7w1/uGvM+h2TIQIDX8/HwsZsz98zMnTvvmXlzk3PCPM/zBAAAAAAABCL8UO8AAAAAAABHMibeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gCqlO+++07CwsLkww8/3O9rL7vsMklPTw9+pwAAAA6BsLAwueGGGw71bqASMPE+AK+++qqEhYWV+q9evXrSs2dPGTNmTKDbfv755+XVV18NdBtARf15PGj/fffddwd939avXy/33XefzJ49+6BvG1ixYoXccMMNkpmZKTVr1pSaNWtK69at5frrr5e5c+ce6t0DDti8efNk0KBBkpaWJlFRUZKamip9+vSRZ5555lDvWhkPP/ywfPrpp4d6N4DDatzgwFU/1DtwJHjggQekSZMm4nmeZGdny6uvviqnnXaafPHFF3L66acHss3nn39e6tatK5dddlkg6wf8eOONN0r9/Prrr8uECRPKxFu1alUp2/vPf/4j+/btK9dr169fL/fff7+kp6dLVlZWpWwfKI8vv/xSzj//fKlevbpcfPHFcuyxx0p4eLgsWrRIPv74Y3nhhRdkxYoVkpaWdqh3FfBlypQp0rNnT2ncuLFceeWV0qBBA1mzZo1MmzZNRowYITfeeOOh3sVSHn74YRk0aJCceeaZh3pXcBQ73MYNDhwT70rQr18/6dChQ+jnK664QurXry/vvPNOYBNvoCr661//WurnadOmyYQJE8rEK0uNGjX2+5o9e/aUe3IOVLZly5bJBRdcIGlpafLNN99IcnJyqeWPPfaYPP/88xIezi+g4fD10EMPSUJCgvz000+SmJhYallOTs6h2amDbNeuXRIREcFYRrkxbo4+XB0CkJiYKNHR0VK9+v/+XaOgoEBuu+02adSokURGRkqLFi3kySefFM/zSuXu2bNHhg0bJs2aNZPIyEhJT0+Xv//971JUVBR6TXp6uixYsEC+//770K/u9ujRQ0REdu/eLffff780b95coqKipE6dOtKlSxeZMGHCQXnvwP5MmDBBunTpIomJiRIbGystWrSQv//972Vet2/fPnnooYekYcOGEhUVJb1795alS5eWes2f/8Z75cqVEhYWJk8++aQ8/fTToXH0/PPPS8eOHUVEZMiQIaFxw59rIGiPP/64FBQUyKhRo8pMukVEqlevLjfddJM0atQoFPv222+la9euEhMTI4mJiXLGGWfIwoULQ8vnzp0rYWFh8vnnn4diP//8s4SFhclf/vKXUuvv16+fHH/88aGf09PT5fTTT5cffvhBOnXqJFFRUdK0aVN5/fXXK/Nt4yizbNkyadOmTZnJg4hIvXr1RETk7LPPLnN+DhgwoMy5PH36dAkLCyv1J3t5eXlyyy23hJ6hMjIy5LHHHivzj6pPPvmkdO7cWerUqSPR0dHSvn37MvVCwsLCpKCgQF577bXQveCPvz24bt06ufzyy6V+/foSGRkpbdq0kVdeeaXUOkpqkbz77rvyj3/8Q1JTU6VmzZqybdu2Ch03HN3KM27+6NNPP5W2bduGzsuxY8eWec0vv/wi/fr1k/j4eImNjZXevXvLtGnTyryuvGPq3Xfflfbt20tcXJzEx8fLMcccIyNGjPD/po9yfONdCfLz8yU3N1c8z5OcnBx55plnZMeOHaFv+TzPk4EDB8rEiRPliiuukKysLBk3bpzccccdsm7dOhk+fHhoXUOHDpXXXntNBg0aJLfddptMnz5dHnnkEVm4cKF88sknIiLy9NNPy4033iixsbFyzz33iIhI/fr1RUTkvvvuk0ceeUSGDh0qnTp1km3btsnMmTNl1qxZ0qdPn4N8ZIDSFixYIKeffrq0a9dOHnjgAYmMjJSlS5fKjz/+WOa1jz76qISHh8vtt98u+fn58vjjj8vFF18s06dP3+92Ro0aJbt27ZKrrrpKIiMj5ayzzpLt27fLv/71L7nqqquka9euIiLSuXPnSn+PwB99+eWXkpGRUWrya/n666+lX79+0rRpU7nvvvtk586d8swzz8hJJ50ks2bNkvT0dGnbtq0kJibKpEmTZODAgSIiMnnyZAkPD5c5c+bItm3bJD4+Xvbt2ydTpkyRq666qtQ2li5dKoMGDZIrrrhCBg8eLK+88opcdtll0r59e2nTpk2lHwMc+dLS0mTq1Kkyf/58adu2rfM1Xbt2lc8++yx0fnqeJz/++KOEh4fL5MmTy5zLJ510koiIFBYWSvfu3WXdunVy9dVXS+PGjWXKlCly9913y4YNG+Tpp58ObWPEiBEycOBAufjii6W4uFjeffddOffcc+XLL7+U/v37i8jvfxJV8oxUMjaaNWsmIiLZ2dlywgknhIpZJSUlyZgxY+SKK66Qbdu2yS233FLqPQ0bNkwiIiLk9ttvl6KiIomIiKjMw4ojXHnGTYkffvhBPv74Y7nuuuskLi5O/v3vf8s555wjq1evljp16ojI789YXbt2lfj4eLnzzjulRo0aMnLkSOnRo4d8//33oftQecfUhAkT5MILL5TevXvLY489JiIiCxculB9//FFuvvnm4A7MkcyDb6NGjfJEpMx/kZGR3quvvhp63aeffuqJiPfggw+Wyh80aJAXFhbmLV261PM8z5s9e7YnIt7QoUNLve7222/3RMT79ttvQ7E2bdp43bt3L7NPxx57rNe/f/9KfJeAf9dff733x8vM8OHDPRHxNm3apOZMnDjRExGvVatWXlFRUSg+YsQIT0S8efPmhWKDBw/20tLSQj+vWLHCExEvPj7ey8nJKbXen376yRMRb9SoUQf+xoByyM/P90TEO/PMM8ss27p1q7dp06bQf4WFhZ7neV5WVpZXr149b/PmzaHXzpkzxwsPD/cuvfTSUKx///5ep06dQj+fffbZ3tlnn+1Vq1bNGzNmjOd5njdr1ixPRLzPPvss9Lq0tDRPRLxJkyaFYjk5OV5kZKR32223Vd6bx1Fl/PjxXrVq1bxq1ap5J554onfnnXd648aN84qLi0OvKbkGjx492vM8z5s7d64nIt65557rHX/88aHXDRw40DvuuONCPw8bNsyLiYnxFi9eXGqbd911l1etWjVv9erVoVjJOCpRXFzstW3b1uvVq1epeExMjDd48OAy7+OKK67wkpOTvdzc3FLxCy64wEtISAitv+Q+1bRp0zLbBMqrPOPG8zxPRLyIiIjQfMHzfr8viIj3zDPPhGJnnnmmFxER4S1btiwUW79+vRcXF+d169YtFCvvmLr55pu9+Ph4b8+ePZX6vo9m/Kp5JXjuuedkwoQJMmHCBHnzzTelZ8+eMnToUPn4449FRGT06NFSrVo1uemmm0rl3XbbbeJ5XujXqUaPHi0iIv/v//2/Mq8TEfnqq6/2uy+JiYmyYMECWbJkyQG/L6Cylfw61Weffbbfv7seMmRIqW8PSr6lXr58+X63c84550hSUpL/HQUqQcmvncbGxpZZ1qNHD0lKSgr999xzz8mGDRtk9uzZctlll0nt2rVDr23Xrp306dMndI8Q+X08zJo1SwoKCkTk929DTjvtNMnKypLJkyeLyO/fHIaFhUmXLl1Kbbt169ah8SQikpSUJC1atCjX2AJc+vTpI1OnTpWBAwfKnDlz5PHHH5e+fftKampq6NfIjzvuOImNjZVJkyaJyO/nZ8OGDeXSSy+VWbNmSWFhoXieJz/88EOp8/ODDz6Qrl27Sq1atSQ3Nzf038knnyx79+4NrU9EJDo6OvT/t27dKvn5+aGxsj+e58lHH30kAwYMEM/zSm2rb9++kp+fX2Y9gwcPLrVNoCLKM25KnHzyyaHfzBD5/b4QHx8fum7v3btXxo8fL2eeeaY0bdo09Lrk5GS56KKL5Icffgjdk8o7phITE6WgoIA/V61ETLwrQadOneTkk0+Wk08+WS6++GL56quvpHXr1nLDDTdIcXGxrFq1SlJSUiQuLq5UXkll51WrVoX+Nzw8XDIyMkq9rkGDBpKYmBh6neWBBx6QvLw8yczMlGOOOUbuuOMOWtWgyjj//PPlpJNOkqFDh0r9+vXlggsukPfff985CW/cuHGpn2vVqiUivz9M7U+TJk0qZ4eBA1Byzd+xY0eZZSNHjgz9Y22Jkmt8ixYtyry+VatWkpubG5pod+3aVfbs2SNTp06V3377TXJycqRr167SrVu3UhPv1q1bl5rEi5QdWyK/j6/yjC1A07FjR/n4449l69atMmPGDLn77rtl+/btMmjQIPn111+lWrVqcuKJJ5Y6P7t27SpdunSRvXv3yrRp0+TXX3+VLVu2lJp4L1myRMaOHVvqH6qSkpLk5JNPFpHSRai+/PJLOeGEEyQqKkpq164tSUlJ8sILL0h+fv5+93/Tpk2Sl5cnL730UpltDRkypMy2RLjX4MDtb9yU2N91e9OmTVJYWKjeP/bt2ydr1qwRkfKPqeuuu04yMzOlX79+0rBhQ7n88sudf1eO8uNvvAMQHh4uPXv2lBEjRvj65jksLMz3trt16ybLli2Tzz77TMaPHy8vv/yyDB8+XF588UUZOnSo7/UClSE6OlomTZokEydOlK+++krGjh0r7733nvTq1UvGjx8v1apVC732j///j7w/FSTUtgMcagkJCZKcnCzz588vs6zkb+1Wrlzpa90dOnSQqKgomTRpkjRu3Fjq1asnmZmZ0rVrV3n++eelqKhIJk+eLGeddVaZ3AMZW8D+RERESMeOHaVjx46SmZkpQ4YMkQ8++EDuvfde6dKlizz00EOya9cumTx5stxzzz2SmJgobdu2lcmTJ4fq1fxx4r1v3z7p06eP3Hnnnc7tZWZmioiE/k68W7du8vzzz0tycrLUqFFDRo0aJW+//fZ+97vkH4D/+te/yuDBg52vadeuXamfudegsljjRqRyr9vlHVP16tWT2bNny7hx42TMmDEyZswYGTVqlFx66aXy2muvVXi7YOIdmD179ojI7990pKWlyddffy3bt28v9a33okWLRERCvVvT0tJk3759smTJklJ9jrOzsyUvL69Uj1drcl67dm0ZMmSIDBkyRHbs2CHdunWT++67j4k3qoTw8HDp3bu39O7dW5566il5+OGH5Z577pGJEyeG/rU1CAfyD1qAX/3795eXX35ZZsyYIZ06dTJfW3KN/+2338osW7RokdStW1diYmJE5PeHtE6dOsnkyZOlcePGoYlK165dpaioSN566y3Jzs6Wbt26VfI7AsqvpNXqhg0bROT387O4uFjeeecdWbduXei8LflNjfr160tmZmZoAi7ye+GzHTt27Pf+8NFHH0lUVJSMGzdOIiMjQ/FRo0aVea3rfpCUlCRxcXGyd+/eQO9FwP78edyUR1JSktSsWVO9f4SHh4e6Z5R3TIn8fq8ZMGCADBgwQPbt2yfXXXedjBw5Uv75z3+W+Q1d7B+/ah6A3bt3y/jx4yUiIkJatWolp512muzdu1eeffbZUq8bPny4hIWFSb9+/URE5LTTThMRKVWhU0TkqaeeEhEJVeQUEYmJiZG8vLwy2968eXOpn2NjYyUjI6NUOzLgUNmyZUuZWFZWlohI4OdoyYTFNW6AoNx5551Ss2ZNufzyyyU7O7vM8j9+W5GcnCxZWVny2muvlTpP58+fL+PHjw/dI0p07dpVpk+fLhMnTgxNYOrWrSutWrUKVaD94zeHQFAmTpzo/OatpC5Bya+/Hn/88VKjRg157LHHpHbt2qEq+l27dpVp06bJ999/X+acPe+882Tq1Kkybty4MuvPy8sLfdFRrVo1CQsLk71794aWr1y5Uj799NMyea5nqGrVqsk555wjH330kfO3VDZt2mQcAaDiyjtuyqNatWpyyimnyGeffVbqN6mys7Pl7bffli5dukh8fLyIlH9M/XlOER4eHvqtD+YV/vCNdyUYM2ZM6NvrnJwcefvtt2XJkiVy1113SXx8vAwYMEB69uwp99xzj6xcuVKOPfZYGT9+vHz22Wdyyy23hIolHHvssTJ48GB56aWXJC8vT7p37y4zZsyQ1157Tc4880zp2bNnaJvt27eXF154QR588EHJyMiQevXqSa9evaR169bSo0cPad++vdSuXVtmzpwpH374odxwww2H5NgAf/TAAw/IpEmTpH///pKWliY5OTny/PPPS8OGDcsUgKpszZo1k8TERHnxxRclLi5OYmJi5Pjjj+dv9BCo5s2by9tvvy0XXnihtGjRQi6++GI59thjxfM8WbFihbz99tsSHh4uDRs2FBGRJ554Qvr16ycnnniiXHHFFaF2YgkJCXLfffeVWnfXrl3loYcekjVr1pSarHTr1k1Gjhwp6enpofUCQbrxxhulsLBQzjrrLGnZsqUUFxfLlClT5L333pP09PTQ30jXrFlT2rdvL9OmTQv18Bb5/ZwtKCiQgoKCMhPvO+64Qz7//HM5/fTTQ23vCgoKZN68efLhhx/KypUrpW7dutK/f3956qmn5NRTT5WLLrpIcnJy5LnnnpOMjIwytW7at28vX3/9tTz11FOSkpIiTZo0keOPP14effRRmThxohx//PFy5ZVXSuvWrWXLli0ya9Ys+frrr53/eAz4Vd5xU14PPvigTJgwQbp06SLXXXedVK9eXUaOHClFRUXy+OOPh15X3jE1dOhQ2bJli/Tq1UsaNmwoq1atkmeeeUaysrJK/WYuKuAQVVM/IrjaiUVFRXlZWVneCy+84O3bty/02u3bt3u33nqrl5KS4tWoUcNr3ry598QTT5R6jed53u7du73777/fa9KkiVejRg2vUaNG3t133+3t2rWr1Os2btzo9e/f34uLi/NEJNRa7MEHH/Q6derkJSYmetHR0V7Lli29hx56qExrAuBg+HM7sW+++cY744wzvJSUFC8iIsJLSUnxLrzwwlItLUratHzwwQel1lXSKuyP7cC0dmJPPPGEc38+++wzr3Xr1l716tVpLYaDaunSpd61117rZWRkeFFRUaHr8zXXXOPNnj271Gu//vpr76STTvKio6O9+Ph4b8CAAd6vv/5aZp3btm3zqlWr5sXFxZVq9/Lmm296IuJdcsklZXLS0tKcLSe7d+/ubFEJlMeYMWO8yy+/3GvZsqUXGxvrRUREeBkZGd6NN97oZWdnl3rtHXfc4YmI99hjj5WKZ2RkeCJSqhVSie3bt3t33323l5GR4UVERHh169b1Onfu7D355JOlnm/++9//es2bN/ciIyO9li1beqNGjfLuvfde78+Pu4sWLfK6devmRUdHeyJSqrVYdna2d/3113uNGjXyatSo4TVo0MDr3bu399JLL4Veo92ngIoo77gREe/6668vk5+WllamLd6sWbO8vn37erGxsV7NmjW9nj17elOmTCmTW54x9eGHH3qnnHKKV69ePS8iIsJr3Lixd/XVV3sbNmyo3ANxFAnzPKqpAAAAAAAQFP7GGwAAAACAADHxBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAhQ9fK+MCwsLMj9AA6JA2ljf6jHhLX9A3lfFdGyZUtn/Nlnn1VzPvjgA2f8l19+UXOKi4ud8d27d6s5bdu2dcbPOussNWfZsmXO+BNPPKHm5OXlqcsOR4fzmKhs6enp6rIePXo442eccYaas3nzZmf8zTffVHNmzZrljGtjT0TknHPOUZf17t3bGS8sLFRztP176aWX1Jwjjd9xcbDGhLadg3UvqFevnrqsV69ezvjQoUPVHO26unDhQjVHu08kJiaqOZ07d3bGp02bpub8/e9/d8Z37typ5vhxqD9TC/cJoKzyjAu+8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQGFeOUsTUoUQR6KqUpnzYFUoz8rKUpddcMEFzrhVIXnv3r3OeExMjJoTHR3tjNepU0fNqUyLFy9Wl+3bt88Zb9GihZqTnZ3tjI8bN07NefLJJ53x+fPnqzkHS1UZE5WtX79+6rJbb73VGbeqFEdERDjju3btUnPi4uKcca0Cv4hI/fr1nfGVK1eqOXv27FGXbdiwwRnPz89XcyIjI53x1NRUNeebb75xxm+66SY1pyqrClXNK/s+UbduXWf85ptvVnNOPvlkZ1w7R0RECgoKKpyjVe3XxpDF6n6xdu1aZ1wbJyL6PWzLli1qzqRJk5zxZ555Rs3ZunWruuxQO1LvE8CBoKo5AAAAAACHGBNvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAAJEOzEc1Q7nlhjx8fHqstdff90Zb9eunZoTHu7+d7jt27erOVrrJKt9i9aCrEaNGmpOQkKCM661qRHRW4NVZns2EZGoqChnXGs5I6K3opo8ebKac8kll1Rsx3w6nMeEiEizZs2c8fvuu0/N0VrC1axZU83Rxot23onobb4aNWqk5mis7VjLtLZhVgsybTxb7ZO0VmN5eXlqzu23364uO9QO13Zi2ngQEfniiy+ccW08iFTuNb+oqEjN0c6t2NjYSt2Odi1OSkpSc6pXr16hdVnLCgsL1ZwXX3zRGf/kk0/UnIPlcL9PAEGgnRgAAAAAAIcYE28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBBVzQOmHTc/FSHj4uLUZV26dHHGx4wZU+HtWJ91tWrVnHGrIm5l8nMeWsf6cK7M+fXXX6vL0tLSnPHNmzerOVolZK2Cq4j+ufs5NlqVaBGR4uJiZ1w7H/1upzL5qUCcnJys5vTt29cZX7RoUcV2bD8O5zEhIvL8888741o1ZhH93LcqKGvV7K1roVbB2MrRqpBr2xexq5pHRkaqyzRatWhrv7Xj3bZtWzVH68bw1VdfGXt3cFSFquZ+vP/+++qyunXrOuNWtXqt+4R1fLSK59Z5qlUityqUa+ecdc5rHTOsLhuVeX+zKqFr+3DmmWeqOTt27KjQfvl1uN8ngCBQ1RwAAAAAgEOMiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAdL7BKFSaC0ktPYsIiIZGRnO+NChQ9WcnTt3OuMFBQVqjtZ6Y8aMGWqOn7ZhWusIq62TluNn+35aTlUl7du3d8a1lmEiIrm5uc641RpMO05W26LU1FRnvGbNmmqO9rlrLWdE9P22xpF2DlltYrTza/v27WrO2rVrK7Qui/V+tPF/++23V3g7R7JXX33VGb/11lvVnE2bNjnj2dnZao7W3tE6jzVauzwRveWTZdu2beoy7V7hh7XfWpumNWvWqDlVoW3Y4UprRdigQQM1R2tVZ7W40q5r1jU/JibGGbeeAbRWY9Y1Ultm3cO0fbO2ox0DK0dr82W1OdT2bcCAAWrOO++8oy4DcOjxjTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAaKqecC0StFW9ctevXo54yeffLKao1VWjoyMVHO0KqR9+vRRc15++WVn3Kr+63meM24dA01sbKy6TKuCWlhYWOHtVCU9e/Z0xq3PVlumHSMR/VwtKipSc/72t7854+vXr1dztHM1JSVFzdmwYYMzblXF1SouW8dNO7/+8pe/qDk33nijM65VlhfRq7Rbn8+gQYOccaqal6Z1ZZg6daqaM3DgQGd8+vTpao72GVrVnTdv3uyMW9XBtfPIqoZs7YO231Yl9KSkJHVZRffhrrvuqvC6sH+1atVyxq2q5to92KpqrlXatro4+LkfaV0ptLjF6myirc/PvlnPNNoYsu4T2udgPaNR1Ryo2vjGGwAAAACAADHxBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBAtBMLmNUmRtOxY0dnPD09Xc3R2mVY7ZbGjRvnjB933HFqzuOPP+6Mz5w5U82ZN2+eM75w4UI1p1OnTs64dmxERKZMmeKMW22EDgdaGymrfYufNnZRUVHOeH5+vprzn//8xxk/5ZRT1BytNdeoUaPUnKuvvtoZnz9/vppTu3ZtZ9xqLaO1xRs+fLiac9111znjWtsmEf1YW63vWrZs6YxnZmaqOYsXL1aXHW3+/e9/q8tuvvlmZ3z16tVqzqZNm5zxgoICNUf7fLdv367maKzz2NoH7bysUaOGmqPtX0JCgpozZswYZ9xqWwb/2rVr54xb54nWasx6btCWWe3ttPaSy5YtU3NWrlzpjFvntrYPVs7u3budcaulmnasTz/99ArvW2JiopqjtbfUWroBqPr4xhsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAAIV5nueV64VhYUHvy2HLOjba4e3Tp4+ao1UOt6pfapU59+3bp+ZofvrpJ3XZ0qVLnXE/1duTk5PVZdr7sfZNq/793HPPqTnffvutumx/DtaY2LlzpzO+Zs0aNaeoqMgZt4a7VtXYymndurUzbp13WoXZF198Uc25/fbbnfFPPvlEzRkwYIAzblUbnzVrljPevn17NUerzm9VBtaqy1vjSKtwO2zYMDXntddeU5dpynlLcKoK9wnt87W6AGjXooceekjN0aqa79ixQ83xc53Uxn9kZGSF1yWiXxuio6PVHK0Kf61atdScW265pUL7VdX5HReHekykpqaqyy6++GJnvG3btmrOww8/7IwvWrSoYju2HzVr1nTGrfNUW2ZVAdfObasSuvYcZNGeXazPR+uCsHXrVjXH6vxSmQ73+wQQhPKMC77xBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAiQ3lfnKHWw2hxYLYCsNlsarfWG1UJHa23TpUsXNadDhw7OuNU+SmvRZLXk0Pb7+uuvV3OaNm3qjGttxqoSq32L1rbI+myrVavmjFvnt9aKZfPmzWqOxno/Wjsj67zX2jpZ70drSWflnHjiieoyzfr1651xq02M1k7MGkdaW6muXbuqOX7aiR3urHGh2bBhgzO+bNkyNadJkybO+K5du9Sc7du3O+PW566tz2pXZ7U0S0pKcsat46Zta9WqVWoODi6tDal1bk2cONEZ/+WXX9Sc+Ph4Z9xqJ6Zdc7dt26bmaPedvLw8NUe75lstfrR9S0hIUHPatGnjjFvXC611mzVWtWOg3UNR9fiZU2jnq/ZcJ6KPc+vct1qr+rmPaqx7lZ+Wx35o7XKt93kgLfMsfOMNAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICoav4nQVWx+7OtW7eqy7TqzlpVYxGRyMhIZ9yqWhgbG+uMW1V5tcrXVmVCrepy586d1RytCmK9evXUnLFjx6rLqrq//e1v6jLtmFvVULWq2dq6RPTP3ar6qFW5r1OnjppTu3ZtZ1yrOikiUr9+fWdcq2Iror+fiIgINScxMdEZP//889WcWrVqOePWeNUq5lo52n5rnwEOnFWNNS4uzhm3roXaddqq7qx97tZ1WutYYfFTxTYnJ6fCOQjGuHHjnPHevXurOeecc44zfsopp6g5WqeEa6+9Vs3RrqsZGRlqjvZ8Yj2jaVWfrWu+Nlascfzmm28641rXAhH9Hm+NVe058eyzz1ZztOeqLVu2qDkITmXOKawK6X62U5mVy0X0a8A//vEPNcfq/lKZrGfFg41vvAEAAAAACBATbwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACRDuxQ6RmzZrqMq2FjdXaprCw0BnPz89XczZv3uyMp6enqzlaywKrzYG239Yx0NphWS0+GjVqpC6r6qZMmaIua9CggTNutWKJj493xmNiYtScJUuWOOPaZyEiMm3aNGfc+py0ZdZ2tDYxVrs87Zy0tqOdq1abmMWLFzvj1vmtvR9rjK9fv94Z//TTT9Uc/I91bLVzcu3atWpOu3btKrydoqIiZ9xqBaO12bPO46ioKHWZ1rLOak9Wt25dZ3zdunVqjsYas5Xd3uZo8uijjzrjVhsd7ZqycOFCNWfAgAHO+L/+9S9j79ysfdPGinXea+PIOq+0a7HV3lJrdWa1iZ0xY4YzvnHjRjVn4sSJzrh2rxahbdjhwk9rsMq+Pl544YXqsuOOO84ZP/fcc9Uc7d6Sm5ur5rzzzjsV3jc/tJaCd955p5rz4IMPVuo+lOAbbwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACRFXzP/FTnduqsqlVv0xJSVFztGqeWlxEJDIy0hkvLi5Wc7RK6ImJiWqOVgndquCsVRO0KkUnJCQ443PnzlVztGPdoUMHNaeqeOGFFyq8rFatWmpO8+bNnfFrr71WzenevbszblVJnT9/vjOel5en5mjVYrXqspXNzxi3Kj77OVcvvvhidRmqjpUrV6rLtHNFu96J6GPW2o5WybZOnTpqjlVdWVufdX/R3itVyKuOjz/+2Bnv3bu3mqPdG8eMGaPmfP755854vXr11JzVq1c749Y1X7tPWBX7rYr5Gu0c1p6PRPTnKq2biIhIWlqaM37LLbdUOKdHjx5qzi+//OKMz549W83BgfFTodzqZKGxOtlo1cY7d+6s5pxyyinqsmXLljnjVqePbdu2OeNWp6TTTjtNXVaZLrjgAmf8+OOPPyjb/yO+8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQEy8AQAAAAAIEO3E/sQq8a+1vrDaiZ1//vnOeIMGDdScTZs2OePR0dFqzr59+5zxmJgYNadRo0bOuNWCTGtbtnv3bjVHa/FhvR+tVc5zzz2n5mRlZVVo+4c7q2XQjBkznHGrZVCvXr2ccWtMaK2TrPNOG0faOWyx2nhoy6zt+GnLp7W3mTJlipqDw8POnTvVZX7OVy3HaquknV/W9q1rQ926dZ3xuLg4NUejtXzCwde6dWtn3DqHN27c6IxPmzZNzTnppJOc8bZt26o52j3ETwtJ67zXtuPnPmHtm7YP2vEUEXn77bedcavN1/Lly53xNWvWqDmLFy9Wlx2ptHaH1rmiPbtY93qNn9ZgVtvehx56yBnX5hMievu7DRs2qDnac6KIfm23ntsXLVrkjDds2FDNGTZsmLpMo7UutI7PU0895Yy3bNlSzWnfvr0z/vPPPxt7t3984w0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiDQAAAABAgI7Mcs8HwKqA7afa4fz5851xq7q0Vk3QqrKpVVbXqv+JiOzatcsZ37x5c4X3Tau8K6JXuLYq765du9YZv+iii9ScJ554whm3KrQeDrSqq1ZFYe1ctapvbtu2zRn3c975qfJpVZ71s77K5Kf6bl5eXqVuR6vQeqiPzeHCTxXyPXv2qMu07hPWfcK65lU0x9qOVXk2JyfHGU9KSlJzduzYoS5D1dC0aVNn3Hqm0aoNW9W5terJ1ljZvn27M65Vo7bW5+d+5IfVmUPr4mKNIe24Wd0EtM/HqoitdczRKqQfLvxUprf4eZ7X9O7dW112zjnnOOPWs6z2DP7rr7+qOdp4iY+PV3O07kEiejcE7TwWEenQoYMzbl1PtONwxx13VHjf5s2bp+ZoHWusuYt23TpQfOMNAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAEKBA24lpJf6tdhBaewmrXYDW2qGy28f4MXr0aGe8oKBAzdFK5UdERKg5WkshreWNiP45WOX1tWNt8fP5aPvWrl07NSc/P79iO3aY0D5bP5/FsmXL1GVaO7HKbrGnvZ/KbidWmS1GrNZtGu14Wqz2OpXZKudoZB1b7VpktfqpVauWM261W6ldu7a6TJObm+uM16xZU81JSEhQl/kZs9pYSktLq/C6Kvsei99p57fWNlREv6ZYbXS0887P/dx6FtTOOWsc+3l+1Pbb2o72LGa9H20cW7TrhXVPTklJccYP93Zi1jNAZd4bb7rpJnXZNddc44zXr19fzdFa41qtr7T3Y21HY41L65hq57+1Pm2+YbU000yZMkVddtZZZ1V4ff/4xz+c8euuu07NWb16tTP+17/+tcLb/yO+8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQAdc1dyq4qhV5qvKVU27deumLjvnnHOc8ZNOOknN0Srcbt68Wc3RKmZalSy1Y21V2NU+u8jISDVHq3huVUe09kGjHYMdO3aoOWeffbYz/sUXX1R4+4cDPxWwtYr5Inq1Y+t80Mayda5qFWatc0jLsarVasfH2k5RUZEzblWQ1vahKl/njkZ+ulxYXSHmz5/vjK9Zs0bN0c4jq/K0VsnWqk6+cuVKdZm2LasS+oYNG5xxrYIyDr7KrOi9ZcsWNSc6OrpC67L2zU+3CivHT8cMrTuIdd/T7m/WPXnjxo3OuJ+q89Zzt9WJ4XDwl7/8xRnv06ePmtOiRQtn3OrQo127YmNj1Zy8vDxnfN26dWqOdl219q0yn7OtjizWuNDOPevZTrsGWM+d2vnfqVMnNWf9+vXOuPXZadXllyxZouZo9+srr7xSzSkPvvEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACNABtxPTSs77Vbt2bWfcalvSvHnzCudoracyMzPVHK3VkNVCQivxX6dOHTVHK5VvtZ3Q2m/Vq1dPzdHa0Vitk6ZMmeKMW2X8tRZtVvuR/Px8Z1xr/SEicsIJJ6jLjkR+WrFYx1wby37at1hjQmPtm9U+RaO1yrD2TXs/VaFVDg6+rl27qsuWL1/ujK9atUrN0a7h27ZtU3Pi4+Odcav9l5+2gcnJyWqOpkGDBuoy7d6Tk5Oj5mhjyU8rOPzOunZqxzU7O1vN0dqJ+eGn1ZnVzkg7f6xrvrYP1rOtn/uR1f5Po+13Ze/bwXbDDTeoy7Rnc+u80z5D65hrbbas9rfadqznX+08LigoUHO0tmV+WnlZbcus8ae107POL+0zsvZB+xyse6LWqnXr1q0VzrHOq6Ba8/GNNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABOuCq5lYl6WHDhjnjSUlJak5iYqIz7qeKo1YZUESvcLd9+3Y1R6uQaFUG1KrLatXBRUTOO+88Z3zmzJlqjlZ9T6vELiKSnp6uLtMcc8wxFdq+iMiaNWuccat6pFZp0KoemZaWpi7D/qWmpjrjVqVIbexZ1bm1Sq3WODpYtH2zqulr+304VJc9EvmpjN2oUSNnvHXr1mqOVtVcu4eJiNStW9cZX7p0qZoTExPjjDdp0kTNse59WpV0P3bs2KEuu+iii5zxp59+Ws2herl/fjoiaNcu65qvVSG2tq99rtY1X3tG89OVws+x0bZv7YP1frRnGmusWtWgKzPnYHvjjTfUZT/99JMz3rlzZzWnbdu2zrj1TKg9s9aqVUvN0aqKW/MT7Vyx5kHaMj+dX7SORyL+OgRYtPuBVcFdm1dZ4097T346P1n7ps2fvvrqKzXnzjvvVJeV4BtvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgACVu52YVqr+3//+t5qTnJzsjFul97VlVuspjVVGX9uO1v7LkpCQoC7T2hk8+uijao62D9dee62as379emfcKq//zTffOONamxwRkebNmzvjderUUXO0dgFaWxIRf22dNm3apC47EvlpkWKx2jdotDFmjXGt5YrVikVbZh0DLcdqyaGdk1ZbPm0frPO7outC+flpSdW3b19n/Ndff1VztLY927ZtU3O0Fo7r1q1Tc1q2bOmMW+9z7dq16rJ27do549nZ2WqOdn232k5p7QkzMjLUHKutGqoG7by3zkftWmy1LPLTXtLP9dNPCzLtmcZ6P1o7Meucz8rKqtD2RapGW879sfZx/vz5zvj06dMrvJ3IyEh1mdaO0bo+adfvlJQUNUcbL9Yx8NMSMzc31xm3Wj5u3rxZXaa1ubPa32nLrHlVZc7t/Jz72nET0VuNHehzGt94AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABCgclc1v/TSS51xrWq3iMiyZcuc8djYWDVHW1a7dm1j79ysqsJaJfI1a9aoOVrl8Jo1a6o5WqXY1157Tc0588wznfEvvvhCzdGqLVrHun379s54z5491Ryt2qJVZVOrLGlVnddY1bK1z7tRo0YV3s7RSKvcrXU0ENEroVs5WmVOq1Kktj7rvNPWV726ftnTcvxU3kxMTKxwDg4NrdL33Llz1RztnLSua1aV3Ypux2JVv9WWWR0wtGuoVcFdW6bdq0Soan4gtm/f7ozHxMSoOVYVbo1WndvPtdhPBwI/nSysasfa+LK2o3VX8VOpevXq1WpOhw4dnHGry4af68XBZlXG1s5XrUuSiL9q1lu2bHHGv/vuOzVHq1BuddvRWJ+Tdu5Z41XbN2s71r1Ke07StiOizzeSkpLUnPj4eGfcmr9px9t6ttPmadp109rOqlWr1Jzy4BtvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgACVu51YTk6OM26134qLi3PGrVYI2vqstlhaSXytTL2I3krAKhOv7cPOnTvVHK1Fi9aGSUTkk08+ccbnzZun5mgtWqw2bFr7D6vVg1Ze33o/WssQq12AlmO1jdDOg8zMTDUH/+OntYvG+pysNi0arY2GnzYiftrRWDnaua+13bH4OTYoH6uN1YYNG5xxq3XKjh07nHGrpUllnit+rrki/lqaae306tevr+asW7fOGbday8Bmtf/x04LIagen0e7bfloqWdc77b1aLUX93A+08Wptx09LTG07K1euVHO0Y+2nrerhoqCgoEJxv7RrrnX8tONuzU+0662fz8lqDaaNc+s+4XdbGq01l9aKWUQfs9Z9VDt21nvV1mflaPc96/2UB994AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABCgclc11yqUWlUc165d64zHxMSoOXXr1nXGrUrbubm5zvimTZvUHK3CnVXxVaukZ1W+1Sq7W5VGtffTqlUrNUer+GhVnd+6daszbh0Dbd+siqZa1UArR6s42aBBAzUnPz/fGc/KylJz8D/WOVlRlV2d+2BVNde246eqec2aNSu2YwhU48aN1WValWKrsqpWddm6H2hVca3taGrVqqUu81Pd1dqHFStWOOPNmzdXc7Kzs53xhIQENUfrwqF1ITnaWNchbZn1uWrPdRat2rG1b346ZmjXduuary2ztq+NSauqs/ZerWrj2rPg4sWL1Rzts7Pej5974tFI60ZkdSnSaM/SgAvfeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEqNw9TGbPnu2Mf/zxx2rO5Zdf7oyvX79ezVm+fLkzvmvXLjUnNjbWGdfaf4no7aq0FjEienuJoqIiNUdrL2G13igsLHTGN2zYoOb4aW+htarwc6yLi4vVHK0VnNUiTms1ZrXJadKkiTOutbU53FV2yy6N1VbFD22//bRB8bNvfo6b1WrNTzsaHHzW56F9vtq1WERvF2fdd7TrpNUeSDtftWuxiH2d1O5Xqampas7MmTOd8W7duqk52v3Kam+ltUijndj+aeeJde3y007MT8tFbUxY+6aN18psTSbi79nJz71Ka6O3YMECNUc7PtZxo50YULXxjTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAASp3VXPNI488oi7TKqHffvvtak56eroznpubq+Zo1bELCgrUHK1iplXVXKvGalXL1SpM+qkAalXL1fbbyvFT/VLLsSqHa9V3a9eureZolUsbNGig5sydO9cZf/PNN9WcN954Q11W1fmp1GrRKi5r1Zv90j5baxxpVZor+xj4UZlVzQ/WPh+N6tatqy7Trp+bNm1Sc9q2beuMR0VFqTnbtm2r0PZF9HM/Li5OzbHWp3WtaNeunZrz1VdfOeNWZwptH7TK5SJ2xXPY/FQ1X716dYW3o1XFt8bK9u3bnXGr+r7GT7VxP1XArXtLZGSkM26N/ZiYGGfcqiyv7YNV2Z0xBFRtfOMNAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAEKBy9x3Q2jFYbQ3GjBlTobiISM+ePZ1xq21ZWlqaM56QkKDmaO/HagGktWmw2ltocnJy1GVaWxCr7YTW4mPHjh1qTmW2O9q9e7eaU1hY6IxbLT4mTJjgjC9cuFDNmTJliroM/lmfk3buW61YtPVZ2/Fz/fHTLs9PSx6Nn/GF4FjtxLTPd/PmzWqOdn+x2vls2LDBGbfaf23dutUZt9pl+jlfLdp9RNs3EX1sWvudnJzsjP/222/G3h09rGuan+ud1t7OorXS0uIi+vOB1VJUu7dYLcgqs0WqNYa046a1DBMRSUlJcca19n4i+nXBusZY1xIAhx7feAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQoHJXNbeqB1emiRMnOuMnnHBChdfVsmVLdZlW4TYvL0/NadiwoTO+cuVKNUer5rls2TI1BygPrQK3X+vXr3fGMzMz1Rytwqx1vdCW1ahRo8I51na042N1IbCqxVZ0O5XZNQAHLjY2Vl2mdV6oVatWhbcTFRWlLisuLnbGrfMuKSnJGd+0aZOaY1VX1tZnVX1v1qyZM26NPz+dCOLi4tRlsK8p2rllVQH3U/3+o48+csbj4+PVHK2Li3XeW/ut0dbnpxq8dZ5q+5afn6/mzJw5U11W0e1U9mcK4OBhhAIAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEqOK9cw4jixYtqtT1zZ8/v1LXB1QliYmJzrjVmkhr32K1JtLanVhtUKxWYxVltRPT2vWsWbNGzalZs6YzrrVgsljH4GC1dDxSNW/eXF22YsUKZ9xqDaaxPkPtXNm1a5eaM2XKFGf8oosuUnOsNk3ffPONM27tt7ZMu2aIiBQUFDjj2rEW0duJ4nfR0dHqMq0tlvW5Wp+f5pFHHqlwDvzR2ktW9mcK4ODhG28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAhTmaWUT//xCpWImcDgr5+nvdKjHhLV9P+/riSeecMYjIyPVnLy8PGfcTxVyq1Lrjh07nHHrfWrHZ8+ePWqOVjm8uLhYzalVq5YzPmPGDDXnyy+/VJcdaofzmLBYlb61c8JPlXmrmv2qVauc8YYNG6o5K1euVJfh4PE7Lg7WmPi///s/Z1yrpC8i8tVXXznj1vXJz/s5kGvK0eyhhx5yxps2barmvP766874mDFjKmWfShyp9wngQJRnXPCNNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAyt1ODAAAAAAAVBzfeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAWLiXYnS09PlsssuC/383XffSVhYmHz33XeHbJ8AAIefsLAwueGGG/b7uldffVXCwsJk5cqVwe8UUEWVjIOZM2ce6l0BqhzXfSI9PV1OP/30Q7dTRykm3uU0b948GTRokKSlpUlUVJSkpqZKnz595JlnnjnUuwZUKSUX+JL/oqKiJDMzU2644QbJzs4OZJtTpkyR++67T/Ly8gJZP1CZDuX95OGHH5ZPP/008O0Af3Y4TY4ZJ/Bjf+d4jx49pG3btgd5r1CVMPEuhylTpkiHDh1kzpw5cuWVV8qzzz4rQ4cOlfDwcBkxYoSa161bN9m5c6d069btIO4tUDU88MAD8sYbb8izzz4rnTt3lhdeeEFOPPFEKSwsrPRtTZkyRe6//34m3qjy/N5PNJdccons3LlT0tLSyvV6JhTA/jFOAASh+qHegcPBQw89JAkJCfLTTz9JYmJiqWU5OTlqXnh4uERFRQW8dwemoKBAYmJiDvVu4AjUr18/6dChg4iIDB06VOrUqSNPPfWUfPbZZ3LhhRce4r0DDg2/9xNNtWrVpFq1auZrPM+TXbt2SXR0dIXXDwAAKgffeJfDsmXLpE2bNmUekkRE6tWrp+a5/sa75NdMfv75Z+ncubNER0dLkyZN5MUXX3Tmvvfee/L3v/9dGjRoIDExMTJw4EBZs2ZNmW1Nnz5dTj31VElISJCaNWtK9+7d5ccffyz1mvvuu0/CwsLk119/lYsuukhq1aolXbp0qdjBAHzq1auXiIisWLFCnnzySencubPUqVNHoqOjpX379vLhhx+WySn5O9dPP/1U2rZtK5GRkdKmTRsZO3Zs6DX33Xef3HHHHSIi0qRJk9CvuJf8LdOECROkS5cukpiYKLGxsdKiRQv5+9//HvwbBhwqej+xzn0R+2/3xo0bJx06dJDo6GgZOXKkhIWFSUFBgbz22muhcfLHuiTAwTR37ly57LLLpGnTphIVFSUNGjSQyy+/XDZv3lzmtevWrZMrrrhCUlJSJDIyUpo0aSLXXnutFBcXq+vfunWrdOrUSRo2bCi//fabiIgUFRXJvffeKxkZGRIZGSmNGjWSO++8U4qKikJ5jBMcLKNGjZJevXpJvXr1JDIyUlq3bi0vvPBCmdeVXNN/+OEH6dSpk0RFRUnTpk3l9ddfL/PaBQsWSK9evSQ6OloaNmwoDz74oOzbt0/dh/Hjx0tWVpZERUVJ69at5eOPPy61fMuWLXL77bfLMcccI7GxsRIfHy/9+vWTOXPmlFnXqlWrZODAgRITEyP16tWTW2+9VcaNG0e9qz/gG+9ySEtLk6lTp8r8+fMr5W8ztm7dKqeddpqcd955cuGFF8r7778v1157rURERMjll19e6rUPPfSQhIWFyd/+9jfJycmRp59+Wk4++WSZPXt26NuLb7/9Vvr16yft27eXe++9V8LDw0ODefLkydKpU6dS6zz33HOlefPm8vDDD4vneQf8foDyWLZsmYiI1KlTRx588EEZOHCgXHzxxVJcXCzvvvuunHvuufLll19K//79S+X98MMP8vHHH8t1110ncXFx8u9//1vOOeccWb16tdSpU0fOPvtsWbx4sbzzzjsyfPhwqVu3roiIJCUlyYIFC+T000+Xdu3ayQMPPCCRkZGydOnSMv8oBRwsFbmf7O/ct/z2229y4YUXytVXXy1XXnmltGjRQt544w0ZOnSodOrUSa666ioREWnWrFmlvTegIiZMmCDLly+XIUOGSIMGDWTBggXy0ksvyYIFC2TatGkSFhYmIiLr16+XTp06SV5enlx11VXSsmVLWbdunXz44YdSWFgoERERZdadm5srffr0kS1btsj3338vzZo1k3379snAgQPlhx9+kKuuukpatWol8+bNk+HDh8vixYtDv1rOOMGBys/Pl9zc3DLx3bt3l/r5hRdekDZt2sjAgQOlevXq8sUXX8h1110n+/btk+uvv77Ua5cuXSqDBg2SK664QgYPHiyvvPKKXHbZZdK+fXtp06aNiIhs3LhRevbsKXv27JG77rpLYmJi5KWXXlJ/22nJkiVy/vnnyzXXXCODBw+WUaNGybnnnitjx46VPn36iIjI8uXL5dNPP5Vzzz1XmjRpItnZ2TJy5Ejp3r27/Prrr5KSkiIiv/8Gba9evWTDhg1y8803S4MGDeTtt9+WiRMnHvDxPKJ42K/x48d71apV86pVq+adeOKJ3p133umNGzfOKy4uLvW6tLQ0b/DgwaGfJ06c6ImIN3HixFCse/funoh4//d//xeKFRUVeVlZWV69evVC6yzJTU1N9bZt2xZ67fvvv++JiDdixAjP8zxv3759XvPmzb2+fft6+/btC72usLDQa9KkidenT59Q7N577/VExLvwwgsr5bgALqNGjfJExPv666+9TZs2eWvWrPHeffddr06dOl50dLS3du1ar7CwsFROcXGx17ZtW69Xr16l4iLiRUREeEuXLg3F5syZ44mI98wzz4RiTzzxhCci3ooVK0rlDx8+3BMRb9OmTZX/RgEfyns/Ke+5XzLe/njup6WleSLijR07tsz2Y2JiSt2ngIOl5Fz96aefPM/zytwHPM/z3nnnHU9EvEmTJoVil156qRceHh7K+6OS554/rnvDhg1emzZtvKZNm3orV64MvfaNN97wwsPDvcmTJ5dax4svvuiJiPfjjz+GYowT+FFyHlr/tWnTJvR61xjo27ev17Rp01Kxkmv6H8dFTk6OFxkZ6d12222h2C233OKJiDd9+vRSr0tISFDvEx999FEolp+f7yUnJ3vHHXdcKLZr1y5v7969pfZnxYoVXmRkpPfAAw+EYv/3f//niYj36aefhmI7d+70WrZsWWYudDTjV83LoU+fPjJ16lQZOHCgzJkzRx5//HHp27evpKamyueff17h9VWvXl2uvvrq0M8RERFy9dVXS05Ojvz888+lXnvppZdKXFxc6OdBgwZJcnKyjB49WkREZs+eLUuWLJGLLrpINm/eLLm5uZKbmysFBQXSu3dvmTRpUplfMbnmmmsqvM9ARZ188smSlJQkjRo1kgsuuEBiY2Plk08+kdTU1FL/+rp161bJz8+Xrl27yqxZs5zr+eO3De3atZP4+HhZvnz5fveh5Nd5P/vsM/NXrYCDpSL3kwM595s0aSJ9+/at9P0HKssf7wO7du2S3NxcOeGEE0REQveCffv2yaeffioDBgwI1Qz5o5JvxUusXbtWunfvLrt375ZJkyaVKjr4wQcfSKtWraRly5ahZ6Xc3NzQn0HxzRwqy3PPPScTJkwo81+7du1Kve6PY6DkW/Lu3bvL8uXLJT8/v9RrW7duLV27dg39nJSUJC1atCh1Pxg9erSccMIJpX7TNSkpSS6++GLnfqakpMhZZ50V+jk+Pl4uvfRS+eWXX2Tjxo0iIhIZGSnh4b9PF/fu3SubN28O/dneH5/Zxo4dK6mpqTJw4MBQLCoqSq688sr9H7CjCL9qXk4dO3aUjz/+WIqLi2XOnDnyySefyPDhw2XQoEEye/Zsad26dbnXlZKSUqagWWZmpoiIrFy5MnTjERFp3rx5qdeFhYVJRkZG6O/5lixZIiIigwcPVreXn58vtWrVCv3cpEmTcu8r4Ndzzz0nmZmZUr16dalfv760aNEidPH+8ssv5cEHH5TZs2eX+du6P2vcuHGZWK1atWTr1q373Yfzzz9fXn75ZRk6dKjcdddd0rt3bzn77LNl0KBBoX0BDrby3k8O5NznOo+qbsuWLXL//ffLu+++W6awYMmkY9OmTbJt27Zy/5nfJZdcItWrV5eFCxdKgwYNSi1bsmSJLFy4UJKSkpy5foobAi6dOnVy/kNRrVq1Sv0K+o8//ij33nuvTJ06tUzHl/z8fElISAj9XJ77wapVq+T4448v87oWLVo49zMjI6PMc9cf5yMNGjSQffv2yYgRI+T555+XFStWyN69e0Ov/eOfPK1atUqaNWtWZn0ZGRnObR+tmHhXUEREhHTs2FE6duwomZmZMmTIEPnggw/k3nvvPST7U/It3hNPPCFZWVnO18TGxpb6mcq2OBi0G8/kyZNl4MCB0q1bN3n++eclOTlZatSoIaNGjZK33367zOu1is1eOeoTREdHy6RJk2TixIny1VdfydixY+W9996TXr16yfjx4/dbDRoI0v7uJwd67gNV2XnnnSdTpkyRO+64Q7KysiQ2Nlb27dsnp556qu/fUDr77LPl9ddflxEjRsgjjzxSatm+ffvkmGOOkaeeesqZ26hRI1/bBPxYtmyZ9O7dW1q2bClPPfWUNGrUSCIiImT06NEyfPjwMmPgQO4HB+Lhhx+Wf/7zn3L55ZfLsGHDpHbt2hIeHi633HILv0noAxPvA1AyqdiwYUOF8tavX1+mjdfixYtF5PfKhX9U8o12Cc/zZOnSpaFfVyn5NcT4+Hg5+eSTK7QfwKHw0UcfSVRUlIwbN04iIyND8VGjRvlep+ub8hLh4eHSu3dv6d27tzz11FPy8MMPyz333CMTJ05kzKDK8Hs/qShrrAAHy9atW+Wbb76R+++/X/71r3+F4n9+5klKSpL4+HiZP39+udZ74403SkZGhvzrX/+ShIQEueuuu0LLmjVrJnPmzJHevXvvdxwwThC0L774QoqKiuTzzz8v9W32gfzJQ1paWpkxJCKhqv5/tnTpUvE8r9T5/uf5yIcffig9e/aU//73v6Vy8/LyQsVsS7b966+/llnf0qVLfb+fIxG/a1kOEydOdP6LUsnfWWu/wqHZs2ePjBw5MvRzcXGxjBw5UpKSkqR9+/alXvv666/L9u3bQz9/+OGHsmHDBunXr5+IiLRv316aNWsmTz75pOzYsaPMtjZt2lShfQOCVq1aNQkLCyv160orV64MVZT1o+QfsfLy8krFt2zZUua1Jb8Z8sdfcQcOlsq+n1RUTExMmXECHGwl3979eSw8/fTTpX4ODw+XM888U7744guZOXNmmfW4xtI///lPuf322+Xuu+8u1ZrpvPPOk3Xr1sl//vOfMjk7d+6UgoKC0M+MEwTNNQby8/MP6EuI0047TaZNmyYzZswIxTZt2iRvvfWW8/Xr16+XTz75JPTztm3b5PXXX5esrKzQn2pUq1atzDj74IMPZN26daViffv2lXXr1pWqVbJr1y7neDua8Y13Odx4441SWFgoZ511lrRs2VKKi4tlypQp8t5770l6eroMGTKkQutLSUmRxx57TFauXCmZmZny3nvvyezZs+Wll16SGjVqlHpt7dq1pUuXLjJkyBDJzs6Wp59+WjIyMkLFCsLDw+Xll1+Wfv36SZs2bWTIkCGSmpoq69atk4kTJ0p8fLx88cUXlXYsgAPVv39/eeqpp+TUU0+Viy66SHJycuS5556TjIwMmTt3rq91lvyD1T333CMXXHCB1KhRQwYMGCAPPPCATJo0Sfr37y9paWmSk5Mjzz//vDRs2JAe9jgkKvt+UlHt27eXr7/+Wp566ilJSUmRJk2aOP8mEAhSfHy8dOvWTR5//HHZvXu3pKamyvjx42XFihVlXvvwww/L+PHjpXv37qE2YBs2bJAPPvhAfvjhh1ARzT964oknJD8/X66//nqJi4uTv/71r3LJJZfI+++/L9dcc41MnDhRTjrpJNm7d68sWrRI3n///VDfexHGCYJ3yimnSEREhAwYMECuvvpq2bFjh/znP/+RevXq+f7NpzvvvFPeeOMNOfXUU+Xmm28OtRNLS0tzPl9lZmbKFVdcIT/99JPUr19fXnnlFcnOzi41+T/99NPlgQcekCFDhkjnzp1l3rx58tZbb0nTpk1Lrevqq6+WZ599Vi688EK5+eabJTk5Wd566y2JiooSEX6LJOTQFFM/vIwZM8a7/PLLvZYtW3qxsbFeRESEl5GR4d14441ednZ26HXlbSfWpk0bb+bMmd6JJ57oRUVFeWlpad6zzz5bapslue+884539913e/Xq1fOio6O9/v37e6tWrSqzj7/88ot39tlne3Xq1PEiIyO9tLQ077zzzvO++eab0GtK2onRWglB+nPLGJf//ve/XvPmzb3IyEivZcuW3qhRo0Ln5x+JiHf99deXyf/zWPM8zxs2bJiXmprqhYeHh9pmfPPNN94ZZ5zhpaSkeBEREV5KSop34YUXeosXL66U9wpUVHnvJ+U997V2Yv3793duf9GiRV63bt286OhoT0RomYSD5pVXXvFExJs1a5bneZ63du1a76yzzvISExO9hIQE79xzz/XWr1/viYh37733lspdtWqVd+mll3pJSUleZGSk17RpU+/666/3ioqKPM9z33f27t3rXXjhhV716tVDLY6Ki4u9xx57zGvTpo0XGRnp1apVy2vfvr13//33e/n5+aFcxgn82N/zT8kcoMTnn3/utWvXzouKivLS09O9xx57LDROynNN7969u9e9e/dSsblz53rdu3f3oqKivNTUVG/YsGHef//7X3Wd48aN89q1axd6Hvvggw9KrW/Xrl3ebbfd5iUnJ3vR0dHeSSed5E2dOtW57eXLl3v9+/f3oqOjvaSkJO+2227zPvroI09EvGnTppXvIB7hwjwv4L/KRyk9evSQ3Nzc/f690nfffSc9e/aUDz74QAYNGnSQ9g4AAKDy/fvf/5abb75Zli5dWqpNHoAj19NPPy233nqrrF27VlJTUw/17hxy/I03AAAAAvXTTz9JTExMqd7aAI4cO3fuLPXzrl27ZOTIkdK8eXMm3f8//sYbAAAAgfjoo4/ku+++k7feekuGDh0q1avz6Akcic4++2xp3LixZGVlSX5+vrz55puyaNEitbjb0YirHwAAAAJx++23y/bt2+WKK66Q4cOHH+rdARCQvn37yssvvyxvvfWW7N27V1q3bi3vvvuunH/++Yd616oM/sYbAAAAAIAA8TfeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAyl1cLSwsLMj9AA6JAylxcLSMiQ4dOqjLBg8e7Ixv3rxZzdm+fbszvmfPHjWnbt26zrj1+a1evdoZP/bYY9Wc+vXrO+NJSUlqTs+ePdVlh6OqNCbCw93/Nrxv375KzdFERESoyxo3buyMt2nTRs2ZPn26M75x48aK7VgArBZPrVu3dsbHjh2r5lRm+RjtMxXx97n64ff9HI73ico+3rGxsc64NVa0c27evHlqzq5du5zxlJQUNSc7O9sZnzNnjpqjsT7rI62cUlW6TwBVRXnGBd94AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABCgclc1B3B0sqp2t23b1hm3Kt82adLEGY+Li1NztKrmW7ZsUXPy8/Od8by8PDVHq8aenp6u5iA4WoXQyq66PHLkSGc8MjJSzSkqKnLGtcr4IiI33XSTM25VQtUqq//yyy9qTnR0tLps9+7dzrhVYVrrRHDqqaeqOYmJic74559/ruZ89NFHzvjBqmKP3/k5di1atFCXadf2zMxMNUfrPrFt2zY1R7sfaOeiiEhUVJQzblXenj17tjN+pFUuB1D5+MYbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgABR1RwAUCVplYX9VF1+5JFH1GW1atVyxtevX6/maNXG16xZo+YkJCQ448nJyWrOO++844y/+OKLas7UqVPVZdnZ2c649V5zc3Od8erV9UeIwsJCZ/y8885Tcxo3buyMDx8+XM2xqk+j8jVr1swZb9iwoZqzatUqZ9w677WOAtr5KyKycuVKZ9y6XmidLKxK6B06dHDGZ86cqeYAgAgT78BpDwV+2uH4aVXh56HkYLXE6Ny5s7psypQpzrjVsmTx4sXOOC0+DkxMTIy6bPny5c54nTp11Jy1a9c6437OVa0VjLU+q52Y1o5Gm2SJ6K3GtIdAAAAAHH34VXMAAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAkRV8yqoMqtwH6yK3j169FCXHXPMMc548+bN1ZyHH37YGbcqX59yyinOeFFRkZqD/cvMzFSXJSUlOeOxsbFqjlYlvWbNmmrOpk2bnPFq1aqpOTVq1HDG4+Pj1Ryt24C2LhGRbt26OeNUNT9w2udhtQdq2rSpM962bVs1Z/Xq1c641tJIRL+2Wvu2bt26Cm8nLS3NGT/33HPVHK2Vl4g+lrZv367maOPMeq979+51xq22ZdpnZI1zbTt+crB/WputjRs3qjnaPdhqvXfJJZc442eddZaa89VXXznjX3/9tZqzcOFCZ9xqW6aNyejoaDVn586d6rKjjfUcd6R1odHeq/U+/eT4uUZX9j4crJzDHd94AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgqpoDAKqkPXv2VDind+/ezrhV3VWrtL9r1y41p3r1it8+tWr/GzZsUHPq1q3rjA8YMEDN+eWXX9RlcXFxzrhVkVk7drt371ZztIr0VkXjiIgIZ7xr165qznfffVfh7eB32mekdQYQ0c/hrKwsNUerXm5VuG/WrJkzbp1z2vmTmpqq5nTu3NkZb9y4cYX3be3atWrOO++8U+GcI5WfitVWVwrtPmF1V5k5c2aF98EPP+/VT05ld2o4WPt9JFcv1zDx/pPKbnOg5VT2ILn00kud8WnTpqk52sPMTTfdpOZoN8p27dqpOUuWLHHGZ82apebccsstzvjs2bPVHARDe/AX0R/itYmMiEhCQoIzvmXLFjVHa5WhPTjubx80WlsnqzVRrVq1KrwdAAAAHF34VXMAAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAkRV8yqoZcuWzrjVvqZHjx7OeIcOHdQcrRrzq6++quZMmjTJGbcqlLdv394Z79ixo5pTXFzsjGdkZKg5S5cuVZfBP60KuYjeBsmq2t+mTRtn3KoObrV10lgVzzWFhYXOuNXtoHXr1hXeDoKjfR7WZ6hVwNeuQ9b6rO4XWluuGjVqqDlFRUXOeEFBgZqjtVWy1mftgzaerXGpXTeioqLUHO3YWa2EtHZiflrRHW20tmGNGjVSc3bu3OmMW/dfrevJjBkz1Jzs7GxnPD09Xc3p1q2bM/7TTz+pOZ06dXLGtRZoIiLffvutM27d90466SRn/LffflNzjtQuLjVr1lSXnXfeec74wIED1Zy5c+c641YLSa2rj/W5JyYmOuNadxcRfVxY3WJyc3PVZRpt37TrvYh9fLROLtZ+5+XlVWhdIvb+abT7hHUP05ZpnWxE9Pc6atQoY+/2j2+8AQAAAAAIEBNvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQVc0BAEeMZs2aOeNWlWut4ml0dLSao1X03r17t5qjVT22Kq5rFWGt7VhVzbV9sI6PtsyqCKtVzLWOqXYckpKS1Bz4p1VCzsnJqXCOVc1//Pjxzvi2bdvUnAEDBjjj48aNU3O0ThbffPONmqONB6sSc506dZxxq9OAdo1JTk5Wc7SK2Dt27FBzDgfaZysikpWV5Yz/4x//UHO0CuWnnnqqmqNdv61K8k2aNHHGrWvxCSec4IxblcsbNGjgjGvnnYjebWDTpk1qTosWLdRlW7ZsqfD6tO4F2r6J6JXQrWrnWvcC6/hon+vChQvVnNjYWGe8efPmak55MPH+E+vm4YfWNqFz585qzsaNG51x6yb13//+1xm/9dZb1Zz169c748OHD1dz6tWr54xbx01rl6G1GRMR6dOnjzNuta+hndiB0R6irVYZ8+fPd8atG5GWoz3QiYg0bNjQGdfaQIno40VrGSai3wytVmfWgxMAAAAgwq+aAwAAAAAQKCbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgqpr/idVCQmuPYlX01srRW9W527Zt64z36NFDzbn66qudcaudgtWWQ2O1GdFoldC1dgUiIqmpqc745Zdfrub8+OOPzrhWRRul1a5d2xm3WpdoVcDr1q2r5mjV060K5X5aE02ZMqVC6xLR2yZZ49VqBYVgaK15RPTz1arOr1Xh165DIiJr1qxxxq1zRWt3ZN13NFYrL4vWaswaF35o+6ddZ0T0Y9q0adNK2aejkXWN1M4Fq7Wc1jJL6+AioreDi4qKUnNWrVrljFtjf/r06c641sFFRKR169bOuHUMtHFs3QuqV3c/bmvrEtG7eSxatEjNORysW7dOXaYd9w4dOqg5HTt2dMbz8/PVHG1Z9+7d1Zzvv//eGU9JSVFzLrnkEmd87Nixak56erozbl2j3333XWdce/4WsZ+5tNZc1vWkVatWzvjUqVPVnM2bNzvjmZmZao7WZcbqpqN1ubGOT5cuXZzxUaNGqTnlwTfeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgJt4AAAAAAASIquYAgMNKcnKyukyrruyn+4RVgfu3335zxq0qxX6qmmuVbK0c6736qcKv7UNRUZGa85e//MUZ16pii+gVqxMTE/Wdg8nqMKGdC1Zlfq0SudWlRKtwb1VI1j7zoUOHqjnaPtSvX1/N0Y6BdW5rFcqtSujataS4uFjN0fb7cK9q3rJlS3WZVsm9cePGao7WuaZZs2ZqjlY5vF27dmrOxIkTnXHrfrRs2TJn3BqX2jVSq/Rvsc4vrYuEiF6hXPt8ROzOBprs7GxnfMCAARXOsToYZWRkOONWtfz4+Hhn3LpulQcT7z+xyvVbDzOanTt3OuPWw1mvXr2c8TfffFPNueaaayq2YweR1pZAO6lFRGbOnOmMWzdD7eaubR+laS0arGOujRetTY21Pmsi0aZNG2fcakui3ahXrlyp5mgPnForChG7hQUAAAAgwq+aAwAAAAAQKCbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgqpr/iZ/K5Zbt27c745MmTVJzrGUarby91RbEz3vVWm9Y69JaLVjtR7TjNmbMGDUnJSXFGU9LS1Nz8D9am5jCwsIKr0trCyQiEhcX54zn5uaqOdr5lZeXp+Zo5751PmzevNkZt9rEWO8VwdBaVYnon4fVRku7flqV9rVzwjoftC4Ald1Nw6Ktz9oH7djt3btXzdGOT0JCgpqzceNGZ1wblyJ6WyCre8HRROv2IaKf91p7PRH9mhsTE6PmaOeJ9Xyi3XcGDhyo5nz//ffOuHUuaG3LtJZhIvp1wWqnpD0HzZ49W81p0KCBuuxwZo3npKQkZ1y7NojobcOs7kHadrRWVSIiTZs2dcbPOOMMNefnn392xq22XHPnznXGtY5HIiJNmjRxxq0WWx07dlSXTZkyxRnv3r27mqNdG6z7tXZtsD477ZqvfaYi+rXOeobU9uFAn/n4xhsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAAFHVHABwWKlfv766TKvAXVRUpOZo1YO3bdum5miVTXfv3q3maNWQrYrrWmVVq9q5VW1cy7P2W9s/q7qrdry1ysAiIosXL67Q9kVEsrKynHGqmv9Oq9otIrJjxw5nXOs8YeVY40vrmGHRqhB/8803as6aNWsqvH2tsrqVU1xc7IxbFeS1Ku1+jps1Hiq7C0IQrKr5K1ascMZ/+OEHNefUU091xrVzSERk0aJFzrh1zdfuEyNGjFBzevbs6YxbFbh79+7tjFvHQFuWmpqq5owePVpd1q5dO2e8VatWas67777rjI8dO1bN0SqUa5XdRUROOOEEZ7x27dpqjubXX39Vl2nniFX5vjyYeB8iVpsara2LVV5fY+VYD2eVSbvAaDdwEf3GYh037WJutYLC/2jn3c6dOyu8Luu8y8/Pd8atC7pm69at6jLt/FqyZIma07hxY2fceqDSWt8BAAAAJfhVcwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACRFXzQ8RPRXErR6s8bVUB11R2q4qYmBhnfPDgwWrOl19+6Yy//fbbao5WxVpr44HStErkWrVzi5WjVQi3Wtholi1bpi479thjnXGtZZGISEFBgTOekJCg5hys7gD4n2bNmqnLtBZXWtsgEZE6deo449a5op3jVostjdUFQLvmWtd26xquscasti2rM4WWY+239l6t49OiRQt12dGkZs2azrh1XdVayFkt37T7aV5enprj57lBG0dWFwntPLHOOW1Z9er647E2Vqz2VXXr1nXGrWOjfaba9UpEJDc3V11WVVjtILds2eKMa20DRUTi4+OdcatFopZj7Zv2TGG1uNO66ljXrdtuu80Zt55l//rXvzrjDRs2VHNGjRqlLvv++++dca09mojIb7/95oxb42LQoEHOuNUGUetMY3Wf0dqqWfumtRrz86z6R3zjDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAqGoOADisJCcnq8uioqKccavqslY92KqErlU99lPB2ararbEql2uVdP0qKipyxiMiItScrVu3OuNW1XftOGidMUTsc+Foop13VrV67bhqFZ9F9HPBD6tyuPZ+rCrEWncXS2xsrDNujS+tWnZmZqaao1VVtsaDVsXaqrx9OFQ1//nnn9VlZ555pjO+dOlSNWfDhg3OePfu3dWcpKQkZ3zEiBFqjnbc77zzTjVHGy933HGHmpOdne2M33zzzWqOVunequx+4oknqss+//xzZ/yZZ55Rc3r06OGMN2jQQM2ZM2eOM65VSBcROf30053xxo0bqznz5893xq3xp1Wxnzp1qppTHkf0xLuy22IdjqxWR35ajflpnaTdCH755Rc1p0OHDs74yJEj1RytxdCUKVOMvUMJ7QHNeojXHgysByCtrYqftm9Wu6fOnTs749ZkSrvhpaSkqDl+xhEAAACOLvyqOQAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABOqKrmh8tlcv98lOhXJOVlaUu09oFvPvuu2qO1i6gb9++ao7W2mbNmjVqDvbPGkdaOxircrjWvsFq96RZsGBBhXO0quoieieETZs2qTlcZw4+rXWKiN0eRKNV7vfTnshqDaYtq+x2YtYx0LoXWGNWu7Za5/6OHTvUZRptv632VlbHgaOJduwKCgoqnGOdC5s3b3bGrTGpnSdWOzHt/LbOK228WuNBa7dk7ZvGanundXex7ntaa0SrpdrhwDon+/Xr54xb9/p33nnHGbfOydq1azvj1vPiRRdd5Ixb1yetxdX06dPVnGXLljnjb7zxhppz9tlnO+PWvWXWrFnqsqZNmzrjkZGRak6tWrWccaulofYZWV2PtM9O276IyJgxY5zxyy67TM3Rxpl17y0PvvEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBHdFVzAMCRx6rqq1Uc1SoEi+iV7q3qu9WqVVOXVZRV9VWrSmtt36pKrbHWp+2fVS26sLDQGS8uLlZztM9Iq6ou4q8i/JGoZs2azrhVnVurNm5Vg9aqGlsV7rUxqXUTENHPR+vz1qodW+O4qKjIGdeOp7Vv1vupX7++M96gQQM1R6sgb13LDgctWrRQl2mVtq0uPK1bt3bGJ0+erOZo4+Kkk05Sc+bOneuMb9u2Tc1p1aqVM7569Wo15+KLL3bGreP25ZdfOuNWpf0uXbqoy7Rq/7Nnz1ZztK4CVlcY7T7Rv39/NWfx4sXO+NNPP63mZGZmOuPW9VG77zVq1EjNKQ8m3kc462HKTzuxv/3tb864dsMTEXnhhRec8UsuuUTN0W44o0ePVnPS0tKccetBD/+jPdBYD73aA4B1zLWLmZ/2QzNnzlSX+ZmwaPtmtdDQbhwAAABACf6pGAAAAACAADHxBgAAAAAgQEy8AQAAAAAIEBNvAAAAAAACxMQbAAAAAIAAUdX8CGdVLk9PT3fG77vvPjVHqwhttQsYNGiQM75kyRI1Ryvxn5KSouZo7Q9QPloVcK0VjIj+OdWqVUvN0db366+/GnvnlpeXV+Ecq+2NnxZR1vpwYKxq8hqt0n5SUpKao7VIsc4vrT2Q1p5IRK+ab5132ri0rndWixSN1grGWp/1+WRnZzvjVmsnra2bdQ3S7nFWq7Mj8V6htQCzulJo5531GWmsVlraZ2E9n1jjSKONFau9XlxcnDNu7Zv2fnJzc9UcrQWi1R5N2+8DbWd0qFnPftpx2rhxo5rz22+/OeNW5xzteWPhwoVqzj/+8Q9nfOrUqWqO1i7utNNOU3O0e1Xjxo3VnNjYWGfcOvcvuugiddnnn3/ujGv3PRH9vNy+fbuak5ycXKHti+j3nbPOOkvNmT59ujP+888/qzlnnHGGM661MysvvvEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACFCVayemtbewWjscjqz2MVrrFKstSGFhoTPesmVLNeeJJ55wxq1WD1q7gNtuu03N8dNuKSsryxlv2rSpmmO1dMD+aeeX1t5DRG+fYrV901pBrFmzxtg7N6tNhdbexmq1pLV2sVrlFBcXq8twYKy2dBrtM9TaBonobb78tOWy7lXatdBql2Ut80PbP6utkXZtsFo+xcTEOONWq6rMzExnXGv3Zu1bvXr11Jx169apyw5XWosr67mhefPmzrj1fKK1dWrbtq2as2PHDmdca/1n0caqxTpPtXvV1q1b1ZyOHTs64/n5+WqO1l7Pas+kjX2t7d7hwrquTp482Rm3Whf27NnTGW/fvr2as379emfcar+1fPlyZ7xFixZqjsZ6Lv7222+dceseprUgs879+fPnq8tmzJjhjFvPg9pnZH122rXGeh7UrltWOzHt+Hz88cdqzhdffFGhdZUX33gDAAAAABAgJt4AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAEKAqV9XcT/VyP1Vf/VTarkzW+9Sq/GmVy0VEUlNTnXGr2rhWOfGEE05Qc84991x1WWXSPh+r2qp1fOCfVUFVO+ZWJV2t+u7SpUsrtmP7oVU8t/Zt586dzrhVfdeq0owDk5iY6IxbVVK16txalW0RkVWrVjnj1ueuVbq3rlFaRWbrfqS9Hz851j5YtG1Zn4NWTXfBggVqTuPGjZ1xq3OAdrytz/tI5Od81K6FmzdvrnCOVe1Yq2puiY2Ndcatc0HLSUhIUHO09eXl5ak56enpzvivv/6q5kyfPt0Z79evn5ozb948Z9x65tU62SxatEjNOdisrifbtm1zxq3xrH1WVtVubTuXXHKJmqNVoLfGi/ZM0blzZzVHG8vaOSSidyOyxuUzzzyjLtMqwtepU0fN0bpPWFXAtbHUq1cvNWfMmDHO+M8//6zmaM8S1vVRq6x+oJ1G+MYbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBVrp2YH4e6NZhFKztv7bOflmr33XefM75+/Xo159hjj3XGzz///Apvv7Jpx8BqbWW1GcH+ace8Zs2aak7Dhg2dca1lmIjejua3334z9q7itmzZ4oxrbSVE9LY31nitytefw512ruzevVvN0drOWK2vxo4d64xr10hrH6xWXprq1fVbsdbSzLreWevT2qdYbca0fbA+B+14a21vRPR2lVqbKBH9OFjXrSOR9hlZzxNazuTJk9Uc7Tyx2nlaLXs0Wksl6zy1znuN1g7Suk/4aX2ptZyyWlFp57Z1z7GekaoKrZWXiN4aNzk5Wc2ZOXOmM249/zZr1swZ37Bhg5qzcuVKZ1xriSWit1X87rvv1Bw/z0i1a9d2xrXnIBG9PZqI/gxnna9paWkVzsnOznbGrfF30kknOePW8Rk9erQz3qJFCzVHa51mnSPlwTfeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgJt4AAAAAAASoylU191MFXKt+Z1Xs0yokWpUG/ajMisf333+/ukyrANquXTs156yzzjrgfSrhp5qots/W+g6Hip1HE62CtEUb41u3bj3Q3Sll7dq1znirVq3UHK0CqVWlnWr6wbGuERrt/LLWpX2G1nVNqxZrVTXXKjJb29GqLlvVqq0K7tYyTW5urjNu3d8aNWrkjP/www9qTn5+vjNujT+tE0FCQoKacyTSKsxrx0dEZNeuXc64NVb8VO3XWOdiXl6eM25V0teqtGvnlYjemcN6n8uXL3fGU1JS1JxNmzY549Y9VKtuvWbNGjXH+ryrCj8dFE488UQ1p3nz5s649Rlq84ZPPvlEzdGqmnfu3FnNmT9/vjM+b948NUcbF1deeaWao93DrIri1rk3btw4Z1yrIC8i8re//c0Zb9u2rZrz0ksvOeNz5sxRc+6++25n3Bp/8fHxzrg2/kX0DhwHem/hG28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAAFW5dmJ+2m+1bt3aGdfamYiIbNu2zRmvWbOmmlNYWFixHfMpNTXVGbdaFmgtGLp27Vop+7Q/1udmtY6o6PoaN25c4XXhwFgtObTxYo0jre1FZbcTy8nJccZbtmyp5mgtRrS4iMi6desqsluoAO08sloKaS2SrNZFWo7WzkdEpEGDBs641mZMRCQ6OtoZr1Onjpqjnce1atVSc6zjs3379grvg3bd1Vo+ieitaqx7hXZMrdY72menHesjldZGr1q1amqO9hxktaTSPlervZ2fFn9aiz2r9Z72rGEdA2191rmtXUvq1aun5mjXkhkzZqg52rHeuXOnmnM4tBPLzs5Wl2nvbeHChWqO9nlY9+3Ro0c741ZL4eOOO84ZnzZtmpqzbNkyZ9x6RtLej9bOTERvn2y1DLPuiUlJSc641RpMa51mtTTTrvnafUpEb+dnjXOtnZg1P9HGktZes7z4xhsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAAJW7qrlWldJPFfLK3s6UKVMqdR8OtZdeeskZz8zMVHP69+8f1O6Ui5+Kpn7WZ1WkRjCsyrNaxXOrYqdWrVKrdu6XVknT2o72Xq3q1tbxwYHRjrtVgTshIcEZt65RcXFxzrh139Eqwlrng1ZtvEaNGmqOVl3WuhZaVXb9VEnXxrl23ET0Y7dx40Y1Z8OGDc74okWL1JzmzZs749aYPRJp551VBVw7RlbV3g4dOlRsxwxFRUXqMq1CsZ/7hHWealXxrWrQGquiuNZlZ/HixWpOt27dnHHruFmVvKuKFi1aqMsuuOACZ3z9+vVqjvZMsWnTJjXnoosucsabNWum5mjdFZo0aaLmNGzY0BkfP368mqNVT7fue36q2VvX/IyMDGfcqlCuVTy39k1bX1ZWlprTrl07Z1zr0iDirxuDdm858cQT1Zzy4BtvAAAAAAACxMQbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgACVu51YZbcNq8ztaO2qRo8ereakpqY644888oia884771Rsxwz/+te/1GWnnnqqMz5ixAg1Z/78+Qe8T1WJ1gLFan+AAxMVFeWMFxQUqDna2LPaiVltQSrTypUrnXGrdZPWWsaitYjCgYuNja1Q3GJ97scff7wzbrWj0doDWe2O/LQ00doqWS2frPYt2rGz2k5t2bLFGW/Tpo2ak5eX54z36dNHzdFatFnXfa21Uv369dUc/M7P9W7nzp3OuDW+tHPLar2njQlrrGj7YF2jtXuV1U4sPz/fGbfaGWn7po0TEX3sW8/Jfj7Tg01r/yWit9nSnk9E9DZWVtu16dOnVzhHO1esdnXaOd6+fXs1RzsnKrvF3YIFC9Rl2phNTk6u8D5Y1+L09HRnXDv3RURWr17tjNeuXVvN0T5X7TnRWma1tywPvvEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgAAx8QYAAAAAIEDlrmreo0cPZ9yq4KpVeNy6dauao1VQtioNalUcreqOzZo1c8Zvu+02Neebb75xxnNyctScU045xRm/6aab1Jzvv//eGb/rrrvUnKrMT6X68HD3vwkdDhU7D1da1VWr8mxERESF4iJ2FdfKpI1L63zUllkVe/ft21exHUO5JSUlOeNLly5VcxISEpxxq/Lsxo0bnXGrkq52T4qOjlZztLGkdQew9sGqVuun8rM1zrUqzlZ1ee34WNcG7f7fsmVLNUfb74PViaWq0yrFi+jVgePj49UcrZL93Llz1RztHLYqF2tVla0crXq59fyojVcrRxtfVvV07RhY405j5VjdCaoK6/zSOklY76t3797O+C+//KLmzJgxwxm3ukV06dLFGbeq2WuV0K1ODZ988okzblVCb9y4sTNuPZ9YHWa096RtR0QfM9bzk/Y8aN1bfvvtN2dcu0+J6N2itHmdiH6vatKkiZpTHnzjDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABCgcvcdSE9Pr1BcRG8FY7US0NoxbNmyRc3RyuWvWbNGzXnrrbeccaslhtayoHPnzmpOu3btnPEff/xRzdFamlmt27SWIVZLjKqssLDQGR8/fvxB3pOjh582QxqtHZyIyM6dOyu8Pq3dktUySGs9Z40jrU2M1S6EFnfB8dOuTvt8rdZg2nmkXYdE9GtuZZ8PiYmJzviKFSt8rU8bS9Z71Vo4Wa00tWNqtUHbvn27M261R9PucX6uW4cz7bmqUaNGas7s2bOdcatlkPbMN2fOHDVHawVlfUbaOWedC1p7pDp16qg52vq01nYiestCawzVq1fPGbfuYdrzcN26ddUc6/hUFQsWLFCXae23rPf14YcfOuNW67nWrVs74xs2bFBztLaT1rzh9NNPd8a1tmkiIvXr13fGreeQefPmOePW3Mlq86W12Vu3bp2aox077f2I6J+r1Xa2YcOGzrh1P1q4cKEznpqaquZobcPef/99Nac8+MYbAAAAAIAAMfEGAAAAACBATLwBAAAAAAgQE28AAAAAAALExBsAAAAAgACVu6r5q6++GuBu/I9WfVKrYiciUrt27QrnaJVd09LS1BytenlcXJyaM3r0aGf87bffVnOsauyaw7V6uUarDHzrrbeqOcOGDQtqd45qW7durXCOVRHWT1VzrUq6Vek0NzfXGbcq6WodEvxUT8eB06oEW50xVq5c6YxrlYhF9A4csbGxao52jmvrEvFXQVmrAq5VVRfRK9JarGOqrc8aF9oyq2K2Nja16s4i+vXJb9X3w9X8+fOdces45OfnO+NWFfDPPvvMGfdzzvmpPG8962jLtM4AInol/ZiYGDVHG8fWvU07plaHhk8++cQZt545rbFSVWjn6v6WHY5ef/31Q70LqGL4xhsAAAAAgAAx8QYAAAAAIEBMvAEAAAAACBATbwAAAAAAAsTEGwAAAACAADHxBgAAAAAgQOVuJ3awbN68uUJxHJm0lkDPPffcwd2Ro4jWBslqj6SNy6ioKDXHT/stP+3EtFY1VhsmrQWS1fLFajmFA7NgwQJnXGszJiLSrl07Z/yee+5Rc7RzxWqrpLWrs9oqNW/e3BkfOHCgmqNdC7XWdyIimZmZ6rItW7Y44zVq1FBzxo8f74xr41JEb9+mHTcrp3379mpOXl6eM/7jjz+qOUeibdu2VShu+ctf/lLhHD/Xdatll8a65mtttqyxou2DdQ/TWPeC6tXdj9tWe72lS5c641oLNABVH994AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABCgKlfVHLD885//PNS7cMSaO3euM/7FF1+oOVolZK1ysojIxIkTK7ZjYlel1WzcuNEZX7JkiZpTq1YtZzwnJ0fNmT9/fsV2DOWmHdtHH31UzenSpYsz/vnnn6s5xcXFFduxSjZs2LBDuv2q4pVXXnHGR4wYoeb88MMPzrhWqR7/o1XatiqUa8v8dLLQukiI6J+fts/WdqxzoV69es64dc3XqpdbFeR37txZ4RyN1U3Az70SwMHDN94AAAAAAASIiTcAAAAAAAFi4g0AAAAAQICYeAMAAAAAECAm3gAAAAAABIiJNwAAAAAAAQrzrH4OAAAAAADggPCNNwAAAAAAAWLiDQAAAABAgJh4AwAAAAAQICbeAAAAAAAEiIk3AAAAAAABYuINAAAAAECAmHgDAAAAABAgJt4AAAAAAASIiTcAAAAAAAH6/wDynZ986w3ZEwAAAABJRU5ErkJggg==\n",
      "text/plain": [
       "<Figure size 1000x500 with 10 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "class_names = ['Tshirt', 'Pants', 'Sweater', 'Gown', 'Jacket',  \n",
    "               'Slipper', 'Shirt', 'Shoes', 'Handbag', 'Boots']  \n",
    "\n",
    "# Create a figure\n",
    "fig, axes = plt.subplots(2, 5, figsize=(10, 5))\n",
    "\n",
    "# Track found classes\n",
    "found_classes = {}\n",
    "\n",
    "# Iterate over dataset and select one sample per class\n",
    "for i, (image, label) in enumerate(zip(train_images, train_labels)):\n",
    "    if label not in found_classes:\n",
    "        found_classes[label] = image\n",
    "        if len(found_classes) == 10:  # Stop when all 10 classes are found\n",
    "            break\n",
    "\n",
    "# Plot the images\n",
    "for i, (label, image) in enumerate(found_classes.items()):\n",
    "    ax = axes[i // 5, i % 5]\n",
    "    ax.imshow(image, cmap='gray')\n",
    "    ax.set_title(class_names[label])\n",
    "    ax.axis('off')\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "aa7eba66",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-03-10T06:17:17.491082Z",
     "iopub.status.busy": "2025-03-10T06:17:17.490704Z",
     "iopub.status.idle": "2025-03-10T06:17:20.767808Z",
     "shell.execute_reply": "2025-03-10T06:17:20.766733Z"
    },
    "papermill": {
     "duration": 3.284337,
     "end_time": "2025-03-10T06:17:20.769616",
     "exception": false,
     "start_time": "2025-03-10T06:17:17.485279",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\u001b[34m\u001b[1mwandb\u001b[0m: Tracking run with wandb version 0.19.1\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Run data is saved locally in \u001b[35m\u001b[1m/kaggle/working/wandb/run-20250310_061717-xqm3m9zz\u001b[0m\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Run \u001b[1m`wandb offline`\u001b[0m to turn off syncing.\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Syncing run \u001b[33mQuestion 1\u001b[0m\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at \u001b[34m\u001b[4mhttps://wandb.ai/cs23m071-indian-institute-of-technology-madras/Deep%20Learning%20Course%20DA6401\u001b[0m\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run at \u001b[34m\u001b[4mhttps://wandb.ai/cs23m071-indian-institute-of-technology-madras/Deep%20Learning%20Course%20DA6401/runs/xqm3m9zz\u001b[0m\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m:                                                                                \n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: 🚀 View run \u001b[33mQuestion 1\u001b[0m at: \u001b[34m\u001b[4mhttps://wandb.ai/cs23m071-indian-institute-of-technology-madras/Deep%20Learning%20Course%20DA6401/runs/xqm3m9zz\u001b[0m\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: ⭐️ View project at: \u001b[34m\u001b[4mhttps://wandb.ai/cs23m071-indian-institute-of-technology-madras/Deep%20Learning%20Course%20DA6401\u001b[0m\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 10 other file(s)\n",
      "\u001b[34m\u001b[1mwandb\u001b[0m: Find logs at: \u001b[35m\u001b[1m./wandb/run-20250310_061717-xqm3m9zz/logs\u001b[0m\n"
     ]
    }
   ],
   "source": [
    "wandb.init(project=\"Deep Learning Course DA6401\", name=\"Question 1\")\n",
    "wandb_images = []\n",
    "\n",
    "for label, image in found_classes.items():\n",
    "    wandb_images.append(wandb.Image(image, caption=class_names[label]))\n",
    "\n",
    "# Log images to WandB\n",
    "wandb.log({\"Fashion-MNIST Samples\": wandb_images})\n",
    "\n",
    "# Finish WandB logging\n",
    "wandb.finish()\n",
    "# input()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "bd0011fd",
   "metadata": {
    "papermill": {
     "duration": 0.004539,
     "end_time": "2025-03-10T06:17:20.779580",
     "exception": false,
     "start_time": "2025-03-10T06:17:20.775041",
     "status": "completed"
    },
    "tags": []
   },
   "source": [
    "# Question 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "5e46db4f",
   "metadata": {
    "execution": {
     "iopub.execute_input": "2025-03-10T06:17:20.790681Z",
     "iopub.status.busy": "2025-03-10T06:17:20.790327Z",
     "iopub.status.idle": "2025-03-10T06:17:20.798225Z",
     "shell.execute_reply": "2025-03-10T06:17:20.797101Z"
    },
    "papermill": {
     "duration": 0.015089,
     "end_time": "2025-03-10T06:17:20.799545",
     "exception": false,
     "start_time": "2025-03-10T06:17:20.784456",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "def one_hot_encode(labels, num_classes=10):\n",
    "    return np.eye(num_classes)[labels]\n",
    "\n",
    "train_labels_one_hot = one_hot_encode(train_labels)\n",
    "test_labels_one_hot = one_hot_encode(test_labels)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "9c336408",
   "metadata": {
    "papermill": {
     "duration": 0.004513,
     "end_time": "2025-03-10T06:17:20.809322",
     "exception": false,
     "start_time": "2025-03-10T06:17:20.804809",
     "status": "completed"
    },
    "tags": []
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kaggle": {
   "accelerator": "none",
   "dataSources": [],
   "dockerImageVersionId": 30918,
   "isGpuEnabled": false,
   "isInternetEnabled": true,
   "language": "python",
   "sourceType": "notebook"
  },
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.10.12"
  },
  "papermill": {
   "default_parameters": {},
   "duration": 36.452455,
   "end_time": "2025-03-10T06:17:23.390405",
   "environment_variables": {},
   "exception": null,
   "input_path": "__notebook__.ipynb",
   "output_path": "__notebook__.ipynb",
   "parameters": {},
   "start_time": "2025-03-10T06:16:46.937950",
   "version": "2.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}