{
  "cells": [
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0vznIiIyiecY",
        "outputId": "9495b7ee-08c6-4b43-f3a4-9d6cb934edd9"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 1: SETUP DRIVE\n",
        "# =========================================\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "import os, shutil, zipfile\n",
        "import numpy as np\n",
        "import tensorflow as tf\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "from sklearn.model_selection import train_test_split\n",
        "\n",
        "base_dir = \"/content/drive/MyDrive/chest_xray_project\"\n",
        "os.makedirs(base_dir, exist_ok=True)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 73
        },
        "id": "N-Q6SUj0ikDU",
        "outputId": "25f9166f-00f3-4104-dbe1-fe45d36506d1"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "     <input type=\"file\" id=\"files-5cbbbabe-900e-4670-8a83-e81088256c10\" name=\"files[]\" multiple disabled\n",
              "        style=\"border:none\" />\n",
              "     <output id=\"result-5cbbbabe-900e-4670-8a83-e81088256c10\">\n",
              "      Upload widget is only available when the cell has been executed in the\n",
              "      current browser session. Please rerun this cell to enable.\n",
              "      </output>\n",
              "      <script>// Copyright 2017 Google LLC\n",
              "//\n",
              "// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
              "// you may not use this file except in compliance with the License.\n",
              "// You may obtain a copy of the License at\n",
              "//\n",
              "//      http://www.apache.org/licenses/LICENSE-2.0\n",
              "//\n",
              "// Unless required by applicable law or agreed to in writing, software\n",
              "// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
              "// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
              "// See the License for the specific language governing permissions and\n",
              "// limitations under the License.\n",
              "\n",
              "/**\n",
              " * @fileoverview Helpers for google.colab Python module.\n",
              " */\n",
              "(function(scope) {\n",
              "function span(text, styleAttributes = {}) {\n",
              "  const element = document.createElement('span');\n",
              "  element.textContent = text;\n",
              "  for (const key of Object.keys(styleAttributes)) {\n",
              "    element.style[key] = styleAttributes[key];\n",
              "  }\n",
              "  return element;\n",
              "}\n",
              "\n",
              "// Max number of bytes which will be uploaded at a time.\n",
              "const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
              "\n",
              "function _uploadFiles(inputId, outputId) {\n",
              "  const steps = uploadFilesStep(inputId, outputId);\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  // Cache steps on the outputElement to make it available for the next call\n",
              "  // to uploadFilesContinue from Python.\n",
              "  outputElement.steps = steps;\n",
              "\n",
              "  return _uploadFilesContinue(outputId);\n",
              "}\n",
              "\n",
              "// This is roughly an async generator (not supported in the browser yet),\n",
              "// where there are multiple asynchronous steps and the Python side is going\n",
              "// to poll for completion of each step.\n",
              "// This uses a Promise to block the python side on completion of each step,\n",
              "// then passes the result of the previous step as the input to the next step.\n",
              "function _uploadFilesContinue(outputId) {\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  const steps = outputElement.steps;\n",
              "\n",
              "  const next = steps.next(outputElement.lastPromiseValue);\n",
              "  return Promise.resolve(next.value.promise).then((value) => {\n",
              "    // Cache the last promise value to make it available to the next\n",
              "    // step of the generator.\n",
              "    outputElement.lastPromiseValue = value;\n",
              "    return next.value.response;\n",
              "  });\n",
              "}\n",
              "\n",
              "/**\n",
              " * Generator function which is called between each async step of the upload\n",
              " * process.\n",
              " * @param {string} inputId Element ID of the input file picker element.\n",
              " * @param {string} outputId Element ID of the output display.\n",
              " * @return {!Iterable<!Object>} Iterable of next steps.\n",
              " */\n",
              "function* uploadFilesStep(inputId, outputId) {\n",
              "  const inputElement = document.getElementById(inputId);\n",
              "  inputElement.disabled = false;\n",
              "\n",
              "  const outputElement = document.getElementById(outputId);\n",
              "  outputElement.innerHTML = '';\n",
              "\n",
              "  const pickedPromise = new Promise((resolve) => {\n",
              "    inputElement.addEventListener('change', (e) => {\n",
              "      resolve(e.target.files);\n",
              "    });\n",
              "  });\n",
              "\n",
              "  const cancel = document.createElement('button');\n",
              "  inputElement.parentElement.appendChild(cancel);\n",
              "  cancel.textContent = 'Cancel upload';\n",
              "  const cancelPromise = new Promise((resolve) => {\n",
              "    cancel.onclick = () => {\n",
              "      resolve(null);\n",
              "    };\n",
              "  });\n",
              "\n",
              "  // Wait for the user to pick the files.\n",
              "  const files = yield {\n",
              "    promise: Promise.race([pickedPromise, cancelPromise]),\n",
              "    response: {\n",
              "      action: 'starting',\n",
              "    }\n",
              "  };\n",
              "\n",
              "  cancel.remove();\n",
              "\n",
              "  // Disable the input element since further picks are not allowed.\n",
              "  inputElement.disabled = true;\n",
              "\n",
              "  if (!files) {\n",
              "    return {\n",
              "      response: {\n",
              "        action: 'complete',\n",
              "      }\n",
              "    };\n",
              "  }\n",
              "\n",
              "  for (const file of files) {\n",
              "    const li = document.createElement('li');\n",
              "    li.append(span(file.name, {fontWeight: 'bold'}));\n",
              "    li.append(span(\n",
              "        `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
              "        `last modified: ${\n",
              "            file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
              "                                    'n/a'} - `));\n",
              "    const percent = span('0% done');\n",
              "    li.appendChild(percent);\n",
              "\n",
              "    outputElement.appendChild(li);\n",
              "\n",
              "    const fileDataPromise = new Promise((resolve) => {\n",
              "      const reader = new FileReader();\n",
              "      reader.onload = (e) => {\n",
              "        resolve(e.target.result);\n",
              "      };\n",
              "      reader.readAsArrayBuffer(file);\n",
              "    });\n",
              "    // Wait for the data to be ready.\n",
              "    let fileData = yield {\n",
              "      promise: fileDataPromise,\n",
              "      response: {\n",
              "        action: 'continue',\n",
              "      }\n",
              "    };\n",
              "\n",
              "    // Use a chunked sending to avoid message size limits. See b/62115660.\n",
              "    let position = 0;\n",
              "    do {\n",
              "      const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
              "      const chunk = new Uint8Array(fileData, position, length);\n",
              "      position += length;\n",
              "\n",
              "      const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
              "      yield {\n",
              "        response: {\n",
              "          action: 'append',\n",
              "          file: file.name,\n",
              "          data: base64,\n",
              "        },\n",
              "      };\n",
              "\n",
              "      let percentDone = fileData.byteLength === 0 ?\n",
              "          100 :\n",
              "          Math.round((position / fileData.byteLength) * 100);\n",
              "      percent.textContent = `${percentDone}% done`;\n",
              "\n",
              "    } while (position < fileData.byteLength);\n",
              "  }\n",
              "\n",
              "  // All done.\n",
              "  yield {\n",
              "    response: {\n",
              "      action: 'complete',\n",
              "    }\n",
              "  };\n",
              "}\n",
              "\n",
              "scope.google = scope.google || {};\n",
              "scope.google.colab = scope.google.colab || {};\n",
              "scope.google.colab._files = {\n",
              "  _uploadFiles,\n",
              "  _uploadFilesContinue,\n",
              "};\n",
              "})(self);\n",
              "</script> "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Saving kaggle.json to kaggle.json\n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 2: KAGGLE API SETUP\n",
        "# =========================================\n",
        "!mkdir -p ~/.kaggle\n",
        "from google.colab import files\n",
        "files.upload()   # 👉 Upload kaggle.json here\n",
        "\n",
        "!mv kaggle.json ~/.kaggle/\n",
        "!chmod 600 ~/.kaggle/kaggle.json"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ly2rL_UGiu_w",
        "outputId": "9f325cb5-9466-4642-b15f-01a6516c1cc6"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Dataset URL: https://www.kaggle.com/datasets/tawsifurrahman/covid19-radiography-database\n",
            "License(s): copyright-authors\n",
            "Downloading covid19-radiography-database.zip to /content\n",
            " 98% 760M/778M [00:07<00:00, 187MB/s]\n",
            "100% 778M/778M [00:07<00:00, 107MB/s]\n",
            "Dataset URL: https://www.kaggle.com/datasets/prashant268/chest-xray-covid19-pneumonia\n",
            "License(s): unknown\n",
            "Downloading chest-xray-covid19-pneumonia.zip to /content\n",
            " 99% 2.04G/2.06G [00:16<00:00, 46.6MB/s]\n",
            "100% 2.06G/2.06G [00:16<00:00, 134MB/s] \n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 3: DOWNLOAD & UNZIP DATASETS\n",
        "# =========================================\n",
        "# Force full downloads\n",
        "!rm -rf /content/COVID-19_Radiography_Dataset /content/Data\n",
        "!rm -f /content/covid19-radiography-database.zip /content/chest-xray-covid19-pneumonia.zip\n",
        "\n",
        "!kaggle datasets download -d tawsifurrahman/covid19-radiography-database -p /content --force\n",
        "!kaggle datasets download -d prashant268/chest-xray-covid19-pneumonia -p /content --force\n",
        "\n",
        "# Unzip main zips\n",
        "!unzip -q /content/covid19-radiography-database.zip -d /content/\n",
        "!unzip -q /content/chest-xray-covid19-pneumonia.zip -d /content/"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xzP-KGcmjonp",
        "outputId": "193837c4-133a-4c50-d184-c1c66ce4cf01"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Before balancing:\n",
            "COVID: 4192  PNEUMONIA: 11630  NORMAL: 11775\n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 4: MERGE INTO 3 CLASSES\n",
        "# =========================================\n",
        "merged_dir = \"/content/merged_dataset\"\n",
        "for cls in [\"COVID\", \"PNEUMONIA\", \"NORMAL\"]:\n",
        "    os.makedirs(os.path.join(merged_dir, cls), exist_ok=True)\n",
        "\n",
        "def copy_images(src_folder, dest_folder):\n",
        "    if not os.path.exists(src_folder):\n",
        "        return\n",
        "    for img in os.listdir(src_folder):\n",
        "        path = os.path.join(src_folder, img)\n",
        "        if os.path.isfile(path) and img.lower().endswith((\"png\",\"jpg\",\"jpeg\")):\n",
        "            shutil.copy(path, dest_folder)\n",
        "\n",
        "# ---- Dataset 1: Radiography (note the /images subfolders!)\n",
        "src1 = \"/content/COVID-19_Radiography_Dataset\"\n",
        "copy_images(os.path.join(src1, \"COVID/images\"), os.path.join(merged_dir, \"COVID\"))\n",
        "copy_images(os.path.join(src1, \"Normal/images\"), os.path.join(merged_dir, \"NORMAL\"))\n",
        "copy_images(os.path.join(src1, \"Viral Pneumonia/images\"), os.path.join(merged_dir, \"PNEUMONIA\"))\n",
        "copy_images(os.path.join(src1, \"Lung_Opacity/images\"), os.path.join(merged_dir, \"PNEUMONIA\"))\n",
        "\n",
        "# ---- Dataset 2: Prashant (Data/train + Data/test)\n",
        "src2 = \"/content/Data\"\n",
        "for subset in [\"train\", \"test\"]:\n",
        "    for cls in [\"COVID19\", \"NORMAL\", \"PNEUMONIA\"]:\n",
        "        src_path = os.path.join(src2, subset, cls)\n",
        "        if os.path.exists(src_path):\n",
        "            cls_target = \"COVID\" if cls == \"COVID19\" else cls\n",
        "            copy_images(src_path, os.path.join(merged_dir, cls_target))\n",
        "\n",
        "# Check merged counts before balancing\n",
        "covid_count = len(os.listdir(os.path.join(merged_dir, \"COVID\")))\n",
        "pneu_count  = len(os.listdir(os.path.join(merged_dir, \"PNEUMONIA\")))\n",
        "normal_count = len(os.listdir(os.path.join(merged_dir, \"NORMAL\")))\n",
        "print(\"Before balancing:\")\n",
        "print(\"COVID:\", covid_count, \" PNEUMONIA:\", pneu_count, \" NORMAL:\", normal_count)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qpvFO3GMkJqM",
        "outputId": "cd0a6133-792b-4e32-cfe4-0abfd7530873"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Augmenting COVID: current=9490, target=11775, generating 2285 new images\n",
            "Generated 500 augmented images so far... current total=9990\n",
            "Generated 1000 augmented images so far... current total=10490\n",
            "Generated 1500 augmented images so far... current total=10990\n",
            "Generated 2000 augmented images so far... current total=11490\n",
            "✅ Finished augmentation for COVID. Final count = 11775\n",
            "PNEUMONIA already has 11630, no augmentation needed\n",
            "NORMAL already has 11775, no augmentation needed\n",
            "\n",
            "Final class counts after balancing:\n",
            "COVID: 11775\n",
            "PNEUMONIA: 11630\n",
            "NORMAL: 11775\n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 5: BALANCE DATASET TO TARGET COUNTS\n",
        "# =========================================\n",
        "import uuid\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "import tensorflow as tf\n",
        "import numpy as np\n",
        "import os\n",
        "\n",
        "def augment_class(class_dir, target_count):\n",
        "    datagen = ImageDataGenerator(\n",
        "        rotation_range=15,\n",
        "        width_shift_range=0.1,\n",
        "        height_shift_range=0.1,\n",
        "        shear_range=0.1,\n",
        "        zoom_range=0.1,\n",
        "        horizontal_flip=True,\n",
        "        fill_mode=\"nearest\"\n",
        "    )\n",
        "\n",
        "    images = [f for f in os.listdir(class_dir) if f.lower().endswith(('.png','.jpg','.jpeg'))]\n",
        "    current_count = len(images)\n",
        "    needed = target_count - current_count\n",
        "\n",
        "    if needed <= 0:\n",
        "        print(f\"{os.path.basename(class_dir)} already has {current_count}, no augmentation needed\")\n",
        "        return\n",
        "\n",
        "    print(f\"Augmenting {os.path.basename(class_dir)}: current={current_count}, target={target_count}, generating {needed} new images\")\n",
        "\n",
        "    i = 0\n",
        "    while len(os.listdir(class_dir)) < target_count:\n",
        "        img_path = os.path.join(class_dir, images[i % len(images)])\n",
        "        img = tf.keras.utils.load_img(img_path, target_size=(224,224))\n",
        "        x = tf.keras.utils.img_to_array(img)\n",
        "        x = np.expand_dims(x, axis=0)\n",
        "\n",
        "        # unique filename using uuid\n",
        "        for batch in datagen.flow(\n",
        "            x, batch_size=1, save_to_dir=class_dir,\n",
        "            save_prefix=str(uuid.uuid4()), save_format=\"png\"\n",
        "        ):\n",
        "            break\n",
        "\n",
        "        i += 1\n",
        "        if i % 500 == 0:\n",
        "            print(f\"Generated {i} augmented images so far... current total={len(os.listdir(class_dir))}\")\n",
        "\n",
        "    print(f\"✅ Finished augmentation for {os.path.basename(class_dir)}. Final count = {len(os.listdir(class_dir))}\")\n",
        "\n",
        "\n",
        "# Paths\n",
        "covid_dir  = os.path.join(merged_dir, \"COVID\")\n",
        "pneu_dir   = os.path.join(merged_dir, \"PNEUMONIA\")\n",
        "normal_dir = os.path.join(merged_dir, \"NORMAL\")\n",
        "\n",
        "# Target counts\n",
        "target_covid  = 11775\n",
        "target_pneu   = 11630\n",
        "target_normal = 11775\n",
        "\n",
        "# Augment each class\n",
        "augment_class(covid_dir, target_covid)\n",
        "augment_class(pneu_dir, target_pneu)\n",
        "augment_class(normal_dir, target_normal)\n",
        "\n",
        "print(\"\\nFinal class counts after balancing:\")\n",
        "print(\"COVID:\", len(os.listdir(covid_dir)))\n",
        "print(\"PNEUMONIA:\", len(os.listdir(pneu_dir)))\n",
        "print(\"NORMAL:\", len(os.listdir(normal_dir)))\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install split-folders"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "erKp93FcDjb4",
        "outputId": "128f7ad1-b843-4331-b4d8-2a108a02e236"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting split-folders\n",
            "  Downloading split_folders-0.5.1-py3-none-any.whl.metadata (6.2 kB)\n",
            "Downloading split_folders-0.5.1-py3-none-any.whl (8.4 kB)\n",
            "Installing collected packages: split-folders\n",
            "Successfully installed split-folders-0.5.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import splitfolders\n",
        "\n",
        "input_folder = merged_dir   # your balanced dataset with COVID, PNEUMONIA, NORMAL\n",
        "output_folder = \"/content/final_dataset\"\n",
        "\n",
        "# Split into 70% train, 15% val, 15% test\n",
        "splitfolders.ratio(input_folder, output=output_folder, seed=42, ratio=(0.7, 0.15, 0.15))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0F9a1RFBDLgU",
        "outputId": "155d9745-5839-4103-d585-5d06c8f471c9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Copying files: 0 files [00:00, ? files/s]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!cp -r /content/final_dataset \"/content/drive/MyDrive/chest_xray_project/\""
      ],
      "metadata": {
        "id": "qZMRavS8EIj-"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-e5zGDxZlDpy",
        "outputId": "c9100023-2ec1-462d-f2ba-a87c55c605df"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: split-folders in /usr/local/lib/python3.12/dist-packages (0.5.1)\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Copying files: 27597 files [00:41, 669.50 files/s] \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "^C\n",
            "\n",
            "✅ Final dataset split into train/val/test and saved to Drive at: chest_xray_project/final_dataset\n",
            "train/COVID → 2934 images\n",
            "train/PNEUMONIA → 8140 images\n",
            "train/NORMAL → 8242 images\n",
            "val/COVID → 628 images\n",
            "val/PNEUMONIA → 1744 images\n",
            "val/NORMAL → 1766 images\n",
            "test/COVID → 630 images\n",
            "test/PNEUMONIA → 1746 images\n",
            "test/NORMAL → 1767 images\n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 6: TRAIN/VAL/TEST SPLIT & SAVE TO DRIVE\n",
        "# =========================================\n",
        "\n",
        "# 1. Install split-folders (only once per Colab session)\n",
        "!pip install split-folders\n",
        "\n",
        "import splitfolders, os\n",
        "\n",
        "# 2. Path to your merged balanced dataset\n",
        "#    (must contain 3 folders: COVID, PNEUMONIA, NORMAL)\n",
        "input_folder = merged_dir    # e.g. \"/content/merged_dataset\"\n",
        "\n",
        "# 3. Output path (where train/val/test will be created)\n",
        "output_folder = \"/content/final_dataset\"\n",
        "\n",
        "# 4. Perform split (70% train, 15% val, 15% test)\n",
        "splitfolders.ratio(input_folder, output=output_folder, seed=42, ratio=(0.7, 0.15, 0.15))\n",
        "\n",
        "# 5. Copy final dataset to Google Drive\n",
        "!cp -r /content/final_dataset \"/content/drive/MyDrive/chest_xray_project/\"\n",
        "\n",
        "print(\"\\n✅ Final dataset split into train/val/test and saved to Drive at: chest_xray_project/final_dataset\")\n",
        "\n",
        "# 6. Sanity check: Count images in each split/class\n",
        "for split in [\"train\", \"val\", \"test\"]:\n",
        "    for cls in [\"COVID\", \"PNEUMONIA\", \"NORMAL\"]:\n",
        "        path = os.path.join(output_folder, split, cls)\n",
        "        print(f\"{split}/{cls} → {len(os.listdir(path))} images\")\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import os\n",
        "\n",
        "drive_path = \"/content/drive/MyDrive/chest_xray_project/final_dataset\"\n",
        "\n",
        "for split in [\"train\", \"val\", \"test\"]:\n",
        "    for cls in [\"COVID\", \"PNEUMONIA\", \"NORMAL\"]:\n",
        "        path = os.path.join(drive_path, split, cls)\n",
        "        print(split, cls, \":\", len(os.listdir(path)))\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bPaXyYSmMg0f",
        "outputId": "9cbf96d5-e479-43b1-dae3-b45b237d5a78"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "train COVID : 10742\n",
            "train PNEUMONIA : 10582\n",
            "train NORMAL : 10723\n",
            "val COVID : 3270\n",
            "val PNEUMONIA : 3219\n",
            "val NORMAL : 3275\n",
            "test COVID : 3271\n",
            "test PNEUMONIA : 3238\n",
            "test NORMAL : 3272\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Kgcy6l3El0fH",
        "outputId": "46a045f5-9f4f-47f4-84fd-cfa6e58449ca"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 32047 images belonging to 3 classes.\n",
            "Found 9764 images belonging to 3 classes.\n",
            "Found 9781 images belonging to 3 classes.\n",
            "\n",
            "✅ Generators ready\n",
            "Classes: {'COVID': 0, 'NORMAL': 1, 'PNEUMONIA': 2}\n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 7: LOAD DATA (from local copy of Drive dataset)\n",
        "# =========================================\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "import os\n",
        "\n",
        "# Copy dataset from Drive -> Colab local storage (much faster for training)\n",
        "!cp -r \"/content/drive/MyDrive/chest_xray_project/final_dataset\" /content/\n",
        "dataset_dir = \"/content/final_dataset\"\n",
        "\n",
        "# Image size and batch size\n",
        "img_size = (224,224)\n",
        "batch_size = 32\n",
        "\n",
        "# Augmentation for training\n",
        "train_datagen = ImageDataGenerator(\n",
        "    rescale=1./255,\n",
        "    rotation_range=15,\n",
        "    width_shift_range=0.1,\n",
        "    height_shift_range=0.1,\n",
        "    shear_range=0.1,\n",
        "    zoom_range=0.1,\n",
        "    horizontal_flip=True\n",
        ")\n",
        "\n",
        "# Only rescaling for validation & test\n",
        "val_test_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "# Train generator\n",
        "train_gen = train_datagen.flow_from_directory(\n",
        "    os.path.join(dataset_dir, \"train\"),\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\"\n",
        ")\n",
        "\n",
        "# Validation generator\n",
        "val_gen = val_test_datagen.flow_from_directory(\n",
        "    os.path.join(dataset_dir, \"val\"),\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\"\n",
        ")\n",
        "\n",
        "# Test generator\n",
        "test_gen = val_test_datagen.flow_from_directory(\n",
        "    os.path.join(dataset_dir, \"test\"),\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "print(\"\\n✅ Generators ready\")\n",
        "print(\"Classes:\", train_gen.class_indices)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "19IS_tMVo3Vu",
        "outputId": "4fda2cda-7829-45b0-b31f-6ee4f98f845c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/densenet/densenet201_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "\u001b[1m74836368/74836368\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 0us/step\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 450ms/step - accuracy: 0.5523 - loss: 0.9502\n",
            "Epoch 1: val_accuracy improved from -inf to 0.81186, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m610s\u001b[0m 542ms/step - accuracy: 0.5525 - loss: 0.9500 - val_accuracy: 0.8119 - val_loss: 0.4728 - learning_rate: 1.0000e-05\n",
            "Epoch 2/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 408ms/step - accuracy: 0.7993 - loss: 0.5125\n",
            "Epoch 2: val_accuracy improved from 0.81186 to 0.84125, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m450s\u001b[0m 449ms/step - accuracy: 0.7993 - loss: 0.5125 - val_accuracy: 0.8413 - val_loss: 0.4020 - learning_rate: 1.0000e-05\n",
            "Epoch 3/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 410ms/step - accuracy: 0.8455 - loss: 0.4073\n",
            "Epoch 3: val_accuracy improved from 0.84125 to 0.86092, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m452s\u001b[0m 452ms/step - accuracy: 0.8455 - loss: 0.4073 - val_accuracy: 0.8609 - val_loss: 0.3599 - learning_rate: 1.0000e-05\n",
            "Epoch 4/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step - accuracy: 0.8667 - loss: 0.3586\n",
            "Epoch 4: val_accuracy improved from 0.86092 to 0.87956, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 452ms/step - accuracy: 0.8667 - loss: 0.3586 - val_accuracy: 0.8796 - val_loss: 0.3119 - learning_rate: 1.0000e-05\n",
            "Epoch 5/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step - accuracy: 0.8782 - loss: 0.3260\n",
            "Epoch 5: val_accuracy improved from 0.87956 to 0.89830, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m454s\u001b[0m 453ms/step - accuracy: 0.8782 - loss: 0.3260 - val_accuracy: 0.8983 - val_loss: 0.2686 - learning_rate: 1.0000e-05\n",
            "Epoch 6/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 409ms/step - accuracy: 0.8885 - loss: 0.3021\n",
            "Epoch 6: val_accuracy did not improve from 0.89830\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m447s\u001b[0m 446ms/step - accuracy: 0.8885 - loss: 0.3021 - val_accuracy: 0.8889 - val_loss: 0.2885 - learning_rate: 1.0000e-05\n",
            "Epoch 7/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 409ms/step - accuracy: 0.9004 - loss: 0.2740\n",
            "Epoch 7: val_accuracy improved from 0.89830 to 0.90434, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m465s\u001b[0m 464ms/step - accuracy: 0.9004 - loss: 0.2740 - val_accuracy: 0.9043 - val_loss: 0.2538 - learning_rate: 1.0000e-05\n",
            "Epoch 8/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step - accuracy: 0.9032 - loss: 0.2680\n",
            "Epoch 8: val_accuracy improved from 0.90434 to 0.91192, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 452ms/step - accuracy: 0.9032 - loss: 0.2680 - val_accuracy: 0.9119 - val_loss: 0.2348 - learning_rate: 1.0000e-05\n",
            "Epoch 9/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 408ms/step - accuracy: 0.9083 - loss: 0.2512\n",
            "Epoch 9: val_accuracy improved from 0.91192 to 0.91417, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m450s\u001b[0m 449ms/step - accuracy: 0.9083 - loss: 0.2512 - val_accuracy: 0.9142 - val_loss: 0.2314 - learning_rate: 1.0000e-05\n",
            "Epoch 10/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 410ms/step - accuracy: 0.9139 - loss: 0.2328\n",
            "Epoch 10: val_accuracy improved from 0.91417 to 0.91428, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 452ms/step - accuracy: 0.9139 - loss: 0.2328 - val_accuracy: 0.9143 - val_loss: 0.2256 - learning_rate: 1.0000e-05\n",
            "Epoch 11/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 410ms/step - accuracy: 0.9156 - loss: 0.2292\n",
            "Epoch 11: val_accuracy improved from 0.91428 to 0.92728, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m452s\u001b[0m 451ms/step - accuracy: 0.9156 - loss: 0.2292 - val_accuracy: 0.9273 - val_loss: 0.1990 - learning_rate: 1.0000e-05\n",
            "Epoch 12/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.9172 - loss: 0.2233\n",
            "Epoch 12: val_accuracy improved from 0.92728 to 0.93056, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m454s\u001b[0m 453ms/step - accuracy: 0.9172 - loss: 0.2233 - val_accuracy: 0.9306 - val_loss: 0.1902 - learning_rate: 1.0000e-05\n",
            "Epoch 13/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step - accuracy: 0.9246 - loss: 0.2109\n",
            "Epoch 13: val_accuracy improved from 0.93056 to 0.93404, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 452ms/step - accuracy: 0.9246 - loss: 0.2109 - val_accuracy: 0.9340 - val_loss: 0.1825 - learning_rate: 1.0000e-05\n",
            "Epoch 14/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.9289 - loss: 0.2022\n",
            "Epoch 14: val_accuracy improved from 0.93404 to 0.93476, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m454s\u001b[0m 453ms/step - accuracy: 0.9289 - loss: 0.2022 - val_accuracy: 0.9348 - val_loss: 0.1821 - learning_rate: 1.0000e-05\n",
            "Epoch 15/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step - accuracy: 0.9289 - loss: 0.1951\n",
            "Epoch 15: val_accuracy improved from 0.93476 to 0.93834, saving model to /content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 452ms/step - accuracy: 0.9289 - loss: 0.1951 - val_accuracy: 0.9383 - val_loss: 0.1725 - learning_rate: 1.0000e-05\n",
            "Restoring model weights from the end of the best epoch: 15.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 8a: DENSENET201 TRAINING (fine-tuned, 15 epochs)\n",
        "# =========================================\n",
        "from tensorflow.keras.applications import DenseNet201\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\n",
        "\n",
        "# Load DenseNet201 backbone\n",
        "densenet_base = DenseNet201(weights=\"imagenet\", include_top=False, input_shape=(224,224,3))\n",
        "\n",
        "# Freeze most layers, unfreeze last 50 for fine-tuning\n",
        "for layer in densenet_base.layers[:-50]:\n",
        "    layer.trainable = False\n",
        "for layer in densenet_base.layers[-50:]:\n",
        "    layer.trainable = True\n",
        "\n",
        "# Classification head\n",
        "x = densenet_base.output\n",
        "x = GlobalAveragePooling2D()(x)\n",
        "x = Dropout(0.4)(x)\n",
        "x = Dense(512, activation=\"relu\")(x)\n",
        "x = Dropout(0.3)(x)\n",
        "predictions = Dense(3, activation=\"softmax\")(x)\n",
        "\n",
        "densenet_model = Model(inputs=densenet_base.input, outputs=predictions)\n",
        "\n",
        "# Compile with smaller LR for fine-tuning\n",
        "densenet_model.compile(\n",
        "    optimizer=Adam(learning_rate=1e-5),\n",
        "    loss=\"categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")\n",
        "\n",
        "# Callbacks\n",
        "checkpoint = ModelCheckpoint(\n",
        "    \"/content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\",\n",
        "    monitor=\"val_accuracy\", save_best_only=True, mode=\"max\", verbose=1\n",
        ")\n",
        "early_stop = EarlyStopping(monitor=\"val_loss\", patience=5, restore_best_weights=True, verbose=1)\n",
        "reduce_lr = ReduceLROnPlateau(monitor=\"val_loss\", factor=0.2, patience=3, min_lr=1e-7, verbose=1)\n",
        "\n",
        "# Train DenseNet201\n",
        "history_densenet = densenet_model.fit(\n",
        "    train_gen,\n",
        "    epochs=15,\n",
        "    validation_data=val_gen,\n",
        "    callbacks=[checkpoint, early_stop, reduce_lr]\n",
        ")\n",
        "\n",
        "densenet_model.save(\"/content/drive/MyDrive/chest_xray_project/densenet201_final_ft.h5\")\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VjSNAQHkwyiM",
        "outputId": "050da389-ae4b-4918-d774-4e29194780b4"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/resnet/resnet152_weights_tf_dim_ordering_tf_kernels_notop.h5\n",
            "\u001b[1m234698864/234698864\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 0us/step\n",
            "Epoch 1/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 428ms/step - accuracy: 0.5887 - loss: 0.8803\n",
            "Epoch 1: val_accuracy improved from -inf to 0.66336, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m529s\u001b[0m 488ms/step - accuracy: 0.5888 - loss: 0.8802 - val_accuracy: 0.6634 - val_loss: 0.8012 - learning_rate: 1.0000e-05\n",
            "Epoch 2/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.7363 - loss: 0.6423\n",
            "Epoch 2: val_accuracy did not improve from 0.66336\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m451s\u001b[0m 450ms/step - accuracy: 0.7363 - loss: 0.6423 - val_accuracy: 0.6448 - val_loss: 0.7868 - learning_rate: 1.0000e-05\n",
            "Epoch 3/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.7500 - loss: 0.6099\n",
            "Epoch 3: val_accuracy improved from 0.66336 to 0.71610, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m457s\u001b[0m 456ms/step - accuracy: 0.7500 - loss: 0.6099 - val_accuracy: 0.7161 - val_loss: 0.7001 - learning_rate: 1.0000e-05\n",
            "Epoch 4/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 410ms/step - accuracy: 0.7664 - loss: 0.5724\n",
            "Epoch 4: val_accuracy did not improve from 0.71610\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m448s\u001b[0m 447ms/step - accuracy: 0.7664 - loss: 0.5724 - val_accuracy: 0.6754 - val_loss: 0.7564 - learning_rate: 1.0000e-05\n",
            "Epoch 5/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 413ms/step - accuracy: 0.7717 - loss: 0.5582\n",
            "Epoch 5: val_accuracy improved from 0.71610 to 0.77704, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m458s\u001b[0m 457ms/step - accuracy: 0.7717 - loss: 0.5582 - val_accuracy: 0.7770 - val_loss: 0.5397 - learning_rate: 1.0000e-05\n",
            "Epoch 6/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 414ms/step - accuracy: 0.7803 - loss: 0.5396\n",
            "Epoch 6: val_accuracy improved from 0.77704 to 0.78042, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m458s\u001b[0m 457ms/step - accuracy: 0.7803 - loss: 0.5396 - val_accuracy: 0.7804 - val_loss: 0.5495 - learning_rate: 1.0000e-05\n",
            "Epoch 7/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.7851 - loss: 0.5289\n",
            "Epoch 7: val_accuracy improved from 0.78042 to 0.81514, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m462s\u001b[0m 461ms/step - accuracy: 0.7851 - loss: 0.5289 - val_accuracy: 0.8151 - val_loss: 0.4688 - learning_rate: 1.0000e-05\n",
            "Epoch 8/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 410ms/step - accuracy: 0.7929 - loss: 0.5140\n",
            "Epoch 8: val_accuracy did not improve from 0.81514\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m448s\u001b[0m 447ms/step - accuracy: 0.7929 - loss: 0.5140 - val_accuracy: 0.7868 - val_loss: 0.5158 - learning_rate: 1.0000e-05\n",
            "Epoch 9/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 413ms/step - accuracy: 0.8028 - loss: 0.4920\n",
            "Epoch 9: val_accuracy did not improve from 0.81514\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m451s\u001b[0m 450ms/step - accuracy: 0.8028 - loss: 0.4920 - val_accuracy: 0.7424 - val_loss: 0.6944 - learning_rate: 1.0000e-05\n",
            "Epoch 10/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.8044 - loss: 0.4910\n",
            "Epoch 10: val_accuracy improved from 0.81514 to 0.83961, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m456s\u001b[0m 455ms/step - accuracy: 0.8044 - loss: 0.4910 - val_accuracy: 0.8396 - val_loss: 0.4137 - learning_rate: 1.0000e-05\n",
            "Epoch 11/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.8075 - loss: 0.4812\n",
            "Epoch 11: val_accuracy did not improve from 0.83961\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m451s\u001b[0m 450ms/step - accuracy: 0.8075 - loss: 0.4812 - val_accuracy: 0.8256 - val_loss: 0.4366 - learning_rate: 1.0000e-05\n",
            "Epoch 12/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 412ms/step - accuracy: 0.8087 - loss: 0.4759\n",
            "Epoch 12: val_accuracy did not improve from 0.83961\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m451s\u001b[0m 450ms/step - accuracy: 0.8087 - loss: 0.4759 - val_accuracy: 0.7127 - val_loss: 0.7975 - learning_rate: 1.0000e-05\n",
            "Epoch 13/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 414ms/step - accuracy: 0.8113 - loss: 0.4771\n",
            "Epoch 13: val_accuracy did not improve from 0.83961\n",
            "\n",
            "Epoch 13: ReduceLROnPlateau reducing learning rate to 1.9999999494757505e-06.\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m453s\u001b[0m 452ms/step - accuracy: 0.8113 - loss: 0.4771 - val_accuracy: 0.6283 - val_loss: 0.9203 - learning_rate: 1.0000e-05\n",
            "Epoch 14/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 414ms/step - accuracy: 0.8281 - loss: 0.4403\n",
            "Epoch 14: val_accuracy improved from 0.83961 to 0.85252, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m458s\u001b[0m 457ms/step - accuracy: 0.8281 - loss: 0.4403 - val_accuracy: 0.8525 - val_loss: 0.3721 - learning_rate: 2.0000e-06\n",
            "Epoch 15/15\n",
            "\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 411ms/step - accuracy: 0.8313 - loss: 0.4197\n",
            "Epoch 15: val_accuracy improved from 0.85252 to 0.86122, saving model to /content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\b\r\u001b[1m1002/1002\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m455s\u001b[0m 454ms/step - accuracy: 0.8313 - loss: 0.4197 - val_accuracy: 0.8612 - val_loss: 0.3497 - learning_rate: 2.0000e-06\n",
            "Restoring model weights from the end of the best epoch: 15.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. \n"
          ]
        }
      ],
      "source": [
        "# =========================================\n",
        "# STEP 8b: RESNET152 TRAINING (fine-tuned, 20 epochs)\n",
        "# =========================================\n",
        "from tensorflow.keras.applications import ResNet152\n",
        "from tensorflow.keras.models import Model\n",
        "from tensorflow.keras.layers import Dense, GlobalAveragePooling2D, Dropout\n",
        "from tensorflow.keras.optimizers import Adam\n",
        "from tensorflow.keras.callbacks import EarlyStopping, ReduceLROnPlateau, ModelCheckpoint\n",
        "\n",
        "# Load ResNet152 backbone\n",
        "resnet_base = ResNet152(weights=\"imagenet\", include_top=False, input_shape=(224,224,3))\n",
        "\n",
        "# Freeze most layers, unfreeze last 50 for fine-tuning\n",
        "for layer in resnet_base.layers[:-50]:\n",
        "    layer.trainable = False\n",
        "for layer in resnet_base.layers[-50:]:\n",
        "    layer.trainable = True\n",
        "\n",
        "# Classification head\n",
        "x = resnet_base.output\n",
        "x = GlobalAveragePooling2D()(x)\n",
        "x = Dropout(0.4)(x)\n",
        "x = Dense(512, activation=\"relu\")(x)\n",
        "x = Dropout(0.3)(x)\n",
        "predictions = Dense(3, activation=\"softmax\")(x)\n",
        "\n",
        "resnet_model = Model(inputs=resnet_base.input, outputs=predictions)\n",
        "\n",
        "# Compile with smaller LR\n",
        "resnet_model.compile(\n",
        "    optimizer=Adam(learning_rate=1e-5),\n",
        "    loss=\"categorical_crossentropy\",\n",
        "    metrics=[\"accuracy\"]\n",
        ")\n",
        "\n",
        "# Callbacks\n",
        "checkpoint = ModelCheckpoint(\n",
        "    \"/content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\",\n",
        "    monitor=\"val_accuracy\", save_best_only=True, mode=\"max\", verbose=1\n",
        ")\n",
        "early_stop = EarlyStopping(monitor=\"val_loss\", patience=5, restore_best_weights=True, verbose=1)\n",
        "reduce_lr = ReduceLROnPlateau(monitor=\"val_loss\", factor=0.2, patience=3, min_lr=1e-7, verbose=1)\n",
        "\n",
        "# Train ResNet152\n",
        "history_resnet = resnet_model.fit(\n",
        "    train_gen,\n",
        "    epochs=15,\n",
        "    validation_data=val_gen,\n",
        "    callbacks=[checkpoint, early_stop, reduce_lr]\n",
        ")\n",
        "\n",
        "resnet_model.save(\"/content/drive/MyDrive/chest_xray_project/resnet152_final_ft.h5\")\n"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tensorflow.keras.models import load_model\n",
        "\n",
        "densenet_model = load_model(\"/content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\")\n",
        "resnet_model   = load_model(\"/content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Fa1cohDAaS4w",
        "outputId": "abac26bc-f9ad-48c7-9dc3-f446dcb8cc97"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "Ez6lLS-7yci9",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "outputId": "c567496a-31ee-4e09-8e26-09bfd6bf3b1d"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
            "/usr/local/lib/python3.12/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "📊 Evaluating DenseNet201...\n",
            "\n",
            "\u001b[1m306/306\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m102s\u001b[0m 207ms/step - accuracy: 0.9231 - loss: 0.2213\n",
            "DenseNet201 Test Accuracy: 93.24%\n",
            "DenseNet201 Test Loss: 0.1895\n",
            "\u001b[1m306/306\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m82s\u001b[0m 193ms/step\n",
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "       COVID       1.00      0.91      0.95      3271\n",
            "      NORMAL       0.87      0.97      0.92      3272\n",
            "   PNEUMONIA       0.95      0.91      0.93      3238\n",
            "\n",
            "    accuracy                           0.93      9781\n",
            "   macro avg       0.94      0.93      0.93      9781\n",
            "weighted avg       0.94      0.93      0.93      9781\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAk8AAAHHCAYAAACmzLxGAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAdW5JREFUeJzt3XlcTfn/B/DXrdz220YbSSREGM0gawZl35msUZgx2beY76AyhrEvYxkzUmPsO5lBlmQJw2gsE0ImS9nSSvv5/eHXGcetq6tS8np+H+fxnXs+n/M5n3O7dd/en8/5HJkgCAKIiIiIqFA0SrsDRERERB8SBk9EREREamDwRERERKQGBk9EREREamDwRERERKQGBk9EREREamDwRERERKQGBk9EREREamDwRERERKQGBk9EREUQHR0NNzc3GBkZQSaTYc+ePcXa/t27dyGTyRAUFFSs7X7IXF1d4erqWtrdoI8Ygyf6IAUFBUEmk4mbjo4OrK2t4e7ujuXLlyMlJaW0u6g2V1dXyGQydO3aVaks7wt04cKFarf74sUL+Pn5ISwsTKns6NGj8PLygoODA/T09FC9enUMHz4ccXFx+bZ15swZtGjRAnp6erC0tMTYsWORmpoqqZOamopZs2ahQ4cOMDU1fS9f/Ldv38aXX36J6tWrQ0dHBwqFAs2bN8eyZcvw8uXLEj23p6cnrly5gjlz5mDDhg349NNPS/R879PQoUMhk8mgUCjyfR+jo6PF38F3+Ww+fPgQfn5+iIyMLIbeEr0/WqXdAaKiCAgIgJ2dHbKyshAfH4+wsDCMHz8eixcvxr59+1C/fv3S7qLaQkJCcPHiRTg7OxdLey9evIC/vz8AKP1r3dfXFwkJCejbty9q1qyJO3fu4Mcff0RISAgiIyNhaWkp1o2MjETbtm1Rp04dLF68GPfv38fChQsRHR2NP/74Q6z39OlTBAQEoGrVqmjQoEG+QVtxOnDgAPr27QttbW0MGTIE9erVQ2ZmJk6dOoUpU6bg2rVrWLt2bYmc++XLl4iIiMD//vc/jB49ukTOYWtri5cvX6JChQol0v7baGlp4cWLF9i/fz/69esnKdu4cSN0dHSQnp7+Tm0/fPgQ/v7+qFatGho2bFjo4w4fPvxO5yMqLgye6IPWsWNHyb/0p0+fjmPHjqFLly7o1q0boqKioKurW4o9VE/VqlWRkpICf39/7Nu3r8TPt3jxYrRo0QIaGv8loTt06IDWrVvjxx9/xHfffSfu/+abb2BiYoKwsDAoFAoAQLVq1TBixAgcPnwYbm5uAAArKyvExcXB0tISFy5cwGeffVZi/Y+JiYGHhwdsbW1x7NgxWFlZiWU+Pj64desWDhw4UGLnf/LkCQDA2Ni4xM6Rl1ktLdra2mjevDk2b96sFDxt2rQJnTt3xs6dO99LX168eAE9PT3I5fL3cj6ignDYjsqdzz//HDNmzMC///6L3377TVJ2/fp19OnTB6amptDR0cGnn36qFKTkDQmePn0aEydORKVKlaCvr4+ePXuKX5Z5Lly4AHd3d1SsWBG6urqws7ODl5eXpE5ubi6WLl2KunXrQkdHBxYWFvjyyy/x/Plzpb4bGhpiwoQJ2L9/P/7666+3XmtiYiLGjx8PGxsbaGtrw97eHj/88ANyc3MBvBruq1SpEgDA399fHGLx8/MDALRq1UoSOOXtMzU1RVRUlLgvOTkZoaGhGDRokBg4AcCQIUNgYGCAbdu2ifu0tbUlGauSNH/+fKSmpmLdunWSwCmPvb09xo0bJ77Ozs7G7NmzUaNGDWhra6NatWr45ptvkJGRITmuWrVq6NKlC06dOoXGjRtDR0cH1atXx6+//irW8fPzg62tLQBgypQpkMlkqFatGoBXw115//06Pz8/yGQyyb7Q0FC0aNECxsbGMDAwQK1atfDNN9+I5QXNeTp27BhatmwJfX19GBsbo3v37pKf2evnu3XrFoYOHQpjY2MYGRlh2LBhePHiRcFv7BsGDBiAP/74A4mJieK+P//8E9HR0RgwYIBS/YSEBEyePBlOTk4wMDCAQqFAx44d8ffff4t1wsLCxMB62LBh4mcz7zpdXV1Rr149XLx4Ea1atYKenp74vrw558nT0xM6OjpK1+/u7g4TExM8fPiw0NdKVBgMnqhcGjx4MABpev/atWto2rQpoqKiMG3aNCxatAj6+vro0aMHdu/erdTGmDFj8Pfff2PWrFkYNWoU9u/fLxmaefz4Mdzc3HD37l1MmzYNK1aswMCBA3H27FlJO19++SWmTJkizsEZNmwYNm7cCHd3d2RlZSmdd9y4cTAxMREDnIK8ePECrVu3xm+//YYhQ4Zg+fLlaN68OaZPn46JEycCACpVqoTVq1cDAHr27IkNGzZgw4YN6NWrV4HtpqamIjU1FRUrVhT3XblyBdnZ2UrzeeRyORo2bIhLly6p7GtJ2b9/P6pXr45mzZoVqv7w4cMxc+ZMNGrUCEuWLEHr1q0xd+5ceHh4KNW9desW+vTpg/bt22PRokUwMTHB0KFDce3aNQBAr169sGTJEgBA//79sWHDBixdulSt/l+7dg1dunRBRkYGAgICsGjRInTr1g2nT59WedyRI0fg7u6Ox48fw8/PDxMnTsSZM2fQvHlz3L17V6l+v379kJKSgrlz56Jfv34ICgoSh3ILo1evXpDJZNi1a5e4b9OmTahduzYaNWqkVP/OnTvYs2cPunTpgsWLF2PKlCm4cuUKWrduLQYyderUQUBAAABg5MiR4mezVatWYjvPnj1Dx44d0bBhQyxduhRt2rTJt3/Lli1DpUqV4OnpiZycHADATz/9hMOHD2PFihWwtrYu9LUSFYpA9AFav369AED4888/C6xjZGQkfPLJJ+Lrtm3bCk5OTkJ6erq4Lzc3V2jWrJlQs2ZNpbbbtWsn5ObmivsnTJggaGpqComJiYIgCMLu3bvf2oeTJ08KAISNGzdK9h88eFBpf+vWrYW6desKgiAI/v7+AgDh4sWLgiAIQkxMjABAWLBggVh/9uzZgr6+vnDz5k1J29OmTRM0NTWF2NhYQRAE4cmTJwIAYdasWQX283WzZ88WAAhHjx4V923fvl0AIISHhyvV79u3r2BpaZlvW3/++acAQFi/fn2hzq2OpKQkAYDQvXv3QtWPjIwUAAjDhw+X7J88ebIAQDh27Ji4z9bWVul6Hz9+LGhrawuTJk0S9+X3cxEEQfD09BRsbW2V+jBr1izh9T+7S5YsEQAIT548KbDfeed4/T1s2LChYG5uLjx79kzc9/fffwsaGhrCkCFDlM7n5eUlabNnz56CmZlZged8/Tr09fUFQRCEPn36CG3bthUEQRBycnIES0tLwd/fP9/3ID09XcjJyVG6Dm1tbSEgIEDcp+rz0bp1awGAsGbNmnzLWrduLdl36NAhAYDw3XffCXfu3BEMDAyEHj16vPUaid4FM09UbhkYGIh33SUkJODYsWPiv8CfPn2Kp0+f4tmzZ3B3d0d0dDQePHggOX7kyJGSIZaWLVsiJycH//77L4D/5rmEhITkm0ECgO3bt8PIyAjt27cXz/n06VM4OzvDwMAAx48fz/e4vOyTquzA9u3b0bJlS5iYmEjabteuHXJychAeHl7o9ypPeHg4/P390a9fP3z++efi/rw7rbS1tZWO0dHRKfE72vKTnJwM4NVQZ2H8/vvvACBm5fJMmjQJAJTmRjk6OqJly5bi60qVKqFWrVq4c+fOO/f5TXmfob1794pDrW8TFxeHyMhIDB06FKampuL++vXro3379uJ1vu6rr76SvG7ZsiWePXsmvoeFMWDAAISFhSE+Ph7Hjh1DfHx8vkN2wKvPSd5wcE5ODp49eyYOSRZmOPr1doYNG1aoum5ubvjyyy8REBCAXr16QUdHBz/99FOhz0WkDgZPVG6lpqaKX6y3bt2CIAiYMWMGKlWqJNlmzZoF4NUw3OuqVq0qeW1iYgIA4lyl1q1bo3fv3vD390fFihXRvXt3rF+/XjJ/Jjo6GklJSTA3N1c6b2pqqtI58xgZGWH8+PHYt29fgUNi0dHROHjwoFK77dq1y/d63ub69evo2bMn6tWrh19++UVSljfp/s25QQCQnp5ebJPyX758ifj4eMlWkLy5V4VdluLff/+FhoYG7O3tJfstLS1hbGwsBsV53vz5A68+A/nNVXtXX3zxBZo3b47hw4fDwsICHh4e2LZtm8pAKq+ftWrVUiqrU6cOnj59irS0NMn+t32WC6NTp04wNDTE1q1bsXHjRnz22WdK72We3NxcLFmyBDVr1oS2tjYqVqyISpUq4fLly0hKSir0OStXrqzW5PCFCxfC1NQUkZGRWL58OczNzQt9LJE6eLcdlUv3799HUlKS+Mc978to8uTJcHd3z/eYN78INDU1860nCAKAV3dB7dixA2fPnsX+/ftx6NAheHl5YdGiRTh79iwMDAyQm5sLc3NzbNy4Md+28iZz52fcuHFYsmQJ/P39851Lk5ubi/bt22Pq1Kn5Hu/g4FBg22+6d++euNDj77//rpTNyZuMnd/6T3FxccU2p2Tr1q1KmYa89/tNCoUC1tbWuHr1qlrneHPCdkHe9vN/l3PkzcfJo6uri/DwcBw/fhwHDhzAwYMHsXXrVnz++ec4fPhwgX1QV1GuJY+2tjZ69eqF4OBg3LlzR+WcvO+//x4zZsyAl5cXZs+eDVNTU2hoaGD8+PGFzrABUDsov3TpkviPhitXrqB///5qHU9UWAyeqFzasGEDAIiBUvXq1QEAFSpUEDMzxaVp06Zo2rQp5syZg02bNmHgwIHYsmULhg8fjho1auDIkSNo3ry52l8EedknPz8/eHp6KpXXqFEDqampb72etwULz549g5ubGzIyMnD06NF871qrV68etLS0cOHCBcnt6pmZmYiMjFS6hf1dubu7IzQ0tND1u3TpgrVr1yIiIgIuLi4q69ra2iI3NxfR0dGoU6eOuP/Ro0dITEwU75wrDiYmJpI70/K8md0CAA0NDbRt2xZt27bF4sWL8f333+N///sfjh8/nu/PNq+fN27cUCq7fv06KlasCH19/aJfRD4GDBiAwMBAaGho5DvJPs+OHTvQpk0brFu3TrI/MTFRciNCYQPZwkhLS8OwYcPg6OiIZs2aYf78+ejZs2eJLpVBHy8O21G5c+zYMcyePRt2dnYYOHAgAMDc3Byurq746aef8s2evLkEQWE8f/5c6V/ueQv95Q1v9evXDzk5OZg9e7bS8dnZ2fl+wb5u/PjxMDY2Fu9Kel2/fv0QERGBQ4cOKZUlJiYiOzsbAKCnpyfue1NaWho6deqEBw8e4Pfff0fNmjXz7YeRkRHatWuH3377TTJMtmHDBqSmpqJv374qr6OwrKys0K5dO8mmytSpU6Gvr4/hw4fj0aNHSuW3b9/GsmXLALwadgKglMVbvHgxAKBz587FcAWv1KhRA0lJSbh8+bK4Ly4uTumuzoSEBKVj3/wMvcnKygoNGzZEcHCw5Gd69epVHD58WLzOktCmTRvMnj0bP/74o8rlKDQ1NZV+N7Zv3640rzAvyHvb70Fh+Pr6IjY2FsHBwVi8eDGqVasGT0/PAt9HoqJg5ok+aH/88QeuX7+O7OxsPHr0CMeOHUNoaChsbW2xb98+yeKCK1euRIsWLeDk5IQRI0agevXqePToESIiInD//n3JGjSFERwcjFWrVqFnz56oUaMGUlJS8PPPP0OhUIhfYK1bt8aXX36JuXPnIjIyEm5ubqhQoQKio6Oxfft2LFu2DH369CnwHEZGRhg3bly+E8enTJmCffv2oUuXLhg6dCicnZ2RlpaGK1euYMeOHbh79664/pSjoyO2bt0KBwcHmJqaol69eqhXrx4GDhyI8+fPw8vLC1FRUZJ1cgwMDNCjRw/x9Zw5c9CsWTO0bt0aI0eOxP3797Fo0SK4ubmhQ4cOkr79+OOPSExMFG9L379/P+7fvw/g1RIQRkZGar3XBalRowY2bdqEL774AnXq1JGsMH7mzBls374dQ4cOBQA0aNAAnp6eWLt2LRITE9G6dWucP38ewcHB6NGjR4G3wb8LDw8P+Pr6omfPnhg7dixevHiB1atXw8HBQTJhOiAgAOHh4ejcuTNsbW3x+PFjrFq1ClWqVEGLFi0KbH/BggXo2LEjXFxc4O3tjZcvX2LFihUwMjJ66xIXRaGhoYFvv/32rfW6dOmCgIAADBs2DM2aNcOVK1ewceNGMQOcp0aNGjA2NsaaNWtgaGgIfX19NGnSBHZ2dmr169ixY1i1ahVmzZolLp2wfv16uLq6YsaMGZg/f75a7RG9VSne6Uf0zvKWE8jb5HK5YGlpKbRv315YtmyZkJycnO9xt2/fFoYMGSJYWloKFSpUECpXrix06dJF2LFjh1Lbby5BcPz4cQGAcPz4cUEQBOGvv/4S+vfvL1StWlXQ1tYWzM3NhS5duggXLlxQOu/atWsFZ2dnQVdXVzA0NBScnJyEqVOnCg8fPhTrvL5UweueP38uGBkZ5XtLfEpKijB9+nTB3t5ekMvlQsWKFYVmzZoJCxcuFDIzM8V6Z86cEZydnQW5XC5ZtiDvlvz8tvxutT958qTQrFkzQUdHR6hUqZLg4+OT73utqt2YmBil+kV18+ZNYcSIEUK1atUEuVwuGBoaCs2bNxdWrFghWZoiKytL8Pf3F+zs7IQKFSoINjY2wvTp0yV18vrfuXNnpfO8eYt8QUsVCIIgHD58WKhXr54gl8uFWrVqCb/99pvSUgVHjx4VunfvLlhbWwtyuVywtrYW+vfvL1l+Ir+lCgRBEI4cOSI0b95c0NXVFRQKhdC1a1fhn3/+kdTJO9+bSyHkfcbf9rN4famCghS0VMGkSZMEKysrQVdXV2jevLkQERGR7xIDe/fuFRwdHQUtLS3JdRb0+5BXltdOcnKyYGtrKzRq1EjIysqS1JswYYKgoaEhREREqLwGInXJBEGNGYNEREREHznOeSIiIiJSA4MnIiIiIjUweCIiIiJSA4MnIiIiIjUweCIiIiJSA4MnIiIiIjVwkcyPSG5uLh4+fAhDQ8NifSwCERGVPEEQkJKSAmtra2holFzuIz09HZmZmcXSllwulyxWXF4wePqIPHz4EDY2NqXdDSIiKoJ79+6hSpUqJdJ2eno6dA3NgOwXxdKepaUlYmJiyl0AxeDpI2JoaAgAkDedDJmWdin3hkratS0TSrsL9B7pyjVLuwtUwlJSklG7hq34t7wkZGZmAtkvoO3oCWjKi9ZYTibi/wlGZmYmgyf6cOUN1cm0tCHTKl8fZFJmqFCUdhfoPdJj8PTReC/TLrR0ICti8CTIyu+0agZPREREJCUDUNQgrRxPrWXwRERERFIyjVdbUdsop8rvlRERERGVAGaeiIiISEomK4Zhu/I7bsfgiYiIiKQ4bKdS+b0yIiIiohLAzBMRERFJcdhOJQZPRERE9IZiGLYrx4Nb5ffKiIiIiEoAM09EREQkxWE7lRg8ERERkRTvtlOp/F4ZERERUQlg5omIiIikOGynEoMnIiIikuKwnUrl98qIiIjo3eRlnoq6FdLq1atRv359KBQKKBQKuLi44I8//hDL09PT4ePjAzMzMxgYGKB379549OiRpI3Y2Fh07twZenp6MDc3x5QpU5CdnS2pExYWhkaNGkFbWxv29vYICgp6p7eHwRMRERGVqipVqmDevHm4ePEiLly4gM8//xzdu3fHtWvXAAATJkzA/v37sX37dpw4cQIPHz5Er169xONzcnLQuXNnZGZm4syZMwgODkZQUBBmzpwp1omJiUHnzp3Rpk0bREZGYvz48Rg+fDgOHTqkdn9lgiAIRb9s+hAkJyfDyMgI2i3+B5mWTml3h0rYv/t8S7sL9B7pyTVLuwtUwpKTk1HZ3ARJSUlQKBQldg4jIyNou0yDTEu7SG0J2RnIiJj3zv01NTXFggUL0KdPH1SqVAmbNm1Cnz59AADXr19HnTp1EBERgaZNm+KPP/5Aly5d8PDhQ1hYWAAA1qxZA19fXzx58gRyuRy+vr44cOAArl69Kp7Dw8MDiYmJOHjwoFp9Y+aJiIiIpGSy/+Y9vfP2atguOTlZsmVkZKg8dU5ODrZs2YK0tDS4uLjg4sWLyMrKQrt27cQ6tWvXRtWqVREREQEAiIiIgJOTkxg4AYC7uzuSk5PF7FVERISkjbw6eW2og8ETERERlRgbGxsYGRmJ29y5c/Otd+XKFRgYGEBbWxtfffUVdu/eDUdHR8THx0Mul8PY2FhS38LCAvHx8QCA+Ph4SeCUV55XpqpOcnIyXr58qdY18W47IiIiktKQvdqK2gaAe/fuSYbttLXzHw6sVasWIiMjkZSUhB07dsDT0xMnTpwoWh9KCIMnIiIikirGpQry7qB7G7lcDnt7ewCAs7Mz/vzzTyxbtgxffPEFMjMzkZiYKMk+PXr0CJaWlgAAS0tLnD9/XtJe3t14r9d58w69R48eQaFQQFdXV61L47AdERERlTm5ubnIyMiAs7MzKlSogKNHj4plN27cQGxsLFxcXAAALi4uuHLlCh4/fizWCQ0NhUKhgKOjo1jn9Tby6uS1oQ5mnoiIiEjqPa8wPn36dHTs2BFVq1ZFSkoKNm3ahLCwMBw6dAhGRkbw9vbGxIkTYWpqCoVCgTFjxsDFxQVNmzYFALi5ucHR0RGDBw/G/PnzER8fj2+//RY+Pj7iMOFXX32FH3/8EVOnToWXlxeOHTuGbdu24cCBA2pfGoMnIiIiknrPK4w/fvwYQ4YMQVxcHIyMjFC/fn0cOnQI7du3BwAsWbIEGhoa6N27NzIyMuDu7o5Vq1aJx2tqaiIkJASjRo2Ci4sL9PX14enpiYCAALGOnZ0dDhw4gAkTJmDZsmWoUqUKfvnlF7i7u6t/aVzn6ePBdZ4+Llzn6ePCdZ7Kv/e6zlPrWUX+nhCy05Fxwr9E+1tamHkiIiIiKT4YWCUGT0RERCTFBwOrxOCJiIiIpJh5Uqn8hoVEREREJYCZJyIiIpLisJ1KDJ6IiIhIisN2KpXfsJCIiIioBDDzRERERG8ohmG7cpyfYfBEREREUhy2U6n8hoVEREREJYCZJyIiIpKSyYrhbrvym3li8ERERERSXKpApfJ7ZUREREQlgJknIiIikuKEcZUYPBEREZEUh+1UYvBEREREUsw8qVR+w0IiIiKiEsDMExEREUlx2E4lBk9EREQkxWE7lcpvWEhERERUAph5IiIiIgmZTAYZM08FYvBEREREEgyeVOOwHREREZEamHkiIiIiKdn/b0Vto5xi8EREREQSHLZTjcN2RERERGpg5omIiIgkmHlSjcETERERSTB4Uo3BE5V5EzyaoUuL2qhpY4b0jGyc/+c+/H45ilv3E8Q61axMMHtkWzStZwN5BS0cvXAbvj8ewpPENABA8/q2CFk0ON/2P/dZh0s348TXo/s0hWfnT2BjboRnyS8QuP8iFm06XbIXSfla+dsRHAy/jNv/PoaOdgU416uGaV91RY2q5gCAxOQ0LA48iJN/3sCDR4kwM9aHW0snTPLuCIWBrqSt7X+cxy9bwxBz/wkM9HTQybUBvpvYpzQui9QQ9zgRASv34WjEP3iZkQW7KhWx/NuBaFinKgDg8bNkBKzch7Dz15Gc8hJNP6mBuRP7iJ8RejcMnlTjnKe3iI+Px5gxY1C9enVoa2vDxsYGXbt2xdGjR8U6Z86cQadOnWBiYgIdHR04OTlh8eLFyMnJAQDs3LkTmpqaePDgQb7nqFmzJiZOnAgAcHV1xfjx48UyV1dX8UOsra2NypUro2vXrti1a1fJXXQZ06y+LX7ZdwFuY9ej17SNqKClgV3zBkJPpwIAQE+nAnbNGwABQPcpv6Hj+CDItTSxeXY/8Xf3/D/3UKvfEskW/Psl3I17Lgmc5n3thsEdG2Lm2iNo7L0GA2Zuw8XrD0vhqgkAzkXexpCeLbBnzTj8tvgrZGXnYPCkNXjxMgMA8OhpMh49Tcb/vu6G0OCpWDh9AE6cu46pP2yRtPPz1jAs+Pl3jBrYFqHBvti4ZBRaN65dGpdEakhMfoHOI5dCS0sTW5aMwqnN38B/bA8YGb4KjAVBgKfvL/j34TNsmD8Cx36dChtLU/QZuxJp//8ZISoJzDypcPfuXTRv3hzGxsZYsGABnJyckJWVhUOHDsHHxwfXr1/H7t270a9fPwwbNgzHjx+HsbExjhw5gqlTpyIiIgLbtm1Dt27dYGZmhuDgYHzzzTeSc4SHh+PWrVvw9vYusB8jRoxAQEAAsrOzcf/+fezevRseHh4YOnQo1q5dW9JvQ6nr+81myeuvF+zHrR0T0bCmFc5ciUWTujaoamGE1qN+RsqLzFd15u9DzO7JaNXQDicuxSArOxePn6eJbWhpaqCTiwPW7v1T3OdQ1QxeXZ3RbMRPYlYrNv49XCAV6NeFX0peL/pmABp1m4ErN+6jScMaqFXdCj99N0wst61cEVNGdML4735DdnYOtLQ0kZTyAgt/+R3r5g1HC2cHsW6dGtbv7Tro3SzfcATWFsZYMWOguM/W2kz87zv3nuDC1bs4uWk6ale3AgAsmNoPdTt/i12HL2Jw92bvvc/lBpcqUInBkwpff/01ZDIZzp8/D319fXF/3bp14eXlhbS0NIwYMQLdunWTBDHDhw+HhYUFunXrhm3btuGLL77A4MGDERQUpBQ8BQYGokmTJqhbt26B/dDT04OlpSUAoEqVKmjatClq164NLy8v9OvXD+3atSvmKy/bFPraAIDnKS8BANoVNCEAyMjKEeukZ2UjVxDQtJ4NTlyKUWqjo4sDTBW62HTob3Ffh6YOuBuXCPemNbGj22eQyYCwSzGY9fNRJKakl+xFUaGkpL76mRsr9Aqsk5yWDgM9HWhpaQIATv55A4Ig4NGTJHw+aC7SXmbAuV41fPt1d1hbmLyXftO7OXTyCto0rQOvbwIRcekWLCsZwatXSwzu8SooysjMBgBoy//7KtPQ0IC8ghbO/X2HwVMRcNhONQ7bFSAhIQEHDx6Ej4+PJHDKY2xsjMOHD+PZs2eYPHmyUnnXrl3h4OCAzZtfZU28vb0RHR2N8PBwsU5qaip27NihMutUEE9PT5iYmHxUw3fAq9/FuaPccPbqPUTdfQIA+DPqAV6kZ8Jv+OfQ1daCnk4FzB7ZDlqaGrA0Nci3ncEdG+LYxTt4+DRF3FfNyhg2Fkbo3qoORs3fi68X7EfDmlYInsF5MWVBbm4u/FfswadOdqj1/1mGNyUkpmJF8GH07+Yi7ot9+Ay5uQJW/nYEs8b2xOqAoUhMfoFBk9YgMyv7fXWf3sG/D58haNcpVLephK1LR2FYrxb4ZslObDlwDgBQs5oFqlia4LvV+5GY/AKZWdlY/msoHj5OxKNnyaXceyrPGDwV4NatWxAEAbVrFzwv4ubNmwCAOnXq5Fteu3ZtsY6joyOaNm2KwMBAsXzbtm0QBAEeHh5q909DQwMODg64e/dugXUyMjKQnJws2T50C8d0RJ1qleA957+g8VnSCwydvQsdmjrg/j5f/LtnCowMdBB5Mw65gqDUhnVFQ3zuXB0b/oiU7JfJZNCRa2HUD/sQcfUeTl/+F2MWhaDVJ9VgX8W0pC+N3mLGkp24GROHH2cNybc8JS0dw3x/hn01C0wY1kHcnysIyMrOgd/YnmjduDYa1a2GFbOGIOb+E0RcuvW+uk/vIDdXQP1aVfDtqK6oX8sGQ3o0x6BuLgje/eoGjgpamgia543bsU9Q020aqrpOxqm/otHWxREa5Tjr8T7IZP9ln959K+2rKDkctiuAkM+XblHrenl5YcKECVixYgUMDQ0RGBiIvn37wtDQ8J37qCqtOnfuXPj7+79T22XR/NHucG9SE50m/SrJGAHA8Yt30MhzJUwVusjOyUVyWgaubx2Pu2HPldoZ4N4ACckv8UfETcn+RwmpyMrOwe0H/93FdzP2KQCgirmR5O4+er9mLNmJo2f+wbYVo2FlbqxUnvoiHUMm/wR9PW2s/c4LFf5/yA4AzM0UAICa1SzFfWbGBjA10sfDR8qfDyo7LCoq4PDazw0AHKpZICTsv+H2BrWrImyDL5JTXyIzKxsVTQzh7rUIDerYvO/ulisyFMOwXTme9MTMUwFq1qwJmUyG69evF1jHweHV5NOoqKh8y6OiosQ6AMQM07Zt2xAdHY3Tp0+/05AdAOTk5CA6Ohp2dnYF1pk+fTqSkpLE7d69e+90rrJg/mh3dG5eC92mbkBsfGKB9RKSXyI5LQMtG1ZDJWN9pQAJAAa6N8CWI5eRnZMr2X/u2n1U0NJENav/5sHkZZzuPUoqngshtQiCgBlLduLQySvYvPRrVH1tsnCelLR0DJq0BvIKmlg3dzh0tCtIyj91evU7cvveY3FfYnIaEpLSUJlznsq0xvWr41bsY8m+2/eewMZS+eemMNBFRRND3I59jMjrsejYyul9dZM+QgyeCmBqagp3d3esXLkSaWlpSuWJiYlwc3ODqakpFi1apFS+b98+REdHo3///uI+Q0ND9O3bF4GBgVi/fj0cHBzQsmXLd+pfcHAwnj9/jt69exdYR1tbGwqFQrJ9iBaO6YB+bZ0wYu4epL7IhLmJPsxN9KHz2iTRAe4N8GmdyqhmZYJ+beshaEYvrNp1Tilb1OqTaqhmZaI0ZAcAYX/dQeTNOPw4uQucaligQU1LLB7fCccu3pFko+j9+XbJTuwJvYDlMwdBX08bj58l4/GzZKRnvLqrMiUtHYMnrcHLl5mY7+uBlLR0sU7O/wfH1W3M4daiHvyX78aFKzG4cScOE7/fhBpVzeHSqGZpXh69xVcerrh49S6WBB3GnXtPsPPQBWzYcwZevf/7u7n36CWcvhiNuw+e4o/wy+g7dhU6tqqPNk3yn05BhVP0IbviyFyVXRy2U2HlypVo3rw5GjdujICAANSvXx/Z2dkIDQ3F6tWrERUVhZ9++gkeHh4YOXIkRo8eDYVCgaNHj2LKlCno06cP+vXrJ2nT29sbLVu2RFRUFHx9fQvVjxcvXiA+Pl6yVMGSJUswatQotGnTpiQuvUzx7vYpAODAIulcl68X7MPmw5cBADWrmGKmVxuYGOoi9lEiFm06jVU7zym1NbhDQ5y7dg/R954plQkC0H/mVvzg444Di4fgRXoWjvx5G9/+FFoCV0WF8dueV3Nbvhi7UrJ/4fT+6NuxMa7evI9L//wLAGjVf46kzqmtM2Bj9SpzuPh/AxGwYg+G+f4MDQ0ZmjSogV8XfCkZ3qOy5xNHWwT/MBzfrd6PRYEHUdXKDN+N74U+HT4T6zx6moyZy3bjSUIKLCoq0K9jY0zyci/FXpcTXKpAJZmgzuSej1BcXBzmzJmDkJAQxMXFoVKlSnB2dsaECRPg6uoKADh58iTmzJmDiIgIpKeno2bNmhg2bBjGjx8PTU3lP861a9fGrVu3cO/ePVhZSe8acnV1RcOGDbF06VLx9YkTJwAAcrkcZmZmcHZ2hpeXF3r27KnWtSQnJ8PIyAjaLf4HmZaO+m8GfVD+3Ve44JzKBz05A8HyLjk5GZXNTZCUlFRiIwl53xMmHr9AJi94SZDCEDJf4PmW4SXa39LC4OkjwuDp48Lg6ePC4Kn8e6/BU/910Chi8JSb+QLPN3uXy+CJw3ZEREQkURxzljjniYiIiD4aDJ5U4912RERERGpg5omIiIikeLedSgyeiIiISILDdqpx2I6IiIhIDcw8ERERkQQzT6ox80REREQS7/vxLHPnzsVnn30GQ0NDmJubo0ePHrhx44akjqurq1L7X331laRObGwsOnfuDD09PZibm2PKlCnIzs6W1AkLC0OjRo2gra0Ne3t7BAUFqf3+MHgiIiKiUnXixAn4+Pjg7NmzCA0NRVZWFtzc3JSeLTtixAjExcWJ2/z588WynJwcdO7cGZmZmThz5gyCg4MRFBSEmTNninViYmLQuXNntGnTBpGRkRg/fjyGDx+OQ4cOqdVfDtsRERGRxPsetjt48KDkdVBQEMzNzXHx4kW0atVK3K+npwdLS8t82zh8+DD++ecfHDlyBBYWFmjYsCFmz54NX19f+Pn5QS6XY82aNbCzs8OiRYsAAHXq1MGpU6ewZMkSuLsX/pmIzDwRERGRlKyYNrx65MvrW0ZGxltPn5SUBAAwNTWV7N+4cSMqVqyIevXqYfr06Xjx4oVYFhERAScnJ1hYWIj73N3dkZycjGvXrol12rVrJ2nT3d0dERERhXlXRMw8ERERUYmxsbGRvJ41axb8/PwKrJ+bm4vx48ejefPmqFevnrh/wIABsLW1hbW1NS5fvgxfX1/cuHEDu3btAgDEx8dLAicA4uv4+HiVdZKTk/Hy5Uvo6uoW6poYPBEREZFEcQ7b3bt3T/JgYG1tbZXH+fj44OrVqzh16pRk/8iRI8X/dnJygpWVFdq2bYvbt2+jRo0aReqrujhsR0RERBLFebedQqGQbKqCp9GjRyMkJATHjx9HlSpVVPaxSZMmAIBbt24BACwtLfHo0SNJnbzXefOkCqqjUCgKnXUCGDwRERHRG973UgWCIGD06NHYvXs3jh07Bjs7u7ceExkZCQCwsrICALi4uODKlSt4/PixWCc0NBQKhQKOjo5inaNHj0raCQ0NhYuLS6H7CjB4IiIiolLm4+OD3377DZs2bYKhoSHi4+MRHx+Ply9fAgBu376N2bNn4+LFi7h79y727duHIUOGoFWrVqhfvz4AwM3NDY6Ojhg8eDD+/vtvHDp0CN9++y18fHzEbNdXX32FO3fuYOrUqbh+/TpWrVqFbdu2YcKECWr1l8ETERERSRXj3XaFsXr1aiQlJcHV1RVWVlbitnXrVgCAXC7HkSNH4Obmhtq1a2PSpEno3bs39u/fL7ahqamJkJAQaGpqwsXFBYMGDcKQIUMQEBAg1rGzs8OBAwcQGhqKBg0aYNGiRfjll1/UWqYA4IRxIiIiesP7XudJEASV5TY2Njhx4sRb27G1tcXvv/+uso6rqysuXbpU6L7lh5knIiIiIjUw80REREQSfDCwagyeiIiISEKGYgie1Jn09IHhsB0RERGRGph5IiIiIgkO26nG4ImIiIik1FxqoMA2yikO2xERERGpgZknIiIikuCwnWoMnoiIiEiCwZNqDJ6IiIhIQiZ7tRW1jfKKc56IiIiI1MDMExEREUm8yjwVddiumDpTBjF4IiIiIqliGLbjUgVEREREBICZJyIiInoD77ZTjcETERERSfBuO9U4bEdERESkBmaeiIiISEJDQwYNjaKljoQiHl+WMXgiIiIiCQ7bqcZhOyIiIiI1MPNEREREErzbTjUGT0RERCTBYTvVGDwRERGRBDNPqnHOExEREZEamHkiIiIiCWaeVGPwRERERBKc86Qah+2IiIiI1MDMExEREUnIUAzDdii/qScGT0RERCTBYTvVOGxHREREpAZmnoiIiEiCd9upxuCJiIiIJDhspxqH7YiIiIjUwMwTERERSXDYTjUGT0RERCTBYTvVGDwRERGRBDNPqnHOExEREZEamHn6CMXunQqFQlHa3aASZvLZ6NLuAr1HjyOWl3YXqIQJwns8WTEM25XjBcYZPBEREZEUh+1U47AdERERkRqYeSIiIiIJ3m2nGoMnIiIikuCwnWoctiMiIiJSAzNPREREJMFhO9UYPBEREZEEh+1U47AdERERkRqYeSIiIiIJZp5UY+aJiIiIJPLmPBV1K6y5c+fis88+g6GhIczNzdGjRw/cuHFDUic9PR0+Pj4wMzODgYEBevfujUePHknqxMbGonPnztDT04O5uTmmTJmC7OxsSZ2wsDA0atQI2trasLe3R1BQkNrvD4MnIiIiksjLPBV1K6wTJ07Ax8cHZ8+eRWhoKLKysuDm5oa0tDSxzoQJE7B//35s374dJ06cwMOHD9GrVy+xPCcnB507d0ZmZibOnDmD4OBgBAUFYebMmWKdmJgYdO7cGW3atEFkZCTGjx+P4cOH49ChQ+q9P4LwXp+WQ6UoOTkZRkZGePQsic+2+wjw2XYfFz7brvxLTk5GFQsTJCWV3N/wvO+J5nMPQ0tHv0htZaen4fR0t3fq75MnT2Bubo4TJ06gVatWSEpKQqVKlbBp0yb06dMHAHD9+nXUqVMHERERaNq0Kf744w906dIFDx8+hIWFBQBgzZo18PX1xZMnTyCXy+Hr64sDBw7g6tWr4rk8PDyQmJiIgwcPFrp/zDwRERGRxPsetntTUlISAMDU1BQAcPHiRWRlZaFdu3Zindq1a6Nq1aqIiIgAAERERMDJyUkMnADA3d0dycnJuHbtmljn9Tby6uS1UVicME5EREQSxTlhPDk5WbJfW1sb2traBR6Xm5uL8ePHo3nz5qhXrx4AID4+HnK5HMbGxpK6FhYWiI+PF+u8HjjlleeVqaqTnJyMly9fQldXt1DXxswTERERlRgbGxsYGRmJ29y5c1XW9/HxwdWrV7Fly5b31EP1MfNEREREEjIUwwrj////9+7dk8x5UpV1Gj16NEJCQhAeHo4qVaqI+y0tLZGZmYnExERJ9unRo0ewtLQU65w/f17SXt7deK/XefMOvUePHkGhUBQ66wQw80RERERv0JDJimUDAIVCIdnyC54EQcDo0aOxe/duHDt2DHZ2dpJyZ2dnVKhQAUePHhX33bhxA7GxsXBxcQEAuLi44MqVK3j8+LFYJzQ0FAqFAo6OjmKd19vIq5PXRmEx80RERESlysfHB5s2bcLevXthaGgozlEyMjKCrq4ujIyM4O3tjYkTJ8LU1BQKhQJjxoyBi4sLmjZtCgBwc3ODo6MjBg8ejPnz5yM+Ph7ffvstfHx8xIDtq6++wo8//oipU6fCy8sLx44dw7Zt23DgwAG1+svgiYiIiCTe94OBV69eDQBwdXWV7F+/fj2GDh0KAFiyZAk0NDTQu3dvZGRkwN3dHatWrRLrampqIiQkBKNGjYKLiwv09fXh6emJgIAAsY6dnR0OHDiACRMmYNmyZahSpQp++eUXuLu7q3VtDJ6IiIhI4n0/nqUwS07q6Ohg5cqVWLlyZYF1bG1t8fvvv6tsx9XVFZcuXSp03/LD4ImIiIgkNGSvtqK2UV5xwjgRERGRGph5IiIiIimZesNuBbVRXjF4IiIiIon3PWH8Q8NhOyIiIiI1MPNEREREErL//19R2yivGDwRERGRBO+2U43DdkRERERqYOaJiIiIJN73IpkfmkIFT/v27St0g926dXvnzhAREVHp4912qhUqeOrRo0ehGpPJZMjJySlKf4iIiIjKtEIFT7m5uSXdDyIiIiojNGQyaBQxdVTU48uyIs15Sk9Ph46OTnH1hYiIiMoADtuppvbddjk5OZg9ezYqV64MAwMD3LlzBwAwY8YMrFu3rtg7SERERO9X3oTxom7lldrB05w5cxAUFIT58+dDLpeL++vVq4dffvmlWDtHREREVNaoHTz9+uuvWLt2LQYOHAhNTU1xf4MGDXD9+vVi7RwRERG9f3nDdkXdyiu15zw9ePAA9vb2Svtzc3ORlZVVLJ0iIiKi0sMJ46qpnXlydHTEyZMnlfbv2LEDn3zySbF0ioiIiKisUjvzNHPmTHh6euLBgwfIzc3Frl27cOPGDfz6668ICQkpiT4SERHReyT7/62obZRXameeunfvjv379+PIkSPQ19fHzJkzERUVhf3796N9+/Yl0UciIiJ6j3i3nWrvtM5Ty5YtERoaWtx9ISIiIirz3nmRzAsXLiAqKgrAq3lQzs7OxdYpIiIiKj0asldbUdsor9QOnu7fv4/+/fvj9OnTMDY2BgAkJiaiWbNm2LJlC6pUqVLcfSQiIqL3qDiG3crzsJ3ac56GDx+OrKwsREVFISEhAQkJCYiKikJubi6GDx9eEn0kIiIiKjPUzjydOHECZ86cQa1atcR9tWrVwooVK9CyZcti7RwRERGVjnKcOCoytYMnGxubfBfDzMnJgbW1dbF0ioiIiEoPh+1UU3vYbsGCBRgzZgwuXLgg7rtw4QLGjRuHhQsXFmvniIiI6P3LmzBe1K28KlTmycTERBJBpqWloUmTJtDSenV4dnY2tLS04OXlhR49epRIR4mIiIjKgkIFT0uXLi3hbhAREVFZwWE71QoVPHl6epZ0P4iIiKiM4ONZVHvnRTIBID09HZmZmZJ9CoWiSB0iIiIiKsvUDp7S0tLg6+uLbdu24dmzZ0rlOTk5xdIxIiIiKh0aMhk0ijjsVtTjyzK177abOnUqjh07htWrV0NbWxu//PIL/P39YW1tjV9//bUk+khERETvkUxWPFt5pXbmaf/+/fj111/h6uqKYcOGoWXLlrC3t4etrS02btyIgQMHlkQ/iYiIiMoEtTNPCQkJqF69OoBX85sSEhIAAC1atEB4eHjx9o6IiIjeu7y77Yq6lVdqZ56qV6+OmJgYVK1aFbVr18a2bdvQuHFj7N+/X3xQMFFpW7fjJAJ3nsS9uFfBfe3qlpji3RHtm9ct5Z6RKl69W8Crd0vYWJkCAK7ficeCdX/gyJl/AACePZujj/unqF+rChQGurBtMwXJqS8lbdSoao6AsT3QpEF1VNDSxD+3HmLOmhCcuhgNAKhXszLGe7ZH04Y1YGqkj9i4BKzfdQo/bQl7r9dKb5eTk4sFv/yBHYf+xONnKbCopIBHpyaYOMxd/GI2dxmb77Ezfbpj9KC277O75UpxDLuV49hJ/eBp2LBh+Pvvv9G6dWtMmzYNXbt2xY8//oisrCwsXry4JPpIpDZrc2PMGt0dNWwqQRAEbD5wDgMnr8WJ36ahTg2r0u4eFeDh40T4/7gXt+89gUwmQ//OTbBx4Ui0HjQP1+/EQ1enAo5G/IOjEf9g1uju+baxZfFXuHPvMbqPWo6XGVkY1b8Ntiz5Co16+uHxsxQ0qG2DJ89TMHJmMB48eo4m9atjyTf9kZuTi5+3M3telqzYcARBu09hxYxBqFXdEn9HxWLsnE1QGOhiRL/WAIArId9JjjkW8Q/Gf78ZXdo0KI0u00dC7WG7CRMmYOzYV5F+u3btcP36dWzatAmXLl3CuHHjir2DRTF06FDIZDLMmzdPsn/Pnj2SdGJOTg6WLFkCJycn6OjowMTEBB07dsTp06clxwUFBYmpSA0NDVhZWeGLL75AbGyspJ6rq2u+5wWAzp07QyaTwc/PT6ls8+bN0NTUhI+Pj1JZWFgYZDIZEhMT1XgHPl4dWznBrXld1KhqDntbC8z4uhv09bRx4WpMaXeNVDh48ipCz/yDO/ee4HbsY3y3ej/SXmTg03p2AIA1m8OwNDgUf165m+/xpkb6sLc1x9LgUFy79RB37j2B/497oa+rjTo1Xj17c+P+s5i+aCfO/HUL/z54hm1//IlN+8/yy7YM+vNKDDq0dEL75nVR1coMXT//BK6Na+Ovf/4V61iYKSTbHyevoEWjmqhWuWIp9vzDl3e3XVG38krt4OlNtra26NWrF+rXr18c/Sl2Ojo6+OGHH/D8+fN8ywVBgIeHBwICAjBu3DhERUUhLCwMNjY2cHV1xZ49eyT1FQoF4uLi8ODBA+zcuRM3btxA3759ldq1sbFBUFCQZN+DBw9w9OhRWFnln/lYt24dpk6dis2bNyM9Pf2drpeU5eTkYufhC3jxMhOfOdmVdneokDQ0ZOjV3hl6unL8eaVwQW9CUhpu3o3HF50bQ09HDk1NDQzt1QKPnyUjMiq2wOMUBjp4nvyiuLpOxeQzJzucvHATt2MfAwCuRj/Aub/voK1LnXzrP05IxpHT1zCga9P32c1yiXfbqVaoYbvly5cXusG8rFRZ0a5dO9y6dQtz587F/Pnzlcq3bduGHTt2YN++fejatau4f+3atXj27BmGDx+O9u3bQ19fH8CrSXSWlpYAACsrK3h7e2Ps2LFITk6WLBDapUsXbNu2DadPn0bz5s0BAMHBwXBzc1PKVAFATEwMzpw5g507d+L48ePYtWsXBgwYUKzvxcfm2q0HcPdahPTMbOjramPDghGoXZ1DdmWdYw1rHAqcBB25FtJeZmDwlJ9xIya+0Mf39PkRvy0YiXsnFiI3V8CT56noM3YVklJe5lu/cX079GzvjC/Gry6uS6BiMnZIO6S8SEczjznQ1JAhJ1fAN192Rh/3z/Ktv/X38zDQ00FnV2YRi4qPZ1GtUMHTkiVLCtWYTCYrc8GTpqYmvv/+ewwYMABjx45FlSpVJOWbNm2Cg4ODJHDKM2nSJOzatQuhoaH5PvD48ePH2L17NzQ1NaGpqSkpk8vlGDhwINavXy8GT0FBQZg/f36+Q3br169H586dYWRkhEGDBmHdunVFDp4yMjKQkZEhvk5OTi5Sex+amrYWCN84HcmpL7H36CV87bcBIT+NYwBVxkX/+witBs6FwkAX3dt+glV+g9Hly2WFDqAWTO2Hp89T0GnEUrzMyMSQHs2wefGXaOu5AI+eSX8H6tSwwsaFI/HDz7/j+LnrJXE5VAR7j17CzkMXsMZ/CGrZWeFq9H3MWLoLFhWN4NG5iVL9zfvPorf7p9DRrlAKvaWPSaGG7WJiYgq13blzp6T7+0569uyJhg0bYtasWUplN2/eRJ06+aeA8/bfvHlT3JeUlAQDAwPo6+vDwsICx48fh4+Pj5iZep2Xlxe2bduGtLQ0hIeHIykpCV26dFGql5ubi6CgIAwaNAgA4OHhgVOnTiEmpmjzc+bOnQsjIyNxs7GxKVJ7Hxp5BS1Ut6mEhnWqYtbo7qhXszLW8I6qMi8rOwcx95/i7+v3ELByH65GP8BXHq6FOrbVZw5wb1EP3v9bj3OX7+DyjfuY/MM2pGdkoX8X6ZdtLTtL7Fk5BsG7z2BR4KESuBIqKv8f92LM4Hbo2d4ZjvbW6NexMb70aIPlv4Yq1T0beRu3Yh9jYDeXUuhp+aNRTFt5VZ6vTeKHH35AcHAwoqKilMoEQSh0O4aGhoiMjMSFCxewaNEiNGrUCHPmzMm3boMGDVCzZk3s2LEDgYGBGDx4MLS0lJN9oaGhSEtLQ6dOnQAAFStWRPv27REYGFjofuVn+vTpSEpKErd79+4Vqb0PXa4gIDMzu7S7QWrSkMkglxfuxmA9HTmAV/8geV2uIEgmr9aubol9q8diy4Fz+G71/uLrLBWrl+mZ0NCQDv1oasiQm8/f7I37I9Cgtg3q1az8vrpXrnGdJ9WK9GDgD0mrVq3g7u6O6dOnY+jQoeJ+BweHfAMqAOJ+BwcHcZ+Ghgbs7e0BvMpM3b59G6NGjcKGDRvybcPLywsrV67EP//8g/Pnz+dbZ926dUhISICurq64Lzc3F5cvX4a/vz80NN4txtXW1oa2tvY7Hfuh8/9xL9o1qwsbSxOkvEjHjoMXcOpiNHau+Lq0u0YqzPTphiNnruFe/HMY6umgT4dP0cK5JnqPWQUAMDczhLmZAtVtXt1JVdfeGikv0nE//jkSk1/g/OUYJKa8wCq/IVjwyx94mZEFzx7NYGtthsOnrwF4NVS3d9VYHDsbhZWbjsHczBAAkJMj4FliaulcOOXLrUU9LA06jCoWpqhV3RJXbtzHmi3H0b+LdEJ4StpL7D8WCb8xPUqno/TR+WiCJwCYN28eGjZsiFq1aon7PDw8MGDAAOzfv19p3tOiRYtgZmaG9u3bF9jmtGnTUKNGDUyYMAGNGjVSKh8wYAAmT56MBg0awNHRUan82bNn2Lt3L7Zs2YK6df9bwDEnJwctWrTA4cOH0aFDh3e53I/a0+epGOX3Kx49TYbCQAd17Stj54qv0aZJ/kO0VDZUNDHAar8hsKioQHJqOq7deoDeY1Yh7Pyr+UjDerXEtJGdxPq//zwBAPC1/wZsDjmHhKQ09Bm7Ct+O6oq9q8ZCS0sD1+/EY+Dktbga/QAA0O3zT1DJ1BBfdGqMLzo1FtuKffgMDborD+1T6Zk7sQ/mrT0A34Xb8DQhFRaVFBjSozkmeUn/Ju4O/QuCIKCXm3Mp9bT8kckAjSImjspx4unjCp6cnJwwcOBAyd2DHh4e2L59Ozw9PbFgwQK0bdsWycnJWLlyJfbt24ft27fnO58pj42NDXr27ImZM2ciJCREqdzExARxcXGoUCH/CYwbNmyAmZkZ+vXrp5Ti7NSpE9atWycJnq5cuQJDQ0PxtUwmQ4MGvLPkTStm8BmLH6Kx321SWf7Dz7/jh59/V1knMioWfcauLFIbVDYY6Ovguwm98d2E3irrDenRHEN6NH9Pvfo4aBRD8FTU48uyjyp4AoCAgABs3bpVfC2TybBt2zYsXboUS5Yswddffw0dHR24uLggLCxMvFNOlQkTJsDFxQXnz59H48aNlcpVPbYmMDAQPXv2zHdsuHfv3hg8eDCePn0q7mvVqpWkjqamJrKzOY+HiIjofZEJ6syW/n8nT57ETz/9hNu3b2PHjh2oXLkyNmzYADs7O7Ro0aIk+knFIDk5GUZGRnj0LEmyJhWVTyafjS7tLtB79Dii8Ovx0YcpOTkZVSxMkJRUcn/D874nfLZcgLaeQZHayniRipUenxa6v+Hh4ViwYAEuXryIuLg47N69W7JM0NChQxEcHCw5xt3dHQcPHhRfJyQkYMyYMdi/fz80NDTQu3dvLFu2DAYG/13L5cuX4ePjgz///BOVKlXCmDFjMHXqVLWuTe2ZyDt37oS7uzt0dXVx6dIlcR2hpKQkfP/99+o2R0RERGVM3rBdUTd1pKWloUGDBli5suBh9w4dOiAuLk7cNm/eLCkfOHAgrl27htDQUISEhCA8PBwjR44Uy5OTk+Hm5gZbW1tcvHgRCxYsgJ+fH9auXatWX9Uetvvuu++wZs0aDBkyBFu2bBH3N2/eHN99952KI4mIiIjy17FjR3Ts2FFlHW1tbfEpH2+KiorCwYMH8eeff+LTTz8FAKxYsQKdOnXCwoULYW1tjY0bNyIzMxOBgYGQy+WoW7cuIiMjsXjxYkmQ9TZqZ55u3LihNO8GAIyMjPjQWiIionKgrD7bLiwsDObm5qhVqxZGjRqFZ8+eiWUREREwNjYWAyfg1SPaNDQ0cO7cObFOq1atIJfLxTru7u64ceNGgc/AzY/amSdLS0vcunUL1apVk+w/deoUqlevrm5zREREVMZoyGSShWXftQ1A+dFg77oGYYcOHdCrVy/Y2dnh9u3b+Oabb9CxY0dERERAU1MT8fHxMDc3lxyjpaUFU1NTxMe/erxTfHw87OykD4i3sLAQy0xMTArVF7WDpxEjRmDcuHEIDAyETCbDw4cPERERgcmTJ2PGjBnqNkdERERlTHE8XiXv+DcfDTZr1qx8n/H6Nh4eHuJ/Ozk5oX79+qhRowbCwsLQtm3bIvRUfWoHT9OmTUNubi7atm2LFy9eoFWrVtDW1sbkyZMxZsyYkugjERERfaDu3bsnuduuuJ58Ub16dVSsWBG3bt1C27ZtYWlpicePH0vqZGdnIyEhQZwnZWlpiUePHknq5L0uaC5VftQOLGUyGf73v/8hISEBV69exdmzZ/HkyRPMnj1b3aaIiIioDCrOOU8KhUKyFVfwdP/+fTx79gxWVlYAABcXFyQmJuLixYtinWPHjiE3NxdNmjQR64SHhyMrK0usExoailq1ahV6yA4oQlZOLpfD0dERjRs3lqyfQERERB82DcjEeU/vvEG9OVOpqamIjIxEZGQkACAmJgaRkZGIjY1FamoqpkyZgrNnz+Lu3bs4evQounfvDnt7e7i7uwN49bzZDh06YMSIETh//jxOnz6N0aNHw8PDA9bW1gBePTJNLpfD29sb165dw9atW7Fs2TJMnDhRrb6qPWzXpk0blU9KPnbsmLpNEhER0UfuwoULaNOmjfg6L6Dx9PTE6tWrcfnyZQQHByMxMRHW1tZwc3PD7NmzJZmsjRs3YvTo0Wjbtq24SObrj2QzMjLC4cOH4ePjA2dnZ1SsWBEzZ85Ua5kC4B2Cp4YNG0peZ2VlITIyElevXoWnp6e6zREREVEZUxxLDah7vKurK1Q99OTQoUNvbcPU1BSbNql+Rmb9+vVx8uRJ9Tr3BrWDpyVLluS738/PD6mpqUXqDBEREZU+PhhYtaLeiSgaNGgQAgMDi6s5IiIiojJJ7cxTQSIiIqCjo1NczREREVEpkclQ5EUyS2KF8bJC7eCpV69ekteCICAuLg4XLlzgIplERETlQGnMefqQqB08GRkZSV5raGigVq1aCAgIgJubW7F1jIiIiKgsUit4ysnJwbBhw+Dk5KTWYlJERET04eCEcdXUmjCuqakJNzc3JCYmllB3iIiIqLTJiul/5ZXad9vVq1cPd+7cKYm+EBERURmQl3kq6lZeqR08fffdd5g8eTJCQkIQFxeH5ORkyUZERERUnhV6zlNAQAAmTZqETp06AQC6desmeUyLIAiQyWTIyckp/l4SERHRe8M5T6oVOnjy9/fHV199hePHj5dkf4iIiKiUyWQylc+xLWwb5VWhg6e85820bt26xDpDREREVNaptVRBeY4iiYiI6BUO26mmVvDk4ODw1gAqISGhSB0iIiKi0sUVxlVTK3jy9/dXWmGciIiI6GOiVvDk4eEBc3PzkuoLERERlQEaMlmRHwxc1OPLskIHT5zvRERE9HHgnCfVCr1IZt7ddkREREQfs0JnnnJzc0uyH0RERFRWFMOE8XL8aDv15jwRERFR+acBGTSKGP0U9fiyjMETERERSXCpAtXUfjAwERER0ceMmSciIiKS4N12qjF4IiIiIgmu86Qah+2IiIiI1MDMExEREUlwwrhqDJ6IiIhIQgPFMGxXjpcq4LAdERERkRqYeSIiIiIJDtupxuCJiIiIJDRQ9KGp8jy0VZ6vjYiIiKjYMfNEREREEjKZDLIijrsV9fiyjMETERERScj+fytqG+UVgyciIiKS4ArjqnHOExEREZEamHkiIiIiJeU3b1R0DJ6IiIhIgus8qcZhOyIiIiI1MPNEREREElyqQDUGT0RERCTBFcZVK8/XRkRERFTsmHkiIiIiCQ7bqcbgiYiIiCS4wrhqHLYjIiIiUgMzT0Tl1J2wxaXdBXqPzDvNK+0uUAkTstPf27k4bKcagyciIiKS4N12qjF4IiIiIglmnlQrz4EhERERUbFj8EREREQSsmLa1BEeHo6uXbvC2toaMpkMe/bskZQLgoCZM2fCysoKurq6aNeuHaKjoyV1EhISMHDgQCgUChgbG8Pb2xupqamSOpcvX0bLli2ho6MDGxsbzJ8/X82eMngiIiKiN+Q9GLiomzrS0tLQoEEDrFy5Mt/y+fPnY/ny5VizZg3OnTsHfX19uLu7Iz39v4n0AwcOxLVr1xAaGoqQkBCEh4dj5MiRYnlycjLc3Nxga2uLixcvYsGCBfDz88PatWvV6ivnPBEREVGp69ixIzp27JhvmSAIWLp0Kb799lt0794dAPDrr7/CwsICe/bsgYeHB6KionDw4EH8+eef+PTTTwEAK1asQKdOnbBw4UJYW1tj48aNyMzMRGBgIORyOerWrYvIyEgsXrxYEmS9DTNPREREJKEBWbFswKtsz+tbRkaG2v2JiYlBfHw82rVrJ+4zMjJCkyZNEBERAQCIiIiAsbGxGDgBQLt27aChoYFz586JdVq1agW5XC7WcXd3x40bN/D8+XM13h8iIiKi1xTnsJ2NjQ2MjIzEbe7cuWr3Jz4+HgBgYWEh2W9hYSGWxcfHw9zcXFKupaUFU1NTSZ382nj9HIXBYTsiIiIqMffu3YNCoRBfa2trl2JvigczT0RERCQhK6b/AYBCoZBs7xI8WVpaAgAePXok2f/o0SOxzNLSEo8fP5aUZ2dnIyEhQVInvzZeP0dhMHgiIiIiidK4204VOzs7WFpa4ujRo+K+5ORknDt3Di4uLgAAFxcXJCYm4uLFi2KdY8eOITc3F02aNBHrhIeHIysrS6wTGhqKWrVqwcTEpND9YfBEREREpS41NRWRkZGIjIwE8GqSeGRkJGJjYyGTyTB+/Hh899132LdvH65cuYIhQ4bA2toaPXr0AADUqVMHHTp0wIgRI3D+/HmcPn0ao0ePhoeHB6ytrQEAAwYMgFwuh7e3N65du4atW7di2bJlmDhxolp95ZwnIiIikpC9drdcUdpQx4ULF9CmTRvxdV5A4+npiaCgIEydOhVpaWkYOXIkEhMT0aJFCxw8eBA6OjriMRs3bsTo0aPRtm1baGhooHfv3li+fLlYbmRkhMOHD8PHxwfOzs6oWLEiZs6cqdYyBQAgEwRBUOsI+mAlJyfDyMgIj54lSSbvUfn0PC2ztLtA71H1ngtLuwtUwoTsdGScnI2kpJL7G573PbHz3G3oGxgWqa201BT0blKjRPtbWph5IiIiIonimLNUjp8LzDlPREREROpg5omIiIgkXl9qoChtlFcMnoiIiEhCQ/ZqK2ob5RWH7YiIiIjUwMwTERERSXDYTjUGT0RERCTBu+1U47AdERERkRqYeSIiIiIJGYo+7FaOE08MnoiIiEiKd9upxmE7IiIiIjUw80REREQSvNtONQZPREREJMG77VRj8EREREQSMhR9wnc5jp0454mIiIhIHcw8ERERkYQGZNAo4ribRjnOPTF4IiIiIgkO26nGYTsiIiIiNTDzRERERFJMPanE4ImIiIgkuM6Tahy2IyIiIlIDM09EREQkVQyLZJbjxBODJyIiIpLilCfVOGxHREREpAZmnoiIiEiKqSeVGDwRERGRBO+2U43BExEREUnIimHCeJEnnJdhnPNEREREpAZmnoiIiEiCU55UY/BEREREUoyeVOKwHREREZEamHkiIiIiCd5tpxqDJyIiIpLg3XaqcdiOiIiISA3MPBEREZEE54urxuCJiIiIpBg9qcRhOyIiIiI1MPNEREREErzbTjUGT0RERCTBu+1UY/BEREREEpzypBrnPBERERGpgZknKrcePk6E34q9OBJxDS/Ts2BXpSJWzhyETxxtS7trVEirNh7BofAruBP7GDraFdCobjX4ftkF1auaAwDuxyWgVf/v8j32R78h6OTaEADw4NFzzFiyA2cv3YK+rjZ6uX+KKSM6Q0tL831dCr1hgocLujSvhZo2ZkjPzMb5f+7D75fjuHU/QaxTzcoYs0e2RdO6NpBX0MTRC3fgu/IwniSmSdpya1wDUwa1QF07c2RkZuP0lVgM8tsJAKhX3Rzjv3BB03o2MFXoIvZREtaHXMJPe/58r9f7wWHqSSUGT1QuJSa/QIfhi9HSuSa2L/saFY0NcPveExgr9Eq7a6SG85G3MbhHc9SvXRU5OTlY8MvvGDLlJxwOmgo9XW1YmRvj3E4/yTGbQyLw85YwtG5cBwCQk5ML72k/o5KpAjt+HIvHCcmY/P0maGlpYsqIzqVwVQQAzZyq4pd9F3HpZhy0NDUwY5grds3tj6Yj1uJFehb0dCpg19z+uHrnMbpP3QgA+GZoK2wO6Iv244IgCK/a6dqiFpaN74TZ68MQHvkvtDQ1UKdaJfE8DWpa4kniC4yctw8PniSjSd3KWDKuE3Jzc/HzvoulcOUfBk4YV61Uh+2GDh0KmUwGmUwGuVwOe3t7BAQEIDs7G2FhYZDJZKhbty5ycnIkxxkbGyMoKEh8Xa1aNbGd17d58+YBgNhWYmKiUh+qVauGpUuXiq/zjj179qykXkZGBszMzCCTyRAWFiYpCwkJQevWrWFoaAg9PT189tlnkv4BwN27dyGTyWBubo6UlBRJWcOGDeHn5ye+dnV1xfjx45X6unnzZmhqasLHx0epjKSWBoeisoUJVs4aDOe61WBbuSI+b1oHdlUqvf1gKjOCFnyJPh0bw8HOEnXsK2PBtP54+Og5rt68DwDQ1NRAJTOFZDt88io6tWkAfT1tAMDJCzdw699HWPy/gXCsWRmuTepggldHbNhzGplZ2aV5eR+1vv/bis2hV3D936e4eucxvl4YAhsLIzSsaQkAaFK3CqpaGMFn4X78c/cJ/rn7BF/PD8EnDlZo1bAaAEBTQ4a5o9pj5i/HsP7AJdx+kIAbsU+xJzxKPM/GQ5cxfXUozlyJxb/xidh29Bo2Hb6MLi1qlcZlUzlR6nOeOnTogLi4OERHR2PSpEnw8/PDggULxPI7d+7g119/fWs7AQEBiIuLk2xjxox5pz7Z2Nhg/fr1kn27d++GgYGBUt0VK1age/fuaN68Oc6dO4fLly/Dw8MDX331FSZPnqxUPyUlBQsXLnynfq1btw5Tp07F5s2bkZ6e/k5tfCwOnryCT+pUxdBp61DTbRpaDZyH4N2nS7tbVEQpqS8BAEaG+WcQr9y4h39uPUC/Tk3EfZeu3UUtOytUMjUU97VqXAupaemIvhtfsh2mQlPovwp2n6e8+tumXUETAoCMrP/+8ZyelY1cQUDTejYAXmWVKldSIDdXwIlVXojaPBbb53whyTwVdK6881D+8u62K+pWXpV68KStrQ1LS0vY2tpi1KhRaNeuHfbt2yeWjxkzBrNmzUJGRobKdgwNDWFpaSnZ9PX136lPnp6e2LJlC16+fCnuCwwMhKenp6TevXv3MGnSJIwfPx7ff/89HB0dYW9vj0mTJmHBggVYtGgRzp07JzlmzJgxWLx4MR4/fqxWn2JiYnDmzBlMmzYNDg4O2LVr1ztd28fi7oOnCNx5EtVtKmHnCh949W6BaYt2YHPI2bcfTGVSbm4uZv+4F8717FCrulW+dbb9fg72thZwrmcn7nuSkIKKrwVOAFDRxFAso9InkwFzv2qHs1fvIeruEwDAn1EP8SI9E37ebaCrrQU9nQqYPaIttDQ1YGn66h+y1axMAADTBrfEwk2n4TFzGxJT0rF/wUAYG+rke67GjpXRs3UdBP9+6f1c3AdKVkxbeVXqwdObdHV1kZmZKb4eP348srOzsWLFivfWB2dnZ1SrVg07d76acBgbG4vw8HAMHjxYUm/Hjh3IysrKN8P05ZdfwsDAAJs3b5bs79+/vzg8qY7169ejc+fOMDIywqBBg7Bu3bq3HpORkYHk5GTJ9rHIzRVQv5YNZvp0Q/1aNhjaqwWG9GiG9btOlXbX6B3NXLoLN2PisHzm4HzL0zMyse/IX5KsE30YFo7ugDrVKsH7+z3ivmdJLzD0u93o0LQm7u+dgn93T4KRgTYio+OQm/tqwpPG/387L9p8GvtP3cDf0fHwWRQCQQB6tKqjdJ461Spho19f/PDbKRy/GPM+Lo3KqTITPAmCgCNHjuDQoUP4/PPPxf16enqYNWsW5s6di6SkpAKP9/X1hYGBgWQ7efLkO/fHy8sLgYGBAICgoCB06tQJlSpJU8E3b96EkZERrKyU/xUsl8tRvXp13Lx5U7I/by7W2rVrcfv27UL1JTc3F0FBQRg0aBAAwMPDA6dOnUJMjOpf/rlz58LIyEjcbGxsCnW+8sCiogK1q1tK9jlUs8T9+Oel1CMqillLd+J4xD/YtPRrWJkb51vnjxOXkZ6RhZ7un0r2VzI1xNM3MkxPn6eIZVS65vu4wb2pPbpO3YiHT6U/p+MXY9Bo6GrU7LcUNfoswVfz98PKzBB3///3OD7h1V13N/59Kh6TmZWDu/HPUaWSQtJWraoVseeHAQj+/RIWbeIQ/lu959STn5+f0rzl2rVri+Xp6enw8fGBmZkZDAwM0Lt3bzx69EjSRmxsLDp37gw9PT2Ym5tjypQpyM4umXmNpR48hYSEwMDAADo6OujYsSO++OILyeRpAPD29oaZmRl++OGHAtuZMmUKIiMjJdunn35aYP23GTRoECIiInDnzh0EBQXBy8vrndt6k7u7O1q0aIEZM2YUqn5oaCjS0tLQqVMnAEDFihXRvn17MbgryPTp05GUlCRu9+7dK3LfPxRNGlRH9L/SodHbsY9RxdK0lHpE70IQBMxauhOHT13Bb0tGwcbKrMC62w6cQ9tmdWFmLJ2b+EndargREycGTABw6sJNGOjrwN7W8s1m6D2a7+OGzs1roduUjYiNL/gfxwnJL5GcloGWDW1RyVgff0REAwD+jo5DemY27G3++1xoaWqgqoUx7j3+r73athWxb8FAbAm9jO+CTpTcBZUjsmL6nzrq1q0rmbd86tR/IwUTJkzA/v37sX37dpw4cQIPHz5Er169xPKcnBx07twZmZmZOHPmDIKDgxEUFISZM2cW23vyulJfqqBNmzZYvXo15HI5rK2toaWl3CUtLS3MmTMHQ4cOxejRo/Ntp2LFirC3t8+3TKF49S+QpKQkGBsbS8oSExNhZGSkdIyZmRm6dOkCb29vpKeno2PHjkp3yTk4OCApKQkPHz6EtbW1pCwzMxO3b99GmzZt8u3TvHnz4OLigilTpuRb/rp169YhISEBurq64r7c3FxcvnwZ/v7+0NDIPwbW1taGtrb2W9svj77u/zncvRdh0fpD6NmuES5eu4vg3aex5Jv+pd01UsPMpTux78hfWDvHCwa62njy7NXQs6GBDnS05WK9u/ef4PzlOwicN1ypjZaf1oK9rQUmfb8J077sgicJKVi87g8M7tEc2vJS/xP40Vo4xh192tTFgFk7kPoyE+Ymr+aoJqdlID3zVbZggFt93Ix9iqdJL9DYsTLmjmqPVbvOi2tBpbzIxPqQvzBtcEs8eJKMe4+SMKZvUwDAnvDrAF4N1e2dPwDHLtzByp3nxfPk5Ap4lvTifV82qaClpQVLS+V/0CQlJWHdunXYtGmTODK1fv161KlTB2fPnkXTpk1x+PBh/PPPPzhy5AgsLCzQsGFDzJ49G76+vvDz84NcLldqt0h9LdbW3oG+vn6BQc/r+vbtiwULFsDf31/tc9SsWRMaGhq4ePEibG3/WyDxzp07SEpKgoODQ77HeXl5oVOnTvD19YWmpvJier1794avry8WLVqERYsWScrWrFmDtLQ09O+f/5d148aN0atXL0ybNk1l3589e4a9e/diy5YtqFu3rrg/JycHLVq0wOHDh9GhQweVbXyMGtW1xYYFIxCwch8W/PIHbK3N8P3E3ujX8bPS7hqpYePeMwCA/uNXSfbP9/VAn46Nxdfb/zgPy0pGaPmZ8u3nmpoaWDd3OL5dsgO9fZZDT0eOXu6fYcIw/t6UJu+uzgCAA4sGSfZ/vWA/NodeAQDUrGKKmV6uMDHUReyjRCzafAardp6X1J/58zFk5+RizdRu0JFr4eKNh+g+dSOSUl/dTdetZW1UMtbHF+2c8EU7J/G42PhENBgi/VzRf4rz2XZvzrct6B/20dHRsLa2ho6ODlxcXDB37lxUrVoVFy9eRFZWFtq1ayfWrV27NqpWrYqIiAg0bdoUERERcHJygoWFhVjH3d0do0aNwrVr1/DJJ58U7WLeUOrBkzrmzZsHd3f3fMtSUlIQHy+97VhPTw8KhQKGhoYYPnw4Jk2aBC0tLTg5OeHevXvw9fVF06ZN0axZs3zb7NChA548eSJmrt5UtWpVzJ8/H5MmTYKOjg4GDx6MChUqYO/evfjmm28wadIkNGlS8OTVOXPmoG7duvlm2/Js2LABZmZm6NevH2RvfJI7deqEdevWMXgqQIeWTujQ0untFanMuhO2uFD1pozorHLBy8qWplj/w8ji6hYVAxO3799axz8wDP6BYSrrZOfkYubPxzDz52P5lv+w4SR+2PDu818/VsW5wPib821nzZqlND2nSZMmCAoKQq1atRAXFwd/f3+0bNkSV69eRXx8PORyudLIkYWFhfi9Hx8fLwmc8srzyorbBxU8ff755/j8889x+PBhpbKZM2cqjW1++eWXWLNmDQBg2bJlmDdvHnx9ffHvv//C0tIS7du3x5w5c5SCkjwymQwVK1ZU2afx48ejevXqWLhwIZYtW4acnBzUrVsXq1evxrBhw1Qe6+DgAC8vL6xdu7bAOoGBgejZs2e+fezduzcGDx6Mp0+fvrWfREREhVaM0dO9e/ckSYj8sk4dO3YU/7t+/fpo0qQJbG1tsW3bNsmUlbJCJgh5i9xTeZecnAwjIyM8epZUYDaNyo/naZlvr0TlRvWe77b4Ln04hOx0ZJycjaSkkvsbnvc9cTE6DgaGRTtHakoynGtavXN/P/vsM7Rr1w7t27dH27Zt8fz5c0n2ydbWFuPHj8eECRMwc+ZM7Nu3D5GRkWJ5TEwMqlevjr/++qvYh+1K/W47IiIiKltK426716WmpuL27duwsrKCs7MzKlSogKNHj4rlN27cQGxsLFxcXAAALi4uuHLlimQB6tDQUCgUCjg6Or77G1GAD2rYjoiIiN6D4ni8ihrHT548GV27doWtrS0ePnyIWbNmQVNTE/3794eRkRG8vb0xceJEmJqaQqFQYMyYMXBxcUHTpq/urnRzc4OjoyMGDx6M+fPnIz4+Ht9++y18fHxK5K5zBk9ERERUqu7fv4/+/fvj2bNnqFSpElq0aIGzZ8+Ki1MvWbIEGhoa6N27NzIyMuDu7o5Vq/67W1JTUxMhISEYNWoUXFxcoK+vD09PT7Wf5lFYnPP0EeGcp48L5zx9XDjnqfx7n3OeLt2Kh2ER5zylpCTjE3vLEu1vaWHmiYiIiKSKc62CcogTxomIiIjUwMwTERERSRT1brm8NsorBk9EREQkUZyPZymPOGxHREREpAZmnoiIiEiC88VVY/BEREREUoyeVGLwRERERBKcMK4a5zwRERERqYGZJyIiIpKQoRjutiuWnpRNDJ6IiIhIglOeVOOwHREREZEamHkiIiIiCS6SqRqDJyIiInoDB+5U4bAdERERkRqYeSIiIiIJDtupxuCJiIiIJDhopxqH7YiIiIjUwMwTERERSXDYTjUGT0RERCTBZ9upxuCJiIiIpDjpSSXOeSIiIiJSAzNPREREJMHEk2oMnoiIiEiCE8ZV47AdERERkRqYeSIiIiIJ3m2nGoMnIiIikuKkJ5U4bEdERESkBmaeiIiISIKJJ9UYPBEREZEE77ZTjcN2RERERGpg5omIiIjeUPS77crzwB2DJyIiIpLgsJ1qHLYjIiIiUgODJyIiIiI1cNiOiIiIJDhspxqDJyIiIpLg41lU47AdERERkRqYeSIiIiIJDtupxuCJiIiIJPh4FtU4bEdERESkBmaeiIiISIqpJ5UYPBEREZEE77ZTjcN2RERERGpg5omIiIgkeLedagyeiIiISIJTnlRj8ERERERSjJ5U4pwnIiIiIjUw80REREQSvNtONQZPREREJMEJ46oxePqICIIAAEhJTi7lntD7kJKWWdpdoPdIyE4v7S5QCROyM179////LS9JycXwPVEcbZRVDJ4+IikpKQAAezubUu4JERG9q5SUFBgZGZVI23K5HJaWlqhZTN8TlpaWkMvlxdJWWSIT3kcIS2VCbm4uHj58CENDQ8jKcz71NcnJybCxscG9e/egUChKuztUgviz/rh8jD9vQRCQkpICa2traGiU3P1e6enpyMwsnsy1XC6Hjo5OsbRVljDz9BHR0NBAlSpVSrsbpUKhUHw0f2A/dvxZf1w+tp93SWWcXqejo1MuA57ixKUKiIiIiNTA4ImIiIhIDQyeqFzT1tbGrFmzoK2tXdpdoRLGn/XHhT9vKk2cME5ERESkBmaeiIiIiNTA4ImIiIhIDQyeiIiIiNTA4ImIiIhIDQyeqEyKj4/HmDFjUL16dWhra8PGxgZdu3bF0aNHxTpnzpxBp06dYGJiAh0dHTg5OWHx4sXIyckBAOzcuROampp48OBBvueoWbMmJk6cCABwdXXF+PHjxTJXV1fIZDLIZDJoa2ujcuXK6Nq1K3bt2lVyF10ODR06FDKZDPPmzZPs37Nnj2SV+5ycHCxZsgROTk7Q0dGBiYkJOnbsiNOnT0uOCwoKEn8uGhoasLKywhdffIHY2FhJvbyf35vnBYDOnTtDJpPBz89PqWzz5s3Q1NSEj4+PUllYWBhkMhkSExPVeAc+XHk/O5lMBrlcDnt7ewQEBCA7O1t8L+rWrSv+vuUxNjZGUFCQ+LpatWpiO69veT8bVe9rtWrVsHTpUvF13rFnz56V1MvIyICZmRlkMhnCwsIkZSEhIWjdujUMDQ2hp6eHzz77TNI/ALh79y5kMhnMzc3Fx1jladiwoeSz8ubfijyqPjtU/jB4ojLn7t27cHZ2xrFjx7BgwQJcuXIFBw8eRJs2bcQ/TLt370br1q1RpUoVHD9+HNevX8e4cePw3XffwcPDA4IgoFu3bjAzM0NwcLDSOcLDw3Hr1i14e3sX2I8RI0YgLi4Ot2/fxs6dO+Ho6AgPDw+MHDmyxK69PNLR0cEPP/yA58+f51suCAI8PDwQEBCAcePGISoqCmFhYbCxsYGrqyv27Nkjqa9QKBAXF4cHDx5g586duHHjBvr27avUro2NjdKX5IMHD3D06FFYWVnl25d169Zh6tSp2Lx5M9LT+aDdDh06IC4uDtHR0Zg0aRL8/PywYMECsfzOnTv49ddf39pOQEAA4uLiJNuYMWPeqU82NjZYv369ZN/u3bthYGCgVHfFihXo3r07mjdvjnPnzuHy5cvw8PDAV199hcmTJyvVT0lJwcKFC9+pX/zsfGQEojKmY8eOQuXKlYXU1FSlsufPnwupqamCmZmZ0KtXL6Xyffv2CQCELVu2CIIgCBMnThRq1qypVM/T01No0qSJ+Lp169bCuHHjCnydJzAwUAAghIaGvsOVfXw8PT2FLl26CLVr1xamTJki7t+9e7eQ9+dny5YtAgBh3759Ssf36tVLMDMzEz8L69evF4yMjCR1li9fLgAQkpKSxH2tW7cWRo0aJZiZmQmnTp0S98+ZM0fo2rWr0KBBA2HWrFmSdu7cuSPo6uoKiYmJQpMmTYSNGzdKyo8fPy4AEJ4/f/4ub8UHx9PTU+jevbtkX/v27YWmTZuK78WUKVMEGxsbIT09XaxjZGQkrF+/Xnxta2srLFmypMDzqHpf3zwWgPDtt98KCoVCePHihaRfM2bMEAAIx48fFwRBEGJjY4UKFSoIEydOVGo37zNz9uxZQRAEISYmRrweAwMD4dGjR2LdNz8r+f1teNtnh8ofZp6oTElISMDBgwfh4+MDfX19pXJjY2McPnwYz549y/dfjl27doWDgwM2b94MAPD29kZ0dDTCw8PFOqmpqdixY4fKrFNBPD09YWJiwuE7NWhqauL777/HihUrcP/+faXyTZs2wcHBAV27dlUqmzRpEp49e4bQ0NB82378+DF2794NTU1NaGpqSsrkcjkGDhwoyVIEBQXBy8sr37bWr1+Pzp07w8jICIMGDcK6devUucyPgq6uruSBsePHj0d2djZWrFjx3vrg7OyMatWqYefOnQCA2NhYhIeHY/DgwZJ6O3bsQFZWVr5/J7788ksYGBiIfyfy9O/fXxyeVAc/Ox8fBk9Upty6dQuCIKB27doF1rl58yYAoE6dOvmW165dW6zj6OiIpk2bIjAwUCzftm2bOFSkLg0NDTg4OODu3btqH/sx69mzJxo2bIhZs2Ypld28ebPAn2Xe/ryfJwAkJSXBwMAA+vr6sLCwwPHjxwsMtr28vLBt2zakpaUhPDwcSUlJ6NKli1K93NxcBAUFYdCgQQAADw8PnDp1CjExMe90veWNIAg4cuQIDh06hM8//1zcr6enh1mzZmHu3LlISkoq8HhfX18YGBhItpMnT75zf7y8vMTf6aCgIHTq1AmVKlWS1Ll58yaMjIzyHaKVy+WoXr265HMFQJyLtXbtWty+fbtQfeFn5+PE4InKFEGNBe8LW9fLyws7duwQJ4IGBgaib9++MDQ0fOc+vj7ZmQrnhx9+QHBwMKKiopTK1Pm5GxoaIjIyEhcuXMCiRYvQqFEjzJkzJ9+6DRo0QM2aNbFjxw4EBgZi8ODB0NLSUqoXGhqKtLQ0dOrUCQBQsWJFtG/fXhJ0f4xCQkJgYGAAHR0ddOzYEV988YXSRHtvb2+YmZnhhx9+KLCdKVOmIDIyUrJ9+umn79yvQYMGISIiAnfu3FGZTXwX7u7uaNGiBWbMmFGo+vzsfJwYPFGZUrNmTchkMly/fr3AOg4ODgCQ75dw3v68OgDEDNO2bdsQHR2N06dPv9OQHfDqrrDo6GjY2dm90/Efs1atWsHd3R3Tp0+X7HdwcFD5s8yrk0dDQwP29vaoU6cOJk6ciKZNm2LUqFEFntfLywsrV67Ejh07CvySXbduHRISEqCrqwstLS1oaWnh999/R3BwMHJzc9W91HKjTZs2iIyMRHR0NF6+fIng4GClDJ+WlhbmzJmDZcuW4eHDh/m2U7FiRdjb20s2XV1dAK9uAACQb+YqMTERRkZGSvvNzMzQpUsXeHt7Iz09HR07dlSq4+DggKSkpHz7lJmZidu3b0s+V6+bN28etm7dikuXLuVb/jp+dj5ODJ6oTDE1NYW7uztWrlyJtLQ0pfLExES4ubnB1NQUixYtUirft28foqOj0b9/f3GfoaEh+vbti8DAQKxfvx4ODg5o2bLlO/UvODgYz58/R+/evd/p+I/dvHnzsH//fkRERIj7PDw8EB0djf379yvVX7RoEczMzNC+ffsC25w2bRq2bt2Kv/76K9/yAQMG4MqVK6hXrx4cHR2Vyp89e4a9e/diy5YtkszIpUuX8Pz5cxw+fPgdrrR80NfXh729PapWrZpvxi5P3759UbduXfj7+6t9jpo1a0JDQwMXL16U7L9z5w6SkpIKDHC8vLwQFhaGIUOGKM13A4DevXujQoUK+f6dWLNmDdLS0iR/J17XuHFj9OrVC9OmTVPZd352Pl4F/zYQlZKVK1eiefPmaNy4MQICAlC/fn1kZ2cjNDQUq1evRlRUFH766Sdx2YDRo0dDoVDg6NGjmDJlCvr06YN+/fpJ2vT29kbLli0RFRUFX1/fQvXjxYsXiI+PR3Z2Nu7fv4/du3djyZIlGDVqFNq0aVMSl17uOTk5YeDAgVi+fLm4z8PDA9u3b4enpycWLFiAtm3bIjk5GStXrsS+ffuwffv2fOcz5bGxsUHPnj0xc+ZMhISEKJWbmJggLi4OFSpUyPf4DRs2wMzMDP369VMaju3UqRPWrVuHDh06iPuuXLkiGfKVyWRo0KBBod+D8mrevHlwd3fPtywlJQXx8fGSfXp6elAoFDA0NMTw4cMxadIkaGlpwcnJCffu3YOvry+aNm2KZs2a5dtmhw4d8OTJEzFz9aaqVati/vz5mDRpEnR0dDB48GBUqFABe/fuxTfffINJkyahSZMmBV7PnDlzULduXZVBo7qfHSpHSvFOP6ICPXz4UPDx8RFsbW0FuVwuVK5cWejWrZt4G7IgCEJ4eLjg7u4uKBQKQS6XC3Xr1hUWLlwoZGdn59tmrVq1BE1NTeHhw4dKZfktVQBAACDI5XLByspK6NKli7Br167ivtRyLb/b3WNiYgS5XC68/ucnKytLWLBggVC3bl1BLpcLCoVCcHd3lywzIAj5L1UgCIIQEREhABDOnTsnCELBS03kef32cycnJ+Hrr7/Ot97WrVsFuVwuPHnyRLyl/s1NU1Pz7W/EByi/n12egpYXcHNzEwAoLVWQ3/v25ZdfinVevnwpzJo1S6hdu7agq6sr2NnZCSNHjhSePHkiaR+AsHv37nz79Pz5c8lSBXn27t0rtGzZUtDX1xd0dHQEZ2dnITAwUFInb6mCS5cuSfaPHDlSAFDgUgWF/exQ+SMTBDVmahIRERF95DjniYiIiEgNDJ6IiIiI1MDgiYiIiEgNDJ6IiIiI1MDgiYiIiEgNDJ6IiIiI1MDgiYiIiEgNDJ6I6L0aOnQoevToIb52dXXF+PHj33s/wsLCIJPJkJiYWGAdmUyGPXv2FLpNPz8/NGzYsEj9unv3LmQyGSIjI4vUDhGVHAZPRIShQ4dCJpNBJpNBLpfD3t4eAQEByM7OLvFz79q1C7Nnzy5U3cIEPEREJY3PtiMiAK+eFbZ+/XpkZGTg999/h4+PDypUqIDp06cr1c3MzIRcLi+W85qamhZLO0RE7wszT0QEANDW1oalpSVsbW0xatQotGvXDvv27QPw31DbnDlzYG1tjVq1agEA7t27h379+sHY2Bimpqbo3r077t69K7aZk5ODiRMnwtjYGGZmZpg6dSrefCLUm8N2GRkZ8PX1hY2NDbS1tWFvb49169bh7t274gOZTUxMIJPJMHToUABAbm4u5s6dCzs7O+jq6qJBgwbYsWOH5Dy///47HBwcoKurizZt2kj6WVi+vr5wcHCAnp4eqlevjhkzZiArK0up3k8//QQbGxvo6emhX79+SEpKkpT/8ssvqFOnDnR0dFC7dm2sWrVK7b4QUelh8ERE+dLV1UVmZqb4+ujRo7hx4wZCQ0MREhKCrKwsuLu7w9DQECdPnsTp06dhYGCADh06iMctWrQIQUFBCAwMxKlTp5CQkIDdu3erPO+QIUOwefNmLF++HFFRUfjpp59gYGAAGxsb7Ny5EwBw48YNxMXFYdmyZQCAuXPn4tdff8WaNWtw7do1TJgwAYMGDcKJEycAvAryevXqha5duyIyMhLDhw/HtGnT1H5PDA0NERQUhH/++QfLli3Dzz//jCVLlkjq3Lp1C9u2bcP+/ftx8OBBXLp0CV9//bVYvnHjRsycORNz5sxBVFQUvv/+e8yYMQPBwcFq94eISkkpP5iYiMoAT09PoXv37oIgCEJubq4QGhoqaGtrC5MnTxbLLSwshIyMDPGYDRs2CLVq1RJyc3PFfRkZGYKurq5w6NAhQRAEwcrKSpg/f75YnpWVJVSpUkU8lyBIn1J/48YNAYAQGhqabz+PHz8uABCeP38u7ktPTxf09PSEM2fOSOp6e3sL/fv3FwRBEKZPny44OjpKyn19fZXaehMAYffu3QWWL1iwQHB2dhZfz5o1S9DU1BTu378v7vvjjz8EDQ0NIS4uThAEQahRo4awadMmSTuzZ88WXFxcBEEQhJiYGAGAcOnSpQLPS0Sli3OeiAgAEBISAgMDA2RlZSE3NxcDBgyAn5+fWO7k5CSZ5/T333/j1q1bMDQ0lLSTnp6O27dvIykpCXFxcWjSpIlYpqWlhU8//VRp6C5PZGQkNDU10bp160L3+9atW3jx4gXat28v2Z+ZmYlPPvkEABAVFSXpBwC4uLgU+hx5tm7diuXLl+P27dtITU1FdnY2FAqFpE7VqlVRuXJlyXlyc3Nx48YNGBoa4vbt2/D29saIESPEOtnZ2TAyMlK7P0RUOhg8EREAoE2bNli9ejXkcjmsra2hpSX986Cvry95nZqaCmdnZ2zcuFGprUqVKr1TH3R1ddU+JjU1FQBw4MABSdACvJrHVVwiIiIwcOBA+Pv7w93dHUZGRtiyZQsWLVqkdl9//vlnpWBOU1Oz2PpKRCWLwRMRAXgVHNnb2xe6fqNGjbB161aYm5srZV/yWFlZ4dy5c2jVqhWAVxmWixcvolGjRvnWd3JyQm5uLk6cOIF27dopledlvnJycsR9jo6O0NbWRmxsbIEZqzp16oiT3/OcPXv27Rf5mjNnzsDW1hb/+9//xH3//vuvUr3Y2Fg8fPgQ1tbW4nk0NDRQq1YtWFhYwNraGnfu3MHAgQPVOj8RlR2cME5E72TgwIGoWLEiunfvjpMnTyImJgZhYWEYO3Ys7t+/DwAYN24c5s2bhz179uD69ev4+uuvVa7RVK1aNXh6esLLywt79uwR29y2bRsAwNbWFjKZDCEhIXjy5AlSU1NhaGiIyZMnY8KECQgODsbt27fx119/YcWKFeIk7K+++grR0dGYMmUKbty4gU2bNiEoKEit661ZsyZiY2OxZcsW3L59G8uXL8938ruOjg48PT3x999/4+TJkxg7diz69esHS0tLAIC/vz/mzp2L5cuX4+bNm7hy5QrWr1+PxYsXq9UfIio9DJ6I6J3o6ekhPDwcVatWRa9evVCnTh14e3sjPT1dzERNmjQJgwcPhqenJ1xcXGBoaIiePXuqbHf16tXo06cPvv76a9SuXRsjRoxAWloaAKBy5crw9/fHtGnTYGFhgdGjRwMAZs+ejRkzZmDu3LmoU6cOOnTogAMHDsDOzg7Aq3lIO3fuxJ49e9CgQQOsWbMG33//vVrX261bN0yYMAGjR49Gw4YNcebMGcyYMUOpnr29PXr16oVOnTrBzc0N9evXlyxFMHz4cPzyyy9Yv349nJyc0Lp1awQFBYl9JaKyTyYUNHOTiIiIiJQw80RERESkBgZPRERERGpg8ERERESkBgZPRERERGpg8ERERESkBgZPRERERGpg8ERERESkBgZPRERERGpg8ERERESkBgZPRERERGpg8ERERESkBgZPRERERGr4P6AuWJ5TZ1ROAAAAAElFTkSuQmCC\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "📊 Evaluating ResNet152...\n",
            "\n",
            "\u001b[1m306/306\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m64s\u001b[0m 152ms/step - accuracy: 0.8628 - loss: 0.3594\n",
            "ResNet152 Test Accuracy: 86.37%\n",
            "ResNet152 Test Loss: 0.3490\n",
            "\u001b[1m306/306\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m57s\u001b[0m 153ms/step\n",
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "       COVID       0.90      0.87      0.88      3271\n",
            "      NORMAL       0.83      0.86      0.85      3272\n",
            "   PNEUMONIA       0.87      0.86      0.86      3238\n",
            "\n",
            "    accuracy                           0.86      9781\n",
            "   macro avg       0.86      0.86      0.86      9781\n",
            "weighted avg       0.86      0.86      0.86      9781\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.metrics import classification_report, confusion_matrix, ConfusionMatrixDisplay\n",
        "from tensorflow.keras.models import load_model\n",
        "\n",
        "# Paths to best fine-tuned models\n",
        "densenet_path = \"/content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\"\n",
        "resnet_path   = \"/content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\"\n",
        "\n",
        "# Load models\n",
        "densenet_model = load_model(densenet_path)\n",
        "resnet_model   = load_model(resnet_path)\n",
        "\n",
        "# Evaluate function\n",
        "def evaluate_model(model, test_gen, model_name):\n",
        "    print(f\"\\n📊 Evaluating {model_name}...\\n\")\n",
        "\n",
        "    # Evaluate on test set\n",
        "    loss, acc = model.evaluate(test_gen, verbose=1)\n",
        "    print(f\"{model_name} Test Accuracy: {acc*100:.2f}%\")\n",
        "    print(f\"{model_name} Test Loss: {loss:.4f}\")\n",
        "\n",
        "    # Predictions\n",
        "    y_pred = model.predict(test_gen, verbose=1)\n",
        "    y_pred_classes = np.argmax(y_pred, axis=1)\n",
        "    y_true = test_gen.classes\n",
        "    class_labels = list(test_gen.class_indices.keys())\n",
        "\n",
        "    # Classification report\n",
        "    print(\"\\nClassification Report:\")\n",
        "    print(classification_report(y_true, y_pred_classes, target_names=class_labels))\n",
        "\n",
        "    # Confusion matrix\n",
        "    cm = confusion_matrix(y_true, y_pred_classes)\n",
        "    disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=class_labels)\n",
        "    disp.plot(cmap=plt.cm.Blues, values_format=\"d\")\n",
        "    plt.title(f\"{model_name} - Confusion Matrix\")\n",
        "    plt.show()\n",
        "\n",
        "# Run evaluation\n",
        "evaluate_model(densenet_model, test_gen, \"DenseNet201\")\n",
        "evaluate_model(resnet_model, test_gen, \"ResNet152\")"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# =========================================\n",
        "# SHORTCUT PIPELINE: USE EXISTING final_dataset IN DRIVE\n",
        "# =========================================\n",
        "\n",
        "# 1. Mount Drive\n",
        "from google.colab import drive\n",
        "drive.mount('/content/drive')\n",
        "\n",
        "# 2. Point to your dataset in Drive\n",
        "dataset_dir = \"/content/drive/MyDrive/chest_xray_project/final_dataset\"\n",
        "\n",
        "# 3. Import libraries\n",
        "import os\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "# Image size and batch size\n",
        "img_size = (224,224)\n",
        "batch_size = 32\n",
        "\n",
        "# 4. Data generators (rescaling + augmentation for train)\n",
        "train_datagen = ImageDataGenerator(\n",
        "    rescale=1./255,\n",
        "    rotation_range=15,\n",
        "    width_shift_range=0.1,\n",
        "    height_shift_range=0.1,\n",
        "    shear_range=0.1,\n",
        "    zoom_range=0.1,\n",
        "    horizontal_flip=True\n",
        ")\n",
        "\n",
        "val_test_datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "train_gen = train_datagen.flow_from_directory(\n",
        "    os.path.join(dataset_dir, \"train\"),\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\"\n",
        ")\n",
        "\n",
        "val_gen = val_test_datagen.flow_from_directory(\n",
        "    os.path.join(dataset_dir, \"val\"),\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\"\n",
        ")\n",
        "\n",
        "test_gen = val_test_datagen.flow_from_directory(\n",
        "    os.path.join(dataset_dir, \"test\"),\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "print(\"\\n✅ Dataset loaded successfully from Drive.\")\n",
        "print(\"Classes:\", train_gen.class_indices)\n",
        "\n",
        "# 5. Load saved models (DenseNet201 & ResNet152)\n",
        "from tensorflow.keras.models import load_model\n",
        "\n",
        "densenet_model = load_model(\"/content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\")\n",
        "resnet_model   = load_model(\"/content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\")\n",
        "\n",
        "print(\"\\n✅ Models loaded successfully from Drive.\")\n",
        "\n",
        "# 6. Evaluate both models on test set\n",
        "print(\"\\n📊 Evaluating DenseNet201...\")\n",
        "densenet_model.evaluate(test_gen, verbose=1)\n",
        "\n",
        "print(\"\\n📊 Evaluating ResNet152...\")\n",
        "resnet_model.evaluate(test_gen, verbose=1)\n"
      ],
      "metadata": {
        "id": "J4CbWJ52cP1D",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "0e2f820e-2120-4fd0-9fe4-446b518e4301"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n",
            "Found 32047 images belonging to 3 classes.\n",
            "Found 9764 images belonging to 3 classes.\n",
            "Found 9781 images belonging to 3 classes.\n",
            "\n",
            "✅ Dataset loaded successfully from Drive.\n",
            "Classes: {'COVID': 0, 'NORMAL': 1, 'PNEUMONIA': 2}\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "✅ Models loaded successfully from Drive.\n",
            "\n",
            "📊 Evaluating DenseNet201...\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.\n",
            "  self._warn_if_super_not_called()\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m306/306\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1632s\u001b[0m 5s/step - accuracy: 0.9230 - loss: 0.2220\n",
            "\n",
            "📊 Evaluating ResNet152...\n",
            "\u001b[1m306/306\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m100s\u001b[0m 272ms/step - accuracy: 0.8743 - loss: 0.3327\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.34922173619270325, 0.8637153506278992]"
            ]
          },
          "metadata": {},
          "execution_count": 1
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# ======================================================\n",
        "# STEP 1: Download Amanullah Asraf dataset from Kaggle\n",
        "# ======================================================\n",
        "!kaggle datasets download -d amanullahasraf/covid19-pneumonia-normal-chest-xray-pa-dataset -p /content\n",
        "!unzip -q /content/covid19-pneumonia-normal-chest-xray-pa-dataset.zip -d /content/amanullah_dataset\n",
        "\n",
        "# Check dataset structure\n",
        "import os\n",
        "print(\"Dataset root contents:\", os.listdir(\"/content/amanullah_dataset\"))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "svJr_CXymnVI",
        "outputId": "da6a07ae-7758-4948-fc2b-75918d2c1e78"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Dataset URL: https://www.kaggle.com/datasets/amanullahasraf/covid19-pneumonia-normal-chest-xray-pa-dataset\n",
            "License(s): CC0-1.0\n",
            "Downloading covid19-pneumonia-normal-chest-xray-pa-dataset.zip to /content\n",
            " 99% 1.88G/1.91G [00:04<00:00, 454MB/s]\n",
            "100% 1.91G/1.91G [00:04<00:00, 486MB/s]\n",
            "Dataset root contents: ['pneumonia', 'normal', 'covid']\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# ======================================================\n",
        "# STEP 2: Setup ImageDataGenerator for test set\n",
        "# ======================================================\n",
        "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
        "\n",
        "dataset_dir = \"/content/amanullah_dataset\"  # Adjust if inside another folder\n",
        "img_size = (224,224)\n",
        "batch_size = 32\n",
        "\n",
        "datagen = ImageDataGenerator(rescale=1./255)\n",
        "\n",
        "# Since it's a 3-class dataset (COVID, PNEUMONIA, NORMAL),\n",
        "# we will use the entire dataset as a test set\n",
        "external_test_gen = datagen.flow_from_directory(\n",
        "    dataset_dir,\n",
        "    target_size=img_size,\n",
        "    batch_size=batch_size,\n",
        "    class_mode=\"categorical\",\n",
        "    shuffle=False\n",
        ")\n",
        "\n",
        "print(\"\\n✅ External test dataset loaded successfully\")\n"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "AEVvnIUZWxSy",
        "outputId": "839060b6-dcec-4938-f07e-6d9598dfe0f9"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Found 6902 images belonging to 3 classes.\n",
            "\n",
            "✅ External test dataset loaded successfully\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# ======================================================\n",
        "# STEP 3: Load your trained models\n",
        "# ======================================================\n",
        "from tensorflow.keras.models import load_model\n",
        "\n",
        "densenet_model = load_model(\"/content/drive/MyDrive/chest_xray_project/densenet201_best_ft.h5\")\n",
        "resnet_model   = load_model(\"/content/drive/MyDrive/chest_xray_project/resnet152_best_ft.h5\")\n",
        "\n",
        "print(\"\\n✅ Models loaded from Drive\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "mUlc840pXBtN",
        "outputId": "2f8a242e-6d2a-4d6f-96ad-38b56bbda348"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n",
            "WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "✅ Models loaded from Drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# ======================================================\n",
        "# STEP 4: Evaluate both models on the new dataset\n",
        "# ======================================================\n",
        "print(\"\\n📊 Evaluating DenseNet201 on external dataset...\")\n",
        "densenet_model.evaluate(external_test_gen, verbose=1)\n",
        "\n",
        "print(\"\\n📊 Evaluating ResNet152 on external dataset...\")\n",
        "resnet_model.evaluate(external_test_gen, verbose=1)"
      ],
      "metadata": {
        "id": "ZYD3DkZEZCWv",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "outputId": "ad326c65-72c7-41d3-e710-6bb4762e7e28"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "📊 Evaluating DenseNet201 on external dataset...\n",
            "\u001b[1m216/216\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m134s\u001b[0m 483ms/step - accuracy: 0.8432 - loss: 0.4823\n",
            "\n",
            "📊 Evaluating ResNet152 on external dataset...\n",
            "\u001b[1m216/216\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m108s\u001b[0m 421ms/step - accuracy: 0.7983 - loss: 0.5240\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0.40924569964408875, 0.8458417654037476]"
            ]
          },
          "metadata": {},
          "execution_count": 6
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import numpy as np\n",
        "import matplotlib.pyplot as plt\n",
        "from sklearn.metrics import classification_report, confusion_matrix, ConfusionMatrixDisplay, roc_curve, auc\n",
        "from sklearn.preprocessing import label_binarize\n",
        "\n",
        "# Helper function: Error Rate\n",
        "def evaluate_with_error_rate(model, generator, name=\"Model\"):\n",
        "    loss, acc = model.evaluate(generator, verbose=0)\n",
        "    error_rate = 1 - acc\n",
        "    print(f\"\\n{name} on {generator.directory.split('/')[-1]} dataset:\")\n",
        "    print(f\" Accuracy: {acc:.4f} | Error Rate: {error_rate:.4f} | Loss: {loss:.4f}\")\n",
        "    return acc, error_rate, loss\n",
        "\n",
        "# Helper function: ROC Curve (One-vs-Rest)\n",
        "def plot_roc_curve(model, generator, dataset_name=\"Dataset\"):\n",
        "    y_true = generator.classes\n",
        "    y_pred = model.predict(generator, verbose=0)\n",
        "    class_names = list(generator.class_indices.keys())\n",
        "    y_true_bin = label_binarize(y_true, classes=range(len(class_names)))\n",
        "\n",
        "    plt.figure(figsize=(8,6))\n",
        "    for i, class_name in enumerate(class_names):\n",
        "        fpr, tpr, _ = roc_curve(y_true_bin[:, i], y_pred[:, i])\n",
        "        roc_auc = auc(fpr, tpr)\n",
        "        plt.plot(fpr, tpr, lw=2, label=f\"{class_name} (AUC = {roc_auc:.2f})\")\n",
        "\n",
        "    plt.plot([0,1],[0,1],'k--')\n",
        "    plt.xlabel(\"False Positive Rate\")\n",
        "    plt.ylabel(\"True Positive Rate\")\n",
        "    plt.title(f\"ROC Curve - {dataset_name}\")\n",
        "    plt.legend(loc=\"lower right\")\n",
        "    plt.show()\n",
        "\n",
        "# Helper function: Confusion Matrix\n",
        "def plot_confusion_matrix(model, generator, name=\"Model\"):\n",
        "    y_true = generator.classes\n",
        "    y_pred = model.predict(generator, verbose=0)\n",
        "    y_pred_classes = np.argmax(y_pred, axis=1)\n",
        "    labels = list(generator.class_indices.keys())\n",
        "\n",
        "    cm = confusion_matrix(y_true, y_pred_classes)\n",
        "    disp = ConfusionMatrixDisplay(confusion_matrix=cm, display_labels=labels)\n",
        "    disp.plot(cmap=plt.cm.Blues, values_format=\"d\")\n",
        "    plt.title(f\"{name} - Confusion Matrix (External Dataset)\")\n",
        "    plt.show()\n",
        "    print(\"\\nClassification Report:\")\n",
        "    print(classification_report(y_true, y_pred_classes, target_names=labels))"
      ],
      "metadata": {
        "id": "DrNnz1990pOa"
      },
      "execution_count": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# DenseNet201\n",
        "evaluate_with_error_rate(densenet_model, test_gen, \"DenseNet201 (Main)\")\n",
        "evaluate_with_error_rate(densenet_model, external_test_gen, \"DenseNet201 (External)\")\n",
        "\n",
        "# ResNet152\n",
        "evaluate_with_error_rate(resnet_model, test_gen, \"ResNet152 (Main)\")\n",
        "evaluate_with_error_rate(resnet_model, external_test_gen, \"ResNet152 (External)\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 0
        },
        "id": "JvBN9Stga1fu",
        "outputId": "80e3cab6-6575-498e-a3b3-6dad356c45df"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "DenseNet201 (Main) on test dataset:\n",
            " Accuracy: 0.9323 | Error Rate: 0.0677 | Loss: 0.1898\n",
            "\n",
            "DenseNet201 (External) on amanullah_dataset dataset:\n",
            " Accuracy: 0.8826 | Error Rate: 0.1174 | Loss: 0.3680\n",
            "\n",
            "ResNet152 (Main) on test dataset:\n",
            " Accuracy: 0.8637 | Error Rate: 0.1363 | Loss: 0.3492\n",
            "\n",
            "ResNet152 (External) on amanullah_dataset dataset:\n",
            " Accuracy: 0.8458 | Error Rate: 0.1542 | Loss: 0.4092\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(0.8458417654037476, 0.15415823459625244, 0.40924516320228577)"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# DenseNet201\n",
        "plot_roc_curve(densenet_model, test_gen, \"Main Dataset (DenseNet201)\")\n",
        "plot_roc_curve(densenet_model, external_test_gen, \"External Dataset (DenseNet201)\")\n",
        "\n",
        "# ResNet152\n",
        "plot_roc_curve(resnet_model, test_gen, \"Main Dataset (ResNet152)\")\n",
        "plot_roc_curve(resnet_model, external_test_gen, \"External Dataset (ResNet152)\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 2082
        },
        "id": "f36aLiS_a5Y4",
        "outputId": "b30aa4cc-a95a-4a6e-88f5-157b6e8edac8"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAArMAAAIjCAYAAAAQgZNYAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAwOFJREFUeJzs3Xd4U9UfBvA3o0kXHVBaVqFM2ZS9QaBSZIsCZcgQFJElSwXZIIIyFaGKIBtaWSL8ZIPsTdl7lu5Sundyfn9U0oaupDS9He/near3nHvuzTdpab85OUMmhBAgIiIiIiqA5FIHQERERESUU0xmiYiIiKjAYjJLRERERAUWk1kiIiIiKrCYzBIRERFRgcVkloiIiIgKLCazRERERFRgMZklIiIiogKLySwRERERFVhMZomIcsnTp08hk8mwbt06qUMpMn744QdUr14dWq1W6lCKnNu3b0OpVOLmzZtSh0JFHJNZore0bt06yGQy3ZdSqUTZsmUxZMgQ+Pn5ZXiNEAIbN25EmzZtYGdnB0tLS9SpUwdz5sxBTExMpo+1a9cuvP/++3BwcIBKpUKZMmXQp08fHD161KBY4+PjsXTpUjRt2hS2trYwNzdHtWrVMHr0aNy/fz9Hz78gGTJkCGQyGWxsbBAXF5fu/IMHD3Tfx0WLFkkQYXrvvvuuLia5XA4bGxu88847+Pjjj3Ho0KG3uvfKlSvzTeLt7++PWbNmwcfHx+BrIiMjsXDhQnz99deQy1P/nKX99/j6+922bVvs27fPBJGneP1GRiaTYceOHenOz5o1CzKZDKGhoUbf+8yZM5g1axbCw8PTnTt48CCGDRuG2rVrQ6FQwMXFJdv43vzatm2brp1Wq8W6devQvXt3ODs7w8rKCrVr18a8efMQHx+vd8+aNWuiS5cumDFjhtHPiSg3KaUOgKiwmDNnDipWrIj4+HicO3cO69atw6lTp3Dz5k2Ym5vr2mk0GvTv3x/e3t5o3bo1Zs2aBUtLS5w8eRKzZ8/Gn3/+icOHD8PJyUl3jRACn3zyCdatW4f69etjwoQJKFWqFAICArBr1y506NABp0+fRosWLTKNLzQ0FJ06dcLly5fRtWtX9O/fH9bW1rh37x62bduG3377DYmJiSZ9jfIDpVKJ2NhY/P333+jTp4/euc2bN8Pc3DzdH21DVahQAXFxcTAzM8uNUHXKlSuH77//HgAQExODhw8fYufOndi0aRP69OmDTZs25egxV65cCQcHBwwZMiRX480Jf39/zJ49Gy4uLnB1dTXomrVr1yI5ORn9+vVLd+69997DoEGDIITAs2fPsGrVKnTr1g3//PMP3N3dczl6fXPmzEGvXr0gk8ly5X5nzpzB7NmzMWTIENjZ2emd27JlC7y8vNCgQQOUKVMm23v169cPnTt31qtr3ry57jg2NhZDhw5Fs2bN8Pnnn8PR0RFnz57FzJkzceTIERw9elTveX3++efo3LkzHj16hMqVK7/dEyXKKUFEb+WPP/4QAMTFixf16r/++msBQHh5eenVz58/XwAQkyZNSnevPXv2CLlcLjp16qRX/+OPPwoA4ssvvxRarTbddRs2bBDnz5/PMs4uXboIuVwutm/fnu5cfHy8mDhxYpbXGyopKUkkJCTkyr1y2+DBg4WVlZXo2LGj6NmzZ7rzVatWFR9++KEAIH788UcJIkyvbdu2olatWunqk5OTxRdffCEAiK+++ipH965Vq5Zo27btW0aYOy5evCgAiD/++MPga+rWrSsGDhyYrh6AGDVqlF7d7du3BQDx/vvvv22oGXry5IkAIFxdXQUAsWPHDr3zM2fOFABESEiI0fd+/e//yZMn6c75+fmJxMREIUTKv/EKFSpkGV92P9cJCQni9OnT6epnz54tAIhDhw7p1ScmJgp7e3sxffp0w54MkQkwmSV6S5kls3v37hUAxPz583V1sbGxwt7eXlSrVk0kJSVleL+hQ4cKAOLs2bO6a4oXLy6qV68ukpOTcxTjuXPnBADx6aefGtS+bdu2GSY5gwcP1vtjmfYP5NKlS0WlSpWEXC4X586dEwqFQsyaNSvdPe7evSsAiJ9//llX9+rVKzFu3DhRrlw5oVKpROXKlcWCBQuERqMx+rlm5XUyu27dOqFWq8WrV6905y5cuKBLQt78o//y5UsxceJEUbt2bWFlZSWKFSsmOnXqJHx8fPTu//r1SJuQvX7MFy9eiB49eggrKyvh4OAgJk6caND3M7NkVoiUhLZmzZrC0tJShIeH6+rXrl0r2rVrJ0qWLClUKpWoUaOGWLlypd61FSpUEAD0vl5/zw19vkII8dNPP4maNWsKCwsLYWdnJxo2bCg2b96s1+bFixdi6NChwtHRUahUKlGzZk2xZs0a3fljx46liyW7xPbx48cCgFi3bl26cxkls0II4eDgIKpVq6ZXFx8fL2bMmCEqV64sVCqVKFeunJg8ebKIj4/Xa3fw4EHRsmVLYWtrK6ysrES1atXElClTdOdff+8XLFggqlWrJurVq6f3xjOzZPbcuXPC3d1d2NjYCAsLC9GmTRtx6tSpdNe9+ZVRYmtoMhsdHW30G87r168LAOKnn35Kd+6DDz4QdevWNep+RLmJY2aJTOTp06cAAHt7e13dqVOn8OrVK/Tv3x9KZcajfAYNGgQA2Lt3r+6asLAw9O/fHwqFIkex7NmzBwDw8ccf5+j67Pzxxx/4+eef8dlnn2Hx4sUoXbo02rZtC29v73Rtvby8oFAo0Lt3bwApH2u2bdsWmzZtwqBBg/DTTz+hZcuWmDJlCiZMmGCSeF9/BLxz505d3ZYtW1C9enU0aNAgXfvHjx9j9+7d6Nq1K5YsWYLJkyfjxo0baNu2Lfz9/bN9PI1GA3d3d5QoUQKLFi1C27ZtsXjxYvz2229v9TwUCgX69euH2NhYnDp1Sle/atUqVKhQAVOnTsXixYvh7OyML774Ar/88ouuzbJly1CuXDlUr14dGzduxMaNG/Htt98a9XxXr16NsWPHombNmli2bBlmz54NV1dXnD9/XtcmKCgIzZo1w+HDhzF69GgsX74cVapUwbBhw7Bs2TIAQI0aNTBnzhwAwGeffaaLp02bNpk+9zNnzgBAht+vjERERODVq1d6/x61Wi26d++ORYsWoVu3bvj555/Rs2dPLF26FH379tW1u3XrFrp27YqEhATMmTMHixcvRvfu3XH69OkMvyfTpk3DtWvXsGvXrixjOnr0KNq0aYPIyEjMnDkT8+fPR3h4ONq3b48LFy4ASPlZfT2MYunSpbrXpmTJkgY97zfNnj0b1tbWMDc3R+PGjXHw4EGDrgsMDAQAODg4pDvXsGFD3Lx5E5GRkTmKieitSZ1NExV0r3tmDx8+LEJCQoSvr6/Yvn27KFmypFCr1cLX11fXdtmyZQKA2LVrV6b3CwsLEwBEr169hBBCLF++PNtrsvPBBx8IAHo9kVkxtmfWxsZGBAcH67X99ddfBQBx48YNvfqaNWuK9u3b68pz584VVlZW4v79+3rtvvnmG6FQKMTz588NitkQr3tJhRDio48+Eh06dBBCCKHRaESpUqXE7NmzM/w4Nj4+Pl0v8ZMnT4RarRZz5szRq0MGPbMA9NoJIUT9+vVFw4YNs405q55ZIYTYtWuXACCWL1+uq4uNjU3Xzt3dXVSqVEmvLrNhBoY+3x49emQZmxBCDBs2TJQuXVqEhobq1Xt4eAhbW1tdrMYOM5g2bZoAIKKiotKdAyCGDRsmQkJCRHBwsLh06ZLo1KlTuu/rxo0bhVwuFydPntS73tPTUwDQfdy+dOnSbIcIpP25SU5OFlWrVtXrnX2zZ1ar1YqqVasKd3d3vR7c2NhYUbFiRfHee+/p6rIaZpBWVj2zz549Ex07dhSrVq0Se/bsEcuWLRPly5cXcrlc7N27N8v7CiGEm5ubsLGxyfB3yJYtWwSAbIc6EZkKe2aJcombmxtKliwJZ2dnfPTRR7CyssKePXtQrlw5XZuoqCgAQLFixTK9z+tzr3s5Xv8/q2uykxv3yMqHH36YrqeoV69eUCqV8PLy0tXdvHkTt2/f1uv1+vPPP9G6dWvY29sjNDRU9+Xm5gaNRoMTJ06YJOb+/fvj+PHjCAwMxNGjRxEYGIj+/ftn2FatVutmy2s0Grx8+RLW1tZ45513cOXKFYMe7/PPP9crt27dGo8fP367JwHA2toaQOrPFgBYWFjojiMiIhAaGoq2bdvi8ePHiIiIyPaehj5fOzs7vHjxAhcvXszwPkII7NixA926dYMQQu/76+7ujoiICINfvze9fPkSSqVS9/zftGbNGpQsWRKOjo5o1KgRjhw5gq+++kqvt//PP/9EjRo1UL16db3Y2rdvDwA4duyY7nkCwF9//WXQEmBpe2d3796dYRsfHx88ePAA/fv3x8uXL3WPHRMTgw4dOuDEiRO5utxY+fLlceDAAXz++efo1q0bxo0bh6tXr6JkyZKYOHFiltfOnz8fhw8fxoIFC9JNQANSP33KyUoNRLmBySxRLvnll19w6NAhbN++HZ07d0ZoaCjUarVem9fJZNrE401vJrw2NjbZXpOd3LhHVipWrJiuzsHBAR06dNAbauDl5QWlUolevXrp6h48eID9+/ejZMmSel9ubm4AgODg4EwfNyIiAoGBgbqvsLAwg2Pu3LkzihUrBi8vL2zevBmNGzdGlSpVMmyr1WqxdOlSVK1aFWq1Gg4ODihZsiSuX79uUHJobm6eLtm3t7fHq1evDI43M9HR0QD036icPn0abm5usLKygp2dHUqWLImpU6cCgEHxGvp8v/76a1hbW6NJkyaoWrUqRo0apffRe0hICMLDw/Hbb7+l+/4OHToUQNbf37fRo0cPHDp0CPv27dMtixUbG6u3hNeDBw9w69atdLFVq1ZNL7a+ffuiZcuWGD58OJycnODh4QFvb+8sk80BAwagSpUqmDNnDoQQ6c4/ePAAADB48OB0j//7778jISHBoO/V2yhevDiGDh2Ke/fu4cWLFxm28fLywrRp0zBs2DCMHDkywzavn19urd5AZCwuzUWUS5o0aYJGjRoBAHr27IlWrVqhf//+uHfvnq73qEaNGgCA69evo2fPnhne5/r16wBS1nAEgOrVqwMAbty4kek12Ul7j9atW2fbXiaTZfgHWKPRZNg+bU9gWh4eHhg6dCh8fHzg6uoKb29vdOjQQW/cnVarxXvvvYevvvoqw3u8TiwyMm7cOKxfv15Xbtu2LY4fP55p+7TUajV69eqF9evX4/Hjx5g1a1ambefPn4/p06fjk08+wdy5c1G8eHHI5XJ8+eWXBvfUmcrrBetfJ+KPHj1Chw4dUL16dSxZsgTOzs5QqVT43//+h6VLlxoUr6HPt0aNGrh37x727t2L/fv3Y8eOHVi5ciVmzJiB2bNn69oOHDgQgwcPzvCx6tatm6PnXaJECSQnJyMqKirDTxzKlSune0PUuXNnODg4YPTo0WjXrp3uzZRWq0WdOnWwZMmSDB/D2dkZQMrP94kTJ3Ds2DHs27cP+/fvh5eXF9q3b4+DBw9m+P193Ts7ZMgQ/PXXX+nOv35tfvzxx0yXIsus1zk3vX6OYWFhep8iAcChQ4cwaNAgdOnSBZ6enpne4/WbsozG0xLlBSazRCagUCjw/fffo127dlixYgW++eYbAECrVq1gZ2eHLVu24Ntvv83wj+CGDRsAAF27dtVdY29vj61bt2Lq1Kk5Soy6deuG77//Hps2bTIombW3t8/wI/Bnz54Z9bg9e/bEiBEjdEMN7t+/jylTpui1qVy5MqKjo3WJhzG++uorDBw4UC9uY/Tv3x9r166FXC6Hh4dHpu22b9+Odu3aYc2aNXr14eHhkv4B12g02LJlCywtLdGqVSsAwN9//42EhATs2bMH5cuX17V9/ZF5Wpn1pBnzfK2srNC3b1/07dsXiYmJ6NWrF7777jtMmTIFJUuWRLFixaDRaLL9/hrbq/f6DdqTJ08MSohHjBiBpUuXYtq0afjggw8gk8lQuXJlXLt2DR06dMj28eVyOTp06IAOHTpgyZIlmD9/Pr799lscO3Ys0+c2cOBAzJs3D7Nnz0b37t31zr1ek9XGxibXXxtjvP53/uYnB+fPn8cHH3yARo0awdvbO9MJq0DK90Aul2f5xpPIlDjMgMhE3n33XTRp0gTLli3TLcJvaWmJSZMm4d69e7qZ42nt27cP69atg7u7O5o1a6a75uuvv8adO3fw9ddfZ9hjumnTJt3s54w0b94cnTp1wu+//57hGL7ExERMmjRJV65cuTLu3r2LkJAQXd21a9cynL2dFTs7O7i7u8Pb2xvbtm2DSqVK17vcp08fnD17FgcOHEh3fXh4OJKTkzO9f82aNeHm5qb7atiwoVHxtWvXDnPnzsWKFStQqlSpTNspFIp0r/uff/6Z6Q5veUGj0WDs2LG4c+cOxo4dqxtK8vrNTtp4IyIi8Mcff6S7h5WVVYa7Shn6fF++fKlXVqlUqFmzJoQQSEpKgkKhwIcffogdO3ZkuOVp2p8vKysrAMgwnoy8Xuj/0qVLBrVXKpWYOHEi7ty5o+sp7dOnD/z8/LB69ep07ePi4nS78WU0fOV1b2pCQkKmj/m6d9bHx0e3oshrDRs2ROXKlbFo0SLdUJG03ua1yUja+73m5+eHtWvXom7duihdurSu/s6dO+jSpQtcXFywd+/eTD95ee3y5cuoVasWbG1tcxwf0dtgzyyRCU2ePBm9e/fGunXrdBOAvvnmG1y9ehULFy7E2bNn8eGHH8LCwgKnTp3Cpk2bUKNGDb2Pzl/f59atW1i8eDGOHTuGjz76CKVKlUJgYCB2796NCxcu6JYqysyGDRvQsWNH9OrVC926dUOHDh1gZWWFBw8eYNu2bQgICNBt4frJJ59gyZIlcHd3x7BhwxAcHAxPT0/UqlXL6OV3+vbti4EDB2LlypVwd3dPN4Fk8uTJ2LNnD7p27YohQ4agYcOGiImJwY0bN7B9+3Y8ffrUZL2fcrkc06ZNy7Zd165dMWfOHAwdOhQtWrTAjRs3sHnzZlSqVMkkcb0pIiICmzZtApCylNnrHcAePXoEDw8PzJ07V9e2Y8eOUKlU6NatG0aMGIHo6GisXr0ajo6OCAgI0Ltvw4YNsWrVKsybNw9VqlSBo6Mj2rdvb/Dz7dixI0qVKoWWLVvCyckJd+7cwYoVK9ClSxfdR/8LFizAsWPH0LRpU3z66aeoWbMmwsLCcOXKFRw+fFiXKFauXBl2dnbw9PREsWLFYGVlhaZNm2Y4HhsAKlWqhNq1a+Pw4cP45JNPDHodhwwZghkzZmDhwoXo2bMnPv74Y3h7e+Pzzz/HsWPH0LJlS2g0Gty9exfe3t44cOAAGjVqhDlz5uDEiRPo0qULKlSogODgYKxcuRLlypXT9YhnZsCAAZg7d266bXrlcjl+//13vP/++6hVqxaGDh2KsmXLws/PD8eOHYONjQ3+/vtv3fcJAL799lt4eHjAzMwM3bp1g5WVFa5fv65LlB8+fIiIiAjMmzcPAFCvXj1069YNQMqnGK+HoJQpUwZPnz7Fr7/+ipiYGCxfvlwXV1RUFNzd3fHq1StMnjw53RbAlStX1tsxLCkpCf/++y+++OILg74HRCYh1TIKRIVFZpsmCJGy5FPlypVF5cqV9RbI12g04o8//hAtW7YUNjY2wtzcXNSqVUvMnj1bREdHZ/pY27dvFx07dhTFixcXSqVSlC5dWvTt21ccP37coFhjY2PFokWLROPGjYW1tbVQqVSiatWqYsyYMeLhw4d6bTdt2iQqVaokVCqVcHV1FQcOHMhy04TMREZGCgsLCwFAbNq0KcM2UVFRYsqUKaJKlSpCpVIJBwcH0aJFC7Fo0SLd7ka5Ie3SXJnJbGmuiRMnitKlSwsLCwvRsmVLcfbs2XRLmGW1acKbXi/VlJ22bdvqLZZvbW0tqlatKgYOHCgOHjyY4TV79uwRdevWFebm5sLFxUUsXLhQrF27Nt3yToGBgaJLly6iWLFiepsmGPp8f/31V9GmTRtRokQJoVarReXKlcXkyZNFRESEXjxBQUFi1KhRwtnZWZiZmYlSpUqJDh06iN9++02v3V9//SVq1qwplEqlQct0LVmyRFhbW6dbigyZbJoghBCzZs0SAMSxY8eEECk7WC1cuFDUqlVLqNVqYW9vLxo2bChmz56tex5HjhwRPXr0EGXKlBEqlUqUKVNG9OvXT285uaz+Lbz+HYEMlve6evWq6NWrl+41rFChgujTp484cuSIXru5c+eKsmXLCrlcrvd9THvvN78GDx6su37Lli2iTZs2omTJkkKpVAoHBwfxwQcfiMuXL+s9zuvnYcg9hRDin3/+EQDEgwcPMny9ifKCTIgMPrMkIiLK5yIiIlCpUiX88MMPGDZsmNThFEk9e/aETCbLdoMIIlNiMktERAXWwoUL8ccff+D27dt6y26R6d25cwd16tSBj48PateuLXU4VIQxmSUiIiKiAotvY4mIiIiowGIyS0REREQFFpNZIiIiIiqwmMwSERERUYFV5DZN0Gq18Pf3R7FixUy6RSARERER5YwQAlFRUShTpky2K5UUuWTW398fzs7OUodBRERERNnw9fVFuXLlsmxT5JLZ11ss+vr66vYyJyIiIqL8IzIyEs7Ozrq8LStFLpl9PbTAxsaGySwRERFRPmbIkFBOACMiIiKiAovJLBEREREVWExmiYiIiKjAYjJLRERERAUWk1kiIiIiKrCYzBIRERFRgcVkloiIiIgKLCazRERERFRgMZklIiIiogKLySwRERERFVhMZomIiIiowGIyS0REREQFFpNZIiIiIiqwmMwSERERUYElaTJ74sQJdOvWDWXKlIFMJsPu3buzveb48eNo0KAB1Go1qlSpgnXr1pk8TiIiIiLKnyRNZmNiYlCvXj388ssvBrV/8uQJunTpgnbt2sHHxwdffvklhg8fjgMHDpg4UiIiIiLKj5RSPvj777+P999/3+D2np6eqFixIhYvXgwAqFGjBk6dOoWlS5fC3d3dVGESERUYyRottCL7di9jEhCbqMm+oTYZENpsm0XEJiIyPhmyNHXquEDItMnZP0YaiuQ4qOOCkCjk8A+Ph6VKYdT1hVlwVDzik7Swk8fDNjEAiXJLaCEgYMA3PJdFIA7BiNT7fitEEorH+yJWaWfQPYIi41HM3AwyWfZt0xIQCFDEwlzk/s/Gc0U0LIUSMhgZ1FtIkmlxXxmO0hrLt7qPlSYCGpkSWplp/s1oNQJyhQxNHTtgRM/5JnmMnJI0mTXW2bNn4ebmplfn7u6OL7/8MtNrEhISkJCQoCtHRkaaKjwiKgBeRmefxN0JiER4bJKuHJOYjLsBUXC0UWfYPjAiHk9CY1DO3sKoWMy0CSiWHIbgqAQ8CI6GRWIYnCy0ULzxmZmjeAkVkqBN82FaJ+0JaCBHZfEckTJrRMEKSRqBRvL7CBPWSMrm17scgHU28TnJwo16PrmtoQnvHSuTIVKe+noGKhXQGJHAxMll8FMqYS4yTyS1AK6p1XDUZP+m4YK5GpctzFE/Pl4XxRVzc1hrtbDSZvxmIkieD/+EWwHAC8PaljRlIAVPsCI+F+5iwBtUIwkh8OrEK7w88BKVvq2EMq/u5fpjvK18+C8hc4GBgXByctKrc3JyQmRkJOLi4mBhkf4Pyffff4/Zs2fnVYhE9JY0WoHb/pFITJMAPAiKxt3AKJSwUhl0j2svwnHleTjCYhJRysYcgZGpfyTUSIQNYgAANrJYOMrC4SILxDsyX9SQP4evcIRG6GeTlgAaAGgsv4t4qBEurNI9ZgvFbQQEFkfyf71FzvIQ4564DIAaKRlQ9h2hehxEeMrBf2EXl0Ubd4MCJglAjFz/e5QkAwIVSsgBCABPzZQIUCrxr6UFApQKuCQlQ/lf4nnG0rg3HXnpqrm5XjlaLke0nHO1SRqaOA381/sj4lwEACDsWBjQWeKgMlCgktmcmDJlCiZMmKArR0ZGwtnZWcKIiAq++CQN4pNSk00hAL/wOLzZSaURAmcfvYQ8TYfXpWevUNxSBTNlSuX+m4GwMTfD49AYgx7bFtGQpflYtbgsCnVlj5EAMzjLgjFEeQBdhRlKyCKhVGsREF8cUAGV5QEG3b8p7hrULiOlZWHIw08nsxUqz7zrSysArRBQK1MSJS1SEsI32SSHQg6BxxZ1IACEKPQzbQEgQKmBQsiQoNHAykyp+9jYIikcSQoLRJiXxjN5PCz+e5OQDIF7ilg8kcfBRWuBy4pIOAoVzP87rxBJSJarESRLQIJMA4s0f6riYNywhdeClQX7z11xpCS5AoBcBsiEgJDJkSgTiNLGo6aqTJ7GE6aJgYBAWaU9qqpSO5lkQkArV0FrZthH5kq5TPczaAwtBOI0CahsWdboa7OTqE1CeQunPB1qICBgp7SGlcI8+8ZZkSuhsXLKvp0B7t6+j0mzvkXE0wgoFAqMGT8CQz8dCMfi5XLl/rmpQP3rLlWqFIKCgvTqgoKCYGNjk2GvLACo1Wqo1Rl/NEhUlCQma5H838eVUfHJCI9NQlBkPO4HRUHxX7aZkKzFlWevoP0vOVXKZbjhl/KO3MJMAaVchqiEnCUTmVEiGVVj76GiPKX3tLgsCpVlAeilOImXwgY15M8BADFCDStZQla3SpXmb1BlmWFJbG7SWP6XRGo1UMSHIcGpPjLMcoUW6mAfxFTtDkAOCzMZZKH3IKvWKX3bSH+gbANAmeb3WUIUUK0TYG4LWDqk3hZAUFww/KP9kaRNSlMv8Cj8EV5EvYBSrsThZ4cREBMAjcjqo8nXf7jCDXvyehQAEgE8y7RFqDwlviBZ4htnYnVHOU1gDfFehfdSHi05FjGJMajvWN/ga8Piw1DKqhRKWmT+pkFAQCM0cLFxyfZ+cpkctRxqwUKZ+vdMDjkUco4bprwjhICnpyfGjx+PhIQEODs7Y9u2bWjRooXUoWWqQCWzzZs3x//+9z+9ukOHDqF58+YSRUQkPa1WICQ6AS9exSI6QYOo+CQcvRuMGy8i8CA49z5ujkvKOOGRQwtrxKKcLBRlZaGoJAtAFPR7ZcrLgvCOzBe2shj4Cwe8K/dBoCiOKnL/LB/TMc2YTYMT2YyY26b8Pz4CMLMEkmKB6l1T6gKvA87NgGKlAMsSQKnagE0WPQ9m5oB1Jj0fChUgV+DN1CO7t9MqTRIiEiMQl007jVaDgJgAyP7r+gyMCcTZ+5txL+wenkY+Ra0StXA+8Hw2d8nf1Ar9V0srtEjSJsHFxgVymVxX9zTyKVqVbaXXe/Y44jHqlqwLO7UdkrRJiE6MRrli5VDXoS6q2FeBndpO19ZcaQ4zuVmePCeiguThw4cYN24ckpKS0K1bN/zxxx8oUaKE1GFlSdJkNjo6Gg8fPtSVnzx5Ah8fHxQvXhzly5fHlClT4Ofnhw0bNgAAPv/8c6xYsQJfffUVPvnkExw9ehTe3t7Yt2+fVE+BKNcJIRAQEY+AiDhsPPsM5YtbIiQ6EY+CoxEYGY/nYSk9VqVtzREQkfMJA+/InsM+zdhKcyTAWRaCuDSpVx3ZY0TACuK/wZj1ZI+gVFtAqYlHM+GTo8dtgJR/81VkWSeyGSpZHQi5CzjWAmz/+3hRCODhYaDxcMC+AhD3CihVF6jYJqUXU5V+fKupJGuTkZAUg7C4MBz1PYqjz4/iedRz1CpRC2f8z8BWbauXUAHAw/CHGd8sB3IjkW1cqnGWH68+iXiCKnZVUMqqlK4uJikGGqFBjeI1Mr1OQCAyMRI1S9RMKQsBc6U5KttWho3aBhZKC1iZ5d33iogyVrVqVSxZsgRJSUn48ssvdW+e8zOZEFlMxTSx48ePo127dunqBw8ejHXr1mHIkCF4+vQpjh8/rnfN+PHjcfv2bZQrVw7Tp0/HkCFDDH7MyMhI2NraIiIiAjY2NrnwLIjeTlyiBmceheLo3WDEJ2mx44qBM4EzIYcWnyr2YYrZVlzXVkSkSOklVSrkqCyeoaQsn67oUb4FUKVDynHcK8C2XEry6lQLsCoJo9fvMZJGq0lZ8icmAL6Rvhm3ERqc8T+DayHXcCP0BmqWqInbL2/DRmWDyMT897pWs68GlVyF5mVSP73SCA0iEyNR0aYiqthVgYWZBeo41IFCpigQf7SIKHcJIbBixQq0bt0arq6uUoejY0y+JmkyKwUms5SXNFqBZy9jEJuoQURcEl7GJGLr+ee46R+BqPicjwOUQQt7RKOhdRgctUFwTHwOc7UFRmi25GL0RpIrgbKNAMfqgNomJRFNKykWKF4RKFEFkCkAtTVgYW/SkJ5GPEVYfJiufCX4Cp5EPIFvlC/8ovxQwqIEZDIZbr+8bdI43mSp1B+GEZuc0tv+rvO72U468Y3yRUXbinCyTBnq4Bfth0q2lfCu87uoZFcJZnIzKOVKfoRORNl69eoVhg0bhl27dqFq1aq4evUqrKzyxyckxuRrBWrMLFF+df1FOA7cCsTzsDhc8w2HQi7DEwNn52fmHadiUMhlqF66GHq6loVZxFNUDjsBx7NzUhu9zoeVyPnygq3Gpx7HhqWMB7UpnVqXGAM41kDqBCYB2Lmk9JTaOgNKw5bLMpUkTRIeRzzGr9d/RWxSLE77nzb42uC44FyNpax1WfhF+6G+Y334R/vD0dIRA2sMRN2SdWFlZgW1Qg1LA2d5ExGZ0vnz59G3b188e/YMKpUKY8eOhaVlwfz9xGSWyEDxSRpcfxGBa77huB8UhdDoBCQka3Hm0ctcuX/lklboXKc0XJ3t0KC8PezlMcD534B/FwK3c5CpKtSAxxagwhsTJGVywCz/rbMZlRiFkNj0a7Mmi2QcfX4Uj8Mf4/iL44hLjkP14im9vnfDcr6MVmbqO9ZHSGwIOlfqrJtwpBePNhkRCRF41/ldNC/dHGYK9oASUcEhhMCSJUvwzTffIDk5GZUrV4aXlxcaNjTlNiWmxWSWKI3b/pG48vwVtl54jlv+KWMgy9iaw/8tJloBQFk7C7SrXhK+YXGoWy5lZn2fRs4oZWsOM7kMeHgE2NwDuFsZOPPI8Bub2wGONYFSdQCVZcrEJ2snwKXlW8Wbm3yCfXDw2UEIIXAh8AKq2FWBTCbDvbB7iEqMQlBsUPY3eYOhSayjhSMAoHOllFW+hRB4GPEQPSv3RHmb8ihhXgLFzYsDAJRyJceMElGhFh0djX79+mHv3r0AgD59+mD16tUFftglk1kq8q75hmPKzhu4HZDxBB5jElmPxs7oWMsJZews4GCthoN1BosyRfoDT08BPzVJfy7MgES29USgfHOg6nsGx2UKQgi8SngFrdDieeRz3Ht1DxcDL8JGZYMDTw8gOinjZcHuv7qfazGo5CokalPWJ61evDqq2lXFxzU/RmW7ylAppB3+QESU31haWiIhIQFqtRrLly/HZ599VijexDOZpSLr9MNQDPjdsKWMHIupU3Y/ikpA+eKWeL9OKZSzs0DlktZwLm4JRxs11MpMFjYPuA782jplrdP4COMDdWkNdJiRMrnKRNtaPo14ikRtInyCfRCZGIk7L+/A3tweoXGheBLxBOWLlde1vRB4AWqFGq8SXpkklh6Ve6T75RqdGI3IxEh0qtgJzUo1Q7li5QrFL2AiIlPTarVISkqCWq2GXC7Hxo0bERgYiHr16kkdWq5hMkuFXnySBn+cfoq1p5+gdhkbKOQyHL6T9cSfye7voKKDFdxqOEFlzFaLvhdSvgKuATe83wgkm0RWaQH0/gOo3MFkk6qEEIhKisKSS0tgo7LBX4/+0pvtn5nHEY/1yq9n3xvKXm2Phk4N8UHVD2CntoO9OmUVAzOFGRwtU4YCZDQ+lYiIci44OBiDBg1C+fLl8dtvvwEAnJyc4OSUO1ve5hdcmosKFa1WYNmRB9h7zR+PjVxNwHNgA7xXs5Rua1fDHlADnFgEnPcE4rJPCvU0GATU9TDJ+NbAmECc8T+DHy7+gJikGDhZOuVobKohXGxcYGVmBRlkqFOyDho5NYKLrQsslBYoZ80eVCIiKfz777/o168fAgICYGFhgVu3bqFixYpSh2UwLs1FRcqrmET4hceh68+ncnT93jGtULusrXEXXfoD2PulERfIgPbfAm0mG/c42UjSJuFGyA0c8z2GdbfWZdrOkETWTG6G7pW740boDQysMRBmCjPd8IIy1mX0ek5VchWsVdZvHT8REeUujUaD+fPnY9asWdBqtahRowa8vb0LVCJrLCazVCAlJmsxddcNbL9s+G5Z5YtbYnaPWqhRKuUdnoO1CkqFgR9tJ8YAXgOBR0cNa//+j4CZecpELYeqBsf4piRNEgRSPzy5/fI2rgZfxb1X97DvsfHbOBc3L64bVvC+y/v4qNpHsFBaoJZDLX7MT0RUwAUGBmLgwIE4cuQIAGDIkCFYsWJFvtkIwVSYzFKBkaTRwu9VHD7fdBl3A6Oybb9pWFO0qFwCMhly/lF38F1gZdPs2xWvDPRcCZRvlqOHOR9wHrse7kJAdADs1HY46mtg0pwFpVyJnlV6op1zO7Qq24rJKhFRIabVauHm5oZbt27B0tISq1atwqBBg6QOK08wmaV8TQiBT9ZdxLF76RfTf1PlklboUrcMxrtVzVnyKgQQHZwy/vXUEsOuGX0ZcKiSbbOoxCgkaZMQlRiFyIRI+IT44G7YXex5tMf4ODNQwaYCelfrDVdHV9QrWXhmqBIRkWHkcjkWLlyIqVOnwsvLC9WrV8/+okKCE8AoXwqOjMfUXTeyXXXApYQl/hrdCrYWOdyFKT4C+KMLEHTDsPblmgAf7wTUxbJsdjHwIkYdGYW45LicxZWGtZm1bser8IRwPAx/iL7v9EWN4jXQpHQTOBdzfuvHICKigsff3x8PHz5EmzZtdHXJyclQKgt+XyUngFGB9eJVLFotPJZlmzK25ihZTA2vEc1hbpbJ2q6Z0WqBncOBmzuMu6z9DPjV+yhlK9iEcIRGPMSFgAt4HvVct7SURmhw7PkxPI18alxMaXzZ4EvUcagDJysnOFk6Qa1QczUAIiJK58CBA/j444+RlJQEHx8fVKhQAQAKRSJrrKL3jClf8rr4HF/vyLp39N68TplvTJAVrRY48xNwY7vhPbD1+gEtxkA41sSA/w3AjSfrgCfrjH/sNKzMrNDQqSHuvrwLtwpuuBt2Fx9U/QBNSjWBo6UjlHL+cyQioqwlJydj+vTpWLBgAQDA1dUVycnJEkclLf71JElotAL+4XHw/PcRNp9/nmm7fk2cMbNbLeN7YF979RRYbsAY0pZfIrHt19j9ZC/2Pt6Lq8GnUelsQLrNAoy1ym0VmpZqCjNFDodBEBER/cfX1xf9+vXD6dOnAQBffPEFFi9eDHNzc4kjkxaTWcpTh24H4dMNl7JtN6SFC6Z0rp6zntiQe8C2AcDLB1k2ix11AfdFHL448gWi/HcCW3fqnc8oka1VohYq2KR8lHP75W20LNsStR1qw9EiZaiBgEAxVTFUtavKBJaIiHLNvn37MGjQIISFhcHGxga///47evfuLXVY+QKTWTK5mIRkXHsRjv6rz2fbdu2QRmhfPYfb7MWGAT9kvih0EoBVrYZiW/AFRCVFAf/7yKjbXxxwEebKov3ul4iIpLFv3z6EhYWhUaNG8PLyQqVKlaQOKd9gMksm8TgkGuO9r+Gab3iW7Zxs1LCzUOGPoY1Rxs4ix48X/0MlHJHFQWFliRMWFnipkOOZmRli5DKEK9L07vodyfZeTUo1Qb/q/dCybEtYKHMeExERUW5ZsmQJXFxcMG7cOKjVaqnDyVe4NBflqqj4JHT7+RSevozNst2GT5qgReUShu/A9YbYpFis8FmBjbc35uj6tKrZV0PLsi0xynUU1Ar+giAiIunt3r0bmzZtgpeXFxSKHM4bKcC4NBfluXl7b+P3U0+ybNPTtQyqlSqGkW0rG73clBAC10Ov47tz3+FO2J0cx6mSq2Bvbo/fO/6OCjYVuOwVERHlKwkJCfjqq6/w008/AQDWrFmDzz77TOKo8jcms/RWvth8Gf+7EZjp+fFu1fBpm4qwVBn3o/bz1Z9xI+QGLgVdQpI2yeDr6jvUhZuLO8yV5qhXsh7KWJeBQqaApZmlUY9PRESU1x49eoS+ffvi8uXLAIBJkyZh6NChEkeV/zGZpRyrPfMAohMyXtuuh2sZzOleG7aWhs3oF0LglN8pfH3i65TJWYbGkJCAH4NDUc65JTD4b4OvIyIiyk/+/PNPDB8+HJGRkShevDg2bNiALl26SB1WgcBklox22z8SnX86meG581M7wMnG8Bn/QggsurQIG25vMKi9c1ISBkRG4cOoGJgLAfRcBdTtC8iL3ngiIiIqHL7//ntMnToVANCyZUts3boVzs7cqtxQTGbJYDdeRKDbilMZn5vVEcXMDeuFjUqMws4HO7Ho0qJs227xC4STRoOSGg10o1ubfQG4zwc43pWIiAqBrl27Yt68eRg3bhzmzJlTJLekfRt8tcgg3hd98dWO6xmeOz7pXYMT2YuBF/HJgU+ybDM/OBTdYjJYDWHoP0CFFgY9DhERUX52//59VKtWDQBQp04dPHz4EKVLl5Y4qoKJySxl6aZfBLr+nHFv7MZhTdC6akmD7qPRauC60TXLNkee+8FRo0l/ouEQoP10wMrBoMciIiLKr+Li4jBu3Dj88ccfOHnyJJo1awYATGTfApNZylSdWQcQFZ9+gtecHrUwqLmLwfd5+OohPtjzQbp6tdwMG32fo0ZiJqsV9PodqMut+oiIqHC4c+cO+vTpg5s3b0Imk+HChQu6ZJZyjsksZej0w9AME9kTk9uhfAnDlrmKS45Dk81NMjz3o7I8Oj3IuMcXFdsCA7YDSpXB8RIREeVn69evxxdffIHY2Fg4OTlh8+bN6NChg9RhFQpMZimdrj+fxE2/SL26LZ82RYvKhn/MHxIbgvZ/tk9XX9KiJA7cvgwzPM/4wh6/APUHGhUvERFRfhUTE4NRo0Zh/fr1AIAOHTpg06ZNKFWqlMSRFR5MZknPogP30iWy3iOao0nF4gZdf8b/DEYcGpHhuYkNJ2JIdBxw+7L+iY93AZXTJ75EREQF3bZt27B+/XrI5XLMnj0bU6ZMKZLb05oSk1nSmeh9DTuuvNCrm/J+dYMS2czGxQKAXCbHtUHXgF0jgWtb9E9+/RSwsM9pyERERPnaJ598ggsXLqB///5o27at1OEUSkxmCQAwb+/tdInstRkdDdrBa8LxCTj07FCG5z6v9zlG3T4JzLJNf3LofiayRERUqERFRWHu3LmYPn06ihUrBplMhl9//VXqsAo1JrNFXEhUAhp/dzhd/bqhjbNNZCMSItBqW6sMz/3S4Re0KdcGOPAtcP+f9A0G7wUqNM9RzERERPnRtWvX0KdPH9y/fx9BQUG6cbJkWkxmi7DM1pD9Z1xr1Chtk+l1lwIv4bvz3+Fh+MN0575u/DUG1vxvApffZeDsivQ3mPyIa8YSEVGhIYTAr7/+ii+//BIJCQkoV64cPvvsM6nDKjKYzBZRGq3IMJHdO6ZVlonszDMzsfPBzgzP7ei+A9XsU3Yzgd8VYPUbk7q+fgZY2OU0ZCIionwnIiICn332Gby9vQGkbE27bt06lChRQuLIig4ms0VQfJIG1afv16v7rE0lTO1cI8vr2nm3Q2hcaLr6DuU7YFm7ZakViTHA6nb6jbosYSJLRESFyq1bt9CjRw88evQISqUSCxcuxPjx4yGTyaQOrUhhMlsEvZnI1i5rk2Ui29arLcLiw9LVz2w+E10qdYGF0iK1MjoYWFRVv2GnBUDjYW8VMxERUX7j4OCA6OhoVKhQAV5eXmjatKnUIRVJTGaLmB6/nE5Xt2dUxpO4AOCLw19kmMge/ugwnKyc9CvjI9InssXKAM1G5ihWIiKi/CYuLg4WFimdOE5OTvjf//6HihUrwt6eq/NIRS51AJR3wmMTcc03XK/u6YIukMvTfxwihMDA/w3ESb+TevUOFg64Nuha+kR2/1RgQXn9uuKVgAm3cyN0IiIiyZ0/fx41atTAtm3bdHUNGjRgIisx9swWEYnJWrjO0V8L9sLUzPeErruhbrq6qx9fhVKewY/Md2WApJj09WOvGh0nERFRfiOEwNKlS/H1118jOTkZCxcuRJ8+fSCXs08wP+B3oYh4cy3Zn/vVh6ONebp2d17eQZ31ddLVz24xO30iG3w3ZTOENxNZ1wHAzPC3DZmIiEhyL1++RPfu3TFx4kQkJyejd+/eOH78OBPZfIQ9s0VAfJIGEXFJenXd6pVJ1+7hq4fos7dPuvorH1+BmfyNDRSC7wArm6V/sJFnAaeabxUvERFRfnDmzBl4eHjA19cXarUay5Ytw4gRI7haQT7DZLaQ02hFutULnnzfOYN2Gnyw54N09ZcHXk6fyAIZJ7LTQgClKsexEhER5RdPnjxB27ZtkZycjKpVq8Lb2xuurq5Sh0UZYDJbiAkhUHnq//TqhrRwSfeOctaZWdjxYIde3TdNvsGAGgMyvvEsW/3y+z8ATUe8dbxERET5RcWKFTFu3DgEBATA09MTxYoVkzokygST2UKs4pT/paub2S11CIAQIsOJXgAyT2RXZzBpjIksEREVAv/++y8qVqyI8uVTVudZuHAh5HI5hxXkcxy9XEh9vOZ8uron33fW+wfZYGODdG2UciVuDL6R/oZCpPTI+l3Srx99KX1bIiKiAkSj0WDu3Llo3749PDw8kJSUMs9EoVAwkS0A2DNbCCUma3Hygf62s28msvuf7EeySNZrc77/eViaWWZ80xWN0tdNeghYl3zreImIiKQSFBSEAQMG4MiRIwCAatWqISkpCWZmGcwXoXyJyWwhVG3aP3rlNxPZuOQ4TD4xWa9NhisWvPb3OODlQ/06TvYiIqIC7ujRo+jfvz+CgoJgaWmJlStXYvDgwVKHRUbiMINCZoKXj155bIeqeolsgiYBTTY30WvzV8+/Mk9kn54CLq/Tr5sZzkSWiIgKLI1Gg5kzZ8LNzQ1BQUGoXbs2Ll68yES2gGLPbCGRpNGi5YKjCI5K0Kuf8F611DbaJDTapD9coG25tqhkWynjmwoBrOuiXzd0P8DxQ0REVIAlJSVh9+7dEEJg+PDhWL58OSwtMxlmR/kek9lCICI2CfXmHExXf/FbN92xb5QvOu9Mv77sig4rMr+xz2b98se7gQrNcxomERFRvmBubg5vb29cvnwZ/fv3lzocektMZguBjBJZr8+aoWQxNQAgPjk+w0T2+qDrWd/4r1GpxzI5ULndW8VJREQkheTkZEyfPh1WVlaYNm0aAOCdd97BO++8I3FklBuYzBZw8/beTlf38Lv3oVSkDId+FP4IPf/qqXfeUmmJs/3PZr3cyHVv/fLIM28bKhERUZ7z9fVFv379cPr0acjlcvTt2xdVq1aVOizKRZwAVoBN2XkDv596olf3dEEXXSJ7++XtdInsO/bv4PyA85DLsvnW7/xUv+xY423DJSIiylP79u2Dq6srTp8+DRsbG2zdupWJbCHEZLaAEkJg64XnenUnJqcOA4hPjkffvX31zlezr4bt3bcbcnP98uencxwnERFRXktKSsLkyZPRtWtXhIWFoWHDhrhy5Qr69OkjdWhkAhxmUEBdef5Kr3zxWzfdGNlETSIab26sd752idrY2nWrYTd/ckK/XKp2juMkIiLKS0IIuLu749ixYwCAsWPH4ocffoBarZY4MjIV9swWUOefhOmObcyVukQWAGafna3XtlfVXoYnsgCwoXvqsWOtHMdIRESU12QyGfr27Qs7Ozvs3LkTy5cvZyJbyDGZLaB+2H9Pdzymfer4n9ikWOx5tEev7czmMw2/sUZ/i1t0+j5H8REREeWVhIQEPHr0SFf+7LPPcPfuXXzwwQcSRkV5hclsAXTpaZheuVPtUrrjplua6p0739+AyV6vJScCc0vo11Vqm6MYiYiI8sLjx4/RsmVLdOjQAa9epQzBk8lkcHJykjgyyitMZgugjzzP6pWdi6fsWvIqXn8crY3KBpZmRuxostZdv9xwSE7CIyIiyhPbt29H/fr1cfnyZURFReH+/ftSh0QSYDJbwHl91kx33Marjd650/2MWIUgIQrwv6Jf12XJ24RGRERkEvHx8Rg1ahR69+6NyMhItGzZEj4+PmjatGn2F1Ohw2S2gHkYHK1XblopZViAb6SvXv3UplONu/H35fTLM8MBucLY8IiIiEzqwYMHaN68OVauXAkA+Oabb3Ds2DE4OztLHBlJhUtzFTCfb7qcYX3nXfrb1Xq842H4TUPe+Fim/sdAVruDERERSWTGjBnw8fGBg4MDNm7ciE6dOkkdEkmMyWwBotUKvZ7ZZX1dAQDnA87rtVvcdnHWW9WmJQTwi/6atOix4m3CJCIiMpkVK1ZAJpPhxx9/RNmyZaUOh/IBDjMoQL7ecV2v3MO1DABg+MHhevUdXToaftO94/XLXRbnKDYiIiJTuHPnDmbOnAnx3+6UJUqUwJYtW5jIkg57ZgsIIQT+vPxCV25YwR4ymQxaodVr96vbr4bfNOQ+cPkP/bqGn7xNmERERLlmw4YNGDlyJGJjY1G5cmUMGjRI6pAoH2LPbAFxNzBKr7xxWBMAgNc9L736FmVbGH7TN4cXTPED5PyRICIiacXExGDo0KEYPHgwYmNj0b59e3TsaMSnjlSkMHMpIMZuvao7LmdvAUuVEg9fPcT88/N19a3KtjL8hokx+mX7ioDa+m3DJCIieis3b95E48aNsW7dOsjlcsyZMwcHDx5EqVKlsr+YiiQOMygAtFqBB2kmfn3WphIevnqID/bob9M3tYkRy3HNL6NfHufzFhESERG9va1bt2LYsGGIi4tD6dKlsWXLFrz77rtSh0X5HJPZAmDHlRd6ZY/G5dFwcz29unENxsHZxsA19sKf65ebj36b8IiIiHKFo6Mj4uPj0bFjR2zcuBGOjo5Sh0QFAJPZAsDrYuqGCG2qlcT622v0zjdwbIDhdYa/eVnmltXRL3ec9zbhERER5VhMTAysrKwAAB06dMC///6Lli1bQs45HGQg/qQUAJeevdIdT3jfET9d/UlXVsgUWP/+esNvFhumX+66jBskEBFRnhNCwNPTExUrVsTDhw919a1bt2YiS0bhT0s+FxmflFqQJePjg930zp/yOGXcDc++sSFCo6E5jIyIiChnIiMj4eHhgZEjRyIkJAS//mrEspJEb5A8mf3ll1/g4uICc3NzNG3aFBcuXMiy/bJly/DOO+/AwsICzs7OGD9+POLj4/Mo2rx39Xm47tii/O965xo5NYK1ysgVCE6m2RShete3iIyIiMh4ly9fRoMGDeDt7Q2lUolFixZh4cKFUodFBZikyayXlxcmTJiAmTNn4sqVK6hXrx7c3d0RHBycYfstW7bgm2++wcyZM3Hnzh2sWbMGXl5emDrViFn8Bczgta+TewGl5VNdffli5fFHpz8yvCZT17bpl93nZ9yOiIgolwkh8PPPP6NFixZ49OgRKlSogJMnT2LixIkcVkBvRdKfniVLluDTTz/F0KFDUbNmTXh6esLS0hJr167NsP2ZM2fQsmVL9O/fHy4uLujYsSP69euXbW9uQeUXHqc7LlZjit65vR/sNf6Gu0bol+0r5CQsIiIio61btw5jx45FYmIievbsiatXr6JZs2ZSh0WFgGTJbGJiIi5fvgw3N7fUYORyuLm54ezZsxle06JFC1y+fFmXvD5+/Bj/+9//0Llz50wfJyEhAZGRkXpfBcXea/4AAJlCf/ev0lalITN20tY1/Z3C8OXNtwmNiIjIKAMGDECrVq2wfPly7Ny5E/b29lKHRIWEZEtzhYaGQqPRwMnJSa/eyckJd+/ezfCa/v37IzQ0FK1atYIQAsnJyfj888+zHGbw/fffY/bs2bkae15ZcSxldqeZ3WW9+gMfHjD+Zrs+0y/bGbgmLRERUQ4IIbBlyxb06dMHZmZmUKlU+PfffzmkgHJdgfqJOn78OObPn4+VK1fiypUr2LlzJ/bt24e5c+dmes2UKVMQERGh+/L19c20bX4TFZ8MAFA77tfVDawx0PheWd+L+uVx1982NCIiokyFhYWhR48eGDhwIGbMmKGrZyJLpiBZz6yDgwMUCgWCgoL06oOCgjLdf3n69On4+OOPMXx4ygYBderUQUxMDD777DN8++23Gf4jUavVUKvVuf8ETCwgImW8rFVV/UR9cK3Bxt3o1VNgjZt+HcfKEhGRiZw5cwYeHh7w9fWFSqVC+fLlpQ6JCjnJ3iKpVCo0bNgQR44c0dVptVocOXIEzZs3z/Ca2NjYdAmrQqEAkPJxRmHS/PujAAC5MkavvpRVxol+ppbrb3uL/t5vExYREVGGtFotFi5ciDZt2sDX1xdVq1bF+fPnMXLkSKlDo0JO0u1sJ0yYgMGDB6NRo0Zo0qQJli1bhpiYGAwdmrKQ/6BBg1C2bFl8//33AIBu3bphyZIlqF+/Ppo2bYqHDx9i+vTp6Natmy6pLQyehP6XwMr118+9MvCKcTc6+sY2tSWqANXc3yIyIiKi9EJCQjB48GD8888/AIB+/frh119/RbFixSSOjIoCSZPZvn37IiQkBDNmzEBgYCBcXV2xf/9+3aSw58+f6/XETps2DTKZDNOmTYOfnx9KliyJbt264bvvvpPqKZjE19tTxrQqrR7q1ZspzIy70Zk3dvsacznjdkRERG8hLCwMJ06cgLm5OX7++WcMGzbM+PkdRDkkE4Xt8/lsREZGwtbWFhEREbCxsZE6nAx9tOoMLj17BXWpXVDZnwcAvF/xffzQ5gfDb/LgELD5o9Ty5MeAVYlcjpSIiCjFX3/9hUqVKqFOnTpSh0KFgDH5GqcV5jMRcUm49OwVAEBh8UxX38CxgeE3EUI/kQWYyBIRUa4JCgpCp06dcOLECV1djx49mMiSJCQdZkDp1Zt9UHesMA/UHbcp18bwm+wYpl/22PK2YREREQEAjhw5ggEDBiAoKAiPHz/GnTt3CtW8FSp42DObj2i0qSM+ZMpwvXOOlo6G3+jmjtRjczugepe3C4yIiIo8jUaDmTNn4r333kNQUBBq1aqF3bt3M5ElybFnNh/x8X2lO1baXNM7p5Qb+K16fl6/POHO24ZFRERFnL+/PwYMGIDjx48DAIYNG4affvoJlpaW0gZGBCaz+crOK366Y3Onf3THn9b51LAbCAGs7ahfp+IvGiIiyjlfX180bNgQISEhsLKywq+//ooBAwZIHRaRDpPZfMT7UspWu3LzF3r1bhXcMmqe3okf9cuD/sqNsIiIqAgrV64c2rVrh3v37sHb2xvVqlWTOiQiPUxm85EkTcqYWVXxk3r1NUvUNOwGx95Yb7fSu7kQFRERFTUvXryAtbU17OzsIJPJ8Pvvv0OpVMLCwkLq0IjS4QSwfCJZo9Udm9mmjpf9vvX3ht0gKlC/PP52boRFRERFzL59++Dq6orhw4frtoovVqwYE1nKt5jM5hPPw2L/O9Lq1b9X4T3DbrD4Hf2ybdm3D4qIiIqMpKQkTJ48GV27dsXLly/x5MkTRERESB0WUbaYzOYTYTGJAAC10x69erVCnf3FDw7rlzstzK2wiIioCHj27BnatGmDRYsWAQDGjBmDM2fOwM7OTtrAiAzAMbP5xLhtPoA8Aari53R1jZwaZX+hVgNs/lC/rumI3A2OiIgKrd27d2Po0KEIDw+Hra0t1q5di169ekkdFpHBmMzmE37hcVA7HtKrW9ZuWfYX3t6tX/54FyCT5VpcRERUeMXFxWHs2LEIDw9HkyZNsG3bNlSsWFHqsIiMwmEG+UBsYjIAQGH1UFf3fsX3Yau2zf7ia9tSj+3KA5Xb53Z4RERUSFlYWGDr1q2YOHEiTp48yUSWCiT2zOYDOy6nrCurME9dkWBKkymGXfzgYOrxe3NzMywiIiqEtm/fjoSEBN3GBy1btkTLli0ljooo55jM5gMnHoTizVUM7M3ts78w7Il+uXqX3AuKiIgKlfj4eEycOBErV66EhYUFGjduzA0QqFBgMpsPHLodBLkqxPgLn5/VLyvMcicgIiIqVB48eIC+ffvi6tWrAICxY8dySAEVGkxmJRaTkDJeVqZ6qaur61DXsIuD02yM0Pbr3AyLiIgKiW3btuHTTz9FdHQ0HBwcsGHDBrz//vtSh0WUa5jMSuzI3WAAgEyeoKtzsXUx7OIzP6celzIwASYioiJBCIEvvvgCnp6eAIDWrVtj69atKFuWm+pQ4cLVDCR2zTccAKCwfKqrq1eyXvYXapL1yxVa5F5QRERU4MlkMjg4OEAmk2HatGk4evQoE1kqlNgzK7E1p1ImcQlN6p7XFkoD9r9+ekK/bFk8N8MiIqICKjo6GtbW1gCAmTNnonPnzmjevLnEURGZDntmJWZnmTJpS+1wXFfnYuOS/YW302x7W+W93A2KiIgKnJiYGHzyySd49913kZCQMnRNqVQykaVCj8msxMJjkwAIvboy1mWyv/DJv6nHDQblblBERFSg3Lp1C02aNMEff/yBq1ev4vjx41KHRJRnmMxKKDAiHgCgsL6jV1/CokT2F4c9Tj2u2jE3wyIiogJCCIG1a9eicePGuH37NkqXLo0jR47A3d1d6tCI8gzHzEro6vNXAACFOkBXV8bKgF7ZtFTWgJl5boZFREQFQFRUFEaOHInNmzcDADp27IiNGzfC0dFR4siI8hZ7ZiX0+3+Tv+QWfrq6CY0mZH/hk5Opx4nRuR0WEREVACNGjMDmzZuhUCgwf/58/PPPP0xkqUhiz6yELj973TPrr6uzVdtmf+F5z9Rjp9q5HRYRERUA8+bNw/Xr1+Hp6YlWrVpJHQ6RZNgzKxEhUid9yVXhuuNq9gbsk313b+qx+3e5GBUREeVXkZGR8Pb21pUrVaqE69evM5GlIo89sxK5FxSVciDT3/zAXm2f9YXJifrlck1yMSoiIsqPrly5gj59+uDRo0ewtbXVTfCSy9knRcR/BRI5cidlG1ul9V29eplMlvWFQTf1yyrL3AyLiIjyESEEVqxYgebNm+PRo0coX748bG0NGI5GVISwZ1YiJx+EAAAsym3S1bUs0zL7Cx8dST2u2Ca3wyIionwiPDwcw4YNw86dOwEA3bt3xx9//IHixbnjI1Fa7JmViKVKiTc3SxhYc2DWF2m1wNF5qeVqnXI/MCIiktzFixfRoEED7Ny5E2ZmZli2bBl2797NRJYoA+yZlYhcBkCWpFfXqmw2g/ivbdUv1+mdu0EREVG+cOfOHTx58gQVK1aEl5cXGjduLHVIRPkWk1mJHL4TDLk6VFdu5NQo+4t8z+mXrbmeIBFRYSGE0M2bGDRoEGJiYtCvXz/Y2dlJGxhRPsdhBhJ5x6kYlNb3dGVzpQG7eF3ZkHrcz8sEURERkRTOnDmDli1bIjQ0tZNj5MiRTGSJDMBkViL3gqIgU6Tu3lXRtmLWF4Q91i+7cF1BIqKCTqvV4ocffkCbNm1w9uxZTJs2TeqQiAocDjOQiFIug6rEaV3Zrbxb1hfsn6pfVlubICoiIsorISEhGDx4MP755x8AgIeHB3744QeJoyIqeJjMSkAIAY3QX8mgin2VrC8ySzMMocNME0RFRER55cSJE+jXrx/8/f1hbm6On376CcOHD89+rXEiSofJrASStQJCaPXqbFQ2WV90a1fqce1eJoiKiIjywu7du/Hhhx9Cq9XinXfegbe3N+rWrSt1WEQFFpNZCdwLjIJclTrIv4pdNr2yb7IskcsRERFRXmnXrh1cXFzQsmVLrFy5EtbWHDZG9DaYzErgflAU5OogXdnaLJtfZJpk/bK6mAmiIiIiU7l+/Trq1KkDmUwGW1tbXLhwAcWLF+ewAqJcwNUMJHAnIBJmxVMnf9UrWS/rC7YPMW1ARERkEhqNBrNmzYKrqytWrVqlqy9RogQTWaJcwp5ZCViolJCl2crW1dE188ZaDXDn79SyU23TBUZERLkmICAAAwYMwLFjxwAAN2/elDgiosKJyawEjt8LhqLYM135Xed3M28ccE2/PGSvaYIiIqJcc+jQIQwcOBDBwcGwsrKCp6cnBg4cKHVYRIUShxlI4IZfhF5ZKc/iPcWLi6nH5ZoAFvYmioqIiN5WcnIypk2bBnd3dwQHB6Nu3bq4dOkSE1kiE2IyKwEhizW88f0DqcdVstlYgYiIJHX9+nUsWLAAQgiMGDEC586dQ/Xq1aUOi6hQ4zCDPCaEgJndZV25gk2FrC94dCT1uFwjE0VFRES5oUGDBvjxxx9RpkwZ9O3bV+pwiIoE9szmsYCIeMiVqcMMHCwcDL+4bEMTRERERDmVlJSEqVOn4s6dO7q68ePHM5ElykNMZvPYNd9wyC18deURdUdk3viNLW9hYWeaoIiIyGjPnz9H27Zt8f3336NPnz5ISkqSOiSiIonJbB7bfysQ0Kp15eLmxTNvHPY4DyIiIiJj7dmzB66urjh79ixsbW0xa9YsmJmZSR0WUZHEZDaPlba1AETqy17SsmTmje/9L/XY1tmEURERkSESExMxfvx49OjRA69evULjxo1x9epVfPjhh1KHRlRkcQJYHktM1gIyja6c5bJcT0+lHtfqabqgiIgoWyEhIejSpQsuXkxZMnH8+PFYsGABVCqVxJERFW1MZvPYwduBkBcP05WVsiy+Bff3px6/08WEURERUXbs7e1hbm4Oe3t7rFu3Dt27d5c6JCICk9k8V9XRGpfkL3VlM3kmY6zenPxVpr4JoyIioowkJCRAJpNBpVJBqVRi69atSE5ORoUK2SyrSER5hmNm89izl7HQJqbu4mWmyCSZvbpRv2xmbsKoiIjoTQ8fPkTz5s3x9ddf6+rKli3LRJYon2Eym8ceh8ZArnoFAChlWSrzhnvGpB5ziAERUZ7y8vJCgwYNcPXqVWzatAmhoaFSh0REmWAym8dK26a+5JlO/rp/UL/cY4UJIyIiotfi4uIwYsQIeHh4ICoqCq1bt8bVq1fh4GDEBjdElKeYzOax4KT7uuMX0S8ybrSlt37ZMou1aImIKFfcvXsXTZs2xW+//QaZTIZvv/0WR48eRbly5aQOjYiywAlgeUijFZAp4nRlt/Ju6RvFhumXR10wcVRERJSQkAA3Nzf4+fnB0dERmzZtwnvvvSd1WERkgLfqmY2Pj8+tOIqEJ6HRkJm90pXLWJdJ3yj2pX655DsmjoqIiNRqNZYuXYp27drBx8eHiSxRAWJ0MqvVajF37lyULVsW1tbWePw4ZcvV6dOnY82aNbkeYGFyLzAaCnWgrpxhMntrV+pxo0/yICoioqLp1q1bOHHihK7cu3dvHDlyBKVLl5YwKiIyltHJ7Lx587Bu3Tr88MMPerue1K5dG7///nuuBlfYBETEQWhTl9gqZ53BOKywx2kKMtMHRURUxAgh8Mcff6Bx48b46KOPEBAQoDsnk/H3LlFBY3Qyu2HDBvz2228YMGAAFAqFrr5evXq4e/durgZX2JibKaAqfkZXLmWVwdJcz1LPo/HwPIiKiKjoiI6OxuDBg/HJJ58gLi4Orq6uen/LiKjgMTqZ9fPzQ5UqVdLVa7VaJCUl5UpQhVWSRqu3YUKGyaytc+qxnXP680RElCPXr19Ho0aNsHHjRsjlcnz33XfYv38/HB0dpQ6NiN6C0clszZo1cfLkyXT127dvR/363HI1K+cev9RtmAAAtmrb9I2enUo9VlnnQVRERIWbEAK//fYbmjZtinv37qFs2bI4fvw4pk6dCrmcK1QSFXRGL801Y8YMDB48GH5+ftBqtdi5cyfu3buHDRs2YO/evaaIsdBQmsUCCSnHDuqy6RskJ+qXOXaLiOityWQynD59GvHx8Xj//fexYcMGboJAVIgY/Za0R48e+Pvvv3H48GFYWVlhxowZuHPnDv7++28uZZKNS76+uuNYTXj6Bml7ZYmI6K0IIXTHv/zyCzw9PbF3714mskSFTI42TWjdujUOHTqU27EUek62Znjy37F7hU7pGwSnmUBX7f08iYmIqLARQmDlypU4evQo/vzzT8jlclhbW2PEiBFSh0ZEJmB0z2ylSpXw8uXLdPXh4eGoVKlSrgRVWN0K8tMdmytV6Rvc8E49rtA8DyIiIipcwsPD0adPH4wePRo7d+7Erl27sr+IiAo0o5PZp0+fQqPRpKtPSEiAn59fBlfQa5b213THMckx6RsUS7NQd6V3TR8QEVEhcvHiRTRo0ADbt2+HmZkZli5dil69ekkdFhGZmMHDDPbs2aM7PnDgAGxtU2fiazQaHDlyBC4uLrkaXGGTkGADdbGU42w3TLB3yZOYiIgKOiEEli9fjq+++gpJSUlwcXGBt7c3GjduLHVoRJQHDE5me/bsCSBlVujgwYP1zpmZmcHFxQWLFy/O1eAKk4RkDZRW93XlpqWbpm8UkmbMrEKdB1ERERV8Y8eOxYoVKwAAvXr1wpo1a2BnZydtUESUZwweZqDVaqHValG+fHkEBwfrylqtFgkJCbh37x66du1qylgLtIjYJGiT7HRlKzMr/QaRAfplM3MQEVH2Bg0aBGtra6xYsQLbt29nIktUxBi9msGTJ0+yb0TpBEclQKaI05VLWpbUb7CkeupxsTJ5FBURUcGj1Wpx/fp1uLq6AgAaN26MZ8+eoXjx4tIGRkSSyNHWJzExMfjf//4HT09P/PTTT3pfxvrll1/g4uICc3NzNG3aFBcuXMiyfXh4OEaNGoXSpUtDrVajWrVq+N///peTp5Gn9t8MhNIqdUysOqthBI2G5kFEREQFT2hoKLp164ZmzZrBx8dHV89ElqjoMrpn9urVq+jcuTNiY2MRExOD4sWLIzQ0FJaWlnB0dMTYsWMNvpeXlxcmTJgAT09PNG3aFMuWLYO7uzvu3buX4V7ZiYmJeO+99+Do6Ijt27ejbNmyePbsWYH4SMnO0gyahJJQqEMAAJZKy9STr57pN24zOQ8jIyIqGE6ePIl+/frBz88ParUa9+7d0/XOElHRZXTP7Pjx49GtWze8evUKFhYWOHfuHJ49e4aGDRti0aJFRt1ryZIl+PTTTzF06FDUrFkTnp6esLS0xNq1azNsv3btWoSFhWH37t1o2bIlXFxc0LZtW9SrV8/Yp5HnEjVayGQpS5opZGaQpd2qNtI/9dipNrexJSJKQ6vVYv78+WjXrh38/PxQrVo1XLhwAX379pU6NCLKB4xOZn18fDBx4kTI5XIoFAokJCTA2dkZP/zwA6ZOnWrwfRITE3H58mW4ubmlBiOXw83NDWfPns3wmj179qB58+YYNWoUnJycULt2bcyfPz/DdW9fS0hIQGRkpN6XFE7eD4VcFQYAsFba6J+MTLM+r2PNPIyKiCh/Cw4Oxvvvv49vv/0WGo0GAwcOxOXLl1G3bl2pQyOifMLoZNbMzAxyecpljo6OeP78OQDA1tYWvr6+Bt8nNDQUGo0GTk5OevVOTk4IDAzM8JrHjx9j+/bt0Gg0+N///ofp06dj8eLFmDdvXqaP8/3338PW1lb35ezsbHCMucnZ3kJ3rJS/MbpDaFOPi1fMo4iIiPK/TZs24eDBg7CwsMDatWuxYcMGWFtbSx0WEeUjRo+ZrV+/Pi5evIiqVauibdu2mDFjBkJDQ7Fx40bUrl3bFDHqaLVaODo64rfffoNCoUDDhg3h5+eHH3/8ETNnzszwmilTpmDChAm6cmRkpCQJ7f47L4AKKccvE4L0Tz48knpsw5UMiIhe+/LLL/Ho0SN88cUXqFWrltThEFE+ZHTP7Pz581G6dMq2q9999x3s7e0xcuRIhISE4NdffzX4Pg4ODlAoFAgK0k/sgoKCUKpUqQyvKV26NKpVqwaFQqGrq1GjBgIDA5GYmJjhNWq1GjY2NnpfUohKDtEdN3Zqpn9SqUpzzPVliajoCggIwMiRIxEXl7KUoVwuxy+//MJElogyZXTPbKNGjXTHjo6O2L9/f44eWKVSoWHDhjhy5IhudzGtVosjR45g9OjRGV7TsmVLbNmyBVqtVjfU4f79+yhdujRUKlWG1+QXCvMXuuPopAj9k1c2pB6X4/aLRFQ0HTp0CAMHDkRwcDCUSiV+/vlnqUMiogIgR+vMZuTKlStG7wA2YcIErF69GuvXr8edO3cwcuRIxMTEYOjQlHVWBw0ahClTpujajxw5EmFhYRg3bhzu37+Pffv2Yf78+Rg1alRuPQ2TUalidcc1S7wxyat4pdRjDjMgoiImOTkZ06ZNg7u7O4KDg1GnTp0C8XudiPIHo3pmDxw4gEOHDkGlUmH48OGoVKkS7t69i2+++QZ///033N3djXrwvn37IiQkBDNmzEBgYCBcXV2xf/9+3aSw58+f63pgAcDZ2RkHDhzA+PHjUbduXZQtWxbjxo3D119/bdTjSkGLZLweHNGoVCP9k2GpmynAzAJEREWFn58f+vXrh5MnTwIAPvvsMyxbtgwWFvxdSESGMTiZXbNmDT799FMUL14cr169wu+//44lS5ZgzJgx6Nu3L27evIkaNWoYHcDo0aMzHVZw/PjxdHXNmzfHuXPnjH4cKWm1AlqRunyYtVmambjaNMuKWeuv7EBEVJidPn0aPXv2RGhoKKytrbF69Wp4eHhIHRYRFTAGDzNYvnw5Fi5ciNDQUHh7eyM0NBQrV67EjRs34OnpmaNEtqgIjU6AwvKJrmwmN0s9mZQ6/ADRb6xyQERUiJUvXx5arRb169fHlStXmMgSUY4Y3DP76NEj9O7dGwDQq1cvKJVK/PjjjyhXrpzJgiss4pO0EMnFdGW9ZDYqzZq6VY0bpkFEVNBERETA1tYWQMrQsaNHj+Kdd96BuTlXciGinDG4ZzYuLg6WlpYAAJlMBrVarVuii7KWrNUC8gRdubR1mtct7lXqcdqdwIiICpm///4blSpVwp49e3R19erVYyJLRG/FqAlgv//+u27nleTkZKxbtw4ODg56bcaOHZt70RUSGq2AstgdXVmtUKeeDLmbelylQx5GRUSUNxITEzFlyhQsWbIEALBy5Up0795d4qiIqLAwOJktX748Vq9erSuXKlUKGzdu1Gsjk8mYzGYgWSugjS8DhUXKWrMlzEuknpSl6RxPjAURUWHy5MkTeHh44MKFCwBSdvRauHChxFERUWFicDL79OlTE4ZRuAVExAGy1FULFPLUHcwQF556XKZ+3gVFRGRiO3fuxCeffIKIiAjY2dlh3bp16NGjh9RhEVEhY/QOYGQ8IQCFeQAAQCHeWDvx9l+pxwozEBEVBlevXsWHH34IAGjWrBm2bduGChUqSBwVERVGTGbzQFLatWTlGv2Tr56mHnOdWSIqJOrXr4+RI0fC2toa3333HczM+GadiEyDyWweSNYm6Y41IlH/pFMt4HFwynGpOnkYFRFR7tq+fTtatWqFUqVKAQB++eUXyGQyiaMiosLO4KW5KOe0WqE7Lmv+RsL68lHqscoqjyIiIso9cXFx+Pzzz9G7d28MGDAAGk3KJ1BMZIkoL7BnNg+kyWWR7ld7xPPUY4UqL8IhIso19+7dQ58+fXD9+nXIZDI0a9YMQojsLyQiyiU56pl99OgRpk2bhn79+iE4OOUj8n/++Qe3bt3K1eAKC01mv9i1Wv0yezGIqADZvHkzGjZsiOvXr6NkyZLYv38/vvvuOyiV7CchorxjdDL777//ok6dOjh//jx27tyJ6OhoAMC1a9cwc+bMXA+wMEjbS6GXr0YHpm9MRJTPxcbGYvjw4Rg4cCBiYmLw7rvvwsfHBx07dpQ6NCIqgoxOZr/55hvMmzcPhw4dgkqV+rF4+/btce7cuVwNrrCIT0pdwUCWdqBBeJohBk618zAiIqKc02q1OH36NGQyGWbOnInDhw+jTJkyUodFREWU0Z8F3bhxA1u2bElX7+joiNDQ0FwJqrB5EBShO9YbcKBJXeUApevlWTxERDkhhIBMJoO1tTW8vb0RHByMDh24DTcRScvonlk7OzsEBASkq7969SrKli2bK0EVNuYW8brjgPi7qSfSLNkFG/ZqEFH+FB0djcGDB2Pp0qW6ujp16jCRJaJ8wehk1sPDA19//TUCAwMhk8l0HzdNmjQJgwYNMkWMBV5ymoledexbpJ5Iiks9lnNBcSLKf27cuIHGjRtjw4YN+PbbbxEUFCR1SEREeoxOZufPn4/q1avD2dkZ0dHRqFmzJtq0aYMWLVpg2rRppoixwEtOswOYKu3yWyH3Uo+5kgER5SNCCKxevRpNmjTB3bt3UaZMGRw4cABOTtypkIjyF6PHzKpUKqxevRrTp0/HzZs3ER0djfr166Nq1aqmiK9QiElIHU6gkKV5/xDgk3psZpF3ARERZSEyMhIjRozAtm3bAACdOnXChg0bULJkSYkjIyJKz+hk9tSpU2jVqhXKly+P8uXLmyKmQueW/yvgv829FHJF6omEqNRjxxp5GxQRUQaSkpLQvHlz3L59GwqFAvPnz8ekSZMgl3PDSCLKn4z+7dS+fXtUrFgRU6dOxe3bt00RU6FT1t5cd6xSpElmHx1NPbavmIcRERFlzMzMDMOGDYOzszNOnDiBr776ioksEeVrRv+G8vf3x8SJE/Hvv/+idu3acHV1xY8//ogXL16YIr5CQStSJ4Cplf9N9IqP0G9k75J3ARERpREREYEHDx7oyuPHj8eNGzfQokWLLK4iIsofjE5mHRwcMHr0aJw+fRqPHj1C7969sX79eri4uKB9+/amiLHAi9O+0h3LX0/0ingj+U87/ICIKI9cunQJ9evXR9euXREVlTL0SSaTwdbWVuLIiIgM81afHVWsWBHffPMNFixYgDp16uDff//NrbgKlbTb2QbG+qUcRAenNqg/MI8jIqKiTgiB5cuXo0WLFnjy5AkSExPh5+cndVhEREbLcTJ7+vRpfPHFFyhdujT69++P2rVrY9++fbkZW6GhRerSXHUdGqQcpBl6gFfP8jgiIirKXr16hV69euHLL79EUlISPvjgA1y9ehXVq1eXOjQiIqMZvZrBlClTsG3bNvj7++O9997D8uXL0aNHD1haWpoivkIh7ZhZpey/4QTa5NQGFdvkcUREVFSdO3cOHh4eePbsGVQqFRYvXoxRo0ZBxrWuiaiAMjqZPXHiBCZPnow+ffrAwcHBFDEVOpo0wwwUr2cFp01mOV6WiPLInDlz8OzZM1SuXBleXl5o2LCh1CEREb0Vo5PZ06dPmyKOQk0IDfBfp4dcllEya/S3gYgoR9auXYvZs2dj4cKFsLGxkTocIqK3ZlAWtWfPHrz//vswMzPDnj17smzbvXv3XAmsMEnSaHSvtPJ1L2xo6jI4TGaJyFROnTqFgwcPYs6cOQCAUqVKYdWqVRJHRUSUewzKonr27InAwEA4OjqiZ8+embaTyWTQaDSZni+q7gVFwqJsyrHi9ZjZtAlsQnTeB0VEhZpWq8XChQsxffp0aDQaNGjQIMvf30REBZVByaxWq83wmAwjV6cuw2Wh+u8lf3ExtUGpOnkcEREVZsHBwfj4449x8OBBAMDAgQPh5uYmcVRERKZh9NJcGzZsQEJCQrr6xMREbNiwIVeCKmxkQqU7jkn6rxfWzCK1gZk5iIhyw/Hjx+Hq6oqDBw/CwsICa9aswYYNG2BtbS11aEREJmF0Mjt06FBERESkq4+KisLQoUNzJajCRojUJW9cbF1SDmRpXnq7CnkbEBEVSkuXLkWHDh0QEBCAGjVq4OLFi/jkk0+47BYRFWpGJ7NCiAx/Mb548YLbH2ZAqxUA0q4z+98wA01iaiOFWd4GRUSFUpUqVaDVajFkyBBcvHgRtWrVkjokIiKTM3gaff369SGTySCTydChQwcolamXajQaPHnyBJ06dTJJkAWZRgjdslwAUt8I3NqVWilnMktEORMeHg47OzsAQLdu3XDx4kU0atRI2qCIiPKQwcns61mwPj4+cHd31xt/pVKp4OLigg8//DDXAyzoNFoBIHXTBLksg85wc671SETGSU5OxuzZs+Hp6YnLly+jfPnyAMBEloiKHIOT2ZkzZwIAXFxc0LdvX5ibc9KSIbRCP5mVQQak2REMAKCyytugiKhA8/PzQ//+/XHixAkAwPbt2zFhwgSJoyIikobRq/UPHjzYFHEUWm/2zMpkMsBnS2qDstxKkogMt3//fnz88ccIDQ2FtbU1Vq9eDQ8PD6nDIiKSjEHJbPHixXH//n04ODjA3t4+y5mxYWFhuRZcYRARlwTI3hhmEPEitUGkvwRREVFBk5SUhBkzZmDBggUAAFdXV3h7e6Nq1aoSR0ZEJC2DktmlS5eiWLFiumMu82K4+CQt0g0z8L+S2qAnt5UkouwtX75cl8iOGjUKixYt4nAvIiIYmMymHVowZMgQU8VSKIk3xsfKZXJAm5xaoeJC5kSUvVGjRmHPnj0YO3YsPvroI6nDISLKN4xeZ/bKlSu4ceOGrvzXX3+hZ8+emDp1KhITE7O4smjSCiBdz+zDw6kNilfM85iIKP9LTEyEp6cnNBoNAMDCwgL//vsvE1kiojcYncyOGDEC9+/fBwA8fvwYffv2haWlJf7880989dVXuR5gQacVAjLZGxPA0jK3y9uAiCjfe/r0KVq3bo2RI0di/vz5unoO8SIiSs/oZPb+/ftwdXUFAPz5559o27YttmzZgnXr1mHHjh25HV+BpxUCCus7urL8zWW5FEYvKEFEhdiuXbtQv359XLhwAXZ2dqhbt67UIRER5Ws52s5Wq03ZnvXw4cPo3LkzAMDZ2RmhoaG5G10hIAQgklPHxVonxaeetCwhQURElB8lJCRg7Nix6NWrF8LDw9GsWTP4+PigR48eUodGRJSvGZ3MNmrUCPPmzcPGjRvx77//okuXLgCAJ0+ewMnJKdcDLOg0WgG5MkpXLh3ul3rSylGCiIgov3n06BFatmyJn3/+GQAwadIknDhxAhUqVJA4MiKi/M/oz7iXLVuGAQMGYPfu3fj2229RpUoVACk70LRo0SLXAyzotEJApnqpK8uTk1JPlqojQURElN9ER0fj5s2bKF68ODZs2KDrJCAiouwZnczWrVtXbzWD13788UcoFIpcCaow0QpAm+AEhXkgAMASaSZwlG8mUVREJDUhhG5CV7169eDl5YUGDRrA2dlZ4siIiAoWo4cZvHb58mVs2rQJmzZtwpUrV2Bubg4zM7PcjK1QSLvOrAIq/TVm5Zz8RVQU3b9/H02bNsWFCxd0dT169GAiS0SUA0ZnU8HBwejbty/+/fdf2NnZAQDCw8PRrl07bNu2DSVLlsztGAs0/4h4pK4zK9PfylbB5J+oqNmyZQtGjBiB6OhojBkzBufOneOSW0REb8HontkxY8YgOjoat27dQlhYGMLCwnDz5k1ERkZi7NixpoixQFPo/ZGSAbFpVnzQavI8HiKSRmxsLIYPH44BAwYgOjoa7777Lnbv3s1ElojoLRndM7t//34cPnwYNWrU0NXVrFkTv/zyCzp27JirwRUGWiGA/zZNUMhkQODN1JPc/YuoSLhz5w769OmDmzdvQiaTYcaMGZg+fTrnGRAR5QKjk1mtVpvh2FgzMzPd+rOUSqT5L2QyQGWZetLSQYKIiCgv3bp1C02aNEFsbCycnJywZcsWtG/fXuqwiIgKDaOHGbRv3x7jxo2Dv7+/rs7Pzw/jx49Hhw4dcjW4wiDtBDAZZIDvxdSTtuUkiIiI8lLNmjXRvn17dOjQAT4+PkxkiYhymdE9sytWrED37t3h4uKim3nr6+uL2rVrY9OmTbkeYEGnFQIypNnCVpbm/YOZRd4HREQmd+vWLVSoUAHW1taQyWTYunUrLCwsOKyAiMgEjE5mnZ2dceXKFRw5cgR37twBANSoUQNubm65HlxhkHbkhQxywMIOSPxvRzA5/7ARFSZCCKxZswZjxozBRx99hA0bNkAmk8Ha2jr7i4mIKEeMSma9vLywZ88eJCYmokOHDhgzZoyp4io00k4Ak8lkqevM2pSVMCoiym1RUVH4/PPPsWXLFgBAaGgoEhISYG5uLnFkRESFm8FjZletWoV+/frh0qVLePDgAUaNGoXJkyebMrZCIWXIbJphBq+TWW6YQFRo+Pj4oGHDhtiyZQsUCgUWLlyIffv2MZElIsoDBiezK1aswMyZM3Hv3j34+Phg/fr1WLlypSljKxS0b04AiwlJKTCZJSrwhBBYtWoVmjVrhgcPHsDZ2RknTpzAV199Bbk8xxssEhGREQz+bfv48WMMHjxYV+7fvz+Sk5MREBBgksAKC22anlkZ0iyOLriMGVFB9+rVK8yaNQsJCQno1q0brl69ihYtWkgdFhFRkWJw92BCQgKsrKx0ZblcDpVKhbi4OJMEVlgERsanjplNe+LVE0niIaLcU7x4cWzevBk3btzAl19+yd28iIgkYNRn3dOnT4elZeqi/4mJifjuu+9ga2urq1uyZEnuRVcIRMUnQdczK9JsX1uZa/ISFTRCCPz8888oU6YMPvroIwCAm5sbV3MhIpKQwclsmzZtcO/ePb26Fi1a4PHjx7oyeyXSszFP3S1Nkfb10SRKEA0R5dSrV6/wySefYPfu3ShWrBiaN2+OsmW5KgkRkdQMTmaPHz9uwjAKN5kyZV1ZvVTfuYkksRCR8c6fP4++ffvi2bNnUKlUmD9/PsqUKSN1WEREhBxsZ0vGk8lSJnvJRXJqpUIlUTREZCitVovFixejVatWePbsGSpXrowzZ85g9OjR/CSKiCif4PpQJiYACCGDTCbwUhubeiIxRrKYiCh7ycnJ6NWrF/7++28AQJ8+fbB69WrY2NhIHBkREaXFntk8VAWpk+dQqq50gRBRtpRKJapUqQK1Wg1PT09s27aNiSwRUT7EZNbEhBCQ/bc0l1nal7t4RYkiIqLMaLVahIeH68oLFizAlStXMGLECA4rICLKp5jMmlzqDmBmiRGp1Wr28BDlJyEhIejSpQu6du2KpKQkAIBKpULNmjUljoyIiLKSo2T25MmTGDhwIJo3bw4/Pz8AwMaNG3Hq1KlcDa4wEGmSWaFIs0+7taME0RBRRv7991+4urpi//79uHLlCq5evSp1SEREZCCjk9kdO3bA3d0dFhYWuHr1KhISEgAAERERmD9/fq4HWOCl2bZWkXZtWfbMEklOo9Fg7ty5aN++Pfz9/VGjRg1cuHABTZpw6TwiooLC6GR23rx58PT0xOrVq2FmlrohQMuWLXHlypVcDa4wSNszq9CkJP6QKwE5R3gQSSkwMBDu7u6YMWMGtFothgwZgosXL6J27dpSh0ZEREYwemmue/fuoU2bNunqbW1t9SZOUIq0yaz89bYJ2uRMWhNRXhk0aBCOHDkCS0tLrFq1CoMGDZI6JCIiygGjuwdLlSqFhw8fpqs/deoUKlWqlKMgfvnlF7i4uMDc3BxNmzbFhQsXDLpu27ZtkMlk6NmzZ44eN2+kTWb/Oy5ZQ6JYiOi1n376Cc2bN8fly5eZyBIRFWBGJ7Offvopxo0bh/Pnz0Mmk8Hf3x+bN2/GpEmTMHLkSKMD8PLywoQJEzBz5kxcuXIF9erVg7u7O4KDg7O87unTp5g0aRJat25t9GPmJW2aMbOy18lscpxE0RAVXf7+/tiyZYuuXL16dZw+fRrVq1eXMCoiInpbRiez33zzDfr3748OHTogOjoabdq0wfDhwzFixAiMGTPG6ACWLFmCTz/9FEOHDkXNmjXh6ekJS0tLrF27NtNrNBoNBgwYgNmzZ+e4NzivpB1moFulUpMkSSxERdWBAwdQr149fPzxxzhx4oSunmvHEhEVfEYnszKZDN9++y3CwsJw8+ZNnDt3DiEhIZg7d67RD56YmIjLly/Dzc0tNSC5HG5ubjh79mym182ZMweOjo4YNmxYto+RkJCAyMhIva+8lWaYwevDSu/mcQxERVNycjKmTJmCTp06ITQ0FHXr1kWpUqWkDouIiHKR0RPAXsuNxcRDQ0Oh0Wjg5OSkV+/k5IS7d+9meM2pU6ewZs0a+Pj4GPQY33//PWbPnv1Wcb6NZJEg2WMTFWW+vr7o168fTp8+DQD44osvsHjxYpibm2dzJRERFSRGJ7Pt2rXL8qO5o0ePvlVAWYmKisLHH3+M1atXw8HBwaBrpkyZggkTJujKkZGRcHZ2NlWI6SRqY3XH19Xq/4Lwz7PHJyqK9u3bh0GDBiEsLAw2Njb4/fff0bt3b6nDIiIiEzA6mXV1ddUrJyUlwcfHBzdv3sTgwYONupeDgwMUCgWCgoL06oOCgjL8KPDRo0d4+vQpunXrpqvTalMmWCmVSty7dw+VK1fWu0atVkP9OomUQNoxsx1i/0tsrZ0yaU1EueH58+cICwtDw4YN4eXlle73AhERFR5GJ7NLly7NsH7WrFmIjo426l4qlQoNGzbEkSNHdMtrabVaHDlyBKNHj07Xvnr16rhx44Ze3bRp0xAVFYXly5fnaY+roURqLps6QNm2nBShEBVqQgjdp0aff/45LCws0K9fP0nfzBIRkenl2jZUAwcOzHIFgsxMmDABq1evxvr163Hnzh2MHDkSMTExGDp0KICUhc2nTJkCADA3N0ft2rX1vuzs7FCsWDHUrl0bKpUqt55OLkq7NNfrA+7+RZSbdu/ejUaNGuk2bpHJZBgyZAgTWSKiIiDHE8DedPbs2RxNrOjbty9CQkIwY8YMBAYGwtXVFfv379dNCnv+/DnkBXjrV72luV5303I5IKJckZCQgK+//hrLly8HACxevDhHK6sQEVHBZXQy26tXL72yEAIBAQG4dOkSpk+fnqMgRo8eneGwAgA4fvx4lteuW7cuR4+ZVwR7ZolM4tGjR+jbty8uX74MAJg0aRJmzJghcVRERJTXjE5mbW1t9cpyuRzvvPMO5syZg44dO+ZaYIVFmiGzTGaJcsmff/6J4cOHIzIyEiVKlMD69evRpUsXqcMiIiIJGJXMajQaDB06FHXq1IG9vb2pYipkMtgBDBxmQJRTv/32G0aMGAEAaNmyJbZt24Zy5TipkoioqDKqi1ChUKBjx466SRaUvQy3s+WYWaIc69WrF5ydnTFlyhQcP36ciSwRURFn9DCD2rVr4/Hjx6hYsaIp4imE0k4Ae33AYQZExjh79iyaN28OIGV96lu3bqFYsWISR0VERPmB0VnVvHnzMGnSJOzduxcBAQGIjIzU+yJ9Is1Cs7oXmz2zRAaJi4vDp59+ihYtWuhN9mQiS0RErxncMztnzhxMnDgRnTt3BgB0795db1vb1wuWazSa3I+yAEubzMpe99KyZ5YoW3fu3EGfPn1w8+ZNyGQyBAQESB0SERHlQwYns7Nnz8bnn3+OY8eOmTKeQiijMbNMZomysmHDBowcORKxsbFwcnLC5s2b0aFDB6nDIiKifMjgZPZ1D2Pbtm1NFkxhlOEEsPgISWIhyu9iYmIwevRo3ZACNzc3bNq0SbeJChER0ZuM6iKUcayn0TJMZouVliQWovzu0qVLWL9+PeRyOebOnau3GyAREVFGjFrNoFq1atkmtGFhYW8VUGETlvw4faUF1+glykjbtm2xaNEiNGzYkJ8CERGRQYxKZmfPnp1uBzDKmizNSxwt/68jnGNmiQAAUVFRmDRpEr766itUrlwZADBhwgSJoyIiooLEqGTWw8MDjo6Opoql0GsQn5ByIFdIGwhRPnDt2jX06dMH9+/fx/Xr13HmzBkOZSIiIqMZ3EXIPzI5JDKoY88sFWFCCHh6eqJp06a4f/8+ypUrh0WLFvF3DBER5YjRqxlQLpCxZ5aKpoiICHz22Wfw9vYGAHTt2hXr1q1DiRIlJI6MiIgKKoOTWa1Wa8o4ihYOM6Ai6MmTJ3jvvffw6NEjKJVKLFy4EOPHj2ePLBERvRWjxsxSLuEwAyqCypYtC3t7e1SoUAFeXl5o2rSp1CEREVEhwGRWCs78I05FQ3h4OKytraFUKqFSqbBz505YW1vD3p7L0xERUe5gF6GJiYxmgKmt8z4Qojx24cIF1K9fHzNnztTVOTs7M5ElIqJcxWQ2rxUrI3UERCYlhMCSJUvQsmVLPH36FN7e3oiJiZE6LCIiKqSYzOY1Tv6iQiwsLAw9evTAxIkTkZycjN69e+PSpUuwsrKSOjQiIiqkmMzmNSazVEidOXMGrq6u+Pvvv6FWq7Fq1Sp4eXlx10AiIjIpTgDLa1xjlgqhiIgIdO7cGREREahatSq8vb3h6uoqdVhERFQEMJnNa1EBUkdAlOtsbW2xfPlyHDx4EJ6enihWrJjUIRERURHBZDavyc2kjoAoV5w4cQJKpRItWrQAAAwePBiDBg3iJghERJSnOGY2r5VrKHUERG9Fo9Fg3rx5aNeuHfr06YPQ0FDdOSayRESU19gzm9c4ZpYKsKCgIAwcOBCHDx8GALi5ucHCwkLiqIiIqChjMpvXuJoBFVBHjx5F//79ERQUBEtLS6xcuRKDBw+WOiwiIiriOMwgr8n5/oEKFq1Wi5kzZ8LNzQ1BQUGoXbs2Ll26xESWiIjyBSazeY1jCqmAkclkuH37NoQQGD58OM6fP48aNWpIHRYREREADjPIe/GRUkdAZBCtVgu5XA6ZTIbff/8dffv2xUcffSR1WERERHrYM2tiQgj9isrtpQmEyEDJycmYMmUKPDw8dD+/tra2TGSJiChfYs+siQm8kcyWritNIEQG8PX1Rb9+/XD69GkAwKhRo9C2bVuJoyIiIsoce2ZN7FXyY/0KcztJ4iDKzr59++Dq6orTp0/DxsYG3t7eTGSJiCjfYzJrYpZyB91xMgBYFpcsFqKMJCUlYfLkyejatSvCwsLQsGFDXLlyBb1795Y6NCIiomxxmIGJCWh1x2WSk7k0F+U7/fr1w44dOwAAY8eOxQ8//AC1Wi1xVERERIZhz6yJCZGazMoBJrOU74wbNw4ODg7YtWsXli9fzkSWiIgKFGZWJpZ2AhiTWcoPEhIS4OPjg6ZNmwIAWrdujadPn8LKykriyIiIiIzHnlkTSzvMQC4AyPiSk3QeP36Mli1bon379rhz546unoksEREVVMysTEy/Z1ZwNQOSzPbt21G/fn1cvnwZ5ubmCAgIkDokIiKit8Zk1sT0emYBQM6XnPJWfHw8Ro0ahd69eyMyMhItWrSAj48P2rfnBh5ERFTwMbMysbQTwCA3ly4QKpIePHiA5s2bY+XKlQCAb775BsePH4ezs7PEkREREeUOzkYyMf+kK7pjGXtlKY9t2rQJPj4+cHBwwMaNG9GpUyepQyIiIspVTGZNzF5ZEbGJIQAASyGTOBoqaqZPn46oqChMnDgRZcuWlTocIiKiXMeuQlNLnf8FCyazZGJ3797F4MGDkZCQAABQKpVYsmQJE1kiIiq02DNrcmmyWZlCujCo0NuwYQNGjhyJ2NhYODs7Y968eVKHREREZHLsmc1L7JglE4iJicHQoUMxePBgxMbGokOHDhg9erTUYREREeUJJrMmJtIec8MEymW3bt1CkyZNsG7dOsjlcsyZMwcHDhxAqVKlpA6NiIgoT3CYQR5Sx4VIHQIVIn/99Rf69euHuLg4lC5dGlu3bkXbtm2lDouIiChPMZk1udR1ZjVKbhlKuad27dowMzNDmzZtsGHDBjg6OkodEhERUZ5jMmtiMpE60CDe/h0JI6HCIDg4WJe0Vq5cGefOncM777wDOdcwJiKiIop/AU0utWdWyM0kjIMKMiEEPD094eLigkOHDunqa9SowUSWiIiKNP4VNDGlSNQdm0c+kzASKqgiIiLg4eGBkSNHIi4uDlu2bJE6JCIionyDyayppRlmkGBbUcJAqCC6fPkyGjZsCG9vbyiVSixatAhr1qyROiwiIqJ8g2Nm81CSRUmpQ6ACQgiBFStWYNKkSUhMTESFChWwbds2NGvWTOrQiIiI8hX2zJpcas+sTMZdE8gwR48exdixY5GYmIiePXvi6tWrTGSJiIgywJ5Zk0u7bQKTWTJMhw4d8Omnn6J27doYM2YM3wgRERFlgslsnmJCQhkTQmDVqlXo06cPHBwcAAC//fabxFERERHlfxxmkJfYu0YZePnyJbp3745Ro0ZhyJAh0Gq12V9EREREANgzmwfSjJllzyy94cyZM/Dw8ICvry/UajW6dOnCIQVERERGYM+syaUms4JJCv1Hq9Vi4cKFaNOmDXx9fVG1alWcO3cOI0eOZDJLRERkBPbM5iH2zBKQMqxg4MCB2L9/PwCgX79++PXXX1GsWDGJIyMiIip42DNrYkKI7BtRkaJQKHDv3j2Ym5tj9erV2Lx5MxNZIiKiHGLPrIml7YuVyfneoajSarWQyWSQyWSws7PD9u3bYWZmhjp16kgdGhERUYHG7CpPcZhBURQUFAR3d3d4enrq6ho0aMBEloiIKBcwmTUxwU0TirSjR4+iXr16OHz4MKZNm4aoqCipQyIiIipUmMzmIc5SLzo0Gg1mzpwJNzc3BAUFoVatWjh58iTHxhIREeUyjpk1OfbMFjX+/v4YMGAAjh8/DgAYNmwYfvrpJ1haWkobGBERUSHEZDYvsWe20IuOjkajRo0QEBAAKysr/PrrrxgwYIDUYRERERVaHGZgcuyZLUqsra0xatQo1KtXD1euXGEiS0REZGJMZvMUX+7C6MWLF3jw4IGu/M033+DcuXOoVq2ahFEREREVDcyuTEyhTUwtcJhBobNv3z64urriww8/RFxcHICUTRHMzc0ljoyIiKhoYDJrcqnDDNQx/hLGQbkpKSkJkydPRteuXfHy5UuYmZkhLCxM6rCIiIiKHCazeSjWoa7UIVAuePbsGdq0aYNFixYBAMaMGYMzZ86gbNmyEkdGRERU9OSLZPaXX36Bi4sLzM3N0bRpU1y4cCHTtqtXr0br1q1hb28Pe3t7uLm5ZdleaskabWpBwY+eC7q//voLrq6uOHfuHGxtbbFjxw789NNPUKvVUodGRERUJEmezHp5eWHChAmYOXMmrly5gnr16sHd3R3BwcEZtj9+/Dj69euHY8eO4ezZs3B2dkbHjh3h5+eXx5EbRqPR6I61MoWEkdDb0mq1WLRoEcLDw9G4cWNcvXoVvXr1kjosIiKiIk0mhBDZNzOdpk2bonHjxlixYgWAlITB2dkZY8aMwTfffJPt9RqNBvb29lixYgUGDRqUbfvIyEjY2toiIiICNjY2bx1/drquaY9nyhAAwMFKX6B065Emf0wyHV9fX3h6emLmzJlQqVRSh0NERFQoGZOvSdozm5iYiMuXL8PNzU1XJ5fL4ebmhrNnzxp0j9jYWCQlJaF48eIZnk9ISEBkZKTeV14y18bqjpVK7lFR0Gzfvh0zZszQlZ2dnfHdd98xkSUiIsonJE1mQ0NDodFo4OTkpFfv5OSEwMBAg+7x9ddfo0yZMnoJcVrff/89bG1tdV/Ozs5vHbcxEmVmumMFJO0EJyPEx8dj1KhR6N27N+bOnYtjx45JHRIRERFlQPIxs29jwYIF2LZtG3bt2pXpup5TpkxBRESE7svX1zdPY9SkmQAmt+Vs94LgwYMHaNGiBVauXAkg5Q1Tq1atJI6KiIiIMiLp594ODg5QKBQICgrSqw8KCkKpUqWyvHbRokVYsGABDh8+jLp1M1/ySq1WSzrTPFmbJpmVc5hBfrd161Z89tlniI6OhoODAzZu3IhOnTpJHRYRERFlQtKeWZVKhYYNG+LIkSO6Oq1WiyNHjqB58+aZXvfDDz9g7ty52L9/Pxo1apQXoeaYUp6665dKydUM8rOJEyeif//+iI6ORps2beDj48NEloiIKJ+TfJjBhAkTsHr1aqxfvx537tzByJEjERMTg6FDhwIABg0ahClTpujaL1y4ENOnT8fatWvh4uKCwMBABAYGIjo6WqqnYDiZ5C83ZaFp06aQyWSYNm0ajhw5wk0QiIiICgDJP/fu27cvQkJCMGPGDAQGBsLV1RX79+/XTQp7/vw55PLUJHDVqlVITEzERx99pHefmTNnYtasWXkZukFkaSZ9ybjObL4TFBSk+1nr06cP6tati+rVq0scFRERERlK8nVm81perzPb5bfmeK5O6TW+1GYl1BVbm/wxKXsxMTEYPXo0/vnnH/j4+GQ7RpuIiIjyToFZZ7Yo0OuZlfPlzg9u3bqFJk2aYN26dQgJCdEbs01EREQFC7OrvMQxs5ISQmDt2rVo3Lgxbt++jdKlS+PIkSMYMGCA1KERERFRDkk+ZrZokWXfhEwiOjoan3/+OTZv3gwA6NixIzZu3AhHR0eJIyMiIqK3wa5CEzMXCbpjGXtmJTNv3jxs3rwZCoUC8+fPxz///MNEloiIqBBgz6yJyaDNvhGZ3LRp03D58mXMnDmTu3kREREVIuwqNLG75mmS2WKcMZ9XIiMjsXjxYrxerMPa2hqHDh1iIktERFTIsGfWxCy0MsTJUxIqbmebN65cuYK+ffvi4cOHAFJ29iIiIqLCiT2zJlZMk/oSK5jMmpQQAitWrEDz5s3x8OFDlC9fHi1btpQ6LCIiIjIhZlcm9nr9AhuNhktzmVB4eDiGDRuGnTt3AgB69OiBtWvXonjx4hJHRkRERKbE7MrE9LZXYzJrEpcuXUL9+vWxc+dOmJmZYdmyZdi1axcTWSIioiKAPbMml5LOygBAxnVmTUGr1eLFixeoWLEivLy80LhxY6lDIiIiojzCZNbEZFmUKOc0Gg0UCgUAoEmTJti1axdatWoFOzs7aQMjIiKiPMXPvfMShxnkijNnzqBmzZq4du2arq5r165MZImIiIogZlcmxjGzuUer1eKHH35AmzZtcP/+fUydOlXqkIiIiEhiHGZgYrK0/2cym2MhISEYPHgw/vnnHwCAh4cHfv31V4mjIiIiIqkxmc1LnACWIydPnoSHhwf8/f1hbm6On376CcOHD4eMrycREVGRx2TWxFRIAGCWUmDPrNFOnTqFd999F1qtFu+88w68vb1Rt25dqcMiIiKifILJrIklI2XGvQwA5GaSxlIQNW/eHO3atUOZMmWwcuVKWFtbSx0SERER5SNMZk0uzUfhcvbMGuL06dNo0KABLCwsoFAo8Pfff8PCwkLqsIiIiCgfYnZlYkL3f47vzI5Go8GsWbPQunVrjB8/XlfPRJaIiIgyw55ZyhcCAgLQv39/HD9+HACQlJSktzECERERUUbYM0uSO3jwIOrVq4fjx4/DysoKGzduxJo1a5jIEhERUbaYzJJkkpOT8e2336JTp04ICQlB3bp1cenSJQwcOFDq0IiIiKiA4DCDPMIRs+kFBwfD09MTQgiMGDECS5cu5fhYIjI5jUaDpKQkqcMgKvJUKhXkuTA5nsksSaZMmTLYsGEDoqKi4OHhIXU4RFTICSEQGBiI8PBwqUMhIgByuRwVK1aESqV6q/swmaU8k5SUhGnTpqFVq1bo1q0bAKBLly4SR0VERcXrRNbR0RGWlpbcRZBIQlqtFv7+/ggICED58uXf6t8jk1kTE9k3KRKeP38ODw8PnD17Fr///jsePXoEOzs7qcMioiJCo9HoEtkSJUpIHQ4RAShZsiT8/f2RnJwMM7OcbyzFCWB5RFaEs9o9e/bA1dUVZ8+eha2tLVavXs1Elojy1OsxspaWlhJHQkSvvR5eoNFo3uo+TGbJZBITEzF+/Hj06NEDr169QuPGjXH16lX06tVL6tCIqIji0AKi/CO3/j1ymIGJFdUO2djYWLz77ru4ePEiAGD8+PFYsGDBWw/yJiIiIkqLPbNkEpaWlqhfvz7s7e3x119/YcmSJUxkiYiKsJcvX8LR0RFPnz6VOpRC45tvvsGYMWOkDkNyTGYp18THxyMsLExXXrZsGXx8fNC9e3cJoyIiKvgCAwMxZswYVKpUCWq1Gs7OzujWrRuOHDmi1+7MmTPo3Lkz7O3tYW5ujjp16mDJkiW6MYk7duyAQqGAn59fho9TtWpVTJgwAQDw7rvv4ssvv9Sde/fddyGTySCTyaBWq1G2bFl069YNO3fuNOg5fPfdd+jRowdcXFzSnXN3d4dCodB9mpfWm3G8tm7dunTzLyIjI/Htt9+ievXqMDc3R6lSpeDm5oadO3dCCNN9Vnr8+HE0aNAAarUaVapUwbp167K9xtvbG66urrC0tESFChXw448/pmuzefNm1KtXD5aWlihdujQ++eQTvHz5Und+0qRJWL9+PR4/fpybT6fAYTJrakVkeNbDhw/RokUL9OnTR/dL08LCAuXLl5c4MiKigu3p06do2LAhjh49ih9//BE3btzA/v370a5dO4waNUrXbteuXWjbti3KlSuHY8eO4e7duxg3bhzmzZsHDw8PCCHQvXt3lChRAuvXr0/3OCdOnMDDhw8xbNiwTGP59NNPERAQgEePHmHHjh2oWbMmPDw88Nlnn2X5HGJjY7FmzZoM7/38+XOcOXMGo0ePxtq1a414ZfSFh4ejRYsW2LBhA6ZMmYIrV67gxIkT6Nu3L7766itERETk+N5ZefLkCbp06YJ27drBx8cHX375JYYPH44DBw5kes0///yDAQMG4PPPP8fNmzexcuVKLF26FCtWrNC1OX36NAYNGoRhw4bh1q1b+PPPP3HhwgV8+umnujYODg5wd3fHqlWrTPLcCgxRxERERAgAIiIiIk8er/3vtUTtdbVF299r5snjSWHr1q2iWLFiAoAoUaKEuHfvntQhERHpiYuLE7dv3xZxcXFSh2K0999/X5QtW1ZER0enO/fq1SshhBDR0dGiRIkSolevXuna7NmzRwAQ27ZtE0IIMWHCBFG1atV07QYPHiyaNm2qK7dt21aMGzcu0/Jra9euFQDEoUOHMn0Of/75pyhZsmSG52bNmiU8PDzEnTt3hK2trYiNjdU7n9nj/vHHH8LW1lZXHjlypLCyshJ+fn7p2kZFRYmkpKRM43sbX331lahVq5ZeXd++fYW7u3um1/Tr10989NFHenU//fSTKFeunNBqtUIIIX788UdRqVKldG3Kli2rV7d+/XpRrly5t3kKksnq36Ux+RongFGOxcXF4csvv8Rvv/0GAGjVqhW2bt2KcuXKSRwZEZFhuv18CiFRCXn6mCWLqfH3mFYGtQ0LC8P+/fvx3XffwcrKKt351x+zHzx4EC9fvsSkSZP+3959hkV1vH8D/+4uLCxdBAUUxQYoMaKoiMZYgiKWYEcFK7G32EtULMEW0aghlkhRQ8Beoth/FjREo4KoICBgB2wUC33v54V/9nHdBV0UcPH+XNe+2Dkzc+6zI3IzO2eOQp0ePXrA2toaISEhcHd3h5eXF1avXo1z587h22+/BQC8fPkSu3fvxpo1a1S+nqFDh2LatGnYu3cvnJ2dldYJDw+Hg4ODQjkRITAwEH5+frC1tUX9+vWxe/duDB48WKUYpFIpQkND4eHhAQsLC4Xjenp6xbYNDw+Hq6trif1v2rQJHh4eSo9FREQoXLeLi4vSpRFFcnNzFbaJk0gkePDgAe7evQsrKys4OTlh7ty5CAsLg6urKx4/fozdu3eja9eucu1atmyJBw8e4M6dO0qXcHwJOJktY5V1N4O4uDj0798f0dHREAgEmDt3LhYuXAgNDf4nxRhTH09e5CI1K6eiwyjW7du3QUSwtbUtsV58fDwAoGHDhkqP29rayuo0atQIrVq1QkBAgCyZ3blzJ4ioVI8WFwqFsLa2LvHGrrt37ypNMk+ePInXr1/DxcUFAODp6Ql/f3+Vk9mnT58iPT39vZ+TMs2bN0dUVFSJdapXr17ssdTUVIXj1atXR1ZWFrKzsyGRSBTauLi4YMqUKRg2bBg6dOiA27dvw9fXFwCQkpICKysrtGnTBsHBwXB3d0dOTg4KCgrQo0cP+Pn5yfVV9LkWJcFfIs48yhwBEFSqpbNEBA8PD0RHR8PU1BTBwcHo1KlTRYfFGGMqM9XX+qzPSSretPSh9UeMGIEpU6Zg/fr10NfXR0BAAPr16wd9fX2Vzvf2eUvaMzQ7Oxva2toK5QEBAXB3d5dNhAwcOBAzZsxAYmIi6tWrp9L5S0sikaB+/fqlbl8aI0eORGJiIrp37478/HwYGBhg8uTJWLhwIYTCN7czxcTEYPLkyViwYAFcXFyQkpKCGTNmYMyYMfD395eLH3izLvlLxcksU5lAIIC/vz/mzJkDf39/mJubV3RIjDFWKh/6dX9FadCgAQQCAW7dulViPWtrawBAbGwsWrdurXA8NjYWjRo1kr0fMGAApkyZgp07d+Lbb7/FhQsXsGzZslLFWFhYiISEBLRo0aLYOiYmJkhPT5cre/78Ofbt24f8/Hy5G5gKCwsREBAAHx8fAICBgYHSm7cyMjJgaGgI4M1jUY2MjN77OSnzscsMzMzMkJaWJleWlpYGAwMDpbOywJvfoytWrMDSpUuRmpoKU1NT2c4UdevWBQAsW7YMbdq0wYwZMwAAX3/9NXR1ddG2bVv8/PPPst+9RbsImZqafuAVVz6czLIPcvPmTURGRsLT0xMA0KRJE4SFhVVwVIwxVrkZGxvDxcUFfn5+mDRpksK62YyMDBgZGaFz584wNjaGr6+vQjJ78OBBJCQkYMmSJbIyfX199OvXDwEBAUhMTIS1tTXatm1bqhi3bt2K9PR09OnTp9g6TZs2xZ9//ilXFhwcjJo1a2L//v1y5cePH4evry8WL14MkUgEGxsbHD9+XKHPq1evypJ4oVCIAQMGYPv27fD29lZY0vDy5Utoa2srXQr3scsMnJycFH4fnjhxAk5OTiX2CQAikQg1atQAAISEhMDJyUmWlL5+/VohXpFIBEB+JvrGjRvQ1NSEnZ3de89XaX3Cm9LUQnnvZtB+SyP6Kugraq+muxlIpVIKCAggiURCmpqadPHixYoOiTHGVKbOuxkkJiaSmZkZNWrUiHbv3k3x8fEUExNDa9euJVtbW1m9Xbt2kUgkopEjR9K1a9coOTmZtmzZQlWqVKG+ffvK7pIvEh4eTgCoSpUqtHz5coXzKtvNYOTIkZSSkkL379+niIgImjlzJmlqatLYsWNLvIbo6GjS0NCg58+fy8qaNGlCs2bNUqibkZFBYrGYDh06JLt+bW1tmjhxIl27do1u3bpFvr6+pKGhQUeOHJG1e/bsGdna2lLNmjVp69atdPPmTYqPjyd/f3+qX7++bOeHTy0pKYl0dHRoxowZFBsbS35+fiQSiejo0aOyOuvXr6eOHTvK3j958oQ2bNhAsbGxFBkZSZMmTSJtbW2537GBgYGkoaFBv//+OyUmJtL58+epefPm1LJlS7nze3t7y/WtTj7VbgaczJYxdU5mX7x4QYMHDya8WfhLnTp1orS0tIoOizHGVKbOySwR0aNHj2j8+PFUu3ZtEovFVKNGDfr+++/p9OnTcvXOnTtHLi4uZGBgQGKxmOzs7GjVqlVUUFCgtF8bGxsSiUT06NEjhWPKktmi3wdisZjMzc2pe/futHfv3g+6hpYtW9LGjRuJiOjy5csEgC5duqS0rqurK/Xq1Uv2/tKlS9SpUycyNTUlQ0NDcnR0pH379im0y8jIoNmzZ1ODBg1ILBZT9erVydnZmfbt26eQzH9Kp0+fJnt7exKLxVS3bl0KDAyUO+7t7U21a9eWvX/y5Am1atWKdHV1SUdHh7777jv6999/Ffpdt24dNWrUiCQSCZmbm5OHhwc9ePBAro6NjQ2FhISUxWWVuU+VzAqIyvCRGJ+hrKwsGBoaIjMzEwYGBmV+vg7+dniqIYRJgRSnvW6W+fk+lejoaPTv3x9xcXEQCoVYsmQJZs+eLVuYzhhj6iQnJwfJycmoU6eO0huRWNk7fPgwZsyYgRs3bvDvkk/kyJEjmDZtGqKjo9VyN6GSfi5VydfU78pZmduyZQsmTJiA3Nxc1KhRAyEhIaVeS8UYY4wBQLdu3ZCQkICHDx/C0tKyosOpFF69eoXAwEC1TGQ/pS/76suROm3NlZmZidzcXLi6umLbtm0wMTGp6JAYY4xVAiU9SICprm/fvhUdwmeBk1kGACgoKJD9ZTd16lTUqlULffr04a+CGGOMMfZZ40yljH3uC5KJCH5+fmjevDlevnwJ4M3+d/369eNEljHGGGOfPc5WysnnuMwgIyMD/fr1w4QJE3Dt2jW5J4owxhhjjKkDXmbwhfrvv//g7u6O5ORkaGpqYuXKlZg0aVJFh8UYY4wxphJOZsvJ57LcgIiwdu1azJw5E/n5+bCyssLOnTtLfAwhY4wxxtjnipcZlJPPZZnBzz//jClTpiA/Px+9e/dGZGQkJ7KMMcYYU1uczH5hRo4ciVq1auG3337D7t27YWRkVNEhMcYYY4yVGiezlZxUKsWJEydk783MzBAXF4fx48dDIPhc5osZY4yxks2fPx+jRo2q6DAqjadPn6JatWp48OBBRYfy0TiZLWMVuVb26dOn6NGjBzp37oydO3fKyvlRjowxpj6GDRsGgUCA5cuXy5Xv379fYVKisLAQa9asQePGjaGtrY0qVarA1dUVFy5ckKsXFBQEgUAAgUAAoVAIc3NzuLu74969e3L12rdvr/TcwJsnegkEAixcuFDhWEhICEQiEcaPH69w7MyZMxAIBMjIyPjATwBITU3F2rVr8dNPPykci4iIgEgkQrdu3VQ6l5WVFX799Ve5stOnT6Nr166oWrUqdHR00KhRI0ybNg0PHz784FhVlZOTg/Hjx6Nq1arQ09NDnz59kJaWVmKbtLQ0DBs2DBYWFtDR0UGXLl2QkJCgUC8iIgIdO3aErq4uDAwM8O233yI7OxsAYGJigiFDhsDb27tMrqs8cTJbTsp7DjQ8PBz29vYICwuDlpYWXr9+Xc4RMMYY+1S0tbWxYsUKpKenF1uHiDBgwAAsXrwYkydPRmxsLM6cOQNLS0u0b98e+/fvl6tvYGCAlJQUPHz4EHv27EFcXBz69eun0K+lpSWCgoLkyh4+fIhTp07B3NxcaSz+/v6YOXMmQkJCkJOTo/L1vmvLli1o3bo1ateurfRcEydOxLlz5/Do0aNSn2PTpk1wdnaGmZkZ9uzZg5iYGGzcuBGZmZnw9fX9mPBLNGXKFPz999/YtWsXzp49i0ePHqF3797F1ici9OzZE0lJSThw4AAiIyNRu3ZtODs749WrV7J6ERER6NKlCzp37oxLly7hv//+w4QJE+T2kB8+fDiCg4Px/PnzMru+ckFfmMzMTAJAmZmZ5XK+b7c0oq+CvqLvtjQql/MVFhaSj48PiUQiAkDW1tZ07dq1cjk3Y4x9rrKzsykmJoays7MrOhSVDR06lLp37062trY0Y8YMWfm+ffvo7V/joaGhBIAOHjyo0Efv3r2patWq9PLlSyIiCgwMJENDQ7k669atU/j92K5dOxo7dixVrVqVzp8/Lyv38fGhHj16UJMmTcjb21uun6SkJJJIJJSRkUGOjo4UHBwsd/z06dMEgNLT0z/4M7Czs6PffvtNofzFixekp6dHt27dInd3d/Lx8fngc9WuXZvWrFlDRET3798nsVhMP/74o9LzqxKrKjIyMkhTU5N27dolK4uNjSUAFBERobRNXFwcAaAbN27IygoLC8nU1JT++OMPWZmjoyPNmzfvvTHUqVOHtmzZ8hFXUXol/Vyqkq/x1lxlrDyXGTx+/Bienp6yNbKenp7YsGED9PT0yjEKxhhTI5vaAS8fl+859aoBo8+q1EQkEmHp0qUYNGgQJk2ahJo1ayrU+euvv2BtbY0ePXooHJs2bRr27t2LEydOoGfPngrHHz9+jH379kEkEkEkEskdE4vF8PDwQGBgINq0aQPgzTKFlStXKl1iEBgYiG7dusHQ0BCenp7w9/fHoEGDVLretz1//hwxMTFo3ry5wrGdO3fC1tYWNjY28PT0xI8//og5c+aofE/Irl27kJeXh5kzZyo9XtLN0q6urggPDy/2eO3atXHz5k2lx65cuYL8/Hw4OzvLymxtbVGrVi1ERESgVatWCm1yc3MByC8ZFAqF0NLSwvnz5/HDDz/g8ePHuHjxIjw8PNC6dWskJibC1tYWPj4++Oabb+T6a9myJcLDw+Hl5VXsNXzuOJktL+WQ1V66dAknTpyARCKBn5+fbJ0VY4yxYrx8DLwo/VfT5alXr16wt7eHt7e30ic2xsfHo2HDhkrbFpXHx8fLyjIzM6Gnpwciki1FmzRpEnR1dRXajxgxAm3btsXatWtx5coVZGZmonv37grJrFQqRVBQENavXw8AGDBgAKZNm4bk5GTUqVOnVNd97949EBEsLCwUjvn7+8PT0xMA0KVLF2RmZuLs2bNo3769SudISEiAgYFBscsmSrJlyxbZOlRlNDU1iz2WmpoKsViskCxXr14dqampStsUJbtz5szBpk2boKurizVr1uDBgwdISUkBACQlJQEAFi5ciFWrVsHe3h7btm3Dd999hxs3bqBBgway/iwsLBAZGfmhl/tZ4mS2EunevTt8fX3h4uICOzu7ig6HMcY+f3rV1OqcK1asQMeOHTF9+nSlx4k+fOZEX18fV69eRX5+Po4cOYLg4GD4+PgordukSRM0aNAAu3fvxunTpzF48GBoaCimECdOnMCrV6/QtWtXAG9uMurUqRMCAgKwZMmSD47tbUWJ4rs3L8fFxeHSpUvYt28fAEBDQwPu7u7w9/dXOZklolJP/tSoUaNU7UpLU1MTe/fuhZeXF4yNjSESieDs7AxXV1fZ+EulUgDA6NGjMXz4cABA06ZNcerUKQQEBGDZsmWy/iQSidrfV8PJbFkrw4nRlJQUTJw4EWvWrIGlpSUAYOrUqWV3QsYYq2xU/Lq/on377bdwcXHBnDlzMGzYMLlj1tbWiI2NVdquqNza2lpWJhQKUb9+fQBvZm4TExMxduxYbN++XWkfI0aMgJ+fH2JiYnDp0iWldfz9/fH8+XNIJBJZmVQqRXR0NBYtWiR389GHMjExAQCkp6fD1NRU7lwFBQVyM7ZEBC0tLfz2228wNDSEgYEBgDez0O/OfmZkZMDQ0BDAm88lMzMTKSkpKs/OfswyAzMzM+Tl5SEjI0MuvrS0NJiZmRXbp4ODA6KiopCZmYm8vDyYmprC0dFRthSj6BoaNWok165hw4YKO1Y8f/5c7nNVR7ybQTn51DntiRMnYG9vjz179mDkyJGfuHfGGGOfq+XLl+Pvv/9GRESEXPmAAQOQkJCAv//+W6GNr68vqlatik6dOhXb7+zZs7Fjxw5cvXpV6fFBgwbh+vXr+OqrrxSSJAB49uwZDhw4gNDQUERFRclekZGRSE9Px/Hjx1W80jfq1asHAwMDxMTEyMoKCgqwbds2+Pr6yp3r2rVrsLCwQEhICACgQYMGEAqFuHLlilyfSUlJyMzMlCX3ffv2hVgsxsqVK5XGUNI2Ylu2bJGL4d1XWFhYsW0dHBygqamJU6dOycri4uJw7949ODk5vfezMTQ0hKmpKRISEnD58mW4ubkBeLPtmIWFBeLi4uTqx8fHK+wIcePGDTRt2vS95/qc8cysmikoKMDChQuxdOlSEBEaN26ssE8eY4yxyqtx48bw8PDAunXr5MoHDBiAXbt2YejQofjll1/w3XffISsrC35+fjh48CB27dqldD1sEUtLS/Tq1QsLFizAoUOHFI5XqVIFKSkpxa4B3b59O6pWrYr+/fsrfGXftWtX+Pv7o0uXLrKy69evQ19fX/ZeIBCgSZMmCv0KhUI4Ozvj/PnzspvXDh06hPT0dHh5eclmV4v06dMH/v7+GDNmDPT19fHDDz9g2rRp0NDQQOPGjXH//n3MmjULrVq1QuvWrWXXvmbNGkyYMAFZWVkYMmQIrKys8ODBA2zbtg16enrFbs/1McsMDA0N4eXlhalTp8LY2BgGBgaYOHEinJyc5G7+srW1xbJly9CrVy8Ab25YMzU1Ra1atXD9+nVMnjwZPXv2ROfOnWWf5YwZM+Dt7Y0mTZrA3t4eW7duxa1bt7B7925Zv69fv8aVK1ewdOnSUl/DZ+GT7rGgBsp7a65v/N9szeX8x8dvzXX//n1q27Yt4c3tZDRq1Ch6/fr1J4iSMcYqN3XfmsvNzU2uLDk5mcRiMb37azw/P59++eUXsrOzI7FYTAYGBuTi4iK3rRaR8q25iIgiIiIIAF28eJGI3mzNNXny5GJje3trrsaNG9O4ceOU1tuxYweJxWJ68uSJbLusd18ikajY84SFhVGNGjWosLCQiIi6d+9OXbt2VVr34sWLBEC2LWV2djZ5e3uTra0tSSQSqlOnDo0aNYqePHmi0PbEiRPk4uJCVapUIW1tbbK1taXp06fTo0ePio3tY2VnZ9O4ceOoSpUqpKOjQ7169aKUlBS5OgAoMDBQ9n7t2rVUs2ZN0tTUpFq1atG8efMoNzdXoe9ly5ZRzZo1SUdHh5ycnCg8PFzu+F9//UU2NjZlcl0f4lNtzSUgUmG1eCWQlZUFQ0NDZGZmytbSlKW2AXbIEAlhnk84/sONUvcTFRUFZ2dnPHv2DHp6evjjjz8wYMCATxgpY4xVXjk5ObI76vkpiOqHiODo6IgpU6Zg4MCBFR1OpdGqVStMmjTpo7ZO+xgl/Vyqkq/xmlk1YW1tDXNzczRt2hRXr17lRJYxxtgXQyAQYPPmzSgoKKjoUCqNp0+fonfv3pXijwNeM/sZS0lJQfXq1SEUCqGjo4OwsDCYmpryrAJjjLEvjr29Pezt7Ss6jErDxMSk2IdEqBuemS1jpV3DcfDgQdjZ2cntBWdpacmJLGOMMcbYWziZ/czk5eVh6tSpcHNzQ3p6Og4dOsRfqzDGGGOMFYOT2c9IcnIy2rZtizVr1gAAfvzxR5w9e1bpU1YYY4wxxhivmf1s7N27FyNGjJA9pSQoKEi2+TFjjDHGGFOOk9lyUtITwB49eoRBgwYhNzcXrVq1QmhoqMITOhhjjDHGmCJOZj8DFhYW+PXXX5GYmIilS5cW+3QVxhhjjDEmj5PZMlbcbgY7d+5EnTp10KJFCwDAmDFjyi8oxhhjjLFKgm8AKydFywyys7MxZswYuLu7w93dHZmZmRUaF2OMMcaAU6dOoWHDhigsLKzoUCqNVq1aYc+ePWV+ns8imfXz84OVlRW0tbXh6OiIS5culVh/165dsLW1hba2Nho3boywsLByirT0CEBcXBxatWqFTZs2QSAQYODAgdDV1a3o0BhjjH3Ghg0bBoFAAIFAALFYjPr162Px4sWybRvPnDkDgUAAOzs7hUSs6IbiIlZWVrK+3n4tX75crq+MjAyFOKysrPDrr7/K3he1/ffff+Xq5ebmomrVqhAIBDhz5ozcsUOHDqFdu3bQ19eHjo4OWrRoIRcfANy5cwcCgQDVqlXDixcv5I7Z29tj4cKFsvft27fHjz/+qBBrSEgIRCIRxo8fr3CsODNnzsS8efMgEonkyrOzs2FsbAwTExPk5uYqtBMIBNi/f79C+bBhw9CzZ0+5stu3b2P48OGoWbMmtLS0UKdOHQwcOBCXL1/+4DhLQ9U8Kz8/H4sXL0a9evWgra2NJk2a4OjRowr1Hj58CE9PT1StWhUSiQSNGzeWu5Z58+Zh9uzZkEqln/ya3lbhyeyOHTswdepUeHt74+rVq2jSpAlcXFzw+PFjpfX/+ecfDBw4EF5eXoiMjETPnj3Rs2dP3Lhxo5wj/zBFywwe/ZsBBwcHREdHw9TUFEePHoWPjw9vu8UYY+y9unTpgpSUFCQkJGDatGlYuHAhfvnlF7k6SUlJ2LZt23v7Wrx4MVJSUuReEydOLFVclpaWCAwMlCvbt28f9PT0FOquX78ebm5uaNOmDS5evIjo6GgMGDAAY8aMwfTp0xXqv3jxAqtWrSpVXP7+/pg5cyZCQkKQk5Pz3vrnz59HYmIi+vTpo3Bsz549sLOzg62trdKk9UNdvnwZDg4OiI+Px6ZNmxATE4N9+/bB1tYW06ZNK3W/76NqngW8SUI3bdqE9evXIyYmBmPGjEGvXr0QGRkpq5Oeno42bdpAU1MTR44cQUxMDHx9fVGlShVZHVdXV7x48QJHjhwps+sDAFAFa9myJY0fP172vrCwkCwsLGjZsmVK6/fv35+6desmV+bo6EijR4/+oPNlZmYSAMrMzCx90Cpw3GhLRm2NCG/yWmrfvj09evSoXM7NGGPsjezsbIqJiaHs7OyKDkVlQ4cOJTc3N7myTp06UatWrYiI6PTp0wSAZsyYQZaWlpSTkyOrZ2hoSIGBgbL3tWvXpjVr1hR7rqK+0tPTFY692xYAzZs3jwwMDOj169dysc2fP58A0OnTp4mI6N69e6SpqUlTp05V6HfdunUEgP79918iIkpOTpZdj56eHqWlpcnqNmnShLy9vWXv27VrR5MnT5brLykpiSQSCWVkZJCjoyMFBwcXe71Fxo8fT3379lV6rH379rRx40basGEDderUSeE4ANq3b59C+dvjJpVKyc7OjhwcHKiwsFChrrLP+1NRNc8iIjI3N6fffvtNrqx3797k4eEhez9r1iz65ptv3nv+4cOHk6enp9JjJf1cqpKvVei0YF5eHq5cuYI5c+bIyoRCIZydnREREaG0TUREBKZOnSpX5uLiUuxfS7m5uXJfC2RlZX184CoQiAQoyCwABID3Am/Mnz9f4SsMxhhjFcP9kDueZj8t13OaSEywo/uOj+pDIpHg2bNncmU//vgj/vzzT6xfv17pTGdZcHBwgJWVFfbs2QNPT0/cu3cP586dg5+fH5YsWSKrt3v3buTn5yuNa/To0Zg7dy5CQkLg6OgoKx84cCBOnDiBxYsX47fffvvgmAIDA9GtWzcYGhrC09MT/v7+GDRoUIltwsPDldZJTExEREQE9u7dCyLClClTcPfuXZW3z4yKisLNmzfx119/QShU/FLcyMio2LZLly7F0qVLS+w/JiYGtWrVUigvTZ4FvMmdtLW15cokEgnOnz8ve3/w4EG4uLigX79+OHv2LGrUqIFx48Zh5MiRcu1atmwpW8ZSVip0mcHTp09RWFiI6tWry5VXr14dqampStukpqaqVH/ZsmUwNDSUvSwtLT9N8B9IIBSg5siaaDHNCgsXLuREljHGPiNPs5/i8evH5fr6mOSZiHDy5EkcO3YMHTt2lDumo6MDb29vLFu2rMSbi2fNmgU9PT25V3h4eKljGjFiBAICAgAAQUFB6Nq1K0xNTeXqxMfHw9DQEObm5grtxWIx6tati/j4eLnyorW8mzdvRmJi4gfFIpVKERQUBE9PTwDAgAEDcP78eSQnJ5fY7u7du7CwsFAoDwgIgKurK6pUqQJjY2O4uLgoLKv4EAkJCQAAW1tblduOGTMGUVFRJb6UxQ6ULs8C3kwSrl69GgkJCZBKpThx4gT27t2LlJQUWZ2kpCRs2LABDRo0wLFjxzB27FhMmjQJW7dulevLwsIC9+/fL9N1s5V+weacOXPkZnKzsrLKNaH9o91WEBVCUyQut3Myxhj7MCYSE7U456FDh6Cnp4f8/HxIpVIMGjRI7kaoIl5eXvD19cWKFSuKnc2bMWMGhg0bJldWo0YNlWMq4unpidmzZyMpKQlBQUFYt25dqft6l4uLC7755hvMnz8ff/3113vrnzhxAq9evULXrl0BACYmJujUqRMCAgLkZorflZ2drTATWVhYiK1bt2Lt2rWyMk9PT0yfPh0LFixQOsNaHKLiNup8P2NjYxgbG5e6fWmsXbsWI0eOhK2tLQQCAerVq4fhw4fL/mgB3vzh0Lx5c9m/s6ZNm+LGjRvYuHEjhg4dKqsnkUgglUqRm5sLiURSJvFWaDJrYmICkUiEtLQ0ufK0tDSYmZkpbWNmZqZSfS0tLWhpaX2agEvBrl7zCjs3Y4yxkn3s1/3lpUOHDtiwYQPEYjEsLCyKvXlYQ0MDPj4+GDZsGCZMmKC0jomJCerXr6/0mIGBAQDIHq3+toyMDBgaGiq0qVq1Krp37w4vLy/k5OTIbvp5m7W1NTIzM/Ho0SOFWcS8vDwkJiaiQ4cOSmNavnw5nJycMGPGDKXH3+bv74/nz5/LJU1SqRTR0dFYtGhRsQmoiYkJ0tPT5cqOHTuGhw8fwt3dXa68sLAQp06dQqdOnQAA+vr6SmfC3/68rK2tAQC3bt1C06ZN33sdb/uYZQalybMAwNTUFPv370dOTg6ePXsGCwsLzJ49G3Xr1pXVMTc3R6NGjeTaNWzYUGErrufPn0NXV7fMElmggpcZiMViODg44NSpU7IyqVSKU6dOwcnJSWkbJycnufrAm7/EiqvPGGOMqTtdXV3Ur18ftWrVeu8uOP369YOdnR0WLVqk8nkaNGgAoVCIK1euyJUnJSUhMzNTlpS9a8SIEThz5gyGDBmidDldnz59oKmpCV9fX4VjGzduxKtXrzBw4EClfbds2RK9e/fG7NmzS4z92bNnOHDgAEJDQ+W+go+MjER6ejqOHz9ebNumTZsiJiZGrszf3x8DBgxQ+Ep/wIAB8Pf3l9WzsbFR+LwKCwtx7do12edlb2+PRo0awdfXV+nX7cq2QivyMcsMSpNnvU1bWxs1atRAQUEB9uzZAzc3N9mxNm3aIC4uTq5+fHy8wnriGzduqJzAq+y9t4iVsdDQUNLS0qKgoCCKiYmhUaNGkZGREaWmphIR0eDBg2n27Nmy+hcuXCANDQ1atWoVxcbGkre3N2lqatL169c/6HzlvZsBY4yxilfZdjN4m7IdCE6dOkUaGhqkoaGhsJvB4sWLKSUlRe719u/EUaNGkZWVFR04cICSkpLo7Nmz1KpVK2rVqhVJpVJZPbx1F79UKqUnT55Qbm4uEb25Ox9v7WZARLRmzRoSCoU0d+5cio2Npdu3b5Ovry9paWnRtGnTZPWKdjOIjIyUlcXFxZGGhgZpa2sXu5vBmjVryNzcXC7GIv379y92twKiNzsqODg4yN4/fvyYNDU16ciRIwp1w8LCSEtLi549e0ZERH/99RdJJBLy8/Oj+Ph4ioyMpBEjRpChoaEslyEiunjxIunr61Pr1q3p8OHDlJiYSNeuXaOff/6Zvv3222Jj+1jvy7OIFHOtf//9l/bs2UOJiYl07tw56tixI9WpU0fu39ilS5dIQ0ODfHx8KCEhgYKDg0lHR4f+/PNPufO3a9eOFi9erDS2T7WbQYUns0RE69evp1q1apFYLKaWLVvKtucgevMhDB06VK7+zp07ydramsRiMdnZ2dHhw4c/+FyczDLG2JfnS0tmiYg6d+5MABSSWfzfVpFvv97e3jI7O5u8vb3J1taWJBIJ1alTh0aNGkVPnjyR6x/FbElFpDyZJSI6cOAAtW3blnR1dUlbW5scHBwoICBAro6yZJboTZINoNhktnHjxjRu3Dil8ezYsYPEYrHCNRR59uwZaWtr061bt4iIaNWqVWRkZER5eXkKdXNzc8nIyIjWrl0rKwsODiYHBwfS19en6tWrU9euXenatWsKbePi4mjIkCFkYWFBYrGYateuTQMHDqSrV68qjetTKSnPIlLMtc6cOUMNGzYkLS0tqlq1Kg0ePJgePnyo0O/ff/9NX331FWlpaZGtrS1t3rxZ7viDBw9IU1OT7t+/rzSuT5XMCog+YlWyGsrKyoKhoSEyMzNla4MYY4xVbjk5OUhOTkadOnUUbvRhDHhzY1xWVhY2bdpU0aFUGrNmzUJ6ejo2b96s9HhJP5eq5GsV/gQwxhhjjLGK9tNPP6F27dpl/ujVL0m1atVK3EXiU6n0W3MxxhhjjL2PkZER5s6dW9FhVCpl+Zjet/HMLGOMMcYYU1uczDLGGGOMMbXFySxjjLEvxhd2zzNjn7VP9fPIySxjjLFKT1NTEwDw+vXrCo6EMVYkLy8PAJQ+aEMVfAMYY4yxSk8kEsHIyAiPHz8GAOjo6EAgEFRwVIx9uaRSKZ48eQIdHZ33PtXufTiZZYwx9kUoehZ9UULLGKtYQqEQtWrV+ug/LDmZZYwx9kUQCAQwNzdHtWrVkJ+fX9HhMPbFE4vFEAo/fsUrJ7OMMca+KCKR6KPX6DHGPh98AxhjjDHGGFNbnMwyxhhjjDG1xcksY4wxxhhTW1/cmtmiDXqzsrIqOBLGGGOMMaZMUZ72IQ9W+OKS2RcvXgAALC0tKzgSxhhjjDFWkhcvXsDQ0LDEOgL6wp7tJ5VK8ejRI+jr65fLhtlZWVmwtLTE/fv3YWBgUObnY58ej6H64zFUfzyG6o3HT/2V9xgSEV68eAELC4v3bt/1xc3MCoVC1KxZs9zPa2BgwD/Aao7HUP3xGKo/HkP1xuOn/spzDN83I1uEbwBjjDHGGGNqi5NZxhhjjDGmtjiZLWNaWlrw9vaGlpZWRYfCSonHUP3xGKo/HkP1xuOn/j7nMfzibgBjjDHGGGOVB8/MMsYYY4wxtcXJLGOMMcYYU1uczDLGGGOMMbXFySxjjDHGGFNbnMx+An5+frCysoK2tjYcHR1x6dKlEuvv2rULtra20NbWRuPGjREWFlZOkbLiqDKGf/zxB9q2bYsqVaqgSpUqcHZ2fu+Ys7Kn6s9hkdDQUAgEAvTs2bNsA2TvpeoYZmRkYPz48TA3N4eWlhasra35/9MKpOr4/frrr7CxsYFEIoGlpSWmTJmCnJyccoqWvevcuXPo0aMHLCwsIBAIsH///ve2OXPmDJo1awYtLS3Ur18fQUFBZR6nUsQ+SmhoKInFYgoICKCbN2/SyJEjycjIiNLS0pTWv3DhAolEIlq5ciXFxMTQvHnzSFNTk65fv17OkbMiqo7hoEGDyM/PjyIjIyk2NpaGDRtGhoaG9ODBg3KOnBVRdQyLJCcnU40aNaht27bk5uZWPsEypVQdw9zcXGrevDl17dqVzp8/T8nJyXTmzBmKiooq58gZkerjFxwcTFpaWhQcHEzJycl07NgxMjc3pylTppRz5KxIWFgY/fTTT7R3714CQPv27SuxflJSEuno6NDUqVMpJiaG1q9fTyKRiI4ePVo+Ab+Fk9mP1LJlSxo/frzsfWFhIVlYWNCyZcuU1u/fvz9169ZNrszR0ZFGjx5dpnGy4qk6hu8qKCggfX192rp1a1mFyN6jNGNYUFBArVu3pi1bttDQoUM5ma1gqo7hhg0bqG7dupSXl1deIbISqDp+48ePp44dO8qVTZ06ldq0aVOmcbIP8yHJ7MyZM8nOzk6uzN3dnVxcXMowMuV4mcFHyMvLw5UrV+Ds7CwrEwqFcHZ2RkREhNI2ERERcvUBwMXFpdj6rGyVZgzf9fr1a+Tn58PY2LiswmQlKO0YLl68GNWqVYOXl1d5hMlKUJoxPHjwIJycnDB+/HhUr14dX331FZYuXYrCwsLyCpv9n9KMX+vWrXHlyhXZUoSkpCSEhYWha9eu5RIz+3ifUz6jUe5nrESePn2KwsJCVK9eXa68evXquHXrltI2qampSuunpqaWWZyseKUZw3fNmjULFhYWCj/UrHyUZgzPnz8Pf39/REVFlUOE7H1KM4ZJSUn43//+Bw8PD4SFheH27dsYN24c8vPz4e3tXR5hs/9TmvEbNGgQnj59im+++QZEhIKCAowZMwZz584tj5DZJ1BcPpOVlYXs7GxIJJJyi4VnZhn7CMuXL0doaCj27dsHbW3tig6HfYAXL15g8ODB+OOPP2BiYlLR4bBSkkqlqFatGjZv3gwHBwe4u7vjp59+wsaNGys6NPYBzpw5g6VLl+L333/H1atXsXfvXhw+fBhLliyp6NCYGuKZ2Y9gYmICkUiEtLQ0ufK0tDSYmZkpbWNmZqZSfVa2SjOGRVatWoXly5fj5MmT+Prrr8syTFYCVccwMTERd+7cQY8ePWRlUqkUAKChoYG4uDjUq1evbINmckrzc2hubg5NTU2IRCJZWcOGDZGamoq8vDyIxeIyjZn9f6UZv/nz52Pw4MH44YcfAACNGzfGq1evMGrUKPz0008QCnmu7XNXXD5jYGBQrrOyAM/MfhSxWAwHBwecOnVKViaVSnHq1Ck4OTkpbePk5CRXHwBOnDhRbH1WtkozhgCwcuVKLFmyBEePHkXz5s3LI1RWDFXH0NbWFtevX0dUVJTs9f3336NDhw6IioqCpaVleYbPULqfwzZt2uD27duyP0QAID4+Hubm5pzIlrPSjN/r168VEtaiP0yIqOyCZZ/MZ5XPlPstZ5VMaGgoaWlpUVBQEMXExNCoUaPIyMiIUlNTiYho8ODBNHv2bFn9CxcukIaGBq1atYpiY2PJ29ubt+aqYKqO4fLly0ksFtPu3bspJSVF9nrx4kVFXcIXT9UxfBfvZlDxVB3De/fukb6+Pk2YMIHi4uLo0KFDVK1aNfr5558r6hK+aKqOn7e3N+nr61NISAglJSXR8ePHqV69etS/f/+KuoQv3osXLygyMpIiIyMJAK1evZoiIyPp7t27REQ0e/ZsGjx4sKx+0dZcM2bMoNjYWPLz8+OtudTZ+vXrqVatWiQWi6lly5b077//yo61a9eOhg4dKld/586dZG1tTWKxmOzs7Ojw4cPlHDF7lypjWLt2bQKg8PL29i7/wJmMqj+Hb+Nk9vOg6hj+888/5OjoSFpaWlS3bl3y8fGhgoKCco6aFVFl/PLz82nhwoVUr1490tbWJktLSxo3bhylp6eXf+CMiIhOnz6t9Hdb0bgNHTqU2rVrp9DG3t6exGIx1a1blwIDA8s9biIiARHP5zPGGGOMMfXEa2YZY4wxxpja4mSWMcYYY4ypLU5mGWOMMcaY2uJkljHGGGOMqS1OZhljjDHGmNriZJYxxhhjjKktTmYZY4wxxpja4mSWMcYYY4ypLU5mGWMMQFBQEIyMjCo6jFITCATYv39/iXWGDRuGnj17lks8jDFWXjiZZYxVGsOGDYNAIFB43b59u6JDQ1BQkCweoVCImjVrYvjw4Xj8+PEn6T8lJQWurq4AgDt37kAgECAqKkquztq1axEUFPRJzlechQsXyq5TJBLB0tISo0aNwvPnz1XqhxNvxtiH0qjoABhj7FPq0qULAgMD5cpMTU0rKBp5BgYGiIuLg1QqxbVr1zB8+HA8evQIx44d++i+zczM3lvH0NDwo8/zIezs7HDy5EkUFhYiNjYWI0aMQGZmJnbs2FEu52eMfVl4ZpYxVqloaWnBzMxM7iUSibB69Wo0btwYurq6sLS0xLhx4/Dy5cti+7l27Ro6dOgAfX19GBgYwMHBAZcvX5YdP3/+PNq2bQuJRAJLS0tMmjQJr169KjE2gUAAMzMzWFhYwNXVFZMmTcLJkyeRnZ0NqVSKxYsXo2bNmtDS0oK9vT2OHj0qa5uXl4cJEybA3Nwc2traqF27NpYtWybXd9Eygzp16gAAmjZtCoFAgPbt2wOQn+3cvHkzLCwsIJVK5WJ0c3PDiBEjZO8PHDiAZs2aQVtbG3Xr1sWiRYtQUFBQ4nVqaGjAzMwMNWrUgLOzM/r164cTJ07IjhcWFsLLywt16tSBRCKBjY0N1q5dKzu+cOFCbN26FQcOHJDN8p45cwYAcP/+ffTv3x9GRkYwNjaGm5sb7ty5U2I8jLHKjZNZxtgXQSgUYt26dbh58ya2bt2K//3vf5g5c2ax9T08PFCzZk38999/uHLlCmbPng1NTU0AQGJiIrp06YI+ffogOjoaO3bswPnz5zFhwgSVYpJIJJBKpSgoKMDatWvh6+uLVatWITo6Gi4uLvj++++RkJAAAFi3bh0OHjyInTt3Ii4uDsHBwbCyslLa76VLlwAAJ0+eREpKCvbu3atQp1+/fnj27BlOnz4tK3v+/DmOHj0KDw8PAEB4eDiGDBmCyZMnIyYmBps2bUJQUBB8fHw++Brv3LmDY8eOQSwWy8qkUilq1qyJXbt2ISYmBgsWLMDcuXOxc+dOAMD06dPRv39/dOnSBSkpKUhJSUHr1q2Rn58PFxcX6OvrIzw8HBcuXICenh66dOmCvLy8D46JMVbJEGOMVRJDhw4lkUhEurq6slffvn2V1t21axdVrVpV9j4wMJAMDQ1l7/X19SkoKEhpWy8vLxo1apRcWXh4OAmFQsrOzlba5t3+4+Pjydrampo3b05ERBYWFuTj4yPXpkWLFjRu3DgiIpo4cSJ17NiRpFKp0v4B0L59+4iIKDk5mQBQZGSkXJ2hQ4eSm5ub7L2bmxuNGDFC9n7Tpk1kYWFBhYWFRET03Xff0dKlS+X62L59O5mbmyuNgYjI29ubhEIh6erqkra2NgEgALR69epi2xARjR8/nvr06VNsrEXntrGxkfsMcnNzSSKR0LFjx0rsnzFWefGaWcZYpdKhQwds2LBB9l5XVxfAm1nKZcuW4datW8jKykJBQQFycnLw+vVr6OjoKPQzdepU/PDDD9i+fbvsq/J69eoBeLMEITo6GsHBwbL6RASpVIrk5GQ0bNhQaWyZmZnQ09ODVCpFTk4OvvnmG2zZsgVZWVl49OgR2rRpI1e/TZs2uHbtGoA3SwQ6deoEGxsbdOnSBd27d0fnzp0/6rPy8PDAyJEj8fvvv0NLSwvBwcEYMGAAhEKh7DovXLggNxNbWFhY4ucGADY2Njh48CBycnLw559/IioqChMnTpSr4+fnh4CAANy7dw/Z2dnIy8uDvb19ifFeu3YNt2/fhr6+vlx5Tk4OEhMTS/EJMMYqA05mGWOViq6uLurXry9XdufOHXTv3h1jx46Fj48PjI2Ncf78eXh5eSEvL09pUrZw4UIMGjQIhw8fxpEjR+Dt7Y3Q0FD06tULL1++xOjRozFp0iSFdrVq1So2Nn19fVy9ehVCoRDm5uaQSCQAgKysrPdeV7NmzZCcnIwjR47g5MmT6N+/P5ydnbF79+73ti1Ojx49QEQ4fPgwWrRogfDwcKxZs0Z2/OXLl1i0aBF69+6t0FZbW7vYfsVisWwMli9fjm7dumHRokVYsmQJACA0NBTTp0+Hr68vnJycoK+vj19++QUXL14sMd6XL1/CwcFB7o+IIp/LTX6MsfLHySxjrNK7cuUKpFIpfH19ZbOOReszS2JtbQ1ra2tMmTIFAwcORGBgIHr16oVmzZohJiZGIWl+H6FQqLSNgYEBLCwscOHCBbRr105WfuHCBbRs2VKunru7O9zd3dG3b1906dIFz58/h7GxsVx/RetTCwsLS4xHW1sbvXv3RnBwMG7fvg0bGxs0a9ZMdrxZs2aIi4tT+TrfNW/ePHTs2BFjx46VXWfr1q0xbtw4WZ13Z1bFYrFC/M2aNcOOHTtQrVo1GBgYfFRMjLHKg28AY4xVevXr10d+fj7Wr1+PpKQkbN++HRs3biy2fnZ2NiZMmIAzZ87g7t27uHDhAv777z/Z8oFZs2bhn3/+wYQJExAVFYWEhAQcOHBA5RvA3jZjxgysWLECO3bsQFxcHGbPno2oqChMnjwZALB69WqEhITg1q1biI+Px65du2BmZqb0QQ/VqlWDRCLB0aNHkZaWhszMzGLP6+HhgcOHDyMgIEB241eRBQsWYNu2bVi0aBFu3ryJ2NhYhIaGYt68eSpdm5OTE77++mssXboUANCgQQNcvnwZx44dQ3x8PObPn4///vtPro2VlRWio6MRFxeHp0+fIj8/Hx4eHjAxMYGbmxvCw8ORnJyMM2fOYNKkSXjw4IFKMTHGKg9OZhljlV6TJk2wevVqrFixAl999RWCg4PltrV6l0gkwrNnzzBkyBBYW1ujf//+cHV1xaJFiwAAX3/9Nc6ePYv4+Hi0bdsWTZs2xYIFC2BhYVHqGCdNmoSpU6di2rRpaNy4MY4ePYqDBw+iQYMGAN4sUVi5ciWaN2+OFi1a4M6dOwgLC5PNNL9NQ0MD69atw6ZNm2BhYQE3N7diz9uxY0cYGxsjLi4OgwYNkjvm4uKCQ4cO4fjx42jRogVatWqFNWvWoHbt2ipf35QpU7Blyxbcv38fo0ePRu/eveHu7g5HR0c8e/ZMbpYWAEaOHAkbGxs0b94cpqamuHDhAnR0dHDu3DnUqlULvXv3RsOGDeHl5YWcnByeqWXsCyYgIqroIBhjjDHGGCsNnplljDHGGGNqi5NZxhhjjDGmtjiZZYwxxhhjaouTWcYYY4wxprY4mWWMMcYYY2qLk1nGGGOMMaa2OJlljDHGGGNqi5NZxhhjjDGmtjiZZYwxxhhjaouTWcYYY4wxprY4mWWMMcYYY2rr/wEL8L9IiAU9hQAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 800x600 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# DenseNet201\n",
        "plot_confusion_matrix(densenet_model, external_test_gen, \"DenseNet201\")\n",
        "\n",
        "# ResNet152\n",
        "plot_confusion_matrix(resnet_model, external_test_gen, \"ResNet152\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1343
        },
        "id": "KoNHTcI_cwMC",
        "outputId": "64b92923-31e4-458b-9adb-fb96f91f8a5b"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "       covid       1.00      0.81      0.89      2276\n",
            "      normal       0.80      0.94      0.87      2313\n",
            "   pneumonia       0.88      0.90      0.89      2313\n",
            "\n",
            "    accuracy                           0.88      6902\n",
            "   macro avg       0.89      0.88      0.88      6902\n",
            "weighted avg       0.89      0.88      0.88      6902\n",
            "\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 2 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\n",
            "Classification Report:\n",
            "              precision    recall  f1-score   support\n",
            "\n",
            "       covid       0.88      0.77      0.82      2276\n",
            "      normal       0.83      0.86      0.84      2313\n",
            "   pneumonia       0.84      0.90      0.87      2313\n",
            "\n",
            "    accuracy                           0.85      6902\n",
            "   macro avg       0.85      0.85      0.85      6902\n",
            "weighted avg       0.85      0.85      0.85      6902\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "\n",
        "def summarize_results(models, datasets, dataset_names):\n",
        "    results = []\n",
        "    for model, model_name in models:\n",
        "        for gen, ds_name in zip(datasets, dataset_names):\n",
        "            loss, acc = model.evaluate(gen, verbose=0)\n",
        "            error_rate = 1 - acc\n",
        "\n",
        "            # AUC (macro average across classes)\n",
        "            y_true = gen.classes\n",
        "            y_pred = model.predict(gen, verbose=0)\n",
        "            y_true_bin = label_binarize(y_true, classes=range(len(gen.class_indices)))\n",
        "            aucs = []\n",
        "            for i in range(y_true_bin.shape[1]):\n",
        "                fpr, tpr, _ = roc_curve(y_true_bin[:, i], y_pred[:, i])\n",
        "                aucs.append(auc(fpr, tpr))\n",
        "            auc_avg = np.mean(aucs)\n",
        "\n",
        "            results.append({\n",
        "                \"Model\": model_name,\n",
        "                \"Dataset\": ds_name,\n",
        "                \"Accuracy\": round(acc*100, 2),\n",
        "                \"Error Rate\": round(error_rate*100, 2),\n",
        "                \"Loss\": round(loss, 4),\n",
        "                \"Avg AUC\": round(auc_avg, 4)\n",
        "            })\n",
        "    return pd.DataFrame(results)\n",
        "\n",
        "# Define models and datasets\n",
        "models = [(densenet_model, \"DenseNet201\"), (resnet_model, \"ResNet152\")]\n",
        "datasets = [test_gen, external_test_gen]\n",
        "dataset_names = [\"Main Dataset\", \"External Dataset\"]\n",
        "\n",
        "# Generate summary table\n",
        "summary_df = summarize_results(models, datasets, dataset_names)\n",
        "import IPython.display as display\n",
        "display.display(summary_df)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 174
        },
        "id": "VRx19moje0_l",
        "outputId": "f60a8120-c1da-4cf9-e5ca-e4bcb6070984"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "         Model           Dataset  Accuracy  Error Rate    Loss  Avg AUC\n",
              "0  DenseNet201      Main Dataset     93.23        6.77  0.1898   0.9916\n",
              "1  DenseNet201  External Dataset     88.26       11.74  0.3680   0.9742\n",
              "2    ResNet152      Main Dataset     86.37       13.63  0.3492   0.9665\n",
              "3    ResNet152  External Dataset     84.58       15.42  0.4092   0.9573"
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-f3411beb-696b-44a7-901e-ab15157c83c5\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>Model</th>\n",
              "      <th>Dataset</th>\n",
              "      <th>Accuracy</th>\n",
              "      <th>Error Rate</th>\n",
              "      <th>Loss</th>\n",
              "      <th>Avg AUC</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>DenseNet201</td>\n",
              "      <td>Main Dataset</td>\n",
              "      <td>93.23</td>\n",
              "      <td>6.77</td>\n",
              "      <td>0.1898</td>\n",
              "      <td>0.9916</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>DenseNet201</td>\n",
              "      <td>External Dataset</td>\n",
              "      <td>88.26</td>\n",
              "      <td>11.74</td>\n",
              "      <td>0.3680</td>\n",
              "      <td>0.9742</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>ResNet152</td>\n",
              "      <td>Main Dataset</td>\n",
              "      <td>86.37</td>\n",
              "      <td>13.63</td>\n",
              "      <td>0.3492</td>\n",
              "      <td>0.9665</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>ResNet152</td>\n",
              "      <td>External Dataset</td>\n",
              "      <td>84.58</td>\n",
              "      <td>15.42</td>\n",
              "      <td>0.4092</td>\n",
              "      <td>0.9573</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-f3411beb-696b-44a7-901e-ab15157c83c5')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-f3411beb-696b-44a7-901e-ab15157c83c5 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-f3411beb-696b-44a7-901e-ab15157c83c5');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "    <div id=\"df-27bf6f2c-08a7-4187-a17e-074a8c1d2f67\">\n",
              "      <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-27bf6f2c-08a7-4187-a17e-074a8c1d2f67')\"\n",
              "                title=\"Suggest charts\"\n",
              "                style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "      </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "      <script>\n",
              "        async function quickchart(key) {\n",
              "          const quickchartButtonEl =\n",
              "            document.querySelector('#' + key + ' button');\n",
              "          quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "          quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "          try {\n",
              "            const charts = await google.colab.kernel.invokeFunction(\n",
              "                'suggestCharts', [key], {});\n",
              "          } catch (error) {\n",
              "            console.error('Error during call to suggestCharts:', error);\n",
              "          }\n",
              "          quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "          quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "        }\n",
              "        (() => {\n",
              "          let quickchartButtonEl =\n",
              "            document.querySelector('#df-27bf6f2c-08a7-4187-a17e-074a8c1d2f67 button');\n",
              "          quickchartButtonEl.style.display =\n",
              "            google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "        })();\n",
              "      </script>\n",
              "    </div>\n",
              "\n",
              "  <div id=\"id_d9b7fc13-380b-41b9-9d33-0da74e70f1d4\">\n",
              "    <style>\n",
              "      .colab-df-generate {\n",
              "        background-color: #E8F0FE;\n",
              "        border: none;\n",
              "        border-radius: 50%;\n",
              "        cursor: pointer;\n",
              "        display: none;\n",
              "        fill: #1967D2;\n",
              "        height: 32px;\n",
              "        padding: 0 0 0 0;\n",
              "        width: 32px;\n",
              "      }\n",
              "\n",
              "      .colab-df-generate:hover {\n",
              "        background-color: #E2EBFA;\n",
              "        box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "        fill: #174EA6;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate {\n",
              "        background-color: #3B4455;\n",
              "        fill: #D2E3FC;\n",
              "      }\n",
              "\n",
              "      [theme=dark] .colab-df-generate:hover {\n",
              "        background-color: #434B5C;\n",
              "        box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "        filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "        fill: #FFFFFF;\n",
              "      }\n",
              "    </style>\n",
              "    <button class=\"colab-df-generate\" onclick=\"generateWithVariable('summary_df')\"\n",
              "            title=\"Generate code using this dataframe.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "       width=\"24px\">\n",
              "    <path d=\"M7,19H8.4L18.45,9,17,7.55,7,17.6ZM5,21V16.75L18.45,3.32a2,2,0,0,1,2.83,0l1.4,1.43a1.91,1.91,0,0,1,.58,1.4,1.91,1.91,0,0,1-.58,1.4L9.25,21ZM18.45,9,17,7.55Zm-12,3A5.31,5.31,0,0,0,4.9,8.1,5.31,5.31,0,0,0,1,6.5,5.31,5.31,0,0,0,4.9,4.9,5.31,5.31,0,0,0,6.5,1,5.31,5.31,0,0,0,8.1,4.9,5.31,5.31,0,0,0,12,6.5,5.46,5.46,0,0,0,6.5,12Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "    <script>\n",
              "      (() => {\n",
              "      const buttonEl =\n",
              "        document.querySelector('#id_d9b7fc13-380b-41b9-9d33-0da74e70f1d4 button.colab-df-generate');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      buttonEl.onclick = () => {\n",
              "        google.colab.notebook.generateWithVariable('summary_df');\n",
              "      }\n",
              "      })();\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "summary_df",
              "summary": "{\n  \"name\": \"summary_df\",\n  \"rows\": 4,\n  \"fields\": [\n    {\n      \"column\": \"Model\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"ResNet152\",\n          \"DenseNet201\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Dataset\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 2,\n        \"samples\": [\n          \"External Dataset\",\n          \"Main Dataset\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Accuracy\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.7294056720430238,\n        \"min\": 84.58,\n        \"max\": 93.23,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          88.26,\n          84.58\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Error Rate\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 3.7294056720430224,\n        \"min\": 6.77,\n        \"max\": 15.42,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          11.74,\n          15.42\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Loss\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.09615562039388718,\n        \"min\": 0.1898,\n        \"max\": 0.4092,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          0.368,\n          0.4092\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"Avg AUC\",\n      \"properties\": {\n        \"dtype\": \"number\",\n        \"std\": 0.014545331438872976,\n        \"min\": 0.9573,\n        \"max\": 0.9916,\n        \"num_unique_values\": 4,\n        \"samples\": [\n          0.9742,\n          0.9573\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "l81j1oU4D-zt"
      },
      "execution_count": null,
      "outputs": []
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": [],
      "machine_shape": "hm"
    },
    "kernelspec": {
      "display_name": "Python 3",
      "name": "python3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}