diff --git "a/visualization_tests.ipynb" "b/visualization_tests.ipynb"
new file mode 100644--- /dev/null
+++ "b/visualization_tests.ipynb"
@@ -0,0 +1,3751 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import subprocess\n",
+    "import os "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3f3f79f43e5948818777317f635745fc",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Fetching 21 files:   0%|          | 0/21 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'/home/afengler/proj_shark/huggingface/shark_detection/videos_example'"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from huggingface_hub import snapshot_download\n",
+    "import cv2 \n",
+    "import dotenv \n",
+    "dotenv.load_dotenv()\n",
+    "import numpy as np\n",
+    "import gradio as gr\n",
+    "import glob\n",
+    "from inference import inference_frame,inference_frame_serial\n",
+    "from inference import inference_frame_par_ready\n",
+    "from inference import process_frame\n",
+    "import os\n",
+    "import pathlib\n",
+    "import multiprocessing as mp\n",
+    "from time import time\n",
+    "\n",
+    "\n",
+    "REPO_ID='SharkSpace/videos_examples'\n",
+    "snapshot_download(repo_id=REPO_ID, token=os.environ.get('SHARK_MODEL'),repo_type='dataset',local_dir='videos_example')\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "torch version: 2.0.0+cu117 cuda: True\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "27969503c96c40cdb4f9da54814fe884",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Fetching 5 files:   0%|          | 0/5 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Loads checkpoint by local backend from path: model/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic/checkpoint_v2.pth\n",
+      "{'type': 'DetLocalVisualizer', 'vis_backends': [{'type': 'LocalVisBackend'}], 'name': 'visualizer'}\n",
+      "['__class__', '__delattr__', '__dict__', '__dir__', '__doc__', '__eq__', '__format__', '__ge__', '__getattribute__', '__gt__', '__hash__', '__init__', '__init_subclass__', '__le__', '__lt__', '__module__', '__ne__', '__new__', '__reduce__', '__reduce_ex__', '__repr__', '__setattr__', '__sizeof__', '__str__', '__subclasshook__', '__weakref__', '_dataset_meta', '_draw_instances', '_draw_panoptic_seg', '_init_manager', '_initialize_fig', '_instance_dict', '_instance_name', '_is_posion_valid', '_vis_backends', 'add_config', 'add_datasample', 'add_graph', 'add_image', 'add_scalar', 'add_scalars', 'alpha', 'ax_save', 'bbox_color', 'check_instance_created', 'close', 'dataset_meta', 'dpi', 'draw_bboxes', 'draw_binary_masks', 'draw_circles', 'draw_featmap', 'draw_lines', 'draw_points', 'draw_polygons', 'draw_texts', 'fig_save', 'fig_save_canvas', 'fig_save_cfg', 'fig_show_cfg', 'get_backend', 'get_current_instance', 'get_image', 'get_instance', 'instance_name', 'line_width', 'mask_color', 'set_image', 'show', 'text_color']\n",
+      "156\n",
+      "156\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/afengler/miniconda3/envs/openmmlab2/lib/python3.8/site-packages/mmengine/utils/manager.py:113: UserWarning: <class 'mmdet.visualization.local_visualizer.DetLocalVisualizer'> instance named of visualizer has been created, the method `get_instance` should not accept any other arguments\n",
+      "  warnings.warn(\n"
+     ]
+    }
+   ],
+   "source": [
+    "import torch, torchvision\n",
+    "print(\"torch version:\",torch.__version__, \"cuda:\",torch.cuda.is_available())\n",
+    "\n",
+    "# Check MMDetection installation\n",
+    "import mmdet\n",
+    "import os\n",
+    "import mmcv\n",
+    "import mmengine\n",
+    "from mmdet.apis import init_detector, inference_detector\n",
+    "from mmdet.utils import register_all_modules\n",
+    "from mmdet.registry import VISUALIZERS\n",
+    "\n",
+    "from huggingface_hub import hf_hub_download\n",
+    "from huggingface_hub import snapshot_download\n",
+    "from time import time\n",
+    "\n",
+    "classes= ['Beach',\n",
+    " 'Sea',\n",
+    " 'Wave',\n",
+    " 'Rock',\n",
+    " 'Breaking wave',\n",
+    " 'Reflection of the sea',\n",
+    " 'Foam',\n",
+    " 'Algae',\n",
+    " 'Vegetation',\n",
+    " 'Watermark',\n",
+    " 'Bird',\n",
+    " 'Ship',\n",
+    " 'Boat',\n",
+    " 'Car',\n",
+    " 'Kayak',\n",
+    " \"Shark's line\",\n",
+    " 'Dock',\n",
+    " 'Dog',\n",
+    " 'Unidentifiable shade',\n",
+    " 'Bird shadow',\n",
+    " 'Boat shadow',\n",
+    " 'Kayal shade',\n",
+    " 'Surfer shadow',\n",
+    " 'Shark shadow',\n",
+    " 'Surfboard shadow',\n",
+    " 'Crocodile',\n",
+    " 'Sea cow',\n",
+    " 'Stingray',\n",
+    " 'Person',\n",
+    " 'Ocean',\n",
+    " 'Surfer',\n",
+    " 'Surfer',\n",
+    " 'Fish',\n",
+    " 'Killer whale',\n",
+    " 'Whale',\n",
+    " 'Dolphin',\n",
+    " 'Miscellaneous',\n",
+    " 'Unidentifiable shark',\n",
+    " 'Carpet shark',\n",
+    " 'Dusty shark',\n",
+    " 'Blue shark',\n",
+    " 'Great white shark',\n",
+    " 'Copper shark',\n",
+    " 'Nurse shark',\n",
+    " 'Silky shark',\n",
+    " 'Leopard shark',\n",
+    " 'Shortfin mako shark',\n",
+    " 'Hammerhead shark',\n",
+    " 'Oceanic whitetip shark',\n",
+    " 'Blacktip shark',\n",
+    " 'Tiger shark',\n",
+    " 'Bull shark']*3\n",
+    "\n",
+    "class_sizes = {'Beach': None,\n",
+    "               'Sea': None,\n",
+    "               'Wave': None,\n",
+    "               'Rock': None,\n",
+    "               'Breaking wave': None,\n",
+    "               'Reflection of the sea': None,\n",
+    "               'Foam': None,\n",
+    "               'Algae': None,\n",
+    "               'Vegetation': None,\n",
+    "               'Watermark': None,\n",
+    "               'Bird': {'feet':[1, 3], 'meter': [0.3, 0.9], 'kg': [0.5, 1.5], 'pounds': [1, 3]},\n",
+    "               'Ship': {'feet':[10, 100], 'meter': [3, 30], 'kg': [1000, 100000], 'pounds': [2200, 220000]},\n",
+    "               'Boat': {'feet':[10, 45], 'meter': [3, 15], 'kg': [750, 80000], 'pounds': [1500, 160000]},\n",
+    "               'Car': {'feet':[10, 20], 'meter': [3, 6], 'kg': [1000, 2000], 'pounds': [2200, 4400]},\n",
+    "               'Kayak': {'feet':[10, 20], 'meter': [3, 6], 'kg': [50, 300], 'pounds': [100, 600]},\n",
+    "               \"Shark's line\": None,\n",
+    "               'Dock': None,\n",
+    "               'Dog': {'feet':[1, 3], 'meter': [0.3, 0.9], 'kg': [10, 50], 'pounds': [20, 100]},\n",
+    "               'Unidentifiable shade': None,\n",
+    "               'Bird shadow': None,\n",
+    "               'Boat shadow': None,\n",
+    "               'Kayal shade': None,\n",
+    "               'Surfer shadow': None,\n",
+    "               'Shark shadow': None,\n",
+    "               'Surfboard shadow': None,\n",
+    "               'Crocodile': {'feet':[10, 20], 'meter': [3, 6], 'kg': [410, 1000], 'pounds': [900, 2200]},\n",
+    "               'Sea cow':  {'feet':[9,12], 'meter': [3, 4], 'kg': [400, 590], 'pounds': [900, 1300]},\n",
+    "               'Stingray': {'feet':[2, 7.5], 'meter': [0.6, 2.5], 'kg': [100, 300], 'pounds': [220, 770]},\n",
+    "               'Person': {'feet':[5, 7], 'meter': [1.5, 2.1], 'kg': [50, 150], 'pounds': [110, 300]},\n",
+    "               'Ocean': None,\n",
+    "               'Surfer': {'feet':[5, 7], 'meter': [1.5, 2.1], 'kg': [50, 150], 'pounds': [110, 300]},\n",
+    "               'Surfer': {'feet':[5, 7], 'meter': [1.5, 2.1], 'kg': [50, 150], 'pounds': [110, 300]},\n",
+    "               'Fish':  {'feet':[1, 3], 'meter': [0.3, 0.9], 'kg': [20, 150], 'pounds': [40, 300]},\n",
+    "               'Killer whale': {'feet':[10, 20], 'meter': [3, 6], 'kg': [3600, 5400], 'pounds': [8000, 12000]},\n",
+    "               'Whale': {'feet':[15, 30], 'meter': [4.5, 10], 'kg': [2500, 80000], 'pounds': [55000, 176000]},\n",
+    "               'Dolphin': {'feet':[6.6, 13.1], 'meter': [2, 4], 'kg': [150, 650], 'pounds': [330, 1430]},\n",
+    "               'Miscellaneous': None,\n",
+    "               'Unidentifiable shark': {'feet': [2, 15], 'meter': [0.6, 4.5], 'kg': [50, 1000], 'pounds': [110, 2200]},\n",
+    "               'Carpet shark': {'feet': [4, 10], 'meter': [1.25, 3], 'kg': [50, 1000], 'pounds': [110, 2200]}, # Prob incorrect\n",
+    "               'Dusty shark': {'feet': [9, 14], 'meter': [3, 4.25], 'kg': [160, 180], 'pounds': [350, 400]},\n",
+    "               'Blue shark': {'feet': [7.9, 12.5], 'meter': [2.4, 3], 'kg': [60, 120], 'pounds': [130, 260]}, \n",
+    "               'Great white shark': {'feet': [13.1, 20], 'meter': [4, 6], 'kg': [680, 1800], 'pounds': [1500, 4000]},\n",
+    "               'Copper shark': {'feet': [7.2, 10.8], 'meter': [2.2, 3.3], 'kg': [130, 300], 'pounds': [290, 660]},\n",
+    "               'Nurse shark': {'feet': [7.9, 9.8], 'meter': [2.4, 3], 'kg': [90, 115], 'pounds': [200, 250]},\n",
+    "               'Silky shark': {'feet': [6.6, 8.2], 'meter': [2, 2.5], 'kg': [300, 380], 'pounds': [660, 840]},\n",
+    "               'Leopard shark': {'feet': [3.9, 4.9], 'meter': [1.2, 1.5], 'kg': [11, 20], 'pounds': [22, 44]},\n",
+    "               'Shortfin mako shark': {'feet': [10.5, 12], 'meter': [3.2, 3.6], 'kg': [60, 135], 'pounds': [130, 300]},\n",
+    "               'Hammerhead shark': {'feet': [4.9, 20], 'meter': [1.5, 6.1], 'kg': [230, 450], 'pounds': [500, 1000]},\n",
+    "               'Oceanic whitetip shark': {'feet': [5.9, 9.8], 'meter': [1.8, 3], 'kg': [36, 170], 'pounds': [80, 375]},\n",
+    "               'Blacktip shark': {'feet': [4.9, 6.6], 'meter': [1.5, 2], 'kg': [40, 100], 'pounds': [90, 220]},\n",
+    "               'Tiger shark': {'feet': [9.8, 18], 'meter': [3, 5.5], 'kg': [385, 635], 'pounds': [850, 1400]},\n",
+    "               'Bull shark': {'feet': [7.9, 11.2], 'meter': [2.4, 3.4], 'kg': [200, 315], 'pounds': [440, 690]},\n",
+    "}\n",
+    "\n",
+    "class_sizes_lower = {k.lower(): v for k, v in class_sizes.items()}\n",
+    "   \n",
+    "classes_is_shark = [1 if 'shark' in x.lower() else 0 for x in classes]\n",
+    "classes_is_human = [1 if 'person' or 'surfer' in x.lower() else 0 for x in classes]\n",
+    "classes_is_unknown = [1 if 'unidentifiable' in x.lower() else 0 for x in classes]\n",
+    "\n",
+    "classes_is_shark_id = [i for i, x in enumerate(classes_is_shark) if x == 1]\n",
+    "classes_is_human_id = [i for i, x in enumerate(classes_is_human) if x == 1]\n",
+    "classes_is_unknown_id = [i for i, x in enumerate(classes_is_unknown) if x == 1]\n",
+    "\n",
+    "\n",
+    "REPO_ID = \"SharkSpace/maskformer_model\"\n",
+    "FILENAME = \"mask2former\"\n",
+    "\n",
+    "snapshot_download(repo_id=REPO_ID, token= os.environ.get('SHARK_MODEL'),local_dir='model/')\n",
+    "\n",
+    "# Choose to use a config and initialize the detector\n",
+    "config_file ='model/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic.py'\n",
+    "#'/content/mmdetection/configs/panoptic_fpn/panoptic-fpn_r50_fpn_ms-3x_coco.py'\n",
+    "# Setup a checkpoint file to load\n",
+    "checkpoint_file ='model/mask2former_swin-t-p4-w7-224_8xb2-lsj-50e_coco-panoptic/checkpoint_v2.pth'\n",
+    "# '/content/drive/MyDrive/Algorithms/weights/shark_panoptic_weights_16_4_23/panoptic-fpn_r50_fpn_ms-3x_coco/epoch_36.pth'\n",
+    "\n",
+    "# register all modules in mmdet into the registries\n",
+    "register_all_modules()\n",
+    "\n",
+    "# build the model from a config file and a checkpoint file\n",
+    "model = init_detector(config_file, checkpoint_file, device='cuda:0')  # or device='cuda:0'\n",
+    "model.dataset_meta['palette'] = model.dataset_meta['palette'] + model.dataset_meta['palette'][-23:]\n",
+    "model.dataset_meta['classes'] = classes\n",
+    "print(model.cfg.visualizer)\n",
+    "# init visualizer(run the block only once in jupyter notebook)\n",
+    "visualizer = VISUALIZERS.build(model.cfg.visualizer)\n",
+    "print(dir(visualizer))\n",
+    "# the dataset_meta is loaded from the checkpoint and\n",
+    "# then pass to the model in init_detector\n",
+    "visualizer.dataset_meta = model.dataset_meta\n",
+    "classes = visualizer.dataset_meta.get('classes', None)\n",
+    "palette = visualizer.dataset_meta.get('palette', None)\n",
+    "\n",
+    "print(len(classes))\n",
+    "print(len(palette))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'beach': None,\n",
+       " 'sea': None,\n",
+       " 'wave': None,\n",
+       " 'rock': None,\n",
+       " 'breaking wave': None,\n",
+       " 'reflection of the sea': None,\n",
+       " 'foam': None,\n",
+       " 'algae': None,\n",
+       " 'vegetation': None,\n",
+       " 'watermark': None,\n",
+       " 'bird': {'feet': [1, 3],\n",
+       "  'meter': [0.3, 0.9],\n",
+       "  'kg': [0.5, 1.5],\n",
+       "  'pounds': [1, 3]},\n",
+       " 'ship': {'feet': [10, 100],\n",
+       "  'meter': [3, 30],\n",
+       "  'kg': [1000, 100000],\n",
+       "  'pounds': [2200, 220000]},\n",
+       " 'boat': {'feet': [10, 45],\n",
+       "  'meter': [3, 15],\n",
+       "  'kg': [750, 80000],\n",
+       "  'pounds': [1500, 160000]},\n",
+       " 'car': {'feet': [10, 20],\n",
+       "  'meter': [3, 6],\n",
+       "  'kg': [1000, 2000],\n",
+       "  'pounds': [2200, 4400]},\n",
+       " 'kayak': {'feet': [10, 20],\n",
+       "  'meter': [3, 6],\n",
+       "  'kg': [50, 300],\n",
+       "  'pounds': [100, 600]},\n",
+       " \"shark's line\": None,\n",
+       " 'dock': None,\n",
+       " 'dog': {'feet': [1, 3],\n",
+       "  'meter': [0.3, 0.9],\n",
+       "  'kg': [10, 50],\n",
+       "  'pounds': [20, 100]},\n",
+       " 'unidentifiable shade': None,\n",
+       " 'bird shadow': None,\n",
+       " 'boat shadow': None,\n",
+       " 'kayal shade': None,\n",
+       " 'surfer shadow': None,\n",
+       " 'shark shadow': None,\n",
+       " 'surfboard shadow': None,\n",
+       " 'crocodile': {'feet': [10, 20],\n",
+       "  'meter': [3, 6],\n",
+       "  'kg': [410, 1000],\n",
+       "  'pounds': [900, 2200]},\n",
+       " 'sea cow': {'feet': [9, 12],\n",
+       "  'meter': [3, 4],\n",
+       "  'kg': [400, 590],\n",
+       "  'pounds': [900, 1300]},\n",
+       " 'stingray': {'feet': [2, 7.5],\n",
+       "  'meter': [0.6, 2.5],\n",
+       "  'kg': [100, 300],\n",
+       "  'pounds': [220, 770]},\n",
+       " 'person': {'feet': [5, 7],\n",
+       "  'meter': [1.5, 2.1],\n",
+       "  'kg': [50, 150],\n",
+       "  'pounds': [110, 300]},\n",
+       " 'ocean': None,\n",
+       " 'surfer': {'feet': [5, 7],\n",
+       "  'meter': [1.5, 2.1],\n",
+       "  'kg': [50, 150],\n",
+       "  'pounds': [110, 300]},\n",
+       " 'fish': {'feet': [1, 3],\n",
+       "  'meter': [0.3, 0.9],\n",
+       "  'kg': [20, 150],\n",
+       "  'pounds': [40, 300]},\n",
+       " 'killer whale': {'feet': [10, 20],\n",
+       "  'meter': [3, 6],\n",
+       "  'kg': [3600, 5400],\n",
+       "  'pounds': [8000, 12000]},\n",
+       " 'whale': {'feet': [15, 30],\n",
+       "  'meter': [4.5, 10],\n",
+       "  'kg': [2500, 80000],\n",
+       "  'pounds': [55000, 176000]},\n",
+       " 'dolphin': {'feet': [6.6, 13.1],\n",
+       "  'meter': [2, 4],\n",
+       "  'kg': [150, 650],\n",
+       "  'pounds': [330, 1430]},\n",
+       " 'miscellaneous': None,\n",
+       " 'unidentifiable shark': {'feet': [2, 15],\n",
+       "  'meter': [0.6, 4.5],\n",
+       "  'kg': [50, 1000],\n",
+       "  'pounds': [110, 2200]},\n",
+       " 'carpet shark': {'feet': [4, 10],\n",
+       "  'meter': [1.25, 3],\n",
+       "  'kg': [50, 1000],\n",
+       "  'pounds': [110, 2200]},\n",
+       " 'dusty shark': {'feet': [9, 14],\n",
+       "  'meter': [3, 4.25],\n",
+       "  'kg': [160, 180],\n",
+       "  'pounds': [350, 400]},\n",
+       " 'blue shark': {'feet': [7.9, 12.5],\n",
+       "  'meter': [2.4, 3],\n",
+       "  'kg': [60, 120],\n",
+       "  'pounds': [130, 260]},\n",
+       " 'great white shark': {'feet': [13.1, 20],\n",
+       "  'meter': [4, 6],\n",
+       "  'kg': [680, 1800],\n",
+       "  'pounds': [1500, 4000]},\n",
+       " 'copper shark': {'feet': [7.2, 10.8],\n",
+       "  'meter': [2.2, 3.3],\n",
+       "  'kg': [130, 300],\n",
+       "  'pounds': [290, 660]},\n",
+       " 'nurse shark': {'feet': [7.9, 9.8],\n",
+       "  'meter': [2.4, 3],\n",
+       "  'kg': [90, 115],\n",
+       "  'pounds': [200, 250]},\n",
+       " 'silky shark': {'feet': [6.6, 8.2],\n",
+       "  'meter': [2, 2.5],\n",
+       "  'kg': [300, 380],\n",
+       "  'pounds': [660, 840]},\n",
+       " 'leopard shark': {'feet': [3.9, 4.9],\n",
+       "  'meter': [1.2, 1.5],\n",
+       "  'kg': [11, 20],\n",
+       "  'pounds': [22, 44]},\n",
+       " 'shortfin mako shark': {'feet': [10.5, 12],\n",
+       "  'meter': [3.2, 3.6],\n",
+       "  'kg': [60, 135],\n",
+       "  'pounds': [130, 300]},\n",
+       " 'hammerhead shark': {'feet': [4.9, 20],\n",
+       "  'meter': [1.5, 6.1],\n",
+       "  'kg': [230, 450],\n",
+       "  'pounds': [500, 1000]},\n",
+       " 'oceanic whitetip shark': {'feet': [5.9, 9.8],\n",
+       "  'meter': [1.8, 3],\n",
+       "  'kg': [36, 170],\n",
+       "  'pounds': [80, 375]},\n",
+       " 'blacktip shark': {'feet': [4.9, 6.6],\n",
+       "  'meter': [1.5, 2],\n",
+       "  'kg': [40, 100],\n",
+       "  'pounds': [90, 220]},\n",
+       " 'tiger shark': {'feet': [9.8, 18],\n",
+       "  'meter': [3, 5.5],\n",
+       "  'kg': [385, 635],\n",
+       "  'pounds': [850, 1400]},\n",
+       " 'bull shark': {'feet': [7.9, 11.2],\n",
+       "  'meter': [2.4, 3.4],\n",
+       "  'kg': [200, 315],\n",
+       "  'pounds': [440, 690]}}"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "class_sizes_lower"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "skip_frames = 7\n",
+    "out_fps = 'auto'\n",
+    "input_video = 'videos_example/421.mp4'\n",
+    "\n",
+    "cap = cv2.VideoCapture(input_video)\n",
+    "\n",
+    "output_path = \"notebook_out_vid.mp4\"\n",
+    "if out_fps != 'auto' and type(out_fps) == int:\n",
+    "    fps = int(out_fps)\n",
+    "else:\n",
+    "    fps = int(cap.get(cv2.CAP_PROP_FPS))\n",
+    "    if out_fps == 'auto':\n",
+    "        fps = int(fps / skip_frames)\n",
+    "\n",
+    "width  = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))\n",
+    "height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))\n",
+    "\n",
+    "video = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*\"mp4v\"), fps, (width, height))\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "iterating, frame = cap.read()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "True"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "iterating"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7f92acf764f0>"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.imshow(frame)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "display_frame = inference_frame_serial(frames[30])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "(array([[[239, 237, 231],\n",
+       "         [222, 221, 208],\n",
+       "         [191, 191, 168],\n",
+       "         ...,\n",
+       "         [186, 185, 162],\n",
+       "         [216, 216, 203],\n",
+       "         [236, 235, 229]],\n",
+       " \n",
+       "        [[239, 237, 231],\n",
+       "         [195, 194, 171],\n",
+       "         [164, 164, 130],\n",
+       "         ...,\n",
+       "         [156, 155, 122],\n",
+       "         [186, 185, 161],\n",
+       "         [236, 235, 229]],\n",
+       " \n",
+       "        [[239, 237, 231],\n",
+       "         [195, 194, 171],\n",
+       "         [164, 164, 130],\n",
+       "         ...,\n",
+       "         [156, 155, 122],\n",
+       "         [186, 185, 161],\n",
+       "         [236, 235, 229]],\n",
+       " \n",
+       "        ...,\n",
+       " \n",
+       "        [[238, 237, 231],\n",
+       "         [223, 222, 210],\n",
+       "         [193, 191, 168],\n",
+       "         ...,\n",
+       "         [192, 189, 167],\n",
+       "         [220, 218, 206],\n",
+       "         [237, 236, 230]],\n",
+       " \n",
+       "        [[238, 237, 231],\n",
+       "         [238, 237, 231],\n",
+       "         [238, 237, 231],\n",
+       "         ...,\n",
+       "         [238, 237, 231],\n",
+       "         [238, 237, 231],\n",
+       "         [238, 237, 231]],\n",
+       " \n",
+       "        [[238, 237, 231],\n",
+       "         [238, 237, 231],\n",
+       "         [238, 237, 231],\n",
+       "         ...,\n",
+       "         [238, 237, 231],\n",
+       "         [238, 237, 231],\n",
+       "         [238, 237, 231]]], dtype=uint8),\n",
+       " <DetDataSample(\n",
+       " \n",
+       "     META INFORMATION\n",
+       "     ori_shape: (854, 480)\n",
+       "     img_path: None\n",
+       "     img_shape: (1333, 749)\n",
+       "     img_id: 0\n",
+       "     scale_factor: (1.5604166666666666, 1.5608899297423888)\n",
+       "     pad_shape: (1344, 768)\n",
+       "     batch_input_shape: (1344, 768)\n",
+       " \n",
+       "     DATA FIELDS\n",
+       "     pred_panoptic_seg: <PixelData(\n",
+       "         \n",
+       "             META INFORMATION\n",
+       "         \n",
+       "             DATA FIELDS\n",
+       "             sem_seg: tensor([[[133, 133, 133,  ..., 133, 133, 133],\n",
+       "                          [133, 133, 133,  ..., 133, 133, 133],\n",
+       "                          [133, 133, 133,  ..., 133, 133, 133],\n",
+       "                          ...,\n",
+       "                          [133, 133, 133,  ..., 133, 133, 133],\n",
+       "                          [133, 133, 133,  ..., 133, 133, 133],\n",
+       "                          [133, 133, 133,  ..., 133, 133, 133]]], device='cuda:0',\n",
+       "                        dtype=torch.int32)\n",
+       "         ) at 0x7f272a0fdac0>\n",
+       "     gt_instances: <InstanceData(\n",
+       "         \n",
+       "             META INFORMATION\n",
+       "         \n",
+       "             DATA FIELDS\n",
+       "             labels: tensor([], device='cuda:0', dtype=torch.int64)\n",
+       "             bboxes: tensor([], device='cuda:0', size=(0, 4))\n",
+       "         ) at 0x7f2734870fa0>\n",
+       "     pred_instances: <InstanceData(\n",
+       "         \n",
+       "             META INFORMATION\n",
+       "         \n",
+       "             DATA FIELDS\n",
+       "             labels: tensor([29, 31, 19, 29, 31, 38, 42, 42,  4, 15, 17, 18, 19, 23, 24, 29, 30, 31,\n",
+       "                         32, 33, 36, 37, 38, 42, 45, 46, 51, 52, 42, 29, 42, 19, 42, 29, 31, 29,\n",
+       "                         31, 29, 31, 29, 31, 29, 31, 37, 38, 29, 31, 29, 29, 29, 31, 31, 38, 42,\n",
+       "                         29, 42, 19, 29, 31, 38, 42, 19, 29, 31, 29, 31, 29, 31, 29, 29, 19, 29,\n",
+       "                         31, 38, 42, 29, 31, 29, 31, 29, 31, 37, 38, 42, 19, 29, 31, 38, 42, 31,\n",
+       "                         19, 29, 31, 29, 31, 29, 31, 29, 31, 31], device='cuda:0')\n",
+       "             scores: tensor([0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 9.8792e-01, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 3.5669e-05, 1.4771e-05, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 1.3098e-05, 1.8196e-05, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 1.2361e-05, 1.5065e-05, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         1.2603e-05, 1.3650e-05, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 1.5639e-05, 2.1127e-05, 1.4168e-05, 1.1925e-05,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 1.4417e-05, 1.7143e-05,\n",
+       "                         1.6082e-05, 1.2884e-05, 2.0254e-05, 1.4664e-05, 1.4642e-05, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 0.0000e+00, 1.1612e-05,\n",
+       "                         9.3502e-06, 1.4317e-05, 1.4583e-05, 0.0000e+00, 0.0000e+00, 0.0000e+00,\n",
+       "                         0.0000e+00, 1.5519e-05, 1.4283e-05, 1.2031e-05], device='cuda:0')\n",
+       "             masks: tensor([[[False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          ...,\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False]],\n",
+       "                 \n",
+       "                         [[False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          ...,\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False]],\n",
+       "                 \n",
+       "                         [[False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          ...,\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False]],\n",
+       "                 \n",
+       "                         ...,\n",
+       "                 \n",
+       "                         [[False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          ...,\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False]],\n",
+       "                 \n",
+       "                         [[False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          ...,\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False]],\n",
+       "                 \n",
+       "                         [[False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          ...,\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False],\n",
+       "                          [False, False, False,  ..., False, False, False]]], device='cuda:0')\n",
+       "             bboxes: tensor([[  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [110.,   0., 177.,  78.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 443.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 439.,   1., 443.],\n",
+       "                         [  0., 439.,   1., 443.],\n",
+       "                         [  0., 439.,   1., 443.],\n",
+       "                         [  0., 439.,   1., 443.],\n",
+       "                         [  0., 439.,   1., 443.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0., 440.,   1., 443.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0.,   0.,   0.,   0.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 439.,   2., 450.],\n",
+       "                         [  0., 440.,   1., 443.]], device='cuda:0')\n",
+       "         ) at 0x7f27348c53a0>\n",
+       "     ignored_instances: <InstanceData(\n",
+       "         \n",
+       "             META INFORMATION\n",
+       "         \n",
+       "             DATA FIELDS\n",
+       "             labels: tensor([], device='cuda:0', dtype=torch.int64)\n",
+       "             bboxes: tensor([], device='cuda:0', size=(0, 4))\n",
+       "         ) at 0x7f272a0e95b0>\n",
+       " ) at 0x7f2734870df0>)"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "display_frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7f2723a9ac40>"
+      ]
+     },
+     "execution_count": 53,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAQcAAAGiCAYAAADqegP6AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOz9e7RlR3UfjP5mrb3P6Xc33VJ3S+iBeAqZh4wwUttOPgcUFKxgO8j3s/0xsJLBiG80JEaMEsfRuATbOCNySEZwnABOcj3A+WIuDvf6EXCMAdnBcRAvERwZDAEikITo1rP79POcvVfV/aPms9bap8/BTsixu6TT5+y116pVr/mbvzmrahaVUgoupAvpQrqQmpS+1QW4kC6kC+l/z3QBHC6kC+lCGk0XwOFCupAupNF0ARwupAvpQhpNF8DhQrqQLqTRdAEcLqQL6UIaTRfA4UK6kC6k0XQBHC6kC+lCGk0XwOFCupAupNF0ARwupAvpQhpN31JwePvb345nPOMZ2LZtG66//np88pOf/FYW50K6kC4kl75l4PCrv/qruPPOO/FTP/VT+MxnPoMXv/jFuOmmm/Doo49+q4p0IV1IF5JL9K3aeHX99dfjO77jO/Av/+W/BADknHH55ZfjDW94A/7+3//734oiXUgX0oXk0uRb8dK1tTXcd999uOuuu/RaSgk33ngj7r333sH9q6urWF1d1c85Zzz55JM4cOAAiOh/SZkvpAvpz0oqpeDkyZO49NJLkdJi4+FbAg6PP/44+r7HoUOHwvVDhw7hC1/4wuD+u+++Gz/zMz/zv6p4F9KF9OciPfTQQ7jssssWfv8tAYfNprvuugt33nmnfj5x4gSuuOIK/PN/fie2b18GQCCiwCJyzkDJ8DYTAQAJUhagFORSkRRiXRHp34WfGeYxzlbk/YkW3WO5lVJQctG8CQAl0vwH1l6x8kjWpdR6yr0bYVF9P0fOBaVkzVPK4+tWON/C+SaiWKdSBs+mrkNKCSkldF2n5SGudi6u7vq8XLN+aPuylILc51pmTvO+BwAkIhAlgICSC0DApOvQdZPanimhFp249bg8Uk/XzvJer01LKbWNuc3msznm8x459zyECoCCUvgdrttKycilYGk6BaWE2doacslIlNB1E5RS0Pe9u9a5usvvMhwL3F61CoSce+Sctc0KtyFQ2zhxnaReVz7z2/F93/ej2L179yBfn74l4HDRRReh6zocO3YsXD927BgOHz48uH95eRnLy8uD69u2LWPbtmUQEbrJBNIcdSCVYceDUP+vDd/nHrnvxxtfnhv7vA44VCFPNridEMnzBU5ARLDlOc4/lMnlIe8AqrBVEDRgq4PLCtzWrZQlBpRcH1NBrdBD/O7c95C3EtWBlYhC2UPdwQOwM3CQihEIOWdkBqTanm25BDAzCygLCExAM4NHKUWBRgWaEtepoOu6Oh64H9ofKFgwCLp89J5S26OUjJzrmOpzjy4RppMugLLUqCKUgZ2Ahghll5YAkIJAKRl9n5FzRkoJk8lkQPPlPUPAtPyBiQOEOjy7boKCgn4+B4AADjt37NC2Wy99S2YrlpaWcN111+Gee+7Razln3HPPPThy5MjGMyITtL6fVxQeAwb3h4jWYHA2PyOvsvs80xjcuLjBF3GJsef8pzoOVNq1jFUBskZ3oLFIAMH3d11CSh2SaNaUQNQIEl9LTvOm1AVwkuwFdEXoJl2HyWRSf7pJGNgFZRQYXGagZFpe38DspfiHHFgUFC23tKXPpRUu1yB6n/ZxqUKXBRhyBYa+75lBlJHuJytLKQoqAD/f9+PPhHYQwBEGYGWxv2P+Y8wxpQ5dl9ClhMl0akDN323UTfctMyvuvPNO3HrrrXjpS1+Kl73sZfj5n/95nD59Gn/jb/yNDecRtLozBQy9nUYVTUB8LTeUEuOgsJlyLPy+oeMQCg+gBGFTruhujyZOAAEidERKsfUZQ4eFJU4JyDkBqGUpFKlqIoKReC5zIlAmKzNZ/RIlUCJ0DDa5ZLiSKjWHe85VQwFCaX1xdXCgToArl2ufUhjISH8raFIYKcqY9HrbP8JBWfhq2bMBc3EqxN+voOHBwwDXC3cLVAUFORdQKiAtZ3b3xjytPpHxhWqgspy+79ELI+sSEm2ME3zLwOGHfuiH8Nhjj+HNb34zjh49imuvvRYf/OAHB07K9ZMNP/1rhPKiFBRuYD9glcLzPQuF3Pkh/LVFJoY3FbwWA8DlgEoilTH9Psgw5JtYOxKqadEOs/NlqC0hQAmxcd3AJ+NYOQMZ0YRRE4pMIAUxxP4VH4GaIk3717tJtb7WIEdzS+8VVhNA1MG6Nwua+lqzsyYmps3ct07MLD82cwbjqdEkOWe0jS4gW9tH/vbfQZ8RM7BQBSR0Vlapd/xc8xM/h/SbAImYYfKOUkoFb/WJbIw6fEsdknfccQfuuOOOP9U8h06ZJhWh4nVg55z/RKxhkD0La+0DN5A9SKwDCAVgljPI2ByA/DkLEAp4qROqNakG8BG+FavA+En9PZlUM6LvM/r5HPP5XL9NzBCqL6IKQAWBjJKpAYE4yCm8lxQgfBvmwkyD65VE+8K0opg7pZiJpawBpNdAYjR4J+iwTQJQq7kShVRYkhfgUrzfyikfp/GJBEjdO9Wc0g4IPoaBX4fMsVh9GZmBwJiMAIP4F6St/Hfesbte2hKzFYuS1xKtd3twXexTskEFVOGlgYBhQPG9uaL26QLjLQw0IiRAvf2lHYDNc3JNbXtvZ7PzrO/7IaBt1JBcgEqijVj0Aaa5XRLYYEcv3y/C2qUOlLheMrAXvGgACt4XwcxCmQvnJ47HLD4HNRWH/R/yFEEOMw/QPhxtmgKFKZ2tcWad/kUGPJUlSdvFJi6QtiAWWG4FSjAQJ4CKgZ8DjAEDcnWq76Y6Fqj2WTUVcyiLlWiD48OlLQ0OrWfXD5SBP4FVm+kuHgYymBoNPwALwAaWv29BUgbg8hsVaAc4BkBM/Hn2olqhGTmlMGDbupvuilp7bFpUB7kb2AJGRBUY5vPqhEusLUuqQmOsuE7Fqf8mjEFaOB69ELeUWYsnZXF2epH+duBi5o9o6RKAVQHW913jxynupfKuXGSq2bWfgLkyiuoUDADv36PVaOuZFcxAbOOwykkpAmibRPsL6xXzQWZ3UnJ5wEweMf82k7Y0OCyq7CJKptpmcN0LVvgy5FF4YG24iZ0925ovMsgGzkr9Vq6zb4ASyE9burxiOzRC6Ua+aqXGJzIAiGIDuu97ZK4KATp7AZLpSXOGkgxu8T+onNg08rC8UnWZxyi+iBUg276Ela/to4EXSr833Q8nrL6hArNwbaVVEe1OYLODqb6YOwjV1neJ4I5NrwMJ4vuhtt+o6HPSRt65KrMgdVapPt91Se/1v6X+mxi9WxscxheHLKaNNmnF9zFYqPe9ZQqW6abLNhh6TltlN0hIy9UIfQmfgv0cTBM4YRtx4snQbgeLMSj/25di6GX318D1qKaGm4fPCUkGuwOElMgQpkCBQBmHvLzAvW+cXoMa1sC2fJ2WNdqddArPgULTl75dqnOXhFTBBLPyTDClz7y4Ts0caSdAZzXCO2pO3A5J+2xsFsP3qQfo1jkpC5+k7KWYw1MWubXrIxTvsLG0xcEhaqEhKvN1KOk0FgcGZjimQWNCsrFkbJritaZ8601nSZ0AVM918Sx4SIv9e4jq1KMAR6w9VCD1b4IO+Fbbyd+JCEVMmXaxUKiugZMIvFFm6FoKmdGQtShaJle2+rwt0iKzBcFojiRvLHKpamcvUKOAUorNFoU2b9YtOEpPbtqPQKAEzEtB35fQRpL61uzjtvOmaFvGlMxEiD6MWC4ZpwIWA1ZQDBj8iknXUZtKWxociMCe23E7PCSWNC843pRoBSRoX+nUBYPLg0ALCAvLErR/iQAQCGosWf1k1wIojWgsz6brq/m5wms+ipU3DjYTupKBnmXdv48ISNQ5IXc3UGwTyQsASiIgLs0IQBHBpjWy4K7Vf1NCEL5BXSmyK2lrI2dmzrRWmcw4+BJUfwfU75FggjvGAsSNxFbCKEPoui6OYULIx7OMWDb3DgVWY0MKQiO+kPOlLQ0OdSVYp7aXpDGYiNq0ES6iurIu27y8v9OLp97vM2+AYVHzF7BJIfkVp2Vhnu0CjE9nNuWKmY9Yk81gE6akOlpWPiWvZZpnWFrIUXd5f2Eh0fuEtSi7IAUJbwYkSsjIXjy5uG3LZzEs2DkrksvvavK1GhSQtmpRzCpisjRtoxC8UG5Mi5dS90IAAngp5CW+LTGPatkMhNtFW2ICyWdvKoSuaFhRzu1KYGMZNa8KOF55SrtsNG1pcAAa9ATL6VDh2v3Nc0EkRrQv34wEIK+zvVVL4fwWCkjnZRLsdW7pcEQ0J6hFcIyLbANuWKrCwEBmTrWGR7E/wjeMYgU2FWsmRW0r3S8heQsouEYReTaq7qQVEO+DCRTXSyblZG2BzshoG5P+h1C+2k6Fb63mZM03mwTV51WWqW6YE+Apw/YUul6U+ZlvpGRemwFeoxDqJ3+PTLH73mIGoe3o7vHLpOX3cH+H5QPEGRI1ZVNDJddJWxocxP4StCVg1DbwaCl+B9XwonWk4alxWpGOep79D1mbISCDuilCa9O3JFU0WS4F4F2FqiFKRip+Csq0RmwHo842gLh07oWqS0urP0wYiIzDyEx8qDDqtBiIUPrsaLqBV5tKQZ0WJBNQ0+Dux72HiNdQiNAnT4/JNXJreMR6MeI4tqb/QDiGVlGFydrE96YtImIgQwZydbbWTXBFgQyUTZkEc820vy1UsnfYbIP15xgYtM5MyU8YdPu9HzMbZQ9bHBzyAD0DZWwofuh8pXz23aIhpnmLoDfP2sIfDFmC81NEUmOfdJmxUEnmyD16+KkyvWcAQdFbPTqNKxUnB3ENkNiMhAwok9p6T0bJADoDStabDQCNtJ0boGOUWN4T2jExN/BsJFSsfl8KmiXVkU1FGY/aw97X4IbmYW3lWYNklUsGURcF07KstxGFfEcdphAwyLrblvTeNGANwjLkvd5EEaCQ3975PTb9uyhtaXDI2egSvABwksaVsQsscGBKw8lAcubFegRMlR03+Hmdoj5vle8yeIl6/HtCT33dgqwe7aIsYQgQQ2Bo3y1tMmgDD7ANMECfqWXLPHMx9qZSKkPwwuzHo77X48J4YZnyky0G88+RtfvoWPfNep5uMXOl/uOnUnPWyeDK7AZ52XLllJLO6mghwWYcWZ0WlkHMmZyRe1nclOA2VXLMD1FyNoMkPG8ymUCm6QEYqyZb9LdBq2Jrg4NpO5jAiZnt0dnJUXWsFZ3q8d7cwAzCawwoFmpl/3dru8ciBPCRegDQZciVCWcUEDp08Na1f1dpBLoprr5K3u/fRkSAaBWIq0oEwUpLVLf+gs2Zvu8DG4rtBIhlEdu/1sA7xsB1MsOFAF4GXL0Njo0MbDVA/QvS5w1ISI+1psFogRH7pwC2G1OHl5/dsPf7lFLS6WSRQ317KAKbOQXo2HFIqe5hqeBC+lwuBSRBiwQsBUhcuUu9GdRFBlnXQ4ijOLbO+dIWB4dhGrN7jTbXqDn1UxzEfus0gbcFN+yhFUbppAAwLg9lJC4PMyZqOQv3WgrvyTq4wX4VSFkhNvuw7usTF2sXHXqqCGVAOU2n10njK4hn3lN1v3YCwhhEcPmdwRfihF5AXPpHBz4S+tLMdXqbDI4eB+ebaFTfbxtUk4hlsSRsUkyY+l0iwmQy0e3QAJTK930PmbdMiWrcBWTpTve+yn7TUse+JPMdiG/J2CKpu0UVHdgXg2qCdJMJlzNVHsEsRoLkIFEEufOkLQ4OpFOZaos7gRwm5zwjExZvx/Ef6ICFUaLCvZKzy2PwhGcKRLxeAkCpzqxS3EIjR/d5EkxnMrrUOfhfv4uteCNUllkWcVmys0ntKXMc5lygS/4p1YEvefReGNu6VyAYLMiBB8ficWs0RWG3OglzGLcqNg4KsVxwQGPTofJl7a/60nk/x2w2g4CTrOMgIpCuW6g+nKQsKagPrZ/3F2hZwudiLLC5RyJLqcnM75AVnyIj8q6Npi0NDmG8+QaTzypkQpXhKEN81s82+E4prLXLiAABQ5AYuza07VnsG01ltNsPUrAdWtDDGITl6U2AReVQK7VhQTIrIoOWRUEYRamLavq+2CpAp7WEzsvlihl+y3ADZGNSzNZEWKVBLXsLnaX8RtkOtbXbeCrcFtpSxIFuKDtfRAn3gDW++F4I4mRthBto+knIjke0wvsjhmsYpDzSDOYHzWq2xO3ZxsqCE5JZXzvLdb60pcEBwMIKe2G3AehobUaNBCsxSorhegJGkXxR8sLvO9mzgIjYw0GswMDTmXAaAeTK7d4hf6/viHTMwVkAAZRQwYdsCZ+VOxeA6nJhH2SWaqHUFNC8pR7OKZbaHYGOsQk7attk+MlpWpWtOJcfar1OvwXW4lgJkdVnMulQSodSMubzHhU0LdhsiO2o5kyGj7yojkIjjfJPKPd8PtfNWb4N5Rl1VAYlYwCgP75eoQ3ke+jvjaQtDg4mhOPJXF/xc/2binjlh9OhfbOBZtFgaxlFCxQh3zzUQLXzG63J9qzsRWj9KIOpKURh92nMpLApOuZUOqCMBTSPQNou1BVmI8sABhkYeJo9mmTgwxZBbTS1/h9xqS5617C9xG/SmpT1H6tTwnRa+3E2m1eAcIudbNES+w+SBLpt+p8JngddD/Kz2VzfKeWToC7DSFPGmgLLdSaFAK8Sq4IQX3MjaUuDg1E0Z0IYy4brEQCD5q2N2feNXqopxC1YtwxDcFo02+G4i5ZByyx2Ky8w8pRwPS2ozqbRwdMUA+JHyHxP0XtlIFoOCOszvGbTsvH+DKIUaHnXWcDa8yZX9HGzgN9L1l4AWADlHUWFQYQ2+Hi8EJX6HmENoe/V1xAXDsnf6vmXscY7QLtOIjMVNgvENFjAamFTvQWVwBopI/VrDKabXTtI01rkqwgOAK/BgAvNr4pmYwCxpcFBklAl7Whnz5VCg0EnjZmDBpUvofacDCxgPdq+AYDwgxWAQwd9VgQ0qyavN1KskPMVhOIGzRenCLUlmsEmC6ckPxMKzYe5tlLRgVMjCiyA4GuIZViAVk0ywDRg8nWQiEkigEmnf3l9hfY3maKQpiHiiNIWIl8hmHjvBgNG3/c8S1QzMT9AXUtAROjnPWazGeZzcUgmDq3n6ldcHfxsjzoQCkrXNWtZyMwJyaBIe7uWEmWCON4SL5rKOQPJHtwMMABbHBy8BtBrzraqTSlbf8HCjqGwwo1ToecZtmRXvloHIEJeZTwGoC+3f6l3WmmwozAQhCpCB2gYJqLVuaLiDxhWUIAn0CsbfCEJJfXTnEL9x4R/HfPhPEl9FgGjo6Z3N3OZklWLf9ft+As2FxWEwLWlrb/LJzMw9L1sHbdISpPJBF3X6bL9ImNFtXcHCb6Sez9tXiNz92GPBA9FLpc5DcuwaCNtq76ttvN8V6mT0im5DZpvWxscittIA2vIStXIqHITnEMoc10R6Z+SvzY+yAcg4DSCu4kvRZrYfq63JRU9scmde8A9ZyyYSlXzJiB+sLY+BgglUK2p70c7buQZWniHgin5fNr2W9yefnCL1g8+lvaVBbYr0iMpm0vJmThtEVqn7nrJ+3DivVSFmYVYbXsU9LkH9YRJN+Fmk6lWBrkioMe+BQFdzj4rK3RrREAc26MF4lq+Os0d11j04agCLmOx6fONpi0ODiPan69JGHXH4OsA0dVilWJtKDT8eVILL20fbARqaES41LnkBnVDcQBnNq3nnwiD3V7q/nbwoVpHKuOEX7S85ay/1GuehmXQthmSNi271/oeYIZmEg2eHZg+HlyUUkNi55rfwJtjPEhSl0BsUvjmrDsve/RynCA/rztWuRHrSWqZ2YAWwJiGK6awM9sD4a5LmUtUQq1TWBzAYeamVD9RIl4QBeiW/Y0ixJYGB7QaMXxVNHYCINS16GAXgTOBHlm81KSWJVD80oLBeFOHzCYer0PMTDu+ISAGOEYTx2vushb7lo3fBSV3uTtmEQYSDW/XMsro9ZWxga3VaxhSaI4FYAFtCgvftqjCiWRmZ1i/RYDVMhIDiKQUX7S9AnUuYZUtSkGfizonSynI86zniUjEqPgOAZN6qfBKyM6FkOtSqt95R6vUjgxsJOl2AO1DBp0uuXbb+DQmsNXBQdPIqGkYQWHBTWRxDUAcpwDSCR4qLKlGUiPRNCnBmSjnZSIyIEbuaE0HNCaIVcspxXFQ1Po2sxi1rBgVxsh3vMCvK5NGyQBE5+WiBxanRUNXQVkEqylUJEsL8hCaznl5LS6Pee0qG6lUAB1YVqyXmYx6jUoXFqrJI57N8ryJAzGXvJ+quAVWAmwlMsk4c+PHSQnXc66mllp+RG2DLUx/RsAhpvZwknqxCnUhF9K+QHf8+U029fbxqL8KFDpISxCrKI5Whkb249fOLJBP6zqOVPuYVqNmVsZPay0cCgVuQVGsASmSxJkRf6cWR9omcHCoEJzXj9sWsDS/XT20DbVMZJbOInLGQDk2Pdz6i/TVvBtTnKJE9ewM4WDtOonquLQ+qYFobTRUNtBZebiBxJQRZ7O0l+y+BRHGlARnOnTIF2HETkmQLTb788UcmGK3qRVEcvcTLGZfQPYRx6GfedA8tKM52Oe65bN3jDKGpqACDK1AKVsQetgI4tjUpSuCy70tny9D0UFayZG9w89YDAVe7F7LYyESjqQBY1DcLZYfvPPY6qKwEZCjMS9KdWKmkiI197lxnWWDVD0012+/tvMwCDWydd10VYVYzpKovpP66gTSdvJ+BTnNS2bUiBu0HlZklci5oOR59Ce48spv2UOhxxsq8SP3XmvrNCIvY2nrgwOnjm0rO/GnjI7PNjS40Lc2zkO78pEfqr8g5IG1Q85uq25pJafm1/yO2W4Qz4OGbhjGQrVuFz2J8jfYgBMq6kwRAmQFJ5FoJf+dUHaRTklRTwlgbMraIDhgqCX1wGP1CBRokISGa5864anvMKGiQuj7OUqpJ2sr2Ljo1rq2ArI4zE6vrngmp4XZ+ZSUzKyhQtVhSS5yVCpWDYpRnQT8vVNZfE5F4wUayBKij8UipRHqGrs/B+CgiOo86AOnoW8Ixwwkes5G3yO/c3aRetxpzhpmjp8JohG+W2BYNJrYii0SKIPT8pesxLm6nrvJ3j3G4Ueu6WVy5fNw67ReMDuGQuoH9TBE3eIk+dWZWteyxd1B9pvsIfc1Da8RBfC3BUl8iztIR3wTlInjbQCTSRWbXArQc+xPV89SoApDHeEl6S7fzCyymi4EJEBWe9Z4GVKcYr9LzJ+SY7jUtKljXsJGBHCGIL44bWlwEIEBbPC3Trh2RaE05nBpqs/WGk8btNgqOTFHiD3MGuRjwYlUYlYMTR0veKMlMTpP/uSk7LTJOty9FVL514WU03KIgKs/pc03ltNO6I4vGv1LNSqg8dnlllEqFQoceKBBE+m/Uf4FyMFCM/TFuBrVdzRlqE5AORgn6bF4El+h65YAInSU0CdATEe/JBuIW9WTjJsC+PCGdcVnsmXwpZpAfnx686O+J+uUPAD1sfFIV6YkY0TqXUqp5vQG7b0tDQ7FdURdn94hl2EMBrXT5bN73rMC8qAh9qX3breCyPclF8asGAqFgWJUnPTroOpC3q5MgM2uiMbI/KEtjlrg5HLByCxKQWkBQtooETokDTAS6uqkNT4fGc2YXlIcKNBAs+umYfWMLQUm4GrrGYxTHFRGGIIzJ4KGbt/pzUzUBU7z+ZzXD6D2cUP3acHzUIAQUKodSjybMJvN0KUO0+kUuc9Ym625PjDuVwA1J5S5yjjlhWCpY4ZQYln6vtcQdOdLWxocPGdAqfbU8Cbyv+qtDpEFIFpwEPqXGzbQqM/wt9/jYfeLhpLOJWHksR6irYvPr3471AyRqrepwAt2nCU3P7ldMy0rqxMTkgthXnyxJM/gf5EpuhGbZ7yA42nM4oE5SWMpIkq0fpSmwHa7gJND7WCKOrYiU5nzfh7yK6VGdrJykeYj97TObQ8OUt6cC7pJpxGnM884ybTtpJtAXaJijoww3gA4Vil0HIUKqMu/7bk/B8xhMAiko11nx9VkditQG9U7KO1LsROtUxflIfmM0XvF+vCdDWojD3Giye4WKmnlqR3dZLmoYPyF3jpK442e6+w5LTJ14gy719C6vwOLnrWHRs2pEbph9TwP0DgGM1paaq6J89LRbn9fdUZm9PNeN2kVFrBEBGLn92w+E/I4cPJ1XafniArzrOwSgqiYTqe82aqg65LuvZhz8Bck0gA6pZRwNoZViBVHL87NCtK5z7rds+7MHM54nC9tzCPn0u///u/j1a9+NS699FIQEX7jN34jfF9KwZvf/GZccskl2L59O2688UZ86UtfCvc8+eSTeO1rX4s9e/Zg3759eP3rX49Tp05ttij1fc3vhklJzzlQbW058Br9IO78r/kXFjWo1woDhtHigv/OFxF1cIqQieNxYAZBIm4vKEx4R8ATrYEuxFEht9qZw1MGUhNTsX2vY1zjpfU/3BWD+5pPg8Z271B/yGh1B+8zpj8EjbgOhLdeu9On+vlcA7v4EopjL8m2dHVKs2JC7aP5bI4+90GwA/spkldndF98WsxW1YkIPrS45OCPUOdmzrrbVIIA51wBLvd9iD9Bi/aejKRNg8Pp06fx4he/GG9/+9tHv3/rW9+KX/iFX8Av/uIv4hOf+AR27tyJm266CefOndN7Xvva1+Jzn/scPvzhD+MDH/gAfv/3fx8/9mM/ttmiGNLLn+t4Ymu3OFCQjiyl7sLjjjSRkYEz8lr/fDbnUhjXOmAWF53CvXVKK4l2glBM8HfMIhwtVVErMcPIlVRClBRZuWggOE59OioMeIkVTWnm8PnQyk+y2bOL2sbKvvgr688FwOXu9VAIp4k9DffaXwRZ/pO2K7lGhZqtzTCf1fUHXUoWmEdyyxlzBhfAmxjSVbX+9TmbGu3dOKr3Oyc4olkRfiB1soC0ChaNSZNzRl6vbV3atFnxqle9Cq961atGvyul4Od//ufxpje9Cd///d8PAPi3//bf4tChQ/iN3/gN/PAP/zD++I//GB/84AfxqU99Ci996UsBAP/iX/wLfO/3fi/+6T/9p7j00ks3WyRNiaiGW+dpJBm0ieqJRHAbVIjLi1J4m3dBDY2RBgPNj+GxxTN1iWqMQymceP1ucAzBS4s8x//YYOHPCzIVwbPCsbEiqKBmRbHP8DJiVEMHVXiBaPEYyCWXgiSe+fOpJecL0bc7UDPOZgVTcPJlt6fDs2OvzwsaTMwOEUw2djRPW9HolACM5aWU0Lkt3PPc13Ek0ajZ0WjNTQGEDDx4AVnJHE0a6OWYwRIVUC1PZL5aH9MDUkoORlPjRRCIA+JuLG2aOayXHnjgARw9ehQ33nijXtu7dy+uv/563HvvvQCAe++9F/v27VNgAIAbb7wRKSV84hOfGM13dXUVKysr4QeA0wquQu4AUa8tdQGL2GWgAQLnXMJ+exkEkmwRTApBPXVqk+9J/H6dglogMaqBJV4ltFqRBA20+HgSk0HrGMwEuccNUim/xkQUeuopcDSVSMpmFyFgIs+qimwqO9oKIxe9KaQ2u2py99r4lMvQMxNXnpG285o3axsX9UfVfrZ70IyZ+XyuQWE8e9DFTVoqGTcecEaEnAh9yej76nuY99U8sfoLXyp8FHHTLiTmipmoAg6p807J86c/VXA4evQoAODQoUPh+qFDh/S7o0eP4uDBg+H7yWSC/fv36z1tuvvuu7F37179ufzyywFgUFGxESklTLoO08kEqeuMWQNuZA9GL1+Wjuerwa42m1MBiJ/R70gsephwkgmumgH8E667d3jYGyhOlxY69RydNl1NLlt7RykFuWcbVbYjeyDiv8UM80FTfDklIrM/STwUlxFJr/vijCSr94IBPcLwvGaW9inFjRVqjRwpqNFuEfzZbIbZbKbbryNi234IWT+wtDRVE6OdCavVj8omZwNiP1tSYzJU0JnzuRgyg+GZlTdl1Rzx5gP3x3w254hV8w0aFDVtidmKu+66C3feead+XllZweWXXx40mDSw99hqZ4M7RkTFe+MdlRehkUYGrEN9PEEPSrI8dgnLlbadtSWvnd47okn53coYXDHkfhWKYoPCp0IZs261GkRu+bC/y8wKBMGQC7IUW94tIdZduG5rD/F7WCuBgnYcr6Z+qTTOt4c3JnzpuQ1GNJ2fM1GIE8HT/mxiQAhIiy8IsmnJ2rm143PubbGRDQ8YMzF/QSmZl1BHpul/yztAUICVhVLGXvlEMQggq03i6g8d636sAkCGn7quecxzjw6yRyiv00kx/amCw+HDhwEAx44dwyWXXKLXjx07hmuvvVbvefTRR8Nz8/kcTz75pD7fpuXlZSwvLy98r7FvN3PgNLjNyZv06GBywk465KPwe1vPg4PkuzTZhm/7tu/CZLqEL3zm0zj11KnG5FmvN2jBp/PFoyJk6jFPp5Ex5/raTIfHIw8+AR6clhWzSswLG29F81JmlBKmS1MVLGVXPK++Ger6zSRhQGRUQXfXAiOgIH+qvwQRGPh3YIzM6mxNhDlmpb5dZ1G3RXnUZfk1pL28E6jfz+ZzPTVMlNacl/Grv0bYhgMGrSccUIMBwrWLsQvuA5nK5Jt09mWD/fOnCg5XXXUVDh8+jHvuuUfBYGVlBZ/4xCdw2223AQCOHDmC48eP47777sN1110HAPjd3/1d5Jxx/fXXb+p9ahO6yort6FcE2q40U4WirzzjkH3zAtaSn89bfnvAueTSZ+LK51wLpCmWlnfgnt/+VTz55GPjqyrRCO0mks9pkjpMl6ZYOX18XWEkIiwvL4fZovZ73S3IWsx/bu/LOWNpeQkXX3rQMQq48Gzjh/9sNhl9LqE/UFDPGhFQGDHLRk0R8f8I+xGmmJ0wOUAs8q+MFWVYQz+UN6sA8BF45pPq2aEon6Xs4sTus5vGRFEHamAeNFROVgipszSQmW+dLLkHH7eAslFs2Dw4nDp1Cl/+8pf18wMPPIDPfvaz2L9/P6644gr8+I//OP7hP/yHeM5znoOrrroK/+Af/ANceuml+IEf+AEAwPOf/3z8lb/yV/A3/+bfxC/+4i9iNpvhjjvuwA//8A9veqbCD2Q5Sq6Cr9lfep+jnLqYhH9rKnXxSuE5Ys9I4PITk6X+mbD/wCVYK1P84ddO4CVXPAsv+Pbr8YmPfQir587hzNmzmEwmOv8skYvbzzI3PekmoER80Imbd+cdetPpFAAwy3Ps3LYdk9WJTptNp1N1kglwppSwY8cOnDt3Lu7047Rr1y4sLS0BAJ566ins2rUL08kUoPpZAGPfvn0AqvY5u3puMHC5+QJwjvTYwr501tTgi9J8YQzpPE6L4AStEiSsyMyHIcsQRaLKgP8J09wFmM97EIGdjEzZ+T1ibviZEsE4A9o6fd7LoTmAlYlBrNO4EBgHBi0gkyhngpRSdEGVyMVGTQrgmwCHT3/60/hLf+kv6WfxBdx6661497vfjb/39/4eTp8+jR/7sR/D8ePH8d3f/d344Ac/iG3btukzv/Irv4I77rgDr3jFK5BSwi233IJf+IVf2GxRZDTqR7VeB3QLSB1PU4LQpzkwb6llsW3XQLOXH0oDNUO+N7EWmxfgy4+dxrMP7sThpz8LZ8+t4tzZM9i9e7dGLD5x4gT279+Pc6urmHQdVlZWcODAAZw7V4Xt5KlT2Lt7D3LJmM1m9bnU4eSpk+j7Htu2bcOuXbuwtraGtXNrmE6n2LlzJ4DK0Hbu2InJdIJTp05h+/bt6LoOZ8+eBRFhz5496lkvpWB1dRVANdlOnDiB3bt3Y9u2bZhMJpjNZ1heXg4A0HUdzp07h6WlpcZUs3+jOea+JafdB3d6YLDBW/uSeC+JCUWXujgrwP95clHfmbQMbD3WPi6mwZUlLkzRi+KnqgvX0QOJn3KUBU6TRHXV43wOOe06l4KssxwAusSLsOpJ26TmcUU+nSb3jMKNQauzAENRAASYYVNk2BtJmwaH7/me7zkvjX3LW96Ct7zlLQvv2b9/P97znvds9tUjL5NOIlDXAS2y6uCu7VIj4ohvwd3HTKPPtWPUF4EGrZ2pMmZurM4zHjvb47Kde7BteTvOnT2NpaUlPPHEE9i1ezeWlpaQc8aJ48exb9++KoizGY4fP44DBw5gx/btmEwrE5BtwSdPnVRB9qdtFyA823Udr9Pv1D9z8uRJzOdz7N+/H7nPOHH6xGCb+unTp7Fnzx5Mp1Osrq5Gk6lxpHkKrWYZ3JTXRsZe5egqzt7mV5SACR0BGiRVn4cBTsscdDxwTEnTqn72RX7ZVKlXElJNcb6amWJla2ev/EwHYJHFKE1AlJC6DqXM40ImSJCWhOXlZeSS0ec1yMAWQNDzTFD3SxCgKyOlHtI41dEKlGI7QtWE0rbZQD/hT3kq83910mPXqM4pU0rOMVWTaDlxCK3NZ3UjDdQMBWCMwzs04dC6vWfM/is548Tpc9i2fTcOX3IZtm3bhtxn7NixE8tLS5jP5+i6Dtu3b9fj26fTKbZv3w4CYW1tDbPZDKdPn8aZM2cAxCCipRScOXMGy8vLmEwm4d3Ly8u1jrMZxBMv3587dw4gKJuQI9yACjBnzpzBfD7H2tqaAlbhQbl9+3Y1b2azmQY3GTtpS7SptPw44x9b79ACQ6X/evx8qlunu4mtH2kXXHkmoyaVEw4PDKOzE1yfep+f+XDTz7X7dUOeB1K/GtLPmuTco6DoupvqU2CnrxRYTYqmNYtbAJVtJs4zB9+u8pxOcbbmCDNApI2hw5YGB1toIlOCok3Ij1Ju3MxRfi1sOODsV8kTCEFc2tQOKNEY0wQsTRO+8o3jyGmKZz77BZjPe5xYOQEi4NTp05jNZhpkZmVlpc5Bs3/g+MoJnD13DmfOnFEfxZkzZ4KPQAT21KlTWFtdxZnTZ4FS/UCnOf9z587hzNkzKvA5Z6ysrOD48eNhsPg2nEwmWFlZUSbSpa6+Y21N/R0rKyuYdBOcOHEiaL7iNG7TUgtYe2ngJAJDbGu7vmitQPzM2+d54ZLOvPiStIAiUtlQcblVmMFk0iF1Eu1p2P+tohAHN1FdXt1NOvZVQYVXipLZzBNQFtzVd7idwaX49RFSzjj+nV/WQA+yRHzjIr8l1jksStoV0hrBDuZ7XON4iigzVJ4q+4xrQwq3dOYE4gAqpeDxxx7GM5+9hkN7lvGFh5/CE6fnuOSyZ2Hbtu04ffqksoCUEtZmM5w5exYodeHM2tpa/Z7qMu/V1dWBGeFXY2pe1GG2NgelyjgA6Hc+icYHoPf5PPu+x+nTp2tbJMK8n+PUmboJjhJpWdbW1urzVFmKHhYLQuGjygVuq6BFe13Koja69sW4NSL0t04SFNdX7h4MQYJS0vDx1k/O/CjjzysQibArYbN3y/GA9f6iwCnv93/LLtUaLapHhtxrBfBOY0pyWE6ET86wtp2uYh0xsYji/VJGwNh0Aa+jGGnwkbSlwYGh3bSKmAPc7dLI5jG230XvIp56qlQWEHut0tJM9dRkO4ERTZ7A6dMryLnH/t37cdHeHXjyTIerLzqMq1/wYhw9+oD6CCTtftruUI09F+0bmEJeu4o5Y78KurVtSP0E8+1nUUctly74BofU006AljfV++ImHf5KZnO8jDFbq4InPgO3rFoF3k2DFrPLvfYUYRwHkaImzEIjufVwilZ3LEH6WDS+HfJijKSwDySz4tCysWJQhgG4dQrGNnzEJ3Nos6ZOCfN+jiJtqhGq632TyYTBtmB1bRWUrQ1rFWqAmcLg0vdyXF6rCK2tVKm5g38zqjVRlCmdP21pcKCCAWKqEPFAHcxJE0Bw0XhZQ6UE5CzHp8cTlmsWCYmKxYpwy1olIMyu7RMsT5dxbKXgeYeWcNkVz8WTTz1ioDNWh7Z84GP76svFOtbyqte+LKGjKWg6B1JxdSMd3HEMONpcGt1U6pLzxFpJNWQxcJDhKCaYLURK2oa+jOJsq30hEZItD36ttorDH20LESivGccWtPkHvRPP11vHBYppaZTK2Dg2ZCpA39t7ZCOf2P7iNJX9Fm25dCZpba06D7tqStT1BTWkYF96xcQMMUvqGFuaLmHSTTCbz2u8SdixjrPZGvp5r+aBVlnb0mJZQla4cuplOrObQI5N3Eja0uCg48JRfwFn/sI8usV74eVMNDtavpQ+aNPWhkxsPxbWsHIuQckFp1ZO4MzJE7ho505MOsLK2YyVc4RDh67E0tI2nDt3enH5nQAA7uQmRnuvRayukRLLddv7z7SYmoeLF8TCZoFoehEi8KAEi3fSO2Q6UmkqkWp3NReUFYQegrEEsHarl9YLWCb9EWYmgAgQjDilaajEm46EEQoj8AKtTkX4qOTcx1T7W9crZNklKWaGnU8pviBZa1JjKdR1K91kgul0gtlsDiJeiFRsPc58PgdQ/T71hO5avr7r0M97UOLzL+dsJqnS0xZwJJGZDOVwn7BBX4eNpC3tkNTkx4XXbPWrwb4I897qI7DHZYmt2Pn2nQSTNVJY03y2hrOnT/JqVcKsBx5+qsfufYdx+PAzm/eKqMkL47ud6uTyr9+RwTkoVFkESn/WyYBsF6euxMtZT5gWf40ydTcbpGsMGBBs+XVbZtPa6rxs8ENYRSiaAoN9Kf2qzMV1YgSmCPLm6LP1CMOmrQA7XZpiMp3W6Ex8vonVxPKybdzVx7G2toZz585pBOm60G3OMRutb+xtdVWlHX5b65u6Tuus5hhsnBbXHmaVFcZfmQ1xSC/KpLjnN5C2NDhUEJR4fs57XCzYRRkBBh3AasePDWY3IPgZ8f7LNBvU5Kj5TjtgMq299vCTPVbzBE9/+rORuomTB8tXhFcWqVRNVO+xDpYSOeH3U1GFv8t1Z2WYUlONLS/0tN4BB5sHk0nHJk0NgKOzOg37KIjTeVL/wdSuq21hlhV8Aq4sQ3gQs6X+7U2ZkMjX1VJmgBsDKy3zwJixTGtfMJvg9zoriB+JdQ6Bf9y12XymOy1jWcwXIi3W9z3ms1n1LRTUiFRsYphJJ40rJ5MNZ1pCn6vpTMp2NpK2NDjo8CuFBZYjOunmoeGAhXxeh1qNUWMBCA3n5QZB7jOeevRR7Oh67Ob9YWfWCh47mXHx4atwycEr0E3cjr1iWlHm4z1FrScd2XtVQF25NC+vPaGXbPCqtpabZRYgMoqgz0TDKIV2zELakAGsd04vDxQiKDlnBZkBcxvtz2FqIGMgyvZs7Kt64K1JSSsTStSMCun9csnvNxFBjj91DUKfcwB0zzAK96eGf1NtXn/LeJ3NZpitzXg5tfUBEBmtMcKk46htLyJjdp5Fdl03fqjwSNrS4KD2Fhmdyrm3TmoFSRIPeo8RcTooDgCvDQJAuIFwauUpoGRMOrkCfOHoHLO0C9e88C9i5/ZdMX9E4e+zaYwxbTwUqPq3Hr+ePBNQ7wDUAcNaONjxorUZdPp5j8zTcQIMVTu5+0kApppX0ZQwaltkoU+RWZBs5kSxeotTMPp7GlCElFnusf4M97qWMTNCikxNHwtlWjS4SMdVzduCt4iwZ6+xG8pe3B/eQexfV9mUxI1khUASXdwFkiWrg5xzYULvFwKSAwVjiRrcCM7vsIG0pcHBBlVNJsB2irKn7qQD2zwSkWFIPsNXBQFt2AeBMFubgUrB3u08J12A42cKvnh0jr0HLsOznv0SPevAU20JBNrPa2APYyVGf1H8U00TaH3MGrfvxhstaB7xbQi4enOm+e1NAtFOoQwCVDDg9cI7ZnBUl6c8O/y+MUIaC4T07kE/NddFuEbtEleuIvfClIqZC65d18mmjjs4Z6CAYi0bAXWZvpTVMVHi9o7sEXG86Ti22pt/xgGEfo5jfqNpa4PDArnxWkeoVN3E5CmZCbE3IUQgvVOy5ukpnoWAE0M093MQCrZ3sQxffbzHo6cSrnzmi7Fnz4H6vCs/eHDIEllZb2ACKTdTGLCwy/FaiX96J5Zl5ZmGOytB3zJoZtPGojHBcxlJNg3JYp5kecOEzAYtv0W+d0b0+uaGBYENZXTKX+sY2BYqe3InhsdXmHZuGrW+L/G+DmE/zhwUpkZk2SQiTCdTTKdLmmkLohJ7Upy72g9uJaTWScHDgaQoqFyiSTfSdAMFsXFs2NrgECLsykUWVqGu6oiRDgWaFmuFEACIY1H6OJFuyXWwweu13Bf0/VxbVDp8noEvPTrHdNseXPXMF4FArojm3CsQv4kFMlWWosUaCu6Q8rvrUc1CJCkMvOKjFZtq9KaKNJAObieg0raBsheEQZ98PnAUOZkN7atnWn5QW4hz0AQz2EuuR6VTS8UG5wNYP3kYjQDqy9aClLAEe09z3im3x4T3tky6TgPnSMhBCwbrGZhHe8emHOvI3vHagETrC/KK4HxpS4ODOYQar7pIXyCyvLde6BX506XjvS3SB2qsHne4+wmnea3DUhLrztJjJzMeOwU8/bLnYdfOvVYe70lX5umoZvOeRSkIraOSGuZ+zOwoYtaIVoQCkRfsRe+SvzUf1w9FGpEa4Sr2+kiNpc0F5PzmKgMDcxOMAIc3+6y0gUl4+3+oQqWfXX2KrYGQ2SRhR0nrVXNKvFiqOif7Zvm2CyFAZqYACM5ocRYqYAqQe6DW7jMzUJSLnE+h/iwPIg1wbSRt6UVQkmqlURvODUDAqHBB4WlNAQjnTIINUn2mlEAdzd6kgcMTAApxozeMAqgHMT9yosfFl+7FxQcvx6kHjgc7mgg6HSsCmnNWlBLBsSfsXxHwYHIQ2Xm1UniypwaOTqXWDedu2tK3DUqpIf15ObHmw4yImJoXANAoyy3olPAq8SOoQEidRjS1KxBaOBaBDuWNTYjhYGkEp0hd+O6U2Ecg+ROIMtDXtk2pAyW3fkLGlg0cNh0s4pZcl3gNdbcw8Rgo+t5UCvQYZor9Z2WXYjdjWWog54Vuwq7Y0sxBkmg9lnsnPILscfD6QaEYW3wD1w6QwChyY+GVb47nq5kgnb5jCkyXhqcKPbqSMcsTXHLJs/SUo/ou0yJSnqq5HHtwzMYcf67+XC4rL9vHxeh7mIrkSkanqvtpzQRXLu9E1anKYszN/w6OtsRAAmNmAZwKovOMwM+Q09giUL5U0jmxHqHg0st6m/MVWHP4inqZDkmek/aQ8maOnxDamFi4nRnhn0myvLrUg2Zk+rVvp0SlYNSYGa1Cc+NYFaZrA+9830j6MwEOcNtydYjoOPID3Wxvx9ACmhpTKMNFNGKSOIos9ux8NsPjxx7GzknGjulw5J06V3DsZMahS5+NffsO6iDSMyPUGSX016YAzdfh6LVPDbPwA0TqVDWdK5L7V7Q8yARxACiOlg/s4KC2hf47QU8ynRaBQUDZbBn+3tv1jmKLSjZgjcxA+YPXroEhmnDLjWNAFWQKxKsk/VF0MAchm28Cquo3mHSYTpeqo5ZNhm0cTwPh3qS+HuKYD8Mk9RUlMS7cvj2KA0V7FoPr66WtDw6ODDgFq4xaBlod8GbHqT0b6GOLqmOU1OiZaFG55+zZ0yAUdJMowAVAnwu+9kSPbmkHLrnkqujMauqjv2UgOo1n5fIPGejZALE1/Ernx2i5y0GZLrePxrVAHJKL/BH6rJoG9SeRP+eDmrLHp/U/xyBQmyLEMGgaKjCsCBqxP8O7HKhGk4KBtTG/spinvH5Dqzi6qMhMNCty4dgQEz0pi7htppMplpeWsby0rDs/DfRotB8GMq7miGMQLXYnYKMxHbY0OIgvIXZNwyBgwiXswcwLOHnz5ws6DeG1paNukqkXkrNnTiGhx/6dFDpU0lOnM06vES655NmYTmpQ19YOHwpdHPylFOTeaLRUIQwduU8HC8K75G8EIYyzHoNrnBKRasOB2YFmvHqwbo7Qk5J7z3/EX+s7y8xlrVTZa0z7O7KMtrPt2UWJuJFk0Zu2Gefvp5vHlpkbE6mp50hkAJA4lN9kOkHXJSwvLxnTFdcCyexa7I/QFAuwXtmB1yyhg/5cMIfiGtJ7t91Aa6hWZahy7Ad0SLY2sz4sfzUDwthIUlv6+FPHsHbuFHZMxzXr2hw4ttJj7/7DOHDgkpBXmG1o+L8MeLFJNcQYf08gWykJOLSIA7S+S97nhDUAQxxzWkdXJrGja+gzbSD9Gdq0XgMOmmU8OWrcmlXk6zbyEwWfe5k28W6qEaUnHJau2MvNbOJroooajmBXi1NeXL75fI5zZ89iNpsDpYJL7uvy6bW1GUrJ2sbSl0YcmzL4t5J9UOUwxn7WQ0WXtjQ4+DqabZtYUGzgtg49CMVWzi0s3qjqeAO6gSpTWj5WIW8PXp7WaNfhnajrGR54vEfutuOKK69Reqdaws2ODCoqHSyd682dMW2vAlG1T7DNBywB2iaJUvWjNIxJkmy4snKuI3EysIOmo8WPiBloHReEXMCF+IDa4LdwNMU/066xiN+7VzfsTeJVyinYwReTugFg8oMRRLkPUkpYmk41CrkyO14RW9uzbQhoBHTDXZs6FdXmgSGw1QIbM66dSmjT9dOWnsqUKcNSrFOpM9bgGVQBms6UFX4WrXcsaCpgNjgKWawIpctmw63Nz2Fl5XE87eIDWJ4S5jMHEPzXybMZx88WXHzwSmxb3oGz507xmRpA5gAOMnlRigVMqdOVGUhJIyzUe8IQMeFK5jdAkXMsHaAAdmwgCPBsBDVilLdzfQpMzLWtmmsjwh8GceGTpGAsbni/YxuuD4pU2pUlWImOnoswV+fyXB9rhcODnMTtkH0UiTV4yXyqWKr3Zl3aHEFXADxodr5nMqmRxeWzn7XoUqdmjCi6AqCfZW2NsXayZjUg0nJ406dIPYfje1Ha0swhzkAUbZyK7LXBOw4Kagq2PfnYW7tDeqpaVSgl4MDEbSpCXbF56tRxTBKwtMC0mGfg0ZMZy9t3YceOPQhTeaNCZX4O62zHLoo4yJzm1MEkt7A9jlg3o6qthx4jbCrKfLgu5ohjLY1948pI2vbU/C3/BSFwZlEVPIuhMILjXB5hY8YcvPk98kQwE81csjElrE6cqvYOtziqNQk5id9CYnnqQUylTvFOui60NckYlo1evp1DCtQ5OJC1vZx5hiKrNjdmX/0ZAAeo5DemmH4lYcGj7ekEXYmap/Ql/HKihgJZh1B0S7LkeOrkE1jCDAd2R0DxJXvyVEaabsehw1fWHCVk2eBOfqMCSGEtbXeJD0XZZGN+iIPVahGdlUJbx/VS0UFL8jIrVJC0dpYhocaQElYUZwIas2WdVFA0+pZOx0EYQ2wzYw21r2uo/jnm85ndN7QEgiknwO9XexJqrEc9tV2QPLwPtj0dxvjkex8PJBwzCD79qo/rVCT8gBbKt4miIjFDorDUvWUNJFmQm7XbQNrSZoUfcJYcC9D70AxCApDrwj1tyOHz7k2QjohRlWXoWDmeePIRrK2exiW7l/DgEqE/x9TZhWxbOZux2hOe9rRD6FKHwmcjA1BA8Wd9SiW8UIWqkP9QdICT266NQRuEr8zkGHwjHykMNpEmgtN4/l69Tz43wOKr1goTGhPFP9r8MaZVdSpXcmfGYn4Cf1CwB28DLJ3Z0mdrCUvfV1Mt+zw8cA3bWKa7/apNwMLMSSQo0pgRpAvN1KFcbK+Gtq7vdxKzJhtrdIopwTOqPw9TmWKJiYMn25r4FhgkXHnPR5xLx+uefM7Rku8JoZ0UKGTLCgoKTp8+gUe+/iVcvJxx0Z72gJ366exawfEzBRcdvAK7du1Dos5Age/S8njgUjALjTDKbmq7cEyFBR5qAg2dqmpOOXOrtZ+lYTH4musA1z7G1hZzhOF79IPrSHs+5mQmo94atll7U8qKLn/LdZd7ifdYUUwbhy4oZlJZCRtzsC0z8V4K8TMocBi4iaCHGTUUBgKE1aNdsmBC2tfk2JzbMbvRtKXBwVxVNVUPcFzV2C6mgTMjVICaTU5GNb19OW5jckH0/X3f46tfux/z1ZO4Yh+h60Zs0AJ843iPbTv24bLLnquDZHBn0VKCQLqQqKXGOo51YHlqqXc0bQdVPgZMjoLKIIRRXwko4qfJRo34xgcRGqlhAvAfI1Wye7Ua4/UQIYETIlmW7g/O9YFpyoJ2sXHhxg9fj/6XOLsRq+8+K2hFM8NrbzXb4A5g0veHR2tfcH8lOTCn60I7B/PK9XGihEm3cWNha4MD8fRlY2/Zjjqbnkupgw8aa0JkGsFTzbgAKDY8UdxN59ABpRScPPkUnnrqKA5sK9ixjQadSwC+frzHybUOVz3rxdi+faezasgGJD+XiHDwokvx3Gdfiysve17Ym6ExLUPMSa9jiwNES0VZSIkD0hpFab0Kgaxv8EJPbVst6iz34sUUIpQ5Ap6Vj0b6pzizyPszNFCuanG3b4EBojIN77yz67WKrv/dtur2aEH/fq22Ogrtc+u81N/8jPgkqjLoeKzFOoc2cHWu+cfDhqU0g/0150lbGhx8yCtP4YJGC50iqFqCILTMXdKAdagKM02b3PdCOPs8x9FvfAXbUsb+3SnkJVJ/bq3gK4/NsWvfITz96c9VCyK8m7XEoYOX4/rv+j685Mj34WXf9QM4ePAK3ovRBDWFVcTzkIGzU4TCxzYcq7/LR7UPA0QYqBQXcI19bn0EA6Lt27C5NzR9+0w10us26b5HGVndasuuTeBbT36UmRF6AxPkTmfE4tShL6AKK0hPBrep9yrEk8kktqOPO8LXKggJa0sNSCCa0mrCuEYT1stVOJ8D2KctDQ6AMQDRgqopPbUmiyLkR6HXr/KNHxIF8WRpfgz6AoJqEkA6oYrT448/jNnqKezfRso0hOLJFOiDT8xxcjXhGc+6FtuWd7gNWOD8CIcPXo6XXv8qbN97Gf7HUwk03Y7t23fDn8WgQu6BYYStGAAZY+hzxkDTCQtDa79CBX/gexHTREBYIkL52JbO9h6Kn5RZWrjov75HtCyiPXUcxIjYQyGoNChqzhKuj4EbON+wl4L7UswUAEGg1W9USvB91KKbWeoP49X1GLrIpR5dVwFi4trb3lPzj/FM4fuMWznxpi/ZxzGwSxekLQ4OvkH4c6NuCsx8AFpPbTtTMcx+zPvs1d/AruY/57M1zOdr2g/ZdZgM3nOzgq881mP33kO4/IqrK8DxApoudbho/2Fc97K/gj0HrsQXj2U89FTvlsRKvcWkyAYYIoC+bA4U9McaLvgI4nMjGsmbPm2iuniHmvwGbefuD98xqBsDcrcGxKsnb4edjI4J+DITq01fJgNID4zyPdfR+TByMbDKpTBLcQclwcxNed4HiJlMJ7yXogtsQ/uK2cjS0hKm02k1WZJt9RbW4Jfr9xz1um+irftm9oxPmESgqOukLT6VqX/xbxp8z8MgDBSihIx4oOhgerDNWjxj7jIB+MY3HsfsXMbS2k70S2vAUg8QsLy0A7v3/iGeLE/DA1+f8QrHmnEv5xAA+MZXEs48Ywnz08DRoydw9txpECXs3rUX+y86jAcefAwPfPZxPPD4HPt2T7DzOGFlZUXLoqwJqNOfDC4tezCzq2lEFhQqzf2Fw4s4EJAy+2claI40kZki5G9rnxymYm5iy4v0d5GBzSUxJuhraPloHRwTMOCwWBQC1jL/L3VJhMp6CpAL8VoLMJXPg7asgChO7MoAxSxYXl6urcKHHs9mc1kOW4GHMk81ki7aAywMoqtdPa2755OznHmsXUBD2c99xnw+Qy5F11psJG1pcBg4V2RALUjSoao5MKIVgREmUbTRW4H5nQ99EocOPgPTyQq+/OUv4snjT6ituWfv76EvCWdnCQWEtdkM08lEF1B1qZ66/W+XO+zZMcHePbtQ8gxf//ojWN62A9Plj+HUmRnmpcNFF+3Hnp3L+OVjX8f33fxSXHnxpaZl4aGrXTNgdryyq/a7htILI/JgMPDAW8sgMDaHC+Zwq18EptLm6b9zJowVktyyZNPoWmC5MWC4AEECqAprBrMtNQkKcibVrrqCNqW6kKtLmABYC6EIiwPGwrcnLr8IngdHwnzeo0NXrwuYO1ZVpzMJfY96LF4ilL7Ovol5UwCdliZlWMX1U0EbCUrSnHeEzufzhUS5TZsCh7vvvhu/9mu/hi984QvYvn07vvM7vxP/+B//Yzzvec/Te86dO4e/83f+Dt773vdidXUVN910E97xjnfg0KFDes+DDz6I2267Db/3e7+HXbt24dZbb8Xdd9+NyeSbxarYIOom8ArMmQgqPG5MnS9/vZnszEgA2P+0/cg5497/8gfY+7S9+K7v/Asa7mvHjl04dfocLj58KU6cOIWHHn4Ez3zmlXr24crJU/jD+z+H5zznubho/x6cPnkCl1/+dDzzWSfx1a89iGc/9/n46kNfx1VXXoHHn3gS+/fuwJ4dU5w7d8bkuHCIc6J6yrhUV4HSgFC/G63v8OL6nu2WT8TnW2+8MhtybTnevGbi1D8gQm5vc6yJfwuTMAAsel1rxw9kdsL6NQgC/tNpnQmqZ5MULCXZWi/mYHYzI6TvqswgYcJAQJS1bLPZPMak7Do9H0RnMsSkQkafzfQ0v1nNqx7a1KznKaWqBMesPIBqCEMZCxs0Kzblc/joRz+K22+/HR//+Mfx4Q9/GLPZDK985Stx+rQdFPvGN74R73//+/G+970PH/3oR/HII4/gNa95jX7f9z1uvvlmrK2t4WMf+xh++Zd/Ge9+97vx5je/eTNF0bRw/Jb4E6bHwhAbF4LS/sf03V5cf/rcV69zSti/fz8e+cYjIJ5//sIXPo89u3dhPpvhqw8+jGdceTmICN/4xjGUUvCFL34ZfZ/x6ONPoC8J3dIOfOG/P4C1nnDg4KU4c3YVlxw+hCefOo5vHD2Kyy97Oo4ePYrcz62csr8je4+1q/ugViONE+yr87e5r78ApQozf+W96nJNZD1M1UrbS15MzX1ei8mgCLY5Pf30ZtfVaEzTycRtMmvbyo43JC5D4vUtFSD42HtmDaVUge54S/dkMkFK1SEty7xjm8pJ5VXAJ9MpJl3HRzYW3iviZ9mqjMjSaYKL6wAEPwXCmJRZN/alFLcHRXd+8szJBoO9bEpVf/CDHwyf3/3ud+PgwYO477778Bf/4l/EiRMn8Eu/9Et4z3veg5e//OUAgHe96114/vOfj49//OO44YYb8KEPfQif//zn8ZGPfASHDh3Ctddei5/92Z/FT/7kT+Knf/qnsbS0NHjv6uoqVldX9XO1ublJRgazaI9cMjo+SAauUfsQLIVtbiJF1IETkvMzGmenSx9/6in08ymOHPlOPPDVr+DyQ1fgqaeexP79B/Cc5zwHDz/8EL7tBS/C0y89jP/6h3+EZz/rGZhMJzj22ONK9aa8W++xJ57CyslTmOW6au6SQwfxxJNP4ey5c1hdPYtPfPzj2Ld3z9DBlzMg8+08QMzO57p6SuyrF/wMg0vhPu8DqJfUyRDMCnKbk1zzRZMvvERJcf00MJzrS2rLV+rsX0gk15yhRBWgOp4FICKdCRITYkLA2tpMbXARUlnHMJ8zMDh2RESYTqf1UxETpR+wER1JhdxxgNBTrSZ8QK/sBPYHGVtfsbD31i5EpOzB2kbGZQHcgVYCtJNuMroe43zpT+RzOHHiBABg//79AID77rsPs9kMN954o95z9dVX44orrsC9996LG264Affeey9e+MIXBjPjpptuwm233YbPfe5z+PZv//bBe+6++278zM/8zOD6+eiRdWBE5taTXYSzLTIx3PUK1hm5rwN627YlPPi1r+Dh8jUU6vG5zz0JAiH3a3js8Uexc+c+HDv2KP74yw9jjim+8JWH9RXbdu3DNgAnzsxw/xe/qq87+3gFv2NPngIALC0l7Nu+hKeeehxPPvEIXvht36kFKl74w1XS/Rl+Hjwy+jEYcNBYYPY/3x5+898JyW3B9kzMg8F4w5pxUvSzJ+tCxSNeWF5yXcyDNn/AmwT1+5QStm3bhul0gpMnT+HcuXO1BKrBq6MyJQqzGbI61Ydxq1kyEKaEIgGIGRFVSVMt42w2AxFhMp3WsrOJ0LZXYSlX5sBbuCUfbWM/ZtmXVctaGVBHNuXsp1Q3kr5pcMg548d//MfxXd/1XXjBC14AADh69CiWlpawb9++cO+hQ4dw9OhRvccDg3wv342lu+66C3feead+XllZweWXX76wbJ5a1iRTVsUNJBlYrHlQPdP8F/QGR8SJClB4fpk77wd+4C8g9RNsm+3FbHoGebpWV2Ny51z1zBfh2170cnz6kYSvP1H3dWSnxT3+D2ykUrC8fYIXXT7Bpctn8bH//Gv42lc/j+l0Eu4pqHlSkWW4VEFQlYoN/NhG0jrhH2Uf4gBMNfBgAyXyfJyqHJ2+tBpKS1rxLTfAbU4LaMAOOek/31SGiyMzMU2qUbSqcK+treo6gppf0rBtORcti59psXUMNipkRsIXty89xDfVdROkLjngqc+Iz0FCDIQT4aUPhIHkjES2LkLQx7ewsTPoP2LeiQ8FpTCr2xhCfNPgcPvtt+OP/uiP8Ad/8AffbBYbTsvLyzwdtDjJ3DK5waqLeWTMe+orf/D1ChD2jNp4MDDxTSqCM5l0mHRTLKclUDdDP826rJYSoZ+fxfbt27BzxxTLp+f67MB0GUmTacIzLp3i2QeAr37xv+GxRx/A0tJ0MCikjDlnPo0qVe1XTPrFd2Iibr8JBYGp21UGGZ7qNGlBm41v8xYYYtaDIc2XU2AMeiebAGIztwDn/67mBdj30LHmz7xdelYdhXx/zhnnzpmp2nUdlnh9Qd06HevmBbvuyqysQAiRd4bmnNVPYAvKao+nrs6I+ChQnIEpCFVe9Zps5RZg6OXYgaYVw5oL2KFGAAJwbpQ8fFOLoO644w584AMfwO/93u/hsssu0+uHDx/G2toajh8/Hu4/duwYDh8+rPccO3Zs8L18980k1WDSGeSBIdJNP2MRFv3o56SaXzSWxPjTE7ZdfISBHR0IS3UAERAGtbfb22SDEHjavgmu2U944hv/Hfd9+sPqo+CK2G/v2ZZaFlud52MhmGrxQyQCovD4sfiRbcN7gjbOGPTWYV3RDtTmJooBW7zDUYTR74mQKio4U9K6y+pAm3Is2i8STr76kYj3kPhrtbQ+JoNyh1IcXa+Iosv0CZj3c8xms7BMPcCjOg9tXAWzAXZAz6CNyAacjl8NTCMg6c/0TDrWN5I2BQ6lFNxxxx349V//dfzu7/4urrrqqvD9ddddh+l0invuuUevffGLX8SDDz6II0eOAACOHDmC+++/H48++qje8+EPfxh79uzBNddcs5ni6GBhN3NFZ0ZVDwpRLv0UGWkjeipmd0L7Iuz0lAHUxBKUlWzVCTTFgX2HcMUV16DQFOfWGo031j+unKkDrr4ogdZO4L/edw/OnDmpN4kW0n8LLEKSgESWSFUWRn3woqCih4VZWM6R5M0U6xOKYLlOKiNQAYjZ4IwPite9RvXPWLnq1GHHwVq6rqva22t1zqPvcxBQAVsx2wQc1tbWMJvP0c/n6Pu5Bv2N28QBXbUqAMD36EwE1f0V25a3YdJNkChhaWkanIctU0odx0h13FdJnFOKfgbHzuI0/8VG0qbMittvvx3vec978Ju/+ZvYvXu3+gj27t2L7du3Y+/evXj961+PO++8E/v378eePXvwhje8AUeOHMENN9wAAHjlK1+Ja665Bq973evw1re+FUePHsWb3vQm3H777ec1HYbJVTLY8BlEyaE53y2MbWHbFA0AY7Ymn0wEDzhGARMREmI4r13bduOqZ74Iz3j2t2OybQ/++GjB4yfN6eS1qO98b2pMCNi9BBx78H/g0WMPYkxwICY602nkjEwUFmmJqaUmQZEBFAW/5RJ2fUFjaXv7+pgpFu/zRGcEAGoVRt9fckbPJo34iIQZefAXc0LfwpmFUGssGH2fUdAHk6Uygh5dV8+UkKlPosoiJl2HeUqYrc14itNARGpeozllDQxrgOlmwtT8i4FfZNt1P+81FL4fbxK6zsILFOt/eZd2Q1Ve3aTuyVhaWsJsVldI+mnR86VNgcM73/lOAMD3fM/3hOvvete78Nf/+l8HALztbW9DSgm33HJLWAQlqes6fOADH8Btt92GI0eOYOfOnbj11lvxlre8ZTNFAWCNH7SLGyAy4O2e5hbAoTwCmJRSrW4UO0y1+EwA04yccs7Yu/sArvuOm7D/4DPw2OkJvvQ/ehxb6XnprZZoQL/bmZecgfm8YPee/Vhe3o4zZ09iLNm8d8079z3kuLywnmDQdlAGFdrOKWEVZJKvWCuxNOssj+Y5fNGofdteJH+R26YIzAOQTU+uv9vMDDjkkq1/qKxgXk3DYqHcZHCIVhVTpDp5RQNL2/L046RokFiAVzYCdaaC207UR+Chrm2kzwjVJ7I2m9U3NL4VAXEJeutNRG8dChC1HlmJoSphEhMz3o2ywU2Bw0ZWVm3btg1vf/vb8fa3v33hPVdeeSX+43/8j5t59WgaG4zk/qufW21VIEtMZcHIGDVFKSO2OgbGc3HovbS0DddedyP2HHw2Pn+s4CuPzTDrXec52i2DY1GbzvqCh5/qcc2hS/HMZ74Qf/zHn3RRrBA6WByqVUMBVaR8OR0YKWhQEEpPspxoyAUUfzuvK5AF1gJOhdU3lbJ4AArjkGoQIFG9DdeF5USzUPY+EPnrBrhWF8fu+Ma+76tQZ/dizlh8K9PJ1PW5YyU5qxkymVj0JvFX5N6tmiR7s3cAe7ovJ3KHA5mJUGT9ApGagtX/lcLW/DaZEiBtCnlvSomPdZSDodP/nEVQWyWZ7duAKQ9EAIbMBGeT0xAk9Bu5dzFALi9vx569F+HxVcLXzhRgaYJuVm1Q6ghpQkgdsLxEmM+BtbMZZU3YSANjBfjaEz2u2L+E57/gO3H8qaP4+iNfVX/D4mQg0WInaT1EEkk9GJ72Si6+HdqNWfHb+slA12Gp1MqbDYpEXCItqNFoiHPVUWurk8we1Ge8WSORn1AycqomX4HIXwKlYfvl3IcFUu0xgMqU+P116pIC/ff+KHV6Owag5kOq52jO53NQ7yNtizBTOIwGYBDJ2frE2YADoC+1DBUUegd2BCQu3QaUPPBnAhyG1nJQPDyYhNFbx9lAq9838+Tu3qFQxM1NkubzNZxceQKHDu/HS56ecGINeOJswjwX7JwS9i4D2yfA05aAM3PgKyc6HHscmK328EIh6fRqxn1fXcPLnnkIL/vOV+Oj9/wqnnjqWNhDsfFUALhTsRwr8O22kXzEYKuAYVAg+DEgdAoMEXLMbymALfm7AhFQp2ZtkHsTMDCQppTIQKZc1xSU4pQFg5VWWOoBF8WZ+QfXUdbDCJgRFWUQmRdNDVmq0H37nEsGZWFZ0G3dXdfpZjAqGR11OjNSgKbsBj42+1B0vPuZOEi7kcWH2Mg0OrDl4zmMJVkUZLvovN1tg9G0ln1WXj3622tYNROcQp3NVvHZz96Dr3/1s9jXP4Hn7DiL6w9mHDlU8JIDPa5cWsGB8gTOPP4l7Jo/gZdclHHZxR0my13oaNWjpZ5xcf/DM+x+2tPxghd9N7Zt27HBro1togWVn1BBbpvz5SIaTULyN7MgFP5xL3LmS/s20/6+H1zpwmMFPm7BOJgRA1S1s3UtgRMarYu+o7ZPLiL8NR/xZanQ8VRge8yc77PWrOVS639y7J0s015eXtYNh3LcIWn5hI1w3q6DZA2Djykq7SemS11rY+dtpJTq0us/P8xhJI0IM2AaSgTF7EG+fzgalSUUFF3qmsDTQV4Fcjp58in8189+BNu378Lu3fuxZ89FAID5fIYnnvg6VlfPYvXcGezYsQcvvvbleOGh56DPCQ8fqwOniCZ25X74qR5P25HwnOdch6eeOob/9ofjC8/GTAmrvKOgiKyozhQMGVhsB7gZhRzuNBZm5hdJe6o32PJZVG47fUy0unnlRWDHIj2ZPS/MhCK74lkHrXWO5WA+UhcmJQLRpOYlxSYzq0qR8yl6x1oap65kqqAiXI1UHcs05mQyqYAxn1no+tzr7MVcNtkJQjllF9grEUjaicFgeXkZs/kMa7Oi5arl//MMDpzahUd1eioF49ecWu53MDHcSkHRFpyBzGCEFZlUN/icPXsSq+dO49FHvxanvTjjkyefxH/9zIfx3d+9F8/bfxgr5zqcXCGUmdBA0uXcfQa+8I0ZDu3dhude/TI88D/+CP2pzdSfhCdxrYeJAF4l2YKEM0JY4usKz9qUAxobQJftdPAxgkGguW1L9BlULGlLaKaLfbZ8ZObFfIJuHUip/ZKI2E1blxCn4qeri/6uswVyFCAzidJpXbUtWN5EK+dc+zZQdvJtbkDXualxPcjGKSYJPZh0Wbbt4Ky3mWnoSy8fCKgnaU2n7MysEaMsCPGfG7NiSFdH1/cXa0RlCog2YiS1MX8/Zejz9ougqjPL24FaIlc8G2FnzpzA/X/0+9jWn8CLDxMOXJQwXXZhxt1jq3PgK4/OsWvvQTzr2S+OddtAu6jTSkaT/wn3OWrs3+HYgM7y+HzBqxmbdg+wK4I8ataMHdU2Vkcx6xD6WVcByl0MYmpza271XgnDJqspO/bkKzPI2XZTihJxgDCZTrG0vIzpdFoXWXWJhdk7CBHaQsok+ywkrodsrZbDbebzufobZGVn/ZnE1mnbQMZmqqyk5IzZ2pozhZNuR99I2tLg0Nqd5AefNFyKjSfUTKguFddU/mG0+lNsOdGQC0Ao2Jr+kgMMLksB8MjXv4TP3Pc72JOP4/pDwBWHOmzfM8Vk2oW8C6p5cWI14dnPvQ67du3VIm+u0eQfbwmHYobkhTnq72JLglVoXCQlAdWmDdofb9KNmXUestXrjhYUvB51VS3FPP3FgQqXjKhu6bbo0Pqglt1YjPkY5LyIpPa8O8+ET3f3Z262J0xlt24jTqfX72t8CILMrPUOUMTv4Q+yEf+DDF1Z2zDv57wYqoLfhJeDb3TMbHlwkESNYOt1/kcOPgmKs0TB8E8bw7DBKAf0kl80M9h7MLRmdaXcqNOt4OsPfwkf+y+/hhOPfhkvPlDwkqcnHD40wbZdE9NGxOzhsR679h3E5c98nkqtOaTGGsnKpPTUrBttjECIxyhU8e0lICvnQnhtHrINnTCm6QGL21hXD0Y6E5mGXTMTX5asWxtryxa3v4S1s1EgycuAp+ZlTj4RwmqyOCe3mI9wYe/dwBF/wtJ0SQHACh+qFx2bBB1XiVyGATg4VL0eEt20qbQHSDf45VyQUTQOxEYdklsaHGoyfiyy3Cog4s++I8T+1wHvRqEnxTbUakqsbYw9oJFOGrD12nFJhYHcvTJannjiEXzyE7+Fr335U7iITuBlBwu+7dIOe/dP0E2MCj7yVI/Tsw6XXH4VJtOJsaHzUEW1a0dsTrGFAwX3Ug5vSkh8BWFlRm9j2yKgg79vDMRi3zjBpLH6Obrh2ljb1l13vlAVfh8ePi6CM5qu3n4OFqTKpNjf5tgTwLV8/B6KVhgFLPzaEhkjwmJKAUqWwLedmXsyxkqxg3a1TcxkquZO0q3aJdvmQTTlWZT+jDgkm9FWmj/5n3ahD39o6LJlWcM3iAHgrjvtH3wLIjDcScGfQQCKv2Y6WOIqnjt3Cp/5zEfw5S9/Fs957nV4xjNeiP2XLOGzaYInnuyR5z3OzQseP5Xx9AOHsGP3Lhx/svFuLMQIm+9uFzQpm2IGIcfe9eJnKVInHldUkEB1UU1yx9DlgkJDYbC3jCcrcxlcFz9ACQIfdy22dfbKQeb6vXbV+Cv8oF/tWPuNBVPZni+QlUHaU94aOKM6bmNZpeyyTFoHXwGzEagZJGsiLHdSJacVJQMNWfmYeF+F+Cxy7nnpeNF3bCRtaeZg87pOO4uAOJW/HmOIogo30lpNZR5ikPu2AQsVFCC+KzjF2vyrENRoPxlPHT+K+z79O/jkJ96P6bnH8JLDhEMHJ1jaMQVRwlNnC7rpMnY/bZ+aNa1Gbp2aIvhCEmIxuE7CuIsdriL+cGFX/uwEs3X9moD1h56ZarG54/XYZnY+qWn1KHDeTDJ/gffXSH4yc2RmqN1rbClS/ejbiMpAGAajPysIma+MTGQ6nWBpacnOtmzMkRphrLdt4QV2Ajc4NKEDBg+CKSVMl6boJjUexWxtrW60Il6X0bTpRtKWZg5OL6vGls+Vm8phJHa3t28B6zxBawKAxEesj7wvNX8Hp+EsNcLHsQO8luMeFVPHdEKVzCRBQQvw9S9/BavHz+Gl33kTXnbwInxle4eHTiTkad26u3vvAXRdV9fkKx1fp7XaPQwQ5lLZhH3nnadi7xa+URyyUmYn0AwkrWMwvCwY3eP3yftKqV0htngpHeqOW5lRMMEnaVC1vY0RyOYoEdpaDAE9jywIgGSrJeF+WzVEU/cASJiAC7Tkx1h71mUpBR0HqAWgW8Fbq09NtGQbpzT6tjt/ouSMft5DMKeGozPnZd9X5TGZTNCljcWT3NLg4LxSKlwEW5o6MP7tweFnwRMiF0IdeviICQWFXAg8IAjAWgesGRlbJKeLro+ZNyceeQKf/k8fxtXXvhTPu+IqPH3nFB0RVk+v4OhDX2PB4TBkfuFOk5sIXACP4tqMTKiLL6R+iCaZ1DsMeL5f4knGOpumdAq6fueYn4Ry8+UupdLjeu/QdBLTh2tS7e7JhLfac5wG2WZdCtJ0ooxHZg5yKdrXSUGkvii5fldfk5pwdt3YTAlaHZCFR3Xfh1/3IsJrjIZBTMwH141i8tU84olb9RSuuQvQw2eaoppl8/kcBIuDuZG0tcGBk2ekavk1FKrEf1wy7723LUnycO9Icr0V4a4Au2covPuNswjUt15zn7UsFARRj4x35Xzi9MP45CeP4fLHr8ZlVzwXBMKXv/hf8fjJrwEJSCXx2QRWb7dhnf0E8gJrNY3arMBQ+PyL5lZrKWMWyQLbmMA4YGoe9uBjAuVbl4Ep9JGcByn7AuK9XnIUtFKSo2PMtEOvG5H6vq+eftbYKdVoUXk+Y6biTsAmV8dkZVcI1b0lXKq2v0eCqvjzMfu+x9raKmQ7dp2lqNOf9T5mQLJkPHsnZAmAJGEL+5wBNiU4Bjh63lVaFWCc/l8vbWlwCHag1zbe4BAzrbTfNHlByT40M9f4gzUNDBw1XiCBlqpH2MyTxtTRX8ONL+rpz2YbtulcXsV///Kn8D8e+CxKKZjNVpUpgJcGi7AnsP0asmEg0PqyqIvQiuCpzW62rW/cAgd8osV5JqZIuzTPCGuIAGGtbuXz8/0t1a/Xu64O+cA6HMCaTwK6BySakDXup5wdmajDvO/d99bfdlK4e0djMjACub/BRJQUHFr/iVwTDR+m5JMfb3XNQu3vGeru4TiDIf4hMU4TrA7iu5BVmASE78+Xtjw42FhrRM5GK+yO8LHJDH6c6iVwzEGxG40TA1AHV4duksKwLyhuw6JRai33iA0RgKGIpmbqzyg3n6+p+QOltlGYiYDcc3yABWaVvd4DRm03Kbuw2vb78G6l+b4Bx94GnSWJZkXcfu2BQMygaGa0JXLAoCxCFkoDFkNShC6FvGY9r0T07eAVgR9fg3IUBgKooLbnUHo5rOsfOvS8+UoiSoUTuon3j2RjBtPppLKeUrC0tITl5eXKPOY9Zhw4V5rB2EpVNjWGhTlhfZTr86WtDQ4cIQcQu9P9bgYZMNTa0f7mf8LYIw5cQorWar7IirXkTu5uENmRY75ArO1tKCZKBgoFA3CodqYs3qJghbDiNxApqGYGg091xvqBcD6NQbAALlIDaztyswXtiVax4UZAogBirwiDiXBiDtXW5xCy8YxBQEq/K/a7mMaO3VLXJ2hwHAmg0zaNt15cOa1/hsrIOxvlXjPpKjDJ6kUxcQRM6pZt21TW8/Zq6i2/6WSiJ3DLGo2UeZarFBdYVtZBSHTrEsq+0RmLLQ0OdjKyLE4pjp7L4BtTf25IVciP4OJvZltaFvwodeb7EpmDZ73xJcIWpgYL6vkXcCxIscE6MjubMcRa1L/tQREXSlR9Edm9X4XASkaALSGXf0giM1s9Eq9psNWILTjIW1pptj9KcQFb3HX5KAyk3jM+gP20reQlAIvsBFL6iIBE1TsfQryzcAcH67D0Vg0VqKiEtB2pziDlIls+6wiUMVNQ1y3M5z2m0wkm04nbP2FbyyOwVHMCQD25i+SU7pk6MYnqorxcYlg8WfBkYCu+tY0BA7DFwYFEFHh0yRSgCpb+459ZkBO5Di/x5oLKFHiSUUclUcxwsJ6BjEPL6VPreYPqFNwwdJwuXgLDix7/NlI5Yg2fE1IqKBwJiQIt1pZrGiXmZ0JMZk4QBuAgQra4au0XsX8C53BlXD8PZ55IXaQ/MnSZOFD9FDYz0AW7XzISoRobH9YfI1RCQFkZVaqH2hRAnMvE6xOE0ssxffUAHTmr0wlvce/lOmmsyjoYkcmApGdnppl7tS26yQSTrrLd3NsmLBqt5TBtaXCQIRYcOrSu/MG0rA4pmJQX/RHtIqg+KxlTPjBXlt+G7JRJUAAIZQ5sorTONgChsyjxUfMNytfB7aehAjfSXPziJ6IE6oylSJ0Wvdsnw0hxyI3dT+5fKedodvU+Ih3gDfwtfqgprWhA09iaubZ9jxi+bT6f2/SkA3ViutJOUbfJsGEcPGThU3UEd9Wm5zMwijoLRa6znvuaeYbBLBUZy7Ev5V81ZWFH9cmp31m2mVPd10FdVTRd16GgOiLnvH5ng9iwtcFBttUCcBUmdfgJVdXpnhKBBEBwUOliKDi6Gb1nSqtlT76eoOyy9d5zkWHT80ZLtZzsxZd3JUrIGAYTtXlugn+FZCufsz9Ri2TxjHN2ydkecFrEZWZNaZQZ7j5P7eO967EH5+BzZZWpU4M4zyuGQKQtUaQcYlpCTTD56fu+hohzWt3XRWYkQITswMEzSG+g1uXv4zhCqMDeTRJAk1pHkrD3M2cm1vtz7qvQNuUZx8k4SyZjOnFgmvl8rmYSUDS2Zc6ZF1bJWGvbdP20pcFBDm4BTKMlIhRKHA3YBNwEwxqotZnLmEcMcfpJpi7rdLLdK9qZQLYIqABuysLeowPFdL4ChDzPg39oIxKozbPIFCicVpYysBDLtuLOIhnDbRwaJifFommVaQkL8HyCNV7DpPQBHeCe5YkHxl1OAGXPsDzKSnO7WZpSeO1S4anLCgjzfo6+r1R8Es6hsDKDwAuOmvoX2Nmj5ALG+tZx1/1ziRLQEUeKqja/LFKrTVHUV6YxI0V55ergztKRLYMgAnVd7W8xU1B4SXtdwp1DGD1zdMvzGGGPi9LWBgf/N9MtFUy2PQEO6jkqaHxr+5137LhVc6XU8w+qMiKz88jExIQoTvH5N/tZEz/Npw7VkcHq5BAA6SrdYKMOWkWum0YnSnXate+R0budhY5BCKgFNuT/admGA2G50hSDGnvCM7r4ks2l2l6y+Kyo+STUW7Y2S/mSrj2QcrcgZuXPpSCJMmnK1gJDu5aimi3OxEyEVAjznNHzSsauSzpLoVvKHVLa9nHzh4ii6vu5Oj8TOzi7rsPq2lpztqa1vYTP3xg0bHFw8NpLpv2EnrfTNhv10tYxQvV0JEdTvWkCMQkA8z+ISTA4Uci858IsIKd1j2ieUXAQWQw0Xx6AE2gspKXyuw5cUrBD6SFBRcK8vic/IOg5iylqbb3HazdollbEFgf0fitfbSY7Tk4BZQQ1fBvomgNuAAXuzCZDWBad3HMIfQP9BsqEYgsOy9Jgijk+KanTUKI/ZfeeUvhkdP7bFirRINO48M5mkkpxgWd4MZXs1QAw2J6t8rFBFN7a4ACjd+LlF3AwFtGYCU67rbdSjJywt/TPOyRDHsIaksw68OYgoXhwYtqOKhoHsDGg0wHkx7Ta7iON1P5djEmIXe1nIjRvpcKiEVvzyJhLobgt2psl3gqyBUkGMgJYyHwc4UIzx7cd2AI0kBHjRkxDGRu2pN2jqOU6PiXr3tyAc32uBQ55LgK4+kKKLcbSps+2ijXkze2TUsLSdAoAzociG8/iieHTpWktlTuz05fBt9FGGdqWBofWrJAkJy8D3A4uUrSS6MAExpPc03UJffaUbygo9V0iAVXgMlNeVRiluLOonAZuytFOZwpAyLWMHEwTAQZZ598YCoMklNoYM4mEWukUvJoDdRVv47SxBKZtPeyamTsUJqlztKmj22thZ0RUMAbG+opQMbr6DdrI1D6EfGJgqCyCtP56/zom0Wgbqh/C1m6YqTL2gGtHpzC0edx4ShxWv5SCec9nTbgxXQqqP4VIp2nFvJrN5/VIRLD/TVsKXMcNIgO2ODiIMUFwu+vY0eCnjxLVqaaq5dw2V/m3mFiEQ2i50ykROsgKNv6qmCC0mjXz9FI0EUxbV5o9QpcH1oSQ2ZGAIVH8NHL0IjO+iGCQAAF/T7ZPAe6rQLakHMIQRsY/oYT7fNXkaHuAIz8r2PE+FN7noO0dyiezDFUgpJHatRYoRR15yrY8OPO1vjetKs/59Q6W/7COdt863w0+m/EYFlKF9xiw+lmrAqCfz61sPOZ6tyOzLk6jsBxb2LJglbI/7uA/F2ZFTRWNk9vA4ueLLVl0Y9EY8nj9dixrGbBU9zYhDQbBoEOL8yQHW9jeUjvNa2hYZ7pq2Z8jC6Mca6gDoI6CemZDWyP2AxQ/eUm8pkLJeEOUo60KP67JDWohFZ6J+fblNkrNzkZ/OA1P/Zg25jqJNm/3K/i2BHx4OgPv4e0VnCVYzYKbvJ0WmF0YSQXrfOeYS27CsjnGVtx7rCtJTSMxd4oKufknKjAIXhTdsAfwMuzeHbirYOuUyZ8Ls6LYohSdWvKNzv9GT7JrcHd/cPIh/sm4rp2hb1AfRNTqw4NXTEvYOPHCBz/WlQ0pcI2MeNEcXssAsJWYIUsbwgNw47qNJbHpYz1cnclaWeFkrKy5ABJfhG8UO1z6wAuZUmChxcW3X7jLFEKObC36Z0q4109Nt6WN/oXYLv5eA4gh+AsAVHAwX4M968eQNZmxOJcnUehTDZnPd9XzKKpjUkLY96hTuVWxxVD0i7BzLG1pcBDnH3+oZxCijO418k6y+q8blITFHdhSfQcIA2oLDAZn0MAjPVOcW78FibGytMO5fXdsn+YvHnNjZWtKFYDR521NZELqqfHY+ysQ5GpLl2p2RWAoatJJkrDutqOwNTfcO0uskzdZWljz/ewdlOTusffFeow107iJYd8L0LV+ibjeotQdq14vBbuOASIwUn4/M6JM2e23YLYZtRt8v24kbW1wkK2u4jFIvPikpdRqb4kwujURZQgMo+9S1mEDU2w+XXnXqr/IJu26fF2ARUtyh4JsgObzQUFdOCSaFJUplGC2+L9HwIpcdi2zGS0cNX8OgWFYGbsjLkbjBvWgo0rbAacs5nKC7Sl1BQJpNMci/PuL7dCU9Qg19JyB0FiVlaWtU7tWN1cnJ3jmSvxd4ndymwWdMvHbtMea07NF75wkqvXMuddgMMLsqtnm2hrjSmosbWlw8J7mGs8ROrDE36cDSgFCpbs2rMK7JP+hhEFqLMEWRUk5wjv4UZ9NRApYVOuRo+19/TbFA2Eg6KtCg3qFgnkDDIE1eMDU9pRB18hvKMP4m0RzCyWucsItFpaEKzo0AzmusfB+CzuXAi5/v/gLmp+5HIjDdRSMejVsqKybWnxUv0BAXdsMVvQeax096s6lxM5bARPZeenNZKkvFcBHIZtMJtougL13A9Wx92/iXrzzne/Ei170IuzZswd79uzBkSNH8Nu//dv6/blz53D77bfjwIED2LVrF2655RYcO3Ys5PHggw/i5ptvxo4dO3Dw4EH8xE/8RF0b/k0kjcXf9+hLzwOWF+y44KB6v/zhhMYvpIJ8JmEDEs3a8hKmUD3fvQUxLbbKzQapDIA4aGNhrFD+P89+nAtxgF2qNVUK+E6yvJQ9ObA02uwpyDBp3cfIQvMYaRnbIehngIpq0eYW+8MBwODrmgWKzOcXdwakMy+GPoMhYzLtXb+vYNMuPxbhWoTSxABn6zv03a4eOq2KWPe6UnKCGEXcxuC27duxvG0Zy8sW5MWUVmyb1gFuecVo3RsFiE2Bw2WXXYaf+7mfw3333YdPf/rTePnLX47v//7vx+c+9zkAwBvf+Ea8//3vx/ve9z589KMfxSOPPILXvOY1+nzf97j55puxtraGj33sY/jlX/5lvPvd78ab3/zmzRRDk2mHog2TeEmqnPrTksGSea97iYKs3wdnERl6L/AvZLfoRMKJjxHQAZFwby6DOwcSF0HKM4OyWIgGeYk2RhnIZribEOqpzzqBo8FTDoRU83shadrE500jI32kbICBrcQrKLr+JAJDNB+GAuLpf9Ww8pMV9M2xHIvamiZWPWOWI69ypglpXhZ23wLB6BQlOylmazPdTGXNRK6fLPiOsIz5fG7LqBlMxoF7caKyGBI3lPbv349/8k/+CX7wB38QF198Md7znvfgB3/wBwEAX/jCF/D85z8f9957L2644Qb89m//Nv7qX/2reOSRR3Do0CEAwC/+4i/iJ3/yJ/HYY49haWlpQ+9cWVnB3r178f/+pTdh+/Zt3Bm+gaADR9YIqEDnEjRNaAxnz3r09ppZoxbnemy65CP7LFqnkTk+hcLHUVM0zwVnTDappZSaJ1neQ4ejOQ1Nu3gFdn5bVFkGxfdJ29dxSa4M0Stcj/WrwVD82n9tc32PURJhCMM6WB5S/+gErvZ3DPbrhS7p9XpvaYSvsElRFxnp0nGyMrRtE9lIMwbEN1KsTrJztkt2aE87YyZrPGazGVDqWr6+7zHve52dkDM7FdRKDu1iBEaYb8KznvsyvOLGH8SJEyewZ8+ehX3+TR9q0/c93vve9+L06dM4cuQI7rvvPsxmM9x44416z9VXX40rrrgC9957LwDg3nvvxQtf+EIFBgC46aabsLKyouxjLK2urmJlZSX8ANwhjv5FJ4/XzaT3K/0vY7xhPC2akUCxuWzpmMGzXpBG9HrDMmHkfHh/W5ZWu2uNVGlHam1UefjO1lpH+Mw1cQBkb4wa0I7IG9Lrthzyt13zZfTC7vpPpweteK1+0yArrgweGMwZWXhhVWzfWGBjIfX7lv6vD6rZ1cOzGFslmpHdsXYGPrxoa86nVeUKCrnYShVhG8I4uEtci0HHl4DPZkLTbxoc7r//fuzatQvLy8v4W3/rb+HXf/3Xcc011+Do0aNYWlrCvn37wv2HDh3C0aNHAQBHjx4NwCDfy3eL0t133429e/fqz+WXX16/ULiWH2kJL2L1hjqwzEdgy1GdJiYEX4VoANUC/L6ca4BQH5jUzyS0Qtv6Lc53nb9U2jj8auT+Vq4BL9cOLMdu8tTcbHBfFhV4XpEXyiBm10jJoruiZk78oiEQGOiawLVtZD4Lb1L651szwOJdGoWvwicLrKKJYVVyAAdnRmxAuoh8hCyvhLiclmtTR+8fMlALwAljJ97vJQNf8k2Jwmng2nYbTJsGh+c973n47Gc/i0984hO47bbbcOutt+Lzn//8ZrPZVLrrrrtw4sQJ/XnooYfC936a0aa0TAvIUfHehhxR1tE2df0f5pYZfSeTif5Mp1NMuslQ+L12d3Zq+/1QoiLTGA5GA0GhH2E6TyvoBd9LnBM0IAy49biU1sdRfNNQznYvMvS1YRkQ2mqwkDch0sxpVyIJwhC4TC+0oOAZTOtvgJqALXuITj0DHXs8Mie4ssnf3lTSv0ptF933w4U1sBo2jYTP9wLt9B+z4Hp83nw+NxbG9y4tLWN5ebmOz+kEKXWqGDeSNj2VubS0hGc/+9kAgOuuuw6f+tSn8M//+T/HD/3QD2FtbQ3Hjx8P7OHYsWM4fPgwAODw4cP45Cc/GfKT2Qy5ZywtL9dKDpPYrZXucX9q3xI4RgL7GaDUSkbacLyqMcK0tI03SECdhmzo/CAjP2BG2MUYWPj7w3VTM0545At/E39PXHMPEG6ohiccnbcClHCvt1lDOYUCF7+bUht/hL465iBXVPgo4BgIvLO9jXno2lDw2ooR6jE0AQxshWYvYm6ePY61Xf0utkX9TFofYx0Gwr7PfNg/KXvdLEU1ypwDXF9pLU0BR9LuLfpXMYYHNp2ICB11oK4epLNRu+JPfJBu5ph41113HabTKe655x797otf/CIefPBBHDlyBABw5MgR3H///Xj00Uf1ng9/+MPYs2cPrrnmmk2/W6iyzBrYwhcbNeQ6SwJ/TKfTSre69kBWCwLqB48eFsv3RBZSwnu9P0I9B0q5HT31wufZg6OTep/WY9AC7ic2jPhhxmxeHVlKPtZBNvd5zIkr163uKgrORImU3Ypewo+nzYqFxfwMkmcgJW2ZHQBQ25Zeq/O1sRkCavIw0Gl9IaHJR2VOTCgDxYqaXTfBZNKBqAYAluJLf4UYIewUDZnyT0HRg3K9QuuSi/hFBoh1WfX/BOZw11134VWvehWuuOIKnDx5Eu95z3vwn/7Tf8Lv/M7vYO/evXj961+PO++8E/v378eePXvwhje8AUeOHMENN9wAAHjlK1+Ja665Bq973evw1re+FUePHsWb3vQm3H777QuYwcZSqRwraLwoTEIponapglvA58brvQW8UIaBwF7idCPFdf/yZSnFCTONDhgtlRNWKhIqDkFRWT1qOYsstV0UgVqueJo9qsXt5sqGRAOTDeKxfCGLe6hhNI5xQeIqFP+gAodtZfcBT6SMLn+fb2BnpGVFu8o1SKnZ79oQLpk56hcXFcsr1Nx2ksqrY6KBzAVAIqlCrd9k0mkUKOqZffE2bHE8Vp8Ch5cfp7lWPG58M61r/2RkjfPhdxVvJG0KHB599FH86I/+KL7xjW9g7969eNGLXoTf+Z3fwV/+y38ZAPC2t70NKSXccsstWF1dxU033YR3vOMd+nzXdfjABz6A2267DUeOHMHOnTtx66234i1vectmiqHJa1ZAxgULUaBv5BrWnUrE2qulhxRHlGv7YsKTkltyy9RRmV99flSTyEWK5oMJPQxwBDhGWQP4naS31oFhESPcW7VtihtE1igibOMAYc0R/Q3KQLTIBqBABTxrP7N1i2NdNuYFsLkezWYpD/BSKFsmXvTr1qfTtpfPxzMEeZewRw8o1nasTEaBwCNleEt4L8H6KqXKHNR0zbalfD6baXkIbqNY0WGhbNTBJ7dJbeu+9C7wUO2FtEGTAsCffJ3DtyLJOod/82/+X9i+Y3lU04ndJQee9HOeLnKKGASOxmMRpPxiEiLTULkxNVDqiUKeUcQRE8FBkV+orgcGmKC4x+2eRi7iKr72uil1q66VJYLCUBmZGWNX9OxJIJhY7h+oR744RuSSOBmrmdBrbIbAbmCYXAWHVFPLeaBFAL3NXV6uuOpATPONZoP4q3y7RBNC6teaG5Zvm8z3AD341jS2jIGa19J0WtdrZHGM9hAfg0QIl3JomxHQpS6s19AYmlRDF1j8DFN2XnE8+7nX4xV/+fzrHLb03gpgnPyq4h3bt+AYBI/XQI+D8JSi500449mAgP+ug9ppH1cO//ox55gvUxjyRT5XzeEHZC2KF2KxxZXQj1db8mwEMgKJT41QuIaitrzN2zy7l/ZSBqE2cgumLNBBQFk4UUI+w5K6CmEowL5fW8bgStnkmON4gAj/YnMxslB2aEu7M8IKsM9mcxCBw9fPUcBbr1OCbJUvui4HCirEp48ZIzDzRYLWCgMpgB7puFkasOXBARjT2l6jRo0sDsYCOUXIjWLOpziRISBsJc4VxvlWzlgiBPP7RmM5uuTXCUQfRVNuQMtCXpJZghJfqwqhQM5VCGLLlFjCuLUFWwwM0l5wMrceJRWWJTk2rIbr2q4vAVnOdYAnBUXDZH6GrF9iqQm+0YfAYKAQtX8cNsYaRIBdH/t6jjbDWLlqq6QuOX1jqydzyRp1vFahPlc1P5+nqat87YTsYE4XA4XK8mznsJyh6eNJLkS1kbSlwUGnilyHWhKnVwfA6KN4cmWuOcspQD55UwEwQc5RkxQtg9G3nEW/jkuhNymGjq8E3R/YCHP1QfKAlWXBPBAMy8YhKZSnla/zpFJM8ww1sSUTtrhE255hplWyEHUn2/64+9rafmpuXOwAcUAbr5FxIP0xLOcwp/HZh2E7tOxhETupeQ78RK7diYVY7pCV2wW2Z2TSdci5d0F+SWOXqBOb6iE6pW1qVJClIjtVBTA2DgzAFgcHYHwAiC1Z7TA5hHZIJSklkIQoEzVFFPLhv3zuo9rWyiDUnuymguBgawfjKLVn+qoaOBujkfqpecG/dLgXMy8scBIPxsozN4EP5vm2A3bNqGiJeYF59E21wZkKTqi06HG6MQv1dsKuuSnLiu0VAKSVy9E+HQrL0JcwZA9iv7fvGDK+8USVAjiFxsPODESLBVnEEmGFkoRZVNNBWEM7prxMJEroIftQgiY5b/ozAA4yF10cojvq17aH2r5QQBhrqpaFjKUqLzYdJzahAZF7mgd71fyZNQcFwQkr3JRO828E3QgfQUrUqwIMD/I66KJ2De2yUYhgYKjvIGc6uFuknOG0qpF3CX12RMQzhmq15ersBbRvhSFSSm5hVAtNG67MgmvSPt6kWS85kFqXpTS3c3+HtTIQ4LSj+1Dk7AleqwBjDCnZyVe+HqbjqjlTT+DOKH19w2YWNm1pcPDOmEpB/cAlvUcPIE2Oyo8BQ+NUbPFF8vUTpSb4XutHh2OcWBXvcwFRQuJvdcbC3xcr6z5TvEOErx2comql3ApWbvXEyDND8inTeP49XAaRaEh/CH+QN7XZO2DgRrNFYbyXRaMoB/JfB3wpBv4tbdCyjwvtmC8itPIIhYsa1+fTtNAAGCKD0HKR/CJ7XVHsrV/zEX3Zgwa/V0C07+fKuKRMlWyUYJbJxi0PgBtNWxocAKCUGjuPSkKfzcEjU4O55BrKOxd0kw7gjSg29SYqwgGD440q/EU6B1i3gZ0WlOdl8HszpWr+jFzdivwsdDSpJtUyafZ6U2UG8mCdgy/tWNfMnXZE0VD2ngWM18oJ0+CT+yUa0JVVrBHAmQIefERQiECFg6Xm3lgDpHvEKUfGuES8xuwKuRT6jEsxSjho8Fx7ToRfx2DDw655EBplEFp90f5Wb2mnGki2+l+yFsQYRVMZflcFr7rikuqhvQWgVBlqH9biyJ8bA4gtDQ5C01U3O3XuF7RIbAfqqR5R1hkaW0Ox5gr5S4fVD+RGVmhecu/3BikZ+VWvtHtXLXuuvg/WzLm5B6gAKEDgSg7REx60BpTe16fYfVKaOEwiVxqMIWP3g9tL8WM5AgecQPg24xIriMuKQG9e2b6Yuoy4dQ0VafOFaSj4Ht9tZWQstoGyAQQg/h6jPdH3U9Yvii8VBxEiklgSNvbad0vjxd5xBeb75Sg8DR2QOhD1HGnNwsxtlDxsaXDwWsv3itfupOrLlsjmnNF1XQCQOtMwjIKs3eOAQTut0UDqXc+5drwUhn8MIEp4xswj0uPozVPf+B1E2wsWurM1jD04CrwAKIbJg4FTrw3zGHPF2NRjpMHDVzRX+f7MAUxC9KWgue2lmaSv3OHI5JgJv3wwW9AUQej3EDysf7yACiDYtfEpzaEZ4wql98S2pUIovYG/rCDV+xPpwUwBzBxASvChfm5buKfTib2PCNT32AQ2bHFwQOxMuxi/l1WQ1Tyo2inxhhdx3oR19vIc5yFUsPhBw9IZqW3ji9DnYaCjGshulFOKvEbzGQXKqnpDLlSwaCmtaVZ3rxsVopsLWkFqQcEBpH72ANDqsLFk3DnMHICZ3QgIANANUT5uwbyfQ00R80DbZ4Lbp2Ia3tpE0aF+M7YuY2FlTDnYojf3LcXP6yaCOmZr2Xka2487qv9QIlCXXBSyyiZ9JxVkzOe8ipKrXBdWifK0qm20iFsfHFBsTpyv1F/CJkSQa1y91HUopZ4nqPvoCXpMe0oMGnzeYIkv0860fQEjTS0dTGRrBPRvL7DeK85bz7EoUk8ED0coUYSRcH3rgiw2afR9jRg3xY57EvzdDgha4NKSheaJ37TMAz40HIGoAzAHQJh0E26+OtDbdSCemRVxYpISelT3LpkrZdCOTek8ALbdOGCi/jnR3mO+f8LoUYfuivRzoQJkO2SHMtVpR3YgErMFZaGI539arjKOnAwUf3yLG6WbQIctDQ5i+hWx1BUXeK05079JN0GPnh1etlqsBm3pkFJXd6/Jll0ARcNuxQUtMiATktH/RamUekYjXOH47wg8ojnrwCIkYyqt2hY7V/Ln360jQHUmyWBtBKBSmRo3IJSGd6WKUm4eiSVG+FYcoibQDWVHUbPJkeiQWRU8M/90UxLsjE6JLl7c6edEhJxyBYiAZJ41eOBrnLeOovuyDGpJFPIfZwvrE3fHZSCVl/UPqSQgFZ7NqusUvD/Jpj6lsO2MG6xJy3C2KJi150lbGxwgS6FLmHovIF5dxkCggGrTQ7bopAOoOnEo2wE1EnFaUVp6tLXZGvkda3bdJwDLy2vkApliZRYglFgHg7yAdFMNwdbNq1+iKVv0IXhm5fwh7uvCQEuFgG5cwGWZOGm5SvhuETCwrWZtJlu2NXJULU9BjLtY7W+h2wzMiZC6DvMyZxpdo44ndKBkuxh9fUdoTbxH+3F9wTHfjuNhizq+fYu0FyuN+qmaurm3dR0VEL17MppHMb9YZmNODgaC5pQCnz9taXAAoA4pwA1OpqN9KTpM1NnFwEAJ8NGqPVVLXQfzDjuJIzvWPAJEcfcvKCO8bAjYkBMacSTy74X9VzVXXR9BlTWJ00yyJKchgykgmr3ATpCq9+lQqpKvmosbNnCnRHKqudNCVHfA+vpqo/kiDKTIr/Zk4HIau3ebjqpJwQA/r174LEfUl+rYLDmjK4WD3SZWIItpvofMtnjB+QcbX2GR3ViVBhfE8KnfmQ9Axp49ZVOdSZ+I+S5GIadDKpAGx+UoxVk3bWlwWNRxCUCXEnoidUTm4lYypupjSF0HwI4m0w5nNSyaXr3E2n2mxeTdgBKLOOCKO0qNnAVQinqgq3fZ01+jI+Ylr9eHpsYiFJE5fULr6BOAqLclxicreWHHbXJm1hg9XzzWaPDLyi8g5hlGYT9D1robba4pUUIu9YBYmpE6MokFKVEH2eZccqlmoryH6slWtWkJNtvj2rJhD+brbNuvBRrfbrGN9Y7GYew1vnYhv9DPRMj0toGIG1kjbU9cPejy+dgPLfCeL21tcBBNCD/sPMWCxmrwh4xOJhMsceQpc+R4FhE7lIC6rl3ubbRLUM5SChkFQZoiQ5GZkbqTbj1u6pb1ZmFKpC8NOw2Z9g4KpfmYQaOBRgpA1EMWZomA5CI7ATEcVGRz/LUe5oSVRoigUuL+Nim+xMlQkKjXuy4hc/v2fR8OaJnNZy5uAVBKBqFjveo0c86VXRGBUGMoSptEcfczFZ5+S1UNIMwgHTbwIsAco//1OvO1gZPR8tPdvjbQR5Lrbw0ea74mfbNorw2mLQ0OnirXJEEvKmOglDBlh1bORaP5TqdTdJ2cJdhDgMHW92eUBrXhQMF72+1rUwn1MdvM5adJfeFrZDuexlTYb9IIJTQK7geCmQgDu79I8S04aY0vyQ4wl1MY4aWw2ZLQLksf3Mr/6LoK2T4um7W0Gvx9dlG9GWhS6dwcf43vKEArbZmd/0f8STIlKkygpx4dOj5guFR2lFoQdwhRYv+BXMsq8FL4iX0kDeFXqXo2GoHPlBnXLZdQR8lzYNb4fmovFm+EcJsK42iY6EbJw9YGhybZZpYaOUckhkDgmUqlyoUpqTggdaAV7wjiCEjScZyXxGOo056lLlN1TEH8Hl58fapfm+DCDaCxZN80K0H5S9/Zg87338kqTNkclTMy9Rp1SbBOl+7yr5wLEnIUChvDvgcQN4QhamnDnOowLqUCQErQoCbeRHPCodPOEgtBaAhVEzKIRqlRuuxARD4hi6cFiy8MREDZwUsUBMmnMcFyjJ2bzMxUa0ZDISEAkUUKesssRO1pXdEYytKEQETVKXaekoAUDByKOOGNrWwkbW1wYBptHVTXEszns7rPYiDMfoVfRkqd7oCzAWf5KU13lM9rK2nmLIOLO7in6rRLsgoTMK87F1znwoPV4Wlvgfs4Xn0/MqFYCDdk/besSaF0k5wDkUCVdpeC0vcO2Nw27RYIFpZteNULSUHBnM2ESbJsK2j4TUKyK7G4PrGQfQIQNXpSXAtK7p0lF8xn87q3RrREKJtNDwootbXxCqQddwL2oki0fcqwj+R9EmRXWQszIcqo6x/4Pa1zd6AcID4w9x6Se8FjFwrSdL5IRC5tbXCQJOYA6oDoObw8iO3NnnRdPlAbvNMpSxEQQOm9yxfwmq/SbFHXAgYejaVDanAmEwYVeKWWZJRAhFXzaDqw7Uw34BQMVHZp5D647ysoEIlW4kKQ2/DjXtnggX4j9VR7IbbAIKkAWclReFOczCjZeZVO4zWazi8tLqVobANZ9wAO1FubtXCYP95v0HvzwIFHcY5eakEwzkItMi3EJyTxHz1ziADh/QzQ8UNsDnpgcBhp/cPDT01EZaGRTYR+Qsyn0R0L05YHh6Ejhw8G4SPPaof1FaUTr4LskjZ2HVSyIs1pU5e3nyoUoSCYVgNM2xDioPZOu0BlxbD1UaeJB0+G5ushQ0iy5CPMRqe/BqYJ58cCIpd4mZNrQ0dWvd8EaATBTbdKI+mryJV5QVKWJGBdIMIJ1L0AsvFK7W8HwGKy+X0xQAUVymT55hLGv2hmYRsdz1IRvCOybbkhyC7y9Jv546h/c5BwME8XPe/BV9HFHMIV1HsDHim3r4QAvlKn4sYGL6oarcUwbW1wCA2jl/TEaz3UA9Aov3ISUKJkJoM+bYKgc+cuXqTvftFMYspUBeqaPfQgBmJrvBEoBA4ZLj99ZBlqXrRBThguHHvwaqG+k3ShlF4NQFavyqExuklnoLr4XjlboxnjnrktSgJm5sOR8SttbBkQ2FyDtT2YKQgjaMG76zpMJ1M71anUQ1xyycpUSjEfU8S2CG5eeVeZi7M2Nq1tdSvuvmEucWzJ7Fnu3TLxYkrJUlHlovNMnGXFk2EQ3NG25wdJ+/b8aUuDg19JB3DH1D9sV5/8wNF1p0msM4Ze/kQEcCdGrd8yTwOIoPVYWAkY3XRVpxVtakwHGJhZgJHf2ftuIrJpDb7PDxJnboXiCqPQQeXvInVOxvxMk4VJlVGWumCg8tSpnuso1ZOaMSMT88YzMBEg+S3nL+S+F6kEAJv25JZV56tnCYP2AE93cuk9kwqAqxQCWngP1Aoe4vT2Y6vepYfaMsABBgbKDN3Y1LeW2vdGKD3zcRVjALdgw9982tLg4FPYoFOKxgeweXT5EorYnjKLM0/zEU2R5VpSbafY65mC2Q9QveLk2jMO+avw3obAVlsT5rxJrM/695g54AdQ8HXI4GpWECYXiSgmigWTunnfzIgEyqUEE2qfh0znEQDqeI7BUNIdL+9MH2/uMGjUuAV8KTXUutAoOAhmE8iBAV9rute1gnE47T+bAWutD2Gg/sDc0vQVMAL4pkXUjyFlrUOysig950Jydgu9Ql21ZhsbWVsfHIJZ4DU3f4ZpHd/0OWeknDmsfDxwtSYDja5LPCPhG3YIEOYos3dXCmz5+USEJky90xiquYdplBaaYg+GRR3AdcAI+IkG8qZq4NBotU501AaN5swQQsZ6x/RJHl1KKJMOs9lcpxbnRTZQ1cVNudQzHJCK5+wKWErNJZK4Fq7e18mJ0sZLmIqX0BXFGjsoGM/m6m85fZ3c9/KXjZVad2EOMh7Mr+IXngEGfDJmh7MRtZCZG14JaFNG9WG1ndT2k5jTG0hbGhxUCeWMMM0LZ2PHX0rFpMPI5QMSSsdP6EOJ1+eXSO1YwkSbSScER5cHj1B24lV+nZD8de31WvZxAj8CO2Y6+KoFrd0iQ/27FCYSDijINZI5Vk1I5Ou6xFkEwYlPs4DKwBghH9H0fPar2uVmpsl0ou3GTEQ1FJqAvxM2iSAl6yh63qYv7SjfD1sPxooQqYD+pSas9YSZEXJLXMRk5k08CkEiTUu5ix+/7r0F2gzMIoQVjTHNMNp0RHiT7Hxpa4OD+1eXFWsHFPY7uI5wNL943lia4U423y6MQxV5CY+5E7ahQCFHq3svv/dbSAdNJh10lnoQ7l00wgg9bJlIqyWar+OHMfUShTkOcKuHTd2OlAHW/IFlFKuL1t1teJPnkixQKkXPIBUml3ndhQxukQ6ZwRBmaIfyFp0WLShIxd6dc8ZsNtPVlw6Voj2vCGFltxmTUO3ASlTpqJJx7SPPemYpdXSbAj2i25AugTVoBmOd7/MPNw/D2K+XtjQ4FBsxcpQiCmq8SI++ZptaY8mgl+g6cZwzSyj6mJonYTEUCLqJxy0Flg1VKfnVcjYqdJCHy0I75SLMV+K0k9LbsaQCKL/b+0pzcwmfiAPdoJRmYNd7ZRMbEYXlyD7neuc4a/BAIyaEDFqJfzibzZQtiMmhRfFOOmcC+vBpYt+LBk7cXl3qNPr4bG0GWiYN8MNZuzc5LRIa1gG3bxs1X2RsIJhWZpo4c+M8Atq8QR3a6+l8KVvLOnwdh5xkcdr64MBJBLzkuo1ZjWoHtwIGhZ04VUjjEj0vLnWhkHxlg06mnWzHp4v5x/Zhx8ilaxCqBykKVIv87r2ePoZvCXq4iQmxgI7Yxl54KjfJMJCqh3y1voGqJRNQj2ArfmDXcmQ+Dp6InYaEBhSs/L5UosKEFicidN0EKc15M5ZrOz5+Xl7uV7CG2IoOHETI/dQ1AAUG+T3pJigoeoL1aCrsKiS4k75iB5Cq/8jefJYpSTi3EvpD+1RYgYwrP/KCCefat33t+aRcMM4Vcz1wadMWB4cSBoNS0tKgI1UR8baWrmJzDe6pa9IHvYSKpAiVNMCQ90vKYgdTXIvgmQucwEbrwRiJ705dCINFiseFblehjqHJTYslEGWXj9eWxdWJwmdoXeJjBsDMHLyWc6d95dwDKaHv5zpDUbi9+vlcfRayDqELPgTn33GUO/qPyJZVpxQETZyRicFk4DBkoA2yp7EaSeseVpY29VcOISaGa30DlZiqryb6IZT5BrLXtH3DUIapFk7KrNxmg9Rha4ODh2si1SyOHNav4DSgfFfq8ehdlsVQdm/NzlFAflj2ZrSLbyQ/e1+cXjRjwrSx2ZoFcAFbJAfFLLEriAc7fN82qoTk7bEussBJ59zVJCg2xosBSayXBTJNPO8qMwrKWpRWu7IFAGGAyRlz9gfMZjPV5n5LtrIEEdycqzCLve/7EC6Izzq2tFyXEO2pY18Pb2/OusdBfB2p+jWJ6jGEDJg+5iiB6+8igeuMQynw0bMJ0cfStnHqElKXkHszh2ChLQbNGehcGBBjvEBVHsei3Dh32NLg4KeWhEWYUwqm4R2Fk07JuVRN1U3gsoGeAyFUwr+rHnLIg2g4EAfNrppOBoPXvjJg/HJhqVMcEiTo5sjEmNtBnJv8lNJ4wLY6F5R6PqiUhrEvt6dfG0yqiWNLeC1fBb91tZGbIcr1sNh+XmcO5mWu61FAxMfH96qrBQBGc3W2e3sPOQGS3Y2y83I5dcqQWHSRYVGwqfQosqeT2Ewi8x/J6eYVIEooxwAYuO9kUZSW2zdZMT9OyTVQbk99VFjKQn2rDu0MU35w76uTOMp6NogPmzk6b5B+7ud+DkSEH//xH9dr586dw+23344DBw5g165duOWWW3Ds2LHw3IMPPoibb74ZO3bswMGDB/ETP/ETYQHLRlNKpLQz59yMzzidmZ0JINNcfebTsOAX/AgrMDuQCWVwginwcNLv1Iww4WzIpf6oSaFv5lIXYw0mkGazivDLXD+xXb7IURk5ibzIBrEIuvwtQ1dA0+fbdXVdSKDNo8BQYDWKSWYsUNyhsWRTbV3XuTBvBuracsGIpmDahb7g8qmfifPpc4/V1VWszWaShRaXUGc9+r5Hn+WnxniUiNjGWIsKoTIHbmSteYk93K7JkIN8pB382gxfl3AOim9j6Tsui41Ljyxw/bxhbPjmweFTn/oU/tW/+ld40YteFK6/8Y1vxPvf/368733vw0c/+lE88sgjeM1rXqPf932Pm2++GWtra/jYxz6GX/7lX8a73/1uvPnNb950GeoRYBML7Q1jE7bqDOOtYT06GHDisGzNFPlOabQ0tryLO1Gm5YjfU4p1skS4DjMp+m5nrvB7RTjFMZdYBZi5Ye8MMwhOdZhQ2aD1kZX8wBk2VzRys249l8FoIAA/KBfkIObRZDrFZDoNqx/FwTvpOkymUw3lR04wUteh6zrdVWtTh9YH/n6JFxFESphTFhCw4K5qnwvTEbZTsq66FWwQoYbrr5oPg1qOmtwYpN5YFRebRrnPGlFb2qod0zZSTPG0StFnrwZko8w2kr4pcDh16hRe+9rX4t/8m3+Dpz3taXr9xIkT+KVf+iX8s3/2z/Dyl78c1113Hd71rnfhYx/7GD7+8Y8DAD70oQ/h85//PP7dv/t3uPbaa/GqV70KP/uzP4u3v/3tWFtb21Q5cu4x4yCjcjKzOCQBmb5KAxOhJuJZBkekPTNwghq0Bdt5re1mwl/tR12+y3lV6ug62j0/xK6okYlMuNUX4vJt89GBE9Q6M5nsGVQeocA+N3IZm/kW/Dql+dESqKRZBWCsyoOxxL5AKZjN55jNZrr/onOMSECwS0lBwwODlM/awAEH2XtLLuhSBZk+9+j5XUl38kK1ukTHLrn+zLl8s9msPqdtCVUEKNamsU+HjCAIbEP5vQkQ+5YVF0yxteOJQrs7hVM2DhHfFDjcfvvtuPnmm3HjjTeG6/fddx9ms1m4fvXVV+OKK67AvffeCwC499578cIXvhCHDh3Se2666SasrKzgc5/73Oj7VldXsbKyEn4AYD7r0c/m6Odmo8rpSGIWhLEeEg+i4mcboI2nP6o9snnLEdkJAKP+gA4kGx8yMG2ptjPpMRhHYpokMynQdL5oofgjVSvQ/zRvR0HDM7Zd3SCvaawFo8lBhP04MyVUCQ58SGDCNQMP5kr7s2lT5cKkDEDMgy4lTKfTph9Mw5ZSMJvNsLa2FkAku/zFvKvfJzMF9N46loQ5+IjX3NSO7Un7Sp9SBNyRdhRTEcoOuwpc/JO8yehMpaA8fNu63tDXCsOQttwgOmzaIfne974Xn/nMZ/CpT31q8N3Ro0extLSEffv2heuHDh3C0aNH9R4PDPK9fDeW7r77bvzMz/zM4Lp0mkxRdbrKDiy/MtQLy0Y1LqXhzC8gDRePGBNtFzWl09bOdNFgp0AzH8/AkRLb60wlS0FBdscSeeG36afEANHUHOI81EHK9SxBOO07uLsGsynFWEmto3tPbBHEI35gjEor6wnTAPWCyVy4DaXNYisAfqpa+iulhJ6ZhTCI5P1OHkzkra6fpL/7vlfzBJyPlLmghq9bmiyh73u3i7TG/SxTP3bysJrSP8K4AqOyuoX68nhIstcn3MMzW8X6IzA3+dQAc9H+l8OEhpHI10ubYg4PPfQQ/vbf/tv4lV/5FWzbtm0zj/6J0l133YUTJ07oz0MPPQRABBUAqmaf8zy5t7W8LejpurYh52HU2MwIG2dRkzpRMIo8ck8QVKfdC5dLMtH8lPoiDG6fa2kGgCQb/pGaumYIoGFFFg1uszQDn5dvF2ZEovlb08tZIINkWp1YCRal773beq3RnVhT+rUKfhZCTBAgbmCSvCQf9U9IeV25iQjdZKIBZERzS1lrOfiYPYeUPlRdyRk+SGzum3lIaci2LcTU4/7xTKClvNJW6n9yzDXOkHh3pLA5jI6Z86VNgcN9992HRx99FC95yUswmVRn4Ec/+lH8wi/8AiaTCQ4dOoS1tTUcP348PHfs2DEcPnwYAHD48OHB7IV8lnvatLy8jD179oQfoBm02jF8WjOfIiROrpgMU2VqThoyUHRDjDF5C6myh2oPk86Hi1OyMoV60OkcOffq3JJj++Q/4YieZpvZ4/wfo6ksFMzhwGBIIAr+EQOqkRyUNjvmJICn2XvTRMDKzbQ0dQuL2MCsK+cB8MgMgi6vhjEL8RcYjfbOwShE/rf3WYhgWb/YDMKo7Z99KDheJZuLjj2v9X2bV6e1mZamECj0e5imd2UG+fZkDuGRpe2z0J9O+WwgbQocXvGKV+D+++/HZz/7Wf156Utfite+9rX693Q6xT333KPPfPGLX8SDDz6II0eOAACOHDmC+++/H48++qje8+EPfxh79uzBNddcs5niRJuqWENL+LaUbFWkNp8DipQSukmnwmxMBPq7dcCt166C6mLeyB4LE3IGrN680xUoYscmSvwjgzrD9vNHZ1cpdY2CrlPwddCKS/lj5WR2JSKDH9Qj3KWABagf0FhlHSJMIQv3QV6Xcw00y2AgOWVmBVakyC5khqpzgJDExBBHXylhv4vU15snouAAsFKpysVPK1b2kJy2NuD3bYJGUWlyYJ8EGNhUrHkm51uQ6/73CECUZpD6l1HsOekOMzE37pDclM9h9+7deMELXhCu7dy5EwcOHNDrr3/963HnnXdi//792LNnD97whjfgyJEjuOGGGwAAr3zlK3HNNdfgda97Hd761rfi6NGjeNOb3oTbb78dy3zQzEaTVpMkzFrdmiudIVGhDTElPFfVsEI7vVBoamxjCxbr76Gw/r4dHJWFMo3nTGWwm8NQtJnTInrSFO+KyM2AE2VB8qDkqWTflaPoO33lJPq1sfSR+gt7YnNDQ5IVIIcAMbXMSX0qbgBqW9TfIhx6rJ2wMmlL144An3ouvgbenbm8tKTF6+dznYqU1ZXC9KTfwgIpfo8wvclkYr6KXs4wcR3vek80vQCwNH8YGaEdZW2GTK26PDhPOfu09qf5mKqSA4j8DBy0bYu+Skw0IRUSpn8MAoquwtxI+lNfIfm2t70NKSXccsstWF1dxU033YR3vOMd+n3XdfjABz6A2267DUeOHMHOnTtx66234i1vecvmX8YN0rHDDwXIGUrXbTms3E9AqhuPzMMsg1yGU5OcCR/QW7+PHv7Mc+IDn4U6xYrvZ9W8YZ7ehhNrZxNQKYl41XVMgmmg2tZRyNq62AehppKLgAvsHcEPIcBDAFnUZPvNIuH2CoiZRgSNruz3EthbrQe6lNCxVm/NRll6LaxA2SLsLFPpmyEwoh5BKMDkfAtipvjZDvUlZAPDekASWMH4UHSOxgPaj359wjDJlCYCixOGI8Dpk62/aSKIQ8Y8j7em3mYWLixMLFnZjPvyf5O0srKCvXv34p3v+HuYTjueWpKlzaZ9dNWkCqlDbaoDcNv27Rxs1r3A0U+IjVZ4F2ZjYEjnaUzDMAUn2tlraECFr9mNl1LCdDKt0bFLNSfkkB4PDmare4YizMNMJJuq1Io5+xqqxchTYqYlgUw5+zb6CSpj0DD/qQMREMOWGaASD9qSM9Zma5jPZpjPe36FNRCJI7HrwrSjCO6k69BNJiDYsulcCjyIGGOxMqjWZyaytLTEp59VB+Ta2hpma2uNVVY4KA9PVTtnYAVh5zuS8ccdkqiueZH1E4LFMtQy97E8Y+PE+kl2qXoxzW59iqzjqWtW/FiJyUCS8JznXY9X3Pj/wIkTJ9R/N5a29N6KtdU1JJqiFCAlsxGDABRbGp0g+wRYewE4d/YcJtMJppMJIzRP9QXzWEKrDSmjAIkfhHafinNgC6aZLem8eslIuodjvN5WR9PudmsxxQEAIa4ANQwkkgexVwbvFdDQ+sHyNDkMwBz8IjBgAOry5Upv/Stce3L/ySpOHwu0tlGpJ2lPJsrmqMlD/DwoUWEAlWH5FafSGl3XAdOpLqaby1GJiTCdTlUbm4qwCoQx0LZrAWp0tsZWRR4869tPHLGt/iaY6anfF5dx4dHZIISWa4N0YEuDg1/A1Pe1oTs3710KkPNcR28GUM/DJX6GT12aThRZSb4PNBsic/Inwrfe58Cfyd3phel81K6wU6xS4ug80k+uWPUAlzj4vYmChl1WIR1/eeHyGV0FHn/8BGazudWav2dLpw5S76wjDH0kXBYxj/p5j/ls5pZwAzu2L2PP7h3WxqXoRqmSbTEUjYCxHYYDo9Pu/V4otY+cWVFQHZLyvsRBb8jvxclZg8oY4LvGpdoXoYOK9Vk0Pjcgn1L/EXAoBrcO/IaUoYKlXVts2oynLQ0ONUXcLWgQ2t1H4SZ+lu1loVyFigZjLnKUuTwoQlei0CqF9cJZ9CUAePGMfq9KFG2X5ZL5gBYrdZHDaANTcIMSGAcbuWXQHK2ucsSB8xfz4Ff//UfwxOMncPDgIVx08UGcOnUSDz/0oG2UIzfovSevKU9BbA/dd8D3XXfdc/GKl19n3nnPQlypwxRfzmGLt5kv0ND2YzWX12Ze4CR5yBF9opElZZ5VSaU4tkFwvSB8U8FGTFg/lTosQfuXv60uKSdnWsC1RSkZCokeCBHbb7z2G0t/ol2Z3/o0PmfbNvtgbpdkoI001zqQvl7ThgEMyZxG7mgyJCmP027eDGjf64HBZTR43YbT+rqslIKXXPcduOmv3IwdO3biJd/+Urzqe1+tTGB5eRt27txZzwXNGdPpFDt27MRkMlWBXVpexs4duzDla0QdlpaWsWP7DiwvLw/NkEW06jw1GFcK66chZV/8/lDO8KqNqebNlk7H0lhZWl7pByCGY4QGf5w/bWnm8M0Jw1j7KDEPQjq8y724cXit+7JWi5aNlX0IAosHQ3vbgqj2G3rcp+l0CS972RH85m/+//DQQw9i544d+H/+rTvwtKftx3w+x//12h/FwYOH8IH3/wb+2/1/iO/93lfj2muvw333fRJ/8J//E06dPo3/8//8v/DsZz8H9933aXzgA7+J5zznOXjZdxzBwYOH8Nhjj+L//nfvXrcMI004vCc4Whtbqqm3h8Mx2l6/3BxAhbL4PzY5RhexiNHyDAnaAuXxzaUtzRy6bjLQFjInrMtv4SIjKcUTuldtyL7v9VgywGxvaeZS/OlaZUgVnY0r1h8g7GT8nIDgB3D00xa9RA3V+ELtWXePfT1OKccByUrrSCuk3ZaWlrBjxw4cO1b3vZw+cwYrKys4cNFF+N7vfTXu/29/iH/9r9+Brz34VVx33Xeg5Ix3vetf4+KLDuKVN92Mvs/4g//8Ufzrf/1O7N27F8+86pnougkOXHQR/j/v/XfIJeMZz3jGCP32RXcenFJsOzy3XdK+Nvag29hH86xat3erIMXX4BcdkcvDmy7ilF0PYGUa08+EWeu6UaJ/8h/e1qLq05GZGz9ToouxguPX5RmrG/xeG01bmjkACINKptDm8znPW/M9SrsbhxFErqsqT4MB6mzkMWefy00z49+1q9k/EJxjPt92YHE5AyJQyAviAyntw3LR0Qb1RxDiBXmHW4vRlMN5Bgf1ld2DFx88hF//9f8vzp07C4Dwqle9Gjt37sT127ahzz1mszXs2rUL3/GyG5CIcPHFF+Oiiw9iZeUEvvSlL+Khh76Gr3/9Iezb+zQAJ0YFOTACwFacAjo74YHVOxmjOeahj7QexAfokDg1WUvHZc2xTXLOdeo6Oo/MObwI44LpGP7R0poDM7ZBC57m95Ka8ljTGRBy/e/yHTTM4rSlwaGivoQXl1V/1bk0m81BhDoTIXPCI41C7HwgzcPbjz4orcRXJOUige4WG3oycK3D5F1u/QREO0H7t2oqAS1XZk9HYE7SMIPlBL2yG4DAg1/3AYj3mmdCfOTnUKOiGHTu3Dl8/esP4brrXoY//OxncPiSS7G0tIRHvv4wTp06iSuf8Qw89NCDKLngG9/4OlLq8PGPf4yXJRdcdtnlyH2PD33kd/Dq7/trBuS9HZ5LiYAcB38ABNdm5p3nHilxAZk860HFT/lJvxTU7d5ycE7PsxU+H/7A7IE7yyln8rME2vctxWuksbGRCl8j/yULuZxSJsqp/XGNpWzGil2VxIBNbMLM2dJmhTcDpBMsCCowmUyxvLSErkuYTDpMJhPdgacdXjMK00EkexskupIeWTfesuJRV3OkWIf4IV7xhsuXfKRopqAp2Y5AOFYj3KG49QaDUthAsrYZMYG00Fp1/ljCV/KmeT/Hf/gPv4EDBw7g+3/gNXjJS67Dr//a+3DixHH8x9/6D/j2b78O3/d9fw3PuOoq/Of//FF0XYe/+le/D694xStx5ZVX4atffQAFBX/5la/CyZUVnFw5gdOnT+PJp55AooQTJ47j5MmTAEnIej5sxgsBC6i2tZ/ic79r8zYatmEV9XmOY+lNyRKBoXX4+VWg0UwQYBo2sd6j47Q0HdcCs7GLwmWS2CDBfPB11/5yOTl2KvtutLSExYVt0pZmDrJZpe/rCjWxEeviEYR16gIcWaMJe+bskdfl494lKwSBQOQMwQNtRehMuOtGeKUQMnUqA49g3GQkm3Z8aQGZU4hmdAfH1nz9tFvMQRbbeC1nAxA4eXIF7/8Pvz547yPfeATvec//DZnGA4Df+q3/YCDI6X3ve2+A1QLggQe+AgJw332fQikF17/sGo2pUJfCF8DFBR0wLq036W+CmRqBrbGp4FZDgGCBgTwF012YnEfJGbpWWp91Yf5cnYr8oV9IPrVEVOq0tG9zW7gFZSbe/+ingFsTS64p+LiKy2VZW2Km9cb5wJYGB1klKKmUGsZLmtNOT6o0Lc9HxUqfFe1cP9eOIUhglnivMXinyQXJnYnhSguj/qblas+VwRFxG0+L+WJRtuHYbLFhLSxZNJMJlNVt954dNRBrwTCvdRLFf9SX4vPQMpSCHTu2oeM9DyrQKYWdlZOu08L5o+w9EBGA4sw3H6PSn71ZUIGg481X3j/UuwVRY/WURVFANGVCG7p/pK4F0ONIst+z4e+rFTALpkhPYgAMWmfxfeQC3RzX9gUrJEd8zpu2NDgsLS1heXmKvu+xtrbGHc9DlyiEAhOqJY0eNBGzBtGWfd9Xm41UpN0oifTOD0ztwOAssvcaH3W9R9JptuJtOCLH5h9aG9P+sMEArb/ou5gD4ruKDUBCXbf/Iz/8Sg27J+2ZeOdf3OEnkNHY6PyNeNsLx/oUdlG3pgPdZFKZAwuvhKgPyZkI5huiQXsKg6gfKRxZoOYFswYxZbpJ3Z2r+zhQWUPp3KwA96FfNSlbuVvIVNBNGUgTbQciOV8lhieMRoq0KDON4vZOSP7elEoJHSVk9Oh7HwOk6VyMDK110pYGh+l0im3btmM+n2Hexw08JvAcS7JUSiVaI1Hycm3iV0TjZkNvL9jtE0IL+W/OIqC8bo9uspFySUHO23EDle3AR34H/l7NK1AZGcAyuIrl4Civ/HQdoeumADiMfJ91Y5jtkZATqCqadt2kOhl9G6Sq+XNhUHFNIdpdzqtIRCiOQouWltBuCkOe/iuo2XWv3cXcJDYbSqkrD9c41OB22j44dq9wWeeYjWy4MkVS3GFDvvlzKUBfANRyM/o74QWDmbDWNg8xMYsz/ayuygRzRkmmZLziMKVEiIPj/GlLg0NtsKz7KpIclprlWhncD0DbqWoV7phs04/Dab4qOMOpqKpNohHhhU/+MjaTIiLJLnJ48lc8KLWIsZDTk81scNGEDZGUwW2xLgwOXvHHfRotX+Hy6VkhHGOBauAXXV+QJCq07cok1s4gqiCdaLC9QwDGt62aBU4w1KckB98wpVaAapyRPkletW35mVIFUJ2T3hfgQIZqBug0gFD9UTARIsMA6ZmqjDUDAJtNEVBVZ3NxlhLjtfpGrLFCW1SQmiMMABlI3A7qUN2wUbHFwaHv51hbXa1+BonhMDcUroPSLYTxFFQ1k1AzsU8bAAhXYOjb7A2QJ8rwIlQflII6vZgCrQz30FBwQmFYZNUMGXS2remokZNF0HPdGMTfJSL0MmAlF4rvGZRNPvFAJtT27brkgBRNveR9ScHGBMhYnmpzEcz6hQlzKdxuAmol7H8QIJEoUTPe2KUtJODVdWzzD1mFgEALMvWd1TyzSE5gZlWDB6nwqh6o9+hZI6o64hoKnYYtxMfy1UOP4ayCdvrST4kTMbDlgnrws5moomAIPDvW1Ot8aUuDw2w2R9eRO+2qaGOIg8+fwCyDRKhh/VhnNJamS3GGQoFDtCxvrGmoXfQvNA3fannyd3k177TF6KP2SbBHTR7Yc6qVeDBQSSDq9ZniB6ie+C0COFLYBh5FgPucTUE5nwn8E2RaSrSmmS5OfwnIMXCLh0TyUb+Rs/EBhJ2aPny7rQ8xrS+RpPx6CNXc0nCA+pCMBXFEJmYHUaATAA4tpz4Ei+yUc+YpcwplsWrHsUJUTd1SCtD3PB4cMDaMyIOkKjk9+oCrRAbGdv7HxrnDlgYHf+S6rReQFOe261Sn2bdVgBLT5E6DchQ2MezI+qhB84hW9048kBcI0xR2b0aN0yIam8XZsRjJLbxbPnKZLN4K2yZO1eSCet5jpRjsITdGVUexrxUcGMb3CWippkKcTlOzRQYwkcYa0Ky0TSTjmNQ0kG95dHtTQRyKMqPhodi/S5bBl1ICYPh3hf4AVNBE4yYiZH5uMpmgA8fZ0HigkTX4afAa2i3UblzzO9ZUr4vKqBpe68gkYozN+Pw0XwkxWGRcMhjL82oSnT9taXDwNrEwAGtos++E5gE2jy3Um5QmWufUbdtVyxlB4IYuXoRJS8LkIlD9cBK1L7cHAl5xWYhUEA0e/Hw6RQEPEOIGF8ENVv7smIWGqRPOqVkVvWdhS9cM2uqEZ2UQJj+f7kFBKG/zIn/mhJ8NqO1oefUaPLgynxAcmL+XuwlsRri8iPNr1zPkUsK6CjV1ckaaTNDBZi3E16XVI+K+piCQ4rDUNtT2McblNb9nYUTmoGyT1EHrXer4ERNJAVEViLwLizp4NG1pcECBG1Dusn6w1jXU9VOAxT1oA6XOsRPgTtNWqqZ3ud/N60gdf/Uod+l0ocf1VidlAuiuHnVJ8VCIPLfQ+0k83h4g7BkFLLJcxOdh9zH1d5S77zNo4DmEyfkoCxAmMMSR0twnObSaVSM/u2eCGZBS1ebSnq0dLfkAOjsBfo8cqCx5ynUPTADUcZyZ5tv5lUKp+GMS07XTfAQQBJQG/o3MioS4rKW4ekpfeNXQVA92OLCaQo5lSQ5F2ri1VzeYtjQ4EGtbr3WElhrlMuEUy1dSEKCRRqMgUPWKrnnwHTpeOJFcNS2Cn0A0t+tApecwiijTWOSeG1PcgbW4Yku9iMCmSAWEnu3aRmSZuttAz9nX0sS1gp/V3lP8QVuqGSDUtkDsGvFhlGxRw4NJAie8ztSQ6U71Jcm7XY3CmBChlyjWDSCIGdJ5PwO/MyyzBp+s1onzOgJqBd2Etpc8UEj/Slj86hC1vpG6CA4nohC8ppSCeeu/GDGXpO3jKe0bd0pucXCIh+TGinutCEVY+ds0tafE0L8xIvrWpk3ecGJTzHblO5mAzB2zls4Up5db7VfcOowkHnx/CrTFjgxiWQCQ2f1j0OXHRCnR/JBMMtNRcygOJN21n6wV8YBbAaVLnb5dlmYTdeG+iLvk/EEN4yhFFwDJjlvxCUjSxUieNnE/jK1wDYfpeDMmJTVLdKqQQ+JLGIB6OjjV07YKXP+YWSDt24KExMOUPpezKyhVouqVj7QDEdWoolw3rU/DFtp2NT+QtLH72UDa0uBQFypNGMUjOJSSeN28UXFtOO+UcQLPIWilbxCQHCb8i2xBK5jLV/IRkODXd50dnOpwQUHM0+mkU5+uJMoW/Mvq90pIS3H+iPo7MSuopNuvBbGlzV5LEpfeV63kjEwJqSsG0EHrCbD5Z+o7O54R8u8YJAeu0gbyjAhGl2KcjMJ2N1wfj5ksY87BNkk/y/1gpiLh8hMvxEqU0Jc+MNc2TxV4vh8E9AJGfV1tisScjQmHmQu1X5QViAmBai4VqWfTXr4MPq/NrHEAtjg4ENWDVBKSCoTajG7uunhpTnEhUj1xKOkiHT1AZMRsME2wGBoUfJrOKSY5EKAyn4kBlcy6AIgH8obk6HJ8MURIS/blFEGof9cNaI4K14KO15UAFNLsEyUUEqD1c+rm9zDlbe+XUPripG3BQdrIU3S/ctLqye90Tkq4PDwdr7fzbAdT+nZbNrl7AHNY+9kOH5a+AME0EMdou3rRC2d9D+dfzOkpJ3enkvQ8j9bT4PPxfhcxq8huBNw482PDTwFvJm1tcIAtYEHhhmSaFzpF6fhQ0Ep9sFLVUoJt5200cX55mRmWx36Lp9tO3XL3yNkSrN3lXaHDSWIuyKCDmhO1QgZdQu1lTl1MJMVE1eA1k7DCT7/3g1rs51i5uoW9ln3ez9m0ISsOWQvoABfNq150eVc0jETLAzZFrcDjBHpgMzt7UNpQP8OXCboephVceVZ9DNkOyfWH+tbvM4CkKqLObpnCkTFYhLUpqzd/VQWArNupe5LgMVDATSnVYMNSTdcVUiev5AguqO7IWLd9IM0ZLeukLQ0Odem0eYYlVRu1no9Q1zNwgyOpfagaPdcDblNX8/EzCsH729BPzypUq/DgUkBpyhWTdxBZZuboqxcCJVYbyTkoqc1LnGGmZVRHV27OS8UlIEwceFFwStDyKuApoSuds2cJOnPpgMnVVA/rtfZogNdpbtkV6QXDg7v2hQdWFmJZIu37yTt5x1LdmxBXX8rv7J4jInRUFzallDDvewUS8dGQB26dDhd4YKFHBnIyhsrvJ1YIOg4KuVPjYzsoEMogcHVs+7Q1qda3iS1taXAIA9AJcj1TUYhuFYbEHuaOp5xkYBcUBRm13TzlRLRBARtwkHs91cOCQegGGPmMdPA0Ax9O88vN+iHmX4WD9FyFyn2NnvvRUott05j2vmiWCSiIppf4ECQmhS4LBltR7OsgbSF9pxbJMQLZnwG4dQyl6AxEkqPw/MpWxH72rECvx0Ghp3brVaFgrq19f4pJUkI/VAEmF6tSzZQG/G1Pia1VACobqfWuG7ByysxyKxsRMNB8uC+EnQgDkT7TH6lnqZvKXEEGIAH4WKjnT1saHKZ8SnJFUfPuz9Zm6KkHujjNKQCgGkbGGKBBPUQLyXUAOmjHktrsfc9Hk9kzQVs1nQkY6ETqyFvMHeVWA4kEi2RjE19LLm9mB3DPaPlV0KGDtpoj9V5b+1DQDisiNtf6airJydNqagGufPp6OMsptqn85cwOseUnDhgKmzI5aGgMqLOYAR58xVSJIeKkrEPTQkvVgI42K1+rp4yXUCZuWZdTVCbVzCzo0SvDkDukuYsyDtPyuZQ6g6L91ygQzQDNOMIYhdtU2tLgIL4EvypsNptVc0LsMqaLXdchEdtxIxqnKlQDCP6y/p2znsy8CHW1k4gGaC35iD3sNSHU7hdNzrpCqGWiusmrmO1aKXwH39uq/Vo7Wu6yDOCdoKL16zs73awl7Qu9l1Sjpk7MFzN1CgoKdW7HRtMKBHTUoTSRiCp5Ksos1ISRdiQClWK+pdCsUbsPA79a3X10cUmTyUSjT3snI6SvuD+9ljZHcg7tXRSIMUzumpZRy88qoRSQWlc8ThIhZanfSLZilsCNBMdk9bq2hZh3G0OJLQ0OMlct00JCxcKiKKqLTSYcOzKXoqc1abxJWYpaMwvaQBNtpFG5O0oxiu4H2EhMAOvIdl2GAAVMA/DAaf0CVvg4OuvYE1NnpLSRgTPAEnTDjjwoQEV1slcoLhQYGD6YxdTIUk27uLz0kqPyAGIgmK4LfUgCvGzSyKnY3p7WHnDmpXynWlgqLUyD7xfWkYBGeKF/694bBojW/BgCg/Qf6mpXGZ/Fg3K9T1mP7p4EiDrYqu3IktrP0okeJIhZh4xp9b20xVyQtjQ4VHOtoJt0yOROHvZoTy7uPxE6InRLSzpQAy0ceRZAFWqODqSNjnElodddB8oATAwQ5L5vCbzR/fhFGKgYfD1ol5BEG+n1yPujWZAgwUdANhNi5QiPMlD4dqtLxtXcIDFXZF1FHJp+oKsAOoDWurq/J12HyXSKnHNdiDSovykJAGHRkG+Bkvn8SwcYwvxSqCx/JyxKmFIxftS2kzaSsi/omgaZgaqWQjPDIuOyKe+i1PpKpBTCuv4kaUuDA1DZw2w+08HgV74BtfH6vlc/gvgaSilIoMFiGp8CbXUmwWLDQpapghe/uOHCnSjaSpYnCZp7E1zewAaGDhjDjHYouD+bHZrBROD3+QFdvAZXkCDoihzLuG0dSPAYpdTqF0lxnQW/BwVhVkNe2voCFrcxlHXN5/PR/tY6Osptgm3fA9BFU9IYnoKrSekAQ9dAuHcU1s4BGxripI7x4r+oTt4KiHUhnMan0HLHest3oT1CUxrIeobk3qh120ja8uAg05H+74KiDkrZ6y+BSz19V4F3zKGla+LLCLMTdkNbGu5YN8/PWqAUjoMAbwdGENA8fHYQ9uHLaPcF772z9KPmaViDaEAd0bXNco7a21gFr0loR2z4RFJgbSNb6yCVZDDxgNS2YEufEUEaMMeyNynCLJAWiZcdc/+r0I28S+5X2u1B1Jk0CgzenioFFgqKza4i08X1c11jYeWs/ShKqzPTSdqyONMUCDMZbZkH47AZx9A21ME4nleTNrVs6qd/+qcHtPvqq6/W78+dO4fbb78dBw4cwK5du3DLLbfg2LFjIY8HH3wQN998M3bs2IGDBw/iJ37iJ+zE5m8i+e5Wmy3JNmzbtyBBRP2Mgkf/1n5VJtLH5bHr2WzVnvSr8OoTBvqOiqoWMYoprEPvRSyPzSZkt3pyQUcXU5h2X2mugefsSXFCyqGrAqUO1sr6AjlhTE2kXHTRV3ZnLkgcT6kyEWn8jDAlNzJoWxPP95UsaR6dEZKSsgJIzXeu04CyMVu8ADY1KhvSioG/HyNgYSyFfWNUN7RJtDF5pmZhJpjVl1kjCCOlXthOAOLsTImm8oYdDvgmmMO3fdu34SMf+YhlMLEs3vjGN+K3fuu38L73vQ979+7FHXfcgde85jX4L//lvwCoiH/zzTfj8OHD+NjHPoZvfOMb+NEf/VFMp1P8o3/0jzZblCDkPoiLCRWH9mqnLkfOVoTLS1HXaY+WPchgMoVsWiUxtU7aGU2PsCaqQVgFDeo/IrimRGy9BqxY/BVrLM3eTAr5D8Vs23ZccDFgC6fkmjCLyJMjW3V+AT6ch5IMzhwHftO+cp9vmUDx5buGpQVTAeDzJCw+gzzjlzJ7p7BWwOwpu241HWUgfryoc1Obu8S24hx0kRKzV3FozmczZVDVx1OfI0hfyCc+F5RSHH9te/rycVsO9nvAAcj/LLNiMpng8OHDg+snTpzAL/3SL+E973kPXv7ylwMA3vWud+H5z38+Pv7xj+OGG27Ahz70IXz+85/HRz7yERw6dAjXXnstfvZnfxY/+ZM/iZ/+6Z/G0tLSpsriYwjqlFRfUVqWiubEB6Zq2K64lkGSDrwAAvKP6xSmfzr9Kc/Wv0w7AoOOiB71ek0DwjhGoSsYBYIWGeFEig3GUgh9XwA31WbAQJadA5rqdpEBmNm8MM1YXy/C0Tow+e8kmnIRpdUmUn/EYKyPAYS0iT2ueeqiM0CjVetPzmF8BDBw11WUnXBJWcj9lr9rPAbP3GxZueQgoCzLqrvJBCVnTCYdum6CWeow7+fo571rG7JfhVkDyfutzL7+AeRcGQl1B2kIoOPrtsG06d0YX/rSl3DppZfimc98Jl772tfiwQcfBADcd999mM1muPHGG/Xeq6++GldccQXuvfdeAMC9996LF77whTh06JDec9NNN2FlZQWf+9znFr5zdXUVKysr4acm6+TMVM/TWQnYqdt5pRFdhwcTo/7hQEJyHw4czUfta0tqK3qaqF9GEPLj15sUEAbhda+yZ4oCJ4PI0UYFGtFsoun5gag8xJFo/gD7XRTMPD2V4wJRoAFW+36Ovp+7wCiSN5t44t9w/dC2XZvEIFLfj4sORc4s8Zu01DcgG62KLYTStoAJjBf+QX81Sc7A8IwozESJOQEzA8H3z+c9+txXk0pMh2SjUE0Jsh27yni5b40Xwp5xjKA1kbXd4JXpei1uaVPgcP311+Pd7343PvjBD+Kd73wnHnjgAfyFv/AXcPLkSRw9ehRLS0vYt29feObQoUM4erQe33706NEADPK9fLco3X333di7d6/+XH755bESqUYdnkwnmE6n7FswJE7EpkXn4gn4360Ka4SvHThyD9p7Gv+CDW0nrLDvSy686EhWuoTM7FoAEAp/E+L3lf47O1UGVLEbhWXIA9W/YmaCHErT6nAZiObT4QFbiu6J0CPtA7sQLWiF9Hm3nnhCrKe2p9f4xRY2tWaLhQI0odGFcqFGWgAT8DHa7fIyUyUyjqjXDXa8U7HPPdZW13ihnu0WtrZhZqeOdGENQ/Ms9ksENN9WrR8tzpisnzZlVrzqVa/Sv1/0ohfh+uuvx5VXXol//+//PbZv376ZrDaV7rrrLtx55536eWVlpQIEd6QsLpJ5a/AAqd5hR/nGKL5okYYOt86l8LxnGXy5KPWze0K0ZNHA+gIREXMGSjl8Ks62JVCNb+mYCwb5+VTLtNjELBqMVu73jj9PWETII6jYVmodj1xeSlGzSj0LgZmdUd6u66JZ1Wpux2B8u/SlDIHFCbD6H0rRaEotAHlQCMvfrQXrjzNHc87oc8/vYMHNWTW/uWso5lR4j0XmDkX1z1DhgC8M6vJbAcdud6Vyo0k/OvPDjWtts+bz+dKf6JTtffv24bnPfS6+/OUv4/Dhw1hbW8Px48fDPceOHVMfxeHDhwezF/J5zI8haXl5GXv27Ak/kkRTCAWXTrddehSCixIMCNSrm+NSWLnXPlBkCu53cAaRewfshGOjeK4QTap2qgxcar8c3suF9AAhWsq/TwapDlZvCrEwC3PIbm9FGQxGobuk5zYMy8akt9iaEzH3BKS6rsN0aYrpdBKAyCy4xmRqX+GfCX0vX8cw9JqHNykFCBrTZMAQfX+7OimwOBtOmKMivTcViEy+BUzkXRBzxPrTHNDGUARerVpub4lnlrDxN+b7GWubRelPBA6nTp3CV77yFVxyySW47rrrMJ1Occ899+j3X/ziF/Hggw/iyJEjAIAjR47g/vvvx6OPPqr3fPjDH8aePXtwzTXXbPr9sjMwl1wdPDkjS9OLuoMDEDQMPNj+JX4/MkjHtE7924VL007Whxzw2KDRd4n9GhB+yB70nrYSDiAIYhP7nYHuvALRbI7uGiYWLYsb7VoiHbiUBpGlFTtD/aysEtQkTK25XZ1ecFPLGpr+EJNGn4U9G2g/PwPXv9pvzDQ7t5wdJOtCveCakHmw82bTEOkb87NYHjZm6m+JRSmBhiQ7fWdgTAY8XhmhGQ5+eFBzndxY2UjalFnxd//u38WrX/1qXHnllXjkkUfwUz/1U+i6Dj/yIz+CvXv34vWvfz3uvPNO7N+/H3v27MEb3vAGHDlyBDfccAMA4JWvfCWuueYavO51r8Nb3/pWHD16FG9605tw++23Y3l5eTNFAYCmA5zWJfP0ggdMBgCh+aVY5zdUrOYB/R6AbvnV60w/w1SZo3oeJ+qripUpmHzMdZQ5LrAJFzANKs7eJECO9oOTjTYj9YUM2KUUrrBQjRWBwlcKBmZTQL91x80rSPCyajR7X/xvYFzjSYU61vYSKDb3vbbPmFlo7eX6T0BG8iYfOBg6AyRh7etxd27RFZywax6mj2xIRVNSTY7k+g1yJKOVU9lcKXrmiJTPMwdX2YY91e8LoJva9MjFTZgVmwKHhx9+GD/yIz+CJ554AhdffDG++7u/Gx//+Mdx8cUXAwDe9ra3IaWEW265Baurq7jpppvwjne8Q5/vug4f+MAHcNttt+HIkSPYuXMnbr31VrzlLW/ZTDE0mSagcM5j/XJc8w8AgG1cOyVGBhJ3K8Gdo+k6muTOISrbwJDZgeqprz4Deay4tzWXRutqLAgEPdrOqpug6xOC7oh6RQafv06CWvDld++CBbWV2BPVl1PCmToVI8zeH9QnJwh/08G8Djvjwjngr/l3wjC6Dj3iSVI+n4UAIXX2AFVgYNbco5urnAC2s1HSTsIKwKwsl1LP10w1DmjPM2mQIwt4o1Vxw6HwlvDa3nJRS2UmEKDtqAsoi9wDLbvwOeOXG0tUNuOh+N8kraysYO/evXjH238S23csw8chUIeO06ig9lp0vGkIuOY9bQegGRCBPSjlg60chFDlxAuxSL/zdn2gfyODWvIJMxXJphNFExWeUsw5hlKXd+g4a95BSepiT3iwEl9D1034XMwSpi/Fr1BcAJQxYiJON2VlDpPI29AjSQSbUsLS0hQpdVhbW0U/77X9vQ+lndLTdnbMgRtc/Q4C8lVDS0AaqFPTn3khz3UcT8SbLPVrMUE49gUvNMvc71L/xKEEPGvU4/V8B3LZFHy4oLImxne2d7bLb2m7bjLBM57x7fg/vuev4cSJE8F/16Ytvrci2uEKDIkGwlRvN5oXNAAwHMww+hiAQyh0agY64ADCdJTeQxL5uQ8wb9rB6OmiAnlNPigoeLw4qfPCLvaA2eiKdUp3tZ5j7w71A8JhN0pr4zV9rvCqSJJt09webAKK3d9utR/MIFHdVSuuQFmuzbQm3j8Gsp4BcGg6gmzGqw0iDFCAvz3fUhdBOQXhe1PNDP5GKL6Mga7UGSIR/sKMJZC5lvBZCbzGitdHHpA2/GbTlgYHL7yS1OHjGERrZ3l6qc9hpHkXNGxgEfWlTSbkzDsv7Tz1ZWNUBVgEXs57yLytM2gBb05wJQJgkAWptdBz3sPthQc2cN19scqKHrVMfebTnEVwZZu8VGZha9XmkWXaXGettdPmLUAEk6EU9ARgBp1pSCLoVkN9F42EcfMlova3ZxTc5vO+B0oJi67gtnlLLdSU+v+39+7BllblnfBvve8+t+6mu2mgu2nl0iIKKIkICq1mzGhHokxKEyf5+IqZOBVLJggzMaaSCVXqTG4SLWfGgjFamUoYU2PGSmomfinHkEGIcYwtIF6GOwhIo9DdNE336dvpc/a7nu+PtZ7betc+FzKJ7HgW1Zy9373edXnWWr/n9zzrBmSG2KAJZPZjBSNpU3cx1Uz5Tb/gvmRnKsjkzeK0KdSCxPm78jm8IEO18ZN0A+lpyUsO/J4WMCCAOnhIhzA0WRkGa9dse8ZyD3fBYLiTIaXZhtYdZsNp8kyM6VoCGAGJnSRHVr/ETjuB8Y3APpEEPjrAypf5FC2xqWu3Co8IrIWDFVSADCgC0/Ig53K4uucQI4HiUPYqtE0jewkAiJMWOb3ST6BO7AzuTWPAXrdlc3xhjhmEymnOGAkIfDxdAuemaQGkTXtNBnsuB/8TIM7yLh2yCvr5X/D1cWYTqV+kVHp/mzDW4OAUX/6sU1rWDzFicANu8PMGIqHCMNe+kD+wk2dAZOpNOp3fLckaIEYATYTbaCVsnrUKydZcCwI97WdAxpoYNt9UnGbkIHNJBbY6MjqIcMrOpqYKlTTe0hkLL0wUIoHAdDzXnfymIWs727ax04BsgvDs1vzCvJxWXfo6AlDd0GUEpLIxpgT7GoY5TV4aDQMu1rGdDqs3meaQjn7zxxJKFO6nYB+UbUsy6bDaUNMElE8+M+Awqn4/tGaF1Tz8mR10Mk7YsIbv6Iy+0hMb1WAcl4JeQ7ZoQ+Q3ecBYGNK+ScibRA2oBYmTIpnTonNhFnfSeQesc3Lazm8GXQ8lpcIBacbVa1sphxDhrLmi1VymsizPQmPbv6n6utbCjV9a3Fa21J832gk4wLQb+wTKumCEdqU0A5NAWQcW5yfby3N0f4qzssOG9Pi6tm2crC3jYGWkIBvNZxQKQM0SZihogAgDELkO/EL/Wdn7lw5jDQ5ihwVd+aWDgjmZGH2VFIqpIoJqTpj3rKCtsPl7MKM5D/rAWp+fg8RGFN+BTd76LQw6VOf8C9Yg4ADqDVoy26c5X75difMXyfDvYl8w50pV4APeQ06XTSUHPgagWGZO8ja+AzS/jsD+1aRIzJMTJ06IJufDfOxAYZrtmITrH1xWwwAyU1hYWHDrIMjkLW3A8vIjGER6yzbHcxueCHL5EPtgpF+g39Yp2Ua6B89OEBK4oDP9j+WZ87KwGEx9l8slxhocAIitnD4DbDvydx6kNXAg2yC203LaFgB62jTZeYREKQOCHI0vAJC4ej7KnPNiB5QZsKZoMlVF5LYc+04No3X981Q0ko7gj08PkoeM2MCYmAodTLkVKE2H47zzIbKGH8jvWhP237MaVKDRIhgVCTsIPQPjOliNKHtq8j8L4iXTK6ewLYLxgGGzgop3ylkTe3YE8nb3JvjVneVUakoHSSZZeVBZRxUd1Kmu/YOnkHk7upNsCXoYEZaLDBh3cHDySBtxAAMIvKvNULmkpEPWaMF1bf7AyrumtTVeTaOnaUyl2kkDB+KBYgApZ2JmPQv7e+lgO6Bd2svvK03Vgd8XIdvaLCaOVzAAx7LqpbMsiVPnCiqJ82yHQUNx2AAxwQ0uW28A4huQ3Ez7EOkMQyE0oAYSQWccSjDg9Lj/eMem19Fcr2jaJfksfF/Ud00FclqOPBrZxph2ovK9GRytZESef/k0lKUsHcYaHESIBKXPGRials8P0JAaQjtDaOrTXS6eZOZT61FefqfWsXqcpF8JbuR0t8boAVgLcqaiMUNk9qFEhIKlcNlth0xgYQejqUmBoroyVQHQZ6e/I7Mrub+D/5miWdJSu5zWynY4HIq25/ZJ9dCBzuYBp8M7M0VJAAIg/C5MfNfurFTYcV0AVwkqPNWKzBpSk1A2JwyLGhEYTAlIDl1eZGb4GPe7HovMCdhN6jXQWyyMNTiIfMke5pF8i8IwUwQbXT6ztu8dXV71T0A6sqX73IHkO5jyc3qLN4aYEYz+WY3bt4weFvBz+Zu/HE9PiCqYiEtMP5bWCftyWCZRrhAtNA8DhPNRFKwqM4OmUece2xVymAkhbUcvloXD1K/s/BRJ1xEAPZZgwYK/y4F4uW7W9JDFUEaetjauDFxm8PDN/oaod2VI24JNgihndvbFlBkbsblRMAzSA2rTQiyStTAqqlJGvm+uNIw1OFgF20NNZ7v2tcJygpgh+d1gOtlozU7C6Xv8oUdGgjkI12ofSalSJnM69CLV0b4XlN2XxQymAwevDS3VVx1leHBZF/BZE6NEwwCYDv1NayZMvWHWeRjg6HIjO9mL442AyOPcxCtYni2QOm8rg36Z/YNLEprgZCxZkXEacp78Iv8uPiiTrkTSy5CtrLW/BMTQCWuzoGDZc4kx6Ge5aBhrcEih3+sJeYVhh7Q5yHRCeYM1EqAastI5QvG3NDlCCHLPZvpppJupl7I4/wBZ5Wff7mmBXJCe151j8IBh7cMdxdkNagRwHnoBL6NS6uyUTQfO2mpTy2s9Vc362syISLkFcCRBRCKZdnTRg66YtM+4vIAeCce/iavHMsDSZ2HMD74F3TIsW09bdmYCtpaWkYCgix1CKBaTsc/BbO0v+EEqavJZgQc2LONTYHamnSmz9YMspjiWCxDjDQ6GIkvH42vHIqELHRpq0LRJKzhBOx5d0mD7JQgLCMZZZuXfA4z8nmUBZQhiHvizESF9OEhH4iXKMvBr9iW/G008k5npxtrJQz5CL5jr30FKM7J2G3VwewjayVUQUKAxfVUBBpI+y424/VhuFhAAuXPEARlS2WNjS2amMjkzBh5OI5ePxzLvWizPluiL1gCDASjP672YZMYhf+PTyIlQHZ9JnAlYpWuTXtzLTx0rrKQkLGtUH1kmgR5rcKi6v5pMTqP01BwXemmIdWwt10FDOnVZPrcahITGm05qUYyLRNwPiimvTL+5IyXPd8wDPmRWRPm6NgZF5bR81WWlyxitVf4lTkzoqNN6QcvWSzfwbId62S0zYYzQfsr1MFovQs78DAiIBk3sZTQ6C6TtaJOt1ZpBonRmMkBYFubAvpeIZy5i2lkNn81Y5xMq0+X/+S6hX7LvRt/RaWSYZ5Bup+bESKVhsiqd9IuFsQYHtbMAgFQbh4DQSi/NtM+wBfO5Bg2u3ciiONXjWVuX7U2m+K4jpAKJ9qSIyFzUaGEZrmaQBqGieYqM9xBkAEkUHAjUufKP0oP8I8+dw5oQQYQqmi7N6Qfp3Dyc7HqCcuxKtThuQYlZDsQDDSHd+wo+/p3laAaYNRlG1qvP4sScKEwyVqRyq3clL6uJ+fhBPvq964YZwBjsdX+M1lTzGdke9lsWs13MZuDW/N+mYACXqOqczQNk2WHMwQHwYrGV54GzSAJEizTY6Oej4tpORQISprz9GrjiFid2wF43KU+dVh9VZqUPWj/toqFhduDPlYBjIZKZMAJFlKImkgaJ9hxVOC27lkoWFTVp+rkJDaiBHOLKRU9TkVGpumSlQJaqXau1HmcvzmpmAhyPHZXs3DQ1YVBxS6llFKd6WWAQx6oNtnxhxDUB5Ad5f52H4RRF3RnsLRD+bcKYg4PRngD49iDVLvl/ntem4EZtcKxg5NAr4pVBpsWIkX+RsvNAZK1EcMua+04+UzaOiyC3KvHMjFP+5v9cZecELcAofcqnOznxBBeNZzkk0V4qo4KZoSckcyVrxRhj3tuhiSmhLgZaJSODZT4Cl4+nUNm84LbsOSJ94qxx7WCzi87I5FHOwvbSMcympigKNFegd1SM/wRjypXMo2ibEQ7spcJYgwPAgjCNFwA+X9Xb2EsmhJGxCyCpPucOYs2JxcpcNlgoqCFMEmzz9xS3+ivKBS5WqyhdZpqaZVbIiyP3Sx7MHz67kgvNMw2G/gZ7Y7SpAxU1lHSEGqSj8oMBT+TP+TufmpRrr2OHwaTIluXtlLP+IMLqQfEIp55nhWbwOYXkwd8PYG2NfgiqXEZ5LaH9xPZ9h50VB7uA3ApA4h8AONgviT00TZSpJzuFVQ2Fkyon438v7VHr5MwdgDUI28i231pabjsqn28gfhJJm2lvvcL6OHWScjFMvZ6GOmetrQOca9MTic3W5clpgGUQVebqe0EGn8wUGiCdHaFpcgdP+ZLLjNOjoLJguSibyKseBRiUkmuJ4QYqz6ZIm9m8jY/Dzox4Uerhvry3w/mmmBGGgtktwiw0bf6Q+wEYL3jOyLT+cn0IhqGuJIw9OLggHTAAhHSBCCAbdGTw2ZmEgl72NIzQ/iKOzC4wU7ROSE3Ippps1uAGn2t4OctR7WBTkjzwfCmLcZ3T1PrZlLxJYTSqY6HlQiY7U1CwFD4slesfYxqyje+IOrUaMBjkMxOJwNuU1dLI5STLRFQEfhWokYUMTNL0OB77Fcwuyzb0L5q1chNhcVLWgRkCZN0MUVrfsqj9aBhDlkGRpBUAx8xtkGhdmpqPoAA0aHz90Jd18A3IlVsxQIw1OPQF06dUMeb5gIzwjjJaTVWAg+tjRrCcR4+aYpTyVmBgTR2C7wjyibJ2C8ZDn9UvmxINoOdVcIcraWQI9YE0QoEkv1omq84PodrVAgMAuSeTQkTXRVcPPohExadmQxMC2jbtH+mGBCDK6d5cVjkF2o6roA4/zUlXVSY5lJXyTKSqQSu+B866t9oyg0xt0ZbtLyIza7YQyW1lqX3KqWXuC+X/Uw15QaWAZihkZUNpJj0PYADGHBwQlCZzcB0tN+aigglKD2EGlaw/qLwic8qcB3J7EXOAXjHt205LJrAwVFSfws9xW/aRro+T9Q8cpZdvv8Onceopt/ALiaD1NKWW/AGWFyFGI782HVEnF9jye8QAlHwRg5AO0RkSoevyTtIANxOQsSnLQM9pZEovbGcUQKbCKjvK5Qpt667iS/VOQFJOcTZFm+QkXTy7N4Nf5E1j+WQMRPBtYryTNIzokpn58D9AAKQJutOzlEHQDyMDLf5zNYw1OPA6fTa93AYsGEoZzMGhVqsyWwhBLtkV7ciax9immq+yDJkx6fTeyGpZ8/+txucfePpO/Q3pmDuuS8hsIkeWgcasInXwfpoaiKuSWYvp3FYzEsfV+PKDvJ87duDr/vJRam2b2iF6+QnocDL5d1lbARKQ51O8uB2i8ZQ6oCpXeRmwVecl03PV8vYchH7boADn4l021TivYABeFIQ3s9g+4GXTniMwlVMxwMrbEZ9kyjSIbk2KXdLtndu9SdSijZcXxhocAAMAgNq91h8gnU4v041FHKZ9waRZBgsQVisBqNqvNoVy4Q2YDnLjm/l3Bi/7L+Wn6/Ll/s0SDELNxLAmA1fBAx3XjcoRxzK1YMYZ9jRcdvaB3J4IJiqqhO2N3ulinIa1tozotGSYB9pIp6DVmMTtwv9CNsH0fooS5IkFlP9yu0pcZp7mKsVASvFLu17ZHtdH2yDIVuGiLob4leWzC7NSMbLJmZmSOtsLeVTD0uyiDGMPDoAOVus0AyAHwApOWxvSdgJAbsRWsPFbcAFtPNEkRHpNmklL8oJnL+K3kPh+Nx07+XpHnuV8A3PWCo3mnFmD6aOgJ76x+jcMRpZ5cyclTat32Kyl06zxzZkYBD1bMdnDkE1fvPs0yS4y6fFpxoihlMeDlTog68ENDM6zkDsKedb8D6b2CtCA61OeARSlCHYQ8poKGPPFSVBNPdgPGt+WUM/ONLKxnc5gz992ARTwDwAcxJSA0kbbCeSewxhBbavOmaLRgQQQbTYv0vv1tepOs+dnJZtIX42n3Dqn8l/+3HWdApZJ39ZDfw9QjCBm/FxbMLG2A8/TcPXRuI4JMrLgnsZ9zQ9MC4ay9oD0lm4+kMQkADutrIe4VGQaeTAF9T2UY7gGFI5VswwYmBkLvEnppq4d8EmhXFvLIK9Sc89W3fPinAs1Lbkv+HyTdZl5SGHCpnKQ7p8RNhv8eRhUBwg2u5YTxhocSmR3vgRKg0U1VSOavpYOh67r3A49tTW9Npdn/BmW0fqOxs/FZLDHqNd6WuUZ1yal3wBNzDtQo0YA03cGpTS4olmD4L39gByJbcwIDg6wct5MaaWcmT6zmUOMUbUumMGNAYCfsRkSh50Ag/x1MvCAUwsWGN0KVH7HgBrsXxWhEadegSfyI5K0LNik33lPg007aIoZCTwoFuJx9F+dqeorM5PTpu/LoC/lZisWir9LhLEGBxSDtRyUFqkpGIEy2hZA4ez8QovbTsBavyyL5mg6DqWzLfn6NG5Md3gsMoWUweY7QJGFKVfUPgftONz41i9hOzKnrVhaVYUQlqLJy+Imlbt3MMqgrNF29B/ZaUHWmFpJBQTb4cURVwGQElxEHkYtBy/INPBM2kr4dZCr/MqRZkDLFrwoGQnTs2yhGLkFS/LgLMU3yq/IspCDzGrYOMWRmouFsQaHckrRCs2S4pKmc4ewAGD/1vIop/Vqw6n3vilPNOZMeUYkA0MNIDgd0T9RZzFk8EjP0d7lHJauSOqDkY66SAj+f2KiBEEYvfjVDqbR6XqZ23Kl9ywIM2MpHH2SUt+8EEkRdA+ISSf/5F8rTA02SfIj+zMS3dffuUYKlVD5uJCBgdlDCPmqFDXzUrlM6bjd8y1gyMyhCQEx1OUoZcjAwOsglmtK2DDe4ACATQXGeXYQlqIIQE9bjzAeU9pLmBOSP5fB/GbBOXAawOjFKGzuMGiNYENSHp+7yYu1dkmSbWl057V2xiKVShEDmw52KMgAauDyy3UJZQKu3DoiRsvXArJtOzYZ6syBlbC8R/rZtp2TUlAWw2V193QCKM0UIk2D8dOxTn7ueay8x+aPrXNJTISD2PtHwEyGK0GuziEho9/Ix6xuBSAx1uAAoD/obOMH1kjmzsystcvVksBoU6zsvOYHP7QKiiqzBAww8B2My2nLLWUxzKaWrzVl+0Ug7TywHUq7q+x9KKlsMGU0NFr7YVFOKauCB08fWzNG6+OBy02VLkFjrF29aB9PnSJ/Xt5gCPCOY2WbfYBOv8uLi5dbzDDAkjwqBW+KLsmSOSrfljUjSxBgqKWTyy4sZJEyjghjDw4c0uWxeTot76lAyOcD5EM5KR+hHIkAcymqG7CFo8pdYJKDm6koO4YdPEwb+Sfzeyi+O02W83L6WMwNSRiE6DqTL6Mvlji78nM9sZJ7bPDOTPGPaIJ1UyUd0NLF4AZSKS9NFxBOkYHBmUipJM4M4GcMCvxcZ4B6RYJE7hW3z2pUdlwOGKcxIeTNYra9HGuxDeyyzG7cimIJsOBdltNwAEEVAyvch1iWLv066DyfMN7gkAXHVmnMvVmnnYygSm3LGr6g/EsppUohel+dbVywRc7LzpqU4NHTVD1WwY8DeJizxvblKp5lccgUqPQ5yy7S38VCqSwNwai+3+ca1HuvGrm0GAybWooeC47m91STQgUoWeRByOePks5SAKQHYPWKWkuTDNIH2PMgEZB2czYqdypMQEnFtguDKOw6Eo2/BOESIFup32EFvssUvv/97+Of/bN/hlNOOQUzMzO48MIL8fWvf11+JyJ86EMfwumnn46ZmRns3LkTjzzyiEvjwIEDuOqqq7B+/Xps3LgR7373u3HkyJGVFsVoNnU48pQbR+A4JS2zBNf5FQyFK6m91aquEUkzEo+0cT7Vyg0sbcZY+5jLaXtaMIkJ/XR5F8HcG0G9kUmw/geblUuzWmjWZKH6T4Iw3JBZvzKXpVyj1l62qw8l3YJV+NLV05ZBnTuCvTWMWSblJeL+4lxoo8j3mhYoi6emFZt9ZTuQ/R/3R6I041ywh7KdJQ9YRmwru7KwInB47rnn8PrXvx4TExP4i7/4C9x///349//+3+Pkk0+WOB/96Edx44034lOf+hTuuOMOrF27Fpdffjnm5uYkzlVXXYX77rsPt956Kz7/+c/jy1/+Mq6++uoVF16oXxZSOXhgrIUl0wLcgETZGcrfjaYg85en9fqDrx9GbgqzIMUAQarRJG2DcEQ6Hy+AxXIw3QbcOfNv2nfSb55psPlkwRNK2y1QNXyZsdk8lf/xdXAr6aGlSVFOXdoB4M1D/64MNjN2tdieaVEGg3LQ2ZkuN+sFo2DMbz2mFFi2lvXJW1UlQqR9Sdo817EJ5pbxytL9UcHNbC0jrMis+MhHPoIzzjgDN998szzbvn27Zk6Ej3/84/jABz6At7/97QCAP/qjP8KWLVvwuc99DldeeSUeeOAB3HLLLbjrrrtwySWXAABuuukmvO1tb8PHPvYxbNu2bfkFCq5rp3pnE6zNQrSdSDo3y8iaGlIHfh7EFrX+BwseltKxD0IoH9O/EFw8tVnTc9ltV9bLeLx7NEA0bRpwBJJdkOovCAh5SbgmGxT0VGH2tK06FzW/QvCw4NTkfR98f2P6LYgcyjMPnL+mZA2WaNSciTz4zd96YKNSPRlGLQPcH7hM9nbySln889EEvTwqzlsb+iWgwG+bhvnLZ17wFXwhQKe8c6xaOs55W6a9TDBZEXP48z//c1xyySX42Z/9WWzevBkXXXQR/vN//s/y++OPP449e/Zg586d8mzDhg249NJLsWvXLgDArl27sHHjRgEGANi5cyeapsEdd9xRzffEiROYnZ11/1zggYkklCakuzLdXgnb0EzZAAP7+rXUcb2OYPJLXxPC8yUrVvSLrXGXaa+eDaz55ER6jkItbepASYtQPhE5IsbOaxYiiUd8CA5GmUojaHjfQlB2UapoJ1RSAAgGpGCeVzP0/6znXcts/jPfnYiESRUARQlUYxedSdF1XZZTnznadwHfB1LRgporAkgVChvglcBi4zWQRC/T0XoU/8TE5ewMK1wmnV4RODz22GP45Cc/iXPPPRd/+Zd/iWuuuQb/+l//a3z6058GAOzZswcAsGXLFvfeli1b5Lc9e/Zg8+bN7vfBYIBNmzZJnDLccMMN2LBhg/w744wz0g+5wSOlgdl1HSIR2raV7b9OWxpB1YOZuVD+p5TRfJc3uBOA4Okta/UyC88KLBhpp/L58MBVnuSDmlZ6nDuQmM5wuICYQSt2EZ0sWELWgMGl6f0WFdMq/9/+VbODUxrt/OLnFSbdi2cHPReyNCG88PSzcSWUuFCR2+h/tsxGAKZP9WU0avCZmo+ud/GuLspyBXc+kGRuZnDL6yH4aD7XVxGWiwsAVggOMUa8+tWvxoc//GFcdNFFuPrqq/Ge97wHn/rUp1aSzIrD9ddfj0OHDsm/J598EgDkcpEm39wcMlfz5oNS2KqTzIQQdCACtnOZDsORrd0ZkOfIm176sr6B/1V+N5n3ywQDGu53BSXuBBQpH+eeb0gSFhGrdRB6bsEqx9FVj1TkaQIZeYNUfiFI+q6+tgql2VIbwKZspa9BZFa8sNhCH8cqHHEswEC0Oem28eJdy4+4PpbdLzUGe3gyKqIwLb3gx56jUfb1RIo9s9VxQL4eS4QVgcPpp5+OCy64wD07//zzsXv3bgDA1q1bAQB79+51cfbu3Su/bd26Ffv27XO/D4dDHDhwQOKUYWpqCuvXr3f/gCS0pmnQNi2atkXTtCCkAdLlw1fEpNDRuShA2NDF/sDi4NqW02wq6Rr6ae29kD+XZoj8VqY/Ig5Rv04xErrhEMPhEKAoPgTvTGPo085ktSKECYwqVCEHY76FAFlbktoooG2atFqA4K67K7Wb0nBbfQWx/lRmH7DI1Muhjhm1NUCoA3tF0xcMJkCnxS1zLM2AUeuxaqavrZkFID3Lo3CgGi6n0CDQV894ibAicHj961+Phx56yD17+OGHcdZZZwFIzsmtW7fitttuk99nZ2dxxx13YMeOHQCAHTt24ODBg7j77rslzu23344YIy699NIVFT61QdLWfDZhE9IOv2E3BBHJPZBqj6InLD8mdI57FDDIe3Zg8wB2Gl5NkWXXqVZJqFb35oYORL6FqW1aBMDZz/ZfjJ3ybDsYiiJamaRyedaiHbnGGhII6PAN0k4Edexa7daTkMUwZEUQGjO4y4j8LYGabOMvE2YtW7Qp32TFU702fs3MkP6UlUITyuv2WE7BjXL1zbjqMT2UujLAcJ/k9u+yL0lZYH/wi+km5Tb1Rr//jwormq345V/+Zbzuda/Dhz/8Yfzcz/0c7rzzTvz+7/8+fv/3f18q9b73vQ+//du/jXPPPRfbt2/HBz/4QWzbtg3veMc7ACSm8ZM/+ZNijiwsLOC6667DlVdeubKZihysg64J6XxFpsR8p6TSZqVgZWDqL98XGdC13wQY6oWs8Mj0TPV3AQyLMBDPzI0jkdkLGgRKl8TESFhYGPrzGUM6t8LnUCmFyawHqFR2ce2QvaLDm2iSG9VO3EzP7UEnbprSgOXoPk5e3sZM4MHu0C9klVEBAjaxNKk8ZZuOgpayRQDIPq9Gymk8OoF6XcCWjYVk+xE7TC2QMjBEM/CbwpSyjkguMz9fbEtcGVYEDq95zWvwZ3/2Z7j++uvxm7/5m9i+fTs+/vGP46qrrpI4v/Zrv4ajR4/i6quvxsGDB/GGN7wBt9xyC6anpyXOZz7zGVx33XV485vfjKZp8M53vhM33njjSooCgDV9Pt48N7LSRN1LwZ/T8wwoK9DmPs8l3lvMGVWaBwYgRr4vnVfT4bTicCibyUKOyrv31FHa5fsx9IBW6vgofD5CzUBDDTjNQJEXTImYuXV5JqRpWrmvQTp7fpcXFFmwc/FMveXGLqulYacoa7SgVv5cMccaoquzDLbYT9czglDW3vtWUmbZn8MyIPiVkAHlNvlURNPWFhis/J1pqP3ZJsS+BQDZ1NWyriQEer6j5AcYZmdnsWHDBvze7/0qpqenhAZak6EJTfZDNHqxCP+f/AIST9O9FuS/NY1iQ4052GduMJrflxI+ayrOOy0oSmv9T8zP5w6kcUG6JTxpvQ4xkqHL6TDYwWDgy2zTYHvclKMGEPyx4fM5ze98NaF9v4sRw4UFd76k+GCcOQaw+cQLqNq29WaFVQyGuXNe0lYOkPlCHjPIWOs6bWzKVLYHH03f5HU0jbZPqlfAYGKQT5lW0bqt9iPSts8pErpumHxnpg7qME4Ap4BJrg15tq4RR7mynLO3vxpv/PGfxqFDh8R/VwtjvbfCnTxtbE2A0Axa6ehyoGleSML0urwpqrQHJR/+3Ud0oTRLSrDggeCOO18Ml3XE5z+pg/Bhue40Ke7wMEtyXUdMAylGvvCkr218hYPydoNgNWDg59WZINJ6y5JkGOZWA1h+NQMdUT6whODv6JQyFJK3pgGg52SUFeW8SRVKGbheKpag4oiEGKKWJ7MSJqm2L4kZICdHcyoVgMimQowdOjZnuA6GgSVZ52Pu2SSCqROZG9+85bLsMN7gAEjjqrMogUbL2sx0FkTkW4MgDq4O/kj5EiBEmCGYK960kSSO1VCGLbhulztJaJpqI3E6rPGcVgXc4CMTX+LksqszixDlqOTMjNz6D8Om+kJQx5bnED1Mo2wCJNIVROZ2cFhN7oCPn1lQybLmQdSfAfJSs9Iuhzmx2WbNHCj4aBmx/JDLJlOHYorksrD5xr+XZowkUQKbOh5j3tuRih4gBkw+Uk+AmtLeXOdHCRDTwjJhL4Glw1iDQ/K+5/smcidq8tr+GCOaNi2f1o6pNzWKl5kac7KSGSr82QzI0DRouGEWMSH4+6j+xofe1thFIN3Dj6B3LTpHXIyIXdcb4EFODDLlkvKr1zrAXARkOqSCm9dCywmU7Wrpi4tp5mKghgIY9BlB5v9KWlY2QQDSxbw64IgPupVB49vMMQ+jFNw6B6qAU1n3DAYJb0J2hMdev7JlZxC1kMamUuz0gF6ZYxMxMLBH2TVqE+f2bvk6hkKxhLylYDlhrMEhmtWABJ22lMaKxsZMkRBavYY9TfsFIE/55SjOnxAMeocQQE2T6F6pagrat2RgFkKq6Tn/wPm55EOuc1SnnpZY7HgxoYr3avkbQ1ZBgpPUarnB7bLl58xSENFSU8QlZXfmhx7LCuaQHFNMNv0aqk1jKj0P+SvJwCNo9tRL109lroQ26BvBpC15Ix38G5smr0xNse10uk9H5VNOUbpZhuzQ7Ejj8KU/0l9CWlPSVIDh+YSxBofQBHG6WGCQgWR8Ck5QhuKGpkEDuIaxwXXYipB7mmWZAFHGcPd2loBhAcrky7Zs5L0A2k+zclJ5VItEDC22nkX9hb0ac6JvV4gmtDMjSj44I6rKRhc2yYMcV/OOFBNA8O/yQnAYZ+tl2ZuwwZUAuKRr4Mj6i1w59HEkQlPMynBEBjEBL5i2tFOmzo0atDIEN6PiYglL5BkUU3kRxvLrPtbg0DYNBu0gbbIyU5f8t0cLA1PAHMpGsX6FSgjmr41T7TwrCURuXr+k3aA0rcW2ech5ykIn2VzFY5QpuQLEqGCBRLJmTZ87E9lORf3u5exsSuaXu1ejArr9gvQBwnACcyJXg9o0oBGVASZLxzWCxF/M9gPcLJG+7p2vbg0NmwcRiMWVfeyDURA2CqwnC/0gXTekurh7KfLv6lfgtopIVyry5UL+WoLRPdyHsQYHnnVI02T9+yZk+s844WT6C0moeicB+CFyIj3WYLVsb9AVoKLNVQ+jIITfK0GG73jsUWPzjIK+p5YUwWkRGDDLBayedETIsqrXwDqAqaipPZ/SmSTQWQTWvMEAXk/2AvTp7TTb0vl3jET8AGQ1awpttaelS7V6mcFvWWXJTtVfUPSXQpa5BuDjh2s+nd5CJmZGqUPkawXzJUIh/c5TqgoMyjYpEmIT0aBRM6VO3qphrMGBiGR7LZB2dwL5BqkC2RldRbPAg0iOlP4ArnPCpMP2snQE8XFofGUqdddPDTTYZCjn+yVejHIVm2q+vGw3BL3tS/IwBrrRREZ64AVFgK13+i9S3cwq/Spab5WVaKyylsZMEFmVdS5kKa8SAKuNLa33khJGmNJXqGBtC/hB7fPxLFDal3x868eyLCv9XxeGlaGUqfNDWDOA/3oLyvVpQ4cKZWISIj2PU02RHwLm0LYtBhMDDIdpschwOJRzHBrrkOFTiKh/C3et89c81KI1UiSwX6CqWdlM6HXg/HPxvdfFC7Di5xSj5C+DivPIMylM47U+UqSiKGpGEHnQYXOlGgplDDMobF2cZuQBBL9AC0SIWYbNiFOx2N6uDSpTgGWHxSg1VfqGVTLVts5Un6CncAUQ0DT54JfgGzjXyToixWRA6LGtAt0FINIdsEFilLVM9Qmo3ne6TNN3rMGhyT4HIkI37BCagInBROpM0Q9we+nKUvbvKL9BTXssaUuPysOmmxJz+bsu4Wze1PmYaUSbiLPbjQPRpCZrIJA7qWMbSket2YBKB/cvFVxI+iPpX0MuLNPikgVj2slvBtGCfY/LU/zui8Wass9g1IRRGdUYRLmnwgIH3CAjpetcJqI8OJXwiGsAGVByNZLyqvXLnIbUms0CyqzRMqJCCMG0GUHu0aSw/D471uDAFLYJaUddjBHz8/No2tYvX7WUzw00qmoFDyrFoK3E8wNpkeJCOxY3OVE+Up/Zho3HpTYspNawbGtzJ9HSZE3G2i/fdC3UNDDFh/SutJux30nt+Weeour/BFiCP32bp+Y84yD3twRDp8WlTlrfdCdIlsti4FVQHed7cfLr9w3rZ0jThHmZvmkneSOoM1vALUa/IhZmxWJIa25C8GUnacc+K+D+Yqc507KODPU9hKhIw4D0UmG8wSH6BuQOGruY1jCwhiQCQt/zzGE5sw01yjnyHWsXwjRX7ih2UxKv1OtNe0njk++Aocg3a1y5h6LQhNLZuHMXvpgUB7r/hMvB2SyLgfrhW5Vh1qputsjEH2kkcPyg07FBbgvi8rFVbbOzoGBTVR8RDzRgNJus+SDcb0VbWobTAw9THFESRgnw2LYSKiUp9Qo2gnHO9l9wsxUBPv3FwliDQxeTnyF5sZMPgrIBzWcqJjqnqG9D2dClv8FOZdU6j2UODgy40Ud1OPNug9SpGkNjWfNYJ6h2Hr9mQTplQeXlM6W/MUY01FbMTTsdBqT1+hGEmDt6psaV8W77p2BJ9p47cMp/KWtTizu19Rx2QGllKvLnyLkA8rYBhfI1/cmDYI0t2r81wCvb2MrBtpfkV/Qv/j2Y303JC7iDlJeQTISyTMGYGSITNicwwkm8SBhvcOgihsN0PmI67KQp6G7jKXoFAPi5DaUjytqeNg0O/VkRk5b5zFrFfrcaRQ4MURUJ8RiSHfi+vKJxrLoKkDlxBrcYI9rQpmXlOdMmO2ubhssfwVSEUAcFHzwbsuV0HVHMi+JtCwxmoLjBZb+bwCCaAE7Q0YBirxSe+vdC2t5vp8Tll8LEqLKjXH5xugJ9pzR/Ltml6T+xibLQyZoX6YzQ6NwdJX6WU6TlOoflLp0Gxh0cYgdCq2sYskSa0KAd5D0XVvMLE+0P5NpgtwyivB9gpCZB3+zoBTP4fTyzHqGXvp8u4zLb4+AFFnn3okENnoFo2zbXrZHOkr6zDFSb8uBKB7wZylowFz9Y2HQwGpz6ACwsCHA3jJc3gZXaGIDcQcqrSjVtje0AwmOUL0eWkTUZa21bm9UqnxtcFgASRcR1zZk6q6B8Vsu/y2d6BuhqYLATlwEkgxJnxP3dMIeUz/IAYqzBwaoAIhLXfQxpqS1PafKpvGClHOygCNVpu+V0EBuX7WYaEW85zcEd1VHRIg3qPdaBkRReWuhV5iga2dHakK9mSx2KD1M18JPSKzVOQLWDuYFsTLFIdiNREQpg6K1QtUzKMqp+Mt4fwxrTMRlTRqqVpqTpfSVSLrO38uy1u/FtCBjmz7UVsVpGNku1wNxGrTnGjqIz2nSvEbNGwMs9pNZcbhhvcMiBbeo0rhIy6tx5Qlp0QCenKQeNm/0RlhkwBV/M9LDmiQUhlNe26wv+exHL2v2WHjonKHgDTrLb0yErhR1JQEQjHZMHVx20lKzzbAa62hSplLJHW/kWcXWssQlj/DQyEAuTjCl3Sb1tCUs/BBdp5DtBBoK81zM16nnYzyUw8IDkfmIX2vWLwDaephnKehqWZE0pWWNizAIE3vGZBr4CgcZjuacvIZ9LgJwnAOhuzB+eqUzo/C2jZWhSBxwOhxhMDKTj6w1K2uMXm6p0WrZ0mlVoqJovo1dG2nd4hkX7lykfmfRsfhwj26S1aThTgUyuSLUX1JYlofucjpaa+xX7MnT6zPIDFSXXmwdOjKrxxbRTQbuBYqd3EQKCbQPObYkO7aA3MKtOplMMHWpbGEq5LTZoWFmMMhmt+VoyUZk1M3UCDMAJwyLZJ9PrqQTwduvhcJhYnihDuCZJnYeZrO9jy8QFAGMODnYtQ9AekWYZoEuAAWThppi10Pf89rVCzRlpO4UMANsCPACYNvfyLMtD5p/mIQPNDABE/5uMCps3GXWZ86N8ihGI5OSsVLdGBznygMinZyU2EsVu7evylD8PDjFRRsjETuUFqPxHgZzLxWpgBpMqIHO79JPsZ0G9v7at2enNTHFUH7BXIiyRoesPzOyEDRggInB/BIZdh9jpiVpZCPDtgXRnCaArTwlpP0bljMxRYbzBYdBgYjCBSOa4rsCdmjdlyZjI3nsCmHYX2r9kCmUnWExr2L+AaSp+Zh1umeum/HKhjRnh/9XrngYXv+Y1JtjBiGTlcBJy8Q+XVYAhPYuxQ9fl6+C6Tqh46p0RFHRJuu2PrN20vObHih+BwYBPxCrNN2fH5zQsyFFmKnKilmUepgWUeZE80xKYmIWQS4CwfaEGCjB1WAoU+uoguxVNmwdkBWdMsyYDtt5Wxn/6zJasrIjMjt70xnLZw1iDQ0CT7eTieRPQ5rMeMqlK1NecQciUupxOGuVbKJ/V4iw1S0FgBpG+RLnoVt8t/0lhIfAhNJLNBW78dFx6SKddCZEqByYPXO5s3kcg90QS6YrK9GK/MsXXJufZNCGtkqCaTkMqK99Wlgc2Dw6m4C4LxpkymZwWf5Z3sz2UtK7O8ihO6+8G/aoD2+7REblU4skgroCILZ+VAcqy5XKHJuS7UzqAgKZNlzVRtLNQmq91MNuy6GdC5DPQHFguHsYaHFhgQpmQBZSVYsMUOAQ52385V5bz7zGf/FuL32a6VnqvF/NcM11XBlE6PrXDMHjVywcZ8kS6urIJjbAjyuAjR9WzvLgoYqCwCdElkMlxIacr63mXwQwgBjiZyWD6wJTFFF0+GhPCOl+FWpfVFXaTZWNmI1g5unM9q8Iq0ybofoU+Myv9Cov5GUaFJeNac8KwyEjq1+H7TZs0nYQudmDgAPcNpWyV+lsABEAxLyoNWCY2jDc4xC4itn1PE1G6IxLIjdu2YME2yAOqmI3Qdz2944ZUjZSDa+C+tEfRy9pTbls2McJim2OYMUTqnXSlZc9QkFeJcnlBCfAY2Nih1cREW2Oweyb0qDEtl6kEmT5G4KWeTo78E8vN6PjcwSNkmUbu5NKX+X/8IcABCn+wp1TDXFEgdXaiI0lPrLsRI6Xmb6o9L8NoQDfmEpcbDG5kWEkDPkeDmdBwOASQfR6GHdh+ameLtE4qzJJRLSeMNTgMuyEGJEfGWscvWAgxU26mh0z7ahq+R+eR+yw3aI4j9rWNUynfYh3JNqhnm4t3Phhg4ANUAxIzimWjh6xtjXbWzJWGRmSzJIQECrk2fD9DSWW1nATekMVx7PoRZgU83Sl5cz0sOzLAYAGJ/Rg64NO7QDbL2lYlw0fUqWMFGps0DymUK1B+hXrfS9OzDIuZohYUvD+FhOHyDW0hs4RIOi2/MByCYkwHxjLAU4S9zIn61ejXKy95DUZ+S4WxBge2p+TYEqaLpnOm/RXp5mm54AMltS3sfENVZXFTCNm7l3+z+yAqYVFgsM4zo45L4KrWGawBybAX9Wgnpax03A5suQ8y+H0msmYu8DLovEhMgIGBl3rvkVlQlh+mdNrWKC4v21TGso5BfGaJGVnQtINaBUFQQLDy6UlP2jb3FmbkSzgRSwf1qDCKZdjvYqpKeVNloqx81FUkSQGlG8Ri12EwGKR1NF1E1w192ly/aJRVCLALwoSF5W8/FMzBTwWa6THzlIiAiERfKSbmOcKGdFRYUkW6qcpQWImzAjvUppcLb74XdBlwwJVrl/NVM0FPYWdQNPWwDEhYQrGnxNgGMhdP2XsegLTPYGX02t/+lPOIfoCkoorXxJUhNCHv61AnqZjUFWLkzBbLGHrlU9Czdak5l2vBsckR79QckbX3ZXaN9GzMJpj3M4h13RBtOwAQsDC/gK7rZDqVGaRjKIbL9nepoie/pcJYgwOR0jFhAjJYimk7KIVbytfAnaZcnAP7F30Q0S9F5xkRt6TKVF2pE0TbhhDyLeLMHwxVJz9Q7HSW7yTkbO+yXKp5883lje5RibIbyzMSfV+n/dJu2Zg1YKe3PeX3iPM3S37b0GbGklIbDjtTXgLAG8aM6cJ1NTb8KOdkOWU66reaA3IxULQDdFQa7nM+80JofkY5ZVipb/P1ifP52sO2bcBL44ngjgbkbs99oIKluRzL12ljDQ56R4NqUw6p8/DBm+qlt2Ex9mAeoCt8EdLw1M+31jGV0Sn7YFMl2DiVTmbLlbzZaaZkmB2uzgwa2eg6mILJx5WQBx0y9Qb0ZixNJe3FgAES0tV/FkxVw2XtGCUFedkdR0dA07SSN4MI8op35WsBMFPSUpeC9XH5HPiVwE5cpsbISCoGexgxA5OsKxAmB1vAXD+SNKQQASBK9SdSdtsOJrBu3QasWbPeMblUJRIWtrBwAoPBZJr6JsLs7AEcP3YkrarshqJYgsmLM1Yl2TuFdNEw1uDgDAixZ3Pj8X4Hir3fAKDcS1FSQmmYnLYM3sUchov9VklD+6F27Bo15fcipS3qbV4BmhSq+euKYmcZWKMneengLjo1KO92ZCCxO/9YG2X/TgiyZiN1SMOysixY8w0G6Sg/ilrGiJhFwe3H/wty0rb4CqCakBTH+iI2chYQNIBu/UzoGjRhgwJDBgqVRzonmovlzBqOK/832puj1Myg/P/JwQQGgwFO27wF57zsfJx62umYmphQJdcLaSYpZEVICJg7cRyHDx8CEeHgc/vw7P5nsDC/gAP79+PE/DzmT8zLEutUwohhPAii+RF59MNYgwM3HAVtnoCApm3SLdIh2a+xQGQA3i4eobF7Grzwgi8GBjVG0Ps9A4U1exLT4eSDfM86AE0TMOyGUI3QdxbWTO8QzADpl9DklzR2Olsigrog7+prxklLtgOy2vIy4DMSeHcmr71IDmIua3pX/T7qQOQ2liPRzBZktyYBSSk4VufqBhN3gAbTOHHiMHgrdDUI0kDkvVyHXggBMzPrsGbNWkxNz2DrtjOwZs0abDn9RZianMSatevQHH8OC098Hcce/zbi/DzadgqDwZRPaGIKgy1nI+5/At3cHML0WsyccR7WTk4hTE7jRS+9AHRuC2oHODZ3HPPzC9i353t45KEH8Oz+feg6oMEUGhxHhx8ScLAdQLq82KK8DDWASHRAfq3/efS6Ag8EPE/di2biBhPfhiqhs4yi95MBCqTB2DSt0HFZSRt0mozZgU2DZ27SOA4OdMqspdgyxnWTFixrkEHiHYtUSxTKAIQZhZD3xhRbzMm9VUokxYd1tmagKr5buZQyEnlSxOEjT2FyssFgMIGFhXkcP3681w4cTj75ZHRdh8OHDy8BEAEnrd+I81/xGlz4ozuwds1atIMBptoGOHEMdPQA5h5/FEefexqH7/0ScPQ5zM8dx/Hjc1i75lScdNKpvtYU0dH/Bg0XgBDS7MU9f5MvRW7RbtyMdmoKzclbMb35TKxZvwmbzjkXZ571Etx7z1fw4P33YbgwUPEuD9vGHBxGBLu+AUbrlc5G+3zUKrjEmIPa1ICbtajauoU2Sx/q5k/JGsp6pLIlh2skXbzVtgPV2oRi5WeqG1+0GqMuA9bLfZBp+yghauFTcUt6njZidTEo/ReZGKYh1VczhRNN5QsuTkonO43JiIRcVMOmLKuRORlAACR/NhRb2oOSybN27QwOHjwIAJicnETbtjhx4gTWrFmD2EVMTk0ixoh169bh4MGDmJqawszMDBYWFnD8+HFs2LAh+QPaSWw6ZQtO3rQZ57/ytThl4ymg/Y+hu/+rOHHsCE7s/y4Off9xTDcLeHbPHsRuiECE6ZlpTE9N4fjxOQB6nicAdDFiYWFobvxKu40xHKJpWwzaFrR3N4YA8OQjON60CO0AE9vOwcyrd+KiV70RRC0euu9RDLskyGViw8rA4eyzz8YTTzzRe/7e974Xn/jEJzA3N4df+ZVfwWc/+1mcOHECl19+OX7v934PW7Zskbi7d+/GNddcg7/6q7/CunXr8K53vQs33HCDXEjzfIKftMmB0v1Ctd9Ku34UMCydr+m/PMgNcAj1hqHYXAb7ziKkhZC35jcNYPY9cLmbEIBGT6sqZ2NiJDQNoQl8wSpTAk6jN+765WCzzDhiA58wTaRec43mTYus7YYYgjpCcvaFPuiYvJiVcPlqpUp7UzJQcVmM7KR1xDxRhcCOu67r0HUd1q9fj7m5ORARBoMBFhYWMDU1hS4fQ3jkyBFMT0/j+PHjOPXUUzE/P4/Tt52JjZu24sVnvASbTjkdJ510MqYGAwSKiM/uxtztf4LDD3wVA1rAcwcOYe3aGdD8PNp1a0HdUMqb8pos2j6BwLAbOvbIv4GAjtLW7bZt8nQ7ELoOiB3mn3gAw2efxvq3X4uXbn85nnhsN+YWQvInLdLWNqxoRN51112yJRUA7r33XvzET/wEfvZnfxYA8Mu//Mv4n//zf+JP//RPsWHDBlx33XX4mZ/5GfzN3/wNgNQQV1xxBbZu3YqvfvWrePrpp/HzP//zmJiYwIc//OGVFAUAhKqKX9Izaq9J4allzQm51Bx31VFYfmZnGuC3aBuGEcz3lC9H0VFFQJ7zz7MUWe4JBDTDBB6ZITUNUDhaE8vInQdpIJdlZwefmg8oBqUxfRiwgq5EFJCwvh22z4HkSAtBrg+goAue1CyAbLHnqcsENI0BDUMXCBmUAtCw3yWVlZ2xPCtgN9w5oWcQOnjwIJqmwaZNm3Ds2DFZLMb9YX4+2emTUzM4fdvZOOelF+D0F78Em7ecgemJSTTzx7Dw7JNYePKbePbRb+DE7AHM7X0cw6OzaNsWJ520FsPhAg4dGmIwaLGwMBS5KbsxgE6ZLXSdY74o2pWXWndDQtPmXapcb/YNDSZAc8dAkTAxmAANU92WE1YEDqeddpr7/ru/+7s455xz8MY3vhGHDh3CH/zBH+CP//iP8aY3vQkAcPPNN+P888/H1772NVx22WX4X//rf+H+++/HF7/4RWzZsgWvetWr8Fu/9Vv4N//m3+Df/bt/h8nJyVq2IwMjKNvR5Tw2UZpPbsS21akhGwfQBrB/Y14RiTDCjzxC5bvxUTyzQcwUTos7ffme0YjliUQgQjSbo9KiGfY/mHsWsikhMwEBZkDlfHVVlZTfWAquFuy/SGBFCPnGpxj5dCwvCcqDtgkN8hyQabMAUBSzSTWlWSql6KuXyRopqZWnU3e87qWJeaekqZfIq2mwfv1GAAkE5ubmsHHjRqxbuw5d16FpBzjjrDOx7cUvxTkvfSXWbzgZk+0A4egBzD92Jw49cicWnvkuDj71BKbagLnjxzBM/B1r1sxgcnISx4/PIUbC2rUzGAxaHD16DCEErFkzg6NHj2HdujWYnBxgZmYaRISFhYW0loWVC5u1bYNB2+rFyVKT3KcjgdoGg7w2pTnpZDRr1mPPE9/BiRPDvJq06S+zHxGeN5efn5/Hf/2v/xXvf//7EULA3XffzBMNJQAAPrxJREFUjYWFBezcuVPinHfeeTjzzDOxa9cuXHbZZdi1axcuvPBCZ2ZcfvnluOaaa3DffffhoosuquZ14sQJnDhxQr7Pzs76CKEwLUxHEN4fIMAwiglYYODFPCOvhVtuMP6FUY+5A3BxnQ3PGjTH5HKBCMMu7bQLix1Zlt8TbZPzEm1sTICs5r0s7e8wgzQAoAjKPgc1I1K5u86DDEI+GDUfRaemSkq0ejdnCHmRlDFViipasE+vBMTYZHMDABpQiFI2fTH9GXYdDhw44NLcv38/JiamcNb2l+PVr/nHOOPMczCRTYVjd30Js089iqO778Pcc88gDhfkvQX4cOzYcRw7pg7OI0eOOs1x5MhRAMDBg9qfZ6bXyOIxmP7RNGkWLjQNJhqzn4RIQBXw/SUMkrJdmJ8HUfJfYISpXQvPGxw+97nP4eDBg/gX/+JfAAD27NmDyclJbNy40cXbsmUL9uzZI3EsMPDv/NuocMMNN+A3fuM3+j/wgIqEDp0cKpttCAWNAPFwl8BQOiY1abMKT9WSy9eq3mIM1YMxLQgE6nw+PHgjUX+gSBL2N6X5RABvmQhFXYQxEeU1DEZ+fDJQ7lF9rYwMJoRyq7MDMssSKMKey0ZZnpSP75N2IUITWhCiOCztrBNPVyZgCeCFB3neQ+Iy8PFngBApmVtNwzNWLBnITlWeahxGEQiaELBh42l47WVvwUtfdiEm548g3ncbZh+8C0e//x0sHDucNDCAmcl1wBJkt9eCpO0rU7kiQ8g0Jg/wZmIKEyefinbhGIZHj0A2aOV2aULyI7SNZ0doWkye8yrE0GB2dlZMriSGv2Pm8Ad/8Ad461vfim3btj3fJJYdrr/+erz//e+X77OzszjjjDPS4SIBqTPGgMjXkgNogtqMtoVGOR/t85ofoscy8l83c1EG8isii6JwFBAonzdhwGqRdOvAwaPVUnEfpzE0XqYDQ8hLB0hMi1JrcTnFuCDVwuaxvkA+PqNRFzupkx6KwrMvLZqmxXBhQcrP5WC5tIN0aVE3HLoBZuvK07TMgphtcU2SeSMSwdqTNqCjlMbkxBS2v+SVeNWrfxwnTU4AD9yO4/d9FfP7n0HsImaaGcyctKbaJiWe1lqOyxhjZrAgTJib4btumJkPCdqvu/StWPejP4Zw6GmcuP0PMbv/cNqbIU6h7F+BKheEBtMX7MDUea/Bk9/7Dp7e8xQiGc2xzPC8wOGJJ57AF7/4RfyP//E/5NnWrVsxPz+PgwcPOvawd+9ebN26VeLceeedLq29e/fKb6PC1NQUpqamKr/4mhLS6TnCHszzUWp9sXUOo4Chmo4mqM/CCAInDCIkbz1l7Ye8Wrgy+JP2LerkSzuiQKpZ7RoQ3p8hS56tCdtLl8xfBQUFPLt+IE+j8vnVpKDjVkiasxbThURpXwXFmJcD22nWnGfU/JcKOnhyqfIBOAHIqxeN2ROAiYlpXPLan8DLX/5qDJ59AsP//ec49tjDGC5ENfsK2Sw2zmpMkh23vBYlRsKw69CEoHtR2AYjQmhaTGw+A2H9aYiTMxisW4vw7GHdNhBCoou6QgwgwsS27Vj7hp/GngN7cNfdX8LRY4cRcLIwjeUiRP+OuGWEm2++GZs3b8YVV1whzy6++GJMTEzgtttuk2cPPfQQdu/ejR07dgAAduzYgXvuuQf79u2TOLfeeivWr1+PCy644HmUxDsUe0ORUoeiqL6G2kCXRUUmrXLBjNPimb7RIs9LZQoehPy5rEnUi2fcZhqbBuz4DZIma0e7ZDr9rDKhbNfzATFNUPCDKZ+ka5xdfXog4u0HNhlynsnkiTIlyD6CGEluLBsOh/KXDRSSPNL3SCofu927BHf+ywqCtbBzZRQF3nTK6fhHP/4zOO+lP4L23r/E8S98EocffhCdBYZ+NZcM1Ti5D6Qj8vIpT/nEMVl/kutPw3kc/faXsfCdb6K7969w7JkD2o/FTI6q/LJ8u4UFxK7DxPQ6nLzpNLTtwLHS0b4pH1bMHGKMuPnmm/Gud73LrU3YsGED3v3ud+P9738/Nm3ahPXr1+Nf/at/hR07duCyyy4DALzlLW/BBRdcgH/+z/85PvrRj2LPnj34wAc+gGuvvXYEM1g88HmHbqaBabMRIPe00g6vzVCUZwCOoouhAIVFg2UQFX+F2IPWLuTolbTUn5Jj2M9Qm14XQuWBGtPOSn/zc1G5bAMrazLOw8x2RXaePqg5wz4JMumaDJi9wNSbz0ss7S+rgalIsJxpsm1qz3uMjhKpozcAOHXzi/H6N/4ENk1PIX7zz3H0m1/C/PGuCgrLGVILXcT+I3NLxqNcXquYiAjrpgZYOznICgmYe/TbWNj9AAJ1ZiGXOpQJQJNX9FCe9h4+/Rhmb/tjnPzj/xQ7XvdPQPEW7P7uM1aQy6jJ8wCHL37xi9i9ezd+4Rd+offbf/yP/xFN0+Cd73ynWwTFoW1bfP7zn8c111yDHTt2YO3atXjXu96F3/zN31xpMQCoxm9anbJLzCpfOiJaUKk7UAcGDi4O4K5nc/GWW0huCDMgpZtW/AY9NmLyD+ZDGmDFcwswnC2fRcGAl9wzsOe9eKcrRIvJg9hnQzIwyZQ3j/fYRefzsn3S4ZJhOVw+gVGxZoJJi6r9mtdPWCAs7zdNSVpQAjadcire8Mad2EhHMLz1D3Dku48jDul5AwMAPPncEfzmlx7BOee/EsePHcM937gzry3Rep1x9kuw6dTT8H++fpfOMuT//8KlL8UVF7xYTx+LhKGZqRNGaFgiCThqd597+Oug44ex8ad+Eee+7BXY+/T/xnBO2dxyworB4S1vectIG3x6ehqf+MQn8IlPfGLk+2eddRa+8IUvrDTbapD1DUjUVdpA7GceAblTjXA48uCwWgfAaJ9BryBBWiaMQmUuZ1EDiIOMj1VTWm2Ifa6FMhbvWM2lNEyEiNAGyx50psCO9BIYeD2CdebyuoReleCduASS8xkW74JBLBe2WGJ+155g1LMSSVlJT5IFXeb2dGzRvDM5MYkfuehibJgeALd9Bocf/Q5iDKNZ1TIDEXDylm04MYx47LFH8YpLduCBb38TLz3/FVi77iTE2OGM7efgsYcfxMsvugQnrd+AJx9/DC97xSvx+CMPA2EI7Re1cyW4/5o+DOjqVwQMBm0C6QNPoTu4FyfNrMVgogGOw7DMpcPz8jm8UEI7aMXL7exjHmwwGhPGToNnD66DVwY3AUt2GGc2iH/B2O9kmpOocK4Fo1FTfJeb4eiWedupv1qIkeQCFB4aztySOtsYkOd692Ix3Uu8I9IzL6a1VPlXlVg2TRKjMczFoCH7SrrYyWnatsze8Vhvw37+AS8553ycccaZaO7/Io7tfhy0CDCsFCq+8+D9eOp7T+C1b3gjXnTm2ZiYnMSGkzdhanoa933zbux+7FHs+f6TeMnLzsPxo0cxOTWFLkY88sC9kClOzpv70iKgJe3K3SQ0mNy6HSf9o3eiPfXF2L9/L+ZPdNpef1c+hxdSSMDQSKXTGnuIBpThVKG4Zah2YEPBShQXjV480y9+2LKZUuYXsnHZtyRCj8q75DmdRX/vmy0KVBaYfP4xa3DucGphsHY3aSGLIA9kOyOh9WETjsWVOzKfaMUD3RY+l1FXTNYBhm83qwFReQcql2N6eg1efv7FCLNPY/jg32DueCc3V5fSej7h5FNOxbYXn4lDBw9i7vgxvPKiSzA/fwLzc3NYGC7g6JFZHJmdxROPPoJ2MMCRw7M4uD/5BIKUIyBMzWD6zHMxMc3+OG8WlYEOP4OFZ57G1LmXYN0b/ymGE9P4znfvxze+fRfmFzLIFDN5i4WxBgeljpDLbNnZ1fHSZwAIPK+ezA9r2y42TWm1tA0jZWtmI3pAwKRGQIY1d3BAbvyUjo0wEDkoCihuk8p0lN8haF2D8hGC3YZdqz+h60jTC01vgOXiqPxCn+5q8YPY+8n8YzRhjsswrrJQYDCMwgslpRkpz0p61gPA+R1M1bBp01Zs3HgKwjf+DMefm5VEy/Z+PsZFCMBz+57Ggb1PS5tZ/xCI8Mg93wQIuOfOr4pc9j/9PUwOGgzaZB600+ux4c3/L6Zf9moo96tUxkijXTiOeN8X0VzwEzh44jju3nULvvf9RzFcGCBgg2eyywhjDQ58iEj6bFcZplORYx44dvUh5ctVR6dpRic/y38N2+2LN6cvdz3wcyJZu5C/ulRrDM8NQBRUOfHGkXRdgcEAEPpLZhMj8AClyXHa6bkOspDcOELrNQ+3mpR6hpGyAeMsbPpOGFO+gglkofMKTrXWcn6FiTNyjUoIOOXUbekA/oNPoRvqWo+/bSAALz55LX7v/3mDzc7JwpZGbyLXbfkbZyYxmJzG2n/8cxi89Edx3/1fx95nnswb1kQ4quiQ0p+amsGrX7MT6y94E8LEAMcPHcOBZ/fmOy8GUhh22i8njDU4NKZNyzqzmRGy4JvQ5MUv0dy2nYL1P0hicInxUIZH6yJuMaj5CEGNXIvqOEa/knaQEDOLEeDFPgtR+oQekvEg47hgaq91c1OGfIO58WQZHe3YA9v/tfKxMzFA2ZMzWWwxndDsdDSX0fo7Qq/d7V9fjkSrTznldIQj+9E9830MuwxS6DXR8wqDpsG2DWtUQdhy5DrzWaDWudjmi5dABEzOYPJF5+DpvU/igQe/jmPH0vLntDGOAV/lykrp1M0vxgUvvwjN3CGcfPJmbDz5VBw9fhixC7nv8JhYXhhrhyTbreyk4oUy9hrzEEI64CRvxOHNP5ZpyEEoIcgSY+52suY/BAGgsjNakyaVi9JKP3PLd113sMazg7Uf+jjS14bGMWD+6TtSDr7/MoS8Oam+KIadW6U97//Z+JQptC0jZfOAL+Eh6dTs0NSq9cuSqtVUtF3hkHw+o9rs//i/AQocAiBL4bWCQfoikPuHeYcdkNwF0h0shInJaQzy0fQWmJ0xEQJ4Vu57Tz6C+XwNwMzkJM4++wLMTK8R+NQy/BCYFZHt1wBQl+6kYA0n8+aBtw/zGQTIJyaPoOQ5sFZzwCCNi558rUlsG1A6ewhLLv+1AMG0XUDMDEjGgnRgipobJUsvLaQEfnnKy/xIosmsZq5YuLlMymJUS/sZBE7LdPiQpisTm+L0VeszaAEk+zz0fT7mz5aJJC8+U7LuFzGzUgAQIw4efAbh7PMwcfo5mDjwLcTiIublhmpLNi3adRvRrlmDML0OEy96KZqJdGpX3PsY5p54EPHonNavoE4BAXTiKOafuB+bLvwxbN56Bo4em83nhvbzt91w/zPfw1Pf/w62n3EO2vnjOOus87Bv3248+uhj6OYhZsVywXCswQFCVYN2/NwbY3FmgBWJ9DVOgwcJVNgMBlYpu4VB8JpVUVwRWmhc4BOZzN2VnFJh0ljPfozlLEbpG0h5RUaM7HzkpfZcK7toRqbGgN4pVU6wbJ6IHcJ5GbOBtJ5NE8whNJ4V2LISIMCQY6Y7TDPzcns+JHd1oPrpVq8MvJxCT7Y8jfvod76Nl738Ymw4/42Y+d4jOHLgmF5uXMjDgW3t2WACoR2g3XAa2nUnYXD6SzH5skuAyWmgHWAI4MTCPNp2AtMXvgmTj34Vx776/+HYoeMi356yIcKJh+/G9PmX4eT1p+CJ0ALog4OVDxDQdQv4P9/6Mk466WSctmkzppoG55zzo3jqe3twZD4z6Xza9nLCWIODc0IKvdROh8CUTXUqrw2QBU+8/C8HNXfVw9zwZxmZ1iFoUCaRSgEoPmQmdXZ9VnrRlQ0oDfXp+rjuuykjlzmww8q8y1cBWnoqtoNWOTsnWWJk2AKcHe0mEZg1uOQqwyo3EVmfTzYdtJwBOtEUJO+ERLldRTRk0tUZEQsIg3aQ117oVYaHDz+He+/Zhde+5k2Yeu0/QffVP8fc4TllUhasJaEJNFPTSQYT02i3nIXB2pPQvvg8tGvWImzYiti2oNBg3/6n8NRj92NhYR7PHdiLY8cOYzAxiZec8yN42cvegDVzhxG/9hc4fiydw8G6yuHD/BwoDg1IjmCc3J657AcP7sOXv/Tfcf4rLsVpp70Iz+7/frpvE23qnY068ZcKYw0OafOKUe0AWIzcSewOzTSuvec+3S7t0615uIPE9R3W0n/OnzWnLL4SDey12uigcfuzHPa7odYZfORWioYQIpsohnLDP1PtqoyFq5KOkLdj0QMJF0QBtVITU87RXVyHhp3NYBPGmguM/7LaE8mPlDDDz+AQpV2P/bwIDz/4bUy0G3HRRT+GtTMb0N7zZSzMzirdn5zBYNtL0U5NAU1Ac9rZaNZvSllOTIGm1mEYI46fOI5Ds8/h6BMPYd++J3H8+BEceHYP5udPaL1yOb/9rb/GmnUbcNZ5P441+59E9+C9GC7Uj8VvT96CMDGN4XDBnM9JRVwDKVmfEBFmZ5/FnV+7BRMTk3n36wwCZtAOJjAxEXp3pY4KYw0OdgpKOnrT5NvgPUNgyEj2aVpOzESgdMiVgzfmwz0sTU3HNQaJb6k0e6G93a6/89qMGiuo+QnYJ8DpgGskfcWaAB5MWJvCvs4+ghFlY3mq3CwwqIkmMUo7xzkra1RHaQehf7ksUT6ghc81qLAQa86IKQaz5V1WUkZJz5qXsevwwL33INI8fuRHL8Gaba/A9HBecgrtAF0zwNzCPEDpsNf9+7+P+fz9wLNP49DsARw/dhhzc8fQdcO0eUxkyfalttiwm8c37/4iJi57G170hp/H+tO+guP378KJZ9J5ESy0sGY9Zi56E+bm5/DU07vRxfKMqXogA+SgiPn5E0k2lAAyxg7D4UI6V2MZYazBQRbz5A7KZwS0PHtgYFYZtFJRq/JqHvv0XoqUtgrz2LKgYLQiO+ECv2MGVJG8UniMjDPKdq8BC5fVLosWEiF3iRZlz3a2LYO9CLe0431m1ofAB5h0xtzol69my4cMpBEWBBKI994ruLf6dIxDlHUAv2nlwYnl5Luuw/333Imnnrof204/G4N2wnIYHHxuHw4dehYEoBsu4PjcUdgFdH0trukLQIB0j04Ajh49hDu/9gVcdPFOvPgVO7H2nNdi5tE7E0g8+yzC9ElY85qfRLv1bNzzra9g/4Gns0/JJD4iOH8MoCxSAJ7bdDHWqmGswQFQ6s62MJAcdC3glta6dwC+OMlpMnuqUM8TD8iWWV3HXgrZ0mM7iNnUKE8tAvoA4GcK7AIl/ptYS7ZUQ8ojiaGixaFatnR8cqftMx+7tkDpPKFW51SmruuEhZFW3pRFzRZCyBfeQsod7TsB6EgPg7Esr0xSrvgrfpSaylH8+Wmm5zyQYgT2P7MHz+7bq2AHiCOZSRkbbJoy78XoiSOVRzidxk/pBxw5cgS7/uYL2LLlLJz78ouw9RU/gbXn7sCa2WeA6fWgdZvw5JOP4NFHH8TCQgSoNZWqMDHLdJ0csiuXGhN9ecAAjDk46Bx4gBmXKZAXhA7EoNpjhKD6WpLc4LCzGyiy1VcLQCIPOvxmnxnUAEfT1bUJepoTDzBYAGCzgfgC3jQT0IhaK+6flLskzMnGdhVXHp2y0CnoUGFQYJo/HHbOPiKkBTXMSqxCswPV+m0cxjXZHChOk7KB8+f1FPKcgtzanRhOutSXQrL1G6xFgzX9Qa5F0b5jzCGAQa5fFtsvqHjGoQOw+8gePLX7Nmw9/UU4a/t2bN66DQtzR/Dw176MJx5/AifmAoANvSKVedjfa8+fbxhvcIA5i7AcjDC3XuXYllaTW75o0mS6nVOxgyMf3JN+qTkUC83sO7lFr37TuQUypRbMv3VdRNsy9QeACDJrPaxZkBNDZ8wi+5vFMDsrwQ+VFms8pdOsS/PAz4DVdUN0nR6ZL3IrZCMyCKpfG57OTMX2J3cxkJOWD+L7MGYS0qGyjA1pWtfXlxdiASfQhecA6EnO1pDRMjOYKej62JVhyIQiBANs9eEaMY+nnnoQe/Y8jOmZGXTDBZw4kU6LRsv9r9/XaliWpEIFQpg2a+br/XZEGG9waILQfA7cyXkwSCO5xiHl/ZQZSOaPTWM2ORkhNwj9Uw2Y648qn1u8YxxnBUWWWRUwPbeDNaBtg4ANO+/4d/YlsI1kdCa4lyQ2wJuUisVSVnbw/clVFbaqefAY4OGbowSAnRrLWp13WAam7lrvpmkxwbdxZ7CnmO5wSDLJt3JL+ciUKQNrojSQmQyRC3I5U7qp9BEdHXagaNemNBasAb2Fm/MVGQc/BtkECyHfZZkvkSn7n/2W5Ti3kI6ubybSMz6uv4cNnJc1p1jkpUnHtpEUssFy8WGswYGXKbtBSvlY8qZOsVh43PkAoFwNWJ1qDEEPcmGwseZFBSh4ADgC44dmvz4VP8Zw2GXbOsXp3PRc0D9Z44I8E+Et2JFimt7k2+OEKCtdrl0dXwZHl7PzkkGNWYAe+gLAsBatnvHq5zYRJ2hIp0mlU5a9LNQdaBmhbvgi0sVvrHV78GdMBmZ32jzZvwFlLP590SkCSbYcLEMZqEZmXpGZ3zxB63+Rrq3tVHeK574rVTNM8HkYGmMNDrGLbhYBQB74druyF7jMoVvfAZEXav7rGIkan0pm+Qg2yVdf9o5QW0IGJG07HmBRpt+Q4yhD4NOcgnQwNpMSQ+GBxWcxyjZr1sQCZKyJdBA4PCJd8MSAlEtj8lZBsZzl9by3xfV4O5sgo8eyI8LCcCHvIFSZcBLpb7q41y52Y38FL3iTYwPZscwmRalIWQ6AkQvXMrMPAwQQnCk1viaqteW29m2eWwz1YAyaoP2xFni2JIGo9gMug8zg2b63zHUNZRhrcBBHFuC1OP9OvKKBoHvMNB4PlEjJSRVCQAfW9rHXGSSv4LsCoHRSnmVHoCma1xBGa3FZS0boc7Dxk0NSNlDxKcaSBiGgUw0ndNl3uBq9JNG+AUQNFIQYzWpX1Gn35uXVysaME1jfBMy0bwh8OGr0ip007wRkZhNWRnKKBGoVVJ2OLDQv78YVmDSgGUzGDJjBv240MrdlHwhUQlpI+bUib84goN4e9qVy7YmWw4AL8i5aMm9SWv+T+sKIMlTCWIMD63BuCvtUtDnxSkkvZOKWZrs05JuIhkM3iBzdzH9h0oZ9ZpiF8gtyGj6/DB7ofeejJF+loPxdb6mG6eRWg9vC57UO2vuTzFRQhWyU4qe7N1UaIXjNmsqc28GUQauV0usv2U29V+vJzkcdWOLIy7Ln3bQJW7ScTNf5sFaVGtms0iDMIKdnKUjVnGxYpXgGUDSFcXbDxCWIUhcGqgu16pv+ODnbpoW0DIJUlFO1gLmtcldkvF4uQIw5OKj2p7LCZB1WEFsWpODAaB4abUT+54Ag+xukWXi05yDPuGWZ0YhZYLV3OfB7xYZt4BHRwIMpdgSesdAVhZDeIvk2wfXxIikzEPSd1LsjUB6QI0nxhis7E5TJbVHu0sQSHdh5MOH6W5OHlWPI7E/bKt2iZZlAetcPRDWl+N26DGBMFscWuF2Dmc40KmCkUFHxXUmoKCB+k/r9QJmFYUbuReso9RA5MqMlwniDg9Xe5Kkha0R7EV1JN4U42J5pzRMZ7CaujRfY7w3Xu0WfyIBhoNBdmboQKpjO2qeQi30nyk7A/FPsdIViDxzMgOmnqfqspKlpcOSj5sV0SiCQ6tdiMAC6bqijmN80RXbOuWAAwvZdA57pJ8OG7GwMMw6QTp0KS1NtbhWD9y0UAzyXm6dTtfi+Dsxn9HuA7XL6YhA2Y4NbY2N+s83vB7WmT65fBSNT488I0u2LfgUB2Z4SXSSMNTik2YrcgZz3FmDtpXqckNz0EIE7BxEVWGuAIeTPDhhsXJNGLoQMSOv0ZHtek1anYoqTaLvXor1c3OE2bB8xG7Gv8DZoR+krncMOSP5e6fKyrZmX5bKsB4MBYp52jF2n2tbKhWziVgNDTT/eQEV2a7trMAlRTJiIGPWQYQdcwuvtoONi8FBXZtU2bWJYlHfr2rnrEQRgFH+wiodZK5tFHV/gY8oiTIG0ryCkKXT5LUgUgBkRIKt9ew5P6fz2WgLqyWJUGG9wEMrIg9IgqGUHZqCzsADkc/4xctWdz6wPCKF4Xgu24cv1GHquAWs9yHblklbawFfaMXMqNZxoL9SXhBeKUz4vNd2VZMkdkZlPSj8BRD6BizeqmcTVecxyUPC0p3OlsgZz5oaaY8pc4Do5Y0Jh7Wn9XGEskwz+VDAuQwBCbEDBDuLSs7WEpGQ+0wCllDOYQ3FNmracAeJADSHnnZWLVVxFlcwfnb0QWVFAaOp9qhbGGhxkysZSVqGKwqtTmwi1JrNHIkVx4iocj8E8T5G9xvPlGRXUHq5jCbML/lyJRIwHUaY1RXsYrZx8I8p1y2mxNGVbgonrSrbU7td+iaXQqiGF/lq7vV8fSsVFkw8JboLugxFAZcLgWIGZZXDsK4ONKROAfAcpmfFkVbb/SpEQGt2uVDoP3dhdBk6wBNhZyiyuZz4Z5eH7ojKTNqQDjCLbBbnu1qy0B9DamiqoU+7fywO58QYHORlUAUHmvfNzppeqlSzlqzdyCQ7BaF8Cknp3L4TeZ+7ksnFLfAy9nKRcI7kr02KrhQQtysIHR2cpUl70VAEIU2TRNlR0UtNBa7KSuQXr/6kE96o0QGrDtPw7Gi2OfMQjN5DaFESZOZl0ieBOvnIWDTNLqVMBg8HHlbR7+BmMLFRuRQIVDZEdp8O8/mSQGYp5lS0kAQkrIPh2EwA0pXPmhcva+FqC1ny5YazBIWnQ1jjb4LilAEPDJzDxaDK0Tzq9tfWzBgx552JGkTQfH514xbQwlN02bm0xS3+9ARntIU9deuJTMEwg9kDH88u0ziOtikynb5MMyF6Z8nt6c6NPs89iDT8IwGDQIsYBFohAeRm1yBKmmwu2JSnFSApOGQzSYCH3vpWVZs9MIcJuf5f0CGIu9ExH005lWV0k97lgpeiRj977RNm/Ekz7McqYQ8hI8regnfKRk8hikxGgkiMzAweMleosHxvGGxzU/8c0VAmTOvyCHPtNNKzKNVkbwTUgwHSMEENQ9uAzrigLHuDmfkqXV9DyVlrKOQcdMFRus7XaYwQLUs3B9zOYvIRh8UAs0w89IEhReOE1U/okm7Zt3SpHru/ifhmVIMvWFqO6WtDgg5oc6THviWDHaNsk5SEDkt9tQj58mlA7hN3JwjSy6WHmU/khvaSAlZkPmz+5IOVeHb9nJudh/waO49lxTb6unxbl+6FwSAK53dh8KP0EgABD1w1di/PAF++5sdfkChdK3nkiQsNLgg3lDpURaSmf1fbyO/nfF4Vyp5bMysQRJoWfITEgZ+xSN1BcRr4GNl7NRtUhpR14YjBIeyxitEkBLWBnILg/2ylWO61qx3HZpnbqmu/TUIdmk/Z1EJA2RRvK3RiPfU6RJ3G8T0MlwuddeFPV1tmJLJdP0xQ5mlOo1DSwjcvrajiNkBke/2oOUZapVp7WrQED9ftGpQ2XCmMNDiE7svI3ec5AHwBxBvGFstoFEwi0MB0wg4FLJwNAJCqunjMKhTt54RxVFlGUr9Kg6XXbYdQsYRs8WtMHFnTScz1urV/I0iSxFSkwyA2EnlYUrW3OGcoYGZom7ayMsbdPgjoP4DxPKBIl/o1P9xJ3Xq9buzUTME6+fF5oAB/048HZOxj9gT5ufQSgMzKkQlBnNzOiXP5R4y4wK81nashCNA+SrERygg6iGJxY2HpKdz4wt8YOyu5Vo5TLCOMNDrZRlWM6W3nYdUbbGw1uW5R0zcCiBLj4PZh/i73DZdVntRZ0NQMfviKsUeYQWSvoZ+crceBiyoGCnrNhbhgTv5UNBrixkeMKGAKAHD+XtHLXdfmOUkC2qxvG0rYNuq4zDIIcfSfkac2QbeuYSxKMHADXvqJNeSBKXXlTXImCKnthRswejQCYrxhs0Hcsi1i0w3ggEyXVmkNvyjYLPgEml7xfApmBNG3jd75yhrmM4n8ok1xBGHNw0KPgvAC8mWDpl2UOCPYIOMMsSm64VCGYflpPWD3yIr+pJrG0Oz3nQeIdlrYTWBbDOfHgdt8ze0iO2qK+ppQ2WLiRdQCcRv6PiDCcX8iXr/CMCSdg1qmaAcNXszEL0mPTScdxzthp1ywLwC7wygM8pJWo8K5V0fZ8poSrR6Wd1VnZ/y1oJAW/JlTA2ZQx582HuzqlNoLF+YVkELkmvRCEScRyXUn+3bEaKdbyoWJFezm7rsMHP/hBbN++HTMzMzjnnHPwW7/1W4VNTfjQhz6E008/HTMzM9i5cyceeeQRl86BAwdw1VVXYf369di4cSPe/e5348iRIyspCoAkKu6krgNDKWAuVW5HbjwDGKQX7sqzoGpIxyK5zymzEpIWl31wvWp0ray2tPZwbRm0yoCLpmwiKRrTOc0N42ls1CzRggvZombNxZu4WPOmKcAsx6wN7T4V/o23y8vCLRhR595t35O+XRWXMgeWVZOvPcykx4xdBVW5S4R8OvVgLwQy8jfMxYprlN+1adNBNoNBm2VjD++tcU/TgBZvcnTX30PITCu1i6wbaRo9haqo5nL9DysCh4985CP45Cc/if/0n/4THnjgAXzkIx/BRz/6Udx0000S56Mf/ShuvPFGfOpTn8Idd9yBtWvX4vLLL8fc3JzEueqqq3Dffffh1ltvxec//3l8+ctfxtVXX72SogAoZRZkELEPIPkjFheEX7hT74dUAYZaqosN+eWGGiAAehQbayLbUd3qPqgmLju39igZMpUCjKgcF84Eoa5Mj0nXPPDZCnqKtWE9AgR5wxiEazhwIHmHwaRfYp8XSTlsmXz+3vPfCDKxStH+I2tUUPQ1BojA5TarYL04wGtNeNbM3qlqKiH9UJbZlzVmfaQvSVnsgj82O7h+zwcUOKzIrPjqV7+Kt7/97bjiiisAAGeffTb+23/7b7jzzjtzHQkf//jH8YEPfABvf/vbAQB/9Ed/hC1btuBzn/scrrzySjzwwAO45ZZbcNddd+GSSy4BANx0001429veho997GPYtm3b8gvkNJBqUB5cIQur68hrfqFnFYZg0ubnpTHA79pxpDMDPhkd5LCxl1E5ps5KQRML4EVDOZZZpiuDDv2yiJYnPZjWzhQs7tgiYRmue5m8zCNnOohtnSkAkZoMTNJs/xcxUSV9Yq2pz7qukwN004t6BkVfk5seEIIxY7i8uZ0o+XvYHyDgZRkECAhNvg6BB3RPOCBKO0ebaPZu2CFu+iXZd81fgu1nJm0QQGXfcs2W6mrYQ+g14uiwIubwute9DrfddhsefvhhAMC3v/1tfOUrX8Fb3/pWAMDjjz+OPXv2YOfOnfLOhg0bcOmll2LXrl0AgF27dmHjxo0CDACwc+dONE2DO+64o5rviRMnMDs76/6lkDfstA2aNt+QXayV5zssrNaTwW3oePnXxu/1sSrycwcrY5vDU0dy5EJ7hdDLIj33TIgHfCWmKZoOTvGwM90vNHsCASsD9AVTyU81PWRASd7yjn3RMJxiwJbo44BrJKPRJknOSLhRYKcpEwYE9b0ED3tafKO5exYAgzby+pclRhul3aNu+ZwAvldm9ZRUnmTNksy+esBeIpVLdPnsYUXM4dd//dcxOzuL8847D23bous6/M7v/A6uuuoqAMCePXsAAFu2bHHvbdmyRX7bs2cPNm/e7AsxGGDTpk0Spww33HADfuM3fqP/A5sPTba32oR1fOp0ctip04acd86nI6ZF0/SXELuopTcDhrpqHP7rtgGb3/JrI0BAf/PTdpXyGIDQfQnamWJMy5IbqIZkmqtlsY7OfkYyeKzaKehUFyMoxuR3sCdH23SCiBo65grTh82LXu9mttcva5PXNzALYTKVZGEPA+I4+ZnYF6SAYEGeQbXRNud+kQkGhOJoCU2bpvSJkGTTdQjtAIyBfOO7FTm5b/2w1DJ1iVfKMBilsRziihUyhz/5kz/BZz7zGfzxH/8xvvGNb+DTn/40Pvaxj+HTn/70SpJZcbj++utx6NAh+ffkk08WMYJZBMM2HTvIitu23cgm+et0vsK5dDL+2wsGSCwZLBf4iPJzzq1abYvOb7oNU3LvHBula4xJEoypsZyeobZBr64JtXz9IAPKyMO+K3VvoHeNuJrB+hds3XvOQPtiYABI51YOh126dYuPn88DmxdJ2TGnsy0KBqqVo9j9KsPgiibSZB9UUGWgbEQZGQHZKdu5OqqVYNKq/OsJc5HgxFgD/WWShxUxh1/91V/Fr//6r+PKK68EAFx44YV44okncMMNN+Bd73oXtm7dCgDYu3cvTj/9dHlv7969eNWrXgUA2Lp1K/bt2+fSHQ6HOHDggLxfhqmpKUxNTfWeq4aGadhgQF+HQupc7E0HRoGo7eScuDr6zDsls2BtzcxCHFrpjkI30yDavcdB3HdxcrkGDnoWYlZf1uZUep87q7llyy+7hevYi4ZiIEufzwNGjlB3g9gWuT8wm9Dofgdic0BlYn0LdvNYaAJCZ8+xJCdLytuSraxZWVjzJFgmVeBgwj/SPmIO97Udp2wxMWdkdBaCLZkUTBrL1OY9ytYLDEa+gGo6lcpndFgRczh27FjvLMC2bWWKavv27di6dStuu+02+X12dhZ33HEHduzYAQDYsWMHDh48iLvvvlvi3H777Ygx4tJLL11JcaC1D6K9iGIWjEHhssMKgtaZAEZ0dGLKbO+RrPUstumppMeefSyi+KV+UqcYlR4X/Nxt0XZygaeTIpAynxqT8REtS2HqHbsOw27oDuPlqTWr7VmbsjNU/SCW/RSF4oEG1aqMJfbyXM0zm2MguR1cZrB4UIfgWF2kWLSRKYfkr9OGYnKYEa1Nn+KKmSfiso5ybzrBpf5/MwTf5sKCqN8/FgkrYg4/9VM/hd/5nd/BmWeeiVe84hX45je/if/wH/4DfuEXfiEVKQS8733vw2//9m/j3HPPxfbt2/HBD34Q27Ztwzve8Q4AwPnnn4+f/MmfxHve8x586lOfwsLCAq677jpceeWVK5upgGoNWTOfuaSn8PZzYFbsR2XFv1DumyjZQiD/BlN+6dC8F0M6blMMkiigWgYZ9zDYMwLuuRMIgc2dVwapVfsmfln2UeWwHY3/L7qJ9CBakUwIQCjuSQjBHA+vmp41rSxLt4yuWiaCOy3V4HK6pyTkdiGoT8GwENK0tS0g9j8Hvn9TccIPND491hfR9xcnQwcKLIMCeLnOiymLnkgq7GSx1wnV6/tGhRWBw0033YQPfvCDeO9734t9+/Zh27Zt+Jf/8l/iQx/6kMT5tV/7NRw9ehRXX301Dh48iDe84Q245ZZbMD09LXE+85nP4LrrrsOb3/xmNE2Dd77znbjxxhtXUhQAyJRdD9HIT20MMKsAMp1t/M+lacCaBbbBYOg6+uAiAxks/NRRxEcgfpCsXRZtz/JHUlCiIlbwh5uITsqDuinsbCICBTL7UUaUIDDSWnDz8shI5P0LrCFhzCtfYJMHejtdCaQr+2xdg70C0JaRy6kuR4Uwo8VZjK61A5qmdTeDc7oMGv3RyHrX+iq0Praqth9x1Ql66IstV2BGg7KMXma2PJq3MjaXf1Cvh69B2elHh0DLcX2+wMLs7Cw2bNiAm278FczMTKJpGrSDgbcJkTsga7rsZFLAINV4pB0USCva0lfT+UeBg+lEkrPxOyB37KbwXRAv2ikat1x7oHdGWgmw1jR7QnJdyFz5xicsSbEaXYgjMxmLIJVOCTfal01BYoxYWFhwzynW5cX5dZktMWgiy0LZhAdPgztgYFU5avvIrdgZEIKAow5kPXMzoB20GLRtmmWxpkIeUZpuzpzQG5BEtt0MWzMDH0HlyJ+bvN7B9xdllP2ZGm1zNmUsKDuzyulGk5JRfC855xK86c3vxKFDh7B+/XqMCuO9t6IJefrSaDr+f+4gJXxyY0biziVMOKOtUn8JPTCvoLnrX6TX28OzDp+c1QS5D5J/Vs0/lz1mu18qXVMKRg52hkNMGqPhPUuiNP3JtN/YzTXNzu+VAM0Vsaaei0HlMXbofXfVMSCrMmKQz+ABGc+uJElEKY4wEVJ58mevv60GZjCq1MWAi2MsPaBTn0spC2EU1tpkO2ARFe6d3SYzUWCU9/2sjAeMNTgAgGzekQZjvQkgQM4mjFDhpbh596CkY6crs4YRTZPj5P/bwWQZB8fhXZcyKBcpvwUUG1PBgpHLvyHaAz79VPy+A1boMgjIG3VgtReKgU9M1m0euT7mUpveYGUZAOKXqelB6bjFAKkuL4YOrPKz5Elk/AbBtW2ewJLsuK1dyWTQa4uYsSWxI7MMBgEjHfnE7MeAvfxfTs619e9DmKucC6H2sB9s4XOnX4wl1sLYg0OGYPmsx7vnBpMr2HWUBuipSDy9Z2mrmhM5fh6kju7Ca3n7HODttYSmSYfN2AYtlYO8a6rCIOY1MQnwMHBpmUweTluZThGMc9FpZ9X8krkUwtatcDQW6aSszQSy+a1pgBj7B8CWYOGXMxvtGiwgkginCcHIxJQzwAwQHrRqYlm5MIOsD7o0kEXbI8hN5X6QO2iH+0YA8lV/iARqoEcPSnzui7TEZcb1MhoMkMCwQ1mOsip0VNJFGG9wELsrAYIgeG7oAPSuhUudpkFD6TRfsNMQecC7y2yNzizdvEtQNGaoOvCKgZq1vrcb4QsL1XSpTKmUqgWDjIlMGFDeWlLO95dAUD5LHbkGeuVpSOkv3/OgGtI4KAs5hZBWF1CuWDkG2BCz9rQFTJsms4XQtmgDKueD+kFQTSeXdylFLCsmoTMZVVddyClSrk1A0ZfS3zSR5VmQzroZGfey8A+0X9h8LWNaPhDUwliDA/djCwy1OF6m6rwJaEzDJ9jl7duAGVDg7c69xEZkmIvjOrkl3Pl7FWA8/WMGlMpC+eBrQsPrS+waA5O+t0PzeoMQ5PwLOdw0FNq8p9V5IPKSY/2F03YelRJD7V+RJ3SAmzx1MOk6EtWGHhjlR2TTMZh3KlLlAQggnxjFB9m6BMukXaj6U/rZ5FKmBXnOrGAG0QQQad9L62dI2YcKpsIeuSx9gGKfjywWZ1/D8wxjDQ4SKtgwqnFV6YW0BMxQUioGRmKmCRza0JozCZYACBPSQRzBNbYrk60GsYe84mACA2EqmWiNHCnk963GZOcqYAcp6XuWTvfqb8qa5SvmFb8SVePJvyVkE3J5WfNz+bWOfiORsi1T1sBtY4qXWZPgiAs6QAWYYkyzMHwydaXYWgz7IzPVEtu9xk+y6BuPZP7HM0ssxxACkx7Pxoqdl0EQRJ85pgVPkxa1UhYJ/wDAgTVQKFhEqHQSjyPsa2C3mwxK69wi0t105AeN2HOlVsumAExasrUa/U6llkbdKebjq3ZsmwZEETDHrkvd2KcCHRBd7IBoQENGuZbe55fLI72L/Tn9zkbw4CLlMbaulZktr2CQYVoubVseKGhbeXBePIaCvGfoAfm8YLa++7RGnw6e8gEgBpJPw4GtHcCuO5qpSwOGMrDNgCfoidpFKXr1t7WQN4ypYuWznDD24GDtLb4enrWcDQq2Ot/rtSzSEfQhyLSP6BvbqTgFY36QEDmfX5WGmk6nLEDrYYGiDwymztlmbUKDLvAVaZy3FYAZzPwhpK3s6g4zaAczYItRzPUR5yCzkD4/97KwFNjIXMtETr62d1veI7MzwZTdFtSUT3076Rm3Ebdpei87pGy/GFkLU8Pc17wzlvue7y/6G4TiB0rnbWquNgcdyFnl9Z2+0q8UVPqFJbcQqoqBS4SxBwduFNFOthP3YwJIjQNzu1LSMgHgfRlGejWtrZ8MyvMPPZSQ9XRgveDTXqSBJV7mJzxgGDRksFgGg+xfaPRYtpyB78qjMvRajtPVVRsAd1oum18jMKr8rtKmHAYkFgl29ogssytLH1hD5nZhmRHyyVU2HcCfy7l46DWts/nKegQrJSl3QD7dslifUjK9JlfGzqT9bYLhMMsOYw0O4uQTbcSauCk0h1+PIIIKrIVSJ4pdMGkwI8gmg1UbSwQZWFmZy2FNhuWUoKDMQZvPe+wzAzDUmzuSHfasb0ITdPemLZvQ+9HdRGhzMDQ3d+DqGgQ5BZmqaVugiabCbnGYpUlGgJKi+B1YDsFFTWXV/xzzyEqdF0m51Y/uNGqXYqUGhpAZWVgfjtFA0i8zOUrlD3myN7dlOaUuMkVAE1Tmulzc9gGVbM1BqYkZpbYCB+U/AHAwi40Ca80EELKkGJBGsyK1y05BQGgbhJi8yYB28jQdyg2fhyN7uyUtWzLbyI4AGoCw7ERj1OsI6Uz2WZpzD9mxxzmkvGPFD+EeBNb/Rb65jrq8t+/kk45o1ZGM6+C+5xdS0nmzWch14OPd2BZW/KXa6w5AWAuTeZ/LSIBuMDJ1Zfn7tRhAubAgx/QDXQAnmPQK0UlHs78Wxhulpd5kvmsCkBPB+VYVdwZGLz+dPRoFDLa/m0IuK4w3OLDGCiRaEtzp8lxd6R+wwa8tMHcY9tYKwKVhzRYzxPlXY/OaTpLL0gcHXqPhcnQpp2oZYDAd3w1vy0h6nVQKrtp1ZHAQ2gNT+yoRuXMs+cRjNs+kSKztshztzIzcBakq1kuDAYAIndHW1n9hB65KwQ8Mbl+nc0VjVwafMIrGgX+wv1fHGoFnGKzJZ4GeIcq8ksyerIgoLwZL51za8lk26RXLouzheYTxBgekaaAIQmgN3e467Tg1xIXVxKxR9Nh2O6J1LNoBy4PEUkRNP9mJjev0eluVUuPEQIBy9aUP9ofRDW+1oWpOcvRXkhPnBaAnvdrsgh98VnMzvR9RFmEBxrYH9NJfu+Q7BD02n1kAsryqbccOY0nYAqWyQOekFP7Dd3z42SHHCCy9XCQIRyP7gIoXU16U62n9MoQogCdvsCMz+6hi9FO6wWSz2PgPKgBFkOcZxhocgDQV1MTUsXip9Eg3vwmx6zAEMGiT0GOMaVqpxwVYA1rmYO1NjQlAOnUIQXYzEhHQlesjDD3m8RnsdCwciLgFPr0xI0TYpc28IpgB4HSkLbsZS+prMXlYzeUplKPovK6jNIPkXEmWh5h/loD3x2VICbjn3g/IcmGQDzl+ZUWnYWksb2Z66VmpAMoCWVpi56jqfU1jaIEtY0xLv/O5H2KumPdlh2uQU7+UJZKT8ehgeRJ6fWexMNbgsHbtBszMTMnWZOu8KacqeyF3zjZvz44UEwtxwqZ8lJlvCEuFKb8nTRCAEJo0VWjAoYvm0FXy+dhOah2p6VQrOGDguHb6kNmJAAm0DzhnFgNEMEzDjTo7jpR52Xx5BBOl6bjYdc4h13XRlMXIsQC6gHwiN8tI6qDlNzyo4E9WZYfMQBT2bDvJzIXDtlL26VUZjCJtLxxDbFy5TCv4vBHyUfTppS6DJAA51zIdhswmjzERkHYct+0g9SUBYgj4EZHb9i/ycYyjAPkQMDk1jeWEsQQHrvzFr34L1q1bV4lR4vWIUCJ1L59FXzXvUO8Xy96FDvrUR6S4WJwUr+QJywvPj17at+zg6LMU/7Uvu3p5aw5MDw79cpR1rznrqi8uJywm1hq1WSyUeYtZscgOyerjvpIbKf9lFGpubj69uQTrGEtwePbZZwEAF1/yYz/gkqyG1TC+4fDhw9iwYcPI38cSHDZt2gQA2L1796KVWw0rD7OzszjjjDPw5JNPLnpK0GpYWXghyZWIcPjw4SXPbB1LcOA9/xs2bPiBC/ofali/fv2qbP8OwgtFrstRqis6mn41rIbV8MMTVsFhNayG1VANYwkOU1NT+Lf/9t9Wb8FaDX+7sCrbv5swjnIdy6PpV8NqWA1/92EsmcNqWA2r4e8+rILDalgNq6EaVsFhNayG1VANq+CwGlbDaqiGVXBYDathNVTDWILDJz7xCZx99tmYnp7GpZdeijvvvPMHXaQXdLjhhhvwmte8BieddBI2b96Md7zjHXjooYdcnLm5OVx77bU45ZRTsG7dOrzzne/E3r17XZzdu3fjiiuuwJo1a7B582b86q/+KobD4d9nVV7Q4Xd/93cRQsD73vc+eTbWcqUxC5/97GdpcnKS/vAP/5Duu+8+es973kMbN26kvXv3/qCL9oINl19+Od18881077330re+9S1629veRmeeeSYdOXJE4vziL/4inXHGGXTbbbfR17/+dbrsssvoda97nfw+HA7pla98Je3cuZO++c1v0he+8AU69dRT6frrr/9BVOkFF+688046++yz6Ud+5Efol37pl+T5OMt17MDhta99LV177bXyves62rZtG91www0/wFKNV9i3bx8BoL/+678mIqKDBw/SxMQE/emf/qnEeeCBBwgA7dq1i4iIvvCFL1DTNLRnzx6J88lPfpLWr19PJ06c+PutwAssHD58mM4991y69dZb6Y1vfKOAw7jLdazMivn5edx9993YuXOnPGuaBjt37sSuXbt+gCUbr3Do0CEAurv17rvvxsLCgpPreeedhzPPPFPkumvXLlx44YXYsmWLxLn88ssxOzuL++677++x9C+8cO211+KKK65w8gPGX65jtStz//796LrOCRIAtmzZggcffPAHVKrxCjFGvO9978PrX/96vPKVrwQA7NmzB5OTk9i4caOLu2XLFuzZs0fi1OTOv/2whs9+9rP4xje+gbvuuqv327jLdazAYTX87cO1116Le++9F1/5yld+0EUZ+/Dkk0/il37pl3Drrbdienp5R6+NUxgrs+LUU09F27Y9b+/evXuxdevWH1Cpxidcd911+PznP4+/+qu/wotf/GJ5vnXrVszPz+PgwYMuvpXr1q1bq3Ln334Yw9133419+/bh1a9+NQaDAQaDAf76r/8aN954IwaDAbZs2TLWch0rcJicnMTFF1+M2267TZ7FGHHbbbdhx44dP8CSvbADEeG6667Dn/3Zn+H222/H9u3b3e8XX3wxJiYmnFwfeugh7N69W+S6Y8cO3HPPPdi3b5/EufXWW7F+/XpccMEFfz8VeYGFN7/5zbjnnnvwrW99S/5dcskluOqqq+TzWMv1B+oOfR7hs5/9LE1NTdF/+S//he6//366+uqraePGjc7buxp8uOaaa2jDhg30pS99iZ5++mn5d+zYMYnzi7/4i3TmmWfS7bffTl//+tdpx44dtGPHDvmdp9ze8pa30Le+9S265ZZb6LTTTntBTLm9kIKdrSAab7mOHTgQEd1000105pln0uTkJL32ta+lr33taz/oIr2gA+TcY//v5ptvljjHjx+n9773vXTyySfTmjVr6Kd/+qfp6aefdul897vfpbe+9a00MzNDp556Kv3Kr/wKLSws/D3X5oUdSnAYZ7munuewGlbDaqiGsfI5rIbVsBr+/sIqOKyG1bAaqmEVHFbDalgN1bAKDqthNayGalgFh9WwGlZDNayCw2pYDauhGlbBYTWshtVQDavgsBpWw2qohlVwWA2rYTVUwyo4rIbVsBqqYRUcVsNqWA3V8P8DS/30MNQpL2AAAAAASUVORK5CYII=",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.imshow(display_frame[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[332., 685., 468., 749.],\n",
+       "       [ 84., 110., 150., 251.]], dtype=float32)"
+      ]
+     },
+     "execution_count": 56,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1 x1 (left, lower pixel number)\n",
+    "# 2 y1 (top , lower pixel number)\n",
+    "# 3 x2 (right, higher pixel number)\n",
+    "# 4 y2 (bottom, higher pixel number)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# 1 x1 (left, lower pixel number)\n",
+    "# 2 y1 (top , lower pixel number)\n",
+    "# 3 x2 (right, higher pixel number)\n",
+    "# 4 y2 (bottom, higher pixel number)\n",
+    "my_bboxes = predictions[30].pred_instances.bboxes[predictions[30].pred_instances.scores.argsort()][::-1][predictions[30].pred_instances.scores[predictions[30].pred_instances.scores.argsort()[::-1]] > 0.5]\n",
+    "my_bboxes\n",
+    "\n",
+    "# Size of a box\n",
+    "box_size = np.linalg.norm(my_bboxes[0,[0,1]] - my_bboxes[0, [2,3]])\n",
+    "\n",
+    "# Middle of a box\n",
+    "box_middle1 = np.array([(my_bboxes[0, 2] + my_bboxes[0, 0]) / 2, (my_bboxes[0, 3] + my_bboxes[0, 1]) / 2])\n",
+    "box_middle2 = np.array([(my_bboxes[1, 2] + my_bboxes[1, 0]) / 2, (my_bboxes[1, 3] + my_bboxes[1, 1]) / 2])\n",
+    "distance = np.linalg.norm(box_middle1 - box_middle2)\n",
+    "print(box_middle1)\n",
+    "print(box_middle2)\n",
+    "print(distance)\n",
+    "\n",
+    "# Distance ratio\n",
+    "distance / box_size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[400. 717.]\n",
+      "[117.  180.5]\n",
+      "606.5651242859253\n"
+     ]
+    }
+   ],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "4.035525587766196"
+      ]
+     },
+     "execution_count": 76,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "distance / box_size"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([468., 749.], dtype=float32)"
+      ]
+     },
+     "execution_count": 66,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "my_bboxes[0, [2,3]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from matplotlib import pyplot as plt\n",
+    "def process_video(input_video, out_fps = 'auto', skip_frames = 7):\n",
+    "    cap = cv2.VideoCapture(input_video)\n",
+    "\n",
+    "    output_path = \"notebook_out_vid.mp4\"\n",
+    "    if out_fps != 'auto' and type(out_fps) == int:\n",
+    "        fps = int(out_fps)\n",
+    "    else:\n",
+    "        fps = int(cap.get(cv2.CAP_PROP_FPS))\n",
+    "        if out_fps == 'auto':\n",
+    "            fps = int(fps / skip_frames)\n",
+    "    print(fps)\n",
+    "    #width  = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))\n",
+    "    #height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))\n",
+    "\n",
+    "    # video = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*\"mp4v\"), fps, (width, height))\n",
+    "    results = []\n",
+    "    frames = []\n",
+    "    iterating, frame = cap.read()\n",
+    "    cnt = 0\n",
+    "    print('starting video processing')\n",
+    "    while iterating:\n",
+    "        if (cnt % skip_frames) == 0:\n",
+    "            #print('cnt')\n",
+    "            # flip frame vertically\n",
+    "            _ , result = inference_frame_serial(frame, visualize = False)\n",
+    "            # Extract information from results\n",
+    "            results.append(result.numpy())\n",
+    "            frames.append(frame)\n",
+    "            # Add extra plot that is result related\n",
+    "\n",
+    "            # video.write(cv2.cvtColor(display_frame, cv2.COLOR_BGR2RGB))\n",
+    "            # yield cv2.cvtColor(display_frame, cv2.COLOR_BGR2RGB), cv2.cvtColor(frame, cv2.COLOR_BGR2RGB), None\n",
+    "            # return result.numpy(), frame\n",
+    "        cnt += 1\n",
+    "        iterating, frame = cap.read()\n",
+    "    \n",
+    "    # video.release()\n",
+    "    return results, frames"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import inference\n",
+    "def get_visualization_from_frame(frame, result):\n",
+    "    # flip frame vertically\n",
+    "    #display_frame = inference.visualizer.draw_result(frame, result)\n",
+    "    # Extract information from results\n",
+    "\n",
+    "    inference.visualizer.add_datasample(\n",
+    "            'result',\n",
+    "            frame,\n",
+    "            data_sample=result,\n",
+    "            draw_gt = None,\n",
+    "            show=False\n",
+    "            )\n",
+    "    display_frame = visualizer.get_image()\n",
+    "\n",
+    "    display_frame = cv2.cvtColor(display_frame, cv2.COLOR_BGR2RGB)\n",
+    "    return display_frame"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n",
+      "starting video processing\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/afengler/miniconda3/envs/openmmlab2/lib/python3.8/site-packages/torch/functional.py:504: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at ../aten/src/ATen/native/TensorShape.cpp:3483.)\n",
+      "  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]\n"
+     ]
+    }
+   ],
+   "source": [
+    "predictions, frames = process_video('videos_example/421.mp4')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([42])"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].pred_instances.labels[predictions[0].pred_instances.scores.argsort()][::-1][predictions[0].pred_instances.scores[predictions[0].pred_instances.scores.argsort()[::-1]] > 0.5]\n",
+    "#predictions[0].pred_instances.scores[predictions[0].pred_instances.scores.argsort()[::-1]] > 0.5"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 52,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def get_top_predictions(prediction = None, threshold = 0.7):\n",
+    "    if prediction is None:\n",
+    "        return None, None\n",
+    "    else:\n",
+    "        sorted_scores_ids = prediction.pred_instances.scores.argsort()[::-1]\n",
+    "        sorted_scores = prediction.pred_instances.scores[sorted_scores_ids]\n",
+    "        sorted_predictions = prediction.pred_instances.labels[sorted_scores_ids]\n",
+    "        return {'pred_above_thresh': sorted_predictions[sorted_scores > threshold], \n",
+    "                'pred_above_thresh_id': sorted_scores_ids[sorted_scores > threshold],\n",
+    "                'pred_above_thresh_scores': sorted_scores[sorted_scores > threshold],\n",
+    "                'pred_above_thresh_bboxes': prediction.pred_instances['bboxes'][sorted_scores_ids][sorted_scores > threshold]}\n",
+    "    \n",
+    "def add_class_labels(top_pred = {}, class_labels = None):\n",
+    "    if class_labels == None:\n",
+    "        print('No class labels provided, returning original dictionary')\n",
+    "        return top_pred\n",
+    "    else:\n",
+    "        top_pred['pred_above_thresh_labels'] = [class_labels[x].lower() for x in top_pred['pred_above_thresh']]\n",
+    "        top_pred['any_detection'] = len(top_pred['pred_above_thresh_labels']) > 0\n",
+    "        if top_pred['any_detection']:\n",
+    "            # Get shark / human / unknown vectors\n",
+    "            top_pred['is_shark'] = np.array([1 if 'shark' in x else 0 for x in top_pred['pred_above_thresh_labels']])\n",
+    "            top_pred['is_human'] = np.array([1 if 'person' in x else 1 if 'surfer' in x else 0 for x in top_pred['pred_above_thresh_labels']])\n",
+    "            top_pred['is_unknown'] = np.array([1 if 'unidentifiable' in x else 0 for x in top_pred['pred_above_thresh_labels']])\n",
+    "            # Get shark / human / unknown  numbers of detections\n",
+    "            top_pred['shark_n'] = np.sum(top_pred['is_shark'])\n",
+    "            top_pred['human_n'] = np.sum(top_pred['is_human'])\n",
+    "            top_pred['unknown_n'] = np.sum(top_pred['is_unknown'])\n",
+    "        return top_pred\n",
+    "\n",
+    "def add_class_sizes(top_pred = {}, class_sizes = None):\n",
+    "    size_list = []\n",
+    "    if top_pred['any_detection']:\n",
+    "        for tmp_pred in top_pred['pred_above_thresh_labels']:\n",
+    "                tmp_class_sizes = class_sizes[tmp_pred.lower()]\n",
+    "                if tmp_class_sizes == None:\n",
+    "                    size_list.append(None)\n",
+    "                else:\n",
+    "                    size_list.append(tmp_class_sizes['feet'])\n",
+    "\n",
+    "        top_pred['pred_above_thresh_sizes'] = size_list\n",
+    "    else:\n",
+    "        top_pred['pred_above_thresh_sizes'] = None\n",
+    "    return top_pred\n",
+    "\n",
+    "def add_class_weights(top_pred = {}, class_weights = None):\n",
+    "    size_list = []\n",
+    "    if top_pred['any_detection']:\n",
+    "        for tmp_pred in top_pred['pred_above_thresh_labels']:\n",
+    "                tmp_class_weights = class_weights[tmp_pred.lower()]\n",
+    "                if tmp_class_weights == None:\n",
+    "                    size_list.append(None)\n",
+    "                else:\n",
+    "                    size_list.append(tmp_class_weights['pounds'])\n",
+    "\n",
+    "        top_pred['pred_above_thresh_weights'] = size_list\n",
+    "    else:\n",
+    "        top_pred['pred_above_thresh_weights'] = None\n",
+    "    return top_pred\n",
+    "\n",
+    "# Sizes\n",
+    "def get_min_distance_shark_person(top_pred, class_sizes = None, dangerous_distance = 100):\n",
+    "    min_dist = 99999\n",
+    "    dist_calculated = False\n",
+    "    # Calculate distance for every pairing of human and shark\n",
+    "    # and accumulate the min distance\n",
+    "    for i, tmp_shark in enumerate(top_pred['is_shark']):\n",
+    "        for j, tmp_person in enumerate(top_pred['is_human']):\n",
+    "            if tmp_shark == 1 and tmp_person == 1:\n",
+    "                dist_calculated = True\n",
+    "                print(top_pred['pred_above_thresh_bboxes'][i])\n",
+    "                print(top_pred['pred_above_thresh_bboxes'][j])\n",
+    "                tmp_dist_feed = _calculate_dist_estimate(top_pred['pred_above_thresh_bboxes'][i], \n",
+    "                                                         top_pred['pred_above_thresh_bboxes'][j], \n",
+    "                                                         [top_pred['pred_above_thresh_labels'][i], top_pred['pred_above_thresh_labels'][j]],\n",
+    "                                                         class_sizes,\n",
+    "                                                         measurement = 'feet')\n",
+    "                print(tmp_dist_feed)\n",
+    "                min_dist = min(min_dist, tmp_dist_feed)\n",
+    "            else:\n",
+    "                pass\n",
+    "    return {'min_dist': str(round(min_dist,1)) + ' feet', \n",
+    "            'any_dist_calculated': dist_calculated, \n",
+    "            'dangerous_dist': min_dist < dangerous_distance}\n",
+    "\n",
+    "def _calculate_dist_estimate(bbox1, bbox2, labels, class_sizes = None, measurement = 'feet'):\n",
+    "    class_feet_size_mean = np.array([class_sizes[labels[0]][measurement][0], \n",
+    "                                     class_sizes[labels[1]][measurement][0]]).mean()\n",
+    "    box_pixel_size_mean = np.array([np.linalg.norm(bbox1[[0, 1]] - bbox1[[2, 3]]), \n",
+    "                                    np.linalg.norm(bbox2[[0, 1]] - bbox2[[2, 3]])]).mean()\n",
+    "    \n",
+    "    # Calculate the max size of the two boxes\n",
+    "    box_center_1 = np.array([(bbox1[2] - bbox1[0])/2 + bbox1[0], \n",
+    "                             (bbox1[3] - bbox1[1])/2 + bbox1[1]])\n",
+    "    box_center_2 = np.array([(bbox2[2] - bbox2[0])/2 + bbox2[0], \n",
+    "                             (bbox2[3] - bbox2[1])/2 + bbox2[1]])\n",
+    "    \n",
+    "    # Return ratio distance\n",
+    "    return np.linalg.norm(box_center_1 - box_center_2) / box_pixel_size_mean * class_feet_size_mean\n",
+    "\n",
+    "# bboxes info!\n",
+    "# 1 x1 (left, lower pixel number)\n",
+    "# 2 y1 (top , lower pixel number)\n",
+    "# 3 x2 (right, higher pixel number)\n",
+    "# 4 y2 (bottom, higher pixel number)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 54,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[ 84. 110. 150. 251.]\n",
+      "[332. 685. 468. 749.]\n",
+      "24.184207818187375\n"
+     ]
+    }
+   ],
+   "source": [
+    "top_pred = get_top_predictions(predictions[30], threshold = 0.5)\n",
+    "top_pred = add_class_labels(top_pred, class_labels = classes)\n",
+    "top_pred = add_class_sizes(top_pred, class_sizes = class_sizes_lower)\n",
+    "top_pred = add_class_weights(top_pred, class_weights = class_sizes_lower)\n",
+    "min_dist = get_min_distance_shark_person(top_pred, class_sizes = class_sizes_lower)\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'pred_above_thresh': array([31, 42]),\n",
+       " 'pred_above_thresh_id': array([21,  2]),\n",
+       " 'pred_above_thresh_scores': array([0.9908303 , 0.98758847], dtype=float32),\n",
+       " 'pred_above_thresh_bboxes': array([[332., 685., 468., 749.],\n",
+       "        [ 84., 110., 150., 251.]], dtype=float32),\n",
+       " 'pred_above_thresh_labels': ['surfer', 'copper shark'],\n",
+       " 'any_detection': True,\n",
+       " 'is_shark': array([0, 1]),\n",
+       " 'is_human': array([1, 0]),\n",
+       " 'is_unknown': array([0, 0]),\n",
+       " 'shark_n': 1,\n",
+       " 'human_n': 1,\n",
+       " 'unknown_n': 0,\n",
+       " 'pred_above_thresh_sizes': [[5, 7], [7.2, 10.8]],\n",
+       " 'pred_above_thresh_weights': [[110, 300], [290, 660]]}"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "top_pred"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.0003097057342529297\n"
+     ]
+    }
+   ],
+   "source": [
+    "from time import time\n",
+    "start = time()\n",
+    "out = get_top_predictions(predictions[0], threshold = 0.5)\n",
+    "print(time() - start)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "out_w_classes = add_class_labels(top_k_pred = out, class_labels = classes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'pred_above_thresh': array([42]),\n",
+       " 'pred_above_thresh_id': array([7]),\n",
+       " 'pred_above_thresh_scores': array([0.98792475], dtype=float32),\n",
+       " 'pred_above_thresh_bboxes': array([[0., 0., 0., 0.]], dtype=float32),\n",
+       " 'pred_above_thresh_labels': ['Copper shark']}"
+      ]
+     },
+     "execution_count": 38,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "out_w_classes"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sorted_scores_ids = predictions[0].pred_instances.scores.argsort()[::-1]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([ 7, 31, 63, 74, 38, 71, 72, 62, 97, 50, 32, 75, 76, 92, 70, 91, 98,\n",
+       "       64, 55, 37, 73, 54, 49, 99, 65, 89, 90, 26, 20, 21, 22, 23, 24, 25,\n",
+       "       77, 18, 27, 28, 29, 30, 95, 94, 33, 19, 17, 35, 16,  1,  2,  3,  4,\n",
+       "        5,  6, 96,  8,  9, 10, 11, 12, 13, 14, 15, 34, 93, 36, 78, 58, 59,\n",
+       "       60, 61, 85, 84, 83, 66, 67, 68, 69, 82, 81, 80, 79, 57, 56, 86, 45,\n",
+       "       39, 40, 41, 42, 43, 44, 46, 87, 47, 48, 88, 51, 52, 53,  0])"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sorted_scores_ids"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[110.,   0., 177.,  78.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   1., 443.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 439.,   1., 443.],\n",
+       "       [  0., 439.,   1., 443.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 439.,   1., 443.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 439.,   1., 443.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 439.,   2., 450.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 439.,   2., 443.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0., 440.,   1., 443.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.]], dtype=float32)"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].pred_instances['bboxes'][sorted_scores_ids]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def check_human():\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7ff3a40e8af0>"
+      ]
+     },
+     "execution_count": 37,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1000x1000 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax, fig = plt.subplots(1,1, figsize=(10,10))\n",
+    "vis_out = get_visualization_from_frame(frames[30], predictions[30])\n",
+    "plt.imshow(vis_out)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "ValueError",
+     "evalue": "19 is not in list",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[53], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m classes\u001b[39m.\u001b[39;49mindex(\u001b[39m19\u001b[39;49m)\n",
+      "\u001b[0;31mValueError\u001b[0m: 19 is not in list"
+     ]
+    }
+   ],
+   "source": [
+    "classes.index(19)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Great white shark'"
+      ]
+     },
+     "execution_count": 57,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classes[41]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "0.98792475"
+      ]
+     },
+     "execution_count": 67,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].pred_instances.scores.max()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       0.0000000e+00, 0.0000000e+00, 0.0000000e+00, 0.0000000e+00,\n",
+       "       6.6777538e-06, 3.6635574e-05, 9.8758847e-01, 9.9083030e-01],\n",
+       "      dtype=float32)"
+      ]
+     },
+     "execution_count": 86,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "pred_id = 30\n",
+    "predictions[pred_id].pred_instances.scores[predictions[pred_id].pred_instances.scores.argsort()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([[  0.,   0.,   0.,   0.],\n",
+       "       [ 84., 110., 150., 251.],\n",
+       "       [ 84., 110., 150., 251.],\n",
+       "       [ 84., 110., 150., 251.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [332., 685., 468., 749.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.],\n",
+       "       [  0.,   0.,   0.,   0.]], dtype=float32)"
+      ]
+     },
+     "execution_count": 87,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[pred_id].pred_instances['bboxes']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<matplotlib.image.AxesImage at 0x7ff3a4d61d30>"
+      ]
+     },
+     "execution_count": 36,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.imshow(predictions[30].pred_panoptic_seg.sem_seg.squeeze())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([29, 42, 38, 31, 42, 29, 29, 38, 31, 38, 37, 31, 29, 31, 29, 29, 31,\n",
+       "       19, 29, 29, 31, 37, 38, 29, 29, 31, 29, 42, 19, 29, 19, 42, 38, 31,\n",
+       "       31, 31, 29, 31, 29, 24, 23, 19, 18, 17, 15,  4, 31, 42, 38, 31, 29,\n",
+       "       19, 31, 30, 29, 31, 33, 29, 31, 29, 42, 29, 42, 52, 32, 29, 46, 45,\n",
+       "       42, 38, 37, 36, 51, 19, 31, 31, 31, 29, 29, 38, 29, 42, 29, 31, 29,\n",
+       "       19, 31, 31, 29, 42, 31, 29, 29, 31, 29, 31, 42, 31, 19, 42])"
+      ]
+     },
+     "execution_count": 52,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].pred_instances.labels[predictions[0].pred_instances.scores.argsort()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([29, 42, 38, 31, 42, 29, 29, 38, 31, 38, 37, 31, 29, 31, 29, 29, 31,\n",
+       "       19, 29, 29, 31, 37, 38, 29, 29, 31, 29, 42, 19, 29, 19, 42, 38, 31,\n",
+       "       31, 31, 29, 31, 29, 24, 23, 19, 18, 17, 15,  4, 31, 42, 38, 31, 29,\n",
+       "       19, 31, 30, 29, 31, 33, 29, 31, 29, 42, 29, 42, 52, 32, 29, 46, 45,\n",
+       "       42, 38, 37, 36, 51, 19, 31, 31, 31, 29, 29, 38, 29, 42, 29, 31, 29,\n",
+       "       19, 31, 31, 29, 42, 31, 29, 29, 31, 29, 31, 42, 31, 19, 42])"
+      ]
+     },
+     "execution_count": 48,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].pred_instances.labels[predictions[0].pred_instances.scores.argsort()]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n",
+      "starting video processing\n",
+      "cnt\n",
+      "inference time: 0.12380337715148926\n",
+      "cnt\n",
+      "inference time: 0.11678862571716309\n",
+      "cnt\n",
+      "inference time: 0.11650824546813965\n",
+      "cnt\n",
+      "inference time: 0.11769247055053711\n",
+      "cnt\n",
+      "inference time: 0.11684751510620117\n",
+      "cnt\n",
+      "inference time: 0.1162269115447998\n",
+      "cnt\n",
+      "inference time: 0.11634016036987305\n",
+      "cnt\n",
+      "inference time: 0.1202244758605957\n",
+      "cnt\n",
+      "inference time: 0.1183769702911377\n",
+      "cnt\n",
+      "inference time: 0.1299581527709961\n",
+      "cnt\n",
+      "inference time: 0.11743426322937012\n",
+      "cnt\n",
+      "inference time: 0.12219834327697754\n",
+      "cnt\n",
+      "inference time: 0.11864471435546875\n",
+      "cnt\n",
+      "inference time: 0.11449122428894043\n",
+      "cnt\n",
+      "inference time: 0.11762261390686035\n",
+      "cnt\n",
+      "inference time: 0.11699914932250977\n",
+      "cnt\n",
+      "inference time: 0.12010049819946289\n",
+      "cnt\n",
+      "inference time: 0.12456440925598145\n",
+      "cnt\n",
+      "inference time: 0.11442089080810547\n",
+      "cnt\n",
+      "inference time: 0.11470508575439453\n",
+      "cnt\n",
+      "inference time: 0.12778210639953613\n",
+      "cnt\n",
+      "inference time: 0.11521315574645996\n",
+      "cnt\n",
+      "inference time: 0.11485767364501953\n",
+      "cnt\n",
+      "inference time: 0.12177467346191406\n",
+      "cnt\n",
+      "inference time: 0.11919307708740234\n",
+      "cnt\n",
+      "inference time: 0.1186685562133789\n",
+      "cnt\n",
+      "inference time: 0.11728978157043457\n",
+      "cnt\n",
+      "inference time: 0.12287211418151855\n",
+      "cnt\n",
+      "inference time: 0.11699318885803223\n",
+      "cnt\n",
+      "inference time: 0.11656665802001953\n",
+      "cnt\n",
+      "inference time: 0.11511421203613281\n",
+      "cnt\n",
+      "inference time: 0.11572575569152832\n",
+      "cnt\n",
+      "inference time: 0.11873674392700195\n",
+      "cnt\n",
+      "inference time: 0.11640024185180664\n",
+      "cnt\n",
+      "inference time: 0.11746740341186523\n",
+      "cnt\n",
+      "inference time: 0.1138458251953125\n",
+      "cnt\n",
+      "inference time: 0.1144263744354248\n",
+      "cnt\n",
+      "inference time: 0.11664700508117676\n",
+      "cnt\n",
+      "inference time: 0.11377954483032227\n",
+      "cnt\n",
+      "inference time: 0.1199030876159668\n",
+      "cnt\n",
+      "inference time: 0.11610555648803711\n",
+      "cnt\n",
+      "inference time: 0.11810922622680664\n",
+      "cnt\n",
+      "inference time: 0.11631608009338379\n",
+      "cnt\n",
+      "inference time: 0.11767840385437012\n",
+      "cnt\n",
+      "inference time: 0.12981843948364258\n",
+      "cnt\n",
+      "inference time: 0.11835265159606934\n",
+      "cnt\n",
+      "inference time: 0.11403799057006836\n",
+      "cnt\n",
+      "inference time: 0.11367321014404297\n",
+      "cnt\n",
+      "inference time: 0.11405324935913086\n",
+      "cnt\n",
+      "inference time: 0.11571669578552246\n",
+      "cnt\n",
+      "inference time: 0.1159203052520752\n",
+      "cnt\n",
+      "inference time: 0.1146693229675293\n",
+      "cnt\n",
+      "inference time: 0.11692118644714355\n",
+      "cnt\n",
+      "inference time: 0.11452150344848633\n",
+      "cnt\n",
+      "inference time: 0.11449575424194336\n",
+      "cnt\n",
+      "inference time: 0.11450338363647461\n",
+      "cnt\n",
+      "inference time: 0.11399507522583008\n",
+      "cnt\n",
+      "inference time: 0.11494684219360352\n",
+      "cnt\n",
+      "inference time: 0.12058711051940918\n",
+      "cnt\n",
+      "inference time: 0.12075018882751465\n",
+      "cnt\n",
+      "inference time: 0.1308131217956543\n",
+      "cnt\n",
+      "inference time: 0.11942124366760254\n",
+      "cnt\n",
+      "inference time: 0.11772751808166504\n",
+      "cnt\n",
+      "inference time: 0.11690902709960938\n",
+      "cnt\n",
+      "inference time: 0.11471176147460938\n",
+      "cnt\n",
+      "inference time: 0.1154329776763916\n",
+      "cnt\n",
+      "inference time: 0.11524581909179688\n",
+      "cnt\n",
+      "inference time: 0.11603093147277832\n",
+      "cnt\n",
+      "inference time: 0.1160879135131836\n",
+      "cnt\n",
+      "inference time: 0.11653423309326172\n",
+      "cnt\n",
+      "inference time: 0.11598634719848633\n",
+      "cnt\n",
+      "inference time: 0.11627054214477539\n",
+      "cnt\n",
+      "inference time: 0.11559891700744629\n",
+      "cnt\n",
+      "inference time: 0.1334848403930664\n",
+      "cnt\n",
+      "inference time: 0.11968493461608887\n",
+      "cnt\n",
+      "inference time: 0.11601519584655762\n",
+      "cnt\n",
+      "inference time: 0.11872100830078125\n",
+      "cnt\n",
+      "inference time: 0.11769819259643555\n",
+      "cnt\n",
+      "inference time: 0.11771655082702637\n",
+      "cnt\n",
+      "inference time: 0.11706733703613281\n",
+      "cnt\n",
+      "inference time: 0.11946415901184082\n",
+      "cnt\n",
+      "inference time: 0.11474466323852539\n",
+      "cnt\n",
+      "inference time: 0.1155083179473877\n",
+      "cnt\n",
+      "inference time: 0.11459231376647949\n",
+      "cnt\n",
+      "inference time: 0.11599445343017578\n",
+      "cnt\n",
+      "inference time: 0.11560654640197754\n",
+      "cnt\n",
+      "inference time: 0.11449408531188965\n",
+      "cnt\n",
+      "inference time: 0.11349964141845703\n",
+      "cnt\n",
+      "inference time: 0.11626219749450684\n",
+      "cnt\n",
+      "inference time: 0.12293672561645508\n",
+      "cnt\n",
+      "inference time: 0.12233781814575195\n",
+      "cnt\n",
+      "inference time: 0.1271193027496338\n",
+      "cnt\n",
+      "inference time: 0.11648178100585938\n",
+      "cnt\n",
+      "inference time: 0.11496710777282715\n",
+      "cnt\n",
+      "inference time: 0.11387276649475098\n",
+      "cnt\n",
+      "inference time: 0.1288468837738037\n",
+      "cnt\n",
+      "inference time: 0.11928796768188477\n",
+      "cnt\n",
+      "inference time: 0.1192770004272461\n",
+      "cnt\n",
+      "inference time: 0.11447834968566895\n",
+      "cnt\n",
+      "inference time: 0.1377561092376709\n",
+      "cnt\n",
+      "inference time: 0.11706805229187012\n",
+      "cnt\n",
+      "inference time: 0.11950564384460449\n",
+      "cnt\n",
+      "inference time: 0.1165165901184082\n",
+      "cnt\n",
+      "inference time: 0.11652421951293945\n",
+      "cnt\n",
+      "inference time: 0.11539220809936523\n",
+      "cnt\n",
+      "inference time: 0.11482000350952148\n",
+      "cnt\n",
+      "inference time: 0.11398553848266602\n",
+      "cnt\n",
+      "inference time: 0.1271207332611084\n",
+      "cnt\n",
+      "inference time: 0.1306924819946289\n",
+      "cnt\n",
+      "inference time: 0.13226938247680664\n",
+      "cnt\n",
+      "inference time: 0.1137075424194336\n",
+      "cnt\n",
+      "inference time: 0.12101054191589355\n",
+      "cnt\n",
+      "inference time: 0.1148686408996582\n",
+      "cnt\n",
+      "inference time: 0.11342811584472656\n",
+      "cnt\n",
+      "inference time: 0.1188807487487793\n",
+      "cnt\n",
+      "inference time: 0.12050747871398926\n",
+      "cnt\n",
+      "inference time: 0.11515998840332031\n",
+      "cnt\n",
+      "inference time: 0.11525821685791016\n",
+      "cnt\n",
+      "inference time: 0.11676549911499023\n",
+      "cnt\n",
+      "inference time: 0.11527085304260254\n",
+      "cnt\n",
+      "inference time: 0.1175241470336914\n",
+      "cnt\n",
+      "inference time: 0.11507344245910645\n"
+     ]
+    }
+   ],
+   "source": [
+    "predictions, frames = process_video('videos_example/421.mp4')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'img_path': None,\n",
+       " 'batch_input_shape': (1344, 768),\n",
+       " 'ori_shape': (854, 480),\n",
+       " 'scale_factor': (1.5604166666666666, 1.5608899297423888),\n",
+       " 'pad_shape': (1344, 768),\n",
+       " 'img_id': 0,\n",
+       " 'img_shape': (1333, 749),\n",
+       " 'pred_panoptic_seg': {'sem_seg': array([[[133, 133, 133, ..., 133, 133, 133],\n",
+       "          [133, 133, 133, ..., 133, 133, 133],\n",
+       "          [133, 133, 133, ..., 133, 133, 133],\n",
+       "          ...,\n",
+       "          [133, 133, 133, ..., 133, 133, 133],\n",
+       "          [133, 133, 133, ..., 133, 133, 133],\n",
+       "          [133, 133, 133, ..., 133, 133, 133]]], dtype=int32)},\n",
+       " 'pred_instances': {'masks': array([[[False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          ...,\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False]],\n",
+       "  \n",
+       "         [[False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          ...,\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False]],\n",
+       "  \n",
+       "         [[False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          ...,\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False]],\n",
+       "  \n",
+       "         ...,\n",
+       "  \n",
+       "         [[False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          ...,\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False]],\n",
+       "  \n",
+       "         [[False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          ...,\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False]],\n",
+       "  \n",
+       "         [[False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          ...,\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False],\n",
+       "          [False, False, False, ..., False, False, False]]]),\n",
+       "  'scores': array([0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 9.87924755e-01,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 3.56690070e-05,\n",
+       "         1.47713909e-05, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 1.30976296e-05, 1.81958803e-05, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 1.23606969e-05, 1.50650985e-05, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 1.26034874e-05, 1.36501594e-05,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 1.56389324e-05, 2.11267688e-05,\n",
+       "         1.41684350e-05, 1.19253382e-05, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 1.44167125e-05, 1.71428474e-05,\n",
+       "         1.60817162e-05, 1.28836919e-05, 2.02543051e-05, 1.46638813e-05,\n",
+       "         1.46417187e-05, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 1.16120636e-05, 9.35017215e-06, 1.43166071e-05,\n",
+       "         1.45832946e-05, 0.00000000e+00, 0.00000000e+00, 0.00000000e+00,\n",
+       "         0.00000000e+00, 1.55185826e-05, 1.42834288e-05, 1.20311070e-05],\n",
+       "        dtype=float32),\n",
+       "  'labels': array([29, 31, 19, 29, 31, 38, 42, 42,  4, 15, 17, 18, 19, 23, 24, 29, 30,\n",
+       "         31, 32, 33, 36, 37, 38, 42, 45, 46, 51, 52, 42, 29, 42, 19, 42, 29,\n",
+       "         31, 29, 31, 29, 31, 29, 31, 29, 31, 37, 38, 29, 31, 29, 29, 29, 31,\n",
+       "         31, 38, 42, 29, 42, 19, 29, 31, 38, 42, 19, 29, 31, 29, 31, 29, 31,\n",
+       "         29, 29, 19, 29, 31, 38, 42, 29, 31, 29, 31, 29, 31, 37, 38, 42, 19,\n",
+       "         29, 31, 38, 42, 31, 19, 29, 31, 29, 31, 29, 31, 29, 31, 31]),\n",
+       "  'bboxes': array([[  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [110.,   0., 177.,  78.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 443.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 439.,   1., 443.],\n",
+       "         [  0., 439.,   1., 443.],\n",
+       "         [  0., 439.,   1., 443.],\n",
+       "         [  0., 439.,   1., 443.],\n",
+       "         [  0., 439.,   1., 443.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0., 440.,   1., 443.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0.,   0.,   0.,   0.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 439.,   2., 450.],\n",
+       "         [  0., 440.,   1., 443.]], dtype=float32)},\n",
+       " 'gt_instances': {'labels': array([], dtype=int64),\n",
+       "  'bboxes': array([], shape=(0, 4), dtype=float32)},\n",
+       " 'ignored_instances': {'labels': array([], dtype=int64),\n",
+       "  'bboxes': array([], shape=(0, 4), dtype=float32)}}"
+      ]
+     },
+     "execution_count": 9,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions.numpy().to_dict()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "dict_keys(['img_id', 'batch_input_shape', 'img_path', 'pad_shape', 'ori_shape', 'img_shape', 'scale_factor', 'ignored_instances', 'pred_instances', 'gt_instances', 'pred_panoptic_seg'])"
+      ]
+     },
+     "execution_count": 20,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].to_dict().keys()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "'dict' object has no attribute 'numpy'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[72], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m predictions[\u001b[39m0\u001b[39;49m][\u001b[39m0\u001b[39;49m]\u001b[39m.\u001b[39;49mnumpy()\n",
+      "\u001b[0;31mAttributeError\u001b[0m: 'dict' object has no attribute 'numpy'"
+     ]
+    }
+   ],
+   "source": [
+    "predictions[0][0]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "['__class__',\n",
+       " '__contains__',\n",
+       " '__delattr__',\n",
+       " '__delitem__',\n",
+       " '__dict__',\n",
+       " '__dir__',\n",
+       " '__doc__',\n",
+       " '__eq__',\n",
+       " '__format__',\n",
+       " '__ge__',\n",
+       " '__getattribute__',\n",
+       " '__gt__',\n",
+       " '__hash__',\n",
+       " '__init__',\n",
+       " '__init_subclass__',\n",
+       " '__le__',\n",
+       " '__lt__',\n",
+       " '__module__',\n",
+       " '__ne__',\n",
+       " '__new__',\n",
+       " '__reduce__',\n",
+       " '__reduce_ex__',\n",
+       " '__repr__',\n",
+       " '__setattr__',\n",
+       " '__sizeof__',\n",
+       " '__str__',\n",
+       " '__subclasshook__',\n",
+       " '__weakref__',\n",
+       " '_data_fields',\n",
+       " '_gt_instances',\n",
+       " '_ignored_instances',\n",
+       " '_metainfo_fields',\n",
+       " '_pred_instances',\n",
+       " '_pred_panoptic_seg',\n",
+       " 'all_items',\n",
+       " 'all_keys',\n",
+       " 'all_values',\n",
+       " 'batch_input_shape',\n",
+       " 'clone',\n",
+       " 'cpu',\n",
+       " 'cuda',\n",
+       " 'detach',\n",
+       " 'get',\n",
+       " 'gt_instances',\n",
+       " 'gt_panoptic_seg',\n",
+       " 'gt_sem_seg',\n",
+       " 'ignored_instances',\n",
+       " 'img_id',\n",
+       " 'img_path',\n",
+       " 'img_shape',\n",
+       " 'items',\n",
+       " 'keys',\n",
+       " 'metainfo',\n",
+       " 'metainfo_items',\n",
+       " 'metainfo_keys',\n",
+       " 'metainfo_values',\n",
+       " 'new',\n",
+       " 'npu',\n",
+       " 'numpy',\n",
+       " 'ori_shape',\n",
+       " 'pad_shape',\n",
+       " 'pop',\n",
+       " 'pred_instances',\n",
+       " 'pred_panoptic_seg',\n",
+       " 'pred_sem_seg',\n",
+       " 'proposals',\n",
+       " 'scale_factor',\n",
+       " 'set_data',\n",
+       " 'set_field',\n",
+       " 'set_metainfo',\n",
+       " 'to',\n",
+       " 'to_dict',\n",
+       " 'to_tensor',\n",
+       " 'update',\n",
+       " 'values']"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "dir(predictions[0])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([42], device='cuda:0')"
+      ]
+     },
+     "execution_count": 62,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].to_dict()['pred_instances']['labels'][predictions[0].to_dict()['pred_instances']['scores'] > 0.5]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'Nurse shark'"
+      ]
+     },
+     "execution_count": 60,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classes[4]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "tensor([[[133, 133, 133,  ..., 133, 133, 133],\n",
+       "         [133, 133, 133,  ..., 133, 133, 133],\n",
+       "         [133, 133, 133,  ..., 133, 133, 133],\n",
+       "         ...,\n",
+       "         [133, 133, 133,  ..., 133, 133, 133],\n",
+       "         [133, 133, 133,  ..., 133, 133, 133],\n",
+       "         [133, 133, 133,  ..., 133, 133, 133]]], device='cuda:0',\n",
+       "       dtype=torch.int32)"
+      ]
+     },
+     "execution_count": 50,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "predictions[0].to_dict()['pred_panoptic_seg']['sem_seg']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n",
+      "True\n",
+      "(854, 480, 3)\n"
+     ]
+    }
+   ],
+   "source": [
+    "process_video('videos_example/421.mp4')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "4\n",
+      "starting video processing\n",
+      "in iteration\n",
+      "inference time: 0.15168356895446777\n",
+      "sending frame\n",
+      "0\n",
+      "[[[231 237 239]\n",
+      "  [208 221 222]\n",
+      "  [168 191 191]\n",
+      "  ...\n",
+      "  [162 185 186]\n",
+      "  [203 216 216]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [171 194 195]\n",
+      "  [130 164 164]\n",
+      "  ...\n",
+      "  [122 155 156]\n",
+      "  [161 185 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [171 194 195]\n",
+      "  [130 164 164]\n",
+      "  ...\n",
+      "  [122 155 156]\n",
+      "  [161 185 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [168 191 193]\n",
+      "  ...\n",
+      "  [167 189 192]\n",
+      "  [206 218 220]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[190 218 183]\n",
+      "  [190 218 183]\n",
+      "  [191 219 184]\n",
+      "  ...\n",
+      "  [146 171 140]\n",
+      "  [146 171 140]\n",
+      "  [146 171 140]]\n",
+      "\n",
+      " [[190 218 183]\n",
+      "  [190 218 183]\n",
+      "  [190 218 183]\n",
+      "  ...\n",
+      "  [149 174 143]\n",
+      "  [150 175 144]\n",
+      "  [150 175 144]]\n",
+      "\n",
+      " [[190 218 183]\n",
+      "  [190 218 183]\n",
+      "  [188 216 181]\n",
+      "  ...\n",
+      "  [153 178 147]\n",
+      "  [156 181 150]\n",
+      "  [156 181 150]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[151 189 151]\n",
+      "  [151 189 151]\n",
+      "  [151 189 151]\n",
+      "  ...\n",
+      "  [134 162 139]\n",
+      "  [133 161 138]\n",
+      "  [133 161 138]]\n",
+      "\n",
+      " [[151 189 151]\n",
+      "  [151 189 151]\n",
+      "  [151 189 151]\n",
+      "  ...\n",
+      "  [134 162 139]\n",
+      "  [133 161 138]\n",
+      "  [133 161 138]]\n",
+      "\n",
+      " [[151 189 151]\n",
+      "  [151 189 151]\n",
+      "  [151 189 151]\n",
+      "  ...\n",
+      "  [134 162 139]\n",
+      "  [133 161 138]\n",
+      "  [133 161 138]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.11629343032836914\n",
+      "sending frame\n",
+      "7\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [169 193 193]\n",
+      "  ...\n",
+      "  [164 188 189]\n",
+      "  [203 216 217]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 167 167]\n",
+      "  ...\n",
+      "  [126 160 161]\n",
+      "  [164 187 188]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 197]\n",
+      "  [132 167 167]\n",
+      "  ...\n",
+      "  [128 161 162]\n",
+      "  [165 189 189]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [168 191 193]\n",
+      "  ...\n",
+      "  [167 189 191]\n",
+      "  [206 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[204 232 197]\n",
+      "  [204 232 197]\n",
+      "  [204 232 197]\n",
+      "  ...\n",
+      "  [165 190 159]\n",
+      "  [168 193 162]\n",
+      "  [171 196 165]]\n",
+      "\n",
+      " [[206 234 199]\n",
+      "  [206 234 199]\n",
+      "  [206 234 199]\n",
+      "  ...\n",
+      "  [165 190 159]\n",
+      "  [168 193 162]\n",
+      "  [171 196 165]]\n",
+      "\n",
+      " [[205 233 198]\n",
+      "  [205 233 198]\n",
+      "  [205 233 198]\n",
+      "  ...\n",
+      "  [166 191 160]\n",
+      "  [170 195 164]\n",
+      "  [173 198 167]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[156 188 155]\n",
+      "  [155 187 154]\n",
+      "  [155 187 154]\n",
+      "  ...\n",
+      "  [132 161 133]\n",
+      "  [132 161 133]\n",
+      "  [132 161 133]]\n",
+      "\n",
+      " [[156 188 155]\n",
+      "  [155 187 154]\n",
+      "  [155 187 154]\n",
+      "  ...\n",
+      "  [133 162 134]\n",
+      "  [133 162 134]\n",
+      "  [133 162 134]]\n",
+      "\n",
+      " [[156 188 155]\n",
+      "  [155 187 154]\n",
+      "  [155 187 154]\n",
+      "  ...\n",
+      "  [133 162 134]\n",
+      "  [133 162 134]\n",
+      "  [133 162 134]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.11545658111572266\n",
+      "sending frame\n",
+      "14\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [168 192 193]\n",
+      "  ...\n",
+      "  [165 189 189]\n",
+      "  [205 218 218]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [126 160 160]\n",
+      "  [166 189 189]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [126 160 160]\n",
+      "  [166 189 189]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 192 194]\n",
+      "  ...\n",
+      "  [167 189 191]\n",
+      "  [206 219 220]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[188 216 181]\n",
+      "  [188 216 181]\n",
+      "  [187 215 180]\n",
+      "  ...\n",
+      "  [180 206 170]\n",
+      "  [186 212 176]\n",
+      "  [189 215 179]]\n",
+      "\n",
+      " [[188 216 181]\n",
+      "  [188 216 181]\n",
+      "  [187 215 180]\n",
+      "  ...\n",
+      "  [180 206 170]\n",
+      "  [186 212 176]\n",
+      "  [189 215 179]]\n",
+      "\n",
+      " [[190 218 183]\n",
+      "  [190 218 183]\n",
+      "  [190 218 183]\n",
+      "  ...\n",
+      "  [180 206 170]\n",
+      "  [185 211 175]\n",
+      "  [191 217 181]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[169 202 166]\n",
+      "  [169 202 166]\n",
+      "  [168 201 165]\n",
+      "  ...\n",
+      "  [132 160 135]\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]]\n",
+      "\n",
+      " [[169 202 166]\n",
+      "  [169 202 166]\n",
+      "  [168 201 165]\n",
+      "  ...\n",
+      "  [129 157 132]\n",
+      "  [129 157 132]\n",
+      "  [129 157 132]]\n",
+      "\n",
+      " [[170 203 167]\n",
+      "  [170 203 167]\n",
+      "  [169 202 166]\n",
+      "  ...\n",
+      "  [129 157 132]\n",
+      "  [129 157 132]\n",
+      "  [129 157 132]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.12410187721252441\n",
+      "sending frame\n",
+      "21\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [168 192 192]\n",
+      "  ...\n",
+      "  [165 189 189]\n",
+      "  [204 217 217]\n",
+      "  [230 236 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 194 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [126 160 160]\n",
+      "  [166 189 189]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 194 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [126 160 160]\n",
+      "  [166 189 189]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 191 193]\n",
+      "  ...\n",
+      "  [166 189 191]\n",
+      "  [205 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[196 219 186]\n",
+      "  [196 219 186]\n",
+      "  [197 220 187]\n",
+      "  ...\n",
+      "  [192 218 182]\n",
+      "  [208 234 198]\n",
+      "  [192 218 182]]\n",
+      "\n",
+      " [[193 216 183]\n",
+      "  [193 216 183]\n",
+      "  [195 218 185]\n",
+      "  ...\n",
+      "  [192 218 182]\n",
+      "  [207 233 197]\n",
+      "  [192 218 182]]\n",
+      "\n",
+      " [[197 220 187]\n",
+      "  [197 220 187]\n",
+      "  [197 220 187]\n",
+      "  ...\n",
+      "  [187 213 177]\n",
+      "  [202 228 192]\n",
+      "  [195 221 185]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[165 198 162]\n",
+      "  [162 195 159]\n",
+      "  [161 194 158]\n",
+      "  ...\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]]\n",
+      "\n",
+      " [[165 198 162]\n",
+      "  [162 195 159]\n",
+      "  [161 194 158]\n",
+      "  ...\n",
+      "  [132 160 135]\n",
+      "  [132 160 135]\n",
+      "  [132 160 135]]\n",
+      "\n",
+      " [[165 198 162]\n",
+      "  [163 196 160]\n",
+      "  [162 195 159]\n",
+      "  ...\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.12969374656677246\n",
+      "sending frame\n",
+      "28\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [168 192 192]\n",
+      "  ...\n",
+      "  [164 188 188]\n",
+      "  [203 217 217]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [125 159 159]\n",
+      "  [164 187 187]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [125 159 159]\n",
+      "  [164 187 187]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 191 193]\n",
+      "  ...\n",
+      "  [166 189 191]\n",
+      "  [205 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[193 216 183]\n",
+      "  [193 216 183]\n",
+      "  [193 216 183]\n",
+      "  ...\n",
+      "  [173 199 163]\n",
+      "  [168 194 158]\n",
+      "  [167 193 157]]\n",
+      "\n",
+      " [[191 214 181]\n",
+      "  [191 214 181]\n",
+      "  [191 214 181]\n",
+      "  ...\n",
+      "  [173 199 163]\n",
+      "  [168 194 158]\n",
+      "  [168 194 158]]\n",
+      "\n",
+      " [[189 215 181]\n",
+      "  [189 215 181]\n",
+      "  [189 215 181]\n",
+      "  ...\n",
+      "  [174 200 164]\n",
+      "  [171 197 161]\n",
+      "  [171 197 161]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[156 188 155]\n",
+      "  [158 190 157]\n",
+      "  [158 190 157]\n",
+      "  ...\n",
+      "  [131 159 134]\n",
+      "  [126 154 129]\n",
+      "  [122 150 125]]\n",
+      "\n",
+      " [[156 188 155]\n",
+      "  [158 190 157]\n",
+      "  [158 190 157]\n",
+      "  ...\n",
+      "  [131 159 134]\n",
+      "  [124 152 127]\n",
+      "  [119 147 122]]\n",
+      "\n",
+      " [[156 188 155]\n",
+      "  [158 190 157]\n",
+      "  [158 190 157]\n",
+      "  ...\n",
+      "  [132 160 135]\n",
+      "  [124 152 127]\n",
+      "  [118 146 121]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.11776423454284668\n",
+      "sending frame\n",
+      "35\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [168 192 192]\n",
+      "  ...\n",
+      "  [161 184 185]\n",
+      "  [202 216 216]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [121 155 156]\n",
+      "  [162 186 186]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [122 156 157]\n",
+      "  [162 186 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 191 193]\n",
+      "  ...\n",
+      "  [167 189 191]\n",
+      "  [205 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[196 222 186]\n",
+      "  [196 222 186]\n",
+      "  [196 222 186]\n",
+      "  ...\n",
+      "  [145 170 139]\n",
+      "  [150 175 144]\n",
+      "  [157 182 151]]\n",
+      "\n",
+      " [[199 225 189]\n",
+      "  [199 225 189]\n",
+      "  [199 225 189]\n",
+      "  ...\n",
+      "  [145 170 139]\n",
+      "  [150 175 144]\n",
+      "  [157 182 151]]\n",
+      "\n",
+      " [[200 226 190]\n",
+      "  [200 226 190]\n",
+      "  [200 226 190]\n",
+      "  ...\n",
+      "  [146 171 140]\n",
+      "  [152 177 146]\n",
+      "  [158 183 152]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[162 194 161]\n",
+      "  [162 194 161]\n",
+      "  [161 193 160]\n",
+      "  ...\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]\n",
+      "  [131 159 134]]\n",
+      "\n",
+      " [[162 194 161]\n",
+      "  [162 194 161]\n",
+      "  [161 193 160]\n",
+      "  ...\n",
+      "  [132 160 135]\n",
+      "  [132 160 135]\n",
+      "  [132 160 135]]\n",
+      "\n",
+      " [[162 194 161]\n",
+      "  [162 194 161]\n",
+      "  [161 193 160]\n",
+      "  ...\n",
+      "  [133 161 136]\n",
+      "  [133 161 136]\n",
+      "  [133 161 136]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.11746597290039062\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/afengler/miniconda3/envs/openmmlab2/lib/python3.8/site-packages/mmengine/visualization/visualizer.py:741: UserWarning: Warning: The bbox is out of bounds, the drawn bbox may not be in the image\n",
+      "  warnings.warn(\n",
+      "/home/afengler/miniconda3/envs/openmmlab2/lib/python3.8/site-packages/mmengine/visualization/visualizer.py:812: UserWarning: Warning: The polygon is out of bounds, the drawn polygon may not be in the image\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "sending frame\n",
+      "42\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [170 193 194]\n",
+      "  ...\n",
+      "  [162 185 186]\n",
+      "  [202 215 216]\n",
+      "  [228 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [173 195 197]\n",
+      "  [134 167 168]\n",
+      "  ...\n",
+      "  [122 155 156]\n",
+      "  [161 184 185]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [173 195 197]\n",
+      "  [134 167 168]\n",
+      "  ...\n",
+      "  [122 155 156]\n",
+      "  [161 185 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 192 193]\n",
+      "  ...\n",
+      "  [167 189 191]\n",
+      "  [206 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[206 232 198]\n",
+      "  [206 232 198]\n",
+      "  [206 232 198]\n",
+      "  ...\n",
+      "  [143 168 137]\n",
+      "  [144 169 138]\n",
+      "  [150 175 144]]\n",
+      "\n",
+      " [[212 238 204]\n",
+      "  [212 238 204]\n",
+      "  [208 234 200]\n",
+      "  ...\n",
+      "  [143 168 137]\n",
+      "  [144 169 138]\n",
+      "  [150 175 144]]\n",
+      "\n",
+      " [[216 239 206]\n",
+      "  [215 238 205]\n",
+      "  [211 234 201]\n",
+      "  ...\n",
+      "  [143 168 137]\n",
+      "  [144 169 138]\n",
+      "  [150 175 144]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[166 200 159]\n",
+      "  [166 200 159]\n",
+      "  [167 201 160]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]]\n",
+      "\n",
+      " [[163 197 156]\n",
+      "  [163 197 156]\n",
+      "  [165 199 158]\n",
+      "  ...\n",
+      "  [134 162 137]\n",
+      "  [134 162 137]\n",
+      "  [134 162 137]]\n",
+      "\n",
+      " [[163 197 156]\n",
+      "  [163 197 156]\n",
+      "  [165 199 158]\n",
+      "  ...\n",
+      "  [136 164 139]\n",
+      "  [136 164 139]\n",
+      "  [136 164 139]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.12016749382019043\n",
+      "sending frame\n",
+      "49\n",
+      "[[[231 237 238]\n",
+      "  [208 220 221]\n",
+      "  [166 190 190]\n",
+      "  ...\n",
+      "  [161 185 186]\n",
+      "  [202 216 216]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [171 193 194]\n",
+      "  [128 161 162]\n",
+      "  ...\n",
+      "  [122 155 156]\n",
+      "  [161 185 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [171 193 194]\n",
+      "  [128 161 162]\n",
+      "  ...\n",
+      "  [122 156 157]\n",
+      "  [161 185 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 221 223]\n",
+      "  [168 191 192]\n",
+      "  ...\n",
+      "  [166 189 191]\n",
+      "  [205 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[188 211 178]\n",
+      "  [188 211 178]\n",
+      "  [188 211 178]\n",
+      "  ...\n",
+      "  [146 171 140]\n",
+      "  [144 169 138]\n",
+      "  [143 168 137]]\n",
+      "\n",
+      " [[186 209 176]\n",
+      "  [186 209 176]\n",
+      "  [186 209 176]\n",
+      "  ...\n",
+      "  [146 171 140]\n",
+      "  [144 169 138]\n",
+      "  [144 169 138]]\n",
+      "\n",
+      " [[184 207 174]\n",
+      "  [184 207 174]\n",
+      "  [184 207 174]\n",
+      "  ...\n",
+      "  [148 173 142]\n",
+      "  [146 171 140]\n",
+      "  [146 171 140]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[152 185 149]\n",
+      "  [152 185 149]\n",
+      "  [152 185 149]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]]\n",
+      "\n",
+      " [[153 186 150]\n",
+      "  [153 186 150]\n",
+      "  [153 186 150]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]]\n",
+      "\n",
+      " [[154 187 151]\n",
+      "  [154 187 151]\n",
+      "  [154 187 151]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]\n",
+      "  [128 156 131]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.11687994003295898\n",
+      "sending frame\n",
+      "56\n",
+      "[[[231 237 239]\n",
+      "  [208 220 221]\n",
+      "  [167 190 191]\n",
+      "  ...\n",
+      "  [162 186 186]\n",
+      "  [203 216 217]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [171 193 195]\n",
+      "  [128 162 163]\n",
+      "  ...\n",
+      "  [122 156 157]\n",
+      "  [163 186 187]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [171 193 195]\n",
+      "  [128 162 163]\n",
+      "  ...\n",
+      "  [123 156 157]\n",
+      "  [164 186 187]\n",
+      "  [229 236 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 224]\n",
+      "  [170 193 194]\n",
+      "  ...\n",
+      "  [167 189 192]\n",
+      "  [206 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[181 204 171]\n",
+      "  [181 204 171]\n",
+      "  [181 204 171]\n",
+      "  ...\n",
+      "  [160 185 154]\n",
+      "  [160 185 154]\n",
+      "  [160 185 154]]\n",
+      "\n",
+      " [[181 204 171]\n",
+      "  [181 204 171]\n",
+      "  [181 204 171]\n",
+      "  ...\n",
+      "  [163 188 157]\n",
+      "  [161 186 155]\n",
+      "  [161 186 155]]\n",
+      "\n",
+      " [[180 203 170]\n",
+      "  [180 203 170]\n",
+      "  [180 203 170]\n",
+      "  ...\n",
+      "  [161 186 155]\n",
+      "  [160 185 154]\n",
+      "  [160 185 154]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[177 205 170]\n",
+      "  [177 205 170]\n",
+      "  [177 205 170]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [127 155 130]\n",
+      "  [127 155 130]]\n",
+      "\n",
+      " [[177 205 170]\n",
+      "  [177 205 170]\n",
+      "  [177 205 170]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [127 155 130]\n",
+      "  [127 155 130]]\n",
+      "\n",
+      " [[177 205 170]\n",
+      "  [177 205 170]\n",
+      "  [177 205 170]\n",
+      "  ...\n",
+      "  [128 156 131]\n",
+      "  [127 155 130]\n",
+      "  [127 155 130]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.11756372451782227\n",
+      "sending frame\n",
+      "63\n",
+      "[[[231 237 239]\n",
+      "  [209 221 222]\n",
+      "  [168 192 193]\n",
+      "  ...\n",
+      "  [162 185 186]\n",
+      "  [203 215 216]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 196]\n",
+      "  [132 166 167]\n",
+      "  ...\n",
+      "  [122 154 156]\n",
+      "  [161 184 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 195 197]\n",
+      "  [132 166 167]\n",
+      "  ...\n",
+      "  [121 154 156]\n",
+      "  [161 184 185]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 191 193]\n",
+      "  ...\n",
+      "  [167 189 191]\n",
+      "  [205 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[192 219 187]\n",
+      "  [192 219 187]\n",
+      "  [192 219 187]\n",
+      "  ...\n",
+      "  [161 181 154]\n",
+      "  [162 182 155]\n",
+      "  [162 182 155]]\n",
+      "\n",
+      " [[192 219 187]\n",
+      "  [192 219 187]\n",
+      "  [193 220 188]\n",
+      "  ...\n",
+      "  [161 181 154]\n",
+      "  [162 182 155]\n",
+      "  [162 182 155]]\n",
+      "\n",
+      " [[192 219 187]\n",
+      "  [192 219 187]\n",
+      "  [193 220 188]\n",
+      "  ...\n",
+      "  [160 180 153]\n",
+      "  [161 181 154]\n",
+      "  [162 182 155]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[166 192 158]\n",
+      "  [166 192 158]\n",
+      "  [166 192 158]\n",
+      "  ...\n",
+      "  [127 154 126]\n",
+      "  [127 154 126]\n",
+      "  [126 153 125]]\n",
+      "\n",
+      " [[166 192 158]\n",
+      "  [166 192 158]\n",
+      "  [167 193 159]\n",
+      "  ...\n",
+      "  [126 153 125]\n",
+      "  [126 153 125]\n",
+      "  [124 151 123]]\n",
+      "\n",
+      " [[166 192 158]\n",
+      "  [166 192 158]\n",
+      "  [167 193 159]\n",
+      "  ...\n",
+      "  [126 153 125]\n",
+      "  [126 153 125]\n",
+      "  [124 151 123]]]\n",
+      "None\n",
+      "in iteration\n",
+      "inference time: 0.1283400058746338\n",
+      "sending frame\n",
+      "70\n",
+      "[[[231 237 239]\n",
+      "  [210 222 223]\n",
+      "  [172 195 195]\n",
+      "  ...\n",
+      "  [161 184 186]\n",
+      "  [202 215 216]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [173 195 197]\n",
+      "  [133 168 168]\n",
+      "  ...\n",
+      "  [120 154 156]\n",
+      "  [161 184 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " [[231 237 239]\n",
+      "  [172 194 195]\n",
+      "  [132 166 166]\n",
+      "  ...\n",
+      "  [121 154 156]\n",
+      "  [161 185 186]\n",
+      "  [229 235 236]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [210 222 223]\n",
+      "  [169 191 193]\n",
+      "  ...\n",
+      "  [167 189 191]\n",
+      "  [206 218 219]\n",
+      "  [230 236 237]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]\n",
+      "\n",
+      " [[231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  ...\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]\n",
+      "  [231 237 238]]]\n",
+      "[[[213 241 204]\n",
+      "  [213 241 204]\n",
+      "  [213 241 204]\n",
+      "  ...\n",
+      "  [145 170 141]\n",
+      "  [148 173 144]\n",
+      "  [148 173 144]]\n",
+      "\n",
+      " [[214 242 205]\n",
+      "  [214 242 205]\n",
+      "  [214 242 205]\n",
+      "  ...\n",
+      "  [145 170 141]\n",
+      "  [148 173 144]\n",
+      "  [148 173 144]]\n",
+      "\n",
+      " [[218 246 209]\n",
+      "  [218 246 209]\n",
+      "  [216 244 207]\n",
+      "  ...\n",
+      "  [144 169 140]\n",
+      "  [146 171 142]\n",
+      "  [146 171 142]]\n",
+      "\n",
+      " ...\n",
+      "\n",
+      " [[166 192 158]\n",
+      "  [166 192 158]\n",
+      "  [168 194 160]\n",
+      "  ...\n",
+      "  [140 167 139]\n",
+      "  [140 167 139]\n",
+      "  [140 167 139]]\n",
+      "\n",
+      " [[166 192 158]\n",
+      "  [166 192 158]\n",
+      "  [168 194 160]\n",
+      "  ...\n",
+      "  [137 164 136]\n",
+      "  [137 164 136]\n",
+      "  [137 164 136]]\n",
+      "\n",
+      " [[166 192 158]\n",
+      "  [166 192 158]\n",
+      "  [168 194 160]\n",
+      "  ...\n",
+      "  [137 164 136]\n",
+      "  [137 164 136]\n",
+      "  [137 164 136]]]\n",
+      "None\n"
+     ]
+    }
+   ],
+   "source": [
+    "cnt = 0\n",
+    "for x,y,z in process_video('videos_example/421.mp4'):\n",
+    "    print(x)\n",
+    "    print(y)\n",
+    "    print(z)\n",
+    "    cnt += 1\n",
+    "    if cnt > 10:\n",
+    "        break\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "cap = cv2.VideoCapture(input_video)\n",
+    "\n",
+    "    output_path = \"notebook_out_vid.mp4\"\n",
+    "    if out_fps != 'auto' and type(out_fps) == int:\n",
+    "        fps = int(out_fps)\n",
+    "    else:\n",
+    "        fps = int(cap.get(cv2.CAP_PROP_FPS))\n",
+    "        if out_fps == 'auto':\n",
+    "            fps = int(fps / skip_frames)\n",
+    "\n",
+    "    width  = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))\n",
+    "    height = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))\n",
+    "\n",
+    "    video = cv2.VideoWriter(output_path, cv2.VideoWriter_fourcc(*\"mp4v\"), fps, (width, height))\n",
+    "\n",
+    "    iterating, frame = cap.read()\n",
+    "    cnt = 0\n",
+    "    \n",
+    "    while iterating:\n",
+    "        if (cnt % skip_frames) == 0:\n",
+    "            # flip frame vertically\n",
+    "            display_frame = inference_frame_serial(frame)\n",
+    "            video.write(cv2.cvtColor(display_frame, cv2.COLOR_BGR2RGB))\n",
+    "            print('sending frame')\n",
+    "            print(cnt)\n",
+    "            yield cv2.cvtColor(display_frame, cv2.COLOR_BGR2RGB), cv2.cvtColor(frame, cv2.COLOR_BGR2RGB), None\n",
+    "        cnt += 1\n",
+    "        iterating, frame = cap.read()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "openmmlab2",
+   "language": "python",
+   "name": "openmmlab2"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.8.16"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}