microsoft / cameratraps Goto Github PK

PyTorch Wildlife: a Collaborative Deep Learning Framework for Conservation.

Home Page: https://cameratraps.readthedocs.io/en/latest/

License: MIT License

Python 1.76% Jupyter Notebook 38.03% Shell 0.05% Python 20.73% Jupyter Notebook 38.03% Shell 0.39% Dockerfile 0.02% HTML 0.37% C# 0.52% Starlark 0.10% Batchfile 0.01%

camera-traps wildlife conservation machine-learning computer-vision megadetector pytorch pytorch-wildlife

cameratraps's People

Contributors

Stargazers

Watchers

Forkers

thomasshupeng kant aench2023 lasvegascoder rahulnangia sirkalcode ychuan1115 trongdamnguyen kevinmiles cinkkkyo bw4sz wqslucifer farcry4998 shibicr93 soberspot alan8656123 won-bae neibla vdedyukhin abfleishman louis030195 ml-lab coreyjaskolski amoliu trendingtechnology lyk125 ivorylu marconis bencevans marireeves biomass-corpus weilxin yazici sixf ktk99 tan12uja battani vratchaudhary beatboxerish dwheelerau jsarni whatname0 bipulroy8 vanhien13 albertofernandezvillan gitlost-murali suhailsaify hanyangzhao simplesoftmx shuhanstack omipan bacmodung shelviaandi chrisyeh96 pomasta hlydecker bhaskers-blu-org2 cuulee cvumf hartmania weecology taffywrinkle claudiusgonzo johnarthur1 helena sjayashree01 matiasgel giladguy pishili hin7141 juliuskramer cmakinen mgood2 daukantas isabella232 edward-l-may alsnothome nathanielrindlaub tzarshippee tobbas75 aayc nicolalove global-localhost global19 global19-atlassian-net ericnewkirk svanbodegraven fredrikorn vijay39312 vlas-sokolov wt3210 ischi94 yibingwei-1 vighneshbirodkar tsuijten col-kol 2hindas gpsbird robert-sipho chingzchen

cameratraps's Issues

`group` class?

Please could you clarify as to what the group class is supposed to represent? Group of animals, group of people, vehicles...?

Thanks

Ben

Are the MDv5 pt files "normal" YOLOv5 model files?

Are the MDv5 pt files "normal" YOLOv5/PyTorch model files? Aka can I use my existing scripts for running YOLOv5 models to run MDv5? or is there something custom about the pt files that I need to be aware of?

Tutorial is out of date

From the main README.md, in section classification (https://github.com/microsoft/CameraTraps#classification),
it states "here's a tutorial on training your own classifier using our detector and our training pipeline." and points to the archived TUTORIAL.md (https://github.com/microsoft/CameraTraps/blob/master/archive/classification_marcel/TUTORIAL.md).

However, the tutorial seems to be far out of sync with the readme in https://github.com/microsoft/CameraTraps/blob/master/classification/README.md.

I am still unsure how to run the training with my dataset with the current master branch.

google.protobuf.message.DecodeError: Error parsing message

hello, i got some errors when run your code when refering to the file of megadetector_colab.ipynb
##########################
!python run_tf_detector_batch.py megadetector_v4_1_0.pb "$images_dir" "$output_file_path" --recursive

Then the error occurs, the messages are showed as follow:
...
GPU:0 with 10672 MB memory) -> physical GPU (device: 0, name: Tesla K80, pci bus id: 0000:90:00.0, compute capability: 3.7)
2020-09-28 13:04:05.656622: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:1 with 10672 MB memory) -> physical GPU (device: 1, name: Tesla K80, pci bus id: 0000:91:00.0, compute capability: 3.7)
2020-09-28 13:04:05.657306: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:2 with 10672 MB memory) -> physical GPU (device: 2, name: Tesla K80, pci bus id: 0000:94:00.0, compute capability: 3.7)
2020-09-28 13:04:05.657562: I tensorflow/core/common_runtime/gpu/gpu_device.cc:1115] Created TensorFlow device (/device:GPU:3 with 10672 MB memory) -> physical GPU (device: 3, name: Tesla K80, pci bus id: 0000:95:00.0, compute capability: 3.7)
tf.test.is_gpu_available: True
3597 image files found in the input directory
TFDetector: Loading graph...
Traceback (most recent call last):
File "run_tf_detector_batch.py", line 375, in
main()
File "run_tf_detector_batch.py", line 357, in main
n_cores=args.ncores)
File "run_tf_detector_batch.py", line 166, in load_and_run_detector_batch
tf_detector = TFDetector(model_file)
File "/data1/user_datas/tianxianhao/DeepLearning/CameraTrap/CameraTraps/detection/run_tf_detector.py", line 147, in init
detection_graph = TFDetector.__load_model(model_path)
File "/data1/user_datas/tianxianhao/DeepLearning/CameraTrap/CameraTraps/detection/run_tf_detector.py", line 212, in __load_model
od_graph_def.ParseFromString(serialized_graph)
google.protobuf.message.DecodeError: Error parsing message
###################
how to solve this problem? please.

Script to convert Mega output JSON to COCO?

Hi, we are trying to do some transfer learning with our Megadetector output JSON (retraining Mobilenet in TF2) and just realized the JSON output format from Megadetector is not in COCO format. Do you know if there is a handy script laying around somewhere that converts the images..detections into annotations and fixes the bounding box coordinates and any other differences i haven't learned about yet! Thank you

Method to look up request IDs from the API

The API rocks! It would be handy to have a method to list a table (or JSON) of all the request ids with date submitted, date completed, job name, number of images, and brief status (e.g. failed, completed, processing). Maybe be able to limit to a date range or job name matcher?

environment.yml file is not downloaded while cloning the respository

hey, why the yml files are not downloaded while cloning the respository

Megadetector v5 release date?

Hey. I'm curious about when will the pytorch code and weights for Megadetector v5 be released. I have seen reference about it here

make_classification_dataset with custom train/test split

Thanks for making this great repo!

I love that make_classification_dataset.py allows you to crop images using the megadetector and create the tfrecords at the same time. One thing that has not been clear to me is how to specify a specific train/test split rather than having the script automatically split across locations.

Is there a way to do this?

Release v4.1

Hey! Im trying to use the current release (v4.1)

When running the data_management/databases/classification/make_classificiation_dataset.py it tries to locate a create_tfrecords_v3 which is seems by the comments to be a script to create tfrecords when using python 3 or higher.

However, this create_tfrecords_v3 does not seem to exist.

I am using the environment-detector.yml conda setup.

TFLite Converter Errors

I am attempting to port the frozen .pb file to a TFLite model for use with the Raspberry Pi and the Google Coral TPU USB Coprocessor and ran into issues running the conversion. I am new to TensorFlow and, while I'm a Software Engineer, I'm using this as a user more than a developer, so bear with me here.

The command I run and samples of the, very verbose, output are below. I know this may not be at the top of your priority list, but if it helps motivation, if this works out we could use MegaDetector on camera traps in the field to detect animals in real-time in the field, like for a predator detector I'm looking for for our farm. I'm able to crunch a detection in 45 seconds on my CPU but am eager to see what the Coral TPU can do. Thanks in advance for any help you're able to provide and I'm happy to roll up my sleeves and dig in if I can get a nudge in the right direction.

Here's the command I run:
tflite_convert --output_file=md_v4.1.0.pb.tflite --graph_def_file md_v4.1.0.pb --input_arrays=image_tensor --output_arrays=detection_boxes,detection_scores,detection_classes --input_shapes=1,640,480,3 --enable_v1_converter

Traceback (most recent call last): File "c:\anaconda3\envs\py36\lib\runpy.py", line 193, in _run_module_as_main "main", mod_spec) File "c:\anaconda3\envs\py36\lib\runpy.py", line 85, in run_code exec(code, run_globals) File "C:\anaconda3\envs\py36\Scripts\tflite_convert.exe_main.py", line 7, in File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\lite\python\tflite_convert.py", line 442, in main app.run(main=run_main, argv=sys.argv[:1]) File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\python\platform\app.py", line 125, in run _sys.exit(main(argv)) File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\lite\python\tflite_convert.py", line 438, in run_main _convert_model(tflite_flags) File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\lite\python\tflite_convert.py", line 191, in _convert_model output_data = converter.convert() File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\lite\python\lite.py", line 455, in convert **converter_kwargs) File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\lite\python\convert.py", line 442, in toco_convert_impl input_data.SerializeToString()) File "c:\anaconda3\envs\py36\lib\site-packages\tensorflow\lite\python\convert.py", line 205, in toco_convert_protos "TOCO failed. See console for info.\n%s\n%s\n" % (stdout, stderr)) tensorflow.lite.python.convert.ConverterError: TOCO failed. See console for info. 2020-12-10 21:12:31.516113: I tensorflow/lite/toco/import_tensorflow.cc:1324] Converting unsupported operation: TensorArrayV3 2020-12-10 21:12:31.516570: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel ('op: "WrapDatasetVariant" device_type: "CPU"') for unknown op: WrapDatasetVariant 2020-12-10 21:12:31.516902: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel ('op: "WrapDatasetVariant" device_type: "GPU" host_memory_arg: "input_handle" host_memory_arg: "output_handle"') for unknown op: WrapDatasetVariant 2020-12-10 21:12:31.517337: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel ('op: "UnwrapDatasetVariant" device_type: "CPU"') for unknown op: UnwrapDatasetVariant 2020-12-10 21:12:31.517673: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel ('op: "UnwrapDatasetVariant" device_type: "GPU" host_memory_arg: "input_handle" host_memory_arg: "output_handle"') for unknown op: UnwrapDatasetVariant 2020-12-10 21:12:31.518258: I tensorflow/lite/toco/import_tensorflow.cc:1373] Unable to determine output type for op: TensorArrayV3 2020-12-10 21:12:31.518503: I tensorflow/lite/toco/import_tensorflow.cc:1324] Converting unsupported operation: TensorArrayScatterV3 2020-12-10 21:12:31.518752: I tensorflow/lite/toco/import_tensorflow.cc:1373] Unable to determine output type for op: TensorArrayScatterV3 2020-12-10 21:12:31.519004: I tensorflow/lite/toco/import_tensorflow.cc:1324] Converting unsupported operation: TensorArrayV3 2020-12-10 21:12:31.519201: I tensorflow/lite/toco/import_tensorflow.cc:1373] Unable to determine output type for op: TensorArrayV3 2020-12-10 21:12:31.519404: I tensorflow/lite/toco/import_tensorflow.cc:1324] Converting unsupported operation: TensorArrayV3 2020-12-10 21:12:31.519606: I tensorflow/lite/toco/import_tensorflow.cc:1373] Unable to determine output type for op: TensorArrayV3 2020-12-10 21:12:31.519863: I tensorflow/lite/toco/import_tensorflow.cc:1324] Converting unsupported operation: Enter 2020-12-10 21:12:31.520066: I tensorflow/lite/toco/import_tensorflow.cc:1373] Unable to determine output type for op: Enter

..........

2020-12-10 21:12:31.887365: I tensorflow/lite/toco/import_tensorflow.cc:1373] Unable to determine output type for op: TensorArrayGatherV3 2020-12-10 21:12:34.795091: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before Removing unused ops: 8696 operators, 17295 arrays (0 quantized) 2020-12-10 21:12:37.623228: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] After Removing unused ops pass 1: 8662 operators, 17241 arrays (0 quantized) 2020-12-10 21:12:41.875052: I tensorflow/lite/toco/graph_transformations/graph_transformations.cc:39] Before general graph transformations: 8662 operators, 17241 arrays (0 quantized) 2020-12-10 21:12:42.990606: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_1/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.114359: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_2/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.249639: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_3/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.371587: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_4/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.490386: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_5/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.610138: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_6/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.729914: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_7/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.845808: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_8/Conv2d_1x1/Conv2D". 2020-12-10 21:12:43.961710: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_9/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.079812: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_10/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.198136: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_11/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.316202: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_12/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.430921: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_13/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.545152: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_14/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.657000: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_15/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.767624: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_16/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.878775: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_17/Conv2d_1x1/Conv2D". 2020-12-10 21:12:44.987341: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_18/Conv2d_1x1/Conv2D". 2020-12-10 21:12:45.098353: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_19/Conv2d_1x1/Conv2D". 2020-12-10 21:12:45.207493: I tensorflow/lite/toco/graph_transformations/identify_dilated_conv.cc:220] Replaced sub-network with Dilated Conv2D op outputting "FirstStageFeatureExtractor/InceptionResnetV2/InceptionResnetV2/Repeat_1/block17_20/Conv2d_1x1/Conv2D". 2020-12-10 21:12:45.215230: F tensorflow/lite/toco/graph_transformations/resolve_constant_slice.cc:59] Check failed: dim_size >= 1 (0 vs. 1)

Program seems to hit a dead-lock when using multiple cores

Hello,
As I wanted to increase the performance of the program run_tf_detector_batch.py, I used the option --ncores you provided. I tried it with 2 or 4 cores but each time, the program is stuck. Here are the last shell outputs I get:

Creating pool with 2 cores
TFDetector: Loading graph...
TFDetector: Loading graph...
TFDetector: Detection graph loaded.
TFDetector: Detection graph loaded.
Loaded model (batch level) in 6.78 seconds
Loaded model (batch level) in 6.78 seconds
Processing image /home/...
Processing image /home/...
2020-08-17 09:43:40.366492: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 20054016 exceeds 10% of system memory.
2020-08-17 09:43:40.366493: W tensorflow/core/framework/cpu_allocator_impl.cc:81] Allocation of 20054016 exceeds 10% of system memory.

When I don't use the ncores option, I process 30 images in ~5 minutes. I've waited 10 minutes with the option, but it didn't process even 1 image.

Do you know what could cause this behaviour ?

What is the price or rate limiting of the batch processing api?

multi-GPU inference

Is there an easy way to use multiple GPUs for inference for the MegaDetector? That could speed things up quite a bit for large datasets.

Using the estimated models outside of MegaDetector

Hi,

Could it be possible to use the estimated models (I mean, the model weights) outside of MegaDetector, for those of us who have their own codes already running?
I would like to reuse your estimated models in my codes implemented in Keras. Do you think it could be possible?

I think this could be very interesting for many people...

is this error means my gpu memory_size is small

is this error means my gpu memory_size is small
[00:00<?, ?it/s]2022-04-25 01:31:03.333175: W tensorflow/core/grappler/costs/op_level_cost_estimator.cc:690] Error in PredictCost() for the op: op: "CropAndResize" attr { key: "T" value { type: DT_FLOAT } } attr { key: "extrapolation_value" value { f: 0 } } attr { key: "method" value { s: "bilinear" } } inputs { dtype: DT_FLOAT shape { dim { size: -1204 } dim { size: -1205 } dim { size: -1206 } dim { size: 1088 } } } inputs { dtype: DT_FLOAT shape { dim { size: -25 } dim { size: 4 } } } inputs { dtype: DT_INT32 shape { dim { size: -25 } } } inputs { dtype: DT_INT32 shape { dim { size: 2 } } value { dtype: DT_INT32 tensor_shape { dim { size: 2 } } int_val: 17 } } device { type: "GPU" vendor: "NVIDIA" model: "NVIDIA GeForce GTX 1050 Ti" frequency: 1392 num_cores: 6 environment { key: "architecture" value: "6.1" } environment { key: "cuda" value: "11020" } environment { key: "cudnn" value: "8100" } num_registers: 65536 l1_cache_size: 24576 l2_cache_size: 1048576 shared_memory_size_per_multiprocessor: 98304 memory_size: 2917584078 bandwidth: 112128000 } outputs { dtype: DT_FLOAT shape { dim { size: -25 } dim { size: 17 } dim { size: 17 } dim { size: 1088 } } }

how to get MegaClassifier pretrained model "MegaClassifier"??

how to download "v0.1_efficientnet-b3_compiled.pt" file?
is it share? or not?

This repo is missing important files

There are important files that Microsoft projects should all have that are not present in this repository. A pull request has been opened to add the missing file(s). When the pr is merged this issue will be closed automatically.

Microsoft teams can learn more about this effort and share feedback within the open source guidance available internally.

Merge this pull request

How to use this with TF Serving?

Hi, I'm a seasoned JS/web/full stack developer but fairly new to ML and almost no Python experience.

I'm trying to setup an endpoint (similar to your API endpoint), but running on Google Cloud Infrastructure, where I can submit an image (or several for batching) and get json results back.

From the documentation I understood that I can download this model (https://lilablobssc.blob.core.windows.net/models/camera_traps/megadetector/md_v4.1.0/md_v4.1.0_saved_model.zip), and exposing it up using TFServing.
However I'm hitting some dead ends on how to input the image as an argument.

I set the model up using tf version 1.15 on Google's Vertex AI Prediction service (https://cloud.google.com/vertex-ai/docs/general/import-model), and tried this for an input argument:

{"instances": [{"b64": "data:image/jpeg;base64,/9j/2wCEABQODxIPDRQSEBIXFRQYHjIhHhwcHj0sLiQySUBMS0dARkVQWnNiUFVtVkVGZIhlbXd7gYKBTmCNl4x9lnN+gXwBFRcXHhoeOyEhO3xTRlN8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fHx8fP/AABEIAeACgAMBIQACEQEDEQH/xAGiAAABBQEBAQEBAQAAAAAAAAAAAQIDBAUGBwgJCgsQAAIBAwMCBAMFBQQEAAABfQECAwAEEQUSITFBBhNRYQcicRQygZGhCCNCscEVUtHwJDNicoIJChYXGBkaJSYnKCkqNDU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6g4SFhoeIiYqSk5SVlpeYmZqio6Slpqeoqaqys7S1tre4ubrCw8TFxsfIycrS09TV1tfY2drh4uPk5ebn6Onq8fLz9PX29/j5+gEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoLEQACAQIEBAMEBwUEBAABAncAAQIDEQQFITEGEkFRB2FxEyIygQgUQpGhscEJIzNS8BVictEKFiQ04SXxFxgZGiYnKCkqNTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqCg4SFhoeIiYqSk5SVlpeYmZqio6Slpqeoqaqys7S1tre4ubrCw8TFxsfIycrS09TV1tfY2dri4+Tl5ufo6ery8/T19vf4+fr/2gAMAwEAAhEDEQA/AOyooAKKACigAooAKKACigQUUAgooGFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQIKKACigYUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFAkFFABRQAUUDCigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKACigAooAKKAEozTM72QgIIBByD3padhXCikUmLRSKCigYUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFAETyBSoP8RwPrSSvsRmyBgZ56fj6VpbqYFfTbo3VhFKc5KjP5fWnJcxm7eLLbgoOO/JI6fgPbmr5feY7alksB1OKVWDAEcg1lbqCFpaRaCk3rv2bhuxnHfFIoWigYUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAc5d6hOL2DzIpIljfJxyD+PQ9+f0FNvNWbe0flhsDlM7g6kfMpx0OeAelbXtoZ8qKtpezWtuEWNQoJI3MBhTg53dyfbninDU5TP5gmLcEJ0Jxz8uMcH3/n0p3uyrF/WLwwW0SpuSQFXXp8y85PP4+vWpdJ1KJ7SKN5N05wMc85OB19B1NG7aJtoaccweR02lSvTI6jjn9alJABJOAOprJqw0MEy/OWZQobbnP8AOs5tSVb1lRt7MCBGqncCOx9D1/AVSjqMuT3scE0UT53SdAASf854/Go9QnMQj2SbWWRS4yB8nc89qSWzGW1I8sHPy4zknNIsqNEsgYbGxg59amzAfRSGFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQBwl/qck0iKwBKj5ZA5ye+eCBn8KqtOG3M+fNP8Q759ferb1EiJJAVUHOQeue30qa2umtphLEFEi9CVzTvZgOluBIoPJbJZizEgkgdu3Srmk3MkV7CIkDEZH1GP8/8A16E7MDQ03VUk1RnlBBlwi4PA578//qrX1C+S3MYEkfLbSS+Cp9wOv0o7MWxkQauUeeG4YyqQcY4UjBycj1/Lr0rLtr6WO88xWLN/CX7emc5x0/8Ar0X1GW5L6Q30bi5yVJYuvI/DPUfX3q9e6mkthi3j85CoAlbrG3BO78Ocj8qXQCzpd3GlkyfakkcAuAPmKgnqeeTk+v07VmrrEkUMsLu8mwqFYnDAj6++B/nNNrXQZt6bepdqVj+YIMk+memfwq/Uy3AKKkAooAQkKCWIAHJJ7UIwdFdTlWGQfai3UBaKACigAooAKKACigAooAKKACigAooAKKACkyM4zz6UALRQAUUAFFABSA5FAhaKBhRQAUUAFFABRQAUUAFFABRQAUUAFFABRQAUUAFFABRQB5e2PMJUbQT0z0pevWqEHUUKe3NMB7jAyOR1p6SsoJHH0pATWk32WeOUru2HcBTZJ3kILMOD36n6nvTuACY5bGeVwRmokb5+ecdqEBK0m7GMYXoD+tWohA8TMZfJkUE5IADfQ9f0zQgGQXjKkcZYhNhG7kbcnPGBnP59fwqG3k8tmKuU4OCRmqYGppmomG8i3y7EJIc4GMdffuP84rorzUIY0jAckykFCvQ/MB1x71LGJp961007GMrGG4yeR2xj8Cever+ecd6lgFIzBFy3SkBkQaqZGvijpsifKu/3QBgdj3wcVZsL1XtVM0i53spO7gYPHJ5PGKuwi/RUDCigBMjOMjPpQzBQSxAA6kmgQEgEZ78CloGFFABRQAUUAFFABRQIKKBhSEZII6igQtBOASelABRQMKM0AFN5DHLDHpQIdRQMKKACgHIyOlACY5yPxpaBBRQMKKAIVmHnhCciRd6HjkcZH6g/jU1U1YQUVIwooAKKACigAooAKKACooriOUuEbJRirD0OaLCPNX+4pphOasA3biAOtPyOv5igBwf5cZxS8NzSAcrHkEbR0FNIwcHHHcUALk5JHOaATnPt2oAcp4+XOfWkZuARzTQA3K5UKq8cc+nWmoQT1qmIfnHXFTSXLSgbmYnP5n1+vr68VIye2vJIUcKyDOM7hk/WulbVFttLjmXEsrrvIDe/U/jx+lJ7DHprdu1mJpAyknBQdcZ6/T3rDk127eJ4WZSrN8sjDBXn2+n1osIzPtMnmSOW+aTO5iOuev581dTUDFbKlsrRv/FIWJJ6dOw9Py9KoDbi1qJNLBM4a4QBcMpJPP4Z4HNW7XV7e4SAFwssh2lTkYOP8cfnUMZd82PCnzF+YZHPX6VlahrsUKqtsyu5bnvjB/rj1pIDI/tmf7d9qG3nClOOVB6ZxUupa28+0QtiJ1yynBwfyz+tUkBRfUrl12tM4IIIbecggY9au2mt3EBjVvmjU5YEklh9Tk07BoTW+vmKdzJGWRjlsN04A4z/AF/SrtzrS/6MLXDGQhmDdVGRx9evr+tKyuIsvq9msnliUMwOCR0HHr+lUb7XgMLbqRiTDMfQf40kMs2WrQzSFWO3cwAJ7n39P61au9QgtQd8ilgcbdwz/nFAMsJIjhSjqwYZGDnIoLiNGaQgKuSSfSkIRJUkXcrAr6g++Kh8yWKcrIVeI87hwU+o7jkc00gJ0kSRAyMGU9CD1p1IBGUMpU9CMGoLaYs0kLsGlhIDH1BGQaa2GSpjsNpHBFMncCKVScHacH14osImopDCoTJsuwjkbZF+T6jqP1H600riIZruKxmVJWxHICV77T6Y9PSrEMqyblB+dOGU9RTfcCvpVw9zZLJIcvk5P+fy/CrlElZ2BBRUjMq71lLWbaHSbD4ZEU7gMcnPTOe1S2E6zSyywOGgkw23B3K2OR+OKtqyETy3SC2MyONquoY9cDcAf0qzSasg6hRUjA5wcdapi9B2M+1ULGJxnJEnp+n6iqSTEZt+zQGCJSd0bbopevyHt16ggfhitDT7555HhuUEcy4IA6Mp7j/PenJ3Aub/AN4UweBnNOqBhRQAUhOOvSgQtFAwyM4zzSAgkjuKBC1E9xFHIIy4Mh6IOW/L096aVwMfVNUjdfIXDRsPm7FT1A/xrEsL/wCzXTyv+8Z/4m5Ocg5+vFWtrCZlcYIPNR7DwT0qUMUphiRThg9R9aAEwMc9aVWHXvQA5juXIAzSg5C7hxQAgJznoBR94ADigBVBzxSr70wGSNgkfnSx8Hj9afQCR8sAMDPWmqQSB68UkA9enX2qQs2zaCcHnGeDSAaRxzwe31qLfg4NUgFxuGfSnKePahgPwTnvUqfOrKB23DPf/PNIZHIzDqRg9RUYbLZJpokfnPT+VIcgDPOc/hQhgBz1HHFPzngDnvQwDgfTvzTgck5PWkMnTacscDIOcHv6/wAjTjEZMYz83y89cjp/MClfUCCIyHKpyv3uv+H1pXkZiWLFiSee7Z6mn1EXLCd7e4SaNixUFQjd/wDJNWr/AFOa4haORVWN8MoXnOCMjP15+lSxlS3vphE0YlZR14PP+elWYtTnw0nmhnSMp838/wD6/wBKHoAkOqTQTEA/uhMzlQM8ZOQM/U1tx6xZvF5hkZfVSpyPyo6ASzX1utsJTLmNztVkPOayGuYrm7t45AUlLbXeMcOnb6Z4H51UdBEseoPGs8TBxMchGcgYGON3+1U9pILmwe3uJMyBgvJ+bqMdfelfULaGnuxHufjjJoDblDKQQRn60gF3DBJ+XHXPaql1M2dkaHzEAkUMv3wDyAexxx6804rULmdrDed9ljjdQs3zZI5ycYJ/M1DMsunSz+VKM7AqyY5ByOo9cEUC2Nm0ihtGa1iyON4B9On8x+tWqJO7uMKq3E8Kpi4ymTgKzbQ345xiktwMnUdVEkclvF5QiA2sc9eQBt55656djWbZ3P2K5SZD5iL94Adun9abA2mnALyRhlt7qPJzjCMeAx7AGtWCUTQpIOjqDTewD6KgZXmeUuUiZEAH3iu4k+mMj2/OsC6a7s5t91hmZllVuAGK8dB9Rn6da1S08ydxb+YXNpD5f3Yw20twdoOPocgofwqzpdwrvBJKwEqkxAnqynBx+BI/Oov1A2ZH2oZAQVHX/P51JSDqFV7i9t7ZN80oAzjjnn8KErjKy6xALV5SkgKcFcHPfHP4daoTarLeK/kmKEKjZDAszcZ46Afn2pqy1YMsQa4psXklCidc/IM4bnANF9rqwxobZBJvTOSfuk9Pr7ikkBkS6rcPc+cs5VyoBC8Ae2DU39vTpcNJgMCoUK3Tjvx+P503uIbHr12Jif3ZLAZBHHH48Uy61Wa5lLbdgcBDswTge5+tFgKSt5tuAOCvIFQyxjduQYHXAoTswKK9uozSHIPqT1oGOx379qTqCaADPGab07UwJFJxj1pR99uOAaQDAeOTS7vnBzTAeDhwRRt54pADjcpYdutInFPoBN1GBx/hTI1bOCOD+noaSAeARuTowz+lOQgg7sdM/wBaBjC5GV6g1GygAH1yKpAyQjG1lGVcccZ/ClZMMAOFI3D6f5z+VK4hwZh82eee+P8AP/6quMsYXzU+4VIYdMHaf58fQ0mNFUneyoepOPoaZGoPBGMjIp7AxMFeeRxnmpFJKc8rQIWQAIzr824YzjvkH+WaapKnJz6dODQA6RBjcPunn6etLGCj4Iww7EZB/CgZYGVcZABYdM4Gf/1cfjT0ZVlHUFjgKe2f8ipAS6Mj3Xkh225IPPAUc9O3QVFKC9yqjADABeenYfrQgYsTbXyVbKnqBx+op0kq7gEPQ52A8Hj/AAyPxoAa0YXIXBA4LDpnvSfdvI42j+WTC7Wzg5zz/WjcGPmfzUDgfOW5VR6/ypkf+sKlQWHA6HnsKfQBZJSMEEqOuOlAZhKHG5ST1UYI+npzigRYimUTje6yLJlGYruOD06+5z+dFvOyho0wGlGzDfwtuwpx27frU7MZei1BI9JjgdXlkQfNliNvPGCPTP8AKnQa28GzzQZFZz5hPUfT9KrcRq39zbpCPMfjKPkAnI3DkGsC+1OS7mDMoRUPC9Tj37ZovoMjz9lnXy3VVcB8OCQhyeDj6D86hkmZ4XkaTd5jDcpPI45/AYFIRtaPOJZmMkxa5VikgYk5ToMf8C/ma2gCqnHzHJP602CI3m2BsoW2nnGPrVS7uI7kG2iKt5ikSMf+WXbp1z1+nWhAc9DdG3aaEsrQuGBUEZyVxkf41V3GNjKn3PuOAeeRQIsfaHe3dWkbYQzAKABjjt25xx7e9dNo3Gl2wJGSpP4Z/wDr0dAL1H41IytI7wsXfaVLAAjjC45/kTWXrEk0yoCAkJyyAj5sjufTr061orCOebfksD7ZBqWyvBDIRIu9HwrZYgD3/ClYCxBNPbTMjSybA3CBjgjOOldHNq9lDGH89ZM9BH8x/wDrfjSeuwzNv9bJ8l7TeoVssG75Bx3+v6VmTTNIrEAlXYu2OzdCf8+tCArkcDbjI65o89cqv3c/e9qNwFI3PwcAgioUb5WX2z+P/wCrNCEKrfMOQc8UhX5G9sGhgAjGCTn0zmkUkOuexoAd/qkDJnPoe1Pcr5cRQENt9fejzAywpLUSA7hj86EMMgqeT7UqnHJ4HagBJAd3HegjgGgBw+7zmnDoSfTNACFFweecUJxHyuQSAfyNMB5iO8Y6EcY70ikg+uKQDlU8L03d6I0JDrnBGD+Ocf1oAkBVztUZ9OOh9P8APrThE0gG1cnrwMkCkMcCks7hMklTg9edvPP1qMqdiN13cdfwH8qYDpbaRAynnaM7u2CM5/Slto8rlsELiTHsDz+lO4WHQRBkEbHBVvlPYZ9fyp7QbhC7A4zggn0Ofw//AFUr6gRRq2xiMAqQRjsf6Z/pUseRE6k7gwILDnocEY9eQaHqBG0LRxlnBDqcDuTjGfyH+eKcYsMUByAxUe3OOT9f8fq73AjXls5I4J5Ht0qaOMMR/CD+OO/9KQDk3eVtI5beMZ77QOPzpkjb5EwADjaMD0AOf/Hv50ICRVLJHtA255IIAJ7fyqFgTtIOE7cHnr278c/j3zQFi4QdisxyyliGx2I7g+v+NVGTMRYMwkBKhevA/wD1j9aSBk6v+8iBdQweRWJHG3P/ANaklGcM3LAbk6jPQ/4/kaQbjHIBcjLMeMtn5jxyPxzUbtgK2GXAwDjHHP51QmTFmHlsmMsAF59M/XngfjS+XISTGApKllY87QCuKWwFoH/RyqIvBIGeoAwce9VZI3jcMgGCc5X+YpIroR5DZ3ngcY9TmmsSGUHAU9v8apEscWUY2nauevQg1akYR3QbJCt85x1yDx/6CPzpMCESj7NIkbYYZxzxgAfzojj3KZcFi/CAnvg5/pRsA+SdykeegXBPUnkn8+34VAHABLjLE8HHOP69aYMcQrZbooyTjucen1qLByOQBz+NJCJ7K7mtLrdFncBt2kZBB7fnitYa5ebRlYiWwenT26/5zQxoptO87SPIJXbAyS+CDnPb/Dt0qv5x88d1DAkMMrx6j0oGVpZQZCfl2tyNvT6U1CR5gJ4fGQKokdFIVQgchhggHGR3rXtL57GIQo5faxC56HOT+XTikxokl1pzexSIqyhRkDGOqjIB9O+cf/XtPrgd49kQ8vb+9D98jop9ueo5p27gZk98gtZIQhKMx8oMf9WGB/UZqpdTF4o1BVAiBNoXHTvnPJx3/Si+oMrxSctuXIZskHvSOQTjGCR+Bo2JLBnXzVZ+CwBJx09aczLFGQiMuADjzM/XsDSGiOV0KmMAhhg8dDUcjFAACQ2Bn09f60IA3GSNSScLnI9KVfLwMlRnnBPNAC+dsYI2QFIP0pNoEhw3APUUARkEPkEYHf1qWOVMNuTgUMAc+XuGM7h0H+faopNykLwGb9KENjZHYRgOSSOlOVv9WpJKgUElIEgZPSgYK80igwOeox2p4XOD0BGc+2cUwHMrbWz2IJH6UhHQZ60gFP3seg/nz/WlSPLqT/q88mgBrxlNp5GRn8e9SwPwCyn5mHzdgRn9cHNMCZ4QId3TYxUHvxnA/SoQuZWTGFJH4A9D/KkhsUL+7jyMA5OSOT0//X+NS7UdtsmFXqD+IOP5f5NDAdDCSIwCF7khuTnAOPcU4CVXBVSrZ3kqPunHI/Dn9aGwJJniEq5i2yGPJYHHdg3t796iaIwAEggNymR0GV/rx9aSGTS/PEjt0KhTnvwf6NTVTyZfvAAKQQ44Oc4P5fyoAVlEefnGd/yhewChRkfiPy6VLA3mSJvjBVeWIOACSDnP1GT9KBEbp5DRQHBALqSR1XIwcev/ANekLAbJyFWKVlMgXkbhgn+v4ULuBOIxIcDLKFJCjg8en1/rTZrciY+YylXBIxyADkfpkZ+lJMoaYlDK6rslzyo6AcYwO2c+vaiNFjJf5nCvxn8aYglfa6ugO/dvG49+KUQhwNoxyzAAenYevfPrigAkykLoqrnBYc4AyMDOfqKR03gnaeHPGevT+nH+eQBwPyFVfpyVBGD17/SqyszJMUPCFSAe/wDkc0ITEkICgZwCxJb6n+XNSh5kkhULltmGQH74OQM/gaYkLK48lcMcAYyOFxk1BHKApD4bPzA9s+lCQ2OXOAQzBcY/QkfhUpG+BTvJ8slNp/iznB/9CoYkOS4W1lkdwGj3FiFGT14/L+pp8wCyMFw8gbACjPpx9Ov5YpdRlaW2YjcQioOMqWOSRnHP49KrNK5O1/mA96taiY/IbuMt6etTRzsUwesa9evGen60NCINqKgLHOOSB3wTVmJCHMTPlUkBGO59f0H5VLAc4VOTu3MOv97n/wCsfxqGU8kdM4Pp2oQ2QrIRnnHfFCuWkBY+wOKokltwN+SxJDZ4HQZx/hUpcKPnYbB3z/SkykQvIScH7pPXGAeak/d+WcZDdwexx/jSsBBNmRicAseSQeKYFOdp6CqRI8OVRkA7E5/A/wCNXFkjEZkYjKkYGTnnPNJjQkV0JCwVAABtxjt1prPsP+yRk+woGKELE4BIAOPX3NV5JGwYwQEPWl1BkRPl8biDnkKentT1+fgf41ZI8qzxjrlevHr/APqpUdmjAAJOQoINIY0HcQSQM9j3pzgyHBBO0ZOPekARxgx+/IJ/lUOwoxDfT6UwG7zntkdPerPWLcnof0oYIhCkrkc468dqVHIB4PP5GkwGiTacg4PfnFP3bzkyY7ZY5/nQIicFsYHIp6sC0YAwAcUwKwyq+ueMUm394FXr1HH9KlFDpgAxOSc9f1/pT4kDRHCnn/63/wBejoMlhXL5xwTgc/e4/wDr1Hs2tzg7Vx6Zw2aL6gSPGBGGGQdpJ98Z/wDrUQnJEbnhuVPofX9BSAkdDLuz9/eSB1OD7f57UttGQJVXGTnt94joCOnP+fYvoMlUKd+QCQwY4OcEA5/oP85qAH99CcdY8EHn+H/9dCEBO+EqVOEJ6tyo/wA8VYVYiFIPzEgA59xkflzQARxhowBu8xSQUHOf6/hSO5I2B9yYLHbz9D+O6kA6IM8afMFbfuAwD/d9fw/P2zUjDYYYgNxTI65+U4x19KBkRzDCUOHVWGMj26/h/jSqySSbX4XIBznJ4AJwfp+tMRGjrNcsTkblwMe2OfyFMiXdAQGJb+6OhB/X0/SgCzcEzyhpdojLK5OcAtgBh+YOPoapiPzBsjGSfn4+hOB+FCEy3MxjO7IO1zgY6jgn9acZwyEvuycufxA/rn86RQ7zDNt2rvYsAxHVfvce3X17DpUJkKL8rZDqAw/D/PP86AEYlUAcbg3oefl659sH9KmtZQAszkKPN79Ox/z9aYiPdlWTczb4wvJ4BA/l/wDX9qCcrJk7QMk4Y9OPU80dQZC+FRWQ5dsHIP3faiJt7mQgHjKqB34H6dfoaoRGjFUZwTyOCOKntXSF/NZlLY4Dc+/4cj9aGJDFYNGWYE4YEjqMDjHt/n1qLiMkbw23dgjjOOh/Skhksb7h3C5+YDoMf/rqJpEAZQSCDwB2HIp2EPV1nH744XG3pmp5JmUK4YZbkhTn8z60mNETh4ljxjy2BACnB4P/ANf9ahZQF3glmLHP0/z/AJ9WhMaRgE8juB6VJvZYyqKMN8uaYAzoo2knC5wB3J/z+lSrMRLIDwz8E9enp+OeaTQDldisrMxCnldzcDn2+g6VXMisp4wSc8UJDZGcFmyPpSomY2OenIHrVEkkJJ+4T5hyCB39Kl3SRs7LuABxncDz2qWNEbO3LMARnqp6VGz7c4GFPAz2p2AFAb5hxjrSu5KgccdCBimIRiGG4jgDGB/n3p8LgHc4yACcf596TAltHwr5j3szdc4Of8k/nT5SSU/dtt6dP0/Mipe5S2I9wkyuM5OVyOn+eOlVpHK5571SExyysy/O7EY6E00OUbIAp2ESebk8k8jFOAIikIP3T0BwT7/hQ9AF8xHJbIUk5DAcD8O1M/eRN8xIP8LDv/8AWpJDBHByNw596bsJ9T6igBMLkEt83oOalTgmLIIY46+tDEhEOYWTAHXtUYX5B+h96QxvRznqOtOkKsuc5PagRHGzB8t+tPbG0HsG/n/+qmA9VXIDjCMvXuDjrn8abGgkuCGPyn5c9MEYHX8DUFjiB8xlTjyypOCOR936c4p0SsISqZAY8NnBxx+vIoAkhXbgSKTtYndjryP8KiWPbMwBGEUk9wTn+pFK4FuPAi8vbwWUEH0A4P58VF5ahkXA34yOMdzwf8aL6jH+aVk3Djbjn1PSmAoj4BJz91hQIGkSN3ZF5YAk9cYOTx+FKxZ9xXOzeDnGRuyOPyP6UAJlTlkPT5CMcZzn9eaNyxyxuUEfGQAe/IoAc0oiuM7ScLnOQSR1P8v8KfkKm1WBI49Mev6YFAECTCGba6bgG7+mCMfr+lOExMjyhsycEAN3Ge3+f1oAk3IVDMflLcH0HGT/AD/KqpcmFmLDO4DGeRnP+FNCJIwcIoxuwQSO3HWiJyxXHzAADbjA9AD/AJ70ASOwaORcncBkjA5PTj6jB/EelQGRVIkKtjP3d3JwAf8AChATSTEnKkEOSTt7Dg4+vGPwpWm2PuQqSy7WVlJ6/TvRYLjorlYt7DkgAKenGM4/X+dNOwqGUFdygEAY5zkfh2oGMG4iONiOd2DjJx3xUkEmwh5ANod2HJxkKBx+X6UxCW+TKCHjYjrjJI5xyP8APWo5Xy7OFBXqcd+c0WAYXG1yVI3DhQen+f5U22dllwBkkcegPP8AiadhDZeIWx0DHA9BSPgeZzznFMQ4MQ4AyFkGMDrzx/MZpqgbXJ4A6e54oGJFkk55POB6nH/6qiPPNMRNGSWwOnB/GpTLuBJUEoPvegNJrUYiq21FJHfAJ9e59KjLg7VcZHqcHH50IBDhTuXinxkuW35AUE/pxTEMdioCcgLz1oBUqoIyxz1J4Pt+lAyaFXI80P5ZBzyOCfb0pjkSbmySe5A4pdQEIGAw6UhZkAZcYPamIUORJ/dPtVhmwhOPmJ5/3eT1qWNEPOeDnaO9MwDkng55+n+f8+jAXACNtJ54Ip0u3zGKHCcY59v8aYhvYehNKpyv4YP+fwoYEiojRruCggnJIzmkJZQojfduHTt+tSMjExLAk7WAxTGIIP8AvZqloIWNtzAEA5I6nryKkdQG2jgMMqSOopgAUfxfXApMApyTtBPJ9/8A9VJgNJKk/L8v3SKUsCGCgAdsmkMAiSDKE7h1Bpd58vaw24piIgM/dByORUsC5J3DORn6UMBg+Rd6k7iDxTWk3FSeAOOKAFQDdz1xg5pxwGyMdqQDWYHJ5NJuzuQDIxke1AFshXAXaMgAkDj8fbrSMMhwzAHAK5HQg54/lWWxoOCuUODk46YznvimghYuPlC5GDzg+lAgLnLNyOvHsR/+qo1dUYqD8y8bg3GM5/pTAmSTfCqhgGBx6d8j+Z/Omb/MG/GCO/8ATFKwXHKXd433ZP8AEB6ZA/wqFJssQRn5ux7dP8KdhDo2X5dp6qR64+Xn+dT5IhlWJgN+OVbHr+NDBEcLBg7EgbTnHr2/rUUj+Yu5W3bfX/PrmmAu/wAxEUj5ivHvzT95fc0mGOMY7elMBjMMSFznLA4B5+uP896d5gRjs2soViT16Z4/T9aAFjZEI/ijKs2Cf0pluFKyDnPJHHU9sfjigB8TrJdRbQQu7A9xnFRgMuGOCmRn8OcUAK8gDFPvK2MZ7YHGPwoLgRDnPZh6mmIYjsEZsdece+DUiOwHnEcIVycfkaLAOncOrEMS2enfg/8A1qYsh3u7dMBeB6cf4UkMmBEdxCSTtRsZHXrz0qIEv8pGME4QnJ9TQBGGMZGPlwSQTUs8g80OuQeppgRySln2Pz3DEcimqSjAjIIGeuKYguBs+TOTknPqM0SN5isT1BP48k/1oARAzQ/7oJB9cYzTck5PHckUwFjypGTgdc4/Gh8ZbHGKAHohMYAxkkYpSVERVWBJOWP54x+dIBrEnnryaCoYOcEHdxnpj/JoAQEYI5OOKfGeWPfB/lTERynPI6N+lNx05FAEqYIw/PUjmhdmSD8pHoetIY8KCPxqJj8oGCPXPrTEOAH3uRx39aGY9BnHakAmcDI3D14yKbkEEhsH0oGKT83XC+uKcAGGAec0wHoo4UnqD/M0wgq75GBSEPU4QEnqTjA5NOiQurBCQ2Dx/e9fx/woGMYDy23c44Gar7vlINUIdGmVJPTvilkcs7NjGTml1AkWTa4LHGOCKcu5idgLH0A/X9TQwEUcFX6DINRgYRs9cUgHxkQ5OQDjoetM+9ycY9KYC4yCcgMO2aUSbmIxjI7UAB+UjPIwRmohjePSgAzhqf5nLcdaQEfIyKIyVkDd+lMC35m0Kx6gk9OvP/1qhM7M4bAz0I7YrJFio0rbh94HHToeaUHK9T/Q/wCeaNhCiXLhtvU4AH0o2jeGI68/jj/69MBFYor8Fclc5HTrzSpOok2DHJ+8Ox/ziiwCvLtnDZ/hBPH1qu3AIHTd60ICWzRWdS3GCOM806SQh2VhkAEA/hwabAYWAAIB6Yz6Uzdnofwp2EOLjcO2Fx+uaVmyC54Yrx9eKQw3437gdy/d+venbiSXb5hwc54x3FMCMDG5QDwoJ/SnIGRsdD1AwOaAEg4+UkjHOamb5YUTqWfAGfvY/wD10ARMCu4MG446c/54oZw23GFGMH396BCFiFJHRuMCiJ9pGcnPbtimAOQMHAwckj60IWAGT8vXHc9elICVZAAWHUg4B78mol3Moz6kBj+GaEguPyBySMk4x2pq4I2E55yOOlMY192cnnHBpwy8TfNyvIz7UEhMRkAH5QOD7UxiApA7qD+eKYxVwExnDdyTxinBNq5Y4B/M/wCApAJu3HptPqKSQ72PYntTEJuIXr70AbumKBgSQ+zI9OO9PUsy4yc+tADFYox6g+mO9Srgk4PQMD+RpMCBjjApVJ2kjHvTEOUZXGPoaQF1bCseOcg0xjwx+7xnGeKB84Ibk+9IAJJUA44yB+dJjOMdhzSEN/L0xSp8pO9dwxTGNzj86VuD7dqBD1bfjs386lKh0LHlsYP4EH/GlsMiBIVsdz+v+cU9VULh+fX0pgI+FHy4Ib+7wKZu+Zg2ODn60ANDsudp4PFJ2yMZxgD3oEOQAgBu+cfWnoSrcDrQwHM4AJDgk9gTj9P61DkgEgZH8qAFyrEHacfWl285Xnn8qAEGcnt60RH98h96AFO4yfKOR1z0psmwSkJnA459aAE4Dckc0p9iKQDDz3ozhsY6GmBIH3KV7jkUiAHcSDzn9azKBGIBbPIx+IH/AOqm+YSBz+HYUwBnO0bepoJbAw3Qcc0CHk5DMe5GePrTFbDZwM9c/wCfrQhi87gGPXj6GiQnJH580IQ9WwijIBUk5/woZt29QoLIOSfXP69qYCLl49uemWGP1/lUYOFB/WgB6LkHnkZ4/DnNAbcNvUY6UAOcjc2QSM5/xpIicEAkN0UelAxc7kPyjJxjjn8KNytEFYjKnrjoKBDeNwUrg52n+VJKAX2k4HQGmBJLIc8gKSQ/Xp7frSFwSuCDn1pANDnfkcq3ODUsiqu3kD3x6E//AFqYEbqS69COBnsaTcOVHB9O1ACgEMpOBgZPt9aRXyAoIIyev+fpQAgHByw4PQ96cWGRhdp9jQAZyvCj+dJC+2ZWJxz1poCWdCCigdUOM/7x/pULIScnjgD9KSAVX2LkDnPU9qaGLH17k0wHg7iOd3FOlIGGweV4z6ikBE2cZpVPpkGmAhb5sHr/AJ707cuejZ9jQA8yRtj72fU0q48xcDCnAH8v50gIn55J5IzSDG3JpoQvII9xnrQfdiSaBicj5h+YqQHdyOuORQxCggjPU55FG4CLHQk9aQDUxnPpSsAR12jsMcGmAwHd14NA5446cUAKu3oeKmZtrhxzuH9KTGNAMa4OCh5x/n8KCysTgHNMQu3Cbt25RyRjHtUbAYJBUD09KBjAxHGeKTODxTEKGPc9DUmemD/Af5GkwG5+UA4FNAI9cHvTAMfwg5J6AVKhVRhwVYUgGMSFz3NKvUEemaAJXK/MRjOeDVcjj3oWwCuB8p6ZppPQCgBWOVGMf1oH3snJ9zSAC/QdQ3GQc446U2Qkdex5xUlDQ5Kk5xu604/KcAEelMQ5Coxnr1pqlWwAWzn0pAOwzLhWBGRj9aWRWQ4AwPX1pgJKdyq350MRISPutihAMK8gNT2U4cluenX6CgBYyY8MvcHg0w4JHbPQCgCRTycZHy/nxR0xgZBBxwOuKAHMMI7d2XkZ6cj/AOvUKq2SfwoAcCccH0NKspICSHK+pycUwBmLT+ZkfezTHJ8wluTmgB5I8mMDkkkn9KVVU4cNx0K+nB70AMJ5HtUgfa6Mxzxj6jmgBp/1m0dM4pgOecUAPWQgjHY9qXO5ST97HJIzmgBgYqOcfl1p4Rjzgkr1IGaAsNPABxx0J96Ov4dDQBYLACHnJKk8/UiopHXcWHUnOPaktwIuen40ZwvP1qgHBtoB61K43x5HIC4GO2Dk/wDoR/KkA0ruI7AjP61EfvU0Af5FKWG4kZ/woAQHnNTB2G1+y/40MCzcIILQkcM5wMj/AD2qiDtAJ6npUxGxSSe/T9aQEgfX3qhCK2DmpEOGDMMoDz6ChgOlTZIQDkZphBIPsR+uf8KSYDm+RRjGetBZmU9OOcH+lMSI9xBxTiARzkZ6GgBQdqhv4j0qbzFYKCOPT0FJjCT92xjf5mGAPbioODtPOfamhDt2QTkk/T+dMJDEAcAe3NAxo60Y5zTEKD2xU6DaEYjsc/kaTGV2bNOXgZNAhDlWyTk+tOZi7Zx9aABjuxn86khQOGJP3ecetJvQaFk24GMg9+Kgfg8HIoQhAxwM546U4cjPFNgMJOcEUDryaQBn5eMYNIOmAcGpGJ1Udu9ODBvrTATIU8jNOG0YPHOB9KAERt2SRg0b9nBwR/OgBzuRGANoGT2HtSbxwMDjHQYoAcCOc4YH1HIpXbCYC8kDOfwpAM3sygYyc5z3pVBeNgp5UZI9f8/1p7AA3MygHB9uKcoPHPTk/wCfpQCE3AqQXIP04p23ZGrcZDDI/X+lA0MI67e4pPmwoOeOlNCJM7nYFRhTjP40kiZdmU55P86QDQCUwOCDxzT8hQclskYP+c0wGg/KVGQD1NJJyQFbOBjjvQAm4gBic4ApVJUKpx15oAQnv09MU/cPLOQcZGefrQA0EHB9OgIo4Jz1oAUOycAnr0pzqAAwPymgCVITcbQhxsHB/H/65qB8B2UHIBwPel1ATGRkHpT3xtQ+opjGAfKMZz6etW/LCLAzfcdQcH1KnI/QfnQxFdjtUj3wKjDENleDQgAk460mTTAUDP41IrZXaaGBNcStLEVc8LtI56f5FVWO459ulJAA5HvQMEAGmAKAT1x71IXDDYowg/M0MQ8ElPmz6fSnyKvko3AJA3Y7n/JNSUQFssc4I7UDkbc8+tUIjz+FOAySD0oAVyWOakiwZ0J+7vAz+NIB95zcfhULcHOMUo7A9xw5X1HvUYIBIH5mqATJJ5JpW5HpQIsxW6zW+9SfMBxiiI/Km7oc1NxlXB9Kch7Hoe9UxA5yQPQYoUe4NACg980scnlOD29qQE1wq+Ujo3BHeqxJBzSWw2NySMU4cgetUIQ5I3UmOBSAQ4Q88j24p20ZO0nnFSMQsCDgYpF4QMBnqT+eKACQdMdMUcKcE55wRQgHLj8O9RNyfamgHZyoz2oJG/PqBQA5du4gnmlY8L7DGKABD+9QnocVIg8pgxHPuegoGJMQtxujPyHlT7ZNCbnl+XGcH8sZ/pSWwDFb5m/3TT4l8yJhnBHIHqKYDGJMzgcEsR9MmkCkqAqkt3poRLL8kKqTiQt8w9aDlUBIxuwR+Wf8/SpGRhyQVwAKQ9sfoKYiSIgnDHgDiklXoR060dQEI4Xng5P0phYHJPHemA4Y6GnBSVZc5OAcepyKBhtXzAu4DAxnHWkUHO0YPOOKVxD0Te+OMjqfSjcC+OVTkZPf/PFAF6JltrTI5eRSPxDcfzrNfhsetC3GPX7jdBnuaTIAU5yehpgKflIB9TV0OklmrMw3RHcPw7flUt6XAoyBvlB64/rUefSqQhc5GKM4HGaYC5JwTkg1JEgJyc4HJoAJidoJABcA4H5/1qMYzk9O9JAJ0GaTOKYEiIz5A+uPWkHyk9iKAJieoGcY5+oFNKsVwx5HapQ2RlhjimjOOKoQdSOKkKlSFHJPWhgNJKtyKl+9EccFRk/nSAWTLBSeDtBPvmoDk+poQwJxkUnHeqEA60NSET2k3kyc/dYc1ZmX96No4Y5B+o/+tUPcpFE8Bc/nSZwTjmrJDheTyadklR0/KgBueeaOh6UAWHkzBEp7Z+tVWOT60ojHgg/Ke4oAwp3dv50CGjrih+DQBESSoHcVJ/Hzx/8AqqSgTGCfYmhXKgjsR24oEKpVmUNwCcHHbmkOwsQXO48cLwPxzQADIO3t6+tIArfLjafWgBQnyv04wev+fWifZ5mU4UjI9qBgpHfn0HvSkEZLHnGTTYhAw24A/OmuzN1JOPWgCQnci+oGPyoV2E2epJ/z/OiwxuNvmnqBxn8aWJzGN64ypoAlOwyOX6sOOxB/z/OoCxPsenHpQhCyHlccfKKe5LRpu7cCgYW67xL0+5x9cjFRY+UE+tMB4B8st2zipHO1k5zlAD+QpAIgJdBnAxj9TSHBHTA5zimAjdeO+TT0Yb93U4x+lIBgbB6cnvSq21uDyO4oAdvyc8DPp6UsjMIsnAAOOnTP/wCqgBcEwKWJ4ZgB9Nv+P6VC5y2TTQhecDI47UjH5eDz3oGKWLcn6VLb7tjjBKFTzjgHFJ7ANcYwfUZFRcU0IKTNMB38OB0qdOIVGOZWx+tIYy4H3G7EY/KovrQtgYHpQD+VMQ5Ww4J6GrMqjAJO4HGDSY0FrCXB5wB1NRSttYbetLqN7DWAKllHy9T7U3HAPFMkXo/TgUYz1+tADlJxzyPQ1LHgo2OhU/pzSYxJWUrFjIJUZP0zUOexJx7U0IbjjNHXimA4L19qb95uegoAdjLH0qxE+YjuJ+XOKl7AisxINIDjmqENzT+gFAwpBxwaBE5w6Fs/d5H51Xb7x7c0kMQdc+lSbg3tQIbQw+UnrQBB0z7VJnkfTFSUAfAPoaReRyexNABnOMnpSHAYjvigBy5ALc9qGPzDjnjmgBeike9NPQDHOKABTgg9BSg/Lgdwf5U2IaMnpT5OJH/3jR1GOGBGrAnO48Y+lOfAmGDwFByfoKAGqR+9DdSD/MUiNtUnv2oAG4VDnkjJ/OhvlIx3ApgOlUsykZOVBJoONsffDEfypAOhbbE5AGcjn1zn/Cos/J+NAD1OIDzzuFNYfuw3qSKAHLvcBV+8Rtx7U1lKMVYENnkHtTAUnCAg/MfTtQuc9eecUgG7SeR09aeq4IORxzxTACTjnrTl+cMpPzHGPf8Az/SkBIGH2cHujkk/XH+FV24Y5GKFuADhW+tKiNIGCKWORwBn1pgLwAe5B9aktgHmjVjkEgc+n+efwoAWUEwxODlcYGe3Xj881XoQDkzvXALHPQU6QLyBgjruxTENjUuwXuf0qSV8SDb0The/T/JpDH3IAhj9i38xVc9TSQMM89vxp6bNvzswIOcAdR9aYDO9TD/VAFvwoBEkUiqAnOOhOO1NkAJ3DsA2D35HFK2o2Njk2ZYKCQevpRvjIIKFfQgj/CmSOTy94OdyA8qwIJ/LP86dMsLNmNSgPrIGpa3AYIyy/IyEe7hf5mnRxkB/niyeBiVTxznofek2NCSKUjiDZBUNkH/epUjG758AdPvAc/j1p3AiYbSADx1BxyRTCOeaYhc4FCgleOtADiwwaljAELnPOOKT2BblfPBFJz0NUAi855p3AAzSYDl5yTTeAMnrQInjOI34zwP51DKPnJHHJpLcfQQY5pAcDHWmIKXa23LHFAEgspWjkI244IyfvDkcf/XxUDZRsHgr1+tRcomiiWRCpwG2nB9wSf5YFRQoXICkdDyfxouOwqoYlgk+Vg5PB56etDoAxZVYoACT6Z6c0xEvlOLcswIb5sZH3hkA/l/jTJIlMBmSQE78FB/CCMj+RouMSRSo3FSp6YP1H+NR84HvmmIsFmQOyrjcrcKOMFR/XFNiP7uTgHC8HuDkf40hjM4ZehHB/SpZYVe7KKxCEblJGe2f/rUwG28PngpvC4Ocn/PtSSg7QT1xtI9MKMfz/SlcAddkzrwevI9Mcf0pCAOmcY4z3oAbgEJzjt9OakuoTCYwWDblyCOh/wA/yIpiGSZ2Rgnjbx+ZoDfIMDgNnP1//VQMVWwHBxz/ADoCFoncEfJjI9aBD4YjIoQFQXYAEnofwqPdvjUehzz/AJ9qAHRsEZTjIBBOe/NaH2JJtOd1ZTcRL5nHVlGAc/QdPpSbtqNGcF3d8YUn8hSRnDL71QhSmYQ4YZ3Fcf1p0yLE5VGLIRkHGMjANACBdxPOBnnNSeVsLZPIOVOOG4z/ACx+dIB8UYcMgOCzIf8Ax1jio5AJLrCnCuTgn6mhAQjvSrg8McDrnHT/ADmmAroY3dDj5f8AIp8QMc0bDJ5DA+/Ufr/KgC1KOHhG7Z8zoSuOnP8ATH1zVAegpIbJSrJN5YcqCQMjIyD60skUkeQ/OMg4piFjTyo2mPUZVcdj602NGkZQoLM33R60ATXqCNYxkHG4Eg1XSNpC+3HyqWOTjgUk9AYw9qUHrTAAPmwOtTrE0jBUBY+1MEaR0N1CoSfPZdy4xtPt9ah+yMnyToyH3GKlsqxS8mRnkVF3FclvoO9Q9KZLHrk5wecetOkjKIjMc7xkYOaBBKvlsB7A1Lj5ECksTwxx34OP1pDG3D7yp9RmmsmzbgghhnnjHJH9KAGdWA4GPSh12nA/OgQ0/epQ3bPGKYBjIPFWIiV4AyWBGD9OKTBFUcGgnrVACY5zTmwcUuoDv4eDUZ5oETR9Gyf4c1DLneR0xSW4xpoFMQ5jjnjNBzj2pDLGWSJMjgMQfRgMfp1qX91NbQRuSqxt8792HOOefX6ce9QWRIsoRtyEYZlyQcZI2kZ9f8KdMp3pcKMJKe3Y4Gf1zQIdLHHOpCr5bBTMuOFztUsMfgcVFE+BKCfleMgj1xyB/T8aAJJSrJb7SCQWBycb845/pT7pUOoyeaSI5UXoOxUYHtQNjr4I1wNzAxuAS57cf/ZA/nUFsrKJbZlw7ngH+8DwD+IoQD2jAnkaJx5fIGO3GB+HFNuo1VEdFUIy8Aexyf1NFwHR20Txli7hQPvjoBzyR14OM/5NEMbRXdtu+Un5efckdD9f0p31EOt40aYoXCrLuAT+6GXg/rUlmibpZplG9CGwx7559u5/OkNEUhJtDCcl4pM5PGRgg/r/ACqFAYJ4gy4ZeqsOnJ//AF00A+8hO+SUhQhkwcHufbt0NPtHU7I2ZirArtYDbuPI+o+vrR0DqMlTyXini+6ckKMgqe4+lS3oiaCKaMjZwCBwRgcD3IweadxAkYWSa2OclecAfOBgj6Hj9aZDaK8iRxsSZYyATyA2T/QD8/wpXAhdWt5ZEG4bGPln1w3B/nUktqMu4cYZ+QVwFBBYdMnp7U79QGvbBj5fETrlWzkgnnB/E/0rTsCDcLvLKS/lbceoYY/Hn6VMndDjuZ8MI8rD7Vk6HMi88EEdfcflUCwlHQsduRvB68VSYiZY4yyBfnhZ1B5wQOc/0/OrMmniUkhxEEBAUgnIycHP0/lmlew7EqQQRTxBo0fdiM5JIJxknnuc/pVXzEYxMYywjkZmycZBAwfyU/lSuFhsKbZflXdscHB9t3pVhFTzcoo8uQZVQc4O4Fh+GPyp3FYy1OdxPcf1pY3CEnAY4xzyKoRabzJrfzIVOI85AP3BgdO/b36VfMUC20iEK52Bg7NySASCPTpj8TUtlIgGJPJkkLhjHkNjgt9fwqr9gkW5lifaSi9Mn5iw+XH4kU72AgbIA4xnv68CrMkuBvdsZA4HQZAJP55qiRZB/r4gMBiSoOTgjt/SicRJNbyxKViKBvvZ5B5xx17496m47GgsUcqK+SkiSIxDfdJDAHtnv096z54ltr8R/K0bnjA6g5Hekuw2Ugc4zzS1ZA6Mru+bj0NaVhci23Ejlsc+nX/GkykW5b93mXa42gHkHvjim3F6bxIzj7gI+tSX0K0kYjnhdXwlwhDZHQ8Aj8yP881nCNvLMm1tv97HFUjNiD7hqQyeZGN55TqQO3r/AJ9aARPNGHdkwWkRVz9RwQf5/nUMb4yr52859RSGSThVK7cMAo5B61PZuRF5TMfKmyhyfu56H8CCfypPYOpnsCpwwwQeaGbDZ9RViGk05cUCHR5Lc9KmgYefGWJAzSYyK5O5lJHzFRmhbcyRb42DkfeQfeHv9KL2QWIR1p2OhpsQ/ocH0qM0ASxfe2/3lx+dKwUvJkZ+UkfhUjIfSlwCMk8+lMQ09PxqQDKY/GgCwrebb+WFJaL5uvBGAD/IfrUIbJY5PPWoKLUMm+KcJ8zAbgR68ZP5A0xGcLsfOGIKhvUZ/wAT+dIZNFOguInVNvG0jPBHXGPqarTIsV0wXlA2Qe5U9P0oWjBkioyWwmQ56FiF+63bP4E/5xToUF1Iqu+HwQpI647eg/KmA6JEuYNuWL4O0dgeoHvnJqFgJJdyqWJJOB39KOoBvCSJIgPTkjPOOv8An6VaudjhlXaFkwwPYcAkjPHUsPxoYxqw509vKA+XlyDy3cfkR+oNQSkSRxMMbwSDk9emP5mjqInmzsjkQneMRkqeMgg5P6/lTAgaRkiwNwKDHG7IxgfpQBKJS9gFRz12nHfPP88ior+NpJFlyAZE5bHUj/622jqPoIzIXkyWCSAbhjkdOaLhAkhQ4UoRtkVcfTIH1/8A10xDjJEySLjG4bzzxkdcfr+lNi+a2eJ9pOMrxz9PrnFJgTWhEk9oHTexBUE4Bzxt/Wkt5EWaES8ukhGOx9c/560AEzLBMUYqdp+RgMlPr2/XNLbt5V6h3lYpRhyD29P6UugEU0ZkMb+Z+82kdCQccZ9h0/KpELOolR9pThsdQRyDx69PxHrT6D6jbpGjv90Z+SRiwIPGDzjPToajeFzagkZETNhlxgrkf/W/A0LRITGW8rRnMZA/CrrMSYpQFKuoVl9QCAf0HP1+tDBbDUQXDMI3PyKAobgr6c/XHHWqb/8ALcDAAckY55yR/WhDZIg8wpjhihLMR3C4/wAn3pYmUfLGzDaMrxznbg49c/zqiSOKJbiPywoEw+62fvex5/X6U23t0d8Sl1BOAV55+n9P8guFi4w+y7diqyRgo2cYYEcdPXmnq+1VODtjyjkjqowVA+ozU76j8iJJfIMb+YnyrtK7T82Cf8etJLOEuEkP/LOM/Mx5JGSP6c0AUWIibGDj+maeWzalsA7SByvHRiaoQs0pN1Jh1TaxI4xk5q4jCa28uRpCEbK8nK5zzk9AcH8celJ7DRYhCSMULSCUqgAUgsWHI5OPT26e9Q3ciSRwzKCTG+EY8fLkkZ9Rx+pqb6jKKQiSGbaB5iEMOeSDxjH4ik+z4TDBvMxnaeOK0uTYkTyjGyzjZkBgQCdvJBwD+ePahoyiAHB9CDkEetIEEqnYkajJb5/5ilsywfGMg8YoKJbhXS1ZCSTE4IOOxHX+VMt3JaWA8RyBmx1AOCQcflS6C6kEgYBEYcjK88H7xpux1mER+Rt2Dnt+X+eaoks3UjKVBLgdHUnjIOMVCsZkJUDkdv5j/CktrjBQGO4qSFznnFK7FZHHI8thtH0zQBPcGOVLplQHLCQNjk5Izj25qOSOOSCEoNmPlLepOSP/ANf+FC0Abd2uwedEuImbaq5yR/nBqvsdTgqQenIxTTuhNWFUkHbTlGGGegoAmEUcmDI5XHBAA9TzUdqsiXEflugcsAOePrkUr9BtEt3D5xFxboNhXcwUAbT34pI7NpBHtdfmXI56n0+v+NCegNalYcnNIRimSSw4VxSj5V9ihHT2xSYyFBg05FzINx+XPPPamIsOkMMy4O5TztkGQR9R/h+NNuI1iuJEjB2fw+wNIY5ImSRZIzIoH8TKeT7YolKhiFwAwO5B2P8AnFQUPnbFrA43ByCgweo4yP1NNgKyfuJASj8IxP3CeAf8+lOwxGQiISxMWYZEgx09/p1okzPtOcED5UJPI9vx7f5BvqBaZ42Qu6EFmPmYH3lbkN+B/pVZVZZPKaPJB4ZRnjr+IpAWJFLyQMgADKMmPjnceR71HfW/2e5zz5MjbkIIJx1/kaED1ImiUY8gllYZ+YgHrVqEots/mIGO0gA5443L+uaHsC3GCY284VgPMToccEH69vb606OOJpDhf3bAMPUdMj6f/WoAakW/zYY+zDcCehHX9M054BCv7okkBWDED+8Qf6UrhYrEKiExMcHDBc52kcfyqaElraMsciKUYzwMHqOfdf1qhWGtAx8l0z82fmz028Z+nTn3pbnJhjZ1YkDYT29vr3OaAI8KoRotxUqG+Yjg9/wqxDAjRho2YBQcc8gA5z9cY/GhsaQGPyY4pRIWJkBBHGBxn+Y/WoSmy4Koej4z68kZpAPCxSzPvlKquVzt3ZPT8uBUqQhIo5VcMUbLjrxkYb9T/nNCYWIrggtNAq4CudvOBgZ/9l/pUUblLd2bJDAjB5GO35UdA6lq4/1WYsHy2KsGPTnj+tEIDB8jCmInOD1X/Io6De42PN0I8LGkiqCxHyhlP07/AOe1K6yC28pwQqE4IGQxI/8A10xECy+W6HeSyYxn2q3LGqxK+BtGFIcHJGAwOO5x/nrgArrKMuYxsjK5AB5HP/1jUHlESKxdRuPBByQOf1+tMktlYpIS25UKHO5Yh14H9f0psykzbn3ErwQykHHXOOozx+eaRQ6FSrRhyjiQZVvmYbhzg9D6Z/yKRJYpInV9yAhdvPXnAPb1P5D0osBBc2/kuqLIZOD2x0OPfPShVaRY3Vc+WSzE9B0/+vTT6iYyWzk2K5x90LgsARj0yfQfrSRBFAVlDrnJUt16jt9f0p3uKxb+0BG2CHdG+GcYB5PP49emKQ3bKwkO1xuIwVA3LxwamwyeDy7ciYeWUcgDJLFR9O34+lEqeYszlcDG7aBxyefyyR+FIoqpwREGJVhtK7cdenrznBqJ4iVb5BkcZXjv3H9aohhgbQC5JwSAzHA/PimbuWHPrTAlJ8zYFBHyYP4E01S0cYdcgsevoKBl+2a2e3aBgFLA4yfuH057ZPHvVIQujgtuBHGSCATikgEnYTQq/UjhumM/5BpuEMXmtu3AY3Drnt+n8qYiW4VriElVJYHdtUdiPmPvyBUUZTzAyMVcHJD9Mj3+vbFCGx8iBkYJ9373qfqRSsd9ugOQU+XnnOef8aBCKSyZRQOChP8Ae7gY/PmpJFjNsSiMo3fdzkg59fz/AFpDEkYS26ogyUIyT7ZJP60Xsxnt0bauVOCwHI46Z/CkgZVVOck8dOe3+NKcIvK4z68k1QgI3sCrfN7k/wAzUhDKokbAkU9iDn8jQBLbMYiwIBGSTke38qGLDpwAd4A7eo/KpGQTx4uHVAcfeA9sZp0KPGQ6hXU8EdfwIqnsT1GwKpkWM5VicA56/WnCFwpbGQP1FJsZDgE+xpGADHb0pklhJihibAK7dpXsw96dcKN4Kcqy4578/wD6qRRXO3zcqGAOWHHT/GlVvmUZwDgN2yMj+opIfUd80qAb1RgcqpHGeM4J/Co8k4yu3acH86AJ5XAkztHlSjcyjrz1H4HOKUny/wB0QZYjyvbI9V9P8eDnpQA5DG9wI1Jw6hQx4wc4BPPbAqMOQVw7KynI9RikP0HGZGZtyZUggAYG3vxxxT7iQvGjFmdJACQx7jI/lRYLkWcoSMYQjpn/AD2p8M77gN3cEnuAD/8Ar/OmJPUjk5IMhyyLgY79f/r0gfJOSCrsDnHIOetAy1BI6XLSMYwu8vywUn6Z9qW5mym1T5ZwQ3GAOQcD06H8MVPYZUi3oQYyCRnGCTjih3JUKqkbuACePw/Wr3ESgo0ciDCkAMvU9sEfj1/CnwlRC0Up3K2MeqnPUfhkUmAyVN8ChXUqhILE9c9P5U+zba7x787lbBX6Hp/ntSezBbgzefbiNvlIfA2jqCOTjI9KgmcySLJt2jYBj1I4P601oDFdd7l2mQdDg5qe1IDmJiNj5G7cDjIxnAND7AtyML5jrvkz8o6nPbIz7c4zU6GSIeej7wGBcEcp6Zz16mkHUsI0FxBMURh5qhck4AI5A9/r1P51Vi/cN5cxChmA+Y9uR+fT6c0eQ/MrQuwffuwDlSPbp0H1qZYld3UEkKBtAY9PYevWqJFRflJP+qDZDgjk+g/z2pJJ3niDMMOuFGwnBUZ/WkFxMMwZQNqkdOB/hzSGF3Uud21QW3A54/DOPqaLiJYCEVzghmBHzZwDg4/WkldZIlkdfnjO188Fl6fnxj/9VHUroQ5kWOIEnIbIyeh4pUePzvuDYTkAjJXngA0xElzjcCVXbhh069T/AFqLcUDEFg+QT257ikhsfLmZAqnDKGLKO+ccj2GDn0+nSvtKsykEHlf6GqXYQoy4YkDdxnNPEMk0ahBuKttxx3/z+tJgiS1kQr5bPnf1P5VKsjLGQxKkkfU56/mcnHvQxjJCAFfGDtwMHHPUH+VKEXnYyHHOCOc0hMidjkn7vHOaarfOvmY2jGVHAAzTEP4RpFYZMeeR64I/wqOcqVQKeNuDg47/AOfzoRTFiJiZiuDlSoIwev8Ak1O77lVxw6E5Hcjjr70CRDKCM/Mp3dSGznmlVgW2jgOMHJ7dv88UxEpCxwAJu3ncHB9AQf8AGmw7ZZlWWVUbb8m9cqTUgyJ5AFQ/ISRjIPPbv/nvSB8xvkjkDnHf/OaqwxUYRvnAwO1KJfKBz/EMAdzS3FckhU/MqlUG3JJGTzj8v1oWOLzCpG7/AGieB+X9KQyUJbqjCSTfIo+RVRgvXHJ/XoKrogJJJUemecfp/KncnQe1qGjzF+9HTCAj+eTVVgVBBDDHHIoTuNkodVkII56fSplZVJDjpyT7UAOkQCRG4yqlSfzx+lQx/ITnOG9Ox7UB1Jrpi0gffuyMHBPaoQxVmOefWkD3CTZIcnaG67lPX9KhKgKckZ+tMQ9Y3dQETOO+eKkB2xbJQpABxz+YpMaKudwAOOBgGpY7fzIiBuE3XBP3h7UxjQC7lQm8nnaOf0pJhOvLxOMd2TH60tAEV2ZC2w8H0zSeZkYfI6nHTH+eKAJFDmMOqOUz0Vs/jipsOcyKpI4JJHc+x/GlcCFmBfJIUdwOP/1fjT0IkjEbYAUkgE+vX+VMACqG4dCpyOGzkGo0ZQwBGB0JoBbi71V0bIZiM7WGRyKcCgVmfJZugXp+lACM4cLhfyP+NOjLYw2cBznuQCB+uKBjWXaSQMjqO+aAwcAswB6DHXj/ACKBD7YgmPceN2xsen+TTnDeaBMFjYHb1GOOoyOM80dQ6AQQJFYMpTDYboTnH5YNRxuY5AQo3DuARn/P0osHUfCWPmqFXIXOewxyfxwKb8wUfMSBxjNACbn4ADF+AAO3Xj+dKAVBdgWKn5gQfl/z/hQBLON7INpVgnY9uT/Ij/JoiZsDJZD0/wB4eh9f8igdxi7VOTgnkZPUc54/Dj/9dEj+aAqqxbALk9gCMc/kPy9aYriABmADLkd2IXPPvxU8akSKz5HljcT0wuc/z4H1pbBcYV3IMHauPuADC0igZ5AJ/vAnH0/lQIR5MSIMD8RQgckxjBODgn0PUfjQCEEuGAYgktnn1/A80SHekcZbK8AAgfL+P5/lQO5K5DA7cbTh888Dkfnmo2+ZcDZgdjgcfXPrmgY6Mb2AZgduePXIx/8AX/CpmtTd3LJbRM7HkkMFx9TRewtxVsryBmRoQu7jcJFyOcg8H2BqqzCVfOZghJwxC5J46++TQmnqhtW3EdEVuZjuUYwyEc+nGcVYiYIPLjdsH+HbwSO/X1//AFUxEbwqt07PsCffUH0PI/mKJpR5ON3qSPUjH6dKQxCpaR4gCSCQB6bT/hTUZozjgOD128+3Xp7UCYszE/vCx5OCfx5qJ03BlX5OO/8AF6df6ZprQQLHh3QtliD8w/i561LFCzpERs2suSWyAB15xzQMU4Vxsii9QVzg4+p4pVYHe7DYQVAI6LwevtwP/r0hjJ4tqhiACSSRkHH/ANY9qhLknkDp6VSJLJkLhMfxADnjPAU/qDVZiwyqliOoOMUkNj4wTEfnKjIHT+f507dF0jV2b26D17UySP5s9uxBHFSr5IOSBkHouMf5/GkMeAVIG7cvO3HPGckfnUUZBRw3H40AMCc5jJz60/c+P9YR9P8A61BJFGXjJYOR+FPZncDeenrxQNDxtbkr7kg9acxU4w+H6fMv9RSAapcMB1VSOR09qQ4yu3gjn8aYxSxbKg8MRxwfpTSTnmkAgIo2gngn8KZLEClRgc803GSKLgNDIr/eY+u1SMfjmrlsq3FxsnJZcfKQ+WHvmpZoRta7rITg8MwVlGSOmckA8dDVVDGCQE9jtpphsSxhtx8pUYtnbuXLfhU8fyhhJPsc9gg/I9P8KBCJGA370BVXoynPPbpQJGtn2ggxsvIDZBBHftwf5Utx7DXt1DL5eGVwSvrj6VHgoWwMEdckD9KYh4jJRjwABwQwznuBnBqMkLmMRMMdSzDn9KYA4BIAXOF9c02Uk4fJOTk5HWgBVnREMbrjnqMEj8P/AK9Ty2rdmZ3bBBA4b6HPX8vx4oYFdfNPTdtPscH2yKkjTGUkTHfB7en9aAI+VYrtyeTwf8+9TxTM+Yy2Vfk85y3r+dAhA5khKuRuUbMjn3A/TFRBmCrk5UHOPQ0DJYpV3qSAvOCFJJweCPypgJUBl5X2FAMcjAjHTPbHXtStICMglWwACOM/5xSELuDEll5YAHBo+0SMhVixXszZP4UDuISzIzLuzgZx3wf6UkZkjAJDJnIyynkdTTEPmUs2DwoUd/U5/Dr39KduUQKsWV+bcxHf0OfzpDI28wKCQCOzA5ppG0cDOOOaAY47wis3fIXJ78VKjAzYYrGM4Y9cCgCGQEt94YJyD6A9OfxqyEcqQcEdckAADr1/LrRsHUakTeYVchN47MDjmhwFBy+UxkEgD8//AK1AEEkm1AE27ehGBuPXr/nvVmGeSNcGRVLHqCoYcfnTY7kTKrfNvZ/7xzwBn+f40okDoYyP3XXjnFAhfLj8tSz5zyAozn8/85oz5IEin5lbAHcDnH8v1ouA6RxNDGG+XaNoB7en1znH4CqgLBiWBGflwfwz/KhATjCmOUMGOTuDZ54GR+uKFkkVSUI2fw/MCR+H/wBagAhbFsE+ULuOQSOemP8AIoeNVG4bdp7FQCf8+1AMRBvlTIA25wPwJH8qdBK3kptfyyOP97B/+v3pAtiOZZFbErITnIJUc/598U5JMKU29eeB/n1pisAnkiUAIc9QPTnnj+lIknmsVjXDEgYIz/OgYeY4PzbSuFPTnHt+dAKO5wr8KcHO7/DFAhmAOqE574/zmpUiCuCHy3ZQeR7kUCHuo3Kjbg56jHQn2qKRZIyQyHPcdf5UIY+XZHIG3oxI+bZhD+IPX9KaUQn7uwk8h/lH69P880hsZnZ95cDGeR1FO2k9Bux6CmSIe24H8aQEMDSAklDIw9No/kKYrgnmgBGVRIGByAO55ofimMZkjg9qeZAz5xxQIjLndTgWPI4zQKw8MQSG4NR5IORSCwwRsWGdrH0PerlhlZmZsDy1yeOuSFH/AKFn8KHsWNmleC5ZdrSQtwwbnIz+lRywlB5sZLQscAk9PY+/86S2G9xm9wpQliuc4zkU5HEeN43IeiEA/Xnt+FMVyUh4W3RMxhk5HJxx6+4prSFUQLJjj09+x9aQIcWjfKtK/JB+dePzH+FRrLGHOIlYDp83P6r/AIUwEZmlIDOFx3f/AOtSxiNjyGYZ7A9O/SgA8gs25VA9gf6cU+EtHMJYYi7R9tpbBPQ+nFFxjJUlba0hLFs9RlqmheVCY9hZWPCsMc+wp6AR3FuZpJHjI80DLR/xfXjr60xYnwWBBUcMxwB+X5UILDJYixLBGwT6Hg0n7pIJAdrMejc8c+9ArD0lMmUkDZAOGA5J60MFVSuD1ySeB+Z4pAKjqUComD3II/yKVXJi8pU+rYGSPc0wGBwfldQoH8R7/Xmms3VfMDqOM4NAhmXLBce/Q9KuJaCVSYyIiBkq3I+v/wCugY1rhGIGP3YUJkDA6cnHucn8fapLWdZGe3lIdWB2Ejow5Gfy9aAGiFWZ3dJQ3DDnbgenfoKaQV4Eu8k8gY/IH3zQA2JpCwQDlv4SOv4d6mlSNCfMUMPSMhQff3H+eKTAZlVGznHfHTFGY1dN+eOSVHX65P4UIBssowCu4spABYDP8/r+dG5wBwUkPTLdvy6f4UWAm81eWBU8csQOahkmDEBXUjqQ45JosMdHGZ+HwsY+8SOlPmRRzBJ5gzj7mM+4PNHUSWgxdzjIDEMOigtkdT/SpDFNGGLW7quOQ6Hkd+v1/wAaBECsSCE3BVHzDHCj+lWBbKAWeVcc/wAOBwMnn1/CmMaobDqh/gJXJyB6/pmqxBZgrnaxAwSP8/5FA+gjFgMEjgkc0mSQPlGfQDrTJJBh1KgZcHkf5+lKG24Vc7iO4xSAkWMw3CefhE4bAx0Pf+dN8tooiFDqM9yOfei4FiJV+znoGUDawXJwPaqxWRYzJGUOfY5H4YpIYr3LOo4EbDPKIAT7n/Go2OGIK7crxn/62P5UxMVcsoJHOQAP8KMDJCt0/D+dAh8AkLbY3wScYwc4pXkmQfJKGA6MrsAPz4paDQ5ZJiQQokYc5LKBn9M96QTSTSnemWyN2fy54pjDymIbaG2E52xLx+gphD+Zs5jbqQ39e9AhGXYM7lI9m4x6g0wjAx1/u8ZpiJGV0kO4FmUDrx+Py9frUZyMZyT2IIoGPldpI1ZyTtHIA96YjREMXHPYf/rNIB0kq7BtjCn0FCSISTkZY9xnFFhEscOQSojJ64ZiBTJSWCliuFG0KvYf5NIYh2MABx7nFNdCFwWZgO27+VMQi9QM8DoaRjhiOmOtAEhlSQ8bY27FRtU/XFKS8UTJulRfTjaT9AealopMWR98SPnIBwT68Z/xojuChZAGkDrhlxnPtj/OKPIrrcCF42AsT90E4IPpwOv41GznzAzAHHBXHX8qBFiCVVbZ91SchXIP4g44P4U5wXEqztlmbIYjGSP8QaGBX2uU46Y/hHOP61cSaHaqPCrLtxhhgfmelDBabkoi01rV9xWJuquTuYHjjCnn9PpWeRDyYUOOoeU8n8BwPxzSVxtLoJgnlgTjnjimje4JLnjjqaskGLDCn5lPPJ6mkVyflkGcnOASKLAW1vbdcKbRUTI4V3x+RPNRTXZ8xvKIKZ43AbsZ4zjvSsU2ViiyHJKqfX1p2FUD5eDnvzTEOY7vmYlSQO4Ge2f8+lMLkFSrFSucGgQ9xE6r8qjB7cCjKq2S20D0zSAH24JIG0jnsc+1OjCuxB2gDjGefTrx/kUxCgsFACEg8Y2559s1OGeO15zG5OMlMELkcf59MUhoajLEMkAyA53nPy+4HGP6VHlwCyMcLj5QPl9Rxj/OKAY0urDBVUYc4PH6/wBTT2lZ1CfJH5YxuKgseSe/1pgPRFG9YWVXZfm3IBkfgOPwoRLeJow8zZIIwi9/UH8vyNIdh8qRqFwd/OGYKM5Ht3/yKh+QZEcqqrdNw6e3fFFwSFVsNy0ZbnA6Dp04GaiYSOxD5Uj724Yb8aAFUZGACVP45pkkY3lVGD3AFO5JIMHagQh+nH0qX7MGw4+TgZUnBPsP8KGwG5l2Lt27ATjgjH58flTy7pgGfcfQEgDuMHt0FLQqwOBJb480BfRvu5+op0QlfYsjB0XleCeepB9enSi4C+X+7VU3FnbaG/iYHOOnY8/981UlK7zFu5XIPIKn6UxC7C8eVhl9dwO4flikaPcm1VBPXOQD/wDqoAJGkMpJb5z8vrU8SqImZ7hS47bT/M4phuAZbyRVm42ry+QT9Bj3NS300cx8q2VmweGHr7AdhU2Ah85YItshXJAwF7evFMSQzh2QqgB3YGTj2P8AntTt1C5KkRmidiyPtzwwOQfrj+tRXMK27AFQnX5ixOT7f5NAiLYrnepYJnaD1JNSEtLI44PVvx7/AJ0DFjd4dxVyHxjePvY9B/8AWqEIJNzYdjnJYjp9TTESHanHmM0gx8w+YAe3/wCulWWP5iRG+DlSAMj8qQDZH8wLhSpXgsGA/TFPDSxgKWJUHqDkf4UBcFfAyCRk9e9DOwDKM5P92kIXaGCh3XcBgH0Hp05pqpwI1wWPagBzQiF2jYhiv49fpUTEqWUeWeOoUfzxmmMb5L7W/duQOSQvajaobhfl4zimICzgc7iPQnIFP3Dqe/p/nikAjZ4OfzFLuwMEZzzkUgGvtYZPX6Ypu1gRxu79c4oAhVwQBt5PU46U/wA3AKqzY7Z5pjJIpDsZFOMigy7gVb5WP8WetKwxYJzgj5vQcgD+VOlKMzb1246fMW/woYEaou3vg5Of071NDKFG3zCD2I/HrQNCMxJLYBx1BOPx9KnQb1ysiLtXkSPkY9B/+sfzpARR3ixEhBtP99PXHPHTuale4glyZ3bPBDAn0+gH6fjRYZF99QV3sD/E3y49804BUJHmq/HWNgcD8+f0ouFhuG3AqMrwBlh/jVhIEa33OyvJkcK4HPFO4kUvORmKttxx74qaWJfkcNnP9zj8ulMCIqEIDKAT6nBp0aqRyGGeh3UAK0bYIKZZeuBkY+oqJossFHBNAhgDI2cdDjoDn/GpY4zI7JyTg4UEDtx1/ChgiUQQRqWupDvA4j5/Xoc/So/Mt1yIoyxxzuI/mMUtXsPTqOM8oUDcsKNjAUdfcZ5/XFJMyrgLiIjnAXr700AbZdzITj2Ixz9OMflUvkMGLPNkkcHbgH1HGaWgEEn3Tt6Actng0+HiMKw4znOc49D1oJ3FY8oCwI4B+bH0/wA/WoVKqQQhIDZwcHj696EMsxSRvI24kFzuPGRn8T9f0olhgmCsA29mxkcA/h+X60bD3IlgUJxH5h67lJ49+MiogHzlAMAkZHSmIefKOGZOR1+bAJ9f8kUhkCgqsg25+6OQPoc5oAncFMLIuNyZ2t1A9P0/Wml/MO4ZBAyP5/4UhEfkg9ioxkkjr70Bl5VskL0YZ5+lAE0Lxlh5yjBOfYeuBUvkD7VMFKjymOBznBBx/MdKB9Ca9j8iNWErAw4U4yAS2ckfU5/KqQdEwVlMWeo8racfUUIYwru+ZgMsvJPcfWmNKAAq+WRnqDz+GaoQ5UZsFoQw6jB2k/j3/OnsuHIGUXrgA8fjz/OkAqPsDKhySOcnmmyI7ZyQF64HT8aBDHtxEAZFZP8Ae4J/OpYXMSFQi5YgfN/Wi4hZCj7eP3gySduMY/z/AJzUskxNwJFcBg2T37np/ntQxjJn8w4eVk3dC3P4ce/t6UgeSPKdT04PX3FIY2QkBXQhQ3PTOD6VG2WyzEv7k5NMTAElsqMmkMjMRlicdMnOKBDydjENjCnBP9ajdz07E9KLCHAF34x06Ln+VKzYI3DPFJoBCWPGSo6YHH6U0B8YHX64oAkVipOQMe1RsmVJPGD254oQEkLlABu3JzSvEYnOMEEfLyeKZW6GjksOee9MLMnRdw7gmkIcwGQSBz2FKCpbOc0MTFKq3ccetM2lRwevbtSQFcowIGPxA4pwZsYbGR2wM0yxysVYMc5xinMSRgjOB19PwoAj3ZUqcD0NLDHI2WjjY45J7D/69AhMlmIZm3DPDdc+mKcz9CWJIxmgdxyu7Dcik+vFEyM2CQQy8lWHGPb2oDcWR324EqkYwVVcYGO3tSGQLIdoEbDpsBAPp/8Ar96BiD99gAEEdAOSfb+f51Is0kK/eZk6lWJ5/lTEOjujIxBjA3g/KD9PXr+dS3Ckr5Um9jnPzMDxjg5x9Tn0JqWug7lbyosbjI3HYoacjwxEhJSYyeV6A/z/AJU7sLIkZ7UEeXLIh7kgtj9BinLtcjMkTgAkktz06njjgelJX6j06EkaQkH/AEqMDowUkD2/h/pTZB5Y3xvCSOgVh0+hx70XDQrSXOSrFvmyRlVAx+lL9s+ZQimVEXA3L1+pp2FcnFyI0MUUkioexUEf+hZFNHl7gyDDccrwAfrzj9R70DJHkMalXUhmGfmYHdyecY9qg3NFvh+6F67WyOvscYz6UCGAByWI3EnsSMfhSfKVHy+ueSe/5+lMQ5XVl3ONrA5DYPX3qX5dm45Qnk4yQeB/hSEIFUrn5cc/OGGMelIQA6h2wDwCP8cmgAVwv30BbPB5yDnrxU0kavatMoVfK+b5Rg4P16AHIxQUJC63KMOFmxw3A3H8eh/z71DsmYFGctjquOQaBEboV9cD+9UsUaIQ/wArNngDt9abFYHDvKJGBLNywxnP1olL7DkHGNuSMfr+ApBYaOgYoPYtwB+dPeRw43HDYyO2R+NBQ9I2Y787gfu4z1/GpIZBbMZXG9oyAfM6g9sdeRxQBFct9pYFVbCnJB5z+X+eaZIuScj0znt9eaBCKdyFM8Z6bv8A69CPv3E7Sr9NxwM/h/WqAazPjyxIVj/uqcinK+0YaT5R/eOaQrkkbgn/AFgJPQL8v8/88irEQMG7dCSc/fL4OPbAqWAmIl25ZA47NIBn8gKEgUrgshTOQEIODn3yfxouArx4bcZsox5JYevbp61FMkKKfLOGUjuT/QUJgSNE3l7o8s4HzIeMe49ahMUflsElXaeigncOfy9DjP5UyrEUf7sgBlKDqSuOe4xnn6mnuqllK5CvyCeAD6ZoEIqFWxgKfXrSNErfKGKkjhT0x6dzRfUQhhIc5Xb2xkUvknb8iKFPHXP8+RRcBu0ZwWOPTGaUh+fMywzz8vP50wHDDxDJDYPDEdvQnP8ASo3SQnKxquBng5/GgB3lPt5257/OD/WmhMdFDHvzSESJCGUllk29OF4/PNOU+biHGePl3Hv+FA0JEpkOwKisRxkn/wCvSrGI5j5sqSRjrjrn6elAiG42yS7kkJOPTH/6qTb8u7Iz3zQAmBkfMB70BvXI4oEIihvlUFznG0Ad6UBPusNq9zjJoNB6QKyExMpA9cA4/wAKa0bI4G056GlfuFiNlCgjnf2JPT8hSxTGOPeI+QQN44/l1phsTyXqSZBtoeW5cLg/XpUTuWY/KnAxwg5/TrUpWBsVZJE6EFRxtxxSqFYDy12t1ABwc/5//XTBCF0YnzeZc58x+v4+1QNHIBtJYKTn2poGOjk8oKTyoORzTWcOMYO8nnnrTEPT5QgYHPQAcE+1aM7M9lHJnMkTBXx3DDjJ/Aj8al9xoqTqjyR7VwxQHnuT6Hn2qMsgfCt3xhhgj/P4UxMI1km3eXCXHrgAflmpEDw5DgrkbCCRyDjgflQFmCnyztAZ+cbcgEe2PXNSDDsAYPmxnaVzkdu3tQOwn2ZoQreSuxvVAT/KpJRGsasqxhT1IjHHccDGeh/KhO4WII/MDboUxxz82D71MhhjXdKeQfuNxgD/AOt/+ugCBjh35ypc7ec45oKhl3AAc/hTEIY9iEAYJHI200KhHJOeCe2aVxEpt/3mYgAQAOnHPfk0I0qD5TnuCVz/AProGOZ5SzMsjHZg8AAAH+XamkrLhS5Eijpt4J/AUILiTM0crDBXJznpx+NSK5jVkcq+4chTk4wcj/8AX6GgZXbYNwVn69SuP61JEx2MH7H1+v8An8aYiWZ1dl2KhYAAsTnd0AGO3So2ZSwwjE9PkGQfwyaQx4mZUPllVboRuByfoKWK3lkTdt3nschgPwHT64o2AngRVd/MkRz08sqG/X64/wDrVIL/AAjFYdxzwgyAPw56jH/16QXII2lZmkkLx4A+8T3OOBjpRdSbi/lhVRm5A5x7f55p2AjChkyuPJJwGyMjPbrTkjiWHctyg4+47HJ/IUXCw0ywRuNgV1GCSwPT/d/Luab5qyEkyMpzxhRj8AKAFDxbdzEs3oOM/pSM+5ACu3HTIJ/mcD8KBCK7qpBZmQ8kZ4/KpBceWv7sEcjPzEUhCtNKWPzthum5s4+npUbsFHyhcn0AGPyoEAbcoDAnjnmhiS6LyUHIHWhAPGEfdExikBwV6gn/ACKRnQgLMJB3O0qD+OfxPPrTGRtCdpO7r91T1I/Pin2xMgMT4APIOO9A9mSF44gVeMmToecAf0qE8gnjFAMa8kpyVbnpmnW0zIW8zLZ5PPX8aLaCJpJlmDBl6twcnI/WoZHWRv8AV8L06jHvkUIBpcBQAWwevH9acIwxJYD8AEx+PSgAMTJsbZgEZHI5/Km4bJIV+O+2gLCiUqFJ4bpkc5pVIPQgN1OeMc9aAHzFZSXXaGH3j2J9c0iv5v3+JOzH+L2NIGRPEV+6vHUZ4/D61Gm9TuGV96oViXGTywJ7nH+NN2fN1GMcZpXAYswL7mYZ/wB3Gae04kyX+bJ43AHNKxpcrl2Rjs4w2QV459qnaQtltoye+ev1oYkNNzIAFYl1BzhjkULNEXUGIgEjcSwOB7cUJA2SywtGwGMg96ayYJIb6Yzz79KEIRQF7855ycUoBONhK/8AAsf570xg2WB3E5HGT2/Go1Aj4y6/7vP6UIGGN3VQ3f5fT6UhkDKEEwxnhBTESRwtFIrZAbO4EgHkVNEsjtISdwZcc/X+WR+YqWxpA8UbqN+VZQOWIAP0PfpimmRAgJRckY5QPg/72eDRqxg1xM/zGZtnsdv/AOuodzYwWABznJ+Y/wBaaQmwDZfDOwIBxk5A47ZpYZig5GVAIPTkHsaYh8TCGcYkdUIPK8HHvVq9kgjghjjhYnG/PJAB7e45/lSdylaxVAcyKpk2fLkEgYx7c0wwyshJYPzwdwJ/Q5707kjVRmQ/LtTPJJx/OrMbRMnI8qQnAYPuByeuOv8AShggCTK2TFEQe7EDPfgk/wAjSus7BJNwiVlGBtbkHHIPPqKQwXy8s7StKV+bkbRn6+v4VC+0gbFbI65bIx6/pQIcWYKI4goJPcZ4okclU2ttIHLZOaAEIeVQCN+ThcADP4YzU0VpcIskmxYsrzvPzEdwAOeaG0kNJtlmCKJRuZ40AB/1nzcZ9OlK0VsybooHcnB3H5Rj1ABx/Kou7lpIbDNbsxjESbgc5bcf5Z/Q1aSW0X5pxFk9C65P5E5odwTQyXUr6ECNY7SKM/d2RE/TFVL68uJG2PKquMArgLz9QP60KK3E5PYriRzFtZkBY/Mcgccfn05x6Ub2VcPuBUdG64/GrZmIrSDfGrEAnDEZyPek2MFKA7tpyQeuP60DRHKW3LhcHjPpj3p07PnjL8YOecn1PvQK48ZR2UHhRuAfjHOacCrnIUYJxgEYP4UxjQ37za+0gdcf/Wp4UENsxkf3SD/9egBUDFThSR6bT+dIyrwCMtnp1/Opb1JGFuRx9BS7s5LAZPfNAC7wSMnj9TRkZ4zjHagQ7KE9MA+v9aY5+YY/PBoQ0NLPvy2Se27j8hTvukEoy4Byvt35qkUSswniA6sPuMeM01lZVG4jJ4I7ipE2NIBxzQEyR259qLiuGwqDwoI5yaY4cg8Dj2pjGhJG4zsHqTgUvllHHl/Px3HFMCPa46nGeualKbflDArjt3oAbyh44I5FRDdkerGhCJ13xOcHOOpUf40jY6iNfXKnBH9KBig7wVJIYdKj8wgsu3OOuBSAdlcFgu30xS5DD5XJP1xQBXCYOWbGKR/mxzwOnoKYC4ZQrBh7HNJl5M5OcdaQxA3GSM08MhGGAVu3zY/TFAFm3lLqyM6AY4DHpTZTuIKyq/Hpjn0xS6gLHM+xhul2j0Lf571HG0e1tmdxxkAe/WnYBgSFZyWJ2+g4wffipg+cDCAnJAdcZGfX/wCvRqNCDLsVVAsncZIJ+napzKiwtGqN5yjlsDI9c4J/WkNaCzODGhaJXZhkkpv6d85qEXCiTcqD5eQPUY7fl/OgHuT3M0kESrE+IpMkIAPm6ck/iR+FRgShSZI2O4jOwg9B7ULYHuNllHPlxo3PVh7fzp9vEhkAwBkHDEZGeKYla4v7oF+PKc8HPTP9OlV5F/eHIYse/Qn8qSBobIM8t36Z60/JVUj4YMep6gdv61QhFRpMBVf0XFOEROTuJVRkjoR+FADkJUkDbGx6FUAz29PamyhvJzltqsO/GeP1qeoXLMTOokYbWjfB8tjndxyf89M1L/aDtbm3jTzFVcAqc7Rk8A9+v5Ci1yr2K088XzFUaMk5ywwAe+Kg89F5GPrmmkJk8cMkoBeEqv3gzcflnr+FTmGyjT5Znlk/2cKPxB61Lb2Q0l1GfaxGuIgiZ67R7/mfzqB7h3X55NwYkEBgvAx26HrTUerBvohbeTLKpUBFb0ycf0/+vTZjNCwiaR2A+6Q3H1x+dO2or6Ci43EtJtMn/PTG1h9fX8asRzSoNwwSx6jn8+fSk0Baa8t9pDwkTHjdGSmT744x9eazWASQqGwo4HTNEVYG7jWlxtypBGMH6e1aENustq7BN0oQ5Gehx1HsfX602JIghXJ2pkMUBBXjk88+uDxTZVZEYyMMAgHCgfge/agYisCpQQ7g3TceB9KbuDAHyo0DZ6E9PxNKxOg5plkXLsVcY+YHr+naollGfmyQeMgHn86EBH5hBDchiMHBwasGXzI1ODuxyzNnI/GmxXEY7VyCWUDOcd/r+tRBg2CAc85yaAEznaPu565pCcE7jxQIUj5eT9D6/wCetORvl9SD3pMA54wfz7U0bSjZfB9aYxYy5cKCDxmj7RIBzGjL2JWnYdxBKAchMOe+6nvMSTjmk0IYZCD/AJ5pyS/Ln0pWESiQNzwP0prONwzg9/WkFxU8tmALhQe3NMNwFG3edv8Ad6H8qooTcsifKjDvyc0hYYBzzQAp46fTmlJOOCcDrzQIa210yNxOOMc5NCZIAIOR2HUCgYMvzjOam8v7RE2XfzV9DjI+nrSv1BFYAfxfOo9f85qQW6sG2nBHQU27agRDDJjbubPfP6YpIiA2CMjr97p+dAwbG4MoCpnAxSqBtbZLGWPbnP8AKhBcYOwXadvHJwKP9U5wrJ6jdQAcZ6Kpx2pVynRl578GgQuUkI+bLYI+VBigDYrKuSOvI5H480DuKBKW2NFuY9Mk5H68VI0Lqqqqh2J+6HyR/hQPUkMd1AjfIV3DHyurfkATUDTu2N5aUIem3hfyFLRjdyRpB5QDAbhyOexFV0kRcgLz13d6aQmy7NGWtWJI3QPgEdFU/wD16puoGfLkyOvp+lCBiKzgZACjpjoTVmPK4dxtX+Htn8PypsSEkmcM28YZsNtIwM+vr/8Ar/ORWjdMlidvIT0/+tSHe4+T/SgQr4JQARk/dI9Py/Wq0TsVVQWUHg4OMj0oBEsgdwzuFC9+gx3qN2DR8Fio6lnyDQDEGfL4+YDkcdKJASB/tr9O+P6UhDpjlVVlUZRfXPA6/qRSK/loqbC2c8557Y/nTsDZPb+Wu6WQBkU4HzEc88nGD2qf7RIHL2kcMYIxmKP5j+J+b9fSkx9CvK0kzkTMzs3Xc2eR6qP603YpITZg+u04xz6fl+FCQA6Km1WXd/wPI/MUAIQCASwI5A+vb8fWmIVo1i2kFBx6EnvnjJqUussYyzEKpUEqG3ck9T6UmMiMWJBIsiIAOPmPHv3pFk2nE1zwOc7dx79KYDJNpcRgMznpgAH9eaR45o2AaJgCcc9c0LzF6EHzNJtVcnuAaeVbYpLNnlQCMdP/ANdMRKg8kDPzEgFvb2qwbngeaob5dqMT0HofUfWkMiYBOV/i6DOdvtSZ78AH1Pr/APqqRPcjCqX5BHH1/OpPKygI2nIJ2+3+RTbEMH3iGQAdDnsac2VLbuvTjtQA12Xy8f3ff1+lQsAD8uWHY4poYoJAyAT/ALVPwFThueuD/SgQ48gMRj37ZoAwOwB+gpCFLYGFH1PaoSSm0qCG69c1SKGtIXIzyfcVJnzEGGY46g9qAFZDjI6f3qcjcEEYyMAgbsfnSEN8s4ODnjPpzTcEdCPYDrQBIEYnHIIx16USKFGSQ3sM5/wpdRCq6MBsj+bso5NIHkwwJAPfIx+hp2KuK25wT8uD02gAf/WqMHD/ADLnHXrQIXed2e/pQWycnI/GiwA7tx5mfoeuKeJE28Zz6UDG7gW6leOCaVXeNlYZz60AOJDtuAGCfugZP0p+HB5VkGe9ICuIJApwp44z7+lO2+aNgyAOjBetFyvUQ27KA2x+v3scfpzUbje2SSfYNnFNCJNgCDoc88jnvSkBQCQOh/D2oAAA2S498+tII0KsTjHsKLgGAFY9gKV3ym0sFz82Mfe79f6UAPhnaPKKqsD90Ogyfpn/ABp5vDhAwYLnDAEY/DAFJrUpPQPs0kp8ySQCMDJYvx7e/wDOo5JY0QokpYj7oAJX8zj+VLfQNtSJcHBctkAY2jOKcVwFxIXPQjYRj8+tUITaM7mzu7c4prHqzksev3ic0wEKkjHO7sKYD0OCfWgQrDB2r93g7fX/ABp5Plupce/DYz+WRj6CgQ9GVfmLHd2xkA/nUhmBxH5MSKx+8q5PXqD1qWihLjzGVQOMcnBHOfWhJHM0b7igBBJHGPXnrjFAnuDTPIwyxJPG78c5/On3EhNuFUnaBhge/JxQIczyq8aiXauF+XnrjPT/ACKGlO4KV37eASPu+v0/P8aCie0snuNxjVdoXIO7Bb3HFNnjaGfbLGMsDls7R9Qf6UX1sO2lyGV2LY3yYH3VzwP8/WmFmXG/Yc+3T+dCJY7zGMW0IAVO44PI98dPSnLMACTvLY6luKAuNyrcAgfUdRUm2OVgCTgk5OTxx6UXYIaId6Bz5OM4wzf4nFNdkdyiKijsIxuB+nHegZPEGVCW8wRcgDeMd8fdIz61M8kj/ufLlEY+ZcsEH1zz780h9Co0Tod5CqxPzEdR6/Xj0pFY5ARowoBOHPT2HPXp27VQiPHlndIDtboR3P8AUYqJFADDcGwOf8kUxE67YhtMYKMBg5OT/n+tIUG8IoU8dWPI78etTcBj53Et8oY5GOwqaKQ+WwJJTHJx7j/61NiAqFHrkZ+Xv/n3pWzxIwBB4wOmOf04pBYQKpBBOM8DPb/PFOEMQByXAxxggYPqRjNF2BG8akgJkD3OfzOPeo1VeoBwvY+tO4D0j/2sE+vagx4OS4dc9VpXATHRcfP169v8imuBJkkcj1OTTAaIwQW4HpilCbSQQc4x1xRcB3llSDnr1yDRtXzMp93GcGgQ9hsCsiMQM7sdCP8A9VQhyWwfXnFCAUMT1YDHTOf509CT68de4FJgNMPPAHXpTWCrkKijHTgU07gCvtwCfrTvNQnpRYYYV2KnaoXksP5U5BtYKqAg/wATrkCgBZCxB3uNp6qMc+/FJHGxBdQgHqR1/TFAwk8rggbsj7rdvxAFWIfLYHy1TIXPzDJH9P0pAVXneSTn5h0xjilwEDE8EjgHtTEPbzDGFbK45+amGTJZUwAT0/pUlCNyfnBPsAP8KeGBTBYsF6KeQOf1piHeYpUhkXcR24+nHSmD5R09sVIDjjcEwpHHT/HrS7Np5wMngBvy/CgBTbO6M4ZVIPzLuxx6iiZfNCvhVj6c5OfpincqwgigLF5W5PRI1wfqD0H5VIJSxAijVG9Qctn1yeho1Y9EQ72ZChwO2H5IH5gVG0RQjmqRLdwCKeVPXjoaUqI2C5344OBxmgQhZecZ254yM/1o3M2GXHyjsc0xjRlH+ba59N4z+VORtjHIiyOQrKT/APWpXEPYMRuVRg/3OB+dQeXtIAZgD0IJoAnmkVbaOJY/KwMsQwO8+vB4qMrHuTa2fn5HfB7/AKfrQMmLYZvujAI4xg8n8elN3bfnZcc4+tIGNGcBlx17U0ksfujOM53dR9PWgSJ7mZWMaK5XMY5Dd/8A9WKqO0icMSAfU0IbLVtfSwsnJHHGOwHH9Ks6nfpebAgLBdxZs45br+gp21KT0sUBu3kN8rHuD+P8qVQN+Cw2/wB49vwoIJN0TMAsoIAx7H1/Xmk/hwGZh29M0higuy4DYUdh0pSCJAOfnHHyn+Z4oECyomBIjOSMsWHfJ7etSLdNwkix/KxBIHIBzkfqaY7gkwZ0SRcBjkdOvYHt6ZoF0YoGhcKYz0DjofUH1pWuJOw0GMudse1fb1/wpo8pW/eb4wTjgZyPzGRRqBMbiARKnLRDg/IDg/Td+uaQC2JUxuBkEkY5+n+fSizQ9BqgfMgfK+nT9PxpXjTcuM5VgDgEZ55wf1pCIFDJ8wKkdCMkE/lSqS0q7SEHGCT+pqgHodykcfLk9eDVkL50DJgAoCR9OKl6AVflwFBbeo+6wxz7Ubycq2VA+vINMQnmLu5z9RSnyyd53k555AFMBZI0TldwJGeSP8mlVRKAqJ37DNSAwqoJwwbnrkY/XmggBcY+hx2pgJtJwWP1H407BwCQefXvRcQpQfdAYqeRnrTvKbGTtBA5ycH06UrgN2YjG4hVPt3+lRBPnDJ39eOapMY7KkDcGA74pAF2YcY9weRQAijBLFx7GmyLkAMV3f7Oef0oAi2YPU08RyY5Uj/e4/nTuBIIkKjc5bvlRnApzyKQCqHA4Ykdf8/WkMC7BCqqFbqDkcVHt3L8559aBMczFACzPg9s9aiUhSSpH40APzvXvjuKRmyoUnOKQEsScfM368jNJsYAZZeeQWkGf50ihCDu/hZsYADZx79aeqY6+nXg4/CgCJhghjyTk4Hr60qMT1oES5yAR8pAx6c+/wCQpCgADZ6nmkARn5iCSV6j/Z96icMrfeOAc4JpgBYA538rjFSFWhAkbIIHyqV5P+H+eKoCS4ixCk6t94gKdoHPOc549KajZiMjqrA8EE4HoOnTn9M0hjYCgmDn5MEH2P8An3p5SRG8sbsjOTGTxQBG4kA+bcdvXjOKdEGBJALHA/EZFO4ChFZsMpY/xYbp+WacW2Op8tR1KcgYH1PU0gLQuI0DGImaVuSWyFx7g/596zniYj7wJPQAcfhxihA2LuMUnJ3MvAyM4/z9Kjwf4gOeTTESSFmf5QBu446nNIq8cDvzz0/z+tIHqP2kR5OeeAR6UyYggAH5umRx1oQMsrMEhRCF2suCWUnvj+lQBULfLIUbPBXI4+tIbEaJdu5mbrnO3Oenv160imLfjawHrkc/4U9RDm2LyBhRxhjUlvdRrMJCgbaCQuB17c0ajTB72STcXORnnIHHpyagZ97EcBc8YX/63NCQXuPCttPKnAJOev8A9Y0/zWlQIWyQeAGII/xzxQCY142f94HL55OACc9/15+lIIJmmEfKseWLDGOep707iaH3EaQXMibhIiEryMFvy/CmFmIKkYGc8f40CJElXblwxxwCen1xSrg79wxjG44BBHT27470hoVIYiMKpYfUg/5PpzTI42jkDDbwegAOKVx2AbRjCYXoTnP40LMXIVh6lQPX/P8AnmmIU42kgkDP5f5/wqucHk0ITJEkIG05we/pUjS/vy5BG45wD0/zzQ9wFaVZUB2jcCcEkDHt1FCNDsKs7L34UH+vpS1GRnyN+RO6kDoIev61NFHasFLXLIxz1iJ4zx3696HfsFiyLeyDAyy7292PP5DI/OpHNig2GIbc5wGfJPTufelqx2Q25W3kB2rhnb73f8+v4VSaPaMElTns3+HT8aExMTIAx1PpjpQrA9eM9PrSsRYUhlTftbH6U1WY8LnPGMU0MU5+6x4PbPSmnOcFiQOAp5IpoEBRlUkscHvjg/jSBcA5JPoQTRcYIpIIyx/4FSFfLw24nHTGadwuPfLA859Tk09YTPjAVto4y4H9aG7D3F8qNc7tqtzkbTkfTnFOhCP8q7QB0LUtRiONi5aX5STjrgiq64Db1I9iDyKYmxBJIvc4pu0qwxGcnpxQAvlFThsjB6UMUB+aPj9f/r0CJVQqcBsg9O1GPlAAzg1JTGTEbunJpUYeWcqc9BR0ENYcYbA74pOhAPSmhDkz2yM8/wBP607DMVjyMZA65oKAfxbSAORkHn2qA5bLEfXjimBYRznK48xe57/ShgrECRiUBwR5nHXn1xS6gB2+WAFdkH3cnp/KkEqoy7htUrg9+9NgEnl7lYBV3j5cA4/wqRBCcbyodmyDjP59aWoCyRojAbmAH91aenkYbDsS4zgcf1o1K0IpEROVYlT0BI4oVQQWJCEgnOOvtSuw0GFVGQrcdCx/z0pqSRqXzGDwQMk8e9MkRwNo6DIzjn/P+RTQVZ1U8+vPb/OaoQ9CDlW/DNCsoGCuO2SM4pAIznaQpPfGO1SeW/lOXk2LuCnd3B3f/E0ACsjoQjN+7QkYOMjJPP5mm7CVYfMQOvy/oeKW2gEiq5aRWQFRgnLAHOe31z/Wo2QOcLhcjnqR/KmMT5kR1cZDY5zT3gXav389eT06H+tAhHQvkFiPqe/TvTWxtXYAQPQZz+NMBy5J2/MM++c0rJliwwVHQAdPbpSGSpneSSMjkMecnofzHX86kMsg3GMoG28FRk9enP5/hSuBUk+ZgvUbeDn3P+FI0YCrjr/epkgUACJnjvmnRFEODls8Ee3cUAKQiOAiNIzZ+ZnOeeo4xSsykfKBnPQd+2aGMYAxwq8D2704kxR4VmO8ZYDjPOP6UCFlQv5jrzG0u0H0PUVABjJwMnqpH86EMUBcEOAc9gcH8ODTwFcAAtkDgnr+VBIKiqhwzZB4IH54OaQfMpJKkkYJxzjGO9AxkoVFGCwI4I+8D7/jUar8pYguB1waq4Crg8LkY7bsVIHdmzwAOnTrSYXHtcPj58HjHpjimGaQty+A3sP50rCHR/NkkEn+6O9OkwDgAjPq2T/SgYgKgLj73ekBJ+XHsKQCkNs3c8dyMU5ZmXAxu/CjcEOBR+VwrY/Oo9uTjmiw2uo4MMENnJ5zTJHY9QPw6mgVhRkYOcA+vT/GkTG4nvTACCADlgDznPSk2sXwePcmi4CgMyncCR0oAG3gZFDAEj+bpx601gQcZI/GlcAx0HAodgzZyGx6DimBKsnzL06jtTskS9cc+nap6lPYW+iED4ToQCc1VVvkPGaEJ7iu27jIHHemA7snP3j+VUgHK+AMEkU9W4IyMDkUmCH79oZBhumOP881IbeVyQilvzyfwoGxVspnwfJYEHrjj9ad9mUKPM83f3IZAB+uTQIUREAr9nZwBwAGz+JFKMQMQ0J8wgHOPu+wwOOaBspyymW4zNskYgYBb/69OMy4z2PTbk/XvRYVxBLhP3efMDY2jnI+n+etKsm4FiA2e+DgUxjmmjVfmjOw8YzmkXYzp5a4HGPzoBEW/OAqnHXAFIXyCRnPGPxoJuMLFsk9BTh8wYk4wOP8/lTGEb4IJqRWVvmI3EdfQ0gIy4Vj3wcjHH9KcUZ40O5sMe/fH/6z+dACplHCgAHOQPb/ADipVKM/scnAHv8A/qpATBC5ZFBGACR9Bke/XH51HMhDjAJPcH/H8RR1K6CR7ejjaD6f/XqVnd0WIKAqfKBu/Un/AD/Shi6Ea5PyDr0IPXP9KXaclHYrx3b0H6UXEIAq8ElWUdTzjn3P6U4cSZKjZn7oPUUANDKvAJYDt2+lPVlCueQWG0ev1/p+NIY2WIo5XZyMduD6/rTUUySRoc4Y+uMCmJld2w7AdjwO5p0WVJIXJx069RTEPjIU9dxPHFKjDZKM9VPXt3/pSYDVB3fLkt2H14qR1Miq/mDj3Oc/5/maAEjxyqbmXJJDHjNLOh25Cgv1bHJz7/59aOoyJyrMHwFI4IxxmmchuDwPuiqESFujA845Pv8A/qpp+VtysDjoB3pAEhBxxkY5oVgv3eKBCMfmyw4+tKXXHIJA4z0osAh3RkgH16jGKejk54AAHI6/5P5UDQqyAAMimP37fhQdjAsMg4G7nNAEZbLsVGOg47UAA9D7UAPJLckc98nvShsg9B6+9ACoNmGwDjsalIjk+Zco47UhkanY+7HU+vOaZIMuwIJJ9TzQIRPu4AGaXYSRTAUhkyCCvTORSB8Hn5iO1IQB2HBU4Pqad0BJH4igYnG8DGOelI5wec/SgBhIxjtTBywFMRKig4YsBg4+tPiJklQYzwOB9KRZNqK4nX0VRzmq6sqEH7y5/Aikge4l1DhgyqSh5BHeoBxgYOaa2E0S7GIwvzBQRkU+GAbczSrEp7n5ifoo/wDrUXGkOaeFWK28RPH35OSfw6D+dM86aRR+9YgcgM36c9aPUH2RWzJvwDgn0AFWI/MyCvBAIbJH0z+tMQoO/czAEEc5+tO8x0GwFgg6p2/LpSEyPhs4Vd468kHH6inM37vd84A+bPmcDt6e9MY1TgHO5mK9yfb1/GkBZQeSO2D2oEG5sDBPPelQtgHaxAyef8/SgBrHnpz3A9aVYy4GDtPY/wCfxoAay7gqpgjB6nnP0+mKCSrgnjIA49v/ANVCYDWHYcinpuRGYKDjByf5fyoGEijO1TkdVJPanQgD5WGD94fUZoAWRdyB1+6CVbnp3/xoDkAg9McmkBOzAyfJkZHHPbtTMsSAw49Ov1FAAAFyCpDZxj1pTjdh0/M0DJVAMu7btQDIB9cf40YXywVIYA7cHn8v8+tIRGT5hJCnK8/Mc4/wp0h3DK5IA5yfekAxdqyEg5XtSwsFI38jgYzjHvVALtYybgSAc4J71JI38afMw4yQOc+tIbGSYMA5UgnOTnI9v/1VVGADg5A74zn/AD/SmiSQb36DI9xShtmGDZB680DFIZRwS2T0AAp2xgpLnB6kdTSERtJlVTGQOhPb/PrUkeHxtyCeMDnnAxj8c/nVDFXYcqwyDxjJ59v5VCUCEq3zD09vWgQ7yyqllYlTx06UgLRAgMdwPORQMazBnLBRgdV9KRrZkIz7Hrmi9hCmPIHp3xz+NRkYOOvpTAcex7j1pFLbvl3YPYf/AFqAHl9xBUkYySR+tN3DJI4pAIHG8v8A1oJw4KnmgB27dnPB/nQGxg4IGTQA7eN24ABew9KkjZd+5jjvnH9KQx1xHtcOCNp7jmod+ZNxoWwPRifxH5eO9LndjFAhSwLdenGcUm44G4ZA6UwBm3njNKZHYE7zupAQ4IxnrUmSQQBx6GmxCErx2z2ppDbuhxn060ASqDlBnnPIz0p9uS0gbJGORUlk18dsuQQWwDk1UwW2gjdyTwKSHIsqm1TDcD92x+X/AGamFtFHtVgqDpvK5J+gHJ/l70tw3IDdW8TEQRHI/iP3z+PRfw596oyEyPvbKg+v+NWlYTfRD0A3Adh3zzSScH5g316c0xDS25eeop8Z2gpuGTwSOwzn+lAEocNuGDz+GKQsG25BIPGKQCmGTdGdjKucZ2806OIAF0LDB544o6DSFUbgSW7Z9Pwpo2knG4jPXGKAshGABIOCOeRyOPSkc7GyMc/pQIaB8wztfj8qcFIG4giQjjHIxxj6UXAAmUZj6DrTTjaepJ4H/wCqgQoKghtmcnrnv9Kc67xkN9c+lMYpjDRhXb5gcYx04/wqFQ3nBN2xsgAnsetCBkjj5lG0YySBjpz0/TFNb7g689OfpSQmKmTL8hwM4B9s0CTcw+UHnoTxTGKz/dIYY549Pej7QwG0NgEcgcZpWAfE2CCQUDLkY6Hj1pm/5dp/MUWBjQ5DEE/561KW8xcA5KgY96BIibhSehB4H1p8T7mBJ9ASaBjt7Mg3EZBx7+tSlgSTEM4AAOMdP50gEIBQDGcHjj39qgGWUFj09+BQDAuAQB16ADgU5Odxdcdhj1psB6gFTsLKf1PrTUDKWYEHGCT6/wCc0hMXCZIA4B4LenrSj7xQjofxH+TigRLGqrMGbHoccYPH9aaQGVgB8wP5ii4xm0BvmJyOnGeh6Uj7TKzZ5bnpxn2ouAhbevzdVORx60uW68cAfWmAmQ3fJxz3z+FN2jJx0xxgdvWi4EeCvTA9yOKDwSHIOO3cU7gHHfrQR8vJ4oEII8FRjg9eaYvU0xkgQ5JwOelOOGGHP60gAx4A6c+hpzLtAAI6c896AFBKHafu+9I8YAGM896BiAHII6U0nHqPpQIUBXOeQe4HNByG4wfp/wDXoAaWIJP8qAcH60hA3Wkz6fjTAQnIxRuz1OKAJAxHX73cmrlntTqMcGoLW5BI+85YZ9eaN3zDpzSQMkjlRi6uuW459R37nHHpTLgo0hgdiADgHrimNMqtbTRvwCw7EA0wBs4br6HiqTTJaa3HbSF5B9KtxWn2mPdGyhs87jg/lQ+4JXAWOQSztuyR9wc/QlhTBZtuI3bcd2wM/kTRcrlHiKGEBZMOSectt6+w5/UU03CqhEYHy+nyhh+JJ/WgdkiFWaUjMn3iMAknFLKZN7Lv4FMm405AAZTgdqcsm0HBxz+dAh4f5dufvE5pGQPzkkZHfkUhiD5UJ7Dnjv2pc456jHc96GIMb+5Yg8D+dKxbnyxuB+nPvQNDGfaMcfhkUiFlYE8jPOKCSXPlqMEbcnnjmnf61CeM+h4P4UihS2clT1+Ydjk4qJkwOgLDkDPamKxGu6OQSE8Ag4+nNMUFD8uCaYDwSo+TOD0OP0pGXpyB/jQIfG3ybevOPpkYpTFkqzOPn5GPX/CgZCD8vr6GnQsQ3fHc+lAiR+hJHX07GkVguG7+1IA3FQcg56gY/wA9qeCx2Y534AGRQMczspX6cZqKSbcXwAN/p0FCQXFCjjjr3zTySGOeR/KkIcHwoJB7c46UckcHkH7uTQNjsrJ7NjpjHemeYOhBJwOegx/nFFhDhJnDDnAxz6fn9acNmeP4hgd/woAaxBVtuQCARuPPufzzUhQgKchfpj6f4UgsMVThuoB5Hc9qJVCljyMYyOuPxHHbr3pjG54CkEAHoTyKeyqMMjFsjgHtQIYAG6/Q554psi85Pzd8DNK9hCbecsPakcYI3jGOcU7gIRkZIJA746Ui7SckkfyqkAoxknkCpDnZ0YN6E8H3xSGNJUcMe2O1IzbeRQA3duxzmnAgHDHOe3pQAx2IbpimA5OcUwF3cZ/CjOOuaAHKcnjGKGdm5OPwAFSA0ZPTtTiRgfLg+opiGEikHOeKYFgJjAzlcZPHSpQ4Gc9M4FQzRDM7gWPGeB/WlX7vPTnHpSAUeWp3hfm6dTyanhkHlOvLd+AT17mhgtyR0Zl3BXKkgcHHJ6DpVWaIpMDNEY8euPmH+falHc0eqGtNEJNsWUAHVTuH4g1Kl4FiMZTP+3g5P1q2SmkQS3U2FQIqkdG9R9DxURkdgxLsM8bRwPyFNIlyCRQEXgknGce1RZJcZ6kc/jTJJYPLQOJfvHhcdj/+umuzOCSDncSfx/yaAGhtvU9DUvDRc8Fsc44oBCM23jGfXvmlC7uhHr060ARBjyO9Lu2tggZoAcJCM4OM9x6U/wA4nDMMn1NFgGMVbnoaBx+I/SkJj1YbMDIOeCOT/nmnIQOdxOfz/wDr0DHeZIucOMjrj+dJlCRvLBu52gZ9utAyNoyrlgfkPBOQe1DkY3AAbiffFMTEY42qoxj73vyf6U4+WzgbSCevzcZoAaPlBJxwc49aN4Dcrjnp6d6AEbhmGc9v/r0zcOhPA7UAPBLcEcH8TSYK5U9aAHqSp3AcDjkgUZ2sB0PY+npSELK2QBgeoIqLbhwT1poGPD5HGRx17UmTnrwKAHoRsORk9fp/nmnZweRlcdfWkNjS+RnIz0oZuQSAe57UWEG4AenoM07dtyM4z2IosA8YdVxJtPT5hwPr+Z/WlBaEgnIB/iH+Pb+fNKww4GOQCAQf0Of50rlpGBAA7e+PoOfxoGiPdlsDLZ6Zpd5VTnHGD14z/nH5UCGFxkY4DdjjinK+M5PftSsSNL8tg9OaGGR8xA9D2NNACLHg/MBgdSDUTDBAOD9KoB0YAO7r6Zp/mAsAV57mgYbt33xx2KgD+lRkc4zSAZ06Zo9DTEOyHG0/eHTNRigY9WI6ZA9qPKYjccAdiWAz+dACqcdCc+/SlyOQcA0gAAcnNABY4AoEMOVOHBFKu0cCmMnb+70NPaFjGrLyO9QWye7kX7PDBGBhec96r8qm1sgfWkDGoB97ew9MDn+dJvcAg5A6n3oJFZuDnLY5+lRSAOrPhQR14600U2Ot0STIwA56ZqxFkyeWU+ZOvNNj0sRHyjKzSMB7DJx27VGWjUjaOD1/Kmrkuw6TKhS/UFuvTtTAgAJ7dRjtQmIa6HIdTg+tCsynPoQT/n8aYMXbliR8v4/lUijA+Ycg556dDzSBCOinAOd+PTtUI3fxHGKaBhhTncwHHbsad1Gwk9RyOcDA7UwEwN3ZF/Wkz26e2aAAH3waUN8uM8YNAEyNhVO7IPUAAYFML7fukdeTmkMUZC7zxt4p/HIxlccAikwEUFS20lWwMD8R+YxQ5ifGDjGc8cH8O1MRGVYNg9T2znNBHluEdWD+hGKBDc/wnkCn8rGMEjPoetAxuOSTnnHShlUklcgc9e3GRQAzqcj2qVZN3y43Y9aYCllcEAEEe+c0q4aQHOMY/Hj/AOtSAbKQWHf5V/kKZnkZHSgQpfBxjmkJ+UZ/LNAD48dC2OlKGBHzfd78UDGKMvwfl60Fixzt3ZPvTEAcruKk/Sm7m7kkGgCzApcMWJOAAtK8m0lQQx9x09v51I+ghIZT8qgE4B78Z/x/SjA3Dd06A0gHuWDKSuDgZHY+/wDnvUIckkswOex5NACh1JAwFDHHAzj6UZYHBXd7imKwgJ+Y8ZIwATS7jtxnAPBBpCGhDgKSME88UFSP4gfbFO4xdvy56D6UgBDEFMjH5e9MBOBkf1pA2T1x9aAGsfpmlByoGeaAGdTkcGnMMjcOPWgABHU9R0pGOeWOaAG78DijfnrRYBwYY6Uu/jFAiNnc9WJoDUwLSyrvJKAn3zxVjzGELIiEnGayZomQKxb7vynHJpo5AHamIcX6qMBT2pTECCwPXt3NAAYpEPzIdp9qjJ2k47UJiFKNuUDPpg9jU24Hex5JxnPemNDGWM5IyARgiofL+X5vUD+dAmTNkryQc8n601IwB97aD170ASfZzs2qdxHb2pgXKkAYPGcdxTuAnyDbtHIHX6GlzvU4IBBpAKU4BJIUfn/nkVBKpJJGMH07U0MTADAHngdfcUEZJwcg1QhpfP3QBigH5TuGPegBY08yRU6ZIGfrUanIBx1HH50APBPOOvJzS7flz145FAEofaSBkNwc5/lRE+3rg4yR7+h/D+tIYLJgEj06f5+lMOCCRwfSgQbyqgbfl6Um4oMDp1x6UAPJRiSBgEnaDTGPI3HOfagBCTtCjkYz+tOiwfvg7fb/AD70wJGDhQuFA9+KiCsG9c9DSQCcliw4I6VL1UMP4RzjtQA0gknOcD0FNwAc9hQIQ8E8YPvRk4GaYwQkHGevB/lTjJtbKgFWzkdjQK4cBCV4yMc/Wm4/velIBV25+8eRjp1oEmVY4yTxzzxTAesgSIKpIYnccfkP6/nQ8m/sOgFIbFUjaR3xxSIwB9aQEijbG2D7kVGCCSTjkdc80IQoUZG4/lTlkYZ2jYehxQIQyYbA5HqRQ5UDBXnsRRYBVUgA8EelMLEHGc49OhoAcpbnHcdajPfuKBjc7vrSE81QC4zySAPWmbir8dqAHyYU5GOeaasu088g9aAEYYOB35FND4zQAmeaXpQAZozzQIM0maAJwA0uM5BNWHmYM4Q/eB5+lZsu5HC3+sJPRO/rwKQE5GOaYdBeNg4+bPB9qcsmF6nGMUCuSLMUXCsw/Gm8k7txI9SOaQxQ+CeOnek6Z54x+dAxmcH+VSK3GQcA/pQSLt+UhTxwaaSchWHHb3FAXJlbIz/sjAx1P+RSb93J6UFBMu/JXGf6YqGCMliWYDAzgDqMgY/WnET3HjBJAABbOfQd/wClQyKu0MF3Bh06bTQhjGXgE88n+h/rTU+bIwT7CrJHS78rkDIH/wBf+tGzMKt/FuIPPGOKABlEa7OpxnJ7fSoxgYHf+lAAPr1ozzxQIf5isoVsjHRsU9gHyCRnqMjtSGMGFBHQ+tIWAAPYg/zNMBrc9aAvegQHLDPXAyeelIc8DtQA4M2RnoOntSsQv3ehoGOTII6kegpS/wA2PL254xk0gDcPmz2709QoQ8E5ODQwFlzk5HAJP1/zzUDHJwMge1CE9xyFcndkqcZ4pCu3GTk+lMAI+b5SGPp3pVX5JAwIIA/DkUgGdMA9KQtz70wEG3uT+VSbQhbI4Bx9aAGAKR16cnikLjNAEqHeCMdBmlRkDAknOfSlYB28liRkE96acjg/L70gEZTnJ3AU5iduBkntSYiPnqRQuTxtJ/pVAPVyO2MUnTpSAN1NDnOF70xisOQoxn2o/dg4GSfWgBpYNkg9PUVG/DYpgAO5cGm4OPpTAeh3DYfwNMbrzwaQCZpc0wDNLSAACe1HIyCMUAWVwpDnstNz0x0qBhnbG3q2KlhXcDnHIzn0oAa3DnHNLvP8Q/SkAHGDg801WIP86ABtxyRkj+VKr5wpPTpTGICBkEdKA2D6g+1AiRH4Pp0ofgncDj1pACSFRjP0p6vzwT60MaJFbOGPb0prq23IJ+lJDBQTwR1OD7gUHaSVJCk/nTQCPHKCdls5C9coSOtQuzN9wKo64XiqTQnoNb5gCeDgD3NNAkJVUHU4HuasQN+8ckAhc8D2pp4HApAIPQDmjC9iST6UxAWwzBF4yR+FSB8c4Bx+lIZK2C3IyG9MVX2gvtzjA6+1JAxTxkmkIJO1aYhO4I5yOaXuSKAAjkY4p6KApJGV46nrz/n8qBiAnK+n9KkjyCXPDAfKNvf1/D+eKTAQ4DfvAOeMAU/tGoAxnP5//qoENLkoBydvQEde+PwqNmUnBHPTNCATOGGO3qKk3A5449qGAw8tx0/rUkT5STcdwC9/0/WgaIWA7E/jTSO/vTEJz0FSkZUt1HX8KAGjHOMimmPOMdD0oGOzmQBSBjjNK44Vhnp/9agBpJx9Kf5m5ACM+4pCHbhgY4NN3c+vuKQhdzYxkZFNww5BBNAxQT0PWm7uPamIBz70EFeuQaYxpOeB09aaPvEUAKM/40hBOePegBo4NSds96AI8HPFPYeYu7+IdaAI6DTAKcOKAEPP1pAzL/hSAtscxYIx2qNc8VA2SyLgA8EdqQHI5zxQMc6kjJABA5xUQZh3xQDHbhSZ6c0CF8zjHOD6GmkYPrmmIlYB4t4+8Bz71GuSQAM7j075oGxwGN3T060srDzTj0AyPpSuAo+Ycdu1AJwMdRQMkjySck49fSpk2ZALFlzjkn1qShTJtdVULtGOCv41Ed8zBWkdUXrlicfhQhCy4ePKcHp0/wA/SojEo8zaGOGIBz/n/JqkwZGMg5YFi2OKVSGYtJxgZx6c44/E1YhCyAfL0PfrTQrkZUg/zoEPjXDoc4BHJB6VGQFwXYD2HJ/woAVicEgfL1//AFmlRl7H8DQDJ7ddzMmM/wAaD/a7D8cj9KgQBnUnkE4pAxoGfvHO7vRtOAecGmAoUflSMDnjpQAhPyk470uTsUbsDH9aAFwBg7jg04My87sL6560rCHJIxPDMUzyc54+lSMyb8MOR0ZR269KQyIgphs5Gcqe1MdTlcHhhxn/AD9aYDCAxznHqashBtBVieOh9KGCI2UdAe/al+UI+MAFV/mKAIcZYDPWg464xTECfe4p27DYHoM/zoAY/wB7rx2pwUrjJ4NLoCFAaPJBKt2IpXbcD7tmgZHvIo3cgkkGmIcwxyDxSbmoAcAD35xzSDikAByDxnB4pOM80ABBPTmnEgAAcnFAiNs55oBHAzj0NMYHgkGmE4oATrUi9MZGR/KgBrDHfNCsyHNABIoHI+6abQAUmaYBS0AW5DhFpkZwx+nesymSqAVG7oeMj0qN8gnBIo6gx+fk3Ek+tMKEdOR79qBCLgk5BpWwDwKYDWGCSDlaRlyMfl/hQIfFJgYxyDUrAAB4/utjPtQx9BBjj9aHCt90DHUn1NSID0yeAO4p8eHBPoCcmmUiBmKnr8vtUsbkEA9AeOKAHyOMqpP3R/WnjKs3BOSevNSPqOVQPmJ+Rv0pmT9x9uAew60wI5E+72bHHtzSeX8uH5J7jrVJiHBUkQKnIHov/wBf6UvlAL9OpGaGx2I3YN8sgwf73Q/jTFhJBZSGUdwKexO44gKoJyQOv/16buLA4VQOuKAFXzP4V54/Cln3MQ/Tf19m7/4/jQA2UKC2zkA8D2qIMx6k00A4Ek96du4xx6/WgBvXBApScqCRz0oAOAuTn6U0SDd90YPYjNAiUgq43kdMAAc//WpxYu7dBjIH5UithIplGVI+U8FfX3pWT5CByPvKfbv/AJ9qNhEAwevQdqsJuBY8NtzxngUMBclxuAAYDpj9aawChuOD0A7dTSKIVOWGaUsuefWqJDceTgD1wMUjY4x3FAho+Y425HtUzgYAX5ccc96TGhCRtxnLCmbxjgHP1oACcrgDmnLGqDMnJpgRl92ew7U1vXB+tAiRDtcMD1BH5jB/nTR70gHDGCT+FIpwGyAQetAgY5UY4FIMZJPIFMYrdAajJHpQAZ7GkOc0wEpQcNQA48j9RTe1IB8bDG1s4NMZCDQAn0pMUwFHHWjv70AaJANrIxwRvqEDAwPxrItjgDkbeRg/TpTZeDyaBByUwvSkBJBHQ9aYhucPxjB7U/a8qldhDKMj/CmBGu6PO4cehoYlRkfMpoEPTDDripo32Yym7sSTx+FJjQMoVgw5XsKiLnB45PekGwBvkwf1p0TFWU/wng0wuM+fcwJPuKcxBVcckA5/Mn+VA7DchnK9CDwalZz5zDpzwKGMlRi6kZ5PTPY0SgFVc5U4wwPrSBDkIxknIPao5NwJIzg8E4BoBjPLD4dic9OakiIdGDIFKfdIzhuvBzT6EkAHyt9c8dx/nn86arhWxG2DxjjHNUtQLLFJAwYhCO4GfpkU142QYTYUIHI78UthtjW4AXqcYpowN0ZH3umfXt/h+NMCM8AevpTCpyD0poRIuQmCgJbjjjikG0gYypzkc5pCBkwTjp29xQVJjUEYAJOfrj/Ci4xApfgHhe57UmdvCk5/vE8//WpgKMYCHpjt2NTbSu5se498nGf1pMaIlGSetTIFXCkkjI6jp702IgdDHIVPGP5f/qpXJDBlJDYBpAWY2zGpCgEE5H1pSqumRjjsfzpDRWYbT71G2M1QgC7j329z6UhIzxnigQEYPTpTkPUN0/lQA4KAep3DnOaUqCcqcZ49OaQxEGw5HJpHYsQW5pgRt1z37Uu/PWgQmT7U4gUAIeBijOT7UhB1NNY4XApjFzlce1J9OBQAwjB96UZ70wFwKMEkYpAKP/rihxtI9+aAGd6k+8nuKGBHgg0EUwAfypV60gGfaZtmzf8ALnPQVct7HUruylu4I99vDne25RjAyeDz0NFkO5S+0S/3v0FaU2i6zDZm5ltXWFV3k5XIHuOo9+OKLIRmi4lBBD8j2FWbC2v9QlMdlE8rDqQAAvXqTwOh60WQXLk+h65bLvezkIJx+72ufyXJqnYW99qUxhs082RVLEZUccDqfqKLIDS/4R/xDjH2bj08yPH86p6hpeqabAJbyERRM20EMh5wT0B9jRZAZ4nkAwG4+lL9pmxjf+gosgL1tZ6nd2Mt1Am+2h3b23KMYGTweelUDPIRgtx9KLIDTl0TWYLRrqW1dYlXcTlcge4zke/HFULd7mWeOKE7pJGCKOOSTgdaLBcsajDqGnzCG9Xy5GXcB8pyMkdvoaSws9Q1R3WyiMpQZboAM+54osgLMWhaxcmYRQBzG/lyYlThgASOvuKsHw94gJybbvn/AFkf+NFh3M++i1HS5xFdjypGUOBlTkcjPH0NVze3BDAyfexngc0WQXEF5OOj/oKU3twf+Wn/AI6KOVBdjWuZmGC+R9BSi7nAI38H2FFkIsafb3+pTtFZL5koUuwyo46d/rT9RstS0wIL2PyhLnbgqd2MZ6fUUWQDrDS9V1KBprOHzIw20ncq88HuR6iobtr6wunt7g+XMmNy/KcZAI6cdMUWAgN5O3V//HRSG5lbq36CiyAT7TKTndz9BSefJ/e/QUWAPPkzndz9KBPIP4v0p2AX7RKf4v0FL9qm2ld/BOegpWAltUvNQuI7a3/eStnauQOgyevHQVHP58E8kM3yyRsVYcHBBwaYDPOf+9+lPF3OFwH4+g/z2oAb9ol/vfoKt38OoabOsV4vlyFd4GVbjkds+lAFY3czAAuDgAD5R2pv2iXP3u2OgpWAVbmVej/oKPtcwz8/U56DrRZDuI1zK3V/0FN85/X9KYri+dJgjdwfak81/X9KAAyuerUvnP8A3v0oAPPkxjdx9KX7RLgjdx9BRYA8+Q/xfoKTz5P736UABmcgAkcewpPNf1oAPNcd/wBKXznH8X6UAJ5r+tHmv6/pQAea/r+lHmN60AHmuO9HmN6/pQAm9vWpIVnnlEcCPLI3RUXJP4CgCaay1GCIyT2lxHGvVnhIA/Eiq3muO9AB5r5znn6VasbW91SYw2iebIq7sZVcDOO+PWgC/wD8Ivrh/wCXP/yKn+NUL20vtNlCXcLwsehIBB6dCOD1HSgCr5r+v6UnmN60AL5j+tJ5jZ60ANrs/Df/ACJmq/8Abb/0WKAOe0DTxqerwW7gmLO6TAJ+Uc846Z6Z9674X0V7rV9pEqu0Yt13KQADn73I55Dr+R/EA88m02WPWDpwP7zzvKVnBUHJwDj0PBrsNe1f/hHLS107TVQSeX95l5VegbHQknJ/Dkc0AYlj4w1OG6RruUTwZAdTGoIGeSMY5x68VHqusR2+vTXuhTFPNQB28sYJOCcAj2HXnOaAOi0TVr278M6heTzb7iHzNj7FGMICOAMda4+/1vUNShWG8uPNjVtwGxRzgjsPc0AZ9FAHZ+G/+RM1X/tt/wCixXPaBp41PV4LdwTFndJgE/KOecdM9M+9AHfC+ivdavtIlV2jFuu5SAAc/e5HPIdfyP48Ja2jWPii3tXyTFeIuSuNw3jBx7jn8aAOh8SaRcax4kghgG1Ft1MkhHCDc35n0H/1zTNd1FPD1ouj6VG8Tld0kxGDz3B7k+vboPYA5yw1vUNNhaGzuPKjZtxGxTzgDuPYV2Gt6te2nhnT7yCbZcTeXvfYpzlCTwRjrQBxN/qF1qUyzXkvmyKu0HaBxknsPc1VoAKKACigDpvAX/Iam/692/8AQlrQ8Vj+0NE+1BUaW0u5InKt9xdxXkZ6nCfn6UAXfDg/s7StLh2okt7I7uC2Sy7GYMOfQJ+frXLeL/8AkZLv/gH/AKAtAGLRQAUUAFaejabb33nTXt4lrbQbd5P3mzk4X3wp9foaAN3XpbHRfECN/ZlvNE1oB5W1VUMXPzdDzgYq7b3emtosmqXWjWNvFyIVIVjKwzx93jkY/M9BQBleCQtu+o6hITstoPmRRyQfm4/74/WofD9pawaZeazfQC5SAiOOE8gscckHj+IevfjpQBbnsbPxBpsF9ZWyWEi3C28qqBtwzAZAAGSNw9O/oKvTf2VaavFog0MOkgA87blvmzyCeSB654wfSgDHh0pLfxvHZRPtjjmEq8ZwAN4Xr+GfxqWeOw1TxjeG+nEFtGfm8xgm8phduc8ZIJ9cDt2ALtjJpHiV7myj0uO0dULxSooB9MkLj1Bxkj8qqxCw8P6NZT3Wnx31zfDzPnwVVcAgDIOOGHbrnngUAS3GiaXJq1pdySpaafdw+eI3cJlvl+X2BDA8E9DjHFS2MmkeJXubKPS47R1QvFKigH0yQuPUHGSPyoAqxCw8P6NZT3Wnx31zfDzPnwVVcAgDIOOGHbrnngVR8T2Fvby2t7ZJ5dtfR+YsZ6qeCeOwww4z69sUAYVafh+0s7zUQuo3CQ26KXO5wofBHy5PTr+n40AdFYyaR4le5so9LjtHVC8UqKAfTJC49QcZI/KqUE+j6Jpds5t4NUurkB5AzKfK4+73x1x0559AKALd2ujaVe2uovZb7S+t2Ig8sNtbKtuwTgcNjA6Y96z9MuNGWa9u5rf7RPJMfsln5R6EnAwMrzuxjtt4zQBd1vTLa6ttLl+yJpl3dTLEYVxwpJ5KjGSOPTrg9qmkl0ax1SLQzpSSqdsTXDAF9zDrnGe45yMdhwKAM+ZtN0WHU9LurXz7nc/kTeWrFVZBsyxwQR3wPpUsQsPD+jWU91p8d9c3w8z58FVXAIAyDjhh26554FAFHxPYW9vLa3tknl219H5ixnqp4J47DDDjPr2xWzY6Fb2Xhu9e7ihkvWt2mwy5aEFTtGD0OQeeOeO1AHE0UAdF4ftLWDTLzWb6AXKQERxwnkFjjkg8fxD178dKvNptn4k05L6zhh0xoZCk+SAgQDJPAGSAR6d89BQBLeaJYSaJYQWc0HzTlXvWQDIUOXOe4+U45xwOe9RapY6XZaBp0kapcxLdhZZ0QB5VG7cAeOMg457DnvQA+4a4hi1aS7nhk0maFktNrq0e4cRqijoRz0HUZ7ZqXzh4U8N2zwxRm+uSpcSAg9MnIzn5eF7cnPegCho3jG6juwuqyedbvxvCAGP34HI9f09Dh6tLZz38k2nRvFA/PlsoXae4GCeO/wCOO1AFKum8Bf8AIam/692/9CWgBmp+JtXt9Tu4YrvbHHM6qPLQ4AYgdq2tbea/8GG51CDyrlWDbNrLtO/b0PP3T39aAM3SpdLhs7eGz00atqEoBmDRkCP6lgQMbgMjjjJPSs/xbZ2tjrLR2YCqyB3RTwjEngDtxg49/TFAGJRQBt6h4day0S31JZzKJQhZBHjYGGck59cD8a2vDqMvgvUyykBxMVJHUeWBkfiD+VADfAlqkUN5qMpRVH7sMWxtAG5s9sfd59jV2Kx0KHVjqUeros5kaQj7RGVy2cjGOnJFAGf4riTT/EdhqRX927KzhTliUIzweOm0fhS+NtPmuXt9RtQZ4PK2sYxuCgZYNkdiCeenHvQAnhfxBKkVppcVg821sNKrn5VZ+WIx0G71qr49/wCQ1D/17r/6E1AF3w3/AMiZqv8A22/9FiuRtmhW6ha5UvAHUyKvUrnkD8KANjUbrw9JYyJp9hcRXJxsd2JA5Gf4j2z2puoeHWstEt9SWcyiUIWQR42BhnJOfXA/GgDa8Ooy+C9TLKQHExUkdR5YGR+IP5U3wJapFDeajKUVR+7DFsbQBubPbH3efY0AXYrHQodWOpR6uizmRpCPtEZXLZyMY6ckVU8RWYh8WaXdKABcSxhuTksrAZ/Ir+VAFvxZ4hm0to7SzGyd1DmUgEKuSMAHvwev/wCqrqUSeKPDyX9rFuvoMK6qnJx95RzyOdw6+nUmgDia7PxJ/wAiZpX/AGx/9FmgDjKKACigAooA6bwF/wAhqb/r3b/0JatW5+2DxNppZ2YySTxRouSWVjnt6hBj8qALbyLH4w0rT4pC0VlAUww5DeWepxz8oX2rnvF//IyXf/AP/QFoAxaKACigAooA6nxtE9x4gtYYl3SSQoqjOMkuwFR+MbgRzWulQyEwWcSgg5yWxxnsflx+ZoAWD/QPA00vSS+m2KyddoPRj6fK/r19zTtHRrzwdqdnbKZLgSrJ5ajnb8p49futx14oAsWNr9l8JvbaoHtVu71FG/5Tt3Jk89OFY8+lbc19qdvrkFjBp5kscKDMxZjjHJLE4GPQ8nHuKAMrTLW3sfEes3iHzrezjLElt7hmG44J7jDjk59e9cnZ2txql+kEZ3zzMSWdvxJJ/M0AdTqNvNo+nPpWkWNxPJMuLm6EDENkdBx6H8PrkivrVtPqWgaJLYwyXCRxGN/LUkhsKOnXqp56fmKAH6/ZzXQ0HSYwBeLBh1Y8L8qjJPT+Funp9Kl1G3m0fTn0rSLG4nkmXFzdCBiGyOg49D+H1yQAV9atp9S0DRJbGGS4SOIxv5akkNhR069VPPT8xUXi79zZaNZyfLcQW/7xP7vCjr06qfyoA5mrFhZzaheRWtuAZJDgbjgDuSfwoA6vUbebR9OfStIsbieSZcXN0IGIbI6Dj0P4fXJFLw5oSPbHVr+J5rdMmKCNd7SkHHIHbPb8+OoAy6stW8Sawxng+yN5ZMazqyAICOAccnLfr24FRWWg3Pk3dza3Aa+0+faIEUMSVI+YZP1wMc4oA17hLm78OC51ZY7bUROiW9xIBE4G4YJxyMZY9OgzjvV/7TqS6rbRXOjQSXOVBvY8lFQnnBIyONwwT17c4IBia5pE2qX2qalbSw+RbsVcMWDZRF3YGPwp2tW0+paBoktjDJcJHEY38tSSGwo6deqnnp+YoA1Xjs47vRLfU5UhlsrTzCruFAcbAvPQ8huAe3pU1paQzR6xK2rW9y15HiR4woWEbWAJwx4we57UAefXMSwXU0UcglRHZVkXo4BxkfWoqAOo0dGvPB2p2dspkuBKsnlqOdvynj1+63HXilEMun+BrqO8jeCS4uB5aupBPK9u33W6+nuKAGX3/Ig6b/18H+clF9/yIOm/9fB/nJQBzNdr41Rr7S9P1GFT5AGSCOVDhSCccdsdepFAHJWFnNqF5Fa24BkkOBuOAO5J/CnajYTabdvbXOzzF/usGGOx9s9cHBoAq103gL/kNTf9e7f+hLQBp3vjb7Jez2/9n7/JkZN3nYzg4zjbXOa7r9xrUq7l8m3TlYg2Rn1J7n+X55ALsOm6lpVpa6lo0z3DXMeJPKhDmPODt755BGccY96f4ygij+wSNDDDeyxlrlY8D5uOSB7lue/qcUAczRQB0GieK7jSrYWzwJcQLnYM7WXJz15yOvbv1o1vxXcarbG2SBLeBsbxnczYOevGB07dutAEMmv58PJpEVttUY3SNJuJ+bccDAxz9ePzrFoA2r3X/t2h2+nS22Gg27ZVk4O0YGVx6H16/lUmkeK73TUSGQC5t0GFRzhlHPAb8uueBgYoA0Ljx5OyAW1jHG+eTI5cY+gArmb2+udQuDPdymWTAGTgYA7ADgUAaWm6/wDYNFu9O+zeZ9o3/vPMxt3KF6Y56etYtABXQaJ4ruNKthbPAlxAudgztZcnPXnI69u/WgA1vxXcarbG2SBLeBsbxnczYOevGB07dutQya/nw8mkRW21RjdI0m4n5txwMDHP14/OgDFroD4m32FhbS2mWspI3V1kwG2cAEYPb368+1AFLXtX/tq9S48jydsYTbv3ZwSc5wPWnaDrk2iXDukYlikADxk4zjOCD260AUr+eG5vJZre3FtG5yIlbIX1x+NaWpa/9v0W0077N5f2fZ+88zO7apXpjjr60AYtFABRQAUUAaeg6v8A2LevceR526Mpt37cZIOc4PpT7HXHstcm1JIsrMzl4t3UMc4zjscdu1ABFrjp4hOryReY25iI92MAqVAzjsMdu1VtXv8A+1NSmvPL8rzNvybt2MKB1wPSgClRQAUUAFFAF251a9u72K8nm33EONj7FGMHI4Ax1qG8u5r65e4uX3yvjc2AM4GOg9hQBe1DWTeaXZafHAIIrYfNgg+Y2MbunH8R/GqVlfXOn3AntJTFJgjIwcg9iDwaAH6hqd5qbo97OZSgwvAAH4DirSeJNXS38gX0mzBGSAW5/wBojP60ALa649tpN7aCLdPdsS9yWyxBxkHI5/i7/wARqnYahdabM01nL5UjLtJ2g8ZB7j2FAGh/wletf8/v/kJP8Kp6frN/piOllcGNHOSu0MM+vIOKACHWb+C+lvY7gi5lBDuVDZHHGCMdh+VXP+Er1r/n9/8AISf4UAU9P1m/0xHSyuDGjnJXaGGfXkHFVrm4mu7h57iQySucsx70ARVasNQutNmaazl8qRl2k7QeMg9x7CgDQ/4SvWv+f3/yEn+FRw+JtXt4Y4YrvbHGoVR5aHAAwO1AEdzr2qXTo8t7IHQEK0eEODjI+XHoPyqva6jd2d2bq3ndZ2zuc8ls9c56/jQAuoaneam6PezmUoMLwAB+A4qx/wAJDq32b7P9vm2eufn65+9979aAKcd5cwwvDFcTJE+dyK5CtkYOR34qfT9Zv9MR0srgxo5yV2hhn15BxQBWubia7uHnuJDJK5yzHvUtrqF1Zw3ENvLsjuF2yjaDuGCO446npQBVooAsWV9c6fcCe0lMUmCMjByD2IPBp+oaneam6PezmUoMLwAB+A4oASTULqSwjsXlzbRNuRNo4PPfGe5ok1C6ksI7F5c20TbkTaODz3xnuaAKtbei+JJtLt5LWaEXdq4OInbG3PXseDzkf/XyAaz+L9Ps0YaTpgjdwdxZVjGR0yFzu6n0rk7m4mu7h57iQySucsx70ARVp6Dq/wDYt69x5Hnboym3ftxkg5zg+lAFO9uPtd7PcbdnnSM+3OcZOcZqCgC9p+s3+mI6WVwY0c5K7Qwz68g4qtc3E13cPPcSGSVzlmPegCKigD//2SkWUQ=="}]}

But I get this error back:
{ "error": "Failed to process element: 0 of \'instances\' list. Error: Invalid argument: JSON Value: {\n \"b64\": \"data:image/jpeg;base64,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\"\n} Type: Object is not of expected type: uint8" }

I'm thinking that maybe the Vertex AI input parameters need to be formatted somehow to match what the model expects, but I can't find the documentation on what arguments the model expects when used with TF Serving?

Any pointers is much appreciated! Am I even on the right path to try and setup the service using Vertex AI's services? Is there maybe a tutorial on how to use the model using TF serving?

MegaDetector crashes on VM instance

I'm trying to run the MegaDetector over some images on a GCP VM instance with a Tesla T4 GPU. I created a conda virtual environment using the environment-detector.yml file with the tensorflow-gpu version set to 1.13.1, and I am trying to run the run_tf_detector_batch.py script as instructed in the MegaDetector page. However, the process crashes while processing the first image (below is a screenshot of my terminal window when that happens):

I've tried to trace the program but haven't been able to figure out what the issue is. Any idea why this might be happening and how to solve it? Thanks!

Confused about language for how to set-up a local batch process with the pre-trained Megadetector_v3

Hi!

I am confused about how to initiate the batch processing functionality of the megadetector. I've now successfully called the single image detection script, but am not completely understanding what phrasing to use when designating a multiple images to be sifted through the run_tf_detector_batch.py

I'm new to all of this, I've learned what a json file is and see that designating one is necessary for the batch process. Would someone be able to point me in the right direction for how to phrase the command to designate multiple images to the batch process script?

Thanks for your time!

edit: Correction, I now understand the purpose of the json file and it's role with using the visualization tool. My main confusion is how do you communicate to the script that an entire directory of images is to be classified as opposed to just one.

ModuleNotFoundError: No module named 'visualization'

Hi there,
I've probably done something stupid, but can't figure out what. I've run this on two different computers (but within the same university, so maybe there are some rights issues) and get to the same error.

Running Windows 10, Anaconda and Git installed fine. I ran the following lines of code without error:

mkdir c:\git
cd c:\git
git clone https://github.com/Microsoft/cameratraps
git clone https://github.com/Microsoft/ai4eutils
cd c:\git\cameratraps
conda env create --file environment-detector.yml
conda activate cameratraps-detector
set PYTHONPATH=%PYTHONPATH%;c:\git\cameratraps;c:\git\ai4eutils;c:\git\yolov5

The git folder is in C:\git and the megadetector file is in C:\megadetector. (i.e. using the suggested defaults).

But when I run the following code, I get the error below.

(cameratraps-detector) PS C:\git\CameraTraps> python detection\run_detector.py "c:\megadetector\md_v5a.0.0.pt" --image_file ".\test_images\test_images\caltech_camera_traps_58a022a4-23d2-11e8-a6a3-ec086b02610b.jpg" --threshold 0.2

Traceback (most recent call last):
File "detection\run_detector.py", line 53, in
import visualization.visualization_utils as viz_utils
ModuleNotFoundError: No module named 'visualization'

I did try do some trouble shooting, and two websites suggested that I run the following code:
pip install tf-keras-vis
pip install keras-vis

I did this. But no change.

What I am I missing? Thank you in advance for your time, and please let me know if there is any additional information that you may need.

Successful run of visualize_detector_output.py outputs empty file "anno_"

After successfully running the run_tf_detector_batch.py on a test-subset of 10 images I'm getting stuck after running visualize_detector_output.py.

I'm able to successfully run visualize_detector_output.py as referenced by this log:

C:\git\cameratraps>python visualization\visualize_detector_output.py G:\Datasets\Test\test.json G:\Datasets\Annotations.jpg -i G:\Datasets\Test\test.json

Options to the script: Namespace(confidence=0.8, detector_output_path='G:\Datasets\Test\test.json', images_dir='G:\Datasets\Test\test.json', out_dir='G:\Datasets\Annotations\.jpg', output_image_width=700, random_seed=None, sample=-1, sas_url=None)
detection_categories provided
Detector output file contains 10 entries.
Starting to annotate the images...
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████| 10/10 [00:00<00:00, 17.83it/s]
Rendered detection results on 10 images, saved to G:\Datasets\Annotations.jpg.

But the output of the script is an empty file "anno_G" with no discernible extension.

Where have I gone wrong!

ModuleNotFoundError: No module named 'ct_utils'

Hello
I'm new to using Tensorflow and Python, and have possibly made a silly mistake, but I keep getting this error when I try and run the run_tf_detector.py script:

python CameraTraps/detection/run_tf_detector.py md_v4.1.0.pb --image_file IMG0027.JPG
Traceback (most recent call last):
File "CameraTraps/detection/run_tf_detector.py", line 54, in
from ct_utils import truncate_float
ModuleNotFoundError: No module named 'ct_utils'

Setup is:
Ubuntu 18.04
python --version
Python 3.6.8

echo $PYTHONPATH
~/ml/microsoft_mega/CameraTraps;~/ml/microsoft_mega/ai4eutils
which was created via
export PYTHONPATH="~/ml/microsoft_mega/CameraTraps;~/ml/microsoft_mega/ai4eutils"
so it is possible I've made a mistake here as the instructions are for Windows.

I'm not using Anaconda, but a Python virtual environment. Tensorflow and other pip libraries all installed without problems.
Many thanks, and apologies if I've overlooked something simple.
Roy

File "path/run_tf_detector.py", line 54, in <module> from ct_utils import truncate_float ModuleNotFoundError: No module named 'ct_utils'

Hi, I'm a wildlife researcher who is very new to scripting/command line interfaces, so I'm sorry if this seems simple!

I'm kind of confused, I was trying to run a quick demo of the megadetector_v3 on some camera trap imagery but can't seem to get the run_tf_detector.py script working due to 'ct_utils' in the root folder not being successfully referenced. I've made sure that my working directory is the root file of the git clone (CameraTraps) and I've tried running it in both 'cameratraps' and 'cameratraps-detector' environments. I've tried moving ct_utils into the detector sub-folder and vice-versa with no success.

Any advice on how to get the ct_utils script referenced when running the run_tf_detector.py script?

I'm following the directions found on: https://github.com/microsoft/CameraTraps/blob/master/megadetector.md

Thanks!

eliminating repeated detection

Hi Dan,
thank you for your quick reply! (Issue #290 )

after running the pipeline:

find_repeat_detections.py
manually removing false posittives
remove_repeat_detections.py
I end up with a json file.
when running this json file in the script postprocess_batch_results.py, I get the following error:
File "load_api_results.py", line 93, in load_api_results
assert s in detection_results, 'Missing field {} in detection results'.format(s)
AssertionError: Missing field info in detection results

Looking at the json file, it doesn't have the same fields as in the output json file of the run_detector_batch.py.

Is there a way use the postprocess_batch_results.py on the json file of the repeat detections?

Thanks

[building a potential Edge AI solution] As an ecologist, what are you looking for to extract from camera traps?

Hey all,

Not sure if it falls under an issue (I'm happy to post or x-post it somewhere more suitable). This repo may be the best place to ask some questions about what's needed to be integrated in camera traps, since individuals with technical backgrounds, with some understanding on research needs, are likely to stumble upon the repo.

I'm an AI for Earth grantee (agritech and their integration within smart cities). I learned about camera traps during the AI for Earth Summit, and coincidentally, as a part of an online competition (Microsoft's Discover AI Upskilling Journey) where organizers have asked participants to look into helping out with camera traps.

However, what is not particularly clear is, what exactly are ecologists looking to extract out of camera trap images?
Animals (detection and classifying which animal)?
Other objects related to poaching (people, cars, trucks)?
Other features (weather conditions, time stamps of when detection happens)?

Understanding what needs to be extracted can help us (researchers and hobbyists) understand what needs to be developed, as well as tailor the hardware and integration to better fit what is needed.

Overview of my project:

The goal of this project is to highlight how effective Edge AI can be in eliminating/filtering out a significant number of inter-steps between data collection and obtaining classification and detection results, potentially along with other data/features that need to be collected or extracted.

Picture legend:
green arrows -> working
red arrows -> not working as intended
blue arrows -> have not tried it yet int this project, but tested out and working in other projects

More information:
The project aims to tie-in features from machine learning and internet of things with hardware devices, similar in some aspects to what is currently used on the ground, in order to reduce the overall time spent ecologists spend on classifications, collecting data, etc... As someone who has never interacted with ecologists, it's difficult to understand what is currently needed for them to better allocate their time and focus on research aspects, rather than countless hours on manual data labelling.

Model: I trained a custom object detection and classification (Yolov4) model for 17 classes, which are all the classes of animals that I was able to manually make out in the MegaDetector demo video. The classes are Armadillo, Bear, Bird, Bull, [Car], Cat, Cattle, Deer, Dog, Fox, Monkey, [Person], Pig, Raccoon, Sheep, Tiger, [Truck]. I added a few classes in [brackets], just in case someone would find the model useful as is.

The images used for training are obtained from Open Images Dataset V6.

Then, I used the model to run object detection and classification on some test images (the sheep image in the overview is one of the test images used) and the MegaDetector demo video.

Testing images (after ~5hrs training):
Yolov4 TFLite (TensorFlow Lite model, converted from yolov4)

Yolov4

Video:
Running the yolov4 model on the MegaDetector demo video (less than 2 minutes for the model to detect and classify the video).

It seems to be pretty ok for some parts, needs more training for other parts.
Some examples for detection/classification:

Some examples for bad detection/classification (model needs more training?):

Extracting more information from images

I was reading that ecologists also look at camera trap images to extract more information about the ecosystem, such as weather conditions.

My hand-waving approach was to use Custom Vision to train weather data. I stumbled upon a Multi-class Weather Dataset for Image Classification, which contains 4 classes of weather conditions. The dataset was used for training.

However, testing the model on some images, the model does not seem to be the best for camera-traps. Even though some classifications were on point, the accuracy is really low.

Another hand-waving approach to extract weather data from camera-trap images (haven't implemented this yet):

It seems that some images display temperature data in each image. Another approach is to extract temperature information as well as time/date stamps from images (OCR). Then use historical weather datasets (such as openweather API) to fetch other weather features such as humidity, wind direction/speed, weather conditions (rainy, cloudy, partially sunny, sunny), etc..

Raspberry pi as an Edge AI Device

As implied earlier, the main reason to convert the Yolov4 model to a TensorFlow Lite model is for it to be run on the raspberry pi. This means that as an image or video is taken, object detection and classification happens on the device itself, where the results can be either uploaded directly to the internet or saved on an SD card.

As the weather information is relatively more challenging to extract directly from images and videos, integrating relatively cheap sensors may provide a more custom overview of the ecosystem. For example, it is possible to add sensors to collect data about emissions such as COx, NOx, NH3, VOCs as well as air quality. It would also allow for more customizability when it comes to choosing a camera that may be a better fit for custom applications, as well as detection sensors (in this example, pyroelectric/ infrared sensor in addition to an ultrasonic sensor).

No module named 'detection'

when i try to run the code on local pc i got this error
Traceback (most recent call last): File "CameraTraps\detection/run_detector_batch.py", line 79, in <module> from detection.run_detector import ImagePathUtils, is_gpu_available, load_detector ModuleNotFoundError: No module named 'detection'

Detection Issues

Dear authors of MegaDetector,

I would be very grateful, if you could help me and my colleagues with a very persistent issue:
We applied MegaDetector (run_tf_detector_batch.py) for a large amount of camera trap imagery. Yet we noticed that for many cases, the locations of the individual bounding boxes, stored in the resulting JSON-file, do not represent the animals’ actual position within the image. Thus, we ran the test version (run_tf_detector.py) for a collection of images. Yet the bounding boxes in the resulting “..._detections”-images just matched perfectly with the animal’s location. Consequently, we performed the batch-version on folders only containing one of these test images and the resulting JSON-files contained the exact same values as after the first run while still not matching the animals position.
We performed these steps on several different PCs (computers and laptops) as well as with different operating systems (Ubuntu and Windows). However, the issue persists.

We would be extremely grateful for your advice and help.

Best regards,
Tobias Pelchen (e-mail: [email protected])

detection issue.pdf

cannot import name 'TFDetector' from 'detection.run_detector

using colab

Traceback (most recent call last):
  File "run_tf_detector_batch.py", line 66, in <module>
    from detection.run_detector import ImagePathUtils, TFDetector
ImportError: cannot import name 'TFDetector' from 'detection.run_detector' (/content/CameraTraps/detection/run_detector.py)

Apple M1 Support

Hi All - very excited about this release!

I know this is probably deep down in the dependencies but wanted to raise given that M1 chips are becoming more common and that Mac instructions are given in the README.

The following error occurred running run_detector.py

Intel MKL FATAL ERROR: This system does not meet the minimum requirements for use of the Intel(R) Math Kernel Library.
The processor must support the Intel(R) Supplemental Streaming SIMD Extensions 3 (Intel(R) SSSE3) instructions.
The processor must support the Intel(R) Streaming SIMD Extensions 4.2 (Intel(R) SSE4.2) instructions.
The processor must support the Intel(R) Advanced Vector Extensions (Intel(R) AVX) instructions.

Failed to load the native TensorFlow runtime.

I'm a little familiar with Python and Anaconda, and have followed the steps for installation on a windows machine. However, I get the error "Failed to load the native TensorFlow runtime" when I try to run_tf_detector.py - can anyone point me to where I am going wrong?

Training megadetector on my own images

Hello,
Thank you so much for this great program!

I have thousands of images from trap cameras, and while megadetector works wonderfully on some landscapes, it fails in other (it detects trees and stones as animals).

What is a useful way to train megadetector on my own set of images?

Cheers,
Bar

CameraTraps/api/batch_processing/api_core/ readme not specific enough

I am attempting to set up the API in my own subscription and I have never used Azure Machine Learning workspace before. In the CameraTraps/api/batch_processing/api_core/README.md it states: to set up a new "AML workspace" but there are two resource types on azure that have similar names to this and it is not clear which I should use. The two names are:

Azure Machine Learning service workspace
Azure Machine Learning Studio workspace

After reading the descriptions, I assume it is the Azure Machine Learning service workspace but I would like clarification.

MegaDetector: broken data stream when reading image file / cannot join current thread

Before I start digging into it further, has anyone come across the following problem? I've run the detector twice and got the same result... thinking along the lines of corrupt file or faulty disk?

Potentially a duplicate of #94 but doesn't contain any logs so unsure.

$ PYTHONPATH=$PYTHONPATH:$(pwd) python3 detection/run_tf_detector_batch.py --recursive --forceCpu --checkpointFrequency 1000
 --outputRelativeFilenames ./detection/megadetector_v3.pb ../borneo-dataset/release/0.5/SAFE/SAFE_2/ ../Borneo-0.5-SAFE2.txt
                                                                                                             
tensorflow tf version: 1.14.0                                     
2019-10-03 12:28:29.084524: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: FMA
2019-10-03 12:28:29.381379: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2400065000 Hz
2019-10-03 12:28:29.386639: I tensorflow/compiler/xla/service/service.cc:168] XLA service 0x3d43f60 executing computations on platform Host. Devices:
2019-10-03 12:28:29.386727: I tensorflow/compiler/xla/service/service.cc:175]   StreamExecutor device (0): <undefined>, <undefined>
tf_detector.py, tf.test.is_gpu_available: False                                               
WARNING: Logging before flag parsing goes to stderr.                            
W1003 12:28:29.404660 140666144171840 deprecation_wrapper.py:119] From detection/run_tf_detector_batch.py:51: The name tf.logging.set_verbosity is deprecated. Please us
e tf.compat.v1.logging.set_verbosity instead.                                                                 
                
W1003 12:28:29.405052 140666144171840 deprecation_wrapper.py:119] From detection/run_tf_detector_batch.py:51: The name tf.logging.ERROR is deprecated. Please use tf.com
pat.v1.logging.ERROR instead. 
                                                                                                                      
Running detector on 57170 images                       
Loading model...                                                                                             
tf_detector.py: Loading graph...                                                
tf_detector.py: Detection graph loaded.                     
Loaded model in 15.1 seconds                                                                                  
Running detector...                     
0it [00:00, ?it/s]2019-10-03 12:28:55.971887: W tensorflow/compiler/jit/mark_for_compilation_pass.cc:1412] (One-time warning): Not using XLA:CPU for cluster because env
var TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set.  If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU.  To confirm that XL
A is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile.
var TF_XLA_FLAGS=--tf_xla_cpu_global_jit was not set.  If you want XLA:CPU, either set that envvar, or use experimental_jit_scope to enable XLA:CPU.  To confirm [0/498]
A is active, pass --vmodule=xla_compilation_cache=1 (as a proper command-line flag, not via TF_XLA_FLAGS) or set the envvar XLA_FLAGS=--xla_hlo_profile.
2019-10-03 12:29:01.395446: W tensorflow/core/framework/allocator.cc:107] Allocation of 377318400 exceeds 10% of system memory.
2019-10-03 12:29:01.487368: W tensorflow/core/framework/allocator.cc:107] Allocation of 377318400 exceeds 10% of system memory.
2019-10-03 12:29:01.982219: W tensorflow/core/framework/allocator.cc:107] Allocation of 99878400 exceeds 10% of system memory.
2019-10-03 12:29:02.555869: W tensorflow/core/framework/allocator.cc:107] Allocation of 159744000 exceeds 10% of system memory.
2019-10-03 12:29:02.715443: W tensorflow/core/framework/allocator.cc:107] Allocation of 159744000 exceeds 10% of system memory.
Checkpointing 1 images to /tmp/detector_batch/tmpud3njeui......done
1000it [2:11:24,  7.87s/it]Checkpointing 1001 images to /tmp/detector_batch/tmp6wgeh416......done                                                                       
2000it [4:23:28,  7.90s/it]Checkpointing 2001 images to /tmp/detector_batch/tmp_6tnl91e......done                                                                       
3000it [6:36:44,  8.07s/it]Checkpointing 3001 images to /tmp/detector_batch/tmpnwm51sek......done                                                       
3344it [7:23:24,  8.08s/it]Traceback (most recent call last):                                                                  
  File "detection/run_tf_detector_batch.py", line 559, in <module>                                                             
    main()                                                                                                                    
  File "detection/run_tf_detector_batch.py", line 554, in main                                                                 
    load_and_run_detector(options)                                                                                             
  File "detection/run_tf_detector_batch.py", line 437, in load_and_run_detector
    boxes,scores,classes,imageFileNames = generate_detections(detector,imageFileNames,options)   
  File "detection/run_tf_detector_batch.py", line 167, in generate_detections                    
    imageNP = PIL.Image.open(image).convert("RGB"); imageNP = np.array(imageNP)                  
  File "/home/bencevans/.local/lib/python3.6/site-packages/PIL/Image.py", line 912, in convert
    self.load()                                                   
  File "/home/bencevans/.local/lib/python3.6/site-packages/PIL/ImageFile.py", line 261, in load
    raise_ioerror(err_code)                                   
  File "/home/bencevans/.local/lib/python3.6/site-packages/PIL/ImageFile.py", line 58, in raise_ioerror
    raise IOError(message + " when reading image file")                        
OSError: broken data stream when reading image file                                           
Exception ignored in: <bound method tqdm.__del__ of 3344it [7:23:25,  8.08s/it]>
Traceback (most recent call last):                                             
  File "/home/bencevans/.local/lib/python3.6/site-packages/tqdm/_tqdm.py", line 931, in __del__
    self.close()
  File "/home/bencevans/.local/lib/python3.6/site-packages/tqdm/_tqdm.py", line 1133, in close 
    self._decr_instances(self)
  File "/home/bencevans/.local/lib/python3.6/site-packages/tqdm/_tqdm.py", line 496, in _decr_instances
    cls.monitor.exit()                                 
  File "/home/bencevans/.local/lib/python3.6/site-packages/tqdm/_monitor.py", line 52, in exit
    self.join()                                                                 
  File "/usr/lib/python3.6/threading.py", line 1053, in join
    raise RuntimeError("cannot join current thread")                                                          
RuntimeError: cannot join current thread

pretrained weights for megadetector v5?

Thanks for continuing to maintain this awesome set of tools! My question is about where to find the latest release. I see megadetector v5 referenced here: https://github.com/microsoft/CameraTraps/blob/main/detection/README.md

But the latest release is for 4.1 https://github.com/microsoft/CameraTraps/releases/tag/v4.1

Are the weights available somewhere else other than the release page? We might be using Megadetector soon in addition to https://github.com/microsoft/SpeciesClassification to detect people, mountain lions, foxes, coyotes, and deer and I was looking to use the most up to date models published here.

class labels significance

Where can I get the mapping between class labels and class names in "run_tf_detector.py" ?

Error installing tensorflow 1.13.1

I couldn't install tensorflow using the readme instructions:

$ pip install tensorflow==1.13.1
ERROR: Could not find a version that satisfies the requirement tensorflow==1.13.1 (from versions: 2.2.0rc1, 2.2.0rc2, 2.2.0rc3, 2.2.0rc4, 2.2.0, 2.2.1, 2.2.2, 2.3.0rc0, 2.3.0rc1, 2.3.0rc2, 2.3.0, 2.3.1, 2.3.2, 2.4.0rc0, 2.4.0rc1, 2.4.0rc2, 2.4.0rc3, 2.4.0rc4, 2.4.0)
ERROR: No matching distribution found for tensorflow==1.13.1

But after some googling this method worked for me:

python -m pip install --upgrade https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-1.13.1-py3-none-any.whl

Model doesn't learn to classify

Hey guys!

So, I've been trying to work with this amazing repo you guys put out there but, even though I can run the scripts and execute training, the model simply doesn't seem to be learning how to classify. My goal is to train a classifier on my own species.

I will try to describe the path I made to get where I am now.
I'm on Ubuntu 18.04, tensorflow-gpu=1.15 and have installed all necessary dependencies to run your repository.
I mainly followed this to try and achieve what I needed: https://github.com/microsoft/CameraTraps/blob/master/classification/TUTORIAL.md

First, I started with a VOC format dataset (consists of images + xml with the detections). Because here we need to use the COCO json format, I used the following script to make such changes:
https://github.com/Tony607/voc2coco/blob/master/voc2coco.py
And also, here's an example of an original XML file.

Now I bring up the question: the "path" field is not correct, as this file is not in the original place anymore. However, it doesn't seem to affect anything, because I can still generate the COCO json. Here's an example extracted from said json:

Which seems ok, since it got the file name right (this is the name it'll search when I point to the images folder, right?) and as I understand COCO json doesn't use xmax and ymax but rather width and height, right as well? The category id also matches the one expected.
Alright, the next step was generating the tf records.
I started trying by using your script, but it seemed to be trying to import a file that did not exist, so instead I went in and used this one (from TF OD API):
https://github.com/tensorflow/models/blob/master/research/object_detection/dataset_tools/create_coco_tf_record.py
As for the test and validation folders, I pointed it to the same and simply ignored the validation files (since here only train and test matters). Everything went well and I got my folder full of tf records (I just had to rename them because the training script here searches for "train-" and "test-" so I add these to the beginning of my file name.
So, with everything in hand, I went to the training part.
I had already the tf records and model checkpoint (inception v4), just needed to prepare some files for training. First copy and modify the dataset python script. I changed the "SPLIT_TO_SIZE" variable to: SPLITS_TO_SIZES = {'train': 7624, 'test': 1885} and "_NUM_CLASSES = 17". Furthermore, I added my dataset to "dataset_factory.py". Finally, I modify the .sh script to adapt and create the one for my own dataset.
DATASET_DIR points to the folder containing the tf records. TRAIN_DIR to the output path (log/date...). CHECKPOINT_PATH to where I had my inception model checkpoint. And MODEL_NAME was still "inception_v4". For better visualization:

Finally, I executed the script by typing: bash ../training_scripts/train_deep_inception_v4.sh
It trained reeeeally slowly, with the loss decreasing .0001 per 300~400 steps. It seemed ok though cause it was actually going down. I left the model training overnight, unfortunately it trained only for a few hours.
However, when I woke up and came to check the model, it had stopped immediately after an evaluation step which outputed accuracy and recall equal to 1, which I knew wasn't right. I then exported the graph to see an actual inference and this is what I got:

So, the detection is working well, since I use the megadetector model you guys provide, however, classification absolutely sucks. What it is doing is simply labeling all animals as the first label it sees on my "label.txt" file. If I change which class comes first, classification changes as well. So, it doesn't like the model is learning to classify anything, and I simply can't find a reason why.
I'm working on this problem for quite a while now, have tried to use TF OD API directly but with no success as well.

Any tips? Directions? Questions?
Please any help is welcome!

Is the batch processing API and the real-time API running the same classifiers ?

Looking into classifying some thermal images to filter out empty images and roughly label when there is are different objects in the pictures. Will process around 3000 images per day and need to label 3-4 different categories - empty , animal, human

Wondering if the live web API or the batch processing would be a better option?
The readme says that the web API runs species classifiers so wondering if they are the same for the batch processing

Also do you use some public discord or slack?

Colab notebook: annotated images not available in [Visualization_Folder]

Thanks for sharing the colab notebook. As a newbie in this, it's very helpful to be able to test your script before investing time into deploying it at full scale on all the camera traps photos in our project (nest success and invasive predator in an endangered Caribbean seabird).

I would like to share with collaborators the annotated images resulting from the script but the Google Drive folder used as [Visualization_Folder] does not contain any file. Also, Colab's runtime keeps disconnecting and cannot make through the annotation/display of 25 samples photos, hence the need to be able to save those images that have gone through the process.
Thus, my question may be very basic: how to save (or access) the images that are annotated and displayed in the last step (cell below)?

Here are the steps of interest:

images_dir = '/content/drive/My Drive/ctrap'

# choose a location for the output JSON file
output_file_path = '/content/drive/My Drive/ctrap/detector_2020-09-28.json'

Here we use the visualize_detector_output.py in the visualization folder of the Camera Traps repo to see the output of the MegaDetector visualized on our images. It will save images annotated with the results (original images will not be modified) to the [Visualization_Folder] you specify here.

visualization_dir = '/content/My Drive/ctrap/visualize_2020-09-28'  # pick a location for annotated images

!python visualize_detector_output.py "$output_file_path" "$visualization_dir" --confidence 0.8 --images_dir "$images_dir"

import os
from PIL import Image

for viz_file_name in os.listdir(visualization_dir):
  print(viz_file_name)
  im = Image.open(os.path.join(visualization_dir, viz_file_name))
  display(im)  # display() is an iPython method that comes with the notebook

I understand that the images are supposed to be saved in the [Visualization_Folder] but this folder is empty (see edited screeenshots below - note that the visualize_2020-09-28 folder is open).

Error when image file is corrupted

Some images, especially from Bushnell cameras, are corrupted (there is missing data). An example is: Snapshot Serengeti\S1\I03\I03_R1\S1_I03_R1_PICT3967.JPG
The run_tf_detector_batch.py script crashes on those images. The only way to process the images is to open them in an image editor and save them again, replacing the bad data with some background value.

Adding the following code to run_tf_detector_batch.py will replace the bad data automatically and allows the batch detector to run over all images without an error;

from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True

Continuing the training of MegaDetector

Hi all! That's a lot for making this fantastic work available, the collective usefulness of the tools provided is truly staggering.

I was trying out MegaDetector and it's working really well. However, it consistently misses some smaller animals that are partially obscured in the grass (so, false negatives), and sometimes has a tendency to pick up inanimate objects like tree stumps as animals (false positives). Confidence thresholding doesn't help to weed out those false positives as it comes at a high price - basically, I'd have to set a threshold close to unity and miss on a lot of robust animal detection that way.

I see that there are checkpoints available for the 4.1 detector version, and was wondering if there's a code snippet one can use for continuing the training?

Alternatively (a bit of a general question, sorry), are they any good strategies to mitigate the issues above?

Limit number of cores used

I'm using the batch detector on a HPC and need to limit the number of cores used to the number requested. If I used the --cores the batch detector creates a pool of workers which uses a lot more memory and does not support logging or checkpointing. Is there a way to limit the number of cores used without creating a workerpool? I think it's related to set_inter_op_parallelism_threads, but I'm not sure how to set tensorflow config from run_tf_detector_batch.py.

I am not properly able to understand the real time api docs , can someone help me out?

Prediction results from locally loaded SavedModel significantly differ from TF Serving model

Hi,

I'm working with MegaDetector v3, 2019.05.30 and noticed that the prediction results for a given image significantly differ between the locally loaded SavedModel and the TFServing model -> where:

locally loaded SavedModel = saved_model_normalized_megadetector_v3_tf19.tar.gz
TFServing model = saved_model_megadetector_v3_tf19.zip

The locally loaded quite underperforms vs. the TFServing model. Is this something you have seen before? Happy to share my code (am on TF2.1)

Thanks & best regards,

Mike

Crop MegaDetector json

Hi,
I've just started using megadetector and I was wondering if you could recommend any good code to crop my images using the boxes identified?
Thanks!

tensorflow-gpu version

Hello, just a quick question about the supported tensorflow-gpu version. I am having installation issues with version 1.13.1 and was wondering if there is a more recent version that works, or if it must necessarily be 1.13.1. Thanks!

tflite version

Hi, that you for all the work done on this model and for sharing it with freely. I am wanting to use it in a real-time situation i.e. to spot monkeys in my vegetable patch. I was hoping to get it working on a rasp pi 4 with Coral Edge TPU. The Coral can only use tensorflow lite and so I paid someone to try convert the MegaDetector into a version that could run on the Coral TPU but that was unfortunately unsuccessful. My question is where you think there is any change or releasing a version that might run on a pi / Coral TPU / tflite?

Batch inference with classifier?

What is the appropriate way to do batch inference using a trained classifier? The classifier documentation lists three methods:

predict_image.py
detect_and_predict_image.py
generate_sample_predictions.py

The first appears not to support batch inference. #2 and #3 do batch inference, but running each of them resulted in the entire data set attempting to be loaded into memory. What is the correct way to perform inference on a large number of images using this repo?

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.

Jobs

Jooble