From 15c4e16a0e7f760d485e9cd3db886c295371266d Mon Sep 17 00:00:00 2001
From: ShrihanSolo <shrihan.agarwal@gmail.com>
Date: Fri, 21 Jun 2024 01:51:01 +0000
Subject: [PATCH] restructuring and preparing 3band

---
 data                                          |    1 +
 {src/sim => sim}/.DS_Store                    |  Bin
 {src/sim => sim}/configs/delve_galgal.yaml    |    0
 {src/sim => sim}/configs/delve_shrihan.yaml   |    0
 .../configs/fid_source.yaml                   |    2 +-
 .../configs/fid_target.yaml                   |    2 +-
 .../sim => sim}/configs/multiband_source.yaml |    2 +-
 .../sim => sim}/configs/multiband_target.yaml |    2 +-
 {src/sim => sim}/configs/pax_source.yaml      |    0
 {src/sim => sim}/configs/pax_source_des.yaml  |    0
 {src/sim => sim}/configs/pax_target.yaml      |    0
 {src/sim => sim}/configs/sky1.yaml            |    0
 {src/sim => sim}/configs/sky100.yaml          |    0
 {src/sim => sim}/configs/sky10000.yaml        |    0
 {src/sim => sim}/configs/test.yaml            |    0
 {notebooks => sim/notebooks}/gen_sim.ipynb    |   60 +-
 .../notebooks}/old/dlsim_Shrihan.ipynb        |    0
 .../notebooks}/old/example.ipynb              |    0
 .../notebooks}/old/explore.ipynb              |    0
 .../notebooks}/old/paxsim_Shrihan.ipynb       |    0
 .../old/sim_training_set_cleaned.ipynb        |    0
 .../old/sky_brightness_testing.ipynb          |    0
 .../notebooks}/old/testsim_Shrihan.ipynb      |    0
 {notebooks => sim/notebooks}/renorm.ipynb     |    0
 {src => sim}/scripts/__init__.py              |    0
 {src => sim}/scripts/__version__.py           |    0
 {src => sim}/scripts/evaluate.py              |    0
 {src => sim}/scripts/paths.py                 |    0
 {src => sim}/scripts/train.py                 |    0
 {src => sim}/static/.gitignore                |    0
 {src => sim}/tex/.gitignore                   |    0
 {src => sim}/tex/bib.bib                      |    0
 {src => sim}/tex/figures/.gitignore           |    0
 {src => sim}/tex/ms.tex                       |    0
 {src => sim}/tex/output/.gitignore            |    0
 {src => sim}/tex/showyourwork.sty             |    0
 src/sim/data/.DS_Store                        |  Bin 6148 -> 0 bytes
 src/sim/data/.gitignore                       |    2 -
 src/sim/data/mb_target/.DS_Store              |  Bin 6148 -> 0 bytes
 test/test_example.py                          |   23 -
 {src => training}/.DS_Store                   |  Bin
 .../MMD_old}/Shrihan_MMD_practice.ipynb       |    0
 .../MMD_old}/Shrihan_Norm2_MMD_practice.ipynb |    0
 .../MMD_old}/Shrihan_Norm_MMD_practice.ipynb  |    0
 .../MMD_paper/fiducial}/ShrihanPaperMMD.ipynb |    0
 .../fiducial}/ShrihanPaperMMD_fidcheck.ipynb  |    0
 .../fiducial/ShrihanPaperMMD_fidcheck2.ipynb  | 1380 +++++++++++++++++
 .../multiband/ShrihanPaperMMD_mb.ipynb        | 1005 ++++++++++++
 .../ShrihanPaperMMD_MinMaxNorm.ipynb          |    0
 .../normalization}/ShrihanPaperMMD_Norm.ipynb |    0
 .../ShrihanPaperMMD_Norm2.ipynb               |    0
 .../original_mmdpaper_notebook.ipynb          |    0
 training/scripts/__init__.py                  |    0
 training/scripts/__version__.py               |    0
 training/scripts/evaluate.py                  |   46 +
 training/scripts/paths.py                     |   29 +
 training/scripts/train.py                     |   39 +
 training/static/.gitignore                    |    2 +
 training/tex/.gitignore                       |    2 +
 training/tex/bib.bib                          |   37 +
 training/tex/figures/.gitignore               |    5 +
 training/tex/ms.tex                           |  254 +++
 training/tex/output/.gitignore                |    5 +
 training/tex/showyourwork.sty                 |   13 +
 64 files changed, 2869 insertions(+), 42 deletions(-)
 create mode 120000 data
 rename {src/sim => sim}/.DS_Store (100%)
 rename {src/sim => sim}/configs/delve_galgal.yaml (100%)
 rename {src/sim => sim}/configs/delve_shrihan.yaml (100%)
 rename src/sim/configs/pax_original_source.yaml => sim/configs/fid_source.yaml (97%)
 rename src/sim/configs/pax_original_target.yaml => sim/configs/fid_target.yaml (99%)
 rename {src/sim => sim}/configs/multiband_source.yaml (97%)
 rename {src/sim => sim}/configs/multiband_target.yaml (99%)
 rename {src/sim => sim}/configs/pax_source.yaml (100%)
 rename {src/sim => sim}/configs/pax_source_des.yaml (100%)
 rename {src/sim => sim}/configs/pax_target.yaml (100%)
 rename {src/sim => sim}/configs/sky1.yaml (100%)
 rename {src/sim => sim}/configs/sky100.yaml (100%)
 rename {src/sim => sim}/configs/sky10000.yaml (100%)
 rename {src/sim => sim}/configs/test.yaml (100%)
 rename {notebooks => sim/notebooks}/gen_sim.ipynb (51%)
 rename {notebooks => sim/notebooks}/old/dlsim_Shrihan.ipynb (100%)
 rename {notebooks => sim/notebooks}/old/example.ipynb (100%)
 rename {notebooks => sim/notebooks}/old/explore.ipynb (100%)
 rename {notebooks => sim/notebooks}/old/paxsim_Shrihan.ipynb (100%)
 rename {notebooks => sim/notebooks}/old/sim_training_set_cleaned.ipynb (100%)
 rename {notebooks => sim/notebooks}/old/sky_brightness_testing.ipynb (100%)
 rename {notebooks => sim/notebooks}/old/testsim_Shrihan.ipynb (100%)
 rename {notebooks => sim/notebooks}/renorm.ipynb (100%)
 rename {src => sim}/scripts/__init__.py (100%)
 rename {src => sim}/scripts/__version__.py (100%)
 rename {src => sim}/scripts/evaluate.py (100%)
 rename {src => sim}/scripts/paths.py (100%)
 rename {src => sim}/scripts/train.py (100%)
 rename {src => sim}/static/.gitignore (100%)
 rename {src => sim}/tex/.gitignore (100%)
 rename {src => sim}/tex/bib.bib (100%)
 rename {src => sim}/tex/figures/.gitignore (100%)
 rename {src => sim}/tex/ms.tex (100%)
 rename {src => sim}/tex/output/.gitignore (100%)
 rename {src => sim}/tex/showyourwork.sty (100%)
 delete mode 100644 src/sim/data/.DS_Store
 delete mode 100644 src/sim/data/.gitignore
 delete mode 100644 src/sim/data/mb_target/.DS_Store
 delete mode 100644 test/test_example.py
 rename {src => training}/.DS_Store (100%)
 rename {notebooks => training/notebooks/MMD_old}/Shrihan_MMD_practice.ipynb (100%)
 rename {notebooks => training/notebooks/MMD_old}/Shrihan_Norm2_MMD_practice.ipynb (100%)
 rename {notebooks => training/notebooks/MMD_old}/Shrihan_Norm_MMD_practice.ipynb (100%)
 rename {notebooks => training/notebooks/MMD_paper/fiducial}/ShrihanPaperMMD.ipynb (100%)
 rename {notebooks => training/notebooks/MMD_paper/fiducial}/ShrihanPaperMMD_fidcheck.ipynb (100%)
 create mode 100644 training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD_fidcheck2.ipynb
 create mode 100644 training/notebooks/MMD_paper/multiband/ShrihanPaperMMD_mb.ipynb
 rename {notebooks => training/notebooks/MMD_paper/normalization}/ShrihanPaperMMD_MinMaxNorm.ipynb (100%)
 rename {notebooks => training/notebooks/MMD_paper/normalization}/ShrihanPaperMMD_Norm.ipynb (100%)
 rename {notebooks => training/notebooks/MMD_paper/normalization}/ShrihanPaperMMD_Norm2.ipynb (100%)
 rename notebooks/mmd_to_send.ipynb => training/notebooks/MMD_paper/original_mmdpaper_notebook.ipynb (100%)
 create mode 100644 training/scripts/__init__.py
 create mode 100644 training/scripts/__version__.py
 create mode 100644 training/scripts/evaluate.py
 create mode 100644 training/scripts/paths.py
 create mode 100644 training/scripts/train.py
 create mode 100644 training/static/.gitignore
 create mode 100644 training/tex/.gitignore
 create mode 100644 training/tex/bib.bib
 create mode 100644 training/tex/figures/.gitignore
 create mode 100644 training/tex/ms.tex
 create mode 100644 training/tex/output/.gitignore
 create mode 100644 training/tex/showyourwork.sty

diff --git a/data b/data
new file mode 120000
index 0000000..b0fe5e7
--- /dev/null
+++ b/data
@@ -0,0 +1 @@
+/deepskieslab/agarwal/data
\ No newline at end of file
diff --git a/src/sim/.DS_Store b/sim/.DS_Store
similarity index 100%
rename from src/sim/.DS_Store
rename to sim/.DS_Store
diff --git a/src/sim/configs/delve_galgal.yaml b/sim/configs/delve_galgal.yaml
similarity index 100%
rename from src/sim/configs/delve_galgal.yaml
rename to sim/configs/delve_galgal.yaml
diff --git a/src/sim/configs/delve_shrihan.yaml b/sim/configs/delve_shrihan.yaml
similarity index 100%
rename from src/sim/configs/delve_shrihan.yaml
rename to sim/configs/delve_shrihan.yaml
diff --git a/src/sim/configs/pax_original_source.yaml b/sim/configs/fid_source.yaml
similarity index 97%
rename from src/sim/configs/pax_original_source.yaml
rename to sim/configs/fid_source.yaml
index 9bdaae0..7cf0a94 100644
--- a/src/sim/configs/pax_original_source.yaml
+++ b/sim/configs/fid_source.yaml
@@ -2,7 +2,7 @@ DATASET:
     NAME: SourceData # set a name, this value is only used if you request the h5 file format
     PARAMETERS:
         SIZE: 50000 # number of images in the full datase.
-        OUTDIR: ../src/sim/data/pax_orig_source # will be created on your system if your request to save images
+        OUTDIR: ../../data/fid_source # will be created on your system if your request to save images
         SEED: 10 
 
 COSMOLOGY:
diff --git a/src/sim/configs/pax_original_target.yaml b/sim/configs/fid_target.yaml
similarity index 99%
rename from src/sim/configs/pax_original_target.yaml
rename to sim/configs/fid_target.yaml
index d563752..ae7bda0 100644
--- a/src/sim/configs/pax_original_target.yaml
+++ b/sim/configs/fid_target.yaml
@@ -2,7 +2,7 @@ DATASET:
     NAME: TargetData # set a name, this value is only used if you request the h5 file format
     PARAMETERS:
         SIZE: 50000 # number of images in the full datase.
-        OUTDIR: pax_orig_target
+        OUTDIR: ../../data/fid_target
         SEED: 10 
 
 COSMOLOGY:
diff --git a/src/sim/configs/multiband_source.yaml b/sim/configs/multiband_source.yaml
similarity index 97%
rename from src/sim/configs/multiband_source.yaml
rename to sim/configs/multiband_source.yaml
index 4a59345..9fadd7f 100644
--- a/src/sim/configs/multiband_source.yaml
+++ b/sim/configs/multiband_source.yaml
@@ -2,7 +2,7 @@ DATASET:
     NAME: SourceData # set a name, this value is only used if you request the h5 file format
     PARAMETERS:
         SIZE: 50000 # number of images in the full datase.
-        OUTDIR: ../src/sim/data/mb_source # will be created on your system if your request to save images
+        OUTDIR: ../../data/mb_source # will be created on your system if your request to save images
         SEED: 10 
 
 COSMOLOGY:
diff --git a/src/sim/configs/multiband_target.yaml b/sim/configs/multiband_target.yaml
similarity index 99%
rename from src/sim/configs/multiband_target.yaml
rename to sim/configs/multiband_target.yaml
index 21617b7..2da4eed 100644
--- a/src/sim/configs/multiband_target.yaml
+++ b/sim/configs/multiband_target.yaml
@@ -2,7 +2,7 @@ DATASET:
     NAME: TargetData # set a name, this value is only used if you request the h5 file format
     PARAMETERS:
         SIZE: 50000 # number of images in the full datase.
-        OUTDIR: ../src/sim/data/mb_target
+        OUTDIR: ../../data/mb_target
         SEED: 10 
 
 COSMOLOGY:
diff --git a/src/sim/configs/pax_source.yaml b/sim/configs/pax_source.yaml
similarity index 100%
rename from src/sim/configs/pax_source.yaml
rename to sim/configs/pax_source.yaml
diff --git a/src/sim/configs/pax_source_des.yaml b/sim/configs/pax_source_des.yaml
similarity index 100%
rename from src/sim/configs/pax_source_des.yaml
rename to sim/configs/pax_source_des.yaml
diff --git a/src/sim/configs/pax_target.yaml b/sim/configs/pax_target.yaml
similarity index 100%
rename from src/sim/configs/pax_target.yaml
rename to sim/configs/pax_target.yaml
diff --git a/src/sim/configs/sky1.yaml b/sim/configs/sky1.yaml
similarity index 100%
rename from src/sim/configs/sky1.yaml
rename to sim/configs/sky1.yaml
diff --git a/src/sim/configs/sky100.yaml b/sim/configs/sky100.yaml
similarity index 100%
rename from src/sim/configs/sky100.yaml
rename to sim/configs/sky100.yaml
diff --git a/src/sim/configs/sky10000.yaml b/sim/configs/sky10000.yaml
similarity index 100%
rename from src/sim/configs/sky10000.yaml
rename to sim/configs/sky10000.yaml
diff --git a/src/sim/configs/test.yaml b/sim/configs/test.yaml
similarity index 100%
rename from src/sim/configs/test.yaml
rename to sim/configs/test.yaml
diff --git a/notebooks/gen_sim.ipynb b/sim/notebooks/gen_sim.ipynb
similarity index 51%
rename from notebooks/gen_sim.ipynb
rename to sim/notebooks/gen_sim.ipynb
index f37fe03..5bf9e1b 100644
--- a/notebooks/gen_sim.ipynb
+++ b/sim/notebooks/gen_sim.ipynb
@@ -2,7 +2,7 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -12,7 +12,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def rename_result(name, head):\n",
+    "    datapath = head / f'data/{name}'\n",
+    "    imgpath = datapath / 'CONFIGURATION_1_images.npy'\n",
+    "    mdpath = datapath / 'CONFIGURATION_1_metadata.csv'\n",
+    "    if imgpath.exists():\n",
+    "        imgpath.rename(datapath / (datapath.name + '.npy'))\n",
+    "    if mdpath.exists():\n",
+    "        mdpath.rename(datapath / (datapath.name + '_metadata.csv'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
    "metadata": {},
    "outputs": [
     {
@@ -22,19 +38,28 @@
       "Entering main organization loop\n",
       "Organizing CONFIGURATION_1\n",
       "Generating images for CONFIGURATION_1\n",
-      "\tProgress: 100.0 %  ---  Elapsed Time: 0 H 8 M 46 S         \n"
+      "\tProgress: 100.0 %  ---  Elapsed Time: 0 H 1 M 58 S         \n"
      ]
     }
    ],
    "source": [
-    "head = Path.cwd().parent\n",
-    "config_file = head / 'src/sim/configs/multiband_source.yaml'\n",
+    "head = Path.cwd().parent.parent\n",
+    "config_file = head / 'sim/configs/fid_source.yaml'\n",
     "dataset = dl.make_dataset(config_file, verbose=True, save_to_disk=True)"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 4,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rename_result('fid_source', head)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
    "metadata": {},
    "outputs": [
     {
@@ -44,16 +69,25 @@
       "Entering main organization loop\n",
       "Organizing CONFIGURATION_1\n",
       "Generating images for CONFIGURATION_1\n",
-      "\tProgress: 100.0 %  ---  Elapsed Time: 0 H 8 M 20 S         \n"
+      "\tProgress: 100.0 %  ---  Elapsed Time: 0 H 1 M 58 S         \n"
      ]
     }
    ],
    "source": [
-    "head = Path.cwd().parent\n",
-    "config_file = head / 'src/sim/configs/multiband_target.yaml'\n",
+    "head = Path.cwd().parent.parent\n",
+    "config_file = head / 'sim/configs/fid_target.yaml'\n",
     "dataset = dl.make_dataset(config_file, verbose=True, save_to_disk=True)"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "rename_result('fid_target', head)"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,
@@ -64,9 +98,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "deeplens",
+   "display_name": "Python [conda env:.conda-deeplens]",
    "language": "python",
-   "name": "python3"
+   "name": "conda-env-.conda-deeplens-py"
   },
   "language_info": {
    "codemirror_mode": {
@@ -78,9 +112,9 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.7.16"
+   "version": "3.7.12"
   }
  },
  "nbformat": 4,
- "nbformat_minor": 2
+ "nbformat_minor": 4
 }
diff --git a/notebooks/old/dlsim_Shrihan.ipynb b/sim/notebooks/old/dlsim_Shrihan.ipynb
similarity index 100%
rename from notebooks/old/dlsim_Shrihan.ipynb
rename to sim/notebooks/old/dlsim_Shrihan.ipynb
diff --git a/notebooks/old/example.ipynb b/sim/notebooks/old/example.ipynb
similarity index 100%
rename from notebooks/old/example.ipynb
rename to sim/notebooks/old/example.ipynb
diff --git a/notebooks/old/explore.ipynb b/sim/notebooks/old/explore.ipynb
similarity index 100%
rename from notebooks/old/explore.ipynb
rename to sim/notebooks/old/explore.ipynb
diff --git a/notebooks/old/paxsim_Shrihan.ipynb b/sim/notebooks/old/paxsim_Shrihan.ipynb
similarity index 100%
rename from notebooks/old/paxsim_Shrihan.ipynb
rename to sim/notebooks/old/paxsim_Shrihan.ipynb
diff --git a/notebooks/old/sim_training_set_cleaned.ipynb b/sim/notebooks/old/sim_training_set_cleaned.ipynb
similarity index 100%
rename from notebooks/old/sim_training_set_cleaned.ipynb
rename to sim/notebooks/old/sim_training_set_cleaned.ipynb
diff --git a/notebooks/old/sky_brightness_testing.ipynb b/sim/notebooks/old/sky_brightness_testing.ipynb
similarity index 100%
rename from notebooks/old/sky_brightness_testing.ipynb
rename to sim/notebooks/old/sky_brightness_testing.ipynb
diff --git a/notebooks/old/testsim_Shrihan.ipynb b/sim/notebooks/old/testsim_Shrihan.ipynb
similarity index 100%
rename from notebooks/old/testsim_Shrihan.ipynb
rename to sim/notebooks/old/testsim_Shrihan.ipynb
diff --git a/notebooks/renorm.ipynb b/sim/notebooks/renorm.ipynb
similarity index 100%
rename from notebooks/renorm.ipynb
rename to sim/notebooks/renorm.ipynb
diff --git a/src/scripts/__init__.py b/sim/scripts/__init__.py
similarity index 100%
rename from src/scripts/__init__.py
rename to sim/scripts/__init__.py
diff --git a/src/scripts/__version__.py b/sim/scripts/__version__.py
similarity index 100%
rename from src/scripts/__version__.py
rename to sim/scripts/__version__.py
diff --git a/src/scripts/evaluate.py b/sim/scripts/evaluate.py
similarity index 100%
rename from src/scripts/evaluate.py
rename to sim/scripts/evaluate.py
diff --git a/src/scripts/paths.py b/sim/scripts/paths.py
similarity index 100%
rename from src/scripts/paths.py
rename to sim/scripts/paths.py
diff --git a/src/scripts/train.py b/sim/scripts/train.py
similarity index 100%
rename from src/scripts/train.py
rename to sim/scripts/train.py
diff --git a/src/static/.gitignore b/sim/static/.gitignore
similarity index 100%
rename from src/static/.gitignore
rename to sim/static/.gitignore
diff --git a/src/tex/.gitignore b/sim/tex/.gitignore
similarity index 100%
rename from src/tex/.gitignore
rename to sim/tex/.gitignore
diff --git a/src/tex/bib.bib b/sim/tex/bib.bib
similarity index 100%
rename from src/tex/bib.bib
rename to sim/tex/bib.bib
diff --git a/src/tex/figures/.gitignore b/sim/tex/figures/.gitignore
similarity index 100%
rename from src/tex/figures/.gitignore
rename to sim/tex/figures/.gitignore
diff --git a/src/tex/ms.tex b/sim/tex/ms.tex
similarity index 100%
rename from src/tex/ms.tex
rename to sim/tex/ms.tex
diff --git a/src/tex/output/.gitignore b/sim/tex/output/.gitignore
similarity index 100%
rename from src/tex/output/.gitignore
rename to sim/tex/output/.gitignore
diff --git a/src/tex/showyourwork.sty b/sim/tex/showyourwork.sty
similarity index 100%
rename from src/tex/showyourwork.sty
rename to sim/tex/showyourwork.sty
diff --git a/src/sim/data/.DS_Store b/src/sim/data/.DS_Store
deleted file mode 100644
index 23809ba40045923db0899fd9fc9866ac7de1d97e..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeHK%TB{E5S)b`3P`9&j{XJyAgan2@Bu)R!lfvPv=T>uIx}7aiO3a%(5_^UAG7Ot
zq}W~nwmx>(zzV>UMQCcwn1*MkPAYjpv=ZY1uXw@^hsSOv&|e(Vx1Zq|TioG*(f1GS
zw(s}c7S8d)i8m4k^f+>hEq2||?nTg^F6RiOcT{2+6Tc#jmKqZjEi4oW1ww&PAQbpn
z1$4R5mKTmuhXSEMDDbI(&WFSzY$|5Qa&)jNDF9K==wfUumyl1Y*i_7poS~V!65Z8m
ziec`~@l<(D#q8+ru$p{WUHKz<v9dbjr$UD{j!}mKp}<suQ}3>H|KISJnN9MiF3}4G
zLV<s#fGsw+n>9C8@78bI(_Ncb?pb8wWi@DQPaXm6=p4B!lRlr+Ca<ZO9Ti36#hn-r
Nfg(s$p};RF@D7TSER+BM

diff --git a/src/sim/data/.gitignore b/src/sim/data/.gitignore
deleted file mode 100644
index 1f2331f..0000000
--- a/src/sim/data/.gitignore
+++ /dev/null
@@ -1,2 +0,0 @@
-*.npy
-*.csv
\ No newline at end of file
diff --git a/src/sim/data/mb_target/.DS_Store b/src/sim/data/mb_target/.DS_Store
deleted file mode 100644
index 5008ddfcf53c02e82d7eee2e57c38e5672ef89f6..0000000000000000000000000000000000000000
GIT binary patch
literal 0
HcmV?d00001

literal 6148
zcmeH~Jr2S!425mzP>H1@V-^m;4Wg<&0T*E43hX&L&p$$qDprKhvt+--jT7}7np#A3
zem<@ulZcFPQ@L2!n>{z**<q8>++&mCkOWA81W14cNZ<zv;LbK1Poaz?KmsK2CSc!(
z0ynLxE!0092;Krf2c+FF_Fe*7ECH>lEfg7;MkzE(HCqgga^y>{tEnwC%0;vJ&^%eQ
zLs35+`xjp>T0<F0fCPF1$Cyrb|F7^5{eNG?83~ZUUlGt@xh*qZDeu<Z%US-OSsOPv
j)R!Z4KLME7ReXlK;d!wEw5GODWMKRea10D2@KpjYNUI8I

diff --git a/test/test_example.py b/test/test_example.py
deleted file mode 100644
index 897c195..0000000
--- a/test/test_example.py
+++ /dev/null
@@ -1,23 +0,0 @@
-"""
-Example of pytest functionality
-
-Goes over some basic assert examples
-"""
-import pytest
-
-
-def test_example_assert_equal():
-    assert 0 == 0
-
-
-def test_example_assert_no_equal():
-    assert 0 != 1
-
-
-def test_example_assert_almost_equal():
-    assert 1.0 == pytest.approx(1.01, .1)
-
-
-"""
-To run this suite of tests, run 'pytest' in the main directory
-"""
\ No newline at end of file
diff --git a/src/.DS_Store b/training/.DS_Store
similarity index 100%
rename from src/.DS_Store
rename to training/.DS_Store
diff --git a/notebooks/Shrihan_MMD_practice.ipynb b/training/notebooks/MMD_old/Shrihan_MMD_practice.ipynb
similarity index 100%
rename from notebooks/Shrihan_MMD_practice.ipynb
rename to training/notebooks/MMD_old/Shrihan_MMD_practice.ipynb
diff --git a/notebooks/Shrihan_Norm2_MMD_practice.ipynb b/training/notebooks/MMD_old/Shrihan_Norm2_MMD_practice.ipynb
similarity index 100%
rename from notebooks/Shrihan_Norm2_MMD_practice.ipynb
rename to training/notebooks/MMD_old/Shrihan_Norm2_MMD_practice.ipynb
diff --git a/notebooks/Shrihan_Norm_MMD_practice.ipynb b/training/notebooks/MMD_old/Shrihan_Norm_MMD_practice.ipynb
similarity index 100%
rename from notebooks/Shrihan_Norm_MMD_practice.ipynb
rename to training/notebooks/MMD_old/Shrihan_Norm_MMD_practice.ipynb
diff --git a/notebooks/ShrihanPaperMMD.ipynb b/training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD.ipynb
similarity index 100%
rename from notebooks/ShrihanPaperMMD.ipynb
rename to training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD.ipynb
diff --git a/notebooks/ShrihanPaperMMD_fidcheck.ipynb b/training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD_fidcheck.ipynb
similarity index 100%
rename from notebooks/ShrihanPaperMMD_fidcheck.ipynb
rename to training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD_fidcheck.ipynb
diff --git a/training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD_fidcheck2.ipynb b/training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD_fidcheck2.ipynb
new file mode 100644
index 0000000..a2ae443
--- /dev/null
+++ b/training/notebooks/MMD_paper/fiducial/ShrihanPaperMMD_fidcheck2.ipynb
@@ -0,0 +1,1380 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "a8aa3fe5-4277-47fc-b26d-baa137256f17",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 10375,
+     "status": "ok",
+     "timestamp": 1718868666013,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "a8aa3fe5-4277-47fc-b26d-baa137256f17",
+    "outputId": "9ad89b68-4fd0-4146-a087-24cd367fb09f"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using cuda device\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Imports we will use\n",
+    "import torch\n",
+    "from torch import nn\n",
+    "import torch.nn.functional as F\n",
+    "from torch.utils.data import DataLoader, TensorDataset\n",
+    "from torch.autograd import Function\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import random\n",
+    "from pathlib import Path\n",
+    "from sklearn.metrics import r2_score\n",
+    "\n",
+    "# For matplotlib\n",
+    "import os\n",
+    "os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'\n",
+    "\n",
+    "# Set Seed\n",
+    "torch.manual_seed(22)\n",
+    "\n",
+    "# Find if cuda is available\n",
+    "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
+    "print(f\"Using {device} device\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "7cc92062-1846-4850-8f8e-206a7c35c171",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 189,
+     "status": "ok",
+     "timestamp": 1718868679894,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "7cc92062-1846-4850-8f8e-206a7c35c171"
+   },
+   "outputs": [],
+   "source": [
+    "# Load data function\n",
+    "def create_dataloader(img_path, metadata_path, batch_size):\n",
+    "    '''\n",
+    "    Creates dataloader for training, reserving the last 1000 images for validation/testing\n",
+    "    '''\n",
+    "    data = np.load(img_path).squeeze()\n",
+    "    length = len(data)\n",
+    "    data_train = torch.tensor(data[:int(.7*length)])\n",
+    "    data_test = torch.tensor(data[int(.7*length):int(.9*length)])\n",
+    "    data_val = torch.tensor(data[int(.9*length):])\n",
+    "\n",
+    "    metadata = pd.read_csv(metadata_path)\n",
+    "    labels = metadata['PLANE_1-OBJECT_1-MASS_PROFILE_1-theta_E-g'].tolist()\n",
+    "    labels_train = torch.tensor(labels[:int(.7*length)])\n",
+    "    labels_test = torch.tensor(labels[int(.7*length):int(.9*length)])\n",
+    "    labels_val = torch.tensor(labels[int(.9*length):])\n",
+    "\n",
+    "    data_train.cuda()\n",
+    "    data_test.cuda()\n",
+    "    data_val.cuda()\n",
+    "    labels_train.cuda()\n",
+    "    labels_test.cuda()\n",
+    "    labels_val.cuda()\n",
+    "\n",
+    "    train_dataset = TensorDataset(data_train, labels_train)\n",
+    "    test_dataset = TensorDataset(data_test, labels_test)\n",
+    "    val_dataset = TensorDataset(data_val, labels_val)\n",
+    "\n",
+    "    train_dataloader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)\n",
+    "    test_dataloader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)\n",
+    "    val_dataloader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=True)\n",
+    "\n",
+    "    return train_dataloader, test_dataloader, val_dataloader, data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "3efc6755-daeb-48ca-bbc7-c5a3b539c5b7",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 19938,
+     "status": "ok",
+     "timestamp": 1718868749575,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "3efc6755-daeb-48ca-bbc7-c5a3b539c5b7"
+   },
+   "outputs": [],
+   "source": [
+    "# Load in data\n",
+    "head = Path.cwd().parents[3]\n",
+    "source_img_path = head / 'data/fid_source/fid_source.npy'\n",
+    "target_img_path = head / 'data/fid_target/fid_target.npy'\n",
+    "source_meta = head / 'data/fid_source/fid_source_metadata.csv'\n",
+    "target_meta = head / 'data/fid_target/fid_target_metadata.csv'\n",
+    "batch_size = 32\n",
+    "source_train_dataloader, source_test_dataloader, source_val_dataloader, source_data = create_dataloader(source_img_path, source_meta, batch_size)\n",
+    "target_train_dataloader, target_test_dataloader, target_val_dataloader, target_data = create_dataloader(target_img_path, target_meta, batch_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "a3045daa-2e71-4335-8259-662a5c7e41a8",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 3,
+     "status": "ok",
+     "timestamp": 1718868749576,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "a3045daa-2e71-4335-8259-662a5c7e41a8"
+   },
+   "outputs": [],
+   "source": [
+    "# Define data visualization function\n",
+    "def visualize_data(data):\n",
+    "    '''\n",
+    "    visualizes 16 random images from dataset\n",
+    "    '''\n",
+    "    #get random indices\n",
+    "    x = np.empty(1)\n",
+    "    i = 1\n",
+    "\n",
+    "    while i < 16:\n",
+    "        example_num = int(random.randrange(0, len(data[0:])))\n",
+    "        if example_num != x[i-1]:\n",
+    "            x = np.append(x, [example_num])\n",
+    "            i += 1\n",
+    "\n",
+    "    #plot the examples for source\n",
+    "    fig1=plt.figure(figsize=(8,8))\n",
+    "\n",
+    "    for i in range(16):\n",
+    "        plt.subplot(4, 4, i + 1)\n",
+    "        plt.axis(\"off\")\n",
+    "\n",
+    "        example_indices = int(x[i])\n",
+    "\n",
+    "        example_image = np.squeeze(data[example_indices:(example_indices + 1)]) #change band by switching 0:1 to 1:2 or 2:3\n",
+    "\n",
+    "        plt.imshow(example_image, aspect='auto', cmap='viridis')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "b72c4588-acb2-478c-96e9-cb09a0380ecd",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 673
+    },
+    "executionInfo": {
+     "elapsed": 559,
+     "status": "ok",
+     "timestamp": 1718868750133,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "b72c4588-acb2-478c-96e9-cb09a0380ecd",
+    "outputId": "651cb9ac-efea-4f14-b3a0-f03648a4081a"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 16 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Visualize source data\n",
+    "visualize_data(source_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "6d6e4147-ce23-4fca-b1aa-42122b0e2501",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 673
+    },
+    "executionInfo": {
+     "elapsed": 665,
+     "status": "ok",
+     "timestamp": 1718868750796,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "6d6e4147-ce23-4fca-b1aa-42122b0e2501",
+    "outputId": "eccb0d95-4566-445f-a058-b1d5b87765b0"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAoAAAAJ8CAYAAABunRBBAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAAEAAElEQVR4nOz9Z5BtWZodhu1jrjd502c+X8+Ur+qq9mame1zPwIxAckhAAEUBlECIpIKKoAFIReiPApQJkBQjFKFQkAQoCiBBjQCKEEKD4dhGT/dMT3dX+6quqlfP1zPpM2/m9e4c/Wj2/db6bp7T971+lVmD+61fJ9/eZ599trvn7bX2+rw4jmNnMBgMBoPBYJgZ+KddAYPBYDAYDAbDycI+AA0Gg8FgMBhmDPYBaDAYDAaDwTBjsA9Ag8FgMBgMhhmDfQAaDAaDwWAwzBjsA9BgMBgMBoNhxmAfgAaDwWAwGAwzBvsANBgMBoPBYJgx2AegwWAwGAwGw4whnDbjF/0/n5zoeQn/rr4v4yg5LSlfWpmQzwuClOJSgp2kPAvLTC0jrTwMtOJDHaMR58M0LEMHavGT3/OnxrTtrvC7w1//ACpzPH7pc/+H8XVYb1Na/GBzfO2FMLRXFrkQaNPhUpmTfBnL2Ud1Seh0Kd/o7NL4Otg9Gl8Pzi5QvsytDfgjQ2m9qyvuOIRHPfrb68FYCaUfvP6Q8kU5KT/YPeT6Ls2Nr324z6s3+OFZKSOaK0EdBpzPl3rEIY+NYTU/vs5sSj3iQpbzzRWkvu2+PGvI4zDOSl/6dzcpzc1J//3We/+ROwl8MfyL8kfafMd1Uc8fPf8R066nWAasC57P99Papeubtg4/bSSt/09ap7T1Kqm8tGelrbvYJylpvzv6B9PV6Sng878q471X49+F2tuwJtVkPg4LnC97JPN6UObPgbAt4yv78GB8HR8eUb7u68+MrzNHMo/9Hq9PoxLMf9WE/Zqk5Q5k/fO7qoyirE+4Tuy/xOt4+ZG817DE75zbl7QoK/2f3etQvjgDv/8wp/w+z11ch6O8WuOXpe1ze/BeHV5Pj56T9blyuzm+3v54hfJl4Ceveo9/k9qrufH1H//6v+emge0AGgwGg8FgMMwY7APQYDAYDAaDYcYwNQWcSj0m0RkJTMZPLCONKnXH0wjxSOWbdtsfrlOpk2mh6AsP6Kt4ANvZiuYhuhkpMN3uSe3kuP6ptE8SNLXBD+Y/T5I6AvgDef/hQonSMl2hX6Pdfbmnr+hL6IfgiLfsPaSH796Xf//oC5RvVAIqol8cX4dbTL1iP8flAicNpE2RYuk+s0T5ct+64Y6DV+TygpzQKNEcUyJ+Q7iDwXpNygC61jnnwiOhFfy6UBGa2g7fezi+Hj17ltIyb92VP4B+H85zfbO3d+QPHHtZ7hMXSTvFK1yPqMi08okgTcoSw/wkOliVkbaeJlKRag4m0L6pa+ETQq+N42epNTJxDVL14HxTSoWmpW/T0tJkSXS/el+6b8r19APGsCh1Km30KW33daEUl/9wa3wdX5infIdXZE6WH3IZ2RuP5L6qrCfRpXXK11mR+TrKy5gc5bgNw7a0W6bBa3KmKWvyKC+/me11XjPKN2R9jcoy93015PObLal7hudalJPyc7e25bkgk3HOuc4a0LcHQBursdG+KL9D+T1+r+yBtGnrLEhe+rzuIu2LY2/9tx5SvtYLq+PrWM1Jf/D43yu2A2gwGAwGg8EwY7APQIPBYDAYDIYZg30AGgwGg8FgMMwYptcAItI0ZWn6PeC2J/R2cYJgME0Dh7c8js4lQRMytV3MY9jbkO4vRb9Hup1UbUuysHJC+/O4SNElTfTXcJiQ84MFHrkP26xZId1fWXQZcajeqyDH5b2dfU6bk2P3/qvPyfV+k7L5DdB2ZmAaKTuiaLkGlec2zLzzvpSxtjy+7s/xtMwvSBlxUbQjkc9jrXNe6l767vuUFsN7xQFY3TxkzSK+S9wUHU24pdqwJ5YGrTM5SprbAZ0e6PfcSM2vQOo/XKvBs7hO3cvSNrn7B5QWdNgy58SRap2UIoKe2sJkOiE1rl3aEist7YkAZXguWW/o+cnvmFqnpN8CN/17TbueJlp96f6h353HEbd/cMjvit5MW5Og7s9riv436FYp3+K3Zf0bKI1u/6po/VAb3D7P2uv570kZ/RXRCgZ9bVsk7RtnOG1QknUn6Cb/jvktsWqJwBJm/m22sxpWYI1X60749j35oybt0bjGlitzv3t9fN17/fL4OnvQonwxrH+5u7uU1vjI2vi6DDq/zZ9lvWHQkTIyTdARKl1+0EPdOK+T2fuPr021HUCDwWAwGAyGGYN9ABoMBoPBYDDMGJ6MAp6gW9G2AOnQ5KP0ExTitBEukiJmpFHA2polzaoA8yE9kGbcH4JthaIOqPwUt/4k6OemUjie1OOnpoN1PSYsHU6HBvHuijWBt8iWBsOXZZs+Bgd5b8Bt4QMlEi/wVvxwXixdMvfApkRZk8RgJeB1Zcve6zEtTffoSBjPnpdn3RXKpnSfnzVaFGoCXf3zN7cpX/F9sLC5wFFGogJYH9yQaBrRIlNCflOonhio5975GuXLA/VafYepCK8BFAlQGNk2O9cPz4vdDdK+UUnZ5UAZUVVb6TzdcT4VnkSi8TgWJknRg9KiFuF6MrHePZl8ZSqo9chD2yPdNVBHz3sCmyqFadfQVInOtFZfqXT+E9iFPQVkdmUdaz+j5jFE4fBBKtJd4jXIW5C/J6jSzvG0d+k2RwIZ1mRO7r8gVObaV1he074odcxucRQnjFDSr8laVX2bJR+dK2CRBf2f2+by2utSj/I9TvNKssa3npd1cu7NPcp39AvPjq9L96WM3gpT4OX7QksffowtcjItGHsQMWn9S0p6hMMS2nq0wP2a2xSqe7DClLULHv832XYADQaDwWAwGGYM9gFoMBgMBoPBMGOYngJOC5Q9JU2B8MLkR08bvBypV015TksPpOXDMj086alpgxSKIe0kHBcBJ9qQKgkV9TgEujHt5FtS/VKQVt5E2vB0aA93Tk5VDct8+tQbyXsGm7KdP1pbpHwO8rkht1n43oPxdf+FC/LvDT5tioHNw4dCxUbnVimf15b7ms/wlv2gKP1cG8pJV7/Op8x654XqDjpC7cSalgbH++CQA5t7sdA00bzQCt11jhhSgJNkUUHKz92v87Mg0oi/yzRN66PSbsUb0g+RjoSClBP0g6fWl9wdOFmnKPbhRaa6TwRJkY+cY6oQ3kOvd7TGaeqV2Fxcn6aUyej5jqd2FZWZ5L4wITWJHp+mpTXTsSOCByfAEx0gNJ402tOU4Ggqj3Pj6chhjl6sja8L28oRIS9zt78I0T5u1LmQRxAl5BzTl92zsDbACeFYUY0ejOXlb8tJ176iSh0M+ZGK4OPD70kE5ffWeM2MgUYdFuQ6LHF5ta9LBI32i2uU1j57bnyd35d2G6zwWpirQ3QSOHFceHeT8uE8r7SZssX1tbcIDg4ZXgtLt0FGM5Df+PZz/Ns1ykrblO+p34lFji4yDWwH0GAwGAwGg2HGYB+ABoPBYDAYDDMG+wA0GAwGg8FgmDE8oQ3MlEfiU6xdJo7fJ+jUpnWun9DyTasBIWsCVQZqeCAtGrGFDdVR1yNKqIfKR476KXVPbQ9oQ3a4T7F+oH/WVi8pUVKmte152tgQa5ZAa+DWxSIgWhHdnKf1SxAZJKqxTsXH8Yv932ILEx/0dqMrZ+FZqp1yok2pvvGAkgYXRffXvCjWBPmSeq8QRWFy3XpuifIFfXCJ3+HxNSxLmT7oaArfvMX1XazJc1FjGfAYGixLu/lV1p6UviNRSPrXzrgkZLbETiKuyPuP3n6P8oVnpYxodYHTNlh/eCJIW/9o7kp/aNsr1ARO6JeTolPoRyWtBWm65hTLkjRdtpeVcUz1VdFoyAZGPctPemfdNkntq3WUo+m019NavaRaZ6XpDU8Jta/dH19HNdbKYVSgTFPa9+hFts4KnxEbLH/A7VR4ANE1YA3tr/KzUB+NETjQ2sU51g7SmuacC8ByJlqWfo4ynC+3I3YsedAQ+wccCaQP0YOKb7Nmr/2SaB1jGGtHF1lTPv+O6Blj1KwWeb0brIvur73CWsTKTSnj6Flpt7l36pSvtwqaaojq4imtPbWosu0pvrvlHhe2A2gwGAwGg8EwY7APQIPBYDAYDIYZw/QUMAX5VlYCRAmkWMJMGZSbqMc0exc8tt/XNApcp1nOIP2Qkg/hF9Rxa6Q6FN0Y49n3FLo5osDm+DBFh6TZEyRQx5P99ZPv+VHGnzJKwAeA/keeGV/nbnEkDNcbuOMQKcsBB3YUbqjGIaRlb0HEjOUa5cOIGcOa0JfDCo+h0aoc988s8tF/DKBT3BAapbPKVEQMTT8oyeDQlE12X+p09BzTNLm6dHp3Qejg4ZXnKF/tHaFSwq26VHVe0T51eVZvuUhp8RUIIn8gdjSDJc43XBLaIzyU8sJVZe0C9IvXYbuL/gWmwU8dSXPmMZxC0uyXpkEiheqccxmWFyRRtp6SVyDt7XkwPgcq8g3+TgQpUpbkgDmJmIweBe+ZQt9SG6ZEakqj3jl61HSSmg8aaMV08JEapc2/WR9fd8/I3A3bXNfSDySyUusjLNeI8rKWBbsi1wi6ys6pJ20/XEten4IjWZ9bZ/k3tHpbLE0Wv7Qxvt79pWcoX3tFxmXYBduvPlu4jHLYR8uUhr/XA1ivF97iCCcjsMHK7EMkkHM1yjeoyDuHXX7nwYK8Z2lT1vg4x/PLH4B8C4rI77L0aJQD+VKRy2hfYBufafDh+FU3GAwGg8FgMJwY7APQYDAYDAaDYcbwZJFAPEUPIC+ZcBLVuZ8QWYK23FN4TrwPyvNzijYDukCfRkPaA0+3afo2iX6ZONGXzR6bzznnPKRc0miKzHRdkRQxRP+dli+Jzn+s04inRHsEXWn74Vl1IvSunIIaXBb398xDFXgb2npY43HTX5ZIHrlNcLVf4tPCmQOgLPckX5Sbo3wB0BT6RFd3WcZNvwyyB9VfI6hib07SQo5x7sK2ZOyX1dgYSfk+dHPlPkc4wVOdA2jfzipTNuUb4lyPJ/Occ24Ip4KJUn/AJ3YbrwrVmylKn4Q1ppgyDyCaSJXTsrcf/+TbU8W0EoqJJKRKp6R5VT6ieqHf0iQvE5ISyJtWD3oWXmdVtAdcQ9UJ4bgHYw0oZm+Y4uAQp5TXBx55InLJ8dIb/dOStGZqTHuS+CTReLY2vs62FLWdlX5FaUi4y6dlu8/KOhm2uHF6SzLXeteERi5uMn+PFHAWImv05/l3cVSTv5EOdc7RuNn/uUvyHqpbM/Ce2SN5bmeJx3xpU+jmQZnT+mUpNL8HUTfO8Vgu35Q1rn1J1vXie7uUL1uEk8/zvD7hszOb0g+ddX5W6Y48awQnqbVEKYB28gbcX7kpo58hbAfQYDAYDAaDYcZgH4AGg8FgMBgMMwb7ADQYDAaDwWCYMTxRJJBUrRikTTirp0SWmNCpHXOPc451dGn6G9S5aVsE1JIk6GjS0vw0jU1aGuheyMXeKf3NQHQJE/rFFJ0OaSxT9ABT616wrXUEgTSriQ8Q6Nwe7rcoDaNEoI4ummO9hdcDXdp91qXFJdCvgdN6b577NehJX3bPiL1JrNqlOy/9FfS5DXs1yTsoyXXzMs+bOJT7SnelHq0LynIAtCO9eU7L70o9Fq7L+w9Karyiuzw49+f3WffTfkbc77V2KHPI1gU/RpxnvWXlel3SIDqJ12U7n7gkuppgg/Wc2p7nxJGmhU2zvUqZg0mRhSbWsWkjgSh9ND0rSduXY/1WDNFzUNc5sWZSJCgVnSNE/XaKPrIHYy2CNU1nTFsLUeyH7at+M5LWzMfS/J2SRVblvfr4Os4ofeiG6NS6H7kwvtaRc/pzoL1t699raY/sIej8tlhHiO3bvihrrV4LMVJRv6LOEcDfNbCwwTXIOeeaV2Td2X9exujZ32VdXh8ia+R/7weU1v6LHx1fZ/dkrcqqoELddbCWgeHQep5tZbJ1Ga+tdZ5raIVzCJFAMsqOp3tW0vpgK1PYYq1klAWbHTWHMpuqX6aA7QAaDAaDwWAwzBjsA9BgMBgMBoNhxvB0IoEkbZdPBOhOthyZtJb5H/95wk0+4ZtV0w34h7ZPSLJ30dR2PoE68bXlANLSyn6DAqDDEW5PudoDRRQ7sEjQkUXASmHC7mFKZ/yn0l8pQeU/SISHElnCazPVGBeEEkDn9ki5rjs8Za8iXGS2xdLF68rWfvl2k/L1F4UqLsIR/s0vLCbWfedFbrPSfWnvlV9+ML6OG+xq33oodezVpIwox+V1XgG7hwz3V9cXamZzDiiGbR6vxW1JQ6uGSM3D7AHQdJqaRJsloAtHc2yREO6I834MND32o3POeU3pcx2I3d9j9/4TQQq1m0gH6n+niBkqCds6Sa7ilP0Uzn21LniZ49dW5xxFWYnBHsnTawTUI8YoIbrvU2xgXEJkEG+o1l2kioEOjnU+lBRpay64TqSD3U9B+yJOyRKrc07WhTjkfui9IFRpcQskFer3pHxHaMPOGZbKFB5I2tFzYoPSvlyjfJkjmONZ6ZNcnfukB+tO6RFTm+01WZQHEFlIW2JlD6XMlT0ZG7uf5HUXqdf8L75KabUbENVjRdaksMvj6+A5qVP1njw3d8ByGIzclG1wGflNedYIIlLp/soCfZuD75POBfX7BNFUMBqTc5MWWdPAdgANBoPBYDAYZgz2AWgwGAwGg8EwY5iaAk6nb493tZ/I54Jj8z0VaHoE6Ft94jbp9NjEydmEE72epjbC5FN2Dk/PIW2qKdQ+bNODw33c5xORHp7o02VMe0I6ljLTon0QraJpb3c6tEcEAbrjqooEsiVULJ5ajBT16A+lbTKPDiktmhP6IQDqMSrwWPDhtOzuJ4R+aF7k+o6Api2d41NarTmhMx/uC8XS2+f6/qXP/fH4+rcfPD++Prg7T/mCR1Ler/zCtyjtwXptfB360nff/aNnKV95A04+16StfXWCOWzKGK0/x5T14neAYrkgfeT3FC19eUnKa6FzP1OWhV3po8H5JUrLPFARBU4CFBUpeZ6lncSniElqncGT/xS1SK9bGE0D6eCUqEI6CD2tm/BcTbcm3qORFtEI1018Vhgk5sO11usx9ZZEKTtHhzZZRqNOlca0ZCb36+RvGT7gdPZR8g9BlqLey4MTrNl9Wcf06e7BPEhZ7vJa2F+RMmpffzi+Hq7zutNfkDJKD4WW7KlIINkGyJw0BQrUbr8qY2hQ4raN4D1rN8QFovyIfycPnpVnN89xGaUNKX/xDTk9/OiLfLo305RRhLQv/s4451whAkcE5UzhdUGyVRGKvX2pSvn8GtDe8I79Ks+N4i05qjxcYMq+cckoYIPBYDAYDAbDT4B9ABoMBoPBYDDMGOwD0GAwGAwGg2HG8ESRQNIQp+nQUMOij9wn6Wq03g5A2hmtt0FdYp61CPQstGbJs8UEaXHQBqGkuHaso9KzkAUJRDvwm3yE20vQvUxo7wbJ+kCuU0okkCn1l14G2k1ZHcTR6fzfIcqCPmSO+zUKRZsSNkR7EdbblG8IeotAtWEEjvr951bH154arpufFC1m+YEkjpQ1y3OvvS/5MqxXK61LX14rbo+v//bXvkD5/l/f/qTUtyDzK1ziMTQ4lDp1Rtw23793bnz9ay99b3z9xgrrqjb+OennhX8q80FHMfFH8qzFb+5QWpwHbdpQyguPlG1PABE+borGKFDa1tGFdSnj9gaXsVhzJ4403d+TaJu1hRVo1jzU1KmIHqRzpmvW+XmDZJsq0hGjVlprqsHOh6KCKH01RS7KJtvP4Lo4YXWFUZdwDdaa5wjaWtvAxLBeg61W3Fc6wqTfnRRrl1Rt5wkC9WWDszVKC8DS5OiaWIkUdvg3DsWSQ6WVRguW5mtnxtc68k9uR9bXnY+Ltq1yn/tkWJD27dV4LHchKpIPxTcuUDZXeiTXey+LBq5yn9fxwg6sO23uryG85sFrot9e/m6H8uH22LAAmvLzrIGsX5F3Wfo+j5sArMpw/BY2WCvo39uUPxZq48tslefQYFl0md0VbsO5m1zmNLAdQIPBYDAYDIYZg30AGgwGg8FgMMwYpqaAU6ndhG30CToEy9BpEd43He2LNiWeDniOZUTKQR4tE0LYA9cO+ljfXLLNwqgi2+r9eUXTQPFRBra5FX2JQal9iEDhHfG2LlmzpLUv1kHROXEChUU2CC45UPpxf58Ugra0Tb/GbZg5gC18tJnIcn9lHu1LGRfYVgQpreyB9En7HB+5HxWk/KMr0hbPvXaP8v3lM2Lh8jff/LOUdmlR6vHld8COJcf9WHlLxpQPTMfRs6q/YSx/5e4VSvqFZ98bX69kJXrG//oTX6Z8//c//MXx9TAv76Up4AhsHEbzRUoL9sSeIkQKr8UUSwh0e3RxTe7f56grUVFokKDAFFYUnvz/YdOiR9CceUKrK68AHBWsSbRuOecijJ6CbakoYJwLOsKH34U1FBO0vARsYZAOnrB9SbO6QksbsoHhPhyB1RPam3gqn9dLqLtzLkb7jQ5ID3SfQJ0m7MISMBEx5JQigeBvUr+iaH9o3+o7YlsyqvLv07Ao/Zd7n+1NQpBOZW7Jujb8zEuUb1SWfNW7Mm5GBe6vfgXst9rcZt0lSavdlLTyA+7ZAFQ0EQy9+19Ua3xTyhvlub9yu1JmYU+edfCsijIEy2vtPYjooSzBajelUsMS90PjMyK9qb5dH1/rqCulLvwOwfwqvrdL+UZLQufn9nmONi/wOjwNbAfQYDAYDAaDYcZgH4AGg8FgMBgMMwb7ADQYDAaDwWCYMUwfCi4lZBiB9BApGhhdBmrKUqxfUHPioc2A0nZ4mWQLgtRQRgjQWMSoAVT1i3JSJx26BXUP/Yo8t7itdCPw/rlN0NuoKqH1g+u6RKDdQay1OJRxSv2KDo00TLGg+QAxmBd9VOm6sh8pgBXGfbEL6X+Sw515UEbu3h6lda5JOKDhspTXOKu1TnL5L/xzfzi+ngtZ5/ZKTnwL/v2Xf4fSvtm4PL5+b0/8Dqq3lGYTmr60JWNjUFZjrSaVyq9x//zBHdEELjwnutJ/8O2PU77auugD3Q8kjFt+n/WGFKLJY11R6aFoG4egWfH3jihflIU1BS2SlAY43Jb7RosVSiP7hBNC6vqH+VAPqLRypMtN0Qp6sO5E8xxyr78kOqJhMaUMqG/miMeFj5YzHRRYqXUBtcdkHaP01fgu2iKmKBor7G+tAcT1GW2ZfG1NA+EYJ6x0UCuObZ+6FmKa+j1x8p5poVBPEr1VGQ+5PbaYymxIyLCjj4qNUvEBW2JljuB34oA1gN2Pyfrkrb08vg66bO/y6GdlHJ77PSlD66bDjoyHQZHbLAOy3y1xvXJRntu6AGHcBi/Iu4Qh5+vtiB6u+D73JWr7dl6XeuS3eXwtvCttk7kvvxNhme1yhqCBDo64H7pL8h0yqsg6mdvlfO0LYp/TXZD6Vm/z78kINZsbHFo09nltnAa2A2gwGAwGg8EwY7APQIPBYDAYDIYZw/Q2MEh7KNrQC8FpHalBbRWCu7TaVmRKSoQA+Txl4UI0r7YqQOC2v7Y+ACoKXdd1JJAogw7n/E3dWQKbAXitlqI9wq4kBlWhSjIDRTfswzZ9mm0NWEZM7X6vgLYwHxbaI7sNXIGqE1pheGtC5WbqyVx568UV+rtwX7bVR7At3zqnolOADcx8RijV9ojp0L938Jnx9Z+u/oDS/v7Rp6S8srS1P+DxXwD6NYZhna1TNpcT1scdZucoLfalvl8qAyWuurH5jrjc58FVIMryfA27QCs2mRJqvwSU0/fvj697z5+hfL15WTdK70sbdi8tUL7CO0Ln+yq6BFmmnAKe2A4J1y5NbaL0BNaa3gpTar0FaYs22Ghoq5dsA9durkbYBAoQqfcmU4UEtNXSchqklHUa2Ft4YO8SZZWFF1QDLTcibWED626g1lOUG6AcaCJ6ElrTpFnCkL2Z+1DA70NUoJuPKK330vnxdfmm/GZ0zjNN6KEz22vPqAeALAnoxu3P8PxcfFv6tXFZaOlYzY3WmrTh3J/hiD5F+K3J9mQ8vLDIEo+PfkEiK/1fv/LL4+uoo35Pz8j4jR4p6cScjKPiBvS/dtVqyz/gmub3eWzkHtTH16MFnqNzX38gz70ivzV7L7LlzPK35XctysGaptow98YN+UPLSlb4PaeB7QAaDAaDwWAwzBjsA9BgMBgMBoNhxjA1BYy0IVK+E2l0CuwxaEOkRJCKyLD7PZ5G44gevC+PAct1Grrak0u+Pn2MNADWaajeC6C3kam4nDwr6PLW7qAkf2eP4HRkjtvah0gIsYqsQNQ50L46IgHS+RPULgDvm4gSMuVJyKcNDCLvVNvQf2dK0k7ekOs+KqoxBeicFYok7EjbZJo8VSLoy793Q6jc/8W1r1O+IljX/2+v/xql7ezJszJ1kAAoxh6Dr/sDeW53nsdrdxEizSjWe7gENM13JAB6qJqiuCllhO3kPm4vS311cPjMobzA0acvjq9L6gQiUinBnlBMuT5TytFybXw9LHOFMZrIaUDPA6KEcb2bcD2ANC15QcoSonoMqjwG2ytSRmcZEhTzGm9Lvmwz+dS/1xN6NNbuAH1MSx4X6Myg1xaMTkHyGjU/8XS4jiaB8CEaDdKhzjF17h0JvaalQlO7JXwIMZiTtvausbxiWII2zAk1WPz6LS5kVSJQdM8wPYxykwjWTIx84ZxzgzK4YIDrRayGdQMjF3WYAr22KI4OI4gKdtRniUcvkndevShuA4MRj5ODeyJl8Yrcr3mIBNK8KGNv7Y8536ACJ47B9SBS3xP+QKRC4SH/JjdfOzu+HkFkpfX/4SHl658TWh2jLIX7HAms9YXnx9eFTX4WyaOmhO0AGgwGg8FgMMwY7APQYDAYDAaDYcZgH4AGg8FgMBgMM4YniwQypW5swgZm6oelWJNU4Zg56k1yybouFyibBdTfgDXBhFYQLQNQH6KOX4dtyZdtcNowD2WCzUDAMgrnoTMLONzHqu6obfS07hHsGdL6S0clSMo3dZSQE4SHNhN3WEfhwPplsC66jMwjdrj3wTIit8e6j+Z50ZwEe/As1TTFR1JGoyBj8m8PP0f5Bn2ISLDDdhd+X/p28QegD+1xnXAMtJalvOKO6tdI+nz+Pe679groheC2QYXH19IPZGD2a/KsXoXH2tI/fGt8PXr5MqWhBi2/I+V5StvXvig+M3N3ZQ75R/z+0ZxYK4TK0sfb2HYnjVTrl4S1ywtS/q+ty4N5HRUgkkCG8/VliLtBFSybMtx+mQbowZSdD60vuMYNua9i/NtLuMc5F4N+1ctqrThGEIHxqd5f24f8GJF6/xFEYAp6aq2KcT5BpQbJEYzIBkZ3F6yNqbrPE0TpB2KlMlqtUVq2Lu/ZXZbfxsYXrnEZYL+EmmfnnDu6JDq91hpYNm1qKx25RC07jk/nnCs8kHH47/8SR0VaC+vj618sSD1+vTFP+RYC0bndXhL94jDi9elLO/LwUU/1D1r/jOBajeXOooyvDEQx0XOoeV7W9VLIadmGtNVwKOWN5pXeEiyNynfkHQfK2gUjiPgt9RGRcjYhCbYDaDAYDAaDwTBjsA9Ag8FgMBgMhhnD9DYwAG0rQlQhWsJ46sg9Wq6oMuhvtAjQNALQt3EBHPOVHcSooO7DIsB2wG/CFvCAaQ8KiI51VxYuwZHQUsUNFZQ8ku3hbAPqrj69My1oN7RF0Ib0SD9o2xpKQ5qG801EBvlx2douBoPZa5rjlOhh/xCOxS/UKC3JxKF3gWmEoC39HOXVWAZ6oLcAW/YqWAHi8rPiVn/n7XVKK92X8vtVruGwBGMqpTnrV2Us5+pyD1ouOOfc0rckFMjOJ/mdPRjaATA4+feZNmity7NCoKIzbVXBKxJpAAOUO+dc7oFQ7oMVoTp6q+ySj1SHAwnHYI2jmATfvzm+jl/gaAXxBW7vE8eUEXG0xQhKGZyv5h2sf8MiyFz0sotqmwFYorRV1BZw39H96HdhYADNG+u1EOlRtOJKi9qkI/WApAblK95QRVbKQmSlKkhZVFMHfWnTYYnHYNAB2xqUvKj+QjlMmrQpzfbqtCyxmq+J9QvKhpxzzh/K37k9aHcV4SSC383WGV7kijvSz/4Afp/U+x6BvKSzJmloe+acc89+TKJ45D2mkf/xwUfH19cy/3R8fUb9jH8mJ330f6qvSh26XPdwR26cu0lJ7uAleZfMEf5Ocj5qw32YD/H0n02dJVnXUMKQ21O/yfD7GoG0IbPDNjA4D0dlfudBNUUGlwDbATQYDAaDwWCYMdgHoMFgMBgMBsOMYeq9TKIDw5TvRthin6A90ugCehjcpyjguCDbnqOKnFJC2sA55/pz8moYPcE55wI40YMNoClgD08BIz2g3+tQqKyMSguAYkmjpfnUGkR+UCcn9bMJ6HI/AJo34m1/dMOn032Pcbpt6r58ysCT31GJ3eT7i/J34V2hZUfrHLw82BSqdHBhidLCzvFUR+V9Hl+NC9I2739b3N7zDW6zzoqUUdjiNAxE3pQi3Jkv8anlxgWhRPdfhPfocZ38QW18Xd7gcTOAyABIbeS3+SQZjr3usrRn8S7XCTEs8FgI5+V0r9+TemRvcMD6aFX6ZbQIEVj2mPaIr0k0kWBH1eOU6LcxtBQCKUaYP6mSFzXPcNxlGjKPwzlervM7ki9sJQe1L+zCetdWibDmxaMUHQKuf9jmehnAU7YBU1R4EjpOcCJwjqlepLmHeW6nUQ5ob7VMZrFN/WRJUdxTJykTgGvhaVG+GvkdkR75HaZU+4syB8MDiRjhPdyifMMXZW6V73Nkic4aRFMaIS3P606+LmNj4S1J2/4k1/edG7LI/e34Zyntf35WIij9J9s/P76+lN+jfP/dvkQxWisdja8zActLDuZkzRwWeKyV70hfDuCQ7dYn+b1K94FuhahjC29zxI36s/Jsv8fzK+zKAC7clPs6Z/h0b/F9eZf+ipTXulyjfEgj6++a8psb7nFhO4AGg8FgMBgMMwb7ADQYDAaDwWCYMdgHoMFgMBgMBsOMYfpIICFoJ6a0AEFn9QmkaMi8DDxLlRFnpcqoPWqvsbajsyTftkFXHZEHuUQZIjrklLYjQA1PGyIQ9JUTOlrENNqUhF/YHugBtW0NZvQGqLfhtqZIIF2lX4kSdDoTdjEJ/ac1fynG4mmWCR8kItB9ekpvkd8QjcVoTWxQ/EPuk/5liRjid5TuE9oNdXPFLc7XuCTjLb8j7Vba5LbNH4Cmbp77vAA2C0cXpbwbf4Vd4jMgexsVpfzKXaV7rYJmJaesWQ6lHuhkP5jjeZO50ZBrsHcZLLPGJmjJHMg0VYSPM2Lrkd8RDdvo/ArXd050NahL9JStzAAsPkoHDUqLy2whcuJIi1qEa5eex6ip1nMJ7VJ6cp3f1/ZNYDEBTRYobVD2UPons8NzAdc10gNrCxey8IJ31mtJyrqeFE0kUmN1UAbrpDKM1SqvTwEsyahRc865TEPaJmhBu+m2TtA569+uGPs55vX/tPTQCG0JkrsPOme0VZq/RPkGFWl7bUUVgmVQ2JR3bpwrUr7WGSlj/ob0cekZnquI994+R3/fXBRLlz94cHV87Z/nsfw7t5+XOoVSv95NDjtSPJD+a69xGZnG8X2++k1ugExLxgr+FkQZpYHENX6F+2GYA0una1LH6tsHnG+e2/THKN1hzXNvVbSD+Xc4ElbzYxeOLSMNtgNoMBgMBoPBMGOwD0CDwWAwGAyGGcP0NjBDoCX0lncCDaJtYHD7fYIeRlsAoIB1YPAoK8/uLEu+xnmuQ29RtnOjPNcjPEK+FbfA1TY6uJ/7YJHg6aDLKXSo1wX6ASwIPE2doNM+2uyodkIn91iXgREFAnhnFfkj0fpF0yHYz+odT4v2QMf7qMzO5xRBBfNV2C6muyj3hS1Fyz4QGhm37NOQPYI2THPp6Sgq4kjmVGkbLDJU26JVQdCTtMPnVP9D8StvcFJ7Re4rbYDNUI/L6J8Ruih3TywYoipTFIfPSz6MYuOcc4UtkSa012VOZZq83GB/oV1S+HCf8mVhnMdVpqK9gyN3qtByGOi7qSMfpdHIXRkjQZPLyGP0hwAjGnGdwh2h4mg9cs7FHbH+SLVEgXUipuUpReajbaXyMg9RyjIo87jozQF9J8Eu3LDE75U9AJmPqnqcZFWW9tvlp1DbSfecIlBCUfjWbUo7+vlr4+vyPaH9NX2Z+01ZKOLPfoTSwvcejK/rvyjlacudxR8CJQ7Doft2jfKNCjIe/CGPm9+4//L4ut2WNeMfv/FRyud3YZ1cl/eiiB6O7YMqd7m+XXGScSE433QW1DcE2N2g1Y2meQubokUY5ZX0JsZ5A7IHbQkHcyX7UGjfqMoSl1FB6tS/ylGQcgfHR/hKw4djJBsMBoPBYDAYTgz2AWgwGAwGg8EwY5g+qnFaBAqgQeh0W/YxghMjXYAUZZ7LQAoYTzP257h+hStCDX18/T6lfWtDAtnv1YBf83hb1oMicSt3IhIIngpWtAcGdkcaNc6rLWCgc4jK1EHZU2j0OMZoJdOd1CbouqdR2ylRQj5I+Dt1qYOmA+EEdlwRyhJPUjrnXLgsaYXv3KO0g1+6Mr7OHcH7q/8qFTekrYoQaeHoAlNMWaBHixtdSuvXZGwXHwoXUbrN9d17XU40I/22+k3Ot/VJoSZ8JVNYeBtOe0LfdZd5flXe3Blfd67JaelRjhug9qbQtPVXOdJK6brMvbAqfEvhXp3y9daFYj+6LH2ycJejFURrUoY+Pe/lUqLrfEDASBAT8yBpzkzMVShjoKgblIrA2uK3uQ9oncDy2syHIu2LlG9afSfkO+iIkEb7Io2qom6gzGdYk/7uV7lPO8uwrl+UcRtklFwhFko5e8htg/OE1mv9vrhOogwn5fdO9/lpRQbBqC6Dly9SGp6qdzhOFDUe/ezr4+s4UHKrZ4R/x99ClJDoZ9UvS58XtpMjt7TPcF/uPhJJiZeT8ovv8ydK53lYx27J+p/h4BxuCIqVo8ucloFAQz7cF2t1AEzL3ZelHivf5XU32JcCDz+xTGlFdHo4L22z+iWOcNJ5WU5BI8Vc+eb7XF5b1szG8/OUhhHOpoXtABoMBoPBYDDMGOwD0GAwGAwGg2HGYB+ABoPBYDAYDDOGx4gEAln1MXjQUVDEEF0GakdSNCZkb5KiNxmAS/xwlXUvf+bS2+Prf7HGnhjv1uT49H9R+Pz4evtwlfJlWvLOQU94+VBbBIClgdbRJTrND7mMGN+zB+IDrR0CHY2XEpEkHqElSlpID7SV+fDrXjDCh44EEi9UIE20F4PVOcpXfGdzfN176Tylle+LxqQHdjHDPI/5yn2IrtCQ6/YSW86U7ogFR2+VNYv4368ItDkHr7C2A7UpaHcRZZWlw4H0SeM8C1pKj6CMtoyvoMtLQFyUcd6vSBlBj/u7tyZtXbndorTRouhqMw0Zo92zbKuDkQdKj6RO2t4gsyNCHe8BO+i7hZo7cdCcSbFwgbmqNWVe2hqH8xXTlB7Y7ybYPuioI4NkjXISJvXFx0cWot8FDWW5EoOeu7Mu82T/Bc43ekHG06cviAYqclynb/SekbIfsDUH2TGhHlbXaZAQ/SRlzTyttU+jtwDRiLb59690W3S4GFmqeaVM+WgO3lFCugT4ymYI9cEBDMlMi9upuyj956ufrsoN0L0OZUxpq6vqt3h9HT+ryc8qbcrf7WWeo2jbVbkvFX70eR5D539HxqEXgx2L6v5oTgSHgXqvENa/la+JvUvrBY6KVLoumsABaKMbn+LoHuW3JV/lep3SDl/i341pYDuABoPBYDAYDDMG+wA0GAwGg8FgmDFMbwODUBYjbIsAaYoeiWHvdNpoIp62QQEQLdXj8lYzsgX+SWUV8ZHsxvj68Py3x9f/6f1fpnytdbkv7IBlh6IekYrE7fYfVdI7Ni3WET6QtkGKRb9/t3dsPucc0zsYPWHE/YXB3DHqhOcUpYru/5oSOSU3/GBTKMDWq2cprXhjd3zduyDWJJlDtl9BGihzwLYY/pFYyXRW18bXhR3e20faA6mYbEPRHutCuWjaP791vIP83B2mc7qLUn7xIdggKEuHuTtyPSxwWvM8WmZIeYMS5+u8Whtfo71DtqHGPFCCgypbyTTPwVwBG4T8ZpvyoUVSuFUfX4+WmCruXJI6FbSkQs+Bk8CUYz/VLiUFGKkH10kdxUM9LDkNbbW0lKOfQEWrdqX1Oi1KRk5oNK/E0WP6iyKBaK5Leb2rPD//9Ze/Nr7+l6rfHV9/tcN+Ht8tnoMKMn1HNCVKY7pqLUiye0mROU3gSSy3ngKyh9Kvh9e4rau34XcHLMaKG7y2+P3k3y4PpEjZIyhfjbXWqvRl5YHUafNT/Ls7d0vaSa9P7VWp4/x1oGjvcL4hMLHlh1KejrL06PNSxzI7qbjDZ+V6UJJxM3eD+3HvFXnn8iOIBLKoIzVJvkGR22ZQhTbwJF9+g9fCg4+JfUzlnvwmFR4p2yYYr81rLG0q32UpzjSwHUCDwWAwGAyGGYN9ABoMBoPBYDDMGKamgIkCTN0eh+3RtGgRilLEQOSedpDH0iFofL4uz81v8qv8fx68BtXgrd3lUE5m3oXI0Nkqb4+PgDoeFuRdeotMN4QteZegzVQh0lx+X+rud5JP8BLFoikKDDavXf0BRNkEqq2BEkY6OFJ9gmXo046nFQlkdAaiQoTKuR6if2T+6C1JeOUa5etekjLCJtNq8aKcbi3dl236/jz3OUYvqECwdW+ZT6n1KxC8WwW9L+aljMJD2b6PCpwvbEFfwis3LnCdcofSr4OScuHPyN9hF4KS6zaERy9+Q6KCbH+BT60h1a3pYaRj8L00PDidOlxPPt2d35DTiZ0LTHvkNx+f9niaSDsdTydn1clRmlv6hDDMzxhO+nuhks3gCVysh3YHwHx6jiel6ffCNSMPNG9GrdWQNprnU++dNUlrXpB3/uzV25Tvr9a+N75eCkRC8WafabMwlPr6ih0PukBtQntMEL5PQtNryveU5DDtVZFaFHZZKkRRhh7A/FnnPilB5J/2S3z6Pv9Q7ss/kt9MHY0nykiZ7RUZT6tv8DjsLCZ/blQgIFPjgrRn9ojz4Snjyl2h87c/xhR4CYJ/DSqU5PI7cBoZZC6xGvOdJfl7+ZtwInjIz2qty3uVNrkfhkVpq/6c5MvvctuUNuTFohy0b47bOtxNlhv4vWS5XOI9j32HwWAwGAwGg+FPNOwD0GAwGAwGg2HGYB+ABoPBYDAYDDOG6W1gQOegLVziYQIvra1DtPVLEtC2oMPH9v0j4NH3QOfwiL9lN98RzdJ/1f0MpS2Vhc9vQISPwVaB8oUgGIlBHqCjQmSOpL5RjpsUoy6Q3kRrT0AHhBogcrF3ysZAO9JjhAJoQ20DQ7eQHlD1K5Y/Yf1zOv93GJZFc1T66nVKi65KVA/vOYkS4O+ykCTKiUXMoMY6uuyO6CqDlmhCw6xqG9DOtc/IuMnvsRjJG8l4KCjdB2pOGldF6xT0Vb/CUGmdFY2hdp3vLEkdh8owP1+XMrc/KvlKD10iGi8tja9zh1ynYQ6i8Kj5UL0peqHoexKRp/8rH6d82d/+1vjaf/n58bXXZS2uq0v/FdRa0z2jBD4ngKn1r2iPFWjddILm1zmeaxFYR0XquX0Za6jli1V5aEcTa72aD/UI0LJCaX4xCbWIeZ4/UUXmQneFtVKNszA+l6XuV0o7lG+AVheRrHd/3HyN8nUeypwpH/H4DFBjjZrItAgfcdp6B2mnpPnTiKBPUJPsHGt+My1ZDAqPONpH65Uz4+tsXa1dG9vyx6qsBTuf4ogTK1+R/itUpf+PrrDeEKVztVvcvmhpE8M4XP0yj42dz4pdCum3fR5rQwx4opbT3gL+A8wNnzOufFfGze7HxZoqv891X3wTIhX1eFEeLEq9RhC5SUdxiuHP4i2xOtM2cKOHYmFXKvIi33iO9dHT4MMxkg0Gg8FgMBgMJwb7ADQYDAaDwWCYMUxNASPtoaNCeCHsRae5ouM2epBMo6D1gVPBxr2WUHSZfaGAaze5vKAvaa1t3rK+X61JeVDdQpPLyB1IfUOIOpJpTX8UG4/Mk/VLL8XVH2nfoTraja72Oi3JoT+NskoLbI59+SGhPXJ3JRj2CChf55zz78r2uKtBNAllsxHuAEWZ5W3zGI7dxzc35Vlnn6V8/gBsUA6EpmpeYBlBri59Wb/KdFnlvvRfe1meq6OJIAWc35fyenPcr/svy31Bj9Pqn5Xxlrkn9Wivc77KHSkDLWzmbrAFhw9RAyJlCzGsgk3IF14fXxfuHFC+6BOvyB8wNzw1JodXIeJL2ng9BcTa3iVhrum5SvYradIYlIroZ6FdVnS8TYtzjtaTyQhMHMXl2Oc65xzQvnFe7tGWIEh59eZVGrD1+YrQ/KOY15bfbV8aX9/qrY6v//t3XqN8lVsgZdARLo7kdyIGqjzWkZXgt4yoct1OEURnSbH+OUksflm8TkZr/BvXXZF1KHdvf3zdubpE+XJ7snZ56jU2/pLIMpa/K/N//l2WZe1/XMosbsk81lExgh5eawpY+mjxTSmj/rqqb0Pu2/mYrN2lDfXbBxKlITPRbv6Hknf3VclXvsf58jvynmEboj1tsKTo8CNSx6DP9chvyUsPwAYsW2eqGKNEDZaFvz66zL8nhR2hwPU6mTswGxiDwWAwGAwGw0+AfQAaDAaDwWAwzBieSiQQTQlLtuld1uOErXh9CjgG2sPfFyov12FK1R8IBZhtMM2B0Q+QffBH6iQZbOf6SAEf6mclB9RGeF2guTQVQSdugeZNOcE7QflCG6ZFIZi2v5Dan7jnlAKgjx4JLesXmOryIBB977xQIrk7u5yvAa7uUZXSgn1J63xOKBDFUrnWKpxGrwPNP+S2xqD01Ts8bg6vgIThNtAeVzi6Am71d+fluUevMe2V2ZDyPvuLb1Hal98BChu6uXuGqYhRVso/+wdwCu4jfMouA4xw7V0+Wej3IerIgWTsXF6gfLktiLSygjwNcza5TZnng0VO03P2JEBr1bTOBnrNxFP/OtoPzleUw+R4vCOt7GVhjdNrBq6n+jQypvnJ+wExzLUY5DvDOaaoMNpBv6yi0RRAXtCU+n55kyP1fNnJ3xs7QvPl3+FnVe9LP2T3+HfCa8rYorVLtzWA1lq1vpEE6kMiQ+hfEacLb8D1Ld49HF8PV3iNQ2CkqnCzTmnrvyXz+ugj8qywzc/qV6Vtyo9QKsXtVNzuwz3q0wPatH0OThJf4jG58h0pY/95mXu59/hZZ/+HrfF184VFSis+kDW+tSLjS6/du68JFdu4IP9+/kvcntW36/Ksaywp8iFyWeGRXNefZ/eChTfktHM0J2tt/oB/dzNNcBxRJ4n7telNXcb1e+w7DAaDwWAwGAx/omEfgAaDwWAwGAwzBvsANBgMBoPBYJgxPD5p7NzU+q9Yyca8UL43JyxMUEtDGjhlOROD4z1EDNA6mux90c6Eh6xfinOisYogwkOsJIse6It8OKatdX7a/ZuAkTb609nAxGlpaGmgrSWwDVMc7xP1LNrqJa2fT8sW5lXQstVblIQ6pcw+2ECAdZBzzrma6C+CI27rCJzsC7fAcmaxTPlQL5K/L3qb9uUa5UNNFEaMcc65TFPK2PykjMlQVxdc8x/9C1LfbJb7+Pq/+l+Or7/XY33g3zr7W+PrL3z93xhfX6qxpcHBW2K5UgeN4vL3uK37NUnT9hEO5kf7omhiwg7XtwdWFTjXsD2dc240L/M3s8f1GJWV5clJAMb+hDaWIibBv+u5hJF0PE4jjSFauug1E61kBsnWWawBVBFttCbwx/+eU7rpsvwdgVXSKMflJemrnXMu0wDt4KGM9436CuULwY6rsiPXc3f4/QsbovML9nkcx2B9Q7ZiSjcdp2gCKd+HRPeHiOD3NKesSfC3ZnBONGuRsl+L8tJ/gzNsJRNuS5mlh7IoDcqsUV77CtjMnJO1Nb+nfhehCTNNnjf4O1zYlLWrO8+6z2FR3vnSPxCd31Ctz9ufB81il/uu/Zq0RxeGnrdJ2VxpW8ZKQX4KnK+sXkYVmaPlW7x2oU3SzsfkuXO3+Xfn4GNi7zL/hrwXv71zo7zM7dwDflbYKrrHhe0AGgwGg8FgMMwY7APQYDAYDAaDYcYwPQWcRvklRYzQAbWntU+AbfqJLfo+1gO39hUtmwG7GGWLgBSwn4EmUPnQqgXd772OClaP9gkT9T2efph4L2V3M843Yb+SZmMAeaekLFIjvDyGjc9JwXvzxvg6fu4ZTgObnSgn/Tr4yAXKF7akX4OGiiBwKP0QVWVLXUe7KLwtUUfiiuSLVQQFtHDpLDN1kumgZYL8e36P++7hL8h13Jb3+s8/+3cp352B2DasqumFLMhff/l3x9d/5+7nKF/rrGSsXZd/b5/hwOPoOu/1FTUJbVW8Wx9fR0WmFbM7cl/rslDFwwW2eglvS1t7qn2DgbL5P2mkrIu03j3OXEIJDMhctE0Llhj7MrY8vWakSUP8421gYkXtkuwFpTzqvTBCTqiWNH9X0nL7GHWD8xVg/OcgYkJui+l/vwEyj6aSg6TQvklIssdyLn2dPC05zME1mU8r+zw/vYKk5b///vi68TleM0vvbo+vu5c56ka8ClZqD4Tm9ZbZ6mTrc2LvVNqWthlleGyUHsiA6C2xdKP0vTvj6+jC+vi68j5/ohQeiCWUg9/uw6vapgoiNTW4/2ubMm5KW0Kylm5xpKJRRdq0Py/17c/xOo6UcOOSjtwh47D6vqx3WubiHKx/YNsTHPHvUwhrbe8s98Oo8Pjj0HYADQaDwWAwGGYM9gFoMBgMBoPBMGOYngJOonkV+ISpn5g2cSoOzdpTaGQ67QbUBlElzjmHkTYCdaq2D3RJivs9UjGeLn+Ke5xTJ3Xx9GBXOddjIHJ92g/LQ/ohjepJOcGLJ9qQivd8RZVjpAF9svCU4J0TesBt7lFadEECxwc3Hoyv/QtrlM8/gigBRw1Ki9fkNJa/K9v0mSbTl+jC36/AqXJFe+T3ZeyNMlxG0JH2Lj+U+w4vqzGJ3QJH1f+Xf/SvUrZ/8vn/2/j60Ygpoc1hbXz9t773K1L0Q6YsskdSfmlD5lqsTg8OyjJuhkV2tS+9B3QRnMAernI+HFF4otO/t0X5okvSf36L56GODPJhgjftfNSRO/BvWDO1bAZXGlp31Vyl+4ZqzUAJDKxBfodPcEYFkM30pYywo06VQvSg4g6vY0gXI1Wsg9pnd2TM+F2ZP15bRYVqQTgavRYmREWKVQQmbLe0aB9P7JbwAWLxLWmnxjWeW3gC11uQOV79Hs+t5kuyZvbm+L0wqkcL8g0V1VjakrYubAHNO880b2dN1qT2svo2+PQVKeOBSFmK7+1Qvtbzsu72ajKuI2Zl3fzbsq4H+xypqHNN1vjCpoyhYY1pZHQWyRxBVKTXOF/1royp+S/dprStf17eK4ThmtvjdTe3K305KsJcayjXA6DfMw3+rmme45PQ08B2AA0Gg8FgMBhmDPYBaDAYDAaDwTBjsA9Ag8FgMBgMhhnDkwm7In0MPkE7MaGNCI7Pp4BaNK09I/sU1KhpfQxqQpQuD20S4jQ7mmmtG7A8redJAEb0cM6xfg/tYnR5KXVCfcvUtgXQRxN94j2GdcUpIDq3TH/7N8TuoPfRq+PrjDpKjxFDXJvDbqBVid+D6AfzrK/IgPN+eCjlaRuYOCNtnd/n/2+hji5Xlz5aeIf7YXBPymxclHvaV3hs/JUf/pXx9Xye3+vWprRVvCP1XX2DsrkiaHhQs9VbUHYM4Naf2eIoBKN50eVFy9JumTpruPwD0F/C+I9WFylf8Ei0np2XzlBa/l7dnThSNF+4DsVD0NFN6KantcRC7Zl6Lt43SNENo+Y3y2IptLpC7WEccp2w9jHYwKAe0Dnngiasa0pfjZGW/B6sVV3WG2IUixjmJ1m7OMfrrlpP6XdiSvsx/s14jChIp2QD01mVeYyaSuecG+X9Y9NaL/CamWmCJVaf3yP7oD6+9sASpvBQRU+CKB7BgWjWirc2KN/gOYkylD3ifsjugVYYImuE6rcbbaXyZdA5K6ufQQ0sXBZZb4dRhwZVeVbuOzcp371/86Xx9fnflTVu7cu7lK/xvNjgxOtspTN/XdbJ3F25r/kK69JzoBUflGWt9dY5OktvQeobdPmd9RiYBrYDaDAYDAaDwTBjsA9Ag8FgMBgMhhnDY9jApFC2SHvgNvpjbI0nHsFPoVSJYgkVtUERPhQFCrRy3JMt2gmrkxhpVKiHdpZPs5JJcJfXEQ0So6RoS5go+VnUDwOwT1D2IzFR1sn9ldivuo4niOj+o/G175/jRKhTblPoRa/R5nxAb/Ve5DJy70lE8N6zsk2fhfKcc675otCU5T++O74ePn+W8iEl1qvx+Cq/L/WKgCpurbLNwAgYaw+6IbPFY77zrtA7ih1w1ZbMqfkbUqfmGR4b7VX5e+6H9fF1dpuyUZBzPf6DO9KGPtC5ozkVraAv1AzaxXg7+5QvWpMy/IGK1nPEFg8nDjVnkuZTaiSQKelGHT2IpCxesl0M0s1xW9mglGCsgUWMp9c4jH6EUZG0XUrKexLdjPcNmNolGyy41hYuFDFF/z5NGQkpMfqHXgvTJDWnBB+ozEyD64SUKlK0vSWeg0jhazo/LmEkDOnzzDavhcPFmpQBdL6XXaB8KB1orauoSIfH26yhZZdzzrmerF37nxK6tfyIxxBGjWlerlLaoCR9WX4g5UVXz1O+2i2ZA8OKvH/vvIpUBHZeSD0751zmQPoBad/sAdPo3SUpv/hA6h5scnSSvZcvjq/nbnMZ899my5xpYDuABoPBYDAYDDMG+wA0GAwGg8FgmDHYB6DBYDAYDAbDjGF6DWCaJQjpJdKO0qccwU+0j0m2d/FA9+cFKVocrQdJslyZMgTbhH4P7Qm0BgafjWGHdHtCvjg6PnzcTwJpIv1k/R61L4a7U+G+uE+U1ue0dDCvPju+HOR5+GZBHxKBRq1/dYXy4TH70nUVTm5R9CJ+F8Pu8Vgu3QEdzJIc1ScbDMdaueJmcjjBGMZv7T3WvWBIou6yaEyikPurX/aPvcc55+beE13JoCaiQq3hqn1HxH7RnOjD/EOukw/2Ee3nuH2zc6LtQ7uPsM7WNEPIRz2Z5xBSXhssZ7TW6zRCFKaEqkzSzcZ6uqToA8m2JTOlFRPq4XpqnOFao/XKTdBQ4rqo1ycMGYnvpbWCaVUcJcwntZYkrsPqWdNabvFNTxa27cOi+0NkjuA3Sc2L3pLMreyB2C+hPYxzzvkdsIHZYHuTeF7WQlwn4gLrhjEtykNYzALPzRDWxsp9rm+Uk7wh2EWNFjnEXRv0d8VtqTtq/pxzrnFV6l6+x2kOtJP9ZWknrINzzhV2pL6Hz8iatPA2l9efk/aoX+W1q3oXfvOhnTLvvE/5vOdEf+gNZYwe/OwFyrf6ew/luedYY1l/nS1+poHtABoMBoPBYDDMGOwD0GAwGAwGg2HG8FT4k0QrkTTH/DRbBA+OiGuKBe+DtEgdYad82qqh0zk+bdooHvqzOYWyJpBtQ8q3d0p0jjQ7Ao5CAE77OpoK3oZRXDT14qe8S4ot0AeJYOdQrhVNFc3B8XxIy91kD5NsmZ3hEZ2zQjkUb4kdyXCZqYhwF6izXckXPc9b9sOCtKE/5DbLbNTH1/GKUBbBPlMM7auy1V+8J470fpMja3SfAcuVrLJmOZQx31sUGrn2Lls6dJ+RZ+XvgB2Log4HZ4T2zu0z5ej1YRzBOIkKbP0wKsq4zDyCOamtRXC+FhTNcRrjMGVdm9ZWhItLnuNJNlLH3Te+P0hZWzTdGsEch/VvQuYSg7QhrXy8J2U99dLWHZTlYP/q98V+0JGg0DIG8+l+SEp7nEggT0gr/7SIQQKiq5B/vz6+bl9hqpAArxKtcj6vI31evCPrLllAOV5rYl/o0M4yz/f5b4qlyaCqov1Af7WQvr1xSPlyeyJzyj6U8qIi269U3xJpT/MFfq/K97fG1yHIiPxhcj+u/Obt8fXuFy9TWhkio5Q3eCxn/+DN8fXwcy+Pr+Nzq5RvWJa2CtryjvldtrdBShyteZxzLr+nIuVMAdsBNBgMBoPBYJgx2AegwWAwGAwGw4zhySKB6BNiCadKJ4pICcrNdAbkSzkhl4q07Xx0108LFI7PxlNQypGe7kujKVL+nU7+pdDj9P6a2o6O76PUE2xp/RrBfZoOPi3aA4LZN19gGiG3J1vx2QdAX+oT4jkpI37nFqUVgX4aLZTH162zTDHUgL5tfubq+Lr8wy3K563Oja/9jop4ANQxBj2PKkxRF+/Is7pnhR7Jd7k8PGVWfP+I0mI44VZ4KLTvYJGjjhTelgDuUU3oBv+AywsgIkv06lVK8zfhZDVECYjyPL4yf/B9qV9N2mnwEtPoIbjpe+qdh+d4DHyo8Bgn+BHTrgVJczCO9TzGk/6avsSoSyBR0YVOu56kuUXgGE9zaUi8P2XNSSkjLaJRYvlTSnROE601WcdKj9h9YPsLcjI/V5f61r75iPLFeOJ+j6NOuJqsNd1zIvnwlJSlcFvWscPXRKIR9DjfYE3meF9FRerWhM5c/K6sNRg9xDnnYnCqaL4o7+iN+Fmlt2Qd85TCoHcRpDJ5GRuROnFfeldOReOJ6OoddjNon5HfBk3Ddn/pI+ProA+StVzyp1cEtHT+oVrHs5JW/u5D99PCdgANBoPBYDAYZgz2AWgwGAwGg8EwY7APQIPBYDAYDIYZw9OJBJKQL03nN62zunbQn9DpJd6XpvUAnj5FKxgPEmwWtC5nWsuAp6wdSdUKpsl0EuxiJpBmA3NagPFVfKS1GOB+f1OsSYYXOFIFauVGn3yR0mKIXOGBjUXldpPyoT6w9JV3JaHI+r1gX6aY11fH9BdFVxOV5L5Rid3kg7fEgiCsgWZP6W2DTnJfokM/alv9Hg+U7nNr4+v8bdHAdF5Yp3yFm/Je/RLbPYRgO4QRWdCKxjnnBp95Rerx7gNJUHqeYVU0NtlDtsgJtcv/hwlPQVPGlk1cBq2FWEaKDnliXUiyWUnTHibZfqn7Jqxk0BZmyrVwam30MNkCI0bNWpqW+U+YDczSV0XPh7o255xb+KFE7umuyHoSzbOdFWrsulfZ3iSG/svWRWOIujnnnBsuSZlzX7kjzzrP6+6wIjq/wiZbWFW/Wx9fN18SixQdqSjKSp3ay1KP5W+wfhEjOuUOWB85LMn6lK3L7wRG9HDOufaz0qa5HalvlOP3RyelsKVsW0BjmdmXMtoXSpQvty/3oVa8c7FG+fIb8jsULXBfDueT7c2SYDuABoPBYDAYDDMG+wA0GAwGg8FgmDFMTQETbTil1YmmFzEiRRxNt40+QSOn2bbgfSkRM9ICsT9Jeak2Ax601ZSUUBrtQTR6mn1CWrB5onAwsoru14R8pwjvSLbA/ZD7v/xDSYvBfsRvK+uQmlCKmW2OhNFfF+rAH0BkhIGKoADUpn9OaNP+AtuqZN4SSiReZ0qkB8/KbguVGdbblM+dF/rVxygbWxy83asJrRCn9JffFkrE31P2LmB3EIO7PkYWcI4DkWd3ub79y0LhhEdAnRSZ2kYn/xgsh3Sg9P6rl+SPIfdD/1mmpk8EU1pMsT1WSr608hFaooJNkWbZRFBrl0ugkXVEI1xrcN3VkUUGCfmcWrtxPZ3SBiYtX9rvhCpE3fgEEp0PiQ0MzoVYrfHh9fvj6/IuSE3u3Kd8vV8Um5LidV5PIlxPoPx+janSsC1r0uEXhEbONFQfQFPnlFxltCTrzignzypsMX2LKF+XNXOwUqa0COyOevP8mVMG2Qi+V+GBioq0LmUiVZ455MhHuZykaZmLV5M1LziA8i8yBYy0dJSR35D2Ctfdi+S+oMPtG7RT5FwJsB1Ag8FgMBgMhhmDfQAaDAaDwWAwzBimpoCnpRuZ5vzpo3hMnFJFeiMhosdPLv4JaN+pI3Akf1NPfYJ52naavPH4f9ZNk0gxafr6w0H7IqKD+vja6zM9MLpydnwdbkm+wXk+IRfWhZYcrPFJKr8vbRAeCLU5qnAkkHAfTp9ubI8vsw0uz5WBRlDtibSv3xLqIKoyjTwqA43QFPrBm6tSvmC7Dn/wWPMgwkkEkVA0hUf0+A6cfN7Zp3yZzZ3x9eDVyypNArjjSepoZ4/y9T5+bXydfVvaOlZB6bObQp1ES3OUlnlYdyeONClHUlSktOhJGlGC9CLtWU96Yh9PCKP0RFHFnHb8GvwjAC2pTuZ6IUTgmXa9hvqlukroNRPrhU2v2/1J6NwPySng3lWRlGSOmJZEyn7vU5Kv86urlG3hXemjuKxOkcL49YDaR2mMc87154USzu+iwwYX112U/h+UeI3z4aT2sCA3DirsMFC6LuuOg4hcQZFp6YOPytq4/Md8QniwJM/O7gCNrE7RBj15z3BX1sLBKq+7xXsio2lfqlFafkfW9daL0va+chiJQnBmgJ+1uVtMKffnpD0651lSU3uL804D2wE0GAwGg8FgmDHYB6DBYDAYDAbDjME+AA0Gg8FgMBhmDNNHAnkcZ/SftrwptS1p7u9kg5KivSPtSIpFQJptwVOxNJhWv5dQv4m/k3RET4on6eMPAlcvjS+9JtuPBPe2xtfYutrqxQP7BK/COgq/K7qSGMYNatmcc85ryLOjC2JFMlJaFLQF6CurAnSN74P2zh8quw/ovqggGhCvwHVHbUr2fbZ0OHxJrCDmvic6mrjMWpwAI4Psiu6v/9ozlA8jiHhqKEdzUqYH76Lrm7sp2snRuWWpU8BjLTwQ/c3oLOsDPySj8nikzLtUWy03paZsyjmZtj4lWU6lrWPT6vdSrVmmta1BnfeUa2ZaGVNDW2L5SXY5pwfUFEc59VN+6cz4cvHrsi72LsxTtv6c3Fd/kbVthe3jf18zR/zvmQ3R2PUuLY2vtVbQOVm7MPKFc84VfvhwfN19UbTcmTpHDGk9L+tECDYo2fus85t/T9bhWEXuwDWpfUneOWzzuA6bUEdYkzIbdcq3/XNiA7b0Pf6taVyWNd+DCEel+/zbhdrzzlmxesltcQQq1HYGXe7z5hXWR0+DD/X6aTAYDAaDwWB4+rAPQIPBYDAYDIYZgxfHeq/bYDAYDAaDwfDPMmwH0GAwGAwGg2HGYB+ABoPBYDAYDDMG+wA0GAwGg8FgmDHYB6DBYDAYDAbDjME+AA0Gg8FgMBhmDPYBaDAYDAaDwTBjsA9Ag8FgMBgMhhmDfQAaDAaDwWAwzBjsA9BgMBgMBoNhxmAfgAaDwWAwGAwzBvsANBgMBoPBYJgx2AegwWAwGAwGw4zBPgANBoPBYDAYZgz2AWgwGAwGg8EwY7APQIPBYDAYDIYZg30AGgwGg8FgMMwY7APQYDAYDAaDYcZgH4AGg8FgMBgMMwb7ADQYDAaDwWCYMdgHoMFgMBgMBsOMwT4ADQaDwWAwGGYM9gFoMBgMBoPBMGOwD0CDwWAwGAyGGYN9ABoMBoPBYDDMGOwD0GAwGAwGg2HGYB+ABoPBYDAYDDOGcNqMX/zsfzi+DvZblNa+sjC+LtxvjK+jcpbyDYuZ8XV3KUNpQT+SSjVH4+vsYZ/zPdqT8pdr42uv2aF8/XPz42t/EFHasCSv7Q3j8fWgElA+vy9pw6J8K5fvNrm8am58PcpxGUFP3sWLpLzGuRzlq70t7dY9UxxfZ/f5/dMwrEibZvekPYLNA8rXv7o6vh6UpS1GWf7/QGGrK2W0uB7NK9Xx9R/9d3996jr+tPhTK/+G/BFwW3uFvPwxlHaPBwPOl5e2j5s8lr2itL2Lpb9clseri2RMxR1pJ8/nNoz70m5ePq/SpF5eAPeFPC2x/l4W5lTI74/1HW1sUVKwtCjZhkMpz/O4CEyD+sZFrrvXg/Gg+iFutd1x8IoFzteUfNgnzld1gjTvsMFpXWn739r/O8c+92nji8FfeLoF4jjT8KFt4yg5n5fyf/kp7/Og3eMoVtm4T8b5RiOnMiY/a1pgfad9L92G3vH1/UAAz/7d6B+e2GO/6P/58bWn1wzoFy/MHPvvP/oHaUNPz2McAyljSN/30wKfO1F20thQ4xPXtThlfqXlw2fTOq7aOsJ1PKM+qRLacOr5pfNhnVRfYtrv9P7+seVp2A6gwWAwGAwGw4zBPgANBoPBYDAYZgxTU8B+R7Y5j15dorTiI6FhNj8vdPDaHzH16IfyvVl9m6m33U8KZVs9kq3NUV5tbZ+XZ3eXhJbKHTDd3Dwnfy/+/l1KC8tC8x2+tjy+HhQVBbon9Qi7sn3bX2QqK2gLbZbfZyp6sCB5PaCigz5v7fYXgWKDXe76c0XKV34k/dA4y7Tk/LtCqXXWS+PrTJXpZqxH5kjqnh3xNj+2fW+Rywi6KbTSCYEoX+dcVJW28hvSD0SvOkfb8l6lzGmDoTsOcZ7HVwxUr9eSZ8VV7i9vIPdFezwfvByUmYH21TRCUyQHcU2od6ShnXPOA0o1OLtOaRFQuH5daNS4yXKG+ALcd19oZE1QxB14576i2IEu96oVSdD5kFaG9owVte21ZX3RdP7o8MidKtKoR0zz06isFLoyjb7F8rEIfc9ToGWJlkO6SpVNNHIaPZxC8xLNlUZD0n1T0uORrlPCu6Tl+7DAm66tJ9KmRQo9nHxLwjhRddKULa3JPj5XSWrihH5QVKnLSH29KGVs4Do+USbUA6Q3adTrZPlYquTzQyVzwd/eOOHaORfDoyfaN4FGToPtABoMBoPBYDDMGOwD0GAwGAwGg2HGYB+ABoPBYDAYDDOGqTWArUui5cnvsQ4nvLUxvl4/mBtfDxdKlC8GDeDhyzVKq70nmqJ+Tfh2f8jfqK010Q1V7/bknirr4fKg32t+7AKlRRnhyjNt0OUNWEeQPYT3RIuNPHP+vUXQcgXMw2dAE9hblfbQz0L+PsrKdf6A9QZhQ+pUu8F6teZF0RvWvrs7vt7/OGs2yw/lSHt3UdpN9yva5+T2+FmHV1nrdmIArUTcYr2lt1+XNNQHVngcolbO+Urb1wC9HfS5p/VrSRYUdbYpQfsY0vw51h+SxnD/kMvIgQ0K1APrqvNpKxavAZpb1NgtL3K+EbzLsuh54519yhdfFK2gd/ch1wP0bmT1UuYxE9dFv4eaQq+k8qHtgtL6hGdY63jiSNOGkR7wMTSzSdpBXca0FjHTPlbrqABJNhVJ/+7cT9BGecnWJIn1eFIt45PoLT+Mmr80TGhRMe0J9JbH5E3Kh2OA+nxivEI+bT/lYK0Nkz9L6L5U7d2UYwXL0FpBLAOeO1G/FI0lWctAvli3Lc4j1PmFyn4szUrGPb7W03YADQaDwWAwGGYM9gFoMBgMBoPBMGOYmgL2cFtSbT0Or54ZXw8gGgVSrc45l98Smqf0UNmgzAsF1lmUbdlMm/NV3hf60u9DxJA+b38OqlJe2FTWHlAtjISR3+FoF1FGvo/DhqQdPMc2MMtviL1H52yF0oKmlJF/IJTX4csLLgkYCUXTzQOguotvb/KzOkK/j+aFRtP9kLsh92X2xVbE6/D7986LNU+20aO04hZToieGMytyrZ3bj4TmRErV66m6plCK3hy0R0okkKgMtioHQBt3mJZ2QPtO2BF0pU2J2l2scZ06ki/a2pHnri5TPocRSTKKOoAIH9GK9KvucwLUV9utBE2po1dmK50YooR4JZgr/eQxg7RvdMTUtr8gz5qgW57U4uJpQVNvSbTs40SqSKCO0yI1pNGtaVYqSRRgqoVHGqaN4oF0YJK1x0+oE71XyrNSrWmmxYfQImbaqBBxyitTxJC0SCAJZU+WgRkV3Uy2NWoc4voKc0W/l48yF0zzU56lI0bh+g82M7hu6TJSLVawrfVvEq75aZQ1RpbCf38K0o402A6gwWAwGAwGw4zBPgANBoPBYDAYZgxTU8AFoG+7yxyBwR/KpmUEDtdhm7dvR0XZ5m2tq9OXsDtauyHPGpZUJBD4ZO3PSRm5g15ivki5bvdrUubcN+QEY+/KCuXL7MoJxt4ZobmWvsd02GBR6KtRnr+phxXZss5tClVc+2aX8g3OCC138LyUV9pk+jq3K23TeplPQPar0ojV20KH5o54G7n1kbPja+yj9lqN8uFe9KigoqQ8UCdQTwjxrXvja3+JT7DGJYy6ApTnYpXy+btwyjYlUDhRmXprH6J1xA04+bvCJ67jbTmN7c3XOA3ph7yME3+vzvmqMvb8RTiZqyJmxEtA7eqIJnDi1utD2iGfWvaK0oYxvGNw9RLng1PFsY5IgqedgUaJ9vgksXdu/dh8/hpT2xhpxSlqW9M2p44kyiaV8p3u/+Fpp3SnxcSpQjqZGR/77z9Km47mxEgNEyc9kfZLo28T6vSk9G0qVZzUXxPrwofvhHDaez0x1Q1IlBWkyAhST/qiq4KKduQl0KhI+U7UD8tIibSjy4hBDoNSGS2boahD+I5DHS0KKHBPrcmYd9o+mXI9wIgpzj3Z+mA7gAaDwWAwGAwzBvsANBgMBoPBYJgx2AegwWAwGAwGw4xhag3g0RWJplC9wbqhUUG486MLoiFafIt1bp1V0Q5mm8xfoxatsyqcfek+RzTYf1H0UOUNsM5QmpX8tuiGmpc4EkS/JN+9g3OiI6tfZa1AHqJkxBDhY5Tl8jJgM1P52h1Ka3/04vi689nz4+u5H+xRvrAu9S1uQz2U3GRUZO0konJHdFmojwy63NbdedEpBGW5LuywTUf+5vb4uvE66w0759j646TgL4PGTmsxwCLF5cGmRduPgHYubrYoCaNzkM6vyLpXNwQ9x7poR+Mc60j8hfnENK+BEUlAD7gw55IQLYjNkH/Ec8OFoEXRGkCMrgG2OPEc2xahrtA7BJ2n1j1hhBNVx7gt8z6uSfmk+XPKTqovWr4YIro451w8L+3hdVnrq6OrnDh0uyTZhaTl0zo0SEuLtIFIs4TxwAYqPToH1CMtkkKKBi6tthwlAvpeaUi1lcb4/sexpsGICai90vck9YN+R6zTh0QDOK1F0LTjcNJK5vh8E0iKBKKe5eGYStHDsYZ4Sj1cVmtb4T6llca8qMOeqC9qVrG+fa1ZRSsZtT6NEuxotCUYpo0Sxq5Tc0DP85SpnQTbATQYDAaDwWCYMdgHoMFgMBgMBsOMYfpIILBjidYmzjkXNoW+qTwQ6mlYUpQX7qJW+duzX5G/y+9DRIM+U1mlTaGv0N5llOdXGZYhYsZDpqKLsI06AKq0vMHPwvK9vmypHzzHz1p4F6wKXj5PacVbYn0xWBU7kubzHAkkA9E/Mi2pR2eZKa78trxLe43TsnVpQ7S6ySi6PV+XZ4UtuY6yykoAKNBhjtNqf3DdnQbigow9TwXdwCgeBGUVgsf7J47+N4T29MpM9RNgC9+DKDRxRu3Dt6GSeUVXIhWdh3poZwpsenTJV9SGA9p3gm5uQj2Qfgg5qo3bEBo9RooJqOyJ8nfY3iU+IzYu3hakKco+Tgr6Pq8ocKR3NIU1YclwwkilxhKigui/U8pIjc5B1UiOWpBq4YJpaImh70ErDWzzNIpa0VdoA+OhBZKOChElUG9qv4KoYmWBkUSJT9ijYNun0vIfEto3ARNUIdr9pNH+hGQrFaZ5lYVbEp2bEp3DKWuWRClHIUV6gxIdZSuD62RUUmVgtaKEf3dMD/tt+c3wW/qHB9pGU7u4xuE4V1QxtqEP7xypfDTOdRSr4PH382wH0GAwGAwGg2HGYB+ABoPBYDAYDDOGqSng/C7QZkPe5jy8Jicna29LlAVNh3mRbPN2F3gLePFbciq2e0ZODrbPMB3UL8l2a+220KFHF3mbt7AnNEX7jErbFUoQad5sg0+LHlyV+xbelW3fxbf4/TESSmudqbd+VU6tVt6WdxyUmVLDqBt+X8rPHvH2endJ6lTc4O3hQVWend+Td2mv8PZ6MJCH5TflJGmstpD756GOigGJLp9xpwKkjvoqCkRNKGDvSKhccnR3iirWJw4xL9INKRFDMN+owmMtDqT/+8tMt+bvA50LNI3nFJ3Tg6gmZYgYss0nmIcX5DSyp6ob1OHkPtASmh4J2nBaGKk+darYQ1pd0zk7dfkjK2NvVD/kfPjOZ1YlAaKWOOdcjDR6RZ0+fwoRD54qpqR209ISqd60e3Du6hO8XsIpTee475DmU2VgtBcvnxydgZ49caoSpBIwZ7xQ0Wb94yMwTFCNKVS05xLo9ylPlU7kSzlJm3qy+gME0byKso6Hg2PzpUUI0ePOg3Ui6WS2zof9P0HrYpvqMa6p3h8/V9Oa2o3hf0Sk3DGiDPxOqDJGBemvCNw99JqJa34GvmWGNa5DWAfJmm5DlD10wB1BRzjpQhr00cTYwmGt1uRIu11MAdsBNBgMBoPBYJgx2AegwWAwGAwGw4zBPgANBoPBYDAYZgzTawBviz3E4cfZ0X+UE9774GXR7I2yzIfPXxe9WXGL+eo4K1VBjj7Wn6hQZGsdLEHUkWgfdG6eotvrl4XDz7QlX9Bnvr38SDj23gJombLJlgDV23xEfFAR/UXvnLRN8cYu5Wu+LNYZwxFE53jAOq/WM6KB6i4q/VZP3iXsSsPp+lbfEz1Y56xYneT2WFPYApuZ+e+z1UfrSs2dBjyIYqG1TvEu1LEoWrb4kDVlbhG0jUrbQrqXkmj2vC7rDQer0pc+aGL9HusyhjUZfIMSj69gEWxmQFek7Xhy7x9I+V2welFRPFBvEmV5akeXRGMX7suY8gbKqqMi7eYdSLvFHR7XI4jWESyypVG8LtF1vEeybvhXL1E+1Hp5GD1E28WA1tOrsgbQa6poKKeNNCuRpFu0zidJs6b1RXgf6im1ZQlaZCjrHdL6pdjt0F+QNmG/gTYY2gYEdX8474ZKlwZ2NGTZpCS/BG05Q1YfGFlFaeWmjZiBlj6RetZpWRFhtJMJS5DjNZCpkWWm1DJ6Wr+WMF49bfOEa6uyxKIoGajzVmMoKsPvMFi/eWod78PvrracQ93fCF5Ff2sE8HPoRaCvr3P/o+Vcbpff2e/g+IXfLm19hHMP7by09lLbzGAZU0YNovo99h0Gg8FgMBgMhj/RsA9Ag8FgMBgMhhnD1BTw7ufPjq8X32D6crAitEzzjOypVh4yzXv0jFBqxR3eNm+fB2oHdj0HBd7WrN0SqgiflT/gbdn2srxaoE5HV+4Ll9C4IFvKYY+/h7tzGNhaLqv3mCpFmxWkfJ1zblg8ns7u1VYoX/ERRCuBZ8U53pb3ISJJZZvr0V2W9oggAHxpg7mT3Y+JDUq+LlvKmfvcr9URUHv6yHnm8bebnwbiRisxjaJ6AI3gnV3jjIdCgU/QFGBdQFYnais+rAv12D0vdHDzDPd/2Em2T+iuIP8A97R5LHcuSz9kmtIPSOX+qL5yXzBSlFDneP5s0qoJKIYi2NaoyCIh0EBIlTvnnI82MCWhlJF6cc45HykRbHdFc/gZoIvQzsY559IsST4opFmJTEv7Al2TGvAd/13TkmjvAhSSl1dWGdC2mrIlignTNPWEf2ubGcwWIgWuonN40MdoJaYpYLScAWmApq8xws+EJRSOLWzPiUAg0A9J1jH67w9hVBA9ZhKtRBTNi2NqaqsXDUijfMoGhsaeqgfaWxHUWEPal39b+f17NblvqL4h2qsQCawKVly6W8EXJnMk5XUPuS3KGzI2gi6/cwYimaEtjn5UPMQxiiHTlLwgjQJO66ME2A6gwWAwGAwGw4zBPgANBoPBYDAYZgzTnwLel23Jxgt86i+/J9vvAVCU/Spv8yJN21nkR4ddoDbfkpODgzJTpc2zslWMp15HOf6W7c2hIz0lOS+CE8cJMaidc664jU7zcrnxaaZYzn5ZqLi9V4qUtnAdKIwUdujhz8uJ0DN/JCcu28tcQYz+0Z9jWm5QlBfF082jPPfDwg+FvsTTU/1nuK3Dhjyrh1FBnHPZ+umcfPNSTirGcyIjwNOhnqaY8DRajU/Suk0Ze3haeLjEp0/7NaD9S8n/j+rVpI7DItd3CMOoelcGR36X6xseyRjqrco48ds8NnygC0ZZJR1wQAMCTRfl1GnhAkgn2kDtKAo5moeoK8qBPsaTukDN+Ht8GhvL8OHEsY4KQCf8lBQhNULLBwWkA/Xz/YTTl4ry0qc2CXiSEqMYaPoO2gnlD3G1RPkwOs2oyGuGPj35Y/id5PmNjguaektLw3Hn9yEqSMj0H550x/bVTg9EiWvaHO5DOnTitOy0UVfSqP3TGIPuJ4whBI4nvWZi+06cHgdZAdKLKrIGngqOC9NFiYmqLBvBNhyWk3+UkfbtV+RaO130K7DuquBB3RWQyizJb9y5pTrl84AC7gykLbYe1ShflMX6KtobxlcOHBc8HVkJqXjo11RaV8ke0ij8JNgOoMFgMBgMBsOMwT4ADQaDwWAwGGYM9gFoMBgMBoPBMGOYWgMYdoS/zt1iLc/B6+L8X70t2qtBWVtiSBn5bY4s0F0WTcBgVbRB2QbroTDCB6K1lmy/gbYvzjkX9ETP0V4WfUyvwhqbvZ+RMs58Ve7J1bkO+y+K7i/sUhJpAHZel2etvsERDOZuSfkjsH7RR9MzG/Xx9dEltjdBjWXzDOi3lHzFi0SngG3RXeDhUADbjonoFDunFIEhTHar9/bq8gfppUY6q9xz2OR/AN0Laqe0/gj1J2jv069yh3VW5D5fOVWMCpLWXUT3e9bR5OvSL/lH0u5+Lzmajt9WaWD30ofoJPlHjcR8oyLoWQpqfh3K/NV6Hg80XD62b1bpz9DxHnVrm2xH5JZEi+l12fpIW9CcCLxkfXFSVIRU7VmarQxG+FAWLmj3EoGWdbjIbdIBHXFf6VVhKXDZhtQxd6Ci1sA6ETaTQ3JEMH5iZfuDWuS4mmAJ45xzkBaCZjE85MUV9YsTSj7UWKF1xkTkEigDooRoa55UfAhsYSa0jB5oQtPeBe/LqPmJ+rNsgh7QORcX88fmi/KcbwRriK/6fFiC3yTQnw7VNwR2NEj0JqJ44Ho9zCv7qUUZv4s1WZ/+2sWvUr68J2toAD+i/4n/y5Rv80CiLPl9rkjQkzEftmVeBloDmGTHpPKl9eWEhnMK2A6gwWAwGAwGw4zBPgANBoPBYDAYZgzTU8At2Q7tnalSWvWm2KB0V2SbM3fAVAHSUo1rbL8x9+be+DrCQNFqW7NxAWxggOXSW8C5hmzZ1q/x0WyicOGyP8fPyu/I31ufkOvadX7WCHbAI9WiI6BOV74l9F2/xlvbnSU4qh/JtjHZ2Tjnjj4i282Ve4pvhrYq7sL1fY4Y0TkjdFtuU7bAe/M1zgcRTjIt3nquP6/sU04KEERbBxTHrXOvC1ECNE24dyD5VGDzeLEmaRBZoz/P1iSlTaEiO0toCcOPioFJGxaZBixsSx8VdlACkLyVPyoBFZMSrUGnRRkZR0FX3itSET666yJnyG+BlU6P+797TtaA3JaOSCJtH4E1T6xo5GBT+gEjOXgqgsCE9cufFCTQwRPQVipkbwL36bFakb4aLMt14zzna69Jef2Ktq2Ry/y2/DFSdGBpSxZbpHn9gYpiAu88UrY1E1YtP657RVGKGEwEI3Wo+0NoJ1+PEcyL9RhOOZbS+ktjyugvTxskCdDUYJIFUcpYm6AQMcIHjMM02UUEspFhiccQ9Z+OCgSUMNK+3pDHK0Y4ovJiLTeQ+g7UmI9GkveVxY3x9aXMDuX7SFbWpEfQvn/mzA8p3693Zb71W2yXNtwE6xuYN16F7eKCFkviEpEWhafXS0xLLO6x7zAYDAaDwWAw/ImGfQAaDAaDwWAwzBjsA9BgMBgMBoNhxjC1BrB5Xnj/4rayVQFLiFJDdGmjd25QvsO/9Onx9dxN1g0dvCZWMmhn0lrjKs7dgbBYoKMLlDOBB5IIbc3RXoe6dzBUV7I+pnpTrrXOC61fMPSXc87FW/L35mfBLka5qBS3IDwNhNOrPGDNSg50WfqYfbhzOL7ef1EsYvwB6w2686JFCM6Kli97lHzEvPDOJv+9cDoawBj0ZZ7W86DWJe24fEHGclxmPcsI7Qha8qxBVemUQBOJdgThhJRD+j/LjisuwqhhcF3Y4fcq3hBbFKyvf8SDaLgkfRL0WR8aQ/gmDPE3rChdGehqMExc7wwP+izoe3U4uQDCxvmgbZkI8YQ6RbB6cU01OVD3onWPylrmRJCm+UrQjiWGHDsO8L4Y+tBTurwRaGB785LWXlHr3RnQg63wuIj6oOfryVjQ49gbJehLR8reJoJ1jItwoyKE4ARrjn5ZWdPAa6KFRz7F6kOHI3SDwbH59PiJI7AiIksYtY5PG3btBBGD7lGHGiSt37ShxZTGFLW4qPuL1XxHu6xhSdKGBd2vsBaqUKJoMxSAXVwcKs0i2MAFaFOm7MHY0ojr0V6Qv7e6smY+HLJ+7/WsaAKfzcg7VgKeQ7kQvlfmeG3Ab48ifAv4bWVnVYbf6Dr8dvlKYwu/J/FAjXk9BqaA7QAaDAaDwWAwzBjsA9BgMBgMBoNhxjA1BRzBVmysjos3X1gYX3uws9v72KcpX/mhUEOH1xSPCijcl0gjXsRUI1IdgyIc9S5ynbJN2QJuv8DbrSu/J2XUn5V/D7pcRncV7DLARsNTbEDYlX/I3+Ut24Or8qylHwAtoZzQm+fAGR+c6xvnuYvKBbHVCNv8rN7SstRjH47Vq6344jZEahhIvtY6U3S1t+rja02Vds6V3algYU6uD5lTHW1tj6/9muSbiB4B1idoF+Occz6kjYAeLd3hiCHNK/L+I6A2MAKNc87l9+G5OqpLW9o+C7ZFOP6dS6Z9YxXVINyqyx9qjmbaIM1YlrYZVJlWzO1LWyF1hrSMcxzVYVDhMjIFqVe4BxFDMoqiAFra7YIlzBJTMRitJdJp7z9yJw6keTUdnGT9oqnhVBoZbWCgzVR/owRkCNZB/RqPQR9o30qZud1WR8b4ECw8tKSGyuvAOtZVNBRRcUzzhU1Yr0sQxUSx+MOCd+y1toFBSrGg1tMQo8ygVERLQ6BMT0/QP8lA2jdI3udBKxltv4QRPpD2HSyypKg/B9R+JrkNMSIV/p4655yPEgP4TQqP1EAEeQRaEHkjHkQRUN35XRXFCda8B7AW7iyzvd29oVjEDBxEzIpVRB74IIhDJTGA8TXKgZVOnutL6zquDUp6kBoJxChgg8FgMBgMBsNPgn0AGgwGg8FgMMwYpqaAK3eFOji6kuwEXrknFFLpNp/0PXpR6Bu9VVzYk63N7rrQa0fneat05StbUsai5Ost8Amm+hW5r/odTmudkevestAD2T3eQs005Pv46LL8u6fYm04HHPRVFIfKPdnC7dUSjn06pgeLj4SyCbu8LZ9/JFvFvVXeiseTmWFOyu+rE6wZ2Fb3IfB2Wbmue3Cac/vnVimtuPMYwdKfIjw4IRpXWEYQ4Km1FpwkVScEI9j2D/aZ2kXgyVk/ZjqrDJRw64KMw5w6SX10Qdq+8kC79ctlpgGRFrLcX35P0uJDoIdXFilfNCft4R/y3IvmRUqBFF72UNEZQDl01oQCwog2zjkXAn0d61UETuBFcPJXyx6Qwo5r0ob6dHMEJ869rX1K8xaZEj5xKGoXT4/SyVFN+cJ9OgIDRXjA8lKoPDgc6DJNLq91KH2gDqK7YV3SCg08sc5jNVOXNQnXBa+TEn2goE+VynvhqU/9Xrg0jrAI3U6R3JcrqFP6UCadntYRQ4BSi4FCix8j+syTUG9PA3RSOS2aDNZPn6LHU8GqfeMiyANADqN/T5prUD4UMcrq33g4ja5Cd6EUKdtM/m3xj+Q7BNePjF5bAqT2uYx+Vepbv18bX//X4aco3/vrsr7OBfLcG+0VytcdwLhuqbGMTYDtq9sa5wCNJyWxSKGAdZnTwHYADQaDwWAwGGYM9gFoMBgMBoPBMGOwD0CDwWAwGAyGGcPUGsD+gmhFqrfZSqBfy8K16C2GRT5WXXog9xVyrJuIgAOPQG80f5Ndt5svLsmzwEE+UprC7jJE07hDSa4Dcja/Ihx7sMzao86haKBcHzQlA2U587zoweIfzFHaEIroLIHGhp0+yLm8BVFXWmv8jd5/Xcpf/xrrbwLQdvl90Qr0atzN3WXRc7SXITpJV1mYVEUDsfQtrjBa1Zwk4jmwn9ne4zSwe/Dma5LQ4THk3xe7mGh1gdJQ3+SH/rH/7pxzoyXQrIE7vbbmmb8OWif1362gK3nDAxX9gioFOrB10Z9oexsclagHdM45fw/6D+ZaPM96XrRj8CEijdbvIQbKZiiG8YXzsnKDFWioN4zhuXGb1xcqvZCntFjpzE4ESVYvjm0aSBuWECHEOceRTpybsH4YF6H+HSNy5CB60qDE69MIIzds8VqQh2GX3wE7q33WHpH1C0R3iXUEDqyf1qWN8sfnU7KmHsg6R3mp06ilyhuC9Y2yIgoqsq4FaTpFxBNGAvkwRglBkKZURwJB3WOe9eZoM9RdlrT2Mo/XQUXaqjcP1lHKwQV/14ub3GbZOmaU+eV3WYtJax6Mfx0JJgtrpjfk9yqBTh/trHYGS5TvN3tyXzkvz+0P+dtlMEDNLiVRG6DO0etPqTGdiPCSvI7EOjLWFLAdQIPBYDAYDIYZg30AGgwGg8FgMMwYpqaAW6uSFe1GnOMj/RgxJP+QLTb2Pi57+wtvMqXYuiZWD9VbYmGBx7l/BNnqD2DXd6icafy+3Hd4jbeb0SYhvi+0hP8cv1dYkC3VF65ujq9/+J1LlK/bAauLAj8rADqmcwYCpfd5a9c7hMglsMVe3NLH2yWtu8S0x6AC1i9Aj+tj8BhgHe1c9LH9bB0oZRUxY/9jbEFyUoiRlp1nut1D6wakfZXDvQOH+0g7sgN10F+QfBlNCcHfxbsyloeKUs00wD5joLguoDooOkmTKVCk/qIFoZ69HvdJDJE2/CbT3tH88ZFb/BT7BL8vaQfPMtWaaQPtraQDSPvi2jBYUPQtyECCXaCH5zj6TwR2FNoiRkdyOXGk2Luk5iN6OCV6AqYp2QXSsiHQdaVNLi8Emyqn1oIMRK7JAe2b2VXt3AD7JaTo9XtlYK4pahTri9DSCNQyDItxYr4M2NZo+y3a2kihzRItUtJcrqbt89MEWN+gpY2XU9Y8JaHKNZE9LGLULWnf9rqSW52TORgU4PdEFej/UNbGITuYuVFe2jBzAAnajoeoXegkPTdaQtkGKupI2JW5UtwCiUGe36t1X9ahzhJYjI3Ub8GBpOUPOS3p2yhWY9KHd0FJQdzn9c0DCl9TvtpOahp8CEeuwWAwGAwGg+GDhH0AGgwGg8FgMMwYpqaAl74p+7JRUVGPZaCe4ETkcJHpsLmbQh00n2FKqvRQtmxb52R/OHvI25xIbQ7KsuXZPMf1rd6Wehw+y2lIKwxqsvWqiEKXzQll8VxFIpC8d3aZy4NTQKUHvA3buCJbwJVb0k4DZrlc4zxQu6tyz8I7TJsUduW6tc79kN+Vd8F2qtxjOhCBQbn9HvMevUU4LbzO1MHiH2240wCeZo1LivdHSgCjgqh8GL3AUyffkAbKP5BnRQVua28kfTSsCbWpT2r6dTghXlSnIPcP5T6MapLhaRkhtXvnkSSs8qk1pJFjRTf7B1KPaFFO58eK2h4W5dntVSkvf8AUS2sdKBsOOuJ8GLI5oEs6SrJQPYR+wHbrqVOb6BBQ5jb0G0yXnwTwdO+Tng71UAGi3f0xQsoIoyeoU8DQxyG2paL1MaKRTgsbcB+cTPSOuFPjLqwhGD1D18kBZZXl/nYjjP6BJzF5DEYhUGBZoNAUBxwTpcaPItoXx7g+Vdl/AgmBpnw1JXxSwGgyadFIdPQPBJyejdY4qs4oJ+V3luB3t8TlVZZkrKxXRMpx0OV1d/ecrLX+QEXCgj7C7wu/rdYCXOMxOpNaM/Gkul/kNT53APd5cl9vTrehvHMf1taJk749+YdQLUcov8JvIz2XHcp5oC28rPp9GiXT3k8C2wE0GAwGg8FgmDHYB6DBYDAYDAbDjME+AA0Gg8FgMBhmDFNrAHtrolHKP2QLl8FVSetVhb8ub+gj0WBnoexdUIuWaQhHjzok55zzgb4vboM+JuJv2eZ5Kb+wTUkuBAuLo6zw/nPPMIG/vS9aqR8ero+v+xscZeEXP/3m+Pr7tTNc30PJewR8fvE+N/0I7GPK9+Rddl9h7V31vmgA8nusHeqsSFuhLcL2R/nM/eobogcLQEfkDVhT0K+KhmP+27uUVv/EujsVhNJfXoN1SqPd/fG1/8x5yaesQiLQBGprFrQmidN0NVilI9FHjUrcXxiRY8L9PUkjNuJ+8Hbkvdwi6HSGXPfgwY78ofRXGDHDA12Nn+F3zO7Ju9SvynhtKY0t6ooaL7JOtfwe6C9Bv7fwlop2ArYFUUX6xD/kfvXaKZY+pwDS9qXov9IigZBlg7Yp8RL0axqg3/KgjMwBjzPU23k9ZR0BNhtxC6xelC4RI35g3SesJ7DuIY8ttPNBzV6kpILDMrRvDnSDfW6nEU41L/n3JHUWQ7thdKNY95cPaXrenpYNTMrYQ/sQtA5xOloERtZRurQRRPjB/hot8nzHll8tyrdBZ6jXIPitibhX8PcqaEHdtdXV4HgrIU/NIYxq4uloImVYQ+CVPdWcETRbdgf+UN2fPZK6hx1ODCCaUtiWumt7O+qjNqyTeh5CH2n9beLvSQpsB9BgMBgMBoNhxmAfgAaDwWAwGAwzhqkp4GFJtmwbzy9QWvW2bFmiZQUGf3bOuTZQlAtfZxsRpKia12rj61xd0ZzLUmW0okB62TnnFt6FCARF3m7tQ/DqGM5pH/7TNco3vCxbtjtVsa35cz/zLS4P9ooP3mRrDv8ZobOuPifvfG+Bj9zHd4UqHABjW9jl94rhVQ6v8Bb7/HuyXZ6H+6Ic98POa6Vj7xkWeVu+tCFpsTpmX/vmI3caGC1L9A//kClFH6ldoIdHZ1WfHAnVP1itUhrZu5SlffsVbpvyPSkfo1No2tjfAvq2oCJhzEFUD6Rzu/xe0blVKW9XrGNGyzXOtyTlZd5nyj6GiCceWvQrK4HDF8SfqHkRsl1keUSpKDSyMrdxvUfyrLCZTGH252XO5+9J+bGmebGOhw1KiqvHRzg5MTyhJQjSNxMWHkj7jKD8tIghSAcpaYAP1NOEJUgXbDaQHtQRGABID3vafiMPNK+2M4JoJRh1aMSqCRcHUEekfUNVd2TiVTf4SHWjpCKNNkV6TVvzfBiREk0G7UOIsle2IjHS9Kpp/D7alkDZHWXhAte3D2WtHSpZFvZlrL48sHyMaDTxXhDhhOaJtiOCORCVVX2BfuWoRVyn3IGkDSro56LqDu3mK1ehsA0yNbBZm7CvQmo7Ze7hO2v5RRw//pi1HUCDwWAwGAyGGYN9ABoMBoPBYDDMGKamgDGQcX6PT+L4Tdn3DMGBu3dpkfIVt4BS/QKflsXg8k2gdtf+mCmfQVn4UQx6ring5lnZ9u2rqBu4ZTualzp1z/AW6r/72pfG17+/+7y8h9rn3e0JDfXFX/wupd06ki3xGw9WpA4HvBUfwqM7F6VO+T3uotaavNfaH9YpbQARKfpzEPD6IVOKo5xQwBiEO+gzB9BehVPLjjE6pxr1hIC0r6eorrgOUUJWZOwFW3XOBxE5fH0KGLbVswdAc95VtGxJyohqQOUOdFQHoSyiKrcinnbFNK+pTsFuAJ0L9Qt26pSPgksoehjzRjXpu/Z5PtHemwN6BIZeJsPv9S9fERnEm42zlPa1C/AuQ+H3WueYLM42jqfj6NSvcxwZo8aUPUZTORUoSjHx5K86zUu0XKA5Jfg7hdrFMvCU7uSpYni2poCxvkhDKVqaao/vomlpPM2oTqKPCpI2KEF0F8WAx0j1ZoBC6/BaiBFn9PpPbZAWCQPlBUivqf5Ki+pyaoA6xep0L9GDQPvGXeY58fSpV1Y0KrRbbl+uuwfKcSOSOdldlt//0ZA7NrclzwqblOSCLvYzdKyOdhEkSCLUHIqzyZE7hgWQqcGQ0lGchrA0ImXtpTCt/lD/DTQ6njLXcx7HqJ8wr93TlybYDqDBYDAYDAbDjME+AA0Gg8FgMBhmDPYBaDAYDAaDwTBjmFoDiMe0R8pWJAvHlvc/LREi8gfMV/erwr0vvKmiicyJPqj4SO7bf4ltHlAriJYoRxdZb9AXtxA3d5N1BNufAW0DWFYMKtwcv7H5yvj6/X2xbWkM2Lfg88s3pX5KIPD5c9fH1/+V+5yUV2QbmPJvyns2wEG9vMGigkFR2r63VKC0PYgaMncbHP5D5WoPWof8juit2me4vMpt0aI1L7J+LeyejibGA01ENK90iKCj8+siMkHNn3Mc/SDYZY1pNCdloKYyo20GMIJKBzShShM1WgLbmp7Sc4DdCdoCxPNznA/0ht6B1Dcua2UmQEfagXp0V+W+WGmdWiDne+ajD8bX60XW2v0HizfG1/92n+vrBTLfcgfy75kmz8OwBWMb2jda4H6lCCpac1Y7HS3qGMoGhixScElSlhhkW6J0Pl4O1hd8X63/QZ1TgoboR88CvWGs2i+L9kBSvo4yQJoytOJQVi9o5zVY4vE5qKAuW8rrz2ud1/Friz/guofgpIEaMuec81uidSN9nNbyodYR7GK01go1gVoPqPWCJwbsVz0v4L3IckjpMqn/htyGmaa0WwZs4IobPJZbqLdsinBOR2DJgLRZ6+2o/1C+qeqL6z9FmtGRYCqyZo5KSosKUUcGJbnuLOtoMsd/a4RtzpdpSr6sWuMCsH7xoH09Fe0J609RaLQNDmg2te7zSWA7gAaDwWAwGAwzBvsANBgMBoPBYJgxTE0BI2VRvL5Naf1zEhkEjz23V7j4EezE5ueYlsPA0wOgijGYsnPOxehaUJDt0dyBpg28Yy+dc65yUwoZAIMUVZmK2W0LhZHPSlrGZ3rgjQMJmfBLy+9Q2n90/ZfH15dqEhUius7U9tFVufbhpP7Bs9yGi29LPUZ5FbnjkWwrt5clbZRlarezKG1dfkd4lGCR+6QFdh65Q37n/P1Tst8AugEjcDjnXFSG+iO1o4LSIyWmI3fQ8XwYUu2zTGfl6jBWqkA3FLi8TF06sz/HfR5AhIagAYNU2Xj4QPtSmrZIQJuQItsMDSEAOr5/d46fNSzJS1+uiP3Mv73y+5TvP6tfG1+vZBSN3pCJjvYJgzI/K78N1DlE+BgtrVO+sC1t6HXZgimaO4VIIGnRPoC+QarQ03wY3ZNCISIdpMcqUo9olZNRD8P7JgLIw7uQdYaiw2g+gYVLntenfk0o4GFRUYUr8ndnVeoxqipqGyhgrynlZw+4Trm61D1bVyEYkCpMobaTaLTHsYE5NYsYfG6QPIbI6kVbBGE7KZuqoA0UcEvKyKjIWvldWE9xeVIBffA3OnuUbDkzKskYCjvcr1rOM35Wnh82gnHZXeS09rIPaUAHV3lej4ryt9+Te7xIyXyAUsbIH84558H3EK3PKtoHjsO4p0KSIGC+TkQC0VGJpoDtABoMBoPBYDDMGOwD0GAwGAwGg2HGMDUFXNiRrdj286uUNgT6NtOSLcq573NA+uaLEBlE7Vjj6dYKRF2I1OnTEQRvrt6TOuEJWOecm78OUUc+wqeA5m/IVuzWJ+S5uQe8VXy0J/WNfdnK7Vzg8t79mf96fP0fbL1GaQWgjkNf2mZY5C3wTBMDVEva0jfVVjG0W/O8ohvhhHRpEwJPD/lZcz/YG1/31yGygqJHio/khHC4y9btw+VTOn3ZkTrFPaYHfHRah3yePj2JNEiBx00E0Qqyu3JsLXPAbT2s4UlNuBxxG/pA8/pdFUEHT/4ChRFleVpGZ0RikdkS6l3THnEGorrUmR7vX6iNrzH6y0gxKlFB2vDrjy6Nr78zd57y3ejIGvCNnUuUlqlLW5U28EQwj+VgH05qL8mpeD3WXF3o4ejsMiX5u6cgRaBIHYoOhr+9IIX3RfouhZYkKjJtHOP9avzg6cNRVtHISOfm4OSookAHZZDNwFodZTgfnu7tLVCSG1TkPYcVOB2ZU9F4BlJ+9lDKK+xwO+UOgaLrq0gYQLHFeOIyJZJCnBIJhDOmSABOEBMRZBA4ppAC15FA8rKOTUQxwjLglfF3xjnnIjyMjhRwyG2IAbSyTX7WCMYenhAeLbLEI06QS4yKPOa7C0ABzyspAjgdDBagbRJOn/+oTvgHp4UtkCzogDQ9mMs4Jgf8W5AYrUbJfGJ9epjSHj9KiO0AGgwGg8FgMMwY7APQYDAYDAaDYcZgH4AGg8FgMBgMM4apNYCZTdHh+HNsK+Lmj3euP3p1ibKVHojmae/lEqWhrqAJ9iNhiznv4QLoVEC/UrvJGpDGeXm10iPm1/deljKqtyXt6BltkSCXaGeRzfKznvknf2187fX5mzo8lL83SiuQkGxbg8fqt19nveHKd0RIkTvkMqq3RDt1+KxoJ6o3W5RvNC/te3RR+q68oSJVgA6mfYUFPWH38fUGTwOk+1tZ5MSm6N7idRh7baV7AS1GVGINYLgnY7S/ImM0DpM1QaiDym93Ka35LEQCUZZGhQ0Zh35T6jiqsrYP6zRaRN8inhv9BRH0+RVliwD2NPUrct1dUo78FbCmAc1q3uOx8Vt3Xxhfd5rchgWwtClugoWLijQwWhL9qX8ofeepyBiuAmuF0nrFR2xBcyJ4AhsY51RkCYzAoO18UOcEZcQqH7YTRpWJtM4PIiGg1so5tmrpl+C6ojSAVYjcMSd1GtRU3WH8+KGKigARYoIh2FR1uE4e/B10wOrriMvLHsKzmjzHUevGkUBUfdGqJyXax4cSaZZQSdCRQFB7puddBtYT0DYHfRV1ZQC/yTBsYi9ZK9he5k8P0hVinQrJnygYWWyY5/GK9i7dRa7H4DyMFbgtUBrA0SGKG+VSW84V92RuZ46ULr0Nf4MuXUekiXXbJyAeSj4vVFFSniAije0AGgwGg8FgMMwY7APQYDAYDAaDYcYwNQXcOydUVtjgbU60CCiAu3+U4S3K9rpQx8UdpkTKX787vt7/pcvj6wyzl3TMGreAK7fZOqJfFgq0s6S+c/F0OzioD2tMLy18R8o/ugxbyu/UKF8WXmV4kSlAry7b6Ghp4A25TpV7cPQ9D7SEch3H4+2FPa7v/ktCDxZ3JK23xF4fYUcqPH9dGtjrcZ/4TaEeO6tsvxHlHn+7+amjfsR/g+M9Rs+IKiw3cHsH48tAHb8frtXG19k9oSVHZaY5e/NCubXWgM7KsW1R2JI2HVSY6uotyXzIgHVHv6qCl4O9C8oeDp/h6VvekGd1lriM1jpYd2D89xr3eQZo33pd2u1vvv1nKV//htC3WRWEYektsDuA+ZXd0pMZ5gNSIF1N58Gc0tYqWgbwIcUEPYPUrotVXlgbUu1IMBIERCpQVPuwLGOhr8ZgtwZREZZB8rHOZVQu1sfXz1Rl3j1b5ahQK1mZd5u9OUq7fiQSmI1DGT+tBs/P7L7UsbiJ0SN4rAZAr3nKEoqsdKBtYs20IZ1PkRROR+LyOIgxmoQaJzpKxBg68klZ2t7TFiMgtwibIDfwWV6C1m89iCzka1cZaN6hsp9Ce5c+jFdPVam7AGsGDH9N8/aXoP/zXJH5BflWaDRlDa5V2Tprp10bX4ctsNjqKasvkPb4fSX1wMhFRNmrRRMtzNCOSPUj0r5IB+u0aWE7gAaDwWAwGAwzBvsANBgMBoPBYJgxTE0B569vjq9Ha/OUlj0EunEBtijVtnT2SPJl4WSjc871XpJIA8Ut2dpsrfN2c+06bN8+I9vX3WU+mZwDuiCjAjQ34EhvH1iKM7/P9d34AkQ1eVdoicMXeJu3CmnDBtejfU7yzl2H05fKJR+B29xn/pDbCemd7irTkhjVAaN/6H7oz8n7h0AvIpXvnHOFreQt5dzBdKeWnjaQ2vHz/P6xiuoxzlfnk6LxIoxfFZQ7OBAaYLAGJ25VhI/CQ6Ezg770eWuV28wfyH3akR4jKmRL0vbaQb+9JGmZjpTXn+N8DV/6dahY7yEMy1EB3iXLc2PQgvpj1Jk7TOfN3YMiVGD3sC1jPv/2w/F1vMBl4KlD6rumooqXZLJ4QxU1wn3IkEgppuTTtDae6FTjk/Nlj83nRSpCDJ7MVFUaFoF6q0prVi5yhJU/dfGd8fW/WHtjfH0+YLoeV4UvtS9T2nZPZDmPYqGAMXKMc86VH0g9CgcwljZ5XPh1iCTTUNFjMOpCX+i2aSMpaMqeoizoqA1JdOsHjTR5ANCNMdTX0+MJ55N+D/jbH0CEG3WCNYA1LgBmc6jMQnBd61fdVNAU8ADG6GAOEstKvrUoa/7ZKkuFekNZJ5dLMqZubqxQPq8t4zKEn2FfNWGmAXOvqxJxjevByfQOS8VwziPtG+soQThGFeVrkUAMBoPBYDAYDD8R9gFoMBgMBoPBMGOwD0CDwWAwGAyGGcPUGkDU/fkt1n1k0c4hFv1J0Fb6qobcV3+1RmmFbeHKw5bct/TVHcq3/9kzkq8L/LiSL6Durfi+0o4MxaqjcU6aYKSsTda+6iBNnrXyNc7Xq8l1fo85+8W30dIFj9IrrRhozPJ78u/tNdbzYNSJwq7SPbwt5XeX5L7iQz7e3jkj4oxRVv4PkN9RVgrwmqgpdM65YYpD+wcJf3E+MS1+sAH5RDcWt7j/vRD0dlW2bcHoL0ELXNeVtgOjhAxAv5dVkWtaqxDVgKcNtekAtFid5WTboroE4HDZA852dE2endvjMnoLkhZCdAWvwf2Y30FNqDw4d8BjPnco5elxmN2R9o5WpR/8Q6Xtw2gNoNPyKmXKhhYRWhN36mZEaTq/ae/TUQHIjQQ0P6oIajMY03qs4nqqdb4YnWFYlj6t5Hmwrmfr4+vnMlLenM99tTEULd7N7iql3W/Uxtfde6Kvrd7nNys/knmX24NIMh1lnYF2QWpcoB5K66gSEaMVR0q+09L8pcBL05GiHrCv2hB0aTiGnHOkD8SIFkGe14xhAconqxduJyVNJaB+fVCRukdlZVNVkXqs1mSsFTOsSV/My1ozl2G93cO2aJHv7sn6NGrwb3JxU14Go4mVHqloHz3QpbeVtg9td6aN9oE6VW3vg3+riEQWCcRgMBgMBoPB8BNhH4AGg8FgMBgMM4apeTz/SM5Bdy8xDYd0a25H6Madj/NZ78oD2QPOqygWOTji37wmW7RBiym68n3Zsg6A6mhc4nxosdGbq1AaHuOuPMBA4ZTN9eZlSxztPEZZ3mpdfFu2fbdfZ4vzEWyX127KFvDiW8o+ARz6K/cl3+ElLq8IdBtGMXHOuagqz6q8Vx9fty9yP5T/4Ib8sbY0vjx6kb1piptSx/wO17dxUZ3xPyFg0HuvxRY5/tLxUSFiFVkCIy14PUUpQkSBYbkm10s8vsjx3QNbnZbijhbkWSRZcM61geodgQtKpqmCl1egn2GMdld5wIYNiGpT5DIykBYD01Pc4P8D+n1Mg2tF82YaQE0qCpOoXozQoGx7MHKLB0HqYxWwPt6QaBPeHI/lWFvGnASIUky2FUGaN1Zt5PkpdjGYN4XK9ND2oZtM5QUdsBFq8pKfO5Bn9+ck36OtGuX7w9LV8XXek/XJ97hOb7dFovOVh1co7eg9+d0oP5Dnlh/xnMnWpfxgV+w8vCZLWeK2zP94mEwBc4LqL2h7L8BsijbG+z4sNjCISL0XUMIkFcgqHhbfRVnkYHSeGMZUrH53gq7c5w9xveNHDcAGRtsR9edhnJfkOltmujWXkzoh7ZsLuP+HkTxgp8syBaR9O3sQnewez43CtrQNWtPldpU1Wxt+X5S9C9K5T2LTouUh/GBuRLOBMRgMBoPBYDD8RNgHoMFgMBgMBsOMYWoKeLAu1EvQU278sAXeWxaqbPX/e4vytT92UR7c4i3b3U8IPYDO4sN5phrDQzhJ/KLUSTuGL70hR2nv/9klSqvegy1reJanTrr6AzzdBPSaYj97NaGsCjtcRrYpz+pARAedD4/4HVwV2nf5W3XK1r4gdHZnmame6j1pmwFQlv0q52v+2vPj61xD6hF2FKW4JdEADj/KJ/oynRTq64MEUBbRITu8e0gpAu0/QQ3DNn28o04I10R+4ME4z+6pSAN4si5EGo2nFNK+GUUP5xICrfSrTLF0l46nAQqKvsVTxmGH78ET7jjmY3XwL3cg/VraENoj00gOXu43FNeDlBjSvmlRGOD0nD7RGF88K3/sqqPPC7XEMj8wpFF+SMtMGRVEUzf4/kghoXTBOcdRBvD+hnI9gPpmAy6jBLScBxGSGhFLT75zJHTud+clapMOxRJ1pIzsFs+FBfg5wJPjxQc8t/C0r9eBk+I95VKA9Limv5A6i5NpOKJ9kUaeiIoB7fYhYHyd44gRTo8Nihgh/aBPAXt56ee4y/PY8+CHDuZ72GBJjd+T8iNwlYi95BPnA2ZlXdiU+4ZwWz9myjoM5b12myrcEaDbk4f1m6qMXUkr70gblh/x+oQytewBSCzaSlIEa1esqXiM/oGngPXp3qQ1RZ/sjZ7unp3tABoMBoPBYDDMGOwD0GAwGAwGg2HGYB+ABoPBYDAYDDOGqTWA/Yrw5t6IhR/5bTmeH/uiKei+cp7ydRfArV6VsfimHPcfVEU3NChxFTsQ4cIDOUf2iLUdzWdr4+vSBvPyGIEBtYiNi6x7QV1h7kDy5ZUMKQIdTaHHz8oeiOYinJO692r8XpV70oZBV96/c1aJJQD5A6VnAd3LKAfRKVTboLaxsAUahYz6/0BdNHaVG2yD0l/ktjoxgMYCtS3Ose6PogRklK3IAuj8lGYjLkjbB9vQ0Uo7FJelPbKPRCuZOWC9Sa4i5en2zSXoPqIMa2fyu6DhOkQ7Ir4P9XyZltKzgvQn15B3Drp6LovFQZQFG6RDtuBwGWh7ZYsR1WTM+rvSNnGJxbNkMwHRWjylU/OhjyaiOuzsuxNHWmQJDCGBEZKUlmfCZoSKAP0W3Jdq84B10nYxYJcUqLT8AMZCR+Z0ps1zpl+CCDEV6UdPVSl7BBGN1PqUacoamtmV8TQRPQE1uh2w3NARU6aMrICY0JdOa52h7WOo0NPZRyHNonov0pTheNJrDpXhJ6cBJjS/c7IW+n2IEKSiYgV9FFyqZ0G9uj3JNyxxvv6ejMtOCXTIPX4vvw9rpnqN8n25Lu5K22gLL7R78Zvwe3LYoHw4l+O2WidhvnmwZupxh+sapQ2nH3cWCcRgMBgMBoPB8BNhH4AGg8FgMBgMM4apKeAIol905nm7OQTKMgY6NPdH71C+3BWhhDvnODrH1qfF0mXlW2ILkDnkrdK9VyXf3F3Zlm2eZT5s8ffujK/7V9cprb0u9e0uy32ZFm+3lu5JPQbzQo/Ur3JEg/n3ZEu8vcL18EayZZ05Eh6ucY4p1Z3X5Uj7wrtg56IocKR5c3t8pH9YlLxHF+S5AZ9ad3M3ZZu6Py/11Q7vuar0kaZK/VEKDfYBwusBbagiRlBAeKQ6NLWB+ZY4qk0EkVsCCIYe7exRPg8oYIpIounLvpQ3zPK8QfsLfG5+m9v26IqMjQJYE3TneWwE/eQ+KTak3ciCSdEGwwpE63lXQoFEixyBw0NqQvcDpCGl7vYPOV9R5pQPET7ieRXtAyjx+MEjLuM06LcniPwwGQnEe+w05arBwPmp6SWw9/BUGo5xH+wtsnvcp1EO6KsQLVGUncUA6MYBrxkBRoiBOUg0r3NEPcY4Vx8n0gFav6RFU0D4FAqE05LsfY77+6SAddL0uMNxA9FOdCQQbFO1dqGlidcAalPNd4wSloO5P6zx7yRKqnxluYaRu1wEllUblM0NS5KGUplQMa9+H6UI3D85+KYImxB1pqnsbZpAdaMMRVPj2IYpY5RthpKjeDCVmzzpJ+ULaQvE8bAdQIPBYDAYDIYZg30AGgwGg8FgMMwY7APQYDAYDAaDYcYwtQYwD3qzPMuhnA8hs/pzouvJPnuJ8o3Koj8ofed9Siu9I/e1XlgZXw8L/I1afiScPWpM5t7j8EfRimi7ususRcAwWb2alF+9xVqU5mUIuzYv+fL7rClAnR7axTjn3KhwPC+vQ3VVbiTo/pTcKP8Q7BN6bIPQnxd7k4UfSr7uKr9/67zYOGSaoIdos6Zg/1Nr4+uc0mLq8HInBQplpHUvDdHUedAWE7Yd27uSr8DWJAGGVAKNhV9WYYfw6H8hOdxZcCDjMthX4eTAumFUAwuOXRa0ZMG2BfV7RaWxwlCGQVfpVDB0G6YNOJ9fOt7ex7urtHegA/JKrGeN59GOJ8XuBKx6KIxfQwl6qtL2/uoKJY1WWMN54phWg6h0YnFKSCfS/fnH23nofKjl1BolCi2nrFM8DK8Gfernec3wk3SPQ6VDwrmmLZZg7qZauCToGWMdSvBJtHfT3qP79bR0fikg3VhG/ZRju8UwNpRNCWoCJ3oY5YIY+rKlxhCMFR/GYXaTNeqjiqwtQZd1hNmGlJ9tpvy2yNJNTjLa6gxt5kJVX1z//CNoDx3GDXWqbfk20OH0uK11bET4G616UsM/Qpoad6ThTFsPpoTtABoMBoPBYDDMGOwD0GAwGAwGg2HGMDUF3Dwr27yaDozmZTu3eE8or6jI27xIS3VeVVFCwNIizc6CaEqwLWmdZxqqfFvotvwub9keXZKt6Pl3wNV7IsKJUFT+QLZec3t8XHxUAIsEZaWCW9FBC2j0Oh/HD+ty5DwEB/XORbbLGSwAVaiCIGT3pfwBRB0Jm9xf+Q7kgwgvWUU9jvIS0aF4p05p0bOnRL0BveXpCB+rS3K9X5d8FY6m4s3X5A9NU7WgDZLsKJxzHka1AHosLmibBaDzNMWwLVqKHLrLK/qtBLZAMaRpooTKV1QEWqlEWRmvvqaAWxCFAWxavFBFUIDoDbGK5OBjhA+kCJW9C7U90hcdLs+rS9voaCLBrrKWOQmkWYIk5XtCJNLB+tk4xVVUCG5nNd4HQI8htaX6IBFp1KOmbJOo3bTIKjguHoOGfRI6jMrXdUIKPC3tBEHjQb8vjgEcQyp6kkuJsuPh+ofXql89oIe9lHYiy6Eer3ExlJHdcYnAaEp+D+rka/st+J3QkWZQfoDjcKBkCVPaDk2M8ySkRvJJKEPbxcAcfeKoNgDbATQYDAaDwWCYMdgHoMFgMBgMBsOMYWoKuHJHTsF4essTtqK760LFYvQQ55zLbwmVhVExnHMugJPEDoo/vKxPJQrFVtiWMrIN3v5EqrS1xlRh7YbQ1Bj5IFCnhZAexQgcgyrTfHDIyhVv7FJa58ri+LpxTSiwoKe27IEqjHPgcK4CVA+Lkta9xvRwfk/qf3RBurb8SJ3gnZO0AtDj7QtcHtLX9VcXKS2vTjufFDyITjJBxWxB2+eAYtAUDVKU+lQk0MoxBfJWEV46IAPIQdpAne7C6Bd6y35F2pTqUT/iMuCkMo7DOK/qBM+KF2suCT6eslUUnncgz46rQJ3riA9AxUY1RbFDxIfo/sPxdVBUcxnWkRhPoy7MUTYPTgvjCW7nnItVv5wIpqV90/I9AXWcRmumnhaG8jwd7QH6wKN/T6GTkG7TURHSykg4tTxBXz4NRPBsjPAx7eneNFpXp6VR2CcFLQ+YMo3WuIlTpTA2NNWP+SCSixcnnHp1PL48JT1xCe4L2lWB1qsEKlc/O+6pUFhYZpwgQ3HORXBf4ild57h9dRqON7hOm19pUYLSytCU8DSwHUCDwWAwGAyGGYN9ABoMBoPBYDDMGOwD0GAwGAwGg2HGMLUGsD8vWpvuAnPNpQ3h4jMN4fYHFS6+X5My8rspNgOgI8g1WAMQtuXv9hpYsyhNGurysH7OOddeF/1S5b26JCiLBA90hMMsRAJRtjLdZdAhNTgiSa+2Or4OBvJe+S2OOoLaiaMronPzlAYgA1rH7KGyJgHNXuW+pOn+Ku5IWq8mmreM0lHmHtSl7udrlNZaZ13liQHtKbSlAWggvDLYAk24s0s/j3bYcyCoif7MmxPNprY6QTsSD61OtP0K2tYoe5cY7FhQV0s6R+f4naH8+NEmZfPOSOQWr6miaUB7UJrWM2GbYpqyWXCg2fMebHEaahYx0oqKGoERVHD8x2CP45xzMWpizq2rMk5pHI4roPVfCZqyx7EOmdISgm9J06GhNUtKBALU802rlZuwnJnStoWCHUynbZzQTaXZ7JAdyZQ2HWlaPixvom0e337jaWPCpiqh3bwcr0HUX6Eak2iRQg/TljOgS+vCWpU2JrWmEHWaoN+csPqC8tHSZsKKBf9WOlXKm2BN9KM0WJNGEMVGvxeMrzQd3rQ2LdPm80LVNsOU6DoJsB1Ag8FgMBgMhhmDfQAaDAaDwWAwzBimpoALD8SN3++XKA1pyu6S0KGjHG8pFyE49O6rbB1ReSDbl/0q0BIqsobfl7+RUg3baps3k/xtG3Rly3b/dYlosfB1prKijDwLqeLuOtd9BPkGz56ltCJY1TTPSNv0FtkSo9iUI+dBX+qXU3QzRlPx+vzOhy/Ujn3uwnfqlA/pvPZFoTk13dy+sjC+zjR4e7n84JSsD5CyOmpwWgHaFClFFcViuC60fCarttHRqqSLruvKPgPtUpDmnWcLE4dRSLpsR+BvCtUZLUFklb0DLgMpC8jnKTrUgTVNpKJu+FhftIhRNjhuR+rkEbXDdSc6u6/aBmwhfE1nYxktkEEgraSofYxCgjY1zjnnDk/5/7BpliBEG06Z73EenWQXoSnPNKoU8nLUkSeMbpBGUyMViVRZSn1TqW28L5UOntKah+55Aor+pEHvnNwPXgjtqelb7H9FlXIfwX1KKhV1jqdltWwEo4RMrCdZkFHBOIm0TReWodcuAEbMmJCveCm2LVRI0txQYyOAuqfQw2n/TlKMyD/23yfq9DiSiATYDqDBYDAYDAbDjME+AA0Gg8FgMBhmDFNTwMN5Oc3nD3mb0x/ItmT5jtByUZ6LjyAg/cK7fAo283Bf/nheKLp+hb9RkR4dwta2pi/DHTmN23huntIqb26Pr4u3pIzD11coX2EHtphh23tY5m3Z3CGcllKU9dEFocoWfiht46mIEXhCMoYt6kGVKcrOqpSHkVCcc27uutBjh88DtTtgyj48ki17PLXdOssnxMrvSx9FOX7n7uIpnb6E02P6tGzcOv50qw6AnrkLVL8OgI5RQiASxgQhBCdpJ2hfrBPS1As1TjyQyB3eQ6lTfHaVsvl4ahfrp2iUqA2O/IoeQTd8DwPAK6rYrSxJGkYCSAl4PkGPA3WOFHjcaPKNUEevBKe2Bzyu46GUHzX5lL1/+UJivU4dOLZ8fTrwCWhERRvR4dMnoH9+VAYUMuUp4wkKjDMee49zmuaaTkLCp1lTMj4NWpZODk95Ivi4v08KFIGCk/BEKJ0WTWl3fZI4KXKLpiVpPUE5TFZFzMI0tSZTtI4UijbOHP+7Q5SvqvtktCc4PQzvnHaCN1WygKel9ZhPmyuApPkwQfOmnDiedk4hbAfQYDAYDAaDYcZgH4AGg8FgMBgMMwb7ADQYDAaDwWCYMUytARyUkrNm68JT+3XR+QwvLlK+EVizZJrMy3euLo+vY/gs7c3xN2r1hmiq+ldFAxZuHVK+zjUpr/SAoyIMV0Wz5fdHkI+jPbTPQCSQYm18HXSZa4/AQb23yrqH4rZoDIIdqePez7BdjAdFVm+KzsnvsS4jgsgHvQXW7KFFTNgBXYayxOmclXYrbMizyu+ztmFQlXdBnadzzo2yp6N7iffr8odytfeKEHUik2xHEDdS7F1AR+iBRQzpC51zbkXGdrwHdZpTtiegddHROWLUcIBOxVfRZOgesF+Z0KygZlFHAslBveC9vEOly8O2As0OWrv86EbQ32K7OxVBBXV/Wm+5JDZDDvWLJdasov42UM86JTMigdbN4bRArVCaRk3rzfwUvVFiGU+Wj3R5qGVKdceYct9AaxanvQ/vmTIqwtT1eJyILNPme0L95U+LCd0bQOvvxtDtidGTtJAQgfoyT/UrtCmtSVq/R3pT1Z6oI0zRX/pkAwPvr/VvoL3zMyoCE+r+8HciVR8Jvxlav5iijyVdHkY4SSmDEKk+mdASC9I0jEmwHUCDwWAwGAyGGYN9ABoMBoPBYDDMGLw4bb/VYDAYDAaDwfDPHGwH0GAwGAwGg2HGYB+ABoPBYDAYDDMG+wA0GAwGg8FgmDHYB6DBYDAYDAbDjME+AA0Gg8FgMBhmDPYBaDAYDAaDwTBjsA9Ag8FgMBgMhhmDfQAaDAaDwWAwzBjsA9BgMBgMBoNhxmAfgAaDwWAwGAwzBvsANBgMBoPBYJgx2AegwWAwGAwGw4zBPgANBoPBYDAYZgz2AWgwGAwGg8EwY7APQIPBYDAYDIYZg30AGgwGg8FgMMwY7APQYDAYDAaDYcZgH4AGg8FgMBgMMwb7ADQYDAaDwWCYMdgHoMFgMBgMBsOMwT4ADQaDwWAwGGYM9gFoMBgMBoPBMGOwD0CDwWAwGAyGGYN9ABoMBoPBYDDMGOwD0GAwGAwGg2HGEE6b8Zezf2l8HY9GnOj5cOkl5vOCIPkBUIaDMlwUJ98STPn9qp4bD4fHlq/Li2NI86BOvsqn2wORUj6XEUH5072/iyP+G98T7pvoh4Q+0v0Tpz0b8LvDX58q39PAF4O/IH943J70XmnjBttXlTF12+OzBjKe/GyGstFYSxn/2PZxv89p2aykYV+qfvWLxcQyksqLer3EfLp8AtSX5objeUNQ7UljLxMm5xsOJF/I7etBe/924/+ZXN+niF8p/xWoAL87thm2A44R55zz87npysB1Qc93XHex/dQ4i5pNeW4uR2lJY2FirYY6YlrUbnM2LF+PH1g3sT2mXcdpLjnHYzBlbuFcwPd1jsdg2jzGttFtiO/1282/m1iPp41P/Sv/l/F1/Rq3YX5HrpuXZBz6alkYzMuYyu1wG66+IfNu/zlpj8az3A+rX5VnN8/Lde0G9//+81J+9ojrEbaljo1n5N/nbnK+nU9LmfPfgzUz5DnUXpXyCjucdvii1P/cb0ta2OH5tflJeefekjx39Y9VeVfknbvPdilt/g9lrMTQvPl9XuO2PyHXtetSfqCW50ERrqtcj+6ilHnrb/y7bhrYDqDBYDAYDAbDjME+AA0Gg8FgMBhmDFNTwEQ3hCkUaAINOVGc2opPKi+NliVKIY1uVpQtUVaZABM4H943GLgk0LMi3kaO8dFYns6H7+xSqHJNAyGwvYGi9GJF0SXRvhOUapSYllqPDxBIAeqxEfWBKkRKdaj7Dt5Zv0eUPKYQfka29ulZKfdMUOxAOcURXvO8ofGKfRfy9E2jfSkfUml63hQKx94TtRTVh004Sh4L2EexGkKen0z7Uj5F+1K9Ot3EtA8KXiEvz2+2OA1pSZjjeI9zzsUwVkl24BTFSHIVtWbAWhh1gaLMK4qS5DXJ/+fHcTYxjlHKUoB3VOs49odfKlIarqF+uST3KBrZx7aCukcHB5wPx79qG5eBdQLHtFrH6Z0jpN55rgZzVUlTdH5am36Q2P2I1H3+HZ4/O5+Ud1n6lrxLd4HHWm5f0trrqoxXpQ1LG5I22OB1p3lerlsXpG0GFW7D5e9KnZrrnBZ2pfywJe1Z2uT+amxKnZoXYEyq9SNsyXv6A06b+6HUv70iac1z6vcPhlQe6PH9l7m8wpZcD0Ieh8Mi1kP+vXmW+2HhLajHeaCleWrQGqrX0/U/TpHsJMB2AA0Gg8FgMBhmDPYBaDAYDAaDwTBjsA9Ag8FgMBgMhhnD1BpA0o35WiuXoFFS+ZLK0/ehjlBbSpAeCq0J9PF+0MRomwpVoFxqjVZCnXS+NPsEfDK1oaoT2g4k2mg45xw2m7Y+QB0EXmttX5LEMEXX91iWPh8k0H5F20JQ/aG/UjRkaSBrDQXSAaWMc7TF0Ho1LJ/Gr9bypej+CCka0yQLGk9bWuB9STYtugyVRtrGNBsT0ukeb6vjXLrG8jTGYQx6yIm6ko4O3leNVWx30gM650aNxvga9YDpWksc79wfHnp/qHUHxyTqNSfaNZtgU5ThuYW6P1yDnVPaPujHCVsVwOhQ/EL8POso0+yMPCg/VR8J4z3VRgnXUzUGJ9ahEwJq1CI1PYsP5B9aZ+TfcyyjdCu/9v74+ui/PEdp+y/C9Svy/nllq5I9lLRuR8aQP+B8jz4v1/ktSnIt0MQVwMJm62PKjieUZw3PgL3PPufL70p5w1+pU1pjqzy+PvN7Ut/Da1zfTFP+7l6RMZR5mHx+IV/gcTMswJiSx7pMk7K5CKrfn5OOHVTUdwIM87DDafmd6TTgVN5j32EwGAwGg8Fg+BMN+wA0GAwGg8FgmDFMbwOTBqRoyOFd0aFBsh1BEuk5Qd9mEug8TQ1lk2k/T9MAP65DyvF+srNIoaj0c5PaY4LKwvdMsHNxzqVHYMBWjFMsXPAerEeK1YumUSetVU4IGOFE26XgeIO663xIA030Od43SLEmmZJ6ZIpNzYcEexekopxzLu505B6wtNDUE9GPKbSUN6XEgsaGbsMS1KObHE2EI3woG5OEKCkTdHMKFR2nRTL5gIB2Q76yd0FwdBdlP5JCqVM+oDlThCzUlmnRXSbWvoSoI55aZ0lSg2uctsfCNTMtKg5VSq1jbaBsS8m0bIxzS6/3GMVpyjGI491Xdkhp7ZtmafZBYliRd9n7OM/P5/+9H46vb/zNV8bX/Xkuo/UN8XCJfrVDaaVvSNvXbknb7D/PvxO9GtC3lw+l7PsVyld7G8aGjvYDkTyQzu7Pc3/V3pF8jVja/bnP36F8t7cuj6/zv1GjtDNHQCPnpbzl73CdDp6T6zAn/Z854jlUuyVzoL9VpbReDaKwwFTZe53fa+Ub8P4FuWfuHWV1Bm1z9DzPpxt/9fE/52wH0GAwGAwGg2HGYB+ABoPBYDAYDDOGqfcM0070Ij1Ep1lTTq3prfhEelS7rAPlgOUjJaXrlHqqFiOcKHqEqK0w4cSmc0w/6xN4CREOJk5BIwWWEDTduZ8QOB1p39Tg6AmRQNJOFWuk0MofJIimSQnYTv2ackp1ItIMMeLJ7ZkY/UVHncGxoqMQJFHRKWOD6NCcGodJtJdzTLNhxBQtsYA2xTk/cUI+JQIHPRspZU03J5yEnRjj0IYT8yFz8vRbgFEsFB2IJ1opTa2fGEEEo2I4p2jJtBOm5IIA/aaOhOKc0VQ0Smr8bLKEgNZGHO9akpMSMSkxYoaeM0C/0vhMcXqYQEJEFg0cgx7JYdS8gLE7IdE4pVPA5dvyjr1FnlvNX355fD0qyftXr+soHpJ25h/y71/9qly3IHJH62Vu9/Kbcl/2N+bG1zndhNDN7TXlJAJN35uXdxmVue/O/eV74+u3vyY07/U/fIbyDdflvuVf2qC0R9+QY9HDsjyr+Ej9FgRQjy0ZkyP1qXF4UeZA9+cblFb4fTn6iyed4xKv8dkm/OYXJe3oqjqZfATRX77Ha3L9M48/Dm0H0GAwGAwGg2HGYB+ABoPBYDAYDDMG+wA0GAwGg8FgmDFMf24YNFUTFiaglYpj1A2p70vU+WmNCV6jtiUl8gGx41qvRpo6JUbAvFhHrVFCrUearQrWMVIu8aPj9XapOkLSlKVoL7V2BuqB+siJ/sJno1ZS66vw2TqaSFq9PkCgvmzC7gJ1fwnRaXS+CZ0q3hdBeXocYr+iRk2Pa7xPl4G6rRQtm4d2PBANIe6xLYYXwnul2btgmtasYr4UHamXYn9CliGoHeuoOUpzY7q6p0WrOSmQHYmOCqHH2o+hLYvQZkSnJelGtXXW8Hjd6MQYRJ2b6m98F2z3iQgxCfek6VX1Ghe1JYJK6rqO69gwWa+L8ydVK45lpK27KUjs1+PKPCH0PiXhJPy3y5S2+Slpj4XvyL83L/JYW3gLbFXOcRu2XhGdb+ZrMh4yBdZ5Nq5Kny99U647qypSxS7YrxS5HlnQtpUeynW/xePk5t0r4+vBJenX1Qv7lO/oj1akvv979r7J/IyUH7ZwbaFsriJyQ9c6I22TPeR8Q/hMGAx4zQyrsJ5C89a+xWNm6xPy8Nz78s7l97lS+UNZ/w6u8bOCzeQ5mwTbATQYDAaDwWCYMdgHoMFgMBgMBsOMYXoKGGkobQmBVI4HlKLeU02zY4mQRgYqYtr6acoixRKF6Icpj/67MHv8vztFMeSS7WjISkbRl3ECRTcRcSIheoRzHKGALDwUXYsUDkb4mHgWRcXQdOPTCSLzuCA6cMpoHI9lb4PPQoophepKpYeKMB50voSINJN0FlB6YXLUGXqufhZGaAD6NtZ2MTiGdJQUALWgjnKRIDGYmF9gIcJjUtUJ55tee1Lq+EGBKP+0tQCjeOhoFxSBQ9HIWAZGflGRMEgqA2PJcyn07YRsAsooiR1N3O2qbMdbAk2MfRy7iq4n+5SU9ydpADw3UtZDNE5S7GdoPOoxSBUEGUKalEPPzylp5KeN4UNoz2scxcP3ZVzWczLf11/Ypnz77bXxdWGXx3IQSv/1vng0vo5vcLSL8q60aeus/Psoz+VV74Llyha3YWcV0sC1JQ64v7pgdxM0ZBzmQ+6v4D2wUvnfNSlt+Ia0WwaSlHuS2/uElJndksR+leuEVjL+Pf7971fBSgamZfU2P+sIon+EopRwvlreCluyBtT+rU1K6/yHYm/j/oabCrYDaDAYDAaDwTBjsA9Ag8FgMBgMhhnDE50C1lv7RB2mnA5Npe8wwgNGCEg7weqnnA5MiKzhnONTthiNQUdWSKjfJGBvd6jqW0qgPXw+RYkRQzw4STzh3J8SJYWisCA1pSlPpOmHQPlpp32MGKJOqabRnh8k6HSzPj2ZNA71+6fJAxKibqRF+PCqcAJPnSqO8yljCp4VlWEMKZrKb8u2f1QAyn6oxjxKB3QaUKU4zjXNS5RwAaM/qDaEOeTpd25IlAvsB70yIB3JfadOuyL1qfv8FE6j09jX61MCLRmpNsLT7GkRUmjNVOPCmxMqLm53IFsy3TxxuhdlBBjRqVpxSaBnpclG9Ljown1IWWspBNHDydKjVCqaMqZEtEmQAOk2jFoQuaWi2mZaKcpTRpyDdbzBcpDgEE7mvi3/7n1lmfKVgaJsXFLj5qHQmd1Afq/mb3A9enDItnsV5nSd67T/gszr4ut7lOZ3ZU06CGQ9HZV4fSrBCdkKnJB9P7dK+eZW5P1Hv79CaTno8tU3hG/d+iRHeCnflPqP4FXy+zxfD9alwPIt/qQ6/4+Fpr3xV6WO+69QNpffkbZBWvrgJX7WACKezf2tc5QWVR5/LbQdQIPBYDAYDIYZg30AGgwGg8FgMMwY7APQYDAYDAaDYcbwZF4eWouBFiaj5CgWZG+idS9orZAQPSMVKeVN1AM0UFFJtA3eQOl5QOeEGi1vpKwfMlJHv6VsFkBj5aHFhori4OC4exyl6FlS2gMtMSiygkvWynlBspWIC1PSPgQRGTxtYYJATaWOIOAn35cYuUVFvvDQwqQoaVGZ80UZ6IeM0hEOpY5RFmxaBko7heMXNXVa54f3ZJTWqYi6P3nHqKBsiwBY96CdbLPhOsqepAxaGtDEavMdjHBCWldl6UFrgKfa5hSkqFhXsjZxzo2aohULymKrotcxjIoxoS8myxHob91XqKGECDET9kBQX23v4qPuOQvP1XMLoruQnVWoxhn0t+cpK5WFBEskbaUDvyE+aKhRezhRR2XbQjZNHbhPtWGSpU+qDYy27TkFK6IfPVguw0P1mwxVPHhBroclyub8RRkPube4bSr3ZOwdXZaH9Rb497R1Tvqr+h35nWyvcb/2VqSdorcWKA2jZOQOIRJIxO/VWZFnlR9gAVyn9X/p7vj61tcuUlrYlLx3/ifyzrlnOcRH555oPXO7UsH2Gj+r9paMjaGaoo/+lNjsjApS92t/v8X5Pi/PWvt6Q+p+liO8zN2VuXx4med5h6WOU8F2AA0Gg8FgMBhmDPYBaDAYDAaDwTBjmJoCJmpMUWjaxmCMiSDnycG7qQxM0zYP+DdSEdpKAGlpRYnEefg7BIou5DoNykDzQXlBh7f8RwWpR6DK8LuQ15f94eCAt4ApAgNaEGh6Ad5fUw+JkSt0GxKFkex+T3/7imI4pQDoqcDxhvRinPz+OuoERTzA8aWpvjXxPhhUsnDN7dSvALWrXVugWvl9sEFS7vcBjiGgx6Ic193vYT5FqxWkHnhfHPKzRjmgvYmiVv0P9HOg6GY3lLkYHAidodua7VSi4//dTVpynDZ8kAMg5eucoixV5I4k6LnElHey/RZJPqBtJ+jLClDRRZYoxOrvcb42U8UYtcXBeHddRf/jH5qKxn7NJP8W4FpDtK+mpRPe/0dlwDwupvQJUsJAFU/0Cf6e6DJOwYrIOecWvyPtVn+e0zyo4oXfkb6886/zuuDflfcfVLRdmLxXpiHPGjAr6db+WK4jiB7S/DSPoQw8q/BindLK/+3c+Lr/l8UiJv7GEuUbwjK8/csiS4hb3P8H/8UFKe+LLCnJ1KSfw+/Jc1vbih+fk/HVBalD5Tavd5kmrpM8FpqXpD1q70ja7mvciJ01yXfwvKQNl7juu6/IuMw0KMnF4XQRrhC2A2gwGAwGg8EwY7APQIPBYDAYDIYZw9QU8PSnccG5fWJbHr439Uk/pHAx6oQ+EYu0HJ7E1HQDVimvKGCgrCKkgLP8PTwswunenrzXsMLlRUDZjVTkB78P9HAXTkQG7CYfNOFEXwdO3EWKN6SIIYrmA2oiLRII0UVp1Bv0gz5Jq13+TwxEgyW7+qedEE6LOkEnfyHSQrTA/dVbFOqscU6e1TrHFABu08dqCuX2IFB4Hk7c9rltIxivQQPGid7yR/pa0YUoRUA6N1LzJsqgxALGdU5JGwZwYlK9V35XxqHfF9rHO+Sg7DR/4VS8X2F6JO4oOhLL0Ce8TwBI+/p63UHnADwtnBLtQp/sRwqXx7Gi4XF+YkQjRetGBXA9UFR+BPIVv4fRmNR7oYNDF04VF9R7RRCppqVO7WIboHxFrXExnJCmsaB/gzKwnipXBVoLh8lUMdG5OB41zYunirXjxClFAtl/WepRepg8DzY/IXNwdKjkSwvShme+xGU0zsv8j16Xhay7z+Or9xDaFJaP0ZGi0aH4dpvHzdxf3Rpf9ztS/v/qL/4m5fv1//OfGl/Xr8g47HW5Dza/CO+plslOG+bDmuTL7nEZSPW21+XF8NSzc84FHUnrfIrXuGeWD8bXh29K5A5N2Rc3pHEwssri15NP+lYeqr78ZcUJTwHbATQYDAaDwWCYMdgHoMFgMBgMBsOMwT4ADQaDwWAwGGYM00cCwaPuWlOGOhW0bNDaFtBVTFg7oEAAbQy0TYfW0vz435UmLaqI7kFHRRiVjtcLDvNKHwMaqD5YwnhKUzDMgUXMQLXNCLRdAyk/e5hs7xLAu3jaBgbaZkL3iFoXbF9t04OaG7RLSIn8MaH5O61IIDhO9DjE8YYaK0/9PwetT7Tucb4mxYPur7fMNjBHF0D3d1bK661yf/Xm5dm5fa4HjmTU/flKAxi0Yd5QxAwd4SZF99gSHZ2XAVsQFXUk6B6v+yNtoGN7G40oI29WgPEVqjnv79WlHkWYryrig5eivzqNKAxoA6MtV9DOCS1hJtc7mHcT+lrQtoH+cSIaDayFw3URDmk7q/4caJ5yXI+wCeMfhsIoz2MpPBTtqY9jMMkCzLkJG5gYrDQoElSk9KU1seYg/Z6OwJESdQrr5edAH6nnO44t/H2a0ApCv6p+iFI0qh8katdBe6aiQPggYazcB513wO9V2JZ2OniO23D+XWmrelbWwud/84Dy3ftVGXveRyWaRnizSvnmbsl1PcNtuHTu4fh6IS8a0P/fxquUb/c1uQ7ARyss85mC9UWpx8Z31ygt7Mh8WPm2jK9H/zKvO8NNmb/da9LHpbe47rlDad/Kf8Npd37u7Pi6Co5Dc9cpm9v7eZjnu8kWa8EZ0R9v51gr3X9Y1dl/ImwH0GAwGAwGg2HGYB+ABoPBYDAYDDOG6SlgtB9JoSwI2pE+hR6m8nDbX9OcuGUPliuxdpOHZ+mICYMiWMmkMBhIgfkQFWFQ5Gf1akDnjHTkErhE6wxFCWUyx3+LB4ra8A6OIFHZQiDVgVRxR9kx0AOAlsmkRGqIHt9l/AMBUtZ6DGGfAy3jFxQVBW2jLUcc0FQ4bgZVbpvuItC+54RvCQrqaH5H7ouOuB5+wrTxB4qm6sN8GGL0DJUvzVojJ3PFB0o5UlQMWiagNU2/rCjganL0A5wfQU/emSKaOOfiKrR9Xca1pksnaFbEaURhQIpW2YX45bLO/aN8miqF9UrLK5AOp/mp1rhoTp4Vw5rcXuc+HeZByqL6LQsRHgJ4leIjpjVjiBBDNjPDlDGorFmoX/G+CQuvhHfW9iswJaODOqeVROYQt4Q2m7AmQ2QSIik5/h3S41FTwieFxjNyPVhgCjS3Cb9xMLz6c9yGwWfq4+vyP6pR2qMvgiylJX23/SnOV9yUMrtvCH0/vMJ1alyUOmUPeCz/8KtXx9eDKlDWWZ4bf+2X/+n4+usH0gCrebZAuXkkEUTKLzBlfXhX6l/56/fH1+EORx3JHsl7Xfk7cn3rL/DYaD4jaZVbKjoT/Ob35pPXqvCR/HaX78q/92t8T6sC+dhxxl3+byWCivs3Ex/F9Zsum8FgMBgMBoPhnxXYB6DBYDAYDAbDjME+AA0Gg8FgMBhmDFNrAEkPpi1A0GYjRaNFobpSnoUaGK17iVHzQ5pCLnFUBM1GysPQ6kVXKuzIe6KuKdIR7oDn76wp/ZIvaWixoS1n8qCJKMC75JT2LuyJroIsQZxzMeZNC3+UECYuGvQoH/Wf7vNTCn+EmNCeok4V9IzapgHtObSuCLVyaBfUL6lxiK+PRajB5h+C7qXBaaVN6b/cHmgWW6of2lB/eMeJcFV4T1aFYcIyoG20PhLfZbgqaQOlAewuwrjuq7kHViOtoTRU2OY6ZUHr6HdBv6ptNbSFCiadxjiENUm3M2nHQIep7atQ96c1jxgiD58VLbLNw6gi2rO9l2TNHBaVXrMm14GWA0N/V+8fHy7QOefCOvQJhoXT4d5QH6e1cTjXUAMZKi0zhsJE7Z3WQ8Nc8JcX+VFQL9RGa1sxl2AzE6m5RWtoir3ZSQKXmsJ9nsfdNdCpQrsNK7yOH+2KVrKqNGrVH8L6J9I+tvBxzpW25VntdVhbmtxO/WVo6wGvp5Vbkrf0Sn18fbDBY74YyNh4682L4+uNS6zzO1+Vv30l9G+1xbbmFuj++g9KlG/356Vfdz8G81xtmwUd+YfuEj+rcgeeK44wbvFTm5Rv48by+HrtS7vj67t/fpXyFe9In7TO8+/fe//asntc2A6gwWAwGAwGw4zBPgANBoPBYDAYZgxTU8CpdGCSFYOyokg9Lo9lIo1Q5m1ZjPgRQYSPYZmpGKQwRgX+zvVg59Tv4h/8HkQPA4I+b/MOICqCppsHVcnbr0ndgy7XaVCRG2MfttFHTB35XXCk32cKGIG0UqztYmALPx6B+72m0yj6i/q/QpL1zwcMpFv8QoETveOjk2j6jayFNCUE7TbKJdOLOIYCoHn9baZi8ntSXvkB1y/sgB1NXawq3BGf7yfbiTQ7HniXuNniNHhnD8oL9hQFvipcT9iTtJFiOn2IQtI5z+MwPJB6hB3JN6hwe2Z3MJID2qIkj60JWckp0W8/BkaZ0IhTotF4EK1j4h0GIPOAMd5f4rXw6KJ0SmcV+uOsjjIk/Zjd4vGOspQAJC/ZXTV+oPpeE+jgMIWCVxIV6mOMuqHsp1CiEBegfZXlTOwlRwLBOR+joiBSYwv6aARzJlC/O2Srpd7rtGxghjVYP4bKfgTmXdgFuUZLreNAXzZeY+kJeqRVvivvGKkuf//PSb68uKq4X/jsm5yvKdTrnW+cp7RMAyKS3JR8rsL99d/8p396fB3+kkQMKWS4T7777qXxdWmpTWlrHxX6dWNP1rvFZ/coX+fLQqm2XpZBlH+P+3tUhN/4da7HPjC4678tfbSxwHRt7YfSD7f/Z3JTlOX1ubAl/Vp7h/tSSz+mge0AGgwGg8FgMMwY7APQYDAYDAaDYcYwfSQQTfsikOpAikZH50D6StPGQF/RKTiFqConOEclOLGpTtX255BG1Sc95dnZOpzGU478QUfuGwKNPMrye6FjeG9BnQJeEKojk5Mt+0yGt7ZbuxA4fiTvH3YUZdOW7edMR51UwwgFeFQ5ja71kv8PgDRyNFLu9xPu/ScDL4RTgYo6Q8oNqbkJ9388LaxPSENEhUwD6PYFHl+FbbyGdlLNUtyROhW2mGLJHMAJyjo42Q+Sac0YIi1MUPZp/YzjAejHiegKPSkj6EIkgAE/q7eM0gk1v84JXdKKYbw2uIxcVdKyhxCtoVikfHFXyot6iqY6jQg1KK/Q9C2eEE6JOkHRaKqVxHx48re7yOVhJIjax2VADg+Zvhx05T59Yju/D3IQHBZZte7siywhbsi1XqtjoK/16W3MS/cpqVBU5v4fo6BOtsMpcjrl7pxyowDqWY8fvAVpYx0JBGjeeKAkGqckQ6i+K23Y/TTX6dr/Uep0/a8Jzekv8qntM/9vadO9l1jO0DkrbdBbgN+4FW6bPJxAztXl37/3n71K+Q5eAir6CksMBlsS1SbKS/nzq0eUr/78wvg6+5aM88IvMH2Ljh7FHPfP1rfWxtcjkGV1CpxviAqjQ3nHYYnXnDNflbn86PM8H7J1qUgTTgG7OR6vnTUZX8vfk/fvLPLv8+Jb0s8Hz/M8b/2cCg0yBWwH0GAwGAwGg2HGYB+ABoPBYDAYDDMG+wA0GAwGg8FgmDE8USQQrT1K07okluHzPVQGut9X1HF8SOstiH5hmFfRCLKoy+Lv3ExLeH+0iAlbrG0IOqJnye9LefrIfW9O2mMi6kgk/3BusT6+Xi4wX383L9qG7Z642odtpZsCLULY5OPoXhc0DMM03R9UErWdWg+IeibV55G2eDghoJ7HqTEUd0Hfk2Irgl0UF5WFA0ZoAI1R7pDL8DHCRSdZH5vblTqFdbYjcPuHcg26v1hpUdEWhKK4aM1fiv7WA/uLuAfvqPL5DamjtwpaLDU04ozUI1Nm7Uy5KO98CFpMjBDinHMxahHTInpgRA1tA+NO3o4I9Xs6igfOLdQrarsY0qUNeC55EKmmtyRCpMYFfvfS6xIx4FfPvTW+/l7lHOX79nuXxteFLdYvlR+CRvkAo9EoTR1EZ/HmRJcYt9SYxnVc6TPjYcJviNaKh8fvSwwryhILNYBas7gJmjDsI61dhnUMI1DFbdbKkfXLhA3a9FL6pwmMOpH/epnSGs9K25z5svz7UFnW5OqwZsbJVjKDSrKVTGFH0poXXSL8s9Kmgw73w5/+y98cX//j77wuVfptjvAy+oj0wwDqu/FPLlC+8OMyLgOf+2twXt55cUF+h/tDnl8ZkCmWNkAb/mvblO/eem18XX6b14PWRemHhe/D7+k+61m7YB8Tvyn5fOXoNKjKff0KPyv4AYyBP++mgu0AGgwGg8FgMMwY7APQYDAYDAaDYcYwfSSQMNn2A2kp2tpPo3XSLBLA/T1WweoHFdkC7VXl+7W9xt+ySMWqnW2X30Vbe3BMbyfTSUFLtmiVObeLMuCm3+V3DrJS5meWJDL0QsjH4F+tPBxf/6PoI+PrJgSrds65QUnqngsUpYZ0ZgeCoWvaLMm2R1M2aG+gIxmk9e0HCBprKs0H6oyiKZTYVoIsKHR0gSKk+cljAy1SYuiHzBHTocEBUGR1tjRAWo2ifWggFU/0ve4veGcV/SRGCg/oyLjDVJfLy/zyhmgDo6oEkWyQ8nXOuWJWMh+UMRoGT0S0borxuT1lq9GDfMpyY1r5yVMFzh8dCQTHZ1beaVKGIO/kqYg2cU7ui7K4xnF//+zyxvj68+V3x9fP5jco3/f/6Nr4OlAuKGETIusg7avGlsupUDA/rru2UUKbFSVloDEJ7REVk21w+ovSNp5anzqLst4VNpmyjkE6hBYx8VHDJcEbgnWMfq+0+allACeEPNhPNZ9RUbf6Mr76wti7i/8905dbX5CIFN0VLqP2DkaTkn9H+yHnnBuUJN/a6zL27t9W0S6+Kn1y+Bw/63Ag/XzxH8m/v/8/VVKEgcyH6gtC8+e+vUDZSl+Uft68xzRyZl9epnpGZBQb9SrlG9VkvDWugcXYO/xeGK3k/N+7SUnv/Y3L42uUqc2/Rdlcvi7vtflpkMCpjw20iGud5bRROcWqLwG2A2gwGAwGg8EwY7APQIPBYDAYDIYZw5PxJ+oUlIfUDrq6K4d3pEQm6CukToA68Ju8Bdw/J3RevypbqiPFxLQvCQ0V1vk1owBP9Mq/59RpYQcRRHygwzQV4RbhZK46FDcKgeoAXvpnStddEqILku//cecLlNavSB0HNT7RlT8QWjn2kk9YEmGB0UPU62O/6pOpmtI6MUDbx6MUOhDfecD0DfZeGoXot6X8UZ7zhSAJwDoFLVWnI4igoGkkHQ1nXF7yVj6dLFXUoZeB/tLRCfAEPkbd0dTe6HhqW0c4iap4ElZRETDOC/NCMccBUyxBF+qEJ9jV2KKTzylRgk4KSY4FzjFFT3NEU6rQV26CXpTFrAsRaKJl7tN/beUPxtefy0s9/t4Rt9FwTuoR9ri+QVPGk4cnXbvMFcdVOGEIJ5g9Nbe8PKxJ+p2JOgd6PMPr06gk9R/Be/Wqah2DadJdVqdbUdoD1xPyAmh7mjOass8eT4H/6L7TcURoXJYGyDR5LTl8Ueq/8jVJe+ffYaq0fAvGa1adloXfmuYF+E1W0WRCUJHE//nK+Hp+hcfa0TUpo/Yul/HON18aX3v/m53xdelLq5SvdUHea/+RRDj52L/F1Ov3vyayB73CD5YgcseBlNG/z44jBWjTKAeuD8+wg8cQoiTd+HeuUBp+Dyz/QBrqwc8p2QfKfHDo1Xi8HvwZScx/l+vb1afpp4DtABoMBoPBYDDMGOwD0GAwGAwGg2HGYB+ABoPBYDAYDDOG6TWAoPub9oi8pywSKBJIhssg7Qy4tQ+W2OF8WJB8nWW57l5grry6JHq4dpnr0QWbmRBsW+busO4jAt1X0FbaEUD2UN7fX2edSr8NtjWRlPfJHOt0vgfarqIvzyqcYb1B/8acS0KcOV7bFWvnetT9ofbylOwMHgcUQUGFXaF3Qf1RktbuRzclJ0F0AdL8Oee8PmjgICLBRAQWdN5XER9i0E+RXkxpTD2YD2jHlKrD1GWg9Qvep+cu6ghD0NgqCVS+IuP1fPWQ0soZSftmXUID5LQkDG1gYE66Q7bLwT6PWp3EtBNDigUSrYUYwUTpNck6RJeXOX5ZjiMex41IynwwFEuMB/3nKJ/fkTYKetwJEaxDAdilOGUjRO8CYzxaYAsXvwH901EWHqg3xfVeaa/7Ncl3eFnaosfyNedgWZtXkuos2Od4oGecmO2wNnhF0ZdHdR7TtE6oddIvqb49IeR35B27a7wWFB7ImNp7BTTKDR5rzcuwjo34vQYgMavclmeNvsBt023Cb5IHmlUl162CTK9X42c1Py9iueF7YrMSv8C/u/NLYu9yeGt+fP3uDmsF0T4l6PKz8g+lYr082Luon8nW8zJuPvfcrfH1d3/jRX4W2ueoRa52XZ5981+BeT3iddfvS9qF35Xn3v1VXnhDsLAbqfb1nkCWbzuABoPBYDAYDDMG+wA0GAwGg8FgmDFMTQEnRo9wil5CCiQtWH1KEHVtLUD1gNtwmzdXZduCpbJQwJkqU0rXu+tSRTje3ZvnPdXSXaBfR0gvqu1b4Me8kbK3AXf5EPaYHwyZ2n0hK234/nBzfD1UAapDfP8wmdqkAPNpLvYpQOuXiUgGCTTVBw60AVFWFb4KdP5jxNqqAi1yQkW/Ab3lo72BirqCUTIo+oMeu1hHTTcnRtBR2RJsJiYoeygj0vQbMCl+me0DuAywGSqCBcci1/3SQn18/XrtPqUNIGzAN51QwJEaMhhdwE1rpaHofG1PdCJIkU3EaOGDfarXQpRh6PW0I2Mm04J2VxTd3T5HCfox9gbcv1Ee20jRl00Y5Chf0PMdhzFSnmq9IwsjPR8x8g2UMawwzXV0QQZKAyJclJ9h6vFoU+jn9gEPrvxBAk0/YEoRx48XQr9qCjzBRsm5yfXlpNC5JO/idZT0aE7eZbgkc2vlK/wbF4At0CjHY2PvVWmb1W/L+w82mPbf+qTkC0FusPwdXp/v/AVJu/QMRyTZaYjUK4KlILzPY6N3U6J6eC914N/ZYirTAQsXFU0jC58Dvbq0hz/k949a0s/3/mORVWTXKRtZrnUu8DoW/ZqM2cI3ZL4uf4/HzAGoNu79aalTYZP36HAdvvZ39ynt7j/PEU+mge0AGgwGg8FgMMwY7APQYDAYDAaDYcYwNY+X6oQ+xKgAsI2a5kytaEk6wQnb756ieLJNcCQfwgmxNtevXZFt1HJWHz+UOmJwdH+gIhqUpMxwH6JsBNxs/SqcFuVDis4NpQ0edmrj60cqdMk9oHq/3rw6vo5GyrkfTvFpuhnpTKQpNIUYD3vH5pugqfCEnOIlT4v2oDpqOhDHIUa70HROyhilE4N0ui9ZskD0ZUoUD+crqg9O9yJlOxGdBPshTUYBbeOrd+boFXBfjamT4TxE2oFIAMN57u9fWnl3fP3nKt+ntN9rvSD39eAkfZ/Hq98D+g3aMNJ0MNJvmnI9hf/CJp7eVml+KSVqCfajjiwEyLSk/Owml/ePNl4fX7+28GB8favJweqDFpy2Vkcd45LQtF5TTmLGKVGcMGqLXp8p6s7/v703jbEkS6/DbkS8PbeXa2VV1l7d1d0z3TM905yN5JAcyWOaFiRaok1rhWHYhi3AFCAbhmHAgn/4l39YAgzBsA14kReIpmSNrIXkDLeRSM5wVnZPd08v1V17ZlXuLzNfvv1F+Meo33fOefkes8dTWYTed35FVtx3I+LGvTei4px7TkGuH/sgSEhUytJctfZYed5SIf7Da79L5X559lOD7fdrl2lfFRMucCzUZQwCfTcuCQSlJ2mD457GPRvPClf+CZ/vxk/ZdcWH1taiDgjbn7K2Xvsdff7Z3+s/NfpVIXdsbX28Zv2hvcDtkp+1Z+i9t1dpX1a286/CiuOf+w9+j8r91t/6icF24yJQpYfch+Z/0mRU9RbPhc1r4KoAz920zZKFrGLnNPVLjwbbR1+6QuVasAo4bnD/av+e0b4zG9aeW69we5ZfsVX85d8zKvf4I0yjX/87Vsd7f4WXxffX9OXjj4Z/AXQ4HA6Hw+GYMPgLoMPhcDgcDseEwV8AHQ6Hw+FwOCYMp/fyQJ2KJksAcEl0lB+jgYnk3RPrB/1J3BEtBlD9RVgF3ZnlYz3OqiMPHYMOBN2zO9PM3+cPQesDmp2+JIvEoG3SxITCrv3unb2Vwfb/nv9JKvfilGl4fnPD1oSnj1mXEKMbT0vaZpSNg2jKohEJEmOTJQTRmDSEJ4lx58hpGifbtITAKSlD9iNoCwO/G7LqQDsJ0DplR8dcDjWG4ywoxumI8LowQUH1V6TZZJA+Eq9F7Hx6U/b38XmrZflCjcp9vHx/sP1CoUL7vgY2JoWKXXPc42uMRkwjdH9CCOmBuf8PJQidXMUTBWlKVSuH2lO4V2lbLIvQikfn04ZpeeKO7Zva4GK31m0+eVizNIbGIc8ZU7vQZ8TOaNQ4GeqPOIZwW8cP1JfVRSsHYyvLw7ZoAPtw+q2Oja29HqdC1Vqm0c01RBuq1/kBRIebdUB7C/ckq/M4phQfnfueUoJSUrO+tvw3btG+u6/fOPE3+69wX1v4prXv489K4YJdc5azeaywx8/uhc+b3m7v903b17wk6Unbdr8u/yqfx71ftD516d++Pdj+5dd/jMpd+Iub9sd908p95GffpXLvfunmYLv+cbbEmp6z8XUEz9fSEd/HqYc2BraXrW8c3uRn0Mwl8JX5nXna1zxn19UFuXVf1iVMf8n0fD2Q9uXXeRzWbHlAKO7x+R6vfvjvef4F0OFwOBwOh2PC4C+ADofD4XA4HBOG09vAQEJAlimNcDI9nElSA9pejLMcCW2wGWix/UT+0H5X2YKQ+By/yzYgiTpp8vnGXfu7cGDnnmsJnYNJGJAYkhbkvRn+JOf+EEIG17XzyGia32repHJ/OLM22N5+bOWmtvhY+WM4J7lmoiyz0ZQ97SNbFbFEQTpnOEb96UPtM+KT6dEoGU3TjbUqGkftjLCBGbKcwX1lCY1vwrJ9uJYhmhutKig9RO4X0nZikYN1RFMQep8X24I5+7tTtWO9tPiIylVjo/e+0+bz/dqB8RTddaNOdGzkDyAZ4tCScciOI0ibdtXS6OztiOj8pA8iRU12IUIbZmD7E89X+QDQJ2No25mH3M6914y+alywe6/ijDwwVMNWV9a2MVLvOrZ6aH2DY2v0+InUBgbaJivYdl/mU5yvu327mq/u8py5uVEdbFd3aVco1GDcwfNEZ7GxNlgIkDNF2gdPm2LzI0bhwNrtta9y28xtgvwAboPKLvY+afd17k1+HUgfW3+oX7e2WXyL22knZ7Tv7F1IIJni+ror1k77N5na/MWXvzbY/sf/4McH2/Of3qFycWT1l+/ZhX30Mzw/ffdlswXKGnwe3/vi3x1sX/vyvzfYzjW5HNoRFX/X7FwKP3ZE5aLfMtq38ROc8NU9tutc+Iad7/6LfCOKMEbrl6zP5+qSzvKK3S+Ul4UQQq744edC/wLocDgcDofDMWHwF0CHw+FwOByOCcOpKeBxVAtRT2OTEIDKkvqiKVgVB/RafMzu1gX4IpwWLJRaP20XYEWPhlxHPfiMvAfpCZJUgOfRL0NodEco1WmgffJ8rMIBfIoHuqGVMFW4sWd0Th6CzRMx9y4e2Pnmjphip1V82NZjkhWycSkLtEqV6ZynQb0phuin5OQVvEMrlnElbZGvK8IkA2i3WJJPMqDLsG0yaUM8dnbMqyJDEfoAUIK6ajmGRBJKYBlHX+uqZaCf06qNm9YFDnY/vAar3eeNOlso8KrIrb797g8bV2nf7969Ptgubds5lneY2k12jUqhK9brGiNTGFqRecZQuh7vFdKLmh4RYM7MGjLIoT9hApEueZ56ZG2RB6ooEiYTpS1KAccdoHZxhbWsZqc0Fk2qAdCcMZRUA/u6MAfJLZyCxISjgi2dfLPEfXV6w66/ssUXnd+DVBN8huhKfJAp0XNMnQPwWlTm8ZRSkZoXgA5c4JWuxzl7nqal0fKdqGx1dGf4vs7egedcZDdp/ef5WGv/0LY3Pm/tVLrCVGnuVVipfoHP6Utvf9zq+6n1wfaPLd4Po/Abh+cH27/28CO0L87ZuSc73MGu/fq/P9j+C5/45mD7e9fWqNydL18bbBdqQG2/yf3w6IYd67lzTFk/+ntXB9sRyCpm3udzWv+i3YcEZF6XvsJ9a2Pa5ob+Vb4PYUMkRqeAfwF0OBwOh8PhmDD4C6DD4XA4HA7HhMFfAB0Oh8PhcDgmDKfXAKIGRFziR+nIhpIKMrB30TpQIwOO7GrEER+ZnqNQszriDmu54m4OtsWaJQkn7ktE29cH6xdMJFEbmBSd7EVukQBNj87daX10KgL+ZmqTzynXAM2iWOSQbc2oVJAQSDdF+jixN0BLi0ySDIaSXM4I4/tXdnK5TC0toL+KxjQDDRfZVqjWDC4f9w3pKEEfFJU5oYFse0AfMmSfMU7PCKAxpZpN+Lt10TQsRxfFqgGkuMvnDwbbTYm4+af7ptl5bYe1M8lblthQfc/uUe5ItKhwH0hTqjpitCNS7enT6IfpmPuBdj5iZ0OAsZbp9cI1xhXrj0mdx+D0A7v2ftG2myt878s72LY6F4I9UBvuj2gtSUcM8yIl5wS2XFEdXVax/t+fgrm7x+XKu9YeKdSfF1liESzBpu6x/cZQQsmgQtH2wZjBtJah5xNZZ8l88iESlH6UiMDOLPcqp6QUQH5XvWVtsfdXuRHz/7Q62O5yoE/YfQnseFbsvp7/VW6b9Z+xbUxkaRywJq3wot2jYp7bbGHKnv93b50bbP+tZ36Fyv1+0yymDj5m11V4dYnKpRftXlZerNG+8EZ1sPmNy1cH27cfLFOxMnTtw5+x58S5hUMqt75u0R3r/+gq7QswFI9uWL/JH4pWvGTtsfAHduDuDI+vOQg8yb/K92H/OU8CcTgcDofD4XD8EfAXQIfD4XA4HI4Jw6kp4BgsK1L5vB5h6gClLIxODMmaTL3FFfj+jDRPU5Y6A+WS7Ntn46jH9BpStpHSHnheSBVKKDnRuRAunkrQeP7Izrczw59lMf0AE0hSyVqPgTkpHhgFUqzxp/LkGNpeqSO8L5j+oTQVUB1kY6Hu/yMoyhBCiPJKzp8NhmhfANFxcF+jYuGE0qMqgetCK52yUKrQByJIa0jF/T7ugA2M0LIRJuWANUtUF8sQoI6z3Gj6DdNwMGkhhBDai1YH0r7Ha3wfO9dsvM0U7fxSEWO8UzOaZuctpl9mwAlhat3qy+2wLQTZ4iAlKvcYpQhDlK/OMWeAHyaZZMg6BZMllPLHsQY0eXzI/SJB6UHP6p99T5JUoDpNTEr2gRLMjZEXTI94VCjVCm2TzgqniPXBNRbFHqi1bHXM3QErJqGKi1vQHmrb0oCUmXSE1CCE0TZCOrfiXPiUKF/Fxd+2c9p7nve1q7Z998/ZGFn5f6pUbutzkKz1gO/x+a/bvo2ftD76+Ce4bWZvWRvOrNtvdl7kebd1zc63G3GfP35s2pNzV/cG23/2N/9jKndubX+w/R999quD7f/xOz9F5abn7P2i+XaV9uEIqDVtXlxdrVG5x6klfIRDu5bdt1epXK5i1zX/No+HB1+EVA9IuJl+wP21dc7KleCZ/+izQgG/B79Z4LGck8fGaeBfAB0Oh8PhcDgmDP4C6HA4HA6HwzFh+BCrgMckfGBYPX5iH0PXRImsssLfjaElkX7BFZyxpEJE6HAvdFjUg1VmBaBRhG1Gmi/Nw4rgnq6kA/fzPaYHOjN2XqUurGZU5gqox3zd6sgfSnrCMaykbo9O+OAfjU5PoNNQNgRpkLx0FaWLzwi04lzov1Er1TVpIZ6bDaNAK6mB9onr3Dm6i7BcFmg17E8hcDJMvi5pIouQGgEr0LMLc1QuwG2I2+DcX+VEAlwJ2ivzPe+W7Tyay7bdeZbb5vm1zcF2KbH+9e2tS1Ru573Fwfb0Oh9r+hGk1Wwb7Rs1eRVrKjKQAcbc1yE8hX44bnUvnTlICKIi3yusA9MoQuA5LjuwFYfRFFOqSc1WVcYl6O8y32VwHonMGRnJI2Bu6fWlHFDWmHyh1DZec1voVqRpS1ZfIm4G+WNwcIBxka/xGCRKXKhoci0Yl9Qx6lmjzgEwF45biX+WaMMK0b4YDFz6slH7t3/B5pmehEVM37G2rr7P9/wYaEl0sMgf8/V3IBhj65OQzrLBx1r9vGlD7t7jFbehZO27uWnzX+UOU8VLz9p1/Q+//4XBdtzgOai9Xh1sz7/M6RwHsGJ4/77RvFlB3nH6ds3zr9o1Hz7L5cqP7dj3fpH3xQewonfNxtd+ia/r2j+wtt/+hI3/fkXGITzLM3msaxraaeBfAB0Oh8PhcDgmDP4C6HA4HA6HwzFh8BdAh8PhcDgcjgnDqTWApN+LRWOCaQfj9BGosRDCmvRWaAkj+h/S38SgZWuqzg9+Jxo4dKRHTQzqXEIIIWrDOQJnn0l9/TJoVkQfWNrrQTnQ4jRHE/a5Y0gC6I5ORVBtC6d/jBEEYB1qd4D1qQ6Gdv4QgoMfASLVIo4CanZEp4Saq2iWHfRRS0TJBTOs4ULNZnfG6u/MqDWLbR+vit0Hlhu9i5Jr0JqoX2StXA9kiar1aa9YX0nmbAwVxJG/2bMT2W9ZJbt73E6oe5m7w3VM3TdtGtlxHLINDFlwjNH5UapLUDui009hPyrgHKSJEQQcW3p9+Hd+jA0MpsfoeASLrAjTYkRrqakeBNLzwf2QeYESc7A+bX/U4WoSCJRNjkDPJzrOQh+1t3Zc1SVSkkyL9YEZ2ofh+UpSD/UfvGYpN9IuJoy2/nnSOHjWtntTfL9u/5Kdfx805UdX+X7NvWdtvfuCpLpAlag3w7SgENjSDOeq2ovcLgdgnxJJV177qm3v/kXT+c1+vkblvv+9y4Pt6Qd2sPoNPtbqb9v2/VXRVC9AH+3YhRV3uW3mP7Vlf/xz0yym0uWb56yhStNiaZRCP2ra+U494DG58zF7vtRfsDqq3+b5pfacHWvulsz/MuefBv4F0OFwOBwOh2PC4C+ADofD4XA4HBOG09vAIO0hn8PJjmNcAgXWp87tUJaW8Osne/yjANSQpCdQ+kNbnPHxPIACiJQqQVoFA+D7Qr2CDUgs1GuMKRHHUK4zenl37hDoC20noESG7ChGON5HapEDbZ1iOaU9KPReaPQ/DlYI4+xBxp0f9FFKowghRDNGdUZQf9Lgtu4sgUwBmk2p3B7Yr7TnuX2RSsly4JI/K31oASxDkL3v8jXGBTjfnCTIpHb/pio2vnp9vq8Pt80WIbpvnEJ5n8996Q2jyou7TDnGB9amSPumbbE7AWoe04ViScbQ5CGqQy2OzgDxtPURtXDJ+tBP0B6rIf0Mrl3HHVGKuK3XitYyB2C3UxEuCOc1rQPn7nGUNdLU42QjMO8OUbZwbLSwysT2Jz6ChCekqGUeJ2syfSYRtWtjKx1D1+IzaYi+RpmT0N5D8+YZYflVu/6dF/n6c5s2P6WfORhs599gOvQQ0jn619mWKX/L+lG/aOXm3uXzOL5o1492MWlB+hrQoTN3uM22X7b623t23HaL54JPv3JrsP3N7OZgu7zE42v7ZbP6mlncp31/5uobg+1/9H98frDdWuR73v37K4Pt2iu27+Lzm1TuANJEot+ap33tT9mzvDBjc0X+iCU1jVVrj9nXbAyd/43HVC4tGo3e4gCm0Jn78LIs/wLocDgcDofDMWHwF0CHw+FwOByOCcPpl9BpqscojFvZB3UMUTfpiM/5QssytQnlhPHLumNoI/ycjzvUMR4ohhjpDAlNx2SRqMvXnJbtE3b+COgipVHQQb/RGl0OKYxTpiAoTTWy3JiVw0P7ntIqYFplqCkECJQUSD+MhiJPANhW2EdlhTgmtHSnwWlfVuZ2ZmE1niwk7ly1+1wBeuDcFNMZl2eMwlgo2Aq5dw9XqFyja9RBEvP9Oe7Yvv0D4557R3xdhR1r0/KmnfvcbR4b5XtGOcYNidCBFZhIucVj0jDikjQOgMa59rtxK1yfECKkqGWeySDih/qnzmPYz4SWjGDlL5VTqhGpcThWJlQ7Jf9oe42ar3VlMs55XVyKLquFj6x/BqHyoyM4X6JRReaDcy3MceNcCbKjOv2N92hUQlAIssIc200lJPEYmlfb6ozw8IvWHsvf4LZJOrC6t2p0aONlptFnX7f26Mgy0tzLtcF24avVwfbhM0KVVq19F75r/avxce6HS1+xfr31We7zf+4z3x5sf/lXPjvYbp7j+/DGG88PtrOrVsfUr85QuZ3PWl+b+22mZX+1+5N2jjes/y5+j+/x1ufsugp7dh47//w8lctQbXCO22buG0APpzbH7X6O543SQ+iXMETf/3fOcbld225e5Dpu/DKMm/8knAr+BdDhcDgcDodjwuAvgA6Hw+FwOBwTBn8BdDgcDofD4ZgwnFoDiEvfh2wLxiVGIEBHoZoy1ASO1PmFwNoutKZRR3rU1WgSxIhyQ/YJeH6ocxqyYwD+XjR7MbYVaHaiIU0dnNUYzR5Zv2hKyigNn+p+KAlktNULn57c4zEOLE8UeP/VIgf1PJj2IVok6l+q7UGdGtSn2s4sb+eRB6f9YpHbsLUM56Q61R640Oetb7y8+JDKpWDDf6m0N9h+72iZyu3WzfpB5WLHW6b7S+pWX2WXz3d63dp05r71+dyRWLhA3xtK+EBtGt4v0bpRfx2XpoB1dKUfqm73DJAeQtKJWoJgObB+Uf0jJSuplhW1vTB2h/o7/tE92X4mhMDpNtLfoynwIsLz0PE+xooHkWECj9jAZDj/4f3WeQv0hul+zX4zwzovmrtVXzpKz6eaTdRHojWPzBkBpXN/HCywQgjVN0H3+W/u0L7Dr5lHCKaElO+wBhKtqPIyjI/vmHYwfckaYKiOqm3X/qRZyeTu8PN062fg/id8z//Bd16x+j91aDvEBia5DrYqb9qBD6/zua9dNrHcesp+Kfma3b+Z2zZW6j9/QOWW/qldf2fOxk3jvKR9bdm+puw7/5vbg+23/vrCYPtPvPg2lfvdrZfsD7DLWXyD63v00zamnvk/ee6793Ol8GHhXwAdDofD4XA4Jgz+AuhwOBwOh8MxYTh9EghSLUqbIeWANg1KRSBlKfuQDiIqUm1QkNtCemSMhUmUCn2RR4oFPuc3JVAcneGRRlVbETy2WMSEPtSJlIhSLEBnENUzxuolU/oLf3faFBak5ZWGG0d1nNYW6EeMcY78dL/QBkJtNqIxUgS0jMB0mSLTHmgLlIMuWUx4bExt2Hkcnxf6rWHtu7dtdMM3kytULgVrkfvTZmnwoFalco0do4CTOt+7qS1IAtmwdirVuG1K29Zfk12gOsXqhdq0o1Yo2H/Tk7dDkHkEzlf7PMoUxtlxnBVwzMgYxD6JiSFKPSIlnMq8E4ElDlnlKI08AmoDQ3Smjlu4J5zApOVg7oI5c0g2Av0ibXCyBI07svoSSRGkJGFbpDWm6HDfkOXYKNpX5zT8HSYk1Y+pGNrHpJIeNM7C6Emifgksct5ZoH1L98He5KctuaL2ZbYwKe9YHbU/Jdd83/jh/Jb1oalHPD7zMI91ZmwOKm9JmkpidaDFVAgh9GF6PYafVb/HFPDBc1aw+pLJYbr/fJHKbX/L7FMSYUbjth279nFIILrHEoPsgpXrTcFJyfRU/oLRvL1vsSzn9l+yv2ffsfq++8bHuJILkIQCiSS5JrdT7hDamkNdwuzt8KHhXwAdDofD4XA4Jgz+AuhwOBwOh8MxYfAXQIfD4XA4HI4Jw6k1gPEYTdUoDEVwJaO1I6jFIpsOie4hzcY4zRvqPqQOsiPIYdSQvA9D/RlqBVVTNmW6h0y0I6O0ckPXP8oWYUzk2lDbYH1oF6PaK0Q6ug1R3xSrlYoKIc4I0biowRGWI2pbFEZYP4QgEYJkkaPxf6ZvikH3lcuNtlWJu9yGxX0r25m1+ne3WUeC3XIfLA3ydb6uGeh6pV2+P5Udu678gW3n6hwNFTXh75r5QmSpWHqgVZHoWYe0qSNA1k84/nXeQI2YjvNTxiH+KEH9STSfdO2oV9Xxg1rTMfZLdKwhrVwnnIRR//5HlSVN7bh27tq9T8fN8Wpvk42Y11K5ftRY4lyt1ix4XB3H2AZjokVpDhkXMwlzaFxmUVl2SoucHzmgO1z9J3zP138KzvHrpvvrXOZnQR9sqwrfnqZ91fesPQ6uWxsmHa4D7WOqt+w3m5/iNowhni4Wp7OFt2B+Orb7PHuP55LVf2YWMW//NdNNFz7FUYCLX7Jn8u6fZc1mu2aazagNEazqfDRv11l9G3SDX2Bt6877oL+8xnreld+wZ3Qfum+vzGM5f2R/d2fsRLr/eo3KTX/FNOB7L3D7pqcP9h3AvwA6HA6Hw+FwTBj8BdDhcDgcDodjwnDqj4bpmM/cUQz0zTjLBvjsn3ZGUwdE5SnFoHTeBxCbBVrSL7YII+0U9BqJbhzttJ+hLcAQdXByZMYQcTUqPUFTQfLwHbkr+/B8f4h0FqVUx9H+2VOg3kJgmmrIgmOUvYvSdHgtQgkRHYd96OCQysVA+8dHxr1G0obJsZ1vvsbH6laNpumV7Vjtx1wu34Ax1bdtTCAJIVCnKuyJBQckmZCli1q4tJjCGPy7lhtHsSPGWKZQGgbe156Mwwj6odCbUW40LfikMNZyagStjakgIbB8YxyliOW0/UZJZeJKhcthnxyXCgTz2jgblCHpBQJp5LHna/ctPeIICrpmpGVV8gJzvs5GbCsG82mzGUYhKltyhc678dTofUO2aGeEuVu2vfMS96HVb1jbFH79W4Ptu//157gSOPXWErdiG6yjWsu2r/Up7svhttnFpGCD1j7H93/567Zv5xXuQ+VduEfQRR/8WzJngPVV8ZEV7O/zc3f3RduO32JqO5m2vlGEJKRija//4Dn7u1eyhpr+Oo+vNjDApXdYOpG07Tr3PmJ1LL3Gc0gDLGfirm1P/d/s9dJYte1YlB6Lb354KYJ/AXQ4HA6Hw+GYMPgLoMPhcDgcDseE4YdYN3ICgDpAOnhckkSkS25GUJFDVOMIikFTIehYukKMUgzgO+qYFWJEI2TyWRppFF0hjJRQdwz1COc4Msg8CM0ZxgAd/jVEHuvA89VVwJisMbTK7imtfBuzonnUtQylfeBqQg2HD7hv9Gp0okqxfk0JAKpYQ+/jplEnBegP5Tzfh7gNVBeuMhbqNTqGczqS1eiYNAP/PExnnfx/Qi03duUq7sP60jGrhcesuKa65T6MK/ukQHS10KE0ZnBOGkMTpsdMS2KdMTB74yh0okOlTZB+TmYk7QCdDkQqg6DxP2pOC0wdj0suwTE5jrLG+61SgxRpXp3/cVU5XFek54TPmlErogOntej5hg+x6vpHiekNa/utl1kKkTu2fQd/+bOD7UwUE83Ldl3ld5hG3v0ESBhKtp2/O0XlMK1i5qEdt1DnOWL7Fetrl7/Mc+HGX7Y2zL1p9Wct7stLr9qx9j9qdeSO+Vg9oHnnXqddYQ/oYVzp3C9I/5q1azm6Bk4Pks6RonpNusLjn4C2ed+20xzPhZg0MnfDEk4256tcYWznW3modPMYt48R8C+ADofD4XA4HBMGfwF0OBwOh8PhmDD4C6DD4XA4HA7HhOHUGkC0dFFdXjZCKzfk0j8m1WLIDf40GGMxMU6jxHWcbPsRQhhrMzCyDgGd16gUkxBChtq2cTq3MRYMpMtDi41xOinQb46z2NDkj3Gay7PCcJrMiHJyrqQJGkqJsTZADdOQPgruUYT9XBMf0HJF+j9qmqL0ZM1SCIGTS0grJ9ePfUrHHvRD7ENDqT6j0hA0hYKSe1hHSW06JhWEbKJoLPO5xyXQ3EkffTpmRB8e49JohuyXwBYGLayiEuvXUtCb0j6ZW1D3p3rgbNT9lv6DOkIqN8Zuash+C64L56q+WLPEYMfCenDR0II1y5BtDZwjWY6pRhuvBc53yFYGx4/2wVMmY/2o8eCL1ofO/QG3zc5L1jb1K3Y1C29wHfUDuyeohwshhBZYpJT2rP9u/CyP96v/2K6/ftHqi2Q+nnvH6ujM8DNp/ldNV1m7CVZX+6OfM1Wory/axuS+7Tv+02zhVfmaWas8/nFrt5VvBS53y+Yx1OjhdgghzL9px9p7me/D/OvwfIV1D2grE0II+UP7O/mS+crkb/A54bE7s3wet//Ch7cj8i+ADofD4XA4HBMGfwF0OBwOh8PhmDCcnsdDq5e8fGocRUsq5RudzjoCqTyylRl3LE3nICf4Me+5SL0pjTwmfJzQPTnFI4QxYeanTerQ+tBNX6ndUXUK/TSKstD6kNobcuF/ShiXwjAy1UQsbMhyR5NmkDpC+k3bekRaTSQ2AGNTGPBaxtCyZF0B5dLT9qEgY6AHv9Prx/ucnnx+IUjij6Zx4LWMS3JARQRacIyh5cdZS50VaJ5QWh9lAzj2dQ5Cu5gpsUEByxGkYtM6B94TVRqN6PtB2i9/ujktnuX0BJKX4HwnfRotUoao0hFpR3Qdso8kCUKB031Q6xsYu1S/0MgkB8EkEKGlyQZsHI18hqiswzNZ7nlr2bZ7i9bu9Ys8tsBVJGx8geeTygOgNl8BG5gt7kMbn7c6L375YLC9+/IslWuchz4qrxC9n60Ntkv/bN6KyeP+4Fk7x+kH9u94vSGE0AOnmuw2n0cMiScRdIejy9yXC3YpoQ+U7erXuA89+tPWz5/7b7nfvP/nq4PtXANoXglcmlq3czq6Bv/+kMu15+E9SabC3J0P/4z2L4AOh8PhcDgcEwZ/AXQ4HA6Hw+GYMJz62zVRWfJZlugxoESGUjzgh8N04+lWUlFQ+DgHdlxVqEkY+DkfqSdNu0B6gFZEynsz/q2UGlI/4yg73BeP+Q226SnZsHEO/0y38C6i9sYFwJ8lRtG8IYQognuENK+kllBfVpnCqFW2uopzBGWbSp+Px8gI8L6MXEkv54jHGkqhGJOMg2dFK1J1HGIddP36f0WktnX12QgnAO1DWKcmA1F1o1fMjpOVPCmQXKUnlOII2ncojQaoWKJ8g1D+2u+o4IixoDQv9lVNfsG+hf9+LO0McxJSsSqboblG3QxG3cdxY4vSYqQ+PKcheQHUj7/TuRv7D67sl8QQkt4o5fshpBg/SjRfNroxzTGNnhbsnKqvWtscfoYpyqv/q11/e57bcOFtvEfWp8rbfL0HN+zvRz9jK2zb87Ja9i1r38c/zffy+f/Syr73V2y7v8r9tfIWrCSH7tRelGfBgj3XF3+DE04Kx3bs3RetksaazKdXRkmqhCq+Y/W/+5/JCvzEVs/nvmW8dP2GUPZHVicmjRz8JN+vyvfgPssr0/GlD/+M9i+ADofD4XA4HBMGfwF0OBwOh8PhmDD4C6DD4XA4HA7HhOH069cztFUZbRfCWjYuR2kikh4wSsszdKxRyQKq5UI6XDVVqAlBPaBqBUfo/oa0h6e0pojGaVGoILbTaGuaIW0ftiHeL9GskL0JJoGIfo0sePT+jEt1eUoYaW8j+iDUxw0lq0AbkG5LNVwjrIWGElLG6jlPbsNx/WtcEgweOxYNEyY5hFMmdYyz3MFjacoFWTCNSRBCO6kIdIPDqT6wb1wfPSuQlk36BWo+SRssY3Vsoo/d/xT0gdq3cF8ybfqicdroIW1od4S2bcz8ROc0xmKpf3RE+0bZsQzZu4COEp8TcXmGy/VGp3NEI441bs4cZ9tD1/nHRA9d/appz3Y/yWNm5WvWR3fAwmXpK6yH2/y0jcFuletoz1odl3+1Ntje+EKVyvXLVn9nxurrVXis1p61No3FBuW9v2LWL/kjqyO9wHU0QOc2ddfOb/YWP4PjLiSSaCAZTFeFmm13bnAfWvl165e7H7MftapcX/uctdvNv819470/b7ZIa1/Zs/pemady9cswT8KlTH+btZ0ZTik8bMLM7Q9vkeVfAB0Oh8PhcDgmDP4C6HA4HA6HwzFhiDLlPR0Oh8PhcDgc/1LDvwA6HA6Hw+FwTBj8BdDhcDgcDodjwuAvgA6Hw+FwOBwTBn8BdDgcDofD4Zgw+Augw+FwOBwOx4TBXwAdDofD4XA4Jgz+AuhwOBwOh8MxYfAXQIfD4XA4HI4Jg78AOhwOh8PhcEwY/AXQ4XA4HA6HY8LgL4AOh8PhcDgcEwZ/AXQ4HA6Hw+GYMPgLoMPhcDgcDseEwV8AHQ6Hw+FwOCYM/gLocDgcDofDMWHwF0CHw+FwOByOCYO/ADocDofD4XBMGPwF0OFwOBwOh2PC4C+ADofD4XA4HBMGfwF0OBwOh8PhmDD4C6DD4XA4HA7HhMFfAB0Oh8PhcDgmDP4C6HA4HA6HwzFh8BdAh8PhcDgcjgmDvwA6HA6Hw+FwTBj8BdDhcDgcDodjwpA7bcGfu/LXB9tZp8M7F+YGm9FRw8rNVKhY1LLfZfUG7yvkbd80/C7LuNzRse3qdu3fp/hYGdQXdbq0L0SRbcfwDizHyg6PoFxi2/OzXN/uvm0vzvOhmu0T69e2Ceub9pt5a8/QT7lcr2fbSRJGob+1Y8UuXeCdzZZt58Z0AThWVp2hXdH+4WD71zb+9ug6fsT4ubVfGmz39/ZpX1yBNu33YUcURiHFtgghxMWi/QHtm2G7hxDi6SnYB8eScgH64dC+Lvydz53873IeIbP+kEnfiLBf43FDCBlcZ1QujT6nlMfAANguIYSQwjXrb/Ac4Voi7a94jjBGM7x3IYQI72u7Tfv6dZsPfqP3yyed+Y8cP3f9Px1sd8/zeM9t27iI4Nobz5+jcuUHVq69ymMrV7d5Mvdg2451levI3X5kf8xZHelsmcrFD7bsnCq8D+fCDOfWtWUu17N7GrXt/NJpri+p1QfbzWe5jvJbj63+MvSnHPeL7rKNrfyW1RcdHlM5nJOyhMd41Ic+ifP//gHXsbZiv1m3dsouclu3V6wPFjflPPJ2/l/55n8Vzgr/2gv/hf0hc1x2b32wHcEcn964xJV8/73BZnKerzk7btofMO76z1+hcrkta9O0Om3HfbRD5UIVnpt7eh+sr0THNldlxQLXgde1ar/JHmxwfS89a9sy/eP59hetDyWP+XmStew8ui/aNee3+f5HDXiGyJzcX7JnebJnYz5r8HMH58ywvDCyPvpJief4cMfa5ssH/8vI3yH8C6DD4XA4HA7HhMFfAB0Oh8PhcDgmDKemgENi74pENQWmeehz/vYelxtTPVECQAFFQi8h3RbNAnUitFG2YZRquMCftiOoI9uxc4xmprkcUE9Zyz6BIwUSQggZ0r6JvFPDp3n+pC40+sVV20YavSzUW2afxJFSVySrRm3osbIZo1jCXs3qEzoYKfawU+N92ehP008SKD+Iq3O8E/sKSgBivicp0IZDdSAliv1Q7iv2B/x8n+I9DiHESLcKkFaOkAIW+paoeKQEuiJtKEFfEWqXaF+ktht8vhFR4HDNKY8vGm8qI4hysDlmikFqDulhGctDNDUgFunHWSCrWFvmN5nK6q0YzRUDlVt+eMTl5oFSfMz7SKIC9y05Yvob2wXntGSX6zv+MaOvpr5zn/ZlszbndZ9bG2znDoWiwu4P/TM+5nLpnM0txd9/i+uYr9o29vdNpgoLQA+iHEjnwqgG1zkl1Db0XaQRuy8xfRm34Fnw0ct2eq/d5nOKLtpxN/h8W69cDU8FW7uDzQgkKSGEEK4Z1RvBnBTff0TFml/42GC78obQqBeWbLtg9yu5zeUCPIfjHbh3M3xO6W3re9EL12lfZ9HuX7Fj/TqdZgo4vg73AeQGocz3P7oPz//FKp8vzKHJOtxLkaj0b9h4iHog35LnSYD2Ta/Iu0bnlJKt6ybTihsgbZPnboT9PJVn8PmV8GHhXwAdDofD4XA4Jgz+AuhwOBwOh8MxYfAXQIfD4XA4HI4Jw+k1gKB5ysQuJdRseXMYYaMRAuuBUEcTQqDl+VHJ9pEVS+Bl7PFd0yJEVbZmiZcXrQ5Z+h+g/mjJllxnYkeANg5odRNE50XljlmXlaG9BVhxxAtsH5E9MruHALqcIZ1fMtq2hnQ1sK8nS+STZVhyj9oR0TZEfdBfRKOtVM4UoA/L1N4HtWPY90RThxrWYQ0cXPMoS5QQQiiAxqhhYyNeqFIxrZ+OpVq/D6DXhb8poZZP/v+mVi34O7i3qF9Uy5UYdITpAViajDrXEIY1evnCifvo3OV80/2a/btqWxByHvE4jeGTwm7NtsVWJdk1XRJapPQr0n4wPofGOGh2++dtflJtXwoWJmTTIhYblbswP8v5omVM4Y7ZoLRvrlK5wiborWD8pHOswUzAcqb9qedoX37fxkLUhGtG24sQQmhb/++ds3k3/3CXiqWLoLc84nHWg/katZPFdx9Tuf6qzcPJHdODZaKnittoOcZtWL7NWvczw4o94/rToo/s2rhO58HqROZxtCPKSmK5cvuh1f/xG4PtGI4bQggpzi0L9uxC+6EQQohRl7h7SPtK+9a/Mhg3yXvrVC67ANYvOFct8fO/D9rB/IZYzsC7RwRudFmRx2hyJDrYf4FeVfp8bO0RH8p8D+8UaLNE7xMhhOSO9cv+NRt78Xlu69AdY7/1Q8C/ADocDofD4XBMGPwF0OFwOBwOh2PC8EPxJ0OpG0g9gsP1EP2FVjLq8I30ENRHqRghhBgsUiL4BJwd1akcOrnHPbGVwM/gQDdF8vkWl7Gr9QuVg2NHQsOlV+1zbrItVDSeErYpfNrNmnJOcB6xLP1Hihmpt+RZXnIf1UfYzOjy9i2gNtT2RajOs0I2yjokiMRA6XEsh22tfQPsTsbVQdRjboztCf6t9ib4CR/DPjT9ButAO5ZIrGnA3mbIFikPSTtopaP9dQTtm0k6SVSA8atJK2hbg79LZT5Aq54pSFY5Zqd9uha9rvAUAPNCb4lTPOIm9E9Ua+QkqaKDthKyD7bTgnWMaI7HewS05LjEgP4UWEdVeN7FlIT2szZXFW9tUjls9+51K5d/VOP6IJGkeI8pW6RzY5iDI7WSmQEKsA5yBZVyAO3dFwqQLHPQ9kvo26ht+/oXjV6M32fqMUWbDpFoaPLKWSErgjXL+s7Icuk5o9jbV5hSLN6CdJZpfq6jZCMBaVMqfSg+hrbGx6TYwFByRV7myQdmT5PNG42cXT1PxXA8dM9bueIeWyRl0L86a1Xal4DNSg7mp+4qv2ugJAKp3Jxa05VhfDXFqgnlLPD+k0qKRwTzOlHPYgOT7ltaSXyVU12yymgJ0Cj4F0CHw+FwOByOCYO/ADocDofD4XBMGE5PAePKSV1Vi/QgUDmasoAUla64zbaNLkB3fw28x9UzqTp84+mCA7fSqJTwAbSpBqVHuIIX6YcaX380A6HkdaavYlzdBKuHsyNe0Rcvm+v6uOQDTKRAKi+EECKg+QJcY9BVhrgCESl7va8I/WQPCSJnCVqNmhcZAVBpmiAzsj7th7A6kahXDVvHFA6gUYfoS6SlNZ0DZBDpgfWHGFaBhxBCQBoVGVClDrFfS//CdovGnBNSFkTfijwAf6dShCEpwQfHFdkHyhmQAtcVxzgHDFHsY8bKEwMkMCRyTe1zQEs9rA2243u8+hRXM+oqYJRl5O8AFatJAjgmgebsPHuBimGqB9KmIYTQm4UVkTAvdC8vUbksb/e0V4KVjReqVK5w19wMeg+ZRk2Sa3YskKEESctpnYM0kS0rp1Rr/NCOFeV4JTHWr/Qw1QH3JcZkKenT0Vt3bHuF2yY+aISngWjdKMruTaYDkwbIPDZByjO/RuWQ2oxaQqOuWJti38hEeoLzUx9WyGruRX9qNEWZfcJWGSPdnOX4WLl9a+s2OGkkj3gldgr9t1/iOSOCR0MfZBVE+QZZIQ4Ue2+N+1pu6/DE3/zgRGy8UT+BFdYhhJBdsfuSFa3l4q7MDZ98wf44kPeahtDPp4B/AXQ4HA6Hw+GYMPgLoMPhcDgcDseEwV8AHQ6Hw+FwOCYMp9cAok6jytYHUR24aLSwEDsL1KxFB6JRooQDUA/o0nT8HeiwUP80BE0gQN1DHnVTrN9CLVK6sXniv4cQQkBncdHKYZ2kw1oSh+/eyXqrqMy6F9IYajoH2OJgmkAQ3RTajGANQ/Y+x6BZUNuXQ7bdOTOMS34YlQQitg0ZLLkn3eS4+lTRQoksoKsS7WGKFkEF0SwCUPen50RpHWjb0hbNB2oCRS+WQr9JoO9p0g7+DlNiUtW9wrWoFjWM0E5qHXSOcI3aTpTcInreUXrDJ4n05mX7Y4xVEGn0JD2Bxq7MJ32wlknPV626TU5P6J4zbRtq71T/SqkbonmNQRMYb0P9qvkF9C6bDjtXYwuXbNb6TO4i680y0Ev2IUEkbrGOs/TQziPFdAad78ByJrrLaUfNTz872C6/DSkL51m/FcBmjHTekrITz1etnLShpqGcFSLQLMai7Yy3zC4kXTFdWv4Pvk/lskumF0U7kxBCiNqo7bPnUH5jn8p1oY8mh2DbU5a5FeYCtT7Cv9tLdqxMbnn3srV1/tjmjO0/eZnKzTywPp9r8PzfPGf1lx+DVvSCJJygBdMStKFcf4r2THofwOIowvUMkjQTNnENBDzzp1kPnlu3cjjWQggh6oxJUBoB/wLocDgcDofDMWHwF0CHw+FwOByOCcOpKWCkiiK1fRhF+6pzO9DIarmCn9XTKSsX14RqxDqQGlLbC/xkn8h5wLJ1DJTGZJEQQshgWXx89SLsGOMELokhSKsS3aZL6efgUy/YsURzbGFAySgpf/KlJBCkgaQcUowZ2MAotY0UQyaUbyTWDWcGpMo1CQMoUbR0yJQCbwC1LQkXlMKBtKQkZhDdCscdsuYBOjMSWon6UaymCQCkSvH61QYHzkOlCJSa04J7rvIIoLNRbhCrxAL7ilqxQD9E+nrcvIF9dygJBaUT2u+UBj8DYPKBpiKU7phdBCUhqbUPUNfpLLdtCjYQSLE2nmH6srwBtlrTNp9GYp3VucB2XIji22DVAvNC8zrTYaV1m7tKj0DWoPMdWNpQylAIoYc0IiSIdC6xdUZ+x8ZnXBfKH9BftDbNyTgu3QOaDvtPU1I8oN2SA2tPvSeYshA95JSUpM11nhU6l60/JHWRYUD/yvIwf7z0LBXrgUUKWseEwBZB+V2xtwIQJQrPzObH2JrmaM3uw9QW36/jFTuPzqzNrdOPhFLtgVVRxa4x3+Q5I39k19KZ4zGaIFXat9/1pFxhy/p56wIk3PzeXSqXLZqFTfTufdoXLVrfxj6lli0RSN3wvubf5PrSa5BIc5etpcLUh0+k8S+ADofD4XA4HBMGfwF0OBwOh8PhmDCcmgJGqoioxiDu/LhyVoO3kTZS6gA/4cPKmUxXHyIlivStrgbE+vTzOK4Cxt/pij5x4R78pi7O7wdAj1aYoqKVtECVDVFvkBKSwqrVqDsm6UCpXaAbccWlJrLg7/DTM6YJhCCrtmWFsB77rIC0/NCqWqBKKeFCEziQzpR7HBVBYoCJGUo1wgo5WjmrMoL+6BXCWffka8l0WKYjZBV9vl90HrqSGFbMZ9i/ktF1EI1+LH2+DVSxpvVQ/xLaF88JKNKxCS9wj4bmnqnR9T8pZAW4P3Lp/arRknENEgIWmQJGmjc55D6Y27d26SxDKsaOXDvQSN3zNi/Gbb6nnTk738Ihj4Xu9VU7j2NYOXks884IuUJ3leeWGMYFUY8hhKSOK0RtnMRNPlZ/xvYld4BenNUVkZb+oCsiwxYkQ8BzqD/L4xPPN52xcvHjXSqXwirQnqRu6Crms0J+GyQABZG54HMIXSWEAs8fAsUuEhW8f41r1cF2+SHLrZqXbJ7IQ//qVbi+yrb1y92P8PxU3Lf+1QFFQMrhHOHoop1Tedt+01eFzkWb4/dvcj+ceWCDtrlo5z7/PVndC8klpbvWn6JlToJpVa2ti7JSvbdaHWwnmNwh5VACl38M7XtOUmfu2Gp3TR3L1pbDh4V/AXQ4HA6Hw+GYMPgLoMPhcDgcDseEwV8AHQ6Hw+FwOCYMp08CAQzp7YC/7l4wAj+3LdYsoHMbpyFDa4H+jYu0L9kzvV1v2XQvuR0+VjoNGgg5VAanj47p2Yw4a4OVBlpTpOfYjiE+Av3eNGv7YtSloZZLbXAOTC+E2qv+1jaVCx95ZrCZiE6FtFcXzlndm1wH6ShRY6g2MKCdU/f76OnIXsiqYkiXCPpA0iyphcsYKxmyFkKtnNSR4e+yMX0Z21T0nEPazA+qa4j1BdYBfWjonOB3aPXyg8KgA0L9qZ47XPOYjAvW/YkWMZoBrdY4exfUweC1iM6PfqdpEE8BqrdCxGCl0f3YVfuNJB8UNiDtYpbnguMroPvbH2MxAm3ROGftN/c6zwsVV13uJgAAQ0BJREFUSCfAdIMQQuiDDQje8H6Ry+WgX7QvQgLJNvfVCO5VZ1qSJbown06BhQdo+UIIoXvRLGjSi6ZriiRlAdstE/1aDvXnoG3O39+hcr0LNpfH7z+E454Pp0Wyf/RHF3oCiFB7rhpl0I4lD0xIly3wnNNes78Lu6zzTXPWpqVtG5PtFXlOwvDPEuuTB9d4nCQteIZKSMjxmv2uX7Jy9TW+r83z1gday/abQo3H1+5n7aQW/4DraCzb32gzs/Xj/Fyffxfssto2vtJ51qIWH9QG291P3KB9SQOeoTBvxC3W/Wb7VgfOhUOactR5X2MtKq6dOC38C6DD4XA4HA7HhMFfAB0Oh8PhcDgmDKengJEOrXMqRAohyvnb5k6dLlapHLnGi1VBBkv8s4ePBtuJfAJFigqX8Pfn+bN0fACfsw/4fMO8URh03Ee85jy7PiL9oy/kGOyLD8Uug04KPlNrmgiEQ6PNTLIiS7sPRjuyZ02w1UBrntIYaxoMqd9kegStRKKGfF5WC5IzAlG0XaHHsH0xWaPD5SgVQ61vRtDDqdoRlUfYxeh9RRpZE0mOoF9iwoUmhiDtC1T8kDUNXf/olBBO8ZC+jKkj2NZK3+I55kbb1uDv9PqpDyH1rMkieFylvY/Onn5DK41IpSxwHcmhXW9a4msfZ+9UOABrEmjnXFvsUuZNAlHatePWn+NkjcpDGO9yu9OC1d9esD6YO+brOnrJ5qep+9Zvm2s875Yf2fzUqfI198t2rMo7Ntd0LnHqSPIHb9j2ebOpaT53jsrl6/AsEHsTkiLt2/UjhRYCW98Q9SY2ZZQ6sn1I+7IfIoHhRwIcx9Mih8GUHXgOZzmeW4qP4FqkT6aLVmcCVjf1NUnW6AJle8HO6fiqSEN6MJ8sSBJGDPRw3epImjJnwu3rnrN73i9zufyO1XH4DO0KBXB7Obpk7TF7j8+3XbU6ji5a36hsSprMko2b8oa8awD6kBoUKV27Zv0cLfL6QjcnWzX7o8ltqOk1p4F/AXQ4HA6Hw+GYMPgLoMPhcDgcDseE4fQUMCYwyOrF6O279seCfXqPlFJFCkhSEYgSgVWEQ6tPcVUhOpwLpYyUdVhmSgQ/g+MK3mihyuW6UCecX6QreMDVPivx8iaihHEFVo2pqxipSKDykNYNIYQoD+kMHTkPXJmJdLCmjuAqU/jNuGQNas8QaOX3mQLPSegcpBRxFWxU5OvSdkOk4K4ez0K6whKvEEMafWjFLYBoT1kJGs1af0j3aif/JoQQgB7JMHUgHrMiVhJOkFaNMShef4fHxhXCSnVin1LKFo6NK9pTXOkWZIU0UJ1K8+K+TBOExiSNPCmkFaCojvl8eudgjMMcl5a4r/aWrF20jghW4OZgXuvNaLvY/Y8h4L60yfejAakI5Q2ZT3Aehs18XVasd0/+VpBr8LzbnbN+gVS2HisC+qo7y3Nm/tlrg+0+pDEUt1leg/N/XBPqrW/9AuUr3cucrJDfgzpRsiSSh2TX6ic3ixCGqLizArpgaB9Ky9amtNJbVtEjtatjvPiwNtje/YxJABrnuY7csf2dQFOU12XF+Sfsmdc+kr7cgD6/aJW0ErkPNbiWLq4C5v7ZWrXrytf4PPLQVTowXFtVriMGpjeFw7YWub+W9oEevzFL+3AMxLCKPZsStxB4T+hCekiuJpIyuH/9JT6WyiBOA/8C6HA4HA6HwzFh8BdAh8PhcDgcjgmDvwA6HA6Hw+FwTBhOrQHMUB8gy97jFmj2UCso+hyyH1lkXR7aJ/Sv2HL/3KN9KkZaprsbg+30xhqf057pPvoLvJQ6PoTEBNQhia4NtYLpNOj8khkqlzsAvV1XtIioWUKtoOjQ0lWzQiCXcLUYAL0JJXqEEALq0sBiRDWApHVEPYskvGQzsKxcNZv1MXY3TxKoURPtGV0n6gNVo4YWMaKVS+arg23UVGZqgxON+L+TtFMojtDUSVlKBVF7G7xm1Dlq3wB9SKS6pObJ93lojO6D3c0YR3qylREtIs4B2E6oBwyBbXxS7K+i7aRkEUV/dArLkwKmTvRFl4eWIz2waSne2uQ6Zq3dMxl3uZr1tRjGZwraoBBCyOB+5w7tN43L3M5pzsodX2KrCNQoVTasjtYKX9fU+2YXcvS89dVck9u/sGfjqXWO68AkiO1/5cpgu3qL55LWGmjbWtbfVXUcH1s/y8QGBW1ccJwU1vl5klbAzgn+Xe1S0HInu8Aa+NyuaAKfBlSzuGP3KwH9eu8SayA78/BMEklxtGjtlnRAv9nngofP2z2KQJenaVFzZbtfnaZEgcDd7e/ZOSViF5NsguUW6AY17auwbfsKh3y+fZHEf4Cjq/z37G3bruzaNdbPc09sLdi1zN2RZxJaxsF2f5rHRrxn+kjUCurzBHV/ySNO0ME55bTwL4AOh8PhcDgcEwZ/AXQ4HA6Hw+GYMJyaAsZUiEySFSjF4Gi0E3ZUHh3ejUH2uftAtykdBDRfBp/v4xonZCDdHFX4m28KS7ATsA/oLvAn1M6C2YdU7hg11jnHlFQGbuVKAfeB2k0gxSMTW5G4AzYz7dHLudHtO2qKnQlY5MQLQrEjMOFhjIt9tG80wlDqhtB5ZwW0dNFEGqS9U6AoY7UVKY+2I8pGUIpqJUMpFkWQQHRHp45oIglR0yhFKHN/xX6OFhSR0s2j0j5CCKE9IkGkw+MwmrL+hZY4kdTHiSlib6PShA9+I3Y52NYJ9Fe1PsK2jirSXzUN5QyQv7892D78DAeyT4FtS27T5gy1rwnB5ppele93fhv68RzYmQjN11yyPtm9AkkFW0xDlbbt2I3z3H655smJPv0i94uDF6uDbaQKc3KrDp4FKla6Z1y2f0DatzPPY4ssaLBvSQJTlrc+3V7lObl0x+gxtO0aSkuANu0s2L78Hl9YfsOo455Q8Y2rJ/f3J43otXcH2/1PPMc7Z2HOAEqxM8dtXXpsY1xthmo3ra+UgQKNUnl2o1ULdKe0wver+ztGP+c+zXN3L7L5pfLA7munzv218tj6Q2cWJBASkFUCdrTOQzTEMBR70CdTeRvC+uOenVMsQzkH0oaDq1zJ1Ka1VeHQ+nVxg9Nk0IIn2TU6OCvyvJvsQbupRV79w0sR/Augw+FwOBwOx4TBXwAdDofD4XA4Jgz+AuhwOBwOh8MxYTh9FBxEgQ1ZTKAeaB6WyKt1Btaxd8D70OoC9UYST4N6KLSAoAimEEIO6ojFsqS7Zvq7XtU0eqr7yBZNE1F/tjrYLu2wCKC9YtqR3DHrbzKwYIjwWkQ3hZYO8Y7pTVB7GUIIUdN4f4rPC2JpA/ckm5Hl4aB7wZikoXg3OLZac2S7bKdwVsA4sag8Yj1/CCHG8+2frHMKIYRM94FOLQY93JC2D2PzYJ/eL9JbzoqdCdinpBWoT2xBUFeaLls/H9KKoj5U9CDRiHEzpE1DixjU24nWDtt+SBPclHH/QTnRsEXYNq0xWj7UZapGc5QdzxNEumT3YOYttmLoLtpYSw5AX/Yc21Tl90HLKdq2zgXTlPXKYGdxwO2c5q39Zu+A7VVRbCqWQfPc4vbb/LT1mQKc75TEycVt+13tWeurcU/sUoq4zXMc2tE0Vq2d1Drj8ArEydXtuIW8RnWBbqohniMQrZidM+1ZplFo+6a3KtxZt3IyL/Q/ct2O+/r7tG/q/Ep4GsA5KNnk52lWsn3Ny9Zfyw85grRxGeIuuzK2oFuitq0vcujiFmgx16yPJvv8etFahgrv8jOpsm/3JQ+nWKzxsdBKaO59u+cH13jeLe/avqTD4+H4AsxxKcTJiSyvtAu2LTB9thbEVqaMkXRcR2vejlXasfZNpyUKbmt3sJ0t2j1BnWsIIUQPH9u29LtoSGf8R8O/ADocDofD4XBMGPwF0OFwOBwOh2PCcPokELRtKfDSbLSmCJgkoFYhzdH2LtkxrONuwCdasd9IwQm7vWz0Rfk2UzFIHWdSR3fGPhf3S0DDJWwR0Fyyc5x6ZJ+2G6vicN+GRIcuv1MjhZM7gGMV+PrjFtCIRBvyp/JIaXUE0O9Zzb6j62/INb8L6SFKwwFFmdV5nX0MiRlnCaJehVIkWh37q1gOIZ2p1PaQfcoHUKoYZQ8gX6D0lBBCAJo+K3M/xLSB9qJRAs0lHpbowt8r2W/yDaZs8nU7x/wUHyu3B/cPzinStgFrmQivS9NUMHVELWKAEqb6heokSQhaRIldDNG+mqbyFIC0jCZGFB7aPISu/Uj5hhBC6EHCRZOp3Rgo//a8jf9Wnu9pcc9+d3jV+k++Ke0MfzYkxSCGId9asnvaL3AfXHgbCkJ90w/4uroVO980EWp76WSab+ejfKzl14C+gySQ/L7MY0AJR3LJ6dXztg3XkhzzHIfPBpQ8DD13Xr812O6/8jzty20zrXpW6P7Ys4PtwjpTwNGhjffybZCQVPl50i9bGzZW+D50Z/B5Zf/efF7uA9igFR7bXJA0mSrNwxSEcoMQQji8bn/PPEBrFq6jsml9vlexvnzum8zf4nzaneI6ivtWf3kb51YuV78Izz8c5pKYMvUQnv8yTaK1TGvZGrGxzBRw5aLdy6m7ZvWCqWUhhHD0xY8Mtme/+ZD2dS9zystp4F8AHQ6Hw+FwOCYM/gLocDgcDofDMWE4/SpgQHQoaR8JpgzASpRjXn2LSQhDjv6YjIG0nKxsQVfz8gP77KsrYPDTfusSrxBuLVj9jXP2Dpw0mR4pwmfqvRcgFWSLaajOtNVRX+M6Zu7bN+HOAoRrN/lbcW8e9iFl8ZhX2/aXq7Zvi/fRqmBY0auUGq5Gxn3RtKxSRdpvWqgDOI8zBdDSQ7Qs0Je44lTpHLzO9ECWfqFMoSJ0LmDkqlWlgIHm7Aste3TZaIDDa9aHmuf5urIcUAywCq6ywX2tcGB1TG+MpnYpdabHfRlDyWlFsKR7YNKOJpwQlYar+xtCg6LUAeoboptxlfWUtK+moZwBsM2ijq76h3uC16dpKbDduMTjbur92mC7uA8rbtuyMrVkbdtchvu9w/e0sWL7UlnBOXPPyvYbdla60rFTBZrvyNr80Y/zuSO9dniDj4VShjZM96VtPlZz0dqwDMqeTFY39yHRJ1fj8RhD+kcE7dafZflOjHMt0PKZOCJg0kZyJBToo63wNFDYAk41L/TtVVshmtStbVpCPWJKTGmXdoX9ZyFpC4Z4vM2dqPqW3b/6ZdvWFbxl6Jdxj8ftzB3ro5XHsJK4qeML+jJIAI4viVQK5v/F1/l95fC6lZ3aQGkDn1O7anMNrm7PRDVUex5Wz6/LvAtVFg9xxTEfq7QNyVUwpzRuLlK52Vc3B9vpAkvs8o/FWeUU8C+ADofD4XA4HBMGfwF0OBwOh8PhmDD4C6DD4XA4HA7HhOHUGsCh1AEEcOfx4vyJ/x6CuKurJkbTRT74zTRrfuID0D1AHf1l1vnVrxrPX9xnHUFrAbRNcEq1l1g7U9gBHV0My8XL/N5ceQx6M5GlNc5ZE5d3QYtSFPuIQ9A97IFmQdophoQHtYghy5HNHaviwjkudwA6r3PL9psa6+Ei1ICJji6piQ70rIA6R00CQY0ppclwP0TdX1TiOoZsUQaQfy+dPHRUkZaCI39nju1S9p+3OjvXTFf0Nz/3K1Tu4wVzf//PH/z8YPvbrz1D5VpHVl/xgM83Avv+/BHYcYg9CepKonXTNkU9scdBuxjRh6I+MhthlxNC4HQR0P0O6YPbcC2afqNWQGeAfsXaIq1y/0ka0AchWSGT/oIapam3d2hf52LVfgfjv36J26VwCJo10CU1l/jeZ3Do7jS3V+2mlY1BRt2rcLmtT4BWDiRwBZEdtRahb8kUkeZBv/rYymG6QwghTIPl1uEVa+t8nduQUlIeSvINpt3M2O/iDk/QcQMuGu6JWjbl3ro72G59+lnaV+quhqeB7pI9G5ND1sDHbdD5NkHn90hSsRas/3bmZHzCoycHzVvc5f51fNG2yyCHRHu0EEI4Br19aZ/3lfch8QUSuTY/x891/B0m6JR3xEqpA6kbeX3WWh/oTdk1q+VMDF2lDeMm1Wbq2++6IqPPQXMfr9p5VN/j8+1Ng33Ose2rvMvCzKwI6Vyi3+6er4YPC/8C6HA4HA6HwzFh8BdAh8PhcDgcjgnD6ZNAmvZZNj1g5/PoOQvKjnBJfCxpH6tGNwa10UDKDoKRg1DAWc04h+zKBdshKQP5I/jMW+Hz6MDq6eaalbty8zGVuz9nXgUZhEZ3a0yHpZAMoLTH1CP7TNutwFL3Lf5knxZsX2/JTlApC/ycj2kCIYSQzllbxfvwqVgtctAiBVNClKJD2lesPtI5oZ/PCkD7ajoJIopPthgJIYRoBjpAKpYrmDSBtKS2jdhEDH4vySIpUH8H17nfdObt2J+9cWew/eOlTSoXAxfzK9d/a7D90U2mntJNo0u64paCQefdWTuP3KFYWoDNQoyWK7FQymCXM2SJg7Qv2vaoZQtaV+A+sffJgM4bsvQJZ4/k2MZT/rFQ6DNA0753f7CZ3bzKlSB1LW1beNX6Qufj1+xYkvyCKQ6rX7OxsP883/wehNXHHbFcWYEEhrv27505Lnd40+5JYdf6eFdvKapI5PNCDuxeZjasj7SqPGaSph1r5oH9JnfYlnL2O5wzQwghS+B3dbtfOFeHEEI2bf4eWRXSaIQ2zEVrtn0sNkUyD58VYrBISUVigIkn6QzIFOLR33z6eb7nMw+s/v1nbc4o7Yq0C6qsbFsfxX4XQghFsD7J5DQKtZPt0jRZowt1FupW3+5HWIqx8h17ELeWRCqEx90/WQIQQgiVTTtJlDbEMukkN+xYc9P8rNncrNqx7llf257iZ8HC2/C+cs145MpD6Yfr9m7UvbxM+9Du57TwL4AOh8PhcDgcEwZ/AXQ4HA6Hw+GYMJx+FXDRPl8mK+ymHg7sE2iGQfNLnB4QYTml7y6Yc3m2ZttDTvuXz8Mf9sm2L59UW4t2aeiEH0IIjatGZ5YWjMr60+dfp3K/Fn90sP3yvAUv//1v/RgfaxU+HW9xk+6u2Pfi5e+AE3pHQu2RAoNvzFFX6IU9o8AjoceTLViShysz+3ysKG9tlVXs87hSxbTiUmi56P6j8FSASR1KS4KMAK8xlKS/duU6EUjhpqNpOgK2m9wT5Ci7wppnBav/IzPWnt9qs/v7T5dqg+3/7dDGRqvJdGgBjlU8knsOl5KrI3XE4wZXDyLNTwkhIYSA7duThA+8D5iGMW7Frqa6ALAOpWmeRhJIvAs8pyQwxIdGAbU+87z9e5fvRwJuBt1VXunYX7O/C7tWX67O9GVrxaiy3Y9Zv2vPM0eFK3qVAi4DLbv947CCucz3Y24OzuOqXcvO/SqVw08KpcfcNp05O4/596wOJega5228zr1ulFfjKh8LnRPaCzwWpt6zlCR0mIhkzKRAAacFkHzI/UKKNbfNYyGryPxyRsht1gbb3Ys8Z3SWwQXjkZ1vr8oryVsLdl3FGj9rGys2jjH95YDNB0Jxz/rQ8TlYmV0XWRZQ5/kDlhTVIRUJrRTKkmqzf9Pqb8KxcvI6cXTFxgOu+g2Bx2J3BuQwkjqSPwbpSR/a6UVO4JopWf/6hYuv0r65qzZu/pvizw62s9ujU6aQDke5SQghpLsWjZMXGVJWEKeGU8C/ADocDofD4XBMGPwF0OFwOBwOh2PC4C+ADofD4XA4HBOGU2sAx1mCkGZtDnR/zZaUs/fNtMHLpZMa6Cqg/uwcaxtGAbn8EELoVkB7pK+5iYkMvnD11mD7zfoFKvYbL/zjwfb/dGD7rt9gm457W2YXEza5SQv7dh6dGUh+eI61GHO3TUcQt02zkJb5unofvWR1r9doXzZldUZgzRG1xAamBfcF0kTSXdY2xKAjHLJSmWfd0pkBtKiRaPkytCaB7WhG7Nmx/6puAi1McLsr6Qot0IdAu2viQwbJInN3WM/SmzINx//8jc8Ptq9fu0nl/rvIfndn2/pacp/VU6iD6RVZ6zV9z9qjX8nBNl8/ap9i7DeidSMbpx5rZ1AvTEk20ocCWO6gdnhI24npLGO0gmeF/rnqYJuSJEII6bTdE0w0yCTRB137VeeL9i5o+9Srsqa6sQy6pAMQTokssgsOKVMbvHP3FbsHuZrVV1phUdXnLtwdbP/CwrcG239n8Seo3Ld+/UU7DZl3p80VJ9QvWL9beJO9s1CL16uaVgqtXUIIoTtt5zt1WyJJAO2rS4PtSDSkhfumqYqxj4vVWe8ZeDbIWOjOS3LNGSGDZ3Jun8dWXLF9KWxHopnFBI3jVdZHHl84OdVl+Q+5v+ZgLqzdsPuqmuekbfc1botGGarEfqN9CC1o6DfiynV4FSzXHnO/wTqnHtu8s/ccz6etJUgaK4Jee5mf/2ug0T7oc1/Y61kj5At2rMYFnjew7bPE+ldhi8+9/8nnBtuRaFExQei08C+ADofD4XA4HBMGfwF0OBwOh8PhmDCcngJugNWDhrUj1TtuKTIsW06WhNpFamfOKDv9ZJ/CZ+9kB23n2Ql+6rHVd/gMfx+OCvb5+bvblmT9N27+Eyr3W+A0fzW/beeQ8WfZS8tGnd495M/olXsQRA7MY2VbaDMMIkeqoyOUxUOgaYVWih7bOQakaLUcJjyANU9YZWdxbOuh/ylInWeGNlCP0teIesRyahWCVu4qU4CkEawj64rsYYQ1SbIndBZQfWpHMHMXh59tP9xao3KFA0g1gEvGdI8QQgCmOKTi6t9eONmqonDAVATSkdGh0YBoFxRCCBFa60gSSIYSDpAbRNpnoK3jss0pqVpEjbBIOrHsWUPHVrt74r7uIs+Z+RpQ8iLzwHSC1uXqYBvTgkIIYeYhJlzYPqThQgghD0zR4TUeC/G83bv8OZuT6ntsU9E+b/3z/93/5GD7ItBfIYTwu1CH2sAgZdedsrY5vM5cYQLxIqUtO7/KQx5brXN2jkhzKjBNKfnuO7zzgqXpRJjoMcXXHzegTwsVnf/OrfA0kIGFU3NNnn/v2LMggzGD0oMQQujMgRxEZCPlLbsPxUObXOpr/DyNO5AeBPcuzQllD02ab0gdkORV3AEbFLFmObxqfWV63c6pucRjo1iz+grHTDeXgPZuLYJllTwmqrfgHeKqne9mg9v6/7r6m4Pt/752jfYt52yS/rXCC3a+DZYl9Sr4PLHN9iqPjdIjGwPN6wu0r3x/tAxiFPwLoMPhcDgcDseEwV8AHQ6Hw+FwOCYMp6aA+/u1wXaSk5WOTaOHicpU1/4D4KzWOMg+wlXAmMawtcflLtiKru5qdbDdq0hoMgSnz77Hp7FfMLqgtGqfmL96+AKV+4XqtwfbXzp8ZbB97xHT1xmsbipsy6dt+IKNq4+603y+SRtWXO1ae6bTTG3gKq7siCkRon2x7WXVWrZjbRoBnR/VZZUmUKzZLH+yzjZ4JdSZAc+pIQkUKa7MBb5hTPKH9tEIpAjR1JQWt98dAz2K51Tm+4Wr87KIaaXyrt3zItC8raqsOIZV60jzJpL9jTSKrgLGFcdJ0yrpVJkaLrWsw2ZlWHEtaTKUEpPJPlgVjP1riIqHtk7hXuLq8xBCyDpw/zSRpjCa+ntSwPSUvlCP+S2Yx6BvFe+x1KB92eib4sMa7euet9W+hV2gimUuwMQMnBf6ZW7nVhVWW+d4H84MSzPWpzsVPt+DrtH1f3H564Ptv/qtv0TlXnjBEpM2X7tC+47gT3xO4NwXQggFaEK8LlwdHEIIlXdB8iJUfH/e+lBux8ZgD1ZRhhBCD1aY47E0gSHZs2cXui2EEEJ241J4GujB6uPyuqwIXZsfbMco65AxmAdZSmmTJxRMl6k9C8+4A+lfsFoWaeNY5tbyPpxHn/dN34FknDnra+ruUX0fZAqrdk55SR3JtezvrrwbdC/ZuKlsGR3cK8mcCavxUxgo6ztVKvfzt/7UYPvfvfD7tO/ZwpadYwLjsCgrqY/BIQTeDQpHIpuBZ1z51fu86yJLuE4D/wLocDgcDofDMWHwF0CHw+FwOByOCYO/ADocDofD4XBMGE6tASQLh4TfG6MZWBaNdhmiGwuZ6TKiplhHQCJF1IBEh6Wq1GHcfm7PdAPlHJ/T8QXj+XV5OyYmPHzt/GD78DnWQ/32+rOD7XrDdAlZR/R7B6ZFyDXFFgKoflxmnrRYs4A2Dn3QQCQHrMWhRI450eWB/iyuw+9U54ZaQbDs6K8tUblkfceqUBuUp5XIAOcbiRaV9IFt0/BE0l9Ri6Z1YIIIaVE1/SYP7vqgnYy6bFuQTpuOJmlyHSVrXrJqSNqse0FLF9TwdERH2ody6oyP+paoD9rDmlwXaExQO5r1RHuH6R+RzAdzMB+ARUzaYs0mzikRWvqodph+xMeK52ZHFHxyyMDeApNTQghkdcXXwTekdHs7jEIK/bW3YjovtIAIIYTClN0fTAUp7UjyAcyNxefYKmJ11rRjn1q4N9h+2KpSuU56sg1MocD94u03TQ+XfZLHQmHb6lh4E+1CqBhpWftl29la4IK5c9A22zxPxnUb/6jRbS/yHD/1rumh01mrr7nGOtSpx7uD7SE7o+xki6UnjeQY5sIe98PCrQ37A+y8eufnqVwG85+2DWqMZ+5Z/Ziy8YM6bLu1aG0Ty9Sy/TG4/29LKlLZnmVos6NawQBNP/vA+pdazuB8OrXO7xrNFWuP1iKkbtT5nHZetH3NK3YxN1d2qVwvtfZIIq7jYwV7lkfwApCr8Njol8Derg3a4S3W5fdn4N3g8U74/wv/AuhwOBwOh8MxYfAXQIfD4XA4HI4Jw+kp4ItGlaYl/lQcN0bQjZrUsFuDYvJpN38ylZMVxE2+Bd+V0fZDbCowdWFo6TssuW4t2Kfizg7buzTWrI78kf1m6nB0CkbMX3bJkbwMDuf5Yy6In/PJ7kBe0cnepC3f2IGyzPaB6lnh64qAHs2AoozvsbVLes5+F63zPkrdOEsgLavULtqP4D451ygPVHFTaEns20hzxrocH6iveHT6TYSUtSRmhNTafmQSTAghB32jOws0f4/7dWfa2qZTkMQMqDN3bOeeO9Bzgm2gsyPta9CG1E7hBHuiD+oocZoItSFICsYQwKG/v09/J9W5ESWfHPLfN6uTSBJSkG7srdicltvi2Jb+ItDkQikWH9g1Yh1Rk61Jyu8bFdWurli5vvQfsJI4PmALk5lFo6LXinbcl6fuUbnfO7w52P76Y0s7+Ni5DSr3rVvPD7b757nPoLRh/yZQdI/4jk89st81l+w3uRbP8cVd67vJIVPA/VmgynaM5i7ucH+PjsF+CMZgIc9zS/NFS4wqvcb2G2qzdVYYldoTQgjpklG9nXNgiXPEfahfhBSPDrdvFtt8cngNnpkrXC5ZNZqyu25zWvmxPrxs8+A671v7qs0Z/RJITzR15RBScpbhHkvfSOBaelPyDgFFp+9bv9n5ONt05WEaa8KYevceW9jltqyPPjjHz9pf3PzMYPvx4+pge/Y1pdut71Vv2zmlJTn3NsyTa+e4jv0Pn4rkXwAdDofD4XA4Jgz+AuhwOBwOh8MxYTg9BYx00LhUAPzNHq84Q9pXV1Jlu0DtwMqk+IgpunQaVtU07HO+roLKHxmNkK/zsXCF8OKbVm7veXbaX/oOfPZeQgpNKItNSFaYkVDqAwgib1u5XE1W9yLVjW2jK86Avh0Oood9uAJbV7Di/Ts2eiS7wKuA4z3Yt8Srx8JeLTwVoKxAViKnsII3Bto3O2D6LQMaOVL6BlaZZm2hR7EYJFxQOaFDaayk3EdjvH9wXYVNdvXvz9mxYqAAutO8sjQPoeepUFh56LO4Gl0pFgy9j1rQn+S6cIxGZaYV8TqzFvTzVFaOx8nJ25rcAiuuk3nph5pCcgbI1sxxvyvpHPk9o8OSOqyAnpU2iiGBoisrrGFVeR7uQSqr/o+eN/obVzrGXT6n7RXoC8fc3//MymuD7VZqffDlIlO7m+XqYPvVvNGhrb6szL0OVN4WU2oRdKGZh9YJG6vcB3desrG78DbMXSIbai1bueltHjMZrjCHNszdekjl0lW7lyjDyG+w1KDzAtBt4kxB4+QMER9CypCmkwB1iNSupqkUDkF6JJKayrb1y8Nr9ru0wv11tgy07GVrw/oc05zTi0AVv87Sje1PGE09dxue3Ufy7ALkGmixwftw/kMXhR/UaR2xU7WxkpfnOqaJpPB87sxxuf41m+P+5h98kfZdv2JJILlNO1ZXDFIK8IjqzNo4rNzn94TOko2p4obISuZGJ1eNgn8BdDgcDofD4Zgw+Augw+FwOBwOx4TBXwAdDofD4XA4JgynX79OSQCi5QG9BSUwzDAnnYF+L2zu0b5oGspifeXRdiOovUgOxM4DNDedea6jtGu6ArTSmL81Rm/QMg1EeZvL9cv2Hl3Z5LZBDQOlOCyxPgZ1GvkdWH8uFjaUNCBazBR0lNF5s4XIxI4ngO4rxttwZ53LLVRtW/Q3lJhxhkCLkajMFhwx/o1JHXr92G6qI2ybTiWeNQsO0rKFwIkUYBEzlE4Cupqswa7uAS1E0JqnIrY1oPvLNaDPH3M/TCE1obQlfQO0P7kj0M52RNuXnqypG0qCQT1vzP+PRGsd1AemosWk+4f3QdI+sO1Re/mDSseZxjwZRMd2PjkZF2kFbHog+SU+YIuGzsWFwbaEtoTuVdCbjXacClMPrZ3bC9ZnWvPcfqvfsLbd/BT3z3ebZmmx2bb+vpBjK59fmjdbmO/VTQOYj3n83CuZRrNXZ6FTb2qE7k+ucel1659Hl6w9pze4D069b/2pP8/PGkyJ6l0EO6s2n29/yuYGTJ2IyzxnFPdB5yuWWOEppNEoVGNKWr8xyTpoA3XwHF9HZ9puzPQD+/dGl9vmuY+azq3etX7YnOdyD3erg+2u6OhKO9ZnGyv2u/k91mHjszxpgk3boxqVq3/UtJ2ZWHjlYIrDFBMJ8aC/i3vw7JbbXXzD2r5xk8936ys2VlDmP3OfDza9bvM6Wh+p9VP+ECxyxCLvh/mc518AHQ6Hw+FwOCYM/gLocDgcDofDMWE4NQWMVOyQDQzQw0zXMEUXbZjrfHaRXawjpEgw4UMcziPYl86DS36bP5UitZWr83tu7sDOsbtgVGxhn+vAEHUMG1eLjSiFBA753Iy0bwz0XVyU5fh37DN6NgP0cH803a4O9NnNy1bsAKjMfabeCGhHMSNr0/FYO0LZX1kbXecTBFGsYj+UYVtBHx2igPEeqTNJpXJiuXha5AzHQOeCrUwqKRjxrCU+DNmlgN0HJrKopRE5/jeNYshkfBG13+C+nKgV0KBuoYB1bH+AeUncwFQfTWRBKx0cy1PShjBXYPtmkpgSQZj9kKWRJrScAdJpoLXVqR/ar7MMCQxSLv+2cWrpFU4WyMNcgIkrWVH6MYzPAmwv7rBc4fAZO4+Ze0y9/b23PjnY/sRlO6dv1a9TuRv5bwy2FwqjEwfqDeuT/ZLYZT20fpFrjraBwXSKQh1tlLi+Lsho0gL3wbgDzyTon/0q34e4BbZKYL9RvsPjOHsE9+TyBd43QjbxpJE1TAKQ7MjOBZvL4/chuWZmhor11kyKgDZSIYQQpXZfko61/f5Hua2/+W1LiZm+YtZvF+fYBu7fuPm9wfbfX/8s7Tu6bscufdv+XeVbSNPn9u36O5fYHiruWrmkJZM8INew49bP8zO5stWHfdY3qu9yPzyEoTL9/dGSNaR9y9s87/bhfaDyaLR9VLJtbarzP9q2nRb+BdDhcDgcDodjwuAvgA6Hw+FwOBwThtMngYxZbZcBJRJ2jSpUKgdXlca7ks6A9AZSY7L6MsY6IMg7K7H7PSaI6GqZ/ox9psUVkboCsrtoFEN8CKuM1dUfmiYR6g3puwzo1vwjvv50wT7N07kLvYYreodo77fu2PYqrAKeFYdwpP2AXotq4qa/X7N900IPN57OKmCkW4dSIDKgs+G6hlYs4wpWWUlMfRZWs4aSfNrH88BUDKGbkaZRyj4Ceg/TH7KOJAsA/Ur3/4hXFSdwT3T1PIbe4/nquAn7QNtgO/XG0O1KAQPSmtUXS1tjW+E160rf9HA0tRGNOfaTQtyG1b0NnuO6KzaOC9tGlaYyB3VfMLlGYZ1TJ3qXbewSlampQIC0BKu8a3yvMI0o1+L2mv+KtfUf/quXBtsz1/m6fvEf/rXBdumy3Y/lGaaDK//M5okWBwuFHkxDMZxiJAwdJjdMAxV7fIXnoHzdfli6V6N97TUbM8UH1r6dtSqVw9XC+ceQiiGpCiRRkHmX5oKzBDyTj59foV2Vu7XBdgSrlPsLstK3avNEQVI3Ikh5qV+07bwoirqXra8sVGyeubu7QOV2GtaGSZv7cmnb/u5MQyJLQ6RS0Ld78/Icxvq27Dwaa+y4kWtiYhL0tQ3uiI0Vu2ZMBSkecbnKYzvHRF55miuQIAayh9yxJEbBOwTJGfTRVZT5GpAufvjV6P4F0OFwOBwOh2PC4C+ADofD4XA4HBMGfwF0OBwOh8PhmDCcPgkE9HFZXaxZmlANWD1EBearM7QjUS77CPQyF0EDU+eEj7QMmrUupgeIPgZ0bnGdifR0CvRRYLkRg7VFCCHkoU5cjp08YkuUGGxbsjxrFqI900ClF5fDKFBSAGpKJGUhQhsMseyIUfcH7Rl1WQ9G+rBN8w9I9b6CbcmQ7mVBbEHOCBFo8TBxIoTAGk7QrEWq38O+MmQrAjpC7L9ix5NloOFAzZ7cr3gK+obcrwzPEfSAQ9Y/qMvDcxdbmQz0dlGQ+4P2Oajtq7OOMMMUjgz0Z3r/i9CmqsVE+xy0FlIdIVjpUGKIaP7I+kePVRxtu/CkgFreSOaMAuprQf/Ze55tk3KY4iJ9EPXWEcx/3YtsdVF8Z8PqnzNrEkyECYHtrbozYiUD2qMLf9f6+9c/9jEudg5SF75qfWv9IuuOIAgllLckPQj6RfHA9s3e436RtOBZAxrP/CGXK98ya5Z0nu1NClvwPKlOwb+zvUuowTMJNaqiB++vWppIsl2jfePSqp4o5mxslR7zOO7Ng34dnndxjed4cNwJzfOseyyvW9nWorXvzH1+1u6u2PPq4U51sN2vc1+bXjOBXO88zye9YzvHuTt4/6lYaC1a35591+5dd4Hnwj4kucQd7oeo+4vbdqz2HJ/vwvdsPt17yfp8mvD1Y2LI1CMey6V9a+Di3piksXfMgqnz4pXBdrIu/j743iRrLLIlnh9OA/8C6HA4HA6HwzFh8BdAh8PhcDgcjgnD6ZNA0N5CqKz+gS2zT4CG1M/o0Qwspc/p0nn7/B7ff2T/DLYvIbDbdQafwKMDcW5H6xMJw052oQ78fK82FRDETLY1QjdjWokaNWRz9um8D2kAhV2muVJoG7S3iQ7luqBcJHQjWXrs2T3JqkyPRGgXgv9+/TKVQzpbQ6mzh4/C0wDRvmq/gPQbUpmaGIKUbZ4/+0dwb/FYkQS+R2gtQ5Q99wCygVGLGKgDtyNNeAGKkKxThLJHOjQ7Znqc7FLQBkZpdLS0gbZRWpao7e5oaoOoeE1CQWspOL9IpyWgxDWtJmuL78IZANNTujeZ2i3ctbSj9gu2DynJEELIgEaqv8x1TL9m1C7OY5HMY71LJikp3rHjdq6y/0rUgZSFTaYKkSprXLD5b/H7LEOoddDqws5j6iH3d7TLyB/z+fZhesI6utM8juOe7as9D/dbnMiSrl1nKnZAxe++N9juvcSpJnROi3CP8N6tcj8rf9/mO3zuhMDpPGeJqAXPp61d2hevWdIWSZ7yox/5U7dY2pRO2+/yDUjWaPONqL5mfQj7U1+Y8d060Ogd7jflbasTad/CIfdDpG97YOcWd/hdowOpLnGfzzd3YPPV0RWbk0p7YgNzCd4vcK6Sh/zUI/td+QF75HRWrI5O1c5p+tv3qVz/6vnBdgEs4rIpnjPbV8xap/igRvviI3kenAL+BdDhcDgcDodjwuAvgA6Hw+FwOBwThtNTwCX4pDrFztoj3yKFKs3g8/MQtYmrSiH5IJIVcumBfR6N8XO2UACYkpDN8Pn2q/ZZNtkHOljClTE9IQUaVc+JKAClvWGVZQ5p0+VFKoe0b+jB6ktdbYv0u1AP6F4fXbFVgRoSTdeyDfSiJEvgKqNomtswmq+GpwJcERpJz0NKHGjDtMHXFVfgWoSyxTppFbDc8wxX0iKlKitdkXolOjhIakgejiUrXaNIVr6OKEerh3XFLZ4+tpuuogWqA69R6fasbuM3laSVuAp9FttGk4G07QcFR68q1vYdWp18BkAKOL/JlE/3oo3rCKhMlaEgj4SrLUMIoXvZqM3ce0YH99dkpes9o/1QopPfOAijkM7xOE4hhL4EqxQPr3C/WHrd9iVt62eNFXZzSKFL90p8f2fv2r1qLcH5HjP1ljSsfcs7VkflnkRQtEevvu8/byspI5gz0wL3Y0yCwkSr4ibfE5wzsxI/NjtyX84KOAbDCj9PwrbRuckhSEM0Iaht7dG5wDKXJtyjuTesvv4MPyfjnvWpbgVWeh/yOH70OTvWzD0+3QwVKscgWVjnZ1dnGaRS4ODRXuTras/asaYey4rjaZDRwHGjHp9veRtkOX27Ru2HKOc4fIFX4k7fs36UtKxfpytcDuVhMdDI6mBRfAhOD/IOpXKm08C/ADocDofD4XBMGPwF0OFwOBwOh2PC4C+ADofD4XA4HBOGU2sA48PRmjq0J0CNQaRWFGjHIdw26uhQK0hWEUE0VWgdoYkO+Js91sQkYPeC2pmhFA/QPVFKiNp5oFZOUydQ93jBluZnogmKepL+8MG/q70NXGcmGqrkEbiGo53JLNsWxJDIQvtU20htw10lEmuVswLZpSR6v+D/M3jvxMKF6tN+0wdNJFqiVMTCBPV84yxM4B5FZbGtQc0e2JkM9Q10f0cNaF7SdLqgdcmplcrJOsJIdbpt0PPhuWt9uE8SfwhwXdEUJw2QJhLnkL5qIOEcVWOpiUJngHTT7ELUsicBrXQE9hPdBZ4zCxu1wXZviTVkyau3BtvZM2bNVL61TeX6kH6Bc3B0zJrM1hXTG+WaPM/k90HnDBYe0xuiqe6phvFf/P5YLMFA91d5zGMrv2/nlT+0fpGIJdbOT5p+eXrD+vTxNdZDVx7a3Bh1pF9ASlRyCHZO0rfSaUz/sGvsVVnnlv/e3cF2LPNpqXH2OtQQ2Joq03EA4wQtRpI9fp6gJVjyO2/TvplXPjrYxnbqzfCxph6Yzu34so3xnZd4bMzetvYt7UsqEnS3tGh9qHWe27pwYG3dXoRzKnN/nbkH91zeIQoPrL+VbsM5TPMc34U+ULlr7xDdRZ7Hkqb18+nb3L6YGkM60jK/Q6CWmN4hdC4E3WsmuvwgqUSngX8BdDgcDofD4Zgw+Augw+FwOBwOx4Th1BQwWYKopQHSnGhhInRNaAF9V+JP7OjoH41bzry2auUggWPIwgVcsdUqAimlCGxbIrWUwL8xJUTp2nmgGIX2RpqarArUAgNc3fFTcVxnCxP6laap4HkVRrchfTqG80s3Nqkc2XloOoUmSJwVsO9JcktAO5K8Js0AkCrty72E/oD9N5MkDKKbwT5ArU7oc356Mo2mx4r03gENQONE7VKAEs6O+Hyx7xG1LxRDhqkbMdxzpYDxPHQfJpxgfdrW+Hc2whImSNtokoHOMWeA7ObVwXaEqUUhhPjgZDf+glg2ZTtmqxHPiqQGrhGTFaIOU2/9Wfu7cB9SHMSKqnxry3bNM92cQb9ASQlasYQQQoSOQMc2fnJH/A2hs2BjsrAv9kAtHHd2jp01tsSYeWBtVXgIKVPnmAJuLxllV35/h/Yl8GxIF+yau/NM8yV1oNRgzsB/DyGE7JLJd7qzQg/viX3WGSEFO7N4h2VO3Y9eG2znbz8eWUcGz674Y8/Tvgio87Bj96EAKSMh8DN0+j3rN1P3eawidazJHVkOaN8FK5c/lGc3UP35A9zHY6O9YPNuocZ1xED1olRAka9Z/8U0Fb3fKJ0Ib9yifWHFLJ36s1YHjqEQWMLWumFpajnph0kdpEI5kWkUlsOHhX8BdDgcDofD4Zgw+Augw+FwOBwOx4TBXwAdDofD4XA4Jgyn1wCiLk9jdzZMYxBfuWg75kRvgtqmR1u0LywtWLld0xuoNUmAJfhZEfQxosvL8NiiPSIlFuoX66LfA60cxcKdW6ByZLsg+i2yS0F9ZFeuC9o3RusXjb7CGLea6LxGAJf6/+AAYBGD119hLVI2C9FyYqWTaqzXGYH0Zm3RVaEVRgptfSw6yhloQz0A2Megnk/jD0lXilo81a+iVc0YWSJZ2qimDq6F7GhU/4bWLGpHNKL+SMZywD4AWslM4vRIi6d6VtDzRUWrb5zeEH0g4mmxi8G+pjrKZEyjPiFkedDNra3wPmzPW5Z3Fc9KXBhEd6HFVgghZGgXhXZOcq2FdyAm7qLpf5IdiUyDOuLNPdrVuwS/A2uWWOaW9jNwTtOmt8IotR/8DTZVyejvC71Fm8fRiiaEEFKMWoN+lt/Yp3I5eE50Pn6D9sVtGxu5dYvMi6Z4XPThWmKIuNN+Fh/ZHBpXWG8WNZ/OXBgfWbupnVX+PmgiYS7o3eEMthxGNdYkQnAVNGWLVSsn+uoU5rzcNvQ9sZgKfRvXaYXnyT5EEhZrdi1xh5/dfWh7XItQqEksKujj0KblBzshGhDqa6yxPrS0CXq7AsxPh9xfk8fwvL50gfahvrVw12yc1Eqve8HeKXINO9/cZo3PHeeXEvdDvS+ngX8BdDgcDofD4Zgw+Augw+FwOBwOx4Th1BRwVrdl9ZEmS1y9ZPvwU7TaxUACRTi3RLuiI6BBkG4r8ifg3q07g+3cBbOEGbLzgM+jUZv3pWC7EO/aOaXznBgRw9J3/Iw+ZPWA6RxVpnoitHHBxIgCfwJOt42mQLooE0sHsgRRJ3CwhUF6WMshZRFF0DYzTL2FNtxLTd24zJ+6zwopUJGaQEGWI0CVRtN6XfBpX/oNucbD5/ZU6BF04ce+F+mIwvvVkaX/eP5kKzPG2iQDaltd4nHsKVWaQp0gS9CEFwLcc6XK0cZJz2NUwolSxUOWLh/UJ/ICbLdIrH8oTeSMEL9117aXF2kfJibEMzZP9le5HCYEKFWWLtjvcgd2fZ0Vnnf7a2AD0gX5Q0vGO84hZaZANRniA3SvsKVErwIWKS2g+Ht87xNIxVDLFUzhiMHOI5Prb63Y+VfuWn09sYGJoJ0K60wPI81X/6TJkqZf3eByaPWEc7dII9I5O6feFNOXOZ2jzwooQ5FnV/rQ7Iki6Ie9P/EKlYt3wC5tidsXn9/xPkgC5LMR0r7tK9bPk4YkS8H9z+1IIknf2jcFKrMriSy54y6UA1q2yXNmDPNfXJf5pGzzLqbQTB8LlQ+SrXTW+nL2gPtQ+lGTH8QHLOfAfpnu2XYkFDDS1CTTUKszTEwq8PyJkoDTwr8AOhwOh8PhcEwY/AXQ4XA4HA6HY8Jw+lXAF2y121CewYat6MWVX0q9RUhFHol7OiYwQIqHBt7nzoMLOVJlsvoyQtf5rrjawwoxok2VRsY6keaSBI4ME04OhCzDVcGYVJGJO/mirRbKoJymLBBlpwkn4H4/bnUkrmCN8rBKUyi6DFZqK/U21FZnBKRNoyLTWRGeP1AAQ20IVKmulo1G3nMZKiR1GEMB4TkqtYu/w9Vueu+QHsYVtnJO+PdQCo/KMT7456asEEfaV68Zf4f1a914zSiPkFXb0RTMD13uy1QOqXJZ7ah94CyQPXPZtutjaBdoS0rBCCFkc0bLpe/dpX0xUuBQrnifV/BmuAoQ5rj+PM+7uJJS0wOyaWs/pPJwFW0IIUy9aRKV/oLRje1VpqWjvvUFTFLQY3fnQFIjqRAFSHhAaVAslBeuuE41CQrmuOKOtWfnKlPbBVgti6usNRUKWy0v/X1IinNG6J+3laNKxUe4GnXL7l1xU6hXkAOhfCGEEKIHkAyFEiihVNM562/571gSRrTKbd2Hld/9d9+nfblVeK7DM7N9neuIkabFFcHyPErL0FeUooe26i0Z7a8rbrtrsDJ3F6hySAIKQVYFa2IW/B2D04kmhkX7ME8Cnd9d5LGMK4mjh5zcla2wzOQ08C+ADofD4XA4HBMGfwF0OBwOh8PhmDD4C6DD4XA4HA7HhOH0GsAt0J+ko/VfqMnJRCsXga1IJnYE0aFpE6KqLEdHkK0GaLmKol/DhAtNE0G9ANQ35OiOaR2ggcv2a1QMkyWypmiCIE0jXbel+fEsL9uPQPfDOjRpa9D6jHOgp/QL0ceQDcoI3VwIrOFUDaDaJDwVaAIFnH/WsutPRQ9HqRuaEoP6S9RvjtMAYnqI3H88w6E0EexfYNOi+r0oB32vLZo9rA/PXZNAEGhboxo6vE5MUxE3/SiC+6+JD72Tr2VIU4i6P9wXiU6tNVoTm9bFkuksAFq2rChWRKBTw/kplQQK1DJ1Pv8i7Ss+PoZy1p+6q1Uqh0kIMdyfqCuJK2CzkjwWuxSYJ3FOVjuLFCyiYkg+KoklVn/R5sL2EtvA9Ms2TqbeMV2a6qai3dpgu3fVtGGqc8N0jqzEGnDUduEgzL9xl8oFmOOyImoAuVh/BtqmIXpOTbw4I+DcHTdGPwt6H7ky2M5tc8ILaidjtCYKIYQqaNGg7+U3WIuK4z+7YZZwQfSxyR1LDEs/+RE+R7B+SXbtXSBX53mH0i4wJafI9x+TUNIFtmaL96AN7tSsDpkzs9g0dfR8HpOs1Ts/T7ty90xHny5XrY4HrN8L51nr+AEKt7kcWtXpEziTtK7T4I/BU9zhcDgcDofDcZbwF0CHw+FwOByOCcPpKWCkcjSsHSlGpCh7Sl8CTaFL6SFsmmxlxDoCnfejKaAY1OolBhpK0gIioKaRKo2UooPPrUhfI+X7g4JwLUJfhYf22TtZO28/UdoMbSLw/NTeAK+zwJ+90bkc9w1R4Gg5g/TLrtBD7TG0ZJnpnbMCutoP3VekYoDmjJXmRDpb2wYpRux7cv0Z3HO0nxlKHcHfiLUE0c9wjpEe68goC2p3lQdUrP9G0r/wfClpQ6h8slNAGYXSt2BhkzXFjggpdrRgkOQW6r94zX3pa3hf5TySFU4UOgtgeoDKXLKSnV//ho33tCjWPnA/ck1Jo4H7g/NEciQ2OtCfMKlAk0WQzm0/c472Fe+YrUTrgs1rSYvPKb8HlDBcc3+W5wGcJwu7Yk3StTr7VeurOaEUu9BuuX07riahFIBGT4vcL3I7QPNBP0M6NIQQcjWbQ7COqCISJUiTIhoy8HWdJSJ47PSWuG3QtgTbUOUa2dvvDbb7H3+O9qFcIP/AKNUh2yeg7GNIYBp6xi2YtCu+95h2oewpxXcBof2xb/dhrKGdj0LvD9onYRqRJksVNmp2TlVr3+4C9/ni25YMkkrfwGdNCjKFZHX0vNV/2yxykudv0D7se/2tbdqXLLkNjMPhcDgcDofjj4C/ADocDofD4XBMGE5PASP1oqHu6PaPtJzShvCJFVf2hcCUFX46joXiyZA22jfneqW8AtIqsi/dMcohXoBVO0LnBFxVg5+H9TM6UNFRjVdZBaSp8dO5UG9I9SLNq470YcwKVgqKhvD5aEdWByFF1BidZBDB5/ygq0r7Y9IvniCIitR7DvQ7UbSarIG0r64kxhXSHUgkEHqAaMkY6tdUkDFpIrhSd2j1OALPH883G3PumuqC0gHoe0PULv6Nq3S1PlwVN4bajbD7aluPSlOR9B+SH8i8MS5B5EkBZROd87yav/Bdo9RSWBGp/9NGGjmWeae3DCv9gL6K7z7ics9eHGznDmGl9CGvzE0hTSRXlxWsMO8UaqNXktJvoP/oitjuMqRCbIyed3I7Ri82Pn6JilXetpWP/WWjDfXcsR8nNV61nJWB5gOJQpoX+dLdh1b/lTUrV+E+mGzbtfSX+J735p+SHOZNowpz17gNKYECVq2mm0wbxui4cXuD9rU+eX2wjakuuPr6BweD5w5sd9eqVCy3D3PcRZYihEdG4eKK69xt7vM41xT2rT9hakcIIXRnbA4qPZL0E+iH7VeeGWwXX73D5TAZpmP15belrwG1nROZBt8HkJHJGMV3iBy882RAr4cQQrhoq4XVSaR36cPLYfwLoMPhcDgcDseEwV8AHQ6Hw+FwOCYM/gLocDgcDofDMWE4vQYQdCSZaqriEZqyRXbFDkfGe1PaRRBrioWqbYu9CyI9NA0gWqyEIPYucqwh3dMHvxFbFVIsQcpC1hJ7A7RjOGQNINmCwPL26Ih1BOSmjikpj9iahVJHSqK9Qo3hrXtwXNZHUH3QFpnuhHbTxIMha5kzQlozLc6Qti+AVQNp3kR7BtrJ7FisNcAKCO1dhux9UH9JFiaiy8yP0NSFELJUz/9fQBNZRtjWpE3W4iQw3rCdQmCtj9rnyEnZcUuQQNKV+40aVklyUO3vAGPGMmk2g9jKoKZQ5w09rzMAWm4U74r9BPSfZN/mgs4VtmhAW4l+ha8pAa1QlqDmk/tFguksOAfNsSVIgDqSnUPaRfplsNzoT4kOE8ZCbsv6ViZJLAVILsmm2VYL73+6ZH218s4WF7tg81Ue0iMwFSSEELqgvSObmsCJLL1Z0Dm+fpfKRagxB61cImkPmfZxQG53zHh6gkBLtPQ+6/dimAt6K6BRkzHYh33Ru/dpX+ld02KSdYrO/WA/1r18cqJFCJx+MWQlN2fPtRwkgYQZLpdOQ38Fy6H8Bj8n8/A+gX0thBDCNtjblGFu0XPCNC1I9IqkDXE+QJ1fCGIRtmnpN2qrlq7A3I31NWUdxVumU8xuXqV9ycGH74f+BdDhcDgcDodjwuAvgA6Hw+FwOBwThijL1Nbb4XA4HA6Hw/EvM/wLoMPhcDgcDseEwV8AHQ6Hw+FwOCYM/gLocDgcDofDMWHwF0CHw+FwOByOCYO/ADocDofD4XBMGPwF0OFwOBwOh2PC4C+ADofD4XA4HBMGfwF0OBwOh8PhmDD4C6DD4XA4HA7HhOH/AzDtk3Z78UUtAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 800x800 with 16 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Visualize target data\n",
+    "visualize_data(target_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7b706147-6d5c-4319-a7b0-87decc1e6a7f",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750796,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "7b706147-6d5c-4319-a7b0-87decc1e6a7f"
+   },
+   "outputs": [],
+   "source": [
+    "# Define and initialize model\n",
+    "class NeuralNetwork(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(NeuralNetwork, self).__init__()\n",
+    "        self.feature = nn.Sequential()\n",
+    "        self.feature.add_module('f_conv1', nn.Conv2d(in_channels=1, out_channels=8, kernel_size=3, padding='same'))\n",
+    "        self.feature.add_module('f_relu1', nn.ReLU(True))\n",
+    "        self.feature.add_module('f_bn1', nn.BatchNorm2d(8))\n",
+    "        self.feature.add_module('f_pool1', nn.MaxPool2d(kernel_size=2, stride=2))\n",
+    "        self.feature.add_module('f_conv2', nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3, padding='same'))\n",
+    "        self.feature.add_module('f_relu2', nn.ReLU(True))\n",
+    "        self.feature.add_module('f_bn2', nn.BatchNorm2d(16))\n",
+    "        self.feature.add_module('f_pool2', nn.MaxPool2d(kernel_size=2, stride=2))\n",
+    "        self.feature.add_module('f_conv3', nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, padding='same'))\n",
+    "        self.feature.add_module('f_relu3', nn.ReLU(True))\n",
+    "        self.feature.add_module('f_bn3', nn.BatchNorm2d(32))\n",
+    "        self.feature.add_module('f_pool3', nn.MaxPool2d(kernel_size=2, stride=2))\n",
+    "\n",
+    "        self.regressor = nn.Sequential()\n",
+    "        self.regressor.add_module('r_fc1', nn.Linear(in_features=32*5*5, out_features=128))\n",
+    "        self.regressor.add_module('r_relu1', nn.ReLU(True))\n",
+    "        #self.regressor.add_module('r_fc2', nn.Linear(in_features=128, out_features=64))\n",
+    "        #self.regressor.add_module('r_relu2', nn.ReLU(True))\n",
+    "        self.regressor.add_module('r_fc3', nn.Linear(in_features=128, out_features=1))\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = x.view(-1, 1, 40, 40)\n",
+    "\n",
+    "        features = self.feature(x)\n",
+    "        features = features.view(-1, 32*5*5)\n",
+    "        estimate = self.regressor(features)\n",
+    "        estimate = F.relu(estimate)\n",
+    "        estimate = estimate.view(-1)\n",
+    "\n",
+    "        return estimate, features\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "cfd79aed-d467-4d59-a44d-df05177dfd58",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750796,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "cfd79aed-d467-4d59-a44d-df05177dfd58"
+   },
+   "outputs": [],
+   "source": [
+    "# code from https://github.com/ZongxianLee/MMD_Loss.Pytorch\n",
+    "\n",
+    "class MMD_loss(nn.Module):\n",
+    "    def __init__(self, kernel_mul = 2.0, kernel_num = 5):\n",
+    "        super(MMD_loss, self).__init__()\n",
+    "        self.kernel_num = kernel_num\n",
+    "        self.kernel_mul = kernel_mul\n",
+    "        self.fix_sigma = None\n",
+    "        return\n",
+    "    def guassian_kernel(self, source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):\n",
+    "        n_samples = int(source.size()[0])+int(target.size()[0])\n",
+    "        total = torch.cat([source, target], dim=0)\n",
+    "\n",
+    "        total0 = total.unsqueeze(0).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))\n",
+    "        total1 = total.unsqueeze(1).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))\n",
+    "        L2_distance = ((total0-total1)**2).sum(2)\n",
+    "        if fix_sigma:\n",
+    "            bandwidth = fix_sigma\n",
+    "        else:\n",
+    "            bandwidth = torch.sum(L2_distance.data) / (n_samples**2-n_samples)\n",
+    "        bandwidth /= kernel_mul ** (kernel_num // 2)\n",
+    "        bandwidth_list = [bandwidth * (kernel_mul**i) for i in range(kernel_num)]\n",
+    "        kernel_val = [torch.exp(-L2_distance / bandwidth_temp) for bandwidth_temp in bandwidth_list]\n",
+    "        return sum(kernel_val)\n",
+    "\n",
+    "    def forward(self, source, target):\n",
+    "        batch_size = int(source.size()[0])\n",
+    "        kernels = self.guassian_kernel(source, target, kernel_mul=self.kernel_mul, kernel_num=self.kernel_num, fix_sigma=self.fix_sigma)\n",
+    "        XX = kernels[:batch_size, :batch_size]\n",
+    "        YY = kernels[batch_size:, batch_size:]\n",
+    "        XY = kernels[:batch_size, batch_size:]\n",
+    "        YX = kernels[batch_size:, :batch_size]\n",
+    "        loss = torch.mean(XX + YY - XY -YX)\n",
+    "        return loss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "ccac040a-7d18-45a4-b390-40e3dfa51756",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750797,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "ccac040a-7d18-45a4-b390-40e3dfa51756"
+   },
+   "outputs": [],
+   "source": [
+    "# Define training loop\n",
+    "def train_loop(source_dataloader, target_dataloader, model, regressor_loss_fn, da_loss, optimizer, n_epoch, epoch):\n",
+    "\n",
+    "    domain_error = 0\n",
+    "    domain_classifier_accuracy = 0\n",
+    "    estimator_error = 0\n",
+    "    score_list = np.array([])\n",
+    "\n",
+    "    len_dataloader = min(len(source_dataloader), len(target_dataloader))\n",
+    "    data_source_iter = iter(source_dataloader)\n",
+    "    data_target_iter = iter(target_dataloader)\n",
+    "\n",
+    "    i = 0\n",
+    "    while i < len_dataloader:\n",
+    "\n",
+    "        p = float(i + epoch * len_dataloader) / n_epoch / len_dataloader\n",
+    "        alpha = 2. / (1. + np.exp(-10 * p)) - 1\n",
+    "\n",
+    "        # Source Training\n",
+    "\n",
+    "        data_source = next(data_source_iter)\n",
+    "        X, y = data_source\n",
+    "        X = X.float()\n",
+    "        X = X.cuda()\n",
+    "        y = y.cuda()\n",
+    "\n",
+    "        model.zero_grad()\n",
+    "        batch_size = len(y)\n",
+    "\n",
+    "        domain_label = torch.zeros(batch_size)\n",
+    "        domain_label = domain_label.long()\n",
+    "        domain_label = domain_label.cuda()\n",
+    "\n",
+    "        estimate_output, domain_output_source = model(X)\n",
+    "\n",
+    "        estimate_loss = regressor_loss_fn(estimate_output, y)\n",
+    "\n",
+    "        # Target Training\n",
+    "\n",
+    "        data_target = next(data_target_iter)\n",
+    "        X_target, _ = data_target\n",
+    "        X_target = X_target.float()\n",
+    "        X_target = X_target.cuda()\n",
+    "\n",
+    "        batch_size = len(X_target)\n",
+    "\n",
+    "        _, domain_output_target = model(X_target)\n",
+    "        domain_loss = da_loss(domain_output_source, domain_output_target)\n",
+    "\n",
+    "        loss = estimate_loss + domain_loss*1.4\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "\n",
+    "        # Update values\n",
+    "\n",
+    "        domain_error += domain_loss.item()\n",
+    "        #domain_classifier_accuracy +=\n",
+    "        estimator_error += estimate_loss.item()\n",
+    "        score = r2_score(y.cpu().detach().numpy(), estimate_output.cpu().detach().numpy())\n",
+    "        score_list = np.append(score_list, score)\n",
+    "\n",
+    "        i += 1\n",
+    "\n",
+    "    score = np.mean(score_list)\n",
+    "    domain_error = domain_error / (len_dataloader)\n",
+    "    estimator_error /= len_dataloader\n",
+    "\n",
+    "    return [domain_error, estimator_error, score]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "98583af6-1fbb-4091-bc22-b1ce362e8f21",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750797,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "98583af6-1fbb-4091-bc22-b1ce362e8f21"
+   },
+   "outputs": [],
+   "source": [
+    "# Define testing loop\n",
+    "\n",
+    "def test_loop(source_dataloader, target_dataloader, model, regressor_loss_fn, da_loss, n_epoch, epoch):\n",
+    "\n",
+    "    with torch.no_grad():\n",
+    "\n",
+    "        len_dataloader = min(len(source_dataloader), len(target_dataloader))\n",
+    "        data_source_iter = iter(source_dataloader)\n",
+    "        data_target_iter = iter(target_dataloader)\n",
+    "\n",
+    "        domain_classifier_error = 0\n",
+    "        domain_classifier_accuracy = 0\n",
+    "        estimator_error = 0\n",
+    "        estimator_error_target = 0\n",
+    "        score_list = np.array([])\n",
+    "        score_list_target = np.array([])\n",
+    "\n",
+    "        i = 0\n",
+    "        while i < len_dataloader:\n",
+    "\n",
+    "            p = float(i + epoch * len_dataloader) / n_epoch / len_dataloader\n",
+    "            alpha = 2. / (1. + np.exp(-10 * p)) - 1\n",
+    "\n",
+    "            # Source Testing\n",
+    "\n",
+    "            data_source = next(data_source_iter)\n",
+    "            X, y = data_source\n",
+    "            X = X.float()\n",
+    "            X = X.cuda()\n",
+    "            y = y.cuda()\n",
+    "\n",
+    "            batch_size = len(y)\n",
+    "\n",
+    "            #domain_label = torch.zeros(batch_size)\n",
+    "            #domain_label = domain_label.long()\n",
+    "            #domain_label = domain_label.cuda()\n",
+    "\n",
+    "            estimate_output, domain_output = model(X)\n",
+    "\n",
+    "            estimate_loss = regressor_loss_fn(estimate_output, y)\n",
+    "            #domain_loss_source = classifier_loss_fn(domain_output, domain_label)\n",
+    "\n",
+    "            # Target Testing\n",
+    "\n",
+    "            data_target = next(data_target_iter)\n",
+    "            X_target, y_target = data_target\n",
+    "            X_target = X_target.float()\n",
+    "            X_target = X_target.cuda()\n",
+    "            y_target = y_target.cuda()\n",
+    "\n",
+    "            batch_size = len(X_target)\n",
+    "\n",
+    "            #domain_label = torch.ones(batch_size)\n",
+    "            #domain_label = domain_label.long()\n",
+    "            #domain_label = domain_label.cuda()\n",
+    "\n",
+    "            estimate_output_target, domain_output = model(X_target)\n",
+    "\n",
+    "            estimate_loss_target = regressor_loss_fn(estimate_output_target, y_target)\n",
+    "            #domain_loss_target = classifier_loss_fn(domain_output, domain_label)\n",
+    "\n",
+    "            # Update values\n",
+    "\n",
+    "           # domain_classifier_error += domain_loss_source.item()\n",
+    "            #domain_classifier_error += domain_loss_target.item()\n",
+    "            #domain_classifier_accuracy +=\n",
+    "            estimator_error += estimate_loss.item()\n",
+    "            estimator_error_target += estimate_loss_target.item()\n",
+    "            score = r2_score(y.cpu(), estimate_output.cpu())\n",
+    "            score_list = np.append(score_list, score)\n",
+    "            score_target = r2_score(y_target.cpu(), estimate_output_target.cpu())\n",
+    "            score_list_target = np.append(score_list_target, score_target)\n",
+    "\n",
+    "            i += 1\n",
+    "\n",
+    "        score = np.mean(score_list)\n",
+    "        score_target = np.mean(score_list_target)\n",
+    "        #classifier_error = domain_classifier_error / (len_dataloader * 2)\n",
+    "        estimator_error /= len_dataloader\n",
+    "        estimator_error_target /= len_dataloader\n",
+    "    classifier_error = 1\n",
+    "    return [classifier_error, estimator_error, estimator_error_target, score, score_target]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "1dfe3810-672c-4a28-b606-b3079a40fca4",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 293833,
+     "status": "ok",
+     "timestamp": 1718869045423,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "1dfe3810-672c-4a28-b606-b3079a40fca4",
+    "outputId": "45493f2a-ea42-401e-f88b-b0ad39b969ed"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1\n",
+      "-------------------------------\n",
+      "12.33421277999878\n",
+      "Train Estimator Error = 0.16444933820188973\n",
+      "Train Estimator R2 Score = 0.6710\n",
+      "Train Domain Classifier Error = 0.197300594592879\n",
+      "Validation Source Estimator Error = 0.03957607594739859\n",
+      "Validation Source R2 Score = 0.9181\n",
+      "Validation Target Estimator Error = 0.17865040874595095\n",
+      "Validation Target R2 Score = 0.6406\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 2\n",
+      "-------------------------------\n",
+      "10.286649942398071\n",
+      "Train Estimator Error = 0.033987110668803534\n",
+      "Train Estimator R2 Score = 0.9313\n",
+      "Train Domain Classifier Error = 0.10603604664246277\n",
+      "Validation Source Estimator Error = 0.026627989835847334\n",
+      "Validation Source R2 Score = 0.9447\n",
+      "Validation Target Estimator Error = 0.12391905738100124\n",
+      "Validation Target R2 Score = 0.7497\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 3\n",
+      "-------------------------------\n",
+      "10.679370164871216\n",
+      "Train Estimator Error = 0.025708429421718748\n",
+      "Train Estimator R2 Score = 0.9480\n",
+      "Train Domain Classifier Error = 0.09875815365143406\n",
+      "Validation Source Estimator Error = 0.025580009335806224\n",
+      "Validation Source R2 Score = 0.9470\n",
+      "Validation Target Estimator Error = 0.11177382997836277\n",
+      "Validation Target R2 Score = 0.7764\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 4\n",
+      "-------------------------------\n",
+      "9.528148651123047\n",
+      "Train Estimator Error = 0.021674147663191916\n",
+      "Train Estimator R2 Score = 0.9560\n",
+      "Train Domain Classifier Error = 0.09356177005732953\n",
+      "Validation Source Estimator Error = 0.023202258696079635\n",
+      "Validation Source R2 Score = 0.9526\n",
+      "Validation Target Estimator Error = 0.09558532137874585\n",
+      "Validation Target R2 Score = 0.8068\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 5\n",
+      "-------------------------------\n",
+      "9.20451831817627\n",
+      "Train Estimator Error = 0.018606798048258863\n",
+      "Train Estimator R2 Score = 0.9622\n",
+      "Train Domain Classifier Error = 0.09366841838989659\n",
+      "Validation Source Estimator Error = 0.016288266745603578\n",
+      "Validation Source R2 Score = 0.9664\n",
+      "Validation Target Estimator Error = 0.06763043769510688\n",
+      "Validation Target R2 Score = 0.8619\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 6\n",
+      "-------------------------------\n",
+      "9.798243761062622\n",
+      "Train Estimator Error = 0.016928718104180444\n",
+      "Train Estimator R2 Score = 0.9657\n",
+      "Train Domain Classifier Error = 0.0902507189198157\n",
+      "Validation Source Estimator Error = 0.014676664193653188\n",
+      "Validation Source R2 Score = 0.9693\n",
+      "Validation Target Estimator Error = 0.06337754338220426\n",
+      "Validation Target R2 Score = 0.8730\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 7\n",
+      "-------------------------------\n",
+      "11.475250482559204\n",
+      "Train Estimator Error = 0.01520067899678604\n",
+      "Train Estimator R2 Score = 0.9690\n",
+      "Train Domain Classifier Error = 0.08746750692971446\n",
+      "Validation Source Estimator Error = 0.015763865929144392\n",
+      "Validation Source R2 Score = 0.9671\n",
+      "Validation Target Estimator Error = 0.07552005605665361\n",
+      "Validation Target R2 Score = 0.8486\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 8\n",
+      "-------------------------------\n",
+      "9.42522406578064\n",
+      "Train Estimator Error = 0.014275324373621787\n",
+      "Train Estimator R2 Score = 0.9710\n",
+      "Train Domain Classifier Error = 0.08944729766323209\n",
+      "Validation Source Estimator Error = 0.013076007443296301\n",
+      "Validation Source R2 Score = 0.9731\n",
+      "Validation Target Estimator Error = 0.0584320479375162\n",
+      "Validation Target R2 Score = 0.8811\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 9\n",
+      "-------------------------------\n",
+      "12.132616519927979\n",
+      "Train Estimator Error = 0.013697150923138045\n",
+      "Train Estimator R2 Score = 0.9721\n",
+      "Train Domain Classifier Error = 0.0871505693820266\n",
+      "Validation Source Estimator Error = 0.015199173455405387\n",
+      "Validation Source R2 Score = 0.9685\n",
+      "Validation Target Estimator Error = 0.06418811832406339\n",
+      "Validation Target R2 Score = 0.8695\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 10\n",
+      "-------------------------------\n",
+      "10.557303428649902\n",
+      "Train Estimator Error = 0.012717660697401796\n",
+      "Train Estimator R2 Score = 0.9741\n",
+      "Train Domain Classifier Error = 0.08522086595806551\n",
+      "Validation Source Estimator Error = 0.011813055145536449\n",
+      "Validation Source R2 Score = 0.9757\n",
+      "Validation Target Estimator Error = 0.04445989502914202\n",
+      "Validation Target R2 Score = 0.9107\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 11\n",
+      "-------------------------------\n",
+      "9.70582914352417\n",
+      "Train Estimator Error = 0.01214050365462082\n",
+      "Train Estimator R2 Score = 0.9753\n",
+      "Train Domain Classifier Error = 0.0820563712908156\n",
+      "Validation Source Estimator Error = 0.011426687608384023\n",
+      "Validation Source R2 Score = 0.9760\n",
+      "Validation Target Estimator Error = 0.04615271602798799\n",
+      "Validation Target R2 Score = 0.9082\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 12\n",
+      "-------------------------------\n",
+      "9.581052541732788\n",
+      "Train Estimator Error = 0.011919633876123692\n",
+      "Train Estimator R2 Score = 0.9758\n",
+      "Train Domain Classifier Error = 0.08348346469750188\n",
+      "Validation Source Estimator Error = 0.010784041379714848\n",
+      "Validation Source R2 Score = 0.9775\n",
+      "Validation Target Estimator Error = 0.04491105257195367\n",
+      "Validation Target R2 Score = 0.9105\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 13\n",
+      "-------------------------------\n",
+      "9.942560195922852\n",
+      "Train Estimator Error = 0.011645885268685967\n",
+      "Train Estimator R2 Score = 0.9764\n",
+      "Train Domain Classifier Error = 0.08307299445940002\n",
+      "Validation Source Estimator Error = 0.010429152624183305\n",
+      "Validation Source R2 Score = 0.9783\n",
+      "Validation Target Estimator Error = 0.04398210141451875\n",
+      "Validation Target R2 Score = 0.9117\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 14\n",
+      "-------------------------------\n",
+      "9.535521030426025\n",
+      "Train Estimator Error = 0.010956779571413531\n",
+      "Train Estimator R2 Score = 0.9777\n",
+      "Train Domain Classifier Error = 0.08009117036220197\n",
+      "Validation Source Estimator Error = 0.01252956654591735\n",
+      "Validation Source R2 Score = 0.9742\n",
+      "Validation Target Estimator Error = 0.04393934647724697\n",
+      "Validation Target R2 Score = 0.9115\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 15\n",
+      "-------------------------------\n",
+      "10.049909353256226\n",
+      "Train Estimator Error = 0.011191575388063146\n",
+      "Train Estimator R2 Score = 0.9773\n",
+      "Train Domain Classifier Error = 0.08100781960232384\n",
+      "Validation Source Estimator Error = 0.010393610967109633\n",
+      "Validation Source R2 Score = 0.9787\n",
+      "Validation Target Estimator Error = 0.034813025829850866\n",
+      "Validation Target R2 Score = 0.9314\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 16\n",
+      "-------------------------------\n",
+      "9.887317895889282\n",
+      "Train Estimator Error = 0.010990695381099511\n",
+      "Train Estimator R2 Score = 0.9777\n",
+      "Train Domain Classifier Error = 0.07481679410402964\n",
+      "Validation Source Estimator Error = 0.010688897747261698\n",
+      "Validation Source R2 Score = 0.9780\n",
+      "Validation Target Estimator Error = 0.03671162581711913\n",
+      "Validation Target R2 Score = 0.9267\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 17\n",
+      "-------------------------------\n",
+      "9.46590256690979\n",
+      "Train Estimator Error = 0.01122740320363329\n",
+      "Train Estimator R2 Score = 0.9771\n",
+      "Train Domain Classifier Error = 0.07215353730602882\n",
+      "Validation Source Estimator Error = 0.01086703451516427\n",
+      "Validation Source R2 Score = 0.9776\n",
+      "Validation Target Estimator Error = 0.03929886768815244\n",
+      "Validation Target R2 Score = 0.9220\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 18\n",
+      "-------------------------------\n",
+      "9.881409645080566\n",
+      "Train Estimator Error = 0.012160148401361578\n",
+      "Train Estimator R2 Score = 0.9753\n",
+      "Train Domain Classifier Error = 0.06331457490854006\n",
+      "Validation Source Estimator Error = 0.011688765506171117\n",
+      "Validation Source R2 Score = 0.9757\n",
+      "Validation Target Estimator Error = 0.04073066228799\n",
+      "Validation Target R2 Score = 0.9182\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 19\n",
+      "-------------------------------\n",
+      "10.647077083587646\n",
+      "Train Estimator Error = 0.012665477483635479\n",
+      "Train Estimator R2 Score = 0.9743\n",
+      "Train Domain Classifier Error = 0.0531838871351353\n",
+      "Validation Source Estimator Error = 0.012146283566928024\n",
+      "Validation Source R2 Score = 0.9747\n",
+      "Validation Target Estimator Error = 0.039233959867221536\n",
+      "Validation Target R2 Score = 0.9208\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 20\n",
+      "-------------------------------\n",
+      "11.093253135681152\n",
+      "Train Estimator Error = 0.01234748291227987\n",
+      "Train Estimator R2 Score = 0.9749\n",
+      "Train Domain Classifier Error = 0.04573969768234265\n",
+      "Validation Source Estimator Error = 0.011225358962680504\n",
+      "Validation Source R2 Score = 0.9770\n",
+      "Validation Target Estimator Error = 0.037646287743737746\n",
+      "Validation Target R2 Score = 0.9244\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 21\n",
+      "-------------------------------\n",
+      "10.098066806793213\n",
+      "Train Estimator Error = 0.011807732323654526\n",
+      "Train Estimator R2 Score = 0.9760\n",
+      "Train Domain Classifier Error = 0.04173214546484801\n",
+      "Validation Source Estimator Error = 0.011837220317713774\n",
+      "Validation Source R2 Score = 0.9757\n",
+      "Validation Target Estimator Error = 0.035724040536079436\n",
+      "Validation Target R2 Score = 0.9286\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 22\n",
+      "-------------------------------\n",
+      "10.087324380874634\n",
+      "Train Estimator Error = 0.01155979186509288\n",
+      "Train Estimator R2 Score = 0.9765\n",
+      "Train Domain Classifier Error = 0.04175722094548958\n",
+      "Validation Source Estimator Error = 0.010796774510934854\n",
+      "Validation Source R2 Score = 0.9776\n",
+      "Validation Target Estimator Error = 0.029455781208386846\n",
+      "Validation Target R2 Score = 0.9411\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 23\n",
+      "-------------------------------\n",
+      "9.403812408447266\n",
+      "Train Estimator Error = 0.01096212370018943\n",
+      "Train Estimator R2 Score = 0.9779\n",
+      "Train Domain Classifier Error = 0.03727273999200879\n",
+      "Validation Source Estimator Error = 0.01076946327771256\n",
+      "Validation Source R2 Score = 0.9777\n",
+      "Validation Target Estimator Error = 0.034017571562509626\n",
+      "Validation Target R2 Score = 0.9327\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 24\n",
+      "-------------------------------\n",
+      "10.204989194869995\n",
+      "Train Estimator Error = 0.010513965448218192\n",
+      "Train Estimator R2 Score = 0.9787\n",
+      "Train Domain Classifier Error = 0.03472416911281005\n",
+      "Validation Source Estimator Error = 0.010430672994939385\n",
+      "Validation Source R2 Score = 0.9785\n",
+      "Validation Target Estimator Error = 0.033311633096568906\n",
+      "Validation Target R2 Score = 0.9334\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 25\n",
+      "-------------------------------\n",
+      "10.29259705543518\n",
+      "Train Estimator Error = 0.010646682369252036\n",
+      "Train Estimator R2 Score = 0.9785\n",
+      "Train Domain Classifier Error = 0.035981600340523875\n",
+      "Validation Source Estimator Error = 0.010258104230995012\n",
+      "Validation Source R2 Score = 0.9788\n",
+      "Validation Target Estimator Error = 0.03641296210728443\n",
+      "Validation Target R2 Score = 0.9272\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 26\n",
+      "-------------------------------\n",
+      "10.207979679107666\n",
+      "Train Estimator Error = 0.010566631928375723\n",
+      "Train Estimator R2 Score = 0.9785\n",
+      "Train Domain Classifier Error = 0.035830488049644824\n",
+      "Validation Source Estimator Error = 0.010909623131274608\n",
+      "Validation Source R2 Score = 0.9775\n",
+      "Validation Target Estimator Error = 0.03616505972210579\n",
+      "Validation Target R2 Score = 0.9278\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 27\n",
+      "-------------------------------\n",
+      "10.255443572998047\n",
+      "Train Estimator Error = 0.010196887276780671\n",
+      "Train Estimator R2 Score = 0.9793\n",
+      "Train Domain Classifier Error = 0.03093918035882891\n",
+      "Validation Source Estimator Error = 0.011571518453965141\n",
+      "Validation Source R2 Score = 0.9764\n",
+      "Validation Target Estimator Error = 0.03323280297599401\n",
+      "Validation Target R2 Score = 0.9339\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 28\n",
+      "-------------------------------\n",
+      "10.197303295135498\n",
+      "Train Estimator Error = 0.010003823992775811\n",
+      "Train Estimator R2 Score = 0.9797\n",
+      "Train Domain Classifier Error = 0.02865755154838074\n",
+      "Validation Source Estimator Error = 0.00992215172814763\n",
+      "Validation Source R2 Score = 0.9785\n",
+      "Validation Target Estimator Error = 0.03619385037310184\n",
+      "Validation Target R2 Score = 0.9273\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 29\n",
+      "-------------------------------\n",
+      "11.239193439483643\n",
+      "Train Estimator Error = 0.010029396919705573\n",
+      "Train Estimator R2 Score = 0.9797\n",
+      "Train Domain Classifier Error = 0.028030373441256324\n",
+      "Validation Source Estimator Error = 0.011323591759487701\n",
+      "Validation Source R2 Score = 0.9744\n",
+      "Validation Target Estimator Error = 0.038434194347518644\n",
+      "Validation Target R2 Score = 0.9225\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 30\n",
+      "-------------------------------\n",
+      "9.549391746520996\n",
+      "Train Estimator Error = 0.01042491172493982\n",
+      "Train Estimator R2 Score = 0.9789\n",
+      "Train Domain Classifier Error = 0.027439469181280412\n",
+      "Validation Source Estimator Error = 0.01315591714172891\n",
+      "Validation Source R2 Score = 0.9733\n",
+      "Validation Target Estimator Error = 0.03496130949752346\n",
+      "Validation Target R2 Score = 0.9303\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Initialize dictionary for training stats\n",
+    "import time\n",
+    "model = NeuralNetwork().cuda()\n",
+    "# Hyper parameter presets\n",
+    "learning_rate = 6e-5\n",
+    "epochs = 30\n",
+    "# Define loss functions and optimizer\n",
+    "regressor_loss_fn = nn.MSELoss().cuda()\n",
+    "optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)\n",
+    "da_loss = MMD_loss()\n",
+    "\n",
+    "stats = {'train_domain_classifier_error':[],\n",
+    "             'train_estimator_error':[],\n",
+    "             'train_score':[],\n",
+    "             'val_domain_classifier_error':[],\n",
+    "             'val_estimator_error':[],\n",
+    "             'val_estimator_error_target':[],\n",
+    "             'val_score':[],\n",
+    "             'val_score_target':[]}\n",
+    "\n",
+    "# Train\n",
+    "for i in range(epochs):\n",
+    "        start_time = time.time()\n",
+    "        print(f\"Epoch {i+1}\\n-------------------------------\")\n",
+    "        vals = train_loop(source_train_dataloader, target_train_dataloader, model,\n",
+    "                   regressor_loss_fn, da_loss, optimizer, epochs, i)\n",
+    "\n",
+    "        vals_validate = test_loop(source_val_dataloader, target_val_dataloader,\n",
+    "                         model, regressor_loss_fn, da_loss, epochs, i)\n",
+    "        print(time.time() - start_time)\n",
+    "\n",
+    "        stats['train_domain_classifier_error'].append(vals[0])\n",
+    "        stats['train_estimator_error'].append(vals[1])\n",
+    "        stats['train_score'].append(vals[2])\n",
+    "        stats['val_domain_classifier_error'].append(vals_validate[0])\n",
+    "        stats['val_estimator_error'].append(vals_validate[1])\n",
+    "        stats['val_estimator_error_target'].append(vals_validate[2])\n",
+    "        stats['val_score'].append(vals_validate[3])\n",
+    "        stats['val_score_target'].append(vals_validate[4])\n",
+    "\n",
+    "        to_print = (\n",
+    "            f'Train Estimator Error = {vals[1]}\\n'\n",
+    "            f'Train Estimator R2 Score = {vals[2]:.4f}\\n'\n",
+    "            f'Train Domain Classifier Error = {vals[0]}\\n'\n",
+    "            f'Validation Source Estimator Error = {vals_validate[1]}\\n'\n",
+    "            f'Validation Source R2 Score = {vals_validate[3]:.4f}\\n'\n",
+    "            f'Validation Target Estimator Error = {vals_validate[2]}\\n'\n",
+    "            f'Validation Target R2 Score = {vals_validate[4]:.4f}\\n'\n",
+    "            f'Validation Domain Classifier Error = {vals_validate[0]}\\n'\n",
+    "        )\n",
+    "\n",
+    "        print(to_print)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "YfplCDIb-UU_",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 490
+    },
+    "executionInfo": {
+     "elapsed": 649,
+     "status": "ok",
+     "timestamp": 1718869045736,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "YfplCDIb-UU_",
+    "outputId": "dbb362ec-4af5-4cb9-c4f9-a0a2766c26c5"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7f2e905a7160>]"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Classifier\n",
+    "eps = np.arange(epochs)\n",
+    "plt.title(\"Classifier Error\")\n",
+    "plt.plot(eps, stats['train_domain_classifier_error'])\n",
+    "plt.plot(eps, stats['val_domain_classifier_error'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "eYG_P_iQ_5Bv",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 490
+    },
+    "executionInfo": {
+     "elapsed": 169,
+     "status": "ok",
+     "timestamp": 1718869045739,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "eYG_P_iQ_5Bv",
+    "outputId": "be450f92-eda7-4e4f-81fe-008c55b2b112"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7f2e905e4a60>]"
+      ]
+     },
+     "execution_count": 17,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Estimator\n",
+    "plt.title(\"Estimator Error\")\n",
+    "plt.plot(eps, stats['train_estimator_error'])\n",
+    "plt.plot(eps, stats['val_estimator_error'])\n",
+    "plt.plot(eps, stats['val_estimator_error_target'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "id": "xS9rtS-T_neg",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 490
+    },
+    "executionInfo": {
+     "elapsed": 237,
+     "status": "ok",
+     "timestamp": 1718869045904,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "xS9rtS-T_neg",
+    "outputId": "d32f40ef-6042-4154-e9ee-1f4e2f90064d"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[<matplotlib.lines.Line2D at 0x7f2e90528e20>]"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# R2 Scores\n",
+    "plt.title(\"R2 Scores\")\n",
+    "plt.plot(eps, stats['train_score'])\n",
+    "plt.plot(eps, stats['val_score'])\n",
+    "plt.plot(eps, stats['val_score_target'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "ed0a8206-7520-4a60-8e17-965a91133b92",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 428
+    },
+    "executionInfo": {
+     "elapsed": 969,
+     "status": "ok",
+     "timestamp": 1718869046858,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "ed0a8206-7520-4a60-8e17-965a91133b92",
+    "outputId": "7df8c563-5826-4e43-d9e6-5e686463551d"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Source R2 Score is 0.9742\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'MMD - Source')"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 400x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Test Source\n",
+    "preds = np.array([])\n",
+    "true = np.array([])\n",
+    "score_list = np.array([])\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    for X, y in source_test_dataloader:\n",
+    "        X = X.float()\n",
+    "        pred, _ = model(X.cuda())\n",
+    "        preds = np.append(preds, pred.cpu())\n",
+    "        true = np.append(true, y.cpu())\n",
+    "        score = r2_score(y.cpu(), pred.cpu())\n",
+    "        score_list = np.append(score_list, score)\n",
+    "\n",
+    "score = np.mean(score_list)\n",
+    "print(f'Source R2 Score is {score:.4f}')\n",
+    "\n",
+    "plt.figure(figsize=(8,8),dpi=50)\n",
+    "plt.scatter(true, preds,  color='black', alpha = 0.05)\n",
+    "line = np.linspace(0, 4, 100)\n",
+    "plt.plot(line, line)\n",
+    "plt.rc('font', size=12)\n",
+    "plt.xlabel('True Theta E')\n",
+    "plt.ylabel('Predicted Theta E');\n",
+    "plt.rc('font', size=20)\n",
+    "plt.title('MMD - Source')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "fc047cd7-bc92-4a30-9beb-7af607da141f",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 444
+    },
+    "executionInfo": {
+     "elapsed": 1283,
+     "status": "ok",
+     "timestamp": 1718869048133,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "fc047cd7-bc92-4a30-9beb-7af607da141f",
+    "outputId": "b6347093-56d9-4a8b-b515-c4c4717cdab4"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Target R2 Score is 0.9299\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'MMD - Target')"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 400x400 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Test target\n",
+    "preds = np.array([])\n",
+    "true = np.array([])\n",
+    "score_list = np.array([])\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    for X, y in target_test_dataloader:\n",
+    "        X = X.float()\n",
+    "        pred, _ = model(X.cuda())\n",
+    "        preds = np.append(preds, pred.cpu())\n",
+    "        true = np.append(true, y.cpu())\n",
+    "        score = r2_score(y.cpu(), pred.cpu())\n",
+    "        score_list = np.append(score_list, score)\n",
+    "\n",
+    "score = np.mean(score_list)\n",
+    "print(f'Target R2 Score is {score:.4f}')\n",
+    "\n",
+    "plt.figure(figsize=(8,8),dpi=50)\n",
+    "plt.scatter(true, preds,  color='black', alpha = 0.05)\n",
+    "line = np.linspace(0, 4, 100)\n",
+    "plt.plot(line, line)\n",
+    "plt.rc('font', size=12)\n",
+    "plt.xlabel('True Theta E')\n",
+    "plt.ylabel('Predicted Theta E');\n",
+    "plt.rc('font', size=20)\n",
+    "plt.title('MMD - Target')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14a94f1e-758e-4a64-b0c7-0f3a5781f7c2",
+   "metadata": {
+    "id": "14a94f1e-758e-4a64-b0c7-0f3a5781f7c2"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": [
+    {
+     "file_id": "1MFScb-3Sbugn4RNiDaeocicJUIHlh_j2",
+     "timestamp": 1717430435817
+    },
+    {
+     "file_id": "1wlKaSdLzleueYrwljtOcqsiOfzEy1dxP",
+     "timestamp": 1717429638462
+    }
+   ]
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (Safe Mode)",
+   "language": "python",
+   "name": "py3-safemode"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/training/notebooks/MMD_paper/multiband/ShrihanPaperMMD_mb.ipynb b/training/notebooks/MMD_paper/multiband/ShrihanPaperMMD_mb.ipynb
new file mode 100644
index 0000000..30bbb4f
--- /dev/null
+++ b/training/notebooks/MMD_paper/multiband/ShrihanPaperMMD_mb.ipynb
@@ -0,0 +1,1005 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "a8aa3fe5-4277-47fc-b26d-baa137256f17",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 10375,
+     "status": "ok",
+     "timestamp": 1718868666013,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "a8aa3fe5-4277-47fc-b26d-baa137256f17",
+    "outputId": "9ad89b68-4fd0-4146-a087-24cd367fb09f"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Using cuda device\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Imports we will use\n",
+    "import torch\n",
+    "from torch import nn\n",
+    "import torch.nn.functional as F\n",
+    "from torch.utils.data import DataLoader, TensorDataset\n",
+    "from torch.autograd import Function\n",
+    "%matplotlib inline\n",
+    "import matplotlib.pyplot as plt\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import random\n",
+    "from pathlib import Path\n",
+    "from sklearn.metrics import r2_score\n",
+    "from astropy.visualization import make_lupton_rgb\n",
+    "\n",
+    "# For matplotlib\n",
+    "import os\n",
+    "os.environ['KMP_DUPLICATE_LIB_OK'] = 'True'\n",
+    "\n",
+    "# Set Seed\n",
+    "torch.manual_seed(22)\n",
+    "\n",
+    "# Find if cuda is available\n",
+    "device = \"cuda\" if torch.cuda.is_available() else \"cpu\"\n",
+    "print(f\"Using {device} device\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "7cc92062-1846-4850-8f8e-206a7c35c171",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 189,
+     "status": "ok",
+     "timestamp": 1718868679894,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "7cc92062-1846-4850-8f8e-206a7c35c171"
+   },
+   "outputs": [],
+   "source": [
+    "# Load data function\n",
+    "def create_dataloader(img_path, metadata_path, batch_size):\n",
+    "    '''\n",
+    "    Creates dataloader for training, reserving the last 10% images for validation/testing\n",
+    "    '''\n",
+    "    data = np.load(img_path).squeeze()\n",
+    "    length = len(data)\n",
+    "    data_train = torch.tensor(data[:int(.7*length)]) # 70% train\n",
+    "    data_test = torch.tensor(data[int(.7*length):int(.9*length)]) # 20% test\n",
+    "    data_val = torch.tensor(data[int(.9*length):]) # 10% validation\n",
+    "\n",
+    "    metadata = pd.read_csv(metadata_path)\n",
+    "    labels = metadata['PLANE_1-OBJECT_1-MASS_PROFILE_1-theta_E-g'].tolist()\n",
+    "    labels_train = torch.tensor(labels[:int(.7*length)])\n",
+    "    labels_test = torch.tensor(labels[int(.7*length):int(.9*length)])\n",
+    "    labels_val = torch.tensor(labels[int(.9*length):])\n",
+    "\n",
+    "    data_train.cuda()\n",
+    "    data_test.cuda()\n",
+    "    data_val.cuda()\n",
+    "    labels_train.cuda()\n",
+    "    labels_test.cuda()\n",
+    "    labels_val.cuda()\n",
+    "\n",
+    "    train_dataset = TensorDataset(data_train, labels_train)\n",
+    "    test_dataset = TensorDataset(data_test, labels_test)\n",
+    "    val_dataset = TensorDataset(data_val, labels_val)\n",
+    "\n",
+    "    train_dataloader = DataLoader(dataset=train_dataset, batch_size=batch_size, shuffle=True)\n",
+    "    test_dataloader = DataLoader(dataset=test_dataset, batch_size=batch_size, shuffle=True)\n",
+    "    val_dataloader = DataLoader(dataset=val_dataset, batch_size=batch_size, shuffle=True)\n",
+    "\n",
+    "    return train_dataloader, test_dataloader, val_dataloader, data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3efc6755-daeb-48ca-bbc7-c5a3b539c5b7",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 19938,
+     "status": "ok",
+     "timestamp": 1718868749575,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "3efc6755-daeb-48ca-bbc7-c5a3b539c5b7"
+   },
+   "outputs": [],
+   "source": [
+    "# Load in data\n",
+    "head = Path.cwd().parents[3]\n",
+    "source_img_path = head / 'data/mb_source/mb_source.npy'\n",
+    "target_img_path = head / 'data/mb_target/mb_target.npy'\n",
+    "source_meta = head / 'data/mb_source/mb_source_metadata.csv'\n",
+    "target_meta = head / 'data/mb_target/mb_target_metadata.csv'\n",
+    "batch_size = 32\n",
+    "source_train_dataloader, source_test_dataloader, source_val_dataloader, source_data = create_dataloader(source_img_path, source_meta, batch_size)\n",
+    "target_train_dataloader, target_test_dataloader, target_val_dataloader, target_data = create_dataloader(target_img_path, target_meta, batch_size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "cc2641b2-6b2f-4cd7-9b29-a8ed7a595103",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<torch.utils.data.dataloader.DataLoader at 0x7f0378734100>"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "source_train_dataloader"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "a3045daa-2e71-4335-8259-662a5c7e41a8",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 3,
+     "status": "ok",
+     "timestamp": 1718868749576,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "a3045daa-2e71-4335-8259-662a5c7e41a8"
+   },
+   "outputs": [],
+   "source": [
+    "# Define data visualization function\n",
+    "def visualize_data(data):\n",
+    "    '''\n",
+    "    visualizes 16 random images from dataset\n",
+    "    '''\n",
+    "    \n",
+    "    data_length = len(data)\n",
+    "    num_indices = 16\n",
+    "    \n",
+    "    # Generate 15 unique random indices using numpy\n",
+    "    random_indices = np.random.choice(data_length, size=num_indices, replace=False)\n",
+    "\n",
+    "    #plot the examples for source\n",
+    "    fig1=plt.figure(figsize=(8,8))\n",
+    "\n",
+    "    for i in range(16):\n",
+    "        plt.subplot(4, 4, i + 1)\n",
+    "        plt.axis(\"off\")\n",
+    "\n",
+    "        img = data[random_indices[i]]\n",
+    "        example_image = make_lupton_rgb(img[0], img[1], img[2]) #change band by switching 0:1 to 1:2 or 2:3\n",
+    "\n",
+    "        plt.imshow(example_image, aspect='auto', cmap='viridis')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "b72c4588-acb2-478c-96e9-cb09a0380ecd",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 673
+    },
+    "executionInfo": {
+     "elapsed": 559,
+     "status": "ok",
+     "timestamp": 1718868750133,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "b72c4588-acb2-478c-96e9-cb09a0380ecd",
+    "outputId": "651cb9ac-efea-4f14-b3a0-f03648a4081a"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 16 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Visualize source data\n",
+    "visualize_data(source_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "6d6e4147-ce23-4fca-b1aa-42122b0e2501",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 673
+    },
+    "executionInfo": {
+     "elapsed": 665,
+     "status": "ok",
+     "timestamp": 1718868750796,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "6d6e4147-ce23-4fca-b1aa-42122b0e2501",
+    "outputId": "eccb0d95-4566-445f-a058-b1d5b87765b0"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 800x800 with 16 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Visualize target data\n",
+    "visualize_data(target_data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7b706147-6d5c-4319-a7b0-87decc1e6a7f",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750796,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "7b706147-6d5c-4319-a7b0-87decc1e6a7f"
+   },
+   "outputs": [],
+   "source": [
+    "# Define and initialize model\n",
+    "class NeuralNetwork(nn.Module):\n",
+    "    def __init__(self):\n",
+    "        super(NeuralNetwork, self).__init__()\n",
+    "        self.feature = nn.Sequential()\n",
+    "        self.feature.add_module('f_conv1', nn.Conv2d(in_channels=1, out_channels=8, kernel_size=3, padding='same'))\n",
+    "        self.feature.add_module('f_relu1', nn.ReLU(True))\n",
+    "        self.feature.add_module('f_bn1', nn.BatchNorm2d(8))\n",
+    "        self.feature.add_module('f_pool1', nn.MaxPool2d(kernel_size=2, stride=2))\n",
+    "        self.feature.add_module('f_conv2', nn.Conv2d(in_channels=8, out_channels=16, kernel_size=3, padding='same'))\n",
+    "        self.feature.add_module('f_relu2', nn.ReLU(True))\n",
+    "        self.feature.add_module('f_bn2', nn.BatchNorm2d(16))\n",
+    "        self.feature.add_module('f_pool2', nn.MaxPool2d(kernel_size=2, stride=2))\n",
+    "        self.feature.add_module('f_conv3', nn.Conv2d(in_channels=16, out_channels=32, kernel_size=3, padding='same'))\n",
+    "        self.feature.add_module('f_relu3', nn.ReLU(True))\n",
+    "        self.feature.add_module('f_bn3', nn.BatchNorm2d(32))\n",
+    "        self.feature.add_module('f_pool3', nn.MaxPool2d(kernel_size=2, stride=2))\n",
+    "\n",
+    "        self.regressor = nn.Sequential()\n",
+    "        self.regressor.add_module('r_fc1', nn.Linear(in_features=32*5*5, out_features=128))\n",
+    "        self.regressor.add_module('r_relu1', nn.ReLU(True))\n",
+    "        #self.regressor.add_module('r_fc2', nn.Linear(in_features=128, out_features=64))\n",
+    "        #self.regressor.add_module('r_relu2', nn.ReLU(True))\n",
+    "        self.regressor.add_module('r_fc3', nn.Linear(in_features=128, out_features=1))\n",
+    "\n",
+    "    def forward(self, x):\n",
+    "        x = x.view(-1, 1, 40, 40)\n",
+    "\n",
+    "        features = self.feature(x)\n",
+    "        features = features.view(-1, 32*5*5)\n",
+    "        estimate = self.regressor(features)\n",
+    "        estimate = F.relu(estimate)\n",
+    "        estimate = estimate.view(-1)\n",
+    "\n",
+    "        return estimate, features\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "cfd79aed-d467-4d59-a44d-df05177dfd58",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750796,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "cfd79aed-d467-4d59-a44d-df05177dfd58"
+   },
+   "outputs": [],
+   "source": [
+    "# code from https://github.com/ZongxianLee/MMD_Loss.Pytorch\n",
+    "\n",
+    "class MMD_loss(nn.Module):\n",
+    "    def __init__(self, kernel_mul = 2.0, kernel_num = 5):\n",
+    "        super(MMD_loss, self).__init__()\n",
+    "        self.kernel_num = kernel_num\n",
+    "        self.kernel_mul = kernel_mul\n",
+    "        self.fix_sigma = None\n",
+    "        return\n",
+    "    def guassian_kernel(self, source, target, kernel_mul=2.0, kernel_num=5, fix_sigma=None):\n",
+    "        n_samples = int(source.size()[0])+int(target.size()[0])\n",
+    "        total = torch.cat([source, target], dim=0)\n",
+    "\n",
+    "        total0 = total.unsqueeze(0).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))\n",
+    "        total1 = total.unsqueeze(1).expand(int(total.size(0)), int(total.size(0)), int(total.size(1)))\n",
+    "        L2_distance = ((total0-total1)**2).sum(2)\n",
+    "        if fix_sigma:\n",
+    "            bandwidth = fix_sigma\n",
+    "        else:\n",
+    "            bandwidth = torch.sum(L2_distance.data) / (n_samples**2-n_samples)\n",
+    "        bandwidth /= kernel_mul ** (kernel_num // 2)\n",
+    "        bandwidth_list = [bandwidth * (kernel_mul**i) for i in range(kernel_num)]\n",
+    "        kernel_val = [torch.exp(-L2_distance / bandwidth_temp) for bandwidth_temp in bandwidth_list]\n",
+    "        return sum(kernel_val)\n",
+    "\n",
+    "    def forward(self, source, target):\n",
+    "        batch_size = int(source.size()[0])\n",
+    "        kernels = self.guassian_kernel(source, target, kernel_mul=self.kernel_mul, kernel_num=self.kernel_num, fix_sigma=self.fix_sigma)\n",
+    "        XX = kernels[:batch_size, :batch_size]\n",
+    "        YY = kernels[batch_size:, batch_size:]\n",
+    "        XY = kernels[:batch_size, batch_size:]\n",
+    "        YX = kernels[batch_size:, :batch_size]\n",
+    "        loss = torch.mean(XX + YY - XY -YX)\n",
+    "        return loss"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "ccac040a-7d18-45a4-b390-40e3dfa51756",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750797,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "ccac040a-7d18-45a4-b390-40e3dfa51756"
+   },
+   "outputs": [],
+   "source": [
+    "# Define training loop\n",
+    "def train_loop(source_dataloader, target_dataloader, model, regressor_loss_fn, da_loss, optimizer, n_epoch, epoch):\n",
+    "\n",
+    "    domain_error = 0\n",
+    "    domain_classifier_accuracy = 0\n",
+    "    estimator_error = 0\n",
+    "    score_list = np.array([])\n",
+    "\n",
+    "    len_dataloader = min(len(source_dataloader), len(target_dataloader))\n",
+    "    data_source_iter = iter(source_dataloader)\n",
+    "    data_target_iter = iter(target_dataloader)\n",
+    "\n",
+    "    i = 0\n",
+    "    while i < len_dataloader:\n",
+    "\n",
+    "        p = float(i + epoch * len_dataloader) / n_epoch / len_dataloader\n",
+    "        alpha = 2. / (1. + np.exp(-10 * p)) - 1\n",
+    "\n",
+    "        # Source Training\n",
+    "\n",
+    "        data_source = next(data_source_iter)\n",
+    "        X, y = data_source\n",
+    "        X = X.float()\n",
+    "        X = X.cuda()\n",
+    "        y = y.cuda()\n",
+    "\n",
+    "        model.zero_grad()\n",
+    "        batch_size = len(y)\n",
+    "\n",
+    "        domain_label = torch.zeros(batch_size)\n",
+    "        domain_label = domain_label.long()\n",
+    "        domain_label = domain_label.cuda()\n",
+    "\n",
+    "        estimate_output, domain_output_source = model(X)\n",
+    "\n",
+    "        estimate_loss = regressor_loss_fn(estimate_output, y)\n",
+    "\n",
+    "        # Target Training\n",
+    "\n",
+    "        data_target = next(data_target_iter)\n",
+    "        X_target, _ = data_target\n",
+    "        X_target = X_target.float()\n",
+    "        X_target = X_target.cuda()\n",
+    "\n",
+    "        batch_size = len(X_target)\n",
+    "\n",
+    "        _, domain_output_target = model(X_target)\n",
+    "        domain_loss = da_loss(domain_output_source, domain_output_target)\n",
+    "\n",
+    "        loss = estimate_loss + domain_loss*1.4\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "\n",
+    "        # Update values\n",
+    "\n",
+    "        domain_error += domain_loss.item()\n",
+    "        #domain_classifier_accuracy +=\n",
+    "        estimator_error += estimate_loss.item()\n",
+    "        score = r2_score(y.cpu().detach().numpy(), estimate_output.cpu().detach().numpy())\n",
+    "        score_list = np.append(score_list, score)\n",
+    "\n",
+    "        i += 1\n",
+    "\n",
+    "    score = np.mean(score_list)\n",
+    "    domain_error = domain_error / (len_dataloader)\n",
+    "    estimator_error /= len_dataloader\n",
+    "\n",
+    "    return [domain_error, estimator_error, score]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "98583af6-1fbb-4091-bc22-b1ce362e8f21",
+   "metadata": {
+    "executionInfo": {
+     "elapsed": 6,
+     "status": "ok",
+     "timestamp": 1718868750797,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "98583af6-1fbb-4091-bc22-b1ce362e8f21"
+   },
+   "outputs": [],
+   "source": [
+    "# Define testing loop\n",
+    "\n",
+    "def test_loop(source_dataloader, target_dataloader, model, regressor_loss_fn, da_loss, n_epoch, epoch):\n",
+    "\n",
+    "    with torch.no_grad():\n",
+    "\n",
+    "        len_dataloader = min(len(source_dataloader), len(target_dataloader))\n",
+    "        data_source_iter = iter(source_dataloader)\n",
+    "        data_target_iter = iter(target_dataloader)\n",
+    "\n",
+    "        domain_classifier_error = 0\n",
+    "        domain_classifier_accuracy = 0\n",
+    "        estimator_error = 0\n",
+    "        estimator_error_target = 0\n",
+    "        score_list = np.array([])\n",
+    "        score_list_target = np.array([])\n",
+    "\n",
+    "        i = 0\n",
+    "        while i < len_dataloader:\n",
+    "\n",
+    "            p = float(i + epoch * len_dataloader) / n_epoch / len_dataloader\n",
+    "            alpha = 2. / (1. + np.exp(-10 * p)) - 1\n",
+    "\n",
+    "            # Source Testing\n",
+    "\n",
+    "            data_source = next(data_source_iter)\n",
+    "            X, y = data_source\n",
+    "            X = X.float()\n",
+    "            X = X.cuda()\n",
+    "            y = y.cuda()\n",
+    "\n",
+    "            batch_size = len(y)\n",
+    "\n",
+    "            #domain_label = torch.zeros(batch_size)\n",
+    "            #domain_label = domain_label.long()\n",
+    "            #domain_label = domain_label.cuda()\n",
+    "\n",
+    "            estimate_output, domain_output = model(X)\n",
+    "\n",
+    "            estimate_loss = regressor_loss_fn(estimate_output, y)\n",
+    "            #domain_loss_source = classifier_loss_fn(domain_output, domain_label)\n",
+    "\n",
+    "            # Target Testing\n",
+    "\n",
+    "            data_target = next(data_target_iter)\n",
+    "            X_target, y_target = data_target\n",
+    "            X_target = X_target.float()\n",
+    "            X_target = X_target.cuda()\n",
+    "            y_target = y_target.cuda()\n",
+    "\n",
+    "            batch_size = len(X_target)\n",
+    "\n",
+    "            #domain_label = torch.ones(batch_size)\n",
+    "            #domain_label = domain_label.long()\n",
+    "            #domain_label = domain_label.cuda()\n",
+    "\n",
+    "            estimate_output_target, domain_output = model(X_target)\n",
+    "\n",
+    "            estimate_loss_target = regressor_loss_fn(estimate_output_target, y_target)\n",
+    "            #domain_loss_target = classifier_loss_fn(domain_output, domain_label)\n",
+    "\n",
+    "            # Update values\n",
+    "\n",
+    "           # domain_classifier_error += domain_loss_source.item()\n",
+    "            #domain_classifier_error += domain_loss_target.item()\n",
+    "            #domain_classifier_accuracy +=\n",
+    "            estimator_error += estimate_loss.item()\n",
+    "            estimator_error_target += estimate_loss_target.item()\n",
+    "            score = r2_score(y.cpu(), estimate_output.cpu())\n",
+    "            score_list = np.append(score_list, score)\n",
+    "            score_target = r2_score(y_target.cpu(), estimate_output_target.cpu())\n",
+    "            score_list_target = np.append(score_list_target, score_target)\n",
+    "\n",
+    "            i += 1\n",
+    "\n",
+    "        score = np.mean(score_list)\n",
+    "        score_target = np.mean(score_list_target)\n",
+    "        #classifier_error = domain_classifier_error / (len_dataloader * 2)\n",
+    "        estimator_error /= len_dataloader\n",
+    "        estimator_error_target /= len_dataloader\n",
+    "    classifier_error = 1\n",
+    "    return [classifier_error, estimator_error, estimator_error_target, score, score_target]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1dfe3810-672c-4a28-b606-b3079a40fca4",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "executionInfo": {
+     "elapsed": 293833,
+     "status": "ok",
+     "timestamp": 1718869045423,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "1dfe3810-672c-4a28-b606-b3079a40fca4",
+    "outputId": "45493f2a-ea42-401e-f88b-b0ad39b969ed"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1\n",
+      "-------------------------------\n",
+      "12.33421277999878\n",
+      "Train Estimator Error = 0.16444933820188973\n",
+      "Train Estimator R2 Score = 0.6710\n",
+      "Train Domain Classifier Error = 0.197300594592879\n",
+      "Validation Source Estimator Error = 0.03957607594739859\n",
+      "Validation Source R2 Score = 0.9181\n",
+      "Validation Target Estimator Error = 0.17865040874595095\n",
+      "Validation Target R2 Score = 0.6406\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 2\n",
+      "-------------------------------\n",
+      "10.286649942398071\n",
+      "Train Estimator Error = 0.033987110668803534\n",
+      "Train Estimator R2 Score = 0.9313\n",
+      "Train Domain Classifier Error = 0.10603604664246277\n",
+      "Validation Source Estimator Error = 0.026627989835847334\n",
+      "Validation Source R2 Score = 0.9447\n",
+      "Validation Target Estimator Error = 0.12391905738100124\n",
+      "Validation Target R2 Score = 0.7497\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 3\n",
+      "-------------------------------\n",
+      "10.679370164871216\n",
+      "Train Estimator Error = 0.025708429421718748\n",
+      "Train Estimator R2 Score = 0.9480\n",
+      "Train Domain Classifier Error = 0.09875815365143406\n",
+      "Validation Source Estimator Error = 0.025580009335806224\n",
+      "Validation Source R2 Score = 0.9470\n",
+      "Validation Target Estimator Error = 0.11177382997836277\n",
+      "Validation Target R2 Score = 0.7764\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 4\n",
+      "-------------------------------\n",
+      "9.528148651123047\n",
+      "Train Estimator Error = 0.021674147663191916\n",
+      "Train Estimator R2 Score = 0.9560\n",
+      "Train Domain Classifier Error = 0.09356177005732953\n",
+      "Validation Source Estimator Error = 0.023202258696079635\n",
+      "Validation Source R2 Score = 0.9526\n",
+      "Validation Target Estimator Error = 0.09558532137874585\n",
+      "Validation Target R2 Score = 0.8068\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 5\n",
+      "-------------------------------\n",
+      "9.20451831817627\n",
+      "Train Estimator Error = 0.018606798048258863\n",
+      "Train Estimator R2 Score = 0.9622\n",
+      "Train Domain Classifier Error = 0.09366841838989659\n",
+      "Validation Source Estimator Error = 0.016288266745603578\n",
+      "Validation Source R2 Score = 0.9664\n",
+      "Validation Target Estimator Error = 0.06763043769510688\n",
+      "Validation Target R2 Score = 0.8619\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 6\n",
+      "-------------------------------\n",
+      "9.798243761062622\n",
+      "Train Estimator Error = 0.016928718104180444\n",
+      "Train Estimator R2 Score = 0.9657\n",
+      "Train Domain Classifier Error = 0.0902507189198157\n",
+      "Validation Source Estimator Error = 0.014676664193653188\n",
+      "Validation Source R2 Score = 0.9693\n",
+      "Validation Target Estimator Error = 0.06337754338220426\n",
+      "Validation Target R2 Score = 0.8730\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 7\n",
+      "-------------------------------\n",
+      "11.475250482559204\n",
+      "Train Estimator Error = 0.01520067899678604\n",
+      "Train Estimator R2 Score = 0.9690\n",
+      "Train Domain Classifier Error = 0.08746750692971446\n",
+      "Validation Source Estimator Error = 0.015763865929144392\n",
+      "Validation Source R2 Score = 0.9671\n",
+      "Validation Target Estimator Error = 0.07552005605665361\n",
+      "Validation Target R2 Score = 0.8486\n",
+      "Validation Domain Classifier Error = 1\n",
+      "\n",
+      "Epoch 8\n",
+      "-------------------------------\n"
+     ]
+    }
+   ],
+   "source": [
+    "# Initialize dictionary for training stats\n",
+    "import time\n",
+    "model = NeuralNetwork().cuda()\n",
+    "# Hyper parameter presets\n",
+    "learning_rate = 6e-5\n",
+    "epochs = 30\n",
+    "# Define loss functions and optimizer\n",
+    "regressor_loss_fn = nn.MSELoss().cuda()\n",
+    "optimizer = torch.optim.Adam(model.parameters(), lr=learning_rate)\n",
+    "da_loss = MMD_loss()\n",
+    "\n",
+    "stats = {'train_domain_classifier_error':[],\n",
+    "             'train_estimator_error':[],\n",
+    "             'train_score':[],\n",
+    "             'val_domain_classifier_error':[],\n",
+    "             'val_estimator_error':[],\n",
+    "             'val_estimator_error_target':[],\n",
+    "             'val_score':[],\n",
+    "             'val_score_target':[]}\n",
+    "\n",
+    "# Train\n",
+    "for i in range(epochs):\n",
+    "        start_time = time.time()\n",
+    "        print(f\"Epoch {i+1}\\n-------------------------------\")\n",
+    "        vals = train_loop(source_train_dataloader, target_train_dataloader, model,\n",
+    "                   regressor_loss_fn, da_loss, optimizer, epochs, i)\n",
+    "\n",
+    "        vals_validate = test_loop(source_val_dataloader, target_val_dataloader,\n",
+    "                         model, regressor_loss_fn, da_loss, epochs, i)\n",
+    "        print(time.time() - start_time)\n",
+    "\n",
+    "        stats['train_domain_classifier_error'].append(vals[0])\n",
+    "        stats['train_estimator_error'].append(vals[1])\n",
+    "        stats['train_score'].append(vals[2])\n",
+    "        stats['val_domain_classifier_error'].append(vals_validate[0])\n",
+    "        stats['val_estimator_error'].append(vals_validate[1])\n",
+    "        stats['val_estimator_error_target'].append(vals_validate[2])\n",
+    "        stats['val_score'].append(vals_validate[3])\n",
+    "        stats['val_score_target'].append(vals_validate[4])\n",
+    "\n",
+    "        to_print = (\n",
+    "            f'Train Estimator Error = {vals[1]}\\n'\n",
+    "            f'Train Estimator R2 Score = {vals[2]:.4f}\\n'\n",
+    "            f'Train Domain Classifier Error = {vals[0]}\\n'\n",
+    "            f'Validation Source Estimator Error = {vals_validate[1]}\\n'\n",
+    "            f'Validation Source R2 Score = {vals_validate[3]:.4f}\\n'\n",
+    "            f'Validation Target Estimator Error = {vals_validate[2]}\\n'\n",
+    "            f'Validation Target R2 Score = {vals_validate[4]:.4f}\\n'\n",
+    "            f'Validation Domain Classifier Error = {vals_validate[0]}\\n'\n",
+    "        )\n",
+    "\n",
+    "        print(to_print)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "YfplCDIb-UU_",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 490
+    },
+    "executionInfo": {
+     "elapsed": 649,
+     "status": "ok",
+     "timestamp": 1718869045736,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "YfplCDIb-UU_",
+    "outputId": "dbb362ec-4af5-4cb9-c4f9-a0a2766c26c5"
+   },
+   "outputs": [],
+   "source": [
+    "# Classifier\n",
+    "eps = np.arange(epochs)\n",
+    "plt.title(\"Classifier Error\")\n",
+    "plt.plot(eps, stats['train_domain_classifier_error'])\n",
+    "plt.plot(eps, stats['val_domain_classifier_error'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "eYG_P_iQ_5Bv",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 490
+    },
+    "executionInfo": {
+     "elapsed": 169,
+     "status": "ok",
+     "timestamp": 1718869045739,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "eYG_P_iQ_5Bv",
+    "outputId": "be450f92-eda7-4e4f-81fe-008c55b2b112"
+   },
+   "outputs": [],
+   "source": [
+    "# Estimator\n",
+    "plt.title(\"Estimator Error\")\n",
+    "plt.plot(eps, stats['train_estimator_error'])\n",
+    "plt.plot(eps, stats['val_estimator_error'])\n",
+    "plt.plot(eps, stats['val_estimator_error_target'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "xS9rtS-T_neg",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 490
+    },
+    "executionInfo": {
+     "elapsed": 237,
+     "status": "ok",
+     "timestamp": 1718869045904,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "xS9rtS-T_neg",
+    "outputId": "d32f40ef-6042-4154-e9ee-1f4e2f90064d"
+   },
+   "outputs": [],
+   "source": [
+    "# R2 Scores\n",
+    "plt.title(\"R2 Scores\")\n",
+    "plt.plot(eps, stats['train_score'])\n",
+    "plt.plot(eps, stats['val_score'])\n",
+    "plt.plot(eps, stats['val_score_target'])"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "ed0a8206-7520-4a60-8e17-965a91133b92",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 428
+    },
+    "executionInfo": {
+     "elapsed": 969,
+     "status": "ok",
+     "timestamp": 1718869046858,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "ed0a8206-7520-4a60-8e17-965a91133b92",
+    "outputId": "7df8c563-5826-4e43-d9e6-5e686463551d"
+   },
+   "outputs": [],
+   "source": [
+    "# Test Source\n",
+    "preds = np.array([])\n",
+    "true = np.array([])\n",
+    "score_list = np.array([])\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    for X, y in source_test_dataloader:\n",
+    "        X = X.float()\n",
+    "        pred, _ = model(X.cuda())\n",
+    "        preds = np.append(preds, pred.cpu())\n",
+    "        true = np.append(true, y.cpu())\n",
+    "        score = r2_score(y.cpu(), pred.cpu())\n",
+    "        score_list = np.append(score_list, score)\n",
+    "\n",
+    "score = np.mean(score_list)\n",
+    "print(f'Source R2 Score is {score:.4f}')\n",
+    "\n",
+    "plt.figure(figsize=(8,8),dpi=50)\n",
+    "plt.scatter(true, preds,  color='black')\n",
+    "line = np.linspace(0, 4, 100)\n",
+    "plt.plot(line, line)\n",
+    "plt.rc('font', size=12)\n",
+    "plt.xlabel('True Theta E')\n",
+    "plt.ylabel('Predicted Theta E');\n",
+    "plt.rc('font', size=20)\n",
+    "plt.title('MMD - Source')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "fc047cd7-bc92-4a30-9beb-7af607da141f",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 444
+    },
+    "executionInfo": {
+     "elapsed": 1283,
+     "status": "ok",
+     "timestamp": 1718869048133,
+     "user": {
+      "displayName": "Shrihan Agarwal",
+      "userId": "00018416289398983661"
+     },
+     "user_tz": 300
+    },
+    "id": "fc047cd7-bc92-4a30-9beb-7af607da141f",
+    "outputId": "b6347093-56d9-4a8b-b515-c4c4717cdab4"
+   },
+   "outputs": [],
+   "source": [
+    "# Test target\n",
+    "preds = np.array([])\n",
+    "true = np.array([])\n",
+    "score_list = np.array([])\n",
+    "\n",
+    "with torch.no_grad():\n",
+    "    for X, y in target_test_dataloader:\n",
+    "        X = X.float()\n",
+    "        pred, _ = model(X.cuda())\n",
+    "        preds = np.append(preds, pred.cpu())\n",
+    "        true = np.append(true, y.cpu())\n",
+    "        score = r2_score(y.cpu(), pred.cpu())\n",
+    "        score_list = np.append(score_list, score)\n",
+    "\n",
+    "score = np.mean(score_list)\n",
+    "print(f'Target R2 Score is {score:.4f}')\n",
+    "\n",
+    "plt.figure(figsize=(8,8),dpi=50)\n",
+    "plt.scatter(true, preds,  color='black')\n",
+    "line = np.linspace(0, 4, 100)\n",
+    "plt.plot(line, line)\n",
+    "plt.rc('font', size=12)\n",
+    "plt.xlabel('True Theta E')\n",
+    "plt.ylabel('Predicted Theta E');\n",
+    "plt.rc('font', size=20)\n",
+    "plt.title('MMD - Target')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14a94f1e-758e-4a64-b0c7-0f3a5781f7c2",
+   "metadata": {
+    "id": "14a94f1e-758e-4a64-b0c7-0f3a5781f7c2"
+   },
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": [
+    {
+     "file_id": "1MFScb-3Sbugn4RNiDaeocicJUIHlh_j2",
+     "timestamp": 1717430435817
+    },
+    {
+     "file_id": "1wlKaSdLzleueYrwljtOcqsiOfzEy1dxP",
+     "timestamp": 1717429638462
+    }
+   ]
+  },
+  "kernelspec": {
+   "display_name": "Python [conda env:.conda-neural]",
+   "language": "python",
+   "name": "conda-env-.conda-neural-py"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.15"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/notebooks/ShrihanPaperMMD_MinMaxNorm.ipynb b/training/notebooks/MMD_paper/normalization/ShrihanPaperMMD_MinMaxNorm.ipynb
similarity index 100%
rename from notebooks/ShrihanPaperMMD_MinMaxNorm.ipynb
rename to training/notebooks/MMD_paper/normalization/ShrihanPaperMMD_MinMaxNorm.ipynb
diff --git a/notebooks/ShrihanPaperMMD_Norm.ipynb b/training/notebooks/MMD_paper/normalization/ShrihanPaperMMD_Norm.ipynb
similarity index 100%
rename from notebooks/ShrihanPaperMMD_Norm.ipynb
rename to training/notebooks/MMD_paper/normalization/ShrihanPaperMMD_Norm.ipynb
diff --git a/notebooks/ShrihanPaperMMD_Norm2.ipynb b/training/notebooks/MMD_paper/normalization/ShrihanPaperMMD_Norm2.ipynb
similarity index 100%
rename from notebooks/ShrihanPaperMMD_Norm2.ipynb
rename to training/notebooks/MMD_paper/normalization/ShrihanPaperMMD_Norm2.ipynb
diff --git a/notebooks/mmd_to_send.ipynb b/training/notebooks/MMD_paper/original_mmdpaper_notebook.ipynb
similarity index 100%
rename from notebooks/mmd_to_send.ipynb
rename to training/notebooks/MMD_paper/original_mmdpaper_notebook.ipynb
diff --git a/training/scripts/__init__.py b/training/scripts/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/training/scripts/__version__.py b/training/scripts/__version__.py
new file mode 100644
index 0000000..e69de29
diff --git a/training/scripts/evaluate.py b/training/scripts/evaluate.py
new file mode 100644
index 0000000..664d20e
--- /dev/null
+++ b/training/scripts/evaluate.py
@@ -0,0 +1,46 @@
+"""
+Simple stub functions to use in inference
+"""
+
+import argparse
+
+
+def load_model(checkpoint_path):
+    """
+    Load the entire model for prediction with an input
+
+    :param checkpoint_path: location
+    :return: loaded model object that can be used with the predict function
+    """
+    pass
+
+
+def predict(input, model):
+    """
+
+    :param input: loaded object used for inference
+    :param model: loaded model
+    :return: Prediction
+    """
+    return 0
+
+def load_inference_object(input_path):
+    """
+
+    :param input_path: path to the object you want to predict
+    :return: loaded object
+    """
+    return 0
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--checkpoint", type=str, help="Checkpoint to unloaded model checkpoint, either weights or the compressed model object")
+    parser.add_argument("--input", type=str, help="path to object to predict quality of")
+    args = parser.parse_args()
+
+    model = load_model(args.checkpoint)
+    pred_obj = load_inference_object(args.input)
+
+    prediction = predict(pred_obj, model)
+    print(prediction)
diff --git a/training/scripts/paths.py b/training/scripts/paths.py
new file mode 100644
index 0000000..8c9434e
--- /dev/null
+++ b/training/scripts/paths.py
@@ -0,0 +1,29 @@
+"""
+Exposes common paths useful for manipulating datasets and generating figures.
+
+"""
+from pathlib import Path
+
+# Absolute path to the top level of the repository
+root = Path(__file__).resolve().parents[2].absolute()
+
+# Absolute path to the `src` folder
+src = root / "src"
+
+# Absolute path to the `src/data` folder (contains datasets)
+data = src / "data"
+
+# Absolute path to the `src/static` folder (contains static images)
+static = src / "static"
+
+# Absolute path to the `src/scripts` folder (contains figure/pipeline scripts)
+scripts = src / "scripts"
+
+# Absolute path to the `src/tex` folder (contains the manuscript)
+tex = src / "tex"
+
+# Absolute path to the `src/tex/figures` folder (contains figure output)
+figures = tex / "figures"
+
+# Absolute path to the `src/tex/output` folder (contains other user-defined output)
+output = tex / "output"
\ No newline at end of file
diff --git a/training/scripts/train.py b/training/scripts/train.py
new file mode 100644
index 0000000..a24465b
--- /dev/null
+++ b/training/scripts/train.py
@@ -0,0 +1,39 @@
+"""
+Simple stubs to use for re-train of the final model
+Can leave a default data source, or specify that 'load data' loads the dataset used in the final version
+"""
+import argparse
+
+
+def architecture():
+    """
+    :return: compiled architecture of the model you want to have trained
+    """
+    return 0
+
+def load_data(data_source):
+    """
+    :return: data loader or full training data, split in val and train
+    """
+    return 0, 0
+
+def train_model(data_source, n_epochs):
+    """
+    :param data_source:
+    :param n_epochs:
+    :return: trained model, or simply None, but saved trained model
+    """
+    data = load_data(data_source)
+    model = architecture()
+
+    return 0
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--data_source", type=str, help="Data used to train the model")
+    parser.add_argument("--n_epochs", type=int, help='Integer number of epochs to train the model')
+
+    args = parser.parse_args()
+
+    train_model(data_source=args.data_source, n_epochs=args.n_epochs)
diff --git a/training/static/.gitignore b/training/static/.gitignore
new file mode 100644
index 0000000..e167a34
--- /dev/null
+++ b/training/static/.gitignore
@@ -0,0 +1,2 @@
+# Anything is game in this folder
+!*
diff --git a/training/tex/.gitignore b/training/tex/.gitignore
new file mode 100644
index 0000000..841b7c7
--- /dev/null
+++ b/training/tex/.gitignore
@@ -0,0 +1,2 @@
+# Don't track TeX temporaries
+*latexindent*
\ No newline at end of file
diff --git a/training/tex/bib.bib b/training/tex/bib.bib
new file mode 100644
index 0000000..5ca6881
--- /dev/null
+++ b/training/tex/bib.bib
@@ -0,0 +1,37 @@
+@article{Hunter:2007,
+  Author = {Hunter, J. D.},
+  Title     = {Matplotlib: A 2D graphics environment},
+  Journal   = {Computing in Science \& Engineering},
+  Volume    = {9},
+  Number    = {3},
+  Pages     = {90--95},
+  abstract  = {Matplotlib is a 2D graphics package used for Python for
+  application development, interactive scripting, and publication-quality
+  image generation across user interfaces and operating systems.},
+  publisher = {IEEE COMPUTER SOC},
+  doi       = {10.1109/MCSE.2007.55},
+  year      = 2007
+ }
+
+@article{         harris2020array,
+ title         = {Array programming with {NumPy}},
+ author        = {Charles R. Harris and K. Jarrod Millman and St{\'{e}}fan J.
+                 van der Walt and Ralf Gommers and Pauli Virtanen and David
+                 Cournapeau and Eric Wieser and Julian Taylor and Sebastian
+                 Berg and Nathaniel J. Smith and Robert Kern and Matti Picus
+                 and Stephan Hoyer and Marten H. van Kerkwijk and Matthew
+                 Brett and Allan Haldane and Jaime Fern{\'{a}}ndez del
+                 R{\'{i}}o and Mark Wiebe and Pearu Peterson and Pierre
+                 G{\'{e}}rard-Marchant and Kevin Sheppard and Tyler Reddy and
+                 Warren Weckesser and Hameer Abbasi and Christoph Gohlke and
+                 Travis E. Oliphant},
+ year          = {2020},
+ month         = sep,
+ journal       = {Nature},
+ volume        = {585},
+ number        = {7825},
+ pages         = {357--362},
+ doi           = {10.1038/s41586-020-2649-2},
+ publisher     = {Springer Science and Business Media {LLC}},
+ url           = {https://doi.org/10.1038/s41586-020-2649-2}
+}
\ No newline at end of file
diff --git a/training/tex/figures/.gitignore b/training/tex/figures/.gitignore
new file mode 100644
index 0000000..9d0f65c
--- /dev/null
+++ b/training/tex/figures/.gitignore
@@ -0,0 +1,5 @@
+# Nothing should be tracked in this folder...
+*
+
+# Except the gitignore file itself!
+!.gitignore
\ No newline at end of file
diff --git a/training/tex/ms.tex b/training/tex/ms.tex
new file mode 100644
index 0000000..ad2222b
--- /dev/null
+++ b/training/tex/ms.tex
@@ -0,0 +1,254 @@
+
+\documentclass[twocolumn]{aastex631}
+
+% Import showyourwork magic
+\usepackage{showyourwork}
+
+\usepackage[utf8]{inputenc}
+\usepackage{amsmath}
+\usepackage{unicode-math}
+
+
+% Recommended, but optional, packages for figures and better typesetting:
+\usepackage{microtype}
+\usepackage{graphicx}
+\usepackage{subfigure}
+\usepackage{booktabs} % for professional tables
+\usepackage{multirow}
+
+% hyperref makes hyperlinks in the resulting PDF.
+% xurl can wrap the link if it spans a column (especially in citations).
+\usepackage{hyperref}
+\usepackage{xurl}
+
+
+% This command creates a new command \editor{} that highlights any of the text in {} with a maroon color, so it can easily be spotted during internal review
+
+\usepackage[textsize=tiny]{todonotes}
+\newcommand{\editor}[1]{{\color{purple} #1}}
+
+\begin{document}
+
+\title{DeepSkies - Template} % Define the title itself, so it may be used in headers
+
+\author{Author 1 \thanks{Corresponding Author, email@domain.com}}
+
+
+\begin{abstract}
+    This document is meant to be used as a lose guide.
+    It includes useful and basic packages and formatting tips to keep you from hunting for formatting code while writing.
+    Please use this as a reference, and especially while writing without a specific journal already in mind.
+    This will not be the format all journals accept, so please use their defined style guides when work on your draft.
+    % Additionally, it's very nice to keep all your sentences on different lines.
+    % It makes editing a lot easier.
+\end{abstract}
+
+\section{Basic Format and Style}
+
+\subsection{Format}
+
+The specific format of the paper if between you and your journal and your editors.
+However, it is a good idea to include the basic sections of "Introduction, Methods, Conclusions".
+
+\subsection{Style}
+
+Names of coding packages denoted with: \texttt{Package}.
+
+
+
+\editor{Here is an quick comment that may appear, indicating an addition by an editor.}
+
+\subsubsection{Tables}
+
+Tables should act as summaries, and include error bars when applicable. Captions should draw attention to the main takeaway and can provide analysis, but not necessary give a full summary.
+Please view sample table formats in the appendix ~\ref{tab:two_column}
+
+
+
+
+\subsubsection{Plots and other graphics}
+
+When making graphics, please keep accessibility in mind.
+All plots should be understandable in both black and white and color.
+This requires things like using color blind friendly color packages (matplotlib's virdis for example), and changing line and marker styles for different elements of a graph.
+Plots also must be clearly labeled and include legends where applicable.
+Captions should both describe what the figure contains and its significance.
+
+When referencing a figure in the main text, please refer to it with \verb|~\ref{figure label}|.
+Please view different figure layouts in the appendix ~\ref{fig:single_graphic_figure}.
+
+
+
+\subsubsection{Equations}
+
+Large equations should be numbered and included in an equation block such that
+\begin{align}
+    E=mc^2 \label{eq:1} \\
+    F=ma \label{eq:2}
+\end{align}
+
+
+Intermediate steps can not include numbers such that
+\begin{align*}
+    A = \pi r^2
+\end{align*}
+
+Or by using:
+
+\begin{align}
+    A
+        &=B         \label{eq:3}\\
+        &=B         \notag\\
+    A
+        &=BCD       \label{eq:4}\\
+        &=B         \notag
+\end{align}
+
+
+Labels are used so that they can be referenced later on using the command \verb|~\ref{eq:equation label}|.  Singular symbols can be added into the middle of sentences using \verb|$\symbol$|, such that \verb|\pi| becomes $\pi$.
+
+\section {Acknowledgements}
+
+Make sure to cite \cite{harris2020array} all of your sources \cite{Hunter:2007}.
+
+
+You can also optionally provide contributions by person:
+
+\paragraph{Author 1}
+Author 1 contributed X Y and Z
+
+\paragraph{Author 2}
+Author 2 contributed A B and C
+
+If you work with the DeepSkies research group; please include the following text:
+
+\emph{We acknowledge the Deep Skies Lab as a community of multi-domain experts and collaborators who’ve facilitated an environment of open discussion, idea-generation, and collaboration. This community was important for the development of this project.}
+
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% bibliography
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+
+
+% Style of the bib may change based on the publications requirements
+
+\bibliography{bib}
+
+
+ % Ending the multicol format before the appendix
+
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+% APPENDIX
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
+\newpage
+\appendix
+\section{Appendix}
+You may include an appendix, it contains extra tables not required to understand the main body, but helpful references.
+
+\subsection{Figure References}
+\begin{figure}[h]
+    \centering
+    \includegraphics[scale=.1]
+  {figures/frog.jpg}
+    \caption{
+        This is a figure (containing a cute, although not colorblind friendly, frog) with a single graphic.
+        Because the original image is very large, it is resized with a smaller scale.
+        }
+    \label{fig:single_graphic_figure}
+\end{figure}
+
+
+\begin{figure}[h]
+    \begin{center}
+    \begin{minipage}{.35\linewidth}
+        \includegraphics[width=\linewidth]{figures/frog2.jpg}
+
+        \caption{An example of using minipage to caption each image in a combined figure separately.}
+    \end{minipage}\hfill
+
+    \begin{minipage}{.35\linewidth}
+        \includegraphics[width=\linewidth]{figures/frog3.jpg}
+
+        \caption{This frog has it's own caption, so they can be referred to separately If you were heartless enough to separate them.}
+    \end{minipage}
+    \label{multifigAB}
+
+    \end{center}
+
+\end{figure}
+
+% Todo Example of running show your work function within the tex to produce table
+
+\subsection{Table References}
+
+\begin{figure}[h]
+    \centering
+    \mbox{\subfigure{\includegraphics[width=.35\linewidth]{figures/frog2.jpg}}\quad
+        \subfigure{\includegraphics[width=.35\linewidth]{figures/frog3.jpg} }}
+    \caption{An example showing two images with a shared caption using subfigure. Now the frogs cannot be separated.}
+    \label{fig:multifigC}
+\end{figure}
+
+\begin{table}[h]
+    \centering
+    \caption{Sample table with two columns and a header, with the caption placed on top.}
+    \label{tab:two_column}
+    \vspace{.2in}
+    \begin{tabular}{c | c}
+        \toprule
+        Header 1     & Header 2 \\
+        \midrule
+        Entry 1      &  0  $\pm$ 0.001  \\
+        Entry 2      &  1  $\pm$ 0.001  \\
+        Entry 3      &  2  $\pm$ 0.001 \\
+        \bottomrule
+    \end{tabular}
+\end{table}
+
+\begin{table}[h]
+    \centering
+    \caption{A Table displaying multi-rows. Horizontal lines can be removed, but tend to lead to confusing tables.}
+    \vspace{.2in}
+    \label{tab:multirow}
+    \begin{tabular}{c|c|c}
+
+        \toprule
+        Header 1 & Header 2 & Header 3 \\
+        \midrule
+
+        \multirow{2}*{Multi-Row}
+            & Row 1 & Row 1 \\
+            \cline{2-3} % \cline{n_rows-n_columns}
+            & Row 2 & Row 2 \\
+
+
+        \hline
+        Single-Row & Row 3  & Row 3\\
+        \bottomrule
+    \end{tabular}
+
+\end{table}
+
+\begin{table}[h]
+    \centering
+    \caption{A Table with multiple columns.}
+    \label{tab:multicol}
+    \vspace{.2in}
+
+        \begin{tabular}{c|c|c}
+            \toprule
+            \multicolumn{2}{c|}{Multi-Column}   & Column 3 \\
+            \midrule
+                        Column 1 & Column 2     & Column 3 \\
+                        Column 1 & Column 2     & Column 3 \\
+            \bottomrule
+        \end{tabular}
+\end{table}
+
+% Todo: Show your work table drawing results from a function
+
+\end{document}
diff --git a/training/tex/output/.gitignore b/training/tex/output/.gitignore
new file mode 100644
index 0000000..9d0f65c
--- /dev/null
+++ b/training/tex/output/.gitignore
@@ -0,0 +1,5 @@
+# Nothing should be tracked in this folder...
+*
+
+# Except the gitignore file itself!
+!.gitignore
\ No newline at end of file
diff --git a/training/tex/showyourwork.sty b/training/tex/showyourwork.sty
new file mode 100644
index 0000000..8432d72
--- /dev/null
+++ b/training/tex/showyourwork.sty
@@ -0,0 +1,13 @@
+\NeedsTeXFormat{LaTeX2e}
+\ProvidesPackage{showyourwork}[2022/01/12 Open source science articles]
+
+\IfFileExists{./showyourwork.tex}{
+    \input{showyourwork.tex}
+}{
+    \newcommand\GitHubURL{}
+    \newcommand\GitHubSHA{}
+    \newcommand\GitHubIcon{}
+    \newcommand\showyourwork{}
+    \newcommand\script[1]{}
+    \newcommand\variable[1]{}
+}
\ No newline at end of file