Mercurial > repos > goeckslab > image_learner

changeset 0:54b871dfc51e draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/goeckslab/gleam.git commit b7411ff35b6228ccdfd36cd4ebd946c03ac7f7e9
author goeckslab
date Tue, 03 Jun 2025 21:22:11 +0000
parents
children
files image_learner.xml image_learner_cli.py test-data/image_classification_results_report_mnist.html test-data/mnist_subset.csv test-data/mnist_subset.zip utils.py
diffstat 6 files changed, 1813 insertions(+), 0 deletions(-) [+]
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/image_learner.xml	Tue Jun 03 21:22:11 2025 +0000
@@ -0,0 +1,270 @@
+<tool id="image_learner" name="Image Learner for Classification" version="0.1.0" profile="22.05">
+    <description>trains and evaluates a image classification model</description>
+    <requirements>
+        <container type="docker">quay.io/goeckslab/galaxy-ludwig-gpu:0.10.1</container>
+    </requirements>
+    <required_files>
+        <include path="utils.py" />
+        <include path="image_learner_cli.py" />
+    </required_files>
+    <stdio>
+        <exit_code range="137" level="fatal_oom" description="Out of Memory" />
+        <exit_code range="1:" level="fatal" description="Error occurred. Please check Tool Standard Error" />
+    </stdio>
+    <command>
+        <![CDATA[
+            #import re
+
+            #if $input_csv
+
+            #set $sanitized_input_csv = re.sub('[^\w\-_\.]', '_', $input_csv.element_identifier.strip())
+            ln -sf '$input_csv' "./${sanitized_input_csv}";
+            #end if
+
+            python '$__tool_directory__/image_learner_cli.py'
+                --csv-file "./${sanitized_input_csv}"
+                --image-zip "$image_zip"
+                --model-name "$model_name"
+                #if $use_pretrained == "true"
+                    --use-pretrained
+                    #if $fine_tune == "true"
+                        --fine-tune
+                    #end if
+                #end if
+                #if $customize_defaults == "true"
+                    #if $epochs
+                        --epochs "$epochs"
+                    #end if
+                    #if $early_stop
+                        --early-stop "$early_stop"
+                    #end if
+                    #if $learning_rate_define == "true"
+                        --learning-rate "$learning_rate"
+                    #end if
+                    #if $batch_size_define == "true"
+                        --batch-size "$batch_size"
+                    #end if
+                    --split-probabilities "$train_split" "$val_split" "$test_split"   
+                #end if
+                --random-seed "$random_seed" 
+                --output-dir "." &&
+
+            mkdir -p '$output_model.extra_files_path' &&
+            cp -r experiment_run/model/*.json experiment_run/model/model_weights '$output_model.extra_files_path' &&
+
+            echo "Image Learner Classification Experiment is Done!"        
+        ]]>
+    </command>
+    
+    <inputs>
+        <param argument="input_csv" type="data" format="csv" optional="false" label="the metadata csv containing image_path column, label column and optional split column" />
+        <param name="image_zip" type="data" format="zip" optional="false" label="Image zip" help="Image zip file containing your image data"/>
+        <param name="model_name" type="select" optional="false" label="Select a model for your experiment" >
+           
+            <option value="resnet18">Resnet18</option>
+            <option value="resnet34">Resnet34</option>
+            <option value="resnet50">Resnet50</option>
+            <option value="resnet101">Resnet101</option>
+            <option value="resnet152">Resnet152</option>
+            <option value="resnext50_32x4d">Resnext50_32x4d</option>
+            <option value="resnext101_32x8d">Resnext101_32x8d</option>
+            <option value="resnext101_64x4d">Resnext101_64x4d</option>
+            <option value="resnext152_32x8d">Resnext152_32x8d</option>
+            <option value="wide_resnet50_2">Wide_resnet50_2</option>
+            <option value="wide_resnet101_2">Wide_resnet101_2</option>
+            <option value="wide_resnet103_2">Wide_resnet103_2</option>
+            <option value="efficientnet_b0">Efficientnet_b0</option>
+            <option value="efficientnet_b1">Efficientnet_b1</option>
+            <option value="efficientnet_b2">Efficientnet_b2</option>
+            <option value="efficientnet_b3">Efficientnet_b3</option>
+            <option value="efficientnet_b4">Efficientnet_b4</option>
+            <option value="efficientnet_b5">Efficientnet_b5</option>
+            <option value="efficientnet_b6">Efficientnet_b6</option>
+            <option value="efficientnet_b7">Efficientnet_b7</option>
+            <option value="efficientnet_v2_s">Efficientnet_v2_s</option>
+            <option value="efficientnet_v2_m">Efficientnet_v2_m</option>
+            <option value="efficientnet_v2_l">Efficientnet_v2_l</option>
+            <option value="regnet_y_400mf">Regnet_y_400mf</option>
+            <option value="regnet_y_800mf">Regnet_y_800mf</option>
+            <option value="regnet_y_1_6gf">Regnet_y_1_6gf</option>
+            <option value="regnet_y_3_2gf">Regnet_y_3_2gf</option>
+            <option value="regnet_y_8gf">Regnet_y_8gf</option>
+            <option value="regnet_y_16gf">Regnet_y_16gf</option>
+            <option value="regnet_y_32gf">Regnet_y_32gf</option>
+            <option value="regnet_y_128gf">Regnet_y_128gf</option>
+            <option value="regnet_x_400mf">Regnet_x_400mf</option>
+            <option value="regnet_x_800mf">Regnet_x_800mf</option>
+            <option value="regnet_x_1_6gf">Regnet_x_1_6gf</option>
+            <option value="regnet_x_3_2gf">Regnet_x_3_2gf</option>
+            <option value="regnet_x_8gf">Regnet_x_8gf</option>
+            <option value="regnet_x_16gf">Regnet_x_16gf</option>
+            <option value="regnet_x_32gf">Regnet_x_32gf</option>
+            <option value="vgg11">Vgg11</option>
+            <option value="vgg11_bn">Vgg11_bn</option>
+            <option value="vgg13">Vgg13</option>
+            <option value="vgg13_bn">Vgg13_bn</option>
+            <option value="vgg16">Vgg16</option>
+            <option value="vgg16_bn">Vgg16_bn</option>
+            <option value="vgg19">Vgg19</option>
+            <option value="vgg19_bn">Vgg19_bn</option>
+            <option value="shufflenet_v2_x0_5">Shufflenet_v2_x0_5</option>
+            <option value="shufflenet_v2_x1_0">Shufflenet_v2_x1_0</option>
+            <option value="shufflenet_v2_x1_5">Shufflenet_v2_x1_5</option>
+            <option value="shufflenet_v2_x2_0">Shufflenet_v2_x2_0</option>
+            <option value="squeezenet1_0">Squeezenet1_0</option>
+            <option value="squeezenet1_1">Squeezenet1_1</option>
+            <option value="swin_t">Swin_t</option>
+            <option value="swin_s">Swin_s</option>
+            <option value="swin_b">Swin_b</option>
+            <option value="swin_v2_t">Swin_v2_t</option>
+            <option value="swin_v2_s">Swin_v2_s</option>
+            <option value="swin_v2_b">Swin_v2_b</option>
+            <option value="vit_b_16">Vit_b_16</option>
+            <option value="vit_b_32">Vit_b_32</option>
+            <option value="vit_l_16">Vit_l_16</option>
+            <option value="vit_l_32">Vit_l_32</option>
+            <option value="vit_h_14">Vit_h_14</option>
+            <option value="convnext_tiny">Convnext_tiny</option>
+            <option value="convnext_small">Convnext_small</option>
+            <option value="convnext_base">Convnext_base</option>
+            <option value="convnext_large">Convnext_large</option>
+            <option value="maxvit_t">Maxvit_t</option>
+            <option value="alexnet">Alexnet</option>
+            <option value="googlenet">Googlenet</option>
+            <option value="inception_v3">Inception_v3</option>
+            <option value="mobilenet_v2">Mobilenet_v2</option>
+            <option value="mobilenet_v3_large">Mobilenet_v3_large</option>
+            <option value="mobilenet_v3_small">Mobilenet_v3_small</option>
+        </param>
+
+        <conditional name="scratch_fine_tune">
+            <param name="use_pretrained" type="select"
+                label="Use pretrained weights?"
+                help="If select no, the encoder, combiner, and decoder will all be initialized and trained from scratch.  
+               (e.g. when your images are very different from ImageNet or no suitable pretrained model exists.)">
+                <option value="false">No</option>
+                <option value="true" selected="true">Yes</option>
+            </param>
+            <when value="true">
+                <param name="fine_tune" type="select" label="Fine tune the encoder?"
+                    help="Whether to fine tune the encoder(combiner and decoder will be fine-tued anyway)" >
+                    <option value="false" >No</option>
+                    <option value="true" selected="true">Yes</option>
+                </param>
+            </when>
+            <when value="false">
+                <!-- No additional parameters to show if the user selects 'No' -->
+            </when>
+        </conditional>
+        <param argument="random_seed" type="integer" value="42" optional="true" label="Random seed (set for reproducibility)" min="0" max="999999"/>
+        <conditional name="advanced_settings">
+            <param name="customize_defaults" type="select" label="Customize Default Settings?" help="Select yes if you want to customize the default settings of the experiment.">
+                <option value="false" selected="true">No</option>
+                <option value="true">Yes</option>
+            </param>
+            <when value="true">
+                <param name="epochs" type="integer" value="10" min="1" max="99999" label="Epochs" help="Total number of full passes through the training dataset. Higher values may improve accuracy but increase training time. Default: 10." />
+                <param name="early_stop" type="integer" value="5" min="1" max="99999" label="Early Stop" help="Number of epochs with no improvement after which training will be stopped. Default: 5." />
+                <conditional name="learning_rate_condition">
+                    <param name="learning_rate_define" type="select" label="Define an initial learning rate?" help="Want to change the initial learning rate from default to a number? See ludwig.ai for more info. Default: No" >
+                        <option value="false" selected="true" >No</option>
+                        <option value="true">Yes</option>
+                    </param>
+                    <when value="true">
+                        <param name="learning_rate" type="float" value="0.001" min="0.0001" max="1.0" label="Learning Rate" help="Initial learning rate for the optimizer. Default: 0.001." />
+                    </when>
+                    <when value="false">
+                        <!-- No additional parameters to show if the user selects 'No' -->
+                    </when>
+                </conditional>
+                <conditional name="batch_size_condition">
+                    <param name="batch_size_define" type="select" label="Define your batch size?" help="Want to change the batch size from auto to a number? See ludwig.ai for more info. Default: No" >
+                        <option value="false" selected="true" >No</option>
+                        <option value="true">Yes</option>
+                    </param>
+                    <when value="true">
+                        <param name="batch_size" type="integer" value="32" min="1" max="99999" label="Batch Size" help="Number of samples per gradient update. Default: 32." />
+                    </when>
+                    <when value="false">
+                        <!-- No additional parameters to show if the user selects 'No' -->
+                    </when>
+                </conditional>
+                <param name="train_split" type="float"
+                        label="Training split proportion (only works if no split column in the metadata csv)"
+                        value="0.7"
+                        help="Fraction of data for training (e.g., 0.7). train split + val split + test split should = 1"/>
+                <param name="val_split"   type="float"
+                        label="Validation split proportion (only works if no split column in the metadata csv)"
+                        value="0.1"
+                        help="Fraction of data for validation (e.g., 0.1). train split + val split + test split should = 1"/>
+                <param name="test_split"  type="float"
+                        label="Test split proportion (only works if no split column in the metadata csv)"
+                        value="0.2"
+                        help="Fraction of data for testing (e.g., 0.2) train split + val split + test split should = 1."/>
+            </when>
+            <when value="false">
+                <!-- No additional parameters to show if the user selects 'No' -->
+            </when>
+        </conditional>    
+    </inputs>       
+    <outputs>
+        <data format="ludwig_model" name="output_model" label="${tool.name} trained model on ${on_string}" />
+        <data format="html" name="output_report" from_work_dir="image_classification_results_report.html" label="${tool.name} report on ${on_string}" />
+        <collection type="list" name="output_pred_csv" label="${tool.name} predictions CSVs/experiment stats/plots on ${on_string}" >
+            <discover_datasets pattern="(?P&lt;designation&gt;predictions\.csv)" format="csv" directory="experiment_run" />
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.json" format="json" directory="experiment_run" />
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.png" format="png" directory="experiment_run/visualizations/train" />
+            <discover_datasets pattern="(?P&lt;designation&gt;.+)\.png" format="png" directory="experiment_run/visualizations/test" />
+        </collection>
+    </outputs>
+    <tests>
+        <test expect_num_outputs="3">
+            <param name="input_csv" value="mnist_subset.csv" ftype="csv" />
+            <param name="image_zip" value="mnist_subset.zip" ftype="zip" />
+            <param name="model_name" value="resnet18" />
+            <output name="output_report" file="image_classification_results_report_mnist.html" compare="sim_size" delta="20000" >
+                <assert_contents>
+                    <has_text text="Epochs" />
+                </assert_contents>
+            </output>
+
+            <output_collection name="output_pred_csv" type="list" >
+                <element name="predictions.csv" >
+                    <assert_contents>
+                        <has_n_columns n="1" />
+                    </assert_contents>
+                </element>
+            </output_collection>
+        </test>
+    </tests>
+    <help>
+        <![CDATA[
+**What it does**
+Image Learner for Classification: trains and evaluates a image classification model. 
+It uses the metadata csv to find the image paths and labels. 
+The metadata csv should contain a column with the name 'image_path' and a column with the name 'label'.
+Optionally, you can also add a column with the name 'split' to specify which split each row belongs to (train, val, test). 
+If you do not provide a split column, the tool will automatically split the data into train, val, and test sets based on the proportions you specify or [0.7, 0.1, 0.2] by default.
+
+
+**Outputs**
+The tool will output a trained model in the form of a ludwig_model file,
+a report in the form of an HTML file, and a collection of CSV/json/png files containing the predictions, experiment stats and visualizations.
+The html report will contain metrics&experiment setup parameters, train&val plots and test plots.
+
+        ]]>
+    </help>
+    <citations>
+            <citation type="bibtex">
+@misc{https://doi.org/10.48550/arxiv.1909.07930,
+    doi = {10.48550/ARXIV.1909.07930},
+    url = {https://arxiv.org/abs/1909.07930},
+    author = {Molino, Piero and Dudin, Yaroslav and Miryala, Sai Sumanth},
+    title = {Ludwig: a type-based declarative deep learning toolbox},
+    publisher = {arXiv},
+    year = {2019},
+    copyright = {arXiv.org perpetual, non-exclusive license}
+}
+            </citation>
+        </citations>
+</tool>
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/image_learner_cli.py	Tue Jun 03 21:22:11 2025 +0000
@@ -0,0 +1,1137 @@
+#!/usr/bin/env python3
+import argparse
+import json
+import logging
+import os
+import shutil
+import sys
+import tempfile
+import zipfile
+from pathlib import Path
+from typing import Any, Dict, Optional, Protocol, Tuple
+
+import pandas as pd
+import yaml
+from ludwig.globals import (
+    DESCRIPTION_FILE_NAME,
+    PREDICTIONS_PARQUET_FILE_NAME,
+    TEST_STATISTICS_FILE_NAME,
+    TRAIN_SET_METADATA_FILE_NAME,
+)
+from ludwig.utils.data_utils import get_split_path
+from ludwig.visualize import get_visualizations_registry
+from sklearn.model_selection import train_test_split
+from utils import encode_image_to_base64, get_html_closing, get_html_template
+
+# --- Constants ---
+SPLIT_COLUMN_NAME = 'split'
+LABEL_COLUMN_NAME = 'label'
+IMAGE_PATH_COLUMN_NAME = 'image_path'
+DEFAULT_SPLIT_PROBABILITIES = [0.7, 0.1, 0.2]
+TEMP_CSV_FILENAME = "processed_data_for_ludwig.csv"
+TEMP_CONFIG_FILENAME = "ludwig_config.yaml"
+TEMP_DIR_PREFIX = "ludwig_api_work_"
+MODEL_ENCODER_TEMPLATES: Dict[str, Any] = {
+    'stacked_cnn': 'stacked_cnn',
+    'resnet18': {'type': 'resnet', 'model_variant': 18},
+    'resnet34': {'type': 'resnet', 'model_variant': 34},
+    'resnet50': {'type': 'resnet', 'model_variant': 50},
+    'resnet101': {'type': 'resnet', 'model_variant': 101},
+    'resnet152': {'type': 'resnet', 'model_variant': 152},
+    'resnext50_32x4d': {'type': 'resnext', 'model_variant': '50_32x4d'},
+    'resnext101_32x8d': {'type': 'resnext', 'model_variant': '101_32x8d'},
+    'resnext101_64x4d': {'type': 'resnext', 'model_variant': '101_64x4d'},
+    'resnext152_32x8d': {'type': 'resnext', 'model_variant': '152_32x8d'},
+    'wide_resnet50_2': {'type': 'wide_resnet', 'model_variant': '50_2'},
+    'wide_resnet101_2': {'type': 'wide_resnet', 'model_variant': '101_2'},
+    'wide_resnet103_2': {'type': 'wide_resnet', 'model_variant': '103_2'},
+    'efficientnet_b0': {'type': 'efficientnet', 'model_variant': 'b0'},
+    'efficientnet_b1': {'type': 'efficientnet', 'model_variant': 'b1'},
+    'efficientnet_b2': {'type': 'efficientnet', 'model_variant': 'b2'},
+    'efficientnet_b3': {'type': 'efficientnet', 'model_variant': 'b3'},
+    'efficientnet_b4': {'type': 'efficientnet', 'model_variant': 'b4'},
+    'efficientnet_b5': {'type': 'efficientnet', 'model_variant': 'b5'},
+    'efficientnet_b6': {'type': 'efficientnet', 'model_variant': 'b6'},
+    'efficientnet_b7': {'type': 'efficientnet', 'model_variant': 'b7'},
+    'efficientnet_v2_s': {'type': 'efficientnet', 'model_variant': 'v2_s'},
+    'efficientnet_v2_m': {'type': 'efficientnet', 'model_variant': 'v2_m'},
+    'efficientnet_v2_l': {'type': 'efficientnet', 'model_variant': 'v2_l'},
+    'regnet_y_400mf': {'type': 'regnet', 'model_variant': 'y_400mf'},
+    'regnet_y_800mf': {'type': 'regnet', 'model_variant': 'y_800mf'},
+    'regnet_y_1_6gf': {'type': 'regnet', 'model_variant': 'y_1_6gf'},
+    'regnet_y_3_2gf': {'type': 'regnet', 'model_variant': 'y_3_2gf'},
+    'regnet_y_8gf': {'type': 'regnet', 'model_variant': 'y_8gf'},
+    'regnet_y_16gf': {'type': 'regnet', 'model_variant': 'y_16gf'},
+    'regnet_y_32gf': {'type': 'regnet', 'model_variant': 'y_32gf'},
+    'regnet_y_128gf': {'type': 'regnet', 'model_variant': 'y_128gf'},
+    'regnet_x_400mf': {'type': 'regnet', 'model_variant': 'x_400mf'},
+    'regnet_x_800mf': {'type': 'regnet', 'model_variant': 'x_800mf'},
+    'regnet_x_1_6gf': {'type': 'regnet', 'model_variant': 'x_1_6gf'},
+    'regnet_x_3_2gf': {'type': 'regnet', 'model_variant': 'x_3_2gf'},
+    'regnet_x_8gf': {'type': 'regnet', 'model_variant': 'x_8gf'},
+    'regnet_x_16gf': {'type': 'regnet', 'model_variant': 'x_16gf'},
+    'regnet_x_32gf': {'type': 'regnet', 'model_variant': 'x_32gf'},
+    'vgg11': {'type': 'vgg', 'model_variant': 11},
+    'vgg11_bn': {'type': 'vgg', 'model_variant': '11_bn'},
+    'vgg13': {'type': 'vgg', 'model_variant': 13},
+    'vgg13_bn': {'type': 'vgg', 'model_variant': '13_bn'},
+    'vgg16': {'type': 'vgg', 'model_variant': 16},
+    'vgg16_bn': {'type': 'vgg', 'model_variant': '16_bn'},
+    'vgg19': {'type': 'vgg', 'model_variant': 19},
+    'vgg19_bn': {'type': 'vgg', 'model_variant': '19_bn'},
+    'shufflenet_v2_x0_5': {'type': 'shufflenet_v2', 'model_variant': 'x0_5'},
+    'shufflenet_v2_x1_0': {'type': 'shufflenet_v2', 'model_variant': 'x1_0'},
+    'shufflenet_v2_x1_5': {'type': 'shufflenet_v2', 'model_variant': 'x1_5'},
+    'shufflenet_v2_x2_0': {'type': 'shufflenet_v2', 'model_variant': 'x2_0'},
+    'squeezenet1_0': {'type': 'squeezenet', 'model_variant': '1_0'},
+    'squeezenet1_1': {'type': 'squeezenet', 'model_variant': '1_1'},
+    'swin_t': {'type': 'swin_transformer', 'model_variant': 't'},
+    'swin_s': {'type': 'swin_transformer', 'model_variant': 's'},
+    'swin_b': {'type': 'swin_transformer', 'model_variant': 'b'},
+    'swin_v2_t': {'type': 'swin_transformer', 'model_variant': 'v2_t'},
+    'swin_v2_s': {'type': 'swin_transformer', 'model_variant': 'v2_s'},
+    'swin_v2_b': {'type': 'swin_transformer', 'model_variant': 'v2_b'},
+    'vit_b_16': {'type': 'vision_transformer', 'model_variant': 'b_16'},
+    'vit_b_32': {'type': 'vision_transformer', 'model_variant': 'b_32'},
+    'vit_l_16': {'type': 'vision_transformer', 'model_variant': 'l_16'},
+    'vit_l_32': {'type': 'vision_transformer', 'model_variant': 'l_32'},
+    'vit_h_14': {'type': 'vision_transformer', 'model_variant': 'h_14'},
+    'convnext_tiny': {'type': 'convnext', 'model_variant': 'tiny'},
+    'convnext_small': {'type': 'convnext', 'model_variant': 'small'},
+    'convnext_base': {'type': 'convnext', 'model_variant': 'base'},
+    'convnext_large': {'type': 'convnext', 'model_variant': 'large'},
+    'maxvit_t': {'type': 'maxvit', 'model_variant': 't'},
+    'alexnet': {'type': 'alexnet'},
+    'googlenet': {'type': 'googlenet'},
+    'inception_v3': {'type': 'inception_v3'},
+    'mobilenet_v2': {'type': 'mobilenet_v2'},
+    'mobilenet_v3_large': {'type': 'mobilenet_v3_large'},
+    'mobilenet_v3_small': {'type': 'mobilenet_v3_small'},
+}
+
+# --- Logging Setup ---
+logging.basicConfig(
+    level=logging.INFO,
+    format='%(asctime)s %(levelname)s %(name)s: %(message)s'
+)
+logger = logging.getLogger("ImageLearner")
+
+
+def format_config_table_html(
+        config: dict,
+        split_info: Optional[str] = None,
+        training_progress: dict = None) -> str:
+    display_keys = [
+        "model_name",
+        "epochs",
+        "batch_size",
+        "fine_tune",
+        "use_pretrained",
+        "learning_rate",
+        "random_seed",
+        "early_stop",
+    ]
+
+    rows = []
+
+    for key in display_keys:
+        val = config.get(key, "N/A")
+        if key == "batch_size":
+            if val is not None:
+                val = int(val)
+            else:
+                if training_progress:
+                    val = "Auto-selected batch size by Ludwig:<br>"
+                    resolved_val = training_progress.get("batch_size")
+                    val += (
+                        f"<span style='font-size: 0.85em;'>{resolved_val}</span><br>"
+                    )
+                else:
+                    val = "auto"
+        if key == "learning_rate":
+            resolved_val = None
+            if val is None or val == "auto":
+                if training_progress:
+                    resolved_val = training_progress.get("learning_rate")
+                    val = (
+                        "Auto-selected learning rate by Ludwig:<br>"
+                        f"<span style='font-size: 0.85em;'>{resolved_val if resolved_val else val}</span><br>"
+                        "<span style='font-size: 0.85em;'>"
+                        "Based on model architecture and training setup (e.g., fine-tuning).<br>"
+                        "See <a href='https://ludwig.ai/latest/configuration/trainer/#trainer-parameters' "
+                        "target='_blank'>Ludwig Trainer Parameters</a> for details."
+                        "</span>"
+                    )
+                else:
+                    val = (
+                        "Auto-selected by Ludwig<br>"
+                        "<span style='font-size: 0.85em;'>"
+                        "Automatically tuned based on architecture and dataset.<br>"
+                        "See <a href='https://ludwig.ai/latest/configuration/trainer/#trainer-parameters' "
+                        "target='_blank'>Ludwig Trainer Parameters</a> for details."
+                        "</span>"
+                    )
+            else:
+                val = f"{val:.6f}"
+        if key == "epochs":
+            if training_progress and "epoch" in training_progress and val > training_progress["epoch"]:
+                val = (
+                    f"Because of early stopping: the training"
+                    f"stopped at epoch {training_progress['epoch']}"
+                )
+
+        if val is None:
+            continue
+        rows.append(
+            f"<tr>"
+            f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>"
+            f"{key.replace('_', ' ').title()}</td>"
+            f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>{val}</td>"
+            f"</tr>"
+        )
+
+    if split_info:
+        rows.append(
+            f"<tr>"
+            f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Data Split</td>"
+            f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>{split_info}</td>"
+            f"</tr>"
+        )
+
+    return (
+        "<h2 style='text-align: center;'>Training Setup</h2>"
+        "<div style='display: flex; justify-content: center;'>"
+        "<table style='border-collapse: collapse; width: 60%; table-layout: auto;'>"
+        "<thead><tr>"
+        "<th style='padding: 10px; border: 1px solid #ccc; text-align: left;'>Parameter</th>"
+        "<th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Value</th>"
+        "</tr></thead><tbody>" + "".join(rows) + "</tbody></table></div><br>"
+        "<p style='text-align: center; font-size: 0.9em;'>"
+        "Model trained using Ludwig.<br>"
+        "If want to learn more about Ludwig default settings,"
+        "please check the their <a href='https://ludwig.ai' target='_blank'>website(ludwig.ai)</a>."
+        "</p><hr>"
+    )
+
+
+def format_stats_table_html(training_stats: dict, test_stats: dict) -> str:
+    train_metrics = training_stats.get("training", {}).get("label", {})
+    val_metrics = training_stats.get("validation", {}).get("label", {})
+    test_metrics = test_stats.get("label", {})
+
+    all_metrics = set(train_metrics) | set(val_metrics) | set(test_metrics)
+
+    def get_last_value(stats, key):
+        val = stats.get(key)
+        if isinstance(val, list) and val:
+            return val[-1]
+        elif isinstance(val, (int, float)):
+            return val
+        return None
+
+    rows = []
+    for metric in sorted(all_metrics):
+        t = get_last_value(train_metrics, metric)
+        v = get_last_value(val_metrics, metric)
+        te = get_last_value(test_metrics, metric)
+        if all(x is not None for x in [t, v, te]):
+            row = (
+                f"<tr>"
+                f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>{metric}</td>"
+                f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>{t:.4f}</td>"
+                f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>{v:.4f}</td>"
+                f"<td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>{te:.4f}</td>"
+                f"</tr>"
+            )
+            rows.append(row)
+
+    if not rows:
+        return "<p><em>No metric values found.</em></p>"
+
+    return (
+        "<h2 style='text-align: center;'>Model Performance Summary</h2>"
+        "<div style='display: flex; justify-content: center;'>"
+        "<table style='border-collapse: collapse; width: 80%; table-layout: fixed;'>"
+        "<colgroup>"
+        "<col style='width: 40%;'>"
+        "<col style='width: 20%;'>"
+        "<col style='width: 20%;'>"
+        "<col style='width: 20%;'>"
+        "</colgroup>"
+        "<thead><tr>"
+        "<th style='padding: 10px; border: 1px solid #ccc; text-align: left;'>Metric</th>"
+        "<th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Train</th>"
+        "<th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Validation</th>"
+        "<th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Test</th>"
+        "</tr></thead><tbody>" + "".join(rows) + "</tbody></table></div><br>"
+    )
+
+
+def build_tabbed_html(
+        metrics_html: str,
+        train_viz_html: str,
+        test_viz_html: str) -> str:
+    return f"""
+<style>
+.tabs {{
+  display: flex;
+  border-bottom: 2px solid #ccc;
+  margin-bottom: 1rem;
+}}
+.tab {{
+  padding: 10px 20px;
+  cursor: pointer;
+  border: 1px solid #ccc;
+  border-bottom: none;
+  background: #f9f9f9;
+  margin-right: 5px;
+  border-top-left-radius: 8px;
+  border-top-right-radius: 8px;
+}}
+.tab.active {{
+  background: white;
+  font-weight: bold;
+}}
+.tab-content {{
+  display: none;
+  padding: 20px;
+  border: 1px solid #ccc;
+  border-top: none;
+}}
+.tab-content.active {{
+  display: block;
+}}
+</style>
+
+<div class="tabs">
+  <div class="tab active" onclick="showTab('metrics')"> Config & Metrics</div>
+  <div class="tab" onclick="showTab('trainval')"> Train/Validation Plots</div>
+  <div class="tab" onclick="showTab('test')"> Test Plots</div>
+</div>
+
+<div id="metrics" class="tab-content active">
+  {metrics_html}
+</div>
+<div id="trainval" class="tab-content">
+  {train_viz_html}
+</div>
+<div id="test" class="tab-content">
+  {test_viz_html}
+</div>
+
+<script>
+function showTab(id) {{
+  document.querySelectorAll('.tab-content').forEach(el => el.classList.remove('active'));
+  document.querySelectorAll('.tab').forEach(el => el.classList.remove('active'));
+  document.getElementById(id).classList.add('active');
+  document.querySelector(`.tab[onclick*="${{id}}"]`).classList.add('active');
+}}
+</script>
+"""
+
+
+def split_data_0_2(
+    df: pd.DataFrame,
+    split_column: str,
+    validation_size: float = 0.15,
+    random_state: int = 42,
+    label_column: Optional[str] = None,
+) -> pd.DataFrame:
+    """
+    Given a DataFrame whose split_column only contains {0,2}, re-assign
+    a portion of the 0s to become 1s (validation). Returns a fresh DataFrame.
+    """
+    # Work on a copy
+    out = df.copy()
+    # Ensure split col is integer dtype
+    out[split_column] = pd.to_numeric(out[split_column], errors="coerce").astype(int)
+
+    idx_train = out.index[out[split_column] == 0].tolist()
+
+    if not idx_train:
+        logger.info("No rows with split=0; nothing to do.")
+        return out
+
+    # Determine stratify array if possible
+    stratify_arr = None
+    if label_column and label_column in out.columns:
+        # Only stratify if at least two classes and enough samples
+        label_counts = out.loc[idx_train, label_column].value_counts()
+        if label_counts.size > 1 and (label_counts.min() * validation_size) >= 1:
+            stratify_arr = out.loc[idx_train, label_column]
+        else:
+            logger.warning("Cannot stratify (too few labels); splitting without stratify.")
+
+    # Edge cases
+    if validation_size <= 0:
+        logger.info("validation_size <= 0; keeping all as train.")
+        return out
+    if validation_size >= 1:
+        logger.info("validation_size >= 1; moving all train → validation.")
+        out.loc[idx_train, split_column] = 1
+        return out
+
+    # Do the split
+    try:
+        train_idx, val_idx = train_test_split(
+            idx_train,
+            test_size=validation_size,
+            random_state=random_state,
+            stratify=stratify_arr
+        )
+    except ValueError as e:
+        logger.warning(f"Stratified split failed ({e}); retrying without stratify.")
+        train_idx, val_idx = train_test_split(
+            idx_train,
+            test_size=validation_size,
+            random_state=random_state,
+            stratify=None
+        )
+
+    # Assign new splits
+    out.loc[train_idx, split_column] = 0
+    out.loc[val_idx, split_column] = 1
+    # idx_test stays at 2
+
+    # Cast back to a clean integer type
+    out[split_column] = out[split_column].astype(int)
+    # print(out)
+    return out
+
+
+class Backend(Protocol):
+    """Interface for a machine learning backend."""
+    def prepare_config(
+        self,
+        config_params: Dict[str, Any],
+        split_config: Dict[str, Any]
+    ) -> str:
+        ...
+
+    def run_experiment(
+        self,
+        dataset_path: Path,
+        config_path: Path,
+        output_dir: Path,
+        random_seed: int,
+    ) -> None:
+        ...
+
+    def generate_plots(
+        self,
+        output_dir: Path
+    ) -> None:
+        ...
+
+    def generate_html_report(
+        self,
+        title: str,
+        output_dir: str
+    ) -> Path:
+        ...
+
+
+class LudwigDirectBackend:
+    """
+    Backend for running Ludwig experiments directly via the internal experiment_cli function.
+    """
+
+    def prepare_config(
+        self,
+        config_params: Dict[str, Any],
+        split_config: Dict[str, Any],
+    ) -> str:
+        """
+        Build and serialize the Ludwig YAML configuration.
+        """
+        logger.info("LudwigDirectBackend: Preparing YAML configuration.")
+
+        model_name = config_params.get("model_name", "resnet18")
+        use_pretrained = config_params.get("use_pretrained", False)
+        fine_tune = config_params.get("fine_tune", False)
+        epochs = config_params.get("epochs", 10)
+        batch_size = config_params.get("batch_size")
+        num_processes = config_params.get("preprocessing_num_processes", 1)
+        early_stop = config_params.get("early_stop", None)
+        learning_rate = config_params.get("learning_rate")
+        learning_rate = "auto" if learning_rate is None else float(learning_rate)
+        trainable = fine_tune or (not use_pretrained)
+        if not use_pretrained and not trainable:
+            logger.warning("trainable=False; use_pretrained=False is ignored.")
+            logger.warning("Setting trainable=True to train the model from scratch.")
+            trainable = True
+
+        # Encoder setup
+        raw_encoder = MODEL_ENCODER_TEMPLATES.get(model_name, model_name)
+        if isinstance(raw_encoder, dict):
+            encoder_config = {
+                **raw_encoder,
+                "use_pretrained": use_pretrained,
+                "trainable": trainable,
+            }
+        else:
+            encoder_config = {"type": raw_encoder}
+
+        # Trainer & optimizer
+        # optimizer = {"type": "adam", "learning_rate": 5e-5} if fine_tune else {"type": "adam"}
+        batch_size_cfg = batch_size or "auto"
+
+        conf: Dict[str, Any] = {
+            "model_type": "ecd",
+            "input_features": [
+                {
+                    "name": IMAGE_PATH_COLUMN_NAME,
+                    "type": "image",
+                    "encoder": encoder_config,
+                }
+            ],
+            "output_features": [
+                {"name": LABEL_COLUMN_NAME, "type": "category"}
+            ],
+            "combiner": {"type": "concat"},
+            "trainer": {
+                "epochs": epochs,
+                "early_stop": early_stop,
+                "batch_size": batch_size_cfg,
+                "learning_rate": learning_rate,
+            },
+            "preprocessing": {
+                "split": split_config,
+                "num_processes": num_processes,
+                "in_memory": False,
+            },
+        }
+
+        logger.debug("LudwigDirectBackend: Config dict built.")
+        try:
+            yaml_str = yaml.dump(conf, sort_keys=False, indent=2)
+            logger.info("LudwigDirectBackend: YAML config generated.")
+            return yaml_str
+        except Exception:
+            logger.error("LudwigDirectBackend: Failed to serialize YAML.", exc_info=True)
+            raise
+
+    def run_experiment(
+        self,
+        dataset_path: Path,
+        config_path: Path,
+        output_dir: Path,
+        random_seed: int = 42,
+    ) -> None:
+        """
+        Invoke Ludwig's internal experiment_cli function to run the experiment.
+        """
+        logger.info("LudwigDirectBackend: Starting experiment execution.")
+
+        try:
+            from ludwig.experiment import experiment_cli
+        except ImportError as e:
+            logger.error(
+                "LudwigDirectBackend: Could not import experiment_cli.",
+                exc_info=True
+            )
+            raise RuntimeError("Ludwig import failed.") from e
+
+        output_dir.mkdir(parents=True, exist_ok=True)
+
+        try:
+            experiment_cli(
+                dataset=str(dataset_path),
+                config=str(config_path),
+                output_directory=str(output_dir),
+                random_seed=random_seed,
+            )
+            logger.info(f"LudwigDirectBackend: Experiment completed. Results in {output_dir}")
+        except TypeError as e:
+            logger.error(
+                "LudwigDirectBackend: Argument mismatch in experiment_cli call.",
+                exc_info=True
+            )
+            raise RuntimeError("Ludwig argument error.") from e
+        except Exception:
+            logger.error(
+                "LudwigDirectBackend: Experiment execution error.",
+                exc_info=True
+            )
+            raise
+
+    def get_training_process(self, output_dir) -> float:
+        """
+        Retrieve the learning rate used in the most recent Ludwig run.
+        Returns:
+            float: learning rate (or None if not found)
+        """
+        output_dir = Path(output_dir)
+        exp_dirs = sorted(
+            output_dir.glob("experiment_run*"),
+            key=lambda p: p.stat().st_mtime
+        )
+
+        if not exp_dirs:
+            logger.warning(f"No experiment run directories found in {output_dir}")
+            return None
+
+        progress_file = exp_dirs[-1] / "model" / "training_progress.json"
+        if not progress_file.exists():
+            logger.warning(f"No training_progress.json found in {progress_file}")
+            return None
+
+        try:
+            with progress_file.open("r", encoding="utf-8") as f:
+                data = json.load(f)
+            return {
+                "learning_rate": data.get("learning_rate"),
+                "batch_size": data.get("batch_size"),
+                "epoch": data.get("epoch"),
+            }
+        except Exception as e:
+            self.logger.warning(f"Failed to read training progress info: {e}")
+            return {}
+
+    def convert_parquet_to_csv(self, output_dir: Path):
+        """Convert the predictions Parquet file to CSV."""
+        output_dir = Path(output_dir)
+        exp_dirs = sorted(
+            output_dir.glob("experiment_run*"),
+            key=lambda p: p.stat().st_mtime
+        )
+        if not exp_dirs:
+            logger.warning(f"No experiment run dirs found in {output_dir}")
+            return
+        exp_dir = exp_dirs[-1]
+        parquet_path = exp_dir / PREDICTIONS_PARQUET_FILE_NAME
+        csv_path = exp_dir / "predictions.csv"
+        try:
+            df = pd.read_parquet(parquet_path)
+            df.to_csv(csv_path, index=False)
+            logger.info(f"Converted Parquet to CSV: {csv_path}")
+        except Exception as e:
+            logger.error(f"Error converting Parquet to CSV: {e}")
+
+    def generate_plots(self, output_dir: Path) -> None:
+        """
+        Generate _all_ registered Ludwig visualizations for the latest experiment run.
+        """
+        logger.info("Generating all Ludwig visualizations…")
+
+        test_plots = {
+            'compare_performance',
+            'compare_classifiers_performance_from_prob',
+            'compare_classifiers_performance_from_pred',
+            'compare_classifiers_performance_changing_k',
+            'compare_classifiers_multiclass_multimetric',
+            'compare_classifiers_predictions',
+            'confidence_thresholding_2thresholds_2d',
+            'confidence_thresholding_2thresholds_3d',
+            'confidence_thresholding',
+            'confidence_thresholding_data_vs_acc',
+            'binary_threshold_vs_metric',
+            'roc_curves',
+            'roc_curves_from_test_statistics',
+            'calibration_1_vs_all',
+            'calibration_multiclass',
+            'confusion_matrix',
+            'frequency_vs_f1',
+        }
+        train_plots = {
+            'learning_curves',
+            'compare_classifiers_performance_subset',
+        }
+
+        # 1) find the most recent experiment directory
+        output_dir = Path(output_dir)
+        exp_dirs = sorted(
+            output_dir.glob("experiment_run*"),
+            key=lambda p: p.stat().st_mtime
+        )
+        if not exp_dirs:
+            logger.warning(f"No experiment run dirs found in {output_dir}")
+            return
+        exp_dir = exp_dirs[-1]
+
+        # 2) ensure viz output subfolder exists
+        viz_dir = exp_dir / "visualizations"
+        viz_dir.mkdir(exist_ok=True)
+        train_viz = viz_dir / "train"
+        test_viz = viz_dir / "test"
+        train_viz.mkdir(parents=True, exist_ok=True)
+        test_viz.mkdir(parents=True, exist_ok=True)
+
+        # 3) helper to check file existence
+        def _check(p: Path) -> Optional[str]:
+            return str(p) if p.exists() else None
+
+        # 4) gather standard Ludwig output files
+        training_stats = _check(exp_dir / "training_statistics.json")
+        test_stats = _check(exp_dir / TEST_STATISTICS_FILE_NAME)
+        probs_path = _check(exp_dir / PREDICTIONS_PARQUET_FILE_NAME)
+        gt_metadata = _check(exp_dir / "model" / TRAIN_SET_METADATA_FILE_NAME)
+
+        # 5) try to read original dataset & split file from description.json
+        dataset_path = None
+        split_file = None
+        desc = exp_dir / DESCRIPTION_FILE_NAME
+        if desc.exists():
+            with open(desc, "r") as f:
+                cfg = json.load(f)
+            dataset_path = _check(Path(cfg.get("dataset", "")))
+            split_file = _check(Path(get_split_path(cfg.get("dataset", ""))))
+
+        # 6) infer output feature name
+        output_feature = ""
+        if desc.exists():
+            try:
+                output_feature = cfg["config"]["output_features"][0]["name"]
+            except Exception:
+                pass
+        if not output_feature and test_stats:
+            with open(test_stats, "r") as f:
+                stats = json.load(f)
+            output_feature = next(iter(stats.keys()), "")
+
+        # 7) loop through every registered viz
+        viz_registry = get_visualizations_registry()
+        for viz_name, viz_func in viz_registry.items():
+            viz_dir_plot = None
+            if viz_name in train_plots:
+                viz_dir_plot = train_viz
+            elif viz_name in test_plots:
+                viz_dir_plot = test_viz
+
+            try:
+                viz_func(
+                    training_statistics=[training_stats] if training_stats else [],
+                    test_statistics=[test_stats] if test_stats else [],
+                    probabilities=[probs_path] if probs_path else [],
+                    output_feature_name=output_feature,
+                    ground_truth_split=2,
+                    top_n_classes=[0],
+                    top_k=3,
+                    ground_truth_metadata=gt_metadata,
+                    ground_truth=dataset_path,
+                    split_file=split_file,
+                    output_directory=str(viz_dir_plot),
+                    normalize=False,
+                    file_format="png",
+                )
+                logger.info(f"✔ Generated {viz_name}")
+            except Exception as e:
+                logger.warning(f"✘ Skipped {viz_name}: {e}")
+
+        logger.info(f"All visualizations written to {viz_dir}")
+
+    def generate_html_report(
+            self,
+            title: str,
+            output_dir: str,
+            config: dict,
+            split_info: str) -> Path:
+        """
+        Assemble an HTML report from visualizations under train_val/ and test/ folders.
+        """
+        cwd = Path.cwd()
+        report_name = title.lower().replace(" ", "_") + "_report.html"
+        report_path = cwd / report_name
+        output_dir = Path(output_dir)
+
+        # Find latest experiment dir
+        exp_dirs = sorted(output_dir.glob("experiment_run*"), key=lambda p: p.stat().st_mtime)
+        if not exp_dirs:
+            raise RuntimeError(f"No 'experiment*' dirs found in {output_dir}")
+        exp_dir = exp_dirs[-1]
+
+        base_viz_dir = exp_dir / "visualizations"
+        train_viz_dir = base_viz_dir / "train"
+        test_viz_dir = base_viz_dir / "test"
+
+        html = get_html_template()
+        html += f"<h1>{title}</h1>"
+
+        metrics_html = ""
+
+        # Load and embed metrics table (training/val/test stats)
+        try:
+            train_stats_path = exp_dir / "training_statistics.json"
+            test_stats_path = exp_dir / TEST_STATISTICS_FILE_NAME
+            if train_stats_path.exists() and test_stats_path.exists():
+                with open(train_stats_path) as f:
+                    train_stats = json.load(f)
+                with open(test_stats_path) as f:
+                    test_stats = json.load(f)
+                output_feature = next(iter(train_stats.keys()), "")
+                if output_feature:
+                    metrics_html += format_stats_table_html(train_stats, test_stats)
+        except Exception as e:
+            logger.warning(f"Could not load stats for HTML report: {e}")
+
+        config_html = ""
+        training_progress = self.get_training_process(output_dir)
+        try:
+            config_html = format_config_table_html(config, split_info, training_progress)
+        except Exception as e:
+            logger.warning(f"Could not load config for HTML report: {e}")
+
+        def render_img_section(title: str, dir_path: Path) -> str:
+            if not dir_path.exists():
+                return f"<h2>{title}</h2><p><em>Directory not found.</em></p>"
+            imgs = sorted(dir_path.glob("*.png"))
+            if not imgs:
+                return f"<h2>{title}</h2><p><em>No plots found.</em></p>"
+
+            section_html = f"<h2 style='text-align: center;'>{title}</h2><div>"
+            for img in imgs:
+                b64 = encode_image_to_base64(str(img))
+                section_html += (
+                    f'<div class="plot" style="margin-bottom:20px;text-align:center;">'
+                    f"<h3>{img.stem.replace('_',' ').title()}</h3>"
+                    f'<img src="data:image/png;base64,{b64}" '
+                    'style="max-width:90%;max-height:600px;border:1px solid #ddd;" />'
+                    "</div>"
+                )
+            section_html += "</div>"
+            return section_html
+
+        train_plots_html = render_img_section("Training & Validation Visualizations", train_viz_dir)
+        test_plots_html = render_img_section("Test Visualizations", test_viz_dir)
+        html += build_tabbed_html(config_html + metrics_html, train_plots_html, test_plots_html)
+        html += get_html_closing()
+
+        try:
+            with open(report_path, "w") as f:
+                f.write(html)
+            logger.info(f"HTML report generated at: {report_path}")
+        except Exception as e:
+            logger.error(f"Failed to write HTML report: {e}")
+            raise
+
+        return report_path
+
+
+class WorkflowOrchestrator:
+    """
+    Manages the image-classification workflow:
+      1. Creates temp dirs
+      2. Extracts images
+      3. Prepares data (CSV + splits)
+      4. Renders a backend config
+      5. Runs the experiment
+      6. Cleans up
+    """
+
+    def __init__(self, args: argparse.Namespace, backend: Backend):
+        self.args = args
+        self.backend = backend
+        self.temp_dir: Optional[Path] = None
+        self.image_extract_dir: Optional[Path] = None
+        logger.info(f"Orchestrator initialized with backend: {type(backend).__name__}")
+
+    def _create_temp_dirs(self) -> None:
+        """Create temporary output and image extraction directories."""
+        try:
+            self.temp_dir = Path(tempfile.mkdtemp(
+                dir=self.args.output_dir,
+                prefix=TEMP_DIR_PREFIX
+            ))
+            self.image_extract_dir = self.temp_dir / "images"
+            self.image_extract_dir.mkdir()
+            logger.info(f"Created temp directory: {self.temp_dir}")
+        except Exception:
+            logger.error("Failed to create temporary directories", exc_info=True)
+            raise
+
+    def _extract_images(self) -> None:
+        """Extract images from ZIP into the temp image directory."""
+        if self.image_extract_dir is None:
+            raise RuntimeError("Temp image directory not initialized.")
+        logger.info(f"Extracting images from {self.args.image_zip} → {self.image_extract_dir}")
+        try:
+            with zipfile.ZipFile(self.args.image_zip, "r") as z:
+                z.extractall(self.image_extract_dir)
+            logger.info("Image extraction complete.")
+        except Exception:
+            logger.error("Error extracting zip file", exc_info=True)
+            raise
+
+    def _prepare_data(self) -> Tuple[Path, Dict[str, Any]]:
+        """
+        Load CSV, update image paths, handle splits, and write prepared CSV.
+        Returns:
+            final_csv_path: Path to the prepared CSV
+            split_config: Dict for backend split settings
+        """
+        if not self.temp_dir or not self.image_extract_dir:
+            raise RuntimeError("Temp dirs not initialized before data prep.")
+
+        # 1) Load
+        try:
+            df = pd.read_csv(self.args.csv_file)
+            logger.info(f"Loaded CSV: {self.args.csv_file}")
+        except Exception:
+            logger.error("Error loading CSV file", exc_info=True)
+            raise
+
+        # 2) Validate columns
+        required = {IMAGE_PATH_COLUMN_NAME, LABEL_COLUMN_NAME}
+        missing = required - set(df.columns)
+        if missing:
+            raise ValueError(f"Missing CSV columns: {', '.join(missing)}")
+
+        # 3) Update image paths
+        try:
+            df[IMAGE_PATH_COLUMN_NAME] = df[IMAGE_PATH_COLUMN_NAME].apply(
+                lambda p: str((self.image_extract_dir / p).resolve())
+            )
+        except Exception:
+            logger.error("Error updating image paths", exc_info=True)
+            raise
+
+        # 4) Handle splits
+        if SPLIT_COLUMN_NAME in df.columns:
+            df, split_config, split_info = self._process_fixed_split(df)
+        else:
+            logger.info("No split column; using random split")
+            split_config = {
+                "type": "random",
+                "probabilities": self.args.split_probabilities
+            }
+            split_info = (
+                f"No split column in CSV. Used random split: "
+                f"{[int(p*100) for p in self.args.split_probabilities]}% for train/val/test."
+            )
+
+        # 5) Write out prepared CSV
+        final_csv = TEMP_CSV_FILENAME
+        try:
+            df.to_csv(final_csv, index=False)
+            logger.info(f"Saved prepared data to {final_csv}")
+        except Exception:
+            logger.error("Error saving prepared CSV", exc_info=True)
+            raise
+
+        return final_csv, split_config, split_info
+
+    def _process_fixed_split(self, df: pd.DataFrame) -> Dict[str, Any]:
+        """Process a fixed split column (0=train,1=val,2=test)."""
+        logger.info(f"Fixed split column '{SPLIT_COLUMN_NAME}' detected.")
+        try:
+            col = df[SPLIT_COLUMN_NAME]
+            df[SPLIT_COLUMN_NAME] = pd.to_numeric(col, errors="coerce").astype(pd.Int64Dtype())
+            if df[SPLIT_COLUMN_NAME].isna().any():
+                logger.warning("Split column contains non-numeric/missing values.")
+
+            unique = set(df[SPLIT_COLUMN_NAME].dropna().unique())
+            logger.info(f"Unique split values: {unique}")
+
+            if unique == {0, 2}:
+                df = split_data_0_2(
+                    df, SPLIT_COLUMN_NAME,
+                    validation_size=self.args.validation_size,
+                    label_column=LABEL_COLUMN_NAME,
+                    random_state=self.args.random_seed
+                )
+                split_info = (
+                    "Detected a split column (with values 0 and 2) in the input CSV. "
+                    f"Used this column as a base and"
+                    f"reassigned {self.args.validation_size * 100:.1f}% "
+                    "of the training set (originally labeled 0) to validation (labeled 1)."
+                )
+
+                logger.info("Applied custom 0/2 split.")
+            elif unique.issubset({0, 1, 2}):
+                split_info = "Used user-defined split column from CSV."
+                logger.info("Using fixed split as-is.")
+            else:
+                raise ValueError(f"Unexpected split values: {unique}")
+
+            return df, {"type": "fixed", "column": SPLIT_COLUMN_NAME}, split_info
+
+        except Exception:
+            logger.error("Error processing fixed split", exc_info=True)
+            raise
+
+    def _cleanup_temp_dirs(self) -> None:
+        """Remove any temporary directories."""
+        if self.temp_dir and self.temp_dir.exists():
+            logger.info(f"Cleaning up temp directory: {self.temp_dir}")
+            shutil.rmtree(self.temp_dir, ignore_errors=True)
+        self.temp_dir = None
+        self.image_extract_dir = None
+
+    def run(self) -> None:
+        """Execute the full workflow end-to-end."""
+        logger.info("Starting workflow...")
+        self.args.output_dir.mkdir(parents=True, exist_ok=True)
+
+        try:
+            self._create_temp_dirs()
+            self._extract_images()
+            csv_path, split_cfg, split_info = self._prepare_data()
+
+            use_pretrained = self.args.use_pretrained or self.args.fine_tune
+
+            backend_args = {
+                "model_name": self.args.model_name,
+                "fine_tune": self.args.fine_tune,
+                "use_pretrained": use_pretrained,
+                "epochs": self.args.epochs,
+                "batch_size": self.args.batch_size,
+                "preprocessing_num_processes": self.args.preprocessing_num_processes,
+                "split_probabilities": self.args.split_probabilities,
+                "learning_rate": self.args.learning_rate,
+                "random_seed": self.args.random_seed,
+                "early_stop": self.args.early_stop,
+            }
+            yaml_str = self.backend.prepare_config(backend_args, split_cfg)
+
+            config_file = self.temp_dir / TEMP_CONFIG_FILENAME
+            config_file.write_text(yaml_str)
+            logger.info(f"Wrote backend config: {config_file}")
+
+            self.backend.run_experiment(
+                csv_path,
+                config_file,
+                self.args.output_dir,
+                self.args.random_seed
+            )
+            logger.info("Workflow completed successfully.")
+            self.backend.generate_plots(self.args.output_dir)
+            report_file = self.backend.generate_html_report(
+                "Image Classification Results",
+                self.args.output_dir,
+                backend_args,
+                split_info
+            )
+            logger.info(f"HTML report generated at: {report_file}")
+            self.backend.convert_parquet_to_csv(self.args.output_dir)
+            logger.info("Converted Parquet to CSV.")
+        except Exception:
+            logger.error("Workflow execution failed", exc_info=True)
+            raise
+
+        finally:
+            self._cleanup_temp_dirs()
+
+
+def parse_learning_rate(s):
+    try:
+        return float(s)
+    except (TypeError, ValueError):
+        return None
+
+
+class SplitProbAction(argparse.Action):
+    def __call__(self, parser, namespace, values, option_string=None):
+        # values is a list of three floats
+        train, val, test = values
+        total = train + val + test
+        if abs(total - 1.0) > 1e-6:
+            parser.error(
+                f"--split-probabilities must sum to 1.0; "
+                f"got {train:.3f} + {val:.3f} + {test:.3f} = {total:.3f}"
+            )
+        setattr(namespace, self.dest, values)
+
+
+def main():
+
+    parser = argparse.ArgumentParser(
+        description="Image Classification Learner with Pluggable Backends"
+    )
+    parser.add_argument(
+        "--csv-file", required=True, type=Path,
+        help="Path to the input CSV"
+    )
+    parser.add_argument(
+        "--image-zip", required=True, type=Path,
+        help="Path to the images ZIP"
+    )
+    parser.add_argument(
+        "--model-name", required=True,
+        choices=MODEL_ENCODER_TEMPLATES.keys(),
+        help="Which model template to use"
+    )
+    parser.add_argument(
+        "--use-pretrained", action="store_true",
+        help="Use pretrained weights for the model"
+    )
+    parser.add_argument(
+        "--fine-tune", action="store_true",
+        help="Enable fine-tuning"
+    )
+    parser.add_argument(
+        "--epochs", type=int, default=10,
+        help="Number of training epochs"
+    )
+    parser.add_argument(
+        "--early-stop", type=int, default=5,
+        help="Early stopping patience"
+    )
+    parser.add_argument(
+        "--batch-size", type=int,
+        help="Batch size (None = auto)"
+    )
+    parser.add_argument(
+        "--output-dir", type=Path, default=Path("learner_output"),
+        help="Where to write outputs"
+    )
+    parser.add_argument(
+        "--validation-size", type=float, default=0.15,
+        help="Fraction for validation (0.0–1.0)"
+    )
+    parser.add_argument(
+        "--preprocessing-num-processes", type=int,
+        default=max(1, os.cpu_count() // 2),
+        help="CPU processes for data prep"
+    )
+    parser.add_argument(
+        "--split-probabilities", type=float, nargs=3,
+        metavar=("train", "val", "test"),
+        action=SplitProbAction,
+        default=[0.7, 0.1, 0.2],
+        help="Random split proportions (e.g., 0.7 0.1 0.2). Only used if no split column is present."
+    )
+    parser.add_argument(
+        "--random-seed", type=int, default=42,
+        help="Random seed used for dataset splitting (default: 42)"
+    )
+    parser.add_argument(
+        "--learning-rate", type=parse_learning_rate, default=None,
+        help="Learning rate. If not provided, Ludwig will auto-select it."
+    )
+
+    args = parser.parse_args()
+
+    # -- Validation --
+    if not 0.0 <= args.validation_size <= 1.0:
+        parser.error("validation-size must be between 0.0 and 1.0")
+    if not args.csv_file.is_file():
+        parser.error(f"CSV not found: {args.csv_file}")
+    if not args.image_zip.is_file():
+        parser.error(f"ZIP not found: {args.image_zip}")
+
+    # --- Instantiate Backend and Orchestrator ---
+    # Use the new LudwigDirectBackend
+    backend_instance = LudwigDirectBackend()
+    orchestrator = WorkflowOrchestrator(args, backend_instance)
+
+    # --- Run Workflow ---
+    exit_code = 0
+    try:
+        orchestrator.run()
+        logger.info("Main script finished successfully.")
+    except Exception as e:
+        logger.error(f"Main script failed.{e}")
+        exit_code = 1
+    finally:
+        sys.exit(exit_code)
+
+
+if __name__ == '__main__':
+    try:
+        import ludwig
+        logger.debug(f"Found Ludwig version: {ludwig.globals.LUDWIG_VERSION}")
+    except ImportError:
+        logger.error("Ludwig library not found. Please ensure Ludwig is installed ('pip install ludwig[image]')")
+        sys.exit(1)
+
+    main()
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/image_classification_results_report_mnist.html	Tue Jun 03 21:22:11 2025 +0000
@@ -0,0 +1,129 @@
+
+    <html>
+    <head>
+        <title>Galaxy-Ludwig Report</title>
+        <style>
+          body {
+              font-family: Arial, sans-serif;
+              margin: 0;
+              padding: 20px;
+              background-color: #f4f4f4;
+          }
+          .container {
+              max-width: 800px;
+              margin: auto;
+              background: white;
+              padding: 20px;
+              box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
+              overflow-x: auto;
+          }
+          h1 {
+              text-align: center;
+              color: #333;
+          }
+          h2 {
+              border-bottom: 2px solid #4CAF50;
+              color: #4CAF50;
+              padding-bottom: 5px;
+          }
+          table {
+              border-collapse: collapse;
+              margin: 20px 0;
+              width: 100%;
+              table-layout: fixed; /* Enforces consistent column widths */
+          }
+          table, th, td {
+              border: 1px solid #ddd;
+          }
+          th, td {
+              padding: 8px;
+              text-align: center; /* Center-align text */
+              vertical-align: middle; /* Center-align content vertically */
+              word-wrap: break-word; /* Break long words to avoid overflow */
+          }
+          th:first-child, td:first-child {
+              width: 5%; /* Smaller width for the first column */
+          }
+          th:nth-child(2), td:nth-child(2) {
+              width: 50%; /* Wider for the metric/description column */
+          }
+          th:last-child, td:last-child {
+              width: 25%; /* Value column gets remaining space */
+          }
+          th {
+              background-color: #4CAF50;
+              color: white;
+          }
+          .plot {
+              text-align: center;
+              margin: 20px 0;
+          }
+          .plot img {
+              max-width: 100%;
+              height: auto;
+          }
+        </style>
+    </head>
+    <body>
+    <div class="container">
+    <h1>Image Classification Results</h1>
+<style>
+.tabs {
+  display: flex;
+  border-bottom: 2px solid #ccc;
+  margin-bottom: 1rem;
+}
+.tab {
+  padding: 10px 20px;
+  cursor: pointer;
+  border: 1px solid #ccc;
+  border-bottom: none;
+  background: #f9f9f9;
+  margin-right: 5px;
+  border-top-left-radius: 8px;
+  border-top-right-radius: 8px;
+}
+.tab.active {
+  background: white;
+  font-weight: bold;
+}
+.tab-content {
+  display: none;
+  padding: 20px;
+  border: 1px solid #ccc;
+  border-top: none;
+}
+.tab-content.active {
+  display: block;
+}
+</style>
+
+<div class="tabs">
+  <div class="tab active" onclick="showTab('metrics')"> Config & Metrics</div>
+  <div class="tab" onclick="showTab('trainval')"> Train/Validation Plots</div>
+  <div class="tab" onclick="showTab('test')"> Test Plots</div>
+</div>
+
+<div id="metrics" class="tab-content active">
+  <h2 style='text-align: center;'>Training Setup</h2><div style='display: flex; justify-content: center;'><table style='border-collapse: collapse; width: 60%; table-layout: auto;'><thead><tr><th style='padding: 10px; border: 1px solid #ccc; text-align: left;'>Parameter</th><th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Value</th></tr></thead><tbody><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Model Name</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>resnet18</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Epochs</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>Because of early stopping: the trainingstopped at epoch 7</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Batch Size</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>Auto-selected batch size by Ludwig:<br><span style='font-size: 0.85em;'>16</span><br></td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Fine Tune</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>True</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Use Pretrained</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>True</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Learning Rate</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>Auto-selected learning rate by Ludwig:<br><span style='font-size: 0.85em;'>1e-05</span><br><span style='font-size: 0.85em;'>Based on model architecture and training setup (e.g., fine-tuning).<br>See <a href='https://ludwig.ai/latest/configuration/trainer/#trainer-parameters' target='_blank'>Ludwig Trainer Parameters</a> for details.</span></td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Random Seedearly Stop</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>N/A</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>Data Split</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>Detected a split column (with values 0 and 2) in the input CSV. Used this column as a base andreassigned 15.0% of the training set (originally labeled 0) to validation (labeled 1).</td></tr></tbody></table></div><br><p style='text-align: center; font-size: 0.9em;'>Model trained using Ludwig.<br>If want to learn more about Ludwig default settings,please check the their <a href='https://ludwig.ai' target='_blank'>website(ludwig.ai)</a>.</p><hr><h2 style='text-align: center;'>Model Performance Summary</h2><div style='display: flex; justify-content: center;'><table style='border-collapse: collapse; width: 80%; table-layout: fixed;'><colgroup><col style='width: 40%;'><col style='width: 20%;'><col style='width: 20%;'><col style='width: 20%;'></colgroup><thead><tr><th style='padding: 10px; border: 1px solid #ccc; text-align: left;'>Metric</th><th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Train</th><th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Validation</th><th style='padding: 10px; border: 1px solid #ccc; text-align: center;'>Test</th></tr></thead><tbody><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>accuracy</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.8417</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.1500</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.2000</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>accuracy_micro</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.8471</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.2000</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.2000</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>hits_at_k</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.9250</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.4500</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.3000</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>loss</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.6749</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>2.7907</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>2.8261</td></tr><tr><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: left;'>roc_auc</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.9998</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.7824</td><td style='padding: 6px 12px; border: 1px solid #ccc; text-align: center;'>0.6917</td></tr></tbody></table></div><br>
+</div>
+<div id="trainval" class="tab-content">
+  <h2 style='text-align: center;'>Training & Validation Visualizations</h2><div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Learning Curves Label Accuracy</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Learning Curves Label Hits At K</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Learning Curves Label Loss</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div></div>
+</div>
+<div id="test" class="tab-content">
+  <h2 style='text-align: center;'>Test Visualizations</h2><div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Compare Classifiers Multiclass Multimetric  Label Best10</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Compare Classifiers Multiclass Multimetric  Label Sorted</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Compare Classifiers Multiclass Multimetric  Label Top10</h3><img src="data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAoAAAAHgCAYAAAA10dzkAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjguNCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8fJSN1AAAACXBIWXMAAA9hAAAPYQGoP6dpAABPN0lEQVR4nO3dd3QU9eL+8SdZEkKTEgJCaAImISQxQYoUKREBQ1GCgECoEZSqV7kUQQXEG0RAwHJFgSCINCF0UIEvTQGRIgEp0quU0GtgM78/+GUvawopGzZx3q9zOIfMfmbm2dlZ8jBl18UwDEMAAAAwDVdnBwAAAMCjRQEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhADrRli1b5Ovrqy1btjx07MmTJ+Xr66sFCxakax0LFiyQr6+vTp48mdGY/3gZ3bYdO3ZUx44dsyiVefj6+urTTz+1/cw+i0cto+/lxH87pkyZ4rAs6fm9AGQGBTAFiW9sX19fffHFF8mOefvtt+Xr66uQkBCHrXfJkiWaNm2aw5aXXYWGhtq2r6+vr2rWrKn27dvrp59+cna0HCU8PFzDhg1L8fHEMpX4x9/fX88++6wGDRqks2fPPrqgWejKlSvy9/fX8uXLUxwzaNAgu+3w4J/169fbxn333Xfq16+f6tevL19fXw0aNChdWU6ePKnBgwerYcOGCgwMVO3atdWhQwdNnDgxw8/PWdatW2dXzJ0hPa/H1atX9e677+qZZ55RcHCwOnbsqD179jzCtEDOksvZAbK73Llza9myZerVq5fd9Js3b2rNmjXKnTu3Q9e3dOlS/fnnn+rSpYvddG9vb+3atUu5cv1zXrJKlSqpa9eukqRz585pzpw56tOnj4YNG6Z27do9shwZ3baO/F9/Rpw7d05//PGH+vXr99Cx/fr1U6lSpRQfH6+dO3cqJiZG27Zt09KlSx2+Dz9qGzdulIuLi+rUqZPqOHd3d40cOTLJdD8/P9vfJ0+erBs3bigwMFDnz59PV45jx47p5ZdfVu7cudWqVSuVKlXK9hp9/fXXaXqdspN169Zp5syZ6tu3r9MypPX1SEhIUI8ePbR//35FRkaqcOHC+u6779SxY0ctWLBA5cqVe3ShgRzin9Mmski9evX0448/at++fXa/KFavXq27d++qTp06j+RQvYuLS47/Rf13xYsX14svvmj7+aWXXlKjRo00bdq0FAvgvXv3lJCQIHd3d4flyOi2dWSGjFi/fr1y586tZ5555qFj69atq8DAQElS69atVbhwYX399ddavXq1wsLCsjpqllq3bp2qVKmixx57LNVxuXLlstvfkjNjxgyVLFlSLi4u6T6yP23aNN28eVMLFy6Ut7e33WNxcXHpWlZm3bx5U3nz5n2k68wKaX09Vq5cqR07dmjChAlq0qSJJOmFF15Q48aN9emnn2rs2LGPKjKQY3AK+CGCg4NVqlQpLVmyxG76kiVLVKdOHRUqVCjJPH+/pilRaGhoqqcwOnbsqLVr1+rUqVO201OhoaGSUr5O7dChQ3rjjTf0zDPPKCgoSI0bN9Ynn3yS6nNatWqVevTooTp16iggIEANGzbU559/LqvVajfu6NGj6tu3r2rXrq3AwEDVrVtX//rXv3Tt2jXbmJ9//lnt2rVT1apVFRISosaNG2vcuHGprj8lXl5eKl++vE6dOmX3nKdMmaJp06bZTqsdOnTI9tz79eun6tWrKzAwUOHh4Vq9enWS5V69elX/+c9/FBoaqoCAANWtW1cDBgzQxYsX7dbz4LY9f/68Bg8erLp16yogIEB16tRRz5497a5LS+66obi4OL3zzjuqVauWAgMD1aJFC8XExNiNefB5zZkzRw0bNlRAQIBatWqlXbt2pXl7rVu3TjVq1JCHh0ea50lUtWpVSdKJEyfspjtqm8bHx2vChAkKDw/X008/reDgYLVv316bN29Od9bUJCQkaMOGDapXr55Dluft7S0XF5cMzXv8+HEVL148SfmTJE9PzyTT1q1bp4iICIWEhKhKlSpq1apVkn9nVqxYofDwcAUFBalGjRrq379/klP3gwYNUkhIiI4fP67u3bsrJCRE/fv3l3R/+0ybNk1NmzZVYGCgatWqpffee09XrlxJ9bkMGjRIM2fOlCS70+WJbt68qVGjRqlevXoKCAhQ48aNNWXKFBmGYbccX19fjRgxQosXL1bjxo1t+9TWrVtTXX+itL4eP/zwg4oWLapGjRrZphUpUkQvvPCCVq9erfj4+DStL1FG9t9p06apQYMGCgoKUkREhA4cOJBkTFrfX8CjwBHANGjWrJkWL16s/v37y8XFRRcvXtTPP/+s0aNHa8OGDQ5bz+uvv65r167pr7/+0uDBgyVJ+fLlS3H8vn371KFDB+XKlUtt27aVt7e3jh8/rjVr1uhf//pXivPFxMQob9686tq1q/LmzavNmzdr4sSJun79ugYOHCjp/j+AkZGRio+PV0REhIoWLaqzZ89q7dq1unr1qgoUKKA///xTr732mnx9fdWvXz+5u7vr2LFj2r59e4ae/927d/XXX38lKdULFizQnTt31KZNG7m7u6tgwYL6888/1a5dOxUvXlzdu3dX3rx5tWLFCvXu3Vuffvqpnn/+eUnSjRs31KFDBx06dEitWrWSv7+/Ll26pDVr1ujs2bMqUqRIsln69u2rgwcPKiIiQt7e3rbX/MyZMypVqlSy89y+fVsdO3bU8ePH1aFDB5UqVUorV67UoEGDdPXqVXXu3Nlu/NKlS3Xjxg21bdtWLi4umjx5svr27atVq1bJzc3todvql19+0VtvvZXGrWsvsWQ/eNTMkdv0+vXrmjdvnpo1a6bWrVvrxo0b+v777/Xqq69q3rx5qlSpUoZy/11sbKwuXryY5gKYWFATubm5qUCBAg7J4u3trU2bNmnTpk2qWbNmqmMXLFigd955R08++aRee+01FShQQHv37tWGDRvUvHlz25jBgwcrMDBQb731luLi4jR9+nRt375dCxcutHvt7t27p8jISD399NMaOHCg7T8F7733nmJiYhQeHq6OHTvq5MmTmjlzpv744w/NmjUrxf2sbdu2OnfunO3fuQcZhqGePXtqy5Ytevnll1WpUiVt2LBBo0eP1tmzZ/XOO+/Yjd+6dauWL1+ujh07yt3dXbNmzbLtBz4+PunezsnZu3ev/P395epqf0wjMDBQc+bM0ZEjR+wK7MOkd/9duHChbty4ofbt2+vOnTuaMWOGOnfurCVLlqho0aKS0v7+Ah4ZA8k6ceKE4ePjY0yePNk4cOCA4ePjY2zdutUwDMP49ttvjeDgYOPmzZvGwIEDjeDgYLt5fXx8jIkTJyZZZoMGDYyBAwfaft68ebPh4+NjbN682TatR48eRoMGDVLMM3/+fNu0Dh06GCEhIcapU6fsxiYkJNj+Pn/+fMPHx8c4ceKEbdqtW7eSLP/dd981nnrqKePOnTuGYRjGH3/8Yfj4+BgrVqxIfgMZhhEdHW34+PgYcXFxKY5JSYMGDYxu3boZcXFxRlxcnLF3717jX//6l+Hj42N88MEHds+5SpUqSdbRuXNno1mzZra8ic+7bdu2RqNGjWzTJkyYYPj4+Bg//vhjkgyJ2+nv2/bKlSu21z41ERERRkREhO3nadOmGT4+PsaiRYts0+Lj4422bdsawcHBxrVr1+zWV716dePy5cu2satWrTJ8fHyMNWvWpL7xDMP45ZdfkryuyUl8/X/55RcjLi7OOHPmjLFy5UrjmWeeMQICAowzZ87Yxjpym967d89uOYZxf7vWqlXLGDx4sN30v79fkttnUzJ+/Phk3y9/N3DgQMPHxyfJnwdfv78LDg62e78+zIEDB4ygoCDDx8fHePHFF42RI0caP/30k3Hz5k27cVevXjVCQkKM1q1bG7dv37Z7LHH7xcfHGzVr1jSaNWtmN+b//u//DB8fH2PChAlJntuYMWPslrV161bDx8fHWLx4sd309evXJzv974YPH274+Pgkmf7TTz8ZPj4+xhdffGE3vW/fvoavr69x7Ngx27TE7RwbG2ubdurUKSMwMNDo3bt3quv/u9Rej+Dg4CT7lWEYxtq1aw0fHx9j/fr1qS777+/ltO6/ie/loKAg46+//rJN//333w0fHx/jP//5j21aWt9fyf1eALICp4DT4Mknn5Svr6+WLVsm6f6Rm+eee0558uRxWqaLFy9q69atatWqlUqWLGn32MNOmTx4yvD69eu6ePGiqlatqlu3bunw4cOSpPz580u6f4H9rVu3kl1O4hGI1atXKyEhId3PYePGjapZs6Zq1qypF198UStXrtSLL75oO32VqFGjRnZH6i5fvqzNmzfrhRdesOW/ePGiLl26pDp16ujo0aO202Q//vij/Pz8kv3fdUrbycPDQ25ubvr1118feqrsQevXr5eXl5eaNWtmm+bm5qaOHTvq5s2bSU57hYWFqWDBgrafUzotm9K6KlasmOLRyL/r0qWLatasqXr16qlfv37KkyeP/vvf/+rxxx+X5PhtarFYbNdIJiQk6PLly7p3754CAgL0xx9/pClzWqxbty7NR/9y586t6Ohouz+JR7wd4cknn9TChQvVokULnTp1StOnT1fv3r1Vq1YtzZ071zbu559/1o0bN9SjR48k154mbr/du3crLi5O7dq1sxtTv359lS9fXmvXrk2y/r9fN7ty5UoVKFBAtWvXtr2eFy9eVOXKlZU3b94MX7u8fv16WSyWJJc/dOvWTYZh2N1VLUkhISEKCAiw/VyyZEk999xz2rhxY5LLTjLq9u3byV6Tmzjtzp076Vpeevffhg0bqnjx4rafg4KC9NRTT2ndunWS0vf+Ah4VTgGnUbNmzRQdHa0uXbpox44dev31152aJ7EkZOQUyp9//qnx48dr8+bNun79ut1jidf3lS5dWl27dlV0dLSWLFmiqlWrKjQ0VC1atLCdMgsLC9O8efM0dOhQjR07VjVr1tTzzz+vJk2aJDkVk5ynnnpKb775plxcXOTh4aEKFSokeyH/30vO8ePHZRiGJkyYoAkTJiS77Li4OBUvXlzHjx+3uy4oLdzd3dW/f3999NFHql27tp566inVr19fL730kry8vFKc79SpUypbtmyS516hQgVJ0unTp+2mlyhRwu7nxDJ49erVh2Zcu3atGjRokKbnI90/FfjEE0/o2rVrmj9/vrZu3Wr3CzMrtmlMTIymTp2qI0eO6O7du7bpaS2tD3P+/Hn98ccfeuONN9I03mKxqFatWg5Zd0qeeOIJffzxx7JarTp48KDWrl2ryZMn691331WpUqVUq1YtHT9+XNL9wpiSxH3liSeeSPJY+fLltW3bNrtpuXLlspX5RMeOHdO1a9dSPB2d0RtTTp06pWLFitn+k5gocT9PvLwgUdmyZZMso1y5crp165YuXryY6nsqrTw8PJK9zi9xWkZu8krP/pvSc1yxYoWk9L2/gEeFAphGzZo107hx4zR06FAVKlRItWvXTvcyHPW/3cy4evWqIiIilD9/fvXr109lypRR7ty5tWfPHo0ZM8buSN6gQYPUsmVLrV69Wj///LNGjhypSZMmae7cuXr88cfl4eGhmTNnasuWLVq7dq02bNig5cuXa86cOZo6daosFkuqWQoXLpymX8h/v8khMWO3bt307LPPJjtPmTJlHrrc1HTp0kWhoaFatWqVNm7cqAkTJuirr77SN998I39//0wtO1FK28f424X0f3fixAkdPnw41c//+7ugoCDbXcANGzZU+/bt9fbbb2vlypXKly+fw7fpokWLNGjQIDVs2FCRkZHy9PSUxWLRpEmT0nSEMy0S74KuUaOGQ5bnSBaLxXbjRHBwsDp16qQlS5ZkWQF1d3dP8h+PhIQEeXp6asyYMcnOk9L1rzmRl5dXsh8Tc+7cOUlSsWLF0rU8R++/j+LfLCC9KIBpVLJkSVWpUkW//vqr2rVrl+pnxhUsWDDJUZz4+Pg0fa5YWu9ALF26tCQle6dZan799VddvnxZn332mapVq2abntK3LiT+EuvVq5e2b9+udu3aadasWbabTFxdXW2ncQcPHqwvv/xSn3zyibZs2ZJlv+wSn7ubm9tD11GmTBn9+eefGVpPmTJl1K1bN3Xr1k1Hjx7VSy+9pKlTp6b4C9Xb21v79+9XQkKC3S/jxNPqfz9Vn1Hr1q1TgQIF9PTTT2dofovForfeekudOnXSzJkz1aNHD4dv0x9++EGlS5fWZ599ZrdPO/IDkTNzF/SjlHj6M7GMJP6i//PPP5M9ciT9b185cuRIkiN4R44cSdO+VKZMGW3atElVqlTJ0DZK6d+ixJtdrl+/bncUMHE///td0MeOHUuyjKNHjypPnjwOK6F+fn7atm1bkvferl27lCdPnmSPpKYmvftvSs8xcVuk5/0FPCpcA5gOb775pvr06fPQrwwqXbq0fvvtN7tpc+fOTdMRwDx58th9zEpKihQpomrVqmn+/PlJTi2mdgQp8R/HB8fEx8fru+++sxt3/fp13bt3z26aj4+PXF1dbadVLl++nGT5iXfHpfdjF9LD09NT1atX15w5c2y/VB/04J2ejRo10r59+5L9hpGUttOtW7eSXDNUpkwZ5cuXL9XnVbduXZ0/f97uGynu3bunGTNmKG/evHaFOzPWrVun2rVrZ+pDwWvUqKGgoCB98803unPnjsO3aeLRzQe38e+//66dO3dmOPOD7t69q59//tlhH//iCL/99pvdqcJEideBJZaQOnXqKF++fJo0aVKS/SxxewUEBMjT01OzZ8+22+fWrVunQ4cOqX79+g/N88ILL8hqtSb7TUb37t176KUGidc4/31c3bp1ZbVabR8Tk2jatGlycXFR3bp17abv2LHD7hs5zpw5o9WrV6t27doPPUuQVk2aNNGFCxf0448/2qZdvHhRK1euVIMGDdL9mZ3p3X9XrVpldw3frl279Pvvv9u2RXreX8CjwhHAdKhevbqqV6/+0HGtW7fW+++/r759+6pWrVrat2+fNm7cqMKFCz903sqVK2v58uWKiopSYGCg8ubNa/sswL8bOnSo2rVrp5YtW6pt27YqVaqUTp06pbVr12rRokXJzhMSEqKCBQtq0KBB6tixo1xcXLRo0aIkZWjz5s0aMWKEmjRponLlyslqtWrRokWyWCxq3LixJOnzzz/Xb7/9pnr16snb21txcXH67rvv9Pjjj2f46FRavf/++2rfvr2aN2+uNm3aqHTp0rpw4YJ27typv/76S4sXL5YkRUZG6ocfftAbb7yhVq1aqXLlyrpy5YrWrFmj4cOH2324d6KjR4+qS5cuatKkiSpWrCiLxaJVq1bpwoULatq0aYqZ2rZtqzlz5mjQoEHas2ePvL299cMPP2j79u165513klwzlRG3b9/Wli1bNHz48EwvKzIyUm+88YYWLFigdu3aOXSb1q9fXz/++KN69+6t+vXr6+TJk5o9e7YqVqyomzdvZjr7tm3bdP369TQVofRYs2aN9u3bJ+l+ydy/f7+tQIWGhia7vyT6+uuvtWfPHj3//PO2jxz5448/tHDhQhUqVMj2MUD58+fX4MGDNXToUL388stq1qyZHnvsMe3bt0+3b9/WRx99JDc3N/Xv31+DBw9WRESEmjZtavsYGG9v7yTfFJSc6tWrq23btpo0aZL27t2r2rVry83NTUePHtXKlSs1ZMgQ24cmJ6dy5cqSpJEjR6pOnTqyWCxq2rSpQkNDVaNGDX3yySe2zyz9+eeftXr1anXu3DnJqUwfHx9FRkbafQyMpDR9w0haX4/GjRsrODhYgwcP1sGDB1W4cGHNmjVLVqs1Q99kkt79t0yZMmrXrp3atWun+Ph4TZ8+XYUKFdKrr75qG5PW9xfwqFAAs0CbNm108uRJff/999qwYYOefvpp2w0kD9O+fXvt3btXCxYs0LRp0+Tt7Z1iAfTz89PcuXM1YcIEzZo1S3fu3FHJkiX1wgsvpLj8woUL68svv9RHH32k8ePH67HHHlOLFi1Us2ZNRUZG2sb5+vqqTp06+r//+z+dPXtWefLkka+vr77++msFBwdLuv8P8KlTpzR//nxdunRJhQsXVvXq1dW3b1+HfbZaSipWrKj58+frs88+U0xMjC5fvqwiRYrI399fvXv3to3Lly+fZs6cqU8//VQ//fSTYmJi5OnpqZo1a6Z4wfXjjz+upk2batOmTVq8eLEsFovKly+v8ePH28pvcjw8PDRjxgyNGTNGMTExun79up544glFRUUpPDzcIc978+bNio+PT3KUJSMaNWqkMmXKaOrUqWrTpo1Dt2l4eLguXLigOXPmaOPGjapYsaI+/vhjrVy5Ur/++mums69bt04VK1ZM9kOXM+PHH3+0++DuP/74w3bX5+OPP55qAXzttde0dOlSbd26VUuWLNHt27fl5eWlpk2bqlevXrbTgNL9/yR6enrqq6++0hdffKFcuXKpfPnydv9GhIeHy8PDQ19//bXGjBmjvHnzqmHDhvr3v//90G89STRixAgFBARo9uzZ+uSTT2SxWOTt7a0WLVqoSpUqqc7bqFEjdezYUcuWLdPixYtlGIaaNm0qV1dX/fe//9XEiRO1fPlyLViwQN7e3howYIC6deuWZDnVqlVTcHCwPv/8c50+fVoVK1ZUVFRUqtsyUVpfD4vFoq+++kqjR4/WjBkzdOfOHQUGBioqKkrly5dP07Z6UHr335deekmurq765ptvFBcXp6CgIL377rt21x6m9f0FPCouxsOuOAeQbQwbNky7d+/W999/7+woThUWFqb69etrwIABzo6CVPj6+qpDhw567733nB0FwN9wBBDIQSpVqpSuj3/5J4qPj1dYWFiqR7oBAKmjAAI5SNu2bZ0dwenc3d3Vp08fZ8cAgByNu4ABAABMhmsAAQAATIYjgAAAACZDAQQAADCZHHsTSEJCgu7duydXV9c0f30aAABmYRiGEhISlCtXriTfFQ3k2AJ47949xcbGOjsGAADZWmBgYLq/Dg//fDm2ACb+byYwMNBh3yfpSFarVbGxsdk2XyJyOhY5HYucjpVTcko5J2t2zpmYjaN/SE6OLYCJp30tFku2e9M9KLvnS0ROxyKnY5HTsXJKTinnZM3OOblMCsnhvwUAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyTikAG7dulWvv/666tSpI19fX61ateqh82zZskUtW7ZUQECAnn/+eS1YsMARUQAAAPAQDimAN2/elK+vr95///00jT9x4oRee+011ahRQ4sWLVLnzp01dOhQbdiwwRFxAAAAkIpcjlhIvXr1VK9evTSPnz17tkqVKqVBgwZJkipUqKBt27Zp2rRpevbZZx0RCQAAAClwyjWAO3fuVM2aNe2m1alTRzt37nRGHAAAAFNxyBHA9Lpw4YKKFi1qN61o0aK6fv26bt++LQ8PjzQvy2q1OjqeQyTmyq75EiUkJChPnjxKSEhwdpRU5ZTtSU7HIqdj5ZScUs7Jmp1zZsdMyD6cUgAdKTY21tkRUpUd8rm5uSnAv5Jcc7klecxiscjf3z/Z+RLu3dXuP/bq7t27WR0xzbLD9kwLcjoWOR0rp+SUck7WnJITSOSUAli0aFFduHDBbtqFCxeUP3/+dB39k6TAwEBZLBZHxnMIq9Wq2NjYbJPP1WKR5r8qXTiQthmK+si11WRVrlw5a4OlUXbbnikhp2OR07FySk4p52TNzjkTswHJcUoBDA4O1vr16+2m/fLLLwoODk73siwWS7Z70z0oW+W7cEA683u6Zsk22f+/bLU9U0FOxyKnY+WUnFLOyZpTcgKJHHITyI0bN7R3717t3btXknTy5Ent3btXp0+fliSNHTtWAwYMsI1/5ZVXdOLECY0ePVqHDh3SzJkztWLFCnXp0sURcQAAAJAKhxwB3L17tzp16mT7OSoqSpLUsmVLjRo1SufPn9eZM2dsj5cuXVqTJk1SVFSUpk+frscff1wjR47kI2AAAAAeAYcUwBo1amj//v0pPj5q1Khk51m4cKEjVg8AAIB04LuAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGQogAACAyTisAM6cOVOhoaEKDAxU69attWvXrlTHT5s2TY0bN1ZQUJDq1aun//znP7pz546j4gAAACAFDimAy5cvV1RUlHr37q2YmBj5+fkpMjJScXFxyY5fsmSJxo4dqz59+mj58uX68MMPtXz5co0bN84RcQAAAJAKhxTA6OhotWnTRq1atVLFihU1fPhweXh4aP78+cmO37Fjh6pUqaLmzZurVKlSqlOnjpo1a/bQo4YAAADIvFyZXUB8fLz27Nmj1157zTbN1dVVtWrV0o4dO5KdJyQkRIsXL9auXbsUFBSkEydOaN26dXrxxRfTvX6r1Zrh7FkpMVd2yWexWDI0X3bJn922Z0rI6VjkdKycklPKOVmzc87smAnZR6YL4KVLl2S1WuXp6Wk33dPTU4cPH052nubNm+vSpUtq3769DMPQvXv39Morr+j1119P9/pjY2MzlPtRyQ758uTJI39//wzNu3//ft26dcvBiTIuO2zPtCCnY5HTsXJKTinnZM0pOYFEmS6AGbFlyxZNmjRJ77//voKCgnT8+HF9+OGH+vzzz9W7d+90LSswMDDDR7eyktVqVWxsbLbNl1a+vr7OjiAp52xPcjoWOR0rp+SUck7W7JwzMRuQnEwXwMKFC8tisSS54SMuLk5FixZNdp4JEyaoRYsWat26taT7JePmzZt677331LNnT7m6pv3SRIvFku3edA/K7vkeJrtlzynbk5yORU7Hyik5pZyTNafkBBJl+iYQd3d3Va5cWZs2bbJNS0hI0KZNmxQSEpLsPLdv305S8hLfOIZhZDYSAAAAUuGQU8Bdu3bVwIEDFRAQoKCgIH3zzTe6deuWwsPDJUkDBgxQ8eLF9fbbb0uSGjRooOjoaPn7+9tOAU+YMEENGjTgf1AAAABZzCEFMCwsTBcvXtTEiRN1/vx5VapUSZMnT7adAj5z5ozdEb+ePXvKxcVF48eP19mzZ1WkSBE1aNBA//rXvxwRBwAAAKlw2E0gERERioiISPaxGTNm2K80Vy716dNHffr0cdTqAQAAkEZ8FzAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmEwuZwcAAADOYRiG7t27J6vV6uwoSAeLxaJcuXLJxcUlw8ugAAIAYELx8fE6c+aMbt686ewoyIC8efOqRIkScnd3z9D8DiuAM2fO1JQpU3T+/Hn5+fnp3XffVVBQUIrjr169qk8++UQ//fSTLl++LG9vb73zzjuqV6+eoyIBAIBkJCQk6MiRI7JYLCpZsqTc3d0zdTQJj45hGIqPj9f58+d15MgRPfnkk3J1Tf8VfQ4pgMuXL1dUVJSGDx+up556St98840iIyO1cuVKeXp6JhkfHx+vrl27ytPTUxMmTFDx4sV1+vRpPfbYY46IAwAAUhEfH6+EhASVLl1aefPmdXYcpFOePHnk5uamY8eOKT4+Xh4eHulehkMKYHR0tNq0aaNWrVpJkoYPH661a9dq/vz56tGjR5Lx8+fP15UrVzR79my5ublJkkqVKuWIKAAAII0ycuQI2UNmX7tMF8D4+Hjt2bNHr732ml2oWrVqaceOHcnOs2bNGgUHB2vEiBFavXq1ihQpombNmql79+6yWCzpWn92vXA1MVd2yZfe7Zoou+TPbtszJeR0LHI6Vk7JKeWcrNk5Z3bMhOwj0wXw0qVLslqtSU71enp66vDhw8nOc+LECW3evFnNmzfXV199pePHj2v48OG6d++e+vTpk671x8bGZjj7o5Ad8uXJk0f+/v4Zmnf//v26deuWgxNlXHbYnmlBTscip2PllJxSzsmaU3IiY7Zs2aJOnTpp69atD71cLT1jnckpdwEbhiFPT0998MEHslgsCggI0NmzZzVlypR0F8DAwMAMH93KSlarVbGxsdk2X1r5+vo6O4KknLM9yelY5HSsnJJTyjlZs3POxGzpni/BkMX10d0Q8qjXlxEhISHauHGjChQo4NCxzpTpAli4cGFZLBbFxcXZTY+Li1PRokWTncfLy0u5cuWye7OUL19e58+fV3x8fLpuabZYLNnuTfeg7J7vYbJb9pyyPcnpWOR0rJySU8o5WXNKzrSwuLrojdk7dPDc9SxfV8Vi+TXhlZAsXUd6e0Vy3N3d5eXl5fCxzpTpAuju7q7KlStr06ZNatiwoaT7t5dv2rRJERERyc5TpUoVLV26VAkJCbaLGI8ePSovL69Mv0gAACBzDp67rj2nrzo7RrI6duyoJ598UpK0aNEi5cqVS+3atdMbb7whFxcXhYaGqlWrVjp27JhWrVqlRo0aadSoUfrtt980btw47d69W4ULF9bzzz+vt956y3YXdHx8vCZMmKClS5cqLi5OJUqUUI8ePdS6deskp3VPnTqlDz74QNu2bdPdu3fl7e2tAQMGqF69esmeAv7hhx80ceJEHTt2TMWKFVNERIS6detme06hoaFq06aNjh07ppUrV6pgwYLq2bOn2rZtm2Xb0SG3/3Tt2lVz585VTEyMDh06pGHDhunWrVsKDw+XJA0YMEBjx461jW/Xrp0uX76sDz/8UEeOHNHatWs1adIkdejQwRFxAADAP1hMTIwsFovmzZunIUOGaNq0aZo3b57t8alTp8rPz08LFy5Ur169dPz4cXXv3l2NGjXS4sWL9cknn2jbtm364IMPbPMMGDBAy5Yt09ChQ7VixQqNGDFC+fLlS3b9I0aMUHx8vL799lstWbJE/fv3T/HjdHbv3q0333xTYWFhWrJkifr06aMJEyZowYIFduOio6MVEBCghQsXqn379ho2bFiK91I4gkOuAQwLC9PFixc1ceJEnT9/XpUqVdLkyZNtp4DPnDljd7tyiRIlNGXKFEVFRalFixYqXry4OnXqpO7duzsiDgAA+AcrUaKE3nnnHbm4uKh8+fI6cOCApk2bpjZt2kiSnnnmGbsjbEOGDFHz5s3VpUsXSVK5cuU0ZMgQdezYUcOGDdPp06e1YsUKRUdHq1atWpKk0qVLp7j+06dPq3Hjxrbr5FMbGx0drZo1a6p3796SpCeeeEIHDx7UlClTbAfKJKlu3bq2A2Hdu3fXtGnTtGXLFpUvXz4DW+jhHHYTSERERIqnfGfMmJFkWkhIiObOneuo1QMAAJN46qmn7L65JDg4WNHR0baPvgkICLAbv2/fPu3fv19LliyxTTMMQwkJCTp58qT2798vi8WiatWqpWn9nTp10rBhw7Rx40bVqlVLjRo1kp+fX7JjDx8+rOeee85uWpUqVTR9+nRZrVbbtaMP3nTp4uKiokWLJrm/wpH4LmAAAPCPkidPHrufb968qVdeeUUdO3ZMMrZEiRI6duxYupbfunVr1alTR2vXrtXPP/+sr776SgMHDkx2+WmVK5d9JXNxcZFhGBle3sPwEeAAACBH2bVrl93Pv//+u8qWLZvindj+/v46ePCgypYtm+SPu7u7fHx8lJCQoK1bt6Y5Q4kSJdSuXTt99tlntnshklO+fHlt377dbtr27dtVrlw5p945TgEEAAA5yunTpxUVFaXDhw9r6dKl+vbbb9WpU6cUx3fv3l07duzQiBEjtHfvXh09elSrVq3SiBEjJN3/OtqWLVvqnXfe0apVq3TixAlt2bJFy5cvT3Z5H374oTZs2KATJ05oz5492rJliypUqJDs2G7dumnTpk36/PPPdeTIEcXExGjmzJl21yg6A6eAAQCAnYrF8mfr9bz00ku6ffu2WrduLYvFok6dOqX6kSl+fn6aMWOGxo8fr/bt20u6f+NGWFiYbcywYcM0btw4DRs2TJcvX1bJkiXtvub2QQkJCRoxYoT++usv5c+fX88++6wGDx6c7NjKlStr/Pjxmjhxov773//Ky8tL/fr1s7sBxBkogEhe/mKyJlhlcU3ndzNnYB4AQPZhTTCy/MOZ/76+9H4TSK5cuTRkyBANHz48yWNr1qxJdp6goCBNnTo1xWXmzp1bgwcPTrbI1ahRQ/v377f9/O6776a4nL+PlaTGjRurcePGKc6TXOZFixalON4RKIBInkchWVwtGrR+kA5fSdvnEJUvWF6j6o7K4mAAgKz0qL+WLbt/Ddw/FQUQqTp85bD2Xtzr7BgAAMCBKIAAACDHSO6zhZF+3AUMAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAEAqPv30U7344ou2nwcNGqRevXo5MVHmUQABAMD/JFj/2euDJD4IGgAAPMjVIs1/VbpwIOvXVdRHajU5U4uIj4+Xu7u7gwKZBwUQAADYu3BAOvO7s1Mkq2PHjnryySdlsVi0ePFi+fj46N1339Xo0aO1bds25cmTR7Vr19bgwYNVpEgRSVJCQoKmTJmiuXPn6syZMypatKjatm2rnj17SpI+/vhjrVq1Sn/99ZeKFi2q5s2bq3fv3nJzc3PmU81SFEAAAJCjxMTEqF27dpo1a5auXbumzp07q3Xr1ho8eLDu3LmjMWPG6M0339T06dMlSWPHjtW8efM0ePBgPf300zp37pyOHDliW16+fPkUFRWlYsWK6cCBA3r33XeVL18+de/e3VlPMctRAAEAQI5Srlw5DRgwQJL0xRdfyN/fX2+99Zbt8f/85z+qV6+ejhw5Ii8vL02fPl3vvfeeWrZsKUkqU6aMqlatahv/4A0dpUqV0pEjR7Rs2TIKIAAAQHZRuXJl29/37dunLVu2KCQkJMm448eP69q1a4qPj9czzzyT4vKWL1+u6dOn68SJE7p586bu3bun/PnzZ0n27IICCAAAcpQ8efLY/n7z5k01aNBA/fv3TzLOy8tLJ06cSHVZO3bsUP/+/dW3b1/VqVNHBQoU0LJlyxQdHe3w3NkJBRAAAORYlStX1g8//CBvb2/lypW01pQrV04eHh7avHmzSpcuneTxHTt2qGTJkrYbQiTp9OnTWZo5O+BzAAEAQI7Vvn17XblyRW+99ZZ27dql48ePa8OGDRo8eLCsVqty586t7t276+OPP9bChQt1/Phx7dy5U/PmzZMklS1bVmfOnNGyZct0/PhxTZ8+XatWrXLys8p6HAEEAAD2ivrkmPUUL15cs2bN0pgxYxQZGan4+HiVLFlSzz77rFxd7x/n6tWrlywWiyZOnKhz587Jy8tLr7zyiiTpueeeU+fOnTVixAjFx8erfv366tmzpz777LNMZ8vOKIAAAOB/EqyZ/nDmdK/P1ZLm4TNmzEgyrVy5cqkWNldXV/Xs2dPuNO+DBgwYYLurOFGXLl1sf+/bt6/69u1r+3nUqFFpzptdcQoYAAD8TzrKWI5cHyRRAAEAAEyHAggAAGAyFEAA2dqDn/cFZEfso8iJKIAAsocEa5JJFotF/v7+sliSuUYomfFAlklhf2MfRU7FXcAAsgdXizT/VenCgYePLerzaO9SBNKzf0rso8j2KIAAso8LB6Qzvzs7BZA89k/8g3AKGAAAwGQogAAAACZDAQQAADmGYRh69913Vb16dfn6+mrv3r3OjpQjUQABAICN9RHfvZze9a1fv14xMTH68ssvtXHjRj355JPaunWrXn/9ddWpU0e+vr5atWpVFqX95+AmEAAAYGNxtWjQ+kE6fOVwlq+rfMHyGlU3fd+re+LECXl5ealKlSq2aTdv3pSvr69atWqlPn36ODpmphmGIavVqly5sk/tyj5JAABAtnD4ymHtvZj9Tq0OGjRIMTExkiRfX195e3trzZo1qlevnurVq5euZe3bt08ffvihdu/eLRcXF5UrV07Dhw9XYGCgJGnbtm0aP368du3aJXd3dwUFBWncuHEqWLCg4uPjNXr0aC1btkzXr19XQECABg8erKCgIEnSli1b1KlTJ3311VeaMGGCDhw4oClTpqhatWr6+uuvNWfOHF24cEHlypVTr1691KRJE8duqDSgAAIAgBxhyJAhKl26tObOnavvv/8++Q/gTqP+/furUqVKGjZsmCwWi/bu3Ss3NzdJ0t69e9WlSxe1atVKQ4YMkcVi0ZYtW2S13j9dPXr0aP3www8aNWqUvL29NXnyZL366qv68ccfVahQIds6xo4dq4EDB6p06dJ67LHHNGnSJC1evFjDhw9XuXLltHXrVv373/9WkSJFVL169Uxtm/SiAAIAgByhQIECypcvnywWi7y8vDK1rNOnTysyMlIVKlSQJJUrV8722OTJkxUQEKBhw4bZpj355JOS7p9unj17tqKiomxHHT/44AP9/PPP+v777/Xqq6/a5unXr59q164tSYqPj9ekSZMUHR2tkJAQSVLp0qW1bds2zZkzhwIIAACQ1bp27aqhQ4dq0aJFqlWrlpo0aaIyZcpIun8EMKXTssePH9fdu3ftrkF0c3NTUFCQDh06ZDc28XSyJB07dky3bt1St27d7MbcvXtXlSpVctTTSjMKIAAAMJ2+ffuqWbNmWrdundavX6+JEyfqk08+0fPPPy8PDw+HrCNPnjy2v9+8eVOSNGnSJBUvXtxunLu7u0PWlx58DAwAADClJ554Ql26dNHUqVPVqFEjzZ8/X9L9G0w2bdqU7DxlypSRm5ubtm/fbpt29+5dxcbGqmLFiimuq0KFCnJ3d9fp06dVtmxZuz8lSpRw7BNLA44AAgCAHO3GjRs6fvy47eeTJ09q7969KliwoEqWLJlk/O3btzV69Gg1btxYpUqV0l9//aXY2Fg1atRIktSjRw81b95cw4YN0yuvvCI3Nzdt2bJFTZo0UZEiRdSuXTuNHj3atvzJkyfr9u3bevnll1PMmD9/fnXr1k1RUVEyDENPP/20rl27pu3btyt//vxq2bKl4zdMKiiAAADATvmC5XPUenbv3q1OnTrZfo6KipIktWzZUqNGJf2cQVdXV12+fFkDBw7UhQsXVLhwYTVq1Ej9+vWTdP/I4NSpUzVu3Di1bt1aHh4eCgoKUrNmzSTdv4PYMAwNGDBAN27cUEBAgCZPnqyCBQummvPNN99UkSJFNGnSJJ08eVIFChSQv7+/Xn/9dYdsh/SgAAIAABtrgjXdH86c2fVZXNP+cS5dunRRly5d7KbVqFFD+/fvT/My3N3dNW7cuFTHVK9eXbNnz072sdy5c2vo0KEaOnRoso+nlMfFxUWdO3dW586d05w1q3ANIAAAsElPGcuJ68N9FEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBADApAzDcHYEZFBmXzsKIAAAJuPm5ibpf19Phpwn8bVLfC3Ti88BBADAZCwWiwoVKqRz585JkvLmzSsXFxcnp0JaGIahmzdv6ty5cypUqJAslox9jA4FEAAAE3r88cclyVYCkbMUKlTI9hpmBAUQAAATcnFxUYkSJVSsWDHdvXvX2XGQDm5ubhk+8peIAggAgIlZLJZMlwnkPNwEAgAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAm47ACOHPmTIWGhiowMFCtW7fWrl270jTfsmXL5Ovrq169ejkqCgAAAFLhkAK4fPlyRUVFqXfv3oqJiZGfn58iIyMVFxeX6nwnT57URx99pKpVqzoiBgAAANLAIQUwOjpabdq0UatWrVSxYkUNHz5cHh4emj9/forzWK1W9e/fX3379lXp0qUdEQMAAABpkOkPgo6Pj9eePXv02muv2aa5urqqVq1a2rFjR4rzff755/L09FTr1q21bdu2DK/farVmeN6slJgru+R7lB/ymRXPObttz5SQM+Myso9ml/zZcXsmJ6fklLJf1oz+G+rM/Nll2yF7ynQBvHTpkqxWqzw9Pe2me3p66vDhw8nO89tvv+n777/XwoULM7t6xcbGZnoZWSkr8rm5uamSf2W55cqen9y+f/9+3bp1K0uWnd1f70TkTJ88efLI398/3fNl5b6WEdllez5MTskpZY+sGd0/pey3jwKJHvlXwV2/fl0DBgzQBx98oCJFimR6eYGBgdnyK2ysVqtiY2OzLJ/FYtEbs3fo4LnrDx1b39dL/27s5/AMKfH19XX4MrN6ezoKOR+trNjXMiKnbM+cklPKWVlT48x9NHEbAsnJdAEsXLiwLBZLkhs+4uLiVLRo0STjT5w4oVOnTqlnz562aQkJCZIkf39/rVy5UmXKlEnz+rP7dxhmZb6D565rz+mrDx1XwStflqw/JVn5emT31zsROR+N7JY9p2zPnJJTyllZk5OTs+OfLdMF0N3dXZUrV9amTZvUsGFDSfcL3aZNmxQREZFkfPny5bVkyRK7aePHj9eNGzc0ZMgQPf7445mNBAAAgFQ45BRw165dNXDgQAUEBCgoKEjffPONbt26pfDwcEnSgAEDVLx4cb399tvKnTu3fHx87OZ/7LHHJCnJdAAAADieQwpgWFiYLl68qIkTJ+r8+fOqVKmSJk+ebDsFfObMGbm68qUjAAAA2YHDbgKJiIhI9pSvJM2YMSPVeUeNGuWoGAAAAHgIDssBAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAHKe/MVkTbCme7aMzAMA/0S5nB0AANLNo5AsrhYNWj9Ih68cTtMs5QuW16i6o7I4GADkDBRAADnW4SuHtffiXmfHAIAch1PAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAgjA4awJhrMjAABSkcvZAQD881hcXfTG7B06eO56msbX9/XSvxv7ZXEqAEAiCiCALHHw3HXtOX01TWMreOXL4jQAgAdxChgAAMBkKIAAAAAmQwEEAAAwGQogAACAyVAAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRAAAMBkKIAAAAAmQwEEAAAwGYcVwJkzZyo0NFSBgYFq3bq1du3aleLYuXPnqn379qpWrZqqVaumLl26pDoeAAAAjuOQArh8+XJFRUWpd+/eiomJkZ+fnyIjIxUXF5fs+C1btqhp06aaPn26Zs+erRIlSqhbt246e/asI+IAAAAgFQ4pgNHR0WrTpo1atWqlihUravjw4fLw8ND8+fOTHT927Fh16NBBlSpVUoUKFTRy5EglJCRo06ZNjogDAACAVGS6AMbHx2vPnj2qVavW/xbq6qpatWppx44daVrGrVu3dO/ePRUsWDCzcQAAAPAQuTK7gEuXLslqtcrT09Nuuqenpw4fPpymZYwZM0bFihWzK5FpZbVa0z3Po5CYK6vyWSyWLFmuI2TFc87q7eko5LyP/TN7yik5peyXNaP7tDPzZ5dth+wp0wUws7766istX75c06dPV+7cudM9f2xsbBakcpysyJcnTx75+/s7fLmOsn//ft26dStLlp3dX+9EZs7J/pn95ZScUvbImpl9Oiv3NyAzMl0ACxcuLIvFkuSGj7i4OBUtWjTVeadMmaKvvvpK0dHR8vPzy9D6AwMDs+XRBqvVqtjY2GybLyv5+vo6fJk5ZXuSM/tj/8z+OaWclTU1WbG/pVXiNgSSk+kC6O7ursqVK2vTpk1q2LChJNlu6IiIiEhxvq+//lpffvmlpkyZosDAwAyv32KxZOt/HLJ7vqyQlc83p2xPcmZf7J85J6eUs7ImJydnxz+bQ04Bd+3aVQMHDlRAQICCgoL0zTff6NatWwoPD5ckDRgwQMWLF9fbb78t6f5p34kTJ2rs2LHy9vbW+fPnJUl58+ZVvnz5HBEJAAAAKXBIAQwLC9PFixc1ceJEnT9/XpUqVdLkyZNtp4DPnDkjV9f/3XA8e/Zs3b17V/369bNbTp8+fdS3b19HRAIAAEAKHHYTSERERIqnfGfMmGH385o1axy1WgAAAKQT3wUMAABgMhRAAAAAk6EAAgAAmAwFEAAAwGQogAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIIAABgMhRAAAAAk6EAAgAAmAwFEAAAR8tfTNYEa7pny8g8QEbkcnYAAAD+cTwKyeJq0aD1g3T4yuE0zVK+YHmNqjsqi4MB91EAAQDIIoevHNbei3udHQNIglPAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAMB1rguHsCIBT5XJ2AAAAHjWLq4vemL1DB89df+jY+r5e+ndjv0eQCnh0KIAAAFM6eO669py++tBxFbzyPYI0wKPFKWAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYjMMK4MyZMxUaGqrAwEC1bt1au3btSnX8ihUr1KRJEwUGBqp58+Zat26do6IAAAAgFQ4pgMuXL1dUVJR69+6tmJgY+fn5KTIyUnFxccmO3759u95++229/PLLWrhwoZ577jn17t1bBw4ccEQcAAAApMIhBTA6Olpt2rRRq1atVLFiRQ0fPlweHh6aP39+suOnT5+uZ599Vq+++qoqVKigN998U/7+/vr2228dEQcAAACpyHQBjI+P1549e1SrVq3/LdTVVbVq1dKOHTuSnWfnzp2qWbOm3bQ6depo586dmY0DAACAh8iV2QVcunRJVqtVnp6edtM9PT11+PDhZOe5cOGCihYtmmT8hQsX0rxewzAk3S+gFoslnamzXkJCgjw8PHT37l1ZrVaHL99isajS4/mUOw1PvZxnnvsZvCpLrrnTtoJC5SWrVT4FfeTu4p6mWco9Vk5WqzVLnm9Wb09HIed96dk/pQzso+yfGZJTckrZax/Nqf+GJi4n8fcl8CAXI5N7xtmzZ1W3bl3Nnj1bISEhtumjR4/W1q1bNW/evCTzBAQEaNSoUWrWrJlt2syZM/X555/rl19+SdN64+PjFRsbm5noAAD84wUGBsrdPW0lFOaR6SOAhQsXlsViSXLDR1xcXJKjfImKFi2a5GhfauOTkytXLgUGBsrV1VUuLi7pDw4AwD+YYRhKSEhQrlyZ/lWPf6BM7xXu7u6qXLmyNm3apIYNG0q6f+h+06ZNioiISHae4OBgbd68WV26dLFN++WXXxQcHJzm9bq6uvI/GgAAgAxwyF3AXbt21dy5cxUTE6NDhw5p2LBhunXrlsLDwyVJAwYM0NixY23jO3XqpA0bNmjq1Kk6dOiQPv30U+3evTvFwggAAADHcchx4bCwMF28eFETJ07U+fPnValSJU2ePNl2SvfMmTNydf1f16xSpYrGjBmj8ePHa9y4cSpXrpw+//xz+fj4OCIOAAAAUpHpm0AAAACQs/BdwAAAACZDAQQAADAZCiAAAIDJUAABAABMhgIImBT3fwGAefHx4A5w8eJFzZ8/Xzt37rR9w0nRokUVEhKi8PBwFSlSxMkJgaQCAwO1aNEiVahQwdlRgBzj3LlzmjVrlrZt26bz58/L1dVVpUuX1nPPPafw8PBs+d30QHL4GJhM2rVrl1599VV5eHioVq1a8vT0lHT/q+02bdqk27dva/LkyQoMDHRy0oc7c+aMJk6cqKioKGdH0e3bt7V7924VKlRIFStWtHvszp07WrFihV566SXnhHvAoUOHtHPnTgUHB6tChQo6dOiQpk+frvj4eLVo0UI1a9Z0dsQUX8/p06erRYsWKlSokCRp8ODBjzDVw928eVMrVqzQ8ePH5eXlpaZNm6pw4cLOjqU9e/boscceU+nSpSVJCxcu1OzZs3XmzBmVLFlSERERatq0qZNT3vfBBx/ohRdeUNWqVZ0d5aG+/fZb7dq1S/Xq1VPTpk21cOFCffXVV0pISFCjRo3Ur18/p3+lWWxsrLp27aoyZcrIw8NDO3fuVLNmzXT37l1t3LhRFSpU0OTJk5U/f36n5gTSggKYSW3atJGfn5+GDx+e5DuJDcPQ+++/r/3792vOnDlOSph2+/btU8uWLbV3716n5jhy5IgiIyN1+vRpubi46Omnn9a4ceNUrFgxSdKFCxf07LPPOj3n+vXr1atXL+XLl0+3bt3SZ599poEDB8rPz08JCQnaunWrpkyZ4vQS6OfnJz8/PxUoUMBu+tatWxUQEKA8efLIxcVF06dPd1LC+8LCwvTdd9+pUKFCOnPmjDp06KCrV6+qXLlyOnHihCwWi+bMmWMrXs7SokULDRo0SLVq1dK8efM0cuRItW7dWhUqVNCRI0c0b948DRkyRC+//LJTc0r3X3sXFxeVKVNGrVq1UsuWLeXl5eXsWEl88cUXmjx5surUqaPt27erU6dOmjJlirp06SJXV1dNmzZN7dq1U79+/Zyas127dqpdu7b69OkjSVq0aJFmzpypuXPn6sqVK+rcubOqVq2qoUOHOjUnkCYGMiUwMNA4ePBgio8fPHjQCAwMfISJUrZq1apU/0RHRxt+fn7Ojmn06tXL6NGjhxEXF2ccPXrU6NGjhxEaGmqcOnXKMAzDOH/+fLbI2bZtW2PcuHGGYRjG0qVLjWrVqtl+NgzDGDNmjNG1a1dnxbOZNGmSERoaavzyyy920/39/Y0///zTSamS8vX1NS5cuGAYhmG8/fbbRtu2bY2rV68ahmEY169fN7p06WK89dZbzoxoGIZhBAUFGSdPnjQMwzBeeuklY86cOXaPL1682AgLC3NGtCR8fX2NX375xRg5cqRRo0YNo3Llysbrr79urFmzxrBarc6OZ9OwYUPjhx9+MAzDMPbu3WtUqlTJWLRoke3xH3/80Xj++eedFc8mKCjIOH78uO1nq9VqVK5c2Th//rxhGIaxceNGo06dOs6KB6QL1wBmUtGiRRUbG5vidVSxsbG2r8Rztt69e8vFxSXVi///fhTTGXbs2KHo6GgVKVJERYoU0Zdffqlhw4apQ4cOmj59uvLkyePsiJKkP//8Ux999JEk6YUXXtCAAQPUuHFj2+PNmzfXggULnBXPpkePHnrmmWf073//W6GhoXrrrbfk5ubm7Fip2rlzp4YPH247apkvXz717dtXb731lpOTSR4eHrp06ZK8vb119uxZBQUF2T3+1FNP6eTJk05Kl5SPj49q1qypAQMG6KefftL8+fPVu3dveXp6Kjw8XOHh4SpbtqxTM547d04BAQGS7h+1dHV1VaVKlWyP+/v769y5c86KZ+Pp6alz587ZjkJfuHBB9+7ds53yLVu2rK5cueLMiECacRdwJkVGRurdd9/VyJEjtXr1av3+++/6/ffftXr1ao0cOVLvv/++IiMjnR1TkuTl5aVPP/1U+/btS/ZPTEyMsyNKun/934PX+ri4uGj48OFq0KCBIiIidPToUeeF+5vEwuzq6ip3d3e706z58uXTtWvXnBXNTlBQkBYsWKCLFy+qVatWOnDgQLYo+3+XmOnOnTtJTlUWL15cFy9edEYsO3Xr1tWsWbMkSdWqVdPKlSvtHl+xYoXKlCnjjGipcnNzU1hYmKZMmaJVq1apTZs2WrJkiZo0aeLsaCpatKgOHjwoSTp69KisVqvtZ0k6ePBgtriZ7rnnntOwYcO0fv16bd68Wf3791e1atXk4eEh6f7lK8WLF3dySiBtOAKYSR06dFDhwoU1bdo0zZo1S1arVZJksVhUuXJlRUVFKSwszMkp76tcubL27Nmjhg0bJvv4w44OPirly5dP9qjqe++9J0nq2bOnM2Il4e3traNHj9p+2c+ZM0clSpSwPX7mzJlsdb1Vvnz59NFHH2nZsmXq2rWrbV/NTjp37qxcuXLp+vXrOnLkiHx8fGyPnT592nbDijP1799f7dq1U0REhAICAhQdHa1ff/3Vdg3gzp079fnnnzs7ZqpKliypvn37qk+fPvrll1+cHUfNmzfXwIED9dxzz2nTpk169dVXNXr0aF2+fFkuLi768ssv7Y6uO8ubb76pIUOGqGfPnrJarQoODtbHH39se9zFxSVbHKUG0oIC6ABhYWEKCwvT3bt3denSJUlS4cKFs91ptldffVU3b95M8fEyZco4/UYASXr++ee1bNmyZO/yfe+995SQkKDZs2c/+mB/065dOyUkJNh+frCsSPdvEnnmmWcedayHatq0qZ5++mnt3r1bJUuWdHYcm8QL6xPlzZvX7uc1a9Zki7tZixcvbrtD9f/+7/9kGIZ27dqlv/76SyEhIZo1a1a2ueu/ZMmScnVN+USPi4uLateu/QgTJa9fv362u2rbtGmjHj16yM/PTx9//LFu3bql0NBQvfHGG86OqXz58mn8+PG6c+eO7t27p3z58tk9XqdOHSclA9KPu4ABAABMhmsAAQAATIYCCAAAYDIUQAAAAJOhAAIAAJgMBRBAmpw8eVK+vr5O/wo+AEDmUQABAABMhgIIAABgMhRAAHYSEhL09ddf6/nnn1dAQIDq16+v//73v0nGWa1WvfPOOwoNDVVQUJAaN26sb775xm7Mli1b9PLLLys4OFhVq1bVK6+8olOnTkmS9u3bp44dOyokJERVqlRReHi4YmNjH8lzBACz45tAANgZO3as5s2bp8GDB+vpp5/WuXPndOTIkSTjEhIS9Pjjj2vChAkqVKiQduzYoffee09eXl4KCwvTvXv31Lt3b7Vu3Vrjxo3T3bt3tWvXLtv3/fbv31+VKlXSsGHDZLFYtHfv3mz37TkA8E9FAQRgc/36dU2fPl3vvfeeWrZsKen+VwRWrVpVJ0+etBvr5uamfv362X4uXbq0du7cqZUrVyosLEzXr1/XtWvX1KBBA9v3JT/4/c6nT59WZGSkbVq5cuWy+NkBABJRAAHYHD58WPHx8Wn+DuOZM2dq/vz5On36tO7cuaO7d+/Kz89PklSoUCGFh4crMjJStWvXVs2aNfXCCy+oWLFikqSuXbtq6NChWrRokWrVqqUmTZrYiiIAIGtxDSAAm9y5c6d57LJly/TRRx+pVatWmjp1qhYuXKjw8HDdvXvXNiYqKkpz5sxRSEiIVqxYocaNG2vnzp2SpL59+2rp0qWqX7++Nm/erLCwMP3000+OfkoAgGRQAAHYlCtXTh4eHtq8efNDx27fvl0hISHq0KGD/P39VbZsWR0/fjzJOH9/f7322muaPXu2fHx8tHTpUttjTzzxhLp06aKpU6eqUaNGmj9/vkOfDwAgeZwCBmCTO3dude/eXR9//LHc3NxUpUoVXbx4UX/++adq1qxpN7Zs2bJauHChNmzYoFKlSmnRokWKjY1VqVKlJEknTpzQ3LlzFRoaqmLFiunIkSM6evSoXnzxRd2+fVujR49W48aNVapUKf3111+KjY1Vo0aNnPG0AcB0KIAA7PTq1UsWi0UTJ07UuXPn5OXlpVdeeSXJuFdeeUV79+7Vv/71L7m4uKhp06Zq37691q9fL0nKkyePDh8+rJiYGF2+fFnFihVThw4d9Morr+jevXu6fPmyBg4cqAsXLqhw4cJq1KiR3U0lAICs42IYhuHsEAAAAHh0uAYQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZCiAAAAAJkMBBAAAMBkKIAAAgMlQAAEAAEyGAggAAGAyFEAAAACToQACAACYDAUQAADAZP4fdu+rPtUueF0AAAAASUVORK5CYII=" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Compare Classifiers Multiclass Multimetric  Label Worst10</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Compare Classifiers Performance From Prob</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Compare Performance Label</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Confusion Matrix  Label Top10</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Confusion Matrix Entropy  Label Top10</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Frequency Vs F1  Label</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div><div class="plot" style="margin-bottom:20px;text-align:center;"><h3>Roc Curves</h3><img src="data:image/png;base64,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" style="max-width:90%;max-height:600px;border:1px solid #ddd;" /></div></div>
+</div>
+
+<script>
+function showTab(id) {
+  document.querySelectorAll('.tab-content').forEach(el => el.classList.remove('active'));
+  document.querySelectorAll('.tab').forEach(el => el.classList.remove('active'));
+  document.getElementById(id).classList.add('active');
+  document.querySelector(`.tab[onclick*="${id}"]`).classList.add('active');
+}
+</script>
+
+    </div>
+    </body>
+    </html>
+    
\ No newline at end of file
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/test-data/mnist_subset.csv	Tue Jun 03 21:22:11 2025 +0000
@@ -0,0 +1,121 @@
+image_path,label,split
+training/0/5680.jpg,0,0
+training/0/5699.jpg,0,0
+training/0/5766.jpg,0,0
+training/0/5524.jpg,0,0
+training/0/5003.jpg,0,0
+training/0/5527.jpg,0,0
+training/0/5359.jpg,0,0
+training/0/5452.jpg,0,0
+training/0/5010.jpg,0,0
+training/0/5405.jpg,0,0
+training/1/6100.jpg,1,0
+training/1/6015.jpg,1,0
+training/1/5754.jpg,1,0
+training/1/6275.jpg,1,0
+training/1/6247.jpg,1,0
+training/1/6552.jpg,1,0
+training/1/6129.jpg,1,0
+training/1/6733.jpg,1,0
+training/1/6590.jpg,1,0
+training/1/6727.jpg,1,0
+training/2/5585.jpg,2,0
+training/2/5865.jpg,2,0
+training/2/4984.jpg,2,0
+training/2/4992.jpg,2,0
+training/2/5008.jpg,2,0
+training/2/5325.jpg,2,0
+training/2/5438.jpg,2,0
+training/2/5807.jpg,2,0
+training/2/5323.jpg,2,0
+training/2/5407.jpg,2,0
+training/3/5869.jpg,3,0
+training/3/5333.jpg,3,0
+training/3/5813.jpg,3,0
+training/3/6093.jpg,3,0
+training/3/5714.jpg,3,0
+training/3/5519.jpg,3,0
+training/3/5586.jpg,3,0
+training/3/5410.jpg,3,0
+training/3/5577.jpg,3,0
+training/3/5710.jpg,3,0
+training/4/5092.jpg,4,0
+training/4/5793.jpg,4,0
+training/4/5610.jpg,4,0
+training/4/5123.jpg,4,0
+training/4/5685.jpg,4,0
+training/4/4972.jpg,4,0
+training/4/4887.jpg,4,0
+training/4/5052.jpg,4,0
+training/4/5348.jpg,4,0
+training/4/5368.jpg,4,0
+training/5/5100.jpg,5,0
+training/5/4442.jpg,5,0
+training/5/4745.jpg,5,0
+training/5/4592.jpg,5,0
+training/5/4707.jpg,5,0
+training/5/5305.jpg,5,0
+training/5/4506.jpg,5,0
+training/5/5118.jpg,5,0
+training/5/4888.jpg,5,0
+training/5/5282.jpg,5,0
+training/6/5553.jpg,6,0
+training/6/5260.jpg,6,0
+training/6/5899.jpg,6,0
+training/6/5231.jpg,6,0
+training/6/5743.jpg,6,0
+training/6/5567.jpg,6,0
+training/6/5823.jpg,6,0
+training/6/5849.jpg,6,0
+training/6/5076.jpg,6,0
+training/6/5435.jpg,6,0
+training/7/6036.jpg,7,0
+training/7/5488.jpg,7,0
+training/7/5506.jpg,7,0
+training/7/6194.jpg,7,0
+training/7/5934.jpg,7,0
+training/7/5634.jpg,7,0
+training/7/5834.jpg,7,0
+training/7/5721.jpg,7,0
+training/7/6204.jpg,7,0
+training/7/5481.jpg,7,0
+training/8/5844.jpg,8,0
+training/8/5001.jpg,8,0
+training/8/5785.jpg,8,0
+training/8/5462.jpg,8,0
+training/8/4938.jpg,8,0
+training/8/4933.jpg,8,0
+training/8/5341.jpg,8,0
+training/8/5057.jpg,8,0
+training/8/4880.jpg,8,0
+training/8/5039.jpg,8,0
+training/9/5193.jpg,9,0
+training/9/5870.jpg,9,0
+training/9/5756.jpg,9,0
+training/9/5186.jpg,9,0
+training/9/5688.jpg,9,0
+training/9/5579.jpg,9,0
+training/9/5444.jpg,9,0
+training/9/5931.jpg,9,0
+training/9/5541.jpg,9,0
+training/9/5786.jpg,9,0
+test/0/833.jpg,0,2
+test/0/855.jpg,0,2
+test/1/1110.jpg,1,2
+test/1/969.jpg,1,2
+test/2/961.jpg,2,2
+test/2/971.jpg,2,2
+test/3/895.jpg,3,2
+test/3/1005.jpg,3,2
+test/4/940.jpg,4,2
+test/4/975.jpg,4,2
+test/5/780.jpg,5,2
+test/5/834.jpg,5,2
+test/6/932.jpg,6,2
+test/6/796.jpg,6,2
+test/7/835.jpg,7,2
+test/7/863.jpg,7,2
+test/8/899.jpg,8,2
+test/8/898.jpg,8,2
+test/9/1007.jpg,9,2
+test/9/954.jpg,9,2
Binary file test-data/mnist_subset.zip has changed
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/utils.py	Tue Jun 03 21:22:11 2025 +0000
@@ -0,0 +1,156 @@
+import base64
+import json
+
+
+def get_html_template():
+    return """
+    <html>
+    <head>
+        <title>Galaxy-Ludwig Report</title>
+        <style>
+          body {
+              font-family: Arial, sans-serif;
+              margin: 0;
+              padding: 20px;
+              background-color: #f4f4f4;
+          }
+          .container {
+              max-width: 800px;
+              margin: auto;
+              background: white;
+              padding: 20px;
+              box-shadow: 0 0 10px rgba(0, 0, 0, 0.1);
+              overflow-x: auto;
+          }
+          h1 {
+              text-align: center;
+              color: #333;
+          }
+          h2 {
+              border-bottom: 2px solid #4CAF50;
+              color: #4CAF50;
+              padding-bottom: 5px;
+          }
+          table {
+              border-collapse: collapse;
+              margin: 20px 0;
+              width: 100%;
+              table-layout: fixed; /* Enforces consistent column widths */
+          }
+          table, th, td {
+              border: 1px solid #ddd;
+          }
+          th, td {
+              padding: 8px;
+              text-align: center; /* Center-align text */
+              vertical-align: middle; /* Center-align content vertically */
+              word-wrap: break-word; /* Break long words to avoid overflow */
+          }
+          th:first-child, td:first-child {
+              width: 5%; /* Smaller width for the first column */
+          }
+          th:nth-child(2), td:nth-child(2) {
+              width: 50%; /* Wider for the metric/description column */
+          }
+          th:last-child, td:last-child {
+              width: 25%; /* Value column gets remaining space */
+          }
+          th {
+              background-color: #4CAF50;
+              color: white;
+          }
+          .plot {
+              text-align: center;
+              margin: 20px 0;
+          }
+          .plot img {
+              max-width: 100%;
+              height: auto;
+          }
+        </style>
+    </head>
+    <body>
+    <div class="container">
+    """
+
+
+def get_html_closing():
+    return """
+    </div>
+    </body>
+    </html>
+    """
+
+
+def encode_image_to_base64(image_path):
+    """Convert an image file to a base64 encoded string."""
+    with open(image_path, "rb") as img_file:
+        return base64.b64encode(img_file.read()).decode("utf-8")
+
+
+def json_to_nested_html_table(json_data, depth=0):
+    """
+    Convert JSON object to an HTML nested table.
+
+    Parameters:
+        json_data (dict or list): The JSON data to convert.
+        depth (int): Current depth level for indentation.
+
+    Returns:
+        str: HTML string for the nested table.
+    """
+    # Base case: if JSON is a simple key-value pair dictionary
+    if isinstance(json_data, dict) and all(
+        not isinstance(v, (dict, list)) for v in json_data.values()
+    ):
+        # Render a flat table
+        rows = [
+            f"<tr><th>{key}</th><td>{value}</td></tr>"
+            for key, value in json_data.items()
+        ]
+        return f"<table>{''.join(rows)}</table>"
+
+    # Base case: if JSON is a list of simple values
+    if isinstance(json_data, list) and all(
+        not isinstance(v, (dict, list)) for v in json_data
+    ):
+        rows = [
+            f"<tr><th>Index {i}</th><td>{value}</td></tr>"
+            for i, value in enumerate(json_data)
+        ]
+        return f"<table>{''.join(rows)}</table>"
+
+    # Recursive case: if JSON contains nested structures
+    if isinstance(json_data, dict):
+        rows = [
+            f"<tr><th style='padding-left:{depth * 20}px;'>{key}</th>"
+            f"<td>{json_to_nested_html_table(value, depth + 1)}</td></tr>"
+            for key, value in json_data.items()
+        ]
+        return f"<table>{''.join(rows)}</table>"
+
+    if isinstance(json_data, list):
+        rows = [
+            f"<tr><th style='padding-left:{depth * 20}px;'>[{i}]</th>"
+            f"<td>{json_to_nested_html_table(value, depth + 1)}</td></tr>"
+            for i, value in enumerate(json_data)
+        ]
+        return f"<table>{''.join(rows)}</table>"
+
+    # Base case: simple value
+    return f"{json_data}"
+
+
+def json_to_html_table(json_data):
+    """
+    Convert JSON to a vertically oriented HTML table.
+
+    Parameters:
+        json_data (str or dict): JSON string or dictionary.
+
+    Returns:
+        str: HTML table representation.
+    """
+    if isinstance(json_data, str):
+        json_data = json.loads(json_data)
+    return json_to_nested_html_table(json_data)