|
|
<!DOCTYPE html> |
|
|
<html lang="en"> |
|
|
<head> |
|
|
<meta charset="UTF-8"> |
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"> |
|
|
<title>Dynamic Emotion Prediction Visualization (Softmax, Mean Subtracted)</title> |
|
|
<style> |
|
|
body { font-family: system-ui, -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, 'Open Sans', 'Helvetica Neue', sans-serif; margin: 20px; background-color: #f9fafb; color: #1f2937; line-height: 1.6; } |
|
|
h1 { text-align: center; color: #111827; border-bottom: 2px solid #e5e7eb; padding-bottom: 10px; margin-bottom: 30px; font-weight: 600;} |
|
|
h2 { font-size: 1.1em; color: #374151; margin-top: 0; font-weight: 500; word-break: break-all; margin-bottom: 15px;} |
|
|
h3 { font-size: 1.0em; color: #4b5563; margin-top: 15px; margin-bottom: 10px; border-top: 1px solid #e5e7eb; padding-top: 15px; font-weight: 600; } |
|
|
.sample { |
|
|
background-color: #ffffff; |
|
|
border: 1px solid #d1d5db; |
|
|
margin-bottom: 25px; |
|
|
padding: 15px; |
|
|
border-radius: 8px; |
|
|
box-shadow: 0 1px 3px 0 rgba(0, 0, 0, 0.1), 0 1px 2px -1px rgba(0, 0, 0, 0.1); |
|
|
overflow: hidden; |
|
|
} |
|
|
.sample-content { display: flex; flex-wrap: wrap; gap: 20px; align-items: flex-start; } |
|
|
.image-container { flex: 0 0 300px; max-width: 100%; } |
|
|
.image-container img { |
|
|
max-width: 100%; height: auto; display: block; border: 1px solid #e5e7eb; border-radius: 6px; |
|
|
background-color: #f3f4f6; |
|
|
} |
|
|
.image-container p { font-size: 0.75em; color: #6b7280; margin-top: 4px; word-wrap: break-word; } |
|
|
.predictions-container { flex: 1; min-width: 350px; } |
|
|
.dimension-grid { |
|
|
display: grid; |
|
|
grid-template-columns: repeat(auto-fill, minmax(300px, 1fr)); |
|
|
gap: 6px 10px; |
|
|
margin-top: 8px; |
|
|
} |
|
|
.dimension-item { |
|
|
background-color: #f9fafb; |
|
|
padding: 4px 8px; |
|
|
border-radius: 4px; |
|
|
border: 1px solid #e5e7eb; |
|
|
display: flex; |
|
|
justify-content: space-between; |
|
|
align-items: center; |
|
|
font-size: 0.8rem; |
|
|
overflow-wrap: break-word; |
|
|
word-break: break-word; |
|
|
hyphens: auto; |
|
|
} |
|
|
.dimension-name { |
|
|
color: #374151; |
|
|
padding-right: 8px; |
|
|
flex-shrink: 1; |
|
|
flex-grow: 1; |
|
|
text-align: left; |
|
|
margin-right: 5px; |
|
|
} |
|
|
.dimension-score { |
|
|
font-weight: 500; |
|
|
color: #111827; |
|
|
background-color: #e5e7eb; |
|
|
padding: 2px 6px; |
|
|
border-radius: 4px; |
|
|
font-family: Menlo, Monaco, Consolas, "Liberation Mono", "Courier New", monospace; |
|
|
min-width: 140px; |
|
|
text-align: right; |
|
|
flex-shrink: 0; |
|
|
} |
|
|
.mean-sub-score-paren { |
|
|
color: #4b5563; |
|
|
font-size: 0.95em; |
|
|
margin-left: 3px; |
|
|
} |
|
|
.raw-score { |
|
|
color: #6b7280; |
|
|
font-size: 0.9em; |
|
|
margin-left: 3px; |
|
|
} |
|
|
|
|
|
|
|
|
.dimension-item.highlight-top1 { border-left: 4px solid #DC2626; background-color: #FEE2E2; } |
|
|
.dimension-item.highlight-top1 .dimension-name { color: #991B1B; font-weight: 600; } |
|
|
.dimension-item.highlight-top1 .dimension-score { font-weight: bold; } |
|
|
|
|
|
.dimension-item.highlight-top2 { border-left: 4px solid #D97706; background-color: #FEF3C7; } |
|
|
.dimension-item.highlight-top2 .dimension-name { color: #92400E; font-weight: 600; } |
|
|
.dimension-item.highlight-top2 .dimension-score { font-weight: 600; } |
|
|
|
|
|
.dimension-item.highlight-top3 { border-left: 4px solid #059669; background-color: #D1FAE5; } |
|
|
.dimension-item.highlight-top3 .dimension-name { color: #047857; font-weight: 600; } |
|
|
.dimension-item.highlight-top3 .dimension-score { font-weight: 500; } |
|
|
|
|
|
.score-na { color: #6b7280; font-style: italic; } |
|
|
|
|
|
.error { color: #991b1b; background-color: #fee2e2; border: 1px solid #fecaca; padding: 8px 10px; margin-top: 8px; border-radius: 4px; font-weight: 500; font-size: 0.85em;} |
|
|
</style> |
|
|
</head> |
|
|
<body> |
|
|
<h1>Dynamic Classifier Prediction Visualization (Softmax, Mean Subtracted)</h1> |
|
|
<p>Displaying 7 samples (out of 7 successfully inferred). Scores are adjusted by subtracting the mean score from neutral images (using stats from neutral_stats_cache.json). |
|
|
For models <b>not</b> containing keywords ['valence', 'arousal', 'dominance', 'vulnerability'], softmax probability over the mean-subtracted scores is shown first, followed by the mean-subtracted and raw scores in parentheses. |
|
|
For excluded models, only mean-subtracted and raw scores are shown. |
|
|
Highlighting indicates the top 3 highest <b>softmax</b> scores among the non-excluded models for each image (1st: Red, 2nd: Orange, 3rd: Green).</p> |
|
|
<hr> |
|
|
<div class="sample"> |
|
|
<h2>1. 1.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,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" alt="Image: 1.jpg"> |
|
|
<p>Path: ./1.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-1.20)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(-0.32)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">-0.43 <span class="raw-score">(2.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.13)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.013 <span class="mean-sub-score-paren">(0.06)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.245 <span class="mean-sub-score-paren">(2.99)</span> <span class="raw-score">(3.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.81)</span> <span class="raw-score">(2.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.046 <span class="mean-sub-score-paren">(1.31)</span> <span class="raw-score">(1.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.008 <span class="mean-sub-score-paren">(-0.40)</span> <span class="raw-score">(1.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.028 <span class="mean-sub-score-paren">(0.82)</span> <span class="raw-score">(0.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.63)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(0.59)</span> <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.019 <span class="mean-sub-score-paren">(0.42)</span> <span class="raw-score">(0.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.029 <span class="mean-sub-score-paren">(0.87)</span> <span class="raw-score">(2.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">-0.15 <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.042 <span class="mean-sub-score-paren">(1.24)</span> <span class="raw-score">(2.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.08)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.037 <span class="mean-sub-score-paren">(1.09)</span> <span class="raw-score">(1.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-1.23)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">0.32 <span class="raw-score">(2.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-1.20)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(0.12)</span> <span class="raw-score">(0.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.64)</span> <span class="raw-score">(-0.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(0.35)</span> <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.033 <span class="mean-sub-score-paren">(0.97)</span> <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(-0.29)</span> <span class="raw-score">(2.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.188 <span class="mean-sub-score-paren">(2.72)</span> <span class="raw-score">(2.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.09)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.026 <span class="mean-sub-score-paren">(0.75)</span> <span class="raw-score">(0.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.008 <span class="mean-sub-score-paren">(-0.46)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.013 <span class="mean-sub-score-paren">(0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.008 <span class="mean-sub-score-paren">(-0.45)</span> <span class="raw-score">(0.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(0.29)</span> <span class="raw-score">(0.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.15)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.02)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.10)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">-0.38 <span class="raw-score">(-0.5)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="sample"> |
|
|
<h2>2. 2.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL/2wBDAQkJCQwLDBgNDRgyIRwhMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjL/wAARCAEsASwDASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9oADAMBAAIRAxEAPwDtKSiivgz6oKKKKAClpKWgQUUYooAKKDSUAFFFFAxaM0nfFZupeItH0kH7fqVtAw/gZwWP/ARzVxpzm7RVyZSUVdmnRXLp4vm1LI0Hw7q2pjtL5XkxH/gTVMIPH95giz0XTVPaaV5nH/fPFd1PK8TP7NvU5J4+hDeR0VGawf8AhHPGMvMviuzh9oNOB/Umj/hGfF0fMfi+3kP92bTlx+hrf+xK9t0Y/wBqUL9TeozXNt/wnGmAtcadpurwjq1nKYZMf7rcU+w8YaZdXYsroTabfH/l2vk8tj9CeD+BrlrZdiKKu43XlqdFLG0aukZHQUtJRXEdYuaM0UlIBaKSigAozRRQAuaKSigQtFFFABmiiigAzRRSUDFzRSUtACUUUUAFGKKKAClpKKBC0UUUAJS0UUAGKxfEHiXT/Dtur3Tl55OIbaPmSU+w9Pek8UeIYvDmlG5Kebcyt5dtBnmRz/QdTXn+l6tbWmoyX8ofWvEM3LvFGZVg/wBhAOBjpnIr18tyx4j95PSP5nBjcaqK5Y6yOltNL8T+Lf3+rXMmlac3K2Vo212H+3Ien0/QV1Oi+EdD0jDWVjarIOTL5Ykcn3d8n8sVzNrqfjG/k3RaKi+hu50Xb/wEZx+VdJZ2vjCUg3eo6dbr/dihMp/kBX1FOjCkuWCsfO1a1So7zZ0nzkAGSRgPVzSge5P1NVraG4jOLi+a4cdR5aoPyH+NXY4w5y0qRgd2P9BVGILDK3KxSH6KasLPPD/rLVHH+3D/AFpGhsnG2S+um/3Ny/1rPudItjl7XxFrtm3tcsyj8GDClc0UbdTettXtAvlvB5QPXauRVPXPDGieKbBoZ7a2uE7Kw4B9iOVPuK5WU+K4o2l0/VLHxDAhwyOqJMPbIO0n2O2o9I8ZWl5dvaXCvp9/EdskUmUZD7g8r+o96FHsXzNdDmr2HU/h9curyXGoeH4yPNSX5riwBOA2f44/9ofTg8V1kEyXVtHcQOJIZFDJIvIYHoQa0NWkXVAthcGOO/ZHayuWUFZOPnjYdwR95ejLkjkVwngjUDoXiObw66vFY3fmS2kEjZNrMh/ewZ7gdQe4we9eLmWXqUHVpqzW56mCx0l7ktUddmiqVx4ttru4kttD0m61yaNtsj2wCQIfQytxn6Zqu8vi/wD1n/CHIU/uw6pGzfkQB+teRDLsTOPMonofX6KdmzVorBHiq0t7hbfV7S80edjhRfRbUY+gkGVP51uqwZQykEEZBByCK56uHqUnaorHTTqwqK8HcWiiisDQKUUlFAC0UlFAhaKKKACkoooAKKWigY0UtFFABRRRQAUUUUAFLmkooAWq1/qFtpljLeXkyxQRDLMf0AHcnsKsMwVSzEBQMkk4AFeV6nfXvjXXC9tK0Gh2blYZQOZXHBdQe/YHsPc134DBSxVS3RbnLisTGhC/Ui1ue28Taxb3GsmSCJF2WmmxZedwTnc4XJBPHA/Oux0bS7+KBEtPDwt7cfdW6lWBfxVct+dWvCWgiyjlm0+G3hb7pmmQuzHuSc5J+prp0sLgnNxqdw/+zEqxL+gJ/WvsoQjRiqcFoj5erVlUk5SKsFvre0I0+mWkf923t2c/mxA/SriWDn/j4vrqf2LCNfyQD+dWIoIofuLz3JJJP4mnuxRCyozkfwrjJ/Oi5iEMKIAkaog+oUfnRLdaZa83Wor/ALtvE8p/8dBrLudVvIgRBot7I3qVwP0zXPX3iLX8lBbTQ/7MagH82amotlLzR01x4v8AC8CMr2mtTLjlhYTD+grmp/FfhW4n2WfiO+0ibsuo2bGMn3PBH51y+peJdUg3faNVgtivJWS4aZx/wFMAfia5mfxHr+pny4F/tO3PB+0WK7D9CWJ/Wm4qOrZvCDm7Rjc7jWrmaCWG6vmgimf5bTXdNl3RSHsrsOx/uv8AgazbzVJvEgjsNVCQ63DlbG/QYZXH/LN/VTkcHjDAisbQdB1+aS8Wzs0tYZIx9ospGLQTKTg4B6MOvU9Otdba+AHZI/tFw6PCU2sTuJ2jjnvgFl9wFNYTxVGnuzphgqstLWMjSvF8upaZDZzv5V1FIslu2eYZVbaV+gLKw/2Swqn4ultfEHiHSrx5/sljdQC6vXQ4MZUbHAx3YbV98Cuys/h5o8DpJJGZHGC2TwT82T/48P8AvkVoTeCtAmVAbEKUbcjKxBU5zx+Paud5jSvszdZbUWqaMSPxVeRwxafolpHY28MY2xKF/cJ2LseFJHOOTWpp3jq0hi8ibxNPPdg/MtqpmCn04Q1zfifwNqENrv0tjf2UeXawkYqzv1LsRzIfY4rn9H8eXFiotjrFnpUafKYodMf5SOxANdlOrTrK8GcNXDzpO0kes/2w2r27W0r2mpwSD5re+tTbuw9iV2n8V/Gualsp/C7vd6HFcS6anz3eiy8ywL3kgOTkD0BINanhvx3JfYgXV9G1sEfNAyPby/gGyDXZmwstZsfOt4preWI58pjh4j6qRn9CQairShUi4TWhFOpUpy5ovUwrR4tR0+G/sJVuLaZd8bp3H09fajvzWSgHgvxDydug6rJ8/ZbS6P8AF/so/wCQautmto5/vDDf3h1r4/G4WWGq2e3Q+hw2MVWN2ZFFTT27wH5hlezDpUNcR3Jpq6CiiloGFFJRQAUUUUAFLSUtACUUUUAFFFFABRRRQAtJSgEkADJPQCqHifVm8OaXEbdUl1a8fybONuVVsZLt7KOT+ArWlSlVmoQWrMqtWNKPNI57xddyajeL4dgkKxBRJqTIcFUP3Ys9i3U+g+tY82q2lgv2W1SM+T8m3eI448dix7+wzTltJLOx8iGV3urhyZLl+WZ25eQ+/XH4Cob7UtO8PWsUGxmcj91bxDc7+/8AiTX3ODwscNSUI/M+XxFeVepdk0Gs6u0e+yaCSMfw2t7yPzGP5VOnji+tGCXd3PaN2F7CQp+jjK/rXmmo+K2ubkyw6bbW0gPEiFhIP+BKRV3TvH13Enk6lAt3F0LD5W/Hsa6DLkPU4fGOqyqGiFpcKejRSKc05/FmunpaKvvuj/xrzgan4OvvnexlgkP/ADziZT/44cU0w+HpTi10rVbo9hudV/NjSbitxxoylokzsdR8U6kFP2zUrO2X0lus/wDjqgVy1zry38v2a0lu9TnP/LOEG3gHux+8R+Iptv4cl1JtkVhFZQZ+ZLYebM3s0jcLXf8Ah7widMiUpptvsHIR7jGT6sQpyf0rkrYyFNWjuelh8ulL3qmi/Ew/D/gKS+VLrUzGEzlYo0xGv+6vf/ebNeiWGjWVgo8mFdwH3m5NDXt7AMSaRO4He1kSQfkSp/SoDrcvRND1pm9PsmP1JxXjValWq7s9aCp0o8sdDXxSgE9AT9BWSt3rs/MGix2w7NfXar/46m406a+1uIYufEOkWn+xHATj8WcfyrNUv5mJ1f5Vc1WVl+8pH1FIKw11K/LYTxTpE5/uyRAZ/wC+ZKtJdaoF3yWdvcp/fs5//ZWA/nUypW2LjPuaVee/ETwFFrdrLqmmxBNTiXc6qMC4Udj/ALXoe/Su4hv4JpPKy0c2M+VKpR/wB6/hmrXSqpVZ0ZqSFUpxqx5WfN/hrVNJEgtdd0SK5t1/5erdjBcQ++5eD/wIfjXv3hiLUNMto7rS9Uk1rRyBgzgfarcEcB8cSJ79R1GRXlfiDw3BbeKNTntoQ8MbiW4jyVeBX5EqkchM55GdpzuBHNdp4BkvPDWp29jOw+xXzH+z7oDCeb1aBwOF3DkY4z8y8MRX0akpxU11Pm6keWbg+h297HY6payWt5FG9vcgrtblTn+E+x7H1rmtKurnwvrMPh3U5nmsLjI0u8kOWBH/ACwc/wB4D7p7jiur1K3trjeIwVinU7k6FG7j2Oea5OSS38W6DeaJqEoi1K2kMRkzhkmTlJF9+h+hrDE4aGIpuMv+GM6NWVOd0dgQGBBAIPY1nXNkUy8XK919KqeEtak1zQIp7gBb2Fmt7tR2lQ4Y/Q8H8a3K+Iq05UpuEt0fQU6tveiYVLV+6sw2ZIhz3X1qhUnbGSkroSiiigsKKKKACnCm04UAN7UUUUAFFFFABS0lXrG3/wCWzj/dH9aCZSUVdktnbCIeY4+c/pXmHi7WIl8XavfXTEwaTBHaxL/tMN749ySo/CvWa8B+IFtLJ46vtGww+3X0N0p7FDHg/kQa9nI0niG3vY8bHScoanRQ3Mv9lw3Mqb55I1YRr3ZuQo/PFctcabdapezwwM7Luxe3qD5pW/55R56KOnp6117x7o9sXylF2xn+7xjP4Co3hSO0TT7ceVGVO9h/DGPvH6npn3NfXnip2PKNWtYobiO1tET5iAu35mfnGdx6j34B7DHJ7LRPC9vYwoZIBcXbfeJXdg+iisfS7UXfi/7RImCkZuNv93P3F/BStd9Y6g+nSPLGqF2UqC/AX3PsOtefi6sl7sT6LLMNFwdWSv2K0lnNblUMBWRhlUAAOPX2Hual0/TLrUnP2eA3e04YhtkCH0Zz94+wz9K2Ija3NoLq8MgsJXxHCoJuL9/cDnb6KO3XAqe7km8uKPVrsaTbEYg0uw+a4cehKg4+iD8a891JWsd0qnREEsVlppWLVPEAhfHFrp6BT+ZDMfwAqU3nhzZuli18j/ns8t2PxyOKt6et9bDGi+F7ewjb/lvfzhJG9yqhmP4mtBn8URgOZNGbPRMzJn23HP8AKs726/kYt82r/UyLafSLzjS/F+oQMP8AlnJMk+P+AuN361eFlfEfN4yOz1XTkz/PFQX2oWjnb4k8MHPTzTbi4j/B1BI/HFU0fwAf9Xo1vO/ZFhkf/wAdGafr+Vybdvz/AMyW4uNAt28vUPEGpalMeBbrKsYb22RDcangiBXOm+BYkTtJdrHET7/Pl/zFSW814kbjRdEtNGt9pLXE0KxEAdwi/MfxIqpcNoMbSnWdbnv7iJfMkjkmKKBv2EiNMDAbrnOKL9F/X3E2tqy2yakTh/D+iAf3ftKf/G6ja1VfnuPCkkX/AE102VSR/wB8FW/Sqn9pfD+LzFZNNGxzHkw53MBk4J644yenPWq7a74BRx5cyW756wPJGR7/ACn9TRyS/lf4jdSHdGtBcR3R+z29412RybDUVKSj3RiAwPuc/UVq2MzOGXdIyg4xKMSRn+63r7Hv79a5u213RdVxFaaidSiDYEVzw2f+mchwc/5yK37Nt+2RZGnTaVWV+HAB5R/Ug9/8nKrFpao0pyTfus5fVHaH4jrcQDM0dmkm0fxqCQ6/irfmBXR21laWMx0uVN2i3/MIX/l3kHzLsPbH3l9MEVx+p3DxfEqzmRSzBZECDq4CqxUe+ASPcV6FLZxXuliGOTapVXhlXnYRyrD6cfhXt4X+DFHgZguTEM2dQs5IUhuDIJRIoEjqMAvj734/zryLxs8mg+LhqEakxX1v5jqP4zHw4+uzDD/dPrXpPh7XRPbz6dqSeW8TeXPHnPkv1BHqh+8D/wDXrkfizpzp4X+2oA8lhOk6MvRkPyt+GGreLa0Zy6OV+4vw/uFOteIoI23RO1vdKR0O9CCfx2iu8rzT4Q20kltqmqEMIJjDawE/xLEmCR+Jr0yvjM1cXipWPbwyapK4VSvLTdmWMc/xD1q5S15x0xk4u6MKird7b+W3mIPlPX2NVKo7YyUldBRRRQUFKKSloASiiigAoopRQBNbQGeXB+6OWrVGAMDpUdvF5MIX+I8n61JSOKpPmYV5LrN5D4i+INxeQIpttJiNmsoH+slJJbn0GSK77xjq7aF4S1PUYziWKEiI/wC23yr+pzXnehWA03R7a36vt3yMerO3JNfQ5FhrydZ9NEeXj6loqHc0GdUQsxCqoJJPQCrcWmNP4aknkBSbUWVEyOUhP/2O5vxrPsLQ+I9dGmqM2FsRJev2cjkRD69W9uO9dn4llFt4eunQAzunk24HeR/kXH5/kK+lk+h5T0PINPj2eKrqQjBuLOOcD0DHIH5YrWucb135Majcyj+Lnge+TVjxRpR0XxHZXC/6rzf7NJ/3YIv/AGY02b5UEm3cU5UerdB/OvOxK/eXPqsslzYbl7M29BE6hhbsv24j9/dMN4tEPOxF7sep7dzxgVZvfEmgeEUlYCWa8kGZJyPMkc+rv1x9OPpXlvinXJraD+x7W7YLndc7OPMc9ST/AErj4IZ7qQRwxvK56KgJpQwfN703oc2IxXLNwpq7PSdU+LGtOc6fLaKityfK5PsQSfzB/Ksyy8Ua7q91LdNOyq92srIpO1eAMAenA/WszT/A99dKGupo7RT2YFm/IV6x4V8FaXZWvmGdbuSRV8wjgbgOuO3PNOrKhSjoiIUMRUfNPRG14W1WfUI7tGzlG8zdnu/zAflz+Ire064/tDS4bxGI3qCVz36H9aq2NpbaZBIIgFVm3ux9gAPwCgD8KzPBV95mgY6+VeS4H+yW3D+Zry5OMryWx3RjJRSK+rXN1daJqAtlZ5rS5nhmRepQ7lPHrtcMP92vHtZ03UNWb7VGjFihZsZ6kZYfQkMR+Ne0ajZ6hZeIJtY0ZY5orrAu7KR9m4jgOjdA2OCDwcVoRw2cULS/ZkgBBZwwAxnk57VvTxCo/DqZTw7rb6HzIuk3/nSxeRJmJtjkqcL61G+m34yPslwV9fKbn9K9z1nU1vrjbCNsCdO24+tamh6ENq3V4Mk8pEf5n/Cux49xjdxJeVxSu5HzpBNcafeJKoaOVDkbhg17/wCBfFEXiOwKuYo7yIASIo2+YMfex2I6HGa3tX8P6XrlqbfULKKZSMBiuGX3DDkV5bfeEdR8Ba9b6pp808+l+YNzp9+MZ6OOhHv/ACrKdelio8r0l0Mo0KmHlzLVGj45aew12LULdgk9reRSxuegJGBn2zivT7DULW80W01i0UR2Nz8skf8Az7S5wyH0G7I9jjsa4LxxZDUoCyg7bu3+UkEfMOnB6dqd8PPE8VvphuLpRJp8+LXWoGGRBLjatwR/cYYD/n2NdGDlenbsYZpTvOM+6Ov17SbmeSPU9M2rqVupXy2OFuY+piY9vVW7H2JrGs9ftNU0y603UYpWs5Q0TxyDDxHoykdiP8DW1e3snhK+S21J3l0ebm11A/MYR/zzmI7DjD9xjPrXO+KY7WDWvt1tJGyShVuChyDn7rfUHjPo3tXbHU8dq2jNj4eXfm+GfsDEGXTJ3smIGNwU5Vse6kV1lcD8OmK6x4oi7C5gf8TFz/Ku+r4jMaahiZpdz3sPLmpphSUtJXEbAyh1KsMg1jzxGGUoenY+orYqC8h82EkD5l5FBrSnyuxlUUUtM7BKUUlKKAG0tAooAKtWUXmTbj0Tn8aq1rWsflW6g9TyaRlVlyxJ6SiikcZyXxMtXu/h9qojBZolSbA9EcE/pmuHvr92tbSCxYfaL0ARP1CJjLP+A/UivYpYo54XilQPG6lWU9GBGCK8Us9JOk+MdV0/zzNb6aiwWxbqiP8APtPuBgZ9q+oyGunGVHruebj4bTOw8I6ctu5jhcxWsMeZCTy+T3PueSa09ImHi/xbayQjdpGnyFo37TSDguP9kfdX1yx9K5C/UzWbxSTOloRunRDjzAOdpPp6jvXX6Bci1tdO0uzUfabp1MxUfcB5Kj6KPwxXvTXU81bmN8Z0GnWGnR5HmiaW+kI/vNNH/Q4/Cuav5mhspJkALIC65HHAOKm+NerreapdBG3IrJZxY7iM7pW+m8qv1U1narHNPoDxQJvleNVC/XFcdZL3bnv5ZJqE7HEaFotx4l1gxlm2Ft0sg5PPYe5r2zTfA9jYWKxIzQtjpGB+pPJNZ3w+0KLTYWA+Z41y7/3nPf8AIYFb2t65cW9zHpWk24utVmGVUnCRL/ec9hXBicROpU5KeyOuhQVGPNL4uphX+kz2DtkiSMfxqP51RSWSF98TsjeqnFaNz4MN0d/iHxqYrpufLjZI0X2AY5/lWLqHhPV/D2y4hvVvrGQ/JOGyjexI6H65HvVRimrNm8cWnLlsOvPFMhhkguLqdiOsTDBb/wCtWx8P73davAxGZCz/AI5Of0Ncpq8fnWHmmMrImDgjkeoq38PpX/4SIQA/IY2fHuP/ANdVUpRdF2LlJqVmenX97HYWrTy5IHAUdWPpXGajq9zqLEOdkQPEa9Px9a6nxRYSSaLDcqCVSUhsehGK4YkbiPzrkoU0ld7mlKUWrooPcajd30VppMY85zlXYZ4HVueAo9T1PAFdGdJ1m02tqPj+3trgjPluqgf+PMD+lZugaZq/iHWZtM0RmtixH9o6jtyLaMfdiT/bxzj1PtXmmrWlvo3ji8s9QiuLu1tL9o5Ukl2yzRq2OW7Ejv716MKLqeS9LnkYrGWm0tT2qHXNW0URtqzW2oac7BRqNk2VUnpvHb+XvXVpJFcwB0KyRSL9QwryCz0awPgb+1dBTVbPVnnlC2+1nhlgLnaszMAmdvcdcdOa2PBvig6XC9jriPZpjzIpXO6LHQjcM4GfWuXE4XlV4bmuHxPtF76sdtrWmi/07y4lAkj5jA/lXkL3Nz4R8VpqVvEWtrolLm3I4k/vKR69x75Fen2niRdUuz/Zqm5jUfJHGRlyf43bpGnoD8x9KTxL4Xi1/R5I3VFvSuRJGMAuOmPx6Gpw1Z0ZWnsy8RCNek4r5FO21jzdJGnQzi50xlElmW+bbGeijP8Ad5Uj0wDXO2wxLqOiyHMaRh4M9onBG3/gJBx7YrK0CW7trR51iM0MMpS8gX70Evd19mAyR0JBxyKi1DVXbxRew6crXF7c2sVtapGM7mbLbvYAHNe9dJXPmeR83KegfCuCWTR77WJx82o3AKk91jQJn8Turv64PS7PxfpWj2ltaS6LFHawrGto0Uj5AHeUHqeecY5ro/D+vprttLvga1vrV/Ku7Vzlon+vdSOQe4r4vMKVSdSVbdN9D3KcXCKi1Y2aKKK801EpRRSUAZV3F5U5wPlbkVBWpfRb4Nw6pz+FZdCO2lLmiFLSUopmglFA6UUASwR+bMi9iefpWvVDT0y7v6DAq/SOSu7ysFLSUUGIV5ZrkB074h6iJOF1OGK5hJ/iKjY4+owD+Nep1g+K/DKeJNPiWOb7Nf2r+baXIGdj9wR3U9CK9DLMVHDV1KWz0Zz4mk6kLI83mvodQsdsBJV50hb2JfkfkD+ddFp+oPpZuruEqt2YTFbu3SNnIy5/3VBNcMtpf6BPqFjqlt5FxDcpqCqrblePPzMh7jr9K6S7iW8sWiEiiGUDe+eDH1PPuP519tGUakeaOqZ4souLszhvFswu47WRdwW7kAtkf7wt14Vj7uzFz9a7BSEKx55xwPpXKa4ReazpbEYNzcB40xjZCuAn0zyfxrppuWUsrqVO5JUXeFPcMo5xXFjHqkfQZOrQlI6TQL5LSO83Y3eXvUeuK5rQJdX8W+JZtI0a6a3mvCZ9QvwMtFADhVX35/NqI4dU1aG4g0qBZCEbfeIx8qEY5JJA5xnAGaXQPBc1hsmtFeQzL807PuU98NtIK/Q8e9clNQptykdOLcqvu0/vOL+IOgReGPHl1prRT/ZIzGytJJukmQqMvuPcnd7A8dq6zw9Yx3Oj6je+Er/VLXFzsh0u7ha4juIti53bVwp3bufTH1r0TT9IgtwHudP0t5h/y0W0Bb/vpiTVy+1eKzRUdizniOCPqx9Aopzx8WuWMbnHTy+ad3I4fTbCSa1nXWdPlsLrC+VGJlcH14yTjAJ59O9HhGx8rxgZkjVYTatjA75Fb93p8lhpV1qF7gXt1+7jjByIg3X6sQOT+FZ/hyZYNYj3D/WKYx9T/wDqrBzbjKx6sIuUNXex3d9cD/hHbiBVLTL86DHXBz/Qj8aoSWkMunTQQ20W2ZDgABCM+jdjVyjvXH7R6eRioJXt11OD03TbSxv/ALOWsrfYcNFPahHP15wT785rsLeC0icSw2dkr9pEt0z+eKtT6fY6rEIb6BZCPuP0YfQ9RWRN4IMZJ0/VZ4B2V13AfkRXQ5ueqlYX7raUfwLV5aQXbCW8YOq9WmYtx6c8Aew61R0+60sT6glhcLLNHGiOWiaSKJck7WI4ySSxH07Coo/AM1w4Oq69d3EXeG3UQg/VslvyIrqtO02y0iySz0+2jt7dOiIMc9yT1J9zzRZJayuZTknpFGBb2sk6FodXAjznbYwxRoD+TH8zVyG2miPN5LMPSVVz+YAq9d6JYXjmVrdY7jtPF8jj/gS4J/Gq0cbwL5ckrSlTjcwGfxx1rCo2a0rPRHm2s20nh/xtc3UDLDFdxi4Dt9wZO11kHeMtjJ/hLA9M1U8NfZvD8niXxbqFqYvJmaCCAnLKTyUB98qufQGuk+IYaG103Uo2VXtrgqWYZUI67TuHdM4DD0JrkGtTqcGk6PFA6Wxurm8ktyckbXCIhPfByPoK9eFX2mHin6P0R5boOGLbS329Wcle+K/EniDWRdJe3Kzbt0UNvIVWMDsAP5nrXqHhbWpLnVNC1qUCObUBJpeoKBgGZAWjYj14I/GuV8SeFZfDWt6bqKwpFb3bmCQRnKq5HH0z/StSwzb6dKV4MOvWUy+xbaGqcQqdSnaC0sbRoyipOTu0/wDg3PaaKCME/WivjTUKMUlLQAEBgQeh4rEdDG7If4Titqs2/TbcbuzDNBvQetitRRRTOoaKWiigDTsV222f7xJqzUduNtvGP9kVJUnBN3k2FFFFBItGaKZK4iieQ9EUsfwGacVd2A8y+IGpJq2px6fpcCG/02TL38jYSIsPmixg78jGR0H1rhll1PTF/su8t1/s+6kWNJIXLLCC3zLk8hSM8HpVC/1bUItJhmtmdZ7tpbu4lUZIDOe/+elS6Vrn9u2kml6iQZZFwj4xv+vuOvvX22FhKhTUY7I5p0qFTSV1Jr5ehNdE3fjWzuCpCGQqg9FCZUY+mD/wKu402xhu5wrpNdynkQeZsQD+85HRfrnPYGuCs3km8QadJKcy7pPMI6b9pLfqQP8AgIr1vwqYxYzKoAk8zLkdTxxWePm4u6OrLYtUGvM1dPiuRMLeHZKI/lk42W8II+6qDlmwe57846VhXHgnWtKlZtA1CGW3JJW3umaNo+fuq65yo7Ajj1ruLSGKC1jjhGEAz7knkk+5NTnNcCqNFXaldOxwdtofjC6kCXtxaWsP8TJctI34AKP1NdPpXh+z0o+aoaa5I+aeTlvw9K16z9Y1W10XS59Qu5AkUKFj6n2HvS5m9ErFupNqzZzXja8UPBblwqxjexJwATwKz/DNssupGVukK7h9TwP61Jp/h46yja5rmZLqdTJb2ob93bKR8v8AvPjGT26Ck8KzCO4mVjgso/Sqk7QaR1UpXp2sd/o9rBeTukxJwuVXOM0atp62MyeUSY3GQD2I7VQjleJw6MVYcgjtUtzezXZUzOG2jAwMVmp0/Z8rWpyunUVXmT93sYmpandabIpTRr69gxl5bXaxT/gBO4/hV/R/Edjq8BktbgShDtdSCrxt6Op5B+tbNrqOmw2wWe1ZpAOW2bs15f8AEeQ6cf8AhJtHzb3lvMqFv+e8THG1x/Fg9M9q1hTi0knq/wCtSHObbco6L+tD1BXVxlSD9KGYKMsQB71w/hbxba+I9Pjmj/dXGPniz0PfFb5ct1JP1rCcpQfLJamsaPMrp6F+a8AG2Pk+tUs00muU8Sa28U/2KFyox85B5Y+n6j86iKlUlY6IU1HRFLx1dpf2N1aRsGjjt5MkdC23+mK8yv21/TtS0dYbhrYTWsQtZoWKpIrfMST3O5jmuzunElpdKvIWNxn8DU3iWS2Hwh0RXCm7kS2Fp/eEgxkj/gOc/UV6dF+zSha92cmNpptNPZfqaeo3V3r/AMPLxNRhVNQsnjkZk5RyrAh19MjOR65rLs0aZ4rZBlrzxBAiD1WEBmP4YrZsHP8Awi2tysOPL2j3bHT8yPzqTwppoufGb4G610GAwBuzXUvMh+oGRWM6ipwm+i/r8wrpRXKnuejnkk+tJS0V8uZCUUUUAFVNRXMaN6HFW6gvV3Wj+2DQXTdpIy6KKSmdwUUClHUUgNpRhVHoBS0UUjzmFFFFAC0yaPzYJIv76Mv5jFPpacXZ3EfOMEDPo9vCw+f7PJAR/tIzAj9ao6Zp8I8ItcsfLuBMXhkVcsHBwoGOTk8V2PibSn0jxbfWSLiO6c6hY56En/WJ+efzqloqRx6YUK4EVzJt3Dkc5/PBr7SFbmpqS66mlOmqvK32aOa07Uopddt2liMNwbna8Z7Eq276ZYivR9N1B9OuRIo3KRh19R/jXl9vp73tlqGurI3mw3G9F9QDk5/Aj8q7s3atbxXEeGSVQw+hGaMSlKxeXXjGSl11PTtP1JJ4RJbSgr3U9vqK0Vvjj5k/I15Tb6k1ttuLeQowIDYPTPr6iux0fW01AeVKAlwBnA6N9P8ACvKqUp09VsdcqUXqdFJfNj5VA9zzXkXxT8Ru2pWGjhyYkkSe49+flB9up/KvT5ZFijeRj8qgsfoK8esEXW9X1bV7pBIlxI0MYbkbBwa1wavJzl0OetTulCG7OgvfGE/h/TstM5h3bUVUDHJ7AnpXOaf44spbtTultJc/K74x+JH9astYXqWxtN9rc22Nq/aVbcF7A44OPWs9PAUN4WKecZG6C2T5F/PP867oxopPmHUeIUr00rdU/wDM9Fs/F7CIC5gEnHDxEDP4VU134hQ6Tpr3HkL5z/LbwM2WdvU46KP16V51d+D/ABloqqtmlzNbt0+ztux9V7Guu8CfDq4uroat4jdpJkPyW7tuKH1b39B2rGVChFc97oxliJS9xQaffojkJZfF+r3Q1C91aSyVjuBe48pVHsgNehaRa3ni+50+CQSS6TZus11dyJtFy6fdRPUZ5JHFejpplgihVtIMDuYwTVoAAYAwBUTxCla0bWM4x5U1FvXe5454u0GbwXr413S1ZdNuX3Txxj/Ut/eA9O+K7jQ9Xi1ewWVWUuAN208HPQj2NdBqVhDqenzWdwoMci4OR0968f0lrjwZ4lfTJtxti58nPp1ZP6ioklWhr8SOii+XTp+X/DnqleS63dNL4juQDg+awB/E/wCA/KvV43WWNZEYMrAEEdxXmN5YMfF90oXLCVwB6k4I/nWeFsm7m873SRbs9Jnn0m6ZAFSOF2Zj0ztPH5VVtfCmreIovDVys8UOmW+mxqrH5mVjncVX16DJr0GSzSy8PT2yD7tu4J9TtOTVTwRKJfBGkOD0tlX8sj+lae3kouUe5jViqlRJ9DI1ae2tbM6dYDOnaXGb2+kzuDFPmSMnuzMAx9gPWuj8A6W+meEbNp8m7vM3lyx6l5Pm5+gwKx/HSRw+EprG3jSN7+eK2RUULuZ3GenfANd2iLFGsa8KihR9AMVwY6r+5UV1f5HPVX7wdSUtJXkCCiiloASo7gZtpB/smpKbL/qH/wB00DW5jUUDpRTPQEFL3FIKWkBt0UinKKfUClpHnBRRRTAKWkpRQBz/AIv8NL4k0kRxOIr+2bzrSf8AuSDsf9k9D/8AWryeC5/0i4guoza3DS7J42HMNwOPybAx6/jXvFecfFDw/ELVfEcMILwYivUA/wBdATjJ91OMH0+levluK5X7Gez2CM3TfMtjyxftfhu+ningZ9NuWIcIMgZ4yPfnoa3NAYzaO1lIf3lrI0JP0OVP5VqWULRWwR5zOvVHYcle2T3+tY9tJ9l8Y3lvyEu4lkH+8vX+te7KXOn3OmNL2Uoyvo9Ldr/8EiuJJbWVi2dnKyL6jv8A4iuh0i9YxQXSt+8Q8keoOD+f9ajuLSO5jZWHLDGf8/hVHQgyLcQsMYZWx6ZGD+q1EmpQN4RlCpZ7M7vxhqf2Lwld3CHDSR7U+pFc14b0hhb2lgDtKxgu3oerH8zVjxfL59lotkTlZJEZh6gDP/staWiSC31kRvwzKU+hIyK5YrkpablRXvuXbQ6G30ixtlG23RmH8Tjcau4CjAAA9BTdwHeuU1bxxbWzNDpkaXkq8NKz7YVP1HLfhx71yQp1KrstQlNR3O4sbYFvOcZVfug9zWfo0rf2vqUYBCGVWA/3o1P868yl+I+vKxzrlnCB0jjt49o/PJ/WsnUfG17fxlL/AF5miPWO2AiDfXZyfzrvjgp2scEqt23L80e7yarp0UvlS39okn9xp1B/LNWldXQOjBlPRgcg/jXy8da0dPlW0LjufKXn86u6d4qt9PlD6feXmnv6xEhfxXlT+VaPAytozP2sP5kfStee+MNLXW9CbUUwl1bSFHZR0Ksdrfhj+dReFPiZDfzx6fq01s00mBBcwnaJG/usv8LemOD7VvaDjUNAvVcZWbLYPfLMa5XCVKWprTkmrmH4L1h7iE2VwNsi5wp/hYfeX6dx7Gr7adu8Ym42/LsSQ/Xaw/8AZRWLpdlKtsmoWqFrqyma1uUHVwh+VvrsIzXcLGpmE4yCYwuD9c/1NZ1moybj1Ou90mNvBusbgesTj/x015b4A+Iek6Z4eh0rVXaB7dmCSBSwZSc846dSK9SvGCWU7HoI2/lXIfCWytLrwa4ubO3maG+mVTLErEfdPBIpRqQhRlKauro48RKUakXHzLOlmfxr4jstV+zyw6DpjGW2My7WupugcA/wr2rvxS4AAAAAHQCivHxFd1pXtZLYzV73e7CiiiucYlLSUUAFNlP7iT/dNOqO4OLaQ/7NA47ox+1FLRTPQEpaSlpAa9s262jPtipKrWLZtyv901ZpHBNWk0FFFFMkKWkooAWq99Zw6jp9zZXC7obiJonHswwanpacZOLuhNXPD9OSewM2j3mReae5hcH+JR91x7EYrG8TX0VnrGkzZxJE5L8/wHj/ABr2zXvCGk+IpI5ryOWO6jXalzbyGOQL6ZHUexrm9V+GujW3hfV0soZZ7+S3YpPcyeZJlfmAB7dO1fRUMxoytzXuyp15unyW26+hzinIqrbxeVqtzjpJGrD8z/jUGh3ZvtEtpwf3mza2f7w4q/DtlZZx3Tbj05rrfu3R6kWqkYyXqSayfO1fTF6iO1Z/0A/qa0NcV9N1S0u048wR/wD1v1GPxrMuhnWI8/w2Qx+Lf/Wrp/G1if8AhFfthG0Qwbw56DADD9QPzrJ7xRnOaim2cZ448dpufTbUllAxKqnG4/3WPoO47/SvMbvUrq8b97KdvZF4UfgKrzTPPO8shy7sWYn1Jya6Xwh4fXVr1Hnt57hGlWGKGFD++kPRS3RR65Ir1aVGFKFkfP1K869S17I5gKxGQpP0FLHFJLIEjRndjgBRkn8K+h7XwfrifbrSK00/Tfsdss4jOZTIrBsAbMAcoQeT+NXR4M03TzpWoXviC3t1vGUTSLDDAdrRsw2sckcgDn1qvavsOdGhH7d/RHhlv4G8QXMYkSx2A9BLIqH8iazNS0fUdJl8u+tZISehIyp+hHBr3qWy8PNJrcMHiXUppYlBsXgbzASY84+VNrfPn8CKpazoy6hZwQ6dLqskcts3nx31vCQsuBtGW28Z3ZxnGBil7aSetjV0KE42gpX9NDwON2jkV0YqykEMOoNfRHwt8Q22taJ9mWVBfRKolgJw3AxuA7g9fY1xekfB15JFk1bUkCdTDaqST7bj0/Ku0g8FaNay+bFYrDHaLi3KEq+4DJcuOTz7+tcWMr0Zrlvqi8Nhq0HromTeHMweLPFFkD8kcsEg+pQg/wDoIrozcILsW3PmGMye2MgfzNcx4Kjaa613UXJYz3SwhjyW8tME/wDfTGr9pc/avGeoKpyltZxxf8CLsT/KvNqxvJ+SR6EG0vmXtYlEenSjuwx+Heuf+D3/ACJ90fXUZj+i1L4m1ERfao8/6uML9OC7H/0EUfB+Jk8AwyEf665mf9QP6VliI8uEb7tGOJ+KPz/Q72iikrxDMWikooAKKKXFACVBfHbakepAqeqWotxGnvmgumryRRoooFM7hB0ooHSikBbsHxKyH+IVo1jRuY5Ff0Oa2QcjI6GhnJXjaVwooopGIUtJRTAKWkooAWj6jI9KQUtCA8HgtTofizW9CbhIpzPAPWNuePwIq7bv5dxcQn2lX6Hr+oP51o/FaybTNf0jxLGp8pv9EuiPTqpP4E/lWRcyCKW3uwcop8tz/st0P4HFfWUZ+2pRn3X4o6sHU9xxf2X+DOh8Q2cccGl63bj/AEaWEQXGOkbcYP03DH/Aqi8SXN14gsbe2uZo106JUDWSMwa5K9dzfwgdgO/WtHwtdQXlvd6BfKskTg7UfoykdPyyPwrn5bWbRtVk0q5YuFBa2mbrJGOx/wBpeAfXg1Md7dUXyxcuSeqMqDwJ4ZnMhlub+DLZQZHA9Dwe9dTpul2mnWFrZQeJtSFraSebBCtwqLG/PIwuc8n86o0mK29vPuaLBUf5UaVzqGgJNJNfa600zqEdrjUXZmUZwCN3Tk8Y7mstvF/gnTmAgSF2HA8m13H8yKjuFt/LZrhIig6mRQQPzos9BvL9g2m6Iiq3SadBEp9wMbj+VNTja8iJwdPSHKvkTD4jJcfJpuh31wOxbEa/1rQ0rVtU1W6VbyS20yFv4Ih5jn23twPyNOTwN4oADA6af9klx+tRy6Brlq6pc6b1ON8Modfxzg/pUTnFr3dBU58ztKX6HbwQpBHtTPuSck/U0y+lWCwuZnOEjidyfYAmoNJs57KyEc83mNnIGchR6A1LqVob6zNp/wAs5mCyn/Yzlh+OMfjXl/b1ZcnbYzfDsZ0fwXbSTDEvkm4kB/vuSxH5tiszwrcJDa61rFw2Ea4Klj3Ea4P/AI8Wq74w1EWmniIDsZGUeg6D865i9l+y6Lp3h9G+ZEFxfNnjJJbB+rE/gtdcIOab7v8AAjltZGR4m1WQaLeXcpInuiQq9wX6D8B/KvWfB+lHRPCOlae4xJFbqZB/tt8zfqa8v8K6O3jbxUl06k6LpbhySOJ5eoA9u59vrXtlcmaVVGMaK9X+hx1JqpU5lstEFFFFeKISiiigAooooAKy7191yR2UYrTdhGjOegGaxSSzFj1JyaEb0I63Ep1NpwpnUNooopALWnZSb4Np6px+FZlTW03kzAn7p4NBnVjzRNWiiikcQUUUUwCilzRQAlLRRQBm69otr4h0S60y7H7qdMBgOUbqGHuDzXiNn9o028uPDerptu7bKDPSaPsR68fp9K9/6cVyvjbwTbeLLJJEcW+p2/NtcgdO+1sdV/lXqZfjFSfs5/C/wZKlKnLnj/w6PMUvZtMuIrncxls/vkdZIT/F9VOM/T3rttZMXiXRo7y0C/2ha4lRQfvY649QQSPxrzV9Sltbt9L1tVgv7aQotypDRsw4IJHGD0P9DVzw9rH2e8OmO5jeP5rZt3VTztB747HuK92pRbSmt0dNOvTqNJPf8zokYOoYZwRnmnpG0jqiKWZjgAd6QksxYnJJya0dDKDV4S5AHOM+uOK55OyuenfQ1dG8OR27C7v1WW5/5ZoeVi+g/ve9dTFcGFcRooJ6seSarClzXBKpJu9zllFS3LX2+bP3h+VPGobhtliDL7VSzRml7SXch0YPoTSCLO6JjtP8JHIqJmCqSTgDkmmNIsalnYKo5JJwBXK674iiaCWOKQJbqMySscZH+H86qEHUloXGPKc14s1fz9RhHJE0wIXOMxpz+GSB+dY+nRzeL9SnsIJWFvzNqF2n8foie3GB7CuO1rWJ9a1aR4NwjYeTEg67f/r9TXuHgbw6vh/wnHE4H2m4BmnPuRwPwFetUSoU13PP9s682o/Cjg/APiG78K2MN2JHm0qSVheW558sZx5qehHGR3Fe9RyJLGskbB0cBlYHgg9CK8A+HqxXavZTqGiaSWN1PdWXmvR/hxqMsUF/4YvJC11pEm2Jm6vA33D+HT8RWGeYBeyjiIL1/wAzx8Bi2606M+j09DuqSlor5U9gSilooASiigkAEngDrQBU1CXbGIh1bk/Ss6pJpPOlZ+x6fSo6Z3U48sbAKWkpwoLGiiiigApaSigDUs5vMi2E/Mv6irFY8chjkDr1H61rRyLIgZehpM5KsLO6HUUUUGIUUUUAFLRRQAVz/jXXm8OeFL2/iP8ApJURW4/6aPwv5cn8K6CvL/ixd/aNS0DRweGle7kHsowv/s1duXUPb4mEHtcwxNT2VKU+yPMtctI4LLT4ZWYr5pDv1JJHzN9c81g3tlc6VfCJiwdTmJ1/i54IrpfGKE2Nuf8Appn9DVqKO31nQ7Z7gZVl2lx1ikHGa+5xP7uXkeVlMHiKLd/e3/EfoviyG8iFrqLiC5HAk6Kx/of0reF5NDgyRGVOolh5/Nf8M1yN1o5vYZLedFS/hHyyjgTL2J/kfeudivdQ0yUxxTzQspwU3cA/TpXD7GM3eJ7v1yrQSVRXXf8AzPZrPxqLdQkl1G6j+GcFGH4mtWLxzpzD52jH+7MprxOHxZrOQiyrKT0BiBJpsnizV2z+9jT/AHYlFZSy9Nlf2lS6r8P+Ce7J4u0+QZiDyf7pH+NVb7xnBaxlmWKEf3ppAP0rwmXXtVnGHvp8eittH6VnvK8jFnZmY92OTRHLY31ZnLNI292J6Rr/AMRzMDHbM07f3iNsa/Qd64i+1i+1BfJklcozbigOd7ep9fbsO1ZsaNJIqIpZmOAB3rrdI0QwSISoku2+6P4U9/8A69dcaVKitEcqqVsVK17I1vh/4U+1atHJcpny/nkz/CP7v1Ne3TOsUEjuQFVCSfQAVjeFdITSdJUYJll+d2PU1m/EjWP7I8GXWxts93i2j9fm+8f++Qfzrx6tR166SPTUI4ek7dDgfhkpk1CeUfc3uw/L/wCvXWanN/wjvjTR/EIO23nb7Deemxvusfof5Vj/AA2tDDaByMFoy5/4EeP0FdV4j0sax4fvbHALvGTH7OOV/UfrX1NSgquGdKXVH5+sV7PHOa7nofQ4PWivC/CPizxDpWmx3ENxJqdpGSlxZXLZkjI6+W3Xp2NexaHrlh4h0uO/06XfC/BU8Mjd1YdiK/P8Zl9XDO71Xc+woYmFa6T1RpUhpaK4DoEqnfz4XygeTy30qzPKsMRc/gPU1jsxdyzHJPJoRtRhd3YlFFFM6wpRSUtACUUCigAooooAKsWtx5D4b7h6+3vVeloE0mrM2xyMjkGis60uvLOxz8h6H0rR7VJxTg4uwUUUUEBS0lZHiPxHp3hjSpL7UJlXCny4Qw3zN2VR3+vatKcJTkoxV2xNpK7IfEvi/SPCtqsmoTEzSA+TbRDdJJ9B2HueK8dufEMni/xfc6tJatapBbrbxws24rznk46nmsi7v7rVtRuNZ1Nt13P82O0SdkX0AFTeGULWElw33ppS2fYcf419tlWWQw8lN6yPncxxrqUpqO2xZ8Z2mNAtZh0wrn8yKyvBt4Mz6fJgq43oD37MPyruNbsBfeD4ExzsKZ9ycj9RXklncyadqMU6gh4XyR/MV6eNp8xnkOJVP5P8Gek/Z9rrGxJC8wueoHdT6/59Kw/FWjCe1N9Av72MfvAP4l9fqP5V0cUsd3bRyxnMcihlIqQqGUqwBBGCPWvGjNwlc+2q0YVabXc8otZWtrqKdDho3DD8DXWeL9JiNumqW6BSSBKFHUHo39K5/WtNOnXbKB+7YkL7Edv5fnXcX4D+DpN//Pop/HArrqTtKMkeRQo3hUpy6anmmPSpIInuLiOFB88jBV+pNek+FfCthdW9oHgjlmuFDs8oyFyM8CrHirwpZ+H7rT7uOONT56ZaMEAjdg5H4ipeMhzci3JWXyUVJs0b7wVZaZ4e0n7IiedkvLOw+Z2K9c+g5wKveGdARrocFkXDSue/otdMLVtT8M2sSEeYFQgn24P6Vp2FlHYWqwx845Zv7x9a8ipiZcrTep7MIQpxtFFgDArxn4oX7614us9EgbKWq/Pjs7ck/goFetarqMWl6dNeTEbY1Jwe59K8N0HzdS1G+1q6y0lxI20n3OT/AEFdOU4f2lXmeyPJznE+ww77s9F8KWwgsJHUYBYIv0UVvGq2nQfZtPgixghcn6nk1Zr6w/Ob3dzzO4QeH/Htxan5bTUcSx+gc/8A18j8RV+HU7jwZrJ1uzjaWwnIXULVf4h2kX0Yf561J8TdOaTR7bU4h+9spRkj+6x/oQPzqWF0vbGN2UMk0YJU9CCORXmYqhCd4SWjPYp4iVPkrx32fyPQND8d+HPEO1LLU4lnb/lhP+7k/I9fwzXRsQilmOAOTmvnSHw7p731zpdzEVdP31vMhwxjPY9iQa2rS88WeHoxHYaiNSsV5FrdnkD0B/8Ar/hXzOIyTrRl8mfQUs1pOSjU0PW7iczyZ6KPuioa47SPiNpd3MtrqcUul3h42XA+Qn2b/GuwR1kQOjKysMhlOQR7GvGrYapRdqisfQUqtOcb03dC0UUVgbBSikpaYCDpRSUtIAooooAKKKKAFq1a3Ziwj8p2PpVSiixMoqSszcBBGQQQe9V77ULPTLR7u/uora3T70krbR/9c+1efa38S7fSXex0dU1C9HBAP7mI+rMOv0FecahcX2uXgvNcvHvJ/wCBDxHH7KvQV6+DyirX96fux/E8TF42lQfLe7O8134svcb7bwvaGTt9vuV2oPdU6n8fyry+6+1alrUlzqF3LeTrgySynOWPYegHpWm8iQRljgKoJx9KpWin7OHb78hMjfU19LhsFRw6tBfPqeLVxtSqm3ohl+5jsJW77cfnW7osXk6PapjB2bj+PNczqc6taFEJOWC5A4/OuwgTy4I0/uqB+lenh17zZ52L92ik+rOwgt/tPhdYh94xZX6g5H8q8d8T2P2fUPtCLiObn6N3/wAa9s0b/kD2v+7/AFNcT4u0YP8AarcLz/rYf54/mK3qw5onJga/sa2uzOW8J6yIZP7OuGxG5zEx7N6fj/Ou2ryDlW7gj9K9A8M65/aUBtrhv9KiXOT/ABr6/X1rw8TS+0j9By7F3SpT+RF4utQ+nrKB83mqPx5H+fpWn4gga38E3cvRF8qAe5JH9BUmp2/2mCCIjINxGT9Acn+Vanj+2+zfDe2i24eW6jZvqdx/wrm9prGPmdVePIpyXVFf4f6hELLTpZXCrGGiYnsRkDP5ipfi1eqLC2RHDHcp4Oe+f6CvNrPUr/wzdS25RSCfnifofQg1q3tzdatodxe3EKRIECwoue7DLf0H41Tw1qqn0OZYlTouFveSPavCV2Lvw9byA5wMfgeR/Ot3tXnvwsvWl0aa0kbL27bCP904/liuv1vUPsGnMyn96/yx/X1/CvKrU2qzijtpy54qXc8/+JmttNENNtny0r+SoB6n+I/0qp4f01RNaWaD93Hjd9ByTWDZlte8S3F6CDb2v7qEswAz65PHqfxr0jQdKayiaabb5kgwu05AX619ZluHVGl5s+F4gxftq3JHaJr0UUV3nz5j+LYRN4R1SPGf9HZh+HP9K5bw9KZvDti5/wCeQX8iR/Su11eLztGvo/71vIP/AB015t4Vs45tAhlSSWGYM6743PPPcHg/lXHid0z0KSUsO0+j/Q0dbBtzaamvW2lAk9424b+hrVqlPHNcafd2lwqsWhZRInCtxxx2NM0+8D6VYyueZVRSf9rGP5iuYUlemvIs3Vnb3kRiuYUlQ9nGaoWltq3hxzLoF8TBnLWNyd0bfQ9q1qqyahBFcmGQlCMfMelROnCouWauisPi61CV6bOm0Hxtp+rTCzulbT9SHBtpzjcf9hujfzrpq8yvtNtNSh8u6hWQD7rdGX3B7UWl94m0UBLK9TUbVelve/fA9A45/OvBxWS681F/Jn1ODz+nNctbR9z06iuItfiVYxMIta0+80yToXK+ZH/30Of0rprbxDo13CJoNVtGjPQ+cq/oea8arg69J2lFnuU8VSqK8ZJl8UtIKWuU6AoooJCgkkADkk9qFqAUVxmufEjStNka105G1O9HG2E/u1Pu3+FcRqGueINd3f2hqLW9u3/LranYuPQnqa9PDZTWratcq8zz8TmVCho3dnpes+M9D0UmOe8Wa5HS3t/3khP0HA/GvPNd8Uav4jDRMzadpp/5YRt+8kH+239BWLEltaLtgiUHuR3+ppGdpDyc+gFfQYTKqNB8z1fmeBis2q1lyw91CxCKBBDbRhR7CrAAiUsxye5pI4xEu5uvf2qCaXfknhRXqeh5F3JkN45ktZ2PfEa/iRmnSqSRH0jA5A6n2+lRzc2lup6vMhP55qeX/WN9aOps3ZIo3yhjaxAYDTKMV2WOa5J08zULBPWcV1nJNdeH6nHjn7sF6nZ6U6Q6JbvIwVFTJYngcmsTVPEeg3epRWGLme5wcNAn3fY5OT9MVzfjfxDLY2lrolrJtkRA0zKeRxwK86DsH3hjuznOec0VK3K7IvCZdzw9pU67HTeLdAFlOb+yPmWMrYJAwY37qw7VgafePY38N0g5jbJHqO4/Kum0vxm2w2msp9st3Xy2kx+82+h/vj68jsazdf0FdPCX1lKLnTLg/uZl52n+63oa5qijJXR6uHnOk1Ce62ff/gnotsUuTCVOUkK4Psa3viZAH8KwADiO9h/LJFcT4SvDLo9q5OWgbYf+AnI/SvTPFln/AGt4dktYhmSQLNDj+JkIfH4gGvn63uVY36M+wlL2tFPujgbvS7O9dXnt0ldT8pIqDVrdf7KMIA/eSRpgf74rV96o3v728srYd5POb/dQf4kVtGbuazhHldlqyz4Dk+x+M9WsxwkjeYo/3hn+lT/ETWnVJILdiZGP2aEDux+8aoWfmWXip7uE4Y2qkH0YMR/KszzG1LXZ74lTFZ7orcyH5d/V5D7L/hWlHD+1xCl0sebjK/1XDyfW7S+Y3yLbTNHXTmWLZGBJdSuuVXP82PQD05qhoPjc6HqhiiEz6Q7cwSNuMf8AtJ6fSsPW9W+3SmC2LC0jYsCfvSt3dvc/oKxq9mU9fd6HzNPDJxftNbn0tBPFdW8c8EgkikUMjr0IPepK8x+GniUox0S6f5Wy1uxPQ90/HqPxr06uuEuaNzwMTQdCo4sjuV3Wky+sbD/x015p4KH/ABTqf9dn/pXpzDcrD1BFeY+DBjQmX+7cSD+Vc2J6GlH+BP1X6nQYycVzETmPwupX71tMcf8AAZDXUelcvGN2h6qn924m/nmuVGtD4X6o6WORZY1kU5VgGH41j6zCPOWTHDrg/hS+HLvz7AwsfmiPH+6eRV7UYfNs3x95PmFPZmVuSdjK0fUmin+w3DZH/LNj6dvwroK4u8RhGJ4xmSI7vqO4rpNJv1vbVfmy4HX1HrQ11Lqw050XnRZEKOoZT1VhkGsebwno08pka1Ck9kcqPyrapakzhVnD4XY9BGKKaOtGTX5xzn6tYcOoHqa8a8R6xrOv3c9veXP2ewSRlFrbnAYA4y5717AzHB57V4rrw8iW5ZCcmZuv1r6LIacKk5NrY8HOq1SnFKDtcqRJb2keyFFUeij+Zpjys/U4HpQF4HXpTcV9Sj5W/NqwqxFGEG9uv8qbborScin3nAVR0zR5CbIZZvMOB90VWumxAQOp4qYUyZFZgp6UyobjJyCLIdvNX+VWJf8AWH3qvMo860HbzP6VduEVWGB2qS6jtFMqQjdrmnr6MzfpXUPdR2SNczfchBcj1x0H51zdv8uu2mP7rfyqx4skZNKRVOA7gN74rspO1NyOapBVatOL/rVnIX15Lf3k11O26WVy7H61WzR2orl1ep7ySSshyjJA967XSImsvO026BkspvkuE6gA/clX0I7/AEri0++K9LsFWS1QsoLeSOcc1rRhdnn4+u6UVbqQeG7dtMlv9LnP72GbeP8AaQjAYflXqWjOdT0RYkkCXNqw2MRnBHKkj0xwfxrzHU2K32iXQ4maVoGb+8noa7fw7O8GoKsZwJEww9a8PNKSpybXqfVZPXeJwalLdaHQ3Xh6xvH8xkaKRuW8o8E1j6p4VtbOCS9tPMadVAkLtnKD09PWutJPmAdsVBdfNZT55+Rv5V5EK001qeknqjyx22TXE/ouxT9ASf1NZulaNPqfh+ztkVzHMglnK8bsnIUt2GeT+Fat4oEFwAOBE2PyrY8Fuf8AhEtKXAw0Yz+Zr6rLIKTdz5nimc6UYcr6sw4fBK6fBJJDBCW2/Mu4sxHpzXAeItHWwlE8AxBIcbf7h9PpX0EqL6V4143bFsygDH2g9vc16ValGMLo+XwOIqusuZ3ucVBNJbzJLGxWRGDKw6givdPCPiNNe01C5AuUGJB6kV4MOtdf4KuJbLU7d4XI81nVwehA6Vz0ZWlY9PMKKqUubqj20dR9a818NIYYdQgP/LK9kX9a9LHQfUV59o6g32t9v+JhJ0qsVokzxqDbpzXoaNcvZn/QNaU/8/M/H4V1mBmuV05Q+mawzDnzpefwriTuzegtJL0/MztAuTBqEIJ+WRQjf5/Ku06jB71wOl/8flr/ANdBXoA61UnqGKXvo5eaPZI8Z7EiqWmTvp2ptFyVHzIPVT1H+fStm+jX7bL16/0rJuYl+1Wr87vN259qafQ0p+9Fp9jsEdZEV0OVYZBp1VrFQtsACcZNWCOam5x8up//2Q==" alt="Image: 2.jpg"> |
|
|
<p>Path: ./2.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.26)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.076 <span class="mean-sub-score-paren">(2.57)</span> <span class="raw-score">(2.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.008 <span class="mean-sub-score-paren">(0.34)</span> <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">0.21 <span class="raw-score">(2.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.453 <span class="mean-sub-score-paren">(4.35)</span> <span class="raw-score">(4.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.050 <span class="mean-sub-score-paren">(2.14)</span> <span class="raw-score">(2.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.27)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.65)</span> <span class="raw-score">(3.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.043 <span class="mean-sub-score-paren">(2.00)</span> <span class="raw-score">(2.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.35)</span> <span class="raw-score">(1.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.71)</span> <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.72)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(0.00)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(0.88)</span> <span class="raw-score">(2.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">-0.79 <span class="raw-score">(-0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(0.04)</span> <span class="raw-score">(1.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.093 <span class="mean-sub-score-paren">(2.76)</span> <span class="raw-score">(2.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.22)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.53)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">-0.10 <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.52)</span> <span class="raw-score">(0.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(0.99)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.12)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.35)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.10)</span> <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.68)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.38)</span> <span class="raw-score">(2.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(0.00)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.007 <span class="mean-sub-score-paren">(0.21)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.09)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.103 <span class="mean-sub-score-paren">(2.86)</span> <span class="raw-score">(2.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.48)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.07)</span> <span class="raw-score">(0.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.18)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.15)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.03)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.06)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.10)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">1.67 <span class="raw-score">(1.5)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="sample"> |
|
|
<h2>3. 3.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,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" alt="Image: 3.jpg"> |
|
|
<p>Path: ./3.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.007 <span class="mean-sub-score-paren">(-1.20)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(-0.32)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.080 <span class="mean-sub-score-paren">(1.22)</span> <span class="raw-score">(1.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">-1.64 <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(-0.12)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.025 <span class="mean-sub-score-paren">(0.05)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(-0.27)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(-0.14)</span> <span class="raw-score">(3.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(-0.45)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.026 <span class="mean-sub-score-paren">(0.10)</span> <span class="raw-score">(2.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.023 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.52)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.033 <span class="mean-sub-score-paren">(0.33)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.024 <span class="mean-sub-score-paren">(0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.039 <span class="mean-sub-score-paren">(0.49)</span> <span class="raw-score">(1.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">-0.02 <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.038 <span class="mean-sub-score-paren">(0.47)</span> <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(-0.08)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.019 <span class="mean-sub-score-paren">(-0.22)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(-0.09)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">-0.86 <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.031 <span class="mean-sub-score-paren">(0.28)</span> <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.032 <span class="mean-sub-score-paren">(0.30)</span> <span class="raw-score">(0.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.037 <span class="mean-sub-score-paren">(0.43)</span> <span class="raw-score">(1.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.025 <span class="mean-sub-score-paren">(0.07)</span> <span class="raw-score">(1.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.68)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.010 <span class="mean-sub-score-paren">(-0.87)</span> <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.024 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.023 <span class="mean-sub-score-paren">(-0.03)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.056 <span class="mean-sub-score-paren">(0.87)</span> <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(-0.09)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.028 <span class="mean-sub-score-paren">(0.16)</span> <span class="raw-score">(0.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(-0.41)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.024 <span class="mean-sub-score-paren">(0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(-0.11)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.019 <span class="mean-sub-score-paren">(-0.22)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.020 <span class="mean-sub-score-paren">(-0.15)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.023 <span class="mean-sub-score-paren">(-0.02)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.022 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(-0.10)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.024 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">0.14 <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="sample"> |
|
|
<h2>4. 4.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,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" alt="Image: 4.jpg"> |
|
|
<p>Path: ./4.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.24)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(0.19)</span> <span class="raw-score">(0.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.32)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">0.07 <span class="raw-score">(2.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.593 <span class="mean-sub-score-paren">(4.71)</span> <span class="raw-score">(4.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(1.37)</span> <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.27)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-1.04)</span> <span class="raw-score">(3.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.057 <span class="mean-sub-score-paren">(2.37)</span> <span class="raw-score">(2.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.56)</span> <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-0.78)</span> <span class="raw-score">(0.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(0.54)</span> <span class="raw-score">(1.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(0.00)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.039 <span class="mean-sub-score-paren">(1.99)</span> <span class="raw-score">(3.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">-0.80 <span class="raw-score">(-0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(0.75)</span> <span class="raw-score">(2.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(0.52)</span> <span class="raw-score">(0.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.059 <span class="mean-sub-score-paren">(2.41)</span> <span class="raw-score">(2.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.45)</span> <span class="raw-score">(0.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">-0.41 <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.74)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.054 <span class="mean-sub-score-paren">(2.32)</span> <span class="raw-score">(2.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(1.05)</span> <span class="raw-score">(1.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.64)</span> <span class="raw-score">(0.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.40)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.67)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.42)</span> <span class="raw-score">(2.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.09)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.46)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(0.79)</span> <span class="raw-score">(2.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.17)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.15)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.02)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.06)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.10)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">0.19 <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="sample"> |
|
|
<h2>5. 5.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,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" alt="Image: 5.jpg"> |
|
|
<p>Path: ./5.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.053 <span class="mean-sub-score-paren">(1.13)</span> <span class="raw-score">(2.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.098 <span class="mean-sub-score-paren">(1.75)</span> <span class="raw-score">(2.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(-0.68)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">-0.84 <span class="raw-score">(1.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(-0.14)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-3.19)</span> <span class="raw-score">(0.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.45)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.32)</span> <span class="raw-score">(1.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.116 <span class="mean-sub-score-paren">(1.92)</span> <span class="raw-score">(3.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.010 <span class="mean-sub-score-paren">(-0.53)</span> <span class="raw-score">(0.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(0.00)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-1.25)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">0.15 <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-1.19)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.028 <span class="mean-sub-score-paren">(0.50)</span> <span class="raw-score">(0.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.22)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.010 <span class="mean-sub-score-paren">(-0.50)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">0.50 <span class="raw-score">(2.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-1.22)</span> <span class="raw-score">(0.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(-0.06)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.23)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.23)</span> <span class="raw-score">(1.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-1.10)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.052 <span class="mean-sub-score-paren">(1.12)</span> <span class="raw-score">(1.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.013 <span class="mean-sub-score-paren">(-0.28)</span> <span class="raw-score">(2.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.032 <span class="mean-sub-score-paren">(0.63)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.076 <span class="mean-sub-score-paren">(1.50)</span> <span class="raw-score">(1.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(-0.09)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(0.07)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.030 <span class="mean-sub-score-paren">(0.56)</span> <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.17)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.030 <span class="mean-sub-score-paren">(0.57)</span> <span class="raw-score">(0.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(-0.15)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(-0.03)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.020 <span class="mean-sub-score-paren">(0.17)</span> <span class="raw-score">(0.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.088 <span class="mean-sub-score-paren">(1.64)</span> <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(0.08)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">1.31 <span class="raw-score">(1.2)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="sample"> |
|
|
<h2>6. 6.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,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" alt="Image: 6.jpg"> |
|
|
<p>Path: ./6.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.008 <span class="mean-sub-score-paren">(-0.60)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.011 <span class="mean-sub-score-paren">(-0.32)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.007 <span class="mean-sub-score-paren">(-0.72)</span> <span class="raw-score">(-0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">-0.69 <span class="raw-score">(2.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.013 <span class="mean-sub-score-paren">(-0.14)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.016 <span class="mean-sub-score-paren">(0.10)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.170 <span class="mean-sub-score-paren">(2.43)</span> <span class="raw-score">(2.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-2.22)</span> <span class="raw-score">(1.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.010 <span class="mean-sub-score-paren">(-0.41)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.036 <span class="mean-sub-score-paren">(0.89)</span> <span class="raw-score">(2.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(-0.51)</span> <span class="raw-score">(1.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.024 <span class="mean-sub-score-paren">(0.48)</span> <span class="raw-score">(1.2)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(0.01)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.017 <span class="mean-sub-score-paren">(0.14)</span> <span class="raw-score">(1.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">-0.41 <span class="raw-score">(-0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(0.18)</span> <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.08)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.22)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(-0.53)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">0.44 <span class="raw-score">(2.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.007 <span class="mean-sub-score-paren">(-0.81)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.06)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.023 <span class="mean-sub-score-paren">(0.45)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.006 <span class="mean-sub-score-paren">(-0.87)</span> <span class="raw-score">(0.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.005 <span class="mean-sub-score-paren">(-1.08)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.036 <span class="mean-sub-score-paren">(0.88)</span> <span class="raw-score">(1.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.012 <span class="mean-sub-score-paren">(-0.20)</span> <span class="raw-score">(2.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.044 <span class="mean-sub-score-paren">(1.08)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.170 <span class="mean-sub-score-paren">(2.43)</span> <span class="raw-score">(2.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.023 <span class="mean-sub-score-paren">(0.43)</span> <span class="raw-score">(0.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.010 <span class="mean-sub-score-paren">(-0.44)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.037 <span class="mean-sub-score-paren">(0.90)</span> <span class="raw-score">(2.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.020 <span class="mean-sub-score-paren">(0.28)</span> <span class="raw-score">(0.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.057 <span class="mean-sub-score-paren">(1.34)</span> <span class="raw-score">(1.5)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(-0.02)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(-0.06)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.029 <span class="mean-sub-score-paren">(0.67)</span> <span class="raw-score">(0.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.015 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">0.17 <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
<div class="sample"> |
|
|
<h2>7. 7.jpg</h2> |
|
|
<div class="sample-content"> |
|
|
<div class="image-container"> |
|
|
<img src="data:image/jpeg;base64,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" alt="Image: 7.jpg"> |
|
|
<p>Path: ./7.jpg</p> |
|
|
</div> |
|
|
<div class="predictions-container"> |
|
|
<h3>Predicted Scores (Softmax / Mean Subtracted / Raw)</h3> |
|
|
<div class="dimension-grid"> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_affection_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-0.86)</span> <span class="raw-score">(0.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top1"> |
|
|
<span class="dimension-name">model_amusement_best</span> |
|
|
<span class="dimension-score ">0.584 <span class="mean-sub-score-paren">(5.05)</span> <span class="raw-score">(5.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top3"> |
|
|
<span class="dimension-name">model_anger_best</span> |
|
|
<span class="dimension-score ">0.075 <span class="mean-sub-score-paren">(2.99)</span> <span class="raw-score">(3.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_arousal_best</span> |
|
|
<span class="dimension-score ">1.70 <span class="raw-score">(4.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_astonishment_surprise_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.16)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_awe_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(0.02)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_bitterness_best</span> |
|
|
<span class="dimension-score ">0.018 <span class="mean-sub-score-paren">(1.56)</span> <span class="raw-score">(1.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_concentration_best</span> |
|
|
<span class="dimension-score ">0.000 <span class="mean-sub-score-paren">(-3.77)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_confusion_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-0.48)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contemplation_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.90)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contempt_best</span> |
|
|
<span class="dimension-score ">0.039 <span class="mean-sub-score-paren">(2.36)</span> <span class="raw-score">(2.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_contentment_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.03)</span> <span class="raw-score">(0.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disappointment_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-0.75)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_disgust_best</span> |
|
|
<span class="dimension-score ">0.014 <span class="mean-sub-score-paren">(1.30)</span> <span class="raw-score">(1.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_distress_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.24)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_dominance_best</span> |
|
|
<span class="dimension-score ">1.31 <span class="raw-score">(1.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_doubt_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.22)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item highlight-top2"> |
|
|
<span class="dimension-name">model_elation_best</span> |
|
|
<span class="dimension-score ">0.107 <span class="mean-sub-score-paren">(3.36)</span> <span class="raw-score">(3.4)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_embarrassment_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.22)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_numbness_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.23)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_emotional_vulnerability_best</span> |
|
|
<span class="dimension-score ">-0.18 <span class="raw-score">(1.6)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fatigue_exhaustion_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.46)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_fear_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.07)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_helplessness_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.25)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_hope_enthusiasm_optimism_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-0.77)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_impatience_and_irritability_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(0.85)</span> <span class="raw-score">(1.9)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_infatuation_best</span> |
|
|
<span class="dimension-score ">0.002 <span class="mean-sub-score-paren">(-0.42)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_interest_best</span> |
|
|
<span class="dimension-score ">0.000 <span class="mean-sub-score-paren">(-2.31)</span> <span class="raw-score">(0.3)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_intoxication_altered_states_of_consciousness_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(0.00)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_jealousy_&_envy_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(1.70)</span> <span class="raw-score">(1.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_longing_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.10)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_malevolence_malice_best</span> |
|
|
<span class="dimension-score ">0.020 <span class="mean-sub-score-paren">(1.70)</span> <span class="raw-score">(1.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pain_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.01)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pleasure_ecstasy_best</span> |
|
|
<span class="dimension-score ">0.021 <span class="mean-sub-score-paren">(1.72)</span> <span class="raw-score">(1.8)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_pride_best</span> |
|
|
<span class="dimension-score ">0.007 <span class="mean-sub-score-paren">(0.65)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_relief_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(0.03)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sadness_best</span> |
|
|
<span class="dimension-score ">0.001 <span class="mean-sub-score-paren">(-1.23)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sexual_lust_best</span> |
|
|
<span class="dimension-score ">0.009 <span class="mean-sub-score-paren">(0.84)</span> <span class="raw-score">(1.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_shame_best</span> |
|
|
<span class="dimension-score ">0.003 <span class="mean-sub-score-paren">(-0.15)</span> <span class="raw-score">(0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_sourness_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.02)</span> <span class="raw-score">(-0.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_teasing_best</span> |
|
|
<span class="dimension-score ">0.010 <span class="mean-sub-score-paren">(0.95)</span> <span class="raw-score">(1.0)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_thankfulness_gratitude_best</span> |
|
|
<span class="dimension-score ">0.004 <span class="mean-sub-score-paren">(-0.04)</span> <span class="raw-score">(0.1)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_triumph_best</span> |
|
|
<span class="dimension-score ">0.008 <span class="mean-sub-score-paren">(0.72)</span> <span class="raw-score">(0.7)</span></span> |
|
|
</div> |
|
|
<div class="dimension-item "> |
|
|
<span class="dimension-name">model_valence_best</span> |
|
|
<span class="dimension-score ">2.10 <span class="raw-score">(1.9)</span></span> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</div> |
|
|
</body> |
|
|
</html> |
|
|
|
