Files
MastersThesis/thesis_output/presentation/slides/09_search_space.html
sergio 125b16c8f7
Some checks failed
build_docker / essential (push) Successful in 1s
build_docker / build_paddle_ocr (push) Failing after 5m31s
build_docker / build_easyocr (push) Failing after 7m40s
build_docker / build_doctr (push) Has been cancelled
build_docker / build_doctr_gpu (push) Has been cancelled
build_docker / build_raytune (push) Has been cancelled
build_docker / build_paddle_ocr_gpu (push) Has been cancelled
build_docker / build_easyocr_gpu (push) Has been cancelled
presentation
2026-04-19 13:34:48 +02:00

44 lines
3.4 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<section>
<h2>Espacio de Búsqueda: 7 Hiperparámetros</h2>
<div class="two-columns-60-40">
<div>
<table class="data-table" style="font-size:0.6em; margin: 2px 0;">
<thead><tr><th>Parámetro</th><th>Tipo</th><th>Rango</th><th>Descripción</th></tr></thead>
<tbody>
<tr><td><code>textline_orientation</code></td><td><span class="tag bool">Booleano</span></td><td>True / False</td><td>Orientación de líneas de texto</td></tr>
<tr><td><code>use_doc_orientation_classify</code></td><td><span class="tag bool">Booleano</span></td><td>True / False</td><td>Clasificación de orientación</td></tr>
<tr><td><code>use_doc_unwarping</code></td><td><span class="tag bool">Booleano</span></td><td>True / False</td><td>Corrección de deformaciones</td></tr>
<tr><td><code>text_det_thresh</code></td><td><span class="tag cont">Continuo</span></td><td>[0.01, 0.50]</td><td>Umbral binarización probabilidad</td></tr>
<tr><td><code>text_det_box_thresh</code></td><td><span class="tag cont">Continuo</span></td><td>[0.01, 0.90]</td><td>Confianza caja de texto</td></tr>
<tr><td><code>text_rec_score_thresh</code></td><td><span class="tag cont">Continuo</span></td><td>[0.01, 0.99]</td><td>Confianza del reconocedor</td></tr>
<tr style="opacity:0.5"><td><code>text_det_unclip_ratio</code></td><td><span class="tag fixed">Fijo</span></td><td>0.0</td><td>Expansión de cajas (no explorado)</td></tr>
</tbody>
</table>
<div style="display: flex; gap: 8px; margin-top: 8px; font-size: 0.5em;">
<div style="flex:1; background: #FFF3E0; border-radius: 6px; padding: 6px 10px; line-height: 1.35;">
<strong style="color:#E65100;">Discretos / Booleanos (3)</strong><span style="color:#E65100; font-weight: 700;">True | False</span><br>
Solo <strong>2 valores</strong> por parámetro (8 combinaciones). Interruptores on/off de módulos del pipeline. Decisiones <em>arquitecturales</em>: cambian <strong>qué</strong> se ejecuta.
</div>
<div style="flex:1; background: #E8F5E9; border-radius: 6px; padding: 6px 10px; line-height: 1.35;">
<strong style="color:#2E7D32;">Continuos / Float (3)</strong><span style="color:#2E7D32; font-weight: 700;">0.01 ← → 0.99</span><br>
Valores reales muestreados uniformemente. <strong>Infinitos valores</strong>, grid search inviable. Ajustan <em>sensibilidad</em> de detección y reconocimiento.
</div>
<div style="flex:0.5; background: var(--unir-gray); border-radius: 6px; padding: 6px 10px; line-height: 1.35;">
<strong style="color:#888;">Fijo (1)</strong><span style="color:#888; font-weight: 700;">0.0</span><br>
Constante en todos los trials. Trabajo futuro.
</div>
</div>
</div>
<div>
<img src="figures/figura_2.png" alt="Ray Tune Cycle" style="width: 100%; border-radius: 8px;">
<div class="fig-caption">Ciclo de optimización con Ray Tune y Optuna</div>
<div class="highlight-box" style="font-size:0.58em; margin-top:8px; padding: 10px 14px;">
<strong>Algoritmo:</strong> TPE (Tree-structured Parzen Estimator)<br>
<strong>Trials:</strong> 64 | <strong>Concurrencia:</strong> 2 workers<br>
<strong>Métrica:</strong> Minimizar CER<br>
<strong>Combinaciones:</strong>× ∞³ = espacio mixto discreto-continuo
</div>
</div>
</div>
</section>