unir/MastersThesis
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

plain image manifests
Some checks failed
build_docker / essential (push) Successful in 0s
Details
build_docker / build_paddle_ocr (push) Failing after 4m7s
Details
build_docker / build_easyocr_gpu (push) Has been cancelled
Details
build_docker / build_doctr (push) Has been cancelled
Details
build_docker / build_doctr_gpu (push) Has been cancelled
Details
build_docker / build_raytune (push) Has been cancelled
Details
build_docker / build_paddle_ocr_gpu (push) Has been cancelled
Details
build_docker / build_easyocr (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Sergio Jimenez Jimenez
2026-04-21 20:54:59 +02:00
parent 5351d4a57b
commit 569a7bca4a
7 changed files with 110 additions and 90 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
thesis_output/presentation/slides/05_script.md
View File

@@ -12,7 +12,7 @@ OE2: preparar un dataset estructurado de 45 páginas con ground truth extraído
OE3: identificar los hiperparámetros críticos mediante análisis de correlación de Pearson.
OE4: ejecutar 64 ensayos automatizados de optimización usando Ray Tune con el algoritmo Optuna TPE.
OE4: ejecutar 64 ensayos automatizados de optimización usando Ray Tune con optimización bayesiana — concretamente, el algoritmo TPE de Optuna, que construye un modelo probabilístico del espacio de búsqueda para proponer configuraciones cada vez más prometedoras.
Y OE5: validar la configuración optimizada contra el baseline en el dataset completo.