| .. |
|
wired_table
|
975ab2f230
feat: 更新二次OCR填充逻辑，增加OCR误合并检测和文本空值处理
|
hai 4 días |
|
__init__.py
|
1cdd879991
feat: 添加 DiT 适配器的可选导入和布局检测支持
|
hai 2 semanas |
|
base.py
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
hai 3 semanas |
|
dit_layout_adapter.py
|
23326cb1b6
feat: 增强布局处理工具类，新增类别合并限制和误检过滤功能
|
hai 2 semanas |
|
docling_layout_adapter.py
|
76f8e864a8
feat: Add .gitignore, implement grid recovery syntax verification, and enhance HuggingFace model loading with local cache prioritization.
|
hai 1 semana |
|
mineru_adapter.py
|
5235aff1b9
feat: 更新MinerU适配器，添加ocr_platform根目录到Python路径并优化坐标处理逻辑
|
hai 2 semanas |
|
mineru_wired_table.py
|
ca0374db5f
feat: 添加 pdf_type 参数以支持不同的 PDF 处理模式，优化识别逻辑
|
hai 5 días |
|
paddle_layout_detector.py
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
hai 3 semanas |
|
paddle_table_classifier.py
|
0b7809226c
feat: 添加PaddleOCR表格分类器适配器，支持有线/无线表格分类
|
hai 5 días |
|
paddle_vl_adapter.py
|
565ef479fa
feat: Implement universal document parser with enhanced processing capabilities
|
hai 3 semanas |
zhch158_admin
975ab2f230
feat: 更新二次OCR填充逻辑，增加OCR误合并检测和文本空值处理