Commit History

Автор SHA1 Съобщение Дата
  myhloli 058d318491 feat(pdf_parse): add footnote block handling in layout split преди 7 месеца
  myhloli ea730ae2e9 refactor(ocr): improve OCR score precision to three decimal places преди 7 месеца
  myhloli 795233d1bb refactor(magic_pdf): remove OCR timing measurement code преди 7 месеца
  myhloli 553f250fc7 refactor(magic_pdf): optimize code and improve logging преди 7 месеца
  myhloli a024c30fc4 feat(ocr): implement dynamic OCR processing for text spans with low contrast преди 7 месеца
  myhloli 3cb156f549 fix(pdf_parse_union_core_v2): suppress FutureWarning from transformers преди 7 месеца
  myhloli 59d6b195b0 refactor(model): integrate AtomModelSingleton for OCR and improve OCR result handling преди 7 месеца
  myhloli a330651d64 feat(ocr): implement separate detection and recognition processes преди 7 месеца
  myhloli 72e66c2d1e refactor(pdf_parse): adjust line calculation for block height преди 7 месеца
  myhloli 71efb101dc refactor(pdf_parse): adjust line calculation for block height преди 7 месеца
  myhloli 3f2bafa88f feat(pre_proc): add function to remove x-overlapping characters in spans преди 8 месеца
  myhloli 7210f7a65a perf(model): enable bfloat16 for layoutreader on supported devices преди 8 месеца
  myhloli cf4ea78dac refactor: remove torchtext deprecation warning handling преди 8 месеца
  myhloli af27c0cc81 refactor(magic_pdf): support mps device and optimize image processing преди 8 месеца
  myhloli 6bfc17119d refactor(pdf_parse): comment out performance measurement and logging преди 8 месеца
  myhloli e516cf535c feat(performance): add performance monitoring and optimization преди 8 месеца
  myhloli 6ec440d6f1 feat(pdf_parse): implement multi-threaded page processing преди 8 месеца
  myhloli 0a246f0f40 refactor(magic_pdf): simplify device selection in model initialization преди 8 месеца
  myhloli 9b00f988ac refactor(magic_pdf): remove bfloat16 support checks and usage преди 8 месеца
  myhloli 30bd3a83c7 fix(pdf_parse): Fixed the issue where some headings were missing in certain complex layouts. преди 9 месеца
  myhloli 5561ac9555 fix(pdf_parse): improve image processing and OCR accuracy преди 9 месеца
  myhloli 9f18ca2019 feat(pdf_parse): improve OCR processing and contrast filtering преди 9 месеца
  myhloli 10e848b39d feat(pdf_parse_union_core_v2): add timing log for LLM aided processes преди 9 месеца
  myhloli 1d08865f4a refactor(pdf_parse): uncomment char bbox validation logic преди 9 месеца
  myhloli ba6c17a9d9 feat(pdf_parse): remove tilted lines for better text extraction преди 10 месеца
  myhloli 8570e006f8 refactor(magic_pdf): improve title block merging logic преди 10 месеца
  Xiaomeng Zhao 206fcb3900 Merge pull request #1537 from myhloli/doclayoutyolo-fix преди 10 месеца
  myhloli c20e9a1e84 feat(layout): improve title block handling and layout detection преди 10 месеца
  Xiaomeng Zhao 9f12c39817 Update pdf_parse_union_core_v2.py преди 10 месеца
  myhloli aaff1a2616 fix(llm_aided): add enable flag check for LLM aided optimizations преди 10 месеца