Commit History

作者 SHA1 備註 提交日期
  myhloli c7e456033d fix: add support for Torch 2.8.0 and MPS devices in batch analysis 3 月之前
  myhloli a5e4179139 fix: adjust batch sizes and improve performance settings in various modules 3 月之前
  myhloli 399023f580 fix: update default value of MINERU_MIN_BATCH_INFERENCE_SIZE to 128 in pipeline_analyze.py 4 月之前
  myhloli b398a2d2b8 fix: update NPU compile mode handling in pipeline_analyze.py 5 月之前
  myhloli 58b8e8a912 fix: add new enum values and improve MIN_BATCH_INFERENCE_SIZE documentation in pipeline_analyze.py 5 月之前
  myhloli 1383787bad fix: refactor formula and table enable handling to use environment variables 5 月之前
  myhloli 98b8c4a967 refactor: streamline formula and table enable configurations in the pipeline 5 月之前
  myhloli 7ae4f80dad feat: enhance device detection to support NPU and improve error handling 5 月之前
  myhloli 15dd9a0ff1 refactor: reorganize config_reader imports and enhance format utilities 5 月之前
  myhloli 2688e3f7d0 refactor: enhance main function parameters and improve device handling logic 5 月之前
  myhloli 51393aa814 refactor: update union_make import and adjust middle JSON structure for consistency 5 月之前
  myhloli a9abb4e201 refactor: enhance OCR processing and paragraph splitting in document analysis pipeline 5 月之前
  myhloli bd2c3d120a refactor: update OCR handling and adjust root directory path for model loading 5 月之前
  myhloli 38ace5dc61 refactor: streamline document analysis and enhance image handling in processing pipeline 5 月之前
  myhloli 6833882585 refactor: enhance language support and improve document parsing for multiple files 5 月之前
  myhloli 8f1f9abec5 refactor: enhance bounding box utilities and add configuration reader for S3 integration 5 月之前
  myhloli 7285ea9285 refactor: improve document analysis by integrating image loading and enhancing data handling 5 月之前
  myhloli ea5cb65a1f refactor: enhance document parsing by supporting multiple PDF files and improving method organization 5 月之前