许瑞 4aa48329a4 feat: draw block based on block_type 1 year ago
..
cli 49076f02f3 fix draw_span_bbox logic 1 year ago
dict2md 81f73a3d9d 避免空para导致的error 1 year ago
filter 1b9d65b3d3 1、Trace类的key增加前置下划线 1 year ago
layout d5dbed7325 目录重构 1 year ago
libs 4aa48329a4 feat: draw block based on block_type 1 year ago
model c460be9196 模型数据初始化时根据置信度进行过滤,预设阈值95% 1 year ago
para 778b1fb7b5 更新了para_split 1 year ago
pipe 1340a97ae2 统一使用ocr组装markdown 1 year ago
post_proc 1b9d65b3d3 1、Trace类的key增加前置下划线 1 year ago
pre_proc ce992f271e 有些ocr的text和block框差异过大,降低fill阈值到0.7 1 year ago
rw 698c4a83d2 修改pipe模块 1 year ago
spark 709a65008a 中间态dict结构调整 1 year ago
train_utils efed5faa53 feat: modify foot note bbox tmp 1 year ago
__init__.py d5dbed7325 目录重构 1 year ago
pdf_parse_by_ocr.py e31066bae5 更新了para_split 1 year ago
pdf_parse_by_ocr_v2.py fa6e305c12 v2pipeline在分段区域增加异常捕获 1 year ago
pdf_parse_by_txt.py d438b97a0a 切图逻辑重构 1 year ago
pdf_parse_by_txt_v2.py fa6e305c12 v2pipeline在分段区域增加异常捕获 1 year ago
pdf_parse_for_train.py d438b97a0a 切图逻辑重构 1 year ago
pipeline.bak 1b9d65b3d3 1、Trace类的key增加前置下划线 1 year ago
pipeline_ocr.bak 1b9d65b3d3 1、Trace类的key增加前置下划线 1 year ago
pipeline_txt.bak 1b9d65b3d3 1、Trace类的key增加前置下划线 1 year ago
user_api.py b16599cdf2 feat: update cli 1 year ago