| .. |
|
cli
|
02d805ea9b
增加重构函数位置
|
1 year ago |
|
dict2md
|
00f16239c6
实现parse_ocr_pdf api,切图逻辑s3使用平铺地址,本地使用层级地址,删除预设s3_image_save_path
|
1 year ago |
|
filter
|
d5dbed7325
目录重构
|
1 year ago |
|
io
|
6bc9df8247
io modules
|
1 year ago |
|
layout
|
d5dbed7325
目录重构
|
1 year ago |
|
libs
|
51bb3b3646
cut_image不报错公式图片,增加parse_union_pdf逻辑
|
1 year ago |
|
para
|
c3b8f6d7bb
OCR line的左右侧如果超过layoutbox,那么让layoutbox截断左右侧
|
1 year ago |
|
post_proc
|
71a042d9fc
footnote检测逻辑更新
|
1 year ago |
|
pre_proc
|
0e2d0b8b4f
parse_pdf_by_ocr 和 cut_image 重构,使用抽象类进行写出操作
|
1 year ago |
|
spark
|
877160a74f
fix parse_union_pdf logic
|
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
|
0e2d0b8b4f
parse_pdf_by_ocr 和 cut_image 重构,使用抽象类进行写出操作
|
1 year ago |
|
pdf_parse_by_txt.py
|
88f5b9325c
parse_pdf_by_txt 和 cut_image 重构,使用抽象类进行写出操作
|
1 year ago |
|
pdf_parse_for_train.py
|
0e2d0b8b4f
parse_pdf_by_ocr 和 cut_image 重构,使用抽象类进行写出操作
|
1 year ago |
|
pipeline.bak
|
c81f699e68
更新libs/config_reader,删除spark/s3.py
|
1 year ago |
|
pipeline_ocr.bak
|
c81f699e68
更新libs/config_reader,删除spark/s3.py
|
1 year ago |
|
pipeline_txt.bak
|
c81f699e68
更新libs/config_reader,删除spark/s3.py
|
1 year ago |