| .. |
|
__init__.py
|
d5dbed7325
目录重构
|
il y a 1 an |
|
boxbase.py
|
1279f2cd0f
feat(model): add support for DocLayout-YOLO model
|
il y a 1 an |
|
calc_span_stats.py
|
d5dbed7325
目录重构
|
il y a 1 an |
|
clean_memory.py
|
4c9bf8abd5
refactor(memory management): remove unused clean_memory function
|
il y a 1 an |
|
commons.py
|
1de37e4c65
add version_name to middle json
|
il y a 1 an |
|
config_reader.py
|
b492c19c4c
refactor: move some constants or enums defs to config folder
|
il y a 1 an |
|
convert_utils.py
|
709a65008a
中间态dict结构调整
|
il y a 1 an |
|
coordinate_transform.py
|
7b0db8a4b3
将fix缩放倍率的bbox写入model_list
|
il y a 1 an |
|
detect_language_from_model.py
|
e492b3dce8
语言检测逻辑移动到parse流程
|
il y a 1 an |
|
draw_bbox.py
|
b492c19c4c
refactor: move some constants or enums defs to config folder
|
il y a 1 an |
|
hash_utils.py
|
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
|
il y a 1 an |
|
json_compressor.py
|
d5dbed7325
目录重构
|
il y a 1 an |
|
language.py
|
57380cbed5
feat(language): add FT LANG cache directory setup
|
il y a 1 an |
|
local_math.py
|
12bec17eed
refactor(magic_pdf): replace math module with local_math
|
il y a 1 an |
|
markdown_utils.py
|
59b0b0c3da
make markdown时特殊符号转义
|
il y a 1 an |
|
nlp_utils.py
|
d5dbed7325
目录重构
|
il y a 1 an |
|
path_utils.py
|
6c656af65f
update:cleanup requirements.txt
|
il y a 1 an |
|
pdf_check.py
|
8998380da5
update check invalid_chars algorithm to improve accuracy
|
il y a 1 an |
|
pdf_image_tools.py
|
309be741e8
refactor(txt_parse): improve text extraction accuracy with new algorithm
|
il y a 1 an |
|
safe_filename.py
|
d5dbed7325
目录重构
|
il y a 1 an |
|
textbase.py
|
d5dbed7325
目录重构
|
il y a 1 an |
|
version.py
|
149132d608
feat(pdf_parse): improve span filtering and add new block types
|
il y a 1 an |
|
vis_utils.py
|
d5dbed7325
目录重构
|
il y a 1 an |
myhloli
309be741e8
refactor(txt_parse): improve text extraction accuracy with new algorithm