使用 deepDoctection 构建端到端文档智能处理流水线教程

!pip install -q "deepdoctection" "transformers>=5.2.0" "timm" "python-doctr" "pdfplumber" "networkx" "lxml"
import os
os.environ["DD_USE_TORCH"]  = "True"
os.environ["DPI"]           = "200"
os.environ["LOG_LEVEL"]     = "INFO"
os.environ["ENABLE_DYNAMIC_OBJECT_TYPES"] = "False"
import json, re, textwrap
from pathlib import Path
from collections import Counter
import numpy as np
import matplotlib.pyplot as plt
from IPython.display import HTML, display
import deepdoctection as dd
print("deepdoctection:", dd.__version__)
import transformers.integrations.peft as _hf_peft
if _hf_peft.is_peft_available():
   _hf_peft.is_peft_available = lambda: False
   print("patched: PEFT adapter lookup disabled for from_pretrained")
!mkdir -p /content/docs /content/imgs
!wget -q -O /content/docs/paper.pdf \
 Click to access 2312.13560.pdf
!wget -q -O /content/imgs/finance.png \
 https://raw.githubusercontent.com/deepdoctection/notebooks/main/sample/finance/1bcac3899c9cb1c0b0f650b1431d3d52_7.png
PDF = Path("/content/docs/paper.pdf")
PNG = Path("/content/imgs/finance.png")
OUT = Path("/content/out"); OUT.mkdir(exist_ok=True)
def show(img, w=16):
   if img is None: return
   plt.figure(figsize=(w, w * 1.3)); plt.axis("off"); plt.imshow(img); plt.show()
def analyze_any(pipe, path, **kw):
   """
   Dispatch correctly for a directory, a PDF, or a single image file.
   DoctectionPipe can stream a directory or a PDF from disk, but a *single*
   image has no reader — path= only supplies the file name / provenance, and
   the pixels must be handed in via bytes=. Without this you get:
     ValueError: When passing a path to a single image, bytes of the image
                 must be passed
   """
   path = Path(path)
   if path.is_dir():
       kw.setdefault("file_type", [".jpg", ".png", ".jpeg", ".tif"])
       return pipe.analyze(path=path, **kw)
   if path.suffix.lower() == ".pdf":
       return pipe.analyze(path=path, **kw)
   if path.suffix.lower() in (".png", ".jpg", ".jpeg", ".tif"):
       return pipe.analyze(path=path, bytes=path.read_bytes(), **kw)
   raise ValueError(f"unsupported input: {path}")

dd.print_model_infos(add_description=False, add_config=False, add_categories=False)
profile = dd.ModelCatalog.get_profile("Aryn/deformable-detr-DocLayNet/model.safetensors")
print("\nlayout model categories:", profile.categories)
print("is registered:", dd.ModelCatalog.is_registered("Aryn/deformable-detr-DocLayNet/model.safetensors"))
config_overwrite = [
   "USE_ROTATOR=False",
   "USE_LAYOUT=True",
   "USE_LAYOUT_NMS=True",
   "USE_TABLE_SEGMENTATION=True",
   "USE_TABLE_REFINEMENT=False",
   "USE_PDF_MINER=False",
   "USE_OCR=True",
   "USE_LAYOUT_LINK=True",
   "LAYOUT.WEIGHTS=Aryn/deformable-detr-DocLayNet/model.safetensors",
   "ITEM.WEIGHTS=deepdoctection/tatr_tab_struct_v2/model.safetensors",
   "ITEM.FILTER=['table']",
   "OCR.USE_DOCTR=True",
   "OCR.USE_TESSERACT=False",
   "OCR.USE_TEXTRACT=False",
   "OCR.WEIGHTS.DOCTR_WORD=doctr/db_resnet50/db_resnet50-ac60cadc.pt",
   "OCR.WEIGHTS.DOCTR_RECOGNITION=doctr/crnn_vgg16_bn/crnn_vgg16_bn-0417f351.pt",
   "SEGMENTATION.THRESHOLD_ROWS=0.4",
   "SEGMENTATION.THRESHOLD_COLS=0.4",
   "SEGMENTATION.FULL_TABLE_TILING=True",
   "WORD_MATCHING.RULE=ioa",
   "WORD_MATCHING.THRESHOLD=0.3",
   "WORD_MATCHING.MAX_PARENT_ONLY=True",
   "TEXT_ORDERING.INCLUDE_RESIDUAL_TEXT_CONTAINER=True",
   "TEXT_ORDERING.PARAGRAPH_BREAK=0.035",
   "TEXT_ORDERING.BROKEN_LINE_TOLERANCE=0.003",
   "LAYOUT_LINK.PARENTAL_CATEGORIES=['figure','table']",
   "LAYOUT_LINK.CHILD_CATEGORIES=['caption']",
]
analyzer = dd.get_dd_analyzer(config_overwrite=config_overwrite)
print("\n--- pipeline ---")
for sid, name in analyzer.get_pipeline_info().items():
   print(f"{sid}  {name}")
print("\n--- what this pipeline produces ---")
print(analyzer.get_meta_annotation())

df = analyze_any(analyzer, PDF, session_id="tutorial01", max_datapoints=3)
df.reset_state()
pages = list(df)
print(f"\nparsed {len(pages)} pages")
page = pages[0]
show(page.viz(show_figures=True, show_residual_layouts=True, show_table_structure=True))
print("== narrative text ==")
print(textwrap.fill(page.text[:900], 110))
print("\n== layout blocks in reading order ==")
for doc_id, img_id, pno, ann_id, order, cat, txt in page.chunks[:12]:
   print(f"[{order:>3}] {str(cat):<15} {txt[:70]!r}")
print("\n== category histogram ==")
print(Counter(a.category_name for a in page.get_annotation()))
for fig in page.figures:
   linked = fig.get_relationship("layout_link")
   print("figure", fig.annotation_id[:8], "-> caption ids:", [i[:8] for i in linked])
if page.words:
   w = page.words[0]
   print("\nword:", w.characters, "| service:", w.service_id,
         "| model:", w.model_id, "| bbox:", [round(x) for x in w.bbox])
tbl_pages = [p for p in pages if p.tables]
if tbl_pages:
   t = tbl_pages[0].tables[0]
   print(f"table {t.number_of_rows}x{t.number_of_columns}, "
         f"max_row_span={t.max_row_span}, max_col_span={t.max_col_span}")
   display(HTML(t.html))
   for row in t.csv[:5]:
       print([c[:22] for c in row])
   for c in t.cells[:5]:
       print(f"  r{c.row_number} c{c.column_number} "
             f"(span {c.row_span}x{c.column_span}) {c.text[:40]!r}")
else:
   print("no table on these pages — the finance.png sample below has one")