magic-pdf 0.5.12__py3-none-any.whl → 0.6.0__py3-none-any.whl

magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml

@@ -0,0 +1,351 @@
+AUG:
+  DETR: true
+CACHE_DIR: /mnt/localdata/users/yupanhuang/cache/huggingface
+CUDNN_BENCHMARK: false
+DATALOADER:
+  ASPECT_RATIO_GROUPING: true
+  FILTER_EMPTY_ANNOTATIONS: false
+  NUM_WORKERS: 4
+  REPEAT_THRESHOLD: 0.0
+  SAMPLER_TRAIN: TrainingSampler
+DATASETS:
+  PRECOMPUTED_PROPOSAL_TOPK_TEST: 1000
+  PRECOMPUTED_PROPOSAL_TOPK_TRAIN: 2000
+  PROPOSAL_FILES_TEST: []
+  PROPOSAL_FILES_TRAIN: []
+  TEST:
+  - scihub_train
+  TRAIN:
+  - scihub_train
+GLOBAL:
+  HACK: 1.0
+ICDAR_DATA_DIR_TEST: ''
+ICDAR_DATA_DIR_TRAIN: ''
+INPUT:
+  CROP:
+    ENABLED: true
+    SIZE:
+    - 384
+    - 600
+    TYPE: absolute_range
+  FORMAT: RGB
+  MASK_FORMAT: polygon
+  MAX_SIZE_TEST: 1333
+  MAX_SIZE_TRAIN: 1333
+  MIN_SIZE_TEST: 800
+  MIN_SIZE_TRAIN:
+  - 480
+  - 512
+  - 544
+  - 576
+  - 608
+  - 640
+  - 672
+  - 704
+  - 736
+  - 768
+  - 800
+  MIN_SIZE_TRAIN_SAMPLING: choice
+  RANDOM_FLIP: horizontal
+MODEL:
+  ANCHOR_GENERATOR:
+    ANGLES:
+    - - -90
+      - 0
+      - 90
+    ASPECT_RATIOS:
+    - - 0.5
+      - 1.0
+      - 2.0
+    NAME: DefaultAnchorGenerator
+    OFFSET: 0.0
+    SIZES:
+    - - 32
+    - - 64
+    - - 128
+    - - 256
+    - - 512
+  BACKBONE:
+    FREEZE_AT: 2
+    NAME: build_vit_fpn_backbone
+  CONFIG_PATH: ''
+  DEVICE: cuda
+  FPN:
+    FUSE_TYPE: sum
+    IN_FEATURES:
+    - layer3
+    - layer5
+    - layer7
+    - layer11
+    NORM: ''
+    OUT_CHANNELS: 256
+  IMAGE_ONLY: true
+  KEYPOINT_ON: false
+  LOAD_PROPOSALS: false
+  MASK_ON: true
+  META_ARCHITECTURE: VLGeneralizedRCNN
+  PANOPTIC_FPN:
+    COMBINE:
+      ENABLED: true
+      INSTANCES_CONFIDENCE_THRESH: 0.5
+      OVERLAP_THRESH: 0.5
+      STUFF_AREA_LIMIT: 4096
+    INSTANCE_LOSS_WEIGHT: 1.0
+  PIXEL_MEAN:
+  - 127.5
+  - 127.5
+  - 127.5
+  PIXEL_STD:
+  - 127.5
+  - 127.5
+  - 127.5
+  PROPOSAL_GENERATOR:
+    MIN_SIZE: 0
+    NAME: RPN
+  RESNETS:
+    DEFORM_MODULATED: false
+    DEFORM_NUM_GROUPS: 1
+    DEFORM_ON_PER_STAGE:
+    - false
+    - false
+    - false
+    - false
+    DEPTH: 50
+    NORM: FrozenBN
+    NUM_GROUPS: 1
+    OUT_FEATURES:
+    - res4
+    RES2_OUT_CHANNELS: 256
+    RES5_DILATION: 1
+    STEM_OUT_CHANNELS: 64
+    STRIDE_IN_1X1: true
+    WIDTH_PER_GROUP: 64
+  RETINANET:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_WEIGHTS:
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    FOCAL_LOSS_ALPHA: 0.25
+    FOCAL_LOSS_GAMMA: 2.0
+    IN_FEATURES:
+    - p3
+    - p4
+    - p5
+    - p6
+    - p7
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.4
+    - 0.5
+    NMS_THRESH_TEST: 0.5
+    NORM: ''
+    NUM_CLASSES: 10
+    NUM_CONVS: 4
+    PRIOR_PROB: 0.01
+    SCORE_THRESH_TEST: 0.05
+    SMOOTH_L1_LOSS_BETA: 0.1
+    TOPK_CANDIDATES_TEST: 1000
+  ROI_BOX_CASCADE_HEAD:
+    BBOX_REG_WEIGHTS:
+    - - 10.0
+      - 10.0
+      - 5.0
+      - 5.0
+    - - 20.0
+      - 20.0
+      - 10.0
+      - 10.0
+    - - 30.0
+      - 30.0
+      - 15.0
+      - 15.0
+    IOUS:
+    - 0.5
+    - 0.6
+    - 0.7
+  ROI_BOX_HEAD:
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS:
+    - 10.0
+    - 10.0
+    - 5.0
+    - 5.0
+    CLS_AGNOSTIC_BBOX_REG: true
+    CONV_DIM: 256
+    FC_DIM: 1024
+    NAME: FastRCNNConvFCHead
+    NORM: ''
+    NUM_CONV: 0
+    NUM_FC: 2
+    POOLER_RESOLUTION: 7
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+    SMOOTH_L1_BETA: 0.0
+    TRAIN_ON_PRED_BOXES: false
+  ROI_HEADS:
+    BATCH_SIZE_PER_IMAGE: 512
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    IOU_LABELS:
+    - 0
+    - 1
+    IOU_THRESHOLDS:
+    - 0.5
+    NAME: CascadeROIHeads
+    NMS_THRESH_TEST: 0.5
+    NUM_CLASSES: 10
+    POSITIVE_FRACTION: 0.25
+    PROPOSAL_APPEND_GT: true
+    SCORE_THRESH_TEST: 0.05
+  ROI_KEYPOINT_HEAD:
+    CONV_DIMS:
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    - 512
+    LOSS_WEIGHT: 1.0
+    MIN_KEYPOINTS_PER_IMAGE: 1
+    NAME: KRCNNConvDeconvUpsampleHead
+    NORMALIZE_LOSS_BY_VISIBLE_KEYPOINTS: true
+    NUM_KEYPOINTS: 17
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  ROI_MASK_HEAD:
+    CLS_AGNOSTIC_MASK: false
+    CONV_DIM: 256
+    NAME: MaskRCNNConvUpsampleHead
+    NORM: ''
+    NUM_CONV: 4
+    POOLER_RESOLUTION: 14
+    POOLER_SAMPLING_RATIO: 0
+    POOLER_TYPE: ROIAlignV2
+  RPN:
+    BATCH_SIZE_PER_IMAGE: 256
+    BBOX_REG_LOSS_TYPE: smooth_l1
+    BBOX_REG_LOSS_WEIGHT: 1.0
+    BBOX_REG_WEIGHTS:
+    - 1.0
+    - 1.0
+    - 1.0
+    - 1.0
+    BOUNDARY_THRESH: -1
+    CONV_DIMS:
+    - -1
+    HEAD_NAME: StandardRPNHead
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    - p6
+    IOU_LABELS:
+    - 0
+    - -1
+    - 1
+    IOU_THRESHOLDS:
+    - 0.3
+    - 0.7
+    LOSS_WEIGHT: 1.0
+    NMS_THRESH: 0.7
+    POSITIVE_FRACTION: 0.5
+    POST_NMS_TOPK_TEST: 1000
+    POST_NMS_TOPK_TRAIN: 2000
+    PRE_NMS_TOPK_TEST: 1000
+    PRE_NMS_TOPK_TRAIN: 2000
+    SMOOTH_L1_BETA: 0.0
+  SEM_SEG_HEAD:
+    COMMON_STRIDE: 4
+    CONVS_DIM: 128
+    IGNORE_VALUE: 255
+    IN_FEATURES:
+    - p2
+    - p3
+    - p4
+    - p5
+    LOSS_WEIGHT: 1.0
+    NAME: SemSegFPNHead
+    NORM: GN
+    NUM_CLASSES: 10
+  VIT:
+    DROP_PATH: 0.1
+    IMG_SIZE:
+    - 224
+    - 224
+    NAME: layoutlmv3_base
+    OUT_FEATURES:
+    - layer3
+    - layer5
+    - layer7
+    - layer11
+    POS_TYPE: abs
+  WEIGHTS: 
+OUTPUT_DIR: 
+SCIHUB_DATA_DIR_TRAIN: /mnt/petrelfs/share_data/zhaozhiyuan/publaynet/layout_scihub/train
+SEED: 42
+SOLVER:
+  AMP:
+    ENABLED: true
+  BACKBONE_MULTIPLIER: 1.0
+  BASE_LR: 0.0002
+  BIAS_LR_FACTOR: 1.0
+  CHECKPOINT_PERIOD: 2000
+  CLIP_GRADIENTS:
+    CLIP_TYPE: full_model
+    CLIP_VALUE: 1.0
+    ENABLED: true
+    NORM_TYPE: 2.0
+  GAMMA: 0.1
+  GRADIENT_ACCUMULATION_STEPS: 1
+  IMS_PER_BATCH: 32
+  LR_SCHEDULER_NAME: WarmupCosineLR
+  MAX_ITER: 20000
+  MOMENTUM: 0.9
+  NESTEROV: false
+  OPTIMIZER: ADAMW
+  REFERENCE_WORLD_SIZE: 0
+  STEPS:
+  - 10000
+  WARMUP_FACTOR: 0.01
+  WARMUP_ITERS: 333
+  WARMUP_METHOD: linear
+  WEIGHT_DECAY: 0.05
+  WEIGHT_DECAY_BIAS: null
+  WEIGHT_DECAY_NORM: 0.0
+TEST:
+  AUG:
+    ENABLED: false
+    FLIP: true
+    MAX_SIZE: 4000
+    MIN_SIZES:
+    - 400
+    - 500
+    - 600
+    - 700
+    - 800
+    - 900
+    - 1000
+    - 1100
+    - 1200
+  DETECTIONS_PER_IMAGE: 100
+  EVAL_PERIOD: 1000
+  EXPECTED_RESULTS: []
+  KEYPOINT_OKS_SIGMAS: []
+  PRECISE_BN:
+    ENABLED: false
+    NUM_ITER: 200
+VERSION: 2
+VIS_PERIOD: 0

magic_pdf/resources/model_config/model_configs.yaml

@@ -0,0 +1,9 @@
+config:
+  device: cpu
+  layout: True
+  formula: True
+
+weights:
+  layout: Layout/model_final.pth
+  mfd: MFD/weights.pt
+  mfr: MFR/UniMERNet

{magic_pdf-0.5.12.dist-info → magic_pdf-0.6.0.dist-info}/METADATA

@@ -1,8 +1,8 @@
 Metadata-Version: 2.1
 Name: magic-pdf
-Version: 0.5.12
+Version: 0.6.0
 Summary: A practical tool for converting PDF to Markdown
-Home-page: https://github.com/magicpdf/Magic-PDF
+Home-page: https://github.com/opendatalab/MinerU
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE.md
@@ -12,15 +12,21 @@ Requires-Dist: click >=8.1.7
 Requires-Dist: PyMuPDF >=1.24.7
 Requires-Dist: loguru >=0.6.0
 Requires-Dist: numpy >=1.21.6
-Requires-Dist: fast-langdetect >=0.1.1
+Requires-Dist: fast-langdetect >=0.2.1
 Requires-Dist: wordninja >=2.0.0
 Requires-Dist: scikit-learn >=1.0.2
 Requires-Dist: pdfminer.six >=20231228
 Provides-Extra: cpu
-Requires-Dist: paddleocr ; extra == 'cpu'
+Requires-Dist: paddleocr ==2.7.3 ; extra == 'cpu'
 Requires-Dist: paddlepaddle ; extra == 'cpu'
+Provides-Extra: full-cpu
+Requires-Dist: unimernet ; extra == 'full-cpu'
+Requires-Dist: matplotlib ; extra == 'full-cpu'
+Requires-Dist: ultralytics ; extra == 'full-cpu'
+Requires-Dist: paddleocr ==2.7.3 ; extra == 'full-cpu'
+Requires-Dist: paddlepaddle ; extra == 'full-cpu'
 Provides-Extra: gpu
-Requires-Dist: paddleocr ; extra == 'gpu'
+Requires-Dist: paddleocr ==2.7.3 ; extra == 'gpu'
 Requires-Dist: paddlepaddle-gpu ; extra == 'gpu'
 
 <div id="top"></div>
@@ -28,9 +34,14 @@ Requires-Dist: paddlepaddle-gpu ; extra == 'gpu'
 
 [![stars](https://img.shields.io/github/stars/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
 [![forks](https://img.shields.io/github/forks/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU)
-[![license](https://img.shields.io/github/license/opendatalab/MinerU.svg)](https://github.com/opendatalab/MinerU/tree/main/LICENSE)
-[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
 [![open issues](https://img.shields.io/github/issues-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
+[![issue resolution](https://img.shields.io/github/issues-closed-raw/opendatalab/MinerU)](https://github.com/opendatalab/MinerU/issues)
+[![PyPI version](https://badge.fury.io/py/magic-pdf.svg)](https://badge.fury.io/py/magic-pdf)
+[![Downloads](https://static.pepy.tech/badge/magic-pdf)](https://pepy.tech/project/magic-pdf)
+[![Downloads](https://static.pepy.tech/badge/magic-pdf/month)](https://pepy.tech/project/magic-pdf)
+
+
+
 
 [English](README.md) | [简体中文](README_zh-CN.md)
 
@@ -45,7 +56,7 @@ Requires-Dist: paddlepaddle-gpu ; extra == 'gpu'
 
 ## Introduction
 
-MinerU is a one-stop, open-source data extraction tool, primarily includes the following features:
+MinerU is a one-stop, open-source, high-quality data extraction tool, includes the following primary features:
 
 - [Magic-PDF](#Magic-PDF)  PDF Document Extraction  
 - [Magic-Doc](#Magic-Doc)  Webpage & E-book Extraction
@@ -71,7 +82,7 @@ Key features include:
 - Available for Windows, Linux, and macOS platforms
 
 
-https://github.com/magicpdf/Magic-PDF/assets/11393164/618937cb-dc6a-4646-b433-e3131a5f4070
+https://github.com/opendatalab/MinerU/assets/11393164/618937cb-dc6a-4646-b433-e3131a5f4070
 
 
 
@@ -88,9 +99,6 @@ https://github.com/magicpdf/Magic-PDF/assets/11393164/618937cb-dc6a-4646-b433-e3
 
 - [PDF-Extract-Kit](https://github.com/opendatalab/PDF-Extract-Kit)
   - A Comprehensive Toolkit for High-Quality PDF Content Extraction
-- [Miner-PDF-Benchmark](https://github.com/opendatalab/Miner-PDF-Benchmark)
-  - An end-to-end PDF document comprehension evaluation suite designed for large-scale model data scenarios
-
 
 ## Getting Started
 
@@ -111,9 +119,10 @@ pip install magic-pdf
 ###### simple
 
 ```bash
-cp magic-pdf.template.json to ~/magic-pdf.json
+cp magic-pdf.template.json ~/magic-pdf.json
 magic-pdf pdf-command --pdf "pdf_path" --model "model_json_path"
 ```
+After the program has finished, you can find the generated markdown files under the directory "/tmp/magic-pdf".
 
 ###### more 
 
@@ -150,26 +159,6 @@ md_content = pipe.pipe_mk_markdown(image_dir, drop_mode="none")
 Demo can be referred to [demo.py](demo/demo.py)
 
 
-## All Thanks To Our Contributors
-
-<a href="https://github.com/magicpdf/Magic-PDF/graphs/contributors">
-  <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
-</a>
-
-
-## License Information
-
-[LICENSE.md](LICENSE.md)
-
-The project currently leverages PyMuPDF to deliver advanced functionalities; however, its adherence to the AGPL license may impose limitations on certain use cases. In upcoming iterations, we intend to explore and transition to a more permissively licensed PDF processing library to enhance user-friendliness and flexibility.
-
-
-## Acknowledgments
-
-- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
-- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
-
-
 # Magic-Doc
 
 
@@ -203,5 +192,50 @@ https://github.com/opendatalab/MinerU/assets/11393164/20438a02-ce6c-4af8-9dde-d7
 
 ## Project Repository
 
-- [Magic-Doc](https://github.com/magicpdf/Magic-Doc)
+- [Magic-Doc](https://github.com/InternLM/magic-doc)
   Outstanding Webpage and E-book Extraction Tool
+
+
+# All Thanks To Our Contributors
+
+<a href="https://github.com/magicpdf/Magic-PDF/graphs/contributors">
+  <img src="https://contrib.rocks/image?repo=opendatalab/MinerU" />
+</a>
+
+
+# License Information
+
+[LICENSE.md](LICENSE.md)
+
+The project currently leverages PyMuPDF to deliver advanced functionalities; however, its adherence to the AGPL license may impose limitations on certain use cases. In upcoming iterations, we intend to explore and transition to a more permissively licensed PDF processing library to enhance user-friendliness and flexibility.
+
+
+# Acknowledgments
+
+- [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)
+- [PyMuPDF](https://github.com/pymupdf/PyMuPDF)
+- [fast-langdetect](https://github.com/LlmKira/fast-langdetect)
+- [pdfminer.six](https://github.com/pdfminer/pdfminer.six)
+
+
+# Citation
+
+```bibtex
+@misc{2024mineru,
+    title={MinerU: A One-stop, Open-source, High-quality Data Extraction Tool},
+    author={MinerU Contributors},
+    howpublished = {\url{https://github.com/opendatalab/MinerU}},
+    year={2024}
+}
+```
+
+
+# Star History
+
+<a>
+ <picture>
+   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date&theme=dark" />
+   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
+   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=opendatalab/MinerU&type=Date" />
+ </picture>
+</a>

{magic_pdf-0.5.12.dist-info → magic_pdf-0.6.0.dist-info}/RECORD

@@ -5,7 +5,7 @@ magic_pdf/pdf_parse_for_train.py,sha256=Oby61DMjJ716Jj_ri7lwXfv2Chus0pbBR2RPXrmB
 magic_pdf/pdf_parse_union_core.py,sha256=a67iQuEfuslAEF-wQplGZKXUuz5mT3HiCyvuR52E6Gw,10584
 magic_pdf/user_api.py,sha256=CVQH-VSiZpz0bSkyMT4czk1epZriIPSJsLsPbluPa9Q,3054
 magic_pdf/cli/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-magic_pdf/cli/magicpdf.py,sha256=BA6lPjBhurXAnfmvdbQiS_atEFq3PVdNYDPkvxs1N0M,11654
+magic_pdf/cli/magicpdf.py,sha256=EcTiX-MaiDc4Fv9qZ_UdjHt5tYnBEu6vlbp0w030sA0,12691
 magic_pdf/dict2md/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/dict2md/mkcontent.py,sha256=rWUY-2opd0jeowEUEVOV_uWcKum1Q7ng4nOoT6-ka_s,17459
 magic_pdf/dict2md/ocr_mkcontent.py,sha256=RyxebPtvFfNce_HCa-_YGxwFx_srzL-BfMKc85V9JG0,15442
@@ -25,7 +25,7 @@ magic_pdf/libs/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/libs/boxbase.py,sha256=MvD0DypR4sTEF3T2RrI_yJ8mPDUBYHAqAaau2mnBSxY,15343
 magic_pdf/libs/calc_span_stats.py,sha256=5vnU27DcbkFDRSAoLqAmX0KQ3I9ehWkEgh_t9hxg_zI,10147
 magic_pdf/libs/commons.py,sha256=6Zu9-OyamyCNDY7qj0SxR-rux-ggj9im3CVPtC4ubB8,7108
-magic_pdf/libs/config_reader.py,sha256=ADe9DknbSBb3-JQlQJix-fkVDPIQCkytl4mKdXnIraA,1607
+magic_pdf/libs/config_reader.py,sha256=wB0Zn6qEwuAWmv2Icz9owPIqxrhFEH5i6sUr8Nt5ULo,1806
 magic_pdf/libs/convert_utils.py,sha256=Ov-lsfCLBPz_15iSJXIslBNmrSf_E_1g_XDWJy8NgO8,143
 magic_pdf/libs/coordinate_transform.py,sha256=Bbop2cP2uz2ZG0U0gwd7J6EKkgABq5Rv03qf2LMPw80,429
 magic_pdf/libs/detect_language_from_model.py,sha256=Uln8F9qs8EJOw4EgI7KRlaU3lD_mK8KMTlADLFtz8fk,816
@@ -34,7 +34,7 @@ magic_pdf/libs/drop_reason.py,sha256=IfjPSrPLMmVziqjOXPep7r_ioQKFRahDgbOW1SD-Tuw
 magic_pdf/libs/drop_tag.py,sha256=bZDg3bIVWvBT1Ec1icwj5WLOkt5-hI6eRYZ2tX9_a74,673
 magic_pdf/libs/hash_utils.py,sha256=VEKK9WfFoZgrPfi8kfITjLpr8Ahufs8tXh9R1Y5lAL8,404
 magic_pdf/libs/json_compressor.py,sha256=6-KCu0lb5ksmyqWtQGb4QqmP-FjRb5dP7P-Hevcn68g,875
-magic_pdf/libs/language.py,sha256=U8bOttqtJiBvqOFUksiHeeC3vgjzJIWTLqQrmorg7T0,683
+magic_pdf/libs/language.py,sha256=l0LGIz-dlerU9Xct-7ypNKGNEI_q-CTadsJAnVTF9VY,692
 magic_pdf/libs/markdown_utils.py,sha256=cLxLXjRhrNp_wCHvtglrGA_FVdrvfd1KULeTtj1p18w,944
 magic_pdf/libs/math.py,sha256=tqljQOgqh3fZc146HYhO88JXJaiXMVwArBkk_CSGICc,177
 magic_pdf/libs/nlp_utils.py,sha256=-X9W3-Ns5ZdDYFvyyEq6i6P2b5hCATaFEZeOjwNOH9M,6901
@@ -44,14 +44,37 @@ magic_pdf/libs/pdf_check.py,sha256=MAe8wzwT0qvPf_I72wEZG7k1g4haNHS7oUtLqkB5rlE,2
 magic_pdf/libs/pdf_image_tools.py,sha256=CAd01giTKr_UJz1_QtDOARG9G9z69GFpzRZwcWSfLtE,1282
 magic_pdf/libs/safe_filename.py,sha256=ckwcM_eqoysTb5id8czp-tXq2G9da0-l3pshZDCHQtE,236
 magic_pdf/libs/textbase.py,sha256=SC1Frhz3Fb7V7n2SFRBsl7Bmg0JZdlvZskq0lfW1vIk,732
-magic_pdf/libs/version.py,sha256=LznNzk7nDbJCv7NVxCOu958-1uT_nFJ79_3vJt7WPDc,23
+magic_pdf/libs/version.py,sha256=cID1jLnC_vj48GgMN6Yb1FA3JsQ95zNmCHmRYE8TFhY,22
 magic_pdf/libs/vis_utils.py,sha256=hTOTEakKV0pGMbk0tbRkVI_tku7A3dGc96ynObZ4kwI,10207
-magic_pdf/model/360_layout_analysis.py,sha256=GbchKPJRVcrxvwNXMnR4vt8lOLPauTWMl-43ayyhX7U,221
-magic_pdf/model/__init__.py,sha256=X6t9kPDqM8hDCbq8fQc_8jILtG6mepDjN_kadUo39Sk,29
-magic_pdf/model/doc_analyze_by_custom_model.py,sha256=8z4NX7Lk7CcPl1BQiNYL6dDiP63M3f6m3dmW6rjHCqg,2370
+magic_pdf/model/__init__.py,sha256=XeYcF4RMZ3DosyLqiz0_n1JVa2k5RhTwUXwKt5sAjEQ,53
+magic_pdf/model/doc_analyze_by_custom_model.py,sha256=kssz_Nn6zTYED_iEgGuFRjus947xoK5dTqj88FOehE0,3256
 magic_pdf/model/magic_model.py,sha256=2H6Gz1mg0f0YCvz-TLIWrAWXCQLgZftBXJNRPlSIjwc,25077
-magic_pdf/model/model_list.py,sha256=dNfnDodnbkgIW0PFDjn_KsQMA8DODOzo4Z4jxfOilaA,44
-magic_pdf/model/pp_structure_v2.py,sha256=fFbAOYEcLXlkCjqZ3yxZXR7nqtp6V8yowyjSibW3lhY,2635
+magic_pdf/model/model_list.py,sha256=AqxAtKGLDn7VVXWYwk0l9LnACxDLyU2jwOJ7vjPZj04,72
+magic_pdf/model/pdf_extract_kit.py,sha256=hiK1zDrwn5QhqUwI7BvM1JOoq_JIab4uVx_flHrBmWE,8374
+magic_pdf/model/pp_structure_v2.py,sha256=apYWwWiCjlks5CLXolcynnuPV7llCm2PdP-6tg0-Kt0,2903
+magic_pdf/model/pek_sub_modules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/pek_sub_modules/post_process.py,sha256=HzRxV2sVR3Qo8XKYEHhT6tae-bYTb6dnAfGP6gfVNaM,1135
+magic_pdf/model/pek_sub_modules/self_modify.py,sha256=XiwLUCiY_E0JkaIQr5m1hOD75-iGrgkMVe-1bzeF_Go,10522
+magic_pdf/model/pek_sub_modules/layoutlmv3/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+magic_pdf/model/pek_sub_modules/layoutlmv3/backbone.py,sha256=1cvSCczgvwOLdvzWyqttoYPMHsXmnzI3w9abJ1bAXoM,7106
+magic_pdf/model/pek_sub_modules/layoutlmv3/beit.py,sha256=e-INve6bpEx_0FM5wYbQcEcelc79tzDlCljTVHaGt1w,30450
+magic_pdf/model/pek_sub_modules/layoutlmv3/deit.py,sha256=Qyn5UWutZ-0GJczexCh-oMMSXtav_g3ovumMFJp8Om4,17000
+magic_pdf/model/pek_sub_modules/layoutlmv3/model_init.py,sha256=POs5s4_9rS-GlE7f_iHBuZpTwOuyfI6VE3DUb37fgxA,4483
+magic_pdf/model/pek_sub_modules/layoutlmv3/rcnn_vl.py,sha256=nI4G6AeLRmjavNhs5S2USKh0ozn-ftMuW0F0m_eVy3c,6649
+magic_pdf/model/pek_sub_modules/layoutlmv3/visualizer.py,sha256=H6UYeCCbaN2gbDjGthTkKkPoyWxfE3azRjsR7fVBwnw,49797
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/__init__.py,sha256=C4N9gXJr7is7uznvQefQ7dOhlzEhdp86Lgh-7p0Y-08,186
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/__init__.py,sha256=W7V62JOh12NdMZj2H1sde3Il0AqW2VKplmHEsLle6tg,76
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/cord.py,sha256=jR_lRZxy8SeEvTK3FdlXmQHF0kefJf7ZqwM_8pvyI5E,8153
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/data_collator.py,sha256=M2TE47BprHSuQJYcoMeWOSpqkr_nh8VK6t2l26XWmxg,6279
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/funsd.py,sha256=Ez9tMeruHncJlkKQ7iRGBB9Pk1uWtgxlGeqs-sOmIG0,5214
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/image_utils.py,sha256=vuNOMzYw_h7jmaD2XUqkGlrjDEPB7XUts16GRICBmG4,10334
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/data/xfund.py,sha256=6jLKyc_4VhbHY4YEzBXm5RkPdsd9ldnUGXFZBLiJ-_s,8270
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/__init__.py,sha256=d5bm3Rx-jTrgfJDWrzD7t5R5CdHfug9dCNvUEneIYW4,190
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/__init__.py,sha256=a04w_C0B4P9jF-3I_tXCj3fLmfFQR5XSKGbhgGm--pM,1216
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/configuration_layoutlmv3.py,sha256=CJBcAmmLeRFVMN1YjWefoUW7hk0KXek0Eb_tergKl4Y,2150
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/modeling_layoutlmv3.py,sha256=mdo8tO-DrJcv0Lbk9Pp98n3NQXYOnFFyXQWjU7t35kA,54633
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3.py,sha256=diKlrfxYjKAmYrUgjYdx-FXLh-swShC3tl-EBX1b3oI,1197
+magic_pdf/model/pek_sub_modules/layoutlmv3/layoutlmft/models/layoutlmv3/tokenization_layoutlmv3_fast.py,sha256=0lxiG69_fGpSSBYA9CBLnDa_qqa1rInZ0pJpqBwZ0Yw,1372
 magic_pdf/para/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/para/block_continuation_processor.py,sha256=IkReB5hirjm0OAirNzQQpnWe2f2bdP3Hug3Ef8qTRDA,22749
 magic_pdf/para/block_termination_processor.py,sha256=YU3ZYqJy9e3OQmOuQYZrR6AUpmAlQ0mhj0PgZZPZ_fM,17957
@@ -66,10 +89,10 @@ magic_pdf/para/para_split_v2.py,sha256=jGOhsubdh_CEgSv9WMNmp1loq1YNlpcAj3yh3g0gP
 magic_pdf/para/raw_processor.py,sha256=mHxD9FrdOSXH7NqM41s55URyCyuyACvm9kKtowkIb3k,6317
 magic_pdf/para/stats.py,sha256=-6Pf9Y8jkP1uJOYWiHUjw9Lb-Fb9GY7MHr_ok7x2GX0,9731
 magic_pdf/para/title_processor.py,sha256=pYZv9vEkIjAtCz8jIUtl9AVUy_ib5SdAZmMVoZtsMRI,38593
-magic_pdf/pipe/AbsPipe.py,sha256=28e3HxybBO86npy_L4WD6F7hfjKHHc86-IhiwzAnLdk,3979
-magic_pdf/pipe/OCRPipe.py,sha256=iKnNveVfsrBGl_2Xtd4hAAS5HntYyjwfBeVIKGc8V5U,1196
-magic_pdf/pipe/TXTPipe.py,sha256=R0UzMZ7Z_59Vh7cPdBAO4gvHtgA5wLoODnCPnpEjbPM,1255
-magic_pdf/pipe/UNIPipe.py,sha256=47a9jx1a_zO4m3sVnhcOnrmNc_QT-TI-9mv2x7L6SrQ,3507
+magic_pdf/pipe/AbsPipe.py,sha256=rMZd0FRTxGWt-7MZNmjgI1bKXlmSb9ZTA6A9fhEE7Gk,4131
+magic_pdf/pipe/OCRPipe.py,sha256=55VGQVxxjunnmt3L8tYlo9A8y3vVB1JRCO9wMQtk-N0,1317
+magic_pdf/pipe/TXTPipe.py,sha256=2Xn0fDDbLm2qW6xtXXHsNwXlAKnMHFbiIgnP1J2zNh8,1376
+magic_pdf/pipe/UNIPipe.py,sha256=0w1XLmUQUxvqm3BaVB800pZIeLiDD3NGvQb32OcI0Fg,3587
 magic_pdf/pipe/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/post_proc/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 magic_pdf/post_proc/detect_para.py,sha256=5LX86ueHQGOV9CNimAxqZH4R3KTi78leum1de_Na0pw,126181
@@ -104,6 +127,9 @@ magic_pdf/pre_proc/remove_rotate_bbox.py,sha256=0FlBXeiEwjZAGAWo-DiMptclFOj04POu
 magic_pdf/pre_proc/resolve_bbox_conflict.py,sha256=bJiegofPUeDyi--oZjfipQ5Q5RLm6TOCW0TLXbPii_Q,7307
 magic_pdf/pre_proc/solve_line_alien.py,sha256=aNoQptPcC38Sm1I2ABhgw8jeH_5kjsRHx3VYlFFtm1g,853
 magic_pdf/pre_proc/statistics.py,sha256=_9jGlXq0iXd03UMxB92ZqCiu7cjNkG5vHvFlTF_9ytA,220
+magic_pdf/resources/model_config/model_configs.yaml,sha256=C_9UfFMlHOX-iSgcwCHjyHKazKKuwpy1RcGHeTQD1kY,139
+magic_pdf/resources/model_config/UniMERNet/demo.yaml,sha256=al9_--m3n2j9zEn9OjlmmpfQbqVBAYFakXc_hY4vDXo,807
+magic_pdf/resources/model_config/layoutlmv3/layoutlmv3_base_inference.yaml,sha256=noqVE3GmZUG86NYDfs9DiFgdQFjXaICyCU7KPzgR3II,6174
 magic_pdf/rw/AbsReaderWriter.py,sha256=1Hd6Xo2g12CaRAo5Sze-R_GSQA6GQ0rQwSmgQvw4V_c,1297
 magic_pdf/rw/DiskReaderWriter.py,sha256=0tt8lbRyqrOfFgGlhjt24YMdj2xN7QUIVysfhFIxPgo,2113
 magic_pdf/rw/S3ReaderWriter.py,sha256=O7Quf3CUqXBjMz4sIE7kNVI3TIQROeg5PuXneAacieY,4474
@@ -115,9 +141,9 @@ magic_pdf/train_utils/convert_to_train_format.py,sha256=ifo2FAoBMa_etCvz0O4v03xO
 magic_pdf/train_utils/extract_caption.py,sha256=gommEqIEWLplSDEJWD7_66daqlOBsWhpRBW1DHpkny4,1825
 magic_pdf/train_utils/remove_footer_header.py,sha256=pyeNNdJ-th3wl5Xwb10ZLYNaFN4-6BmahoMFE8VTNNs,5978
 magic_pdf/train_utils/vis_utils.py,sha256=MV9N9cT3ifJ35u7LFKGF9I_bOIQrtU1zcsxu2hj3aqM,10111
-magic_pdf-0.5.12.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
-magic_pdf-0.5.12.dist-info/METADATA,sha256=iNTDKGkj4D77ErkS0P1dNZ4ttFriYHbTSjsEE3f8MP0,5917
-magic_pdf-0.5.12.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
-magic_pdf-0.5.12.dist-info/entry_points.txt,sha256=NbSkSmE08UuTwdoJD8Uofq8iyufySA4x7jmIIk4YCzI,57
-magic_pdf-0.5.12.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
-magic_pdf-0.5.12.dist-info/RECORD,,
+magic_pdf-0.6.0.dist-info/LICENSE.md,sha256=hIahDEOTzuHCU5J2nd07LWwkLW7Hko4UFO__ffsvB-8,34523
+magic_pdf-0.6.0.dist-info/METADATA,sha256=rqkC7PCOuqDzqnsVWW8DSqwogF3jHwGp6-sS8xjCi6o,7093
+magic_pdf-0.6.0.dist-info/WHEEL,sha256=GJ7t_kWBFywbagK5eo9IoUwLW6oyOeTKmQ-9iHFVNxQ,92
+magic_pdf-0.6.0.dist-info/entry_points.txt,sha256=NbSkSmE08UuTwdoJD8Uofq8iyufySA4x7jmIIk4YCzI,57
+magic_pdf-0.6.0.dist-info/top_level.txt,sha256=J9I0AzmHWGkp9c6DL8Oe4mEx3yYphLzkRn4H25Lg1rE,10
+magic_pdf-0.6.0.dist-info/RECORD,,

magic_pdf/model/360_layout_analysis.py

@@ -1,8 +0,0 @@
-from ultralytics import YOLO
-
-image_path = ''  # 待预测图片路径
-model_path = ''  # 权重路径
-model = YOLO(model_path)
-
-result = model(image_path, save=True, conf=0.5, save_crop=False, line_width=2)
-print(result)